diff options
Diffstat (limited to 'net')
511 files changed, 18533 insertions, 7872 deletions
diff --git a/net/6lowpan/ndisc.c b/net/6lowpan/ndisc.c index 16be8f8b2f8c..c40b98f7743c 100644 --- a/net/6lowpan/ndisc.c +++ b/net/6lowpan/ndisc.c @@ -11,11 +11,6 @@ #include "6lowpan_i.h" -static int lowpan_ndisc_is_useropt(u8 nd_opt_type) -{ - return nd_opt_type == ND_OPT_6CO; -} - #if IS_ENABLED(CONFIG_IEEE802154_6LOWPAN) #define NDISC_802154_SHORT_ADDR_LENGTH 1 static int lowpan_ndisc_parse_802154_options(const struct net_device *dev, @@ -222,7 +217,6 @@ static void lowpan_ndisc_prefix_rcv_add_addr(struct net *net, #endif const struct ndisc_ops lowpan_ndisc_ops = { - .is_useropt = lowpan_ndisc_is_useropt, #if IS_ENABLED(CONFIG_IEEE802154_6LOWPAN) .parse_options = lowpan_ndisc_parse_options, .update = lowpan_ndisc_update, diff --git a/net/8021q/vlan_dev.c b/net/8021q/vlan_dev.c index 3efba4f857ac..458040e8a0e0 100644 --- a/net/8021q/vlan_dev.c +++ b/net/8021q/vlan_dev.c @@ -564,17 +564,20 @@ static int vlan_dev_init(struct net_device *dev) NETIF_F_FRAGLIST | NETIF_F_GSO_SOFTWARE | NETIF_F_GSO_ENCAP_ALL | NETIF_F_HIGHDMA | NETIF_F_SCTP_CRC | - NETIF_F_ALL_FCOE; + NETIF_F_FCOE_CRC | NETIF_F_FSO; if (real_dev->vlan_features & NETIF_F_HW_MACSEC) dev->hw_features |= NETIF_F_HW_MACSEC; - dev->features |= dev->hw_features | NETIF_F_LLTX; + dev->features |= dev->hw_features; + dev->lltx = true; + dev->fcoe_mtu = true; netif_inherit_tso_max(dev, real_dev); if (dev->features & NETIF_F_VLAN_FEATURES) netdev_warn(real_dev, "VLAN features are set incorrectly. Q-in-Q configurations may not work correctly.\n"); - dev->vlan_features = real_dev->vlan_features & ~NETIF_F_ALL_FCOE; + dev->vlan_features = real_dev->vlan_features & + ~(NETIF_F_FCOE_CRC | NETIF_F_FSO); dev->hw_enc_features = vlan_tnl_features(real_dev); dev->mpls_features = real_dev->mpls_features; @@ -655,7 +658,6 @@ static netdev_features_t vlan_dev_fix_features(struct net_device *dev, lower_features |= NETIF_F_HW_CSUM; features = netdev_intersect_features(features, lower_features); features |= old_features & (NETIF_F_SOFT_FEATURES | NETIF_F_GSO_SOFTWARE); - features |= NETIF_F_LLTX; return features; } @@ -677,7 +679,7 @@ static void vlan_ethtool_get_drvinfo(struct net_device *dev, } static int vlan_ethtool_get_ts_info(struct net_device *dev, - struct ethtool_ts_info *info) + struct kernel_ethtool_ts_info *info) { const struct vlan_dev_priv *vlan = vlan_dev_priv(dev); return ethtool_get_ts_info_by_layer(vlan->real_dev, info); diff --git a/net/8021q/vlanproc.c b/net/8021q/vlanproc.c index 87b959da00cd..fa67374bda49 100644 --- a/net/8021q/vlanproc.c +++ b/net/8021q/vlanproc.c @@ -238,9 +238,9 @@ static int vlandev_seq_show(struct seq_file *seq, void *offset) stats = dev_get_stats(vlandev, &temp); seq_printf(seq, - "%s VID: %d REORDER_HDR: %i dev->priv_flags: %llx\n", + "%s VID: %d REORDER_HDR: %i dev->priv_flags: %x\n", vlandev->name, vlan->vlan_id, - (int)(vlan->flags & 1), vlandev->priv_flags); + (int)(vlan->flags & 1), (u32)vlandev->priv_flags); seq_printf(seq, fmt64, "total frames received", stats->rx_packets); seq_printf(seq, fmt64, "total bytes received", stats->rx_bytes); diff --git a/net/9p/Kconfig b/net/9p/Kconfig index bcdab9c23b40..63f988f0c9e8 100644 --- a/net/9p/Kconfig +++ b/net/9p/Kconfig @@ -40,6 +40,12 @@ config NET_9P_XEN This builds support for a transport for 9pfs between two Xen domains. +config NET_9P_USBG + bool "9P USB Gadget Transport" + depends on USB_GADGET=y || USB_GADGET=NET_9P + help + This builds support for a transport for 9pfs over + usb gadget. config NET_9P_RDMA depends on INET && INFINIBAND && INFINIBAND_ADDR_TRANS diff --git a/net/9p/Makefile b/net/9p/Makefile index 1df9b344c30b..22794a451c3f 100644 --- a/net/9p/Makefile +++ b/net/9p/Makefile @@ -4,6 +4,7 @@ obj-$(CONFIG_NET_9P_FD) += 9pnet_fd.o obj-$(CONFIG_NET_9P_XEN) += 9pnet_xen.o obj-$(CONFIG_NET_9P_VIRTIO) += 9pnet_virtio.o obj-$(CONFIG_NET_9P_RDMA) += 9pnet_rdma.o +obj-$(CONFIG_NET_9P_USBG) += 9pnet_usbg.o 9pnet-objs := \ mod.o \ @@ -23,3 +24,6 @@ obj-$(CONFIG_NET_9P_RDMA) += 9pnet_rdma.o 9pnet_rdma-objs := \ trans_rdma.o \ + +9pnet_usbg-objs := \ + trans_usbg.o \ diff --git a/net/9p/trans_usbg.c b/net/9p/trans_usbg.c new file mode 100644 index 000000000000..975b76839dca --- /dev/null +++ b/net/9p/trans_usbg.c @@ -0,0 +1,956 @@ +// SPDX-License-Identifier: GPL-2.0+ +/* + * trans_usbg.c - USB peripheral usb9pfs configuration driver and transport. + * + * Copyright (C) 2024 Michael Grzeschik <m.grzeschik@pengutronix.de> + */ + +/* Gadget usb9pfs only needs two bulk endpoints, and will use the usb9pfs + * transport to mount host exported filesystem via usb gadget. + */ + +/* +--------------------------+ | +--------------------------+ + * | 9PFS mounting client | | | 9PFS exporting server | + * SW | | | | | + * | (this:trans_usbg) | | |(e.g. diod or nfs-ganesha)| + * +-------------^------------+ | +-------------^------------+ + * | | | + * ------------------|------------------------------------|------------- + * | | | + * +-------------v------------+ | +-------------v------------+ + * | | | | | + * HW | USB Device Controller <---------> USB Host Controller | + * | | | | | + * +--------------------------+ | +--------------------------+ + */ + +#include <linux/cleanup.h> +#include <linux/kernel.h> +#include <linux/module.h> +#include <linux/usb/composite.h> +#include <linux/usb/func_utils.h> + +#include <net/9p/9p.h> +#include <net/9p/client.h> +#include <net/9p/transport.h> + +#define DEFAULT_BUFLEN 16384 + +struct f_usb9pfs { + struct p9_client *client; + + /* 9p request lock for en/dequeue */ + spinlock_t lock; + + struct usb_request *in_req; + struct usb_request *out_req; + + struct usb_ep *in_ep; + struct usb_ep *out_ep; + + struct completion send; + struct completion received; + + unsigned int buflen; + + struct usb_function function; +}; + +static inline struct f_usb9pfs *func_to_usb9pfs(struct usb_function *f) +{ + return container_of(f, struct f_usb9pfs, function); +} + +struct f_usb9pfs_opts { + struct usb_function_instance func_inst; + unsigned int buflen; + + struct f_usb9pfs_dev *dev; + + /* Read/write access to configfs attributes is handled by configfs. + * + * This is to protect the data from concurrent access by read/write + * and create symlink/remove symlink. + */ + struct mutex lock; + int refcnt; +}; + +struct f_usb9pfs_dev { + struct f_usb9pfs *usb9pfs; + struct f_usb9pfs_opts *opts; + char tag[41]; + bool inuse; + + struct list_head usb9pfs_instance; +}; + +static DEFINE_MUTEX(usb9pfs_lock); +static struct list_head usbg_instance_list; + +static int usb9pfs_queue_tx(struct f_usb9pfs *usb9pfs, struct p9_req_t *p9_tx_req, + gfp_t gfp_flags) +{ + struct usb_composite_dev *cdev = usb9pfs->function.config->cdev; + struct usb_request *req = usb9pfs->in_req; + int ret; + + if (!(p9_tx_req->tc.size % usb9pfs->in_ep->maxpacket)) + req->zero = 1; + + req->buf = p9_tx_req->tc.sdata; + req->length = p9_tx_req->tc.size; + req->context = p9_tx_req; + + dev_dbg(&cdev->gadget->dev, "%s usb9pfs send --> %d/%d, zero: %d\n", + usb9pfs->in_ep->name, req->actual, req->length, req->zero); + + ret = usb_ep_queue(usb9pfs->in_ep, req, gfp_flags); + if (ret) + req->context = NULL; + + dev_dbg(&cdev->gadget->dev, "tx submit --> %d\n", ret); + + return ret; +} + +static int usb9pfs_queue_rx(struct f_usb9pfs *usb9pfs, struct usb_request *req, + gfp_t gfp_flags) +{ + struct usb_composite_dev *cdev = usb9pfs->function.config->cdev; + int ret; + + ret = usb_ep_queue(usb9pfs->out_ep, req, gfp_flags); + + dev_dbg(&cdev->gadget->dev, "rx submit --> %d\n", ret); + + return ret; +} + +static int usb9pfs_transmit(struct f_usb9pfs *usb9pfs, struct p9_req_t *p9_req) +{ + int ret = 0; + + guard(spinlock_irqsave)(&usb9pfs->lock); + + ret = usb9pfs_queue_tx(usb9pfs, p9_req, GFP_ATOMIC); + if (ret) + return ret; + + list_del(&p9_req->req_list); + + p9_req_get(p9_req); + + return ret; +} + +static void usb9pfs_tx_complete(struct usb_ep *ep, struct usb_request *req) +{ + struct f_usb9pfs *usb9pfs = ep->driver_data; + struct usb_composite_dev *cdev = usb9pfs->function.config->cdev; + struct p9_req_t *p9_tx_req = req->context; + unsigned long flags; + + /* reset zero packages */ + req->zero = 0; + + if (req->status) { + dev_err(&cdev->gadget->dev, "%s usb9pfs complete --> %d, %d/%d\n", + ep->name, req->status, req->actual, req->length); + return; + } + + dev_dbg(&cdev->gadget->dev, "%s usb9pfs complete --> %d, %d/%d\n", + ep->name, req->status, req->actual, req->length); + + spin_lock_irqsave(&usb9pfs->lock, flags); + WRITE_ONCE(p9_tx_req->status, REQ_STATUS_SENT); + + p9_req_put(usb9pfs->client, p9_tx_req); + + req->context = NULL; + + spin_unlock_irqrestore(&usb9pfs->lock, flags); + + complete(&usb9pfs->send); +} + +static struct p9_req_t *usb9pfs_rx_header(struct f_usb9pfs *usb9pfs, void *buf) +{ + struct p9_req_t *p9_rx_req; + struct p9_fcall rc; + int ret; + + /* start by reading header */ + rc.sdata = buf; + rc.offset = 0; + rc.capacity = P9_HDRSZ; + rc.size = P9_HDRSZ; + + p9_debug(P9_DEBUG_TRANS, "mux %p got %zu bytes\n", usb9pfs, + rc.capacity - rc.offset); + + ret = p9_parse_header(&rc, &rc.size, NULL, NULL, 0); + if (ret) { + p9_debug(P9_DEBUG_ERROR, + "error parsing header: %d\n", ret); + return NULL; + } + + p9_debug(P9_DEBUG_TRANS, + "mux %p pkt: size: %d bytes tag: %d\n", + usb9pfs, rc.size, rc.tag); + + p9_rx_req = p9_tag_lookup(usb9pfs->client, rc.tag); + if (!p9_rx_req || p9_rx_req->status != REQ_STATUS_SENT) { + p9_debug(P9_DEBUG_ERROR, "Unexpected packet tag %d\n", rc.tag); + return NULL; + } + + if (rc.size > p9_rx_req->rc.capacity) { + p9_debug(P9_DEBUG_ERROR, + "requested packet size too big: %d for tag %d with capacity %zd\n", + rc.size, rc.tag, p9_rx_req->rc.capacity); + p9_req_put(usb9pfs->client, p9_rx_req); + return NULL; + } + + if (!p9_rx_req->rc.sdata) { + p9_debug(P9_DEBUG_ERROR, + "No recv fcall for tag %d (req %p), disconnecting!\n", + rc.tag, p9_rx_req); + p9_req_put(usb9pfs->client, p9_rx_req); + return NULL; + } + + return p9_rx_req; +} + +static void usb9pfs_rx_complete(struct usb_ep *ep, struct usb_request *req) +{ + struct f_usb9pfs *usb9pfs = ep->driver_data; + struct usb_composite_dev *cdev = usb9pfs->function.config->cdev; + struct p9_req_t *p9_rx_req; + + if (req->status) { + dev_err(&cdev->gadget->dev, "%s usb9pfs complete --> %d, %d/%d\n", + ep->name, req->status, req->actual, req->length); + return; + } + + p9_rx_req = usb9pfs_rx_header(usb9pfs, req->buf); + if (!p9_rx_req) + return; + + memcpy(p9_rx_req->rc.sdata, req->buf, req->actual); + + p9_rx_req->rc.size = req->actual; + + p9_client_cb(usb9pfs->client, p9_rx_req, REQ_STATUS_RCVD); + p9_req_put(usb9pfs->client, p9_rx_req); + + complete(&usb9pfs->received); +} + +static void disable_ep(struct usb_composite_dev *cdev, struct usb_ep *ep) +{ + int value; + + value = usb_ep_disable(ep); + if (value < 0) + dev_info(&cdev->gadget->dev, + "disable %s --> %d\n", ep->name, value); +} + +static void disable_usb9pfs(struct f_usb9pfs *usb9pfs) +{ + struct usb_composite_dev *cdev = + usb9pfs->function.config->cdev; + + if (usb9pfs->in_req) { + usb_ep_free_request(usb9pfs->in_ep, usb9pfs->in_req); + usb9pfs->in_req = NULL; + } + + if (usb9pfs->out_req) { + usb_ep_free_request(usb9pfs->out_ep, usb9pfs->out_req); + usb9pfs->out_req = NULL; + } + + disable_ep(cdev, usb9pfs->in_ep); + disable_ep(cdev, usb9pfs->out_ep); + dev_dbg(&cdev->gadget->dev, "%s disabled\n", + usb9pfs->function.name); +} + +static int alloc_requests(struct usb_composite_dev *cdev, + struct f_usb9pfs *usb9pfs) +{ + int ret; + + usb9pfs->in_req = usb_ep_alloc_request(usb9pfs->in_ep, GFP_ATOMIC); + if (!usb9pfs->in_req) { + ret = -ENOENT; + goto fail; + } + + usb9pfs->out_req = alloc_ep_req(usb9pfs->out_ep, usb9pfs->buflen); + if (!usb9pfs->out_req) { + ret = -ENOENT; + goto fail_in; + } + + usb9pfs->in_req->complete = usb9pfs_tx_complete; + usb9pfs->out_req->complete = usb9pfs_rx_complete; + + /* length will be set in complete routine */ + usb9pfs->in_req->context = usb9pfs; + usb9pfs->out_req->context = usb9pfs; + + return 0; + +fail_in: + usb_ep_free_request(usb9pfs->in_ep, usb9pfs->in_req); +fail: + return ret; +} + +static int enable_endpoint(struct usb_composite_dev *cdev, + struct f_usb9pfs *usb9pfs, struct usb_ep *ep) +{ + int ret; + + ret = config_ep_by_speed(cdev->gadget, &usb9pfs->function, ep); + if (ret) + return ret; + + ret = usb_ep_enable(ep); + if (ret < 0) + return ret; + + ep->driver_data = usb9pfs; + + return 0; +} + +static int +enable_usb9pfs(struct usb_composite_dev *cdev, struct f_usb9pfs *usb9pfs) +{ + struct p9_client *client; + int ret = 0; + + ret = enable_endpoint(cdev, usb9pfs, usb9pfs->in_ep); + if (ret) + goto out; + + ret = enable_endpoint(cdev, usb9pfs, usb9pfs->out_ep); + if (ret) + goto disable_in; + + ret = alloc_requests(cdev, usb9pfs); + if (ret) + goto disable_out; + + client = usb9pfs->client; + if (client) + client->status = Connected; + + dev_dbg(&cdev->gadget->dev, "%s enabled\n", usb9pfs->function.name); + return 0; + +disable_out: + usb_ep_disable(usb9pfs->out_ep); +disable_in: + usb_ep_disable(usb9pfs->in_ep); +out: + return ret; +} + +static int p9_usbg_create(struct p9_client *client, const char *devname, char *args) +{ + struct f_usb9pfs_dev *dev; + struct f_usb9pfs *usb9pfs; + int ret = -ENOENT; + int found = 0; + + if (!devname) + return -EINVAL; + + guard(mutex)(&usb9pfs_lock); + + list_for_each_entry(dev, &usbg_instance_list, usb9pfs_instance) { + if (!strncmp(devname, dev->tag, strlen(devname))) { + if (!dev->inuse) { + dev->inuse = true; + found = 1; + break; + } + ret = -EBUSY; + break; + } + } + + if (!found) { + pr_err("no channels available for device %s\n", devname); + return ret; + } + + usb9pfs = dev->usb9pfs; + if (!usb9pfs) + return -EINVAL; + + client->trans = (void *)usb9pfs; + if (!usb9pfs->in_req) + client->status = Disconnected; + else + client->status = Connected; + usb9pfs->client = client; + + client->trans_mod->maxsize = usb9pfs->buflen; + + complete(&usb9pfs->received); + + return 0; +} + +static void usb9pfs_clear_tx(struct f_usb9pfs *usb9pfs) +{ + struct p9_req_t *req; + + guard(spinlock_irqsave)(&usb9pfs->lock); + + req = usb9pfs->in_req->context; + if (!req) + return; + + if (!req->t_err) + req->t_err = -ECONNRESET; + + p9_client_cb(usb9pfs->client, req, REQ_STATUS_ERROR); +} + +static void p9_usbg_close(struct p9_client *client) +{ + struct f_usb9pfs *usb9pfs; + struct f_usb9pfs_dev *dev; + struct f_usb9pfs_opts *opts; + + if (!client) + return; + + usb9pfs = client->trans; + if (!usb9pfs) + return; + + client->status = Disconnected; + + usb9pfs_clear_tx(usb9pfs); + + opts = container_of(usb9pfs->function.fi, + struct f_usb9pfs_opts, func_inst); + + dev = opts->dev; + + mutex_lock(&usb9pfs_lock); + dev->inuse = false; + mutex_unlock(&usb9pfs_lock); +} + +static int p9_usbg_request(struct p9_client *client, struct p9_req_t *p9_req) +{ + struct f_usb9pfs *usb9pfs = client->trans; + int ret; + + if (client->status != Connected) + return -EBUSY; + + ret = wait_for_completion_killable(&usb9pfs->received); + if (ret) + return ret; + + ret = usb9pfs_transmit(usb9pfs, p9_req); + if (ret) + return ret; + + ret = wait_for_completion_killable(&usb9pfs->send); + if (ret) + return ret; + + return usb9pfs_queue_rx(usb9pfs, usb9pfs->out_req, GFP_ATOMIC); +} + +static int p9_usbg_cancel(struct p9_client *client, struct p9_req_t *req) +{ + struct f_usb9pfs *usb9pfs = client->trans; + int ret = 1; + + p9_debug(P9_DEBUG_TRANS, "client %p req %p\n", client, req); + + guard(spinlock_irqsave)(&usb9pfs->lock); + + if (req->status == REQ_STATUS_UNSENT) { + list_del(&req->req_list); + WRITE_ONCE(req->status, REQ_STATUS_FLSHD); + p9_req_put(client, req); + ret = 0; + } + + return ret; +} + +static struct p9_trans_module p9_usbg_trans = { + .name = "usbg", + .create = p9_usbg_create, + .close = p9_usbg_close, + .request = p9_usbg_request, + .cancel = p9_usbg_cancel, + .owner = THIS_MODULE, +}; + +/*-------------------------------------------------------------------------*/ + +#define USB_PROTOCOL_9PFS 0x09 + +static struct usb_interface_descriptor usb9pfs_intf = { + .bLength = sizeof(usb9pfs_intf), + .bDescriptorType = USB_DT_INTERFACE, + + .bNumEndpoints = 2, + .bInterfaceClass = USB_CLASS_VENDOR_SPEC, + .bInterfaceSubClass = USB_SUBCLASS_VENDOR_SPEC, + .bInterfaceProtocol = USB_PROTOCOL_9PFS, + + /* .iInterface = DYNAMIC */ +}; + +/* full speed support: */ + +static struct usb_endpoint_descriptor fs_usb9pfs_source_desc = { + .bLength = USB_DT_ENDPOINT_SIZE, + .bDescriptorType = USB_DT_ENDPOINT, + + .bEndpointAddress = USB_DIR_IN, + .bmAttributes = USB_ENDPOINT_XFER_BULK, +}; + +static struct usb_endpoint_descriptor fs_usb9pfs_sink_desc = { + .bLength = USB_DT_ENDPOINT_SIZE, + .bDescriptorType = USB_DT_ENDPOINT, + + .bEndpointAddress = USB_DIR_OUT, + .bmAttributes = USB_ENDPOINT_XFER_BULK, +}; + +static struct usb_descriptor_header *fs_usb9pfs_descs[] = { + (struct usb_descriptor_header *)&usb9pfs_intf, + (struct usb_descriptor_header *)&fs_usb9pfs_sink_desc, + (struct usb_descriptor_header *)&fs_usb9pfs_source_desc, + NULL, +}; + +/* high speed support: */ + +static struct usb_endpoint_descriptor hs_usb9pfs_source_desc = { + .bLength = USB_DT_ENDPOINT_SIZE, + .bDescriptorType = USB_DT_ENDPOINT, + + .bmAttributes = USB_ENDPOINT_XFER_BULK, + .wMaxPacketSize = cpu_to_le16(512), +}; + +static struct usb_endpoint_descriptor hs_usb9pfs_sink_desc = { + .bLength = USB_DT_ENDPOINT_SIZE, + .bDescriptorType = USB_DT_ENDPOINT, + + .bmAttributes = USB_ENDPOINT_XFER_BULK, + .wMaxPacketSize = cpu_to_le16(512), +}; + +static struct usb_descriptor_header *hs_usb9pfs_descs[] = { + (struct usb_descriptor_header *)&usb9pfs_intf, + (struct usb_descriptor_header *)&hs_usb9pfs_source_desc, + (struct usb_descriptor_header *)&hs_usb9pfs_sink_desc, + NULL, +}; + +/* super speed support: */ + +static struct usb_endpoint_descriptor ss_usb9pfs_source_desc = { + .bLength = USB_DT_ENDPOINT_SIZE, + .bDescriptorType = USB_DT_ENDPOINT, + + .bmAttributes = USB_ENDPOINT_XFER_BULK, + .wMaxPacketSize = cpu_to_le16(1024), +}; + +static struct usb_ss_ep_comp_descriptor ss_usb9pfs_source_comp_desc = { + .bLength = USB_DT_SS_EP_COMP_SIZE, + .bDescriptorType = USB_DT_SS_ENDPOINT_COMP, + .bMaxBurst = 0, + .bmAttributes = 0, + .wBytesPerInterval = 0, +}; + +static struct usb_endpoint_descriptor ss_usb9pfs_sink_desc = { + .bLength = USB_DT_ENDPOINT_SIZE, + .bDescriptorType = USB_DT_ENDPOINT, + + .bmAttributes = USB_ENDPOINT_XFER_BULK, + .wMaxPacketSize = cpu_to_le16(1024), +}; + +static struct usb_ss_ep_comp_descriptor ss_usb9pfs_sink_comp_desc = { + .bLength = USB_DT_SS_EP_COMP_SIZE, + .bDescriptorType = USB_DT_SS_ENDPOINT_COMP, + .bMaxBurst = 0, + .bmAttributes = 0, + .wBytesPerInterval = 0, +}; + +static struct usb_descriptor_header *ss_usb9pfs_descs[] = { + (struct usb_descriptor_header *)&usb9pfs_intf, + (struct usb_descriptor_header *)&ss_usb9pfs_source_desc, + (struct usb_descriptor_header *)&ss_usb9pfs_source_comp_desc, + (struct usb_descriptor_header *)&ss_usb9pfs_sink_desc, + (struct usb_descriptor_header *)&ss_usb9pfs_sink_comp_desc, + NULL, +}; + +/* function-specific strings: */ +static struct usb_string strings_usb9pfs[] = { + [0].s = "usb9pfs input to output", + { } /* end of list */ +}; + +static struct usb_gadget_strings stringtab_usb9pfs = { + .language = 0x0409, /* en-us */ + .strings = strings_usb9pfs, +}; + +static struct usb_gadget_strings *usb9pfs_strings[] = { + &stringtab_usb9pfs, + NULL, +}; + +/*-------------------------------------------------------------------------*/ + +static int usb9pfs_func_bind(struct usb_configuration *c, + struct usb_function *f) +{ + struct f_usb9pfs *usb9pfs = func_to_usb9pfs(f); + struct f_usb9pfs_opts *opts; + struct usb_composite_dev *cdev = c->cdev; + int ret; + int id; + + /* allocate interface ID(s) */ + id = usb_interface_id(c, f); + if (id < 0) + return id; + usb9pfs_intf.bInterfaceNumber = id; + + id = usb_string_id(cdev); + if (id < 0) + return id; + strings_usb9pfs[0].id = id; + usb9pfs_intf.iInterface = id; + + /* allocate endpoints */ + usb9pfs->in_ep = usb_ep_autoconfig(cdev->gadget, + &fs_usb9pfs_source_desc); + if (!usb9pfs->in_ep) + goto autoconf_fail; + + usb9pfs->out_ep = usb_ep_autoconfig(cdev->gadget, + &fs_usb9pfs_sink_desc); + if (!usb9pfs->out_ep) + goto autoconf_fail; + + /* support high speed hardware */ + hs_usb9pfs_source_desc.bEndpointAddress = + fs_usb9pfs_source_desc.bEndpointAddress; + hs_usb9pfs_sink_desc.bEndpointAddress = + fs_usb9pfs_sink_desc.bEndpointAddress; + + /* support super speed hardware */ + ss_usb9pfs_source_desc.bEndpointAddress = + fs_usb9pfs_source_desc.bEndpointAddress; + ss_usb9pfs_sink_desc.bEndpointAddress = + fs_usb9pfs_sink_desc.bEndpointAddress; + + ret = usb_assign_descriptors(f, fs_usb9pfs_descs, hs_usb9pfs_descs, + ss_usb9pfs_descs, ss_usb9pfs_descs); + if (ret) + return ret; + + opts = container_of(f->fi, struct f_usb9pfs_opts, func_inst); + opts->dev->usb9pfs = usb9pfs; + + dev_dbg(&cdev->gadget->dev, "%s speed %s: IN/%s, OUT/%s\n", + (gadget_is_superspeed(c->cdev->gadget) ? "super" : + (gadget_is_dualspeed(c->cdev->gadget) ? "dual" : "full")), + f->name, usb9pfs->in_ep->name, usb9pfs->out_ep->name); + + return 0; + +autoconf_fail: + ERROR(cdev, "%s: can't autoconfigure on %s\n", + f->name, cdev->gadget->name); + return -ENODEV; +} + +static void usb9pfs_func_unbind(struct usb_configuration *c, + struct usb_function *f) +{ + struct f_usb9pfs *usb9pfs = func_to_usb9pfs(f); + + disable_usb9pfs(usb9pfs); +} + +static void usb9pfs_free_func(struct usb_function *f) +{ + struct f_usb9pfs *usb9pfs = func_to_usb9pfs(f); + struct f_usb9pfs_opts *opts; + + kfree(usb9pfs); + + opts = container_of(f->fi, struct f_usb9pfs_opts, func_inst); + + mutex_lock(&opts->lock); + opts->refcnt--; + mutex_unlock(&opts->lock); + + usb_free_all_descriptors(f); +} + +static int usb9pfs_set_alt(struct usb_function *f, + unsigned int intf, unsigned int alt) +{ + struct f_usb9pfs *usb9pfs = func_to_usb9pfs(f); + struct usb_composite_dev *cdev = f->config->cdev; + + return enable_usb9pfs(cdev, usb9pfs); +} + +static void usb9pfs_disable(struct usb_function *f) +{ + struct f_usb9pfs *usb9pfs = func_to_usb9pfs(f); + + usb9pfs_clear_tx(usb9pfs); +} + +static struct usb_function *usb9pfs_alloc(struct usb_function_instance *fi) +{ + struct f_usb9pfs_opts *usb9pfs_opts; + struct f_usb9pfs *usb9pfs; + + usb9pfs = kzalloc(sizeof(*usb9pfs), GFP_KERNEL); + if (!usb9pfs) + return ERR_PTR(-ENOMEM); + + spin_lock_init(&usb9pfs->lock); + + init_completion(&usb9pfs->send); + init_completion(&usb9pfs->received); + + usb9pfs_opts = container_of(fi, struct f_usb9pfs_opts, func_inst); + + mutex_lock(&usb9pfs_opts->lock); + usb9pfs_opts->refcnt++; + mutex_unlock(&usb9pfs_opts->lock); + + usb9pfs->buflen = usb9pfs_opts->buflen; + + usb9pfs->function.name = "usb9pfs"; + usb9pfs->function.bind = usb9pfs_func_bind; + usb9pfs->function.unbind = usb9pfs_func_unbind; + usb9pfs->function.set_alt = usb9pfs_set_alt; + usb9pfs->function.disable = usb9pfs_disable; + usb9pfs->function.strings = usb9pfs_strings; + + usb9pfs->function.free_func = usb9pfs_free_func; + + return &usb9pfs->function; +} + +static inline struct f_usb9pfs_opts *to_f_usb9pfs_opts(struct config_item *item) +{ + return container_of(to_config_group(item), struct f_usb9pfs_opts, + func_inst.group); +} + +static inline struct f_usb9pfs_opts *fi_to_f_usb9pfs_opts(struct usb_function_instance *fi) +{ + return container_of(fi, struct f_usb9pfs_opts, func_inst); +} + +static void usb9pfs_attr_release(struct config_item *item) +{ + struct f_usb9pfs_opts *usb9pfs_opts = to_f_usb9pfs_opts(item); + + usb_put_function_instance(&usb9pfs_opts->func_inst); +} + +static struct configfs_item_operations usb9pfs_item_ops = { + .release = usb9pfs_attr_release, +}; + +static ssize_t f_usb9pfs_opts_buflen_show(struct config_item *item, char *page) +{ + struct f_usb9pfs_opts *opts = to_f_usb9pfs_opts(item); + int ret; + + mutex_lock(&opts->lock); + ret = sysfs_emit(page, "%d\n", opts->buflen); + mutex_unlock(&opts->lock); + + return ret; +} + +static ssize_t f_usb9pfs_opts_buflen_store(struct config_item *item, + const char *page, size_t len) +{ + struct f_usb9pfs_opts *opts = to_f_usb9pfs_opts(item); + int ret; + u32 num; + + guard(mutex)(&opts->lock); + + if (opts->refcnt) + return -EBUSY; + + ret = kstrtou32(page, 0, &num); + if (ret) + return ret; + + opts->buflen = num; + + return len; +} + +CONFIGFS_ATTR(f_usb9pfs_opts_, buflen); + +static struct configfs_attribute *usb9pfs_attrs[] = { + &f_usb9pfs_opts_attr_buflen, + NULL, +}; + +static const struct config_item_type usb9pfs_func_type = { + .ct_item_ops = &usb9pfs_item_ops, + .ct_attrs = usb9pfs_attrs, + .ct_owner = THIS_MODULE, +}; + +static struct f_usb9pfs_dev *_usb9pfs_do_find_dev(const char *tag) +{ + struct f_usb9pfs_dev *usb9pfs_dev; + + if (!tag) + return NULL; + + list_for_each_entry(usb9pfs_dev, &usbg_instance_list, usb9pfs_instance) { + if (strcmp(usb9pfs_dev->tag, tag) == 0) + return usb9pfs_dev; + } + + return NULL; +} + +static int usb9pfs_tag_instance(struct f_usb9pfs_dev *dev, const char *tag) +{ + struct f_usb9pfs_dev *existing; + int ret = 0; + + guard(mutex)(&usb9pfs_lock); + + existing = _usb9pfs_do_find_dev(tag); + if (!existing) + strscpy(dev->tag, tag, ARRAY_SIZE(dev->tag)); + else if (existing != dev) + ret = -EBUSY; + + return ret; +} + +static int usb9pfs_set_inst_tag(struct usb_function_instance *fi, const char *tag) +{ + if (strlen(tag) >= sizeof_field(struct f_usb9pfs_dev, tag)) + return -ENAMETOOLONG; + return usb9pfs_tag_instance(fi_to_f_usb9pfs_opts(fi)->dev, tag); +} + +static void usb9pfs_free_instance(struct usb_function_instance *fi) +{ + struct f_usb9pfs_opts *usb9pfs_opts = + container_of(fi, struct f_usb9pfs_opts, func_inst); + struct f_usb9pfs_dev *dev = usb9pfs_opts->dev; + + mutex_lock(&usb9pfs_lock); + list_del(&dev->usb9pfs_instance); + mutex_unlock(&usb9pfs_lock); + + kfree(usb9pfs_opts); +} + +static struct usb_function_instance *usb9pfs_alloc_instance(void) +{ + struct f_usb9pfs_opts *usb9pfs_opts; + struct f_usb9pfs_dev *dev; + + usb9pfs_opts = kzalloc(sizeof(*usb9pfs_opts), GFP_KERNEL); + if (!usb9pfs_opts) + return ERR_PTR(-ENOMEM); + + mutex_init(&usb9pfs_opts->lock); + + usb9pfs_opts->func_inst.set_inst_name = usb9pfs_set_inst_tag; + usb9pfs_opts->func_inst.free_func_inst = usb9pfs_free_instance; + + usb9pfs_opts->buflen = DEFAULT_BUFLEN; + + dev = kzalloc(sizeof(*dev), GFP_KERNEL); + if (IS_ERR(dev)) { + kfree(usb9pfs_opts); + return ERR_CAST(dev); + } + + usb9pfs_opts->dev = dev; + dev->opts = usb9pfs_opts; + + config_group_init_type_name(&usb9pfs_opts->func_inst.group, "", + &usb9pfs_func_type); + + mutex_lock(&usb9pfs_lock); + list_add_tail(&dev->usb9pfs_instance, &usbg_instance_list); + mutex_unlock(&usb9pfs_lock); + + return &usb9pfs_opts->func_inst; +} +DECLARE_USB_FUNCTION(usb9pfs, usb9pfs_alloc_instance, usb9pfs_alloc); + +static int __init usb9pfs_modinit(void) +{ + int ret; + + INIT_LIST_HEAD(&usbg_instance_list); + + ret = usb_function_register(&usb9pfsusb_func); + if (!ret) + v9fs_register_trans(&p9_usbg_trans); + + return ret; +} + +static void __exit usb9pfs_modexit(void) +{ + usb_function_unregister(&usb9pfsusb_func); + v9fs_unregister_trans(&p9_usbg_trans); +} + +module_init(usb9pfs_modinit); +module_exit(usb9pfs_modexit); + +MODULE_ALIAS_9P("usbg"); +MODULE_LICENSE("GPL"); +MODULE_DESCRIPTION("USB gadget 9pfs transport"); +MODULE_AUTHOR("Michael Grzeschik"); diff --git a/net/Kconfig b/net/Kconfig index f0a8692496ff..a629f92dc86b 100644 --- a/net/Kconfig +++ b/net/Kconfig @@ -66,6 +66,12 @@ config SKB_DECRYPTED config SKB_EXTENSIONS bool +config NET_DEVMEM + def_bool y + depends on DMA_SHARED_BUFFER + depends on GENERIC_ALLOCATOR + depends on PAGE_POOL + menu "Networking options" source "net/packet/Kconfig" @@ -290,15 +296,21 @@ config MAX_SKB_FRAGS If unsure, say 17. config RPS - bool + bool "Receive packet steering" depends on SMP && SYSFS default y + help + Software receive side packet steering (RPS) distributes the + load of received packet processing across multiple CPUs. config RFS_ACCEL - bool + bool "Hardware acceleration of RFS" depends on RPS select CPU_RMAP default y + help + Allowing drivers for multiqueue hardware with flow filter tables to + accelerate RFS. config SOCK_RX_QUEUE_MAPPING bool @@ -351,7 +363,7 @@ config BPF_STREAM_PARSER BPF_MAP_TYPE_SOCKMAP. config NET_FLOW_LIMIT - bool + bool "Net flow limit" depends on RPS default y help @@ -502,6 +514,7 @@ config FAILOVER config ETHTOOL_NETLINK bool "Netlink interface for ethtool" + select DIMLIB default y help An alternative userspace interface for ethtool based on generic diff --git a/net/atm/ioctl.c b/net/atm/ioctl.c index f81f8d56f5c0..0f7a39aeccc8 100644 --- a/net/atm/ioctl.c +++ b/net/atm/ioctl.c @@ -68,7 +68,7 @@ static int do_vcc_ioctl(struct socket *sock, unsigned int cmd, goto done; } error = put_user(sk->sk_sndbuf - sk_wmem_alloc_get(sk), - (int __user *)argp) ? -EFAULT : 0; + (int __user *)argp); goto done; case SIOCINQ: { @@ -83,7 +83,7 @@ static int do_vcc_ioctl(struct socket *sock, unsigned int cmd, skb = skb_peek(&sk->sk_receive_queue); amount = skb ? skb->len : 0; spin_unlock_irq(&sk->sk_receive_queue.lock); - error = put_user(amount, (int __user *)argp) ? -EFAULT : 0; + error = put_user(amount, (int __user *)argp); goto done; } case ATM_SETSC: diff --git a/net/batman-adv/originator.c b/net/batman-adv/originator.c index ac74f6ead62d..8f6dd2c6ee41 100644 --- a/net/batman-adv/originator.c +++ b/net/batman-adv/originator.c @@ -12,6 +12,7 @@ #include <linux/errno.h> #include <linux/etherdevice.h> #include <linux/gfp.h> +#include <linux/if_vlan.h> #include <linux/jiffies.h> #include <linux/kref.h> #include <linux/list.h> @@ -132,6 +133,29 @@ batadv_orig_node_vlan_get(struct batadv_orig_node *orig_node, } /** + * batadv_vlan_id_valid() - check if vlan id is in valid batman-adv encoding + * @vid: the VLAN identifier + * + * Return: true when either no vlan is set or if VLAN is in correct range, + * false otherwise + */ +static bool batadv_vlan_id_valid(unsigned short vid) +{ + unsigned short non_vlan = vid & ~(BATADV_VLAN_HAS_TAG | VLAN_VID_MASK); + + if (vid == 0) + return true; + + if (!(vid & BATADV_VLAN_HAS_TAG)) + return false; + + if (non_vlan) + return false; + + return true; +} + +/** * batadv_orig_node_vlan_new() - search and possibly create an orig_node_vlan * object * @orig_node: the originator serving the VLAN @@ -149,6 +173,9 @@ batadv_orig_node_vlan_new(struct batadv_orig_node *orig_node, { struct batadv_orig_node_vlan *vlan; + if (!batadv_vlan_id_valid(vid)) + return NULL; + spin_lock_bh(&orig_node->vlan_list_lock); /* first look if an object for this vid already exists */ diff --git a/net/batman-adv/soft-interface.c b/net/batman-adv/soft-interface.c index 30ecbc2ef1fd..2758aba47a2f 100644 --- a/net/batman-adv/soft-interface.c +++ b/net/batman-adv/soft-interface.c @@ -1020,9 +1020,10 @@ static void batadv_softif_init_early(struct net_device *dev) dev->netdev_ops = &batadv_netdev_ops; dev->needs_free_netdev = true; dev->priv_destructor = batadv_softif_free; - dev->features |= NETIF_F_HW_VLAN_CTAG_FILTER | NETIF_F_NETNS_LOCAL; - dev->features |= NETIF_F_LLTX; + dev->features |= NETIF_F_HW_VLAN_CTAG_FILTER; dev->priv_flags |= IFF_NO_QUEUE; + dev->lltx = true; + dev->netns_local = true; /* can't call min_mtu, because the needed variables * have not been initialized yet diff --git a/net/batman-adv/translation-table.c b/net/batman-adv/translation-table.c index b21ff3c36b07..2243cec18ecc 100644 --- a/net/batman-adv/translation-table.c +++ b/net/batman-adv/translation-table.c @@ -209,6 +209,20 @@ batadv_tt_global_hash_find(struct batadv_priv *bat_priv, const u8 *addr, } /** + * batadv_tt_local_entry_free_rcu() - free the tt_local_entry + * @rcu: rcu pointer of the tt_local_entry + */ +static void batadv_tt_local_entry_free_rcu(struct rcu_head *rcu) +{ + struct batadv_tt_local_entry *tt_local_entry; + + tt_local_entry = container_of(rcu, struct batadv_tt_local_entry, + common.rcu); + + kmem_cache_free(batadv_tl_cache, tt_local_entry); +} + +/** * batadv_tt_local_entry_release() - release tt_local_entry from lists and queue * for free after rcu grace period * @ref: kref pointer of the nc_node @@ -222,7 +236,7 @@ static void batadv_tt_local_entry_release(struct kref *ref) batadv_softif_vlan_put(tt_local_entry->vlan); - kfree_rcu(tt_local_entry, common.rcu); + call_rcu(&tt_local_entry->common.rcu, batadv_tt_local_entry_free_rcu); } /** @@ -241,6 +255,20 @@ batadv_tt_local_entry_put(struct batadv_tt_local_entry *tt_local_entry) } /** + * batadv_tt_global_entry_free_rcu() - free the tt_global_entry + * @rcu: rcu pointer of the tt_global_entry + */ +static void batadv_tt_global_entry_free_rcu(struct rcu_head *rcu) +{ + struct batadv_tt_global_entry *tt_global_entry; + + tt_global_entry = container_of(rcu, struct batadv_tt_global_entry, + common.rcu); + + kmem_cache_free(batadv_tg_cache, tt_global_entry); +} + +/** * batadv_tt_global_entry_release() - release tt_global_entry from lists and * queue for free after rcu grace period * @ref: kref pointer of the nc_node @@ -254,7 +282,7 @@ void batadv_tt_global_entry_release(struct kref *ref) batadv_tt_global_del_orig_list(tt_global_entry); - kfree_rcu(tt_global_entry, common.rcu); + call_rcu(&tt_global_entry->common.rcu, batadv_tt_global_entry_free_rcu); } /** @@ -380,6 +408,19 @@ static void batadv_tt_global_size_dec(struct batadv_orig_node *orig_node, } /** + * batadv_tt_orig_list_entry_free_rcu() - free the orig_entry + * @rcu: rcu pointer of the orig_entry + */ +static void batadv_tt_orig_list_entry_free_rcu(struct rcu_head *rcu) +{ + struct batadv_tt_orig_list_entry *orig_entry; + + orig_entry = container_of(rcu, struct batadv_tt_orig_list_entry, rcu); + + kmem_cache_free(batadv_tt_orig_cache, orig_entry); +} + +/** * batadv_tt_orig_list_entry_release() - release tt orig entry from lists and * queue for free after rcu grace period * @ref: kref pointer of the tt orig entry @@ -392,7 +433,7 @@ static void batadv_tt_orig_list_entry_release(struct kref *ref) refcount); batadv_orig_node_put(orig_entry->orig_node); - kfree_rcu(orig_entry, rcu); + call_rcu(&orig_entry->rcu, batadv_tt_orig_list_entry_free_rcu); } /** diff --git a/net/batman-adv/types.h b/net/batman-adv/types.h index 00840d5784fe..04f6398b3a40 100644 --- a/net/batman-adv/types.h +++ b/net/batman-adv/types.h @@ -287,7 +287,7 @@ struct batadv_frag_table_entry { /** @lock: lock to protect the list of fragments */ spinlock_t lock; - /** @timestamp: time (jiffie) of last received fragment */ + /** @timestamp: time (jiffy) of last received fragment */ unsigned long timestamp; /** @seqno: sequence number of the fragments in the list */ diff --git a/net/bluetooth/Makefile b/net/bluetooth/Makefile index 628d448d78be..5a3835b7dfcd 100644 --- a/net/bluetooth/Makefile +++ b/net/bluetooth/Makefile @@ -14,8 +14,7 @@ bluetooth_6lowpan-y := 6lowpan.o bluetooth-y := af_bluetooth.o hci_core.o hci_conn.o hci_event.o mgmt.o \ hci_sock.o hci_sysfs.o l2cap_core.o l2cap_sock.o smp.o lib.o \ - ecdh_helper.o hci_request.o mgmt_util.o mgmt_config.o hci_codec.o \ - eir.o hci_sync.o + ecdh_helper.o mgmt_util.o mgmt_config.o hci_codec.o eir.o hci_sync.o bluetooth-$(CONFIG_DEV_COREDUMP) += coredump.o diff --git a/net/bluetooth/cmtp/Kconfig b/net/bluetooth/cmtp/Kconfig index c8337786da6b..34e923466236 100644 --- a/net/bluetooth/cmtp/Kconfig +++ b/net/bluetooth/cmtp/Kconfig @@ -1,7 +1,7 @@ # SPDX-License-Identifier: GPL-2.0-only config BT_CMTP - tristate "CMTP protocol support" - depends on BT_BREDR && ISDN_CAPI + tristate "CMTP protocol support (DEPRECATED)" + depends on BT_BREDR && ISDN_CAPI && DEPRECATED help CMTP (CAPI Message Transport Protocol) is a transport layer for CAPI messages. CMTP is required for the Bluetooth Common diff --git a/net/bluetooth/cmtp/capi.c b/net/bluetooth/cmtp/capi.c index f3bedc3b613a..884703fda979 100644 --- a/net/bluetooth/cmtp/capi.c +++ b/net/bluetooth/cmtp/capi.c @@ -248,18 +248,10 @@ static void cmtp_recv_interopmsg(struct cmtp_session *session, struct sk_buff *s break; case CAPI_FUNCTION_GET_MANUFACTURER: - if (skb->len < CAPI_MSG_BASELEN + 15) - break; - - if (!info && ctrl) { - int len = min_t(uint, CAPI_MANUFACTURER_LEN, - skb->data[CAPI_MSG_BASELEN + 14]); - - memset(ctrl->manu, 0, CAPI_MANUFACTURER_LEN); - strncpy(ctrl->manu, - skb->data + CAPI_MSG_BASELEN + 15, len); - } - + if (!info && ctrl && skb->len > CAPI_MSG_BASELEN + 14) + strscpy_pad(ctrl->manu, + skb->data + CAPI_MSG_BASELEN + 15, + skb->data[CAPI_MSG_BASELEN + 14]); break; case CAPI_FUNCTION_GET_VERSION: @@ -276,18 +268,10 @@ static void cmtp_recv_interopmsg(struct cmtp_session *session, struct sk_buff *s break; case CAPI_FUNCTION_GET_SERIAL_NUMBER: - if (skb->len < CAPI_MSG_BASELEN + 17) - break; - - if (!info && ctrl) { - int len = min_t(uint, CAPI_SERIAL_LEN, - skb->data[CAPI_MSG_BASELEN + 16]); - - memset(ctrl->serial, 0, CAPI_SERIAL_LEN); - strncpy(ctrl->serial, - skb->data + CAPI_MSG_BASELEN + 17, len); - } - + if (!info && ctrl && skb->len > CAPI_MSG_BASELEN + 16) + strscpy_pad(ctrl->serial, + skb->data + CAPI_MSG_BASELEN + 17, + skb->data[CAPI_MSG_BASELEN + 16]); break; } diff --git a/net/bluetooth/hci_conn.c b/net/bluetooth/hci_conn.c index 0c76dcde5361..d083117ee36c 100644 --- a/net/bluetooth/hci_conn.c +++ b/net/bluetooth/hci_conn.c @@ -34,7 +34,6 @@ #include <net/bluetooth/iso.h> #include <net/bluetooth/mgmt.h> -#include "hci_request.h" #include "smp.h" #include "eir.h" @@ -107,8 +106,7 @@ void hci_connect_le_scan_cleanup(struct hci_conn *conn, u8 status) * where a timeout + cancel does indicate an actual failure. */ if (status && status != HCI_ERROR_UNKNOWN_CONN_ID) - mgmt_connect_failed(hdev, &conn->dst, conn->type, - conn->dst_type, status); + mgmt_connect_failed(hdev, conn, status); /* The connection attempt was doing scan for new RPA, and is * in scan phase. If params are not associated with any other @@ -779,7 +777,6 @@ static int hci_le_big_terminate(struct hci_dev *hdev, u8 big, struct hci_conn *c if (!d) return -ENOMEM; - memset(d, 0, sizeof(*d)); d->big = big; d->sync_handle = conn->sync_handle; @@ -899,8 +896,8 @@ static int hci_conn_hash_alloc_unset(struct hci_dev *hdev) U16_MAX, GFP_ATOMIC); } -struct hci_conn *hci_conn_add(struct hci_dev *hdev, int type, bdaddr_t *dst, - u8 role, u16 handle) +static struct hci_conn *__hci_conn_add(struct hci_dev *hdev, int type, bdaddr_t *dst, + u8 role, u16 handle) { struct hci_conn *conn; @@ -1041,7 +1038,16 @@ struct hci_conn *hci_conn_add_unset(struct hci_dev *hdev, int type, if (unlikely(handle < 0)) return ERR_PTR(-ECONNREFUSED); - return hci_conn_add(hdev, type, dst, role, handle); + return __hci_conn_add(hdev, type, dst, role, handle); +} + +struct hci_conn *hci_conn_add(struct hci_dev *hdev, int type, bdaddr_t *dst, + u8 role, u16 handle) +{ + if (handle > HCI_CONN_HANDLE_MAX) + return ERR_PTR(-EINVAL); + + return __hci_conn_add(hdev, type, dst, role, handle); } static void hci_conn_cleanup_child(struct hci_conn *conn, u8 reason) @@ -1242,8 +1248,7 @@ void hci_conn_failed(struct hci_conn *conn, u8 status) hci_le_conn_failed(conn, status); break; case ACL_LINK: - mgmt_connect_failed(hdev, &conn->dst, conn->type, - conn->dst_type, status); + mgmt_connect_failed(hdev, conn, status); break; } @@ -2944,5 +2949,9 @@ int hci_abort_conn(struct hci_conn *conn, u8 reason) return 0; } - return hci_cmd_sync_queue_once(hdev, abort_conn_sync, conn, NULL); + /* Run immediately if on cmd_sync_work since this may be called + * as a result to MGMT_OP_DISCONNECT/MGMT_OP_UNPAIR which does + * already queue its callback on cmd_sync_work. + */ + return hci_cmd_sync_run_once(hdev, abort_conn_sync, conn, NULL); } diff --git a/net/bluetooth/hci_core.c b/net/bluetooth/hci_core.c index dd3b0f501018..d6976db02c06 100644 --- a/net/bluetooth/hci_core.c +++ b/net/bluetooth/hci_core.c @@ -40,7 +40,6 @@ #include <net/bluetooth/l2cap.h> #include <net/bluetooth/mgmt.h> -#include "hci_request.h" #include "hci_debugfs.h" #include "smp.h" #include "leds.h" @@ -63,50 +62,6 @@ DEFINE_MUTEX(hci_cb_list_lock); /* HCI ID Numbering */ static DEFINE_IDA(hci_index_ida); -static int hci_scan_req(struct hci_request *req, unsigned long opt) -{ - __u8 scan = opt; - - BT_DBG("%s %x", req->hdev->name, scan); - - /* Inquiry and Page scans */ - hci_req_add(req, HCI_OP_WRITE_SCAN_ENABLE, 1, &scan); - return 0; -} - -static int hci_auth_req(struct hci_request *req, unsigned long opt) -{ - __u8 auth = opt; - - BT_DBG("%s %x", req->hdev->name, auth); - - /* Authentication */ - hci_req_add(req, HCI_OP_WRITE_AUTH_ENABLE, 1, &auth); - return 0; -} - -static int hci_encrypt_req(struct hci_request *req, unsigned long opt) -{ - __u8 encrypt = opt; - - BT_DBG("%s %x", req->hdev->name, encrypt); - - /* Encryption */ - hci_req_add(req, HCI_OP_WRITE_ENCRYPT_MODE, 1, &encrypt); - return 0; -} - -static int hci_linkpol_req(struct hci_request *req, unsigned long opt) -{ - __le16 policy = cpu_to_le16(opt); - - BT_DBG("%s %x", req->hdev->name, policy); - - /* Default link policy */ - hci_req_add(req, HCI_OP_WRITE_DEF_LINK_POLICY, 2, &policy); - return 0; -} - /* Get HCI device by index. * Device is held on return. */ struct hci_dev *hci_dev_get(int index) @@ -164,13 +119,6 @@ void hci_discovery_set_state(struct hci_dev *hdev, int state) case DISCOVERY_STARTING: break; case DISCOVERY_FINDING: - /* If discovery was not started then it was initiated by the - * MGMT interface so no MGMT event shall be generated either - */ - if (old_state != DISCOVERY_STARTING) { - hdev->discovery.state = old_state; - return; - } mgmt_discovering(hdev, 1); break; case DISCOVERY_RESOLVING: @@ -356,33 +304,12 @@ static int inquiry_cache_dump(struct hci_dev *hdev, int num, __u8 *buf) return copied; } -static int hci_inq_req(struct hci_request *req, unsigned long opt) -{ - struct hci_inquiry_req *ir = (struct hci_inquiry_req *) opt; - struct hci_dev *hdev = req->hdev; - struct hci_cp_inquiry cp; - - BT_DBG("%s", hdev->name); - - if (test_bit(HCI_INQUIRY, &hdev->flags)) - return 0; - - /* Start Inquiry */ - memcpy(&cp.lap, &ir->lap, 3); - cp.length = ir->length; - cp.num_rsp = ir->num_rsp; - hci_req_add(req, HCI_OP_INQUIRY, sizeof(cp), &cp); - - return 0; -} - int hci_inquiry(void __user *arg) { __u8 __user *ptr = arg; struct hci_inquiry_req ir; struct hci_dev *hdev; int err = 0, do_inquiry = 0, max_rsp; - long timeo; __u8 *buf; if (copy_from_user(&ir, ptr, sizeof(ir))) @@ -421,11 +348,11 @@ int hci_inquiry(void __user *arg) } hci_dev_unlock(hdev); - timeo = ir.length * msecs_to_jiffies(2000); - if (do_inquiry) { - err = hci_req_sync(hdev, hci_inq_req, (unsigned long) &ir, - timeo, NULL); + hci_req_sync_lock(hdev); + err = hci_inquiry_sync(hdev, ir.length, ir.num_rsp); + hci_req_sync_unlock(hdev); + if (err < 0) goto done; @@ -735,6 +662,7 @@ int hci_dev_cmd(unsigned int cmd, void __user *arg) { struct hci_dev *hdev; struct hci_dev_req dr; + __le16 policy; int err = 0; if (copy_from_user(&dr, arg, sizeof(dr))) @@ -761,8 +689,8 @@ int hci_dev_cmd(unsigned int cmd, void __user *arg) switch (cmd) { case HCISETAUTH: - err = hci_req_sync(hdev, hci_auth_req, dr.dev_opt, - HCI_INIT_TIMEOUT, NULL); + err = hci_cmd_sync_status(hdev, HCI_OP_WRITE_AUTH_ENABLE, + 1, &dr.dev_opt, HCI_CMD_TIMEOUT); break; case HCISETENCRYPT: @@ -773,19 +701,21 @@ int hci_dev_cmd(unsigned int cmd, void __user *arg) if (!test_bit(HCI_AUTH, &hdev->flags)) { /* Auth must be enabled first */ - err = hci_req_sync(hdev, hci_auth_req, dr.dev_opt, - HCI_INIT_TIMEOUT, NULL); + err = hci_cmd_sync_status(hdev, + HCI_OP_WRITE_AUTH_ENABLE, + 1, &dr.dev_opt, + HCI_CMD_TIMEOUT); if (err) break; } - err = hci_req_sync(hdev, hci_encrypt_req, dr.dev_opt, - HCI_INIT_TIMEOUT, NULL); + err = hci_cmd_sync_status(hdev, HCI_OP_WRITE_ENCRYPT_MODE, + 1, &dr.dev_opt, HCI_CMD_TIMEOUT); break; case HCISETSCAN: - err = hci_req_sync(hdev, hci_scan_req, dr.dev_opt, - HCI_INIT_TIMEOUT, NULL); + err = hci_cmd_sync_status(hdev, HCI_OP_WRITE_SCAN_ENABLE, + 1, &dr.dev_opt, HCI_CMD_TIMEOUT); /* Ensure that the connectable and discoverable states * get correctly modified as this was a non-mgmt change. @@ -795,8 +725,10 @@ int hci_dev_cmd(unsigned int cmd, void __user *arg) break; case HCISETLINKPOL: - err = hci_req_sync(hdev, hci_linkpol_req, dr.dev_opt, - HCI_INIT_TIMEOUT, NULL); + policy = cpu_to_le16(dr.dev_opt); + + err = hci_cmd_sync_status(hdev, HCI_OP_WRITE_DEF_LINK_POLICY, + 2, &policy, HCI_CMD_TIMEOUT); break; case HCISETLINKMODE: @@ -837,7 +769,7 @@ int hci_get_dev_list(void __user *arg) struct hci_dev *hdev; struct hci_dev_list_req *dl; struct hci_dev_req *dr; - int n = 0, size, err; + int n = 0, err; __u16 dev_num; if (get_user(dev_num, (__u16 __user *) arg)) @@ -846,12 +778,11 @@ int hci_get_dev_list(void __user *arg) if (!dev_num || dev_num > (PAGE_SIZE * 2) / sizeof(*dr)) return -EINVAL; - size = sizeof(*dl) + dev_num * sizeof(*dr); - - dl = kzalloc(size, GFP_KERNEL); + dl = kzalloc(struct_size(dl, dev_req, dev_num), GFP_KERNEL); if (!dl) return -ENOMEM; + dl->dev_num = dev_num; dr = dl->dev_req; read_lock(&hci_dev_list_lock); @@ -865,8 +796,8 @@ int hci_get_dev_list(void __user *arg) if (hci_dev_test_flag(hdev, HCI_AUTO_OFF)) flags &= ~BIT(HCI_UP); - (dr + n)->dev_id = hdev->id; - (dr + n)->dev_opt = flags; + dr[n].dev_id = hdev->id; + dr[n].dev_opt = flags; if (++n >= dev_num) break; @@ -874,9 +805,7 @@ int hci_get_dev_list(void __user *arg) read_unlock(&hci_dev_list_lock); dl->dev_num = n; - size = sizeof(*dl) + n * sizeof(*dr); - - err = copy_to_user(arg, dl, size); + err = copy_to_user(arg, dl, struct_size(dl, dev_req, n)); kfree(dl); return err ? -EFAULT : 0; @@ -2477,10 +2406,16 @@ static int hci_suspend_notifier(struct notifier_block *nb, unsigned long action, /* To avoid a potential race with hci_unregister_dev. */ hci_dev_hold(hdev); - if (action == PM_SUSPEND_PREPARE) + switch (action) { + case PM_HIBERNATION_PREPARE: + case PM_SUSPEND_PREPARE: ret = hci_suspend_dev(hdev); - else if (action == PM_POST_SUSPEND) + break; + case PM_POST_HIBERNATION: + case PM_POST_SUSPEND: ret = hci_resume_dev(hdev); + break; + } if (ret) bt_dev_err(hdev, "Suspend notifier action (%lu) failed: %d", @@ -2615,7 +2550,6 @@ struct hci_dev *hci_alloc_dev_priv(int sizeof_priv) INIT_DELAYED_WORK(&hdev->ncmd_timer, hci_ncmd_timeout); hci_devcd_setup(hdev); - hci_request_setup(hdev); hci_init_sysfs(hdev); discovery_init(hdev); @@ -2751,7 +2685,11 @@ void hci_unregister_dev(struct hci_dev *hdev) list_del(&hdev->list); write_unlock(&hci_dev_list_lock); + cancel_work_sync(&hdev->rx_work); + cancel_work_sync(&hdev->cmd_work); + cancel_work_sync(&hdev->tx_work); cancel_work_sync(&hdev->power_on); + cancel_work_sync(&hdev->error_reset); hci_cmd_sync_clear(hdev); @@ -2944,15 +2882,31 @@ int hci_reset_dev(struct hci_dev *hdev) } EXPORT_SYMBOL(hci_reset_dev); +static u8 hci_dev_classify_pkt_type(struct hci_dev *hdev, struct sk_buff *skb) +{ + if (hdev->classify_pkt_type) + return hdev->classify_pkt_type(hdev, skb); + + return hci_skb_pkt_type(skb); +} + /* Receive frame from HCI drivers */ int hci_recv_frame(struct hci_dev *hdev, struct sk_buff *skb) { + u8 dev_pkt_type; + if (!hdev || (!test_bit(HCI_UP, &hdev->flags) && !test_bit(HCI_INIT, &hdev->flags))) { kfree_skb(skb); return -ENXIO; } + /* Check if the driver agree with packet type classification */ + dev_pkt_type = hci_dev_classify_pkt_type(hdev, skb); + if (hci_skb_pkt_type(skb) != dev_pkt_type) { + hci_skb_pkt_type(skb) = dev_pkt_type; + } + switch (hci_skb_pkt_type(skb)) { case HCI_EVENT_PKT: break; @@ -3097,7 +3051,7 @@ int hci_send_cmd(struct hci_dev *hdev, __u16 opcode, __u32 plen, BT_DBG("%s opcode 0x%4.4x plen %d", hdev->name, opcode, plen); - skb = hci_prepare_cmd(hdev, opcode, plen, param); + skb = hci_cmd_sync_alloc(hdev, opcode, plen, param, NULL); if (!skb) { bt_dev_err(hdev, "no memory for command"); return -ENOMEM; @@ -3132,7 +3086,7 @@ int __hci_cmd_send(struct hci_dev *hdev, u16 opcode, u32 plen, return -EINVAL; } - skb = hci_prepare_cmd(hdev, opcode, plen, param); + skb = hci_cmd_sync_alloc(hdev, opcode, plen, param, NULL); if (!skb) { bt_dev_err(hdev, "no memory for command (opcode 0x%4.4x)", opcode); @@ -3716,19 +3670,19 @@ static void hci_sched_le(struct hci_dev *hdev) { struct hci_chan *chan; struct sk_buff *skb; - int quote, cnt, tmp; + int quote, *cnt, tmp; BT_DBG("%s", hdev->name); if (!hci_conn_num(hdev, LE_LINK)) return; - cnt = hdev->le_pkts ? hdev->le_cnt : hdev->acl_cnt; + cnt = hdev->le_pkts ? &hdev->le_cnt : &hdev->acl_cnt; - __check_timeout(hdev, cnt, LE_LINK); + __check_timeout(hdev, *cnt, LE_LINK); - tmp = cnt; - while (cnt && (chan = hci_chan_sent(hdev, LE_LINK, "e))) { + tmp = *cnt; + while (*cnt && (chan = hci_chan_sent(hdev, LE_LINK, "e))) { u32 priority = (skb_peek(&chan->data_q))->priority; while (quote-- && (skb = skb_peek(&chan->data_q))) { BT_DBG("chan %p skb %p len %d priority %u", chan, skb, @@ -3743,7 +3697,7 @@ static void hci_sched_le(struct hci_dev *hdev) hci_send_frame(hdev, skb); hdev->le_last_tx = jiffies; - cnt--; + (*cnt)--; chan->sent++; chan->conn->sent++; @@ -3753,12 +3707,7 @@ static void hci_sched_le(struct hci_dev *hdev) } } - if (hdev->le_pkts) - hdev->le_cnt = cnt; - else - hdev->acl_cnt = cnt; - - if (cnt != tmp) + if (*cnt != tmp) hci_prio_recalculate(hdev, LE_LINK); } @@ -4117,7 +4066,7 @@ static void hci_send_cmd_sync(struct hci_dev *hdev, struct sk_buff *skb) return; } - if (hci_req_status_pend(hdev) && + if (hdev->req_status == HCI_REQ_PEND && !hci_dev_test_and_set_flag(hdev, HCI_CMD_PENDING)) { kfree_skb(hdev->req_skb); hdev->req_skb = skb_clone(hdev->sent_cmd, GFP_KERNEL); diff --git a/net/bluetooth/hci_debugfs.c b/net/bluetooth/hci_debugfs.c index ce3ff2fa72e5..f625074d1f00 100644 --- a/net/bluetooth/hci_debugfs.c +++ b/net/bluetooth/hci_debugfs.c @@ -28,7 +28,6 @@ #include <net/bluetooth/hci_core.h> #include "smp.h" -#include "hci_request.h" #include "hci_debugfs.h" #define DEFINE_QUIRK_ATTRIBUTE(__name, __quirk) \ diff --git a/net/bluetooth/hci_event.c b/net/bluetooth/hci_event.c index a487f9df8145..1c82dcdf6e8f 100644 --- a/net/bluetooth/hci_event.c +++ b/net/bluetooth/hci_event.c @@ -33,7 +33,6 @@ #include <net/bluetooth/hci_core.h> #include <net/bluetooth/mgmt.h> -#include "hci_request.h" #include "hci_debugfs.h" #include "hci_codec.h" #include "smp.h" @@ -1722,9 +1721,10 @@ static void le_set_scan_enable_complete(struct hci_dev *hdev, u8 enable) switch (enable) { case LE_SCAN_ENABLE: hci_dev_set_flag(hdev, HCI_LE_SCAN); - if (hdev->le_scan_type == LE_SCAN_ACTIVE) + if (hdev->le_scan_type == LE_SCAN_ACTIVE) { clear_pending_adv_report(hdev); - hci_discovery_set_state(hdev, DISCOVERY_FINDING); + hci_discovery_set_state(hdev, DISCOVERY_FINDING); + } break; case LE_SCAN_DISABLE: @@ -5920,7 +5920,7 @@ static struct hci_conn *check_pending_le_conn(struct hci_dev *hdev, * while we have an existing one in peripheral role. */ if (hdev->conn_hash.le_num_peripheral > 0 && - (!test_bit(HCI_QUIRK_VALID_LE_STATES, &hdev->quirks) || + (test_bit(HCI_QUIRK_BROKEN_LE_STATES, &hdev->quirks) || !(hdev->le_states[3] & 0x10))) return NULL; @@ -6311,6 +6311,13 @@ static void hci_le_ext_adv_report_evt(struct hci_dev *hdev, void *data, evt_type = __le16_to_cpu(info->type) & LE_EXT_ADV_EVT_TYPE_MASK; legacy_evt_type = ext_evt_type_to_legacy(hdev, evt_type); + + if (test_bit(HCI_QUIRK_FIXUP_LE_EXT_ADV_REPORT_PHY, + &hdev->quirks)) { + info->primary_phy &= 0x1f; + info->secondary_phy &= 0x1f; + } + if (legacy_evt_type != LE_ADV_INVALID) { process_adv_report(hdev, legacy_evt_type, &info->bdaddr, info->bdaddr_type, NULL, 0, @@ -6660,6 +6667,7 @@ static void hci_le_cis_estabilished_evt(struct hci_dev *hdev, void *data, struct bt_iso_qos *qos; bool pending = false; u16 handle = __le16_to_cpu(ev->handle); + u32 c_sdu_interval, p_sdu_interval; bt_dev_dbg(hdev, "status 0x%2.2x", ev->status); @@ -6684,12 +6692,25 @@ static void hci_le_cis_estabilished_evt(struct hci_dev *hdev, void *data, pending = test_and_clear_bit(HCI_CONN_CREATE_CIS, &conn->flags); - /* Convert ISO Interval (1.25 ms slots) to SDU Interval (us) */ - qos->ucast.in.interval = le16_to_cpu(ev->interval) * 1250; - qos->ucast.out.interval = qos->ucast.in.interval; + /* BLUETOOTH CORE SPECIFICATION Version 5.4 | Vol 6, Part G + * page 3075: + * Transport_Latency_C_To_P = CIG_Sync_Delay + (FT_C_To_P) × + * ISO_Interval + SDU_Interval_C_To_P + * ... + * SDU_Interval = (CIG_Sync_Delay + (FT) x ISO_Interval) - + * Transport_Latency + */ + c_sdu_interval = (get_unaligned_le24(ev->cig_sync_delay) + + (ev->c_ft * le16_to_cpu(ev->interval) * 1250)) - + get_unaligned_le24(ev->c_latency); + p_sdu_interval = (get_unaligned_le24(ev->cig_sync_delay) + + (ev->p_ft * le16_to_cpu(ev->interval) * 1250)) - + get_unaligned_le24(ev->p_latency); switch (conn->role) { case HCI_ROLE_SLAVE: + qos->ucast.in.interval = c_sdu_interval; + qos->ucast.out.interval = p_sdu_interval; /* Convert Transport Latency (us) to Latency (msec) */ qos->ucast.in.latency = DIV_ROUND_CLOSEST(get_unaligned_le24(ev->c_latency), @@ -6703,6 +6724,8 @@ static void hci_le_cis_estabilished_evt(struct hci_dev *hdev, void *data, qos->ucast.out.phy = ev->p_phy; break; case HCI_ROLE_MASTER: + qos->ucast.in.interval = p_sdu_interval; + qos->ucast.out.interval = c_sdu_interval; /* Convert Transport Latency (us) to Latency (msec) */ qos->ucast.out.latency = DIV_ROUND_CLOSEST(get_unaligned_le24(ev->c_latency), @@ -6893,6 +6916,10 @@ static void hci_le_big_sync_established_evt(struct hci_dev *hdev, void *data, bis = hci_conn_hash_lookup_handle(hdev, handle); if (!bis) { + if (handle > HCI_CONN_HANDLE_MAX) { + bt_dev_dbg(hdev, "ignore too large handle %u", handle); + continue; + } bis = hci_conn_add(hdev, ISO_LINK, BDADDR_ANY, HCI_ROLE_SLAVE, handle); if (IS_ERR(bis)) @@ -6961,6 +6988,8 @@ static void hci_le_big_info_adv_report_evt(struct hci_dev *hdev, void *data, if (!pa_sync) goto unlock; + pa_sync->iso_qos.bcast.encryption = ev->encryption; + /* Notify iso layer */ hci_connect_cfm(pa_sync, 0); diff --git a/net/bluetooth/hci_request.c b/net/bluetooth/hci_request.c deleted file mode 100644 index efea25eb56ce..000000000000 --- a/net/bluetooth/hci_request.c +++ /dev/null @@ -1,903 +0,0 @@ -/* - BlueZ - Bluetooth protocol stack for Linux - - Copyright (C) 2014 Intel Corporation - - This program is free software; you can redistribute it and/or modify - it under the terms of the GNU General Public License version 2 as - published by the Free Software Foundation; - - THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS - OR IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY, - FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT OF THIRD PARTY RIGHTS. - IN NO EVENT SHALL THE COPYRIGHT HOLDER(S) AND AUTHOR(S) BE LIABLE FOR ANY - CLAIM, OR ANY SPECIAL INDIRECT OR CONSEQUENTIAL DAMAGES, OR ANY DAMAGES - WHATSOEVER RESULTING FROM LOSS OF USE, DATA OR PROFITS, WHETHER IN AN - ACTION OF CONTRACT, NEGLIGENCE OR OTHER TORTIOUS ACTION, ARISING OUT OF - OR IN CONNECTION WITH THE USE OR PERFORMANCE OF THIS SOFTWARE. - - ALL LIABILITY, INCLUDING LIABILITY FOR INFRINGEMENT OF ANY PATENTS, - COPYRIGHTS, TRADEMARKS OR OTHER RIGHTS, RELATING TO USE OF THIS - SOFTWARE IS DISCLAIMED. -*/ - -#include <linux/sched/signal.h> - -#include <net/bluetooth/bluetooth.h> -#include <net/bluetooth/hci_core.h> -#include <net/bluetooth/mgmt.h> - -#include "smp.h" -#include "hci_request.h" -#include "msft.h" -#include "eir.h" - -void hci_req_init(struct hci_request *req, struct hci_dev *hdev) -{ - skb_queue_head_init(&req->cmd_q); - req->hdev = hdev; - req->err = 0; -} - -void hci_req_purge(struct hci_request *req) -{ - skb_queue_purge(&req->cmd_q); -} - -bool hci_req_status_pend(struct hci_dev *hdev) -{ - return hdev->req_status == HCI_REQ_PEND; -} - -static int req_run(struct hci_request *req, hci_req_complete_t complete, - hci_req_complete_skb_t complete_skb) -{ - struct hci_dev *hdev = req->hdev; - struct sk_buff *skb; - unsigned long flags; - - bt_dev_dbg(hdev, "length %u", skb_queue_len(&req->cmd_q)); - - /* If an error occurred during request building, remove all HCI - * commands queued on the HCI request queue. - */ - if (req->err) { - skb_queue_purge(&req->cmd_q); - return req->err; - } - - /* Do not allow empty requests */ - if (skb_queue_empty(&req->cmd_q)) - return -ENODATA; - - skb = skb_peek_tail(&req->cmd_q); - if (complete) { - bt_cb(skb)->hci.req_complete = complete; - } else if (complete_skb) { - bt_cb(skb)->hci.req_complete_skb = complete_skb; - bt_cb(skb)->hci.req_flags |= HCI_REQ_SKB; - } - - spin_lock_irqsave(&hdev->cmd_q.lock, flags); - skb_queue_splice_tail(&req->cmd_q, &hdev->cmd_q); - spin_unlock_irqrestore(&hdev->cmd_q.lock, flags); - - queue_work(hdev->workqueue, &hdev->cmd_work); - - return 0; -} - -int hci_req_run(struct hci_request *req, hci_req_complete_t complete) -{ - return req_run(req, complete, NULL); -} - -int hci_req_run_skb(struct hci_request *req, hci_req_complete_skb_t complete) -{ - return req_run(req, NULL, complete); -} - -void hci_req_sync_complete(struct hci_dev *hdev, u8 result, u16 opcode, - struct sk_buff *skb) -{ - bt_dev_dbg(hdev, "result 0x%2.2x", result); - - if (hdev->req_status == HCI_REQ_PEND) { - hdev->req_result = result; - hdev->req_status = HCI_REQ_DONE; - if (skb) { - kfree_skb(hdev->req_skb); - hdev->req_skb = skb_get(skb); - } - wake_up_interruptible(&hdev->req_wait_q); - } -} - -/* Execute request and wait for completion. */ -int __hci_req_sync(struct hci_dev *hdev, int (*func)(struct hci_request *req, - unsigned long opt), - unsigned long opt, u32 timeout, u8 *hci_status) -{ - struct hci_request req; - int err = 0; - - bt_dev_dbg(hdev, "start"); - - hci_req_init(&req, hdev); - - hdev->req_status = HCI_REQ_PEND; - - err = func(&req, opt); - if (err) { - if (hci_status) - *hci_status = HCI_ERROR_UNSPECIFIED; - return err; - } - - err = hci_req_run_skb(&req, hci_req_sync_complete); - if (err < 0) { - hdev->req_status = 0; - - /* ENODATA means the HCI request command queue is empty. - * This can happen when a request with conditionals doesn't - * trigger any commands to be sent. This is normal behavior - * and should not trigger an error return. - */ - if (err == -ENODATA) { - if (hci_status) - *hci_status = 0; - return 0; - } - - if (hci_status) - *hci_status = HCI_ERROR_UNSPECIFIED; - - return err; - } - - err = wait_event_interruptible_timeout(hdev->req_wait_q, - hdev->req_status != HCI_REQ_PEND, timeout); - - if (err == -ERESTARTSYS) - return -EINTR; - - switch (hdev->req_status) { - case HCI_REQ_DONE: - err = -bt_to_errno(hdev->req_result); - if (hci_status) - *hci_status = hdev->req_result; - break; - - case HCI_REQ_CANCELED: - err = -hdev->req_result; - if (hci_status) - *hci_status = HCI_ERROR_UNSPECIFIED; - break; - - default: - err = -ETIMEDOUT; - if (hci_status) - *hci_status = HCI_ERROR_UNSPECIFIED; - break; - } - - kfree_skb(hdev->req_skb); - hdev->req_skb = NULL; - hdev->req_status = hdev->req_result = 0; - - bt_dev_dbg(hdev, "end: err %d", err); - - return err; -} - -int hci_req_sync(struct hci_dev *hdev, int (*req)(struct hci_request *req, - unsigned long opt), - unsigned long opt, u32 timeout, u8 *hci_status) -{ - int ret; - - /* Serialize all requests */ - hci_req_sync_lock(hdev); - /* check the state after obtaing the lock to protect the HCI_UP - * against any races from hci_dev_do_close when the controller - * gets removed. - */ - if (test_bit(HCI_UP, &hdev->flags)) - ret = __hci_req_sync(hdev, req, opt, timeout, hci_status); - else - ret = -ENETDOWN; - hci_req_sync_unlock(hdev); - - return ret; -} - -struct sk_buff *hci_prepare_cmd(struct hci_dev *hdev, u16 opcode, u32 plen, - const void *param) -{ - int len = HCI_COMMAND_HDR_SIZE + plen; - struct hci_command_hdr *hdr; - struct sk_buff *skb; - - skb = bt_skb_alloc(len, GFP_ATOMIC); - if (!skb) - return NULL; - - hdr = skb_put(skb, HCI_COMMAND_HDR_SIZE); - hdr->opcode = cpu_to_le16(opcode); - hdr->plen = plen; - - if (plen) - skb_put_data(skb, param, plen); - - bt_dev_dbg(hdev, "skb len %d", skb->len); - - hci_skb_pkt_type(skb) = HCI_COMMAND_PKT; - hci_skb_opcode(skb) = opcode; - - return skb; -} - -/* Queue a command to an asynchronous HCI request */ -void hci_req_add_ev(struct hci_request *req, u16 opcode, u32 plen, - const void *param, u8 event) -{ - struct hci_dev *hdev = req->hdev; - struct sk_buff *skb; - - bt_dev_dbg(hdev, "opcode 0x%4.4x plen %d", opcode, plen); - - /* If an error occurred during request building, there is no point in - * queueing the HCI command. We can simply return. - */ - if (req->err) - return; - - skb = hci_prepare_cmd(hdev, opcode, plen, param); - if (!skb) { - bt_dev_err(hdev, "no memory for command (opcode 0x%4.4x)", - opcode); - req->err = -ENOMEM; - return; - } - - if (skb_queue_empty(&req->cmd_q)) - bt_cb(skb)->hci.req_flags |= HCI_REQ_START; - - hci_skb_event(skb) = event; - - skb_queue_tail(&req->cmd_q, skb); -} - -void hci_req_add(struct hci_request *req, u16 opcode, u32 plen, - const void *param) -{ - bt_dev_dbg(req->hdev, "HCI_REQ-0x%4.4x", opcode); - hci_req_add_ev(req, opcode, plen, param, 0); -} - -static void start_interleave_scan(struct hci_dev *hdev) -{ - hdev->interleave_scan_state = INTERLEAVE_SCAN_NO_FILTER; - queue_delayed_work(hdev->req_workqueue, - &hdev->interleave_scan, 0); -} - -static bool is_interleave_scanning(struct hci_dev *hdev) -{ - return hdev->interleave_scan_state != INTERLEAVE_SCAN_NONE; -} - -static void cancel_interleave_scan(struct hci_dev *hdev) -{ - bt_dev_dbg(hdev, "cancelling interleave scan"); - - cancel_delayed_work_sync(&hdev->interleave_scan); - - hdev->interleave_scan_state = INTERLEAVE_SCAN_NONE; -} - -/* Return true if interleave_scan wasn't started until exiting this function, - * otherwise, return false - */ -static bool __hci_update_interleaved_scan(struct hci_dev *hdev) -{ - /* Do interleaved scan only if all of the following are true: - * - There is at least one ADV monitor - * - At least one pending LE connection or one device to be scanned for - * - Monitor offloading is not supported - * If so, we should alternate between allowlist scan and one without - * any filters to save power. - */ - bool use_interleaving = hci_is_adv_monitoring(hdev) && - !(list_empty(&hdev->pend_le_conns) && - list_empty(&hdev->pend_le_reports)) && - hci_get_adv_monitor_offload_ext(hdev) == - HCI_ADV_MONITOR_EXT_NONE; - bool is_interleaving = is_interleave_scanning(hdev); - - if (use_interleaving && !is_interleaving) { - start_interleave_scan(hdev); - bt_dev_dbg(hdev, "starting interleave scan"); - return true; - } - - if (!use_interleaving && is_interleaving) - cancel_interleave_scan(hdev); - - return false; -} - -void hci_req_add_le_scan_disable(struct hci_request *req, bool rpa_le_conn) -{ - struct hci_dev *hdev = req->hdev; - - if (hdev->scanning_paused) { - bt_dev_dbg(hdev, "Scanning is paused for suspend"); - return; - } - - if (use_ext_scan(hdev)) { - struct hci_cp_le_set_ext_scan_enable cp; - - memset(&cp, 0, sizeof(cp)); - cp.enable = LE_SCAN_DISABLE; - hci_req_add(req, HCI_OP_LE_SET_EXT_SCAN_ENABLE, sizeof(cp), - &cp); - } else { - struct hci_cp_le_set_scan_enable cp; - - memset(&cp, 0, sizeof(cp)); - cp.enable = LE_SCAN_DISABLE; - hci_req_add(req, HCI_OP_LE_SET_SCAN_ENABLE, sizeof(cp), &cp); - } - - /* Disable address resolution */ - if (hci_dev_test_flag(hdev, HCI_LL_RPA_RESOLUTION) && !rpa_le_conn) { - __u8 enable = 0x00; - - hci_req_add(req, HCI_OP_LE_SET_ADDR_RESOLV_ENABLE, 1, &enable); - } -} - -static void del_from_accept_list(struct hci_request *req, bdaddr_t *bdaddr, - u8 bdaddr_type) -{ - struct hci_cp_le_del_from_accept_list cp; - - cp.bdaddr_type = bdaddr_type; - bacpy(&cp.bdaddr, bdaddr); - - bt_dev_dbg(req->hdev, "Remove %pMR (0x%x) from accept list", &cp.bdaddr, - cp.bdaddr_type); - hci_req_add(req, HCI_OP_LE_DEL_FROM_ACCEPT_LIST, sizeof(cp), &cp); - - if (use_ll_privacy(req->hdev)) { - struct smp_irk *irk; - - irk = hci_find_irk_by_addr(req->hdev, bdaddr, bdaddr_type); - if (irk) { - struct hci_cp_le_del_from_resolv_list cp; - - cp.bdaddr_type = bdaddr_type; - bacpy(&cp.bdaddr, bdaddr); - - hci_req_add(req, HCI_OP_LE_DEL_FROM_RESOLV_LIST, - sizeof(cp), &cp); - } - } -} - -/* Adds connection to accept list if needed. On error, returns -1. */ -static int add_to_accept_list(struct hci_request *req, - struct hci_conn_params *params, u8 *num_entries, - bool allow_rpa) -{ - struct hci_cp_le_add_to_accept_list cp; - struct hci_dev *hdev = req->hdev; - - /* Already in accept list */ - if (hci_bdaddr_list_lookup(&hdev->le_accept_list, ¶ms->addr, - params->addr_type)) - return 0; - - /* Select filter policy to accept all advertising */ - if (*num_entries >= hdev->le_accept_list_size) - return -1; - - /* Accept list can not be used with RPAs */ - if (!allow_rpa && - !hci_dev_test_flag(hdev, HCI_ENABLE_LL_PRIVACY) && - hci_find_irk_by_addr(hdev, ¶ms->addr, params->addr_type)) { - return -1; - } - - /* During suspend, only wakeable devices can be in accept list */ - if (hdev->suspended && - !(params->flags & HCI_CONN_FLAG_REMOTE_WAKEUP)) - return 0; - - *num_entries += 1; - cp.bdaddr_type = params->addr_type; - bacpy(&cp.bdaddr, ¶ms->addr); - - bt_dev_dbg(hdev, "Add %pMR (0x%x) to accept list", &cp.bdaddr, - cp.bdaddr_type); - hci_req_add(req, HCI_OP_LE_ADD_TO_ACCEPT_LIST, sizeof(cp), &cp); - - if (use_ll_privacy(hdev)) { - struct smp_irk *irk; - - irk = hci_find_irk_by_addr(hdev, ¶ms->addr, - params->addr_type); - if (irk) { - struct hci_cp_le_add_to_resolv_list cp; - - cp.bdaddr_type = params->addr_type; - bacpy(&cp.bdaddr, ¶ms->addr); - memcpy(cp.peer_irk, irk->val, 16); - - if (hci_dev_test_flag(hdev, HCI_PRIVACY)) - memcpy(cp.local_irk, hdev->irk, 16); - else - memset(cp.local_irk, 0, 16); - - hci_req_add(req, HCI_OP_LE_ADD_TO_RESOLV_LIST, - sizeof(cp), &cp); - } - } - - return 0; -} - -static u8 update_accept_list(struct hci_request *req) -{ - struct hci_dev *hdev = req->hdev; - struct hci_conn_params *params; - struct bdaddr_list *b; - u8 num_entries = 0; - bool pend_conn, pend_report; - /* We allow usage of accept list even with RPAs in suspend. In the worst - * case, we won't be able to wake from devices that use the privacy1.2 - * features. Additionally, once we support privacy1.2 and IRK - * offloading, we can update this to also check for those conditions. - */ - bool allow_rpa = hdev->suspended; - - if (use_ll_privacy(hdev)) - allow_rpa = true; - - /* Go through the current accept list programmed into the - * controller one by one and check if that address is still - * in the list of pending connections or list of devices to - * report. If not present in either list, then queue the - * command to remove it from the controller. - */ - list_for_each_entry(b, &hdev->le_accept_list, list) { - pend_conn = hci_pend_le_action_lookup(&hdev->pend_le_conns, - &b->bdaddr, - b->bdaddr_type); - pend_report = hci_pend_le_action_lookup(&hdev->pend_le_reports, - &b->bdaddr, - b->bdaddr_type); - - /* If the device is not likely to connect or report, - * remove it from the accept list. - */ - if (!pend_conn && !pend_report) { - del_from_accept_list(req, &b->bdaddr, b->bdaddr_type); - continue; - } - - /* Accept list can not be used with RPAs */ - if (!allow_rpa && - !hci_dev_test_flag(hdev, HCI_ENABLE_LL_PRIVACY) && - hci_find_irk_by_addr(hdev, &b->bdaddr, b->bdaddr_type)) { - return 0x00; - } - - num_entries++; - } - - /* Since all no longer valid accept list entries have been - * removed, walk through the list of pending connections - * and ensure that any new device gets programmed into - * the controller. - * - * If the list of the devices is larger than the list of - * available accept list entries in the controller, then - * just abort and return filer policy value to not use the - * accept list. - */ - list_for_each_entry(params, &hdev->pend_le_conns, action) { - if (add_to_accept_list(req, params, &num_entries, allow_rpa)) - return 0x00; - } - - /* After adding all new pending connections, walk through - * the list of pending reports and also add these to the - * accept list if there is still space. Abort if space runs out. - */ - list_for_each_entry(params, &hdev->pend_le_reports, action) { - if (add_to_accept_list(req, params, &num_entries, allow_rpa)) - return 0x00; - } - - /* Use the allowlist unless the following conditions are all true: - * - We are not currently suspending - * - There are 1 or more ADV monitors registered and it's not offloaded - * - Interleaved scanning is not currently using the allowlist - */ - if (!idr_is_empty(&hdev->adv_monitors_idr) && !hdev->suspended && - hci_get_adv_monitor_offload_ext(hdev) == HCI_ADV_MONITOR_EXT_NONE && - hdev->interleave_scan_state != INTERLEAVE_SCAN_ALLOWLIST) - return 0x00; - - /* Select filter policy to use accept list */ - return 0x01; -} - -static bool scan_use_rpa(struct hci_dev *hdev) -{ - return hci_dev_test_flag(hdev, HCI_PRIVACY); -} - -static void hci_req_start_scan(struct hci_request *req, u8 type, u16 interval, - u16 window, u8 own_addr_type, u8 filter_policy, - bool filter_dup, bool addr_resolv) -{ - struct hci_dev *hdev = req->hdev; - - if (hdev->scanning_paused) { - bt_dev_dbg(hdev, "Scanning is paused for suspend"); - return; - } - - if (use_ll_privacy(hdev) && addr_resolv) { - u8 enable = 0x01; - - hci_req_add(req, HCI_OP_LE_SET_ADDR_RESOLV_ENABLE, 1, &enable); - } - - /* Use ext scanning if set ext scan param and ext scan enable is - * supported - */ - if (use_ext_scan(hdev)) { - struct hci_cp_le_set_ext_scan_params *ext_param_cp; - struct hci_cp_le_set_ext_scan_enable ext_enable_cp; - struct hci_cp_le_scan_phy_params *phy_params; - u8 data[sizeof(*ext_param_cp) + sizeof(*phy_params) * 2]; - u32 plen; - - ext_param_cp = (void *)data; - phy_params = (void *)ext_param_cp->data; - - memset(ext_param_cp, 0, sizeof(*ext_param_cp)); - ext_param_cp->own_addr_type = own_addr_type; - ext_param_cp->filter_policy = filter_policy; - - plen = sizeof(*ext_param_cp); - - if (scan_1m(hdev) || scan_2m(hdev)) { - ext_param_cp->scanning_phys |= LE_SCAN_PHY_1M; - - memset(phy_params, 0, sizeof(*phy_params)); - phy_params->type = type; - phy_params->interval = cpu_to_le16(interval); - phy_params->window = cpu_to_le16(window); - - plen += sizeof(*phy_params); - phy_params++; - } - - if (scan_coded(hdev)) { - ext_param_cp->scanning_phys |= LE_SCAN_PHY_CODED; - - memset(phy_params, 0, sizeof(*phy_params)); - phy_params->type = type; - phy_params->interval = cpu_to_le16(interval); - phy_params->window = cpu_to_le16(window); - - plen += sizeof(*phy_params); - phy_params++; - } - - hci_req_add(req, HCI_OP_LE_SET_EXT_SCAN_PARAMS, - plen, ext_param_cp); - - memset(&ext_enable_cp, 0, sizeof(ext_enable_cp)); - ext_enable_cp.enable = LE_SCAN_ENABLE; - ext_enable_cp.filter_dup = filter_dup; - - hci_req_add(req, HCI_OP_LE_SET_EXT_SCAN_ENABLE, - sizeof(ext_enable_cp), &ext_enable_cp); - } else { - struct hci_cp_le_set_scan_param param_cp; - struct hci_cp_le_set_scan_enable enable_cp; - - memset(¶m_cp, 0, sizeof(param_cp)); - param_cp.type = type; - param_cp.interval = cpu_to_le16(interval); - param_cp.window = cpu_to_le16(window); - param_cp.own_address_type = own_addr_type; - param_cp.filter_policy = filter_policy; - hci_req_add(req, HCI_OP_LE_SET_SCAN_PARAM, sizeof(param_cp), - ¶m_cp); - - memset(&enable_cp, 0, sizeof(enable_cp)); - enable_cp.enable = LE_SCAN_ENABLE; - enable_cp.filter_dup = filter_dup; - hci_req_add(req, HCI_OP_LE_SET_SCAN_ENABLE, sizeof(enable_cp), - &enable_cp); - } -} - -static void set_random_addr(struct hci_request *req, bdaddr_t *rpa); -static int hci_update_random_address(struct hci_request *req, - bool require_privacy, bool use_rpa, - u8 *own_addr_type) -{ - struct hci_dev *hdev = req->hdev; - int err; - - /* If privacy is enabled use a resolvable private address. If - * current RPA has expired or there is something else than - * the current RPA in use, then generate a new one. - */ - if (use_rpa) { - /* If Controller supports LL Privacy use own address type is - * 0x03 - */ - if (use_ll_privacy(hdev)) - *own_addr_type = ADDR_LE_DEV_RANDOM_RESOLVED; - else - *own_addr_type = ADDR_LE_DEV_RANDOM; - - if (rpa_valid(hdev)) - return 0; - - err = smp_generate_rpa(hdev, hdev->irk, &hdev->rpa); - if (err < 0) { - bt_dev_err(hdev, "failed to generate new RPA"); - return err; - } - - set_random_addr(req, &hdev->rpa); - - return 0; - } - - /* In case of required privacy without resolvable private address, - * use an non-resolvable private address. This is useful for active - * scanning and non-connectable advertising. - */ - if (require_privacy) { - bdaddr_t nrpa; - - while (true) { - /* The non-resolvable private address is generated - * from random six bytes with the two most significant - * bits cleared. - */ - get_random_bytes(&nrpa, 6); - nrpa.b[5] &= 0x3f; - - /* The non-resolvable private address shall not be - * equal to the public address. - */ - if (bacmp(&hdev->bdaddr, &nrpa)) - break; - } - - *own_addr_type = ADDR_LE_DEV_RANDOM; - set_random_addr(req, &nrpa); - return 0; - } - - /* If forcing static address is in use or there is no public - * address use the static address as random address (but skip - * the HCI command if the current random address is already the - * static one. - * - * In case BR/EDR has been disabled on a dual-mode controller - * and a static address has been configured, then use that - * address instead of the public BR/EDR address. - */ - if (hci_dev_test_flag(hdev, HCI_FORCE_STATIC_ADDR) || - !bacmp(&hdev->bdaddr, BDADDR_ANY) || - (!hci_dev_test_flag(hdev, HCI_BREDR_ENABLED) && - bacmp(&hdev->static_addr, BDADDR_ANY))) { - *own_addr_type = ADDR_LE_DEV_RANDOM; - if (bacmp(&hdev->static_addr, &hdev->random_addr)) - hci_req_add(req, HCI_OP_LE_SET_RANDOM_ADDR, 6, - &hdev->static_addr); - return 0; - } - - /* Neither privacy nor static address is being used so use a - * public address. - */ - *own_addr_type = ADDR_LE_DEV_PUBLIC; - - return 0; -} - -/* Ensure to call hci_req_add_le_scan_disable() first to disable the - * controller based address resolution to be able to reconfigure - * resolving list. - */ -void hci_req_add_le_passive_scan(struct hci_request *req) -{ - struct hci_dev *hdev = req->hdev; - u8 own_addr_type; - u8 filter_policy; - u16 window, interval; - /* Default is to enable duplicates filter */ - u8 filter_dup = LE_SCAN_FILTER_DUP_ENABLE; - /* Background scanning should run with address resolution */ - bool addr_resolv = true; - - if (hdev->scanning_paused) { - bt_dev_dbg(hdev, "Scanning is paused for suspend"); - return; - } - - /* Set require_privacy to false since no SCAN_REQ are send - * during passive scanning. Not using an non-resolvable address - * here is important so that peer devices using direct - * advertising with our address will be correctly reported - * by the controller. - */ - if (hci_update_random_address(req, false, scan_use_rpa(hdev), - &own_addr_type)) - return; - - if (hdev->enable_advmon_interleave_scan && - __hci_update_interleaved_scan(hdev)) - return; - - bt_dev_dbg(hdev, "interleave state %d", hdev->interleave_scan_state); - /* Adding or removing entries from the accept list must - * happen before enabling scanning. The controller does - * not allow accept list modification while scanning. - */ - filter_policy = update_accept_list(req); - - /* When the controller is using random resolvable addresses and - * with that having LE privacy enabled, then controllers with - * Extended Scanner Filter Policies support can now enable support - * for handling directed advertising. - * - * So instead of using filter polices 0x00 (no accept list) - * and 0x01 (accept list enabled) use the new filter policies - * 0x02 (no accept list) and 0x03 (accept list enabled). - */ - if (hci_dev_test_flag(hdev, HCI_PRIVACY) && - (hdev->le_features[0] & HCI_LE_EXT_SCAN_POLICY)) - filter_policy |= 0x02; - - if (hdev->suspended) { - window = hdev->le_scan_window_suspend; - interval = hdev->le_scan_int_suspend; - } else if (hci_is_le_conn_scanning(hdev)) { - window = hdev->le_scan_window_connect; - interval = hdev->le_scan_int_connect; - } else if (hci_is_adv_monitoring(hdev)) { - window = hdev->le_scan_window_adv_monitor; - interval = hdev->le_scan_int_adv_monitor; - - /* Disable duplicates filter when scanning for advertisement - * monitor for the following reasons. - * - * For HW pattern filtering (ex. MSFT), Realtek and Qualcomm - * controllers ignore RSSI_Sampling_Period when the duplicates - * filter is enabled. - * - * For SW pattern filtering, when we're not doing interleaved - * scanning, it is necessary to disable duplicates filter, - * otherwise hosts can only receive one advertisement and it's - * impossible to know if a peer is still in range. - */ - filter_dup = LE_SCAN_FILTER_DUP_DISABLE; - } else { - window = hdev->le_scan_window; - interval = hdev->le_scan_interval; - } - - bt_dev_dbg(hdev, "LE passive scan with accept list = %d", - filter_policy); - hci_req_start_scan(req, LE_SCAN_PASSIVE, interval, window, - own_addr_type, filter_policy, filter_dup, - addr_resolv); -} - -static int hci_req_add_le_interleaved_scan(struct hci_request *req, - unsigned long opt) -{ - struct hci_dev *hdev = req->hdev; - int ret = 0; - - hci_dev_lock(hdev); - - if (hci_dev_test_flag(hdev, HCI_LE_SCAN)) - hci_req_add_le_scan_disable(req, false); - hci_req_add_le_passive_scan(req); - - switch (hdev->interleave_scan_state) { - case INTERLEAVE_SCAN_ALLOWLIST: - bt_dev_dbg(hdev, "next state: allowlist"); - hdev->interleave_scan_state = INTERLEAVE_SCAN_NO_FILTER; - break; - case INTERLEAVE_SCAN_NO_FILTER: - bt_dev_dbg(hdev, "next state: no filter"); - hdev->interleave_scan_state = INTERLEAVE_SCAN_ALLOWLIST; - break; - case INTERLEAVE_SCAN_NONE: - BT_ERR("unexpected error"); - ret = -1; - } - - hci_dev_unlock(hdev); - - return ret; -} - -static void interleave_scan_work(struct work_struct *work) -{ - struct hci_dev *hdev = container_of(work, struct hci_dev, - interleave_scan.work); - u8 status; - unsigned long timeout; - - if (hdev->interleave_scan_state == INTERLEAVE_SCAN_ALLOWLIST) { - timeout = msecs_to_jiffies(hdev->advmon_allowlist_duration); - } else if (hdev->interleave_scan_state == INTERLEAVE_SCAN_NO_FILTER) { - timeout = msecs_to_jiffies(hdev->advmon_no_filter_duration); - } else { - bt_dev_err(hdev, "unexpected error"); - return; - } - - hci_req_sync(hdev, hci_req_add_le_interleaved_scan, 0, - HCI_CMD_TIMEOUT, &status); - - /* Don't continue interleaving if it was canceled */ - if (is_interleave_scanning(hdev)) - queue_delayed_work(hdev->req_workqueue, - &hdev->interleave_scan, timeout); -} - -static void set_random_addr(struct hci_request *req, bdaddr_t *rpa) -{ - struct hci_dev *hdev = req->hdev; - - /* If we're advertising or initiating an LE connection we can't - * go ahead and change the random address at this time. This is - * because the eventual initiator address used for the - * subsequently created connection will be undefined (some - * controllers use the new address and others the one we had - * when the operation started). - * - * In this kind of scenario skip the update and let the random - * address be updated at the next cycle. - */ - if (hci_dev_test_flag(hdev, HCI_LE_ADV) || - hci_lookup_le_connect(hdev)) { - bt_dev_dbg(hdev, "Deferring random address update"); - hci_dev_set_flag(hdev, HCI_RPA_EXPIRED); - return; - } - - hci_req_add(req, HCI_OP_LE_SET_RANDOM_ADDR, 6, rpa); -} - -void hci_request_setup(struct hci_dev *hdev) -{ - INIT_DELAYED_WORK(&hdev->interleave_scan, interleave_scan_work); -} - -void hci_request_cancel_all(struct hci_dev *hdev) -{ - hci_cmd_sync_cancel_sync(hdev, ENODEV); - - cancel_interleave_scan(hdev); -} diff --git a/net/bluetooth/hci_request.h b/net/bluetooth/hci_request.h deleted file mode 100644 index c91f2838f542..000000000000 --- a/net/bluetooth/hci_request.h +++ /dev/null @@ -1,71 +0,0 @@ -/* - BlueZ - Bluetooth protocol stack for Linux - Copyright (C) 2014 Intel Corporation - - This program is free software; you can redistribute it and/or modify - it under the terms of the GNU General Public License version 2 as - published by the Free Software Foundation; - - THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS - OR IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY, - FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT OF THIRD PARTY RIGHTS. - IN NO EVENT SHALL THE COPYRIGHT HOLDER(S) AND AUTHOR(S) BE LIABLE FOR ANY - CLAIM, OR ANY SPECIAL INDIRECT OR CONSEQUENTIAL DAMAGES, OR ANY DAMAGES - WHATSOEVER RESULTING FROM LOSS OF USE, DATA OR PROFITS, WHETHER IN AN - ACTION OF CONTRACT, NEGLIGENCE OR OTHER TORTIOUS ACTION, ARISING OUT OF - OR IN CONNECTION WITH THE USE OR PERFORMANCE OF THIS SOFTWARE. - - ALL LIABILITY, INCLUDING LIABILITY FOR INFRINGEMENT OF ANY PATENTS, - COPYRIGHTS, TRADEMARKS OR OTHER RIGHTS, RELATING TO USE OF THIS - SOFTWARE IS DISCLAIMED. -*/ - -#include <asm/unaligned.h> - -#define HCI_REQ_DONE 0 -#define HCI_REQ_PEND 1 -#define HCI_REQ_CANCELED 2 - -#define hci_req_sync_lock(hdev) mutex_lock(&hdev->req_lock) -#define hci_req_sync_unlock(hdev) mutex_unlock(&hdev->req_lock) - -struct hci_request { - struct hci_dev *hdev; - struct sk_buff_head cmd_q; - - /* If something goes wrong when building the HCI request, the error - * value is stored in this field. - */ - int err; -}; - -void hci_req_init(struct hci_request *req, struct hci_dev *hdev); -void hci_req_purge(struct hci_request *req); -bool hci_req_status_pend(struct hci_dev *hdev); -int hci_req_run(struct hci_request *req, hci_req_complete_t complete); -int hci_req_run_skb(struct hci_request *req, hci_req_complete_skb_t complete); -void hci_req_sync_complete(struct hci_dev *hdev, u8 result, u16 opcode, - struct sk_buff *skb); -void hci_req_add(struct hci_request *req, u16 opcode, u32 plen, - const void *param); -void hci_req_add_ev(struct hci_request *req, u16 opcode, u32 plen, - const void *param, u8 event); -void hci_req_cmd_complete(struct hci_dev *hdev, u16 opcode, u8 status, - hci_req_complete_t *req_complete, - hci_req_complete_skb_t *req_complete_skb); - -int hci_req_sync(struct hci_dev *hdev, int (*req)(struct hci_request *req, - unsigned long opt), - unsigned long opt, u32 timeout, u8 *hci_status); -int __hci_req_sync(struct hci_dev *hdev, int (*func)(struct hci_request *req, - unsigned long opt), - unsigned long opt, u32 timeout, u8 *hci_status); - -struct sk_buff *hci_prepare_cmd(struct hci_dev *hdev, u16 opcode, u32 plen, - const void *param); - -void hci_req_add_le_scan_disable(struct hci_request *req, bool rpa_le_conn); -void hci_req_add_le_passive_scan(struct hci_request *req); - -void hci_request_setup(struct hci_dev *hdev); -void hci_request_cancel_all(struct hci_dev *hdev); diff --git a/net/bluetooth/hci_sync.c b/net/bluetooth/hci_sync.c index a8a7d2b36870..40ccdef168d7 100644 --- a/net/bluetooth/hci_sync.c +++ b/net/bluetooth/hci_sync.c @@ -12,7 +12,6 @@ #include <net/bluetooth/hci_core.h> #include <net/bluetooth/mgmt.h> -#include "hci_request.h" #include "hci_codec.h" #include "hci_debugfs.h" #include "smp.h" @@ -49,9 +48,8 @@ static void hci_cmd_sync_complete(struct hci_dev *hdev, u8 result, u16 opcode, wake_up_interruptible(&hdev->req_wait_q); } -static struct sk_buff *hci_cmd_sync_alloc(struct hci_dev *hdev, u16 opcode, - u32 plen, const void *param, - struct sock *sk) +struct sk_buff *hci_cmd_sync_alloc(struct hci_dev *hdev, u16 opcode, u32 plen, + const void *param, struct sock *sk) { int len = HCI_COMMAND_HDR_SIZE + plen; struct hci_command_hdr *hdr; @@ -114,7 +112,7 @@ static void hci_cmd_sync_add(struct hci_request *req, u16 opcode, u32 plen, skb_queue_tail(&req->cmd_q, skb); } -static int hci_cmd_sync_run(struct hci_request *req) +static int hci_req_sync_run(struct hci_request *req) { struct hci_dev *hdev = req->hdev; struct sk_buff *skb; @@ -147,6 +145,13 @@ static int hci_cmd_sync_run(struct hci_request *req) return 0; } +static void hci_request_init(struct hci_request *req, struct hci_dev *hdev) +{ + skb_queue_head_init(&req->cmd_q); + req->hdev = hdev; + req->err = 0; +} + /* This function requires the caller holds hdev->req_lock. */ struct sk_buff *__hci_cmd_sync_sk(struct hci_dev *hdev, u16 opcode, u32 plen, const void *param, u8 event, u32 timeout, @@ -158,13 +163,13 @@ struct sk_buff *__hci_cmd_sync_sk(struct hci_dev *hdev, u16 opcode, u32 plen, bt_dev_dbg(hdev, "Opcode 0x%4.4x", opcode); - hci_req_init(&req, hdev); + hci_request_init(&req, hdev); hci_cmd_sync_add(&req, opcode, plen, param, event, sk); hdev->req_status = HCI_REQ_PEND; - err = hci_cmd_sync_run(&req); + err = hci_req_sync_run(&req); if (err < 0) return ERR_PTR(err); @@ -280,6 +285,19 @@ int __hci_cmd_sync_status(struct hci_dev *hdev, u16 opcode, u32 plen, } EXPORT_SYMBOL(__hci_cmd_sync_status); +int hci_cmd_sync_status(struct hci_dev *hdev, u16 opcode, u32 plen, + const void *param, u32 timeout) +{ + int err; + + hci_req_sync_lock(hdev); + err = __hci_cmd_sync_status(hdev, opcode, plen, param, timeout); + hci_req_sync_unlock(hdev); + + return err; +} +EXPORT_SYMBOL(hci_cmd_sync_status); + static void hci_cmd_sync_work(struct work_struct *work) { struct hci_dev *hdev = container_of(work, struct hci_dev, cmd_sync_work); @@ -334,10 +352,9 @@ static int scan_disable_sync(struct hci_dev *hdev, void *data) return hci_scan_disable_sync(hdev); } -static int hci_inquiry_sync(struct hci_dev *hdev, u8 length); static int interleaved_inquiry_sync(struct hci_dev *hdev, void *data) { - return hci_inquiry_sync(hdev, DISCOV_INTERLEAVED_INQUIRY_LEN); + return hci_inquiry_sync(hdev, DISCOV_INTERLEAVED_INQUIRY_LEN, 0); } static void le_scan_disable(struct work_struct *work) @@ -358,8 +375,6 @@ static void le_scan_disable(struct work_struct *work) goto _return; } - hdev->discovery.scan_start = 0; - /* If we were running LE only scan, change discovery state. If * we were running both LE and BR/EDR inquiry simultaneously, * and BR/EDR inquiry is already finished, stop discovery, @@ -557,6 +572,53 @@ unlock: hci_dev_unlock(hdev); } +static bool is_interleave_scanning(struct hci_dev *hdev) +{ + return hdev->interleave_scan_state != INTERLEAVE_SCAN_NONE; +} + +static int hci_passive_scan_sync(struct hci_dev *hdev); + +static void interleave_scan_work(struct work_struct *work) +{ + struct hci_dev *hdev = container_of(work, struct hci_dev, + interleave_scan.work); + unsigned long timeout; + + if (hdev->interleave_scan_state == INTERLEAVE_SCAN_ALLOWLIST) { + timeout = msecs_to_jiffies(hdev->advmon_allowlist_duration); + } else if (hdev->interleave_scan_state == INTERLEAVE_SCAN_NO_FILTER) { + timeout = msecs_to_jiffies(hdev->advmon_no_filter_duration); + } else { + bt_dev_err(hdev, "unexpected error"); + return; + } + + hci_passive_scan_sync(hdev); + + hci_dev_lock(hdev); + + switch (hdev->interleave_scan_state) { + case INTERLEAVE_SCAN_ALLOWLIST: + bt_dev_dbg(hdev, "next state: allowlist"); + hdev->interleave_scan_state = INTERLEAVE_SCAN_NO_FILTER; + break; + case INTERLEAVE_SCAN_NO_FILTER: + bt_dev_dbg(hdev, "next state: no filter"); + hdev->interleave_scan_state = INTERLEAVE_SCAN_ALLOWLIST; + break; + case INTERLEAVE_SCAN_NONE: + bt_dev_err(hdev, "unexpected error"); + } + + hci_dev_unlock(hdev); + + /* Don't continue interleaving if it was canceled */ + if (is_interleave_scanning(hdev)) + queue_delayed_work(hdev->req_workqueue, + &hdev->interleave_scan, timeout); +} + void hci_cmd_sync_init(struct hci_dev *hdev) { INIT_WORK(&hdev->cmd_sync_work, hci_cmd_sync_work); @@ -568,6 +630,7 @@ void hci_cmd_sync_init(struct hci_dev *hdev) INIT_WORK(&hdev->reenable_adv_work, reenable_adv); INIT_DELAYED_WORK(&hdev->le_scan_disable, le_scan_disable); INIT_DELAYED_WORK(&hdev->adv_instance_expire, adv_timeout_expire); + INIT_DELAYED_WORK(&hdev->interleave_scan, interleave_scan_work); } static void _hci_cmd_sync_cancel_entry(struct hci_dev *hdev, @@ -719,6 +782,44 @@ int hci_cmd_sync_queue_once(struct hci_dev *hdev, hci_cmd_sync_work_func_t func, } EXPORT_SYMBOL(hci_cmd_sync_queue_once); +/* Run HCI command: + * + * - hdev must be running + * - if on cmd_sync_work then run immediately otherwise queue + */ +int hci_cmd_sync_run(struct hci_dev *hdev, hci_cmd_sync_work_func_t func, + void *data, hci_cmd_sync_work_destroy_t destroy) +{ + /* Only queue command if hdev is running which means it had been opened + * and is either on init phase or is already up. + */ + if (!test_bit(HCI_RUNNING, &hdev->flags)) + return -ENETDOWN; + + /* If on cmd_sync_work then run immediately otherwise queue */ + if (current_work() == &hdev->cmd_sync_work) + return func(hdev, data); + + return hci_cmd_sync_submit(hdev, func, data, destroy); +} +EXPORT_SYMBOL(hci_cmd_sync_run); + +/* Run HCI command entry once: + * + * - Lookup if an entry already exist and only if it doesn't creates a new entry + * and run it. + * - if on cmd_sync_work then run immediately otherwise queue + */ +int hci_cmd_sync_run_once(struct hci_dev *hdev, hci_cmd_sync_work_func_t func, + void *data, hci_cmd_sync_work_destroy_t destroy) +{ + if (hci_cmd_sync_lookup_entry(hdev, func, data, destroy)) + return 0; + + return hci_cmd_sync_run(hdev, func, data, destroy); +} +EXPORT_SYMBOL(hci_cmd_sync_run_once); + /* Lookup HCI command entry: * * - Return first entry that matches by function callback or data or @@ -2101,11 +2202,6 @@ static void hci_start_interleave_scan(struct hci_dev *hdev) &hdev->interleave_scan, 0); } -static bool is_interleave_scanning(struct hci_dev *hdev) -{ - return hdev->interleave_scan_state != INTERLEAVE_SCAN_NONE; -} - static void cancel_interleave_scan(struct hci_dev *hdev) { bt_dev_dbg(hdev, "cancelling interleave scan"); @@ -2918,6 +3014,27 @@ static int hci_passive_scan_sync(struct hci_dev *hdev) */ filter_policy = hci_update_accept_list_sync(hdev); + /* If suspended and filter_policy set to 0x00 (no acceptlist) then + * passive scanning cannot be started since that would require the host + * to be woken up to process the reports. + */ + if (hdev->suspended && !filter_policy) { + /* Check if accept list is empty then there is no need to scan + * while suspended. + */ + if (list_empty(&hdev->le_accept_list)) + return 0; + + /* If there are devices is the accept_list that means some + * devices could not be programmed which in non-suspended case + * means filter_policy needs to be set to 0x00 so the host needs + * to filter, but since this is treating suspended case we + * can ignore device needing host to filter to allow devices in + * the acceptlist to be able to wakeup the system. + */ + filter_policy = 0x01; + } + /* When the controller is using random resolvable addresses and * with that having LE privacy enabled, then controllers with * Extended Scanner Filter Policies support can now enable support @@ -2940,6 +3057,20 @@ static int hci_passive_scan_sync(struct hci_dev *hdev) } else if (hci_is_adv_monitoring(hdev)) { window = hdev->le_scan_window_adv_monitor; interval = hdev->le_scan_int_adv_monitor; + + /* Disable duplicates filter when scanning for advertisement + * monitor for the following reasons. + * + * For HW pattern filtering (ex. MSFT), Realtek and Qualcomm + * controllers ignore RSSI_Sampling_Period when the duplicates + * filter is enabled. + * + * For SW pattern filtering, when we're not doing interleaved + * scanning, it is necessary to disable duplicates filter, + * otherwise hosts can only receive one advertisement and it's + * impossible to know if a peer is still in range. + */ + filter_dups = LE_SCAN_FILTER_DUP_DISABLE; } else { window = hdev->le_scan_window; interval = hdev->le_scan_interval; @@ -5004,7 +5135,9 @@ int hci_dev_close_sync(struct hci_dev *hdev) cancel_delayed_work(&hdev->ncmd_timer); cancel_delayed_work(&hdev->le_scan_disable); - hci_request_cancel_all(hdev); + hci_cmd_sync_cancel_sync(hdev, ENODEV); + + cancel_interleave_scan(hdev); if (hdev->adv_instance_timeout) { cancel_delayed_work_sync(&hdev->adv_instance_expire); @@ -5247,7 +5380,10 @@ int hci_stop_discovery_sync(struct hci_dev *hdev) if (!e) return 0; - return hci_remote_name_cancel_sync(hdev, &e->data.bdaddr); + /* Ignore cancel errors since it should interfere with stopping + * of the discovery. + */ + hci_remote_name_cancel_sync(hdev, &e->data.bdaddr); } return 0; @@ -5651,7 +5787,7 @@ int hci_update_connectable_sync(struct hci_dev *hdev) return hci_update_passive_scan_sync(hdev); } -static int hci_inquiry_sync(struct hci_dev *hdev, u8 length) +int hci_inquiry_sync(struct hci_dev *hdev, u8 length, u8 num_rsp) { const u8 giac[3] = { 0x33, 0x8b, 0x9e }; const u8 liac[3] = { 0x00, 0x8b, 0x9e }; @@ -5674,6 +5810,7 @@ static int hci_inquiry_sync(struct hci_dev *hdev, u8 length) memcpy(&cp.lap, giac, sizeof(cp.lap)); cp.length = length; + cp.num_rsp = num_rsp; return __hci_cmd_sync_status(hdev, HCI_OP_INQUIRY, sizeof(cp), &cp, HCI_CMD_TIMEOUT); @@ -5760,7 +5897,7 @@ static int hci_start_interleaved_discovery_sync(struct hci_dev *hdev) if (err) return err; - return hci_inquiry_sync(hdev, DISCOV_BREDR_INQUIRY_LEN); + return hci_inquiry_sync(hdev, DISCOV_BREDR_INQUIRY_LEN, 0); } int hci_start_discovery_sync(struct hci_dev *hdev) @@ -5772,7 +5909,7 @@ int hci_start_discovery_sync(struct hci_dev *hdev) switch (hdev->discovery.type) { case DISCOV_TYPE_BREDR: - return hci_inquiry_sync(hdev, DISCOV_BREDR_INQUIRY_LEN); + return hci_inquiry_sync(hdev, DISCOV_BREDR_INQUIRY_LEN, 0); case DISCOV_TYPE_INTERLEAVED: /* When running simultaneous discovery, the LE scanning time * should occupy the whole discovery time sine BR/EDR inquiry @@ -5842,7 +5979,6 @@ static int hci_pause_discovery_sync(struct hci_dev *hdev) return err; hdev->discovery_paused = true; - hdev->discovery_old_state = old_state; hci_discovery_set_state(hdev, DISCOVERY_STOPPED); return 0; @@ -6711,3 +6847,21 @@ int hci_cancel_connect_sync(struct hci_dev *hdev, struct hci_conn *conn) return -ENOENT; } + +int hci_le_conn_update_sync(struct hci_dev *hdev, struct hci_conn *conn, + struct hci_conn_params *params) +{ + struct hci_cp_le_conn_update cp; + + memset(&cp, 0, sizeof(cp)); + cp.handle = cpu_to_le16(conn->handle); + cp.conn_interval_min = cpu_to_le16(params->conn_min_interval); + cp.conn_interval_max = cpu_to_le16(params->conn_max_interval); + cp.conn_latency = cpu_to_le16(params->conn_latency); + cp.supervision_timeout = cpu_to_le16(params->supervision_timeout); + cp.min_ce_len = cpu_to_le16(0x0000); + cp.max_ce_len = cpu_to_le16(0x0000); + + return __hci_cmd_sync_status(hdev, HCI_OP_LE_CONN_UPDATE, + sizeof(cp), &cp, HCI_CMD_TIMEOUT); +} diff --git a/net/bluetooth/iso.c b/net/bluetooth/iso.c index cc055b952ce6..d5e00d0dd1a0 100644 --- a/net/bluetooth/iso.c +++ b/net/bluetooth/iso.c @@ -1356,8 +1356,7 @@ static int iso_sock_recvmsg(struct socket *sock, struct msghdr *msg, lock_sock(sk); switch (sk->sk_state) { case BT_CONNECT2: - if (pi->conn->hcon && - test_bit(HCI_CONN_PA_SYNC, &pi->conn->hcon->flags)) { + if (test_bit(BT_SK_PA_SYNC, &pi->flags)) { iso_conn_big_sync(sk); sk->sk_state = BT_LISTEN; } else { @@ -1721,11 +1720,6 @@ static void iso_sock_ready(struct sock *sk) release_sock(sk); } -struct iso_list_data { - struct hci_conn *hcon; - int count; -}; - static bool iso_match_big(struct sock *sk, void *data) { struct hci_evt_le_big_sync_estabilished *ev = data; diff --git a/net/bluetooth/l2cap_core.c b/net/bluetooth/l2cap_core.c index aed025734d04..9988ba382b68 100644 --- a/net/bluetooth/l2cap_core.c +++ b/net/bluetooth/l2cap_core.c @@ -6761,6 +6761,8 @@ static void l2cap_conless_channel(struct l2cap_conn *conn, __le16 psm, BT_DBG("chan %p, len %d", chan, skb->len); + l2cap_chan_lock(chan); + if (chan->state != BT_BOUND && chan->state != BT_CONNECTED) goto drop; @@ -6772,11 +6774,13 @@ static void l2cap_conless_channel(struct l2cap_conn *conn, __le16 psm, bt_cb(skb)->l2cap.psm = psm; if (!chan->ops->recv(chan, skb)) { + l2cap_chan_unlock(chan); l2cap_chan_put(chan); return; } drop: + l2cap_chan_unlock(chan); l2cap_chan_put(chan); free_skb: kfree_skb(skb); diff --git a/net/bluetooth/l2cap_sock.c b/net/bluetooth/l2cap_sock.c index 6db60946c627..ba437c6f6ee5 100644 --- a/net/bluetooth/l2cap_sock.c +++ b/net/bluetooth/l2cap_sock.c @@ -1239,6 +1239,10 @@ static void l2cap_sock_kill(struct sock *sk) BT_DBG("sk %p state %s", sk, state_to_string(sk->sk_state)); + /* Sock is dead, so set chan data to NULL, avoid other task use invalid + * sock pointer. + */ + l2cap_pi(sk)->chan->data = NULL; /* Kill poor orphan */ l2cap_chan_put(l2cap_pi(sk)->chan); @@ -1481,12 +1485,16 @@ static struct l2cap_chan *l2cap_sock_new_connection_cb(struct l2cap_chan *chan) static int l2cap_sock_recv_cb(struct l2cap_chan *chan, struct sk_buff *skb) { - struct sock *sk = chan->data; - struct l2cap_pinfo *pi = l2cap_pi(sk); + struct sock *sk; + struct l2cap_pinfo *pi; int err; - lock_sock(sk); + sk = chan->data; + if (!sk) + return -ENXIO; + pi = l2cap_pi(sk); + lock_sock(sk); if (chan->mode == L2CAP_MODE_ERTM && !list_empty(&pi->rx_busy)) { err = -ENOMEM; goto done; diff --git a/net/bluetooth/leds.c b/net/bluetooth/leds.c index f46847632ffa..6e349704efe4 100644 --- a/net/bluetooth/leds.c +++ b/net/bluetooth/leds.c @@ -48,7 +48,7 @@ static int power_activate(struct led_classdev *led_cdev) htrig = to_hci_basic_led_trigger(led_cdev->trigger); powered = test_bit(HCI_UP, &htrig->hdev->flags); - led_trigger_event(led_cdev->trigger, powered ? LED_FULL : LED_OFF); + led_set_brightness(led_cdev, powered ? LED_FULL : LED_OFF); return 0; } diff --git a/net/bluetooth/mgmt.c b/net/bluetooth/mgmt.c index 80f220b7e19d..e4f564d6f6fb 100644 --- a/net/bluetooth/mgmt.c +++ b/net/bluetooth/mgmt.c @@ -33,7 +33,6 @@ #include <net/bluetooth/l2cap.h> #include <net/bluetooth/mgmt.h> -#include "hci_request.h" #include "smp.h" #include "mgmt_util.h" #include "mgmt_config.h" @@ -42,7 +41,7 @@ #include "aosp.h" #define MGMT_VERSION 1 -#define MGMT_REVISION 22 +#define MGMT_REVISION 23 static const u16 mgmt_commands[] = { MGMT_OP_READ_INDEX_LIST, @@ -2831,16 +2830,6 @@ static int load_link_keys(struct sock *sk, struct hci_dev *hdev, void *data, bt_dev_dbg(hdev, "debug_keys %u key_count %u", cp->debug_keys, key_count); - for (i = 0; i < key_count; i++) { - struct mgmt_link_key_info *key = &cp->keys[i]; - - /* Considering SMP over BREDR/LE, there is no need to check addr_type */ - if (key->type > 0x08) - return mgmt_cmd_status(sk, hdev->id, - MGMT_OP_LOAD_LINK_KEYS, - MGMT_STATUS_INVALID_PARAMS); - } - hci_dev_lock(hdev); hci_link_keys_clear(hdev); @@ -2865,6 +2854,19 @@ static int load_link_keys(struct sock *sk, struct hci_dev *hdev, void *data, continue; } + if (key->addr.type != BDADDR_BREDR) { + bt_dev_warn(hdev, + "Invalid link address type %u for %pMR", + key->addr.type, &key->addr.bdaddr); + continue; + } + + if (key->type > 0x08) { + bt_dev_warn(hdev, "Invalid link key type %u for %pMR", + key->type, &key->addr.bdaddr); + continue; + } + /* Always ignore debug keys and require a new pairing if * the user wants to use them. */ @@ -2922,7 +2924,12 @@ static int unpair_device_sync(struct hci_dev *hdev, void *data) if (!conn) return 0; - return hci_abort_conn_sync(hdev, conn, HCI_ERROR_REMOTE_USER_TERM); + /* Disregard any possible error since the likes of hci_abort_conn_sync + * will clean up the connection no matter the error. + */ + hci_abort_conn(conn, HCI_ERROR_REMOTE_USER_TERM); + + return 0; } static int unpair_device(struct sock *sk, struct hci_dev *hdev, void *data, @@ -3054,13 +3061,44 @@ unlock: return err; } +static void disconnect_complete(struct hci_dev *hdev, void *data, int err) +{ + struct mgmt_pending_cmd *cmd = data; + + cmd->cmd_complete(cmd, mgmt_status(err)); + mgmt_pending_free(cmd); +} + +static int disconnect_sync(struct hci_dev *hdev, void *data) +{ + struct mgmt_pending_cmd *cmd = data; + struct mgmt_cp_disconnect *cp = cmd->param; + struct hci_conn *conn; + + if (cp->addr.type == BDADDR_BREDR) + conn = hci_conn_hash_lookup_ba(hdev, ACL_LINK, + &cp->addr.bdaddr); + else + conn = hci_conn_hash_lookup_le(hdev, &cp->addr.bdaddr, + le_addr_type(cp->addr.type)); + + if (!conn) + return -ENOTCONN; + + /* Disregard any possible error since the likes of hci_abort_conn_sync + * will clean up the connection no matter the error. + */ + hci_abort_conn(conn, HCI_ERROR_REMOTE_USER_TERM); + + return 0; +} + static int disconnect(struct sock *sk, struct hci_dev *hdev, void *data, u16 len) { struct mgmt_cp_disconnect *cp = data; struct mgmt_rp_disconnect rp; struct mgmt_pending_cmd *cmd; - struct hci_conn *conn; int err; bt_dev_dbg(hdev, "sock %p", sk); @@ -3083,27 +3121,7 @@ static int disconnect(struct sock *sk, struct hci_dev *hdev, void *data, goto failed; } - if (pending_find(MGMT_OP_DISCONNECT, hdev)) { - err = mgmt_cmd_complete(sk, hdev->id, MGMT_OP_DISCONNECT, - MGMT_STATUS_BUSY, &rp, sizeof(rp)); - goto failed; - } - - if (cp->addr.type == BDADDR_BREDR) - conn = hci_conn_hash_lookup_ba(hdev, ACL_LINK, - &cp->addr.bdaddr); - else - conn = hci_conn_hash_lookup_le(hdev, &cp->addr.bdaddr, - le_addr_type(cp->addr.type)); - - if (!conn || conn->state == BT_OPEN || conn->state == BT_CLOSED) { - err = mgmt_cmd_complete(sk, hdev->id, MGMT_OP_DISCONNECT, - MGMT_STATUS_NOT_CONNECTED, &rp, - sizeof(rp)); - goto failed; - } - - cmd = mgmt_pending_add(sk, MGMT_OP_DISCONNECT, hdev, data, len); + cmd = mgmt_pending_new(sk, MGMT_OP_DISCONNECT, hdev, data, len); if (!cmd) { err = -ENOMEM; goto failed; @@ -3111,9 +3129,10 @@ static int disconnect(struct sock *sk, struct hci_dev *hdev, void *data, cmd->cmd_complete = generic_cmd_complete; - err = hci_disconnect(conn, HCI_ERROR_REMOTE_USER_TERM); + err = hci_cmd_sync_queue(hdev, disconnect_sync, cmd, + disconnect_complete); if (err < 0) - mgmt_pending_remove(cmd); + mgmt_pending_free(cmd); failed: hci_dev_unlock(hdev); @@ -3457,6 +3476,10 @@ static int pair_device(struct sock *sk, struct hci_dev *hdev, void *data, * will be kept and this function does nothing. */ p = hci_conn_params_add(hdev, &cp->addr.bdaddr, addr_type); + if (!p) { + err = -EIO; + goto unlock; + } if (p->auto_connect == HCI_AUTO_CONN_EXPLICIT) p->auto_connect = HCI_AUTO_CONN_DISABLED; @@ -7069,7 +7092,6 @@ static int load_irks(struct sock *sk, struct hci_dev *hdev, void *cp_data, for (i = 0; i < irk_count; i++) { struct mgmt_irk_info *irk = &cp->irks[i]; - u8 addr_type = le_addr_type(irk->addr.type); if (hci_is_blocked_key(hdev, HCI_BLOCKED_KEY_TYPE_IRK, @@ -7079,12 +7101,8 @@ static int load_irks(struct sock *sk, struct hci_dev *hdev, void *cp_data, continue; } - /* When using SMP over BR/EDR, the addr type should be set to BREDR */ - if (irk->addr.type == BDADDR_BREDR) - addr_type = BDADDR_BREDR; - hci_add_irk(hdev, &irk->addr.bdaddr, - addr_type, irk->val, + le_addr_type(irk->addr.type), irk->val, BDADDR_ANY); } @@ -7149,15 +7167,6 @@ static int load_long_term_keys(struct sock *sk, struct hci_dev *hdev, bt_dev_dbg(hdev, "key_count %u", key_count); - for (i = 0; i < key_count; i++) { - struct mgmt_ltk_info *key = &cp->keys[i]; - - if (!ltk_is_valid(key)) - return mgmt_cmd_status(sk, hdev->id, - MGMT_OP_LOAD_LONG_TERM_KEYS, - MGMT_STATUS_INVALID_PARAMS); - } - hci_dev_lock(hdev); hci_smp_ltks_clear(hdev); @@ -7165,7 +7174,6 @@ static int load_long_term_keys(struct sock *sk, struct hci_dev *hdev, for (i = 0; i < key_count; i++) { struct mgmt_ltk_info *key = &cp->keys[i]; u8 type, authenticated; - u8 addr_type = le_addr_type(key->addr.type); if (hci_is_blocked_key(hdev, HCI_BLOCKED_KEY_TYPE_LTK, @@ -7175,6 +7183,12 @@ static int load_long_term_keys(struct sock *sk, struct hci_dev *hdev, continue; } + if (!ltk_is_valid(key)) { + bt_dev_warn(hdev, "Invalid LTK for %pMR", + &key->addr.bdaddr); + continue; + } + switch (key->type) { case MGMT_LTK_UNAUTHENTICATED: authenticated = 0x00; @@ -7200,12 +7214,8 @@ static int load_long_term_keys(struct sock *sk, struct hci_dev *hdev, continue; } - /* When using SMP over BR/EDR, the addr type should be set to BREDR */ - if (key->addr.type == BDADDR_BREDR) - addr_type = BDADDR_BREDR; - hci_add_ltk(hdev, &key->addr.bdaddr, - addr_type, type, authenticated, + le_addr_type(key->addr.type), type, authenticated, key->val, key->enc_size, key->ediv, key->rand); } @@ -7813,6 +7823,18 @@ unlock: return err; } +static int conn_update_sync(struct hci_dev *hdev, void *data) +{ + struct hci_conn_params *params = data; + struct hci_conn *conn; + + conn = hci_conn_hash_lookup_le(hdev, ¶ms->addr, params->addr_type); + if (!conn) + return -ECANCELED; + + return hci_le_conn_update_sync(hdev, conn, params); +} + static int load_conn_param(struct sock *sk, struct hci_dev *hdev, void *data, u16 len) { @@ -7846,12 +7868,14 @@ static int load_conn_param(struct sock *sk, struct hci_dev *hdev, void *data, hci_dev_lock(hdev); - hci_conn_params_clear_disabled(hdev); + if (param_count > 1) + hci_conn_params_clear_disabled(hdev); for (i = 0; i < param_count; i++) { struct mgmt_conn_param *param = &cp->params[i]; struct hci_conn_params *hci_param; u16 min, max, latency, timeout; + bool update = false; u8 addr_type; bt_dev_dbg(hdev, "Adding %pMR (type %u)", ¶m->addr.bdaddr, @@ -7879,6 +7903,19 @@ static int load_conn_param(struct sock *sk, struct hci_dev *hdev, void *data, continue; } + /* Detect when the loading is for an existing parameter then + * attempt to trigger the connection update procedure. + */ + if (!i && param_count == 1) { + hci_param = hci_conn_params_lookup(hdev, + ¶m->addr.bdaddr, + addr_type); + if (hci_param) + update = true; + else + hci_conn_params_clear_disabled(hdev); + } + hci_param = hci_conn_params_add(hdev, ¶m->addr.bdaddr, addr_type); if (!hci_param) { @@ -7890,6 +7927,25 @@ static int load_conn_param(struct sock *sk, struct hci_dev *hdev, void *data, hci_param->conn_max_interval = max; hci_param->conn_latency = latency; hci_param->supervision_timeout = timeout; + + /* Check if we need to trigger a connection update */ + if (update) { + struct hci_conn *conn; + + /* Lookup for existing connection as central and check + * if parameters match and if they don't then trigger + * a connection update. + */ + conn = hci_conn_hash_lookup_le(hdev, &hci_param->addr, + addr_type); + if (conn && conn->role == HCI_ROLE_MASTER && + (conn->le_conn_min_interval != min || + conn->le_conn_max_interval != max || + conn->le_conn_latency != latency || + conn->le_supv_timeout != timeout)) + hci_cmd_sync_queue(hdev, conn_update_sync, + hci_param, NULL); + } } hci_dev_unlock(hdev); @@ -9453,7 +9509,7 @@ void mgmt_new_link_key(struct hci_dev *hdev, struct link_key *key, ev.store_hint = persistent; bacpy(&ev.key.addr.bdaddr, &key->bdaddr); - ev.key.addr.type = link_to_bdaddr(key->link_type, key->bdaddr_type); + ev.key.addr.type = BDADDR_BREDR; ev.key.type = key->type; memcpy(ev.key.val, key->val, HCI_LINK_KEY_SIZE); ev.key.pin_len = key->pin_len; @@ -9504,7 +9560,7 @@ void mgmt_new_ltk(struct hci_dev *hdev, struct smp_ltk *key, bool persistent) ev.store_hint = persistent; bacpy(&ev.key.addr.bdaddr, &key->bdaddr); - ev.key.addr.type = link_to_bdaddr(key->link_type, key->bdaddr_type); + ev.key.addr.type = link_to_bdaddr(LE_LINK, key->bdaddr_type); ev.key.type = mgmt_ltk_type(key); ev.key.enc_size = key->enc_size; ev.key.ediv = key->ediv; @@ -9533,7 +9589,7 @@ void mgmt_new_irk(struct hci_dev *hdev, struct smp_irk *irk, bool persistent) bacpy(&ev.rpa, &irk->rpa); bacpy(&ev.irk.addr.bdaddr, &irk->bdaddr); - ev.irk.addr.type = link_to_bdaddr(irk->link_type, irk->addr_type); + ev.irk.addr.type = link_to_bdaddr(LE_LINK, irk->addr_type); memcpy(ev.irk.val, irk->val, sizeof(irk->val)); mgmt_event(MGMT_EV_NEW_IRK, hdev, &ev, sizeof(ev), NULL); @@ -9562,7 +9618,7 @@ void mgmt_new_csrk(struct hci_dev *hdev, struct smp_csrk *csrk, ev.store_hint = persistent; bacpy(&ev.key.addr.bdaddr, &csrk->bdaddr); - ev.key.addr.type = link_to_bdaddr(csrk->link_type, csrk->bdaddr_type); + ev.key.addr.type = link_to_bdaddr(LE_LINK, csrk->bdaddr_type); ev.key.type = csrk->type; memcpy(ev.key.val, csrk->val, sizeof(csrk->val)); @@ -9640,18 +9696,6 @@ void mgmt_device_connected(struct hci_dev *hdev, struct hci_conn *conn, mgmt_event_skb(skb, NULL); } -static void disconnect_rsp(struct mgmt_pending_cmd *cmd, void *data) -{ - struct sock **sk = data; - - cmd->cmd_complete(cmd, 0); - - *sk = cmd->sk; - sock_hold(*sk); - - mgmt_pending_remove(cmd); -} - static void unpair_device_rsp(struct mgmt_pending_cmd *cmd, void *data) { struct hci_dev *hdev = data; @@ -9695,8 +9739,6 @@ void mgmt_device_disconnected(struct hci_dev *hdev, bdaddr_t *bdaddr, if (link_type != ACL_LINK && link_type != LE_LINK) return; - mgmt_pending_foreach(MGMT_OP_DISCONNECT, hdev, disconnect_rsp, &sk); - bacpy(&ev.addr.bdaddr, bdaddr); ev.addr.type = link_to_bdaddr(link_type, addr_type); ev.reason = reason; @@ -9709,9 +9751,6 @@ void mgmt_device_disconnected(struct hci_dev *hdev, bdaddr_t *bdaddr, if (sk) sock_put(sk); - - mgmt_pending_foreach(MGMT_OP_UNPAIR_DEVICE, hdev, unpair_device_rsp, - hdev); } void mgmt_disconnect_failed(struct hci_dev *hdev, bdaddr_t *bdaddr, @@ -9740,13 +9779,18 @@ void mgmt_disconnect_failed(struct hci_dev *hdev, bdaddr_t *bdaddr, mgmt_pending_remove(cmd); } -void mgmt_connect_failed(struct hci_dev *hdev, bdaddr_t *bdaddr, u8 link_type, - u8 addr_type, u8 status) +void mgmt_connect_failed(struct hci_dev *hdev, struct hci_conn *conn, u8 status) { struct mgmt_ev_connect_failed ev; - bacpy(&ev.addr.bdaddr, bdaddr); - ev.addr.type = link_to_bdaddr(link_type, addr_type); + if (test_and_clear_bit(HCI_CONN_MGMT_CONNECTED, &conn->flags)) { + mgmt_device_disconnected(hdev, &conn->dst, conn->type, + conn->dst_type, status, true); + return; + } + + bacpy(&ev.addr.bdaddr, &conn->dst); + ev.addr.type = link_to_bdaddr(conn->type, conn->dst_type); ev.status = mgmt_status(status); mgmt_event(MGMT_EV_CONNECT_FAILED, hdev, &ev, sizeof(ev), NULL); diff --git a/net/bluetooth/msft.c b/net/bluetooth/msft.c index d039683d3bdd..5a8ccc491b14 100644 --- a/net/bluetooth/msft.c +++ b/net/bluetooth/msft.c @@ -7,7 +7,6 @@ #include <net/bluetooth/hci_core.h> #include <net/bluetooth/mgmt.h> -#include "hci_request.h" #include "mgmt_util.h" #include "msft.h" diff --git a/net/bluetooth/rfcomm/tty.c b/net/bluetooth/rfcomm/tty.c index 69c75c041fe1..af80d599c337 100644 --- a/net/bluetooth/rfcomm/tty.c +++ b/net/bluetooth/rfcomm/tty.c @@ -504,7 +504,7 @@ static int rfcomm_get_dev_list(void __user *arg) struct rfcomm_dev *dev; struct rfcomm_dev_list_req *dl; struct rfcomm_dev_info *di; - int n = 0, size, err; + int n = 0, err; u16 dev_num; BT_DBG(""); @@ -515,12 +515,11 @@ static int rfcomm_get_dev_list(void __user *arg) if (!dev_num || dev_num > (PAGE_SIZE * 4) / sizeof(*di)) return -EINVAL; - size = sizeof(*dl) + dev_num * sizeof(*di); - - dl = kzalloc(size, GFP_KERNEL); + dl = kzalloc(struct_size(dl, dev_info, dev_num), GFP_KERNEL); if (!dl) return -ENOMEM; + dl->dev_num = dev_num; di = dl->dev_info; mutex_lock(&rfcomm_dev_lock); @@ -528,12 +527,12 @@ static int rfcomm_get_dev_list(void __user *arg) list_for_each_entry(dev, &rfcomm_dev_list, list) { if (!tty_port_get(&dev->port)) continue; - (di + n)->id = dev->id; - (di + n)->flags = dev->flags; - (di + n)->state = dev->dlc->state; - (di + n)->channel = dev->channel; - bacpy(&(di + n)->src, &dev->src); - bacpy(&(di + n)->dst, &dev->dst); + di[n].id = dev->id; + di[n].flags = dev->flags; + di[n].state = dev->dlc->state; + di[n].channel = dev->channel; + bacpy(&di[n].src, &dev->src); + bacpy(&di[n].dst, &dev->dst); tty_port_put(&dev->port); if (++n >= dev_num) break; @@ -542,9 +541,7 @@ static int rfcomm_get_dev_list(void __user *arg) mutex_unlock(&rfcomm_dev_lock); dl->dev_num = n; - size = sizeof(*dl) + n * sizeof(*di); - - err = copy_to_user(arg, dl, size); + err = copy_to_user(arg, dl, struct_size(dl, dev_info, n)); kfree(dl); return err ? -EFAULT : 0; diff --git a/net/bluetooth/smp.c b/net/bluetooth/smp.c index 1e7ea3a4b7ef..8b9724fd752a 100644 --- a/net/bluetooth/smp.c +++ b/net/bluetooth/smp.c @@ -914,7 +914,7 @@ static int tk_request(struct l2cap_conn *conn, u8 remote_oob, u8 auth, * Confirms and the responder Enters the passkey. */ if (smp->method == OVERLAP) { - if (hcon->role == HCI_ROLE_MASTER) + if (test_bit(SMP_FLAG_INITIATOR, &smp->flags)) smp->method = CFM_PASSKEY; else smp->method = REQ_PASSKEY; @@ -964,7 +964,7 @@ static u8 smp_confirm(struct smp_chan *smp) smp_send_cmd(smp->conn, SMP_CMD_PAIRING_CONFIRM, sizeof(cp), &cp); - if (conn->hcon->out) + if (test_bit(SMP_FLAG_INITIATOR, &smp->flags)) SMP_ALLOW_CMD(smp, SMP_CMD_PAIRING_CONFIRM); else SMP_ALLOW_CMD(smp, SMP_CMD_PAIRING_RANDOM); @@ -980,7 +980,8 @@ static u8 smp_random(struct smp_chan *smp) int ret; bt_dev_dbg(conn->hcon->hdev, "conn %p %s", conn, - conn->hcon->out ? "initiator" : "responder"); + test_bit(SMP_FLAG_INITIATOR, &smp->flags) ? "initiator" : + "responder"); ret = smp_c1(smp->tk, smp->rrnd, smp->preq, smp->prsp, hcon->init_addr_type, &hcon->init_addr, @@ -994,7 +995,7 @@ static u8 smp_random(struct smp_chan *smp) return SMP_CONFIRM_FAILED; } - if (hcon->out) { + if (test_bit(SMP_FLAG_INITIATOR, &smp->flags)) { u8 stk[16]; __le64 rand = 0; __le16 ediv = 0; @@ -1059,7 +1060,6 @@ static void smp_notify_keys(struct l2cap_conn *conn) } if (smp->remote_irk) { - smp->remote_irk->link_type = hcon->type; mgmt_new_irk(hdev, smp->remote_irk, persistent); /* Now that user space can be considered to know the @@ -1079,28 +1079,24 @@ static void smp_notify_keys(struct l2cap_conn *conn) } if (smp->csrk) { - smp->csrk->link_type = hcon->type; smp->csrk->bdaddr_type = hcon->dst_type; bacpy(&smp->csrk->bdaddr, &hcon->dst); mgmt_new_csrk(hdev, smp->csrk, persistent); } if (smp->responder_csrk) { - smp->responder_csrk->link_type = hcon->type; smp->responder_csrk->bdaddr_type = hcon->dst_type; bacpy(&smp->responder_csrk->bdaddr, &hcon->dst); mgmt_new_csrk(hdev, smp->responder_csrk, persistent); } if (smp->ltk) { - smp->ltk->link_type = hcon->type; smp->ltk->bdaddr_type = hcon->dst_type; bacpy(&smp->ltk->bdaddr, &hcon->dst); mgmt_new_ltk(hdev, smp->ltk, persistent); } if (smp->responder_ltk) { - smp->responder_ltk->link_type = hcon->type; smp->responder_ltk->bdaddr_type = hcon->dst_type; bacpy(&smp->responder_ltk->bdaddr, &hcon->dst); mgmt_new_ltk(hdev, smp->responder_ltk, persistent); @@ -1120,8 +1116,6 @@ static void smp_notify_keys(struct l2cap_conn *conn) key = hci_add_link_key(hdev, smp->conn->hcon, &hcon->dst, smp->link_key, type, 0, &persistent); if (key) { - key->link_type = hcon->type; - key->bdaddr_type = hcon->dst_type; mgmt_new_link_key(hdev, key, persistent); /* Don't keep debug keys around if the relevant @@ -1256,14 +1250,15 @@ static void smp_distribute_keys(struct smp_chan *smp) rsp = (void *) &smp->prsp[1]; /* The responder sends its keys first */ - if (hcon->out && (smp->remote_key_dist & KEY_DIST_MASK)) { + if (test_bit(SMP_FLAG_INITIATOR, &smp->flags) && + (smp->remote_key_dist & KEY_DIST_MASK)) { smp_allow_key_dist(smp); return; } req = (void *) &smp->preq[1]; - if (hcon->out) { + if (test_bit(SMP_FLAG_INITIATOR, &smp->flags)) { keydist = &rsp->init_key_dist; *keydist &= req->init_key_dist; } else { @@ -1432,7 +1427,7 @@ static int sc_mackey_and_ltk(struct smp_chan *smp, u8 mackey[16], u8 ltk[16]) struct hci_conn *hcon = smp->conn->hcon; u8 *na, *nb, a[7], b[7]; - if (hcon->out) { + if (test_bit(SMP_FLAG_INITIATOR, &smp->flags)) { na = smp->prnd; nb = smp->rrnd; } else { @@ -1460,7 +1455,7 @@ static void sc_dhkey_check(struct smp_chan *smp) a[6] = hcon->init_addr_type; b[6] = hcon->resp_addr_type; - if (hcon->out) { + if (test_bit(SMP_FLAG_INITIATOR, &smp->flags)) { local_addr = a; remote_addr = b; memcpy(io_cap, &smp->preq[1], 3); @@ -1539,7 +1534,7 @@ static u8 sc_passkey_round(struct smp_chan *smp, u8 smp_op) /* The round is only complete when the initiator * receives pairing random. */ - if (!hcon->out) { + if (!test_bit(SMP_FLAG_INITIATOR, &smp->flags)) { smp_send_cmd(conn, SMP_CMD_PAIRING_RANDOM, sizeof(smp->prnd), smp->prnd); if (smp->passkey_round == 20) @@ -1567,7 +1562,7 @@ static u8 sc_passkey_round(struct smp_chan *smp, u8 smp_op) SMP_ALLOW_CMD(smp, SMP_CMD_PAIRING_RANDOM); - if (hcon->out) { + if (test_bit(SMP_FLAG_INITIATOR, &smp->flags)) { smp_send_cmd(conn, SMP_CMD_PAIRING_RANDOM, sizeof(smp->prnd), smp->prnd); return 0; @@ -1578,7 +1573,7 @@ static u8 sc_passkey_round(struct smp_chan *smp, u8 smp_op) case SMP_CMD_PUBLIC_KEY: default: /* Initiating device starts the round */ - if (!hcon->out) + if (!test_bit(SMP_FLAG_INITIATOR, &smp->flags)) return 0; bt_dev_dbg(hdev, "Starting passkey round %u", @@ -1623,7 +1618,7 @@ static int sc_user_reply(struct smp_chan *smp, u16 mgmt_op, __le32 passkey) } /* Initiator sends DHKey check first */ - if (hcon->out) { + if (test_bit(SMP_FLAG_INITIATOR, &smp->flags)) { sc_dhkey_check(smp); SMP_ALLOW_CMD(smp, SMP_CMD_DHKEY_CHECK); } else if (test_and_clear_bit(SMP_FLAG_DHKEY_PENDING, &smp->flags)) { @@ -1746,7 +1741,7 @@ static u8 smp_cmd_pairing_req(struct l2cap_conn *conn, struct sk_buff *skb) struct smp_cmd_pairing rsp, *req = (void *) skb->data; struct l2cap_chan *chan = conn->smp; struct hci_dev *hdev = conn->hcon->hdev; - struct smp_chan *smp; + struct smp_chan *smp = chan->data; u8 key_size, auth, sec_level; int ret; @@ -1755,16 +1750,14 @@ static u8 smp_cmd_pairing_req(struct l2cap_conn *conn, struct sk_buff *skb) if (skb->len < sizeof(*req)) return SMP_INVALID_PARAMS; - if (conn->hcon->role != HCI_ROLE_SLAVE) + if (smp && test_bit(SMP_FLAG_INITIATOR, &smp->flags)) return SMP_CMD_NOTSUPP; - if (!chan->data) + if (!smp) { smp = smp_chan_create(conn); - else - smp = chan->data; - - if (!smp) - return SMP_UNSPECIFIED; + if (!smp) + return SMP_UNSPECIFIED; + } /* We didn't start the pairing, so match remote */ auth = req->auth_req & AUTH_REQ_MASK(hdev); @@ -1946,7 +1939,7 @@ static u8 smp_cmd_pairing_rsp(struct l2cap_conn *conn, struct sk_buff *skb) if (skb->len < sizeof(*rsp)) return SMP_INVALID_PARAMS; - if (conn->hcon->role != HCI_ROLE_MASTER) + if (!test_bit(SMP_FLAG_INITIATOR, &smp->flags)) return SMP_CMD_NOTSUPP; skb_pull(skb, sizeof(*rsp)); @@ -2041,7 +2034,7 @@ static u8 sc_check_confirm(struct smp_chan *smp) if (smp->method == REQ_PASSKEY || smp->method == DSP_PASSKEY) return sc_passkey_round(smp, SMP_CMD_PAIRING_CONFIRM); - if (conn->hcon->out) { + if (test_bit(SMP_FLAG_INITIATOR, &smp->flags)) { smp_send_cmd(conn, SMP_CMD_PAIRING_RANDOM, sizeof(smp->prnd), smp->prnd); SMP_ALLOW_CMD(smp, SMP_CMD_PAIRING_RANDOM); @@ -2063,7 +2056,7 @@ static int fixup_sc_false_positive(struct smp_chan *smp) u8 auth; /* The issue is only observed when we're in responder role */ - if (hcon->out) + if (test_bit(SMP_FLAG_INITIATOR, &smp->flags)) return SMP_UNSPECIFIED; if (hci_dev_test_flag(hdev, HCI_SC_ONLY)) { @@ -2099,7 +2092,8 @@ static u8 smp_cmd_pairing_confirm(struct l2cap_conn *conn, struct sk_buff *skb) struct hci_dev *hdev = hcon->hdev; bt_dev_dbg(hdev, "conn %p %s", conn, - hcon->out ? "initiator" : "responder"); + test_bit(SMP_FLAG_INITIATOR, &smp->flags) ? "initiator" : + "responder"); if (skb->len < sizeof(smp->pcnf)) return SMP_INVALID_PARAMS; @@ -2121,7 +2115,7 @@ static u8 smp_cmd_pairing_confirm(struct l2cap_conn *conn, struct sk_buff *skb) return ret; } - if (conn->hcon->out) { + if (test_bit(SMP_FLAG_INITIATOR, &smp->flags)) { smp_send_cmd(conn, SMP_CMD_PAIRING_RANDOM, sizeof(smp->prnd), smp->prnd); SMP_ALLOW_CMD(smp, SMP_CMD_PAIRING_RANDOM); @@ -2156,7 +2150,7 @@ static u8 smp_cmd_pairing_random(struct l2cap_conn *conn, struct sk_buff *skb) if (!test_bit(SMP_FLAG_SC, &smp->flags)) return smp_random(smp); - if (hcon->out) { + if (test_bit(SMP_FLAG_INITIATOR, &smp->flags)) { pkax = smp->local_pk; pkbx = smp->remote_pk; na = smp->prnd; @@ -2169,7 +2163,7 @@ static u8 smp_cmd_pairing_random(struct l2cap_conn *conn, struct sk_buff *skb) } if (smp->method == REQ_OOB) { - if (!hcon->out) + if (!test_bit(SMP_FLAG_INITIATOR, &smp->flags)) smp_send_cmd(conn, SMP_CMD_PAIRING_RANDOM, sizeof(smp->prnd), smp->prnd); SMP_ALLOW_CMD(smp, SMP_CMD_DHKEY_CHECK); @@ -2180,7 +2174,7 @@ static u8 smp_cmd_pairing_random(struct l2cap_conn *conn, struct sk_buff *skb) if (smp->method == REQ_PASSKEY || smp->method == DSP_PASSKEY) return sc_passkey_round(smp, SMP_CMD_PAIRING_RANDOM); - if (hcon->out) { + if (test_bit(SMP_FLAG_INITIATOR, &smp->flags)) { u8 cfm[16]; err = smp_f4(smp->tfm_cmac, smp->remote_pk, smp->local_pk, @@ -2221,7 +2215,7 @@ mackey_and_ltk: return SMP_UNSPECIFIED; if (smp->method == REQ_OOB) { - if (hcon->out) { + if (test_bit(SMP_FLAG_INITIATOR, &smp->flags)) { sc_dhkey_check(smp); SMP_ALLOW_CMD(smp, SMP_CMD_DHKEY_CHECK); } @@ -2295,10 +2289,27 @@ bool smp_sufficient_security(struct hci_conn *hcon, u8 sec_level, return false; } +static void smp_send_pairing_req(struct smp_chan *smp, __u8 auth) +{ + struct smp_cmd_pairing cp; + + if (smp->conn->hcon->type == ACL_LINK) + build_bredr_pairing_cmd(smp, &cp, NULL); + else + build_pairing_cmd(smp->conn, &cp, NULL, auth); + + smp->preq[0] = SMP_CMD_PAIRING_REQ; + memcpy(&smp->preq[1], &cp, sizeof(cp)); + + smp_send_cmd(smp->conn, SMP_CMD_PAIRING_REQ, sizeof(cp), &cp); + SMP_ALLOW_CMD(smp, SMP_CMD_PAIRING_RSP); + + set_bit(SMP_FLAG_INITIATOR, &smp->flags); +} + static u8 smp_cmd_security_req(struct l2cap_conn *conn, struct sk_buff *skb) { struct smp_cmd_security_req *rp = (void *) skb->data; - struct smp_cmd_pairing cp; struct hci_conn *hcon = conn->hcon; struct hci_dev *hdev = hcon->hdev; struct smp_chan *smp; @@ -2347,16 +2358,20 @@ static u8 smp_cmd_security_req(struct l2cap_conn *conn, struct sk_buff *skb) skb_pull(skb, sizeof(*rp)); - memset(&cp, 0, sizeof(cp)); - build_pairing_cmd(conn, &cp, NULL, auth); + smp_send_pairing_req(smp, auth); - smp->preq[0] = SMP_CMD_PAIRING_REQ; - memcpy(&smp->preq[1], &cp, sizeof(cp)); + return 0; +} - smp_send_cmd(conn, SMP_CMD_PAIRING_REQ, sizeof(cp), &cp); - SMP_ALLOW_CMD(smp, SMP_CMD_PAIRING_RSP); +static void smp_send_security_req(struct smp_chan *smp, __u8 auth) +{ + struct smp_cmd_security_req cp; - return 0; + cp.auth_req = auth; + smp_send_cmd(smp->conn, SMP_CMD_SECURITY_REQ, sizeof(cp), &cp); + SMP_ALLOW_CMD(smp, SMP_CMD_PAIRING_REQ); + + clear_bit(SMP_FLAG_INITIATOR, &smp->flags); } int smp_conn_security(struct hci_conn *hcon, __u8 sec_level) @@ -2427,23 +2442,11 @@ int smp_conn_security(struct hci_conn *hcon, __u8 sec_level) authreq |= SMP_AUTH_MITM; } - if (hcon->role == HCI_ROLE_MASTER) { - struct smp_cmd_pairing cp; - - build_pairing_cmd(conn, &cp, NULL, authreq); - smp->preq[0] = SMP_CMD_PAIRING_REQ; - memcpy(&smp->preq[1], &cp, sizeof(cp)); - - smp_send_cmd(conn, SMP_CMD_PAIRING_REQ, sizeof(cp), &cp); - SMP_ALLOW_CMD(smp, SMP_CMD_PAIRING_RSP); - } else { - struct smp_cmd_security_req cp; - cp.auth_req = authreq; - smp_send_cmd(conn, SMP_CMD_SECURITY_REQ, sizeof(cp), &cp); - SMP_ALLOW_CMD(smp, SMP_CMD_PAIRING_REQ); - } + if (hcon->role == HCI_ROLE_MASTER) + smp_send_pairing_req(smp, authreq); + else + smp_send_security_req(smp, authreq); - set_bit(SMP_FLAG_INITIATOR, &smp->flags); ret = 0; unlock: @@ -2694,8 +2697,6 @@ static int smp_cmd_sign_info(struct l2cap_conn *conn, struct sk_buff *skb) static u8 sc_select_method(struct smp_chan *smp) { - struct l2cap_conn *conn = smp->conn; - struct hci_conn *hcon = conn->hcon; struct smp_cmd_pairing *local, *remote; u8 local_mitm, remote_mitm, local_io, remote_io, method; @@ -2708,7 +2709,7 @@ static u8 sc_select_method(struct smp_chan *smp) * the "struct smp_cmd_pairing" from them we need to skip the * first byte which contains the opcode. */ - if (hcon->out) { + if (test_bit(SMP_FLAG_INITIATOR, &smp->flags)) { local = (void *) &smp->preq[1]; remote = (void *) &smp->prsp[1]; } else { @@ -2777,7 +2778,7 @@ static int smp_cmd_public_key(struct l2cap_conn *conn, struct sk_buff *skb) /* Non-initiating device sends its public key after receiving * the key from the initiating device. */ - if (!hcon->out) { + if (!test_bit(SMP_FLAG_INITIATOR, &smp->flags)) { err = sc_send_public_key(smp); if (err) return err; @@ -2839,7 +2840,7 @@ static int smp_cmd_public_key(struct l2cap_conn *conn, struct sk_buff *skb) } if (smp->method == REQ_OOB) { - if (hcon->out) + if (test_bit(SMP_FLAG_INITIATOR, &smp->flags)) smp_send_cmd(conn, SMP_CMD_PAIRING_RANDOM, sizeof(smp->prnd), smp->prnd); @@ -2848,7 +2849,7 @@ static int smp_cmd_public_key(struct l2cap_conn *conn, struct sk_buff *skb) return 0; } - if (hcon->out) + if (test_bit(SMP_FLAG_INITIATOR, &smp->flags)) SMP_ALLOW_CMD(smp, SMP_CMD_PAIRING_CONFIRM); if (smp->method == REQ_PASSKEY) { @@ -2863,7 +2864,7 @@ static int smp_cmd_public_key(struct l2cap_conn *conn, struct sk_buff *skb) /* The Initiating device waits for the non-initiating device to * send the confirm value. */ - if (conn->hcon->out) + if (test_bit(SMP_FLAG_INITIATOR, &smp->flags)) return 0; err = smp_f4(smp->tfm_cmac, smp->local_pk, smp->remote_pk, smp->prnd, @@ -2897,7 +2898,7 @@ static int smp_cmd_dhkey_check(struct l2cap_conn *conn, struct sk_buff *skb) a[6] = hcon->init_addr_type; b[6] = hcon->resp_addr_type; - if (hcon->out) { + if (test_bit(SMP_FLAG_INITIATOR, &smp->flags)) { local_addr = a; remote_addr = b; memcpy(io_cap, &smp->prsp[1], 3); @@ -2922,7 +2923,7 @@ static int smp_cmd_dhkey_check(struct l2cap_conn *conn, struct sk_buff *skb) if (crypto_memneq(check->e, e, 16)) return SMP_DHKEY_CHECK_FAILED; - if (!hcon->out) { + if (!test_bit(SMP_FLAG_INITIATOR, &smp->flags)) { if (test_bit(SMP_FLAG_WAIT_USER, &smp->flags)) { set_bit(SMP_FLAG_DHKEY_PENDING, &smp->flags); return 0; @@ -2934,7 +2935,7 @@ static int smp_cmd_dhkey_check(struct l2cap_conn *conn, struct sk_buff *skb) sc_add_ltk(smp); - if (hcon->out) { + if (test_bit(SMP_FLAG_INITIATOR, &smp->flags)) { hci_le_start_enc(hcon, 0, 0, smp->tk, smp->enc_key_size); hcon->enc_key_size = smp->enc_key_size; } @@ -3083,7 +3084,6 @@ static void bredr_pairing(struct l2cap_chan *chan) struct l2cap_conn *conn = chan->conn; struct hci_conn *hcon = conn->hcon; struct hci_dev *hdev = hcon->hdev; - struct smp_cmd_pairing req; struct smp_chan *smp; bt_dev_dbg(hdev, "chan %p", chan); @@ -3135,14 +3135,7 @@ static void bredr_pairing(struct l2cap_chan *chan) bt_dev_dbg(hdev, "starting SMP over BR/EDR"); - /* Prepare and send the BR/EDR SMP Pairing Request */ - build_bredr_pairing_cmd(smp, &req, NULL); - - smp->preq[0] = SMP_CMD_PAIRING_REQ; - memcpy(&smp->preq[1], &req, sizeof(req)); - - smp_send_cmd(conn, SMP_CMD_PAIRING_REQ, sizeof(req), &req); - SMP_ALLOW_CMD(smp, SMP_CMD_PAIRING_RSP); + smp_send_pairing_req(smp, 0x00); } static void smp_resume_cb(struct l2cap_chan *chan) diff --git a/net/bpf/bpf_dummy_struct_ops.c b/net/bpf/bpf_dummy_struct_ops.c index 891cdf61c65a..f71f67c6896b 100644 --- a/net/bpf/bpf_dummy_struct_ops.c +++ b/net/bpf/bpf_dummy_struct_ops.c @@ -115,7 +115,7 @@ static int check_test_run_args(struct bpf_prog *prog, struct bpf_dummy_ops_test_ offset = btf_ctx_arg_offset(bpf_dummy_ops_btf, func_proto, arg_no); info = find_ctx_arg_info(prog->aux, offset); - if (info && (info->reg_type & PTR_MAYBE_NULL)) + if (info && type_may_be_null(info->reg_type)) continue; return -EINVAL; @@ -272,12 +272,12 @@ static int bpf_dummy_init_member(const struct btf_type *t, return -EOPNOTSUPP; } -static int bpf_dummy_reg(void *kdata) +static int bpf_dummy_reg(void *kdata, struct bpf_link *link) { return -EOPNOTSUPP; } -static void bpf_dummy_unreg(void *kdata) +static void bpf_dummy_unreg(void *kdata, struct bpf_link *link) { } diff --git a/net/bpf/test_run.c b/net/bpf/test_run.c index 36ae54f57bf5..6d7a442ceb89 100644 --- a/net/bpf/test_run.c +++ b/net/bpf/test_run.c @@ -127,9 +127,10 @@ struct xdp_test_data { #define TEST_XDP_FRAME_SIZE (PAGE_SIZE - sizeof(struct xdp_page_head)) #define TEST_XDP_MAX_BATCH 256 -static void xdp_test_run_init_page(struct page *page, void *arg) +static void xdp_test_run_init_page(netmem_ref netmem, void *arg) { - struct xdp_page_head *head = phys_to_virt(page_to_phys(page)); + struct xdp_page_head *head = + phys_to_virt(page_to_phys(netmem_to_page(netmem))); struct xdp_buff *new_ctx, *orig_ctx; u32 headroom = XDP_PACKET_HEADROOM; struct xdp_test_data *xdp = arg; @@ -283,9 +284,10 @@ static int xdp_recv_frames(struct xdp_frame **frames, int nframes, static int xdp_test_run_batch(struct xdp_test_data *xdp, struct bpf_prog *prog, u32 repeat) { - struct bpf_redirect_info *ri = this_cpu_ptr(&bpf_redirect_info); + struct bpf_net_context __bpf_net_ctx, *bpf_net_ctx; int err = 0, act, ret, i, nframes = 0, batch_sz; struct xdp_frame **frames = xdp->frames; + struct bpf_redirect_info *ri; struct xdp_page_head *head; struct xdp_frame *frm; bool redirect = false; @@ -295,6 +297,8 @@ static int xdp_test_run_batch(struct xdp_test_data *xdp, struct bpf_prog *prog, batch_sz = min_t(u32, repeat, xdp->batch_size); local_bh_disable(); + bpf_net_ctx = bpf_net_ctx_set(&__bpf_net_ctx); + ri = bpf_net_ctx_get_ri(); xdp_set_return_frame_no_direct(); for (i = 0; i < batch_sz; i++) { @@ -359,6 +363,7 @@ out: } xdp_clear_return_frame_no_direct(); + bpf_net_ctx_clear(bpf_net_ctx); local_bh_enable(); return err; } @@ -394,6 +399,7 @@ static int bpf_test_run_xdp_live(struct bpf_prog *prog, struct xdp_buff *ctx, static int bpf_test_run(struct bpf_prog *prog, void *ctx, u32 repeat, u32 *retval, u32 *time, bool xdp) { + struct bpf_net_context __bpf_net_ctx, *bpf_net_ctx; struct bpf_prog_array_item item = {.prog = prog}; struct bpf_run_ctx *old_ctx; struct bpf_cg_run_ctx run_ctx; @@ -419,10 +425,14 @@ static int bpf_test_run(struct bpf_prog *prog, void *ctx, u32 repeat, do { run_ctx.prog_item = &item; local_bh_disable(); + bpf_net_ctx = bpf_net_ctx_set(&__bpf_net_ctx); + if (xdp) *retval = bpf_prog_run_xdp(prog, ctx); else *retval = bpf_prog_run(prog, ctx); + + bpf_net_ctx_clear(bpf_net_ctx); local_bh_enable(); } while (bpf_test_timer_continue(&t, 1, repeat, &ret, time)); bpf_reset_run_ctx(old_ctx); @@ -983,7 +993,8 @@ int bpf_prog_test_run_skb(struct bpf_prog *prog, const union bpf_attr *kattr, void *data; int ret; - if (kattr->test.flags || kattr->test.cpu || kattr->test.batch_size) + if ((kattr->test.flags & ~BPF_F_TEST_SKB_CHECKSUM_COMPLETE) || + kattr->test.cpu || kattr->test.batch_size) return -EINVAL; data = bpf_test_init(kattr, kattr->test.data_size_in, @@ -1031,6 +1042,7 @@ int bpf_prog_test_run_skb(struct bpf_prog *prog, const union bpf_attr *kattr, skb_reserve(skb, NET_SKB_PAD + NET_IP_ALIGN); __skb_put(skb, size); + if (ctx && ctx->ifindex > 1) { dev = dev_get_by_index(net, ctx->ifindex); if (!dev) { @@ -1066,9 +1078,19 @@ int bpf_prog_test_run_skb(struct bpf_prog *prog, const union bpf_attr *kattr, __skb_push(skb, hh_len); if (is_direct_pkt_access) bpf_compute_data_pointers(skb); + ret = convert___skb_to_skb(skb, ctx); if (ret) goto out; + + if (kattr->test.flags & BPF_F_TEST_SKB_CHECKSUM_COMPLETE) { + const int off = skb_network_offset(skb); + int len = skb->len - off; + + skb->csum = skb_checksum(skb, off, len, 0); + skb->ip_summed = CHECKSUM_COMPLETE; + } + ret = bpf_test_run(prog, skb, repeat, &retval, &duration, false); if (ret) goto out; @@ -1083,6 +1105,20 @@ int bpf_prog_test_run_skb(struct bpf_prog *prog, const union bpf_attr *kattr, } memset(__skb_push(skb, hh_len), 0, hh_len); } + + if (kattr->test.flags & BPF_F_TEST_SKB_CHECKSUM_COMPLETE) { + const int off = skb_network_offset(skb); + int len = skb->len - off; + __wsum csum; + + csum = skb_checksum(skb, off, len, 0); + + if (csum_fold(skb->csum) != csum_fold(csum)) { + ret = -EBADMSG; + goto out; + } + } + convert_skb_to___skb(skb, ctx); size = skb->len; diff --git a/net/bridge/br_device.c b/net/bridge/br_device.c index fb1115857e49..26b79feb385d 100644 --- a/net/bridge/br_device.c +++ b/net/bridge/br_device.c @@ -487,9 +487,11 @@ void br_dev_setup(struct net_device *dev) dev->ethtool_ops = &br_ethtool_ops; SET_NETDEV_DEVTYPE(dev, &br_type); dev->priv_flags = IFF_EBRIDGE | IFF_NO_QUEUE; + dev->lltx = true; + dev->netns_local = true; - dev->features = COMMON_FEATURES | NETIF_F_LLTX | NETIF_F_NETNS_LOCAL | - NETIF_F_HW_VLAN_CTAG_TX | NETIF_F_HW_VLAN_STAG_TX; + dev->features = COMMON_FEATURES | NETIF_F_HW_VLAN_CTAG_TX | + NETIF_F_HW_VLAN_STAG_TX; dev->hw_features = COMMON_FEATURES | NETIF_F_HW_VLAN_CTAG_TX | NETIF_F_HW_VLAN_STAG_TX; dev->vlan_features = COMMON_FEATURES; diff --git a/net/bridge/br_fdb.c b/net/bridge/br_fdb.c index c77591e63841..ad7a42b505ef 100644 --- a/net/bridge/br_fdb.c +++ b/net/bridge/br_fdb.c @@ -1469,12 +1469,10 @@ int br_fdb_external_learn_add(struct net_bridge *br, struct net_bridge_port *p, modified = true; } - if (test_bit(BR_FDB_ADDED_BY_EXT_LEARN, &fdb->flags)) { + if (test_and_set_bit(BR_FDB_ADDED_BY_EXT_LEARN, &fdb->flags)) { /* Refresh entry */ fdb->used = jiffies; - } else if (!test_bit(BR_FDB_ADDED_BY_USER, &fdb->flags)) { - /* Take over SW learned entry */ - set_bit(BR_FDB_ADDED_BY_EXT_LEARN, &fdb->flags); + } else { modified = true; } diff --git a/net/bridge/br_forward.c b/net/bridge/br_forward.c index d97064d460dc..e19b583ff2c6 100644 --- a/net/bridge/br_forward.c +++ b/net/bridge/br_forward.c @@ -25,8 +25,8 @@ static inline int should_deliver(const struct net_bridge_port *p, vg = nbp_vlan_group_rcu(p); return ((p->flags & BR_HAIRPIN_MODE) || skb->dev != p->dev) && - p->state == BR_STATE_FORWARDING && br_allowed_egress(vg, skb) && - nbp_switchdev_allowed_egress(p, skb) && + (br_mst_is_enabled(p->br) || p->state == BR_STATE_FORWARDING) && + br_allowed_egress(vg, skb) && nbp_switchdev_allowed_egress(p, skb) && !br_skb_isolated(p, skb); } diff --git a/net/bridge/br_multicast.c b/net/bridge/br_multicast.c index 9a1cb5079a7a..b2ae0d2434d2 100644 --- a/net/bridge/br_multicast.c +++ b/net/bridge/br_multicast.c @@ -2045,16 +2045,14 @@ void br_multicast_del_port(struct net_bridge_port *port) { struct net_bridge *br = port->br; struct net_bridge_port_group *pg; - HLIST_HEAD(deleted_head); struct hlist_node *n; /* Take care of the remaining groups, only perm ones should be left */ spin_lock_bh(&br->multicast_lock); hlist_for_each_entry_safe(pg, n, &port->mglist, mglist) br_multicast_find_del_pg(br, pg); - hlist_move_list(&br->mcast_gc_list, &deleted_head); spin_unlock_bh(&br->multicast_lock); - br_multicast_gc(&deleted_head); + flush_work(&br->mcast_gc_work); br_multicast_port_ctx_deinit(&port->multicast_ctx); free_percpu(port->mcast_stats); } diff --git a/net/bridge/br_netfilter_hooks.c b/net/bridge/br_netfilter_hooks.c index bf30c50b5689..0e8bc0ea6175 100644 --- a/net/bridge/br_netfilter_hooks.c +++ b/net/bridge/br_netfilter_hooks.c @@ -36,6 +36,7 @@ #include <net/route.h> #include <net/netfilter/br_netfilter.h> #include <net/netns/generic.h> +#include <net/inet_dscp.h> #include <linux/uaccess.h> #include "br_private.h" @@ -137,6 +138,7 @@ static inline bool is_pppoe_ipv6(const struct sk_buff *skb, #define NF_BRIDGE_MAX_MAC_HEADER_LENGTH (PPPOE_SES_HLEN + ETH_HLEN) struct brnf_frag_data { + local_lock_t bh_lock; char mac[NF_BRIDGE_MAX_MAC_HEADER_LENGTH]; u8 encap_size; u8 size; @@ -144,7 +146,9 @@ struct brnf_frag_data { __be16 vlan_proto; }; -static DEFINE_PER_CPU(struct brnf_frag_data, brnf_frag_data_storage); +static DEFINE_PER_CPU(struct brnf_frag_data, brnf_frag_data_storage) = { + .bh_lock = INIT_LOCAL_LOCK(bh_lock), +}; static void nf_bridge_info_free(struct sk_buff *skb) { @@ -399,7 +403,7 @@ static int br_nf_pre_routing_finish(struct net *net, struct sock *sk, struct sk_ goto free_skb; rt = ip_route_output(net, iph->daddr, 0, - RT_TOS(iph->tos), 0, + iph->tos & INET_DSCP_MASK, 0, RT_SCOPE_UNIVERSE); if (!IS_ERR(rt)) { /* - Bridged-and-DNAT'ed traffic doesn't @@ -619,8 +623,12 @@ static unsigned int br_nf_local_in(void *priv, if (likely(nf_ct_is_confirmed(ct))) return NF_ACCEPT; + if (WARN_ON_ONCE(refcount_read(&nfct->use) != 1)) { + nf_reset_ct(skb); + return NF_ACCEPT; + } + WARN_ON_ONCE(skb_shared(skb)); - WARN_ON_ONCE(refcount_read(&nfct->use) != 1); /* We can't call nf_confirm here, it would create a dependency * on nf_conntrack module. @@ -850,6 +858,7 @@ static int br_nf_dev_queue_xmit(struct net *net, struct sock *sk, struct sk_buff { struct nf_bridge_info *nf_bridge = nf_bridge_info_get(skb); unsigned int mtu, mtu_reserved; + int ret; mtu_reserved = nf_bridge_mtu_reduction(skb); mtu = skb->dev->mtu; @@ -882,6 +891,7 @@ static int br_nf_dev_queue_xmit(struct net *net, struct sock *sk, struct sk_buff IPCB(skb)->frag_max_size = nf_bridge->frag_max_size; + local_lock_nested_bh(&brnf_frag_data_storage.bh_lock); data = this_cpu_ptr(&brnf_frag_data_storage); if (skb_vlan_tag_present(skb)) { @@ -897,7 +907,9 @@ static int br_nf_dev_queue_xmit(struct net *net, struct sock *sk, struct sk_buff skb_copy_from_linear_data_offset(skb, -data->size, data->mac, data->size); - return br_nf_ip_fragment(net, sk, skb, br_nf_push_frag_xmit); + ret = br_nf_ip_fragment(net, sk, skb, br_nf_push_frag_xmit); + local_unlock_nested_bh(&brnf_frag_data_storage.bh_lock); + return ret; } if (IS_ENABLED(CONFIG_NF_DEFRAG_IPV6) && skb->protocol == htons(ETH_P_IPV6)) { @@ -909,6 +921,7 @@ static int br_nf_dev_queue_xmit(struct net *net, struct sock *sk, struct sk_buff IP6CB(skb)->frag_max_size = nf_bridge->frag_max_size; + local_lock_nested_bh(&brnf_frag_data_storage.bh_lock); data = this_cpu_ptr(&brnf_frag_data_storage); data->encap_size = nf_bridge_encap_header_len(skb); data->size = ETH_HLEN + data->encap_size; @@ -916,8 +929,12 @@ static int br_nf_dev_queue_xmit(struct net *net, struct sock *sk, struct sk_buff skb_copy_from_linear_data_offset(skb, -data->size, data->mac, data->size); - if (v6ops) - return v6ops->fragment(net, sk, skb, br_nf_push_frag_xmit); + if (v6ops) { + ret = v6ops->fragment(net, sk, skb, br_nf_push_frag_xmit); + local_unlock_nested_bh(&brnf_frag_data_storage.bh_lock); + return ret; + } + local_unlock_nested_bh(&brnf_frag_data_storage.bh_lock); kfree_skb(skb); return -EMSGSIZE; @@ -1177,7 +1194,7 @@ int br_nf_hook_thresh(unsigned int hook, struct net *net, #ifdef CONFIG_SYSCTL static -int brnf_sysctl_call_tables(struct ctl_table *ctl, int write, +int brnf_sysctl_call_tables(const struct ctl_table *ctl, int write, void *buffer, size_t *lenp, loff_t *ppos) { int ret; diff --git a/net/bridge/br_netlink_tunnel.c b/net/bridge/br_netlink_tunnel.c index 17abf092f7ca..71a12da30004 100644 --- a/net/bridge/br_netlink_tunnel.c +++ b/net/bridge/br_netlink_tunnel.c @@ -315,8 +315,8 @@ int br_process_vlan_tunnel_info(const struct net_bridge *br, if (curr_change) *changed = curr_change; - __vlan_tunnel_handle_range(p, &v_start, &v_end, v, - curr_change); + __vlan_tunnel_handle_range(p, &v_start, &v_end, v, + curr_change); } if (v_start && v_end) br_vlan_notify(br, p, v_start->vid, v_end->vid, diff --git a/net/bridge/netfilter/ebtables.c b/net/bridge/netfilter/ebtables.c index cbd0e3586c3f..3e67d4aff419 100644 --- a/net/bridge/netfilter/ebtables.c +++ b/net/bridge/netfilter/ebtables.c @@ -1256,7 +1256,7 @@ int ebt_register_table(struct net *net, const struct ebt_table *input_table, goto free_unlock; } - ops = kmemdup(template_ops, sizeof(*ops) * num_ops, GFP_KERNEL); + ops = kmemdup_array(template_ops, num_ops, sizeof(*ops), GFP_KERNEL); if (!ops) { ret = -ENOMEM; if (newinfo->nentries) diff --git a/net/bridge/netfilter/nf_conntrack_bridge.c b/net/bridge/netfilter/nf_conntrack_bridge.c index c3c51b9a6826..816bb0fde718 100644 --- a/net/bridge/netfilter/nf_conntrack_bridge.c +++ b/net/bridge/netfilter/nf_conntrack_bridge.c @@ -32,7 +32,7 @@ static int nf_br_ip_fragment(struct net *net, struct sock *sk, struct sk_buff *)) { int frag_max_size = BR_INPUT_SKB_CB(skb)->frag_max_size; - bool mono_delivery_time = skb->mono_delivery_time; + u8 tstamp_type = skb->tstamp_type; unsigned int hlen, ll_rs, mtu; ktime_t tstamp = skb->tstamp; struct ip_frag_state state; @@ -82,7 +82,7 @@ static int nf_br_ip_fragment(struct net *net, struct sock *sk, if (iter.frag) ip_fraglist_prepare(skb, &iter); - skb_set_delivery_time(skb, tstamp, mono_delivery_time); + skb_set_delivery_time(skb, tstamp, tstamp_type); err = output(net, sk, data, skb); if (err || !iter.frag) break; @@ -113,7 +113,7 @@ slow_path: goto blackhole; } - skb_set_delivery_time(skb2, tstamp, mono_delivery_time); + skb_set_delivery_time(skb2, tstamp, tstamp_type); err = output(net, sk, data, skb2); if (err) goto blackhole; diff --git a/net/bridge/netfilter/nft_meta_bridge.c b/net/bridge/netfilter/nft_meta_bridge.c index bd4d1b4d745f..d12a221366d6 100644 --- a/net/bridge/netfilter/nft_meta_bridge.c +++ b/net/bridge/netfilter/nft_meta_bridge.c @@ -142,7 +142,7 @@ static int nft_meta_bridge_set_init(const struct nft_ctx *ctx, } priv->len = len; - err = nft_parse_register_load(tb[NFTA_META_SREG], &priv->sreg, len); + err = nft_parse_register_load(ctx, tb[NFTA_META_SREG], &priv->sreg, len); if (err < 0) return err; @@ -168,8 +168,7 @@ static bool nft_meta_bridge_set_reduce(struct nft_regs_track *track, } static int nft_meta_bridge_set_validate(const struct nft_ctx *ctx, - const struct nft_expr *expr, - const struct nft_data **data) + const struct nft_expr *expr) { struct nft_meta *priv = nft_expr_priv(expr); unsigned int hooks; @@ -179,7 +178,7 @@ static int nft_meta_bridge_set_validate(const struct nft_ctx *ctx, hooks = 1 << NF_BR_PRE_ROUTING; break; default: - return nft_meta_set_validate(ctx, expr, data); + return nft_meta_set_validate(ctx, expr); } return nft_chain_validate_hooks(ctx->chain, hooks); diff --git a/net/bridge/netfilter/nft_reject_bridge.c b/net/bridge/netfilter/nft_reject_bridge.c index 71b54fed7263..1cb5c16e97b7 100644 --- a/net/bridge/netfilter/nft_reject_bridge.c +++ b/net/bridge/netfilter/nft_reject_bridge.c @@ -170,8 +170,7 @@ out: } static int nft_reject_bridge_validate(const struct nft_ctx *ctx, - const struct nft_expr *expr, - const struct nft_data **data) + const struct nft_expr *expr) { return nft_chain_validate_hooks(ctx->chain, (1 << NF_BR_PRE_ROUTING) | (1 << NF_BR_LOCAL_IN)); diff --git a/net/caif/cfpkt_skbuff.c b/net/caif/cfpkt_skbuff.c index 7796414d47e5..96236d21b18e 100644 --- a/net/caif/cfpkt_skbuff.c +++ b/net/caif/cfpkt_skbuff.c @@ -21,13 +21,6 @@ do { \ pr_warn(errmsg); \ } while (0) -struct cfpktq { - struct sk_buff_head head; - atomic_t count; - /* Lock protects count updates */ - spinlock_t lock; -}; - /* * net/caif/ is generic and does not * understand SKB, so we do this typecast @@ -305,10 +298,8 @@ struct cfpkt *cfpkt_append(struct cfpkt *dstpkt, if (unlikely(is_erronous(dstpkt) || is_erronous(addpkt))) { return dstpkt; } - if (expectlen > addlen) - neededtailspace = expectlen; - else - neededtailspace = addlen; + + neededtailspace = max(expectlen, addlen); if (dst->tail + neededtailspace > dst->end) { /* Create a dumplicate of 'dst' with more tail space */ diff --git a/net/caif/chnl_net.c b/net/caif/chnl_net.c index 47901bd4def1..94ad09e36df2 100644 --- a/net/caif/chnl_net.c +++ b/net/caif/chnl_net.c @@ -47,7 +47,6 @@ struct chnl_net { struct caif_connect_request conn_req; struct list_head list_field; struct net_device *netdev; - char name[256]; wait_queue_head_t netmgmt_wq; /* Flow status to remember and control the transmission. */ bool flowenabled; @@ -347,7 +346,6 @@ static int chnl_net_init(struct net_device *dev) struct chnl_net *priv; ASSERT_RTNL(); priv = netdev_priv(dev); - strncpy(priv->name, dev->name, sizeof(priv->name)); INIT_LIST_HEAD(&priv->list_field); return 0; } diff --git a/net/can/Kconfig b/net/can/Kconfig index cb56be8e3862..af64a6f76458 100644 --- a/net/can/Kconfig +++ b/net/can/Kconfig @@ -56,18 +56,17 @@ config CAN_GW source "net/can/j1939/Kconfig" config CAN_ISOTP - tristate "ISO 15765-2:2016 CAN transport protocol" + tristate "ISO 15765-2 CAN transport protocol" help CAN Transport Protocols offer support for segmented Point-to-Point communication between CAN nodes via two defined CAN Identifiers. + This protocol driver implements segmented data transfers for CAN CC + (aka Classical CAN, CAN 2.0B) and CAN FD frame types which were + introduced with ISO 15765-2:2016. As CAN frames can only transport a small amount of data bytes - (max. 8 bytes for 'classic' CAN and max. 64 bytes for CAN FD) this + (max. 8 bytes for CAN CC and max. 64 bytes for CAN FD) this segmentation is needed to transport longer Protocol Data Units (PDU) as needed e.g. for vehicle diagnosis (UDS, ISO 14229) or IP-over-CAN traffic. - This protocol driver implements data transfers according to - ISO 15765-2:2016 for 'classic' CAN and CAN FD frame types. - If you want to perform automotive vehicle diagnostic services (UDS), - say 'y'. endif diff --git a/net/can/bcm.c b/net/can/bcm.c index 27d5fcf0eac9..217049fa496e 100644 --- a/net/can/bcm.c +++ b/net/can/bcm.c @@ -1470,6 +1470,12 @@ static void bcm_notify(struct bcm_sock *bo, unsigned long msg, /* remove device reference, if this is our bound device */ if (bo->bound && bo->ifindex == dev->ifindex) { +#if IS_ENABLED(CONFIG_PROC_FS) + if (sock_net(sk)->can.bcmproc_dir && bo->bcm_proc_read) { + remove_proc_entry(bo->procname, sock_net(sk)->can.bcmproc_dir); + bo->bcm_proc_read = NULL; + } +#endif bo->bound = 0; bo->ifindex = 0; notify_enodev = 1; diff --git a/net/can/isotp.c b/net/can/isotp.c index 25bac0fafc83..16046931542a 100644 --- a/net/can/isotp.c +++ b/net/can/isotp.c @@ -72,7 +72,7 @@ #include <net/sock.h> #include <net/net_namespace.h> -MODULE_DESCRIPTION("PF_CAN isotp 15765-2:2016 protocol"); +MODULE_DESCRIPTION("PF_CAN ISO 15765-2 transport protocol"); MODULE_LICENSE("Dual BSD/GPL"); MODULE_AUTHOR("Oliver Hartkopp <socketcan@hartkopp.net>"); MODULE_ALIAS("can-proto-6"); @@ -83,10 +83,11 @@ MODULE_ALIAS("can-proto-6"); (CAN_EFF_MASK | CAN_EFF_FLAG | CAN_RTR_FLAG) : \ (CAN_SFF_MASK | CAN_EFF_FLAG | CAN_RTR_FLAG)) -/* ISO 15765-2:2016 supports more than 4095 byte per ISO PDU as the FF_DL can - * take full 32 bit values (4 Gbyte). We would need some good concept to handle - * this between user space and kernel space. For now set the static buffer to - * something about 8 kbyte to be able to test this new functionality. +/* Since ISO 15765-2:2016 the CAN isotp protocol supports more than 4095 + * byte per ISO PDU as the FF_DL can take full 32 bit values (4 Gbyte). + * We would need some good concept to handle this between user space and + * kernel space. For now set the static buffer to something about 8 kbyte + * to be able to test this new functionality. */ #define DEFAULT_MAX_PDU_SIZE 8300 diff --git a/net/can/j1939/main.c b/net/can/j1939/main.c index a6fb89fa6278..7e8a20f2fc42 100644 --- a/net/can/j1939/main.c +++ b/net/can/j1939/main.c @@ -30,10 +30,6 @@ MODULE_ALIAS("can-proto-" __stringify(CAN_J1939)); /* CAN_HDR: #bytes before can_frame data part */ #define J1939_CAN_HDR (offsetof(struct can_frame, data)) -/* CAN_FTR: #bytes beyond data part */ -#define J1939_CAN_FTR (sizeof(struct can_frame) - J1939_CAN_HDR - \ - sizeof(((struct can_frame *)0)->data)) - /* lowest layer */ static void j1939_can_recv(struct sk_buff *iskb, void *data) { @@ -342,7 +338,7 @@ int j1939_send_one(struct j1939_priv *priv, struct sk_buff *skb) memset(cf, 0, J1939_CAN_HDR); /* make it a full can frame again */ - skb_put(skb, J1939_CAN_FTR + (8 - dlc)); + skb_put_zero(skb, 8 - dlc); canid = CAN_EFF_FLAG | (skcb->priority << 26) | diff --git a/net/can/j1939/transport.c b/net/can/j1939/transport.c index fe3df23a2595..319f47df3330 100644 --- a/net/can/j1939/transport.c +++ b/net/can/j1939/transport.c @@ -1179,10 +1179,10 @@ static enum hrtimer_restart j1939_tp_txtimer(struct hrtimer *hrtimer) break; case -ENETDOWN: /* In this case we should get a netdev_event(), all active - * sessions will be cleared by - * j1939_cancel_all_active_sessions(). So handle this as an - * error, but let j1939_cancel_all_active_sessions() do the - * cleanup including propagation of the error to user space. + * sessions will be cleared by j1939_cancel_active_session(). + * So handle this as an error, but let + * j1939_cancel_active_session() do the cleanup including + * propagation of the error to user space. */ break; case -EOVERFLOW: @@ -1593,8 +1593,8 @@ j1939_session *j1939_xtp_rx_rts_session_new(struct j1939_priv *priv, struct j1939_sk_buff_cb skcb = *j1939_skb_to_cb(skb); struct j1939_session *session; const u8 *dat; + int len, ret; pgn_t pgn; - int len; netdev_dbg(priv->ndev, "%s\n", __func__); @@ -1653,7 +1653,22 @@ j1939_session *j1939_xtp_rx_rts_session_new(struct j1939_priv *priv, session->tskey = priv->rx_tskey++; j1939_sk_errqueue(session, J1939_ERRQUEUE_RX_RTS); - WARN_ON_ONCE(j1939_session_activate(session)); + ret = j1939_session_activate(session); + if (ret) { + /* Entering this scope indicates an issue with the J1939 bus. + * Possible scenarios include: + * - A time lapse occurred, and a new session was initiated + * due to another packet being sent correctly. This could + * have been caused by too long interrupt, debugger, or being + * out-scheduled by another task. + * - The bus is receiving numerous erroneous packets, either + * from a malfunctioning device or during a test scenario. + */ + netdev_alert(priv->ndev, "%s: 0x%p: concurrent session with same addr (%02x %02x) is already active.\n", + __func__, session, skcb.addr.sa, skcb.addr.da); + j1939_session_put(session); + return NULL; + } return session; } @@ -1681,6 +1696,8 @@ static int j1939_xtp_rx_rts_session_active(struct j1939_session *session, j1939_session_timers_cancel(session); j1939_session_cancel(session, J1939_XTP_ABORT_BUSY); + if (session->transmission) + j1939_session_deactivate_activate_next(session); return -EBUSY; } diff --git a/net/ceph/crush/mapper.c b/net/ceph/crush/mapper.c index 1daf95e17d67..3a5bd1cd1e99 100644 --- a/net/ceph/crush/mapper.c +++ b/net/ceph/crush/mapper.c @@ -429,7 +429,10 @@ static int is_out(const struct crush_map *map, /** * crush_choose_firstn - choose numrep distinct items of given type * @map: the crush_map + * @work: working space initialized by crush_init_workspace() * @bucket: the bucket we are choose an item from + * @weight: weight vector (for map leaves) + * @weight_max: size of weight vector * @x: crush input value * @numrep: the number of items to choose * @type: the type of item to choose @@ -445,6 +448,7 @@ static int is_out(const struct crush_map *map, * @vary_r: pass r to recursive calls * @out2: second output vector for leaf items (if @recurse_to_leaf) * @parent_r: r value passed from the parent + * @choose_args: weights and ids for each known bucket */ static int crush_choose_firstn(const struct crush_map *map, struct crush_work *work, @@ -636,9 +640,8 @@ reject: } -/** +/* * crush_choose_indep: alternative breadth-first positionally stable mapping - * */ static void crush_choose_indep(const struct crush_map *map, struct crush_work *work, diff --git a/net/ceph/mon_client.c b/net/ceph/mon_client.c index f263f7e91a21..ab66b599ac47 100644 --- a/net/ceph/mon_client.c +++ b/net/ceph/mon_client.c @@ -1085,13 +1085,19 @@ static void delayed_work(struct work_struct *work) struct ceph_mon_client *monc = container_of(work, struct ceph_mon_client, delayed_work.work); - dout("monc delayed_work\n"); mutex_lock(&monc->mutex); + dout("%s mon%d\n", __func__, monc->cur_mon); + if (monc->cur_mon < 0) { + goto out; + } + if (monc->hunting) { dout("%s continuing hunt\n", __func__); reopen_session(monc); } else { int is_auth = ceph_auth_is_authenticated(monc->auth); + + dout("%s is_authed %d\n", __func__, is_auth); if (ceph_con_keepalive_expired(&monc->con, CEPH_MONC_PING_TIMEOUT)) { dout("monc keepalive timeout\n"); @@ -1116,6 +1122,8 @@ static void delayed_work(struct work_struct *work) } } __schedule_delayed(monc); + +out: mutex_unlock(&monc->mutex); } @@ -1232,13 +1240,15 @@ EXPORT_SYMBOL(ceph_monc_init); void ceph_monc_stop(struct ceph_mon_client *monc) { dout("stop\n"); - cancel_delayed_work_sync(&monc->delayed_work); mutex_lock(&monc->mutex); __close_session(monc); + monc->hunting = false; monc->cur_mon = -1; mutex_unlock(&monc->mutex); + cancel_delayed_work_sync(&monc->delayed_work); + /* * flush msgr queue before we destroy ourselves to ensure that: * - any work that references our embedded con is finished. diff --git a/net/core/Makefile b/net/core/Makefile index 62be9aef2528..c3ebbaf9c81e 100644 --- a/net/core/Makefile +++ b/net/core/Makefile @@ -19,6 +19,7 @@ obj-$(CONFIG_NETDEV_ADDR_LIST_TEST) += dev_addr_lists_test.o obj-y += net-sysfs.o obj-y += hotdata.o +obj-y += netdev_rx_queue.o obj-$(CONFIG_PAGE_POOL) += page_pool.o page_pool_user.o obj-$(CONFIG_PROC_FS) += net-procfs.o obj-$(CONFIG_NET_PKTGEN) += pktgen.o @@ -43,3 +44,4 @@ obj-$(CONFIG_BPF_SYSCALL) += sock_map.o obj-$(CONFIG_BPF_SYSCALL) += bpf_sk_storage.o obj-$(CONFIG_OF) += of_net.o obj-$(CONFIG_NET_TEST) += net_test.o +obj-$(CONFIG_NET_DEVMEM) += devmem.o diff --git a/net/core/datagram.c b/net/core/datagram.c index e614cfd8e14a..f0693707aece 100644 --- a/net/core/datagram.c +++ b/net/core/datagram.c @@ -407,6 +407,9 @@ static int __skb_datagram_iter(const struct sk_buff *skb, int offset, return 0; } + if (!skb_frags_readable(skb)) + goto short_copy; + /* Copy paged appendix. Hmm... why does this look so complicated? */ for (i = 0; i < skb_shinfo(skb)->nr_frags; i++) { int end; @@ -416,15 +419,23 @@ static int __skb_datagram_iter(const struct sk_buff *skb, int offset, end = start + skb_frag_size(frag); if ((copy = end - offset) > 0) { - struct page *page = skb_frag_page(frag); - u8 *vaddr = kmap(page); + u32 p_off, p_len, copied; + struct page *p; + u8 *vaddr; if (copy > len) copy = len; - n = INDIRECT_CALL_1(cb, simple_copy_to_iter, - vaddr + skb_frag_off(frag) + offset - start, - copy, data, to); - kunmap(page); + + n = 0; + skb_frag_foreach_page(frag, + skb_frag_off(frag) + offset - start, + copy, p, p_off, p_len, copied) { + vaddr = kmap_local_page(p); + n += INDIRECT_CALL_1(cb, simple_copy_to_iter, + vaddr + p_off, p_len, data, to); + kunmap_local(vaddr); + } + offset += n; if (n != copy) goto short_copy; @@ -610,16 +621,13 @@ fault: } EXPORT_SYMBOL(skb_copy_datagram_from_iter); -int __zerocopy_sg_from_iter(struct msghdr *msg, struct sock *sk, - struct sk_buff *skb, struct iov_iter *from, - size_t length) +int zerocopy_fill_skb_from_iter(struct sk_buff *skb, + struct iov_iter *from, size_t length) { - int frag; + int frag = skb_shinfo(skb)->nr_frags; - if (msg && msg->msg_ubuf && msg->sg_from_iter) - return msg->sg_from_iter(sk, skb, from, length); - - frag = skb_shinfo(skb)->nr_frags; + if (!skb_frags_readable(skb)) + return -EFAULT; while (length && iov_iter_count(from)) { struct page *head, *last_head = NULL; @@ -627,7 +635,6 @@ int __zerocopy_sg_from_iter(struct msghdr *msg, struct sock *sk, int refs, order, n = 0; size_t start; ssize_t copied; - unsigned long truesize; if (frag == MAX_SKB_FRAGS) return -EMSGSIZE; @@ -639,17 +646,9 @@ int __zerocopy_sg_from_iter(struct msghdr *msg, struct sock *sk, length -= copied; - truesize = PAGE_ALIGN(copied + start); skb->data_len += copied; skb->len += copied; - skb->truesize += truesize; - if (sk && sk->sk_type == SOCK_STREAM) { - sk_wmem_queued_add(sk, truesize); - if (!skb_zcopy_pure(skb)) - sk_mem_charge(sk, truesize); - } else { - refcount_add(truesize, &skb->sk->sk_wmem_alloc); - } + skb->truesize += PAGE_ALIGN(copied + start); head = compound_head(pages[n]); order = compound_order(head); @@ -692,6 +691,30 @@ int __zerocopy_sg_from_iter(struct msghdr *msg, struct sock *sk, } return 0; } + +int __zerocopy_sg_from_iter(struct msghdr *msg, struct sock *sk, + struct sk_buff *skb, struct iov_iter *from, + size_t length) +{ + unsigned long orig_size = skb->truesize; + unsigned long truesize; + int ret; + + if (msg && msg->msg_ubuf && msg->sg_from_iter) + ret = msg->sg_from_iter(skb, from, length); + else + ret = zerocopy_fill_skb_from_iter(skb, from, length); + + truesize = skb->truesize - orig_size; + if (sk && sk->sk_type == SOCK_STREAM) { + sk_wmem_queued_add(sk, truesize); + if (!skb_zcopy_pure(skb)) + sk_mem_charge(sk, truesize); + } else { + refcount_add(truesize, &skb->sk->sk_wmem_alloc); + } + return ret; +} EXPORT_SYMBOL(__zerocopy_sg_from_iter); /** diff --git a/net/core/dev.c b/net/core/dev.c index 4d4de9008f6f..cd479f5f22f6 100644 --- a/net/core/dev.c +++ b/net/core/dev.c @@ -158,8 +158,10 @@ #include <net/page_pool/types.h> #include <net/page_pool/helpers.h> #include <net/rps.h> +#include <linux/phy_link_topology.h> #include "dev.h" +#include "devmem.h" #include "net-sysfs.h" static DEFINE_SPINLOCK(ptype_lock); @@ -229,7 +231,7 @@ static inline void backlog_lock_irq_save(struct softnet_data *sd, { if (IS_ENABLED(CONFIG_RPS) || use_backlog_threads()) spin_lock_irqsave(&sd->input_pkt_queue.lock, *flags); - else if (!IS_ENABLED(CONFIG_PREEMPT_RT)) + else local_irq_save(*flags); } @@ -237,7 +239,7 @@ static inline void backlog_lock_irq_disable(struct softnet_data *sd) { if (IS_ENABLED(CONFIG_RPS) || use_backlog_threads()) spin_lock_irq(&sd->input_pkt_queue.lock); - else if (!IS_ENABLED(CONFIG_PREEMPT_RT)) + else local_irq_disable(); } @@ -246,7 +248,7 @@ static inline void backlog_unlock_irq_restore(struct softnet_data *sd, { if (IS_ENABLED(CONFIG_RPS) || use_backlog_threads()) spin_unlock_irqrestore(&sd->input_pkt_queue.lock, *flags); - else if (!IS_ENABLED(CONFIG_PREEMPT_RT)) + else local_irq_restore(*flags); } @@ -254,7 +256,7 @@ static inline void backlog_unlock_irq_enable(struct softnet_data *sd) { if (IS_ENABLED(CONFIG_RPS) || use_backlog_threads()) spin_unlock_irq(&sd->input_pkt_queue.lock); - else if (!IS_ENABLED(CONFIG_PREEMPT_RT)) + else local_irq_enable(); } @@ -449,7 +451,9 @@ static RAW_NOTIFIER_HEAD(netdev_chain); * queue in the local softnet handler. */ -DEFINE_PER_CPU_ALIGNED(struct softnet_data, softnet_data); +DEFINE_PER_CPU_ALIGNED(struct softnet_data, softnet_data) = { + .process_queue_bh_lock = INIT_LOCAL_LOCK(process_queue_bh_lock), +}; EXPORT_PER_CPU_SYMBOL(softnet_data); /* Page_pool has a lockless array/stack to alloc/recycle pages. @@ -1226,9 +1230,9 @@ int dev_change_name(struct net_device *dev, const char *newname) memcpy(oldname, dev->name, IFNAMSIZ); - write_seqlock(&netdev_rename_lock); + write_seqlock_bh(&netdev_rename_lock); err = dev_get_valid_name(net, dev, newname); - write_sequnlock(&netdev_rename_lock); + write_sequnlock_bh(&netdev_rename_lock); if (err < 0) { up_write(&devnet_rename_sem); @@ -1269,9 +1273,9 @@ rollback: if (err >= 0) { err = ret; down_write(&devnet_rename_sem); - write_seqlock(&netdev_rename_lock); + write_seqlock_bh(&netdev_rename_lock); memcpy(dev->name, oldname, IFNAMSIZ); - write_sequnlock(&netdev_rename_lock); + write_sequnlock_bh(&netdev_rename_lock); memcpy(oldname, newname, IFNAMSIZ); WRITE_ONCE(dev->name_assign_type, old_assign_type); old_assign_type = NET_NAME_RENAMED; @@ -2160,7 +2164,7 @@ EXPORT_SYMBOL(net_disable_timestamp); static inline void net_timestamp_set(struct sk_buff *skb) { skb->tstamp = 0; - skb->mono_delivery_time = 0; + skb->tstamp_type = SKB_CLOCK_REALTIME; if (static_branch_unlikely(&netstamp_needed_key)) skb->tstamp = ktime_get_real(); } @@ -3308,6 +3312,10 @@ int skb_checksum_help(struct sk_buff *skb) return -EINVAL; } + if (!skb_frags_readable(skb)) { + return -EFAULT; + } + /* Before computing a checksum, we should make sure no frag could * be modified by an external entity : checksum could be wrong. */ @@ -3384,6 +3392,7 @@ int skb_crc32c_csum_help(struct sk_buff *skb) out: return ret; } +EXPORT_SYMBOL(skb_crc32c_csum_help); __be16 skb_network_protocol(struct sk_buff *skb, int *depth) { @@ -3429,8 +3438,9 @@ static int illegal_highdma(struct net_device *dev, struct sk_buff *skb) if (!(dev->features & NETIF_F_HIGHDMA)) { for (i = 0; i < skb_shinfo(skb)->nr_frags; i++) { skb_frag_t *frag = &skb_shinfo(skb)->frags[i]; + struct page *page = skb_frag_page(frag); - if (PageHighMem(skb_frag_page(frag))) + if (page && PageHighMem(page)) return 1; } } @@ -3703,7 +3713,7 @@ struct sk_buff *validate_xmit_skb_list(struct sk_buff *skb, struct net_device *d next = skb->next; skb_mark_not_on_list(skb); - /* in case skb wont be segmented, point to itself */ + /* in case skb won't be segmented, point to itself */ skb->prev = skb; skb = validate_xmit_skb(skb, dev, again); @@ -3940,6 +3950,7 @@ netdev_tx_queue_mapping(struct net_device *dev, struct sk_buff *skb) return netdev_get_tx_queue(dev, netdev_cap_txqueue(dev, qm)); } +#ifndef CONFIG_PREEMPT_RT static bool netdev_xmit_txqueue_skipped(void) { return __this_cpu_read(softnet_data.xmit.skip_txqueue); @@ -3950,6 +3961,19 @@ void netdev_xmit_skip_txqueue(bool skip) __this_cpu_write(softnet_data.xmit.skip_txqueue, skip); } EXPORT_SYMBOL_GPL(netdev_xmit_skip_txqueue); + +#else +static bool netdev_xmit_txqueue_skipped(void) +{ + return current->net_xmit.skip_txqueue; +} + +void netdev_xmit_skip_txqueue(bool skip) +{ + current->net_xmit.skip_txqueue = skip; +} +EXPORT_SYMBOL_GPL(netdev_xmit_skip_txqueue); +#endif #endif /* CONFIG_NET_EGRESS */ #ifdef CONFIG_NET_XGRESS @@ -4029,10 +4053,13 @@ sch_handle_ingress(struct sk_buff *skb, struct packet_type **pt_prev, int *ret, { struct bpf_mprog_entry *entry = rcu_dereference_bh(skb->dev->tcx_ingress); enum skb_drop_reason drop_reason = SKB_DROP_REASON_TC_INGRESS; + struct bpf_net_context __bpf_net_ctx, *bpf_net_ctx; int sch_ret; if (!entry) return skb; + + bpf_net_ctx = bpf_net_ctx_set(&__bpf_net_ctx); if (*pt_prev) { *ret = deliver_skb(skb, *pt_prev, orig_dev); *pt_prev = NULL; @@ -4061,10 +4088,12 @@ ingress_verdict: break; } *ret = NET_RX_SUCCESS; + bpf_net_ctx_clear(bpf_net_ctx); return NULL; case TC_ACT_SHOT: kfree_skb_reason(skb, drop_reason); *ret = NET_RX_DROP; + bpf_net_ctx_clear(bpf_net_ctx); return NULL; /* used by tc_run */ case TC_ACT_STOLEN: @@ -4074,8 +4103,10 @@ ingress_verdict: fallthrough; case TC_ACT_CONSUMED: *ret = NET_RX_SUCCESS; + bpf_net_ctx_clear(bpf_net_ctx); return NULL; } + bpf_net_ctx_clear(bpf_net_ctx); return skb; } @@ -4085,11 +4116,14 @@ sch_handle_egress(struct sk_buff *skb, int *ret, struct net_device *dev) { struct bpf_mprog_entry *entry = rcu_dereference_bh(dev->tcx_egress); enum skb_drop_reason drop_reason = SKB_DROP_REASON_TC_EGRESS; + struct bpf_net_context __bpf_net_ctx, *bpf_net_ctx; int sch_ret; if (!entry) return skb; + bpf_net_ctx = bpf_net_ctx_set(&__bpf_net_ctx); + /* qdisc_skb_cb(skb)->pkt_len & tcx_set_ingress() was * already set by the caller. */ @@ -4105,10 +4139,12 @@ egress_verdict: /* No need to push/pop skb's mac_header here on egress! */ skb_do_redirect(skb); *ret = NET_XMIT_SUCCESS; + bpf_net_ctx_clear(bpf_net_ctx); return NULL; case TC_ACT_SHOT: kfree_skb_reason(skb, drop_reason); *ret = NET_XMIT_DROP; + bpf_net_ctx_clear(bpf_net_ctx); return NULL; /* used by tc_run */ case TC_ACT_STOLEN: @@ -4118,8 +4154,10 @@ egress_verdict: fallthrough; case TC_ACT_CONSUMED: *ret = NET_XMIT_SUCCESS; + bpf_net_ctx_clear(bpf_net_ctx); return NULL; } + bpf_net_ctx_clear(bpf_net_ctx); return skb; } @@ -4215,13 +4253,6 @@ u16 dev_pick_tx_zero(struct net_device *dev, struct sk_buff *skb, } EXPORT_SYMBOL(dev_pick_tx_zero); -u16 dev_pick_tx_cpu_id(struct net_device *dev, struct sk_buff *skb, - struct net_device *sb_dev) -{ - return (u16)raw_smp_processor_id() % dev->real_num_tx_queues; -} -EXPORT_SYMBOL(dev_pick_tx_cpu_id); - u16 netdev_pick_tx(struct net_device *dev, struct sk_buff *skb, struct net_device *sb_dev) { @@ -5096,11 +5127,14 @@ static DEFINE_STATIC_KEY_FALSE(generic_xdp_needed_key); int do_xdp_generic(struct bpf_prog *xdp_prog, struct sk_buff **pskb) { + struct bpf_net_context __bpf_net_ctx, *bpf_net_ctx; + if (xdp_prog) { struct xdp_buff xdp; u32 act; int err; + bpf_net_ctx = bpf_net_ctx_set(&__bpf_net_ctx); act = netif_receive_generic_xdp(pskb, &xdp, xdp_prog); if (act != XDP_PASS) { switch (act) { @@ -5114,11 +5148,14 @@ int do_xdp_generic(struct bpf_prog *xdp_prog, struct sk_buff **pskb) generic_xdp_tx(*pskb, xdp_prog); break; } + bpf_net_ctx_clear(bpf_net_ctx); return XDP_DROP; } + bpf_net_ctx_clear(bpf_net_ctx); } return XDP_PASS; out_redir: + bpf_net_ctx_clear(bpf_net_ctx); kfree_skb_reason(*pskb, SKB_DROP_REASON_XDP); return XDP_DROP; } @@ -5212,7 +5249,7 @@ int netif_rx(struct sk_buff *skb) } EXPORT_SYMBOL(netif_rx); -static __latent_entropy void net_tx_action(struct softirq_action *h) +static __latent_entropy void net_tx_action(void) { struct softnet_data *sd = this_cpu_ptr(&softnet_data); @@ -5234,7 +5271,7 @@ static __latent_entropy void net_tx_action(struct softirq_action *h) trace_consume_skb(skb, net_tx_action); else trace_kfree_skb(skb, net_tx_action, - get_kfree_skb_cb(skb)->reason); + get_kfree_skb_cb(skb)->reason, NULL); if (skb->fclone != SKB_FCLONE_UNAVAILABLE) __kfree_skb(skb); @@ -5689,10 +5726,9 @@ static void __netif_receive_skb_list_core(struct list_head *head, bool pfmemallo struct packet_type *pt_curr = NULL; /* Current (common) orig_dev of sublist */ struct net_device *od_curr = NULL; - struct list_head sublist; struct sk_buff *skb, *next; + LIST_HEAD(sublist); - INIT_LIST_HEAD(&sublist); list_for_each_entry_safe(skb, next, head, list) { struct net_device *orig_dev = skb->dev; struct packet_type *pt_prev = NULL; @@ -5830,9 +5866,8 @@ static int netif_receive_skb_internal(struct sk_buff *skb) void netif_receive_skb_list_internal(struct list_head *head) { struct sk_buff *skb, *next; - struct list_head sublist; + LIST_HEAD(sublist); - INIT_LIST_HEAD(&sublist); list_for_each_entry_safe(skb, next, head, list) { net_timestamp_check(READ_ONCE(net_hotdata.tstamp_prequeue), skb); @@ -5935,6 +5970,7 @@ static void flush_backlog(struct work_struct *work) } backlog_unlock_irq_enable(sd); + local_lock_nested_bh(&softnet_data.process_queue_bh_lock); skb_queue_walk_safe(&sd->process_queue, skb, tmp) { if (skb->dev->reg_state == NETREG_UNREGISTERING) { __skb_unlink(skb, &sd->process_queue); @@ -5942,6 +5978,7 @@ static void flush_backlog(struct work_struct *work) rps_input_queue_head_incr(sd); } } + local_unlock_nested_bh(&softnet_data.process_queue_bh_lock); local_bh_enable(); } @@ -6063,7 +6100,9 @@ static int process_backlog(struct napi_struct *napi, int quota) while (again) { struct sk_buff *skb; + local_lock_nested_bh(&softnet_data.process_queue_bh_lock); while ((skb = __skb_dequeue(&sd->process_queue))) { + local_unlock_nested_bh(&softnet_data.process_queue_bh_lock); rcu_read_lock(); __netif_receive_skb(skb); rcu_read_unlock(); @@ -6072,7 +6111,9 @@ static int process_backlog(struct napi_struct *napi, int quota) return work; } + local_lock_nested_bh(&softnet_data.process_queue_bh_lock); } + local_unlock_nested_bh(&softnet_data.process_queue_bh_lock); backlog_lock_irq_disable(sd); if (skb_queue_empty(&sd->input_pkt_queue)) { @@ -6087,8 +6128,10 @@ static int process_backlog(struct napi_struct *napi, int quota) napi->state &= NAPIF_STATE_THREADED; again = false; } else { + local_lock_nested_bh(&softnet_data.process_queue_bh_lock); skb_queue_splice_tail_init(&sd->input_pkt_queue, &sd->process_queue); + local_unlock_nested_bh(&softnet_data.process_queue_bh_lock); } backlog_unlock_irq_enable(sd); } @@ -6301,6 +6344,7 @@ enum { static void busy_poll_stop(struct napi_struct *napi, void *have_poll_lock, unsigned flags, u16 budget) { + struct bpf_net_context __bpf_net_ctx, *bpf_net_ctx; bool skip_schedule = false; unsigned long timeout; int rc; @@ -6318,6 +6362,7 @@ static void busy_poll_stop(struct napi_struct *napi, void *have_poll_lock, clear_bit(NAPI_STATE_IN_BUSY_POLL, &napi->state); local_bh_disable(); + bpf_net_ctx = bpf_net_ctx_set(&__bpf_net_ctx); if (flags & NAPI_F_PREFER_BUSY_POLL) { napi->defer_hard_irqs_count = READ_ONCE(napi->dev->napi_defer_hard_irqs); @@ -6340,6 +6385,7 @@ static void busy_poll_stop(struct napi_struct *napi, void *have_poll_lock, netpoll_poll_unlock(have_poll_lock); if (rc == budget) __busy_poll_stop(napi, skip_schedule); + bpf_net_ctx_clear(bpf_net_ctx); local_bh_enable(); } @@ -6349,6 +6395,7 @@ static void __napi_busy_loop(unsigned int napi_id, { unsigned long start_time = loop_end ? busy_loop_current_time() : 0; int (*napi_poll)(struct napi_struct *napi, int budget); + struct bpf_net_context __bpf_net_ctx, *bpf_net_ctx; void *have_poll_lock = NULL; struct napi_struct *napi; @@ -6367,6 +6414,7 @@ restart: int work = 0; local_bh_disable(); + bpf_net_ctx = bpf_net_ctx_set(&__bpf_net_ctx); if (!napi_poll) { unsigned long val = READ_ONCE(napi->state); @@ -6397,6 +6445,7 @@ count: __NET_ADD_STATS(dev_net(napi->dev), LINUX_MIB_BUSYPOLLRXPACKETS, work); skb_defer_free_flush(this_cpu_ptr(&softnet_data)); + bpf_net_ctx_clear(bpf_net_ctx); local_bh_enable(); if (!loop_end || loop_end(loop_end_arg, start_time)) @@ -6824,6 +6873,7 @@ static int napi_thread_wait(struct napi_struct *napi) static void napi_threaded_poll_loop(struct napi_struct *napi) { + struct bpf_net_context __bpf_net_ctx, *bpf_net_ctx; struct softnet_data *sd; unsigned long last_qs = jiffies; @@ -6832,6 +6882,8 @@ static void napi_threaded_poll_loop(struct napi_struct *napi) void *have; local_bh_disable(); + bpf_net_ctx = bpf_net_ctx_set(&__bpf_net_ctx); + sd = this_cpu_ptr(&softnet_data); sd->in_napi_threaded_poll = true; @@ -6847,6 +6899,7 @@ static void napi_threaded_poll_loop(struct napi_struct *napi) net_rps_action_and_irq_enable(sd); } skb_defer_free_flush(sd); + bpf_net_ctx_clear(bpf_net_ctx); local_bh_enable(); if (!repoll) @@ -6867,15 +6920,17 @@ static int napi_threaded_poll(void *data) return 0; } -static __latent_entropy void net_rx_action(struct softirq_action *h) +static __latent_entropy void net_rx_action(void) { struct softnet_data *sd = this_cpu_ptr(&softnet_data); unsigned long time_limit = jiffies + usecs_to_jiffies(READ_ONCE(net_hotdata.netdev_budget_usecs)); + struct bpf_net_context __bpf_net_ctx, *bpf_net_ctx; int budget = READ_ONCE(net_hotdata.netdev_budget); LIST_HEAD(list); LIST_HEAD(repoll); + bpf_net_ctx = bpf_net_ctx_set(&__bpf_net_ctx); start: sd->in_net_rx_action = true; local_irq_disable(); @@ -6928,7 +6983,8 @@ start: sd->in_net_rx_action = false; net_rps_action_and_irq_enable(sd); -end:; +end: + bpf_net_ctx_clear(bpf_net_ctx); } struct netdev_adjacent { @@ -9215,7 +9271,7 @@ EXPORT_SYMBOL(netdev_port_same_parent_id); */ int dev_change_proto_down(struct net_device *dev, bool proto_down) { - if (!(dev->priv_flags & IFF_CHANGE_PROTO_DOWN)) + if (!dev->change_proto_down) return -EOPNOTSUPP; if (!netif_device_present(dev)) return -ENODEV; @@ -9312,6 +9368,20 @@ u8 dev_xdp_prog_count(struct net_device *dev) } EXPORT_SYMBOL_GPL(dev_xdp_prog_count); +int dev_xdp_propagate(struct net_device *dev, struct netdev_bpf *bpf) +{ + if (!dev->netdev_ops->ndo_bpf) + return -EOPNOTSUPP; + + if (dev_get_min_mp_channel_count(dev)) { + NL_SET_ERR_MSG(bpf->extack, "unable to propagate XDP to device using memory provider"); + return -EBUSY; + } + + return dev->netdev_ops->ndo_bpf(dev, bpf); +} +EXPORT_SYMBOL_GPL(dev_xdp_propagate); + u32 dev_xdp_prog_id(struct net_device *dev, enum bpf_xdp_mode mode) { struct bpf_prog *prog = dev_xdp_prog(dev, mode); @@ -9340,6 +9410,11 @@ static int dev_xdp_install(struct net_device *dev, enum bpf_xdp_mode mode, struct netdev_bpf xdp; int err; + if (dev_get_min_mp_channel_count(dev)) { + NL_SET_ERR_MSG(extack, "unable to install XDP to device using memory provider"); + return -EBUSY; + } + memset(&xdp, 0, sizeof(xdp)); xdp.command = mode == XDP_MODE_HW ? XDP_SETUP_PROG_HW : XDP_SETUP_PROG; xdp.extack = extack; @@ -9764,6 +9839,20 @@ err_out: return err; } +u32 dev_get_min_mp_channel_count(const struct net_device *dev) +{ + int i; + + ASSERT_RTNL(); + + for (i = dev->real_num_rx_queues - 1; i >= 0; i--) + if (dev->_rx[i].mp_params.mp_priv) + /* The channel count is the idx plus 1. */ + return i + 1; + + return 0; +} + /** * dev_index_reserve() - allocate an ifindex in a namespace * @net: the applicable net namespace @@ -9855,6 +9944,15 @@ static void netdev_sync_lower_features(struct net_device *upper, } } +static bool netdev_has_ip_or_hw_csum(netdev_features_t features) +{ + netdev_features_t ip_csum_mask = NETIF_F_IP_CSUM | NETIF_F_IPV6_CSUM; + bool ip_csum = (features & ip_csum_mask) == ip_csum_mask; + bool hw_csum = features & NETIF_F_HW_CSUM; + + return ip_csum || hw_csum; +} + static netdev_features_t netdev_fix_features(struct net_device *dev, netdev_features_t features) { @@ -9936,15 +10034,9 @@ static netdev_features_t netdev_fix_features(struct net_device *dev, features &= ~NETIF_F_LRO; } - if (features & NETIF_F_HW_TLS_TX) { - bool ip_csum = (features & (NETIF_F_IP_CSUM | NETIF_F_IPV6_CSUM)) == - (NETIF_F_IP_CSUM | NETIF_F_IPV6_CSUM); - bool hw_csum = features & NETIF_F_HW_CSUM; - - if (!ip_csum && !hw_csum) { - netdev_dbg(dev, "Dropping TLS TX HW offload feature since no CSUM feature.\n"); - features &= ~NETIF_F_HW_TLS_TX; - } + if ((features & NETIF_F_HW_TLS_TX) && !netdev_has_ip_or_hw_csum(features)) { + netdev_dbg(dev, "Dropping TLS TX HW offload feature since no CSUM feature.\n"); + features &= ~NETIF_F_HW_TLS_TX; } if ((features & NETIF_F_HW_TLS_RX) && !(features & NETIF_F_RXCSUM)) { @@ -9952,6 +10044,11 @@ static netdev_features_t netdev_fix_features(struct net_device *dev, features &= ~NETIF_F_HW_TLS_RX; } + if ((features & NETIF_F_GSO_UDP_L4) && !netdev_has_ip_or_hw_csum(features)) { + netdev_dbg(dev, "Dropping USO feature since no CSUM feature.\n"); + features &= ~NETIF_F_GSO_UDP_L4; + } + return features; } @@ -10256,6 +10353,17 @@ static void netdev_do_free_pcpu_stats(struct net_device *dev) } } +static void netdev_free_phy_link_topology(struct net_device *dev) +{ + struct phy_link_topology *topo = dev->link_topo; + + if (IS_ENABLED(CONFIG_PHYLIB) && topo) { + xa_destroy(&topo->phys); + kfree(topo); + dev->link_topo = NULL; + } +} + /** * register_netdevice() - register a network device * @dev: device to register @@ -10285,6 +10393,10 @@ int register_netdevice(struct net_device *dev) if (ret) return ret; + /* rss ctx ID 0 is reserved for the default context, start from 1 */ + xa_init_flags(&dev->ethtool->rss_ctx, XA_FLAGS_ALLOC1); + mutex_init(&dev->ethtool->rss_lock); + spin_lock_init(&dev->addr_list_lock); netdev_set_addr_lockdep_class(dev); @@ -10703,6 +10815,54 @@ void netdev_run_todo(void) wake_up(&netdev_unregistering_wq); } +/* Collate per-cpu network dstats statistics + * + * Read per-cpu network statistics from dev->dstats and populate the related + * fields in @s. + */ +static void dev_fetch_dstats(struct rtnl_link_stats64 *s, + const struct pcpu_dstats __percpu *dstats) +{ + int cpu; + + for_each_possible_cpu(cpu) { + u64 rx_packets, rx_bytes, rx_drops; + u64 tx_packets, tx_bytes, tx_drops; + const struct pcpu_dstats *stats; + unsigned int start; + + stats = per_cpu_ptr(dstats, cpu); + do { + start = u64_stats_fetch_begin(&stats->syncp); + rx_packets = u64_stats_read(&stats->rx_packets); + rx_bytes = u64_stats_read(&stats->rx_bytes); + rx_drops = u64_stats_read(&stats->rx_drops); + tx_packets = u64_stats_read(&stats->tx_packets); + tx_bytes = u64_stats_read(&stats->tx_bytes); + tx_drops = u64_stats_read(&stats->tx_drops); + } while (u64_stats_fetch_retry(&stats->syncp, start)); + + s->rx_packets += rx_packets; + s->rx_bytes += rx_bytes; + s->rx_dropped += rx_drops; + s->tx_packets += tx_packets; + s->tx_bytes += tx_bytes; + s->tx_dropped += tx_drops; + } +} + +/* ndo_get_stats64 implementation for dtstats-based accounting. + * + * Populate @s from dev->stats and dev->dstats. This is used internally by the + * core for NETDEV_PCPU_STAT_DSTAT-type stats collection. + */ +static void dev_get_dstats64(const struct net_device *dev, + struct rtnl_link_stats64 *s) +{ + netdev_stats_to_stats64(s, &dev->stats); + dev_fetch_dstats(s, dev->dstats); +} + /* Convert net_device_stats to rtnl_link_stats64. rtnl_link_stats64 has * all the same fields in the same order as net_device_stats, with only * the type differing, but rtnl_link_stats64 may have additional fields @@ -10751,7 +10911,7 @@ noinline void netdev_core_stats_inc(struct net_device *dev, u32 offset) return; } - field = (__force unsigned long __percpu *)((__force void *)p + offset); + field = (unsigned long __percpu *)((void __percpu *)p + offset); this_cpu_inc(*field); } EXPORT_SYMBOL_GPL(netdev_core_stats_inc); @@ -10779,6 +10939,8 @@ struct rtnl_link_stats64 *dev_get_stats(struct net_device *dev, netdev_stats_to_stats64(storage, ops->ndo_get_stats(dev)); } else if (dev->pcpu_stat_type == NETDEV_PCPU_STAT_TSTATS) { dev_get_tstats64(dev, storage); + } else if (dev->pcpu_stat_type == NETDEV_PCPU_STAT_DSTATS) { + dev_get_dstats64(dev, storage); } else { netdev_stats_to_stats64(storage, &dev->stats); } @@ -10896,13 +11058,6 @@ void netdev_sw_irq_coalesce_default_on(struct net_device *dev) } EXPORT_SYMBOL_GPL(netdev_sw_irq_coalesce_default_on); -void netdev_freemem(struct net_device *dev) -{ - char *addr = (char *)dev - dev->padded; - - kvfree(addr); -} - /** * alloc_netdev_mqs - allocate network device * @sizeof_priv: size of private data to allocate space for @@ -10922,8 +11077,6 @@ struct net_device *alloc_netdev_mqs(int sizeof_priv, const char *name, unsigned int txqs, unsigned int rxqs) { struct net_device *dev; - unsigned int alloc_size; - struct net_device *p; BUG_ON(strlen(name) >= sizeof(dev->name)); @@ -10937,21 +11090,12 @@ struct net_device *alloc_netdev_mqs(int sizeof_priv, const char *name, return NULL; } - alloc_size = sizeof(struct net_device); - if (sizeof_priv) { - /* ensure 32-byte alignment of private area */ - alloc_size = ALIGN(alloc_size, NETDEV_ALIGN); - alloc_size += sizeof_priv; - } - /* ensure 32-byte alignment of whole construct */ - alloc_size += NETDEV_ALIGN - 1; - - p = kvzalloc(alloc_size, GFP_KERNEL_ACCOUNT | __GFP_RETRY_MAYFAIL); - if (!p) + dev = kvzalloc(struct_size(dev, priv, sizeof_priv), + GFP_KERNEL_ACCOUNT | __GFP_RETRY_MAYFAIL); + if (!dev) return NULL; - dev = PTR_ALIGN(p, NETDEV_ALIGN); - dev->padded = (char *)dev - (char *)p; + dev->priv_len = sizeof_priv; ref_tracker_dir_init(&dev->refcnt_tracker, 128, name); #ifdef CONFIG_PCPU_DEV_REFCNT @@ -10998,6 +11142,7 @@ struct net_device *alloc_netdev_mqs(int sizeof_priv, const char *name, #ifdef CONFIG_NET_SCHED hash_init(dev->qdisc_hash); #endif + dev->priv_flags = IFF_XMIT_DST_RELEASE | IFF_XMIT_DST_RELEASE_PERM; setup(dev); @@ -11015,8 +11160,11 @@ struct net_device *alloc_netdev_mqs(int sizeof_priv, const char *name, dev->real_num_rx_queues = rxqs; if (netif_alloc_rx_queues(dev)) goto free_all; + dev->ethtool = kzalloc(sizeof(*dev->ethtool), GFP_KERNEL_ACCOUNT); + if (!dev->ethtool) + goto free_all; - strcpy(dev->name, name); + strscpy(dev->name, name); dev->name_assign_type = name_assign_type; dev->group = INIT_NETDEV_GROUP; if (!dev->ethtool_ops) @@ -11035,7 +11183,7 @@ free_pcpu: free_percpu(dev->pcpu_refcnt); free_dev: #endif - netdev_freemem(dev); + kvfree(dev); return NULL; } EXPORT_SYMBOL(alloc_netdev_mqs); @@ -11065,6 +11213,7 @@ void free_netdev(struct net_device *dev) return; } + kfree(dev->ethtool); netif_free_tx_queues(dev); netif_free_rx_queues(dev); @@ -11086,10 +11235,12 @@ void free_netdev(struct net_device *dev) free_percpu(dev->xdp_bulkq); dev->xdp_bulkq = NULL; + netdev_free_phy_link_topology(dev); + /* Compatibility with error handling in drivers */ if (dev->reg_state == NETREG_UNINITIALIZED || dev->reg_state == NETREG_DUMMY) { - netdev_freemem(dev); + kvfree(dev); return; } @@ -11130,6 +11281,34 @@ void synchronize_net(void) } EXPORT_SYMBOL(synchronize_net); +static void netdev_rss_contexts_free(struct net_device *dev) +{ + struct ethtool_rxfh_context *ctx; + unsigned long context; + + mutex_lock(&dev->ethtool->rss_lock); + xa_for_each(&dev->ethtool->rss_ctx, context, ctx) { + struct ethtool_rxfh_param rxfh; + + rxfh.indir = ethtool_rxfh_context_indir(ctx); + rxfh.key = ethtool_rxfh_context_key(ctx); + rxfh.hfunc = ctx->hfunc; + rxfh.input_xfrm = ctx->input_xfrm; + rxfh.rss_context = context; + rxfh.rss_delete = true; + + xa_erase(&dev->ethtool->rss_ctx, context); + if (dev->ethtool_ops->create_rxfh_context) + dev->ethtool_ops->remove_rxfh_context(dev, ctx, + context, NULL); + else + dev->ethtool_ops->set_rxfh(dev, &rxfh, NULL); + kfree(ctx); + } + xa_destroy(&dev->ethtool->rss_ctx); + mutex_unlock(&dev->ethtool->rss_lock); +} + /** * unregister_netdevice_queue - remove device from the kernel * @dev: device @@ -11210,6 +11389,7 @@ void unregister_netdevice_many_notify(struct list_head *head, dev_tcx_uninstall(dev); dev_xdp_uninstall(dev); bpf_dev_bound_netdev_unregister(dev); + dev_dmabuf_uninstall(dev); netdev_offload_xstats_disable_all(dev); @@ -11233,11 +11413,15 @@ void unregister_netdevice_many_notify(struct list_head *head, netdev_name_node_alt_flush(dev); netdev_name_node_free(dev->name_node); + netdev_rss_contexts_free(dev); + call_netdevice_notifiers(NETDEV_PRE_UNINIT, dev); if (dev->netdev_ops->ndo_uninit) dev->netdev_ops->ndo_uninit(dev); + mutex_destroy(&dev->ethtool->rss_lock); + if (skb) rtmsg_ifinfo_send(skb, dev, GFP_KERNEL, portid, nlh); @@ -11270,7 +11454,7 @@ void unregister_netdevice_many_notify(struct list_head *head, * @head: list of devices * * Note: As most callers use a stack allocated list_head, - * we force a list_del() to make sure stack wont be corrupted later. + * we force a list_del() to make sure stack won't be corrupted later. */ void unregister_netdevice_many(struct list_head *head) { @@ -11325,10 +11509,10 @@ int __dev_change_net_namespace(struct net_device *dev, struct net *net, /* Don't allow namespace local devices to be moved. */ err = -EINVAL; - if (dev->features & NETIF_F_NETNS_LOCAL) + if (dev->netns_local) goto out; - /* Ensure the device has been registrered */ + /* Ensure the device has been registered */ if (dev->reg_state != NETREG_REGISTERED) goto out; @@ -11419,9 +11603,9 @@ int __dev_change_net_namespace(struct net_device *dev, struct net *net, if (new_name[0]) { /* Rename the netdev to prepared name */ - write_seqlock(&netdev_rename_lock); + write_seqlock_bh(&netdev_rename_lock); strscpy(dev->name, new_name, IFNAMSIZ); - write_sequnlock(&netdev_rename_lock); + write_sequnlock_bh(&netdev_rename_lock); } /* Fixup kobjects */ @@ -11707,7 +11891,7 @@ static void __net_exit default_device_exit_net(struct net *net) char fb_name[IFNAMSIZ]; /* Ignore unmoveable devices (i.e. loopback) */ - if (dev->features & NETIF_F_NETNS_LOCAL) + if (dev->netns_local) continue; /* Leave virtual devices for the generic cleanup */ @@ -11768,7 +11952,7 @@ static struct pernet_operations __net_initdata default_device_ops = { static void __init net_dev_struct_check(void) { /* TX read-mostly hotpath */ - CACHELINE_ASSERT_GROUP_MEMBER(struct net_device, net_device_read_tx, priv_flags); + CACHELINE_ASSERT_GROUP_MEMBER(struct net_device, net_device_read_tx, priv_flags_fast); CACHELINE_ASSERT_GROUP_MEMBER(struct net_device, net_device_read_tx, netdev_ops); CACHELINE_ASSERT_GROUP_MEMBER(struct net_device, net_device_read_tx, header_ops); CACHELINE_ASSERT_GROUP_MEMBER(struct net_device, net_device_read_tx, _tx); diff --git a/net/core/dev.h b/net/core/dev.h index b7b518bc2be5..5654325c5b71 100644 --- a/net/core/dev.h +++ b/net/core/dev.h @@ -150,6 +150,8 @@ struct napi_struct *napi_by_id(unsigned int napi_id); void kick_defer_list_purge(struct softnet_data *sd, unsigned int cpu); #define XMIT_RECURSION_LIMIT 8 + +#ifndef CONFIG_PREEMPT_RT static inline bool dev_xmit_recursion(void) { return unlikely(__this_cpu_read(softnet_data.xmit.recursion) > @@ -165,5 +167,25 @@ static inline void dev_xmit_recursion_dec(void) { __this_cpu_dec(softnet_data.xmit.recursion); } +#else +static inline bool dev_xmit_recursion(void) +{ + return unlikely(current->net_xmit.recursion > XMIT_RECURSION_LIMIT); +} + +static inline void dev_xmit_recursion_inc(void) +{ + current->net_xmit.recursion++; +} + +static inline void dev_xmit_recursion_dec(void) +{ + current->net_xmit.recursion--; +} +#endif + +int dev_set_hwtstamp_phylib(struct net_device *dev, + struct kernel_hwtstamp_config *cfg, + struct netlink_ext_ack *extack); #endif diff --git a/net/core/dev_addr_lists.c b/net/core/dev_addr_lists.c index baa63dee2829..166e404f7c03 100644 --- a/net/core/dev_addr_lists.c +++ b/net/core/dev_addr_lists.c @@ -262,7 +262,7 @@ static int __hw_addr_sync_multiple(struct netdev_hw_addr_list *to_list, } /* This function only works where there is a strict 1-1 relationship - * between source and destionation of they synch. If you ever need to + * between source and destination of they synch. If you ever need to * sync addresses to more then 1 destination, you need to use * __hw_addr_sync_multiple(). */ @@ -299,8 +299,8 @@ void __hw_addr_unsync(struct netdev_hw_addr_list *to_list, EXPORT_SYMBOL(__hw_addr_unsync); /** - * __hw_addr_sync_dev - Synchonize device's multicast list - * @list: address list to syncronize + * __hw_addr_sync_dev - Synchronize device's multicast list + * @list: address list to synchronize * @dev: device to sync * @sync: function to call if address should be added * @unsync: function to call if address should be removed diff --git a/net/core/dev_ioctl.c b/net/core/dev_ioctl.c index 9a66cf5015f2..473c437b6b53 100644 --- a/net/core/dev_ioctl.c +++ b/net/core/dev_ioctl.c @@ -259,9 +259,7 @@ static int dev_eth_ioctl(struct net_device *dev, * @dev: Network device * @cfg: Timestamping configuration structure * - * Helper for enforcing a common policy that phylib timestamping, if available, - * should take precedence in front of hardware timestamping provided by the - * netdev. + * Helper for calling the default hardware provider timestamping. * * Note: phy_mii_ioctl() only handles SIOCSHWTSTAMP (not SIOCGHWTSTAMP), and * there only exists a phydev->mii_ts->hwtstamp() method. So this will return @@ -271,7 +269,7 @@ static int dev_eth_ioctl(struct net_device *dev, static int dev_get_hwtstamp_phylib(struct net_device *dev, struct kernel_hwtstamp_config *cfg) { - if (phy_has_hwtstamp(dev->phydev)) + if (phy_is_default_hwtstamp(dev->phydev)) return phy_hwtstamp_get(dev->phydev, cfg); return dev->netdev_ops->ndo_hwtstamp_get(dev, cfg); @@ -319,28 +317,27 @@ static int dev_get_hwtstamp(struct net_device *dev, struct ifreq *ifr) * should take precedence in front of hardware timestamping provided by the * netdev. If the netdev driver needs to perform specific actions even for PHY * timestamping to work properly (a switch port must trap the timestamped - * frames and not forward them), it must set IFF_SEE_ALL_HWTSTAMP_REQUESTS in - * dev->priv_flags. + * frames and not forward them), it must set dev->see_all_hwtstamp_requests. */ int dev_set_hwtstamp_phylib(struct net_device *dev, struct kernel_hwtstamp_config *cfg, struct netlink_ext_ack *extack) { const struct net_device_ops *ops = dev->netdev_ops; - bool phy_ts = phy_has_hwtstamp(dev->phydev); + bool phy_ts = phy_is_default_hwtstamp(dev->phydev); struct kernel_hwtstamp_config old_cfg = {}; bool changed = false; int err; cfg->source = phy_ts ? HWTSTAMP_SOURCE_PHYLIB : HWTSTAMP_SOURCE_NETDEV; - if (phy_ts && (dev->priv_flags & IFF_SEE_ALL_HWTSTAMP_REQUESTS)) { + if (phy_ts && dev->see_all_hwtstamp_requests) { err = ops->ndo_hwtstamp_get(dev, &old_cfg); if (err) return err; } - if (!phy_ts || (dev->priv_flags & IFF_SEE_ALL_HWTSTAMP_REQUESTS)) { + if (!phy_ts || dev->see_all_hwtstamp_requests) { err = ops->ndo_hwtstamp_set(dev, cfg, extack); if (err) { if (extack->_msg) @@ -349,7 +346,7 @@ int dev_set_hwtstamp_phylib(struct net_device *dev, } } - if (phy_ts && (dev->priv_flags & IFF_SEE_ALL_HWTSTAMP_REQUESTS)) + if (phy_ts && dev->see_all_hwtstamp_requests) changed = kernel_hwtstamp_config_changed(&old_cfg, cfg); if (phy_ts) { @@ -363,7 +360,6 @@ int dev_set_hwtstamp_phylib(struct net_device *dev, return 0; } -EXPORT_SYMBOL_GPL(dev_set_hwtstamp_phylib); static int dev_set_hwtstamp(struct net_device *dev, struct ifreq *ifr) { diff --git a/net/core/devmem.c b/net/core/devmem.c new file mode 100644 index 000000000000..11b91c12ee11 --- /dev/null +++ b/net/core/devmem.c @@ -0,0 +1,389 @@ +// SPDX-License-Identifier: GPL-2.0-or-later +/* + * Devmem TCP + * + * Authors: Mina Almasry <almasrymina@google.com> + * Willem de Bruijn <willemdebruijn.kernel@gmail.com> + * Kaiyuan Zhang <kaiyuanz@google.com + */ + +#include <linux/dma-buf.h> +#include <linux/genalloc.h> +#include <linux/mm.h> +#include <linux/netdevice.h> +#include <linux/types.h> +#include <net/netdev_queues.h> +#include <net/netdev_rx_queue.h> +#include <net/page_pool/helpers.h> +#include <trace/events/page_pool.h> + +#include "devmem.h" +#include "mp_dmabuf_devmem.h" +#include "page_pool_priv.h" + +/* Device memory support */ + +/* Protected by rtnl_lock() */ +static DEFINE_XARRAY_FLAGS(net_devmem_dmabuf_bindings, XA_FLAGS_ALLOC1); + +static void net_devmem_dmabuf_free_chunk_owner(struct gen_pool *genpool, + struct gen_pool_chunk *chunk, + void *not_used) +{ + struct dmabuf_genpool_chunk_owner *owner = chunk->owner; + + kvfree(owner->niovs); + kfree(owner); +} + +static dma_addr_t net_devmem_get_dma_addr(const struct net_iov *niov) +{ + struct dmabuf_genpool_chunk_owner *owner = net_iov_owner(niov); + + return owner->base_dma_addr + + ((dma_addr_t)net_iov_idx(niov) << PAGE_SHIFT); +} + +void __net_devmem_dmabuf_binding_free(struct net_devmem_dmabuf_binding *binding) +{ + size_t size, avail; + + gen_pool_for_each_chunk(binding->chunk_pool, + net_devmem_dmabuf_free_chunk_owner, NULL); + + size = gen_pool_size(binding->chunk_pool); + avail = gen_pool_avail(binding->chunk_pool); + + if (!WARN(size != avail, "can't destroy genpool. size=%zu, avail=%zu", + size, avail)) + gen_pool_destroy(binding->chunk_pool); + + dma_buf_unmap_attachment_unlocked(binding->attachment, binding->sgt, + DMA_FROM_DEVICE); + dma_buf_detach(binding->dmabuf, binding->attachment); + dma_buf_put(binding->dmabuf); + xa_destroy(&binding->bound_rxqs); + kfree(binding); +} + +struct net_iov * +net_devmem_alloc_dmabuf(struct net_devmem_dmabuf_binding *binding) +{ + struct dmabuf_genpool_chunk_owner *owner; + unsigned long dma_addr; + struct net_iov *niov; + ssize_t offset; + ssize_t index; + + dma_addr = gen_pool_alloc_owner(binding->chunk_pool, PAGE_SIZE, + (void **)&owner); + if (!dma_addr) + return NULL; + + offset = dma_addr - owner->base_dma_addr; + index = offset / PAGE_SIZE; + niov = &owner->niovs[index]; + + niov->pp_magic = 0; + niov->pp = NULL; + atomic_long_set(&niov->pp_ref_count, 0); + + return niov; +} + +void net_devmem_free_dmabuf(struct net_iov *niov) +{ + struct net_devmem_dmabuf_binding *binding = net_iov_binding(niov); + unsigned long dma_addr = net_devmem_get_dma_addr(niov); + + if (WARN_ON(!gen_pool_has_addr(binding->chunk_pool, dma_addr, + PAGE_SIZE))) + return; + + gen_pool_free(binding->chunk_pool, dma_addr, PAGE_SIZE); +} + +void net_devmem_unbind_dmabuf(struct net_devmem_dmabuf_binding *binding) +{ + struct netdev_rx_queue *rxq; + unsigned long xa_idx; + unsigned int rxq_idx; + + if (binding->list.next) + list_del(&binding->list); + + xa_for_each(&binding->bound_rxqs, xa_idx, rxq) { + WARN_ON(rxq->mp_params.mp_priv != binding); + + rxq->mp_params.mp_priv = NULL; + + rxq_idx = get_netdev_rx_queue_index(rxq); + + WARN_ON(netdev_rx_queue_restart(binding->dev, rxq_idx)); + } + + xa_erase(&net_devmem_dmabuf_bindings, binding->id); + + net_devmem_dmabuf_binding_put(binding); +} + +int net_devmem_bind_dmabuf_to_queue(struct net_device *dev, u32 rxq_idx, + struct net_devmem_dmabuf_binding *binding, + struct netlink_ext_ack *extack) +{ + struct netdev_rx_queue *rxq; + u32 xa_idx; + int err; + + if (rxq_idx >= dev->real_num_rx_queues) { + NL_SET_ERR_MSG(extack, "rx queue index out of range"); + return -ERANGE; + } + + rxq = __netif_get_rx_queue(dev, rxq_idx); + if (rxq->mp_params.mp_priv) { + NL_SET_ERR_MSG(extack, "designated queue already memory provider bound"); + return -EEXIST; + } + +#ifdef CONFIG_XDP_SOCKETS + if (rxq->pool) { + NL_SET_ERR_MSG(extack, "designated queue already in use by AF_XDP"); + return -EBUSY; + } +#endif + + err = xa_alloc(&binding->bound_rxqs, &xa_idx, rxq, xa_limit_32b, + GFP_KERNEL); + if (err) + return err; + + rxq->mp_params.mp_priv = binding; + + err = netdev_rx_queue_restart(dev, rxq_idx); + if (err) + goto err_xa_erase; + + return 0; + +err_xa_erase: + rxq->mp_params.mp_priv = NULL; + xa_erase(&binding->bound_rxqs, xa_idx); + + return err; +} + +struct net_devmem_dmabuf_binding * +net_devmem_bind_dmabuf(struct net_device *dev, unsigned int dmabuf_fd, + struct netlink_ext_ack *extack) +{ + struct net_devmem_dmabuf_binding *binding; + static u32 id_alloc_next; + struct scatterlist *sg; + struct dma_buf *dmabuf; + unsigned int sg_idx, i; + unsigned long virtual; + int err; + + dmabuf = dma_buf_get(dmabuf_fd); + if (IS_ERR(dmabuf)) + return ERR_CAST(dmabuf); + + binding = kzalloc_node(sizeof(*binding), GFP_KERNEL, + dev_to_node(&dev->dev)); + if (!binding) { + err = -ENOMEM; + goto err_put_dmabuf; + } + + binding->dev = dev; + + err = xa_alloc_cyclic(&net_devmem_dmabuf_bindings, &binding->id, + binding, xa_limit_32b, &id_alloc_next, + GFP_KERNEL); + if (err < 0) + goto err_free_binding; + + xa_init_flags(&binding->bound_rxqs, XA_FLAGS_ALLOC); + + refcount_set(&binding->ref, 1); + + binding->dmabuf = dmabuf; + + binding->attachment = dma_buf_attach(binding->dmabuf, dev->dev.parent); + if (IS_ERR(binding->attachment)) { + err = PTR_ERR(binding->attachment); + NL_SET_ERR_MSG(extack, "Failed to bind dmabuf to device"); + goto err_free_id; + } + + binding->sgt = dma_buf_map_attachment_unlocked(binding->attachment, + DMA_FROM_DEVICE); + if (IS_ERR(binding->sgt)) { + err = PTR_ERR(binding->sgt); + NL_SET_ERR_MSG(extack, "Failed to map dmabuf attachment"); + goto err_detach; + } + + /* For simplicity we expect to make PAGE_SIZE allocations, but the + * binding can be much more flexible than that. We may be able to + * allocate MTU sized chunks here. Leave that for future work... + */ + binding->chunk_pool = + gen_pool_create(PAGE_SHIFT, dev_to_node(&dev->dev)); + if (!binding->chunk_pool) { + err = -ENOMEM; + goto err_unmap; + } + + virtual = 0; + for_each_sgtable_dma_sg(binding->sgt, sg, sg_idx) { + dma_addr_t dma_addr = sg_dma_address(sg); + struct dmabuf_genpool_chunk_owner *owner; + size_t len = sg_dma_len(sg); + struct net_iov *niov; + + owner = kzalloc_node(sizeof(*owner), GFP_KERNEL, + dev_to_node(&dev->dev)); + if (!owner) { + err = -ENOMEM; + goto err_free_chunks; + } + + owner->base_virtual = virtual; + owner->base_dma_addr = dma_addr; + owner->num_niovs = len / PAGE_SIZE; + owner->binding = binding; + + err = gen_pool_add_owner(binding->chunk_pool, dma_addr, + dma_addr, len, dev_to_node(&dev->dev), + owner); + if (err) { + kfree(owner); + err = -EINVAL; + goto err_free_chunks; + } + + owner->niovs = kvmalloc_array(owner->num_niovs, + sizeof(*owner->niovs), + GFP_KERNEL); + if (!owner->niovs) { + err = -ENOMEM; + goto err_free_chunks; + } + + for (i = 0; i < owner->num_niovs; i++) { + niov = &owner->niovs[i]; + niov->owner = owner; + page_pool_set_dma_addr_netmem(net_iov_to_netmem(niov), + net_devmem_get_dma_addr(niov)); + } + + virtual += len; + } + + return binding; + +err_free_chunks: + gen_pool_for_each_chunk(binding->chunk_pool, + net_devmem_dmabuf_free_chunk_owner, NULL); + gen_pool_destroy(binding->chunk_pool); +err_unmap: + dma_buf_unmap_attachment_unlocked(binding->attachment, binding->sgt, + DMA_FROM_DEVICE); +err_detach: + dma_buf_detach(dmabuf, binding->attachment); +err_free_id: + xa_erase(&net_devmem_dmabuf_bindings, binding->id); +err_free_binding: + kfree(binding); +err_put_dmabuf: + dma_buf_put(dmabuf); + return ERR_PTR(err); +} + +void dev_dmabuf_uninstall(struct net_device *dev) +{ + struct net_devmem_dmabuf_binding *binding; + struct netdev_rx_queue *rxq; + unsigned long xa_idx; + unsigned int i; + + for (i = 0; i < dev->real_num_rx_queues; i++) { + binding = dev->_rx[i].mp_params.mp_priv; + if (!binding) + continue; + + xa_for_each(&binding->bound_rxqs, xa_idx, rxq) + if (rxq == &dev->_rx[i]) { + xa_erase(&binding->bound_rxqs, xa_idx); + break; + } + } +} + +/*** "Dmabuf devmem memory provider" ***/ + +int mp_dmabuf_devmem_init(struct page_pool *pool) +{ + struct net_devmem_dmabuf_binding *binding = pool->mp_priv; + + if (!binding) + return -EINVAL; + + if (!pool->dma_map) + return -EOPNOTSUPP; + + if (pool->dma_sync) + return -EOPNOTSUPP; + + if (pool->p.order != 0) + return -E2BIG; + + net_devmem_dmabuf_binding_get(binding); + return 0; +} + +netmem_ref mp_dmabuf_devmem_alloc_netmems(struct page_pool *pool, gfp_t gfp) +{ + struct net_devmem_dmabuf_binding *binding = pool->mp_priv; + struct net_iov *niov; + netmem_ref netmem; + + niov = net_devmem_alloc_dmabuf(binding); + if (!niov) + return 0; + + netmem = net_iov_to_netmem(niov); + + page_pool_set_pp_info(pool, netmem); + + pool->pages_state_hold_cnt++; + trace_page_pool_state_hold(pool, netmem, pool->pages_state_hold_cnt); + return netmem; +} + +void mp_dmabuf_devmem_destroy(struct page_pool *pool) +{ + struct net_devmem_dmabuf_binding *binding = pool->mp_priv; + + net_devmem_dmabuf_binding_put(binding); +} + +bool mp_dmabuf_devmem_release_page(struct page_pool *pool, netmem_ref netmem) +{ + long refcount = atomic_long_read(netmem_get_pp_ref_count_ref(netmem)); + + if (WARN_ON_ONCE(!netmem_is_net_iov(netmem))) + return false; + + if (WARN_ON_ONCE(refcount != 1)) + return false; + + page_pool_clear_pp_info(netmem); + + net_devmem_free_dmabuf(netmem_to_net_iov(netmem)); + + /* We don't want the page pool put_page()ing our net_iovs. */ + return false; +} diff --git a/net/core/devmem.h b/net/core/devmem.h new file mode 100644 index 000000000000..76099ef9c482 --- /dev/null +++ b/net/core/devmem.h @@ -0,0 +1,180 @@ +/* SPDX-License-Identifier: GPL-2.0-or-later */ +/* + * Device memory TCP support + * + * Authors: Mina Almasry <almasrymina@google.com> + * Willem de Bruijn <willemb@google.com> + * Kaiyuan Zhang <kaiyuanz@google.com> + * + */ +#ifndef _NET_DEVMEM_H +#define _NET_DEVMEM_H + +struct netlink_ext_ack; + +struct net_devmem_dmabuf_binding { + struct dma_buf *dmabuf; + struct dma_buf_attachment *attachment; + struct sg_table *sgt; + struct net_device *dev; + struct gen_pool *chunk_pool; + + /* The user holds a ref (via the netlink API) for as long as they want + * the binding to remain alive. Each page pool using this binding holds + * a ref to keep the binding alive. Each allocated net_iov holds a + * ref. + * + * The binding undos itself and unmaps the underlying dmabuf once all + * those refs are dropped and the binding is no longer desired or in + * use. + */ + refcount_t ref; + + /* The list of bindings currently active. Used for netlink to notify us + * of the user dropping the bind. + */ + struct list_head list; + + /* rxq's this binding is active on. */ + struct xarray bound_rxqs; + + /* ID of this binding. Globally unique to all bindings currently + * active. + */ + u32 id; +}; + +#if defined(CONFIG_NET_DEVMEM) +/* Owner of the dma-buf chunks inserted into the gen pool. Each scatterlist + * entry from the dmabuf is inserted into the genpool as a chunk, and needs + * this owner struct to keep track of some metadata necessary to create + * allocations from this chunk. + */ +struct dmabuf_genpool_chunk_owner { + /* Offset into the dma-buf where this chunk starts. */ + unsigned long base_virtual; + + /* dma_addr of the start of the chunk. */ + dma_addr_t base_dma_addr; + + /* Array of net_iovs for this chunk. */ + struct net_iov *niovs; + size_t num_niovs; + + struct net_devmem_dmabuf_binding *binding; +}; + +void __net_devmem_dmabuf_binding_free(struct net_devmem_dmabuf_binding *binding); +struct net_devmem_dmabuf_binding * +net_devmem_bind_dmabuf(struct net_device *dev, unsigned int dmabuf_fd, + struct netlink_ext_ack *extack); +void net_devmem_unbind_dmabuf(struct net_devmem_dmabuf_binding *binding); +int net_devmem_bind_dmabuf_to_queue(struct net_device *dev, u32 rxq_idx, + struct net_devmem_dmabuf_binding *binding, + struct netlink_ext_ack *extack); +void dev_dmabuf_uninstall(struct net_device *dev); + +static inline struct dmabuf_genpool_chunk_owner * +net_iov_owner(const struct net_iov *niov) +{ + return niov->owner; +} + +static inline unsigned int net_iov_idx(const struct net_iov *niov) +{ + return niov - net_iov_owner(niov)->niovs; +} + +static inline struct net_devmem_dmabuf_binding * +net_iov_binding(const struct net_iov *niov) +{ + return net_iov_owner(niov)->binding; +} + +static inline unsigned long net_iov_virtual_addr(const struct net_iov *niov) +{ + struct dmabuf_genpool_chunk_owner *owner = net_iov_owner(niov); + + return owner->base_virtual + + ((unsigned long)net_iov_idx(niov) << PAGE_SHIFT); +} + +static inline u32 net_iov_binding_id(const struct net_iov *niov) +{ + return net_iov_owner(niov)->binding->id; +} + +static inline void +net_devmem_dmabuf_binding_get(struct net_devmem_dmabuf_binding *binding) +{ + refcount_inc(&binding->ref); +} + +static inline void +net_devmem_dmabuf_binding_put(struct net_devmem_dmabuf_binding *binding) +{ + if (!refcount_dec_and_test(&binding->ref)) + return; + + __net_devmem_dmabuf_binding_free(binding); +} + +struct net_iov * +net_devmem_alloc_dmabuf(struct net_devmem_dmabuf_binding *binding); +void net_devmem_free_dmabuf(struct net_iov *ppiov); + +#else +struct net_devmem_dmabuf_binding; + +static inline void +__net_devmem_dmabuf_binding_free(struct net_devmem_dmabuf_binding *binding) +{ +} + +static inline struct net_devmem_dmabuf_binding * +net_devmem_bind_dmabuf(struct net_device *dev, unsigned int dmabuf_fd, + struct netlink_ext_ack *extack) +{ + return ERR_PTR(-EOPNOTSUPP); +} + +static inline void +net_devmem_unbind_dmabuf(struct net_devmem_dmabuf_binding *binding) +{ +} + +static inline int +net_devmem_bind_dmabuf_to_queue(struct net_device *dev, u32 rxq_idx, + struct net_devmem_dmabuf_binding *binding, + struct netlink_ext_ack *extack) + +{ + return -EOPNOTSUPP; +} + +static inline void dev_dmabuf_uninstall(struct net_device *dev) +{ +} + +static inline struct net_iov * +net_devmem_alloc_dmabuf(struct net_devmem_dmabuf_binding *binding) +{ + return NULL; +} + +static inline void net_devmem_free_dmabuf(struct net_iov *ppiov) +{ +} + +static inline unsigned long net_iov_virtual_addr(const struct net_iov *niov) +{ + return 0; +} + +static inline u32 net_iov_binding_id(const struct net_iov *niov) +{ + return 0; +} +#endif + +#endif /* _NET_DEVMEM_H */ diff --git a/net/core/drop_monitor.c b/net/core/drop_monitor.c index 430ed18f8584..2e0ae3328232 100644 --- a/net/core/drop_monitor.c +++ b/net/core/drop_monitor.c @@ -109,7 +109,8 @@ static u32 net_dm_queue_len = 1000; struct net_dm_alert_ops { void (*kfree_skb_probe)(void *ignore, struct sk_buff *skb, void *location, - enum skb_drop_reason reason); + enum skb_drop_reason reason, + struct sock *rx_sk); void (*napi_poll_probe)(void *ignore, struct napi_struct *napi, int work, int budget); void (*work_item_func)(struct work_struct *work); @@ -264,7 +265,8 @@ out: static void trace_kfree_skb_hit(void *ignore, struct sk_buff *skb, void *location, - enum skb_drop_reason reason) + enum skb_drop_reason reason, + struct sock *rx_sk) { trace_drop_common(skb, location); } @@ -491,7 +493,8 @@ static const struct net_dm_alert_ops net_dm_alert_summary_ops = { static void net_dm_packet_trace_kfree_skb_hit(void *ignore, struct sk_buff *skb, void *location, - enum skb_drop_reason reason) + enum skb_drop_reason reason, + struct sock *rx_sk) { ktime_t tstamp = ktime_get_real(); struct per_cpu_dm_data *data; diff --git a/net/core/fib_rules.c b/net/core/fib_rules.c index 6ebffbc63236..154a2681f55c 100644 --- a/net/core/fib_rules.c +++ b/net/core/fib_rules.c @@ -11,6 +11,7 @@ #include <linux/list.h> #include <linux/module.h> #include <net/net_namespace.h> +#include <net/inet_dscp.h> #include <net/sock.h> #include <net/fib_rules.h> #include <net/ip_tunnels.h> @@ -72,7 +73,7 @@ int fib_default_rule_add(struct fib_rules_ops *ops, r->suppress_prefixlen = -1; r->suppress_ifgroup = -1; - /* The lock is not required here, the list in unreacheable + /* The lock is not required here, the list in unreachable * at the moment this function is called */ list_add_tail(&r->list, &ops->rules_list); return 0; @@ -766,7 +767,8 @@ static const struct nla_policy fib_rule_policy[FRA_MAX + 1] = { [FRA_PROTOCOL] = { .type = NLA_U8 }, [FRA_IP_PROTO] = { .type = NLA_U8 }, [FRA_SPORT_RANGE] = { .len = sizeof(struct fib_rule_port_range) }, - [FRA_DPORT_RANGE] = { .len = sizeof(struct fib_rule_port_range) } + [FRA_DPORT_RANGE] = { .len = sizeof(struct fib_rule_port_range) }, + [FRA_DSCP] = NLA_POLICY_MAX(NLA_U8, INET_DSCP_MASK >> 2), }; int fib_nl_newrule(struct sk_buff *skb, struct nlmsghdr *nlh, @@ -1205,8 +1207,7 @@ static void notify_rule_change(int event, struct fib_rule *rule, rtnl_notify(skb, net, pid, ops->nlgroup, nlh, GFP_KERNEL); return; errout: - if (err < 0) - rtnl_set_sk_err(net, ops->nlgroup, err); + rtnl_set_sk_err(net, ops->nlgroup, err); } static void attach_rules(struct list_head *rules, struct net_device *dev) diff --git a/net/core/filter.c b/net/core/filter.c index 9933851c685e..cd3524cb326b 100644 --- a/net/core/filter.c +++ b/net/core/filter.c @@ -84,6 +84,7 @@ #include <net/netkit.h> #include <linux/un.h> #include <net/xdp_sock_drv.h> +#include <net/inet_dscp.h> #include "dev.h" @@ -1265,8 +1266,8 @@ static struct bpf_prog *bpf_migrate_filter(struct bpf_prog *fp) * so we need to keep the user BPF around until the 2nd * pass. At this time, the user BPF is stored in fp->insns. */ - old_prog = kmemdup(fp->insns, old_len * sizeof(struct sock_filter), - GFP_KERNEL | __GFP_NOWARN); + old_prog = kmemdup_array(fp->insns, old_len, sizeof(struct sock_filter), + GFP_KERNEL | __GFP_NOWARN); if (!old_prog) { err = -ENOMEM; goto out_err; @@ -1658,9 +1659,12 @@ struct bpf_scratchpad { __be32 diff[MAX_BPF_STACK / sizeof(__be32)]; u8 buff[MAX_BPF_STACK]; }; + local_lock_t bh_lock; }; -static DEFINE_PER_CPU(struct bpf_scratchpad, bpf_sp); +static DEFINE_PER_CPU(struct bpf_scratchpad, bpf_sp) = { + .bh_lock = INIT_LOCAL_LOCK(bh_lock), +}; static inline int __bpf_try_make_writable(struct sk_buff *skb, unsigned int write_len) @@ -2021,6 +2025,7 @@ BPF_CALL_5(bpf_csum_diff, __be32 *, from, u32, from_size, struct bpf_scratchpad *sp = this_cpu_ptr(&bpf_sp); u32 diff_size = from_size + to_size; int i, j = 0; + __wsum ret; /* This is quite flexible, some examples: * @@ -2034,12 +2039,15 @@ BPF_CALL_5(bpf_csum_diff, __be32 *, from, u32, from_size, diff_size > sizeof(sp->diff))) return -EINVAL; + local_lock_nested_bh(&bpf_sp.bh_lock); for (i = 0; i < from_size / sizeof(__be32); i++, j++) sp->diff[j] = ~from[i]; for (i = 0; i < to_size / sizeof(__be32); i++, j++) sp->diff[j] = to[i]; - return csum_partial(sp->diff, diff_size, seed); + ret = csum_partial(sp->diff, diff_size, seed); + local_unlock_nested_bh(&bpf_sp.bh_lock); + return ret; } static const struct bpf_func_proto bpf_csum_diff_proto = { @@ -2279,12 +2287,12 @@ static int __bpf_redirect_neigh_v6(struct sk_buff *skb, struct net_device *dev, err = bpf_out_neigh_v6(net, skb, dev, nh); if (unlikely(net_xmit_eval(err))) - dev->stats.tx_errors++; + DEV_STATS_INC(dev, tx_errors); else ret = NET_XMIT_SUCCESS; goto out_xmit; out_drop: - dev->stats.tx_errors++; + DEV_STATS_INC(dev, tx_errors); kfree_skb(skb); out_xmit: return ret; @@ -2364,7 +2372,7 @@ static int __bpf_redirect_neigh_v4(struct sk_buff *skb, struct net_device *dev, struct flowi4 fl4 = { .flowi4_flags = FLOWI_FLAG_ANYSRC, .flowi4_mark = skb->mark, - .flowi4_tos = RT_TOS(ip4h->tos), + .flowi4_tos = ip4h->tos & INET_DSCP_MASK, .flowi4_oif = dev->ifindex, .flowi4_proto = ip4h->protocol, .daddr = ip4h->daddr, @@ -2385,12 +2393,12 @@ static int __bpf_redirect_neigh_v4(struct sk_buff *skb, struct net_device *dev, err = bpf_out_neigh_v4(net, skb, dev, nh); if (unlikely(net_xmit_eval(err))) - dev->stats.tx_errors++; + DEV_STATS_INC(dev, tx_errors); else ret = NET_XMIT_SUCCESS; goto out_xmit; out_drop: - dev->stats.tx_errors++; + DEV_STATS_INC(dev, tx_errors); kfree_skb(skb); out_xmit: return ret; @@ -2476,9 +2484,6 @@ static const struct bpf_func_proto bpf_clone_redirect_proto = { .arg3_type = ARG_ANYTHING, }; -DEFINE_PER_CPU(struct bpf_redirect_info, bpf_redirect_info); -EXPORT_PER_CPU_SYMBOL_GPL(bpf_redirect_info); - static struct net_device *skb_get_peer_dev(struct net_device *dev) { const struct net_device_ops *ops = dev->netdev_ops; @@ -2491,7 +2496,7 @@ static struct net_device *skb_get_peer_dev(struct net_device *dev) int skb_do_redirect(struct sk_buff *skb) { - struct bpf_redirect_info *ri = this_cpu_ptr(&bpf_redirect_info); + struct bpf_redirect_info *ri = bpf_net_ctx_get_ri(); struct net *net = dev_net(skb->dev); struct net_device *dev; u32 flags = ri->flags; @@ -2524,7 +2529,7 @@ out_drop: BPF_CALL_2(bpf_redirect, u32, ifindex, u64, flags) { - struct bpf_redirect_info *ri = this_cpu_ptr(&bpf_redirect_info); + struct bpf_redirect_info *ri = bpf_net_ctx_get_ri(); if (unlikely(flags & (~(BPF_F_INGRESS) | BPF_F_REDIRECT_INTERNAL))) return TC_ACT_SHOT; @@ -2545,7 +2550,7 @@ static const struct bpf_func_proto bpf_redirect_proto = { BPF_CALL_2(bpf_redirect_peer, u32, ifindex, u64, flags) { - struct bpf_redirect_info *ri = this_cpu_ptr(&bpf_redirect_info); + struct bpf_redirect_info *ri = bpf_net_ctx_get_ri(); if (unlikely(flags)) return TC_ACT_SHOT; @@ -2567,7 +2572,7 @@ static const struct bpf_func_proto bpf_redirect_peer_proto = { BPF_CALL_4(bpf_redirect_neigh, u32, ifindex, struct bpf_redir_neigh *, params, int, plen, u64, flags) { - struct bpf_redirect_info *ri = this_cpu_ptr(&bpf_redirect_info); + struct bpf_redirect_info *ri = bpf_net_ctx_get_ri(); if (unlikely((plen && plen < sizeof(*params)) || flags)) return TC_ACT_SHOT; @@ -3185,6 +3190,7 @@ BPF_CALL_3(bpf_skb_vlan_push, struct sk_buff *, skb, __be16, vlan_proto, bpf_push_mac_rcsum(skb); ret = skb_vlan_push(skb, vlan_proto, vlan_tci); bpf_pull_mac_rcsum(skb); + skb_reset_mac_len(skb); bpf_compute_data_pointers(skb); return ret; @@ -3544,13 +3550,20 @@ static int bpf_skb_net_grow(struct sk_buff *skb, u32 off, u32 len_diff, if (skb_is_gso(skb)) { struct skb_shared_info *shinfo = skb_shinfo(skb); - /* Due to header grow, MSS needs to be downgraded. */ - if (!(flags & BPF_F_ADJ_ROOM_FIXED_GSO)) - skb_decrease_gso_size(shinfo, len_diff); - /* Header must be checked, and gso_segs recomputed. */ shinfo->gso_type |= gso_type; shinfo->gso_segs = 0; + + /* Due to header growth, MSS needs to be downgraded. + * There is a BUG_ON() when segmenting the frag_list with + * head_frag true, so linearize the skb after downgrading + * the MSS. + */ + if (!(flags & BPF_F_ADJ_ROOM_FIXED_GSO)) { + skb_decrease_gso_size(shinfo, len_diff); + if (shinfo->frag_list) + return skb_linearize(skb); + } } return 0; @@ -4273,50 +4286,50 @@ static const struct bpf_func_proto bpf_xdp_adjust_meta_proto = { */ void xdp_do_flush(void) { - __dev_flush(); - __cpu_map_flush(); - __xsk_map_flush(); + struct list_head *lh_map, *lh_dev, *lh_xsk; + + bpf_net_ctx_get_all_used_flush_lists(&lh_map, &lh_dev, &lh_xsk); + if (lh_dev) + __dev_flush(lh_dev); + if (lh_map) + __cpu_map_flush(lh_map); + if (lh_xsk) + __xsk_map_flush(lh_xsk); } EXPORT_SYMBOL_GPL(xdp_do_flush); #if defined(CONFIG_DEBUG_NET) && defined(CONFIG_BPF_SYSCALL) void xdp_do_check_flushed(struct napi_struct *napi) { - bool ret; + struct list_head *lh_map, *lh_dev, *lh_xsk; + bool missed = false; - ret = dev_check_flush(); - ret |= cpu_map_check_flush(); - ret |= xsk_map_check_flush(); + bpf_net_ctx_get_all_used_flush_lists(&lh_map, &lh_dev, &lh_xsk); + if (lh_dev) { + __dev_flush(lh_dev); + missed = true; + } + if (lh_map) { + __cpu_map_flush(lh_map); + missed = true; + } + if (lh_xsk) { + __xsk_map_flush(lh_xsk); + missed = true; + } - WARN_ONCE(ret, "Missing xdp_do_flush() invocation after NAPI by %ps\n", + WARN_ONCE(missed, "Missing xdp_do_flush() invocation after NAPI by %ps\n", napi->poll); } #endif -void bpf_clear_redirect_map(struct bpf_map *map) -{ - struct bpf_redirect_info *ri; - int cpu; - - for_each_possible_cpu(cpu) { - ri = per_cpu_ptr(&bpf_redirect_info, cpu); - /* Avoid polluting remote cacheline due to writes if - * not needed. Once we pass this test, we need the - * cmpxchg() to make sure it hasn't been changed in - * the meantime by remote CPU. - */ - if (unlikely(READ_ONCE(ri->map) == map)) - cmpxchg(&ri->map, map, NULL); - } -} - DEFINE_STATIC_KEY_FALSE(bpf_master_redirect_enabled_key); EXPORT_SYMBOL_GPL(bpf_master_redirect_enabled_key); u32 xdp_master_redirect(struct xdp_buff *xdp) { + struct bpf_redirect_info *ri = bpf_net_ctx_get_ri(); struct net_device *master, *slave; - struct bpf_redirect_info *ri = this_cpu_ptr(&bpf_redirect_info); master = netdev_master_upper_dev_get_rcu(xdp->rxq->dev); slave = master->netdev_ops->ndo_xdp_get_xmit_slave(master, xdp); @@ -4388,7 +4401,7 @@ static __always_inline int __xdp_do_redirect_frame(struct bpf_redirect_info *ri, map = READ_ONCE(ri->map); /* The map pointer is cleared when the map is being torn - * down by bpf_clear_redirect_map() + * down by dev_map_free() */ if (unlikely(!map)) { err = -ENOENT; @@ -4433,7 +4446,7 @@ err: int xdp_do_redirect(struct net_device *dev, struct xdp_buff *xdp, struct bpf_prog *xdp_prog) { - struct bpf_redirect_info *ri = this_cpu_ptr(&bpf_redirect_info); + struct bpf_redirect_info *ri = bpf_net_ctx_get_ri(); enum bpf_map_type map_type = ri->map_type; if (map_type == BPF_MAP_TYPE_XSKMAP) @@ -4447,7 +4460,7 @@ EXPORT_SYMBOL_GPL(xdp_do_redirect); int xdp_do_redirect_frame(struct net_device *dev, struct xdp_buff *xdp, struct xdp_frame *xdpf, struct bpf_prog *xdp_prog) { - struct bpf_redirect_info *ri = this_cpu_ptr(&bpf_redirect_info); + struct bpf_redirect_info *ri = bpf_net_ctx_get_ri(); enum bpf_map_type map_type = ri->map_type; if (map_type == BPF_MAP_TYPE_XSKMAP) @@ -4464,7 +4477,7 @@ static int xdp_do_generic_redirect_map(struct net_device *dev, enum bpf_map_type map_type, u32 map_id, u32 flags) { - struct bpf_redirect_info *ri = this_cpu_ptr(&bpf_redirect_info); + struct bpf_redirect_info *ri = bpf_net_ctx_get_ri(); struct bpf_map *map; int err; @@ -4476,7 +4489,7 @@ static int xdp_do_generic_redirect_map(struct net_device *dev, map = READ_ONCE(ri->map); /* The map pointer is cleared when the map is being torn - * down by bpf_clear_redirect_map() + * down by dev_map_free() */ if (unlikely(!map)) { err = -ENOENT; @@ -4518,7 +4531,7 @@ err: int xdp_do_generic_redirect(struct net_device *dev, struct sk_buff *skb, struct xdp_buff *xdp, struct bpf_prog *xdp_prog) { - struct bpf_redirect_info *ri = this_cpu_ptr(&bpf_redirect_info); + struct bpf_redirect_info *ri = bpf_net_ctx_get_ri(); enum bpf_map_type map_type = ri->map_type; void *fwd = ri->tgt_value; u32 map_id = ri->map_id; @@ -4554,7 +4567,7 @@ err: BPF_CALL_2(bpf_xdp_redirect, u32, ifindex, u64, flags) { - struct bpf_redirect_info *ri = this_cpu_ptr(&bpf_redirect_info); + struct bpf_redirect_info *ri = bpf_net_ctx_get_ri(); if (unlikely(flags)) return XDP_ABORTED; @@ -5267,6 +5280,11 @@ static int bpf_sol_tcp_setsockopt(struct sock *sk, int optname, return -EINVAL; inet_csk(sk)->icsk_rto_min = timeout; break; + case TCP_BPF_SOCK_OPS_CB_FLAGS: + if (val & ~(BPF_SOCK_OPS_ALL_CB_FLAGS)) + return -EINVAL; + tp->bpf_sock_ops_cb_flags = val; + break; default: return -EINVAL; } @@ -5355,6 +5373,17 @@ static int sol_tcp_sockopt(struct sock *sk, int optname, if (*optlen < 1) return -EINVAL; break; + case TCP_BPF_SOCK_OPS_CB_FLAGS: + if (*optlen != sizeof(int)) + return -EINVAL; + if (getopt) { + struct tcp_sock *tp = tcp_sk(sk); + int cb_flags = tp->bpf_sock_ops_cb_flags; + + memcpy(optval, &cb_flags, *optlen); + return 0; + } + return bpf_sol_tcp_setsockopt(sk, optname, optval, *optlen); default: if (getopt) return -EINVAL; @@ -5888,7 +5917,7 @@ static int bpf_ipv4_fib_lookup(struct net *net, struct bpf_fib_lookup *params, fl4.flowi4_iif = params->ifindex; fl4.flowi4_oif = 0; } - fl4.flowi4_tos = params->tos & IPTOS_RT_MASK; + fl4.flowi4_tos = params->tos & INET_DSCP_MASK; fl4.flowi4_scope = RT_SCOPE_UNIVERSE; fl4.flowi4_flags = 0; @@ -6251,20 +6280,25 @@ BPF_CALL_5(bpf_skb_check_mtu, struct sk_buff *, skb, int ret = BPF_MTU_CHK_RET_FRAG_NEEDED; struct net_device *dev = skb->dev; int skb_len, dev_len; - int mtu; + int mtu = 0; - if (unlikely(flags & ~(BPF_MTU_CHK_SEGS))) - return -EINVAL; + if (unlikely(flags & ~(BPF_MTU_CHK_SEGS))) { + ret = -EINVAL; + goto out; + } - if (unlikely(flags & BPF_MTU_CHK_SEGS && (len_diff || *mtu_len))) - return -EINVAL; + if (unlikely(flags & BPF_MTU_CHK_SEGS && (len_diff || *mtu_len))) { + ret = -EINVAL; + goto out; + } dev = __dev_via_ifindex(dev, ifindex); - if (unlikely(!dev)) - return -ENODEV; + if (unlikely(!dev)) { + ret = -ENODEV; + goto out; + } mtu = READ_ONCE(dev->mtu); - dev_len = mtu + dev->hard_header_len; /* If set use *mtu_len as input, L3 as iph->tot_len (like fib_lookup) */ @@ -6282,15 +6316,12 @@ BPF_CALL_5(bpf_skb_check_mtu, struct sk_buff *, skb, */ if (skb_is_gso(skb)) { ret = BPF_MTU_CHK_RET_SUCCESS; - if (flags & BPF_MTU_CHK_SEGS && !skb_gso_validate_network_len(skb, mtu)) ret = BPF_MTU_CHK_RET_SEGS_TOOBIG; } out: - /* BPF verifier guarantees valid pointer */ *mtu_len = mtu; - return ret; } @@ -6300,19 +6331,21 @@ BPF_CALL_5(bpf_xdp_check_mtu, struct xdp_buff *, xdp, struct net_device *dev = xdp->rxq->dev; int xdp_len = xdp->data_end - xdp->data; int ret = BPF_MTU_CHK_RET_SUCCESS; - int mtu, dev_len; + int mtu = 0, dev_len; /* XDP variant doesn't support multi-buffer segment check (yet) */ - if (unlikely(flags)) - return -EINVAL; + if (unlikely(flags)) { + ret = -EINVAL; + goto out; + } dev = __dev_via_ifindex(dev, ifindex); - if (unlikely(!dev)) - return -ENODEV; + if (unlikely(!dev)) { + ret = -ENODEV; + goto out; + } mtu = READ_ONCE(dev->mtu); - - /* Add L2-header as dev MTU is L3 size */ dev_len = mtu + dev->hard_header_len; /* Use *mtu_len as input, L3 as iph->tot_len (like fib_lookup) */ @@ -6322,10 +6355,8 @@ BPF_CALL_5(bpf_xdp_check_mtu, struct xdp_buff *, xdp, xdp_len += len_diff; /* minus result pass check */ if (xdp_len > dev_len) ret = BPF_MTU_CHK_RET_FRAG_NEEDED; - - /* BPF verifier guarantees valid pointer */ +out: *mtu_len = mtu; - return ret; } @@ -6335,7 +6366,8 @@ static const struct bpf_func_proto bpf_skb_check_mtu_proto = { .ret_type = RET_INTEGER, .arg1_type = ARG_PTR_TO_CTX, .arg2_type = ARG_ANYTHING, - .arg3_type = ARG_PTR_TO_INT, + .arg3_type = ARG_PTR_TO_FIXED_SIZE_MEM | MEM_UNINIT | MEM_ALIGNED, + .arg3_size = sizeof(u32), .arg4_type = ARG_ANYTHING, .arg5_type = ARG_ANYTHING, }; @@ -6346,7 +6378,8 @@ static const struct bpf_func_proto bpf_xdp_check_mtu_proto = { .ret_type = RET_INTEGER, .arg1_type = ARG_PTR_TO_CTX, .arg2_type = ARG_ANYTHING, - .arg3_type = ARG_PTR_TO_INT, + .arg3_type = ARG_PTR_TO_FIXED_SIZE_MEM | MEM_UNINIT | MEM_ALIGNED, + .arg3_size = sizeof(u32), .arg4_type = ARG_ANYTHING, .arg5_type = ARG_ANYTHING, }; @@ -6455,6 +6488,7 @@ BPF_CALL_4(bpf_lwt_seg6_store_bytes, struct sk_buff *, skb, u32, offset, void *srh_tlvs, *srh_end, *ptr; int srhoff = 0; + lockdep_assert_held(&srh_state->bh_lock); if (srh == NULL) return -EINVAL; @@ -6511,6 +6545,7 @@ BPF_CALL_4(bpf_lwt_seg6_action, struct sk_buff *, skb, int hdroff = 0; int err; + lockdep_assert_held(&srh_state->bh_lock); switch (action) { case SEG6_LOCAL_ACTION_END_X: if (!seg6_bpf_has_valid_srh(skb)) @@ -6587,6 +6622,7 @@ BPF_CALL_3(bpf_lwt_seg6_adjust_srh, struct sk_buff *, skb, u32, offset, int srhoff = 0; int ret; + lockdep_assert_held(&srh_state->bh_lock); if (unlikely(srh == NULL)) return -EINVAL; @@ -6820,7 +6856,7 @@ static const struct bpf_func_proto bpf_skc_lookup_tcp_proto = { .ret_type = RET_PTR_TO_SOCK_COMMON_OR_NULL, .arg1_type = ARG_PTR_TO_CTX, .arg2_type = ARG_PTR_TO_MEM | MEM_RDONLY, - .arg3_type = ARG_CONST_SIZE, + .arg3_type = ARG_CONST_SIZE_OR_ZERO, .arg4_type = ARG_ANYTHING, .arg5_type = ARG_ANYTHING, }; @@ -6839,7 +6875,7 @@ static const struct bpf_func_proto bpf_sk_lookup_tcp_proto = { .ret_type = RET_PTR_TO_SOCKET_OR_NULL, .arg1_type = ARG_PTR_TO_CTX, .arg2_type = ARG_PTR_TO_MEM | MEM_RDONLY, - .arg3_type = ARG_CONST_SIZE, + .arg3_type = ARG_CONST_SIZE_OR_ZERO, .arg4_type = ARG_ANYTHING, .arg5_type = ARG_ANYTHING, }; @@ -6858,7 +6894,7 @@ static const struct bpf_func_proto bpf_sk_lookup_udp_proto = { .ret_type = RET_PTR_TO_SOCKET_OR_NULL, .arg1_type = ARG_PTR_TO_CTX, .arg2_type = ARG_PTR_TO_MEM | MEM_RDONLY, - .arg3_type = ARG_CONST_SIZE, + .arg3_type = ARG_CONST_SIZE_OR_ZERO, .arg4_type = ARG_ANYTHING, .arg5_type = ARG_ANYTHING, }; @@ -6882,7 +6918,7 @@ static const struct bpf_func_proto bpf_tc_skc_lookup_tcp_proto = { .ret_type = RET_PTR_TO_SOCK_COMMON_OR_NULL, .arg1_type = ARG_PTR_TO_CTX, .arg2_type = ARG_PTR_TO_MEM | MEM_RDONLY, - .arg3_type = ARG_CONST_SIZE, + .arg3_type = ARG_CONST_SIZE_OR_ZERO, .arg4_type = ARG_ANYTHING, .arg5_type = ARG_ANYTHING, }; @@ -6906,7 +6942,7 @@ static const struct bpf_func_proto bpf_tc_sk_lookup_tcp_proto = { .ret_type = RET_PTR_TO_SOCKET_OR_NULL, .arg1_type = ARG_PTR_TO_CTX, .arg2_type = ARG_PTR_TO_MEM | MEM_RDONLY, - .arg3_type = ARG_CONST_SIZE, + .arg3_type = ARG_CONST_SIZE_OR_ZERO, .arg4_type = ARG_ANYTHING, .arg5_type = ARG_ANYTHING, }; @@ -6930,7 +6966,7 @@ static const struct bpf_func_proto bpf_tc_sk_lookup_udp_proto = { .ret_type = RET_PTR_TO_SOCKET_OR_NULL, .arg1_type = ARG_PTR_TO_CTX, .arg2_type = ARG_PTR_TO_MEM | MEM_RDONLY, - .arg3_type = ARG_CONST_SIZE, + .arg3_type = ARG_CONST_SIZE_OR_ZERO, .arg4_type = ARG_ANYTHING, .arg5_type = ARG_ANYTHING, }; @@ -6968,7 +7004,7 @@ static const struct bpf_func_proto bpf_xdp_sk_lookup_udp_proto = { .ret_type = RET_PTR_TO_SOCKET_OR_NULL, .arg1_type = ARG_PTR_TO_CTX, .arg2_type = ARG_PTR_TO_MEM | MEM_RDONLY, - .arg3_type = ARG_CONST_SIZE, + .arg3_type = ARG_CONST_SIZE_OR_ZERO, .arg4_type = ARG_ANYTHING, .arg5_type = ARG_ANYTHING, }; @@ -6992,7 +7028,7 @@ static const struct bpf_func_proto bpf_xdp_skc_lookup_tcp_proto = { .ret_type = RET_PTR_TO_SOCK_COMMON_OR_NULL, .arg1_type = ARG_PTR_TO_CTX, .arg2_type = ARG_PTR_TO_MEM | MEM_RDONLY, - .arg3_type = ARG_CONST_SIZE, + .arg3_type = ARG_CONST_SIZE_OR_ZERO, .arg4_type = ARG_ANYTHING, .arg5_type = ARG_ANYTHING, }; @@ -7016,7 +7052,7 @@ static const struct bpf_func_proto bpf_xdp_sk_lookup_tcp_proto = { .ret_type = RET_PTR_TO_SOCKET_OR_NULL, .arg1_type = ARG_PTR_TO_CTX, .arg2_type = ARG_PTR_TO_MEM | MEM_RDONLY, - .arg3_type = ARG_CONST_SIZE, + .arg3_type = ARG_CONST_SIZE_OR_ZERO, .arg4_type = ARG_ANYTHING, .arg5_type = ARG_ANYTHING, }; @@ -7036,7 +7072,7 @@ static const struct bpf_func_proto bpf_sock_addr_skc_lookup_tcp_proto = { .ret_type = RET_PTR_TO_SOCK_COMMON_OR_NULL, .arg1_type = ARG_PTR_TO_CTX, .arg2_type = ARG_PTR_TO_MEM | MEM_RDONLY, - .arg3_type = ARG_CONST_SIZE, + .arg3_type = ARG_CONST_SIZE_OR_ZERO, .arg4_type = ARG_ANYTHING, .arg5_type = ARG_ANYTHING, }; @@ -7055,7 +7091,7 @@ static const struct bpf_func_proto bpf_sock_addr_sk_lookup_tcp_proto = { .ret_type = RET_PTR_TO_SOCKET_OR_NULL, .arg1_type = ARG_PTR_TO_CTX, .arg2_type = ARG_PTR_TO_MEM | MEM_RDONLY, - .arg3_type = ARG_CONST_SIZE, + .arg3_type = ARG_CONST_SIZE_OR_ZERO, .arg4_type = ARG_ANYTHING, .arg5_type = ARG_ANYTHING, }; @@ -7074,7 +7110,7 @@ static const struct bpf_func_proto bpf_sock_addr_sk_lookup_udp_proto = { .ret_type = RET_PTR_TO_SOCKET_OR_NULL, .arg1_type = ARG_PTR_TO_CTX, .arg2_type = ARG_PTR_TO_MEM | MEM_RDONLY, - .arg3_type = ARG_CONST_SIZE, + .arg3_type = ARG_CONST_SIZE_OR_ZERO, .arg4_type = ARG_ANYTHING, .arg5_type = ARG_ANYTHING, }; @@ -7731,17 +7767,21 @@ BPF_CALL_3(bpf_skb_set_tstamp, struct sk_buff *, skb, return -EOPNOTSUPP; switch (tstamp_type) { - case BPF_SKB_TSTAMP_DELIVERY_MONO: + case BPF_SKB_CLOCK_REALTIME: + skb->tstamp = tstamp; + skb->tstamp_type = SKB_CLOCK_REALTIME; + break; + case BPF_SKB_CLOCK_MONOTONIC: if (!tstamp) return -EINVAL; skb->tstamp = tstamp; - skb->mono_delivery_time = 1; + skb->tstamp_type = SKB_CLOCK_MONOTONIC; break; - case BPF_SKB_TSTAMP_UNSPEC: - if (tstamp) + case BPF_SKB_CLOCK_TAI: + if (!tstamp) return -EINVAL; - skb->tstamp = 0; - skb->mono_delivery_time = 0; + skb->tstamp = tstamp; + skb->tstamp_type = SKB_CLOCK_TAI; break; default: return -EINVAL; @@ -8561,13 +8601,16 @@ static bool bpf_skb_is_valid_access(int off, int size, enum bpf_access_type type if (off + size > offsetofend(struct __sk_buff, cb[4])) return false; break; + case bpf_ctx_range(struct __sk_buff, data): + case bpf_ctx_range(struct __sk_buff, data_meta): + case bpf_ctx_range(struct __sk_buff, data_end): + if (info->is_ldsx || size != size_default) + return false; + break; case bpf_ctx_range_till(struct __sk_buff, remote_ip6[0], remote_ip6[3]): case bpf_ctx_range_till(struct __sk_buff, local_ip6[0], local_ip6[3]): case bpf_ctx_range_till(struct __sk_buff, remote_ip4, remote_ip4): case bpf_ctx_range_till(struct __sk_buff, local_ip4, local_ip4): - case bpf_ctx_range(struct __sk_buff, data): - case bpf_ctx_range(struct __sk_buff, data_meta): - case bpf_ctx_range(struct __sk_buff, data_end): if (size != size_default) return false; break; @@ -9011,6 +9054,14 @@ static bool xdp_is_valid_access(int off, int size, } } return false; + } else { + switch (off) { + case offsetof(struct xdp_md, data_meta): + case offsetof(struct xdp_md, data): + case offsetof(struct xdp_md, data_end): + if (info->is_ldsx) + return false; + } } switch (off) { @@ -9336,12 +9387,12 @@ static bool flow_dissector_is_valid_access(int off, int size, switch (off) { case bpf_ctx_range(struct __sk_buff, data): - if (size != size_default) + if (info->is_ldsx || size != size_default) return false; info->reg_type = PTR_TO_PACKET; return true; case bpf_ctx_range(struct __sk_buff, data_end): - if (size != size_default) + if (info->is_ldsx || size != size_default) return false; info->reg_type = PTR_TO_PACKET_END; return true; @@ -9392,16 +9443,17 @@ static struct bpf_insn *bpf_convert_tstamp_type_read(const struct bpf_insn *si, { __u8 value_reg = si->dst_reg; __u8 skb_reg = si->src_reg; - /* AX is needed because src_reg and dst_reg could be the same */ - __u8 tmp_reg = BPF_REG_AX; - - *insn++ = BPF_LDX_MEM(BPF_B, tmp_reg, skb_reg, - SKB_BF_MONO_TC_OFFSET); - *insn++ = BPF_JMP32_IMM(BPF_JSET, tmp_reg, - SKB_MONO_DELIVERY_TIME_MASK, 2); - *insn++ = BPF_MOV32_IMM(value_reg, BPF_SKB_TSTAMP_UNSPEC); - *insn++ = BPF_JMP_A(1); - *insn++ = BPF_MOV32_IMM(value_reg, BPF_SKB_TSTAMP_DELIVERY_MONO); + BUILD_BUG_ON(__SKB_CLOCK_MAX != (int)BPF_SKB_CLOCK_TAI); + BUILD_BUG_ON(SKB_CLOCK_REALTIME != (int)BPF_SKB_CLOCK_REALTIME); + BUILD_BUG_ON(SKB_CLOCK_MONOTONIC != (int)BPF_SKB_CLOCK_MONOTONIC); + BUILD_BUG_ON(SKB_CLOCK_TAI != (int)BPF_SKB_CLOCK_TAI); + *insn++ = BPF_LDX_MEM(BPF_B, value_reg, skb_reg, SKB_BF_MONO_TC_OFFSET); + *insn++ = BPF_ALU32_IMM(BPF_AND, value_reg, SKB_TSTAMP_TYPE_MASK); +#ifdef __BIG_ENDIAN_BITFIELD + *insn++ = BPF_ALU32_IMM(BPF_RSH, value_reg, SKB_TSTAMP_TYPE_RSHIFT); +#else + BUILD_BUG_ON(!(SKB_TSTAMP_TYPE_MASK & 0x1)); +#endif return insn; } @@ -9444,11 +9496,12 @@ static struct bpf_insn *bpf_convert_tstamp_read(const struct bpf_prog *prog, __u8 tmp_reg = BPF_REG_AX; *insn++ = BPF_LDX_MEM(BPF_B, tmp_reg, skb_reg, SKB_BF_MONO_TC_OFFSET); - *insn++ = BPF_ALU32_IMM(BPF_AND, tmp_reg, - TC_AT_INGRESS_MASK | SKB_MONO_DELIVERY_TIME_MASK); - *insn++ = BPF_JMP32_IMM(BPF_JNE, tmp_reg, - TC_AT_INGRESS_MASK | SKB_MONO_DELIVERY_TIME_MASK, 2); - /* skb->tc_at_ingress && skb->mono_delivery_time, + /* check if ingress mask bits is set */ + *insn++ = BPF_JMP32_IMM(BPF_JSET, tmp_reg, TC_AT_INGRESS_MASK, 1); + *insn++ = BPF_JMP_A(4); + *insn++ = BPF_JMP32_IMM(BPF_JSET, tmp_reg, SKB_TSTAMP_TYPE_MASK, 1); + *insn++ = BPF_JMP_A(2); + /* skb->tc_at_ingress && skb->tstamp_type, * read 0 as the (rcv) timestamp. */ *insn++ = BPF_MOV64_IMM(value_reg, 0); @@ -9473,7 +9526,7 @@ static struct bpf_insn *bpf_convert_tstamp_write(const struct bpf_prog *prog, * the bpf prog is aware the tstamp could have delivery time. * Thus, write skb->tstamp as is if tstamp_type_access is true. * Otherwise, writing at ingress will have to clear the - * mono_delivery_time bit also. + * skb->tstamp_type bit also. */ if (!prog->tstamp_type_access) { __u8 tmp_reg = BPF_REG_AX; @@ -9483,8 +9536,8 @@ static struct bpf_insn *bpf_convert_tstamp_write(const struct bpf_prog *prog, *insn++ = BPF_JMP32_IMM(BPF_JSET, tmp_reg, TC_AT_INGRESS_MASK, 1); /* goto <store> */ *insn++ = BPF_JMP_A(2); - /* <clear>: mono_delivery_time */ - *insn++ = BPF_ALU32_IMM(BPF_AND, tmp_reg, ~SKB_MONO_DELIVERY_TIME_MASK); + /* <clear>: skb->tstamp_type */ + *insn++ = BPF_ALU32_IMM(BPF_AND, tmp_reg, ~SKB_TSTAMP_TYPE_MASK); *insn++ = BPF_STX_MEM(BPF_B, skb_reg, tmp_reg, SKB_BF_MONO_TC_OFFSET); } #endif @@ -11040,7 +11093,6 @@ const struct bpf_verifier_ops lwt_seg6local_verifier_ops = { }; const struct bpf_prog_ops lwt_seg6local_prog_ops = { - .test_run = bpf_prog_test_run_skb, }; const struct bpf_verifier_ops cg_sock_verifier_ops = { @@ -11858,28 +11910,34 @@ bpf_sk_base_func_proto(enum bpf_func_id func_id, const struct bpf_prog *prog) } __bpf_kfunc_start_defs(); -__bpf_kfunc int bpf_dynptr_from_skb(struct sk_buff *skb, u64 flags, - struct bpf_dynptr_kern *ptr__uninit) +__bpf_kfunc int bpf_dynptr_from_skb(struct __sk_buff *s, u64 flags, + struct bpf_dynptr *ptr__uninit) { + struct bpf_dynptr_kern *ptr = (struct bpf_dynptr_kern *)ptr__uninit; + struct sk_buff *skb = (struct sk_buff *)s; + if (flags) { - bpf_dynptr_set_null(ptr__uninit); + bpf_dynptr_set_null(ptr); return -EINVAL; } - bpf_dynptr_init(ptr__uninit, skb, BPF_DYNPTR_TYPE_SKB, 0, skb->len); + bpf_dynptr_init(ptr, skb, BPF_DYNPTR_TYPE_SKB, 0, skb->len); return 0; } -__bpf_kfunc int bpf_dynptr_from_xdp(struct xdp_buff *xdp, u64 flags, - struct bpf_dynptr_kern *ptr__uninit) +__bpf_kfunc int bpf_dynptr_from_xdp(struct xdp_md *x, u64 flags, + struct bpf_dynptr *ptr__uninit) { + struct bpf_dynptr_kern *ptr = (struct bpf_dynptr_kern *)ptr__uninit; + struct xdp_buff *xdp = (struct xdp_buff *)x; + if (flags) { - bpf_dynptr_set_null(ptr__uninit); + bpf_dynptr_set_null(ptr); return -EINVAL; } - bpf_dynptr_init(ptr__uninit, xdp, BPF_DYNPTR_TYPE_XDP, 0, xdp_get_buff_len(xdp)); + bpf_dynptr_init(ptr, xdp, BPF_DYNPTR_TYPE_XDP, 0, xdp_get_buff_len(xdp)); return 0; } @@ -11905,10 +11963,11 @@ __bpf_kfunc int bpf_sock_addr_set_sun_path(struct bpf_sock_addr_kern *sa_kern, return 0; } -__bpf_kfunc int bpf_sk_assign_tcp_reqsk(struct sk_buff *skb, struct sock *sk, +__bpf_kfunc int bpf_sk_assign_tcp_reqsk(struct __sk_buff *s, struct sock *sk, struct bpf_tcp_req_attrs *attrs, int attrs__sz) { #if IS_ENABLED(CONFIG_SYN_COOKIES) + struct sk_buff *skb = (struct sk_buff *)s; const struct request_sock_ops *ops; struct inet_request_sock *ireq; struct tcp_request_sock *treq; @@ -12003,22 +12062,23 @@ __bpf_kfunc int bpf_sk_assign_tcp_reqsk(struct sk_buff *skb, struct sock *sk, __bpf_kfunc_end_defs(); -int bpf_dynptr_from_skb_rdonly(struct sk_buff *skb, u64 flags, - struct bpf_dynptr_kern *ptr__uninit) +int bpf_dynptr_from_skb_rdonly(struct __sk_buff *skb, u64 flags, + struct bpf_dynptr *ptr__uninit) { + struct bpf_dynptr_kern *ptr = (struct bpf_dynptr_kern *)ptr__uninit; int err; err = bpf_dynptr_from_skb(skb, flags, ptr__uninit); if (err) return err; - bpf_dynptr_set_rdonly(ptr__uninit); + bpf_dynptr_set_rdonly(ptr); return 0; } BTF_KFUNCS_START(bpf_kfunc_check_set_skb) -BTF_ID_FLAGS(func, bpf_dynptr_from_skb) +BTF_ID_FLAGS(func, bpf_dynptr_from_skb, KF_TRUSTED_ARGS) BTF_KFUNCS_END(bpf_kfunc_check_set_skb) BTF_KFUNCS_START(bpf_kfunc_check_set_xdp) @@ -12067,6 +12127,7 @@ static int __init bpf_kfunc_init(void) ret = ret ?: register_btf_kfunc_id_set(BPF_PROG_TYPE_LWT_XMIT, &bpf_kfunc_set_skb); ret = ret ?: register_btf_kfunc_id_set(BPF_PROG_TYPE_LWT_SEG6LOCAL, &bpf_kfunc_set_skb); ret = ret ?: register_btf_kfunc_id_set(BPF_PROG_TYPE_NETFILTER, &bpf_kfunc_set_skb); + ret = ret ?: register_btf_kfunc_id_set(BPF_PROG_TYPE_TRACING, &bpf_kfunc_set_skb); ret = ret ?: register_btf_kfunc_id_set(BPF_PROG_TYPE_XDP, &bpf_kfunc_set_xdp); ret = ret ?: register_btf_kfunc_id_set(BPF_PROG_TYPE_CGROUP_SOCK_ADDR, &bpf_kfunc_set_sock_addr); diff --git a/net/core/flow_dissector.c b/net/core/flow_dissector.c index f82e9a7d3b37..0e638a37aa09 100644 --- a/net/core/flow_dissector.c +++ b/net/core/flow_dissector.c @@ -299,9 +299,10 @@ void skb_flow_dissect_meta(const struct sk_buff *skb, EXPORT_SYMBOL(skb_flow_dissect_meta); static void -skb_flow_dissect_set_enc_addr_type(enum flow_dissector_key_id type, - struct flow_dissector *flow_dissector, - void *target_container) +skb_flow_dissect_set_enc_control(enum flow_dissector_key_id type, + u32 ctrl_flags, + struct flow_dissector *flow_dissector, + void *target_container) { struct flow_dissector_key_control *ctrl; @@ -312,6 +313,7 @@ skb_flow_dissect_set_enc_addr_type(enum flow_dissector_key_id type, FLOW_DISSECTOR_KEY_ENC_CONTROL, target_container); ctrl->addr_type = type; + ctrl->flags = ctrl_flags; } void @@ -367,6 +369,7 @@ skb_flow_dissect_tunnel_info(const struct sk_buff *skb, { struct ip_tunnel_info *info; struct ip_tunnel_key *key; + u32 ctrl_flags = 0; /* A quick check to see if there might be something to do. */ if (!dissector_uses_key(flow_dissector, @@ -391,11 +394,20 @@ skb_flow_dissect_tunnel_info(const struct sk_buff *skb, key = &info->key; + if (test_bit(IP_TUNNEL_CSUM_BIT, key->tun_flags)) + ctrl_flags |= FLOW_DIS_F_TUNNEL_CSUM; + if (test_bit(IP_TUNNEL_DONT_FRAGMENT_BIT, key->tun_flags)) + ctrl_flags |= FLOW_DIS_F_TUNNEL_DONT_FRAGMENT; + if (test_bit(IP_TUNNEL_OAM_BIT, key->tun_flags)) + ctrl_flags |= FLOW_DIS_F_TUNNEL_OAM; + if (test_bit(IP_TUNNEL_CRIT_OPT_BIT, key->tun_flags)) + ctrl_flags |= FLOW_DIS_F_TUNNEL_CRIT_OPT; + switch (ip_tunnel_info_af(info)) { case AF_INET: - skb_flow_dissect_set_enc_addr_type(FLOW_DISSECTOR_KEY_IPV4_ADDRS, - flow_dissector, - target_container); + skb_flow_dissect_set_enc_control(FLOW_DISSECTOR_KEY_IPV4_ADDRS, + ctrl_flags, flow_dissector, + target_container); if (dissector_uses_key(flow_dissector, FLOW_DISSECTOR_KEY_ENC_IPV4_ADDRS)) { struct flow_dissector_key_ipv4_addrs *ipv4; @@ -408,9 +420,9 @@ skb_flow_dissect_tunnel_info(const struct sk_buff *skb, } break; case AF_INET6: - skb_flow_dissect_set_enc_addr_type(FLOW_DISSECTOR_KEY_IPV6_ADDRS, - flow_dissector, - target_container); + skb_flow_dissect_set_enc_control(FLOW_DISSECTOR_KEY_IPV6_ADDRS, + ctrl_flags, flow_dissector, + target_container); if (dissector_uses_key(flow_dissector, FLOW_DISSECTOR_KEY_ENC_IPV6_ADDRS)) { struct flow_dissector_key_ipv6_addrs *ipv6; @@ -422,6 +434,10 @@ skb_flow_dissect_tunnel_info(const struct sk_buff *skb, ipv6->dst = key->u.ipv6.dst; } break; + default: + skb_flow_dissect_set_enc_control(0, ctrl_flags, flow_dissector, + target_container); + break; } if (dissector_uses_key(flow_dissector, FLOW_DISSECTOR_KEY_ENC_KEYID)) { @@ -1101,7 +1117,7 @@ bool __skb_flow_dissect(const struct net *net, } } - WARN_ON_ONCE(!net); + DEBUG_NET_WARN_ON_ONCE(!net); if (net) { enum netns_bpf_attach_type type = NETNS_BPF_FLOW_DISSECTOR; struct bpf_prog_array *run_array; @@ -1792,6 +1808,13 @@ u32 flow_hash_from_keys(struct flow_keys *keys) } EXPORT_SYMBOL(flow_hash_from_keys); +u32 flow_hash_from_keys_seed(struct flow_keys *keys, + const siphash_key_t *keyval) +{ + return __flow_hash_from_keys(keys, keyval); +} +EXPORT_SYMBOL(flow_hash_from_keys_seed); + static inline u32 ___skb_get_hash(const struct sk_buff *skb, struct flow_keys *keys, const siphash_key_t *keyval) @@ -1831,22 +1854,23 @@ EXPORT_SYMBOL(make_flow_keys_digest); static struct flow_dissector flow_keys_dissector_symmetric __read_mostly; -u32 __skb_get_hash_symmetric(const struct sk_buff *skb) +u32 __skb_get_hash_symmetric_net(const struct net *net, const struct sk_buff *skb) { struct flow_keys keys; __flow_hash_secret_init(); memset(&keys, 0, sizeof(keys)); - __skb_flow_dissect(NULL, skb, &flow_keys_dissector_symmetric, + __skb_flow_dissect(net, skb, &flow_keys_dissector_symmetric, &keys, NULL, 0, 0, 0, 0); return __flow_hash_from_keys(&keys, &hashrnd); } -EXPORT_SYMBOL_GPL(__skb_get_hash_symmetric); +EXPORT_SYMBOL_GPL(__skb_get_hash_symmetric_net); /** - * __skb_get_hash: calculate a flow hash + * __skb_get_hash_net: calculate a flow hash + * @net: associated network namespace, derived from @skb if NULL * @skb: sk_buff to calculate flow hash from * * This function calculates a flow hash based on src/dst addresses @@ -1854,18 +1878,24 @@ EXPORT_SYMBOL_GPL(__skb_get_hash_symmetric); * on success, zero indicates no valid hash. Also, sets l4_hash in skb * if hash is a canonical 4-tuple hash over transport ports. */ -void __skb_get_hash(struct sk_buff *skb) +void __skb_get_hash_net(const struct net *net, struct sk_buff *skb) { struct flow_keys keys; u32 hash; + memset(&keys, 0, sizeof(keys)); + + __skb_flow_dissect(net, skb, &flow_keys_dissector, + &keys, NULL, 0, 0, 0, + FLOW_DISSECTOR_F_STOP_AT_FLOW_LABEL); + __flow_hash_secret_init(); - hash = ___skb_get_hash(skb, &keys, &hashrnd); + hash = __flow_hash_from_keys(&keys, &hashrnd); __skb_set_sw_hash(skb, hash, flow_keys_have_l4(&keys)); } -EXPORT_SYMBOL(__skb_get_hash); +EXPORT_SYMBOL(__skb_get_hash_net); __u32 skb_get_hash_perturb(const struct sk_buff *skb, const siphash_key_t *perturb) diff --git a/net/core/gen_estimator.c b/net/core/gen_estimator.c index fae9c4694186..412816076b8b 100644 --- a/net/core/gen_estimator.c +++ b/net/core/gen_estimator.c @@ -206,7 +206,7 @@ void gen_kill_estimator(struct net_rate_estimator __rcu **rate_est) { struct net_rate_estimator *est; - est = xchg((__force struct net_rate_estimator **)rate_est, NULL); + est = unrcu_pointer(xchg(rate_est, NULL)); if (est) { timer_shutdown_sync(&est->timer); kfree_rcu(est, rcu); diff --git a/net/core/gro.c b/net/core/gro.c index b3b43de1a650..802b4a062400 100644 --- a/net/core/gro.c +++ b/net/core/gro.c @@ -374,7 +374,7 @@ static void gro_list_prepare(const struct list_head *head, skb_mac_header(skb), maclen); - /* in most common scenarions 'slow_gro' is 0 + /* in most common scenarios 'slow_gro' is 0 * otherwise we are already on some slower paths * either skip all the infrequent tests altogether or * avoid trying too hard to skip each of them individually @@ -408,7 +408,8 @@ static inline void skb_gro_reset_offset(struct sk_buff *skb, u32 nhoff) pinfo = skb_shinfo(skb); frag0 = &pinfo->frags[0]; - if (pinfo->nr_frags && !PageHighMem(skb_frag_page(frag0)) && + if (pinfo->nr_frags && skb_frag_page(frag0) && + !PageHighMem(skb_frag_page(frag0)) && (!NET_IP_ALIGN || !((skb_frag_off(frag0) + nhoff) & 3))) { NAPI_GRO_CB(skb)->frag0 = skb_frag_address(frag0); NAPI_GRO_CB(skb)->frag0_len = min_t(unsigned int, diff --git a/net/core/link_watch.c b/net/core/link_watch.c index 8ec35194bfcb..ab150641142a 100644 --- a/net/core/link_watch.c +++ b/net/core/link_watch.c @@ -148,9 +148,9 @@ static void linkwatch_schedule_work(int urgent) * override the existing timer. */ if (test_bit(LW_URGENT, &linkwatch_flags)) - mod_delayed_work(system_wq, &linkwatch_work, 0); + mod_delayed_work(system_unbound_wq, &linkwatch_work, 0); else - schedule_delayed_work(&linkwatch_work, delay); + queue_delayed_work(system_unbound_wq, &linkwatch_work, delay); } diff --git a/net/core/lwt_bpf.c b/net/core/lwt_bpf.c index 4a0797f0a154..1a14f915b7a4 100644 --- a/net/core/lwt_bpf.c +++ b/net/core/lwt_bpf.c @@ -12,6 +12,7 @@ #include <net/gre.h> #include <net/ip6_route.h> #include <net/ipv6_stubs.h> +#include <net/inet_dscp.h> struct bpf_lwt_prog { struct bpf_prog *prog; @@ -38,13 +39,14 @@ static inline struct bpf_lwt *bpf_lwt_lwtunnel(struct lwtunnel_state *lwt) static int run_lwt_bpf(struct sk_buff *skb, struct bpf_lwt_prog *lwt, struct dst_entry *dst, bool can_redirect) { + struct bpf_net_context __bpf_net_ctx, *bpf_net_ctx; int ret; - /* Migration disable and BH disable are needed to protect per-cpu - * redirect_info between BPF prog and skb_do_redirect(). + /* Disabling BH is needed to protect per-CPU bpf_redirect_info between + * BPF prog and skb_do_redirect(). */ - migrate_disable(); local_bh_disable(); + bpf_net_ctx = bpf_net_ctx_set(&__bpf_net_ctx); bpf_compute_data_pointers(skb); ret = bpf_prog_run_save_cb(lwt->prog, skb); @@ -77,8 +79,8 @@ static int run_lwt_bpf(struct sk_buff *skb, struct bpf_lwt_prog *lwt, break; } + bpf_net_ctx_clear(bpf_net_ctx); local_bh_enable(); - migrate_enable(); return ret; } @@ -204,7 +206,7 @@ static int bpf_lwt_xmit_reroute(struct sk_buff *skb) fl4.flowi4_oif = oif; fl4.flowi4_mark = skb->mark; fl4.flowi4_uid = sock_net_uid(net, sk); - fl4.flowi4_tos = RT_TOS(iph->tos); + fl4.flowi4_tos = iph->tos & INET_DSCP_MASK; fl4.flowi4_flags = FLOWI_FLAG_ANYSRC; fl4.flowi4_proto = iph->protocol; fl4.daddr = iph->daddr; diff --git a/net/core/mp_dmabuf_devmem.h b/net/core/mp_dmabuf_devmem.h new file mode 100644 index 000000000000..67cd0dd7319c --- /dev/null +++ b/net/core/mp_dmabuf_devmem.h @@ -0,0 +1,44 @@ +/* SPDX-License-Identifier: GPL-2.0-or-later */ +/* + * Dmabuf device memory provider. + * + * Authors: Mina Almasry <almasrymina@google.com> + * + */ +#ifndef _NET_MP_DMABUF_DEVMEM_H +#define _NET_MP_DMABUF_DEVMEM_H + +#include <net/netmem.h> + +#if defined(CONFIG_NET_DEVMEM) +int mp_dmabuf_devmem_init(struct page_pool *pool); + +netmem_ref mp_dmabuf_devmem_alloc_netmems(struct page_pool *pool, gfp_t gfp); + +void mp_dmabuf_devmem_destroy(struct page_pool *pool); + +bool mp_dmabuf_devmem_release_page(struct page_pool *pool, netmem_ref netmem); +#else +static inline int mp_dmabuf_devmem_init(struct page_pool *pool) +{ + return -EOPNOTSUPP; +} + +static inline netmem_ref +mp_dmabuf_devmem_alloc_netmems(struct page_pool *pool, gfp_t gfp) +{ + return 0; +} + +static inline void mp_dmabuf_devmem_destroy(struct page_pool *pool) +{ +} + +static inline bool +mp_dmabuf_devmem_release_page(struct page_pool *pool, netmem_ref netmem) +{ + return false; +} +#endif + +#endif /* _NET_MP_DMABUF_DEVMEM_H */ diff --git a/net/core/neighbour.c b/net/core/neighbour.c index 45fd88405b6b..77b819cd995b 100644 --- a/net/core/neighbour.c +++ b/net/core/neighbour.c @@ -3530,8 +3530,7 @@ static void __neigh_notify(struct neighbour *n, int type, int flags, rtnl_notify(skb, net, 0, RTNLGRP_NEIGH, NULL, GFP_ATOMIC); return; errout: - if (err < 0) - rtnl_set_sk_err(net, RTNLGRP_NEIGH, err); + rtnl_set_sk_err(net, RTNLGRP_NEIGH, err); } void neigh_app_ns(struct neighbour *n) @@ -3543,7 +3542,7 @@ EXPORT_SYMBOL(neigh_app_ns); #ifdef CONFIG_SYSCTL static int unres_qlen_max = INT_MAX / SKB_TRUESIZE(ETH_FRAME_LEN); -static int proc_unres_qlen(struct ctl_table *ctl, int write, +static int proc_unres_qlen(const struct ctl_table *ctl, int write, void *buffer, size_t *lenp, loff_t *ppos) { int size, ret; @@ -3578,7 +3577,7 @@ static void neigh_copy_dflt_parms(struct net *net, struct neigh_parms *p, rcu_read_unlock(); } -static void neigh_proc_update(struct ctl_table *ctl, int write) +static void neigh_proc_update(const struct ctl_table *ctl, int write) { struct net_device *dev = ctl->extra1; struct neigh_parms *p = ctl->extra2; @@ -3595,7 +3594,7 @@ static void neigh_proc_update(struct ctl_table *ctl, int write) neigh_copy_dflt_parms(net, p, index); } -static int neigh_proc_dointvec_zero_intmax(struct ctl_table *ctl, int write, +static int neigh_proc_dointvec_zero_intmax(const struct ctl_table *ctl, int write, void *buffer, size_t *lenp, loff_t *ppos) { @@ -3610,7 +3609,7 @@ static int neigh_proc_dointvec_zero_intmax(struct ctl_table *ctl, int write, return ret; } -static int neigh_proc_dointvec_ms_jiffies_positive(struct ctl_table *ctl, int write, +static int neigh_proc_dointvec_ms_jiffies_positive(const struct ctl_table *ctl, int write, void *buffer, size_t *lenp, loff_t *ppos) { struct ctl_table tmp = *ctl; @@ -3626,7 +3625,7 @@ static int neigh_proc_dointvec_ms_jiffies_positive(struct ctl_table *ctl, int wr return ret; } -int neigh_proc_dointvec(struct ctl_table *ctl, int write, void *buffer, +int neigh_proc_dointvec(const struct ctl_table *ctl, int write, void *buffer, size_t *lenp, loff_t *ppos) { int ret = proc_dointvec(ctl, write, buffer, lenp, ppos); @@ -3636,7 +3635,7 @@ int neigh_proc_dointvec(struct ctl_table *ctl, int write, void *buffer, } EXPORT_SYMBOL(neigh_proc_dointvec); -int neigh_proc_dointvec_jiffies(struct ctl_table *ctl, int write, void *buffer, +int neigh_proc_dointvec_jiffies(const struct ctl_table *ctl, int write, void *buffer, size_t *lenp, loff_t *ppos) { int ret = proc_dointvec_jiffies(ctl, write, buffer, lenp, ppos); @@ -3646,7 +3645,7 @@ int neigh_proc_dointvec_jiffies(struct ctl_table *ctl, int write, void *buffer, } EXPORT_SYMBOL(neigh_proc_dointvec_jiffies); -static int neigh_proc_dointvec_userhz_jiffies(struct ctl_table *ctl, int write, +static int neigh_proc_dointvec_userhz_jiffies(const struct ctl_table *ctl, int write, void *buffer, size_t *lenp, loff_t *ppos) { @@ -3656,7 +3655,7 @@ static int neigh_proc_dointvec_userhz_jiffies(struct ctl_table *ctl, int write, return ret; } -int neigh_proc_dointvec_ms_jiffies(struct ctl_table *ctl, int write, +int neigh_proc_dointvec_ms_jiffies(const struct ctl_table *ctl, int write, void *buffer, size_t *lenp, loff_t *ppos) { int ret = proc_dointvec_ms_jiffies(ctl, write, buffer, lenp, ppos); @@ -3666,7 +3665,7 @@ int neigh_proc_dointvec_ms_jiffies(struct ctl_table *ctl, int write, } EXPORT_SYMBOL(neigh_proc_dointvec_ms_jiffies); -static int neigh_proc_dointvec_unres_qlen(struct ctl_table *ctl, int write, +static int neigh_proc_dointvec_unres_qlen(const struct ctl_table *ctl, int write, void *buffer, size_t *lenp, loff_t *ppos) { @@ -3676,7 +3675,7 @@ static int neigh_proc_dointvec_unres_qlen(struct ctl_table *ctl, int write, return ret; } -static int neigh_proc_base_reachable_time(struct ctl_table *ctl, int write, +static int neigh_proc_base_reachable_time(const struct ctl_table *ctl, int write, void *buffer, size_t *lenp, loff_t *ppos) { diff --git a/net/core/net-sysfs.c b/net/core/net-sysfs.c index 4c27a360c294..05cf5347f25e 100644 --- a/net/core/net-sysfs.c +++ b/net/core/net-sysfs.c @@ -32,6 +32,7 @@ #ifdef CONFIG_SYSFS static const char fmt_hex[] = "%#x\n"; static const char fmt_dec[] = "%d\n"; +static const char fmt_uint[] = "%u\n"; static const char fmt_ulong[] = "%lu\n"; static const char fmt_u64[] = "%llu\n"; @@ -235,7 +236,7 @@ static ssize_t speed_show(struct device *dev, if (!rtnl_trylock()) return restart_syscall(); - if (netif_running(netdev) && netif_device_present(netdev)) { + if (netif_running(netdev)) { struct ethtool_link_ksettings cmd; if (!__ethtool_get_link_ksettings(netdev, &cmd)) @@ -425,6 +426,9 @@ NETDEVICE_SHOW_RW(gro_flush_timeout, fmt_ulong); static int change_napi_defer_hard_irqs(struct net_device *dev, unsigned long val) { + if (val > S32_MAX) + return -ERANGE; + WRITE_ONCE(dev->napi_defer_hard_irqs, val); return 0; } @@ -438,7 +442,7 @@ static ssize_t napi_defer_hard_irqs_store(struct device *dev, return netdev_store(dev, attr, buf, len, change_napi_defer_hard_irqs); } -NETDEVICE_SHOW_RW(napi_defer_hard_irqs, fmt_dec); +NETDEVICE_SHOW_RW(napi_defer_hard_irqs, fmt_uint); static ssize_t ifalias_store(struct device *dev, struct device_attribute *attr, const char *buf, size_t len) @@ -1056,7 +1060,7 @@ static const void *rx_queue_namespace(const struct kobject *kobj) struct device *dev = &queue->dev->dev; const void *ns = NULL; - if (dev->class && dev->class->ns_type) + if (dev->class && dev->class->namespace) ns = dev->class->namespace(dev); return ns; @@ -1524,7 +1528,7 @@ static const struct attribute_group dql_group = { }; #else /* Fake declaration, all the code using it should be dead */ -extern const struct attribute_group dql_group; +static const struct attribute_group dql_group = {}; #endif /* CONFIG_BQL */ #ifdef CONFIG_XPS @@ -1740,7 +1744,7 @@ static const void *netdev_queue_namespace(const struct kobject *kobj) struct device *dev = &queue->dev->dev; const void *ns = NULL; - if (dev->class && dev->class->ns_type) + if (dev->class && dev->class->namespace) ns = dev->class->namespace(dev); return ns; @@ -1764,8 +1768,7 @@ static const struct kobj_type netdev_queue_ktype = { static bool netdev_uses_bql(const struct net_device *dev) { - if (dev->features & NETIF_F_LLTX || - dev->priv_flags & IFF_NO_QUEUE) + if (dev->lltx || (dev->priv_flags & IFF_NO_QUEUE)) return false; return IS_ENABLED(CONFIG_BQL); @@ -2028,7 +2031,7 @@ static void netdev_release(struct device *d) * device is dead and about to be freed. */ kfree(rcu_access_pointer(dev->ifalias)); - netdev_freemem(dev); + kvfree(dev); } static const void *net_namespace(const struct device *d) diff --git a/net/core/net_namespace.c b/net/core/net_namespace.c index 6a823ba906c6..e39479f1c9a4 100644 --- a/net/core/net_namespace.c +++ b/net/core/net_namespace.c @@ -125,7 +125,7 @@ static int ops_init(const struct pernet_operations *ops, struct net *net) int err = -ENOMEM; void *data = NULL; - if (ops->id && ops->size) { + if (ops->id) { data = kzalloc(ops->size, GFP_KERNEL); if (!data) goto out; @@ -140,7 +140,7 @@ static int ops_init(const struct pernet_operations *ops, struct net *net) if (!err) return 0; - if (ops->id && ops->size) { + if (ops->id) { ng = rcu_dereference_protected(net->gen, lockdep_is_held(&pernet_ops_rwsem)); ng->ptr[*ops->id] = NULL; @@ -182,7 +182,8 @@ static void ops_free_list(const struct pernet_operations *ops, struct list_head *net_exit_list) { struct net *net; - if (ops->size && ops->id) { + + if (ops->id) { list_for_each_entry(net, net_exit_list, exit_list) kfree(net_generic(net, *ops->id)); } @@ -308,16 +309,38 @@ struct net *get_net_ns_by_id(const struct net *net, int id) } EXPORT_SYMBOL_GPL(get_net_ns_by_id); +static __net_init void preinit_net_sysctl(struct net *net) +{ + net->core.sysctl_somaxconn = SOMAXCONN; + /* Limits per socket sk_omem_alloc usage. + * TCP zerocopy regular usage needs 128 KB. + */ + net->core.sysctl_optmem_max = 128 * 1024; + net->core.sysctl_txrehash = SOCK_TXREHASH_ENABLED; +} + /* init code that must occur even if setup_net() is not called. */ -static __net_init void preinit_net(struct net *net) +static __net_init void preinit_net(struct net *net, struct user_namespace *user_ns) { + refcount_set(&net->passive, 1); + refcount_set(&net->ns.count, 1); + ref_tracker_dir_init(&net->refcnt_tracker, 128, "net refcnt"); ref_tracker_dir_init(&net->notrefcnt_tracker, 128, "net notrefcnt"); + + get_random_bytes(&net->hash_mix, sizeof(u32)); + net->dev_base_seq = 1; + net->user_ns = user_ns; + + idr_init(&net->netns_ids); + spin_lock_init(&net->nsid_lock); + mutex_init(&net->ipv4.ra_mutex); + preinit_net_sysctl(net); } /* * setup_net runs the initializers for the network namespace object. */ -static __net_init int setup_net(struct net *net, struct user_namespace *user_ns) +static __net_init int setup_net(struct net *net) { /* Must be called with pernet_ops_rwsem held */ const struct pernet_operations *ops, *saved_ops; @@ -325,19 +348,9 @@ static __net_init int setup_net(struct net *net, struct user_namespace *user_ns) LIST_HEAD(dev_kill_list); int error = 0; - refcount_set(&net->ns.count, 1); - ref_tracker_dir_init(&net->refcnt_tracker, 128, "net refcnt"); - - refcount_set(&net->passive, 1); - get_random_bytes(&net->hash_mix, sizeof(u32)); preempt_disable(); net->net_cookie = gen_cookie_next(&net_cookie); preempt_enable(); - net->dev_base_seq = 1; - net->user_ns = user_ns; - idr_init(&net->netns_ids); - spin_lock_init(&net->nsid_lock); - mutex_init(&net->ipv4.ra_mutex); list_for_each_entry(ops, &pernet_list, list) { error = ops_init(ops, net); @@ -382,32 +395,6 @@ out_undo: goto out; } -static int __net_init net_defaults_init_net(struct net *net) -{ - net->core.sysctl_somaxconn = SOMAXCONN; - /* Limits per socket sk_omem_alloc usage. - * TCP zerocopy regular usage needs 128 KB. - */ - net->core.sysctl_optmem_max = 128 * 1024; - net->core.sysctl_txrehash = SOCK_TXREHASH_ENABLED; - - return 0; -} - -static struct pernet_operations net_defaults_ops = { - .init = net_defaults_init_net, -}; - -static __init int net_defaults_init(void) -{ - if (register_pernet_subsys(&net_defaults_ops)) - panic("Cannot initialize net default settings"); - - return 0; -} - -core_initcall(net_defaults_init); - #ifdef CONFIG_NET_NS static struct ucounts *inc_net_namespaces(struct user_namespace *ns) { @@ -496,8 +483,7 @@ struct net *copy_net_ns(unsigned long flags, goto dec_ucounts; } - preinit_net(net); - refcount_set(&net->passive, 1); + preinit_net(net, user_ns); net->ucounts = ucounts; get_user_ns(user_ns); @@ -505,7 +491,7 @@ struct net *copy_net_ns(unsigned long flags, if (rv < 0) goto put_userns; - rv = setup_net(net, user_ns); + rv = setup_net(net); up_read(&pernet_ops_rwsem); @@ -711,11 +697,11 @@ struct net *get_net_ns_by_fd(int fd) struct fd f = fdget(fd); struct net *net = ERR_PTR(-EINVAL); - if (!f.file) + if (!fd_file(f)) return ERR_PTR(-EBADF); - if (proc_ns_file(f.file)) { - struct ns_common *ns = get_proc_ns(file_inode(f.file)); + if (proc_ns_file(fd_file(f))) { + struct ns_common *ns = get_proc_ns(file_inode(fd_file(f))); if (ns->ops == &netns_operations) net = get_net(container_of(ns, struct net, ns)); } @@ -1199,9 +1185,10 @@ void __init net_ns_init(void) #ifdef CONFIG_KEYS init_net.key_domain = &init_net_key_domain; #endif + preinit_net(&init_net, &init_user_ns); + down_write(&pernet_ops_rwsem); - preinit_net(&init_net); - if (setup_net(&init_net, &init_user_ns)) + if (setup_net(&init_net)) panic("Could not setup the initial network namespace"); init_net_initialized = true; @@ -1244,7 +1231,7 @@ static int __register_pernet_operations(struct list_head *list, LIST_HEAD(net_exit_list); list_add_tail(&ops->list, list); - if (ops->init || (ops->id && ops->size)) { + if (ops->init || ops->id) { /* We held write locked pernet_ops_rwsem, and parallel * setup_net() and cleanup_net() are not possible. */ @@ -1310,6 +1297,9 @@ static int register_pernet_operations(struct list_head *list, { int error; + if (WARN_ON(!!ops->id ^ !!ops->size)) + return -EINVAL; + if (ops->id) { error = ida_alloc_min(&net_generic_ids, MIN_PERNET_OPS_ID, GFP_KERNEL); diff --git a/net/core/netdev-genl-gen.c b/net/core/netdev-genl-gen.c index 8350a0afa9ec..b28424ae06d5 100644 --- a/net/core/netdev-genl-gen.c +++ b/net/core/netdev-genl-gen.c @@ -9,6 +9,7 @@ #include "netdev-genl-gen.h" #include <uapi/linux/netdev.h> +#include <linux/list.h> /* Integer value ranges */ static const struct netlink_range_validation netdev_a_page_pool_id_range = { @@ -27,6 +28,11 @@ const struct nla_policy netdev_page_pool_info_nl_policy[NETDEV_A_PAGE_POOL_IFIND [NETDEV_A_PAGE_POOL_IFINDEX] = NLA_POLICY_FULL_RANGE(NLA_U32, &netdev_a_page_pool_ifindex_range), }; +const struct nla_policy netdev_queue_id_nl_policy[NETDEV_A_QUEUE_TYPE + 1] = { + [NETDEV_A_QUEUE_ID] = { .type = NLA_U32, }, + [NETDEV_A_QUEUE_TYPE] = NLA_POLICY_MAX(NLA_U32, 1), +}; + /* NETDEV_CMD_DEV_GET - do */ static const struct nla_policy netdev_dev_get_nl_policy[NETDEV_A_DEV_IFINDEX + 1] = { [NETDEV_A_DEV_IFINDEX] = NLA_POLICY_MIN(NLA_U32, 1), @@ -74,6 +80,13 @@ static const struct nla_policy netdev_qstats_get_nl_policy[NETDEV_A_QSTATS_SCOPE [NETDEV_A_QSTATS_SCOPE] = NLA_POLICY_MASK(NLA_UINT, 0x1), }; +/* NETDEV_CMD_BIND_RX - do */ +static const struct nla_policy netdev_bind_rx_nl_policy[NETDEV_A_DMABUF_FD + 1] = { + [NETDEV_A_DMABUF_IFINDEX] = NLA_POLICY_MIN(NLA_U32, 1), + [NETDEV_A_DMABUF_FD] = { .type = NLA_U32, }, + [NETDEV_A_DMABUF_QUEUES] = NLA_POLICY_NESTED(netdev_queue_id_nl_policy), +}; + /* Ops table for netdev */ static const struct genl_split_ops netdev_nl_ops[] = { { @@ -151,6 +164,13 @@ static const struct genl_split_ops netdev_nl_ops[] = { .maxattr = NETDEV_A_QSTATS_SCOPE, .flags = GENL_CMD_CAP_DUMP, }, + { + .cmd = NETDEV_CMD_BIND_RX, + .doit = netdev_nl_bind_rx_doit, + .policy = netdev_bind_rx_nl_policy, + .maxattr = NETDEV_A_DMABUF_FD, + .flags = GENL_ADMIN_PERM | GENL_CMD_CAP_DO, + }, }; static const struct genl_multicast_group netdev_nl_mcgrps[] = { @@ -168,4 +188,7 @@ struct genl_family netdev_nl_family __ro_after_init = { .n_split_ops = ARRAY_SIZE(netdev_nl_ops), .mcgrps = netdev_nl_mcgrps, .n_mcgrps = ARRAY_SIZE(netdev_nl_mcgrps), + .sock_priv_size = sizeof(struct list_head), + .sock_priv_init = (void *)netdev_nl_sock_priv_init, + .sock_priv_destroy = (void *)netdev_nl_sock_priv_destroy, }; diff --git a/net/core/netdev-genl-gen.h b/net/core/netdev-genl-gen.h index 4db40fd5b4a9..8cda334fd042 100644 --- a/net/core/netdev-genl-gen.h +++ b/net/core/netdev-genl-gen.h @@ -10,9 +10,11 @@ #include <net/genetlink.h> #include <uapi/linux/netdev.h> +#include <linux/list.h> /* Common nested types */ extern const struct nla_policy netdev_page_pool_info_nl_policy[NETDEV_A_PAGE_POOL_IFINDEX + 1]; +extern const struct nla_policy netdev_queue_id_nl_policy[NETDEV_A_QUEUE_TYPE + 1]; int netdev_nl_dev_get_doit(struct sk_buff *skb, struct genl_info *info); int netdev_nl_dev_get_dumpit(struct sk_buff *skb, struct netlink_callback *cb); @@ -30,6 +32,7 @@ int netdev_nl_napi_get_doit(struct sk_buff *skb, struct genl_info *info); int netdev_nl_napi_get_dumpit(struct sk_buff *skb, struct netlink_callback *cb); int netdev_nl_qstats_get_dumpit(struct sk_buff *skb, struct netlink_callback *cb); +int netdev_nl_bind_rx_doit(struct sk_buff *skb, struct genl_info *info); enum { NETDEV_NLGRP_MGMT, @@ -38,4 +41,7 @@ enum { extern struct genl_family netdev_nl_family; +void netdev_nl_sock_priv_init(struct list_head *priv); +void netdev_nl_sock_priv_destroy(struct list_head *priv); + #endif /* _LINUX_NETDEV_GEN_H */ diff --git a/net/core/netdev-genl.c b/net/core/netdev-genl.c index 05f9515d2c05..1cb954f2d39e 100644 --- a/net/core/netdev-genl.c +++ b/net/core/netdev-genl.c @@ -3,16 +3,17 @@ #include <linux/netdevice.h> #include <linux/notifier.h> #include <linux/rtnetlink.h> +#include <net/busy_poll.h> #include <net/net_namespace.h> +#include <net/netdev_queues.h> +#include <net/netdev_rx_queue.h> #include <net/sock.h> #include <net/xdp.h> #include <net/xdp_sock.h> -#include <net/netdev_rx_queue.h> -#include <net/netdev_queues.h> -#include <net/busy_poll.h> -#include "netdev-genl-gen.h" #include "dev.h" +#include "devmem.h" +#include "netdev-genl-gen.h" struct netdev_nl_dump_ctx { unsigned long ifindex; @@ -216,10 +217,12 @@ int netdev_nl_napi_get_doit(struct sk_buff *skb, struct genl_info *info) rtnl_lock(); napi = napi_by_id(napi_id); - if (napi) + if (napi) { err = netdev_nl_napi_fill_one(rsp, napi, info); - else - err = -EINVAL; + } else { + NL_SET_BAD_ATTR(info->extack, info->attrs[NETDEV_A_NAPI_ID]); + err = -ENOENT; + } rtnl_unlock(); @@ -292,6 +295,7 @@ static int netdev_nl_queue_fill_one(struct sk_buff *rsp, struct net_device *netdev, u32 q_idx, u32 q_type, const struct genl_info *info) { + struct net_devmem_dmabuf_binding *binding; struct netdev_rx_queue *rxq; struct netdev_queue *txq; void *hdr; @@ -311,6 +315,12 @@ netdev_nl_queue_fill_one(struct sk_buff *rsp, struct net_device *netdev, if (rxq->napi && nla_put_u32(rsp, NETDEV_A_QUEUE_NAPI_ID, rxq->napi->napi_id)) goto nla_put_failure; + + binding = rxq->mp_params.mp_priv; + if (binding && + nla_put_u32(rsp, NETDEV_A_QUEUE_DMABUF, binding->id)) + goto nla_put_failure; + break; case NETDEV_QUEUE_TYPE_TX: txq = netdev_get_tx_queue(netdev, q_idx); @@ -721,6 +731,129 @@ int netdev_nl_qstats_get_dumpit(struct sk_buff *skb, return err; } +int netdev_nl_bind_rx_doit(struct sk_buff *skb, struct genl_info *info) +{ + struct nlattr *tb[ARRAY_SIZE(netdev_queue_id_nl_policy)]; + struct net_devmem_dmabuf_binding *binding; + struct list_head *sock_binding_list; + u32 ifindex, dmabuf_fd, rxq_idx; + struct net_device *netdev; + struct sk_buff *rsp; + struct nlattr *attr; + int rem, err = 0; + void *hdr; + + if (GENL_REQ_ATTR_CHECK(info, NETDEV_A_DEV_IFINDEX) || + GENL_REQ_ATTR_CHECK(info, NETDEV_A_DMABUF_FD) || + GENL_REQ_ATTR_CHECK(info, NETDEV_A_DMABUF_QUEUES)) + return -EINVAL; + + ifindex = nla_get_u32(info->attrs[NETDEV_A_DEV_IFINDEX]); + dmabuf_fd = nla_get_u32(info->attrs[NETDEV_A_DMABUF_FD]); + + sock_binding_list = genl_sk_priv_get(&netdev_nl_family, + NETLINK_CB(skb).sk); + if (IS_ERR(sock_binding_list)) + return PTR_ERR(sock_binding_list); + + rsp = genlmsg_new(GENLMSG_DEFAULT_SIZE, GFP_KERNEL); + if (!rsp) + return -ENOMEM; + + hdr = genlmsg_iput(rsp, info); + if (!hdr) { + err = -EMSGSIZE; + goto err_genlmsg_free; + } + + rtnl_lock(); + + netdev = __dev_get_by_index(genl_info_net(info), ifindex); + if (!netdev || !netif_device_present(netdev)) { + err = -ENODEV; + goto err_unlock; + } + + if (dev_xdp_prog_count(netdev)) { + NL_SET_ERR_MSG(info->extack, "unable to bind dmabuf to device with XDP program attached"); + err = -EEXIST; + goto err_unlock; + } + + binding = net_devmem_bind_dmabuf(netdev, dmabuf_fd, info->extack); + if (IS_ERR(binding)) { + err = PTR_ERR(binding); + goto err_unlock; + } + + nla_for_each_attr_type(attr, NETDEV_A_DMABUF_QUEUES, + genlmsg_data(info->genlhdr), + genlmsg_len(info->genlhdr), rem) { + err = nla_parse_nested( + tb, ARRAY_SIZE(netdev_queue_id_nl_policy) - 1, attr, + netdev_queue_id_nl_policy, info->extack); + if (err < 0) + goto err_unbind; + + if (NL_REQ_ATTR_CHECK(info->extack, attr, tb, NETDEV_A_QUEUE_ID) || + NL_REQ_ATTR_CHECK(info->extack, attr, tb, NETDEV_A_QUEUE_TYPE)) { + err = -EINVAL; + goto err_unbind; + } + + if (nla_get_u32(tb[NETDEV_A_QUEUE_TYPE]) != NETDEV_QUEUE_TYPE_RX) { + NL_SET_BAD_ATTR(info->extack, tb[NETDEV_A_QUEUE_TYPE]); + err = -EINVAL; + goto err_unbind; + } + + rxq_idx = nla_get_u32(tb[NETDEV_A_QUEUE_ID]); + + err = net_devmem_bind_dmabuf_to_queue(netdev, rxq_idx, binding, + info->extack); + if (err) + goto err_unbind; + } + + list_add(&binding->list, sock_binding_list); + + nla_put_u32(rsp, NETDEV_A_DMABUF_ID, binding->id); + genlmsg_end(rsp, hdr); + + err = genlmsg_reply(rsp, info); + if (err) + goto err_unbind; + + rtnl_unlock(); + + return 0; + +err_unbind: + net_devmem_unbind_dmabuf(binding); +err_unlock: + rtnl_unlock(); +err_genlmsg_free: + nlmsg_free(rsp); + return err; +} + +void netdev_nl_sock_priv_init(struct list_head *priv) +{ + INIT_LIST_HEAD(priv); +} + +void netdev_nl_sock_priv_destroy(struct list_head *priv) +{ + struct net_devmem_dmabuf_binding *binding; + struct net_devmem_dmabuf_binding *temp; + + list_for_each_entry_safe(binding, temp, priv, list) { + rtnl_lock(); + net_devmem_unbind_dmabuf(binding); + rtnl_unlock(); + } +} + static int netdev_genl_netdevice_event(struct notifier_block *nb, unsigned long event, void *ptr) { diff --git a/net/core/netdev_rx_queue.c b/net/core/netdev_rx_queue.c new file mode 100644 index 000000000000..e217a5838c87 --- /dev/null +++ b/net/core/netdev_rx_queue.c @@ -0,0 +1,81 @@ +// SPDX-License-Identifier: GPL-2.0-or-later + +#include <linux/netdevice.h> +#include <net/netdev_queues.h> +#include <net/netdev_rx_queue.h> + +#include "page_pool_priv.h" + +int netdev_rx_queue_restart(struct net_device *dev, unsigned int rxq_idx) +{ + struct netdev_rx_queue *rxq = __netif_get_rx_queue(dev, rxq_idx); + void *new_mem, *old_mem; + int err; + + if (!dev->queue_mgmt_ops || !dev->queue_mgmt_ops->ndo_queue_stop || + !dev->queue_mgmt_ops->ndo_queue_mem_free || + !dev->queue_mgmt_ops->ndo_queue_mem_alloc || + !dev->queue_mgmt_ops->ndo_queue_start) + return -EOPNOTSUPP; + + ASSERT_RTNL(); + + new_mem = kvzalloc(dev->queue_mgmt_ops->ndo_queue_mem_size, GFP_KERNEL); + if (!new_mem) + return -ENOMEM; + + old_mem = kvzalloc(dev->queue_mgmt_ops->ndo_queue_mem_size, GFP_KERNEL); + if (!old_mem) { + err = -ENOMEM; + goto err_free_new_mem; + } + + err = dev->queue_mgmt_ops->ndo_queue_mem_alloc(dev, new_mem, rxq_idx); + if (err) + goto err_free_old_mem; + + err = page_pool_check_memory_provider(dev, rxq); + if (err) + goto err_free_new_queue_mem; + + err = dev->queue_mgmt_ops->ndo_queue_stop(dev, old_mem, rxq_idx); + if (err) + goto err_free_new_queue_mem; + + err = dev->queue_mgmt_ops->ndo_queue_start(dev, new_mem, rxq_idx); + if (err) + goto err_start_queue; + + dev->queue_mgmt_ops->ndo_queue_mem_free(dev, old_mem); + + kvfree(old_mem); + kvfree(new_mem); + + return 0; + +err_start_queue: + /* Restarting the queue with old_mem should be successful as we haven't + * changed any of the queue configuration, and there is not much we can + * do to recover from a failure here. + * + * WARN if we fail to recover the old rx queue, and at least free + * old_mem so we don't also leak that. + */ + if (dev->queue_mgmt_ops->ndo_queue_start(dev, old_mem, rxq_idx)) { + WARN(1, + "Failed to restart old queue in error path. RX queue %d may be unhealthy.", + rxq_idx); + dev->queue_mgmt_ops->ndo_queue_mem_free(dev, old_mem); + } + +err_free_new_queue_mem: + dev->queue_mgmt_ops->ndo_queue_mem_free(dev, new_mem); + +err_free_old_mem: + kvfree(old_mem); + +err_free_new_mem: + kvfree(new_mem); + + return err; +} diff --git a/net/core/netmem_priv.h b/net/core/netmem_priv.h new file mode 100644 index 000000000000..7eadb8393e00 --- /dev/null +++ b/net/core/netmem_priv.h @@ -0,0 +1,31 @@ +/* SPDX-License-Identifier: GPL-2.0 */ + +#ifndef __NETMEM_PRIV_H +#define __NETMEM_PRIV_H + +static inline unsigned long netmem_get_pp_magic(netmem_ref netmem) +{ + return __netmem_clear_lsb(netmem)->pp_magic; +} + +static inline void netmem_or_pp_magic(netmem_ref netmem, unsigned long pp_magic) +{ + __netmem_clear_lsb(netmem)->pp_magic |= pp_magic; +} + +static inline void netmem_clear_pp_magic(netmem_ref netmem) +{ + __netmem_clear_lsb(netmem)->pp_magic = 0; +} + +static inline void netmem_set_pp(netmem_ref netmem, struct page_pool *pool) +{ + __netmem_clear_lsb(netmem)->pp = pool; +} + +static inline void netmem_set_dma_addr(netmem_ref netmem, + unsigned long dma_addr) +{ + __netmem_clear_lsb(netmem)->dma_addr = dma_addr; +} +#endif diff --git a/net/core/netpoll.c b/net/core/netpoll.c index 55bcacf67df3..ca52cbe0f63c 100644 --- a/net/core/netpoll.c +++ b/net/core/netpoll.c @@ -48,8 +48,6 @@ static struct sk_buff_head skb_pool; -DEFINE_STATIC_SRCU(netpoll_srcu); - #define USEC_PER_POLL 50 #define MAX_SKB_SIZE \ @@ -162,7 +160,7 @@ static void poll_one_napi(struct napi_struct *napi) if (test_and_set_bit(NAPI_STATE_NPSVC, &napi->state)) return; - /* We explicilty pass the polling call a budget of 0 to + /* We explicitly pass the polling call a budget of 0 to * indicate that we are clearing the Tx path only. */ work = napi->poll(napi, 0); @@ -220,26 +218,21 @@ EXPORT_SYMBOL(netpoll_poll_dev); void netpoll_poll_disable(struct net_device *dev) { struct netpoll_info *ni; - int idx; + might_sleep(); - idx = srcu_read_lock(&netpoll_srcu); - ni = srcu_dereference(dev->npinfo, &netpoll_srcu); + ni = rtnl_dereference(dev->npinfo); if (ni) down(&ni->dev_lock); - srcu_read_unlock(&netpoll_srcu, idx); } -EXPORT_SYMBOL(netpoll_poll_disable); void netpoll_poll_enable(struct net_device *dev) { struct netpoll_info *ni; - rcu_read_lock(); - ni = rcu_dereference(dev->npinfo); + + ni = rtnl_dereference(dev->npinfo); if (ni) up(&ni->dev_lock); - rcu_read_unlock(); } -EXPORT_SYMBOL(netpoll_poll_enable); static void refill_skbs(void) { @@ -626,12 +619,9 @@ int __netpoll_setup(struct netpoll *np, struct net_device *ndev) const struct net_device_ops *ops; int err; - np->dev = ndev; - strscpy(np->dev_name, ndev->name, IFNAMSIZ); - if (ndev->priv_flags & IFF_DISABLE_NETPOLL) { np_err(np, "%s doesn't support polling, aborting\n", - np->dev_name); + ndev->name); err = -ENOTSUPP; goto out; } @@ -649,7 +639,7 @@ int __netpoll_setup(struct netpoll *np, struct net_device *ndev) refcount_set(&npinfo->refcnt, 1); - ops = np->dev->netdev_ops; + ops = ndev->netdev_ops; if (ops->ndo_netpoll_setup) { err = ops->ndo_netpoll_setup(ndev, npinfo); if (err) @@ -660,6 +650,8 @@ int __netpoll_setup(struct netpoll *np, struct net_device *ndev) refcount_inc(&npinfo->refcnt); } + np->dev = ndev; + strscpy(np->dev_name, ndev->name, IFNAMSIZ); npinfo->netpoll = np; /* last thing to do is link it to the net device structure */ @@ -677,6 +669,7 @@ EXPORT_SYMBOL_GPL(__netpoll_setup); int netpoll_setup(struct netpoll *np) { struct net_device *ndev = NULL; + bool ip_overwritten = false; struct in_device *in_dev; int err; @@ -741,6 +734,7 @@ put_noaddr: } np->local_ip.ip = ifa->ifa_local; + ip_overwritten = true; np_info(np, "local IP %pI4\n", &np->local_ip.ip); } else { #if IS_ENABLED(CONFIG_IPV6) @@ -757,6 +751,7 @@ put_noaddr: !!(ipv6_addr_type(&np->remote_ip.in6) & IPV6_ADDR_LINKLOCAL)) continue; np->local_ip.in6 = ifp->addr; + ip_overwritten = true; err = 0; break; } @@ -787,6 +782,9 @@ put_noaddr: return 0; put: + DEBUG_NET_WARN_ON_ONCE(np->dev); + if (ip_overwritten) + memset(&np->local_ip, 0, sizeof(np->local_ip)); netdev_put(ndev, &np->dev_tracker); unlock: rtnl_unlock(); @@ -826,8 +824,6 @@ void __netpoll_cleanup(struct netpoll *np) if (!npinfo) return; - synchronize_srcu(&netpoll_srcu); - if (refcount_dec_and_test(&npinfo->refcnt)) { const struct net_device_ops *ops; @@ -853,14 +849,20 @@ void __netpoll_free(struct netpoll *np) } EXPORT_SYMBOL_GPL(__netpoll_free); +void do_netpoll_cleanup(struct netpoll *np) +{ + __netpoll_cleanup(np); + netdev_put(np->dev, &np->dev_tracker); + np->dev = NULL; +} +EXPORT_SYMBOL(do_netpoll_cleanup); + void netpoll_cleanup(struct netpoll *np) { rtnl_lock(); if (!np->dev) goto out; - __netpoll_cleanup(np); - netdev_put(np->dev, &np->dev_tracker); - np->dev = NULL; + do_netpoll_cleanup(np); out: rtnl_unlock(); } diff --git a/net/core/page_pool.c b/net/core/page_pool.c index f4444b4e39e6..a813d30d2135 100644 --- a/net/core/page_pool.c +++ b/net/core/page_pool.c @@ -11,6 +11,7 @@ #include <linux/slab.h> #include <linux/device.h> +#include <net/netdev_rx_queue.h> #include <net/page_pool/helpers.h> #include <net/xdp.h> @@ -24,8 +25,12 @@ #include <trace/events/page_pool.h> +#include "mp_dmabuf_devmem.h" +#include "netmem_priv.h" #include "page_pool_priv.h" +DEFINE_STATIC_KEY_FALSE(page_pool_mem_providers); + #define DEFER_TIME (msecs_to_jiffies(1000)) #define DEFER_WARN_INTERVAL (60 * HZ) @@ -178,7 +183,8 @@ static void page_pool_struct_check(void) CACHELINE_ASSERT_GROUP_MEMBER(struct page_pool, frag, frag_users); CACHELINE_ASSERT_GROUP_MEMBER(struct page_pool, frag, frag_page); CACHELINE_ASSERT_GROUP_MEMBER(struct page_pool, frag, frag_offset); - CACHELINE_ASSERT_GROUP_SIZE(struct page_pool, frag, 4 * sizeof(long)); + CACHELINE_ASSERT_GROUP_SIZE(struct page_pool, frag, + PAGE_POOL_FRAG_GROUP_ALIGN); } static int page_pool_init(struct page_pool *pool, @@ -186,6 +192,8 @@ static int page_pool_init(struct page_pool *pool, int cpuid) { unsigned int ring_qsize = 1024; /* Default */ + struct netdev_rx_queue *rxq; + int err; page_pool_struct_check(); @@ -267,7 +275,37 @@ static int page_pool_init(struct page_pool *pool, if (pool->dma_map) get_device(pool->p.dev); + if (pool->slow.flags & PP_FLAG_ALLOW_UNREADABLE_NETMEM) { + /* We rely on rtnl_lock()ing to make sure netdev_rx_queue + * configuration doesn't change while we're initializing + * the page_pool. + */ + ASSERT_RTNL(); + rxq = __netif_get_rx_queue(pool->slow.netdev, + pool->slow.queue_idx); + pool->mp_priv = rxq->mp_params.mp_priv; + } + + if (pool->mp_priv) { + err = mp_dmabuf_devmem_init(pool); + if (err) { + pr_warn("%s() mem-provider init failed %d\n", __func__, + err); + goto free_ptr_ring; + } + + static_branch_inc(&page_pool_mem_providers); + } + return 0; + +free_ptr_ring: + ptr_ring_cleanup(&pool->ring, NULL); +#ifdef CONFIG_PAGE_POOL_STATS + if (!pool->system) + free_percpu(pool->recycle_stats); +#endif + return err; } static void page_pool_uninit(struct page_pool *pool) @@ -327,19 +365,18 @@ struct page_pool *page_pool_create(const struct page_pool_params *params) } EXPORT_SYMBOL(page_pool_create); -static void page_pool_return_page(struct page_pool *pool, struct page *page); +static void page_pool_return_page(struct page_pool *pool, netmem_ref netmem); -noinline -static struct page *page_pool_refill_alloc_cache(struct page_pool *pool) +static noinline netmem_ref page_pool_refill_alloc_cache(struct page_pool *pool) { struct ptr_ring *r = &pool->ring; - struct page *page; + netmem_ref netmem; int pref_nid; /* preferred NUMA node */ /* Quicker fallback, avoid locks when ring is empty */ if (__ptr_ring_empty(r)) { alloc_stat_inc(pool, empty); - return NULL; + return 0; } /* Softirq guarantee CPU and thus NUMA node is stable. This, @@ -354,57 +391,57 @@ static struct page *page_pool_refill_alloc_cache(struct page_pool *pool) /* Refill alloc array, but only if NUMA match */ do { - page = __ptr_ring_consume(r); - if (unlikely(!page)) + netmem = (__force netmem_ref)__ptr_ring_consume(r); + if (unlikely(!netmem)) break; - if (likely(page_to_nid(page) == pref_nid)) { - pool->alloc.cache[pool->alloc.count++] = page; + if (likely(netmem_is_pref_nid(netmem, pref_nid))) { + pool->alloc.cache[pool->alloc.count++] = netmem; } else { /* NUMA mismatch; * (1) release 1 page to page-allocator and * (2) break out to fallthrough to alloc_pages_node. * This limit stress on page buddy alloactor. */ - page_pool_return_page(pool, page); + page_pool_return_page(pool, netmem); alloc_stat_inc(pool, waive); - page = NULL; + netmem = 0; break; } } while (pool->alloc.count < PP_ALLOC_CACHE_REFILL); /* Return last page */ if (likely(pool->alloc.count > 0)) { - page = pool->alloc.cache[--pool->alloc.count]; + netmem = pool->alloc.cache[--pool->alloc.count]; alloc_stat_inc(pool, refill); } - return page; + return netmem; } /* fast path */ -static struct page *__page_pool_get_cached(struct page_pool *pool) +static netmem_ref __page_pool_get_cached(struct page_pool *pool) { - struct page *page; + netmem_ref netmem; /* Caller MUST guarantee safe non-concurrent access, e.g. softirq */ if (likely(pool->alloc.count)) { /* Fast-path */ - page = pool->alloc.cache[--pool->alloc.count]; + netmem = pool->alloc.cache[--pool->alloc.count]; alloc_stat_inc(pool, fast); } else { - page = page_pool_refill_alloc_cache(pool); + netmem = page_pool_refill_alloc_cache(pool); } - return page; + return netmem; } static void __page_pool_dma_sync_for_device(const struct page_pool *pool, - const struct page *page, + netmem_ref netmem, u32 dma_sync_size) { #if defined(CONFIG_HAS_DMA) && defined(CONFIG_DMA_NEED_SYNC) - dma_addr_t dma_addr = page_pool_get_dma_addr(page); + dma_addr_t dma_addr = page_pool_get_dma_addr_netmem(netmem); dma_sync_size = min(dma_sync_size, pool->p.max_len); __dma_sync_single_for_device(pool->p.dev, dma_addr + pool->p.offset, @@ -414,14 +451,14 @@ static void __page_pool_dma_sync_for_device(const struct page_pool *pool, static __always_inline void page_pool_dma_sync_for_device(const struct page_pool *pool, - const struct page *page, + netmem_ref netmem, u32 dma_sync_size) { if (pool->dma_sync && dma_dev_need_sync(pool->p.dev)) - __page_pool_dma_sync_for_device(pool, page, dma_sync_size); + __page_pool_dma_sync_for_device(pool, netmem, dma_sync_size); } -static bool page_pool_dma_map(struct page_pool *pool, struct page *page) +static bool page_pool_dma_map(struct page_pool *pool, netmem_ref netmem) { dma_addr_t dma; @@ -430,51 +467,28 @@ static bool page_pool_dma_map(struct page_pool *pool, struct page *page) * into page private data (i.e 32bit cpu with 64bit DMA caps) * This mapping is kept for lifetime of page, until leaving pool. */ - dma = dma_map_page_attrs(pool->p.dev, page, 0, - (PAGE_SIZE << pool->p.order), - pool->p.dma_dir, DMA_ATTR_SKIP_CPU_SYNC | - DMA_ATTR_WEAK_ORDERING); + dma = dma_map_page_attrs(pool->p.dev, netmem_to_page(netmem), 0, + (PAGE_SIZE << pool->p.order), pool->p.dma_dir, + DMA_ATTR_SKIP_CPU_SYNC | + DMA_ATTR_WEAK_ORDERING); if (dma_mapping_error(pool->p.dev, dma)) return false; - if (page_pool_set_dma_addr(page, dma)) + if (page_pool_set_dma_addr_netmem(netmem, dma)) goto unmap_failed; - page_pool_dma_sync_for_device(pool, page, pool->p.max_len); + page_pool_dma_sync_for_device(pool, netmem, pool->p.max_len); return true; unmap_failed: - WARN_ON_ONCE("unexpected DMA address, please report to netdev@"); + WARN_ONCE(1, "unexpected DMA address, please report to netdev@"); dma_unmap_page_attrs(pool->p.dev, dma, PAGE_SIZE << pool->p.order, pool->p.dma_dir, DMA_ATTR_SKIP_CPU_SYNC | DMA_ATTR_WEAK_ORDERING); return false; } -static void page_pool_set_pp_info(struct page_pool *pool, - struct page *page) -{ - page->pp = pool; - page->pp_magic |= PP_SIGNATURE; - - /* Ensuring all pages have been split into one fragment initially: - * page_pool_set_pp_info() is only called once for every page when it - * is allocated from the page allocator and page_pool_fragment_page() - * is dirtying the same cache line as the page->pp_magic above, so - * the overhead is negligible. - */ - page_pool_fragment_page(page, 1); - if (pool->has_init_callback) - pool->slow.init_callback(page, pool->slow.init_arg); -} - -static void page_pool_clear_pp_info(struct page *page) -{ - page->pp_magic = 0; - page->pp = NULL; -} - static struct page *__page_pool_alloc_page_order(struct page_pool *pool, gfp_t gfp) { @@ -485,34 +499,34 @@ static struct page *__page_pool_alloc_page_order(struct page_pool *pool, if (unlikely(!page)) return NULL; - if (pool->dma_map && unlikely(!page_pool_dma_map(pool, page))) { + if (pool->dma_map && unlikely(!page_pool_dma_map(pool, page_to_netmem(page)))) { put_page(page); return NULL; } alloc_stat_inc(pool, slow_high_order); - page_pool_set_pp_info(pool, page); + page_pool_set_pp_info(pool, page_to_netmem(page)); /* Track how many pages are held 'in-flight' */ pool->pages_state_hold_cnt++; - trace_page_pool_state_hold(pool, page, pool->pages_state_hold_cnt); + trace_page_pool_state_hold(pool, page_to_netmem(page), + pool->pages_state_hold_cnt); return page; } /* slow path */ -noinline -static struct page *__page_pool_alloc_pages_slow(struct page_pool *pool, - gfp_t gfp) +static noinline netmem_ref __page_pool_alloc_pages_slow(struct page_pool *pool, + gfp_t gfp) { const int bulk = PP_ALLOC_CACHE_REFILL; unsigned int pp_order = pool->p.order; bool dma_map = pool->dma_map; - struct page *page; + netmem_ref netmem; int i, nr_pages; /* Don't support bulk alloc for high-order pages */ if (unlikely(pp_order)) - return __page_pool_alloc_page_order(pool, gfp); + return page_to_netmem(__page_pool_alloc_page_order(pool, gfp)); /* Unnecessary as alloc cache is empty, but guarantees zero count */ if (unlikely(pool->alloc.count > 0)) @@ -521,56 +535,66 @@ static struct page *__page_pool_alloc_pages_slow(struct page_pool *pool, /* Mark empty alloc.cache slots "empty" for alloc_pages_bulk_array */ memset(&pool->alloc.cache, 0, sizeof(void *) * bulk); - nr_pages = alloc_pages_bulk_array_node(gfp, pool->p.nid, bulk, - pool->alloc.cache); + nr_pages = alloc_pages_bulk_array_node(gfp, + pool->p.nid, bulk, + (struct page **)pool->alloc.cache); if (unlikely(!nr_pages)) - return NULL; + return 0; /* Pages have been filled into alloc.cache array, but count is zero and * page element have not been (possibly) DMA mapped. */ for (i = 0; i < nr_pages; i++) { - page = pool->alloc.cache[i]; - if (dma_map && unlikely(!page_pool_dma_map(pool, page))) { - put_page(page); + netmem = pool->alloc.cache[i]; + if (dma_map && unlikely(!page_pool_dma_map(pool, netmem))) { + put_page(netmem_to_page(netmem)); continue; } - page_pool_set_pp_info(pool, page); - pool->alloc.cache[pool->alloc.count++] = page; + page_pool_set_pp_info(pool, netmem); + pool->alloc.cache[pool->alloc.count++] = netmem; /* Track how many pages are held 'in-flight' */ pool->pages_state_hold_cnt++; - trace_page_pool_state_hold(pool, page, + trace_page_pool_state_hold(pool, netmem, pool->pages_state_hold_cnt); } /* Return last page */ if (likely(pool->alloc.count > 0)) { - page = pool->alloc.cache[--pool->alloc.count]; + netmem = pool->alloc.cache[--pool->alloc.count]; alloc_stat_inc(pool, slow); } else { - page = NULL; + netmem = 0; } /* When page just alloc'ed is should/must have refcnt 1. */ - return page; + return netmem; } /* For using page_pool replace: alloc_pages() API calls, but provide * synchronization guarantee for allocation side. */ -struct page *page_pool_alloc_pages(struct page_pool *pool, gfp_t gfp) +netmem_ref page_pool_alloc_netmem(struct page_pool *pool, gfp_t gfp) { - struct page *page; + netmem_ref netmem; /* Fast-path: Get a page from cache */ - page = __page_pool_get_cached(pool); - if (page) - return page; + netmem = __page_pool_get_cached(pool); + if (netmem) + return netmem; /* Slow-path: cache empty, do real allocation */ - page = __page_pool_alloc_pages_slow(pool, gfp); - return page; + if (static_branch_unlikely(&page_pool_mem_providers) && pool->mp_priv) + netmem = mp_dmabuf_devmem_alloc_netmems(pool, gfp); + else + netmem = __page_pool_alloc_pages_slow(pool, gfp); + return netmem; +} +EXPORT_SYMBOL(page_pool_alloc_netmem); + +struct page *page_pool_alloc_pages(struct page_pool *pool, gfp_t gfp) +{ + return netmem_to_page(page_pool_alloc_netmem(pool, gfp)); } EXPORT_SYMBOL(page_pool_alloc_pages); ALLOW_ERROR_INJECTION(page_pool_alloc_pages, NULL); @@ -599,8 +623,30 @@ s32 page_pool_inflight(const struct page_pool *pool, bool strict) return inflight; } -static __always_inline -void __page_pool_release_page_dma(struct page_pool *pool, struct page *page) +void page_pool_set_pp_info(struct page_pool *pool, netmem_ref netmem) +{ + netmem_set_pp(netmem, pool); + netmem_or_pp_magic(netmem, PP_SIGNATURE); + + /* Ensuring all pages have been split into one fragment initially: + * page_pool_set_pp_info() is only called once for every page when it + * is allocated from the page allocator and page_pool_fragment_page() + * is dirtying the same cache line as the page->pp_magic above, so + * the overhead is negligible. + */ + page_pool_fragment_netmem(netmem, 1); + if (pool->has_init_callback) + pool->slow.init_callback(netmem, pool->slow.init_arg); +} + +void page_pool_clear_pp_info(netmem_ref netmem) +{ + netmem_clear_pp_magic(netmem); + netmem_set_pp(netmem, NULL); +} + +static __always_inline void __page_pool_release_page_dma(struct page_pool *pool, + netmem_ref netmem) { dma_addr_t dma; @@ -610,13 +656,13 @@ void __page_pool_release_page_dma(struct page_pool *pool, struct page *page) */ return; - dma = page_pool_get_dma_addr(page); + dma = page_pool_get_dma_addr_netmem(netmem); /* When page is unmapped, it cannot be returned to our pool */ dma_unmap_page_attrs(pool->p.dev, dma, PAGE_SIZE << pool->p.order, pool->p.dma_dir, DMA_ATTR_SKIP_CPU_SYNC | DMA_ATTR_WEAK_ORDERING); - page_pool_set_dma_addr(page, 0); + page_pool_set_dma_addr_netmem(netmem, 0); } /* Disconnects a page (from a page_pool). API users can have a need @@ -624,35 +670,41 @@ void __page_pool_release_page_dma(struct page_pool *pool, struct page *page) * a regular page (that will eventually be returned to the normal * page-allocator via put_page). */ -void page_pool_return_page(struct page_pool *pool, struct page *page) +void page_pool_return_page(struct page_pool *pool, netmem_ref netmem) { int count; + bool put; - __page_pool_release_page_dma(pool, page); - - page_pool_clear_pp_info(page); + put = true; + if (static_branch_unlikely(&page_pool_mem_providers) && pool->mp_priv) + put = mp_dmabuf_devmem_release_page(pool, netmem); + else + __page_pool_release_page_dma(pool, netmem); /* This may be the last page returned, releasing the pool, so * it is not safe to reference pool afterwards. */ count = atomic_inc_return_relaxed(&pool->pages_state_release_cnt); - trace_page_pool_state_release(pool, page, count); + trace_page_pool_state_release(pool, netmem, count); - put_page(page); + if (put) { + page_pool_clear_pp_info(netmem); + put_page(netmem_to_page(netmem)); + } /* An optimization would be to call __free_pages(page, pool->p.order) * knowing page is not part of page-cache (thus avoiding a * __page_cache_release() call). */ } -static bool page_pool_recycle_in_ring(struct page_pool *pool, struct page *page) +static bool page_pool_recycle_in_ring(struct page_pool *pool, netmem_ref netmem) { int ret; /* BH protection not needed if current is softirq */ if (in_softirq()) - ret = ptr_ring_produce(&pool->ring, page); + ret = ptr_ring_produce(&pool->ring, (__force void *)netmem); else - ret = ptr_ring_produce_bh(&pool->ring, page); + ret = ptr_ring_produce_bh(&pool->ring, (__force void *)netmem); if (!ret) { recycle_stat_inc(pool, ring); @@ -667,7 +719,7 @@ static bool page_pool_recycle_in_ring(struct page_pool *pool, struct page *page) * * Caller must provide appropriate safe context. */ -static bool page_pool_recycle_in_cache(struct page *page, +static bool page_pool_recycle_in_cache(netmem_ref netmem, struct page_pool *pool) { if (unlikely(pool->alloc.count == PP_ALLOC_CACHE_SIZE)) { @@ -676,14 +728,16 @@ static bool page_pool_recycle_in_cache(struct page *page, } /* Caller MUST have verified/know (page_ref_count(page) == 1) */ - pool->alloc.cache[pool->alloc.count++] = page; + pool->alloc.cache[pool->alloc.count++] = netmem; recycle_stat_inc(pool, cached); return true; } -static bool __page_pool_page_can_be_recycled(const struct page *page) +static bool __page_pool_page_can_be_recycled(netmem_ref netmem) { - return page_ref_count(page) == 1 && !page_is_pfmemalloc(page); + return netmem_is_net_iov(netmem) || + (page_ref_count(netmem_to_page(netmem)) == 1 && + !page_is_pfmemalloc(netmem_to_page(netmem))); } /* If the page refcnt == 1, this will try to recycle the page. @@ -692,8 +746,8 @@ static bool __page_pool_page_can_be_recycled(const struct page *page) * If the page refcnt != 1, then the page will be returned to memory * subsystem. */ -static __always_inline struct page * -__page_pool_put_page(struct page_pool *pool, struct page *page, +static __always_inline netmem_ref +__page_pool_put_page(struct page_pool *pool, netmem_ref netmem, unsigned int dma_sync_size, bool allow_direct) { lockdep_assert_no_hardirq(); @@ -707,17 +761,18 @@ __page_pool_put_page(struct page_pool *pool, struct page *page, * page is NOT reusable when allocated when system is under * some pressure. (page_is_pfmemalloc) */ - if (likely(__page_pool_page_can_be_recycled(page))) { + if (likely(__page_pool_page_can_be_recycled(netmem))) { /* Read barrier done in page_ref_count / READ_ONCE */ - page_pool_dma_sync_for_device(pool, page, dma_sync_size); + page_pool_dma_sync_for_device(pool, netmem, dma_sync_size); - if (allow_direct && page_pool_recycle_in_cache(page, pool)) - return NULL; + if (allow_direct && page_pool_recycle_in_cache(netmem, pool)) + return 0; /* Page found as candidate for recycling */ - return page; + return netmem; } + /* Fallback/non-XDP mode: API user have elevated refcnt. * * Many drivers split up the page into fragments, and some @@ -732,9 +787,9 @@ __page_pool_put_page(struct page_pool *pool, struct page *page, * will be invoking put_page. */ recycle_stat_inc(pool, released_refcnt); - page_pool_return_page(pool, page); + page_pool_return_page(pool, netmem); - return NULL; + return 0; } static bool page_pool_napi_local(const struct page_pool *pool) @@ -760,19 +815,28 @@ static bool page_pool_napi_local(const struct page_pool *pool) return napi && READ_ONCE(napi->list_owner) == cpuid; } -void page_pool_put_unrefed_page(struct page_pool *pool, struct page *page, - unsigned int dma_sync_size, bool allow_direct) +void page_pool_put_unrefed_netmem(struct page_pool *pool, netmem_ref netmem, + unsigned int dma_sync_size, bool allow_direct) { if (!allow_direct) allow_direct = page_pool_napi_local(pool); - page = __page_pool_put_page(pool, page, dma_sync_size, allow_direct); - if (page && !page_pool_recycle_in_ring(pool, page)) { + netmem = + __page_pool_put_page(pool, netmem, dma_sync_size, allow_direct); + if (netmem && !page_pool_recycle_in_ring(pool, netmem)) { /* Cache full, fallback to free pages */ recycle_stat_inc(pool, ring_full); - page_pool_return_page(pool, page); + page_pool_return_page(pool, netmem); } } +EXPORT_SYMBOL(page_pool_put_unrefed_netmem); + +void page_pool_put_unrefed_page(struct page_pool *pool, struct page *page, + unsigned int dma_sync_size, bool allow_direct) +{ + page_pool_put_unrefed_netmem(pool, page_to_netmem(page), dma_sync_size, + allow_direct); +} EXPORT_SYMBOL(page_pool_put_unrefed_page); /** @@ -800,16 +864,16 @@ void page_pool_put_page_bulk(struct page_pool *pool, void **data, allow_direct = page_pool_napi_local(pool); for (i = 0; i < count; i++) { - struct page *page = virt_to_head_page(data[i]); + netmem_ref netmem = page_to_netmem(virt_to_head_page(data[i])); /* It is not the last user for the page frag case */ - if (!page_pool_is_last_ref(page)) + if (!page_pool_is_last_ref(netmem)) continue; - page = __page_pool_put_page(pool, page, -1, allow_direct); + netmem = __page_pool_put_page(pool, netmem, -1, allow_direct); /* Approved for bulk recycling in ptr_ring cache */ - if (page) - data[bulk_len++] = page; + if (netmem) + data[bulk_len++] = (__force void *)netmem; } if (!bulk_len) @@ -835,98 +899,106 @@ void page_pool_put_page_bulk(struct page_pool *pool, void **data, * since put_page() with refcnt == 1 can be an expensive operation */ for (; i < bulk_len; i++) - page_pool_return_page(pool, data[i]); + page_pool_return_page(pool, (__force netmem_ref)data[i]); } EXPORT_SYMBOL(page_pool_put_page_bulk); -static struct page *page_pool_drain_frag(struct page_pool *pool, - struct page *page) +static netmem_ref page_pool_drain_frag(struct page_pool *pool, + netmem_ref netmem) { long drain_count = BIAS_MAX - pool->frag_users; /* Some user is still using the page frag */ - if (likely(page_pool_unref_page(page, drain_count))) - return NULL; + if (likely(page_pool_unref_netmem(netmem, drain_count))) + return 0; - if (__page_pool_page_can_be_recycled(page)) { - page_pool_dma_sync_for_device(pool, page, -1); - return page; + if (__page_pool_page_can_be_recycled(netmem)) { + page_pool_dma_sync_for_device(pool, netmem, -1); + return netmem; } - page_pool_return_page(pool, page); - return NULL; + page_pool_return_page(pool, netmem); + return 0; } static void page_pool_free_frag(struct page_pool *pool) { long drain_count = BIAS_MAX - pool->frag_users; - struct page *page = pool->frag_page; + netmem_ref netmem = pool->frag_page; - pool->frag_page = NULL; + pool->frag_page = 0; - if (!page || page_pool_unref_page(page, drain_count)) + if (!netmem || page_pool_unref_netmem(netmem, drain_count)) return; - page_pool_return_page(pool, page); + page_pool_return_page(pool, netmem); } -struct page *page_pool_alloc_frag(struct page_pool *pool, - unsigned int *offset, - unsigned int size, gfp_t gfp) +netmem_ref page_pool_alloc_frag_netmem(struct page_pool *pool, + unsigned int *offset, unsigned int size, + gfp_t gfp) { unsigned int max_size = PAGE_SIZE << pool->p.order; - struct page *page = pool->frag_page; + netmem_ref netmem = pool->frag_page; if (WARN_ON(size > max_size)) - return NULL; + return 0; size = ALIGN(size, dma_get_cache_alignment()); *offset = pool->frag_offset; - if (page && *offset + size > max_size) { - page = page_pool_drain_frag(pool, page); - if (page) { + if (netmem && *offset + size > max_size) { + netmem = page_pool_drain_frag(pool, netmem); + if (netmem) { alloc_stat_inc(pool, fast); goto frag_reset; } } - if (!page) { - page = page_pool_alloc_pages(pool, gfp); - if (unlikely(!page)) { - pool->frag_page = NULL; - return NULL; + if (!netmem) { + netmem = page_pool_alloc_netmem(pool, gfp); + if (unlikely(!netmem)) { + pool->frag_page = 0; + return 0; } - pool->frag_page = page; + pool->frag_page = netmem; frag_reset: pool->frag_users = 1; *offset = 0; pool->frag_offset = size; - page_pool_fragment_page(page, BIAS_MAX); - return page; + page_pool_fragment_netmem(netmem, BIAS_MAX); + return netmem; } pool->frag_users++; pool->frag_offset = *offset + size; alloc_stat_inc(pool, fast); - return page; + return netmem; +} +EXPORT_SYMBOL(page_pool_alloc_frag_netmem); + +struct page *page_pool_alloc_frag(struct page_pool *pool, unsigned int *offset, + unsigned int size, gfp_t gfp) +{ + return netmem_to_page(page_pool_alloc_frag_netmem(pool, offset, size, + gfp)); } EXPORT_SYMBOL(page_pool_alloc_frag); static void page_pool_empty_ring(struct page_pool *pool) { - struct page *page; + netmem_ref netmem; /* Empty recycle ring */ - while ((page = ptr_ring_consume_bh(&pool->ring))) { + while ((netmem = (__force netmem_ref)ptr_ring_consume_bh(&pool->ring))) { /* Verify the refcnt invariant of cached pages */ - if (!(page_ref_count(page) == 1)) + if (!(netmem_ref_count(netmem) == 1)) pr_crit("%s() page_pool refcnt %d violation\n", - __func__, page_ref_count(page)); + __func__, netmem_ref_count(netmem)); - page_pool_return_page(pool, page); + page_pool_return_page(pool, netmem); } } @@ -937,12 +1009,18 @@ static void __page_pool_destroy(struct page_pool *pool) page_pool_unlist(pool); page_pool_uninit(pool); + + if (pool->mp_priv) { + mp_dmabuf_devmem_destroy(pool); + static_branch_dec(&page_pool_mem_providers); + } + kfree(pool); } static void page_pool_empty_alloc_cache_once(struct page_pool *pool) { - struct page *page; + netmem_ref netmem; if (pool->destroy_cnt) return; @@ -952,8 +1030,8 @@ static void page_pool_empty_alloc_cache_once(struct page_pool *pool) * call concurrently. */ while (pool->alloc.count) { - page = pool->alloc.cache[--pool->alloc.count]; - page_pool_return_page(pool, page); + netmem = pool->alloc.cache[--pool->alloc.count]; + page_pool_return_page(pool, netmem); } } @@ -1014,7 +1092,7 @@ void page_pool_use_xdp_mem(struct page_pool *pool, void (*disconnect)(void *), pool->xdp_mem_id = mem->id; } -static void page_pool_disable_direct_recycling(struct page_pool *pool) +void page_pool_disable_direct_recycling(struct page_pool *pool) { /* Disable direct recycling based on pool->cpuid. * Paired with READ_ONCE() in page_pool_napi_local(). @@ -1027,11 +1105,12 @@ static void page_pool_disable_direct_recycling(struct page_pool *pool) /* To avoid races with recycling and additional barriers make sure * pool and NAPI are unlinked when NAPI is disabled. */ - WARN_ON(!test_bit(NAPI_STATE_SCHED, &pool->p.napi->state) || - READ_ONCE(pool->p.napi->list_owner) != -1); + WARN_ON(!test_bit(NAPI_STATE_SCHED, &pool->p.napi->state)); + WARN_ON(READ_ONCE(pool->p.napi->list_owner) != -1); WRITE_ONCE(pool->p.napi, NULL); } +EXPORT_SYMBOL(page_pool_disable_direct_recycling); void page_pool_destroy(struct page_pool *pool) { @@ -1059,15 +1138,15 @@ EXPORT_SYMBOL(page_pool_destroy); /* Caller must provide appropriate safe context, e.g. NAPI. */ void page_pool_update_nid(struct page_pool *pool, int new_nid) { - struct page *page; + netmem_ref netmem; trace_page_pool_update_nid(pool, new_nid); pool->p.nid = new_nid; /* Flush pool alloc cache, as refill will check NUMA node */ while (pool->alloc.count) { - page = pool->alloc.cache[--pool->alloc.count]; - page_pool_return_page(pool, page); + netmem = pool->alloc.cache[--pool->alloc.count]; + page_pool_return_page(pool, netmem); } } EXPORT_SYMBOL(page_pool_update_nid); diff --git a/net/core/page_pool_priv.h b/net/core/page_pool_priv.h index 90665d40f1eb..57439787b9c2 100644 --- a/net/core/page_pool_priv.h +++ b/net/core/page_pool_priv.h @@ -3,10 +3,56 @@ #ifndef __PAGE_POOL_PRIV_H #define __PAGE_POOL_PRIV_H +#include <net/page_pool/helpers.h> + +#include "netmem_priv.h" + s32 page_pool_inflight(const struct page_pool *pool, bool strict); int page_pool_list(struct page_pool *pool); void page_pool_detached(struct page_pool *pool); void page_pool_unlist(struct page_pool *pool); +static inline bool +page_pool_set_dma_addr_netmem(netmem_ref netmem, dma_addr_t addr) +{ + if (PAGE_POOL_32BIT_ARCH_WITH_64BIT_DMA) { + netmem_set_dma_addr(netmem, addr >> PAGE_SHIFT); + + /* We assume page alignment to shave off bottom bits, + * if this "compression" doesn't work we need to drop. + */ + return addr != (dma_addr_t)netmem_get_dma_addr(netmem) + << PAGE_SHIFT; + } + + netmem_set_dma_addr(netmem, addr); + return false; +} + +static inline bool page_pool_set_dma_addr(struct page *page, dma_addr_t addr) +{ + return page_pool_set_dma_addr_netmem(page_to_netmem(page), addr); +} + +#if defined(CONFIG_PAGE_POOL) +void page_pool_set_pp_info(struct page_pool *pool, netmem_ref netmem); +void page_pool_clear_pp_info(netmem_ref netmem); +int page_pool_check_memory_provider(struct net_device *dev, + struct netdev_rx_queue *rxq); +#else +static inline void page_pool_set_pp_info(struct page_pool *pool, + netmem_ref netmem) +{ +} +static inline void page_pool_clear_pp_info(netmem_ref netmem) +{ +} +static inline int page_pool_check_memory_provider(struct net_device *dev, + struct netdev_rx_queue *rxq) +{ + return 0; +} +#endif + #endif diff --git a/net/core/page_pool_user.c b/net/core/page_pool_user.c index 3a3277ba167b..48335766c1bf 100644 --- a/net/core/page_pool_user.c +++ b/net/core/page_pool_user.c @@ -4,10 +4,12 @@ #include <linux/netdevice.h> #include <linux/xarray.h> #include <net/net_debug.h> -#include <net/page_pool/types.h> +#include <net/netdev_rx_queue.h> #include <net/page_pool/helpers.h> +#include <net/page_pool/types.h> #include <net/sock.h> +#include "devmem.h" #include "page_pool_priv.h" #include "netdev-genl-gen.h" @@ -212,6 +214,7 @@ static int page_pool_nl_fill(struct sk_buff *rsp, const struct page_pool *pool, const struct genl_info *info) { + struct net_devmem_dmabuf_binding *binding = pool->mp_priv; size_t inflight, refsz; void *hdr; @@ -241,6 +244,9 @@ page_pool_nl_fill(struct sk_buff *rsp, const struct page_pool *pool, pool->user.detach_time)) goto err_cancel; + if (binding && nla_put_u32(rsp, NETDEV_A_PAGE_POOL_DMABUF, binding->id)) + goto err_cancel; + genlmsg_end(rsp, hdr); return 0; @@ -344,6 +350,30 @@ void page_pool_unlist(struct page_pool *pool) mutex_unlock(&page_pools_lock); } +int page_pool_check_memory_provider(struct net_device *dev, + struct netdev_rx_queue *rxq) +{ + struct net_devmem_dmabuf_binding *binding = rxq->mp_params.mp_priv; + struct page_pool *pool; + struct hlist_node *n; + + if (!binding) + return 0; + + mutex_lock(&page_pools_lock); + hlist_for_each_entry_safe(pool, n, &dev->page_pools, user.list) { + if (pool->mp_priv != binding) + continue; + + if (pool->slow.queue_idx == get_netdev_rx_queue_index(rxq)) { + mutex_unlock(&page_pools_lock); + return 0; + } + } + mutex_unlock(&page_pools_lock); + return -ENODATA; +} + static void page_pool_unreg_netdev_wipe(struct net_device *netdev) { struct page_pool *pool; diff --git a/net/core/pktgen.c b/net/core/pktgen.c index ea55a758a475..34f68ef74b8f 100644 --- a/net/core/pktgen.c +++ b/net/core/pktgen.c @@ -69,7 +69,7 @@ * * By design there should only be *one* "controlling" process. In practice * multiple write accesses gives unpredictable result. Understood by "write" - * to /proc gives result code thats should be read be the "writer". + * to /proc gives result code that should be read be the "writer". * For practical use this should be no problem. * * Note when adding devices to a specific CPU there good idea to also assign @@ -2371,11 +2371,11 @@ static void get_ipsec_sa(struct pktgen_dev *pkt_dev, int flow) if (pkt_dev->spi) { /* We need as quick as possible to find the right SA - * Searching with minimum criteria to archieve this. + * Searching with minimum criteria to achieve, this. */ x = xfrm_state_lookup_byspi(pn->net, htonl(pkt_dev->spi), AF_INET); } else { - /* slow path: we dont already have xfrm_state */ + /* slow path: we don't already have xfrm_state */ x = xfrm_stateonly_find(pn->net, DUMMY_MARK, 0, (xfrm_address_t *)&pkt_dev->cur_daddr, (xfrm_address_t *)&pkt_dev->cur_saddr, @@ -3654,7 +3654,7 @@ static int pktgen_thread_worker(void *arg) struct pktgen_dev *pkt_dev = NULL; int cpu = t->cpu; - WARN_ON(smp_processor_id() != cpu); + WARN_ON_ONCE(smp_processor_id() != cpu); init_waitqueue_head(&t->queue); complete(&t->start_done); @@ -3838,8 +3838,8 @@ static int pktgen_add_device(struct pktgen_thread *t, const char *ifname) pkt_dev->ipsmode = XFRM_MODE_TRANSPORT; pkt_dev->ipsproto = IPPROTO_ESP; - /* xfrm tunnel mode needs additional dst to extract outter - * ip header protocol/ttl/id field, here creat a phony one. + /* xfrm tunnel mode needs additional dst to extract outer + * ip header protocol/ttl/id field, here create a phony one. * instead of looking for a valid rt, which definitely hurting * performance under such circumstance. */ @@ -3989,6 +3989,7 @@ static int __net_init pg_net_init(struct net *net) goto remove; } + cpus_read_lock(); for_each_online_cpu(cpu) { int err; @@ -3997,6 +3998,7 @@ static int __net_init pg_net_init(struct net *net) pr_warn("Cannot create thread for cpu %d (%d)\n", cpu, err); } + cpus_read_unlock(); if (list_empty(&pn->pktgen_threads)) { pr_err("Initialization failed for all threads\n"); diff --git a/net/core/rtnetlink.c b/net/core/rtnetlink.c index 4668d6718040..f0a520987085 100644 --- a/net/core/rtnetlink.c +++ b/net/core/rtnetlink.c @@ -2724,7 +2724,7 @@ static int do_set_proto_down(struct net_device *dev, bool proto_down; int err; - if (!(dev->priv_flags & IFF_CHANGE_PROTO_DOWN)) { + if (!dev->change_proto_down) { NL_SET_ERR_MSG(extack, "Protodown not supported by device"); return -EOPNOTSUPP; } @@ -3288,7 +3288,7 @@ static int rtnl_dellink(struct sk_buff *skb, struct nlmsghdr *nlh, if (ifm->ifi_index > 0) dev = __dev_get_by_index(tgt_net, ifm->ifi_index); else if (tb[IFLA_IFNAME] || tb[IFLA_ALT_IFNAME]) - dev = rtnl_dev_get(net, tb); + dev = rtnl_dev_get(tgt_net, tb); else if (tb[IFLA_GROUP]) err = rtnl_group_dellink(tgt_net, nla_get_u32(tb[IFLA_GROUP])); else @@ -3969,22 +3969,28 @@ static int rtnl_dellinkprop(struct sk_buff *skb, struct nlmsghdr *nlh, return rtnl_linkprop(RTM_DELLINKPROP, skb, nlh, extack); } -static u32 rtnl_calcit(struct sk_buff *skb, struct nlmsghdr *nlh) +static noinline_for_stack u32 rtnl_calcit(struct sk_buff *skb, + struct nlmsghdr *nlh) { struct net *net = sock_net(skb->sk); size_t min_ifinfo_dump_size = 0; - struct nlattr *tb[IFLA_MAX+1]; u32 ext_filter_mask = 0; struct net_device *dev; - int hdrlen; + struct nlattr *nla; + int hdrlen, rem; /* Same kernel<->userspace interface hack as in rtnl_dump_ifinfo. */ hdrlen = nlmsg_len(nlh) < sizeof(struct ifinfomsg) ? sizeof(struct rtgenmsg) : sizeof(struct ifinfomsg); - if (nlmsg_parse_deprecated(nlh, hdrlen, tb, IFLA_MAX, ifla_policy, NULL) >= 0) { - if (tb[IFLA_EXT_MASK]) - ext_filter_mask = nla_get_u32(tb[IFLA_EXT_MASK]); + if (nlh->nlmsg_len < nlmsg_msg_size(hdrlen)) + return NLMSG_GOODSIZE; + + nla_for_each_attr_type(nla, IFLA_EXT_MASK, + nlmsg_attrdata(nlh, hdrlen), + nlmsg_attrlen(nlh, hdrlen), rem) { + if (nla_len(nla) == sizeof(u32)) + ext_filter_mask = nla_get_u32(nla); } if (!ext_filter_mask) @@ -4081,8 +4087,7 @@ struct sk_buff *rtmsg_ifinfo_build_skb(int type, struct net_device *dev, } return skb; errout: - if (err < 0) - rtnl_set_sk_err(net, RTNLGRP_LINK, err); + rtnl_set_sk_err(net, RTNLGRP_LINK, err); return NULL; } @@ -6486,6 +6491,7 @@ static int rtnl_mdb_del(struct sk_buff *skb, struct nlmsghdr *nlh, static int rtnl_dumpit(struct sk_buff *skb, struct netlink_callback *cb) { + const bool needs_lock = !(cb->flags & RTNL_FLAG_DUMP_UNLOCKED); rtnl_dumpit_func dumpit = cb->data; int err; @@ -6495,7 +6501,11 @@ static int rtnl_dumpit(struct sk_buff *skb, struct netlink_callback *cb) if (!dumpit) return 0; + if (needs_lock) + rtnl_lock(); err = dumpit(skb, cb); + if (needs_lock) + rtnl_unlock(); /* Old dump handlers used to send NLM_DONE as in a separate recvmsg(). * Some applications which parse netlink manually depend on this. @@ -6515,7 +6525,8 @@ static int rtnetlink_dump_start(struct sock *ssk, struct sk_buff *skb, const struct nlmsghdr *nlh, struct netlink_dump_control *control) { - if (control->flags & RTNL_FLAG_DUMP_SPLIT_NLM_DONE) { + if (control->flags & RTNL_FLAG_DUMP_SPLIT_NLM_DONE || + !(control->flags & RTNL_FLAG_DUMP_UNLOCKED)) { WARN_ON(control->data); control->data = control->dump; control->dump = rtnl_dumpit; @@ -6703,7 +6714,6 @@ static int __net_init rtnetlink_net_init(struct net *net) struct netlink_kernel_cfg cfg = { .groups = RTNLGRP_MAX, .input = rtnetlink_rcv, - .cb_mutex = &rtnl_mutex, .flags = NL_CFG_F_NONROOT_RECV, .bind = rtnetlink_bind, }; diff --git a/net/core/skbuff.c b/net/core/skbuff.c index 466999a7515e..74149dc4ee31 100644 --- a/net/core/skbuff.c +++ b/net/core/skbuff.c @@ -88,6 +88,7 @@ #include <linux/textsearch.h> #include "dev.h" +#include "netmem_priv.h" #include "sock_destructor.h" #ifdef CONFIG_SKB_EXTENSIONS @@ -277,6 +278,7 @@ static void *page_frag_alloc_1k(struct page_frag_1k *nc, gfp_t gfp_mask) #endif struct napi_alloc_cache { + local_lock_t bh_lock; struct page_frag_cache page; struct page_frag_1k page_small; unsigned int skb_count; @@ -284,7 +286,9 @@ struct napi_alloc_cache { }; static DEFINE_PER_CPU(struct page_frag_cache, netdev_alloc_cache); -static DEFINE_PER_CPU(struct napi_alloc_cache, napi_alloc_cache); +static DEFINE_PER_CPU(struct napi_alloc_cache, napi_alloc_cache) = { + .bh_lock = INIT_LOCAL_LOCK(bh_lock), +}; /* Double check that napi_get_frags() allocates skbs with * skb->head being backed by slab, not a page fragment. @@ -306,11 +310,16 @@ void napi_get_frags_check(struct napi_struct *napi) void *__napi_alloc_frag_align(unsigned int fragsz, unsigned int align_mask) { struct napi_alloc_cache *nc = this_cpu_ptr(&napi_alloc_cache); + void *data; fragsz = SKB_DATA_ALIGN(fragsz); - return __page_frag_alloc_align(&nc->page, fragsz, GFP_ATOMIC, - align_mask); + local_lock_nested_bh(&napi_alloc_cache.bh_lock); + data = __page_frag_alloc_align(&nc->page, fragsz, + GFP_ATOMIC | __GFP_NOWARN, align_mask); + local_unlock_nested_bh(&napi_alloc_cache.bh_lock); + return data; + } EXPORT_SYMBOL(__napi_alloc_frag_align); @@ -318,19 +327,16 @@ void *__netdev_alloc_frag_align(unsigned int fragsz, unsigned int align_mask) { void *data; - fragsz = SKB_DATA_ALIGN(fragsz); if (in_hardirq() || irqs_disabled()) { struct page_frag_cache *nc = this_cpu_ptr(&netdev_alloc_cache); - data = __page_frag_alloc_align(nc, fragsz, GFP_ATOMIC, + fragsz = SKB_DATA_ALIGN(fragsz); + data = __page_frag_alloc_align(nc, fragsz, + GFP_ATOMIC | __GFP_NOWARN, align_mask); } else { - struct napi_alloc_cache *nc; - local_bh_disable(); - nc = this_cpu_ptr(&napi_alloc_cache); - data = __page_frag_alloc_align(&nc->page, fragsz, GFP_ATOMIC, - align_mask); + data = __napi_alloc_frag_align(fragsz, align_mask); local_bh_enable(); } return data; @@ -342,16 +348,20 @@ static struct sk_buff *napi_skb_cache_get(void) struct napi_alloc_cache *nc = this_cpu_ptr(&napi_alloc_cache); struct sk_buff *skb; + local_lock_nested_bh(&napi_alloc_cache.bh_lock); if (unlikely(!nc->skb_count)) { nc->skb_count = kmem_cache_alloc_bulk(net_hotdata.skbuff_cache, - GFP_ATOMIC, + GFP_ATOMIC | __GFP_NOWARN, NAPI_SKB_CACHE_BULK, nc->skb_cache); - if (unlikely(!nc->skb_count)) + if (unlikely(!nc->skb_count)) { + local_unlock_nested_bh(&napi_alloc_cache.bh_lock); return NULL; + } } skb = nc->skb_cache[--nc->skb_count]; + local_unlock_nested_bh(&napi_alloc_cache.bh_lock); kasan_mempool_unpoison_object(skb, kmem_cache_size(net_hotdata.skbuff_cache)); return skb; @@ -410,7 +420,8 @@ struct sk_buff *slab_build_skb(void *data) struct sk_buff *skb; unsigned int size; - skb = kmem_cache_alloc(net_hotdata.skbuff_cache, GFP_ATOMIC); + skb = kmem_cache_alloc(net_hotdata.skbuff_cache, + GFP_ATOMIC | __GFP_NOWARN); if (unlikely(!skb)) return NULL; @@ -461,7 +472,8 @@ struct sk_buff *__build_skb(void *data, unsigned int frag_size) { struct sk_buff *skb; - skb = kmem_cache_alloc(net_hotdata.skbuff_cache, GFP_ATOMIC); + skb = kmem_cache_alloc(net_hotdata.skbuff_cache, + GFP_ATOMIC | __GFP_NOWARN); if (unlikely(!skb)) return NULL; @@ -744,9 +756,13 @@ struct sk_buff *__netdev_alloc_skb(struct net_device *dev, unsigned int len, pfmemalloc = nc->pfmemalloc; } else { local_bh_disable(); + local_lock_nested_bh(&napi_alloc_cache.bh_lock); + nc = this_cpu_ptr(&napi_alloc_cache.page); data = page_frag_alloc(nc, len, gfp_mask); pfmemalloc = nc->pfmemalloc; + + local_unlock_nested_bh(&napi_alloc_cache.bh_lock); local_bh_enable(); } @@ -810,11 +826,11 @@ struct sk_buff *napi_alloc_skb(struct napi_struct *napi, unsigned int len) goto skb_success; } - nc = this_cpu_ptr(&napi_alloc_cache); - if (sk_memalloc_socks()) gfp_mask |= __GFP_MEMALLOC; + local_lock_nested_bh(&napi_alloc_cache.bh_lock); + nc = this_cpu_ptr(&napi_alloc_cache); if (NAPI_HAS_SMALL_PAGE_FRAG && len <= SKB_WITH_OVERHEAD(1024)) { /* we are artificially inflating the allocation size, but * that is not as bad as it may look like, as: @@ -836,6 +852,7 @@ struct sk_buff *napi_alloc_skb(struct napi_struct *napi, unsigned int len) data = page_frag_alloc(&nc->page, len, gfp_mask); pfmemalloc = nc->page.pfmemalloc; } + local_unlock_nested_bh(&napi_alloc_cache.bh_lock); if (unlikely(!data)) return NULL; @@ -904,9 +921,9 @@ static void skb_clone_fraglist(struct sk_buff *skb) skb_get(list); } -static bool is_pp_page(struct page *page) +static bool is_pp_netmem(netmem_ref netmem) { - return (page->pp_magic & ~0x3UL) == PP_SIGNATURE; + return (netmem_get_pp_magic(netmem) & ~0x3UL) == PP_SIGNATURE; } int skb_pp_cow_data(struct page_pool *pool, struct sk_buff **pskb, @@ -1002,9 +1019,9 @@ int skb_cow_data_for_xdp(struct page_pool *pool, struct sk_buff **pskb, EXPORT_SYMBOL(skb_cow_data_for_xdp); #if IS_ENABLED(CONFIG_PAGE_POOL) -bool napi_pp_put_page(struct page *page) +bool napi_pp_put_page(netmem_ref netmem) { - page = compound_head(page); + netmem = netmem_compound_head(netmem); /* page->pp_magic is OR'ed with PP_SIGNATURE after the allocation * in order to preserve any existing bits, such as bit 0 for the @@ -1013,10 +1030,10 @@ bool napi_pp_put_page(struct page *page) * and page_is_pfmemalloc() is checked in __page_pool_put_page() * to avoid recycling the pfmemalloc page. */ - if (unlikely(!is_pp_page(page))) + if (unlikely(!is_pp_netmem(netmem))) return false; - page_pool_put_full_page(page->pp, page, false); + page_pool_put_full_netmem(netmem_get_pp(netmem), netmem, false); return true; } @@ -1027,7 +1044,7 @@ static bool skb_pp_recycle(struct sk_buff *skb, void *data) { if (!IS_ENABLED(CONFIG_PAGE_POOL) || !skb->pp_recycle) return false; - return napi_pp_put_page(virt_to_page(data)); + return napi_pp_put_page(page_to_netmem(virt_to_page(data))); } /** @@ -1043,7 +1060,7 @@ static bool skb_pp_recycle(struct sk_buff *skb, void *data) static int skb_pp_frag_ref(struct sk_buff *skb) { struct skb_shared_info *shinfo; - struct page *head_page; + netmem_ref head_netmem; int i; if (!skb->pp_recycle) @@ -1052,11 +1069,11 @@ static int skb_pp_frag_ref(struct sk_buff *skb) shinfo = skb_shinfo(skb); for (i = 0; i < shinfo->nr_frags; i++) { - head_page = compound_head(skb_frag_page(&shinfo->frags[i])); - if (likely(is_pp_page(head_page))) - page_pool_ref_page(head_page); + head_netmem = netmem_compound_head(shinfo->frags[i].netmem); + if (likely(is_pp_netmem(head_netmem))) + page_pool_ref_netmem(head_netmem); else - page_ref_inc(head_page); + page_ref_inc(netmem_to_page(head_netmem)); } return 0; } @@ -1190,7 +1207,8 @@ void __kfree_skb(struct sk_buff *skb) EXPORT_SYMBOL(__kfree_skb); static __always_inline -bool __kfree_skb_reason(struct sk_buff *skb, enum skb_drop_reason reason) +bool __sk_skb_reason_drop(struct sock *sk, struct sk_buff *skb, + enum skb_drop_reason reason) { if (unlikely(!skb_unref(skb))) return false; @@ -1203,26 +1221,27 @@ bool __kfree_skb_reason(struct sk_buff *skb, enum skb_drop_reason reason) if (reason == SKB_CONSUMED) trace_consume_skb(skb, __builtin_return_address(0)); else - trace_kfree_skb(skb, __builtin_return_address(0), reason); + trace_kfree_skb(skb, __builtin_return_address(0), reason, sk); return true; } /** - * kfree_skb_reason - free an sk_buff with special reason + * sk_skb_reason_drop - free an sk_buff with special reason + * @sk: the socket to receive @skb, or NULL if not applicable * @skb: buffer to free * @reason: reason why this skb is dropped * - * Drop a reference to the buffer and free it if the usage count has - * hit zero. Meanwhile, pass the drop reason to 'kfree_skb' - * tracepoint. + * Drop a reference to the buffer and free it if the usage count has hit + * zero. Meanwhile, pass the receiving socket and drop reason to + * 'kfree_skb' tracepoint. */ void __fix_address -kfree_skb_reason(struct sk_buff *skb, enum skb_drop_reason reason) +sk_skb_reason_drop(struct sock *sk, struct sk_buff *skb, enum skb_drop_reason reason) { - if (__kfree_skb_reason(skb, reason)) + if (__sk_skb_reason_drop(sk, skb, reason)) __kfree_skb(skb); } -EXPORT_SYMBOL(kfree_skb_reason); +EXPORT_SYMBOL(sk_skb_reason_drop); #define KFREE_SKB_BULK_SIZE 16 @@ -1261,7 +1280,7 @@ kfree_skb_list_reason(struct sk_buff *segs, enum skb_drop_reason reason) while (segs) { struct sk_buff *next = segs->next; - if (__kfree_skb_reason(segs, reason)) { + if (__sk_skb_reason_drop(NULL, segs, reason)) { skb_poison_list(segs); kfree_skb_add_bulk(segs, &sa, reason); } @@ -1352,6 +1371,14 @@ void skb_dump(const char *level, const struct sk_buff *skb, bool full_pkt) struct page *p; u8 *vaddr; + if (skb_frag_is_net_iov(frag)) { + printk("%sskb frag %d: not readable\n", level, i); + len -= skb_frag_size(frag); + if (!len) + break; + continue; + } + skb_frag_foreach_page(frag, skb_frag_off(frag), skb_frag_size(frag), p, p_off, p_len, copied) { @@ -1433,6 +1460,7 @@ static void napi_skb_cache_put(struct sk_buff *skb) if (!kasan_mempool_poison_object(skb)) return; + local_lock_nested_bh(&napi_alloc_cache.bh_lock); nc->skb_cache[nc->skb_count++] = skb; if (unlikely(nc->skb_count == NAPI_SKB_CACHE_SIZE)) { @@ -1444,6 +1472,7 @@ static void napi_skb_cache_put(struct sk_buff *skb) nc->skb_cache + NAPI_SKB_CACHE_HALF); nc->skb_count = NAPI_SKB_CACHE_HALF; } + local_unlock_nested_bh(&napi_alloc_cache.bh_lock); } void __napi_kfree_skb(struct sk_buff *skb, enum skb_drop_reason reason) @@ -1854,7 +1883,6 @@ int skb_zerocopy_iter_stream(struct sock *sk, struct sk_buff *skb, struct msghdr *msg, int len, struct ubuf_info *uarg) { - struct ubuf_info *orig_uarg = skb_zcopy(skb); int err, orig_len = skb->len; if (uarg->ops->link_skb) { @@ -1862,6 +1890,8 @@ int skb_zerocopy_iter_stream(struct sock *sk, struct sk_buff *skb, if (err) return err; } else { + struct ubuf_info *orig_uarg = skb_zcopy(skb); + /* An skb can only point to one uarg. This edge case happens * when TCP appends to an skb, but zerocopy_realloc triggered * a new alloc. @@ -1882,8 +1912,7 @@ int skb_zerocopy_iter_stream(struct sock *sk, struct sk_buff *skb, return err; } - if (!uarg->ops->link_skb) - skb_zcopy_set(skb, uarg, NULL); + skb_zcopy_set(skb, uarg, NULL); return skb->len - orig_len; } EXPORT_SYMBOL_GPL(skb_zerocopy_iter_stream); @@ -1943,6 +1972,9 @@ int skb_copy_ubufs(struct sk_buff *skb, gfp_t gfp_mask) if (skb_shared(skb) || skb_unclone(skb, gfp_mask)) return -EINVAL; + if (!skb_frags_readable(skb)) + return -EFAULT; + if (!num_frags) goto release; @@ -2116,6 +2148,9 @@ struct sk_buff *skb_copy(const struct sk_buff *skb, gfp_t gfp_mask) unsigned int size; int headerlen; + if (!skb_frags_readable(skb)) + return NULL; + if (WARN_ON_ONCE(skb_shinfo(skb)->gso_type & SKB_GSO_FRAGLIST)) return NULL; @@ -2454,6 +2489,9 @@ struct sk_buff *skb_copy_expand(const struct sk_buff *skb, struct sk_buff *n; int oldheadroom; + if (!skb_frags_readable(skb)) + return NULL; + if (WARN_ON_ONCE(skb_shinfo(skb)->gso_type & SKB_GSO_FRAGLIST)) return NULL; @@ -2798,6 +2836,9 @@ void *__pskb_pull_tail(struct sk_buff *skb, int delta) */ int i, k, eat = (skb->tail + delta) - skb->end; + if (!skb_frags_readable(skb)) + return NULL; + if (eat > 0 || skb_cloned(skb)) { if (pskb_expand_head(skb, 0, eat > 0 ? eat + 128 : 0, GFP_ATOMIC)) @@ -2951,6 +2992,9 @@ int skb_copy_bits(const struct sk_buff *skb, int offset, void *to, int len) to += copy; } + if (!skb_frags_readable(skb)) + goto fault; + for (i = 0; i < skb_shinfo(skb)->nr_frags; i++) { int end; skb_frag_t *f = &skb_shinfo(skb)->frags[i]; @@ -3139,9 +3183,15 @@ static bool __skb_splice_bits(struct sk_buff *skb, struct pipe_inode_info *pipe, /* * then map the fragments */ + if (!skb_frags_readable(skb)) + return false; + for (seg = 0; seg < skb_shinfo(skb)->nr_frags; seg++) { const skb_frag_t *f = &skb_shinfo(skb)->frags[seg]; + if (WARN_ON_ONCE(!skb_frag_page(f))) + return false; + if (__splice_segment(skb_frag_page(f), skb_frag_off(f), skb_frag_size(f), offset, len, spd, false, sk, pipe)) @@ -3359,6 +3409,9 @@ int skb_store_bits(struct sk_buff *skb, int offset, const void *from, int len) from += copy; } + if (!skb_frags_readable(skb)) + goto fault; + for (i = 0; i < skb_shinfo(skb)->nr_frags; i++) { skb_frag_t *frag = &skb_shinfo(skb)->frags[i]; int end; @@ -3438,6 +3491,9 @@ __wsum __skb_checksum(const struct sk_buff *skb, int offset, int len, pos = copy; } + if (WARN_ON_ONCE(!skb_frags_readable(skb))) + return 0; + for (i = 0; i < skb_shinfo(skb)->nr_frags; i++) { int end; skb_frag_t *frag = &skb_shinfo(skb)->frags[i]; @@ -3538,6 +3594,9 @@ __wsum skb_copy_and_csum_bits(const struct sk_buff *skb, int offset, pos = copy; } + if (!skb_frags_readable(skb)) + return 0; + for (i = 0; i < skb_shinfo(skb)->nr_frags; i++) { int end; @@ -4029,6 +4088,7 @@ static inline void skb_split_inside_header(struct sk_buff *skb, skb_shinfo(skb1)->frags[i] = skb_shinfo(skb)->frags[i]; skb_shinfo(skb1)->nr_frags = skb_shinfo(skb)->nr_frags; + skb1->unreadable = skb->unreadable; skb_shinfo(skb)->nr_frags = 0; skb1->data_len = skb->data_len; skb1->len += skb1->data_len; @@ -4076,6 +4136,8 @@ static inline void skb_split_no_header(struct sk_buff *skb, pos += size; } skb_shinfo(skb1)->nr_frags = k; + + skb1->unreadable = skb->unreadable; } /** @@ -4139,6 +4201,9 @@ int skb_shift(struct sk_buff *tgt, struct sk_buff *skb, int shiftlen) if (skb_zcopy(tgt) || skb_zcopy(skb)) return 0; + DEBUG_NET_WARN_ON_ONCE(tgt->pp_recycle != skb->pp_recycle); + DEBUG_NET_WARN_ON_ONCE(skb_cmp_decrypted(tgt, skb)); + todo = shiftlen; from = 0; to = skb_shinfo(tgt)->nr_frags; @@ -4147,8 +4212,7 @@ int skb_shift(struct sk_buff *tgt, struct sk_buff *skb, int shiftlen) /* Actual merge is delayed until the point when we know we can * commit all, so that we don't have to undo partial changes */ - if (!to || - !skb_can_coalesce(tgt, to, skb_frag_page(fragfrom), + if (!skb_can_coalesce(tgt, to, skb_frag_page(fragfrom), skb_frag_off(fragfrom))) { merge = -1; } else { @@ -4311,6 +4375,9 @@ next_skb: return block_limit - abs_offset; } + if (!skb_frags_readable(st->cur_skb)) + return 0; + if (st->frag_idx == 0 && !st->frag_data) st->stepped_offset += skb_headlen(st->cur_skb); @@ -4387,6 +4454,41 @@ void skb_abort_seq_read(struct skb_seq_state *st) } EXPORT_SYMBOL(skb_abort_seq_read); +/** + * skb_copy_seq_read() - copy from a skb_seq_state to a buffer + * @st: source skb_seq_state + * @offset: offset in source + * @to: destination buffer + * @len: number of bytes to copy + * + * Copy @len bytes from @offset bytes into the source @st to the destination + * buffer @to. `offset` should increase (or be unchanged) with each subsequent + * call to this function. If offset needs to decrease from the previous use `st` + * should be reset first. + * + * Return: 0 on success or -EINVAL if the copy ended early + */ +int skb_copy_seq_read(struct skb_seq_state *st, int offset, void *to, int len) +{ + const u8 *data; + u32 sqlen; + + for (;;) { + sqlen = skb_seq_read(offset, &data, st); + if (sqlen == 0) + return -EINVAL; + if (sqlen >= len) { + memcpy(to, data, len); + return 0; + } + memcpy(to, data, sqlen); + to += sqlen; + offset += sqlen; + len -= sqlen; + } +} +EXPORT_SYMBOL(skb_copy_seq_read); + #define TS_SKB_CB(state) ((struct skb_seq_state *) &((state)->cb)) static unsigned int skb_ts_get_next_block(unsigned int offset, const u8 **text, @@ -5139,7 +5241,7 @@ EXPORT_SYMBOL_GPL(skb_to_sgvec); * 3. sg_unmark_end * 4. skb_to_sgvec(payload2) * - * When mapping mutilple payload conditionally, skb_to_sgvec_nomark + * When mapping multiple payload conditionally, skb_to_sgvec_nomark * is more preferable. */ int skb_to_sgvec_nomark(struct sk_buff *skb, struct scatterlist *sg, @@ -5923,7 +6025,10 @@ bool skb_try_coalesce(struct sk_buff *to, struct sk_buff *from, if (to->pp_recycle != from->pp_recycle) return false; - if (len <= skb_tailroom(to)) { + if (skb_frags_readable(from) != skb_frags_readable(to)) + return false; + + if (len <= skb_tailroom(to) && skb_frags_readable(from)) { if (len) BUG_ON(skb_copy_bits(from, 0, skb_put(to, len), len)); *delta_truesize = 0; @@ -5997,7 +6102,7 @@ EXPORT_SYMBOL(skb_try_coalesce); * @skb: buffer to clean * @xnet: packet is crossing netns * - * skb_scrub_packet can be used after encapsulating or decapsulting a packet + * skb_scrub_packet can be used after encapsulating or decapsulating a packet * into/from a tunnel. Some information have to be cleared during these * operations. * skb_scrub_packet can also be used to clean a skb before injecting it in @@ -6100,6 +6205,9 @@ int skb_ensure_writable(struct sk_buff *skb, unsigned int write_len) if (!pskb_may_pull(skb, write_len)) return -ENOMEM; + if (!skb_frags_readable(skb)) + return -EFAULT; + if (!skb_cloned(skb) || skb_clone_writable(skb, write_len)) return 0; @@ -6219,7 +6327,7 @@ int skb_vlan_push(struct sk_buff *skb, __be16 vlan_proto, u16 vlan_tci) return err; skb->protocol = skb->vlan_proto; - skb->mac_len += VLAN_HLEN; + skb->network_header -= VLAN_HLEN; skb_postpush_rcsum(skb, skb->data + (2 * ETH_ALEN), VLAN_HLEN); } @@ -6779,7 +6887,7 @@ void skb_condense(struct sk_buff *skb) { if (skb->data_len) { if (skb->data_len > skb->end - skb->tail || - skb_cloned(skb)) + skb_cloned(skb) || !skb_frags_readable(skb)) return; /* Nice, we can free page frag(s) right now */ diff --git a/net/core/skmsg.c b/net/core/skmsg.c index fd20aae30be2..b1dcbd3be89e 100644 --- a/net/core/skmsg.c +++ b/net/core/skmsg.c @@ -293,7 +293,7 @@ out: /* If we trim data a full sg elem before curr pointer update * copybreak and current so that any future copy operations * start at new copy location. - * However trimed data that has not yet been used in a copy op + * However trimmed data that has not yet been used in a copy op * does not require an update. */ if (!msg->sg.size) { @@ -434,7 +434,8 @@ int sk_msg_recvmsg(struct sock *sk, struct sk_psock *psock, struct msghdr *msg, page = sg_page(sge); if (copied + copy > len) copy = len - copied; - copy = copy_page_to_iter(page, sge->offset, copy, iter); + if (copy) + copy = copy_page_to_iter(page, sge->offset, copy, iter); if (!copy) { copied = copied ? copied : -EFAULT; goto out; diff --git a/net/core/sock.c b/net/core/sock.c index 100e975073ca..fe87f9bd8f16 100644 --- a/net/core/sock.c +++ b/net/core/sock.c @@ -124,6 +124,7 @@ #include <linux/netdevice.h> #include <net/protocol.h> #include <linux/skbuff.h> +#include <linux/skbuff_ref.h> #include <net/net_namespace.h> #include <net/request_sock.h> #include <net/sock.h> @@ -1049,6 +1050,69 @@ static int sock_reserve_memory(struct sock *sk, int bytes) return 0; } +#ifdef CONFIG_PAGE_POOL + +/* This is the number of tokens that the user can SO_DEVMEM_DONTNEED in + * 1 syscall. The limit exists to limit the amount of memory the kernel + * allocates to copy these tokens. + */ +#define MAX_DONTNEED_TOKENS 128 + +static noinline_for_stack int +sock_devmem_dontneed(struct sock *sk, sockptr_t optval, unsigned int optlen) +{ + unsigned int num_tokens, i, j, k, netmem_num = 0; + struct dmabuf_token *tokens; + netmem_ref netmems[16]; + int ret = 0; + + if (!sk_is_tcp(sk)) + return -EBADF; + + if (optlen % sizeof(struct dmabuf_token) || + optlen > sizeof(*tokens) * MAX_DONTNEED_TOKENS) + return -EINVAL; + + tokens = kvmalloc_array(optlen, sizeof(*tokens), GFP_KERNEL); + if (!tokens) + return -ENOMEM; + + num_tokens = optlen / sizeof(struct dmabuf_token); + if (copy_from_sockptr(tokens, optval, optlen)) { + kvfree(tokens); + return -EFAULT; + } + + xa_lock_bh(&sk->sk_user_frags); + for (i = 0; i < num_tokens; i++) { + for (j = 0; j < tokens[i].token_count; j++) { + netmem_ref netmem = (__force netmem_ref)__xa_erase( + &sk->sk_user_frags, tokens[i].token_start + j); + + if (netmem && + !WARN_ON_ONCE(!netmem_is_net_iov(netmem))) { + netmems[netmem_num++] = netmem; + if (netmem_num == ARRAY_SIZE(netmems)) { + xa_unlock_bh(&sk->sk_user_frags); + for (k = 0; k < netmem_num; k++) + WARN_ON_ONCE(!napi_pp_put_page(netmems[k])); + netmem_num = 0; + xa_lock_bh(&sk->sk_user_frags); + } + ret++; + } + } + } + + xa_unlock_bh(&sk->sk_user_frags); + for (k = 0; k < netmem_num; k++) + WARN_ON_ONCE(!napi_pp_put_page(netmems[k])); + + kvfree(tokens); + return ret; +} +#endif + void sockopt_lock_sock(struct sock *sk) { /* When current->bpf_ctx is set, the setsockopt is called from @@ -1083,6 +1147,17 @@ bool sockopt_capable(int cap) } EXPORT_SYMBOL(sockopt_capable); +static int sockopt_validate_clockid(__kernel_clockid_t value) +{ + switch (value) { + case CLOCK_REALTIME: + case CLOCK_MONOTONIC: + case CLOCK_TAI: + return 0; + } + return -EINVAL; +} + /* * This is meant for all protocols to use and covers goings on * at the socket level. Everything here is generic. @@ -1200,6 +1275,10 @@ int sk_setsockopt(struct sock *sk, int level, int optname, ret = -EOPNOTSUPP; return ret; } +#ifdef CONFIG_PAGE_POOL + case SO_DEVMEM_DONTNEED: + return sock_devmem_dontneed(sk, optval, optlen); +#endif } sockopt_lock_sock(sk); @@ -1497,6 +1576,11 @@ set_sndbuf: ret = -EPERM; break; } + + ret = sockopt_validate_clockid(sk_txtime.clockid); + if (ret) + break; + sock_valbool_flag(sk, SOCK_TXTIME, true); sk->sk_clockid = sk_txtime.clockid; sk->sk_txtime_deadline_mode = @@ -2032,7 +2116,7 @@ static inline void sock_lock_init(struct sock *sk) /* * Copy all fields from osk to nsk but nsk->sk_refcnt must not change yet, - * even temporarly, because of RCU lookups. sk_node should also be left as is. + * even temporarily, because of RCU lookups. sk_node should also be left as is. * We must not copy fields between sk_dontcopy_begin and sk_dontcopy_end */ static void sock_copy(struct sock *nsk, const struct sock *osk) @@ -2262,7 +2346,12 @@ static void sk_init_common(struct sock *sk) lockdep_set_class_and_name(&sk->sk_error_queue.lock, af_elock_keys + sk->sk_family, af_family_elock_key_strings[sk->sk_family]); - lockdep_set_class_and_name(&sk->sk_callback_lock, + if (sk->sk_kern_sock) + lockdep_set_class_and_name(&sk->sk_callback_lock, + af_kern_callback_keys + sk->sk_family, + af_family_kern_clock_key_strings[sk->sk_family]); + else + lockdep_set_class_and_name(&sk->sk_callback_lock, af_callback_keys + sk->sk_family, af_family_clock_key_strings[sk->sk_family]); } @@ -2517,7 +2606,7 @@ void skb_set_owner_w(struct sk_buff *skb, struct sock *sk) skb_set_hash_from_sk(skb, sk); /* * We used to take a refcount on sk, but following operation - * is enough to guarantee sk_free() wont free this sock until + * is enough to guarantee sk_free() won't free this sock until * all in-flight packets are completed */ refcount_add(skb->truesize, &sk->sk_wmem_alloc); @@ -3408,7 +3497,7 @@ static void sock_def_destruct(struct sock *sk) void sk_send_sigurg(struct sock *sk) { if (sk->sk_socket && sk->sk_socket->file) - if (send_sigurg(&sk->sk_socket->file->f_owner)) + if (send_sigurg(sk->sk_socket->file)) sk_wake_async(sk, SOCK_WAKE_URG, POLL_PRI); } EXPORT_SYMBOL(sk_send_sigurg); @@ -3460,18 +3549,6 @@ void sock_init_data_uid(struct socket *sock, struct sock *sk, kuid_t uid) } sk->sk_uid = uid; - rwlock_init(&sk->sk_callback_lock); - if (sk->sk_kern_sock) - lockdep_set_class_and_name( - &sk->sk_callback_lock, - af_kern_callback_keys + sk->sk_family, - af_family_kern_clock_key_strings[sk->sk_family]); - else - lockdep_set_class_and_name( - &sk->sk_callback_lock, - af_callback_keys + sk->sk_family, - af_family_clock_key_strings[sk->sk_family]); - sk->sk_state_change = sock_def_wakeup; sk->sk_data_ready = sock_def_readable; sk->sk_write_space = sock_def_write_space; @@ -3688,7 +3765,7 @@ EXPORT_SYMBOL(sock_recv_errqueue); * * FIX: POSIX 1003.1g is very ambiguous here. It states that * asynchronous errors should be reported by getsockopt. We assume - * this means if you specify SO_ERROR (otherwise whats the point of it). + * this means if you specify SO_ERROR (otherwise what is the point of it). */ int sock_common_getsockopt(struct socket *sock, int level, int optname, char __user *optval, int __user *optlen) diff --git a/net/core/sock_diag.c b/net/core/sock_diag.c index 654122838025..a08eed9b9142 100644 --- a/net/core/sock_diag.c +++ b/net/core/sock_diag.c @@ -18,7 +18,7 @@ static const struct sock_diag_handler __rcu *sock_diag_handlers[AF_MAX]; -static struct sock_diag_inet_compat __rcu *inet_rcv_compat; +static const struct sock_diag_inet_compat __rcu *inet_rcv_compat; static struct workqueue_struct *broadcast_wq; @@ -187,8 +187,7 @@ void sock_diag_broadcast_destroy(struct sock *sk) void sock_diag_register_inet_compat(const struct sock_diag_inet_compat *ptr) { - xchg((__force const struct sock_diag_inet_compat **)&inet_rcv_compat, - ptr); + xchg(&inet_rcv_compat, RCU_INITIALIZER(ptr)); } EXPORT_SYMBOL_GPL(sock_diag_register_inet_compat); @@ -196,8 +195,7 @@ void sock_diag_unregister_inet_compat(const struct sock_diag_inet_compat *ptr) { const struct sock_diag_inet_compat *old; - old = xchg((__force const struct sock_diag_inet_compat **)&inet_rcv_compat, - NULL); + old = unrcu_pointer(xchg(&inet_rcv_compat, NULL)); WARN_ON_ONCE(old != ptr); } EXPORT_SYMBOL_GPL(sock_diag_unregister_inet_compat); diff --git a/net/core/sock_map.c b/net/core/sock_map.c index d3dbb92153f2..242c91a6e3d3 100644 --- a/net/core/sock_map.c +++ b/net/core/sock_map.c @@ -67,46 +67,39 @@ static struct bpf_map *sock_map_alloc(union bpf_attr *attr) int sock_map_get_from_fd(const union bpf_attr *attr, struct bpf_prog *prog) { - u32 ufd = attr->target_fd; struct bpf_map *map; - struct fd f; int ret; if (attr->attach_flags || attr->replace_bpf_fd) return -EINVAL; - f = fdget(ufd); + CLASS(fd, f)(attr->target_fd); map = __bpf_map_get(f); if (IS_ERR(map)) return PTR_ERR(map); mutex_lock(&sockmap_mutex); ret = sock_map_prog_update(map, prog, NULL, NULL, attr->attach_type); mutex_unlock(&sockmap_mutex); - fdput(f); return ret; } int sock_map_prog_detach(const union bpf_attr *attr, enum bpf_prog_type ptype) { - u32 ufd = attr->target_fd; struct bpf_prog *prog; struct bpf_map *map; - struct fd f; int ret; if (attr->attach_flags || attr->replace_bpf_fd) return -EINVAL; - f = fdget(ufd); + CLASS(fd, f)(attr->target_fd); map = __bpf_map_get(f); if (IS_ERR(map)) return PTR_ERR(map); prog = bpf_prog_get(attr->attach_bpf_fd); - if (IS_ERR(prog)) { - ret = PTR_ERR(prog); - goto put_map; - } + if (IS_ERR(prog)) + return PTR_ERR(prog); if (prog->type != ptype) { ret = -EINVAL; @@ -118,8 +111,6 @@ int sock_map_prog_detach(const union bpf_attr *attr, enum bpf_prog_type ptype) mutex_unlock(&sockmap_mutex); put_prog: bpf_prog_put(prog); -put_map: - fdput(f); return ret; } @@ -1183,6 +1174,7 @@ static void sock_hash_free(struct bpf_map *map) sock_put(elem->sk); sock_hash_free_elem(htab, elem); } + cond_resched(); } /* wait for psock readers accessing its map link */ @@ -1550,18 +1542,17 @@ int sock_map_bpf_prog_query(const union bpf_attr *attr, union bpf_attr __user *uattr) { __u32 __user *prog_ids = u64_to_user_ptr(attr->query.prog_ids); - u32 prog_cnt = 0, flags = 0, ufd = attr->target_fd; + u32 prog_cnt = 0, flags = 0; struct bpf_prog **pprog; struct bpf_prog *prog; struct bpf_map *map; - struct fd f; u32 id = 0; int ret; if (attr->query.query_flags) return -EINVAL; - f = fdget(ufd); + CLASS(fd, f)(attr->target_fd); map = __bpf_map_get(f); if (IS_ERR(map)) return PTR_ERR(map); @@ -1593,7 +1584,6 @@ end: copy_to_user(&uattr->query.prog_cnt, &prog_cnt, sizeof(prog_cnt))) ret = -EFAULT; - fdput(f); return ret; } diff --git a/net/core/sock_reuseport.c b/net/core/sock_reuseport.c index 5a165286e4d8..4211710393a8 100644 --- a/net/core/sock_reuseport.c +++ b/net/core/sock_reuseport.c @@ -173,10 +173,9 @@ static bool __reuseport_detach_closed_sock(struct sock *sk, static struct sock_reuseport *__reuseport_alloc(unsigned int max_socks) { - unsigned int size = sizeof(struct sock_reuseport) + - sizeof(struct sock *) * max_socks; - struct sock_reuseport *reuse = kzalloc(size, GFP_ATOMIC); + struct sock_reuseport *reuse; + reuse = kzalloc(struct_size(reuse, socks, max_socks), GFP_ATOMIC); if (!reuse) return NULL; diff --git a/net/core/sysctl_net_core.c b/net/core/sysctl_net_core.c index c9fb9ad87485..86a2476678c4 100644 --- a/net/core/sysctl_net_core.c +++ b/net/core/sysctl_net_core.c @@ -95,7 +95,7 @@ static struct cpumask *rps_default_mask_cow_alloc(struct net *net) return rps_default_mask; } -static int rps_default_mask_sysctl(struct ctl_table *table, int write, +static int rps_default_mask_sysctl(const struct ctl_table *table, int write, void *buffer, size_t *lenp, loff_t *ppos) { struct net *net = (struct net *)table->data; @@ -126,7 +126,7 @@ done: return err; } -static int rps_sock_flow_sysctl(struct ctl_table *table, int write, +static int rps_sock_flow_sysctl(const struct ctl_table *table, int write, void *buffer, size_t *lenp, loff_t *ppos) { unsigned int orig_size, size; @@ -198,7 +198,7 @@ static int rps_sock_flow_sysctl(struct ctl_table *table, int write, #ifdef CONFIG_NET_FLOW_LIMIT static DEFINE_MUTEX(flow_limit_update_mutex); -static int flow_limit_cpu_sysctl(struct ctl_table *table, int write, +static int flow_limit_cpu_sysctl(const struct ctl_table *table, int write, void *buffer, size_t *lenp, loff_t *ppos) { struct sd_flow_limit *cur; @@ -255,7 +255,7 @@ done: return ret; } -static int flow_limit_table_len_sysctl(struct ctl_table *table, int write, +static int flow_limit_table_len_sysctl(const struct ctl_table *table, int write, void *buffer, size_t *lenp, loff_t *ppos) { unsigned int old, *ptr; @@ -277,7 +277,7 @@ static int flow_limit_table_len_sysctl(struct ctl_table *table, int write, #endif /* CONFIG_NET_FLOW_LIMIT */ #ifdef CONFIG_NET_SCHED -static int set_default_qdisc(struct ctl_table *table, int write, +static int set_default_qdisc(const struct ctl_table *table, int write, void *buffer, size_t *lenp, loff_t *ppos) { char id[IFNAMSIZ]; @@ -296,7 +296,7 @@ static int set_default_qdisc(struct ctl_table *table, int write, } #endif -static int proc_do_dev_weight(struct ctl_table *table, int write, +static int proc_do_dev_weight(const struct ctl_table *table, int write, void *buffer, size_t *lenp, loff_t *ppos) { static DEFINE_MUTEX(dev_weight_mutex); @@ -314,7 +314,7 @@ static int proc_do_dev_weight(struct ctl_table *table, int write, return ret; } -static int proc_do_rss_key(struct ctl_table *table, int write, +static int proc_do_rss_key(const struct ctl_table *table, int write, void *buffer, size_t *lenp, loff_t *ppos) { struct ctl_table fake_table; @@ -327,7 +327,7 @@ static int proc_do_rss_key(struct ctl_table *table, int write, } #ifdef CONFIG_BPF_JIT -static int proc_dointvec_minmax_bpf_enable(struct ctl_table *table, int write, +static int proc_dointvec_minmax_bpf_enable(const struct ctl_table *table, int write, void *buffer, size_t *lenp, loff_t *ppos) { @@ -360,7 +360,7 @@ static int proc_dointvec_minmax_bpf_enable(struct ctl_table *table, int write, # ifdef CONFIG_HAVE_EBPF_JIT static int -proc_dointvec_minmax_bpf_restricted(struct ctl_table *table, int write, +proc_dointvec_minmax_bpf_restricted(const struct ctl_table *table, int write, void *buffer, size_t *lenp, loff_t *ppos) { if (!capable(CAP_SYS_ADMIN)) @@ -371,7 +371,7 @@ proc_dointvec_minmax_bpf_restricted(struct ctl_table *table, int write, # endif /* CONFIG_HAVE_EBPF_JIT */ static int -proc_dolongvec_minmax_bpf_restricted(struct ctl_table *table, int write, +proc_dolongvec_minmax_bpf_restricted(const struct ctl_table *table, int write, void *buffer, size_t *lenp, loff_t *ppos) { if (!capable(CAP_SYS_ADMIN)) @@ -383,38 +383,6 @@ proc_dolongvec_minmax_bpf_restricted(struct ctl_table *table, int write, static struct ctl_table net_core_table[] = { { - .procname = "wmem_max", - .data = &sysctl_wmem_max, - .maxlen = sizeof(int), - .mode = 0644, - .proc_handler = proc_dointvec_minmax, - .extra1 = &min_sndbuf, - }, - { - .procname = "rmem_max", - .data = &sysctl_rmem_max, - .maxlen = sizeof(int), - .mode = 0644, - .proc_handler = proc_dointvec_minmax, - .extra1 = &min_rcvbuf, - }, - { - .procname = "wmem_default", - .data = &sysctl_wmem_default, - .maxlen = sizeof(int), - .mode = 0644, - .proc_handler = proc_dointvec_minmax, - .extra1 = &min_sndbuf, - }, - { - .procname = "rmem_default", - .data = &sysctl_rmem_default, - .maxlen = sizeof(int), - .mode = 0644, - .proc_handler = proc_dointvec_minmax, - .extra1 = &min_rcvbuf, - }, - { .procname = "mem_pcpu_rsv", .data = &net_hotdata.sysctl_mem_pcpu_rsv, .maxlen = sizeof(int), @@ -697,6 +665,41 @@ static struct ctl_table netns_core_table[] = { .extra2 = SYSCTL_ONE, .proc_handler = proc_dou8vec_minmax, }, + /* sysctl_core_net_init() will set the values after this + * to readonly in network namespaces + */ + { + .procname = "wmem_max", + .data = &sysctl_wmem_max, + .maxlen = sizeof(int), + .mode = 0644, + .proc_handler = proc_dointvec_minmax, + .extra1 = &min_sndbuf, + }, + { + .procname = "rmem_max", + .data = &sysctl_rmem_max, + .maxlen = sizeof(int), + .mode = 0644, + .proc_handler = proc_dointvec_minmax, + .extra1 = &min_rcvbuf, + }, + { + .procname = "wmem_default", + .data = &sysctl_wmem_default, + .maxlen = sizeof(int), + .mode = 0644, + .proc_handler = proc_dointvec_minmax, + .extra1 = &min_sndbuf, + }, + { + .procname = "rmem_default", + .data = &sysctl_rmem_default, + .maxlen = sizeof(int), + .mode = 0644, + .proc_handler = proc_dointvec_minmax, + .extra1 = &min_rcvbuf, + }, }; static int __init fb_tunnels_only_for_init_net_sysctl_setup(char *str) @@ -724,8 +727,14 @@ static __net_init int sysctl_core_net_init(struct net *net) if (tbl == NULL) goto err_dup; - for (i = 0; i < table_size; ++i) + for (i = 0; i < table_size; ++i) { + if (tbl[i].data == &sysctl_wmem_max) + break; + tbl[i].data += (char *)net - (char *)&init_net; + } + for (; i < table_size; ++i) + tbl[i].mode &= ~0222; } net->core.sysctl_hdr = register_net_sysctl_sz(net, "net/core", tbl, table_size); diff --git a/net/core/timestamping.c b/net/core/timestamping.c index 04840697fe79..3717fb152ecc 100644 --- a/net/core/timestamping.c +++ b/net/core/timestamping.c @@ -25,7 +25,8 @@ void skb_clone_tx_timestamp(struct sk_buff *skb) struct sk_buff *clone; unsigned int type; - if (!skb->sk) + if (!skb->sk || !skb->dev || + !phy_is_default_hwtstamp(skb->dev->phydev)) return; type = classify(skb); @@ -47,7 +48,7 @@ bool skb_defer_rx_timestamp(struct sk_buff *skb) struct mii_timestamper *mii_ts; unsigned int type; - if (!skb->dev || !skb->dev->phydev || !skb->dev->phydev->mii_ts) + if (!skb->dev || !phy_is_default_hwtstamp(skb->dev->phydev)) return false; if (skb_headroom(skb) < ETH_HLEN) diff --git a/net/core/utils.c b/net/core/utils.c index c994e95172ac..27f4cffaae05 100644 --- a/net/core/utils.c +++ b/net/core/utils.c @@ -1,6 +1,6 @@ // SPDX-License-Identifier: GPL-2.0-or-later /* - * Generic address resultion entity + * Generic address resolution entity * * Authors: * net_random Alan Cox diff --git a/net/core/xdp.c b/net/core/xdp.c index 41693154e426..bcc5551c6424 100644 --- a/net/core/xdp.c +++ b/net/core/xdp.c @@ -127,10 +127,8 @@ void xdp_unreg_mem_model(struct xdp_mem_info *mem) return; if (type == MEM_TYPE_PAGE_POOL) { - rcu_read_lock(); - xa = rhashtable_lookup(mem_id_ht, &id, mem_id_rht_params); + xa = rhashtable_lookup_fast(mem_id_ht, &id, mem_id_rht_params); page_pool_destroy(xa->page_pool); - rcu_read_unlock(); } } EXPORT_SYMBOL_GPL(xdp_unreg_mem_model); @@ -295,10 +293,8 @@ static struct xdp_mem_allocator *__xdp_reg_mem_model(struct xdp_mem_info *mem, mutex_lock(&mem_id_lock); ret = __mem_id_init_hash_table(); mutex_unlock(&mem_id_lock); - if (ret < 0) { - WARN_ON(1); + if (ret < 0) return ERR_PTR(ret); - } } xdp_alloc = kzalloc(sizeof(*xdp_alloc), gfp); diff --git a/net/dccp/ipv4.c b/net/dccp/ipv4.c index ff41bd6f99c3..5926159a6f20 100644 --- a/net/dccp/ipv4.c +++ b/net/dccp/ipv4.c @@ -657,8 +657,11 @@ int dccp_v4_conn_request(struct sock *sk, struct sk_buff *skb) if (dccp_v4_send_response(sk, req)) goto drop_and_free; - inet_csk_reqsk_queue_hash_add(sk, req, DCCP_TIMEOUT_INIT); - reqsk_put(req); + if (unlikely(!inet_csk_reqsk_queue_hash_add(sk, req, DCCP_TIMEOUT_INIT))) + reqsk_free(req); + else + reqsk_put(req); + return 0; drop_and_free: diff --git a/net/dccp/ipv6.c b/net/dccp/ipv6.c index 85f4b8fdbe5e..da5dba120bc9 100644 --- a/net/dccp/ipv6.c +++ b/net/dccp/ipv6.c @@ -400,8 +400,11 @@ static int dccp_v6_conn_request(struct sock *sk, struct sk_buff *skb) if (dccp_v6_send_response(sk, req)) goto drop_and_free; - inet_csk_reqsk_queue_hash_add(sk, req, DCCP_TIMEOUT_INIT); - reqsk_put(req); + if (unlikely(!inet_csk_reqsk_queue_hash_add(sk, req, DCCP_TIMEOUT_INIT))) + reqsk_free(req); + else + reqsk_put(req); + return 0; drop_and_free: diff --git a/net/dccp/minisocks.c b/net/dccp/minisocks.c index 251a57cf5822..fecc8190064f 100644 --- a/net/dccp/minisocks.c +++ b/net/dccp/minisocks.c @@ -54,17 +54,10 @@ void dccp_time_wait(struct sock *sk, int state, int timeo) if (state == DCCP_TIME_WAIT) timeo = DCCP_TIMEWAIT_LEN; - /* tw_timer is pinned, so we need to make sure BH are disabled - * in following section, otherwise timer handler could run before - * we complete the initialization. - */ - local_bh_disable(); - inet_twsk_schedule(tw, timeo); /* Linkage updates. * Note that access to tw after this point is illegal. */ - inet_twsk_hashdance(tw, sk, &dccp_hashinfo); - local_bh_enable(); + inet_twsk_hashdance_schedule(tw, sk, &dccp_hashinfo, timeo); } else { /* Sorry, if we're out of memory, just CLOSE this * socket up. We've got bigger problems than diff --git a/net/devlink/dpipe.c b/net/devlink/dpipe.c index a72a9292efc5..55009b377447 100644 --- a/net/devlink/dpipe.c +++ b/net/devlink/dpipe.c @@ -839,7 +839,7 @@ EXPORT_SYMBOL_GPL(devlink_dpipe_table_counter_enabled); */ int devl_dpipe_table_register(struct devlink *devlink, const char *table_name, - struct devlink_dpipe_table_ops *table_ops, + const struct devlink_dpipe_table_ops *table_ops, void *priv, bool counter_control_extern) { struct devlink_dpipe_table *table; diff --git a/net/dsa/Kconfig b/net/dsa/Kconfig index 8e698bea99a3..2dfe9063613f 100644 --- a/net/dsa/Kconfig +++ b/net/dsa/Kconfig @@ -129,7 +129,7 @@ config NET_DSA_TAG_RTL4_A tristate "Tag driver for Realtek 4 byte protocol A tags" help Say Y or M if you want to enable support for tagging frames for the - Realtek switches with 4 byte protocol A tags, sich as found in + Realtek switches with 4 byte protocol A tags, such as found in the Realtek RTL8366RB. config NET_DSA_TAG_RTL8_4 @@ -166,6 +166,12 @@ config NET_DSA_TAG_TRAILER Say Y or M if you want to enable support for tagging frames at with a trailed. e.g. Marvell 88E6060. +config NET_DSA_TAG_VSC73XX_8021Q + tristate "Tag driver for Microchip/Vitesse VSC73xx family of switches, using VLAN" + help + Say Y or M if you want to enable support for tagging frames with a + custom VLAN-based header. + config NET_DSA_TAG_XRS700X tristate "Tag driver for XRS700x switches" help diff --git a/net/dsa/Makefile b/net/dsa/Makefile index 8a1894a42552..555c07cfeb71 100644 --- a/net/dsa/Makefile +++ b/net/dsa/Makefile @@ -37,6 +37,7 @@ obj-$(CONFIG_NET_DSA_TAG_RTL8_4) += tag_rtl8_4.o obj-$(CONFIG_NET_DSA_TAG_RZN1_A5PSW) += tag_rzn1_a5psw.o obj-$(CONFIG_NET_DSA_TAG_SJA1105) += tag_sja1105.o obj-$(CONFIG_NET_DSA_TAG_TRAILER) += tag_trailer.o +obj-$(CONFIG_NET_DSA_TAG_VSC73XX_8021Q) += tag_vsc73xx_8021q.o obj-$(CONFIG_NET_DSA_TAG_XRS700X) += tag_xrs700x.o # for tracing framework to find trace.h diff --git a/net/dsa/dsa.c b/net/dsa/dsa.c index 12521a7d4048..668c729946ea 100644 --- a/net/dsa/dsa.c +++ b/net/dsa/dsa.c @@ -1507,9 +1507,7 @@ static int dsa_switch_probe(struct dsa_switch *ds) if (ds->phylink_mac_ops) { if (ds->ops->phylink_mac_select_pcs || - ds->ops->phylink_mac_prepare || ds->ops->phylink_mac_config || - ds->ops->phylink_mac_finish || ds->ops->phylink_mac_link_down || ds->ops->phylink_mac_link_up) return -EINVAL; diff --git a/net/dsa/port.c b/net/dsa/port.c index 9a249d4ac3a5..25258b33e59e 100644 --- a/net/dsa/port.c +++ b/net/dsa/port.c @@ -1467,10 +1467,34 @@ int dsa_port_change_conduit(struct dsa_port *dp, struct net_device *conduit, */ dsa_user_unsync_ha(dev); + /* If live-changing, we also need to uninstall the user device address + * from the port FDB and the conduit interface. + */ + if (dev->flags & IFF_UP) + dsa_user_host_uc_uninstall(dev); + err = dsa_port_assign_conduit(dp, conduit, extack, true); if (err) goto rewind_old_addrs; + /* If the port doesn't have its own MAC address and relies on the DSA + * conduit's one, inherit it again from the new DSA conduit. + */ + if (is_zero_ether_addr(dp->mac)) + eth_hw_addr_inherit(dev, conduit); + + /* If live-changing, we need to install the user device address to the + * port FDB and the conduit interface. + */ + if (dev->flags & IFF_UP) { + err = dsa_user_host_uc_install(dev, dev->dev_addr); + if (err) { + NL_SET_ERR_MSG_MOD(extack, + "Failed to install host UC address"); + goto rewind_addr_inherit; + } + } + dsa_user_sync_ha(dev); if (vlan_filtering) { @@ -1500,10 +1524,26 @@ rewind_new_vlan: rewind_new_addrs: dsa_user_unsync_ha(dev); + if (dev->flags & IFF_UP) + dsa_user_host_uc_uninstall(dev); + +rewind_addr_inherit: + if (is_zero_ether_addr(dp->mac)) + eth_hw_addr_inherit(dev, old_conduit); + dsa_port_assign_conduit(dp, old_conduit, NULL, false); /* Restore the objects on the old CPU port */ rewind_old_addrs: + if (dev->flags & IFF_UP) { + tmp = dsa_user_host_uc_install(dev, dev->dev_addr); + if (tmp) { + dev_err(ds->dev, + "port %d failed to restore host UC address: %pe\n", + dp->index, ERR_PTR(tmp)); + } + } + dsa_user_sync_ha(dev); if (vlan_filtering) { @@ -1549,21 +1589,6 @@ dsa_port_phylink_mac_select_pcs(struct phylink_config *config, return pcs; } -static int dsa_port_phylink_mac_prepare(struct phylink_config *config, - unsigned int mode, - phy_interface_t interface) -{ - struct dsa_port *dp = dsa_phylink_to_port(config); - struct dsa_switch *ds = dp->ds; - int err = 0; - - if (ds->ops->phylink_mac_prepare) - err = ds->ops->phylink_mac_prepare(ds, dp->index, mode, - interface); - - return err; -} - static void dsa_port_phylink_mac_config(struct phylink_config *config, unsigned int mode, const struct phylink_link_state *state) @@ -1577,21 +1602,6 @@ static void dsa_port_phylink_mac_config(struct phylink_config *config, ds->ops->phylink_mac_config(ds, dp->index, mode, state); } -static int dsa_port_phylink_mac_finish(struct phylink_config *config, - unsigned int mode, - phy_interface_t interface) -{ - struct dsa_port *dp = dsa_phylink_to_port(config); - struct dsa_switch *ds = dp->ds; - int err = 0; - - if (ds->ops->phylink_mac_finish) - err = ds->ops->phylink_mac_finish(ds, dp->index, mode, - interface); - - return err; -} - static void dsa_port_phylink_mac_link_down(struct phylink_config *config, unsigned int mode, phy_interface_t interface) @@ -1624,9 +1634,7 @@ static void dsa_port_phylink_mac_link_up(struct phylink_config *config, static const struct phylink_mac_ops dsa_port_phylink_mac_ops = { .mac_select_pcs = dsa_port_phylink_mac_select_pcs, - .mac_prepare = dsa_port_phylink_mac_prepare, .mac_config = dsa_port_phylink_mac_config, - .mac_finish = dsa_port_phylink_mac_finish, .mac_link_down = dsa_port_phylink_mac_link_down, .mac_link_up = dsa_port_phylink_mac_link_up, }; diff --git a/net/dsa/tag.c b/net/dsa/tag.c index 6e402d49afd3..79ad105902d9 100644 --- a/net/dsa/tag.c +++ b/net/dsa/tag.c @@ -105,8 +105,9 @@ static int dsa_switch_rcv(struct sk_buff *skb, struct net_device *dev, p = netdev_priv(skb->dev); - if (unlikely(cpu_dp->ds->untag_bridge_pvid)) { - nskb = dsa_untag_bridge_pvid(skb); + if (unlikely(cpu_dp->ds->untag_bridge_pvid || + cpu_dp->ds->untag_vlan_aware_bridge_pvid)) { + nskb = dsa_software_vlan_untag(skb); if (!nskb) { kfree_skb(skb); return 0; diff --git a/net/dsa/tag.h b/net/dsa/tag.h index f6b9c73718df..d5707870906b 100644 --- a/net/dsa/tag.h +++ b/net/dsa/tag.h @@ -44,46 +44,81 @@ static inline struct net_device *dsa_conduit_find_user(struct net_device *dev, return NULL; } -/* If under a bridge with vlan_filtering=0, make sure to send pvid-tagged - * frames as untagged, since the bridge will not untag them. +/** + * dsa_software_untag_vlan_aware_bridge: Software untagging for VLAN-aware bridge + * @skb: Pointer to received socket buffer (packet) + * @br: Pointer to bridge upper interface of ingress port + * @vid: Parsed VID from packet + * + * The bridge can process tagged packets. Software like STP/PTP may not. The + * bridge can also process untagged packets, to the same effect as if they were + * tagged with the PVID of the ingress port. So packets tagged with the PVID of + * the bridge port must be software-untagged, to support both use cases. */ -static inline struct sk_buff *dsa_untag_bridge_pvid(struct sk_buff *skb) +static inline void dsa_software_untag_vlan_aware_bridge(struct sk_buff *skb, + struct net_device *br, + u16 vid) { - struct dsa_port *dp = dsa_user_to_port(skb->dev); - struct net_device *br = dsa_port_bridge_dev_get(dp); - struct net_device *dev = skb->dev; - struct net_device *upper_dev; - u16 vid, pvid, proto; + u16 pvid, proto; int err; - if (!br || br_vlan_enabled(br)) - return skb; - err = br_vlan_get_proto(br, &proto); if (err) - return skb; + return; - /* Move VLAN tag from data to hwaccel */ - if (!skb_vlan_tag_present(skb) && skb->protocol == htons(proto)) { - skb = skb_vlan_untag(skb); - if (!skb) - return NULL; - } + err = br_vlan_get_pvid_rcu(skb->dev, &pvid); + if (err) + return; - if (!skb_vlan_tag_present(skb)) - return skb; + if (vid == pvid && skb->vlan_proto == htons(proto)) + __vlan_hwaccel_clear_tag(skb); +} - vid = skb_vlan_tag_get_id(skb); +/** + * dsa_software_untag_vlan_unaware_bridge: Software untagging for VLAN-unaware bridge + * @skb: Pointer to received socket buffer (packet) + * @br: Pointer to bridge upper interface of ingress port + * @vid: Parsed VID from packet + * + * The bridge ignores all VLAN tags. Software like STP/PTP may not (it may run + * on the plain port, or on a VLAN upper interface). Maybe packets are coming + * to software as tagged with a driver-defined VID which is NOT equal to the + * PVID of the bridge port (since the bridge is VLAN-unaware, its configuration + * should NOT be committed to hardware). DSA needs a method for this private + * VID to be communicated by software to it, and if packets are tagged with it, + * software-untag them. Note: the private VID may be different per bridge, to + * support the FDB isolation use case. + * + * FIXME: this is currently implemented based on the broken assumption that + * the "private VID" used by the driver in VLAN-unaware mode is equal to the + * bridge PVID. It should not be, except for a coincidence; the bridge PVID is + * irrelevant to the data path in the VLAN-unaware mode. Thus, the VID that + * this function removes is wrong. + * + * All users of ds->untag_bridge_pvid should fix their drivers, if necessary, + * to make the two independent. Only then, if there still remains a need to + * strip the private VID from packets, then a new ds->ops->get_private_vid() + * API shall be introduced to communicate to DSA what this VID is, which needs + * to be stripped here. + */ +static inline void dsa_software_untag_vlan_unaware_bridge(struct sk_buff *skb, + struct net_device *br, + u16 vid) +{ + struct net_device *upper_dev; + u16 pvid, proto; + int err; - /* We already run under an RCU read-side critical section since - * we are called from netif_receive_skb_list_internal(). - */ - err = br_vlan_get_pvid_rcu(dev, &pvid); + err = br_vlan_get_proto(br, &proto); if (err) - return skb; + return; - if (vid != pvid) - return skb; + err = br_vlan_get_pvid_rcu(skb->dev, &pvid); + if (err) + return; + + if (vid != pvid || skb->vlan_proto != htons(proto)) + return; /* The sad part about attempting to untag from DSA is that we * don't know, unless we check, if the skb will end up in @@ -95,10 +130,50 @@ static inline struct sk_buff *dsa_untag_bridge_pvid(struct sk_buff *skb) * definitely keep the tag, to make sure it keeps working. */ upper_dev = __vlan_find_dev_deep_rcu(br, htons(proto), vid); - if (upper_dev) + if (!upper_dev) + __vlan_hwaccel_clear_tag(skb); +} + +/** + * dsa_software_vlan_untag: Software VLAN untagging in DSA receive path + * @skb: Pointer to socket buffer (packet) + * + * Receive path method for switches which cannot avoid tagging all packets + * towards the CPU port. Called when ds->untag_bridge_pvid (legacy) or + * ds->untag_vlan_aware_bridge_pvid is set to true. + * + * As a side effect of this method, any VLAN tag from the skb head is moved + * to hwaccel. + */ +static inline struct sk_buff *dsa_software_vlan_untag(struct sk_buff *skb) +{ + struct dsa_port *dp = dsa_user_to_port(skb->dev); + struct net_device *br = dsa_port_bridge_dev_get(dp); + u16 vid; + + /* software untagging for standalone ports not yet necessary */ + if (!br) return skb; - __vlan_hwaccel_clear_tag(skb); + /* Move VLAN tag from data to hwaccel */ + if (!skb_vlan_tag_present(skb)) { + skb = skb_vlan_untag(skb); + if (!skb) + return NULL; + } + + if (!skb_vlan_tag_present(skb)) + return skb; + + vid = skb_vlan_tag_get_id(skb); + + if (br_vlan_enabled(br)) { + if (dp->ds->untag_vlan_aware_bridge_pvid) + dsa_software_untag_vlan_aware_bridge(skb, br, vid); + } else { + if (dp->ds->untag_bridge_pvid) + dsa_software_untag_vlan_unaware_bridge(skb, br, vid); + } return skb; } diff --git a/net/dsa/tag_8021q.c b/net/dsa/tag_8021q.c index 71b26ae6db39..3ee53e28ec2e 100644 --- a/net/dsa/tag_8021q.c +++ b/net/dsa/tag_8021q.c @@ -286,7 +286,8 @@ int dsa_switch_tag_8021q_vlan_del(struct dsa_switch *ds, * be used for VLAN-unaware bridging. */ int dsa_tag_8021q_bridge_join(struct dsa_switch *ds, int port, - struct dsa_bridge bridge) + struct dsa_bridge bridge, bool *tx_fwd_offload, + struct netlink_ext_ack *extack) { struct dsa_port *dp = dsa_to_port(ds, port); u16 standalone_vid, bridge_vid; @@ -304,6 +305,8 @@ int dsa_tag_8021q_bridge_join(struct dsa_switch *ds, int port, dsa_port_tag_8021q_vlan_del(dp, standalone_vid, false); + *tx_fwd_offload = true; + return 0; } EXPORT_SYMBOL_GPL(dsa_tag_8021q_bridge_join); @@ -468,8 +471,8 @@ struct sk_buff *dsa_8021q_xmit(struct sk_buff *skb, struct net_device *netdev, } EXPORT_SYMBOL_GPL(dsa_8021q_xmit); -struct net_device *dsa_tag_8021q_find_port_by_vbid(struct net_device *conduit, - int vbid) +static struct net_device * +dsa_tag_8021q_find_port_by_vbid(struct net_device *conduit, int vbid) { struct dsa_port *cpu_dp = conduit->dsa_ptr; struct dsa_switch_tree *dst = cpu_dp->dst; @@ -495,30 +498,91 @@ struct net_device *dsa_tag_8021q_find_port_by_vbid(struct net_device *conduit, return NULL; } -EXPORT_SYMBOL_GPL(dsa_tag_8021q_find_port_by_vbid); +struct net_device *dsa_tag_8021q_find_user(struct net_device *conduit, + int source_port, int switch_id, + int vid, int vbid) +{ + /* Always prefer precise source port information, if available */ + if (source_port != -1 && switch_id != -1) + return dsa_conduit_find_user(conduit, switch_id, source_port); + else if (vbid >= 1) + return dsa_tag_8021q_find_port_by_vbid(conduit, vbid); + + return dsa_find_designated_bridge_port_by_vid(conduit, vid); +} +EXPORT_SYMBOL_GPL(dsa_tag_8021q_find_user); + +/** + * dsa_8021q_rcv - Decode source information from tag_8021q header + * @skb: RX socket buffer + * @source_port: pointer to storage for precise source port information. + * If this is known already from outside tag_8021q, the pre-initialized + * value is preserved. If not known, pass -1. + * @switch_id: similar to source_port. + * @vbid: pointer to storage for imprecise bridge ID. Must be pre-initialized + * with -1. If a positive value is returned, the source_port and switch_id + * are invalid. + * @vid: pointer to storage for original VID, in case tag_8021q decoding failed. + * + * If the packet has a tag_8021q header, decode it and set @source_port, + * @switch_id and @vbid, and strip the header. Otherwise set @vid and keep the + * header in the hwaccel area of the packet. + */ void dsa_8021q_rcv(struct sk_buff *skb, int *source_port, int *switch_id, - int *vbid) + int *vbid, int *vid) { - u16 vid, tci; + int tmp_source_port, tmp_switch_id, tmp_vbid; + __be16 vlan_proto; + u16 tmp_vid, tci; if (skb_vlan_tag_present(skb)) { + vlan_proto = skb->vlan_proto; tci = skb_vlan_tag_get(skb); __vlan_hwaccel_clear_tag(skb); } else { + struct vlan_ethhdr *hdr = vlan_eth_hdr(skb); + + vlan_proto = hdr->h_vlan_proto; skb_push_rcsum(skb, ETH_HLEN); __skb_vlan_pop(skb, &tci); skb_pull_rcsum(skb, ETH_HLEN); } - vid = tci & VLAN_VID_MASK; + tmp_vid = tci & VLAN_VID_MASK; + if (!vid_is_dsa_8021q(tmp_vid)) { + /* Not a tag_8021q frame, so return the VID to the + * caller for further processing, and put the tag back + */ + if (vid) + *vid = tmp_vid; + + __vlan_hwaccel_put_tag(skb, vlan_proto, tci); + + return; + } - *source_port = dsa_8021q_rx_source_port(vid); - *switch_id = dsa_8021q_rx_switch_id(vid); + tmp_source_port = dsa_8021q_rx_source_port(tmp_vid); + tmp_switch_id = dsa_8021q_rx_switch_id(tmp_vid); + tmp_vbid = dsa_tag_8021q_rx_vbid(tmp_vid); + + /* Precise source port information is unknown when receiving from a + * VLAN-unaware bridging domain, and tmp_source_port and tmp_switch_id + * are zeroes in this case. + * + * Preserve the source information from hardware-specific mechanisms, + * if available. This allows us to not overwrite a valid source port + * and switch ID with less precise values. + */ + if (tmp_vbid == 0 && *source_port == -1) + *source_port = tmp_source_port; + if (tmp_vbid == 0 && *switch_id == -1) + *switch_id = tmp_switch_id; if (vbid) - *vbid = dsa_tag_8021q_rx_vbid(vid); + *vbid = tmp_vbid; skb->priority = (tci & VLAN_PRIO_MASK) >> VLAN_PRIO_SHIFT; + return; } EXPORT_SYMBOL_GPL(dsa_8021q_rcv); diff --git a/net/dsa/tag_8021q.h b/net/dsa/tag_8021q.h index 41f7167ac520..27b8906f99ec 100644 --- a/net/dsa/tag_8021q.h +++ b/net/dsa/tag_8021q.h @@ -14,10 +14,11 @@ struct sk_buff *dsa_8021q_xmit(struct sk_buff *skb, struct net_device *netdev, u16 tpid, u16 tci); void dsa_8021q_rcv(struct sk_buff *skb, int *source_port, int *switch_id, - int *vbid); + int *vbid, int *vid); -struct net_device *dsa_tag_8021q_find_port_by_vbid(struct net_device *conduit, - int vbid); +struct net_device *dsa_tag_8021q_find_user(struct net_device *conduit, + int source_port, int switch_id, + int vid, int vbid); int dsa_switch_tag_8021q_vlan_add(struct dsa_switch *ds, struct dsa_notifier_tag_8021q_vlan_info *info); diff --git a/net/dsa/tag_ksz.c b/net/dsa/tag_ksz.c index ee7b272ab715..281bbac5539d 100644 --- a/net/dsa/tag_ksz.c +++ b/net/dsa/tag_ksz.c @@ -111,9 +111,10 @@ static struct sk_buff *ksz_common_rcv(struct sk_buff *skb, * DA(6bytes)|SA(6bytes)|....|Data(nbytes)|tag0(1byte)|FCS(4bytes) * --------------------------------------------------------------------------- * tag0 : zero-based value represents port - * (eg, 0x00=port1, 0x02=port3, 0x06=port7) + * (eg, 0x0=port1, 0x2=port3, 0x3=port4) */ +#define KSZ8795_TAIL_TAG_EG_PORT_M GENMASK(1, 0) #define KSZ8795_TAIL_TAG_OVERRIDE BIT(6) #define KSZ8795_TAIL_TAG_LOOKUP BIT(7) @@ -141,7 +142,8 @@ static struct sk_buff *ksz8795_rcv(struct sk_buff *skb, struct net_device *dev) { u8 *tag = skb_tail_pointer(skb) - KSZ_EGRESS_TAG_LEN; - return ksz_common_rcv(skb, dev, tag[0] & 7, KSZ_EGRESS_TAG_LEN); + return ksz_common_rcv(skb, dev, tag[0] & KSZ8795_TAIL_TAG_EG_PORT_M, + KSZ_EGRESS_TAG_LEN); } static const struct dsa_device_ops ksz8795_netdev_ops = { @@ -176,8 +178,9 @@ MODULE_ALIAS_DSA_TAG_DRIVER(DSA_TAG_PROTO_KSZ8795, KSZ8795_NAME); #define KSZ9477_INGRESS_TAG_LEN 2 #define KSZ9477_PTP_TAG_LEN 4 -#define KSZ9477_PTP_TAG_INDICATION 0x80 +#define KSZ9477_PTP_TAG_INDICATION BIT(7) +#define KSZ9477_TAIL_TAG_EG_PORT_M GENMASK(2, 0) #define KSZ9477_TAIL_TAG_PRIO GENMASK(8, 7) #define KSZ9477_TAIL_TAG_OVERRIDE BIT(9) #define KSZ9477_TAIL_TAG_LOOKUP BIT(10) @@ -310,7 +313,7 @@ static struct sk_buff *ksz9477_rcv(struct sk_buff *skb, struct net_device *dev) { /* Tag decoding */ u8 *tag = skb_tail_pointer(skb) - KSZ_EGRESS_TAG_LEN; - unsigned int port = tag[0] & 7; + unsigned int port = tag[0] & KSZ9477_TAIL_TAG_EG_PORT_M; unsigned int len = KSZ_EGRESS_TAG_LEN; /* Extra 4-bytes PTP timestamp */ diff --git a/net/dsa/tag_ocelot.c b/net/dsa/tag_ocelot.c index e0e4300bfbd3..bf6608fc6be7 100644 --- a/net/dsa/tag_ocelot.c +++ b/net/dsa/tag_ocelot.c @@ -8,40 +8,6 @@ #define OCELOT_NAME "ocelot" #define SEVILLE_NAME "seville" -/* If the port is under a VLAN-aware bridge, remove the VLAN header from the - * payload and move it into the DSA tag, which will make the switch classify - * the packet to the bridge VLAN. Otherwise, leave the classified VLAN at zero, - * which is the pvid of standalone and VLAN-unaware bridge ports. - */ -static void ocelot_xmit_get_vlan_info(struct sk_buff *skb, struct dsa_port *dp, - u64 *vlan_tci, u64 *tag_type) -{ - struct net_device *br = dsa_port_bridge_dev_get(dp); - struct vlan_ethhdr *hdr; - u16 proto, tci; - - if (!br || !br_vlan_enabled(br)) { - *vlan_tci = 0; - *tag_type = IFH_TAG_TYPE_C; - return; - } - - hdr = skb_vlan_eth_hdr(skb); - br_vlan_get_proto(br, &proto); - - if (ntohs(hdr->h_vlan_proto) == proto) { - vlan_remove_tag(skb, &tci); - *vlan_tci = tci; - } else { - rcu_read_lock(); - br_vlan_get_pvid_rcu(br, &tci); - rcu_read_unlock(); - *vlan_tci = tci; - } - - *tag_type = (proto != ETH_P_8021Q) ? IFH_TAG_TYPE_S : IFH_TAG_TYPE_C; -} - static void ocelot_xmit_common(struct sk_buff *skb, struct net_device *netdev, __be32 ifh_prefix, void **ifh) { @@ -53,7 +19,8 @@ static void ocelot_xmit_common(struct sk_buff *skb, struct net_device *netdev, u32 rew_op = 0; u64 qos_class; - ocelot_xmit_get_vlan_info(skb, dp, &vlan_tci, &tag_type); + ocelot_xmit_get_vlan_info(skb, dsa_port_bridge_dev_get(dp), &vlan_tci, + &tag_type); qos_class = netdev_get_num_tc(netdev) ? netdev_get_prio_tc_map(netdev, skb->priority) : skb->priority; diff --git a/net/dsa/tag_ocelot_8021q.c b/net/dsa/tag_ocelot_8021q.c index b059381310fe..8e8b1bef6af6 100644 --- a/net/dsa/tag_ocelot_8021q.c +++ b/net/dsa/tag_ocelot_8021q.c @@ -81,7 +81,7 @@ static struct sk_buff *ocelot_rcv(struct sk_buff *skb, { int src_port, switch_id; - dsa_8021q_rcv(skb, &src_port, &switch_id, NULL); + dsa_8021q_rcv(skb, &src_port, &switch_id, NULL, NULL); skb->dev = dsa_conduit_find_user(netdev, switch_id, src_port); if (!skb->dev) diff --git a/net/dsa/tag_sja1105.c b/net/dsa/tag_sja1105.c index 1aba1d05c27a..3e902af7eea6 100644 --- a/net/dsa/tag_sja1105.c +++ b/net/dsa/tag_sja1105.c @@ -472,37 +472,14 @@ static bool sja1110_skb_has_inband_control_extension(const struct sk_buff *skb) return ntohs(eth_hdr(skb)->h_proto) == ETH_P_SJA1110; } -/* If the VLAN in the packet is a tag_8021q one, set @source_port and - * @switch_id and strip the header. Otherwise set @vid and keep it in the - * packet. - */ -static void sja1105_vlan_rcv(struct sk_buff *skb, int *source_port, - int *switch_id, int *vbid, u16 *vid) -{ - struct vlan_ethhdr *hdr = vlan_eth_hdr(skb); - u16 vlan_tci; - - if (skb_vlan_tag_present(skb)) - vlan_tci = skb_vlan_tag_get(skb); - else - vlan_tci = ntohs(hdr->h_vlan_TCI); - - if (vid_is_dsa_8021q(vlan_tci & VLAN_VID_MASK)) - return dsa_8021q_rcv(skb, source_port, switch_id, vbid); - - /* Try our best with imprecise RX */ - *vid = vlan_tci & VLAN_VID_MASK; -} - static struct sk_buff *sja1105_rcv(struct sk_buff *skb, struct net_device *netdev) { - int source_port = -1, switch_id = -1, vbid = -1; + int source_port = -1, switch_id = -1, vbid = -1, vid = -1; struct sja1105_meta meta = {0}; struct ethhdr *hdr; bool is_link_local; bool is_meta; - u16 vid; hdr = eth_hdr(skb); is_link_local = sja1105_is_link_local(skb); @@ -524,37 +501,16 @@ static struct sk_buff *sja1105_rcv(struct sk_buff *skb, /* Normal data plane traffic and link-local frames are tagged with * a tag_8021q VLAN which we have to strip */ - if (sja1105_skb_has_tag_8021q(skb)) { - int tmp_source_port = -1, tmp_switch_id = -1; - - sja1105_vlan_rcv(skb, &tmp_source_port, &tmp_switch_id, &vbid, - &vid); - /* Preserve the source information from the INCL_SRCPT option, - * if available. This allows us to not overwrite a valid source - * port and switch ID with zeroes when receiving link-local - * frames from a VLAN-unaware bridged port (non-zero vbid) or a - * VLAN-aware bridged port (non-zero vid). Furthermore, the - * tag_8021q source port information is only of trust when the - * vbid is 0 (precise port). Otherwise, tmp_source_port and - * tmp_switch_id will be zeroes. - */ - if (vbid == 0 && source_port == -1) - source_port = tmp_source_port; - if (vbid == 0 && switch_id == -1) - switch_id = tmp_switch_id; - } else if (source_port == -1 && switch_id == -1) { + if (sja1105_skb_has_tag_8021q(skb)) + dsa_8021q_rcv(skb, &source_port, &switch_id, &vbid, &vid); + else if (source_port == -1 && switch_id == -1) /* Packets with no source information have no chance of * getting accepted, drop them straight away. */ return NULL; - } - if (source_port != -1 && switch_id != -1) - skb->dev = dsa_conduit_find_user(netdev, switch_id, source_port); - else if (vbid >= 1) - skb->dev = dsa_tag_8021q_find_port_by_vbid(netdev, vbid); - else - skb->dev = dsa_find_designated_bridge_port_by_vid(netdev, vid); + skb->dev = dsa_tag_8021q_find_user(netdev, source_port, switch_id, + vid, vbid); if (!skb->dev) { netdev_warn(netdev, "Couldn't decode source port\n"); return NULL; @@ -677,9 +633,8 @@ static struct sk_buff *sja1110_rcv_inband_control_extension(struct sk_buff *skb, static struct sk_buff *sja1110_rcv(struct sk_buff *skb, struct net_device *netdev) { - int source_port = -1, switch_id = -1, vbid = -1; + int source_port = -1, switch_id = -1, vbid = -1, vid = -1; bool host_only = false; - u16 vid = 0; if (sja1110_skb_has_inband_control_extension(skb)) { skb = sja1110_rcv_inband_control_extension(skb, &source_port, @@ -691,14 +646,11 @@ static struct sk_buff *sja1110_rcv(struct sk_buff *skb, /* Packets with in-band control extensions might still have RX VLANs */ if (likely(sja1105_skb_has_tag_8021q(skb))) - sja1105_vlan_rcv(skb, &source_port, &switch_id, &vbid, &vid); - - if (vbid >= 1) - skb->dev = dsa_tag_8021q_find_port_by_vbid(netdev, vbid); - else if (source_port == -1 || switch_id == -1) - skb->dev = dsa_find_designated_bridge_port_by_vid(netdev, vid); - else - skb->dev = dsa_conduit_find_user(netdev, switch_id, source_port); + dsa_8021q_rcv(skb, &source_port, &switch_id, &vbid, &vid); + + skb->dev = dsa_tag_8021q_find_user(netdev, source_port, switch_id, + vid, vbid); + if (!skb->dev) { netdev_warn(netdev, "Couldn't decode source port\n"); return NULL; diff --git a/net/dsa/tag_vsc73xx_8021q.c b/net/dsa/tag_vsc73xx_8021q.c new file mode 100644 index 000000000000..af121a9aff7f --- /dev/null +++ b/net/dsa/tag_vsc73xx_8021q.c @@ -0,0 +1,68 @@ +// SPDX-License-Identifier: GPL-2.0 OR MIT +/* Copyright (C) 2024 Pawel Dembicki <paweldembicki@gmail.com> + */ +#include <linux/dsa/8021q.h> + +#include "tag.h" +#include "tag_8021q.h" + +#define VSC73XX_8021Q_NAME "vsc73xx-8021q" + +static struct sk_buff * +vsc73xx_xmit(struct sk_buff *skb, struct net_device *netdev) +{ + struct dsa_port *dp = dsa_user_to_port(netdev); + u16 queue_mapping = skb_get_queue_mapping(skb); + u16 tx_vid = dsa_tag_8021q_standalone_vid(dp); + u8 pcp; + + if (skb->offload_fwd_mark) { + unsigned int bridge_num = dsa_port_bridge_num_get(dp); + struct net_device *br = dsa_port_bridge_dev_get(dp); + + if (br_vlan_enabled(br)) + return skb; + + tx_vid = dsa_tag_8021q_bridge_vid(bridge_num); + } + + pcp = netdev_txq_to_tc(netdev, queue_mapping); + + return dsa_8021q_xmit(skb, netdev, ETH_P_8021Q, + ((pcp << VLAN_PRIO_SHIFT) | tx_vid)); +} + +static struct sk_buff * +vsc73xx_rcv(struct sk_buff *skb, struct net_device *netdev) +{ + int src_port = -1, switch_id = -1, vbid = -1, vid = -1; + + dsa_8021q_rcv(skb, &src_port, &switch_id, &vbid, &vid); + + skb->dev = dsa_tag_8021q_find_user(netdev, src_port, switch_id, + vid, vbid); + if (!skb->dev) { + dev_warn_ratelimited(&netdev->dev, + "Couldn't decode source port\n"); + return NULL; + } + + dsa_default_offload_fwd_mark(skb); + + return skb; +} + +static const struct dsa_device_ops vsc73xx_8021q_netdev_ops = { + .name = VSC73XX_8021Q_NAME, + .proto = DSA_TAG_PROTO_VSC73XX_8021Q, + .xmit = vsc73xx_xmit, + .rcv = vsc73xx_rcv, + .needed_headroom = VLAN_HLEN, + .promisc_on_conduit = true, +}; + +MODULE_LICENSE("GPL"); +MODULE_DESCRIPTION("DSA tag driver for VSC73XX family of switches, using VLAN"); +MODULE_ALIAS_DSA_TAG_DRIVER(DSA_TAG_PROTO_VSC73XX_8021Q, VSC73XX_8021Q_NAME); + +module_dsa_tag_driver(vsc73xx_8021q_netdev_ops); diff --git a/net/dsa/user.c b/net/dsa/user.c index 867c5fe9a4da..74eda9b30608 100644 --- a/net/dsa/user.c +++ b/net/dsa/user.c @@ -355,60 +355,82 @@ static int dsa_user_get_iflink(const struct net_device *dev) return READ_ONCE(dsa_user_to_conduit(dev)->ifindex); } -static int dsa_user_open(struct net_device *dev) +int dsa_user_host_uc_install(struct net_device *dev, const u8 *addr) { struct net_device *conduit = dsa_user_to_conduit(dev); struct dsa_port *dp = dsa_user_to_port(dev); struct dsa_switch *ds = dp->ds; int err; - err = dev_open(conduit, NULL); - if (err < 0) { - netdev_err(dev, "failed to open conduit %s\n", conduit->name); - goto out; - } - if (dsa_switch_supports_uc_filtering(ds)) { - err = dsa_port_standalone_host_fdb_add(dp, dev->dev_addr, 0); + err = dsa_port_standalone_host_fdb_add(dp, addr, 0); if (err) goto out; } - if (!ether_addr_equal(dev->dev_addr, conduit->dev_addr)) { - err = dev_uc_add(conduit, dev->dev_addr); + if (!ether_addr_equal(addr, conduit->dev_addr)) { + err = dev_uc_add(conduit, addr); if (err < 0) goto del_host_addr; } - err = dsa_port_enable_rt(dp, dev->phydev); - if (err) - goto del_unicast; - return 0; -del_unicast: - if (!ether_addr_equal(dev->dev_addr, conduit->dev_addr)) - dev_uc_del(conduit, dev->dev_addr); del_host_addr: if (dsa_switch_supports_uc_filtering(ds)) - dsa_port_standalone_host_fdb_del(dp, dev->dev_addr, 0); + dsa_port_standalone_host_fdb_del(dp, addr, 0); out: return err; } -static int dsa_user_close(struct net_device *dev) +void dsa_user_host_uc_uninstall(struct net_device *dev) { struct net_device *conduit = dsa_user_to_conduit(dev); struct dsa_port *dp = dsa_user_to_port(dev); struct dsa_switch *ds = dp->ds; - dsa_port_disable_rt(dp); - if (!ether_addr_equal(dev->dev_addr, conduit->dev_addr)) dev_uc_del(conduit, dev->dev_addr); if (dsa_switch_supports_uc_filtering(ds)) dsa_port_standalone_host_fdb_del(dp, dev->dev_addr, 0); +} + +static int dsa_user_open(struct net_device *dev) +{ + struct net_device *conduit = dsa_user_to_conduit(dev); + struct dsa_port *dp = dsa_user_to_port(dev); + int err; + + err = dev_open(conduit, NULL); + if (err < 0) { + netdev_err(dev, "failed to open conduit %s\n", conduit->name); + goto out; + } + + err = dsa_user_host_uc_install(dev, dev->dev_addr); + if (err) + goto out; + + err = dsa_port_enable_rt(dp, dev->phydev); + if (err) + goto out_del_host_uc; + + return 0; + +out_del_host_uc: + dsa_user_host_uc_uninstall(dev); +out: + return err; +} + +static int dsa_user_close(struct net_device *dev) +{ + struct dsa_port *dp = dsa_user_to_port(dev); + + dsa_port_disable_rt(dp); + + dsa_user_host_uc_uninstall(dev); return 0; } @@ -448,7 +470,6 @@ static void dsa_user_set_rx_mode(struct net_device *dev) static int dsa_user_set_mac_address(struct net_device *dev, void *a) { - struct net_device *conduit = dsa_user_to_conduit(dev); struct dsa_port *dp = dsa_user_to_port(dev); struct dsa_switch *ds = dp->ds; struct sockaddr *addr = a; @@ -470,34 +491,16 @@ static int dsa_user_set_mac_address(struct net_device *dev, void *a) if (!(dev->flags & IFF_UP)) goto out_change_dev_addr; - if (dsa_switch_supports_uc_filtering(ds)) { - err = dsa_port_standalone_host_fdb_add(dp, addr->sa_data, 0); - if (err) - return err; - } + err = dsa_user_host_uc_install(dev, addr->sa_data); + if (err) + return err; - if (!ether_addr_equal(addr->sa_data, conduit->dev_addr)) { - err = dev_uc_add(conduit, addr->sa_data); - if (err < 0) - goto del_unicast; - } - - if (!ether_addr_equal(dev->dev_addr, conduit->dev_addr)) - dev_uc_del(conduit, dev->dev_addr); - - if (dsa_switch_supports_uc_filtering(ds)) - dsa_port_standalone_host_fdb_del(dp, dev->dev_addr, 0); + dsa_user_host_uc_uninstall(dev); out_change_dev_addr: eth_hw_addr_set(dev, addr->sa_data); return 0; - -del_unicast: - if (dsa_switch_supports_uc_filtering(ds)) - dsa_port_standalone_host_fdb_del(dp, addr->sa_data, 0); - - return err; } struct dsa_user_dump_ctx { @@ -1726,7 +1729,7 @@ static int dsa_user_set_rxnfc(struct net_device *dev, } static int dsa_user_get_ts_info(struct net_device *dev, - struct ethtool_ts_info *ts) + struct kernel_ethtool_ts_info *ts) { struct dsa_user_priv *p = netdev_priv(dev); struct dsa_switch *ds = p->dp->ds; @@ -2639,11 +2642,12 @@ void dsa_user_setup_tagger(struct net_device *user) user->features = conduit->vlan_features | NETIF_F_HW_TC; user->hw_features |= NETIF_F_HW_TC; - user->features |= NETIF_F_LLTX; if (user->needed_tailroom) user->features &= ~(NETIF_F_SG | NETIF_F_FRAGLIST); if (ds->needs_standalone_vlan_filtering) user->features |= NETIF_F_HW_VLAN_CTAG_FILTER; + + user->lltx = true; } int dsa_user_suspend(struct net_device *user_dev) @@ -2879,12 +2883,6 @@ int dsa_user_change_conduit(struct net_device *dev, struct net_device *conduit, ERR_PTR(err)); } - /* If the port doesn't have its own MAC address and relies on the DSA - * conduit's one, inherit it again from the new DSA conduit. - */ - if (is_zero_ether_addr(dp->mac)) - eth_hw_addr_inherit(dev, conduit); - return 0; out_revert_conduit_link: diff --git a/net/dsa/user.h b/net/dsa/user.h index 996069130bea..016884bead3c 100644 --- a/net/dsa/user.h +++ b/net/dsa/user.h @@ -42,6 +42,8 @@ int dsa_user_suspend(struct net_device *user_dev); int dsa_user_resume(struct net_device *user_dev); int dsa_user_register_notifier(void); void dsa_user_unregister_notifier(void); +int dsa_user_host_uc_install(struct net_device *dev, const u8 *addr); +void dsa_user_host_uc_uninstall(struct net_device *dev); void dsa_user_sync_ha(struct net_device *dev); void dsa_user_unsync_ha(struct net_device *dev); void dsa_user_setup_tagger(struct net_device *user); diff --git a/net/ethtool/Makefile b/net/ethtool/Makefile index 504f954a1b28..9b540644ba31 100644 --- a/net/ethtool/Makefile +++ b/net/ethtool/Makefile @@ -8,4 +8,5 @@ ethtool_nl-y := netlink.o bitset.o strset.o linkinfo.o linkmodes.o rss.o \ linkstate.o debug.o wol.o features.o privflags.o rings.o \ channels.o coalesce.o pause.o eee.o tsinfo.o cabletest.o \ tunnels.o fec.o eeprom.o stats.o phc_vclocks.o mm.o \ - module.o pse-pd.o plca.o mm.o + module.o cmis_fw_update.o cmis_cdb.o pse-pd.o plca.o mm.o \ + phy.o diff --git a/net/ethtool/cabletest.c b/net/ethtool/cabletest.c index 06a151165c31..f22051f33868 100644 --- a/net/ethtool/cabletest.c +++ b/net/ethtool/cabletest.c @@ -13,7 +13,7 @@ const struct nla_policy ethnl_cable_test_act_policy[] = { [ETHTOOL_A_CABLE_TEST_HEADER] = - NLA_POLICY_NESTED(ethnl_header_policy), + NLA_POLICY_NESTED(ethnl_header_policy_phy), }; static int ethnl_cable_test_started(struct phy_device *phydev, u8 cmd) @@ -58,6 +58,7 @@ int ethnl_act_cable_test(struct sk_buff *skb, struct genl_info *info) struct ethnl_req_info req_info = {}; const struct ethtool_phy_ops *ops; struct nlattr **tb = info->attrs; + struct phy_device *phydev; struct net_device *dev; int ret; @@ -69,12 +70,16 @@ int ethnl_act_cable_test(struct sk_buff *skb, struct genl_info *info) return ret; dev = req_info.dev; - if (!dev->phydev) { + + rtnl_lock(); + phydev = ethnl_req_get_phydev(&req_info, + tb[ETHTOOL_A_CABLE_TEST_HEADER], + info->extack); + if (IS_ERR_OR_NULL(phydev)) { ret = -EOPNOTSUPP; - goto out_dev_put; + goto out_rtnl; } - rtnl_lock(); ops = ethtool_phy_ops; if (!ops || !ops->start_cable_test) { ret = -EOPNOTSUPP; @@ -85,17 +90,15 @@ int ethnl_act_cable_test(struct sk_buff *skb, struct genl_info *info) if (ret < 0) goto out_rtnl; - ret = ops->start_cable_test(dev->phydev, info->extack); + ret = ops->start_cable_test(phydev, info->extack); ethnl_ops_complete(dev); if (!ret) - ethnl_cable_test_started(dev->phydev, - ETHTOOL_MSG_CABLE_TEST_NTF); + ethnl_cable_test_started(phydev, ETHTOOL_MSG_CABLE_TEST_NTF); out_rtnl: rtnl_unlock(); -out_dev_put: ethnl_parse_header_dev_put(&req_info); return ret; } @@ -160,7 +163,8 @@ void ethnl_cable_test_finished(struct phy_device *phydev) } EXPORT_SYMBOL_GPL(ethnl_cable_test_finished); -int ethnl_cable_test_result(struct phy_device *phydev, u8 pair, u8 result) +int ethnl_cable_test_result_with_src(struct phy_device *phydev, u8 pair, + u8 result, u32 src) { struct nlattr *nest; int ret = -EMSGSIZE; @@ -173,6 +177,10 @@ int ethnl_cable_test_result(struct phy_device *phydev, u8 pair, u8 result) goto err; if (nla_put_u8(phydev->skb, ETHTOOL_A_CABLE_RESULT_CODE, result)) goto err; + if (src != ETHTOOL_A_CABLE_INF_SRC_UNSPEC) { + if (nla_put_u32(phydev->skb, ETHTOOL_A_CABLE_RESULT_SRC, src)) + goto err; + } nla_nest_end(phydev->skb, nest); return 0; @@ -181,9 +189,10 @@ err: nla_nest_cancel(phydev->skb, nest); return ret; } -EXPORT_SYMBOL_GPL(ethnl_cable_test_result); +EXPORT_SYMBOL_GPL(ethnl_cable_test_result_with_src); -int ethnl_cable_test_fault_length(struct phy_device *phydev, u8 pair, u32 cm) +int ethnl_cable_test_fault_length_with_src(struct phy_device *phydev, u8 pair, + u32 cm, u32 src) { struct nlattr *nest; int ret = -EMSGSIZE; @@ -197,6 +206,11 @@ int ethnl_cable_test_fault_length(struct phy_device *phydev, u8 pair, u32 cm) goto err; if (nla_put_u32(phydev->skb, ETHTOOL_A_CABLE_FAULT_LENGTH_CM, cm)) goto err; + if (src != ETHTOOL_A_CABLE_INF_SRC_UNSPEC) { + if (nla_put_u32(phydev->skb, ETHTOOL_A_CABLE_FAULT_LENGTH_SRC, + src)) + goto err; + } nla_nest_end(phydev->skb, nest); return 0; @@ -205,11 +219,7 @@ err: nla_nest_cancel(phydev->skb, nest); return ret; } -EXPORT_SYMBOL_GPL(ethnl_cable_test_fault_length); - -struct cable_test_tdr_req_info { - struct ethnl_req_info base; -}; +EXPORT_SYMBOL_GPL(ethnl_cable_test_fault_length_with_src); static const struct nla_policy cable_test_tdr_act_cfg_policy[] = { [ETHTOOL_A_CABLE_TEST_TDR_CFG_FIRST] = { .type = NLA_U32 }, @@ -220,7 +230,7 @@ static const struct nla_policy cable_test_tdr_act_cfg_policy[] = { const struct nla_policy ethnl_cable_test_tdr_act_policy[] = { [ETHTOOL_A_CABLE_TEST_TDR_HEADER] = - NLA_POLICY_NESTED(ethnl_header_policy), + NLA_POLICY_NESTED(ethnl_header_policy_phy), [ETHTOOL_A_CABLE_TEST_TDR_CFG] = { .type = NLA_NESTED }, }; @@ -309,6 +319,7 @@ int ethnl_act_cable_test_tdr(struct sk_buff *skb, struct genl_info *info) struct ethnl_req_info req_info = {}; const struct ethtool_phy_ops *ops; struct nlattr **tb = info->attrs; + struct phy_device *phydev; struct phy_tdr_config cfg; struct net_device *dev; int ret; @@ -321,10 +332,6 @@ int ethnl_act_cable_test_tdr(struct sk_buff *skb, struct genl_info *info) return ret; dev = req_info.dev; - if (!dev->phydev) { - ret = -EOPNOTSUPP; - goto out_dev_put; - } ret = ethnl_act_cable_test_tdr_cfg(tb[ETHTOOL_A_CABLE_TEST_TDR_CFG], info, &cfg); @@ -332,6 +339,14 @@ int ethnl_act_cable_test_tdr(struct sk_buff *skb, struct genl_info *info) goto out_dev_put; rtnl_lock(); + phydev = ethnl_req_get_phydev(&req_info, + tb[ETHTOOL_A_CABLE_TEST_TDR_HEADER], + info->extack); + if (IS_ERR_OR_NULL(phydev)) { + ret = -EOPNOTSUPP; + goto out_rtnl; + } + ops = ethtool_phy_ops; if (!ops || !ops->start_cable_test_tdr) { ret = -EOPNOTSUPP; @@ -342,12 +357,12 @@ int ethnl_act_cable_test_tdr(struct sk_buff *skb, struct genl_info *info) if (ret < 0) goto out_rtnl; - ret = ops->start_cable_test_tdr(dev->phydev, info->extack, &cfg); + ret = ops->start_cable_test_tdr(phydev, info->extack, &cfg); ethnl_ops_complete(dev); if (!ret) - ethnl_cable_test_started(dev->phydev, + ethnl_cable_test_started(phydev, ETHTOOL_MSG_CABLE_TEST_TDR_NTF); out_rtnl: diff --git a/net/ethtool/channels.c b/net/ethtool/channels.c index 7b4bbd674bae..ca4f80282448 100644 --- a/net/ethtool/channels.c +++ b/net/ethtool/channels.c @@ -114,8 +114,7 @@ ethnl_set_channels(struct ethnl_req_info *req_info, struct genl_info *info) struct net_device *dev = req_info->dev; struct ethtool_channels channels = {}; struct nlattr **tb = info->attrs; - u32 err_attr, max_rxfh_in_use; - u64 max_rxnfc_in_use; + u32 err_attr; int ret; dev->ethtool_ops->get_channels(dev, &channels); @@ -166,22 +165,9 @@ ethnl_set_channels(struct ethnl_req_info *req_info, struct genl_info *info) return -EINVAL; } - /* ensure the new Rx count fits within the configured Rx flow - * indirection table/rxnfc settings - */ - if (ethtool_get_max_rxnfc_channel(dev, &max_rxnfc_in_use)) - max_rxnfc_in_use = 0; - if (!netif_is_rxfh_configured(dev) || - ethtool_get_max_rxfh_channel(dev, &max_rxfh_in_use)) - max_rxfh_in_use = 0; - if (channels.combined_count + channels.rx_count <= max_rxfh_in_use) { - GENL_SET_ERR_MSG(info, "requested channel counts are too low for existing indirection table settings"); - return -EINVAL; - } - if (channels.combined_count + channels.rx_count <= max_rxnfc_in_use) { - GENL_SET_ERR_MSG(info, "requested channel counts are too low for existing ntuple filter settings"); - return -EINVAL; - } + ret = ethtool_check_max_channel(dev, channels, info); + if (ret) + return ret; /* Disabling channels, query zero-copy AF_XDP sockets */ from_channel = channels.combined_count + diff --git a/net/ethtool/cmis.h b/net/ethtool/cmis.h new file mode 100644 index 000000000000..3e7c293af78c --- /dev/null +++ b/net/ethtool/cmis.h @@ -0,0 +1,123 @@ +/* SPDX-License-Identifier: GPL-2.0-only */ + +#define ETHTOOL_CMIS_CDB_LPL_MAX_PL_LENGTH 120 +#define ETHTOOL_CMIS_CDB_CMD_PAGE 0x9F +#define ETHTOOL_CMIS_CDB_PAGE_I2C_ADDR 0x50 + +/** + * struct ethtool_cmis_cdb - CDB commands parameters + * @cmis_rev: CMIS revision major. + * @read_write_len_ext: Allowable additional number of byte octets to the LPL + * in a READ or a WRITE CDB commands. + * @max_completion_time: Maximum CDB command completion time in msec. + */ +struct ethtool_cmis_cdb { + u8 cmis_rev; + u8 read_write_len_ext; + u16 max_completion_time; +}; + +enum ethtool_cmis_cdb_cmd_id { + ETHTOOL_CMIS_CDB_CMD_QUERY_STATUS = 0x0000, + ETHTOOL_CMIS_CDB_CMD_MODULE_FEATURES = 0x0040, + ETHTOOL_CMIS_CDB_CMD_FW_MANAGMENT_FEATURES = 0x0041, + ETHTOOL_CMIS_CDB_CMD_START_FW_DOWNLOAD = 0x0101, + ETHTOOL_CMIS_CDB_CMD_WRITE_FW_BLOCK_LPL = 0x0103, + ETHTOOL_CMIS_CDB_CMD_COMPLETE_FW_DOWNLOAD = 0x0107, + ETHTOOL_CMIS_CDB_CMD_RUN_FW_IMAGE = 0x0109, + ETHTOOL_CMIS_CDB_CMD_COMMIT_FW_IMAGE = 0x010A, +}; + +/** + * struct ethtool_cmis_cdb_request - CDB commands request fields as decribed in + * the CMIS standard + * @id: Command ID. + * @epl_len: EPL memory length. + * @lpl_len: LPL memory length. + * @chk_code: Check code for the previous field and the payload. + * @resv1: Added to match the CMIS standard request continuity. + * @resv2: Added to match the CMIS standard request continuity. + * @payload: Payload for the CDB commands. + */ +struct ethtool_cmis_cdb_request { + __be16 id; + struct_group(body, + __be16 epl_len; + u8 lpl_len; + u8 chk_code; + u8 resv1; + u8 resv2; + u8 payload[ETHTOOL_CMIS_CDB_LPL_MAX_PL_LENGTH]; + ); +}; + +#define CDB_F_COMPLETION_VALID BIT(0) +#define CDB_F_STATUS_VALID BIT(1) +#define CDB_F_MODULE_STATE_VALID BIT(2) + +/** + * struct ethtool_cmis_cdb_cmd_args - CDB commands execution arguments + * @req: CDB command fields as described in the CMIS standard. + * @max_duration: Maximum duration time for command completion in msec. + * @read_write_len_ext: Allowable additional number of byte octets to the LPL + * in a READ or a WRITE commands. + * @msleep_pre_rpl: Waiting time before checking reply in msec. + * @rpl_exp_len: Expected reply length in bytes. + * @flags: Validation flags for CDB commands. + * @err_msg: Error message to be sent to user space. + */ +struct ethtool_cmis_cdb_cmd_args { + struct ethtool_cmis_cdb_request req; + u16 max_duration; + u8 read_write_len_ext; + u8 msleep_pre_rpl; + u8 rpl_exp_len; + u8 flags; + char *err_msg; +}; + +/** + * struct ethtool_cmis_cdb_rpl_hdr - CDB commands reply header arguments + * @rpl_len: Reply length. + * @rpl_chk_code: Reply check code. + */ +struct ethtool_cmis_cdb_rpl_hdr { + u8 rpl_len; + u8 rpl_chk_code; +}; + +/** + * struct ethtool_cmis_cdb_rpl - CDB commands reply arguments + * @hdr: CDB commands reply header arguments. + * @payload: Payload for the CDB commands reply. + */ +struct ethtool_cmis_cdb_rpl { + struct ethtool_cmis_cdb_rpl_hdr hdr; + u8 payload[ETHTOOL_CMIS_CDB_LPL_MAX_PL_LENGTH]; +}; + +u32 ethtool_cmis_get_max_payload_size(u8 num_of_byte_octs); + +void ethtool_cmis_cdb_compose_args(struct ethtool_cmis_cdb_cmd_args *args, + enum ethtool_cmis_cdb_cmd_id cmd, u8 *pl, + u8 lpl_len, u16 max_duration, + u8 read_write_len_ext, u16 msleep_pre_rpl, + u8 rpl_exp_len, u8 flags); + +void ethtool_cmis_cdb_check_completion_flag(u8 cmis_rev, u8 *flags); + +void ethtool_cmis_page_init(struct ethtool_module_eeprom *page_data, + u8 page, u32 offset, u32 length); + +struct ethtool_cmis_cdb * +ethtool_cmis_cdb_init(struct net_device *dev, + const struct ethtool_module_fw_flash_params *params, + struct ethnl_module_fw_flash_ntf_params *ntf_params); +void ethtool_cmis_cdb_fini(struct ethtool_cmis_cdb *cdb); + +int ethtool_cmis_wait_for_cond(struct net_device *dev, u8 flags, u8 flag, + u16 max_duration, u32 offset, + bool (*cond_success)(u8), bool (*cond_fail)(u8), u8 *state); + +int ethtool_cmis_cdb_execute_cmd(struct net_device *dev, + struct ethtool_cmis_cdb_cmd_args *args); diff --git a/net/ethtool/cmis_cdb.c b/net/ethtool/cmis_cdb.c new file mode 100644 index 000000000000..4d5581147952 --- /dev/null +++ b/net/ethtool/cmis_cdb.c @@ -0,0 +1,610 @@ +// SPDX-License-Identifier: GPL-2.0-only + +#include <linux/ethtool.h> +#include <linux/jiffies.h> + +#include "common.h" +#include "module_fw.h" +#include "cmis.h" + +/* For accessing the LPL field on page 9Fh, the allowable length extension is + * min(i, 15) byte octets where i specifies the allowable additional number of + * byte octets in a READ or a WRITE. + */ +u32 ethtool_cmis_get_max_payload_size(u8 num_of_byte_octs) +{ + return 8 * (1 + min_t(u8, num_of_byte_octs, 15)); +} + +void ethtool_cmis_cdb_compose_args(struct ethtool_cmis_cdb_cmd_args *args, + enum ethtool_cmis_cdb_cmd_id cmd, u8 *pl, + u8 lpl_len, u16 max_duration, + u8 read_write_len_ext, u16 msleep_pre_rpl, + u8 rpl_exp_len, u8 flags) +{ + args->req.id = cpu_to_be16(cmd); + args->req.lpl_len = lpl_len; + if (pl) + memcpy(args->req.payload, pl, args->req.lpl_len); + + args->max_duration = max_duration; + args->read_write_len_ext = + ethtool_cmis_get_max_payload_size(read_write_len_ext); + args->msleep_pre_rpl = msleep_pre_rpl; + args->rpl_exp_len = rpl_exp_len; + args->flags = flags; + args->err_msg = NULL; +} + +void ethtool_cmis_page_init(struct ethtool_module_eeprom *page_data, + u8 page, u32 offset, u32 length) +{ + page_data->page = page; + page_data->offset = offset; + page_data->length = length; + page_data->i2c_address = ETHTOOL_CMIS_CDB_PAGE_I2C_ADDR; +} + +#define CMIS_REVISION_PAGE 0x00 +#define CMIS_REVISION_OFFSET 0x01 + +struct cmis_rev_rpl { + u8 rev; +}; + +static u8 cmis_rev_rpl_major(struct cmis_rev_rpl *rpl) +{ + return rpl->rev >> 4; +} + +static int cmis_rev_major_get(struct net_device *dev, u8 *rev_major) +{ + const struct ethtool_ops *ops = dev->ethtool_ops; + struct ethtool_module_eeprom page_data = {0}; + struct netlink_ext_ack extack = {}; + struct cmis_rev_rpl rpl = {}; + int err; + + ethtool_cmis_page_init(&page_data, CMIS_REVISION_PAGE, + CMIS_REVISION_OFFSET, sizeof(rpl)); + page_data.data = (u8 *)&rpl; + + err = ops->get_module_eeprom_by_page(dev, &page_data, &extack); + if (err < 0) { + if (extack._msg) + netdev_err(dev, "%s\n", extack._msg); + return err; + } + + *rev_major = cmis_rev_rpl_major(&rpl); + + return 0; +} + +#define CMIS_CDB_ADVERTISEMENT_PAGE 0x01 +#define CMIS_CDB_ADVERTISEMENT_OFFSET 0xA3 + +/* Based on section 8.4.11 "CDB Messaging Support Advertisement" in CMIS + * standard revision 5.2. + */ +struct cmis_cdb_advert_rpl { + u8 inst_supported; + u8 read_write_len_ext; + u8 resv1; + u8 resv2; +}; + +static u8 cmis_cdb_advert_rpl_inst_supported(struct cmis_cdb_advert_rpl *rpl) +{ + return rpl->inst_supported >> 6; +} + +static int cmis_cdb_advertisement_get(struct ethtool_cmis_cdb *cdb, + struct net_device *dev, + struct ethnl_module_fw_flash_ntf_params *ntf_params) +{ + const struct ethtool_ops *ops = dev->ethtool_ops; + struct ethtool_module_eeprom page_data = {}; + struct cmis_cdb_advert_rpl rpl = {}; + struct netlink_ext_ack extack = {}; + int err; + + ethtool_cmis_page_init(&page_data, CMIS_CDB_ADVERTISEMENT_PAGE, + CMIS_CDB_ADVERTISEMENT_OFFSET, sizeof(rpl)); + page_data.data = (u8 *)&rpl; + + err = ops->get_module_eeprom_by_page(dev, &page_data, &extack); + if (err < 0) { + if (extack._msg) + netdev_err(dev, "%s\n", extack._msg); + return err; + } + + if (!cmis_cdb_advert_rpl_inst_supported(&rpl)) { + ethnl_module_fw_flash_ntf_err(dev, ntf_params, + "CDB functionality is not supported", + NULL); + return -EOPNOTSUPP; + } + + cdb->read_write_len_ext = rpl.read_write_len_ext; + + return 0; +} + +#define CMIS_PASSWORD_ENTRY_PAGE 0x00 +#define CMIS_PASSWORD_ENTRY_OFFSET 0x7A + +struct cmis_password_entry_pl { + __be32 password; +}; + +/* See section 9.3.1 "CMD 0000h: Query Status" in CMIS standard revision 5.2. + * struct cmis_cdb_query_status_pl and struct cmis_cdb_query_status_rpl are + * structured layouts of the flat arrays, + * struct ethtool_cmis_cdb_request::payload and + * struct ethtool_cmis_cdb_rpl::payload respectively. + */ +struct cmis_cdb_query_status_pl { + u16 response_delay; +}; + +struct cmis_cdb_query_status_rpl { + u8 length; + u8 status; +}; + +static int +cmis_cdb_validate_password(struct ethtool_cmis_cdb *cdb, + struct net_device *dev, + const struct ethtool_module_fw_flash_params *params, + struct ethnl_module_fw_flash_ntf_params *ntf_params) +{ + const struct ethtool_ops *ops = dev->ethtool_ops; + struct cmis_cdb_query_status_pl qs_pl = {0}; + struct ethtool_module_eeprom page_data = {}; + struct ethtool_cmis_cdb_cmd_args args = {}; + struct cmis_password_entry_pl pe_pl = {}; + struct cmis_cdb_query_status_rpl *rpl; + struct netlink_ext_ack extack = {}; + int err; + + ethtool_cmis_page_init(&page_data, CMIS_PASSWORD_ENTRY_PAGE, + CMIS_PASSWORD_ENTRY_OFFSET, sizeof(pe_pl)); + page_data.data = (u8 *)&pe_pl; + + pe_pl = *((struct cmis_password_entry_pl *)page_data.data); + pe_pl.password = params->password; + err = ops->set_module_eeprom_by_page(dev, &page_data, &extack); + if (err < 0) { + if (extack._msg) + netdev_err(dev, "%s\n", extack._msg); + return err; + } + + ethtool_cmis_cdb_compose_args(&args, ETHTOOL_CMIS_CDB_CMD_QUERY_STATUS, + (u8 *)&qs_pl, sizeof(qs_pl), 0, + cdb->read_write_len_ext, 1000, + sizeof(*rpl), + CDB_F_COMPLETION_VALID | CDB_F_STATUS_VALID); + + err = ethtool_cmis_cdb_execute_cmd(dev, &args); + if (err < 0) { + ethnl_module_fw_flash_ntf_err(dev, ntf_params, + "Query Status command failed", + args.err_msg); + return err; + } + + rpl = (struct cmis_cdb_query_status_rpl *)args.req.payload; + if (!rpl->length || !rpl->status) { + ethnl_module_fw_flash_ntf_err(dev, ntf_params, + "Password was not accepted", + NULL); + return -EINVAL; + } + + return 0; +} + +/* Some CDB commands asserts the CDB completion flag only from CMIS + * revision 5. Therefore, check the relevant validity flag only when + * the revision supports it. + */ +void ethtool_cmis_cdb_check_completion_flag(u8 cmis_rev, u8 *flags) +{ + *flags |= cmis_rev >= 5 ? CDB_F_COMPLETION_VALID : 0; +} + +#define CMIS_CDB_MODULE_FEATURES_RESV_DATA 34 + +/* See section 9.4.1 "CMD 0040h: Module Features" in CMIS standard revision 5.2. + * struct cmis_cdb_module_features_rpl is structured layout of the flat + * array, ethtool_cmis_cdb_rpl::payload. + */ +struct cmis_cdb_module_features_rpl { + u8 resv1[CMIS_CDB_MODULE_FEATURES_RESV_DATA]; + __be16 max_completion_time; +}; + +static u16 +cmis_cdb_module_features_completion_time(struct cmis_cdb_module_features_rpl *rpl) +{ + return be16_to_cpu(rpl->max_completion_time); +} + +static int cmis_cdb_module_features_get(struct ethtool_cmis_cdb *cdb, + struct net_device *dev, + struct ethnl_module_fw_flash_ntf_params *ntf_params) +{ + struct ethtool_cmis_cdb_cmd_args args = {}; + struct cmis_cdb_module_features_rpl *rpl; + u8 flags = CDB_F_STATUS_VALID; + int err; + + ethtool_cmis_cdb_check_completion_flag(cdb->cmis_rev, &flags); + ethtool_cmis_cdb_compose_args(&args, + ETHTOOL_CMIS_CDB_CMD_MODULE_FEATURES, + NULL, 0, 0, cdb->read_write_len_ext, + 1000, sizeof(*rpl), flags); + + err = ethtool_cmis_cdb_execute_cmd(dev, &args); + if (err < 0) { + ethnl_module_fw_flash_ntf_err(dev, ntf_params, + "Module Features command failed", + args.err_msg); + return err; + } + + rpl = (struct cmis_cdb_module_features_rpl *)args.req.payload; + cdb->max_completion_time = + cmis_cdb_module_features_completion_time(rpl); + + return 0; +} + +struct ethtool_cmis_cdb * +ethtool_cmis_cdb_init(struct net_device *dev, + const struct ethtool_module_fw_flash_params *params, + struct ethnl_module_fw_flash_ntf_params *ntf_params) +{ + struct ethtool_cmis_cdb *cdb; + int err; + + cdb = kzalloc(sizeof(*cdb), GFP_KERNEL); + if (!cdb) + return ERR_PTR(-ENOMEM); + + err = cmis_rev_major_get(dev, &cdb->cmis_rev); + if (err < 0) + goto err; + + if (cdb->cmis_rev < 4) { + ethnl_module_fw_flash_ntf_err(dev, ntf_params, + "CMIS revision doesn't support module firmware flashing", + NULL); + err = -EOPNOTSUPP; + goto err; + } + + err = cmis_cdb_advertisement_get(cdb, dev, ntf_params); + if (err < 0) + goto err; + + if (params->password_valid) { + err = cmis_cdb_validate_password(cdb, dev, params, ntf_params); + if (err < 0) + goto err; + } + + err = cmis_cdb_module_features_get(cdb, dev, ntf_params); + if (err < 0) + goto err; + + return cdb; + +err: + ethtool_cmis_cdb_fini(cdb); + return ERR_PTR(err); +} + +void ethtool_cmis_cdb_fini(struct ethtool_cmis_cdb *cdb) +{ + kfree(cdb); +} + +static bool is_completed(u8 data) +{ + return !!(data & 0x40); +} + +#define CMIS_CDB_STATUS_SUCCESS 0x01 + +static bool status_success(u8 data) +{ + return data == CMIS_CDB_STATUS_SUCCESS; +} + +#define CMIS_CDB_STATUS_FAIL 0x40 + +static bool status_fail(u8 data) +{ + return data & CMIS_CDB_STATUS_FAIL; +} + +struct cmis_wait_for_cond_rpl { + u8 state; +}; + +static int +ethtool_cmis_module_poll(struct net_device *dev, + struct cmis_wait_for_cond_rpl *rpl, u32 offset, + bool (*cond_success)(u8), bool (*cond_fail)(u8)) +{ + const struct ethtool_ops *ops = dev->ethtool_ops; + struct ethtool_module_eeprom page_data = {0}; + struct netlink_ext_ack extack = {}; + int err; + + ethtool_cmis_page_init(&page_data, 0, offset, sizeof(rpl)); + page_data.data = (u8 *)rpl; + + err = ops->get_module_eeprom_by_page(dev, &page_data, &extack); + if (err < 0) { + if (extack._msg) + netdev_err_once(dev, "%s\n", extack._msg); + return -EBUSY; + } + + if ((*cond_success)(rpl->state)) + return 0; + + if (*cond_fail && (*cond_fail)(rpl->state)) + return -EIO; + + return -EBUSY; +} + +int ethtool_cmis_wait_for_cond(struct net_device *dev, u8 flags, u8 flag, + u16 max_duration, u32 offset, + bool (*cond_success)(u8), bool (*cond_fail)(u8), + u8 *state) +{ + struct cmis_wait_for_cond_rpl rpl = {}; + unsigned long end; + int err; + + if (!(flags & flag)) + return 0; + + if (max_duration == 0) + max_duration = U16_MAX; + + end = jiffies + msecs_to_jiffies(max_duration); + do { + err = ethtool_cmis_module_poll(dev, &rpl, offset, cond_success, + cond_fail); + if (err != -EBUSY) + goto out; + + msleep(20); + } while (time_before(jiffies, end)); + + err = ethtool_cmis_module_poll(dev, &rpl, offset, cond_success, + cond_fail); + if (err == -EBUSY) + err = -ETIMEDOUT; + +out: + *state = rpl.state; + return err; +} + +#define CMIS_CDB_COMPLETION_FLAG_OFFSET 0x08 + +static int cmis_cdb_wait_for_completion(struct net_device *dev, + struct ethtool_cmis_cdb_cmd_args *args) +{ + u8 flag; + int err; + + /* Some vendors demand waiting time before checking completion flag + * in some CDB commands. + */ + msleep(args->msleep_pre_rpl); + + err = ethtool_cmis_wait_for_cond(dev, args->flags, + CDB_F_COMPLETION_VALID, + args->max_duration, + CMIS_CDB_COMPLETION_FLAG_OFFSET, + is_completed, NULL, &flag); + if (err < 0) + args->err_msg = "Completion Flag did not set on time"; + + return err; +} + +#define CMIS_CDB_STATUS_OFFSET 0x25 + +static void cmis_cdb_status_fail_msg_get(u8 status, char **err_msg) +{ + switch (status) { + case 0b10000001: + *err_msg = "CDB Status is in progress: Busy capturing command"; + break; + case 0b10000010: + *err_msg = + "CDB Status is in progress: Busy checking/validating command"; + break; + case 0b10000011: + *err_msg = "CDB Status is in progress: Busy executing"; + break; + case 0b01000000: + *err_msg = "CDB status failed: no specific failure"; + break; + case 0b01000010: + *err_msg = + "CDB status failed: Parameter range error or parameter not supported"; + break; + case 0b01000101: + *err_msg = "CDB status failed: CdbChkCode error"; + break; + case 0b01000110: + *err_msg = "CDB status failed: Password error"; + break; + default: + *err_msg = "Unknown failure reason"; + } +}; + +static int cmis_cdb_wait_for_status(struct net_device *dev, + struct ethtool_cmis_cdb_cmd_args *args) +{ + u8 status; + int err; + + /* Some vendors demand waiting time before checking status in some + * CDB commands. + */ + msleep(args->msleep_pre_rpl); + + err = ethtool_cmis_wait_for_cond(dev, args->flags, CDB_F_STATUS_VALID, + args->max_duration, + CMIS_CDB_STATUS_OFFSET, + status_success, status_fail, &status); + if (err < 0 && !args->err_msg) + cmis_cdb_status_fail_msg_get(status, &args->err_msg); + + return err; +} + +#define CMIS_CDB_REPLY_OFFSET 0x86 + +static int cmis_cdb_process_reply(struct net_device *dev, + struct ethtool_module_eeprom *page_data, + struct ethtool_cmis_cdb_cmd_args *args) +{ + u8 rpl_hdr_len = sizeof(struct ethtool_cmis_cdb_rpl_hdr); + u8 rpl_exp_len = args->rpl_exp_len + rpl_hdr_len; + const struct ethtool_ops *ops = dev->ethtool_ops; + struct netlink_ext_ack extack = {}; + struct ethtool_cmis_cdb_rpl *rpl; + int err; + + if (!args->rpl_exp_len) + return 0; + + ethtool_cmis_page_init(page_data, ETHTOOL_CMIS_CDB_CMD_PAGE, + CMIS_CDB_REPLY_OFFSET, rpl_exp_len); + page_data->data = kmalloc(page_data->length, GFP_KERNEL); + if (!page_data->data) + return -ENOMEM; + + err = ops->get_module_eeprom_by_page(dev, page_data, &extack); + if (err < 0) { + if (extack._msg) + netdev_err(dev, "%s\n", extack._msg); + goto out; + } + + rpl = (struct ethtool_cmis_cdb_rpl *)page_data->data; + if ((args->rpl_exp_len > rpl->hdr.rpl_len + rpl_hdr_len) || + !rpl->hdr.rpl_chk_code) { + err = -EIO; + goto out; + } + + args->req.lpl_len = rpl->hdr.rpl_len; + memcpy(args->req.payload, rpl->payload, args->req.lpl_len); + +out: + kfree(page_data->data); + return err; +} + +static int +__ethtool_cmis_cdb_execute_cmd(struct net_device *dev, + struct ethtool_module_eeprom *page_data, + u8 page, u32 offset, u32 length, void *data) +{ + const struct ethtool_ops *ops = dev->ethtool_ops; + struct netlink_ext_ack extack = {}; + int err; + + ethtool_cmis_page_init(page_data, page, offset, length); + page_data->data = kmemdup(data, page_data->length, GFP_KERNEL); + if (!page_data->data) + return -ENOMEM; + + err = ops->set_module_eeprom_by_page(dev, page_data, &extack); + if (err < 0) { + if (extack._msg) + netdev_err(dev, "%s\n", extack._msg); + } + + kfree(page_data->data); + return err; +} + +static u8 cmis_cdb_calc_checksum(const void *data, size_t size) +{ + const u8 *bytes = (const u8 *)data; + u8 checksum = 0; + + for (size_t i = 0; i < size; i++) + checksum += bytes[i]; + + return ~checksum; +} + +#define CMIS_CDB_CMD_ID_OFFSET 0x80 + +int ethtool_cmis_cdb_execute_cmd(struct net_device *dev, + struct ethtool_cmis_cdb_cmd_args *args) +{ + struct ethtool_module_eeprom page_data = {}; + u32 offset; + int err; + + args->req.chk_code = + cmis_cdb_calc_checksum(&args->req, sizeof(args->req)); + + if (args->req.lpl_len > args->read_write_len_ext) { + args->err_msg = "LPL length is longer than CDB read write length extension allows"; + return -EINVAL; + } + + /* According to the CMIS standard, there are two options to trigger the + * CDB commands. The default option is triggering the command by writing + * the CMDID bytes. Therefore, the command will be split to 2 calls: + * First, with everything except the CMDID field and then the CMDID + * field. + */ + offset = CMIS_CDB_CMD_ID_OFFSET + + offsetof(struct ethtool_cmis_cdb_request, body); + err = __ethtool_cmis_cdb_execute_cmd(dev, &page_data, + ETHTOOL_CMIS_CDB_CMD_PAGE, offset, + sizeof(args->req.body), + &args->req.body); + if (err < 0) + return err; + + offset = CMIS_CDB_CMD_ID_OFFSET + + offsetof(struct ethtool_cmis_cdb_request, id); + err = __ethtool_cmis_cdb_execute_cmd(dev, &page_data, + ETHTOOL_CMIS_CDB_CMD_PAGE, offset, + sizeof(args->req.id), + &args->req.id); + if (err < 0) + return err; + + err = cmis_cdb_wait_for_completion(dev, args); + if (err < 0) + return err; + + err = cmis_cdb_wait_for_status(dev, args); + if (err < 0) + return err; + + return cmis_cdb_process_reply(dev, &page_data, args); +} diff --git a/net/ethtool/cmis_fw_update.c b/net/ethtool/cmis_fw_update.c new file mode 100644 index 000000000000..655ff5224ffa --- /dev/null +++ b/net/ethtool/cmis_fw_update.c @@ -0,0 +1,403 @@ +// SPDX-License-Identifier: GPL-2.0-only + +#include <linux/ethtool.h> +#include <linux/firmware.h> + +#include "common.h" +#include "module_fw.h" +#include "cmis.h" + +struct cmis_fw_update_fw_mng_features { + u8 start_cmd_payload_size; + u16 max_duration_start; + u16 max_duration_write; + u16 max_duration_complete; +}; + +/* See section 9.4.2 "CMD 0041h: Firmware Management Features" in CMIS standard + * revision 5.2. + * struct cmis_cdb_fw_mng_features_rpl is a structured layout of the flat + * array, ethtool_cmis_cdb_rpl::payload. + */ +struct cmis_cdb_fw_mng_features_rpl { + u8 resv1; + u8 resv2; + u8 start_cmd_payload_size; + u8 resv3; + u8 read_write_len_ext; + u8 write_mechanism; + u8 resv4; + u8 resv5; + __be16 max_duration_start; + __be16 resv6; + __be16 max_duration_write; + __be16 max_duration_complete; + __be16 resv7; +}; + +enum cmis_cdb_fw_write_mechanism { + CMIS_CDB_FW_WRITE_MECHANISM_LPL = 0x01, + CMIS_CDB_FW_WRITE_MECHANISM_BOTH = 0x11, +}; + +static int +cmis_fw_update_fw_mng_features_get(struct ethtool_cmis_cdb *cdb, + struct net_device *dev, + struct cmis_fw_update_fw_mng_features *fw_mng, + struct ethnl_module_fw_flash_ntf_params *ntf_params) +{ + struct ethtool_cmis_cdb_cmd_args args = {}; + struct cmis_cdb_fw_mng_features_rpl *rpl; + u8 flags = CDB_F_STATUS_VALID; + int err; + + ethtool_cmis_cdb_check_completion_flag(cdb->cmis_rev, &flags); + ethtool_cmis_cdb_compose_args(&args, + ETHTOOL_CMIS_CDB_CMD_FW_MANAGMENT_FEATURES, + NULL, 0, cdb->max_completion_time, + cdb->read_write_len_ext, 1000, + sizeof(*rpl), flags); + + err = ethtool_cmis_cdb_execute_cmd(dev, &args); + if (err < 0) { + ethnl_module_fw_flash_ntf_err(dev, ntf_params, + "FW Management Features command failed", + args.err_msg); + return err; + } + + rpl = (struct cmis_cdb_fw_mng_features_rpl *)args.req.payload; + if (!(rpl->write_mechanism == CMIS_CDB_FW_WRITE_MECHANISM_LPL || + rpl->write_mechanism == CMIS_CDB_FW_WRITE_MECHANISM_BOTH)) { + ethnl_module_fw_flash_ntf_err(dev, ntf_params, + "Write LPL is not supported", + NULL); + return -EOPNOTSUPP; + } + + /* Above, we used read_write_len_ext that we got from CDB + * advertisement. Update it with the value that we got from module + * features query, which is specific for Firmware Management Commands + * (IDs 0100h-01FFh). + */ + cdb->read_write_len_ext = rpl->read_write_len_ext; + fw_mng->start_cmd_payload_size = rpl->start_cmd_payload_size; + fw_mng->max_duration_start = be16_to_cpu(rpl->max_duration_start); + fw_mng->max_duration_write = be16_to_cpu(rpl->max_duration_write); + fw_mng->max_duration_complete = be16_to_cpu(rpl->max_duration_complete); + + return 0; +} + +/* See section 9.7.2 "CMD 0101h: Start Firmware Download" in CMIS standard + * revision 5.2. + * struct cmis_cdb_start_fw_download_pl is a structured layout of the + * flat array, ethtool_cmis_cdb_request::payload. + */ +struct cmis_cdb_start_fw_download_pl { + __struct_group(cmis_cdb_start_fw_download_pl_h, head, /* no attrs */, + __be32 image_size; + __be32 resv1; + ); + u8 vendor_data[ETHTOOL_CMIS_CDB_LPL_MAX_PL_LENGTH - + sizeof(struct cmis_cdb_start_fw_download_pl_h)]; +}; + +static int +cmis_fw_update_start_download(struct ethtool_cmis_cdb *cdb, + struct ethtool_cmis_fw_update_params *fw_update, + struct cmis_fw_update_fw_mng_features *fw_mng) +{ + u8 vendor_data_size = fw_mng->start_cmd_payload_size; + struct cmis_cdb_start_fw_download_pl pl = {}; + struct ethtool_cmis_cdb_cmd_args args = {}; + u8 lpl_len; + int err; + + pl.image_size = cpu_to_be32(fw_update->fw->size); + memcpy(pl.vendor_data, fw_update->fw->data, vendor_data_size); + + lpl_len = offsetof(struct cmis_cdb_start_fw_download_pl, + vendor_data[vendor_data_size]); + + ethtool_cmis_cdb_compose_args(&args, + ETHTOOL_CMIS_CDB_CMD_START_FW_DOWNLOAD, + (u8 *)&pl, lpl_len, + fw_mng->max_duration_start, + cdb->read_write_len_ext, 1000, 0, + CDB_F_COMPLETION_VALID | CDB_F_STATUS_VALID); + + err = ethtool_cmis_cdb_execute_cmd(fw_update->dev, &args); + if (err < 0) + ethnl_module_fw_flash_ntf_err(fw_update->dev, + &fw_update->ntf_params, + "Start FW download command failed", + args.err_msg); + + return err; +} + +/* See section 9.7.4 "CMD 0103h: Write Firmware Block LPL" in CMIS standard + * revision 5.2. + * struct cmis_cdb_write_fw_block_lpl_pl is a structured layout of the + * flat array, ethtool_cmis_cdb_request::payload. + */ +struct cmis_cdb_write_fw_block_lpl_pl { + __be32 block_address; + u8 fw_block[ETHTOOL_CMIS_CDB_LPL_MAX_PL_LENGTH - sizeof(__be32)]; +}; + +static int +cmis_fw_update_write_image(struct ethtool_cmis_cdb *cdb, + struct ethtool_cmis_fw_update_params *fw_update, + struct cmis_fw_update_fw_mng_features *fw_mng) +{ + u8 start = fw_mng->start_cmd_payload_size; + u32 offset, max_block_size, max_lpl_len; + u32 image_size = fw_update->fw->size; + int err; + + max_lpl_len = min_t(u32, + ethtool_cmis_get_max_payload_size(cdb->read_write_len_ext), + ETHTOOL_CMIS_CDB_LPL_MAX_PL_LENGTH); + max_block_size = + max_lpl_len - sizeof_field(struct cmis_cdb_write_fw_block_lpl_pl, + block_address); + + for (offset = start; offset < image_size; offset += max_block_size) { + struct cmis_cdb_write_fw_block_lpl_pl pl = { + .block_address = cpu_to_be32(offset - start), + }; + struct ethtool_cmis_cdb_cmd_args args = {}; + u32 block_size, lpl_len; + + ethnl_module_fw_flash_ntf_in_progress(fw_update->dev, + &fw_update->ntf_params, + offset - start, + image_size); + block_size = min_t(u32, max_block_size, image_size - offset); + memcpy(pl.fw_block, &fw_update->fw->data[offset], block_size); + lpl_len = block_size + + sizeof_field(struct cmis_cdb_write_fw_block_lpl_pl, + block_address); + + ethtool_cmis_cdb_compose_args(&args, + ETHTOOL_CMIS_CDB_CMD_WRITE_FW_BLOCK_LPL, + (u8 *)&pl, lpl_len, + fw_mng->max_duration_write, + cdb->read_write_len_ext, 1, 0, + CDB_F_COMPLETION_VALID | CDB_F_STATUS_VALID); + + err = ethtool_cmis_cdb_execute_cmd(fw_update->dev, &args); + if (err < 0) { + ethnl_module_fw_flash_ntf_err(fw_update->dev, + &fw_update->ntf_params, + "Write FW block LPL command failed", + args.err_msg); + return err; + } + } + + return 0; +} + +static int +cmis_fw_update_complete_download(struct ethtool_cmis_cdb *cdb, + struct net_device *dev, + struct cmis_fw_update_fw_mng_features *fw_mng, + struct ethnl_module_fw_flash_ntf_params *ntf_params) +{ + struct ethtool_cmis_cdb_cmd_args args = {}; + int err; + + ethtool_cmis_cdb_compose_args(&args, + ETHTOOL_CMIS_CDB_CMD_COMPLETE_FW_DOWNLOAD, + NULL, 0, fw_mng->max_duration_complete, + cdb->read_write_len_ext, 1000, 0, + CDB_F_COMPLETION_VALID | CDB_F_STATUS_VALID); + + err = ethtool_cmis_cdb_execute_cmd(dev, &args); + if (err < 0) + ethnl_module_fw_flash_ntf_err(dev, ntf_params, + "Complete FW download command failed", + args.err_msg); + + return err; +} + +static int +cmis_fw_update_download_image(struct ethtool_cmis_cdb *cdb, + struct ethtool_cmis_fw_update_params *fw_update, + struct cmis_fw_update_fw_mng_features *fw_mng) +{ + int err; + + err = cmis_fw_update_start_download(cdb, fw_update, fw_mng); + if (err < 0) + return err; + + err = cmis_fw_update_write_image(cdb, fw_update, fw_mng); + if (err < 0) + return err; + + err = cmis_fw_update_complete_download(cdb, fw_update->dev, fw_mng, + &fw_update->ntf_params); + if (err < 0) + return err; + + return 0; +} + +enum { + CMIS_MODULE_LOW_PWR = 1, + CMIS_MODULE_READY = 3, +}; + +static bool module_is_ready(u8 data) +{ + u8 state = (data >> 1) & 7; + + return state == CMIS_MODULE_READY || state == CMIS_MODULE_LOW_PWR; +} + +#define CMIS_MODULE_READY_MAX_DURATION_MSEC 1000 +#define CMIS_MODULE_STATE_OFFSET 3 + +static int +cmis_fw_update_wait_for_module_state(struct net_device *dev, u8 flags) +{ + u8 state; + + return ethtool_cmis_wait_for_cond(dev, flags, CDB_F_MODULE_STATE_VALID, + CMIS_MODULE_READY_MAX_DURATION_MSEC, + CMIS_MODULE_STATE_OFFSET, + module_is_ready, NULL, &state); +} + +/* See section 9.7.10 "CMD 0109h: Run Firmware Image" in CMIS standard + * revision 5.2. + * struct cmis_cdb_run_fw_image_pl is a structured layout of the flat + * array, ethtool_cmis_cdb_request::payload. + */ +struct cmis_cdb_run_fw_image_pl { + u8 resv1; + u8 image_to_run; + u16 delay_to_reset; +}; + +static int +cmis_fw_update_run_image(struct ethtool_cmis_cdb *cdb, struct net_device *dev, + struct ethnl_module_fw_flash_ntf_params *ntf_params) +{ + struct ethtool_cmis_cdb_cmd_args args = {}; + struct cmis_cdb_run_fw_image_pl pl = {0}; + int err; + + ethtool_cmis_cdb_compose_args(&args, ETHTOOL_CMIS_CDB_CMD_RUN_FW_IMAGE, + (u8 *)&pl, sizeof(pl), + cdb->max_completion_time, + cdb->read_write_len_ext, 1000, 0, + CDB_F_MODULE_STATE_VALID); + + err = ethtool_cmis_cdb_execute_cmd(dev, &args); + if (err < 0) { + ethnl_module_fw_flash_ntf_err(dev, ntf_params, + "Run image command failed", + args.err_msg); + return err; + } + + err = cmis_fw_update_wait_for_module_state(dev, args.flags); + if (err < 0) + ethnl_module_fw_flash_ntf_err(dev, ntf_params, + "Module is not ready on time after reset", + NULL); + + return err; +} + +static int +cmis_fw_update_commit_image(struct ethtool_cmis_cdb *cdb, + struct net_device *dev, + struct ethnl_module_fw_flash_ntf_params *ntf_params) +{ + struct ethtool_cmis_cdb_cmd_args args = {}; + int err; + + ethtool_cmis_cdb_compose_args(&args, + ETHTOOL_CMIS_CDB_CMD_COMMIT_FW_IMAGE, + NULL, 0, cdb->max_completion_time, + cdb->read_write_len_ext, 1000, 0, + CDB_F_COMPLETION_VALID | CDB_F_STATUS_VALID); + + err = ethtool_cmis_cdb_execute_cmd(dev, &args); + if (err < 0) + ethnl_module_fw_flash_ntf_err(dev, ntf_params, + "Commit image command failed", + args.err_msg); + + return err; +} + +static int cmis_fw_update_reset(struct net_device *dev) +{ + __u32 reset_data = ETH_RESET_PHY; + + return dev->ethtool_ops->reset(dev, &reset_data); +} + +void +ethtool_cmis_fw_update(struct ethtool_cmis_fw_update_params *fw_update) +{ + struct ethnl_module_fw_flash_ntf_params *ntf_params = + &fw_update->ntf_params; + struct cmis_fw_update_fw_mng_features fw_mng = {0}; + struct net_device *dev = fw_update->dev; + struct ethtool_cmis_cdb *cdb; + int err; + + cdb = ethtool_cmis_cdb_init(dev, &fw_update->params, ntf_params); + if (IS_ERR(cdb)) + goto err_send_ntf; + + ethnl_module_fw_flash_ntf_start(dev, ntf_params); + + err = cmis_fw_update_fw_mng_features_get(cdb, dev, &fw_mng, ntf_params); + if (err < 0) + goto err_cdb_fini; + + err = cmis_fw_update_download_image(cdb, fw_update, &fw_mng); + if (err < 0) + goto err_cdb_fini; + + err = cmis_fw_update_run_image(cdb, dev, ntf_params); + if (err < 0) + goto err_cdb_fini; + + /* The CDB command "Run Firmware Image" resets the firmware, so the new + * one might have different settings. + * Free the old CDB instance, and init a new one. + */ + ethtool_cmis_cdb_fini(cdb); + + cdb = ethtool_cmis_cdb_init(dev, &fw_update->params, ntf_params); + if (IS_ERR(cdb)) + goto err_send_ntf; + + err = cmis_fw_update_commit_image(cdb, dev, ntf_params); + if (err < 0) + goto err_cdb_fini; + + err = cmis_fw_update_reset(dev); + if (err < 0) + goto err_cdb_fini; + + ethnl_module_fw_flash_ntf_complete(dev, ntf_params); + ethtool_cmis_cdb_fini(cdb); + return; + +err_cdb_fini: + ethtool_cmis_cdb_fini(cdb); +err_send_ntf: + ethnl_module_fw_flash_ntf_err(dev, ntf_params, NULL, NULL); +} diff --git a/net/ethtool/coalesce.c b/net/ethtool/coalesce.c index 83112c1a71ae..3e18ca1ccc5e 100644 --- a/net/ethtool/coalesce.c +++ b/net/ethtool/coalesce.c @@ -1,5 +1,6 @@ // SPDX-License-Identifier: GPL-2.0-only +#include <linux/dim.h> #include "netlink.h" #include "common.h" @@ -82,6 +83,14 @@ static int coalesce_prepare_data(const struct ethnl_req_info *req_base, static int coalesce_reply_size(const struct ethnl_req_info *req_base, const struct ethnl_reply_data *reply_base) { + int modersz = nla_total_size(0) + /* _PROFILE_IRQ_MODERATION, nest */ + nla_total_size(sizeof(u32)) + /* _IRQ_MODERATION_USEC */ + nla_total_size(sizeof(u32)) + /* _IRQ_MODERATION_PKTS */ + nla_total_size(sizeof(u32)); /* _IRQ_MODERATION_COMPS */ + + int total_modersz = nla_total_size(0) + /* _{R,T}X_PROFILE, nest */ + modersz * NET_DIM_PARAMS_NUM_PROFILES; + return nla_total_size(sizeof(u32)) + /* _RX_USECS */ nla_total_size(sizeof(u32)) + /* _RX_MAX_FRAMES */ nla_total_size(sizeof(u32)) + /* _RX_USECS_IRQ */ @@ -108,7 +117,8 @@ static int coalesce_reply_size(const struct ethnl_req_info *req_base, nla_total_size(sizeof(u8)) + /* _USE_CQE_MODE_RX */ nla_total_size(sizeof(u32)) + /* _TX_AGGR_MAX_BYTES */ nla_total_size(sizeof(u32)) + /* _TX_AGGR_MAX_FRAMES */ - nla_total_size(sizeof(u32)); /* _TX_AGGR_TIME_USECS */ + nla_total_size(sizeof(u32)) + /* _TX_AGGR_TIME_USECS */ + total_modersz * 2; /* _{R,T}X_PROFILE */ } static bool coalesce_put_u32(struct sk_buff *skb, u16 attr_type, u32 val, @@ -127,6 +137,74 @@ static bool coalesce_put_bool(struct sk_buff *skb, u16 attr_type, u32 val, return nla_put_u8(skb, attr_type, !!val); } +/** + * coalesce_put_profile - fill reply with a nla nest with four child nla nests. + * @skb: socket buffer the message is stored in + * @attr_type: nest attr type ETHTOOL_A_COALESCE_*X_PROFILE + * @profile: data passed to userspace + * @coal_flags: modifiable parameters supported by the driver + * + * Put a dim profile nest attribute. Refer to ETHTOOL_A_PROFILE_IRQ_MODERATION. + * + * Return: 0 on success or a negative error code. + */ +static int coalesce_put_profile(struct sk_buff *skb, u16 attr_type, + const struct dim_cq_moder *profile, + u8 coal_flags) +{ + struct nlattr *profile_attr, *moder_attr; + int i, ret; + + if (!profile || !coal_flags) + return 0; + + profile_attr = nla_nest_start(skb, attr_type); + if (!profile_attr) + return -EMSGSIZE; + + for (i = 0; i < NET_DIM_PARAMS_NUM_PROFILES; i++) { + moder_attr = nla_nest_start(skb, + ETHTOOL_A_PROFILE_IRQ_MODERATION); + if (!moder_attr) { + ret = -EMSGSIZE; + goto cancel_profile; + } + + if (coal_flags & DIM_COALESCE_USEC) { + ret = nla_put_u32(skb, ETHTOOL_A_IRQ_MODERATION_USEC, + profile[i].usec); + if (ret) + goto cancel_moder; + } + + if (coal_flags & DIM_COALESCE_PKTS) { + ret = nla_put_u32(skb, ETHTOOL_A_IRQ_MODERATION_PKTS, + profile[i].pkts); + if (ret) + goto cancel_moder; + } + + if (coal_flags & DIM_COALESCE_COMPS) { + ret = nla_put_u32(skb, ETHTOOL_A_IRQ_MODERATION_COMPS, + profile[i].comps); + if (ret) + goto cancel_moder; + } + + nla_nest_end(skb, moder_attr); + } + + nla_nest_end(skb, profile_attr); + + return 0; + +cancel_moder: + nla_nest_cancel(skb, moder_attr); +cancel_profile: + nla_nest_cancel(skb, profile_attr); + return ret; +} + static int coalesce_fill_reply(struct sk_buff *skb, const struct ethnl_req_info *req_base, const struct ethnl_reply_data *reply_base) @@ -135,6 +213,8 @@ static int coalesce_fill_reply(struct sk_buff *skb, const struct kernel_ethtool_coalesce *kcoal = &data->kernel_coalesce; const struct ethtool_coalesce *coal = &data->coalesce; u32 supported = data->supported_params; + struct dim_irq_moder *moder; + int ret = 0; if (coalesce_put_u32(skb, ETHTOOL_A_COALESCE_RX_USECS, coal->rx_coalesce_usecs, supported) || @@ -192,11 +272,42 @@ static int coalesce_fill_reply(struct sk_buff *skb, kcoal->tx_aggr_time_usecs, supported)) return -EMSGSIZE; - return 0; + if (!req_base->dev || !req_base->dev->irq_moder) + return 0; + + moder = req_base->dev->irq_moder; + rcu_read_lock(); + if (moder->profile_flags & DIM_PROFILE_RX) { + ret = coalesce_put_profile(skb, ETHTOOL_A_COALESCE_RX_PROFILE, + rcu_dereference(moder->rx_profile), + moder->coal_flags); + if (ret) + goto out; + } + + if (moder->profile_flags & DIM_PROFILE_TX) + ret = coalesce_put_profile(skb, ETHTOOL_A_COALESCE_TX_PROFILE, + rcu_dereference(moder->tx_profile), + moder->coal_flags); + +out: + rcu_read_unlock(); + return ret; } /* COALESCE_SET */ +static const struct nla_policy coalesce_irq_moderation_policy[] = { + [ETHTOOL_A_IRQ_MODERATION_USEC] = { .type = NLA_U32 }, + [ETHTOOL_A_IRQ_MODERATION_PKTS] = { .type = NLA_U32 }, + [ETHTOOL_A_IRQ_MODERATION_COMPS] = { .type = NLA_U32 }, +}; + +static const struct nla_policy coalesce_profile_policy[] = { + [ETHTOOL_A_PROFILE_IRQ_MODERATION] = + NLA_POLICY_NESTED(coalesce_irq_moderation_policy), +}; + const struct nla_policy ethnl_coalesce_set_policy[] = { [ETHTOOL_A_COALESCE_HEADER] = NLA_POLICY_NESTED(ethnl_header_policy), @@ -227,6 +338,10 @@ const struct nla_policy ethnl_coalesce_set_policy[] = { [ETHTOOL_A_COALESCE_TX_AGGR_MAX_BYTES] = { .type = NLA_U32 }, [ETHTOOL_A_COALESCE_TX_AGGR_MAX_FRAMES] = { .type = NLA_U32 }, [ETHTOOL_A_COALESCE_TX_AGGR_TIME_USECS] = { .type = NLA_U32 }, + [ETHTOOL_A_COALESCE_RX_PROFILE] = + NLA_POLICY_NESTED(coalesce_profile_policy), + [ETHTOOL_A_COALESCE_TX_PROFILE] = + NLA_POLICY_NESTED(coalesce_profile_policy), }; static int @@ -234,6 +349,7 @@ ethnl_set_coalesce_validate(struct ethnl_req_info *req_info, struct genl_info *info) { const struct ethtool_ops *ops = req_info->dev->ethtool_ops; + struct dim_irq_moder *irq_moder = req_info->dev->irq_moder; struct nlattr **tb = info->attrs; u32 supported_params; u16 a; @@ -243,6 +359,12 @@ ethnl_set_coalesce_validate(struct ethnl_req_info *req_info, /* make sure that only supported parameters are present */ supported_params = ops->supported_coalesce_params; + if (irq_moder && irq_moder->profile_flags & DIM_PROFILE_RX) + supported_params |= ETHTOOL_COALESCE_RX_PROFILE; + + if (irq_moder && irq_moder->profile_flags & DIM_PROFILE_TX) + supported_params |= ETHTOOL_COALESCE_TX_PROFILE; + for (a = ETHTOOL_A_COALESCE_RX_USECS; a < __ETHTOOL_A_COALESCE_CNT; a++) if (tb[a] && !(supported_params & attr_to_mask(a))) { NL_SET_ERR_MSG_ATTR(info->extack, tb[a], @@ -253,6 +375,138 @@ ethnl_set_coalesce_validate(struct ethnl_req_info *req_info, return 1; } +/** + * ethnl_update_irq_moder - update a specific field in the given profile + * @irq_moder: place that collects dim related information + * @irq_field: field in profile to modify + * @attr_type: attr type ETHTOOL_A_IRQ_MODERATION_* + * @tb: netlink attribute with new values or null + * @coal_bit: DIM_COALESCE_* bit from coal_flags + * @mod: pointer to bool for modification tracking + * @extack: netlink extended ack + * + * Return: 0 on success or a negative error code. + */ +static int ethnl_update_irq_moder(struct dim_irq_moder *irq_moder, + u16 *irq_field, u16 attr_type, + struct nlattr **tb, + u8 coal_bit, bool *mod, + struct netlink_ext_ack *extack) +{ + int ret = 0; + u32 val; + + if (!tb[attr_type]) + return 0; + + if (irq_moder->coal_flags & coal_bit) { + val = nla_get_u32(tb[attr_type]); + if (*irq_field == val) + return 0; + + *irq_field = val; + *mod = true; + } else { + NL_SET_BAD_ATTR(extack, tb[attr_type]); + ret = -EOPNOTSUPP; + } + + return ret; +} + +/** + * ethnl_update_profile - get a profile nest with child nests from userspace. + * @dev: netdevice to update the profile + * @dst: profile get from the driver and modified by ethnl_update_profile. + * @nests: nest attr ETHTOOL_A_COALESCE_*X_PROFILE to set profile. + * @mod: pointer to bool for modification tracking + * @extack: Netlink extended ack + * + * Layout of nests: + * Nested ETHTOOL_A_COALESCE_*X_PROFILE attr + * Nested ETHTOOL_A_PROFILE_IRQ_MODERATION attr + * ETHTOOL_A_IRQ_MODERATION_USEC attr + * ETHTOOL_A_IRQ_MODERATION_PKTS attr + * ETHTOOL_A_IRQ_MODERATION_COMPS attr + * ... + * Nested ETHTOOL_A_PROFILE_IRQ_MODERATION attr + * ETHTOOL_A_IRQ_MODERATION_USEC attr + * ETHTOOL_A_IRQ_MODERATION_PKTS attr + * ETHTOOL_A_IRQ_MODERATION_COMPS attr + * + * Return: 0 on success or a negative error code. + */ +static int ethnl_update_profile(struct net_device *dev, + struct dim_cq_moder __rcu **dst, + const struct nlattr *nests, + bool *mod, + struct netlink_ext_ack *extack) +{ + int len_irq_moder = ARRAY_SIZE(coalesce_irq_moderation_policy); + struct nlattr *tb[ARRAY_SIZE(coalesce_irq_moderation_policy)]; + struct dim_irq_moder *irq_moder = dev->irq_moder; + struct dim_cq_moder *new_profile, *old_profile; + int ret, rem, i = 0, len; + struct nlattr *nest; + + if (!nests) + return 0; + + if (!*dst) + return -EOPNOTSUPP; + + old_profile = rtnl_dereference(*dst); + len = NET_DIM_PARAMS_NUM_PROFILES * sizeof(*old_profile); + new_profile = kmemdup(old_profile, len, GFP_KERNEL); + if (!new_profile) + return -ENOMEM; + + nla_for_each_nested_type(nest, ETHTOOL_A_PROFILE_IRQ_MODERATION, + nests, rem) { + ret = nla_parse_nested(tb, len_irq_moder - 1, nest, + coalesce_irq_moderation_policy, + extack); + if (ret) + goto err_out; + + ret = ethnl_update_irq_moder(irq_moder, &new_profile[i].usec, + ETHTOOL_A_IRQ_MODERATION_USEC, + tb, DIM_COALESCE_USEC, + mod, extack); + if (ret) + goto err_out; + + ret = ethnl_update_irq_moder(irq_moder, &new_profile[i].pkts, + ETHTOOL_A_IRQ_MODERATION_PKTS, + tb, DIM_COALESCE_PKTS, + mod, extack); + if (ret) + goto err_out; + + ret = ethnl_update_irq_moder(irq_moder, &new_profile[i].comps, + ETHTOOL_A_IRQ_MODERATION_COMPS, + tb, DIM_COALESCE_COMPS, + mod, extack); + if (ret) + goto err_out; + + i++; + } + + /* After the profile is modified, dim itself is a dynamic + * mechanism and will quickly fit to the appropriate + * coalescing parameters according to the new profile. + */ + rcu_assign_pointer(*dst, new_profile); + kfree_rcu(old_profile, rcu); + + return 0; + +err_out: + kfree(new_profile); + return ret; +} + static int __ethnl_set_coalesce(struct ethnl_req_info *req_info, struct genl_info *info, bool *dual_change) @@ -317,6 +571,22 @@ __ethnl_set_coalesce(struct ethnl_req_info *req_info, struct genl_info *info, ethnl_update_u32(&kernel_coalesce.tx_aggr_time_usecs, tb[ETHTOOL_A_COALESCE_TX_AGGR_TIME_USECS], &mod); + if (dev->irq_moder && dev->irq_moder->profile_flags & DIM_PROFILE_RX) { + ret = ethnl_update_profile(dev, &dev->irq_moder->rx_profile, + tb[ETHTOOL_A_COALESCE_RX_PROFILE], + &mod, info->extack); + if (ret < 0) + return ret; + } + + if (dev->irq_moder && dev->irq_moder->profile_flags & DIM_PROFILE_TX) { + ret = ethnl_update_profile(dev, &dev->irq_moder->tx_profile, + tb[ETHTOOL_A_COALESCE_TX_PROFILE], + &mod, info->extack); + if (ret < 0) + return ret; + } + /* Update operation modes */ ethnl_update_bool32(&coalesce.use_adaptive_rx_coalesce, tb[ETHTOOL_A_COALESCE_USE_ADAPTIVE_RX], &mod_mode); diff --git a/net/ethtool/common.c b/net/ethtool/common.c index 6b2a360dcdf0..dd345efa114b 100644 --- a/net/ethtool/common.c +++ b/net/ethtool/common.c @@ -6,6 +6,7 @@ #include <linux/rtnetlink.h> #include <linux/ptp_clock_kernel.h> +#include "netlink.h" #include "common.h" const char netdev_features_strings[NETDEV_FEATURE_COUNT][ETH_GSTRING_LEN] = { @@ -24,8 +25,6 @@ const char netdev_features_strings[NETDEV_FEATURE_COUNT][ETH_GSTRING_LEN] = { [NETIF_F_HW_VLAN_STAG_FILTER_BIT] = "rx-vlan-stag-filter", [NETIF_F_VLAN_CHALLENGED_BIT] = "vlan-challenged", [NETIF_F_GSO_BIT] = "tx-generic-segmentation", - [NETIF_F_LLTX_BIT] = "tx-lockless", - [NETIF_F_NETNS_LOCAL_BIT] = "netns-local", [NETIF_F_GRO_BIT] = "rx-gro", [NETIF_F_GRO_HW_BIT] = "rx-gro-hw", [NETIF_F_LRO_BIT] = "rx-lro", @@ -51,7 +50,6 @@ const char netdev_features_strings[NETDEV_FEATURE_COUNT][ETH_GSTRING_LEN] = { [NETIF_F_FCOE_CRC_BIT] = "tx-checksum-fcoe-crc", [NETIF_F_SCTP_CRC_BIT] = "tx-checksum-sctp", - [NETIF_F_FCOE_MTU_BIT] = "fcoe-mtu", [NETIF_F_NTUPLE_BIT] = "rx-ntuple-filter", [NETIF_F_RXHASH_BIT] = "rx-hashing", [NETIF_F_RXCSUM_BIT] = "rx-checksum", @@ -211,6 +209,7 @@ const char link_mode_names[][ETH_GSTRING_LEN] = { __DEFINE_LINK_MODE_NAME(10, T1S, Full), __DEFINE_LINK_MODE_NAME(10, T1S, Half), __DEFINE_LINK_MODE_NAME(10, T1S_P2MP, Half), + __DEFINE_LINK_MODE_NAME(10, T1BRR, Full), }; static_assert(ARRAY_SIZE(link_mode_names) == __ETHTOOL_LINK_MODE_MASK_NBITS); @@ -251,6 +250,7 @@ static_assert(ARRAY_SIZE(link_mode_names) == __ETHTOOL_LINK_MODE_MASK_NBITS); #define __LINK_MODE_LANES_T1S_P2MP 1 #define __LINK_MODE_LANES_VR8 8 #define __LINK_MODE_LANES_DR8_2 8 +#define __LINK_MODE_LANES_T1BRR 1 #define __DEFINE_LINK_MODE_PARAMS(_speed, _type, _duplex) \ [ETHTOOL_LINK_MODE(_speed, _type, _duplex)] = { \ @@ -374,6 +374,7 @@ const struct link_mode_info link_mode_params[] = { __DEFINE_LINK_MODE_PARAMS(10, T1S, Full), __DEFINE_LINK_MODE_PARAMS(10, T1S, Half), __DEFINE_LINK_MODE_PARAMS(10, T1S_P2MP, Half), + __DEFINE_LINK_MODE_PARAMS(10, T1BRR, Full), }; static_assert(ARRAY_SIZE(link_mode_params) == __ETHTOOL_LINK_MODE_MASK_NBITS); @@ -426,6 +427,7 @@ const char sof_timestamping_names[][ETH_GSTRING_LEN] = { [const_ilog2(SOF_TIMESTAMPING_OPT_TX_SWHW)] = "option-tx-swhw", [const_ilog2(SOF_TIMESTAMPING_BIND_PHC)] = "bind-phc", [const_ilog2(SOF_TIMESTAMPING_OPT_ID_TCP)] = "option-id-tcp", + [const_ilog2(SOF_TIMESTAMPING_OPT_RX_FILTER)] = "option-rx-filter", }; static_assert(ARRAY_SIZE(sof_timestamping_names) == __SOF_TIMESTAMPING_CNT); @@ -536,7 +538,7 @@ static int ethtool_get_rxnfc_rule_count(struct net_device *dev) return info.rule_cnt; } -int ethtool_get_max_rxnfc_channel(struct net_device *dev, u64 *max) +static int ethtool_get_max_rxnfc_channel(struct net_device *dev, u64 *max) { const struct ethtool_ops *ops = dev->ethtool_ops; struct ethtool_rxnfc *info; @@ -587,41 +589,107 @@ err_free_info: return err; } -int ethtool_get_max_rxfh_channel(struct net_device *dev, u32 *max) +static u32 ethtool_get_max_rss_ctx_channel(struct net_device *dev) +{ + struct ethtool_rxfh_context *ctx; + unsigned long context; + u32 max_ring = 0; + + mutex_lock(&dev->ethtool->rss_lock); + xa_for_each(&dev->ethtool->rss_ctx, context, ctx) { + u32 i, *tbl; + + tbl = ethtool_rxfh_context_indir(ctx); + for (i = 0; i < ctx->indir_size; i++) + max_ring = max(max_ring, tbl[i]); + } + mutex_unlock(&dev->ethtool->rss_lock); + + return max_ring; +} + +static u32 ethtool_get_max_rxfh_channel(struct net_device *dev) { struct ethtool_rxfh_param rxfh = {}; - u32 dev_size, current_max = 0; + u32 dev_size, current_max; int ret; + /* While we do track whether RSS context has an indirection + * table explicitly set by the user, no driver looks at that bit. + * Assume drivers won't auto-regenerate the additional tables, + * to be safe. + */ + current_max = ethtool_get_max_rss_ctx_channel(dev); + + if (!netif_is_rxfh_configured(dev)) + return current_max; + if (!dev->ethtool_ops->get_rxfh_indir_size || !dev->ethtool_ops->get_rxfh) - return -EOPNOTSUPP; + return current_max; dev_size = dev->ethtool_ops->get_rxfh_indir_size(dev); if (dev_size == 0) - return -EOPNOTSUPP; + return current_max; rxfh.indir = kcalloc(dev_size, sizeof(rxfh.indir[0]), GFP_USER); if (!rxfh.indir) - return -ENOMEM; + return U32_MAX; ret = dev->ethtool_ops->get_rxfh(dev, &rxfh); - if (ret) - goto out; + if (ret) { + current_max = U32_MAX; + goto out_free; + } while (dev_size--) current_max = max(current_max, rxfh.indir[dev_size]); - *max = current_max; - -out: +out_free: kfree(rxfh.indir); - return ret; + return current_max; +} + +int ethtool_check_max_channel(struct net_device *dev, + struct ethtool_channels channels, + struct genl_info *info) +{ + u64 max_rxnfc_in_use; + u32 max_rxfh_in_use; + int max_mp_in_use; + + /* ensure the new Rx count fits within the configured Rx flow + * indirection table/rxnfc settings + */ + if (ethtool_get_max_rxnfc_channel(dev, &max_rxnfc_in_use)) + max_rxnfc_in_use = 0; + max_rxfh_in_use = ethtool_get_max_rxfh_channel(dev); + if (channels.combined_count + channels.rx_count <= max_rxfh_in_use) { + if (info) + GENL_SET_ERR_MSG_FMT(info, "requested channel counts are too low for existing indirection table (%d)", max_rxfh_in_use); + return -EINVAL; + } + if (channels.combined_count + channels.rx_count <= max_rxnfc_in_use) { + if (info) + GENL_SET_ERR_MSG(info, "requested channel counts are too low for existing ntuple filter settings"); + return -EINVAL; + } + + max_mp_in_use = dev_get_min_mp_channel_count(dev); + if (channels.combined_count + channels.rx_count <= max_mp_in_use) { + if (info) + GENL_SET_ERR_MSG_FMT(info, "requested channel counts are too low for existing memory provider setting (%d)", max_mp_in_use); + return -EINVAL; + } + + return 0; } int ethtool_check_ops(const struct ethtool_ops *ops) { if (WARN_ON(ops->set_coalesce && !ops->supported_coalesce_params)) return -EINVAL; + if (WARN_ON(ops->rxfh_max_num_contexts == 1)) + return -EINVAL; /* NOTE: sufficiently insane drivers may swap ethtool_ops at runtime, * the fact that ops are checked at registration time does not * mean the ops attached to a netdev later on are sane. @@ -629,29 +697,30 @@ int ethtool_check_ops(const struct ethtool_ops *ops) return 0; } -int __ethtool_get_ts_info(struct net_device *dev, struct ethtool_ts_info *info) +int __ethtool_get_ts_info(struct net_device *dev, struct kernel_ethtool_ts_info *info) { const struct ethtool_ops *ops = dev->ethtool_ops; struct phy_device *phydev = dev->phydev; + int err = 0; memset(info, 0, sizeof(*info)); info->cmd = ETHTOOL_GET_TS_INFO; + info->phc_index = -1; - if (phy_has_tsinfo(phydev)) - return phy_ts_info(phydev, info); - if (ops->get_ts_info) - return ops->get_ts_info(dev, info); + if (phy_is_default_hwtstamp(phydev) && phy_has_tsinfo(phydev)) + err = phy_ts_info(phydev, info); + else if (ops->get_ts_info) + err = ops->get_ts_info(dev, info); - info->so_timestamping = SOF_TIMESTAMPING_RX_SOFTWARE | - SOF_TIMESTAMPING_SOFTWARE; - info->phc_index = -1; + info->so_timestamping |= SOF_TIMESTAMPING_RX_SOFTWARE | + SOF_TIMESTAMPING_SOFTWARE; - return 0; + return err; } int ethtool_get_phc_vclocks(struct net_device *dev, int **vclock_index) { - struct ethtool_ts_info info = { }; + struct kernel_ethtool_ts_info info = { }; int num = 0; if (!__ethtool_get_ts_info(dev, &info)) @@ -661,7 +730,7 @@ int ethtool_get_phc_vclocks(struct net_device *dev, int **vclock_index) } EXPORT_SYMBOL(ethtool_get_phc_vclocks); -int ethtool_get_ts_info_by_layer(struct net_device *dev, struct ethtool_ts_info *info) +int ethtool_get_ts_info_by_layer(struct net_device *dev, struct kernel_ethtool_ts_info *info) { return __ethtool_get_ts_info(dev, info); } @@ -712,3 +781,17 @@ ethtool_forced_speed_maps_init(struct ethtool_forced_speed_map *maps, u32 size) } } EXPORT_SYMBOL_GPL(ethtool_forced_speed_maps_init); + +void ethtool_rxfh_context_lost(struct net_device *dev, u32 context_id) +{ + struct ethtool_rxfh_context *ctx; + + WARN_ONCE(!rtnl_is_locked() && + !lockdep_is_held_type(&dev->ethtool->rss_lock, -1), + "RSS context lock assertion failed\n"); + + netdev_err(dev, "device error, RSS context %d lost\n", context_id); + ctx = xa_erase(&dev->ethtool->rss_ctx, context_id); + kfree(ctx); +} +EXPORT_SYMBOL(ethtool_rxfh_context_lost); diff --git a/net/ethtool/common.h b/net/ethtool/common.h index 28b8aaaf9bcb..d55d5201b085 100644 --- a/net/ethtool/common.h +++ b/net/ethtool/common.h @@ -20,6 +20,8 @@ struct link_mode_info { u8 duplex; }; +struct genl_info; + extern const char netdev_features_strings[NETDEV_FEATURE_COUNT][ETH_GSTRING_LEN]; extern const char @@ -42,9 +44,10 @@ int __ethtool_get_link(struct net_device *dev); bool convert_legacy_settings_to_link_ksettings( struct ethtool_link_ksettings *link_ksettings, const struct ethtool_cmd *legacy_settings); -int ethtool_get_max_rxfh_channel(struct net_device *dev, u32 *max); -int ethtool_get_max_rxnfc_channel(struct net_device *dev, u64 *max); -int __ethtool_get_ts_info(struct net_device *dev, struct ethtool_ts_info *info); +int ethtool_check_max_channel(struct net_device *dev, + struct ethtool_channels channels, + struct genl_info *info); +int __ethtool_get_ts_info(struct net_device *dev, struct kernel_ethtool_ts_info *info); extern const struct ethtool_phy_ops *ethtool_phy_ops; extern const struct ethtool_pse_ops *ethtool_pse_ops; diff --git a/net/ethtool/eeprom.c b/net/ethtool/eeprom.c index 6209c3a9c8f7..3b8209e930fd 100644 --- a/net/ethtool/eeprom.c +++ b/net/ethtool/eeprom.c @@ -91,6 +91,12 @@ static int get_module_eeprom_by_page(struct net_device *dev, { const struct ethtool_ops *ops = dev->ethtool_ops; + if (dev->ethtool->module_fw_flash_in_progress) { + NL_SET_ERR_MSG(extack, + "Module firmware flashing is in progress"); + return -EBUSY; + } + if (dev->sfp_bus) return sfp_get_module_eeprom_by_page(dev->sfp_bus, page_data, extack); diff --git a/net/ethtool/ioctl.c b/net/ethtool/ioctl.c index e645d751a5e8..65cfe76dafbe 100644 --- a/net/ethtool/ioctl.c +++ b/net/ethtool/ioctl.c @@ -65,7 +65,8 @@ u32 ethtool_op_get_link(struct net_device *dev) } EXPORT_SYMBOL(ethtool_op_get_link); -int ethtool_op_get_ts_info(struct net_device *dev, struct ethtool_ts_info *info) +int ethtool_op_get_ts_info(struct net_device *dev, + struct kernel_ethtool_ts_info *info) { info->so_timestamping = SOF_TIMESTAMPING_TX_SOFTWARE | @@ -441,6 +442,9 @@ int __ethtool_get_link_ksettings(struct net_device *dev, if (!dev->ethtool_ops->get_link_ksettings) return -EOPNOTSUPP; + if (!netif_device_present(dev)) + return -ENODEV; + memset(link_ksettings, 0, sizeof(*link_ksettings)); return dev->ethtool_ops->get_link_ksettings(dev, link_ksettings); } @@ -658,6 +662,9 @@ static int ethtool_get_settings(struct net_device *dev, void __user *useraddr) if (!dev->ethtool_ops->get_link_ksettings) return -EOPNOTSUPP; + if (dev->ethtool->module_fw_flash_in_progress) + return -EBUSY; + memset(&link_ksettings, 0, sizeof(link_ksettings)); err = dev->ethtool_ops->get_link_ksettings(dev, &link_ksettings); if (err < 0) @@ -1199,6 +1206,7 @@ static noinline_for_stack int ethtool_get_rxfh(struct net_device *dev, const struct ethtool_ops *ops = dev->ethtool_ops; struct ethtool_rxfh_param rxfh_dev = {}; u32 user_indir_size, user_key_size; + struct ethtool_rxfh_context *ctx; struct ethtool_rxfh rxfh; u32 indir_bytes; u8 *rss_config; @@ -1222,7 +1230,8 @@ static noinline_for_stack int ethtool_get_rxfh(struct net_device *dev, if (rxfh.rsvd8[0] || rxfh.rsvd8[1] || rxfh.rsvd32) return -EINVAL; /* Most drivers don't handle rss_context, check it's 0 as well */ - if (rxfh.rss_context && !ops->cap_rss_ctx_supported) + if (rxfh.rss_context && !(ops->cap_rss_ctx_supported || + ops->create_rxfh_context)) return -EOPNOTSUPP; rxfh.indir_size = rxfh_dev.indir_size; @@ -1246,11 +1255,31 @@ static noinline_for_stack int ethtool_get_rxfh(struct net_device *dev, if (user_key_size) rxfh_dev.key = rss_config + indir_bytes; - rxfh_dev.rss_context = rxfh.rss_context; - - ret = dev->ethtool_ops->get_rxfh(dev, &rxfh_dev); - if (ret) - goto out; + if (rxfh.rss_context) { + ctx = xa_load(&dev->ethtool->rss_ctx, rxfh.rss_context); + if (!ctx) { + ret = -ENOENT; + goto out; + } + if (rxfh_dev.indir) + memcpy(rxfh_dev.indir, ethtool_rxfh_context_indir(ctx), + indir_bytes); + if (!ops->rxfh_per_ctx_key) { + rxfh_dev.key_size = 0; + } else { + if (rxfh_dev.key) + memcpy(rxfh_dev.key, + ethtool_rxfh_context_key(ctx), + user_key_size); + rxfh_dev.hfunc = ctx->hfunc; + } + rxfh_dev.input_xfrm = ctx->input_xfrm; + ret = 0; + } else { + ret = dev->ethtool_ops->get_rxfh(dev, &rxfh_dev); + if (ret) + goto out; + } if (copy_to_user(useraddr + offsetof(struct ethtool_rxfh, hfunc), &rxfh_dev.hfunc, sizeof(rxfh.hfunc))) { @@ -1261,6 +1290,11 @@ static noinline_for_stack int ethtool_get_rxfh(struct net_device *dev, sizeof(rxfh.input_xfrm))) { ret = -EFAULT; } else if (copy_to_user(useraddr + + offsetof(struct ethtool_rxfh, key_size), + &rxfh_dev.key_size, + sizeof(rxfh.key_size))) { + ret = -EFAULT; + } else if (copy_to_user(useraddr + offsetof(struct ethtool_rxfh, rss_config[0]), rss_config, total_size)) { ret = -EFAULT; @@ -1271,17 +1305,54 @@ out: return ret; } +static struct ethtool_rxfh_context * +ethtool_rxfh_ctx_alloc(const struct ethtool_ops *ops, + u32 indir_size, u32 key_size) +{ + size_t indir_bytes, flex_len, key_off, size; + struct ethtool_rxfh_context *ctx; + u32 priv_bytes, indir_max; + u16 key_max; + + key_max = max(key_size, ops->rxfh_key_space); + indir_max = max(indir_size, ops->rxfh_indir_space); + + priv_bytes = ALIGN(ops->rxfh_priv_size, sizeof(u32)); + indir_bytes = array_size(indir_max, sizeof(u32)); + + key_off = size_add(priv_bytes, indir_bytes); + flex_len = size_add(key_off, key_max); + size = struct_size_t(struct ethtool_rxfh_context, data, flex_len); + + ctx = kzalloc(size, GFP_KERNEL_ACCOUNT); + if (!ctx) + return NULL; + + ctx->indir_size = indir_size; + ctx->key_size = key_size; + ctx->key_off = key_off; + ctx->priv_size = ops->rxfh_priv_size; + + ctx->hfunc = ETH_RSS_HASH_NO_CHANGE; + ctx->input_xfrm = RXH_XFRM_NO_CHANGE; + + return ctx; +} + static noinline_for_stack int ethtool_set_rxfh(struct net_device *dev, void __user *useraddr) { u32 rss_cfg_offset = offsetof(struct ethtool_rxfh, rss_config[0]); const struct ethtool_ops *ops = dev->ethtool_ops; u32 dev_indir_size = 0, dev_key_size = 0, i; + u32 user_indir_len = 0, indir_bytes = 0; struct ethtool_rxfh_param rxfh_dev = {}; + struct ethtool_rxfh_context *ctx = NULL; struct netlink_ext_ack *extack = NULL; struct ethtool_rxnfc rx_rings; struct ethtool_rxfh rxfh; - u32 indir_bytes = 0; + bool locked = false; /* dev->ethtool->rss_lock taken */ + bool create = false; u8 *rss_config; int ret; @@ -1300,33 +1371,45 @@ static noinline_for_stack int ethtool_set_rxfh(struct net_device *dev, if (rxfh.rsvd8[0] || rxfh.rsvd8[1] || rxfh.rsvd32) return -EINVAL; /* Most drivers don't handle rss_context, check it's 0 as well */ - if (rxfh.rss_context && !ops->cap_rss_ctx_supported) + if (rxfh.rss_context && !(ops->cap_rss_ctx_supported || + ops->create_rxfh_context)) return -EOPNOTSUPP; /* Check input data transformation capabilities */ if (rxfh.input_xfrm && rxfh.input_xfrm != RXH_XFRM_SYM_XOR && rxfh.input_xfrm != RXH_XFRM_NO_CHANGE) return -EINVAL; - if ((rxfh.input_xfrm & RXH_XFRM_SYM_XOR) && + if (rxfh.input_xfrm != RXH_XFRM_NO_CHANGE && + (rxfh.input_xfrm & RXH_XFRM_SYM_XOR) && !ops->cap_rss_sym_xor_supported) return -EOPNOTSUPP; + create = rxfh.rss_context == ETH_RXFH_CONTEXT_ALLOC; - /* If either indir, hash key or function is valid, proceed further. - * Must request at least one change: indir size, hash key, function - * or input transformation. - */ if ((rxfh.indir_size && rxfh.indir_size != ETH_RXFH_INDIR_NO_CHANGE && rxfh.indir_size != dev_indir_size) || - (rxfh.key_size && (rxfh.key_size != dev_key_size)) || + (rxfh.key_size && rxfh.key_size != dev_key_size)) + return -EINVAL; + + /* Must request at least one change: indir size, hash key, function + * or input transformation. + * There's no need for any of it in case of context creation. + */ + if (!create && (rxfh.indir_size == ETH_RXFH_INDIR_NO_CHANGE && rxfh.key_size == 0 && rxfh.hfunc == ETH_RSS_HASH_NO_CHANGE && rxfh.input_xfrm == RXH_XFRM_NO_CHANGE)) return -EINVAL; - if (rxfh.indir_size != ETH_RXFH_INDIR_NO_CHANGE) - indir_bytes = dev_indir_size * sizeof(rxfh_dev.indir[0]); + indir_bytes = dev_indir_size * sizeof(rxfh_dev.indir[0]); - rss_config = kzalloc(indir_bytes + rxfh.key_size, GFP_USER); + /* Check settings which may be global rather than per RSS-context */ + if (rxfh.rss_context && !ops->rxfh_per_ctx_key) + if (rxfh.key_size || + (rxfh.hfunc && rxfh.hfunc != ETH_RSS_HASH_NO_CHANGE) || + (rxfh.input_xfrm && rxfh.input_xfrm != RXH_XFRM_NO_CHANGE)) + return -EOPNOTSUPP; + + rss_config = kzalloc(indir_bytes + dev_key_size, GFP_USER); if (!rss_config) return -ENOMEM; @@ -1341,6 +1424,7 @@ static noinline_for_stack int ethtool_set_rxfh(struct net_device *dev, */ if (rxfh.indir_size && rxfh.indir_size != ETH_RXFH_INDIR_NO_CHANGE) { + user_indir_len = indir_bytes; rxfh_dev.indir = (u32 *)rss_config; rxfh_dev.indir_size = dev_indir_size; ret = ethtool_copy_validate_indir(rxfh_dev.indir, @@ -1367,20 +1451,82 @@ static noinline_for_stack int ethtool_set_rxfh(struct net_device *dev, rxfh_dev.key_size = dev_key_size; rxfh_dev.key = rss_config + indir_bytes; if (copy_from_user(rxfh_dev.key, - useraddr + rss_cfg_offset + indir_bytes, + useraddr + rss_cfg_offset + user_indir_len, rxfh.key_size)) { ret = -EFAULT; goto out; } } + if (rxfh.rss_context) { + mutex_lock(&dev->ethtool->rss_lock); + locked = true; + } + if (create) { + if (rxfh_dev.rss_delete) { + ret = -EINVAL; + goto out; + } + ctx = ethtool_rxfh_ctx_alloc(ops, dev_indir_size, dev_key_size); + if (!ctx) { + ret = -ENOMEM; + goto out; + } + + if (ops->create_rxfh_context) { + u32 limit = ops->rxfh_max_num_contexts ?: U32_MAX; + u32 ctx_id; + + /* driver uses new API, core allocates ID */ + ret = xa_alloc(&dev->ethtool->rss_ctx, &ctx_id, ctx, + XA_LIMIT(1, limit - 1), + GFP_KERNEL_ACCOUNT); + if (ret < 0) { + kfree(ctx); + goto out; + } + WARN_ON(!ctx_id); /* can't happen */ + rxfh.rss_context = ctx_id; + } + } else if (rxfh.rss_context) { + ctx = xa_load(&dev->ethtool->rss_ctx, rxfh.rss_context); + if (!ctx) { + ret = -ENOENT; + goto out; + } + } rxfh_dev.hfunc = rxfh.hfunc; rxfh_dev.rss_context = rxfh.rss_context; rxfh_dev.input_xfrm = rxfh.input_xfrm; - ret = ops->set_rxfh(dev, &rxfh_dev, extack); - if (ret) + if (rxfh.rss_context && ops->create_rxfh_context) { + if (create) { + ret = ops->create_rxfh_context(dev, ctx, &rxfh_dev, + extack); + /* Make sure driver populates defaults */ + WARN_ON_ONCE(!ret && !rxfh_dev.key && + !memchr_inv(ethtool_rxfh_context_key(ctx), + 0, ctx->key_size)); + } else if (rxfh_dev.rss_delete) { + ret = ops->remove_rxfh_context(dev, ctx, + rxfh.rss_context, + extack); + } else { + ret = ops->modify_rxfh_context(dev, ctx, &rxfh_dev, + extack); + } + } else { + ret = ops->set_rxfh(dev, &rxfh_dev, extack); + } + if (ret) { + if (create) { + /* failed to create, free our new tracking entry */ + if (ops->create_rxfh_context) + xa_erase(&dev->ethtool->rss_ctx, rxfh.rss_context); + kfree(ctx); + } goto out; + } if (copy_to_user(useraddr + offsetof(struct ethtool_rxfh, rss_context), &rxfh_dev.rss_context, sizeof(rxfh_dev.rss_context))) @@ -1393,8 +1539,62 @@ static noinline_for_stack int ethtool_set_rxfh(struct net_device *dev, else if (rxfh.indir_size != ETH_RXFH_INDIR_NO_CHANGE) dev->priv_flags |= IFF_RXFH_CONFIGURED; } + /* Update rss_ctx tracking */ + if (create && !ops->create_rxfh_context) { + /* driver uses old API, it chose context ID */ + if (WARN_ON(xa_load(&dev->ethtool->rss_ctx, rxfh_dev.rss_context))) { + /* context ID reused, our tracking is screwed */ + kfree(ctx); + goto out; + } + /* Allocate the exact ID the driver gave us */ + if (xa_is_err(xa_store(&dev->ethtool->rss_ctx, rxfh_dev.rss_context, + ctx, GFP_KERNEL))) { + kfree(ctx); + goto out; + } + + /* Fetch the defaults for the old API, in the new API drivers + * should write defaults into ctx themselves. + */ + rxfh_dev.indir = (u32 *)rss_config; + rxfh_dev.indir_size = dev_indir_size; + + rxfh_dev.key = rss_config + indir_bytes; + rxfh_dev.key_size = dev_key_size; + + ret = ops->get_rxfh(dev, &rxfh_dev); + if (WARN_ON(ret)) { + xa_erase(&dev->ethtool->rss_ctx, rxfh.rss_context); + kfree(ctx); + goto out; + } + } + if (rxfh_dev.rss_delete) { + WARN_ON(xa_erase(&dev->ethtool->rss_ctx, rxfh.rss_context) != ctx); + kfree(ctx); + } else if (ctx) { + if (rxfh_dev.indir) { + for (i = 0; i < dev_indir_size; i++) + ethtool_rxfh_context_indir(ctx)[i] = rxfh_dev.indir[i]; + ctx->indir_configured = + rxfh.indir_size && + rxfh.indir_size != ETH_RXFH_INDIR_NO_CHANGE; + } + if (rxfh_dev.key) { + memcpy(ethtool_rxfh_context_key(ctx), rxfh_dev.key, + dev_key_size); + ctx->key_configured = !!rxfh.key_size; + } + if (rxfh_dev.hfunc != ETH_RSS_HASH_NO_CHANGE) + ctx->hfunc = rxfh_dev.hfunc; + if (rxfh_dev.input_xfrm != RXH_XFRM_NO_CHANGE) + ctx->input_xfrm = rxfh_dev.input_xfrm; + } out: + if (locked) + mutex_unlock(&dev->ethtool->rss_lock); kfree(rss_config); return ret; } @@ -1449,6 +1649,9 @@ static int ethtool_reset(struct net_device *dev, char __user *useraddr) if (!dev->ethtool_ops->reset) return -EOPNOTSUPP; + if (dev->ethtool->module_fw_flash_in_progress) + return -EBUSY; + if (copy_from_user(&reset, useraddr, sizeof(reset))) return -EFAULT; @@ -1503,7 +1706,7 @@ static int ethtool_set_wol(struct net_device *dev, char __user *useraddr) if (ret) return ret; - dev->wol_enabled = !!wol.wolopts; + dev->ethtool->wol_enabled = !!wol.wolopts; ethtool_notify(dev, ETHTOOL_MSG_WOL_NTF, NULL); return 0; @@ -1888,8 +2091,6 @@ static noinline_for_stack int ethtool_set_channels(struct net_device *dev, { struct ethtool_channels channels, curr = { .cmd = ETHTOOL_GCHANNELS }; u16 from_channel, to_channel; - u64 max_rxnfc_in_use; - u32 max_rxfh_in_use; unsigned int i; int ret; @@ -1919,16 +2120,9 @@ static noinline_for_stack int ethtool_set_channels(struct net_device *dev, (!channels.rx_count || !channels.tx_count)) return -EINVAL; - /* ensure the new Rx count fits within the configured Rx flow - * indirection table/rxnfc settings */ - if (ethtool_get_max_rxnfc_channel(dev, &max_rxnfc_in_use)) - max_rxnfc_in_use = 0; - if (!netif_is_rxfh_configured(dev) || - ethtool_get_max_rxfh_channel(dev, &max_rxfh_in_use)) - max_rxfh_in_use = 0; - if (channels.combined_count + channels.rx_count <= - max_t(u64, max_rxnfc_in_use, max_rxfh_in_use)) - return -EINVAL; + ret = ethtool_check_max_channel(dev, channels, NULL); + if (ret) + return ret; /* Disabling channels, query zero-copy AF_XDP sockets */ from_channel = channels.combined_count + @@ -2443,13 +2637,20 @@ out: static int ethtool_get_ts_info(struct net_device *dev, void __user *useraddr) { - struct ethtool_ts_info info; + struct kernel_ethtool_ts_info kernel_info; + struct ethtool_ts_info info = {}; int err; - err = __ethtool_get_ts_info(dev, &info); + err = __ethtool_get_ts_info(dev, &kernel_info); if (err) return err; + info.cmd = kernel_info.cmd; + info.so_timestamping = kernel_info.so_timestamping; + info.phc_index = kernel_info.phc_index; + info.tx_types = kernel_info.tx_types; + info.rx_filters = kernel_info.rx_filters; + if (copy_to_user(useraddr, &info, sizeof(info))) return -EFAULT; @@ -2462,6 +2663,9 @@ int ethtool_get_module_info_call(struct net_device *dev, const struct ethtool_ops *ops = dev->ethtool_ops; struct phy_device *phydev = dev->phydev; + if (dev->ethtool->module_fw_flash_in_progress) + return -EBUSY; + if (dev->sfp_bus) return sfp_get_module_info(dev->sfp_bus, modinfo); @@ -2499,6 +2703,9 @@ int ethtool_get_module_eeprom_call(struct net_device *dev, const struct ethtool_ops *ops = dev->ethtool_ops; struct phy_device *phydev = dev->phydev; + if (dev->ethtool->module_fw_flash_in_progress) + return -EBUSY; + if (dev->sfp_bus) return sfp_get_module_eeprom(dev->sfp_bus, ee, data); diff --git a/net/ethtool/linkinfo.c b/net/ethtool/linkinfo.c index 5c317d23787b..30b8ce275159 100644 --- a/net/ethtool/linkinfo.c +++ b/net/ethtool/linkinfo.c @@ -35,7 +35,7 @@ static int linkinfo_prepare_data(const struct ethnl_req_info *req_base, if (ret < 0) return ret; ret = __ethtool_get_link_ksettings(dev, &data->ksettings); - if (ret < 0 && info) + if (ret < 0) GENL_SET_ERR_MSG(info, "failed to retrieve link settings"); ethnl_ops_complete(dev); diff --git a/net/ethtool/linkmodes.c b/net/ethtool/linkmodes.c index b2591db49f7d..259cd9ef1f2a 100644 --- a/net/ethtool/linkmodes.c +++ b/net/ethtool/linkmodes.c @@ -40,7 +40,7 @@ static int linkmodes_prepare_data(const struct ethnl_req_info *req_base, return ret; ret = __ethtool_get_link_ksettings(dev, &data->ksettings); - if (ret < 0 && info) { + if (ret < 0) { GENL_SET_ERR_MSG(info, "failed to retrieve link settings"); goto out; } diff --git a/net/ethtool/linkstate.c b/net/ethtool/linkstate.c index b2de2108b356..34d76e87847d 100644 --- a/net/ethtool/linkstate.c +++ b/net/ethtool/linkstate.c @@ -37,6 +37,8 @@ static int linkstate_get_sqi(struct net_device *dev) mutex_lock(&phydev->lock); if (!phydev->drv || !phydev->drv->get_sqi) ret = -EOPNOTSUPP; + else if (!phydev->link) + ret = -ENETDOWN; else ret = phydev->drv->get_sqi(phydev); mutex_unlock(&phydev->lock); @@ -55,6 +57,8 @@ static int linkstate_get_sqi_max(struct net_device *dev) mutex_lock(&phydev->lock); if (!phydev->drv || !phydev->drv->get_sqi_max) ret = -EOPNOTSUPP; + else if (!phydev->link) + ret = -ENETDOWN; else ret = phydev->drv->get_sqi_max(phydev); mutex_unlock(&phydev->lock); @@ -62,6 +66,17 @@ static int linkstate_get_sqi_max(struct net_device *dev) return ret; }; +static bool linkstate_sqi_critical_error(int sqi) +{ + return sqi < 0 && sqi != -EOPNOTSUPP && sqi != -ENETDOWN; +} + +static bool linkstate_sqi_valid(struct linkstate_reply_data *data) +{ + return data->sqi >= 0 && data->sqi_max >= 0 && + data->sqi <= data->sqi_max; +} + static int linkstate_get_link_ext_state(struct net_device *dev, struct linkstate_reply_data *data) { @@ -93,12 +108,12 @@ static int linkstate_prepare_data(const struct ethnl_req_info *req_base, data->link = __ethtool_get_link(dev); ret = linkstate_get_sqi(dev); - if (ret < 0 && ret != -EOPNOTSUPP) + if (linkstate_sqi_critical_error(ret)) goto out; data->sqi = ret; ret = linkstate_get_sqi_max(dev); - if (ret < 0 && ret != -EOPNOTSUPP) + if (linkstate_sqi_critical_error(ret)) goto out; data->sqi_max = ret; @@ -136,11 +151,10 @@ static int linkstate_reply_size(const struct ethnl_req_info *req_base, len = nla_total_size(sizeof(u8)) /* LINKSTATE_LINK */ + 0; - if (data->sqi != -EOPNOTSUPP) - len += nla_total_size(sizeof(u32)); - - if (data->sqi_max != -EOPNOTSUPP) - len += nla_total_size(sizeof(u32)); + if (linkstate_sqi_valid(data)) { + len += nla_total_size(sizeof(u32)); /* LINKSTATE_SQI */ + len += nla_total_size(sizeof(u32)); /* LINKSTATE_SQI_MAX */ + } if (data->link_ext_state_provided) len += nla_total_size(sizeof(u8)); /* LINKSTATE_EXT_STATE */ @@ -164,13 +178,14 @@ static int linkstate_fill_reply(struct sk_buff *skb, nla_put_u8(skb, ETHTOOL_A_LINKSTATE_LINK, !!data->link)) return -EMSGSIZE; - if (data->sqi != -EOPNOTSUPP && - nla_put_u32(skb, ETHTOOL_A_LINKSTATE_SQI, data->sqi)) - return -EMSGSIZE; + if (linkstate_sqi_valid(data)) { + if (nla_put_u32(skb, ETHTOOL_A_LINKSTATE_SQI, data->sqi)) + return -EMSGSIZE; - if (data->sqi_max != -EOPNOTSUPP && - nla_put_u32(skb, ETHTOOL_A_LINKSTATE_SQI_MAX, data->sqi_max)) - return -EMSGSIZE; + if (nla_put_u32(skb, ETHTOOL_A_LINKSTATE_SQI_MAX, + data->sqi_max)) + return -EMSGSIZE; + } if (data->link_ext_state_provided) { if (nla_put_u8(skb, ETHTOOL_A_LINKSTATE_EXT_STATE, diff --git a/net/ethtool/module.c b/net/ethtool/module.c index ceb575efc290..6988e07bdcd6 100644 --- a/net/ethtool/module.c +++ b/net/ethtool/module.c @@ -1,10 +1,14 @@ // SPDX-License-Identifier: GPL-2.0-only #include <linux/ethtool.h> +#include <linux/firmware.h> +#include <linux/sfp.h> +#include <net/devlink.h> #include "netlink.h" #include "common.h" #include "bitset.h" +#include "module_fw.h" struct module_req_info { struct ethnl_req_info base; @@ -33,6 +37,12 @@ static int module_get_power_mode(struct net_device *dev, if (!ops->get_module_power_mode) return 0; + if (dev->ethtool->module_fw_flash_in_progress) { + NL_SET_ERR_MSG(extack, + "Module firmware flashing is in progress"); + return -EBUSY; + } + return ops->get_module_power_mode(dev, &data->power, extack); } @@ -109,6 +119,12 @@ ethnl_set_module_validate(struct ethnl_req_info *req_info, if (!tb[ETHTOOL_A_MODULE_POWER_MODE_POLICY]) return 0; + if (req_info->dev->ethtool->module_fw_flash_in_progress) { + NL_SET_ERR_MSG(info->extack, + "Module firmware flashing is in progress"); + return -EBUSY; + } + if (!ops->get_module_power_mode || !ops->set_module_power_mode) { NL_SET_ERR_MSG_ATTR(info->extack, tb[ETHTOOL_A_MODULE_POWER_MODE_POLICY], @@ -158,3 +174,381 @@ const struct ethnl_request_ops ethnl_module_request_ops = { .set = ethnl_set_module, .set_ntf_cmd = ETHTOOL_MSG_MODULE_NTF, }; + +/* MODULE_FW_FLASH_ACT */ + +const struct nla_policy +ethnl_module_fw_flash_act_policy[ETHTOOL_A_MODULE_FW_FLASH_PASSWORD + 1] = { + [ETHTOOL_A_MODULE_FW_FLASH_HEADER] = + NLA_POLICY_NESTED(ethnl_header_policy), + [ETHTOOL_A_MODULE_FW_FLASH_FILE_NAME] = { .type = NLA_NUL_STRING }, + [ETHTOOL_A_MODULE_FW_FLASH_PASSWORD] = { .type = NLA_U32 }, +}; + +static LIST_HEAD(module_fw_flash_work_list); +static DEFINE_SPINLOCK(module_fw_flash_work_list_lock); + +static int +module_flash_fw_work_list_add(struct ethtool_module_fw_flash *module_fw, + struct genl_info *info) +{ + struct ethtool_module_fw_flash *work; + + /* First, check if already registered. */ + spin_lock(&module_fw_flash_work_list_lock); + list_for_each_entry(work, &module_fw_flash_work_list, list) { + if (work->fw_update.ntf_params.portid == info->snd_portid && + work->fw_update.dev == module_fw->fw_update.dev) { + spin_unlock(&module_fw_flash_work_list_lock); + return -EALREADY; + } + } + + list_add_tail(&module_fw->list, &module_fw_flash_work_list); + spin_unlock(&module_fw_flash_work_list_lock); + + return 0; +} + +static void module_flash_fw_work_list_del(struct list_head *list) +{ + spin_lock(&module_fw_flash_work_list_lock); + list_del(list); + spin_unlock(&module_fw_flash_work_list_lock); +} + +static void module_flash_fw_work(struct work_struct *work) +{ + struct ethtool_module_fw_flash *module_fw; + + module_fw = container_of(work, struct ethtool_module_fw_flash, work); + + ethtool_cmis_fw_update(&module_fw->fw_update); + + module_flash_fw_work_list_del(&module_fw->list); + module_fw->fw_update.dev->ethtool->module_fw_flash_in_progress = false; + netdev_put(module_fw->fw_update.dev, &module_fw->dev_tracker); + release_firmware(module_fw->fw_update.fw); + kfree(module_fw); +} + +#define MODULE_EEPROM_PHYS_ID_PAGE 0 +#define MODULE_EEPROM_PHYS_ID_I2C_ADDR 0x50 + +static int module_flash_fw_work_init(struct ethtool_module_fw_flash *module_fw, + struct net_device *dev, + struct netlink_ext_ack *extack) +{ + const struct ethtool_ops *ops = dev->ethtool_ops; + struct ethtool_module_eeprom page_data = {}; + u8 phys_id; + int err; + + /* Fetch the SFF-8024 Identifier Value. For all supported standards, it + * is located at I2C address 0x50, byte 0. See section 4.1 in SFF-8024, + * revision 4.9. + */ + page_data.page = MODULE_EEPROM_PHYS_ID_PAGE; + page_data.offset = SFP_PHYS_ID; + page_data.length = sizeof(phys_id); + page_data.i2c_address = MODULE_EEPROM_PHYS_ID_I2C_ADDR; + page_data.data = &phys_id; + + err = ops->get_module_eeprom_by_page(dev, &page_data, extack); + if (err < 0) + return err; + + switch (phys_id) { + case SFF8024_ID_QSFP_DD: + case SFF8024_ID_OSFP: + case SFF8024_ID_DSFP: + case SFF8024_ID_QSFP_PLUS_CMIS: + case SFF8024_ID_SFP_DD_CMIS: + case SFF8024_ID_SFP_PLUS_CMIS: + INIT_WORK(&module_fw->work, module_flash_fw_work); + break; + default: + NL_SET_ERR_MSG(extack, + "Module type does not support firmware flashing"); + return -EOPNOTSUPP; + } + + return 0; +} + +void ethnl_module_fw_flash_sock_destroy(struct ethnl_sock_priv *sk_priv) +{ + struct ethtool_module_fw_flash *work; + + spin_lock(&module_fw_flash_work_list_lock); + list_for_each_entry(work, &module_fw_flash_work_list, list) { + if (work->fw_update.dev == sk_priv->dev && + work->fw_update.ntf_params.portid == sk_priv->portid) { + work->fw_update.ntf_params.closed_sock = true; + break; + } + } + spin_unlock(&module_fw_flash_work_list_lock); +} + +static int +module_flash_fw_schedule(struct net_device *dev, const char *file_name, + struct ethtool_module_fw_flash_params *params, + struct sk_buff *skb, struct genl_info *info) +{ + struct ethtool_cmis_fw_update_params *fw_update; + struct ethtool_module_fw_flash *module_fw; + int err; + + module_fw = kzalloc(sizeof(*module_fw), GFP_KERNEL); + if (!module_fw) + return -ENOMEM; + + fw_update = &module_fw->fw_update; + fw_update->params = *params; + err = request_firmware_direct(&fw_update->fw, + file_name, &dev->dev); + if (err) { + NL_SET_ERR_MSG(info->extack, + "Failed to request module firmware image"); + goto err_free; + } + + err = module_flash_fw_work_init(module_fw, dev, info->extack); + if (err < 0) + goto err_release_firmware; + + dev->ethtool->module_fw_flash_in_progress = true; + netdev_hold(dev, &module_fw->dev_tracker, GFP_KERNEL); + fw_update->dev = dev; + fw_update->ntf_params.portid = info->snd_portid; + fw_update->ntf_params.seq = info->snd_seq; + fw_update->ntf_params.closed_sock = false; + + err = ethnl_sock_priv_set(skb, dev, fw_update->ntf_params.portid, + ETHTOOL_SOCK_TYPE_MODULE_FW_FLASH); + if (err < 0) + goto err_release_firmware; + + err = module_flash_fw_work_list_add(module_fw, info); + if (err < 0) + goto err_release_firmware; + + schedule_work(&module_fw->work); + + return 0; + +err_release_firmware: + release_firmware(fw_update->fw); +err_free: + kfree(module_fw); + return err; +} + +static int module_flash_fw(struct net_device *dev, struct nlattr **tb, + struct sk_buff *skb, struct genl_info *info) +{ + struct ethtool_module_fw_flash_params params = {}; + const char *file_name; + struct nlattr *attr; + + if (GENL_REQ_ATTR_CHECK(info, ETHTOOL_A_MODULE_FW_FLASH_FILE_NAME)) + return -EINVAL; + + file_name = nla_data(tb[ETHTOOL_A_MODULE_FW_FLASH_FILE_NAME]); + + attr = tb[ETHTOOL_A_MODULE_FW_FLASH_PASSWORD]; + if (attr) { + params.password = cpu_to_be32(nla_get_u32(attr)); + params.password_valid = true; + } + + return module_flash_fw_schedule(dev, file_name, ¶ms, skb, info); +} + +static int ethnl_module_fw_flash_validate(struct net_device *dev, + struct netlink_ext_ack *extack) +{ + struct devlink_port *devlink_port = dev->devlink_port; + const struct ethtool_ops *ops = dev->ethtool_ops; + + if (!ops->set_module_eeprom_by_page || + !ops->get_module_eeprom_by_page) { + NL_SET_ERR_MSG(extack, + "Flashing module firmware is not supported by this device"); + return -EOPNOTSUPP; + } + + if (!ops->reset) { + NL_SET_ERR_MSG(extack, + "Reset module is not supported by this device, so flashing is not permitted"); + return -EOPNOTSUPP; + } + + if (dev->ethtool->module_fw_flash_in_progress) { + NL_SET_ERR_MSG(extack, "Module firmware flashing already in progress"); + return -EBUSY; + } + + if (dev->flags & IFF_UP) { + NL_SET_ERR_MSG(extack, "Netdevice is up, so flashing is not permitted"); + return -EBUSY; + } + + if (devlink_port && devlink_port->attrs.split) { + NL_SET_ERR_MSG(extack, "Can't perform firmware flashing on a split port"); + return -EOPNOTSUPP; + } + + return 0; +} + +int ethnl_act_module_fw_flash(struct sk_buff *skb, struct genl_info *info) +{ + struct ethnl_req_info req_info = {}; + struct nlattr **tb = info->attrs; + struct net_device *dev; + int ret; + + ret = ethnl_parse_header_dev_get(&req_info, + tb[ETHTOOL_A_MODULE_FW_FLASH_HEADER], + genl_info_net(info), info->extack, + true); + if (ret < 0) + return ret; + dev = req_info.dev; + + rtnl_lock(); + ret = ethnl_ops_begin(dev); + if (ret < 0) + goto out_rtnl; + + ret = ethnl_module_fw_flash_validate(dev, info->extack); + if (ret < 0) + goto out_rtnl; + + ret = module_flash_fw(dev, tb, skb, info); + + ethnl_ops_complete(dev); + +out_rtnl: + rtnl_unlock(); + ethnl_parse_header_dev_put(&req_info); + return ret; +} + +/* MODULE_FW_FLASH_NTF */ + +static int +ethnl_module_fw_flash_ntf_put_err(struct sk_buff *skb, char *err_msg, + char *sub_err_msg) +{ + int err_msg_len, sub_err_msg_len, total_len; + struct nlattr *attr; + + if (!err_msg) + return 0; + + err_msg_len = strlen(err_msg); + total_len = err_msg_len + 2; /* For period and NUL. */ + + if (sub_err_msg) { + sub_err_msg_len = strlen(sub_err_msg); + total_len += sub_err_msg_len + 2; /* For ", ". */ + } + + attr = nla_reserve(skb, ETHTOOL_A_MODULE_FW_FLASH_STATUS_MSG, + total_len); + if (!attr) + return -ENOMEM; + + if (sub_err_msg) + sprintf(nla_data(attr), "%s, %s.", err_msg, sub_err_msg); + else + sprintf(nla_data(attr), "%s.", err_msg); + + return 0; +} + +static void +ethnl_module_fw_flash_ntf(struct net_device *dev, + enum ethtool_module_fw_flash_status status, + struct ethnl_module_fw_flash_ntf_params *ntf_params, + char *err_msg, char *sub_err_msg, + u64 done, u64 total) +{ + struct sk_buff *skb; + void *hdr; + int ret; + + if (ntf_params->closed_sock) + return; + + skb = genlmsg_new(NLMSG_GOODSIZE, GFP_KERNEL); + if (!skb) + return; + + hdr = ethnl_unicast_put(skb, ntf_params->portid, ++ntf_params->seq, + ETHTOOL_MSG_MODULE_FW_FLASH_NTF); + if (!hdr) + goto err_skb; + + ret = ethnl_fill_reply_header(skb, dev, + ETHTOOL_A_MODULE_FW_FLASH_HEADER); + if (ret < 0) + goto err_skb; + + if (nla_put_u32(skb, ETHTOOL_A_MODULE_FW_FLASH_STATUS, status)) + goto err_skb; + + ret = ethnl_module_fw_flash_ntf_put_err(skb, err_msg, sub_err_msg); + if (ret < 0) + goto err_skb; + + if (nla_put_uint(skb, ETHTOOL_A_MODULE_FW_FLASH_DONE, done)) + goto err_skb; + + if (nla_put_uint(skb, ETHTOOL_A_MODULE_FW_FLASH_TOTAL, total)) + goto err_skb; + + genlmsg_end(skb, hdr); + genlmsg_unicast(dev_net(dev), skb, ntf_params->portid); + return; + +err_skb: + nlmsg_free(skb); +} + +void ethnl_module_fw_flash_ntf_err(struct net_device *dev, + struct ethnl_module_fw_flash_ntf_params *params, + char *err_msg, char *sub_err_msg) +{ + ethnl_module_fw_flash_ntf(dev, ETHTOOL_MODULE_FW_FLASH_STATUS_ERROR, + params, err_msg, sub_err_msg, 0, 0); +} + +void +ethnl_module_fw_flash_ntf_start(struct net_device *dev, + struct ethnl_module_fw_flash_ntf_params *params) +{ + ethnl_module_fw_flash_ntf(dev, ETHTOOL_MODULE_FW_FLASH_STATUS_STARTED, + params, NULL, NULL, 0, 0); +} + +void +ethnl_module_fw_flash_ntf_complete(struct net_device *dev, + struct ethnl_module_fw_flash_ntf_params *params) +{ + ethnl_module_fw_flash_ntf(dev, ETHTOOL_MODULE_FW_FLASH_STATUS_COMPLETED, + params, NULL, NULL, 0, 0); +} + +void +ethnl_module_fw_flash_ntf_in_progress(struct net_device *dev, + struct ethnl_module_fw_flash_ntf_params *params, + u64 done, u64 total) +{ + ethnl_module_fw_flash_ntf(dev, + ETHTOOL_MODULE_FW_FLASH_STATUS_IN_PROGRESS, + params, NULL, NULL, done, total); +} diff --git a/net/ethtool/module_fw.h b/net/ethtool/module_fw.h new file mode 100644 index 000000000000..634543a12d0c --- /dev/null +++ b/net/ethtool/module_fw.h @@ -0,0 +1,75 @@ +/* SPDX-License-Identifier: GPL-2.0-only */ + +#include <uapi/linux/ethtool.h> +#include "netlink.h" + +/** + * struct ethnl_module_fw_flash_ntf_params - module firmware flashing + * notifications parameters + * @portid: Netlink portid of sender. + * @seq: Sequence number of sender. + * @closed_sock: Indicates whether the socket was closed from user space. + */ +struct ethnl_module_fw_flash_ntf_params { + u32 portid; + u32 seq; + bool closed_sock; +}; + +/** + * struct ethtool_module_fw_flash_params - module firmware flashing parameters + * @password: Module password. Only valid when @pass_valid is set. + * @password_valid: Whether the module password is valid or not. + */ +struct ethtool_module_fw_flash_params { + __be32 password; + u8 password_valid:1; +}; + +/** + * struct ethtool_cmis_fw_update_params - CMIS firmware update specific + * parameters + * @dev: Pointer to the net_device to be flashed. + * @params: Module firmware flashing parameters. + * @ntf_params: Module firmware flashing notification parameters. + * @fw: Firmware to flash. + */ +struct ethtool_cmis_fw_update_params { + struct net_device *dev; + struct ethtool_module_fw_flash_params params; + struct ethnl_module_fw_flash_ntf_params ntf_params; + const struct firmware *fw; +}; + +/** + * struct ethtool_module_fw_flash - module firmware flashing + * @list: List node for &module_fw_flash_work_list. + * @dev_tracker: Refcount tracker for @dev. + * @work: The flashing firmware work. + * @fw_update: CMIS firmware update specific parameters. + */ +struct ethtool_module_fw_flash { + struct list_head list; + netdevice_tracker dev_tracker; + struct work_struct work; + struct ethtool_cmis_fw_update_params fw_update; +}; + +void ethnl_module_fw_flash_sock_destroy(struct ethnl_sock_priv *sk_priv); + +void +ethnl_module_fw_flash_ntf_err(struct net_device *dev, + struct ethnl_module_fw_flash_ntf_params *params, + char *err_msg, char *sub_err_msg); +void +ethnl_module_fw_flash_ntf_start(struct net_device *dev, + struct ethnl_module_fw_flash_ntf_params *params); +void +ethnl_module_fw_flash_ntf_complete(struct net_device *dev, + struct ethnl_module_fw_flash_ntf_params *params); +void +ethnl_module_fw_flash_ntf_in_progress(struct net_device *dev, + struct ethnl_module_fw_flash_ntf_params *params, + u64 done, u64 total); + +void ethtool_cmis_fw_update(struct ethtool_cmis_fw_update_params *params); diff --git a/net/ethtool/netlink.c b/net/ethtool/netlink.c index bd04f28d5cf4..e3f0ef6b851b 100644 --- a/net/ethtool/netlink.c +++ b/net/ethtool/netlink.c @@ -2,8 +2,10 @@ #include <net/sock.h> #include <linux/ethtool_netlink.h> +#include <linux/phy_link_topology.h> #include <linux/pm_runtime.h> #include "netlink.h" +#include "module_fw.h" static struct genl_family ethtool_genl_family; @@ -30,6 +32,53 @@ const struct nla_policy ethnl_header_policy_stats[] = { ETHTOOL_FLAGS_STATS), }; +const struct nla_policy ethnl_header_policy_phy[] = { + [ETHTOOL_A_HEADER_DEV_INDEX] = { .type = NLA_U32 }, + [ETHTOOL_A_HEADER_DEV_NAME] = { .type = NLA_NUL_STRING, + .len = ALTIFNAMSIZ - 1 }, + [ETHTOOL_A_HEADER_FLAGS] = NLA_POLICY_MASK(NLA_U32, + ETHTOOL_FLAGS_BASIC), + [ETHTOOL_A_HEADER_PHY_INDEX] = NLA_POLICY_MIN(NLA_U32, 1), +}; + +const struct nla_policy ethnl_header_policy_phy_stats[] = { + [ETHTOOL_A_HEADER_DEV_INDEX] = { .type = NLA_U32 }, + [ETHTOOL_A_HEADER_DEV_NAME] = { .type = NLA_NUL_STRING, + .len = ALTIFNAMSIZ - 1 }, + [ETHTOOL_A_HEADER_FLAGS] = NLA_POLICY_MASK(NLA_U32, + ETHTOOL_FLAGS_STATS), + [ETHTOOL_A_HEADER_PHY_INDEX] = NLA_POLICY_MIN(NLA_U32, 1), +}; + +int ethnl_sock_priv_set(struct sk_buff *skb, struct net_device *dev, u32 portid, + enum ethnl_sock_type type) +{ + struct ethnl_sock_priv *sk_priv; + + sk_priv = genl_sk_priv_get(ðtool_genl_family, NETLINK_CB(skb).sk); + if (IS_ERR(sk_priv)) + return PTR_ERR(sk_priv); + + sk_priv->dev = dev; + sk_priv->portid = portid; + sk_priv->type = type; + + return 0; +} + +static void ethnl_sock_priv_destroy(void *priv) +{ + struct ethnl_sock_priv *sk_priv = priv; + + switch (sk_priv->type) { + case ETHTOOL_SOCK_TYPE_MODULE_FW_FLASH: + ethnl_module_fw_flash_sock_destroy(sk_priv); + break; + default: + break; + } +} + int ethnl_ops_begin(struct net_device *dev) { int ret; @@ -89,7 +138,7 @@ int ethnl_parse_header_dev_get(struct ethnl_req_info *req_info, const struct nlattr *header, struct net *net, struct netlink_ext_ack *extack, bool require_dev) { - struct nlattr *tb[ARRAY_SIZE(ethnl_header_policy)]; + struct nlattr *tb[ARRAY_SIZE(ethnl_header_policy_phy)]; const struct nlattr *devname_attr; struct net_device *dev = NULL; u32 flags = 0; @@ -104,7 +153,7 @@ int ethnl_parse_header_dev_get(struct ethnl_req_info *req_info, /* No validation here, command policy should have a nested policy set * for the header, therefore validation should have already been done. */ - ret = nla_parse_nested(tb, ARRAY_SIZE(ethnl_header_policy) - 1, header, + ret = nla_parse_nested(tb, ARRAY_SIZE(ethnl_header_policy_phy) - 1, header, NULL, extack); if (ret < 0) return ret; @@ -145,11 +194,45 @@ int ethnl_parse_header_dev_get(struct ethnl_req_info *req_info, return -EINVAL; } + if (tb[ETHTOOL_A_HEADER_PHY_INDEX]) { + if (dev) { + req_info->phy_index = nla_get_u32(tb[ETHTOOL_A_HEADER_PHY_INDEX]); + } else { + NL_SET_ERR_MSG_ATTR(extack, header, + "phy_index set without a netdev"); + return -EINVAL; + } + } + req_info->dev = dev; req_info->flags = flags; return 0; } +struct phy_device *ethnl_req_get_phydev(const struct ethnl_req_info *req_info, + const struct nlattr *header, + struct netlink_ext_ack *extack) +{ + struct phy_device *phydev; + + ASSERT_RTNL(); + + if (!req_info->dev) + return NULL; + + if (!req_info->phy_index) + return req_info->dev->phydev; + + phydev = phy_link_topo_get_phy(req_info->dev, req_info->phy_index); + if (!phydev) { + NL_SET_ERR_MSG_ATTR(extack, header, + "no phy matching phyindex"); + return ERR_PTR(-ENODEV); + } + + return phydev; +} + /** * ethnl_fill_reply_header() - Put common header into a reply message * @skb: skb with the message @@ -239,6 +322,11 @@ void *ethnl_bcastmsg_put(struct sk_buff *skb, u8 cmd) cmd); } +void *ethnl_unicast_put(struct sk_buff *skb, u32 portid, u32 seq, u8 cmd) +{ + return genlmsg_put(skb, portid, seq, ðtool_genl_family, 0, cmd); +} + int ethnl_multicast(struct sk_buff *skb, struct net_device *dev) { return genlmsg_multicast_netns(ðtool_genl_family, dev_net(dev), skb, @@ -760,10 +848,22 @@ static void ethnl_notify_features(struct netdev_notifier_info *info) static int ethnl_netdev_event(struct notifier_block *this, unsigned long event, void *ptr) { + struct netdev_notifier_info *info = ptr; + struct netlink_ext_ack *extack; + struct net_device *dev; + + dev = netdev_notifier_info_to_dev(info); + extack = netdev_notifier_info_to_extack(info); + switch (event) { case NETDEV_FEAT_CHANGE: ethnl_notify_features(ptr); break; + case NETDEV_PRE_UP: + if (dev->ethtool->module_fw_flash_in_progress) { + NL_SET_ERR_MSG(extack, "Can't set port up while flashing module firmware"); + return NOTIFY_BAD; + } } return NOTIFY_DONE; @@ -1081,6 +1181,8 @@ static const struct genl_ops ethtool_genl_ops[] = { { .cmd = ETHTOOL_MSG_RSS_GET, .doit = ethnl_default_doit, + .start = ethnl_rss_dump_start, + .dumpit = ethnl_rss_dumpit, .policy = ethnl_rss_get_policy, .maxattr = ARRAY_SIZE(ethnl_rss_get_policy) - 1, }, @@ -1125,6 +1227,22 @@ static const struct genl_ops ethtool_genl_ops[] = { .policy = ethnl_mm_set_policy, .maxattr = ARRAY_SIZE(ethnl_mm_set_policy) - 1, }, + { + .cmd = ETHTOOL_MSG_MODULE_FW_FLASH_ACT, + .flags = GENL_UNS_ADMIN_PERM, + .doit = ethnl_act_module_fw_flash, + .policy = ethnl_module_fw_flash_act_policy, + .maxattr = ARRAY_SIZE(ethnl_module_fw_flash_act_policy) - 1, + }, + { + .cmd = ETHTOOL_MSG_PHY_GET, + .doit = ethnl_phy_doit, + .start = ethnl_phy_start, + .dumpit = ethnl_phy_dumpit, + .done = ethnl_phy_done, + .policy = ethnl_phy_get_policy, + .maxattr = ARRAY_SIZE(ethnl_phy_get_policy) - 1, + }, }; static const struct genl_multicast_group ethtool_nl_mcgrps[] = { @@ -1141,6 +1259,8 @@ static struct genl_family ethtool_genl_family __ro_after_init = { .resv_start_op = ETHTOOL_MSG_MODULE_GET + 1, .mcgrps = ethtool_nl_mcgrps, .n_mcgrps = ARRAY_SIZE(ethtool_nl_mcgrps), + .sock_priv_size = sizeof(struct ethnl_sock_priv), + .sock_priv_destroy = ethnl_sock_priv_destroy, }; /* module setup */ diff --git a/net/ethtool/netlink.h b/net/ethtool/netlink.h index 9a333a8d04c1..203b08eb6c6f 100644 --- a/net/ethtool/netlink.h +++ b/net/ethtool/netlink.h @@ -21,6 +21,7 @@ struct sk_buff *ethnl_reply_init(size_t payload, struct net_device *dev, u8 cmd, void **ehdrp); void *ethnl_dump_put(struct sk_buff *skb, struct netlink_callback *cb, u8 cmd); void *ethnl_bcastmsg_put(struct sk_buff *skb, u8 cmd); +void *ethnl_unicast_put(struct sk_buff *skb, u32 portid, u32 seq, u8 cmd); int ethnl_multicast(struct sk_buff *skb, struct net_device *dev); /** @@ -250,6 +251,9 @@ static inline unsigned int ethnl_reply_header_size(void) * @dev: network device the request is for (may be null) * @dev_tracker: refcount tracker for @dev reference * @flags: request flags common for all request types + * @phy_index: phy_device index connected to @dev this request is for. Can be + * 0 if the request doesn't target a phy, or if the @dev's attached + * phy is targeted. * * This is a common base for request specific structures holding data from * parsed userspace request. These always embed struct ethnl_req_info at @@ -259,6 +263,7 @@ struct ethnl_req_info { struct net_device *dev; netdevice_tracker dev_tracker; u32 flags; + u32 phy_index; }; static inline void ethnl_parse_header_dev_put(struct ethnl_req_info *req_info) @@ -267,6 +272,27 @@ static inline void ethnl_parse_header_dev_put(struct ethnl_req_info *req_info) } /** + * ethnl_req_get_phydev() - Gets the phy_device targeted by this request, + * if any. Must be called under rntl_lock(). + * @req_info: The ethnl request to get the phy from. + * @header: The netlink header, used for error reporting. + * @extack: The netlink extended ACK, for error reporting. + * + * The caller must hold RTNL, until it's done interacting with the returned + * phy_device. + * + * Return: A phy_device pointer corresponding either to the passed phy_index + * if one is provided. If not, the phy_device attached to the + * net_device targeted by this request is returned. If there's no + * targeted net_device, or no phy_device is attached, NULL is + * returned. If the provided phy_index is invalid, an error pointer + * is returned. + */ +struct phy_device *ethnl_req_get_phydev(const struct ethnl_req_info *req_info, + const struct nlattr *header, + struct netlink_ext_ack *extack); + +/** * struct ethnl_reply_data - base type of reply data for GET requests * @dev: device for current reply message; in single shot requests it is * equal to ðnl_req_info.dev; in dumps it's different for each @@ -283,6 +309,19 @@ struct ethnl_reply_data { int ethnl_ops_begin(struct net_device *dev); void ethnl_ops_complete(struct net_device *dev); +enum ethnl_sock_type { + ETHTOOL_SOCK_TYPE_MODULE_FW_FLASH, +}; + +struct ethnl_sock_priv { + struct net_device *dev; + u32 portid; + enum ethnl_sock_type type; +}; + +int ethnl_sock_priv_set(struct sk_buff *skb, struct net_device *dev, u32 portid, + enum ethnl_sock_type type); + /** * struct ethnl_request_ops - unified handling of GET and SET requests * @request_cmd: command id for request (GET) @@ -395,9 +434,12 @@ extern const struct ethnl_request_ops ethnl_rss_request_ops; extern const struct ethnl_request_ops ethnl_plca_cfg_request_ops; extern const struct ethnl_request_ops ethnl_plca_status_request_ops; extern const struct ethnl_request_ops ethnl_mm_request_ops; +extern const struct ethnl_request_ops ethnl_phy_request_ops; extern const struct nla_policy ethnl_header_policy[ETHTOOL_A_HEADER_FLAGS + 1]; extern const struct nla_policy ethnl_header_policy_stats[ETHTOOL_A_HEADER_FLAGS + 1]; +extern const struct nla_policy ethnl_header_policy_phy[ETHTOOL_A_HEADER_PHY_INDEX + 1]; +extern const struct nla_policy ethnl_header_policy_phy_stats[ETHTOOL_A_HEADER_PHY_INDEX + 1]; extern const struct nla_policy ethnl_strset_get_policy[ETHTOOL_A_STRSET_COUNTS_ONLY + 1]; extern const struct nla_policy ethnl_linkinfo_get_policy[ETHTOOL_A_LINKINFO_HEADER + 1]; extern const struct nla_policy ethnl_linkinfo_set_policy[ETHTOOL_A_LINKINFO_TP_MDIX_CTRL + 1]; @@ -435,12 +477,14 @@ extern const struct nla_policy ethnl_module_get_policy[ETHTOOL_A_MODULE_HEADER + extern const struct nla_policy ethnl_module_set_policy[ETHTOOL_A_MODULE_POWER_MODE_POLICY + 1]; extern const struct nla_policy ethnl_pse_get_policy[ETHTOOL_A_PSE_HEADER + 1]; extern const struct nla_policy ethnl_pse_set_policy[ETHTOOL_A_PSE_MAX + 1]; -extern const struct nla_policy ethnl_rss_get_policy[ETHTOOL_A_RSS_CONTEXT + 1]; +extern const struct nla_policy ethnl_rss_get_policy[ETHTOOL_A_RSS_START_CONTEXT + 1]; extern const struct nla_policy ethnl_plca_get_cfg_policy[ETHTOOL_A_PLCA_HEADER + 1]; extern const struct nla_policy ethnl_plca_set_cfg_policy[ETHTOOL_A_PLCA_MAX + 1]; extern const struct nla_policy ethnl_plca_get_status_policy[ETHTOOL_A_PLCA_HEADER + 1]; extern const struct nla_policy ethnl_mm_get_policy[ETHTOOL_A_MM_HEADER + 1]; extern const struct nla_policy ethnl_mm_set_policy[ETHTOOL_A_MM_MAX + 1]; +extern const struct nla_policy ethnl_module_fw_flash_act_policy[ETHTOOL_A_MODULE_FW_FLASH_PASSWORD + 1]; +extern const struct nla_policy ethnl_phy_get_policy[ETHTOOL_A_PHY_HEADER + 1]; int ethnl_set_features(struct sk_buff *skb, struct genl_info *info); int ethnl_act_cable_test(struct sk_buff *skb, struct genl_info *info); @@ -448,6 +492,13 @@ int ethnl_act_cable_test_tdr(struct sk_buff *skb, struct genl_info *info); int ethnl_tunnel_info_doit(struct sk_buff *skb, struct genl_info *info); int ethnl_tunnel_info_start(struct netlink_callback *cb); int ethnl_tunnel_info_dumpit(struct sk_buff *skb, struct netlink_callback *cb); +int ethnl_act_module_fw_flash(struct sk_buff *skb, struct genl_info *info); +int ethnl_rss_dump_start(struct netlink_callback *cb); +int ethnl_rss_dumpit(struct sk_buff *skb, struct netlink_callback *cb); +int ethnl_phy_start(struct netlink_callback *cb); +int ethnl_phy_doit(struct sk_buff *skb, struct genl_info *info); +int ethnl_phy_dumpit(struct sk_buff *skb, struct netlink_callback *cb); +int ethnl_phy_done(struct netlink_callback *cb); extern const char stats_std_names[__ETHTOOL_STATS_CNT][ETH_GSTRING_LEN]; extern const char stats_eth_phy_names[__ETHTOOL_A_STATS_ETH_PHY_CNT][ETH_GSTRING_LEN]; diff --git a/net/ethtool/phy.c b/net/ethtool/phy.c new file mode 100644 index 000000000000..ed8f690f6bac --- /dev/null +++ b/net/ethtool/phy.c @@ -0,0 +1,306 @@ +// SPDX-License-Identifier: GPL-2.0-only +/* + * Copyright 2023 Bootlin + * + */ +#include "common.h" +#include "netlink.h" + +#include <linux/phy.h> +#include <linux/phy_link_topology.h> +#include <linux/sfp.h> + +struct phy_req_info { + struct ethnl_req_info base; + struct phy_device_node *pdn; +}; + +#define PHY_REQINFO(__req_base) \ + container_of(__req_base, struct phy_req_info, base) + +const struct nla_policy ethnl_phy_get_policy[ETHTOOL_A_PHY_HEADER + 1] = { + [ETHTOOL_A_PHY_HEADER] = NLA_POLICY_NESTED(ethnl_header_policy), +}; + +/* Caller holds rtnl */ +static ssize_t +ethnl_phy_reply_size(const struct ethnl_req_info *req_base, + struct netlink_ext_ack *extack) +{ + struct phy_req_info *req_info = PHY_REQINFO(req_base); + struct phy_device_node *pdn = req_info->pdn; + struct phy_device *phydev = pdn->phy; + size_t size = 0; + + ASSERT_RTNL(); + + /* ETHTOOL_A_PHY_INDEX */ + size += nla_total_size(sizeof(u32)); + + /* ETHTOOL_A_DRVNAME */ + if (phydev->drv) + size += nla_total_size(strlen(phydev->drv->name) + 1); + + /* ETHTOOL_A_NAME */ + size += nla_total_size(strlen(dev_name(&phydev->mdio.dev)) + 1); + + /* ETHTOOL_A_PHY_UPSTREAM_TYPE */ + size += nla_total_size(sizeof(u32)); + + if (phy_on_sfp(phydev)) { + const char *upstream_sfp_name = sfp_get_name(pdn->parent_sfp_bus); + + /* ETHTOOL_A_PHY_UPSTREAM_SFP_NAME */ + if (upstream_sfp_name) + size += nla_total_size(strlen(upstream_sfp_name) + 1); + + /* ETHTOOL_A_PHY_UPSTREAM_INDEX */ + size += nla_total_size(sizeof(u32)); + } + + /* ETHTOOL_A_PHY_DOWNSTREAM_SFP_NAME */ + if (phydev->sfp_bus) { + const char *sfp_name = sfp_get_name(phydev->sfp_bus); + + if (sfp_name) + size += nla_total_size(strlen(sfp_name) + 1); + } + + return size; +} + +static int +ethnl_phy_fill_reply(const struct ethnl_req_info *req_base, struct sk_buff *skb) +{ + struct phy_req_info *req_info = PHY_REQINFO(req_base); + struct phy_device_node *pdn = req_info->pdn; + struct phy_device *phydev = pdn->phy; + enum phy_upstream ptype; + + ptype = pdn->upstream_type; + + if (nla_put_u32(skb, ETHTOOL_A_PHY_INDEX, phydev->phyindex) || + nla_put_string(skb, ETHTOOL_A_PHY_NAME, dev_name(&phydev->mdio.dev)) || + nla_put_u32(skb, ETHTOOL_A_PHY_UPSTREAM_TYPE, ptype)) + return -EMSGSIZE; + + if (phydev->drv && + nla_put_string(skb, ETHTOOL_A_PHY_DRVNAME, phydev->drv->name)) + return -EMSGSIZE; + + if (ptype == PHY_UPSTREAM_PHY) { + struct phy_device *upstream = pdn->upstream.phydev; + const char *sfp_upstream_name; + + /* Parent index */ + if (nla_put_u32(skb, ETHTOOL_A_PHY_UPSTREAM_INDEX, upstream->phyindex)) + return -EMSGSIZE; + + if (pdn->parent_sfp_bus) { + sfp_upstream_name = sfp_get_name(pdn->parent_sfp_bus); + if (sfp_upstream_name && + nla_put_string(skb, ETHTOOL_A_PHY_UPSTREAM_SFP_NAME, + sfp_upstream_name)) + return -EMSGSIZE; + } + } + + if (phydev->sfp_bus) { + const char *sfp_name = sfp_get_name(phydev->sfp_bus); + + if (sfp_name && + nla_put_string(skb, ETHTOOL_A_PHY_DOWNSTREAM_SFP_NAME, + sfp_name)) + return -EMSGSIZE; + } + + return 0; +} + +static int ethnl_phy_parse_request(struct ethnl_req_info *req_base, + struct nlattr **tb, + struct netlink_ext_ack *extack) +{ + struct phy_link_topology *topo = req_base->dev->link_topo; + struct phy_req_info *req_info = PHY_REQINFO(req_base); + struct phy_device *phydev; + + phydev = ethnl_req_get_phydev(req_base, tb[ETHTOOL_A_PHY_HEADER], + extack); + if (!phydev) + return 0; + + if (IS_ERR(phydev)) + return PTR_ERR(phydev); + + if (!topo) + return 0; + + req_info->pdn = xa_load(&topo->phys, phydev->phyindex); + + return 0; +} + +int ethnl_phy_doit(struct sk_buff *skb, struct genl_info *info) +{ + struct phy_req_info req_info = {}; + struct nlattr **tb = info->attrs; + struct sk_buff *rskb; + void *reply_payload; + int reply_len; + int ret; + + ret = ethnl_parse_header_dev_get(&req_info.base, + tb[ETHTOOL_A_PHY_HEADER], + genl_info_net(info), info->extack, + true); + if (ret < 0) + return ret; + + rtnl_lock(); + + ret = ethnl_phy_parse_request(&req_info.base, tb, info->extack); + if (ret < 0) + goto err_unlock_rtnl; + + /* No PHY, return early */ + if (!req_info.pdn) + goto err_unlock_rtnl; + + ret = ethnl_phy_reply_size(&req_info.base, info->extack); + if (ret < 0) + goto err_unlock_rtnl; + reply_len = ret + ethnl_reply_header_size(); + + rskb = ethnl_reply_init(reply_len, req_info.base.dev, + ETHTOOL_MSG_PHY_GET_REPLY, + ETHTOOL_A_PHY_HEADER, + info, &reply_payload); + if (!rskb) { + ret = -ENOMEM; + goto err_unlock_rtnl; + } + + ret = ethnl_phy_fill_reply(&req_info.base, rskb); + if (ret) + goto err_free_msg; + + rtnl_unlock(); + ethnl_parse_header_dev_put(&req_info.base); + genlmsg_end(rskb, reply_payload); + + return genlmsg_reply(rskb, info); + +err_free_msg: + nlmsg_free(rskb); +err_unlock_rtnl: + rtnl_unlock(); + ethnl_parse_header_dev_put(&req_info.base); + return ret; +} + +struct ethnl_phy_dump_ctx { + struct phy_req_info *phy_req_info; + unsigned long ifindex; + unsigned long phy_index; +}; + +int ethnl_phy_start(struct netlink_callback *cb) +{ + const struct genl_info *info = genl_info_dump(cb); + struct ethnl_phy_dump_ctx *ctx = (void *)cb->ctx; + int ret; + + BUILD_BUG_ON(sizeof(*ctx) > sizeof(cb->ctx)); + + ctx->phy_req_info = kzalloc(sizeof(*ctx->phy_req_info), GFP_KERNEL); + if (!ctx->phy_req_info) + return -ENOMEM; + + ret = ethnl_parse_header_dev_get(&ctx->phy_req_info->base, + info->attrs[ETHTOOL_A_PHY_HEADER], + sock_net(cb->skb->sk), cb->extack, + false); + ctx->ifindex = 0; + ctx->phy_index = 0; + + if (ret) + kfree(ctx->phy_req_info); + + return ret; +} + +int ethnl_phy_done(struct netlink_callback *cb) +{ + struct ethnl_phy_dump_ctx *ctx = (void *)cb->ctx; + + if (ctx->phy_req_info->base.dev) + ethnl_parse_header_dev_put(&ctx->phy_req_info->base); + + kfree(ctx->phy_req_info); + + return 0; +} + +static int ethnl_phy_dump_one_dev(struct sk_buff *skb, struct net_device *dev, + struct netlink_callback *cb) +{ + struct ethnl_phy_dump_ctx *ctx = (void *)cb->ctx; + struct phy_req_info *pri = ctx->phy_req_info; + struct phy_device_node *pdn; + int ret = 0; + void *ehdr; + + if (!dev->link_topo) + return 0; + + xa_for_each_start(&dev->link_topo->phys, ctx->phy_index, pdn, ctx->phy_index) { + ehdr = ethnl_dump_put(skb, cb, ETHTOOL_MSG_PHY_GET_REPLY); + if (!ehdr) { + ret = -EMSGSIZE; + break; + } + + ret = ethnl_fill_reply_header(skb, dev, ETHTOOL_A_PHY_HEADER); + if (ret < 0) { + genlmsg_cancel(skb, ehdr); + break; + } + + pri->pdn = pdn; + ret = ethnl_phy_fill_reply(&pri->base, skb); + if (ret < 0) { + genlmsg_cancel(skb, ehdr); + break; + } + + genlmsg_end(skb, ehdr); + } + + return ret; +} + +int ethnl_phy_dumpit(struct sk_buff *skb, struct netlink_callback *cb) +{ + struct ethnl_phy_dump_ctx *ctx = (void *)cb->ctx; + struct net *net = sock_net(skb->sk); + struct net_device *dev; + int ret = 0; + + rtnl_lock(); + + if (ctx->phy_req_info->base.dev) { + ret = ethnl_phy_dump_one_dev(skb, ctx->phy_req_info->base.dev, cb); + } else { + for_each_netdev_dump(net, dev, ctx->ifindex) { + ret = ethnl_phy_dump_one_dev(skb, dev, cb); + if (ret) + break; + + ctx->phy_index = 0; + } + } + rtnl_unlock(); + + return ret; +} diff --git a/net/ethtool/plca.c b/net/ethtool/plca.c index b1e2e3b5027f..d95d92f173a6 100644 --- a/net/ethtool/plca.c +++ b/net/ethtool/plca.c @@ -25,7 +25,7 @@ struct plca_reply_data { const struct nla_policy ethnl_plca_get_cfg_policy[] = { [ETHTOOL_A_PLCA_HEADER] = - NLA_POLICY_NESTED(ethnl_header_policy), + NLA_POLICY_NESTED(ethnl_header_policy_phy), }; static void plca_update_sint(int *dst, struct nlattr **tb, u32 attrid, @@ -58,10 +58,14 @@ static int plca_get_cfg_prepare_data(const struct ethnl_req_info *req_base, struct plca_reply_data *data = PLCA_REPDATA(reply_base); struct net_device *dev = reply_base->dev; const struct ethtool_phy_ops *ops; + struct nlattr **tb = info->attrs; + struct phy_device *phydev; int ret; + phydev = ethnl_req_get_phydev(req_base, tb[ETHTOOL_A_PLCA_HEADER], + info->extack); // check that the PHY device is available and connected - if (!dev->phydev) { + if (IS_ERR_OR_NULL(phydev)) { ret = -EOPNOTSUPP; goto out; } @@ -80,7 +84,7 @@ static int plca_get_cfg_prepare_data(const struct ethnl_req_info *req_base, memset(&data->plca_cfg, 0xff, sizeof_field(struct plca_reply_data, plca_cfg)); - ret = ops->get_plca_cfg(dev->phydev, &data->plca_cfg); + ret = ops->get_plca_cfg(phydev, &data->plca_cfg); ethnl_ops_complete(dev); out: @@ -129,7 +133,7 @@ static int plca_get_cfg_fill_reply(struct sk_buff *skb, const struct nla_policy ethnl_plca_set_cfg_policy[] = { [ETHTOOL_A_PLCA_HEADER] = - NLA_POLICY_NESTED(ethnl_header_policy), + NLA_POLICY_NESTED(ethnl_header_policy_phy), [ETHTOOL_A_PLCA_ENABLED] = NLA_POLICY_MAX(NLA_U8, 1), [ETHTOOL_A_PLCA_NODE_ID] = NLA_POLICY_MAX(NLA_U32, 255), [ETHTOOL_A_PLCA_NODE_CNT] = NLA_POLICY_RANGE(NLA_U32, 1, 255), @@ -141,15 +145,17 @@ const struct nla_policy ethnl_plca_set_cfg_policy[] = { static int ethnl_set_plca(struct ethnl_req_info *req_info, struct genl_info *info) { - struct net_device *dev = req_info->dev; const struct ethtool_phy_ops *ops; struct nlattr **tb = info->attrs; struct phy_plca_cfg plca_cfg; + struct phy_device *phydev; bool mod = false; int ret; + phydev = ethnl_req_get_phydev(req_info, tb[ETHTOOL_A_PLCA_HEADER], + info->extack); // check that the PHY device is available and connected - if (!dev->phydev) + if (IS_ERR_OR_NULL(phydev)) return -EOPNOTSUPP; ops = ethtool_phy_ops; @@ -168,7 +174,7 @@ ethnl_set_plca(struct ethnl_req_info *req_info, struct genl_info *info) if (!mod) return 0; - ret = ops->set_plca_cfg(dev->phydev, &plca_cfg, info->extack); + ret = ops->set_plca_cfg(phydev, &plca_cfg, info->extack); return ret < 0 ? ret : 1; } @@ -191,7 +197,7 @@ const struct ethnl_request_ops ethnl_plca_cfg_request_ops = { const struct nla_policy ethnl_plca_get_status_policy[] = { [ETHTOOL_A_PLCA_HEADER] = - NLA_POLICY_NESTED(ethnl_header_policy), + NLA_POLICY_NESTED(ethnl_header_policy_phy), }; static int plca_get_status_prepare_data(const struct ethnl_req_info *req_base, @@ -201,10 +207,14 @@ static int plca_get_status_prepare_data(const struct ethnl_req_info *req_base, struct plca_reply_data *data = PLCA_REPDATA(reply_base); struct net_device *dev = reply_base->dev; const struct ethtool_phy_ops *ops; + struct nlattr **tb = info->attrs; + struct phy_device *phydev; int ret; + phydev = ethnl_req_get_phydev(req_base, tb[ETHTOOL_A_PLCA_HEADER], + info->extack); // check that the PHY device is available and connected - if (!dev->phydev) { + if (IS_ERR_OR_NULL(phydev)) { ret = -EOPNOTSUPP; goto out; } @@ -223,7 +233,7 @@ static int plca_get_status_prepare_data(const struct ethnl_req_info *req_base, memset(&data->plca_st, 0xff, sizeof_field(struct plca_reply_data, plca_st)); - ret = ops->get_plca_status(dev->phydev, &data->plca_st); + ret = ops->get_plca_status(phydev, &data->plca_st); ethnl_ops_complete(dev); out: return ret; diff --git a/net/ethtool/pse-pd.c b/net/ethtool/pse-pd.c index 2c981d443f27..a0705edca22a 100644 --- a/net/ethtool/pse-pd.c +++ b/net/ethtool/pse-pd.c @@ -28,17 +28,15 @@ struct pse_reply_data { /* PSE_GET */ const struct nla_policy ethnl_pse_get_policy[ETHTOOL_A_PSE_HEADER + 1] = { - [ETHTOOL_A_PSE_HEADER] = NLA_POLICY_NESTED(ethnl_header_policy), + [ETHTOOL_A_PSE_HEADER] = NLA_POLICY_NESTED(ethnl_header_policy_phy), }; -static int pse_get_pse_attributes(struct net_device *dev, +static int pse_get_pse_attributes(struct phy_device *phydev, struct netlink_ext_ack *extack, struct pse_reply_data *data) { - struct phy_device *phydev = dev->phydev; - if (!phydev) { - NL_SET_ERR_MSG(extack, "No PHY is attached"); + NL_SET_ERR_MSG(extack, "No PHY found"); return -EOPNOTSUPP; } @@ -58,13 +56,20 @@ static int pse_prepare_data(const struct ethnl_req_info *req_base, { struct pse_reply_data *data = PSE_REPDATA(reply_base); struct net_device *dev = reply_base->dev; + struct nlattr **tb = info->attrs; + struct phy_device *phydev; int ret; ret = ethnl_ops_begin(dev); if (ret < 0) return ret; - ret = pse_get_pse_attributes(dev, info->extack, data); + phydev = ethnl_req_get_phydev(req_base, tb[ETHTOOL_A_PSE_HEADER], + info->extack); + if (IS_ERR(phydev)) + return -ENODEV; + + ret = pse_get_pse_attributes(phydev, info->extack, data); ethnl_ops_complete(dev); @@ -86,10 +91,56 @@ static int pse_reply_size(const struct ethnl_req_info *req_base, len += nla_total_size(sizeof(u32)); /* _C33_PSE_ADMIN_STATE */ if (st->c33_pw_status > 0) len += nla_total_size(sizeof(u32)); /* _C33_PSE_PW_D_STATUS */ + if (st->c33_pw_class > 0) + len += nla_total_size(sizeof(u32)); /* _C33_PSE_PW_CLASS */ + if (st->c33_actual_pw > 0) + len += nla_total_size(sizeof(u32)); /* _C33_PSE_ACTUAL_PW */ + if (st->c33_ext_state_info.c33_pse_ext_state > 0) { + len += nla_total_size(sizeof(u32)); /* _C33_PSE_EXT_STATE */ + if (st->c33_ext_state_info.__c33_pse_ext_substate > 0) + /* _C33_PSE_EXT_SUBSTATE */ + len += nla_total_size(sizeof(u32)); + } + if (st->c33_avail_pw_limit > 0) + /* _C33_AVAIL_PSE_PW_LIMIT */ + len += nla_total_size(sizeof(u32)); + if (st->c33_pw_limit_nb_ranges > 0) + /* _C33_PSE_PW_LIMIT_RANGES */ + len += st->c33_pw_limit_nb_ranges * + (nla_total_size(0) + + nla_total_size(sizeof(u32)) * 2); return len; } +static int pse_put_pw_limit_ranges(struct sk_buff *skb, + const struct pse_control_status *st) +{ + const struct ethtool_c33_pse_pw_limit_range *pw_limit_ranges; + int i; + + pw_limit_ranges = st->c33_pw_limit_ranges; + for (i = 0; i < st->c33_pw_limit_nb_ranges; i++) { + struct nlattr *nest; + + nest = nla_nest_start(skb, ETHTOOL_A_C33_PSE_PW_LIMIT_RANGES); + if (!nest) + return -EMSGSIZE; + + if (nla_put_u32(skb, ETHTOOL_A_C33_PSE_PW_LIMIT_MIN, + pw_limit_ranges->min) || + nla_put_u32(skb, ETHTOOL_A_C33_PSE_PW_LIMIT_MAX, + pw_limit_ranges->max)) { + nla_nest_cancel(skb, nest); + return -EMSGSIZE; + } + nla_nest_end(skb, nest); + pw_limit_ranges++; + } + + return 0; +} + static int pse_fill_reply(struct sk_buff *skb, const struct ethnl_req_info *req_base, const struct ethnl_reply_data *reply_base) @@ -117,30 +168,65 @@ static int pse_fill_reply(struct sk_buff *skb, st->c33_pw_status)) return -EMSGSIZE; + if (st->c33_pw_class > 0 && + nla_put_u32(skb, ETHTOOL_A_C33_PSE_PW_CLASS, + st->c33_pw_class)) + return -EMSGSIZE; + + if (st->c33_actual_pw > 0 && + nla_put_u32(skb, ETHTOOL_A_C33_PSE_ACTUAL_PW, + st->c33_actual_pw)) + return -EMSGSIZE; + + if (st->c33_ext_state_info.c33_pse_ext_state > 0) { + if (nla_put_u32(skb, ETHTOOL_A_C33_PSE_EXT_STATE, + st->c33_ext_state_info.c33_pse_ext_state)) + return -EMSGSIZE; + + if (st->c33_ext_state_info.__c33_pse_ext_substate > 0 && + nla_put_u32(skb, ETHTOOL_A_C33_PSE_EXT_SUBSTATE, + st->c33_ext_state_info.__c33_pse_ext_substate)) + return -EMSGSIZE; + } + + if (st->c33_avail_pw_limit > 0 && + nla_put_u32(skb, ETHTOOL_A_C33_PSE_AVAIL_PW_LIMIT, + st->c33_avail_pw_limit)) + return -EMSGSIZE; + + if (st->c33_pw_limit_nb_ranges > 0 && + pse_put_pw_limit_ranges(skb, st)) + return -EMSGSIZE; + return 0; } +static void pse_cleanup_data(struct ethnl_reply_data *reply_base) +{ + const struct pse_reply_data *data = PSE_REPDATA(reply_base); + + kfree(data->status.c33_pw_limit_ranges); +} + /* PSE_SET */ const struct nla_policy ethnl_pse_set_policy[ETHTOOL_A_PSE_MAX + 1] = { - [ETHTOOL_A_PSE_HEADER] = NLA_POLICY_NESTED(ethnl_header_policy), + [ETHTOOL_A_PSE_HEADER] = NLA_POLICY_NESTED(ethnl_header_policy_phy), [ETHTOOL_A_PODL_PSE_ADMIN_CONTROL] = NLA_POLICY_RANGE(NLA_U32, ETHTOOL_PODL_PSE_ADMIN_STATE_DISABLED, ETHTOOL_PODL_PSE_ADMIN_STATE_ENABLED), [ETHTOOL_A_C33_PSE_ADMIN_CONTROL] = NLA_POLICY_RANGE(NLA_U32, ETHTOOL_C33_PSE_ADMIN_STATE_DISABLED, ETHTOOL_C33_PSE_ADMIN_STATE_ENABLED), + [ETHTOOL_A_C33_PSE_AVAIL_PW_LIMIT] = { .type = NLA_U32 }, }; static int -ethnl_set_pse_validate(struct ethnl_req_info *req_info, struct genl_info *info) +ethnl_set_pse_validate(struct phy_device *phydev, struct genl_info *info) { - struct net_device *dev = req_info->dev; struct nlattr **tb = info->attrs; - struct phy_device *phydev; - phydev = dev->phydev; - if (!phydev) { + if (IS_ERR_OR_NULL(phydev)) { NL_SET_ERR_MSG(info->extack, "No PHY is attached"); return -EOPNOTSUPP; } @@ -165,26 +251,53 @@ ethnl_set_pse_validate(struct ethnl_req_info *req_info, struct genl_info *info) return -EOPNOTSUPP; } - return 1; + return 0; } static int ethnl_set_pse(struct ethnl_req_info *req_info, struct genl_info *info) { - struct net_device *dev = req_info->dev; - struct pse_control_config config = {}; struct nlattr **tb = info->attrs; struct phy_device *phydev; + int ret; + + phydev = ethnl_req_get_phydev(req_info, tb[ETHTOOL_A_PSE_HEADER], + info->extack); + ret = ethnl_set_pse_validate(phydev, info); + if (ret) + return ret; + + if (tb[ETHTOOL_A_C33_PSE_AVAIL_PW_LIMIT]) { + unsigned int pw_limit; + + pw_limit = nla_get_u32(tb[ETHTOOL_A_C33_PSE_AVAIL_PW_LIMIT]); + ret = pse_ethtool_set_pw_limit(phydev->psec, info->extack, + pw_limit); + if (ret) + return ret; + } - phydev = dev->phydev; /* These values are already validated by the ethnl_pse_set_policy */ - if (pse_has_podl(phydev->psec)) - config.podl_admin_control = nla_get_u32(tb[ETHTOOL_A_PODL_PSE_ADMIN_CONTROL]); - if (pse_has_c33(phydev->psec)) - config.c33_admin_control = nla_get_u32(tb[ETHTOOL_A_C33_PSE_ADMIN_CONTROL]); + if (tb[ETHTOOL_A_PODL_PSE_ADMIN_CONTROL] || + tb[ETHTOOL_A_C33_PSE_ADMIN_CONTROL]) { + struct pse_control_config config = {}; + + if (tb[ETHTOOL_A_PODL_PSE_ADMIN_CONTROL]) + config.podl_admin_control = nla_get_u32(tb[ETHTOOL_A_PODL_PSE_ADMIN_CONTROL]); + if (tb[ETHTOOL_A_C33_PSE_ADMIN_CONTROL]) + config.c33_admin_control = nla_get_u32(tb[ETHTOOL_A_C33_PSE_ADMIN_CONTROL]); + + /* pse_ethtool_set_config() will do nothing if the config + * is zero + */ + ret = pse_ethtool_set_config(phydev->psec, info->extack, + &config); + if (ret) + return ret; + } - /* Return errno directly - PSE has no notification */ - return pse_ethtool_set_config(phydev->psec, info->extack, &config); + /* Return errno or zero - PSE has no notification */ + return ret; } const struct ethnl_request_ops ethnl_pse_request_ops = { @@ -197,8 +310,8 @@ const struct ethnl_request_ops ethnl_pse_request_ops = { .prepare_data = pse_prepare_data, .reply_size = pse_reply_size, .fill_reply = pse_fill_reply, + .cleanup_data = pse_cleanup_data, - .set_validate = ethnl_set_pse_validate, .set = ethnl_set_pse, /* PSE has no notification */ }; diff --git a/net/ethtool/rss.c b/net/ethtool/rss.c index 71679137eff2..e07386275e14 100644 --- a/net/ethtool/rss.c +++ b/net/ethtool/rss.c @@ -10,6 +10,7 @@ struct rss_req_info { struct rss_reply_data { struct ethnl_reply_data base; + bool no_key_fields; u32 indir_size; u32 hkey_size; u32 hfunc; @@ -27,6 +28,7 @@ struct rss_reply_data { const struct nla_policy ethnl_rss_get_policy[] = { [ETHTOOL_A_RSS_HEADER] = NLA_POLICY_NESTED(ethnl_header_policy), [ETHTOOL_A_RSS_CONTEXT] = { .type = NLA_U32 }, + [ETHTOOL_A_RSS_START_CONTEXT] = { .type = NLA_U32 }, }; static int @@ -37,18 +39,18 @@ rss_parse_request(struct ethnl_req_info *req_info, struct nlattr **tb, if (tb[ETHTOOL_A_RSS_CONTEXT]) request->rss_context = nla_get_u32(tb[ETHTOOL_A_RSS_CONTEXT]); + if (tb[ETHTOOL_A_RSS_START_CONTEXT]) { + NL_SET_BAD_ATTR(extack, tb[ETHTOOL_A_RSS_START_CONTEXT]); + return -EINVAL; + } return 0; } static int -rss_prepare_data(const struct ethnl_req_info *req_base, - struct ethnl_reply_data *reply_base, - const struct genl_info *info) +rss_prepare_get(const struct rss_req_info *request, struct net_device *dev, + struct rss_reply_data *data, const struct genl_info *info) { - struct rss_reply_data *data = RSS_REPDATA(reply_base); - struct rss_req_info *request = RSS_REQINFO(req_base); - struct net_device *dev = reply_base->dev; struct ethtool_rxfh_param rxfh = {}; const struct ethtool_ops *ops; u32 total_size, indir_bytes; @@ -56,12 +58,6 @@ rss_prepare_data(const struct ethnl_req_info *req_base, int ret; ops = dev->ethtool_ops; - if (!ops->get_rxfh) - return -EOPNOTSUPP; - - /* Some drivers don't handle rss_context */ - if (request->rss_context && !ops->cap_rss_ctx_supported) - return -EOPNOTSUPP; ret = ethnl_ops_begin(dev); if (ret < 0) @@ -91,7 +87,6 @@ rss_prepare_data(const struct ethnl_req_info *req_base, rxfh.indir = data->indir_table; rxfh.key_size = data->hkey_size; rxfh.key = data->hkey; - rxfh.rss_context = request->rss_context; ret = ops->get_rxfh(dev, &rxfh); if (ret) @@ -105,13 +100,75 @@ out_ops: } static int +rss_prepare_ctx(const struct rss_req_info *request, struct net_device *dev, + struct rss_reply_data *data, const struct genl_info *info) +{ + struct ethtool_rxfh_context *ctx; + u32 total_size, indir_bytes; + u8 *rss_config; + + ctx = xa_load(&dev->ethtool->rss_ctx, request->rss_context); + if (!ctx) + return -ENOENT; + + data->indir_size = ctx->indir_size; + data->hkey_size = ctx->key_size; + data->hfunc = ctx->hfunc; + data->input_xfrm = ctx->input_xfrm; + + indir_bytes = data->indir_size * sizeof(u32); + total_size = indir_bytes + data->hkey_size; + rss_config = kzalloc(total_size, GFP_KERNEL); + if (!rss_config) + return -ENOMEM; + + data->indir_table = (u32 *)rss_config; + memcpy(data->indir_table, ethtool_rxfh_context_indir(ctx), indir_bytes); + + if (data->hkey_size) { + data->hkey = rss_config + indir_bytes; + memcpy(data->hkey, ethtool_rxfh_context_key(ctx), + data->hkey_size); + } + + return 0; +} + +static int +rss_prepare_data(const struct ethnl_req_info *req_base, + struct ethnl_reply_data *reply_base, + const struct genl_info *info) +{ + struct rss_reply_data *data = RSS_REPDATA(reply_base); + struct rss_req_info *request = RSS_REQINFO(req_base); + struct net_device *dev = reply_base->dev; + const struct ethtool_ops *ops; + + ops = dev->ethtool_ops; + if (!ops->get_rxfh) + return -EOPNOTSUPP; + + /* Some drivers don't handle rss_context */ + if (request->rss_context) { + if (!ops->cap_rss_ctx_supported && !ops->create_rxfh_context) + return -EOPNOTSUPP; + + data->no_key_fields = !ops->rxfh_per_ctx_key; + return rss_prepare_ctx(request, dev, data, info); + } + + return rss_prepare_get(request, dev, data, info); +} + +static int rss_reply_size(const struct ethnl_req_info *req_base, const struct ethnl_reply_data *reply_base) { const struct rss_reply_data *data = RSS_REPDATA(reply_base); int len; - len = nla_total_size(sizeof(u32)) + /* _RSS_HFUNC */ + len = nla_total_size(sizeof(u32)) + /* _RSS_CONTEXT */ + nla_total_size(sizeof(u32)) + /* _RSS_HFUNC */ nla_total_size(sizeof(u32)) + /* _RSS_INPUT_XFRM */ nla_total_size(sizeof(u32) * data->indir_size) + /* _RSS_INDIR */ nla_total_size(data->hkey_size); /* _RSS_HKEY */ @@ -124,14 +181,24 @@ rss_fill_reply(struct sk_buff *skb, const struct ethnl_req_info *req_base, const struct ethnl_reply_data *reply_base) { const struct rss_reply_data *data = RSS_REPDATA(reply_base); + struct rss_req_info *request = RSS_REQINFO(req_base); + + if (request->rss_context && + nla_put_u32(skb, ETHTOOL_A_RSS_CONTEXT, request->rss_context)) + return -EMSGSIZE; + + if ((data->indir_size && + nla_put(skb, ETHTOOL_A_RSS_INDIR, + sizeof(u32) * data->indir_size, data->indir_table))) + return -EMSGSIZE; + + if (data->no_key_fields) + return 0; if ((data->hfunc && nla_put_u32(skb, ETHTOOL_A_RSS_HFUNC, data->hfunc)) || (data->input_xfrm && nla_put_u32(skb, ETHTOOL_A_RSS_INPUT_XFRM, data->input_xfrm)) || - (data->indir_size && - nla_put(skb, ETHTOOL_A_RSS_INDIR, - sizeof(u32) * data->indir_size, data->indir_table)) || (data->hkey_size && nla_put(skb, ETHTOOL_A_RSS_HKEY, data->hkey_size, data->hkey))) return -EMSGSIZE; @@ -146,6 +213,146 @@ static void rss_cleanup_data(struct ethnl_reply_data *reply_base) kfree(data->indir_table); } +struct rss_nl_dump_ctx { + unsigned long ifindex; + unsigned long ctx_idx; + + /* User wants to only dump contexts from given ifindex */ + unsigned int match_ifindex; + unsigned int start_ctx; +}; + +static struct rss_nl_dump_ctx *rss_dump_ctx(struct netlink_callback *cb) +{ + NL_ASSERT_DUMP_CTX_FITS(struct rss_nl_dump_ctx); + + return (struct rss_nl_dump_ctx *)cb->ctx; +} + +int ethnl_rss_dump_start(struct netlink_callback *cb) +{ + const struct genl_info *info = genl_info_dump(cb); + struct rss_nl_dump_ctx *ctx = rss_dump_ctx(cb); + struct ethnl_req_info req_info = {}; + struct nlattr **tb = info->attrs; + int ret; + + /* Filtering by context not supported */ + if (tb[ETHTOOL_A_RSS_CONTEXT]) { + NL_SET_BAD_ATTR(info->extack, tb[ETHTOOL_A_RSS_CONTEXT]); + return -EINVAL; + } + if (tb[ETHTOOL_A_RSS_START_CONTEXT]) { + ctx->start_ctx = nla_get_u32(tb[ETHTOOL_A_RSS_START_CONTEXT]); + ctx->ctx_idx = ctx->start_ctx; + } + + ret = ethnl_parse_header_dev_get(&req_info, + tb[ETHTOOL_A_RSS_HEADER], + sock_net(cb->skb->sk), cb->extack, + false); + if (req_info.dev) { + ctx->match_ifindex = req_info.dev->ifindex; + ctx->ifindex = ctx->match_ifindex; + ethnl_parse_header_dev_put(&req_info); + req_info.dev = NULL; + } + + return ret; +} + +static int +rss_dump_one_ctx(struct sk_buff *skb, struct netlink_callback *cb, + struct net_device *dev, u32 rss_context) +{ + const struct genl_info *info = genl_info_dump(cb); + struct rss_reply_data data = {}; + struct rss_req_info req = {}; + void *ehdr; + int ret; + + req.rss_context = rss_context; + + ehdr = ethnl_dump_put(skb, cb, ETHTOOL_MSG_RSS_GET_REPLY); + if (!ehdr) + return -EMSGSIZE; + + ret = ethnl_fill_reply_header(skb, dev, ETHTOOL_A_RSS_HEADER); + if (ret < 0) + goto err_cancel; + + /* Context 0 is not currently storred or cached in the XArray */ + if (!rss_context) + ret = rss_prepare_get(&req, dev, &data, info); + else + ret = rss_prepare_ctx(&req, dev, &data, info); + if (ret) + goto err_cancel; + + ret = rss_fill_reply(skb, &req.base, &data.base); + if (ret) + goto err_cleanup; + genlmsg_end(skb, ehdr); + + rss_cleanup_data(&data.base); + return 0; + +err_cleanup: + rss_cleanup_data(&data.base); +err_cancel: + genlmsg_cancel(skb, ehdr); + return ret; +} + +static int +rss_dump_one_dev(struct sk_buff *skb, struct netlink_callback *cb, + struct net_device *dev) +{ + struct rss_nl_dump_ctx *ctx = rss_dump_ctx(cb); + int ret; + + if (!dev->ethtool_ops->get_rxfh) + return 0; + + if (!ctx->ctx_idx) { + ret = rss_dump_one_ctx(skb, cb, dev, 0); + if (ret) + return ret; + ctx->ctx_idx++; + } + + for (; xa_find(&dev->ethtool->rss_ctx, &ctx->ctx_idx, + ULONG_MAX, XA_PRESENT); ctx->ctx_idx++) { + ret = rss_dump_one_ctx(skb, cb, dev, ctx->ctx_idx); + if (ret) + return ret; + } + ctx->ctx_idx = ctx->start_ctx; + + return 0; +} + +int ethnl_rss_dumpit(struct sk_buff *skb, struct netlink_callback *cb) +{ + struct rss_nl_dump_ctx *ctx = rss_dump_ctx(cb); + struct net *net = sock_net(skb->sk); + struct net_device *dev; + int ret = 0; + + rtnl_lock(); + for_each_netdev_dump(net, dev, ctx->ifindex) { + if (ctx->match_ifindex && ctx->match_ifindex != ctx->ifindex) + break; + + ret = rss_dump_one_dev(skb, cb, dev); + if (ret) + break; + } + rtnl_unlock(); + + return ret; +} + const struct ethnl_request_ops ethnl_rss_request_ops = { .request_cmd = ETHTOOL_MSG_RSS_GET, .reply_cmd = ETHTOOL_MSG_RSS_GET_REPLY, diff --git a/net/ethtool/strset.c b/net/ethtool/strset.c index c678b484a079..b3382b3cf325 100644 --- a/net/ethtool/strset.c +++ b/net/ethtool/strset.c @@ -126,7 +126,7 @@ struct strset_reply_data { const struct nla_policy ethnl_strset_get_policy[] = { [ETHTOOL_A_STRSET_HEADER] = - NLA_POLICY_NESTED(ethnl_header_policy), + NLA_POLICY_NESTED(ethnl_header_policy_phy), [ETHTOOL_A_STRSET_STRINGSETS] = { .type = NLA_NESTED }, [ETHTOOL_A_STRSET_COUNTS_ONLY] = { .type = NLA_FLAG }, }; @@ -233,17 +233,18 @@ static void strset_cleanup_data(struct ethnl_reply_data *reply_base) } static int strset_prepare_set(struct strset_info *info, struct net_device *dev, - unsigned int id, bool counts_only) + struct phy_device *phydev, unsigned int id, + bool counts_only) { const struct ethtool_phy_ops *phy_ops = ethtool_phy_ops; const struct ethtool_ops *ops = dev->ethtool_ops; void *strings; int count, ret; - if (id == ETH_SS_PHY_STATS && dev->phydev && + if (id == ETH_SS_PHY_STATS && phydev && !ops->get_ethtool_phy_stats && phy_ops && phy_ops->get_sset_count) - ret = phy_ops->get_sset_count(dev->phydev); + ret = phy_ops->get_sset_count(phydev); else if (ops->get_sset_count && ops->get_strings) ret = ops->get_sset_count(dev, id); else @@ -258,10 +259,10 @@ static int strset_prepare_set(struct strset_info *info, struct net_device *dev, strings = kcalloc(count, ETH_GSTRING_LEN, GFP_KERNEL); if (!strings) return -ENOMEM; - if (id == ETH_SS_PHY_STATS && dev->phydev && + if (id == ETH_SS_PHY_STATS && phydev && !ops->get_ethtool_phy_stats && phy_ops && phy_ops->get_strings) - phy_ops->get_strings(dev->phydev, strings); + phy_ops->get_strings(phydev, strings); else ops->get_strings(dev, id, strings); info->strings = strings; @@ -279,6 +280,8 @@ static int strset_prepare_data(const struct ethnl_req_info *req_base, const struct strset_req_info *req_info = STRSET_REQINFO(req_base); struct strset_reply_data *data = STRSET_REPDATA(reply_base); struct net_device *dev = reply_base->dev; + struct nlattr **tb = info->attrs; + struct phy_device *phydev; unsigned int i; int ret; @@ -289,14 +292,20 @@ static int strset_prepare_data(const struct ethnl_req_info *req_base, for (i = 0; i < ETH_SS_COUNT; i++) { if ((req_info->req_ids & (1U << i)) && data->sets[i].per_dev) { - if (info) - GENL_SET_ERR_MSG(info, "requested per device strings without dev"); + GENL_SET_ERR_MSG(info, "requested per device strings without dev"); return -EINVAL; } } return 0; } + phydev = ethnl_req_get_phydev(req_base, tb[ETHTOOL_A_HEADER_FLAGS], + info->extack); + + /* phydev can be NULL, check for errors only */ + if (IS_ERR(phydev)) + return PTR_ERR(phydev); + ret = ethnl_ops_begin(dev); if (ret < 0) goto err_strset; @@ -305,7 +314,7 @@ static int strset_prepare_data(const struct ethnl_req_info *req_base, !data->sets[i].per_dev) continue; - ret = strset_prepare_set(&data->sets[i], dev, i, + ret = strset_prepare_set(&data->sets[i], dev, phydev, i, req_info->counts_only); if (ret < 0) goto err_ops; diff --git a/net/ethtool/tsinfo.c b/net/ethtool/tsinfo.c index 57d496287e52..03d12d6f79ca 100644 --- a/net/ethtool/tsinfo.c +++ b/net/ethtool/tsinfo.c @@ -12,7 +12,7 @@ struct tsinfo_req_info { struct tsinfo_reply_data { struct ethnl_reply_data base; - struct ethtool_ts_info ts_info; + struct kernel_ethtool_ts_info ts_info; struct ethtool_ts_stats stats; }; @@ -55,7 +55,7 @@ static int tsinfo_reply_size(const struct ethnl_req_info *req_base, { const struct tsinfo_reply_data *data = TSINFO_REPDATA(reply_base); bool compact = req_base->flags & ETHTOOL_FLAG_COMPACT_BITSETS; - const struct ethtool_ts_info *ts_info = &data->ts_info; + const struct kernel_ethtool_ts_info *ts_info = &data->ts_info; int len = 0; int ret; @@ -136,7 +136,7 @@ static int tsinfo_fill_reply(struct sk_buff *skb, { const struct tsinfo_reply_data *data = TSINFO_REPDATA(reply_base); bool compact = req_base->flags & ETHTOOL_FLAG_COMPACT_BITSETS; - const struct ethtool_ts_info *ts_info = &data->ts_info; + const struct kernel_ethtool_ts_info *ts_info = &data->ts_info; int ret; if (ts_info->so_timestamping) { diff --git a/net/ethtool/wol.c b/net/ethtool/wol.c index 0ed56c9ac1bc..a39d8000d808 100644 --- a/net/ethtool/wol.c +++ b/net/ethtool/wol.c @@ -137,7 +137,7 @@ ethnl_set_wol(struct ethnl_req_info *req_info, struct genl_info *info) ret = dev->ethtool_ops->set_wol(dev, &wol); if (ret) return ret; - dev->wol_enabled = !!wol.wolopts; + dev->ethtool->wol_enabled = !!wol.wolopts; return 1; } diff --git a/net/handshake/netlink.c b/net/handshake/netlink.c index 89637e732866..7e46d130dce2 100644 --- a/net/handshake/netlink.c +++ b/net/handshake/netlink.c @@ -153,7 +153,7 @@ int handshake_nl_done_doit(struct sk_buff *skb, struct genl_info *info) if (!req) { err = -EBUSY; trace_handshake_cmd_done_err(net, req, sock->sk, err); - fput(sock->file); + sockfd_put(sock); return err; } @@ -164,7 +164,7 @@ int handshake_nl_done_doit(struct sk_buff *skb, struct genl_info *info) status = nla_get_u32(info->attrs[HANDSHAKE_A_DONE_STATUS]); handshake_complete(req, status, info); - fput(sock->file); + sockfd_put(sock); return 0; } diff --git a/net/hsr/hsr_device.c b/net/hsr/hsr_device.c index e6904288d40d..ebdfd5b64e17 100644 --- a/net/hsr/hsr_device.c +++ b/net/hsr/hsr_device.c @@ -73,9 +73,15 @@ static void hsr_check_announce(struct net_device *hsr_dev) mod_timer(&hsr->announce_timer, jiffies + msecs_to_jiffies(HSR_ANNOUNCE_INTERVAL)); } + + if (hsr->redbox && !timer_pending(&hsr->announce_proxy_timer)) + mod_timer(&hsr->announce_proxy_timer, jiffies + + msecs_to_jiffies(HSR_ANNOUNCE_INTERVAL) / 2); } else { /* Deactivate the announce timer */ timer_delete(&hsr->announce_timer); + if (hsr->redbox) + timer_delete(&hsr->announce_proxy_timer); } } @@ -279,10 +285,11 @@ out: return NULL; } -static void send_hsr_supervision_frame(struct hsr_port *master, - unsigned long *interval) +static void send_hsr_supervision_frame(struct hsr_port *port, + unsigned long *interval, + const unsigned char *addr) { - struct hsr_priv *hsr = master->hsr; + struct hsr_priv *hsr = port->hsr; __u8 type = HSR_TLV_LIFE_CHECK; struct hsr_sup_payload *hsr_sp; struct hsr_sup_tlv *hsr_stlv; @@ -296,9 +303,9 @@ static void send_hsr_supervision_frame(struct hsr_port *master, hsr->announce_count++; } - skb = hsr_init_skb(master); + skb = hsr_init_skb(port); if (!skb) { - netdev_warn_once(master->dev, "HSR: Could not send supervision frame\n"); + netdev_warn_once(port->dev, "HSR: Could not send supervision frame\n"); return; } @@ -321,11 +328,12 @@ static void send_hsr_supervision_frame(struct hsr_port *master, hsr_stag->tlv.HSR_TLV_length = hsr->prot_version ? sizeof(struct hsr_sup_payload) : 12; - /* Payload: MacAddressA */ + /* Payload: MacAddressA / SAN MAC from ProxyNodeTable */ hsr_sp = skb_put(skb, sizeof(struct hsr_sup_payload)); - ether_addr_copy(hsr_sp->macaddress_A, master->dev->dev_addr); + ether_addr_copy(hsr_sp->macaddress_A, addr); - if (hsr->redbox) { + if (hsr->redbox && + hsr_is_node_in_db(&hsr->proxy_node_db, addr)) { hsr_stlv = skb_put(skb, sizeof(struct hsr_sup_tlv)); hsr_stlv->HSR_TLV_type = PRP_TLV_REDBOX_MAC; hsr_stlv->HSR_TLV_length = sizeof(struct hsr_sup_payload); @@ -340,13 +348,14 @@ static void send_hsr_supervision_frame(struct hsr_port *master, return; } - hsr_forward_skb(skb, master); + hsr_forward_skb(skb, port); spin_unlock_bh(&hsr->seqnr_lock); return; } static void send_prp_supervision_frame(struct hsr_port *master, - unsigned long *interval) + unsigned long *interval, + const unsigned char *addr) { struct hsr_priv *hsr = master->hsr; struct hsr_sup_payload *hsr_sp; @@ -396,7 +405,7 @@ static void hsr_announce(struct timer_list *t) rcu_read_lock(); master = hsr_port_get_hsr(hsr, HSR_PT_MASTER); - hsr->proto_ops->send_sv_frame(master, &interval); + hsr->proto_ops->send_sv_frame(master, &interval, master->dev->dev_addr); if (is_admin_up(master->dev)) mod_timer(&hsr->announce_timer, jiffies + interval); @@ -404,6 +413,41 @@ static void hsr_announce(struct timer_list *t) rcu_read_unlock(); } +/* Announce (supervision frame) timer function for RedBox + */ +static void hsr_proxy_announce(struct timer_list *t) +{ + struct hsr_priv *hsr = from_timer(hsr, t, announce_proxy_timer); + struct hsr_port *interlink; + unsigned long interval = 0; + struct hsr_node *node; + + rcu_read_lock(); + /* RedBOX sends supervisory frames to HSR network with MAC addresses + * of SAN nodes stored in ProxyNodeTable. + */ + interlink = hsr_port_get_hsr(hsr, HSR_PT_INTERLINK); + if (!interlink) + goto done; + + list_for_each_entry_rcu(node, &hsr->proxy_node_db, mac_list) { + if (hsr_addr_is_redbox(hsr, node->macaddress_A)) + continue; + hsr->proto_ops->send_sv_frame(interlink, &interval, + node->macaddress_A); + } + + if (is_admin_up(interlink->dev)) { + if (!interval) + interval = msecs_to_jiffies(HSR_ANNOUNCE_INTERVAL); + + mod_timer(&hsr->announce_proxy_timer, jiffies + interval); + } + +done: + rcu_read_unlock(); +} + void hsr_del_ports(struct hsr_priv *hsr) { struct hsr_port *port; @@ -514,6 +558,12 @@ void hsr_dev_setup(struct net_device *dev) dev->netdev_ops = &hsr_device_ops; SET_NETDEV_DEVTYPE(dev, &hsr_type); dev->priv_flags |= IFF_NO_QUEUE | IFF_DISABLE_NETPOLL; + /* Prevent recursive tx locking */ + dev->lltx = true; + /* Not sure about this. Taken from bridge code. netdevice.h says + * it means "Does not change network namespaces". + */ + dev->netns_local = true; dev->needs_free_netdev = true; @@ -523,16 +573,10 @@ void hsr_dev_setup(struct net_device *dev) dev->features = dev->hw_features; - /* Prevent recursive tx locking */ - dev->features |= NETIF_F_LLTX; /* VLAN on top of HSR needs testing and probably some work on * hsr_header_create() etc. */ dev->features |= NETIF_F_VLAN_CHALLENGED; - /* Not sure about this. Taken from bridge code. netdev_features.h says - * it means "Does not change network namespaces". - */ - dev->features |= NETIF_F_NETNS_LOCAL; } /* Return true if dev is a HSR master; return false otherwise. @@ -585,11 +629,11 @@ int hsr_dev_finalize(struct net_device *hsr_dev, struct net_device *slave[2], /* Overflow soon to find bugs easier: */ hsr->sequence_nr = HSR_SEQNR_START; hsr->sup_sequence_nr = HSR_SUP_SEQNR_START; - hsr->interlink_sequence_nr = HSR_SEQNR_START; timer_setup(&hsr->announce_timer, hsr_announce, 0); timer_setup(&hsr->prune_timer, hsr_prune_nodes, 0); timer_setup(&hsr->prune_proxy_timer, hsr_prune_proxy_nodes, 0); + timer_setup(&hsr->announce_proxy_timer, hsr_proxy_announce, 0); ether_addr_copy(hsr->sup_multicast_addr, def_multicast_addr); hsr->sup_multicast_addr[ETH_ALEN - 1] = multicast_spec; diff --git a/net/hsr/hsr_forward.c b/net/hsr/hsr_forward.c index 05a61b8286ec..b38060246e62 100644 --- a/net/hsr/hsr_forward.c +++ b/net/hsr/hsr_forward.c @@ -117,6 +117,35 @@ static bool is_supervision_frame(struct hsr_priv *hsr, struct sk_buff *skb) return true; } +static bool is_proxy_supervision_frame(struct hsr_priv *hsr, + struct sk_buff *skb) +{ + struct hsr_sup_payload *payload; + struct ethhdr *eth_hdr; + u16 total_length = 0; + + eth_hdr = (struct ethhdr *)skb_mac_header(skb); + + /* Get the HSR protocol revision. */ + if (eth_hdr->h_proto == htons(ETH_P_HSR)) + total_length = sizeof(struct hsrv1_ethhdr_sp); + else + total_length = sizeof(struct hsrv0_ethhdr_sp); + + if (!pskb_may_pull(skb, total_length + sizeof(struct hsr_sup_payload))) + return false; + + skb_pull(skb, total_length); + payload = (struct hsr_sup_payload *)skb->data; + skb_push(skb, total_length); + + /* For RedBox (HSR-SAN) check if we have received the supervision + * frame with MAC addresses from own ProxyNodeTable. + */ + return hsr_is_node_in_db(&hsr->proxy_node_db, + payload->macaddress_A); +} + static struct sk_buff *create_stripped_skb_hsr(struct sk_buff *skb_in, struct hsr_frame_info *frame) { @@ -392,9 +421,9 @@ static int hsr_xmit(struct sk_buff *skb, struct hsr_port *port, bool prp_drop_frame(struct hsr_frame_info *frame, struct hsr_port *port) { return ((frame->port_rcv->type == HSR_PT_SLAVE_A && - port->type == HSR_PT_SLAVE_B) || + port->type == HSR_PT_SLAVE_B) || (frame->port_rcv->type == HSR_PT_SLAVE_B && - port->type == HSR_PT_SLAVE_A)); + port->type == HSR_PT_SLAVE_A)); } bool hsr_drop_frame(struct hsr_frame_info *frame, struct hsr_port *port) @@ -499,7 +528,8 @@ static void hsr_forward_do(struct hsr_frame_info *frame) frame->sequence_nr)) continue; - if (frame->is_supervision && port->type == HSR_PT_MASTER) { + if (frame->is_supervision && port->type == HSR_PT_MASTER && + !frame->is_proxy_supervision) { hsr_handle_sup_frame(frame); continue; } @@ -637,6 +667,9 @@ static int fill_frame_info(struct hsr_frame_info *frame, memset(frame, 0, sizeof(*frame)); frame->is_supervision = is_supervision_frame(port->hsr, skb); + if (frame->is_supervision && hsr->redbox) + frame->is_proxy_supervision = + is_proxy_supervision_frame(port->hsr, skb); n_db = &hsr->node_db; if (port->type == HSR_PT_INTERLINK) @@ -688,7 +721,7 @@ void hsr_forward_skb(struct sk_buff *skb, struct hsr_port *port) /* Gets called for ingress frames as well as egress from master port. * So check and increment stats for master port only here. */ - if (port->type == HSR_PT_MASTER) { + if (port->type == HSR_PT_MASTER || port->type == HSR_PT_INTERLINK) { port->dev->stats.tx_packets++; port->dev->stats.tx_bytes += skb->len; } diff --git a/net/hsr/hsr_framereg.c b/net/hsr/hsr_framereg.c index 614df9649794..73bc6f659812 100644 --- a/net/hsr/hsr_framereg.c +++ b/net/hsr/hsr_framereg.c @@ -36,6 +36,14 @@ static bool seq_nr_after(u16 a, u16 b) #define seq_nr_before(a, b) seq_nr_after((b), (a)) #define seq_nr_before_or_eq(a, b) (!seq_nr_after((a), (b))) +bool hsr_addr_is_redbox(struct hsr_priv *hsr, unsigned char *addr) +{ + if (!hsr->redbox || !is_valid_ether_addr(hsr->macaddress_redbox)) + return false; + + return ether_addr_equal(addr, hsr->macaddress_redbox); +} + bool hsr_addr_is_self(struct hsr_priv *hsr, unsigned char *addr) { struct hsr_self_node *sn; @@ -591,6 +599,10 @@ void hsr_prune_proxy_nodes(struct timer_list *t) spin_lock_bh(&hsr->list_lock); list_for_each_entry_safe(node, tmp, &hsr->proxy_node_db, mac_list) { + /* Don't prune RedBox node. */ + if (hsr_addr_is_redbox(hsr, node->macaddress_A)) + continue; + timestamp = node->time_in[HSR_PT_INTERLINK]; /* Prune old entries */ diff --git a/net/hsr/hsr_framereg.h b/net/hsr/hsr_framereg.h index 7619e31c1d2d..993fa950d814 100644 --- a/net/hsr/hsr_framereg.h +++ b/net/hsr/hsr_framereg.h @@ -22,6 +22,7 @@ struct hsr_frame_info { struct hsr_node *node_src; u16 sequence_nr; bool is_supervision; + bool is_proxy_supervision; bool is_vlan; bool is_local_dest; bool is_local_exclusive; @@ -35,6 +36,7 @@ struct hsr_node *hsr_get_node(struct hsr_port *port, struct list_head *node_db, enum hsr_port_type rx_port); void hsr_handle_sup_frame(struct hsr_frame_info *frame); bool hsr_addr_is_self(struct hsr_priv *hsr, unsigned char *addr); +bool hsr_addr_is_redbox(struct hsr_priv *hsr, unsigned char *addr); void hsr_addr_subst_source(struct hsr_node *node, struct sk_buff *skb); void hsr_addr_subst_dest(struct hsr_node *node_src, struct sk_buff *skb, diff --git a/net/hsr/hsr_main.h b/net/hsr/hsr_main.h index 23850b16d1ea..fcfeb79bb040 100644 --- a/net/hsr/hsr_main.h +++ b/net/hsr/hsr_main.h @@ -170,7 +170,8 @@ struct hsr_node; struct hsr_proto_ops { /* format and send supervision frame */ - void (*send_sv_frame)(struct hsr_port *port, unsigned long *interval); + void (*send_sv_frame)(struct hsr_port *port, unsigned long *interval, + const unsigned char addr[ETH_ALEN]); void (*handle_san_frame)(bool san, enum hsr_port_type port, struct hsr_node *node); bool (*drop_frame)(struct hsr_frame_info *frame, struct hsr_port *port); @@ -197,11 +198,11 @@ struct hsr_priv { struct list_head proxy_node_db; /* RedBox HSR proxy nodes */ struct hsr_self_node __rcu *self_node; /* MACs of slaves */ struct timer_list announce_timer; /* Supervision frame dispatch */ + struct timer_list announce_proxy_timer; struct timer_list prune_timer; struct timer_list prune_proxy_timer; int announce_count; u16 sequence_nr; - u16 interlink_sequence_nr; /* Interlink port seq_nr */ u16 sup_sequence_nr; /* For HSRv1 separate seq_nr for supervision */ enum hsr_version prot_version; /* Indicate if HSRv0, HSRv1 or PRPv1 */ spinlock_t seqnr_lock; /* locking for sequence_nr */ diff --git a/net/hsr/hsr_netlink.c b/net/hsr/hsr_netlink.c index 898f18c6da53..f6ff0b61e08a 100644 --- a/net/hsr/hsr_netlink.c +++ b/net/hsr/hsr_netlink.c @@ -131,6 +131,7 @@ static void hsr_dellink(struct net_device *dev, struct list_head *head) del_timer_sync(&hsr->prune_timer); del_timer_sync(&hsr->prune_proxy_timer); del_timer_sync(&hsr->announce_timer); + timer_delete_sync(&hsr->announce_proxy_timer); hsr_debugfs_term(hsr); hsr_del_ports(hsr); diff --git a/net/hsr/hsr_slave.c b/net/hsr/hsr_slave.c index af6cf64a00e0..464f683e016d 100644 --- a/net/hsr/hsr_slave.c +++ b/net/hsr/hsr_slave.c @@ -67,7 +67,16 @@ static rx_handler_result_t hsr_handle_frame(struct sk_buff **pskb) skb_set_network_header(skb, ETH_HLEN + HSR_HLEN); skb_reset_mac_len(skb); - hsr_forward_skb(skb, port); + /* Only the frames received over the interlink port will assign a + * sequence number and require synchronisation vs other sender. + */ + if (port->type == HSR_PT_INTERLINK) { + spin_lock_bh(&hsr->seqnr_lock); + hsr_forward_skb(skb, port); + spin_unlock_bh(&hsr->seqnr_lock); + } else { + hsr_forward_skb(skb, port); + } finish_consume: return RX_HANDLER_CONSUMED; diff --git a/net/ieee802154/6lowpan/core.c b/net/ieee802154/6lowpan/core.c index 77b4e92027c5..175efd860f7b 100644 --- a/net/ieee802154/6lowpan/core.c +++ b/net/ieee802154/6lowpan/core.c @@ -116,7 +116,7 @@ static void lowpan_setup(struct net_device *ldev) ldev->netdev_ops = &lowpan_netdev_ops; ldev->header_ops = &lowpan_header_ops; ldev->needs_free_netdev = true; - ldev->features |= NETIF_F_NETNS_LOCAL; + ldev->netns_local = true; } static int lowpan_validate(struct nlattr *tb[], struct nlattr *data[], diff --git a/net/ieee802154/6lowpan/reassembly.c b/net/ieee802154/6lowpan/reassembly.c index 56ef873828f4..867d637d86f0 100644 --- a/net/ieee802154/6lowpan/reassembly.c +++ b/net/ieee802154/6lowpan/reassembly.c @@ -130,7 +130,7 @@ static int lowpan_frag_queue(struct lowpan_frag_queue *fq, goto err; fq->q.stamp = skb->tstamp; - fq->q.mono_delivery_time = skb->mono_delivery_time; + fq->q.tstamp_type = skb->tstamp_type; if (frag_type == LOWPAN_DISPATCH_FRAG1) fq->q.flags |= INET_FRAG_FIRST_IN; diff --git a/net/ieee802154/core.c b/net/ieee802154/core.c index 60e8fff1347e..88adb04e4072 100644 --- a/net/ieee802154/core.c +++ b/net/ieee802154/core.c @@ -226,11 +226,11 @@ int cfg802154_switch_netns(struct cfg802154_registered_device *rdev, list_for_each_entry(wpan_dev, &rdev->wpan_dev_list, list) { if (!wpan_dev->netdev) continue; - wpan_dev->netdev->features &= ~NETIF_F_NETNS_LOCAL; + wpan_dev->netdev->netns_local = false; err = dev_change_net_namespace(wpan_dev->netdev, net, "wpan%d"); if (err) break; - wpan_dev->netdev->features |= NETIF_F_NETNS_LOCAL; + wpan_dev->netdev->netns_local = true; } if (err) { @@ -242,11 +242,11 @@ int cfg802154_switch_netns(struct cfg802154_registered_device *rdev, list) { if (!wpan_dev->netdev) continue; - wpan_dev->netdev->features &= ~NETIF_F_NETNS_LOCAL; + wpan_dev->netdev->netns_local = false; err = dev_change_net_namespace(wpan_dev->netdev, net, "wpan%d"); WARN_ON(err); - wpan_dev->netdev->features |= NETIF_F_NETNS_LOCAL; + wpan_dev->netdev->netns_local = true; } return err; @@ -291,7 +291,7 @@ static int cfg802154_netdev_notifier_call(struct notifier_block *nb, switch (state) { /* TODO NETDEV_DEVTYPE */ case NETDEV_REGISTER: - dev->features |= NETIF_F_NETNS_LOCAL; + dev->netns_local = true; wpan_dev->identifier = ++rdev->wpan_dev_id; list_add_rcu(&wpan_dev->list, &rdev->wpan_dev_list); rdev->devlist_generation++; diff --git a/net/ipv4/Kconfig b/net/ipv4/Kconfig index 8e94ed7c56a0..6d2c97f8e9ef 100644 --- a/net/ipv4/Kconfig +++ b/net/ipv4/Kconfig @@ -661,7 +661,8 @@ config TCP_CONG_CDG For further details see: D.A. Hayes and G. Armitage. "Revisiting TCP congestion control using - delay gradients." In Networking 2011. Preprint: http://goo.gl/No3vdg + delay gradients." In Networking 2011. Preprint: + http://caia.swin.edu.au/cv/dahayes/content/networking2011-cdg-preprint.pdf config TCP_CONG_BBR tristate "BBR TCP" diff --git a/net/ipv4/bpf_tcp_ca.c b/net/ipv4/bpf_tcp_ca.c index 18227757ec0c..554804774628 100644 --- a/net/ipv4/bpf_tcp_ca.c +++ b/net/ipv4/bpf_tcp_ca.c @@ -14,10 +14,6 @@ /* "extern" is to avoid sparse warning. It is only used in bpf_struct_ops.c. */ static struct bpf_struct_ops bpf_tcp_congestion_ops; -static u32 unsupported_ops[] = { - offsetof(struct tcp_congestion_ops, get_info), -}; - static const struct btf_type *tcp_sock_type; static u32 tcp_sock_id, sock_id; static const struct btf_type *tcp_congestion_ops_type; @@ -45,18 +41,6 @@ static int bpf_tcp_ca_init(struct btf *btf) return 0; } -static bool is_unsupported(u32 member_offset) -{ - unsigned int i; - - for (i = 0; i < ARRAY_SIZE(unsupported_ops); i++) { - if (member_offset == unsupported_ops[i]) - return true; - } - - return false; -} - static bool bpf_tcp_ca_is_valid_access(int off, int size, enum bpf_access_type type, const struct bpf_prog *prog, @@ -251,26 +235,17 @@ static int bpf_tcp_ca_init_member(const struct btf_type *t, return 0; } -static int bpf_tcp_ca_check_member(const struct btf_type *t, - const struct btf_member *member, - const struct bpf_prog *prog) -{ - if (is_unsupported(__btf_member_bit_offset(t, member) / 8)) - return -ENOTSUPP; - return 0; -} - -static int bpf_tcp_ca_reg(void *kdata) +static int bpf_tcp_ca_reg(void *kdata, struct bpf_link *link) { return tcp_register_congestion_control(kdata); } -static void bpf_tcp_ca_unreg(void *kdata) +static void bpf_tcp_ca_unreg(void *kdata, struct bpf_link *link) { tcp_unregister_congestion_control(kdata); } -static int bpf_tcp_ca_update(void *kdata, void *old_kdata) +static int bpf_tcp_ca_update(void *kdata, void *old_kdata, struct bpf_link *link) { return tcp_update_congestion_control(kdata, old_kdata); } @@ -354,7 +329,6 @@ static struct bpf_struct_ops bpf_tcp_congestion_ops = { .reg = bpf_tcp_ca_reg, .unreg = bpf_tcp_ca_unreg, .update = bpf_tcp_ca_update, - .check_member = bpf_tcp_ca_check_member, .init_member = bpf_tcp_ca_init_member, .init = bpf_tcp_ca_init, .validate = bpf_tcp_ca_validate, diff --git a/net/ipv4/cipso_ipv4.c b/net/ipv4/cipso_ipv4.c index e9cb27061c12..8cc0e2f4159d 100644 --- a/net/ipv4/cipso_ipv4.c +++ b/net/ipv4/cipso_ipv4.c @@ -1976,7 +1976,7 @@ int cipso_v4_req_setattr(struct request_sock *req, buf = NULL; req_inet = inet_rsk(req); - opt = xchg((__force struct ip_options_rcu **)&req_inet->ireq_opt, opt); + opt = unrcu_pointer(xchg(&req_inet->ireq_opt, RCU_INITIALIZER(opt))); if (opt) kfree_rcu(opt, rcu); diff --git a/net/ipv4/devinet.c b/net/ipv4/devinet.c index d09f557eaa77..ab76744383cf 100644 --- a/net/ipv4/devinet.c +++ b/net/ipv4/devinet.c @@ -216,17 +216,27 @@ static void devinet_sysctl_unregister(struct in_device *idev) /* Locks all the inet devices. */ -static struct in_ifaddr *inet_alloc_ifa(void) +static struct in_ifaddr *inet_alloc_ifa(struct in_device *in_dev) { - return kzalloc(sizeof(struct in_ifaddr), GFP_KERNEL_ACCOUNT); + struct in_ifaddr *ifa; + + ifa = kzalloc(sizeof(*ifa), GFP_KERNEL_ACCOUNT); + if (!ifa) + return NULL; + + in_dev_hold(in_dev); + ifa->ifa_dev = in_dev; + + INIT_HLIST_NODE(&ifa->hash); + + return ifa; } static void inet_rcu_free_ifa(struct rcu_head *head) { struct in_ifaddr *ifa = container_of(head, struct in_ifaddr, rcu_head); - if (ifa->ifa_dev) - in_dev_put(ifa->ifa_dev); + in_dev_put(ifa->ifa_dev); kfree(ifa); } @@ -574,17 +584,9 @@ static int inet_set_ifa(struct net_device *dev, struct in_ifaddr *ifa) ASSERT_RTNL(); - if (!in_dev) { - inet_free_ifa(ifa); - return -ENOBUFS; - } ipv4_devconf_setall(in_dev); neigh_parms_data_state_setall(in_dev->arp_parms); - if (ifa->ifa_dev != in_dev) { - WARN_ON(ifa->ifa_dev); - in_dev_hold(in_dev); - ifa->ifa_dev = in_dev; - } + if (ipv4_is_loopback(ifa->ifa_local)) ifa->ifa_scope = RT_SCOPE_HOST; return inet_insert_ifa(ifa); @@ -701,8 +703,6 @@ errout: return err; } -#define INFINITY_LIFE_TIME 0xFFFFFFFF - static void check_lifetime(struct work_struct *work) { unsigned long now, next, next_sec, next_sched; @@ -875,7 +875,7 @@ static struct in_ifaddr *rtm_to_ifaddr(struct net *net, struct nlmsghdr *nlh, if (!in_dev) goto errout; - ifa = inet_alloc_ifa(); + ifa = inet_alloc_ifa(in_dev); if (!ifa) /* * A potential indev allocation can be left alive, it stays @@ -885,19 +885,15 @@ static struct in_ifaddr *rtm_to_ifaddr(struct net *net, struct nlmsghdr *nlh, ipv4_devconf_setall(in_dev); neigh_parms_data_state_setall(in_dev->arp_parms); - in_dev_hold(in_dev); if (!tb[IFA_ADDRESS]) tb[IFA_ADDRESS] = tb[IFA_LOCAL]; - INIT_HLIST_NODE(&ifa->hash); ifa->ifa_prefixlen = ifm->ifa_prefixlen; ifa->ifa_mask = inet_make_mask(ifm->ifa_prefixlen); ifa->ifa_flags = tb[IFA_FLAGS] ? nla_get_u32(tb[IFA_FLAGS]) : ifm->ifa_flags; ifa->ifa_scope = ifm->ifa_scope; - ifa->ifa_dev = in_dev; - ifa->ifa_local = nla_get_in_addr(tb[IFA_LOCAL]); ifa->ifa_address = nla_get_in_addr(tb[IFA_ADDRESS]); @@ -1184,10 +1180,12 @@ int devinet_ioctl(struct net *net, unsigned int cmd, struct ifreq *ifr) if (!ifa) { ret = -ENOBUFS; - ifa = inet_alloc_ifa(); + if (!in_dev) + break; + ifa = inet_alloc_ifa(in_dev); if (!ifa) break; - INIT_HLIST_NODE(&ifa->hash); + if (colon) memcpy(ifa->ifa_label, ifr->ifr_name, IFNAMSIZ); else @@ -1586,16 +1584,13 @@ static int inetdev_event(struct notifier_block *this, unsigned long event, if (!inetdev_valid_mtu(dev->mtu)) break; if (dev->flags & IFF_LOOPBACK) { - struct in_ifaddr *ifa = inet_alloc_ifa(); + struct in_ifaddr *ifa = inet_alloc_ifa(in_dev); if (ifa) { - INIT_HLIST_NODE(&ifa->hash); ifa->ifa_local = ifa->ifa_address = htonl(INADDR_LOOPBACK); ifa->ifa_prefixlen = 8; ifa->ifa_mask = inet_make_mask(8); - in_dev_hold(in_dev); - ifa->ifa_dev = in_dev; ifa->ifa_scope = RT_SCOPE_HOST; memcpy(ifa->ifa_label, dev->name, IFNAMSIZ); set_ifa_lifetime(ifa, INFINITY_LIFE_TIME, @@ -1948,8 +1943,7 @@ static void rtmsg_ifa(int event, struct in_ifaddr *ifa, struct nlmsghdr *nlh, rtnl_notify(skb, net, portid, RTNLGRP_IPV4_IFADDR, nlh, GFP_KERNEL); return; errout: - if (err < 0) - rtnl_set_sk_err(net, RTNLGRP_IPV4_IFADDR, err); + rtnl_set_sk_err(net, RTNLGRP_IPV4_IFADDR, err); } static size_t inet_get_link_af_size(const struct net_device *dev, @@ -2145,8 +2139,7 @@ void inet_netconf_notify_devconf(struct net *net, int event, int type, rtnl_notify(skb, net, 0, RTNLGRP_IPV4_NETCONF, NULL, GFP_KERNEL); return; errout: - if (err < 0) - rtnl_set_sk_err(net, RTNLGRP_IPV4_NETCONF, err); + rtnl_set_sk_err(net, RTNLGRP_IPV4_NETCONF, err); } static const struct nla_policy devconf_ipv4_policy[NETCONFA_MAX+1] = { @@ -2390,7 +2383,7 @@ static int devinet_conf_ifindex(struct net *net, struct ipv4_devconf *cnf) } } -static int devinet_conf_proc(struct ctl_table *ctl, int write, +static int devinet_conf_proc(const struct ctl_table *ctl, int write, void *buffer, size_t *lenp, loff_t *ppos) { int old_value = *(int *)ctl->data; @@ -2442,7 +2435,7 @@ static int devinet_conf_proc(struct ctl_table *ctl, int write, return ret; } -static int devinet_sysctl_forward(struct ctl_table *ctl, int write, +static int devinet_sysctl_forward(const struct ctl_table *ctl, int write, void *buffer, size_t *lenp, loff_t *ppos) { int *valp = ctl->data; @@ -2489,7 +2482,7 @@ static int devinet_sysctl_forward(struct ctl_table *ctl, int write, return ret; } -static int ipv4_doint_and_flush(struct ctl_table *ctl, int write, +static int ipv4_doint_and_flush(const struct ctl_table *ctl, int write, void *buffer, size_t *lenp, loff_t *ppos) { int *valp = ctl->data; diff --git a/net/ipv4/esp4.c b/net/ipv4/esp4.c index 3968d3f98e08..f3281312eb5e 100644 --- a/net/ipv4/esp4.c +++ b/net/ipv4/esp4.c @@ -115,7 +115,8 @@ static void esp_ssg_unref(struct xfrm_state *x, void *tmp, struct sk_buff *skb) */ if (req->src != req->dst) for (sg = sg_next(req->src); sg; sg = sg_next(sg)) - skb_page_unref(sg_page(sg), skb->pp_recycle); + skb_page_unref(page_to_netmem(sg_page(sg)), + skb->pp_recycle); } #ifdef CONFIG_INET_ESPINTCP @@ -239,8 +240,7 @@ static int esp_output_tail_tcp(struct xfrm_state *x, struct sk_buff *skb) #else static int esp_output_tail_tcp(struct xfrm_state *x, struct sk_buff *skb) { - kfree_skb(skb); - + WARN_ON(1); return -EOPNOTSUPP; } #endif @@ -349,6 +349,7 @@ static struct ip_esp_hdr *esp_output_udp_encap(struct sk_buff *skb, { struct udphdr *uh; unsigned int len; + struct xfrm_offload *xo = xfrm_offload(skb); len = skb->len + esp->tailen - skb_transport_offset(skb); if (len + sizeof(struct iphdr) > IP_MAX_MTU) @@ -360,7 +361,12 @@ static struct ip_esp_hdr *esp_output_udp_encap(struct sk_buff *skb, uh->len = htons(len); uh->check = 0; - *skb_mac_header(skb) = IPPROTO_UDP; + /* For IPv4 ESP with UDP encapsulation, if xo is not null, the skb is in the crypto offload + * data path, which means that esp_output_udp_encap is called outside of the XFRM stack. + * In this case, the mac header doesn't point to the IPv4 protocol field, so don't set it. + */ + if (!xo || encap_type != UDP_ENCAP_ESPINUDP) + *skb_mac_header(skb) = IPPROTO_UDP; return (struct ip_esp_hdr *)(uh + 1); } diff --git a/net/ipv4/esp4_offload.c b/net/ipv4/esp4_offload.c index b3271957ad9a..80c4ea0e12f4 100644 --- a/net/ipv4/esp4_offload.c +++ b/net/ipv4/esp4_offload.c @@ -56,6 +56,13 @@ static struct sk_buff *esp4_gro_receive(struct list_head *head, x = xfrm_state_lookup(dev_net(skb->dev), skb->mark, (xfrm_address_t *)&ip_hdr(skb)->daddr, spi, IPPROTO_ESP, AF_INET); + + if (unlikely(x && x->dir && x->dir != XFRM_SA_DIR_IN)) { + /* non-offload path will record the error and audit log */ + xfrm_state_put(x); + x = NULL; + } + if (!x) goto out_reset; @@ -264,6 +271,7 @@ static int esp_xmit(struct xfrm_state *x, struct sk_buff *skb, netdev_features_ struct esp_info esp; bool hw_offload = true; __u32 seq; + int encap_type = 0; esp.inplace = true; @@ -296,8 +304,10 @@ static int esp_xmit(struct xfrm_state *x, struct sk_buff *skb, netdev_features_ esp.esph = ip_esp_hdr(skb); + if (x->encap) + encap_type = x->encap->encap_type; - if (!hw_offload || !skb_is_gso(skb)) { + if (!hw_offload || !skb_is_gso(skb) || (hw_offload && encap_type == UDP_ENCAP_ESPINUDP)) { esp.nfrags = esp_output_head(x, skb, &esp); if (esp.nfrags < 0) return esp.nfrags; @@ -324,6 +334,18 @@ static int esp_xmit(struct xfrm_state *x, struct sk_buff *skb, netdev_features_ esp.seqno = cpu_to_be64(seq + ((u64)xo->seq.hi << 32)); + if (hw_offload && encap_type == UDP_ENCAP_ESPINUDP) { + /* In the XFRM stack, the encapsulation protocol is set to iphdr->protocol by + * setting *skb_mac_header(skb) (see esp_output_udp_encap()) where skb->mac_header + * points to iphdr->protocol (see xfrm4_tunnel_encap_add()). + * However, in esp_xmit(), skb->mac_header doesn't point to iphdr->protocol. + * Therefore, the protocol field needs to be corrected. + */ + ip_hdr(skb)->protocol = IPPROTO_UDP; + + esph->seq_no = htonl(seq); + } + ip_hdr(skb)->tot_len = htons(skb->len); ip_send_check(ip_hdr(skb)); diff --git a/net/ipv4/fib_frontend.c b/net/ipv4/fib_frontend.c index 7ad2cafb9276..793e6781399a 100644 --- a/net/ipv4/fib_frontend.c +++ b/net/ipv4/fib_frontend.c @@ -293,7 +293,7 @@ __be32 fib_compute_spec_dst(struct sk_buff *skb) .flowi4_iif = LOOPBACK_IFINDEX, .flowi4_l3mdev = l3mdev_master_ifindex_rcu(dev), .daddr = ip_hdr(skb)->saddr, - .flowi4_tos = ip_hdr(skb)->tos & IPTOS_RT_MASK, + .flowi4_tos = ip_hdr(skb)->tos & INET_DSCP_MASK, .flowi4_scope = scope, .flowi4_mark = vmark ? skb->mark : 0, }; @@ -1343,7 +1343,7 @@ static void nl_fib_lookup(struct net *net, struct fib_result_nl *frn) struct flowi4 fl4 = { .flowi4_mark = frn->fl_mark, .daddr = frn->fl_addr, - .flowi4_tos = frn->fl_tos, + .flowi4_tos = frn->fl_tos & INET_DSCP_MASK, .flowi4_scope = frn->fl_scope, }; struct fib_table *tb; diff --git a/net/ipv4/fib_rules.c b/net/ipv4/fib_rules.c index 5bdd1c016009..b07292d50ee7 100644 --- a/net/ipv4/fib_rules.c +++ b/net/ipv4/fib_rules.c @@ -37,6 +37,7 @@ struct fib4_rule { u8 dst_len; u8 src_len; dscp_t dscp; + u8 dscp_full:1; /* DSCP or TOS selector */ __be32 src; __be32 srcmask; __be32 dst; @@ -186,7 +187,15 @@ INDIRECT_CALLABLE_SCOPE int fib4_rule_match(struct fib_rule *rule, ((daddr ^ r->dst) & r->dstmask)) return 0; - if (r->dscp && r->dscp != inet_dsfield_to_dscp(fl4->flowi4_tos)) + /* When DSCP selector is used we need to match on the entire DSCP field + * in the flow information structure. When TOS selector is used we need + * to mask the upper three DSCP bits prior to matching to maintain + * legacy behavior. + */ + if (r->dscp_full && r->dscp != inet_dsfield_to_dscp(fl4->flowi4_tos)) + return 0; + else if (!r->dscp_full && r->dscp && + !fib_dscp_masked_match(r->dscp, fl4)) return 0; if (rule->ip_proto && (rule->ip_proto != fl4->flowi4_proto)) @@ -217,6 +226,20 @@ static struct fib_table *fib_empty_table(struct net *net) return NULL; } +static int fib4_nl2rule_dscp(const struct nlattr *nla, struct fib4_rule *rule4, + struct netlink_ext_ack *extack) +{ + if (rule4->dscp) { + NL_SET_ERR_MSG(extack, "Cannot specify both TOS and DSCP"); + return -EINVAL; + } + + rule4->dscp = inet_dsfield_to_dscp(nla_get_u8(nla) << 2); + rule4->dscp_full = true; + + return 0; +} + static int fib4_rule_configure(struct fib_rule *rule, struct sk_buff *skb, struct fib_rule_hdr *frh, struct nlattr **tb, @@ -238,6 +261,10 @@ static int fib4_rule_configure(struct fib_rule *rule, struct sk_buff *skb, } rule4->dscp = inet_dsfield_to_dscp(frh->tos); + if (tb[FRA_DSCP] && + fib4_nl2rule_dscp(tb[FRA_DSCP], rule4, extack) < 0) + goto errout; + /* split local/main if they are not already split */ err = fib_unmerge(net); if (err) @@ -320,9 +347,19 @@ static int fib4_rule_compare(struct fib_rule *rule, struct fib_rule_hdr *frh, if (frh->dst_len && (rule4->dst_len != frh->dst_len)) return 0; - if (frh->tos && inet_dscp_to_dsfield(rule4->dscp) != frh->tos) + if (frh->tos && + (rule4->dscp_full || + inet_dscp_to_dsfield(rule4->dscp) != frh->tos)) return 0; + if (tb[FRA_DSCP]) { + dscp_t dscp; + + dscp = inet_dsfield_to_dscp(nla_get_u8(tb[FRA_DSCP]) << 2); + if (!rule4->dscp_full || rule4->dscp != dscp) + return 0; + } + #ifdef CONFIG_IP_ROUTE_CLASSID if (tb[FRA_FLOW] && (rule4->tclassid != nla_get_u32(tb[FRA_FLOW]))) return 0; @@ -344,7 +381,15 @@ static int fib4_rule_fill(struct fib_rule *rule, struct sk_buff *skb, frh->dst_len = rule4->dst_len; frh->src_len = rule4->src_len; - frh->tos = inet_dscp_to_dsfield(rule4->dscp); + + if (rule4->dscp_full) { + frh->tos = 0; + if (nla_put_u8(skb, FRA_DSCP, + inet_dscp_to_dsfield(rule4->dscp) >> 2)) + goto nla_put_failure; + } else { + frh->tos = inet_dscp_to_dsfield(rule4->dscp); + } if ((rule4->dst_len && nla_put_in_addr(skb, FRA_DST, rule4->dst)) || @@ -366,7 +411,8 @@ static size_t fib4_rule_nlmsg_payload(struct fib_rule *rule) { return nla_total_size(4) /* dst */ + nla_total_size(4) /* src */ - + nla_total_size(4); /* flow */ + + nla_total_size(4) /* flow */ + + nla_total_size(1); /* dscp */ } static void fib4_rule_flush_cache(struct fib_rules_ops *ops) diff --git a/net/ipv4/fib_semantics.c b/net/ipv4/fib_semantics.c index f669da98d11d..ba2df3d2ac15 100644 --- a/net/ipv4/fib_semantics.c +++ b/net/ipv4/fib_semantics.c @@ -543,8 +543,7 @@ void rtmsg_fib(int event, __be32 key, struct fib_alias *fa, info->nlh, GFP_KERNEL); return; errout: - if (err < 0) - rtnl_set_sk_err(info->nl_net, RTNLGRP_IPV4_ROUTE, err); + rtnl_set_sk_err(info->nl_net, RTNLGRP_IPV4_ROUTE, err); } static int fib_detect_death(struct fib_info *fi, int order, @@ -1030,7 +1029,7 @@ bool fib_metrics_match(struct fib_config *cfg, struct fib_info *fi) bool ecn_ca = false; nla_strscpy(tmp, nla, sizeof(tmp)); - val = tcp_ca_get_key_by_name(fi->fib_net, tmp, &ecn_ca); + val = tcp_ca_get_key_by_name(tmp, &ecn_ca); } else { if (nla_len(nla) != sizeof(u32)) return false; @@ -1459,8 +1458,7 @@ struct fib_info *fib_create_info(struct fib_config *cfg, fi = kzalloc(struct_size(fi, fib_nh, nhs), GFP_KERNEL); if (!fi) goto failure; - fi->fib_metrics = ip_fib_metrics_init(fi->fib_net, cfg->fc_mx, - cfg->fc_mx_len, extack); + fi->fib_metrics = ip_fib_metrics_init(cfg->fc_mx, cfg->fc_mx_len, extack); if (IS_ERR(fi->fib_metrics)) { err = PTR_ERR(fi->fib_metrics); kfree(fi); @@ -2067,8 +2065,7 @@ static void fib_select_default(const struct flowi4 *flp, struct fib_result *res) if (fa->fa_slen != slen) continue; - if (fa->fa_dscp && - fa->fa_dscp != inet_dsfield_to_dscp(flp->flowi4_tos)) + if (fa->fa_dscp && !fib_dscp_masked_match(fa->fa_dscp, flp)) continue; if (fa->tb_id != tb->tb_id) continue; @@ -2270,6 +2267,15 @@ void fib_select_path(struct net *net, struct fib_result *res, fib_select_default(fl4, res); check_saddr: - if (!fl4->saddr) - fl4->saddr = fib_result_prefsrc(net, res); + if (!fl4->saddr) { + struct net_device *l3mdev; + + l3mdev = dev_get_by_index_rcu(net, fl4->flowi4_l3mdev); + + if (!l3mdev || + l3mdev_master_dev_rcu(FIB_RES_DEV(*res)) == l3mdev) + fl4->saddr = fib_result_prefsrc(net, res); + else + fl4->saddr = inet_select_addr(l3mdev, 0, RT_SCOPE_LINK); + } } diff --git a/net/ipv4/fib_trie.c b/net/ipv4/fib_trie.c index f474106464d2..09e31757e96c 100644 --- a/net/ipv4/fib_trie.c +++ b/net/ipv4/fib_trie.c @@ -1580,8 +1580,7 @@ found: if (index >= (1ul << fa->fa_slen)) continue; } - if (fa->fa_dscp && - inet_dscp_to_dsfield(fa->fa_dscp) != flp->flowi4_tos) + if (fa->fa_dscp && !fib_dscp_masked_match(fa->fa_dscp, flp)) continue; /* Paired with WRITE_ONCE() in fib_release_info() */ if (READ_ONCE(fi->fib_dead)) @@ -1629,6 +1628,7 @@ set_result: res->nhc = nhc; res->type = fa->fa_type; res->scope = fi->fib_scope; + res->dscp = fa->fa_dscp; res->fi = fi; res->table = tb; res->fa_head = &n->leaf; diff --git a/net/ipv4/fou_core.c b/net/ipv4/fou_core.c index a8494f796dca..3e30745e2c09 100644 --- a/net/ipv4/fou_core.c +++ b/net/ipv4/fou_core.c @@ -50,7 +50,7 @@ struct fou_net { static inline struct fou *fou_from_sock(struct sock *sk) { - return sk->sk_user_data; + return rcu_dereference_sk_user_data(sk); } static int fou_recv_pull(struct sk_buff *skb, struct fou *fou, size_t len) @@ -233,9 +233,15 @@ static struct sk_buff *fou_gro_receive(struct sock *sk, struct sk_buff *skb) { const struct net_offload __rcu **offloads; - u8 proto = fou_from_sock(sk)->protocol; + struct fou *fou = fou_from_sock(sk); const struct net_offload *ops; struct sk_buff *pp = NULL; + u8 proto; + + if (!fou) + goto out; + + proto = fou->protocol; /* We can clear the encap_mark for FOU as we are essentially doing * one of two possible things. We are either adding an L4 tunnel @@ -263,14 +269,24 @@ static int fou_gro_complete(struct sock *sk, struct sk_buff *skb, int nhoff) { const struct net_offload __rcu **offloads; - u8 proto = fou_from_sock(sk)->protocol; + struct fou *fou = fou_from_sock(sk); const struct net_offload *ops; - int err = -ENOSYS; + u8 proto; + int err; + + if (!fou) { + err = -ENOENT; + goto out; + } + + proto = fou->protocol; offloads = NAPI_GRO_CB(skb)->is_ipv6 ? inet6_offloads : inet_offloads; ops = rcu_dereference(offloads[proto]); - if (WARN_ON(!ops || !ops->callbacks.gro_complete)) + if (WARN_ON(!ops || !ops->callbacks.gro_complete)) { + err = -ENOSYS; goto out; + } err = ops->callbacks.gro_complete(skb, nhoff); @@ -322,6 +338,9 @@ static struct sk_buff *gue_gro_receive(struct sock *sk, skb_gro_remcsum_init(&grc); + if (!fou) + goto out; + off = skb_gro_offset(skb); len = off + sizeof(*guehdr); @@ -433,7 +452,7 @@ next_proto: offloads = NAPI_GRO_CB(skb)->is_ipv6 ? inet6_offloads : inet_offloads; ops = rcu_dereference(offloads[proto]); - if (WARN_ON_ONCE(!ops || !ops->callbacks.gro_receive)) + if (!ops || !ops->callbacks.gro_receive) goto out; pp = call_gro_receive(ops->callbacks.gro_receive, head, skb); diff --git a/net/ipv4/icmp.c b/net/ipv4/icmp.c index ab6d0d98dbc3..e1384e7331d8 100644 --- a/net/ipv4/icmp.c +++ b/net/ipv4/icmp.c @@ -93,6 +93,7 @@ #include <net/ip_fib.h> #include <net/l3mdev.h> #include <net/addrconf.h> +#include <net/inet_dscp.h> #define CREATE_TRACE_POINTS #include <trace/events/icmp.h> @@ -220,61 +221,56 @@ static inline void icmp_xmit_unlock(struct sock *sk) spin_unlock(&sk->sk_lock.slock); } -int sysctl_icmp_msgs_per_sec __read_mostly = 1000; -int sysctl_icmp_msgs_burst __read_mostly = 50; - -static struct { - spinlock_t lock; - u32 credit; - u32 stamp; -} icmp_global = { - .lock = __SPIN_LOCK_UNLOCKED(icmp_global.lock), -}; - /** * icmp_global_allow - Are we allowed to send one more ICMP message ? + * @net: network namespace * * Uses a token bucket to limit our ICMP messages to ~sysctl_icmp_msgs_per_sec. * Returns false if we reached the limit and can not send another packet. - * Note: called with BH disabled + * Works in tandem with icmp_global_consume(). */ -bool icmp_global_allow(void) +bool icmp_global_allow(struct net *net) { - u32 credit, delta, incr = 0, now = (u32)jiffies; - bool rc = false; + u32 delta, now, oldstamp; + int incr, new, old; - /* Check if token bucket is empty and cannot be refilled - * without taking the spinlock. The READ_ONCE() are paired - * with the following WRITE_ONCE() in this same function. + /* Note: many cpus could find this condition true. + * Then later icmp_global_consume() could consume more credits, + * this is an acceptable race. */ - if (!READ_ONCE(icmp_global.credit)) { - delta = min_t(u32, now - READ_ONCE(icmp_global.stamp), HZ); - if (delta < HZ / 50) - return false; - } + if (atomic_read(&net->ipv4.icmp_global_credit) > 0) + return true; - spin_lock(&icmp_global.lock); - delta = min_t(u32, now - icmp_global.stamp, HZ); - if (delta >= HZ / 50) { - incr = READ_ONCE(sysctl_icmp_msgs_per_sec) * delta / HZ; - if (incr) - WRITE_ONCE(icmp_global.stamp, now); - } - credit = min_t(u32, icmp_global.credit + incr, - READ_ONCE(sysctl_icmp_msgs_burst)); - if (credit) { - /* We want to use a credit of one in average, but need to randomize - * it for security reasons. - */ - credit = max_t(int, credit - get_random_u32_below(3), 0); - rc = true; + now = jiffies; + oldstamp = READ_ONCE(net->ipv4.icmp_global_stamp); + delta = min_t(u32, now - oldstamp, HZ); + if (delta < HZ / 50) + return false; + + incr = READ_ONCE(net->ipv4.sysctl_icmp_msgs_per_sec) * delta / HZ; + if (!incr) + return false; + + if (cmpxchg(&net->ipv4.icmp_global_stamp, oldstamp, now) == oldstamp) { + old = atomic_read(&net->ipv4.icmp_global_credit); + do { + new = min(old + incr, READ_ONCE(net->ipv4.sysctl_icmp_msgs_burst)); + } while (!atomic_try_cmpxchg(&net->ipv4.icmp_global_credit, &old, new)); } - WRITE_ONCE(icmp_global.credit, credit); - spin_unlock(&icmp_global.lock); - return rc; + return true; } EXPORT_SYMBOL(icmp_global_allow); +void icmp_global_consume(struct net *net) +{ + int credits = get_random_u32_below(3); + + /* Note: this might make icmp_global.credit negative. */ + if (credits) + atomic_sub(credits, &net->ipv4.icmp_global_credit); +} +EXPORT_SYMBOL(icmp_global_consume); + static bool icmpv4_mask_allow(struct net *net, int type, int code) { if (type > NR_ICMP_TYPES) @@ -291,14 +287,16 @@ static bool icmpv4_mask_allow(struct net *net, int type, int code) return false; } -static bool icmpv4_global_allow(struct net *net, int type, int code) +static bool icmpv4_global_allow(struct net *net, int type, int code, + bool *apply_ratelimit) { if (icmpv4_mask_allow(net, type, code)) return true; - if (icmp_global_allow()) + if (icmp_global_allow(net)) { + *apply_ratelimit = true; return true; - + } __ICMP_INC_STATS(net, ICMP_MIB_RATELIMITGLOBAL); return false; } @@ -308,15 +306,16 @@ static bool icmpv4_global_allow(struct net *net, int type, int code) */ static bool icmpv4_xrlim_allow(struct net *net, struct rtable *rt, - struct flowi4 *fl4, int type, int code) + struct flowi4 *fl4, int type, int code, + bool apply_ratelimit) { struct dst_entry *dst = &rt->dst; struct inet_peer *peer; bool rc = true; int vif; - if (icmpv4_mask_allow(net, type, code)) - goto out; + if (!apply_ratelimit) + return true; /* No rate limit on loopback */ if (dst->dev && (dst->dev->flags&IFF_LOOPBACK)) @@ -331,6 +330,8 @@ static bool icmpv4_xrlim_allow(struct net *net, struct rtable *rt, out: if (!rc) __ICMP_INC_STATS(net, ICMP_MIB_RATELIMITHOST); + else + icmp_global_consume(net); return rc; } @@ -402,6 +403,7 @@ static void icmp_reply(struct icmp_bxm *icmp_param, struct sk_buff *skb) struct ipcm_cookie ipc; struct rtable *rt = skb_rtable(skb); struct net *net = dev_net(rt->dst.dev); + bool apply_ratelimit = false; struct flowi4 fl4; struct sock *sk; struct inet_sock *inet; @@ -413,11 +415,11 @@ static void icmp_reply(struct icmp_bxm *icmp_param, struct sk_buff *skb) if (ip_options_echo(net, &icmp_param->replyopts.opt.opt, skb)) return; - /* Needed by both icmp_global_allow and icmp_xmit_lock */ + /* Needed by both icmpv4_global_allow and icmp_xmit_lock */ local_bh_disable(); - /* global icmp_msgs_per_sec */ - if (!icmpv4_global_allow(net, type, code)) + /* is global icmp_msgs_per_sec exhausted ? */ + if (!icmpv4_global_allow(net, type, code, &apply_ratelimit)) goto out_bh_enable; sk = icmp_xmit_lock(net); @@ -443,14 +445,14 @@ static void icmp_reply(struct icmp_bxm *icmp_param, struct sk_buff *skb) fl4.saddr = saddr; fl4.flowi4_mark = mark; fl4.flowi4_uid = sock_net_uid(net, NULL); - fl4.flowi4_tos = RT_TOS(ip_hdr(skb)->tos); + fl4.flowi4_tos = ip_hdr(skb)->tos & INET_DSCP_MASK; fl4.flowi4_proto = IPPROTO_ICMP; fl4.flowi4_oif = l3mdev_master_ifindex(skb->dev); security_skb_classify_flow(skb, flowi4_to_flowi_common(&fl4)); rt = ip_route_output_key(net, &fl4); if (IS_ERR(rt)) goto out_unlock; - if (icmpv4_xrlim_allow(net, rt, &fl4, type, code)) + if (icmpv4_xrlim_allow(net, rt, &fl4, type, code, apply_ratelimit)) icmp_push_reply(sk, icmp_param, &fl4, &ipc, &rt); ip_rt_put(rt); out_unlock: @@ -496,7 +498,7 @@ static struct rtable *icmp_route_lookup(struct net *net, fl4->saddr = saddr; fl4->flowi4_mark = mark; fl4->flowi4_uid = sock_net_uid(net, NULL); - fl4->flowi4_tos = RT_TOS(tos); + fl4->flowi4_tos = tos & INET_DSCP_MASK; fl4->flowi4_proto = IPPROTO_ICMP; fl4->fl4_icmp_type = type; fl4->fl4_icmp_code = code; @@ -545,7 +547,7 @@ static struct rtable *icmp_route_lookup(struct net *net, orefdst = skb_in->_skb_refdst; /* save old refdst */ skb_dst_set(skb_in, NULL); err = ip_route_input(skb_in, fl4_dec.daddr, fl4_dec.saddr, - RT_TOS(tos), rt2->dst.dev); + tos, rt2->dst.dev); dst_release(&rt2->dst); rt2 = skb_rtable(skb_in); @@ -596,6 +598,7 @@ void __icmp_send(struct sk_buff *skb_in, int type, int code, __be32 info, int room; struct icmp_bxm icmp_param; struct rtable *rt = skb_rtable(skb_in); + bool apply_ratelimit = false; struct ipcm_cookie ipc; struct flowi4 fl4; __be32 saddr; @@ -677,7 +680,7 @@ void __icmp_send(struct sk_buff *skb_in, int type, int code, __be32 info, } } - /* Needed by both icmp_global_allow and icmp_xmit_lock */ + /* Needed by both icmpv4_global_allow and icmp_xmit_lock */ local_bh_disable(); /* Check global sysctl_icmp_msgs_per_sec ratelimit, unless @@ -685,7 +688,7 @@ void __icmp_send(struct sk_buff *skb_in, int type, int code, __be32 info, * loopback, then peer ratelimit still work (in icmpv4_xrlim_allow) */ if (!(skb_in->dev && (skb_in->dev->flags&IFF_LOOPBACK)) && - !icmpv4_global_allow(net, type, code)) + !icmpv4_global_allow(net, type, code, &apply_ratelimit)) goto out_bh_enable; sk = icmp_xmit_lock(net); @@ -744,7 +747,7 @@ void __icmp_send(struct sk_buff *skb_in, int type, int code, __be32 info, goto out_unlock; /* peer icmp_ratelimit */ - if (!icmpv4_xrlim_allow(net, rt, &fl4, type, code)) + if (!icmpv4_xrlim_allow(net, rt, &fl4, type, code, apply_ratelimit)) goto ende; /* RFC says return as much as we can without exceeding 576 bytes. */ @@ -1487,6 +1490,8 @@ static int __net_init icmp_sk_init(struct net *net) net->ipv4.sysctl_icmp_ratelimit = 1 * HZ; net->ipv4.sysctl_icmp_ratemask = 0x1818; net->ipv4.sysctl_icmp_errors_use_inbound_ifaddr = 0; + net->ipv4.sysctl_icmp_msgs_per_sec = 1000; + net->ipv4.sysctl_icmp_msgs_burst = 50; return 0; } diff --git a/net/ipv4/inet_connection_sock.c b/net/ipv4/inet_connection_sock.c index d81f74ce0f02..2c5632d4fddb 100644 --- a/net/ipv4/inet_connection_sock.c +++ b/net/ipv4/inet_connection_sock.c @@ -236,7 +236,7 @@ static bool inet_bhash2_conflict(const struct sock *sk, #define sk_for_each_bound_bhash(__sk, __tb2, __tb) \ hlist_for_each_entry(__tb2, &(__tb)->bhash2, bhash_node) \ - sk_for_each_bound(sk2, &(__tb2)->owners) + sk_for_each_bound((__sk), &(__tb2)->owners) /* This should be called only when the tb and tb2 hashbuckets' locks are held */ static int inet_csk_bind_conflict(const struct sock *sk, @@ -714,6 +714,7 @@ struct sock *inet_csk_accept(struct sock *sk, struct proto_accept_arg *arg) out: release_sock(sk); if (newsk && mem_cgroup_sockets_enabled) { + gfp_t gfp = GFP_KERNEL | __GFP_NOFAIL; int amt = 0; /* atomically get the memory usage, set and charge the @@ -731,8 +732,8 @@ out: } if (amt) - mem_cgroup_charge_skmem(newsk->sk_memcg, amt, - GFP_KERNEL | __GFP_NOFAIL); + mem_cgroup_charge_skmem(newsk->sk_memcg, amt, gfp); + kmem_cache_charge(newsk, gfp); release_sock(newsk); } @@ -911,6 +912,64 @@ int inet_rtx_syn_ack(const struct sock *parent, struct request_sock *req) } EXPORT_SYMBOL(inet_rtx_syn_ack); +static struct request_sock * +reqsk_alloc_noprof(const struct request_sock_ops *ops, struct sock *sk_listener, + bool attach_listener) +{ + struct request_sock *req; + + req = kmem_cache_alloc_noprof(ops->slab, GFP_ATOMIC | __GFP_NOWARN); + if (!req) + return NULL; + req->rsk_listener = NULL; + if (attach_listener) { + if (unlikely(!refcount_inc_not_zero(&sk_listener->sk_refcnt))) { + kmem_cache_free(ops->slab, req); + return NULL; + } + req->rsk_listener = sk_listener; + } + req->rsk_ops = ops; + req_to_sk(req)->sk_prot = sk_listener->sk_prot; + sk_node_init(&req_to_sk(req)->sk_node); + sk_tx_queue_clear(req_to_sk(req)); + req->saved_syn = NULL; + req->syncookie = 0; + req->timeout = 0; + req->num_timeout = 0; + req->num_retrans = 0; + req->sk = NULL; + refcount_set(&req->rsk_refcnt, 0); + + return req; +} +#define reqsk_alloc(...) alloc_hooks(reqsk_alloc_noprof(__VA_ARGS__)) + +struct request_sock *inet_reqsk_alloc(const struct request_sock_ops *ops, + struct sock *sk_listener, + bool attach_listener) +{ + struct request_sock *req = reqsk_alloc(ops, sk_listener, + attach_listener); + + if (req) { + struct inet_request_sock *ireq = inet_rsk(req); + + ireq->ireq_opt = NULL; +#if IS_ENABLED(CONFIG_IPV6) + ireq->pktopts = NULL; +#endif + atomic64_set(&ireq->ir_cookie, 0); + ireq->ireq_state = TCP_NEW_SYN_RECV; + write_pnet(&ireq->ireq_net, sock_net(sk_listener)); + ireq->ireq_family = sk_listener->sk_family; + req->timeout = TCP_TIMEOUT_INIT; + } + + return req; +} +EXPORT_SYMBOL(inet_reqsk_alloc); + static struct request_sock *inet_reqsk_clone(struct request_sock *req, struct sock *sk) { @@ -1122,25 +1181,34 @@ drop: inet_csk_reqsk_queue_drop_and_put(oreq->rsk_listener, oreq); } -static void reqsk_queue_hash_req(struct request_sock *req, +static bool reqsk_queue_hash_req(struct request_sock *req, unsigned long timeout) { + bool found_dup_sk = false; + + if (!inet_ehash_insert(req_to_sk(req), NULL, &found_dup_sk)) + return false; + + /* The timer needs to be setup after a successful insertion. */ timer_setup(&req->rsk_timer, reqsk_timer_handler, TIMER_PINNED); mod_timer(&req->rsk_timer, jiffies + timeout); - inet_ehash_insert(req_to_sk(req), NULL, NULL); /* before letting lookups find us, make sure all req fields * are committed to memory and refcnt initialized. */ smp_wmb(); refcount_set(&req->rsk_refcnt, 2 + 1); + return true; } -void inet_csk_reqsk_queue_hash_add(struct sock *sk, struct request_sock *req, +bool inet_csk_reqsk_queue_hash_add(struct sock *sk, struct request_sock *req, unsigned long timeout) { - reqsk_queue_hash_req(req, timeout); + if (!reqsk_queue_hash_req(req, timeout)) + return false; + inet_csk_reqsk_queue_added(sk); + return true; } EXPORT_SYMBOL_GPL(inet_csk_reqsk_queue_hash_add); diff --git a/net/ipv4/inet_diag.c b/net/ipv4/inet_diag.c index 7adace541fe2..67639309163d 100644 --- a/net/ipv4/inet_diag.c +++ b/net/ipv4/inet_diag.c @@ -442,7 +442,7 @@ static int inet_twsk_diag_fill(struct sock *sk, inet_diag_msg_common_fill(r, sk); r->idiag_retrans = 0; - r->idiag_state = tw->tw_substate; + r->idiag_state = READ_ONCE(tw->tw_substate); r->idiag_timer = 3; tmo = tw->tw_timer.expires - jiffies; r->idiag_expires = jiffies_delta_to_msecs(tmo); @@ -1209,7 +1209,7 @@ next_chunk: if (num < s_num) goto next_normal; state = (sk->sk_state == TCP_TIME_WAIT) ? - inet_twsk(sk)->tw_substate : sk->sk_state; + READ_ONCE(inet_twsk(sk)->tw_substate) : sk->sk_state; if (!(idiag_states & (1 << state))) goto next_normal; if (r->sdiag_family != AF_UNSPEC && @@ -1383,6 +1383,7 @@ static int inet_diag_dump_compat(struct sk_buff *skb, req.sdiag_family = AF_UNSPEC; /* compatibility */ req.sdiag_protocol = inet_diag_type2proto(cb->nlh->nlmsg_type); req.idiag_ext = rc->idiag_ext; + req.pad = 0; req.idiag_states = rc->idiag_states; req.id = rc->id; @@ -1398,6 +1399,7 @@ static int inet_diag_get_exact_compat(struct sk_buff *in_skb, req.sdiag_family = rc->idiag_family; req.sdiag_protocol = inet_diag_type2proto(nlh->nlmsg_type); req.idiag_ext = rc->idiag_ext; + req.pad = 0; req.idiag_states = rc->idiag_states; req.id = rc->id; diff --git a/net/ipv4/inet_fragment.c b/net/ipv4/inet_fragment.c index faaec92a46ac..d179a2c84222 100644 --- a/net/ipv4/inet_fragment.c +++ b/net/ipv4/inet_fragment.c @@ -619,7 +619,7 @@ void inet_frag_reasm_finish(struct inet_frag_queue *q, struct sk_buff *head, skb_mark_not_on_list(head); head->prev = NULL; head->tstamp = q->stamp; - head->mono_delivery_time = q->mono_delivery_time; + head->tstamp_type = q->tstamp_type; if (sk) refcount_add(sum_truesize - head_truesize, &sk->sk_wmem_alloc); diff --git a/net/ipv4/inet_hashtables.c b/net/ipv4/inet_hashtables.c index 48d0d494185b..9bfcfd016e18 100644 --- a/net/ipv4/inet_hashtables.c +++ b/net/ipv4/inet_hashtables.c @@ -310,7 +310,7 @@ inet_lhash2_bucket_sk(struct inet_hashinfo *h, struct sock *sk) return inet_lhash2_bucket(h, hash); } -static inline int compute_score(struct sock *sk, struct net *net, +static inline int compute_score(struct sock *sk, const struct net *net, const unsigned short hnum, const __be32 daddr, const int dif, const int sdif) { @@ -348,7 +348,7 @@ static inline int compute_score(struct sock *sk, struct net *net, * Return: NULL if sk doesn't have SO_REUSEPORT set, otherwise a pointer to * the selected sock or an error. */ -struct sock *inet_lookup_reuseport(struct net *net, struct sock *sk, +struct sock *inet_lookup_reuseport(const struct net *net, struct sock *sk, struct sk_buff *skb, int doff, __be32 saddr, __be16 sport, __be32 daddr, unsigned short hnum, @@ -374,7 +374,7 @@ EXPORT_SYMBOL_GPL(inet_lookup_reuseport); */ /* called with rcu_read_lock() : No refcount taken on the socket */ -static struct sock *inet_lhash2_lookup(struct net *net, +static struct sock *inet_lhash2_lookup(const struct net *net, struct inet_listen_hashbucket *ilb2, struct sk_buff *skb, int doff, const __be32 saddr, __be16 sport, @@ -401,7 +401,7 @@ static struct sock *inet_lhash2_lookup(struct net *net, return result; } -struct sock *inet_lookup_run_sk_lookup(struct net *net, +struct sock *inet_lookup_run_sk_lookup(const struct net *net, int protocol, struct sk_buff *skb, int doff, __be32 saddr, __be16 sport, @@ -423,7 +423,7 @@ struct sock *inet_lookup_run_sk_lookup(struct net *net, return sk; } -struct sock *__inet_lookup_listener(struct net *net, +struct sock *__inet_lookup_listener(const struct net *net, struct inet_hashinfo *hashinfo, struct sk_buff *skb, int doff, const __be32 saddr, __be16 sport, @@ -488,7 +488,7 @@ void sock_edemux(struct sk_buff *skb) } EXPORT_SYMBOL(sock_edemux); -struct sock *__inet_lookup_established(struct net *net, +struct sock *__inet_lookup_established(const struct net *net, struct inet_hashinfo *hashinfo, const __be32 saddr, const __be16 sport, const __be32 daddr, const u16 hnum, diff --git a/net/ipv4/inet_timewait_sock.c b/net/ipv4/inet_timewait_sock.c index e28075f0006e..337390ba85b4 100644 --- a/net/ipv4/inet_timewait_sock.c +++ b/net/ipv4/inet_timewait_sock.c @@ -92,13 +92,22 @@ static void inet_twsk_add_node_rcu(struct inet_timewait_sock *tw, hlist_nulls_add_head_rcu(&tw->tw_node, list); } +static void inet_twsk_schedule(struct inet_timewait_sock *tw, int timeo) +{ + __inet_twsk_schedule(tw, timeo, false); +} + /* - * Enter the time wait state. This is called with locally disabled BH. + * Enter the time wait state. * Essentially we whip up a timewait bucket, copy the relevant info into it * from the SK, and mess with hash chains and list linkage. + * + * The caller must not access @tw anymore after this function returns. */ -void inet_twsk_hashdance(struct inet_timewait_sock *tw, struct sock *sk, - struct inet_hashinfo *hashinfo) +void inet_twsk_hashdance_schedule(struct inet_timewait_sock *tw, + struct sock *sk, + struct inet_hashinfo *hashinfo, + int timeo) { const struct inet_sock *inet = inet_sk(sk); const struct inet_connection_sock *icsk = inet_csk(sk); @@ -114,6 +123,7 @@ void inet_twsk_hashdance(struct inet_timewait_sock *tw, struct sock *sk, hashinfo->bhash_size)]; bhead2 = inet_bhashfn_portaddr(hashinfo, sk, twsk_net(tw), inet->inet_num); + local_bh_disable(); spin_lock(&bhead->lock); spin_lock(&bhead2->lock); @@ -129,26 +139,34 @@ void inet_twsk_hashdance(struct inet_timewait_sock *tw, struct sock *sk, spin_lock(lock); + /* Step 2: Hash TW into tcp ehash chain */ inet_twsk_add_node_rcu(tw, &ehead->chain); /* Step 3: Remove SK from hash chain */ if (__sk_nulls_del_node_init_rcu(sk)) sock_prot_inuse_add(sock_net(sk), sk->sk_prot, -1); - spin_unlock(lock); + /* Ensure above writes are committed into memory before updating the + * refcount. + * Provides ordering vs later refcount_inc(). + */ + smp_wmb(); /* tw_refcnt is set to 3 because we have : * - one reference for bhash chain. * - one reference for ehash chain. * - one reference for timer. - * We can use atomic_set() because prior spin_lock()/spin_unlock() - * committed into memory all tw fields. * Also note that after this point, we lost our implicit reference * so we are not allowed to use tw anymore. */ refcount_set(&tw->tw_refcnt, 3); + + inet_twsk_schedule(tw, timeo); + + spin_unlock(lock); + local_bh_enable(); } -EXPORT_SYMBOL_GPL(inet_twsk_hashdance); +EXPORT_SYMBOL_GPL(inet_twsk_hashdance_schedule); static void tw_timer_handler(struct timer_list *t) { @@ -192,7 +210,7 @@ struct inet_timewait_sock *inet_twsk_alloc(const struct sock *sk, tw->tw_prot = sk->sk_prot_creator; atomic64_set(&tw->tw_cookie, atomic64_read(&sk->sk_cookie)); twsk_net_set(tw, sock_net(sk)); - timer_setup(&tw->tw_timer, tw_timer_handler, TIMER_PINNED); + timer_setup(&tw->tw_timer, tw_timer_handler, 0); /* * Because we use RCU lookups, we should not set tw_refcnt * to a non null value before everything is setup for this @@ -217,7 +235,34 @@ EXPORT_SYMBOL_GPL(inet_twsk_alloc); */ void inet_twsk_deschedule_put(struct inet_timewait_sock *tw) { - if (del_timer_sync(&tw->tw_timer)) + struct inet_hashinfo *hashinfo = tw->tw_dr->hashinfo; + spinlock_t *lock = inet_ehash_lockp(hashinfo, tw->tw_hash); + + /* inet_twsk_purge() walks over all sockets, including tw ones, + * and removes them via inet_twsk_deschedule_put() after a + * refcount_inc_not_zero(). + * + * inet_twsk_hashdance_schedule() must (re)init the refcount before + * arming the timer, i.e. inet_twsk_purge can obtain a reference to + * a twsk that did not yet schedule the timer. + * + * The ehash lock synchronizes these two: + * After acquiring the lock, the timer is always scheduled (else + * timer_shutdown returns false), because hashdance_schedule releases + * the ehash lock only after completing the timer initialization. + * + * Without grabbing the ehash lock, we get: + * 1) cpu x sets twsk refcount to 3 + * 2) cpu y bumps refcount to 4 + * 3) cpu y calls inet_twsk_deschedule_put() and shuts timer down + * 4) cpu x tries to start timer, but mod_timer is a noop post-shutdown + * -> timer refcount is never decremented. + */ + spin_lock(lock); + /* Makes sure hashdance_schedule() has completed */ + spin_unlock(lock); + + if (timer_shutdown_sync(&tw->tw_timer)) inet_twsk_kill(tw); inet_twsk_put(tw); } diff --git a/net/ipv4/ip_fragment.c b/net/ipv4/ip_fragment.c index 08e2c92e25ab..a92664a5ef2e 100644 --- a/net/ipv4/ip_fragment.c +++ b/net/ipv4/ip_fragment.c @@ -355,7 +355,7 @@ static int ip_frag_queue(struct ipq *qp, struct sk_buff *skb) qp->iif = dev->ifindex; qp->q.stamp = skb->tstamp; - qp->q.mono_delivery_time = skb->mono_delivery_time; + qp->q.tstamp_type = skb->tstamp_type; qp->q.meat += skb->len; qp->ecn |= ecn; add_frag_mem_limit(qp->q.fqdir, skb->truesize); diff --git a/net/ipv4/ip_gre.c b/net/ipv4/ip_gre.c index ba205473522e..5f6fd382af38 100644 --- a/net/ipv4/ip_gre.c +++ b/net/ipv4/ip_gre.c @@ -44,6 +44,7 @@ #include <net/gre.h> #include <net/dst_metadata.h> #include <net/erspan.h> +#include <net/inet_dscp.h> /* Problems & solutions @@ -930,7 +931,7 @@ static int ipgre_open(struct net_device *dev) t->parms.iph.daddr, t->parms.iph.saddr, t->parms.o_key, - RT_TOS(t->parms.iph.tos), + t->parms.iph.tos & INET_DSCP_MASK, t->parms.link); if (IS_ERR(rt)) return -EADDRNOTAVAIL; @@ -996,7 +997,7 @@ static void __gre_tunnel_init(struct net_device *dev) tunnel->hlen = tunnel->tun_hlen + tunnel->encap_hlen; dev->needed_headroom = tunnel->hlen + sizeof(tunnel->parms.iph); - dev->features |= GRE_FEATURES | NETIF_F_LLTX; + dev->features |= GRE_FEATURES; dev->hw_features |= GRE_FEATURES; /* TCP offload with GRE SEQ is not supported, nor can we support 2 @@ -1010,6 +1011,8 @@ static void __gre_tunnel_init(struct net_device *dev) dev->features |= NETIF_F_GSO_SOFTWARE; dev->hw_features |= NETIF_F_GSO_SOFTWARE; + + dev->lltx = true; } static int ipgre_tunnel_init(struct net_device *dev) diff --git a/net/ipv4/ip_input.c b/net/ipv4/ip_input.c index d6fbcbd2358a..b6e7d4921309 100644 --- a/net/ipv4/ip_input.c +++ b/net/ipv4/ip_input.c @@ -596,9 +596,8 @@ static void ip_list_rcv_finish(struct net *net, struct sock *sk, { struct sk_buff *skb, *next, *hint = NULL; struct dst_entry *curr_dst = NULL; - struct list_head sublist; + LIST_HEAD(sublist); - INIT_LIST_HEAD(&sublist); list_for_each_entry_safe(skb, next, head, list) { struct net_device *dev = skb->dev; struct dst_entry *dst; @@ -646,9 +645,8 @@ void ip_list_rcv(struct list_head *head, struct packet_type *pt, struct net_device *curr_dev = NULL; struct net *curr_net = NULL; struct sk_buff *skb, *next; - struct list_head sublist; + LIST_HEAD(sublist); - INIT_LIST_HEAD(&sublist); list_for_each_entry_safe(skb, next, head, list) { struct net_device *dev = skb->dev; struct net *net = dev_net(dev); diff --git a/net/ipv4/ip_output.c b/net/ipv4/ip_output.c index 9500031a1f55..49811c9281d4 100644 --- a/net/ipv4/ip_output.c +++ b/net/ipv4/ip_output.c @@ -77,6 +77,7 @@ #include <net/inetpeer.h> #include <net/inet_ecn.h> #include <net/lwtunnel.h> +#include <net/inet_dscp.h> #include <linux/bpf-cgroup.h> #include <linux/igmp.h> #include <linux/netfilter_ipv4.h> @@ -493,7 +494,7 @@ int __ip_queue_xmit(struct sock *sk, struct sk_buff *skb, struct flowi *fl, inet->inet_dport, inet->inet_sport, sk->sk_protocol, - RT_TOS(tos), + tos & INET_DSCP_MASK, sk->sk_bound_dev_if); if (IS_ERR(rt)) goto no_route; @@ -764,7 +765,7 @@ int ip_do_fragment(struct net *net, struct sock *sk, struct sk_buff *skb, { struct iphdr *iph; struct sk_buff *skb2; - bool mono_delivery_time = skb->mono_delivery_time; + u8 tstamp_type = skb->tstamp_type; struct rtable *rt = skb_rtable(skb); unsigned int mtu, hlen, ll_rs; struct ip_fraglist_iter iter; @@ -856,7 +857,7 @@ int ip_do_fragment(struct net *net, struct sock *sk, struct sk_buff *skb, } } - skb_set_delivery_time(skb, tstamp, mono_delivery_time); + skb_set_delivery_time(skb, tstamp, tstamp_type); err = output(net, sk, skb); if (!err) @@ -912,7 +913,7 @@ slow_path: /* * Put this fragment into the sending queue. */ - skb_set_delivery_time(skb2, tstamp, mono_delivery_time); + skb_set_delivery_time(skb2, tstamp, tstamp_type); err = output(net, sk, skb2); if (err) goto fail; @@ -1457,7 +1458,10 @@ struct sk_buff *__ip_make_skb(struct sock *sk, skb->priority = (cork->tos != -1) ? cork->priority: READ_ONCE(sk->sk_priority); skb->mark = cork->mark; - skb->tstamp = cork->transmit_time; + if (sk_is_tcp(sk)) + skb_set_delivery_time(skb, cork->transmit_time, SKB_CLOCK_MONOTONIC); + else + skb_set_delivery_type_by_clockid(skb, cork->transmit_time, sk->sk_clockid); /* * Steal rt from cork.dst to avoid a pair of atomic_inc/atomic_dec * on dst refcount @@ -1618,7 +1622,7 @@ void ip_send_unicast_reply(struct sock *sk, struct sk_buff *skb, flowi4_init_output(&fl4, oif, IP4_REPLY_MARK(net, skb->mark) ?: sk->sk_mark, - RT_TOS(arg->tos), + arg->tos & INET_DSCP_MASK, RT_SCOPE_UNIVERSE, ip_hdr(skb)->protocol, ip_reply_arg_flowi_flags(arg), daddr, saddr, @@ -1649,7 +1653,8 @@ void ip_send_unicast_reply(struct sock *sk, struct sk_buff *skb, arg->csumoffset) = csum_fold(csum_add(nskb->csum, arg->csum)); nskb->ip_summed = CHECKSUM_NONE; - nskb->mono_delivery_time = !!transmit_time; + if (transmit_time) + nskb->tstamp_type = SKB_CLOCK_MONOTONIC; if (txhash) skb_set_hash(nskb, txhash, PKT_HASH_TYPE_L4); ip_push_pending_frames(sk, &fl4); diff --git a/net/ipv4/ip_tunnel.c b/net/ipv4/ip_tunnel.c index bccef2fcf620..d591c73e2c0e 100644 --- a/net/ipv4/ip_tunnel.c +++ b/net/ipv4/ip_tunnel.c @@ -43,6 +43,7 @@ #include <net/rtnetlink.h> #include <net/udp.h> #include <net/dst_metadata.h> +#include <net/inet_dscp.h> #if IS_ENABLED(CONFIG_IPV6) #include <net/ipv6.h> @@ -293,7 +294,7 @@ static int ip_tunnel_bind_dev(struct net_device *dev) ip_tunnel_init_flow(&fl4, iph->protocol, iph->daddr, iph->saddr, tunnel->parms.o_key, - RT_TOS(iph->tos), dev_net(dev), + iph->tos & INET_DSCP_MASK, dev_net(dev), tunnel->parms.link, tunnel->fwmark, 0, 0); rt = ip_route_output_key(tunnel->net, &fl4); @@ -609,9 +610,9 @@ void ip_md_tunnel_xmit(struct sk_buff *skb, struct net_device *dev, tos = ipv6_get_dsfield((const struct ipv6hdr *)inner_iph); } ip_tunnel_init_flow(&fl4, proto, key->u.ipv4.dst, key->u.ipv4.src, - tunnel_id_to_key32(key->tun_id), RT_TOS(tos), - dev_net(dev), 0, skb->mark, skb_get_hash(skb), - key->flow_flags); + tunnel_id_to_key32(key->tun_id), + tos & INET_DSCP_MASK, dev_net(dev), 0, skb->mark, + skb_get_hash(skb), key->flow_flags); if (!tunnel_hlen) tunnel_hlen = ip_encap_hlen(&tun_info->encap); @@ -772,7 +773,7 @@ void ip_tunnel_xmit(struct sk_buff *skb, struct net_device *dev, } ip_tunnel_init_flow(&fl4, protocol, dst, tnl_params->saddr, - tunnel->parms.o_key, RT_TOS(tos), + tunnel->parms.o_key, tos & INET_DSCP_MASK, dev_net(dev), READ_ONCE(tunnel->parms.link), tunnel->fwmark, skb_get_hash(skb), 0); @@ -1099,7 +1100,6 @@ static void ip_tunnel_dev_free(struct net_device *dev) gro_cells_destroy(&tunnel->gro_cells); dst_cache_destroy(&tunnel->dst_cache); - free_percpu(dev->tstats); } void ip_tunnel_dellink(struct net_device *dev, struct list_head *head) @@ -1162,7 +1162,7 @@ int ip_tunnel_init_net(struct net *net, unsigned int ip_tnl_net_id, * Allowing to move it to another netns is clearly unsafe. */ if (!IS_ERR(itn->fb_tunnel_dev)) { - itn->fb_tunnel_dev->features |= NETIF_F_NETNS_LOCAL; + itn->fb_tunnel_dev->netns_local = true; itn->fb_tunnel_dev->mtu = ip_tunnel_bind_dev(itn->fb_tunnel_dev); ip_tunnel_add(itn, netdev_priv(itn->fb_tunnel_dev)); itn->type = itn->fb_tunnel_dev->type; @@ -1313,26 +1313,21 @@ int ip_tunnel_init(struct net_device *dev) dev->needs_free_netdev = true; dev->priv_destructor = ip_tunnel_dev_free; - dev->tstats = netdev_alloc_pcpu_stats(struct pcpu_sw_netstats); - if (!dev->tstats) - return -ENOMEM; + dev->pcpu_stat_type = NETDEV_PCPU_STAT_TSTATS; err = dst_cache_init(&tunnel->dst_cache, GFP_KERNEL); - if (err) { - free_percpu(dev->tstats); + if (err) return err; - } err = gro_cells_init(&tunnel->gro_cells, dev); if (err) { dst_cache_destroy(&tunnel->dst_cache); - free_percpu(dev->tstats); return err; } tunnel->dev = dev; tunnel->net = dev_net(dev); - strcpy(tunnel->parms.name, dev->name); + strscpy(tunnel->parms.name, dev->name); iph->version = 4; iph->ihl = 5; diff --git a/net/ipv4/ip_vti.c b/net/ipv4/ip_vti.c index 14536da9f5dc..f0b4419cef34 100644 --- a/net/ipv4/ip_vti.c +++ b/net/ipv4/ip_vti.c @@ -443,7 +443,7 @@ static int vti_tunnel_init(struct net_device *dev) dev->flags = IFF_NOARP; dev->addr_len = 4; - dev->features |= NETIF_F_LLTX; + dev->lltx = true; netif_keep_dst(dev); return ip_tunnel_init(dev); diff --git a/net/ipv4/ipip.c b/net/ipv4/ipip.c index 923a2ef68c2f..dc0db5895e0e 100644 --- a/net/ipv4/ipip.c +++ b/net/ipv4/ipip.c @@ -378,7 +378,7 @@ static void ipip_tunnel_setup(struct net_device *dev) dev->type = ARPHRD_TUNNEL; dev->flags = IFF_NOARP; dev->addr_len = 4; - dev->features |= NETIF_F_LLTX; + dev->lltx = true; netif_keep_dst(dev); dev->features |= IPIP_FEATURES; diff --git a/net/ipv4/ipmr.c b/net/ipv4/ipmr.c index 6c750bd13dd8..089864c6a35e 100644 --- a/net/ipv4/ipmr.c +++ b/net/ipv4/ipmr.c @@ -62,6 +62,7 @@ #include <net/fib_rules.h> #include <linux/netconf.h> #include <net/rtnh.h> +#include <net/inet_dscp.h> #include <linux/nospec.h> @@ -536,7 +537,7 @@ static void reg_vif_setup(struct net_device *dev) dev->flags = IFF_NOARP; dev->netdev_ops = ®_vif_netdev_ops; dev->needs_free_netdev = true; - dev->features |= NETIF_F_NETNS_LOCAL; + dev->netns_local = true; } static struct net_device *ipmr_reg_vif(struct net *net, struct mr_table *mrt) @@ -1868,7 +1869,7 @@ static void ipmr_queue_xmit(struct net *net, struct mr_table *mrt, vif->remote, vif->local, 0, 0, IPPROTO_IPIP, - RT_TOS(iph->tos), vif->link); + iph->tos & INET_DSCP_MASK, vif->link); if (IS_ERR(rt)) goto out_free; encap = sizeof(struct iphdr); @@ -1876,7 +1877,7 @@ static void ipmr_queue_xmit(struct net *net, struct mr_table *mrt, rt = ip_route_output_ports(net, &fl4, NULL, iph->daddr, 0, 0, 0, IPPROTO_IPIP, - RT_TOS(iph->tos), vif->link); + iph->tos & INET_DSCP_MASK, vif->link); if (IS_ERR(rt)) goto out_free; } @@ -2080,7 +2081,7 @@ static struct mr_table *ipmr_rt_fib_lookup(struct net *net, struct sk_buff *skb) struct flowi4 fl4 = { .daddr = iph->daddr, .saddr = iph->saddr, - .flowi4_tos = RT_TOS(iph->tos), + .flowi4_tos = iph->tos & INET_DSCP_MASK, .flowi4_oif = (rt_is_output_route(rt) ? skb->dev->ifindex : 0), .flowi4_iif = (rt_is_output_route(rt) ? @@ -2406,8 +2407,7 @@ static void mroute_netlink_event(struct mr_table *mrt, struct mfc_cache *mfc, errout: kfree_skb(skb); - if (err < 0) - rtnl_set_sk_err(net, RTNLGRP_IPV4_MROUTE, err); + rtnl_set_sk_err(net, RTNLGRP_IPV4_MROUTE, err); } static size_t igmpmsg_netlink_msgsize(size_t payloadlen) diff --git a/net/ipv4/metrics.c b/net/ipv4/metrics.c index 0e3ee1532848..8ddac1f595ed 100644 --- a/net/ipv4/metrics.c +++ b/net/ipv4/metrics.c @@ -7,7 +7,7 @@ #include <net/net_namespace.h> #include <net/tcp.h> -static int ip_metrics_convert(struct net *net, struct nlattr *fc_mx, +static int ip_metrics_convert(struct nlattr *fc_mx, int fc_mx_len, u32 *metrics, struct netlink_ext_ack *extack) { @@ -31,7 +31,7 @@ static int ip_metrics_convert(struct net *net, struct nlattr *fc_mx, char tmp[TCP_CA_NAME_MAX]; nla_strscpy(tmp, nla, sizeof(tmp)); - val = tcp_ca_get_key_by_name(net, tmp, &ecn_ca); + val = tcp_ca_get_key_by_name(tmp, &ecn_ca); if (val == TCP_CA_UNSPEC) { NL_SET_ERR_MSG(extack, "Unknown tcp congestion algorithm"); return -EINVAL; @@ -63,7 +63,7 @@ static int ip_metrics_convert(struct net *net, struct nlattr *fc_mx, return 0; } -struct dst_metrics *ip_fib_metrics_init(struct net *net, struct nlattr *fc_mx, +struct dst_metrics *ip_fib_metrics_init(struct nlattr *fc_mx, int fc_mx_len, struct netlink_ext_ack *extack) { @@ -77,7 +77,7 @@ struct dst_metrics *ip_fib_metrics_init(struct net *net, struct nlattr *fc_mx, if (unlikely(!fib_metrics)) return ERR_PTR(-ENOMEM); - err = ip_metrics_convert(net, fc_mx, fc_mx_len, fib_metrics->metrics, + err = ip_metrics_convert(fc_mx, fc_mx_len, fib_metrics->metrics, extack); if (!err) { refcount_set(&fib_metrics->refcnt, 1); diff --git a/net/ipv4/netfilter.c b/net/ipv4/netfilter.c index 591a2737808e..e0aab66cd925 100644 --- a/net/ipv4/netfilter.c +++ b/net/ipv4/netfilter.c @@ -14,6 +14,7 @@ #include <net/route.h> #include <net/xfrm.h> #include <net/ip.h> +#include <net/inet_dscp.h> #include <net/netfilter/nf_queue.h> /* route_me_harder function, used by iptable_nat, iptable_mangle + ip_queue */ @@ -43,7 +44,7 @@ int ip_route_me_harder(struct net *net, struct sock *sk, struct sk_buff *skb, un */ fl4.daddr = iph->daddr; fl4.saddr = saddr; - fl4.flowi4_tos = RT_TOS(iph->tos); + fl4.flowi4_tos = iph->tos & INET_DSCP_MASK; fl4.flowi4_oif = sk ? sk->sk_bound_dev_if : 0; fl4.flowi4_l3mdev = l3mdev_master_ifindex(dev); fl4.flowi4_mark = skb->mark; diff --git a/net/ipv4/netfilter/arp_tables.c b/net/ipv4/netfilter/arp_tables.c index 14365b20f1c5..1cdd9c28ab2d 100644 --- a/net/ipv4/netfilter/arp_tables.c +++ b/net/ipv4/netfilter/arp_tables.c @@ -826,7 +826,7 @@ static int get_info(struct net *net, void __user *user, const int *len) sizeof(info.underflow)); info.num_entries = private->number; info.size = private->size; - strcpy(info.name, name); + strscpy(info.name, name); if (copy_to_user(user, &info, *len) != 0) ret = -EFAULT; @@ -1547,7 +1547,7 @@ int arpt_register_table(struct net *net, goto out_free; } - ops = kmemdup(template_ops, sizeof(*ops) * num_ops, GFP_KERNEL); + ops = kmemdup_array(template_ops, num_ops, sizeof(*ops), GFP_KERNEL); if (!ops) { ret = -ENOMEM; goto out_free; diff --git a/net/ipv4/netfilter/ip_tables.c b/net/ipv4/netfilter/ip_tables.c index fe89a056eb06..3d101613f27f 100644 --- a/net/ipv4/netfilter/ip_tables.c +++ b/net/ipv4/netfilter/ip_tables.c @@ -981,7 +981,7 @@ static int get_info(struct net *net, void __user *user, const int *len) sizeof(info.underflow)); info.num_entries = private->number; info.size = private->size; - strcpy(info.name, name); + strscpy(info.name, name); if (copy_to_user(user, &info, *len) != 0) ret = -EFAULT; @@ -1767,7 +1767,7 @@ int ipt_register_table(struct net *net, const struct xt_table *table, goto out_free; } - ops = kmemdup(template_ops, sizeof(*ops) * num_ops, GFP_KERNEL); + ops = kmemdup_array(template_ops, num_ops, sizeof(*ops), GFP_KERNEL); if (!ops) { ret = -ENOMEM; goto out_free; diff --git a/net/ipv4/netfilter/ipt_rpfilter.c b/net/ipv4/netfilter/ipt_rpfilter.c index ded5bef02f77..1ce7a1655b97 100644 --- a/net/ipv4/netfilter/ipt_rpfilter.c +++ b/net/ipv4/netfilter/ipt_rpfilter.c @@ -8,6 +8,7 @@ #include <linux/module.h> #include <linux/skbuff.h> #include <linux/netdevice.h> +#include <net/inet_dscp.h> #include <linux/ip.h> #include <net/ip.h> #include <net/ip_fib.h> @@ -75,7 +76,7 @@ static bool rpfilter_mt(const struct sk_buff *skb, struct xt_action_param *par) flow.daddr = iph->saddr; flow.saddr = rpfilter_get_saddr(iph->daddr); flow.flowi4_mark = info->flags & XT_RPFILTER_VALID_MARK ? skb->mark : 0; - flow.flowi4_tos = iph->tos & IPTOS_RT_MASK; + flow.flowi4_tos = iph->tos & INET_DSCP_MASK; flow.flowi4_scope = RT_SCOPE_UNIVERSE; flow.flowi4_l3mdev = l3mdev_master_ifindex_rcu(xt_in(par)); flow.flowi4_uid = sock_net_uid(xt_net(par), NULL); diff --git a/net/ipv4/netfilter/iptable_nat.c b/net/ipv4/netfilter/iptable_nat.c index 4d42d0756fd7..a5db7c67d61b 100644 --- a/net/ipv4/netfilter/iptable_nat.c +++ b/net/ipv4/netfilter/iptable_nat.c @@ -145,25 +145,27 @@ static struct pernet_operations iptable_nat_net_ops = { static int __init iptable_nat_init(void) { - int ret = xt_register_template(&nf_nat_ipv4_table, - iptable_nat_table_init); + int ret; + /* net->gen->ptr[iptable_nat_net_id] must be allocated + * before calling iptable_nat_table_init(). + */ + ret = register_pernet_subsys(&iptable_nat_net_ops); if (ret < 0) return ret; - ret = register_pernet_subsys(&iptable_nat_net_ops); - if (ret < 0) { - xt_unregister_template(&nf_nat_ipv4_table); - return ret; - } + ret = xt_register_template(&nf_nat_ipv4_table, + iptable_nat_table_init); + if (ret < 0) + unregister_pernet_subsys(&iptable_nat_net_ops); return ret; } static void __exit iptable_nat_exit(void) { - unregister_pernet_subsys(&iptable_nat_net_ops); xt_unregister_template(&nf_nat_ipv4_table); + unregister_pernet_subsys(&iptable_nat_net_ops); } module_init(iptable_nat_init); diff --git a/net/ipv4/netfilter/nf_dup_ipv4.c b/net/ipv4/netfilter/nf_dup_ipv4.c index 6cc5743c553a..f4aed0789d69 100644 --- a/net/ipv4/netfilter/nf_dup_ipv4.c +++ b/net/ipv4/netfilter/nf_dup_ipv4.c @@ -15,6 +15,7 @@ #include <net/icmp.h> #include <net/ip.h> #include <net/route.h> +#include <net/inet_dscp.h> #include <net/netfilter/ipv4/nf_dup_ipv4.h> #if IS_ENABLED(CONFIG_NF_CONNTRACK) #include <net/netfilter/nf_conntrack.h> @@ -32,7 +33,7 @@ static bool nf_dup_ipv4_route(struct net *net, struct sk_buff *skb, fl4.flowi4_oif = oif; fl4.daddr = gw->s_addr; - fl4.flowi4_tos = RT_TOS(iph->tos); + fl4.flowi4_tos = iph->tos & INET_DSCP_MASK; fl4.flowi4_scope = RT_SCOPE_UNIVERSE; fl4.flowi4_flags = FLOWI_FLAG_KNOWN_NH; rt = ip_route_output_key(net, &fl4); diff --git a/net/ipv4/netfilter/nf_reject_ipv4.c b/net/ipv4/netfilter/nf_reject_ipv4.c index 04504b2b51df..87fd945a0d27 100644 --- a/net/ipv4/netfilter/nf_reject_ipv4.c +++ b/net/ipv4/netfilter/nf_reject_ipv4.c @@ -239,9 +239,8 @@ static int nf_reject_fill_skb_dst(struct sk_buff *skb_in) void nf_send_reset(struct net *net, struct sock *sk, struct sk_buff *oldskb, int hook) { - struct sk_buff *nskb; - struct iphdr *niph; const struct tcphdr *oth; + struct sk_buff *nskb; struct tcphdr _oth; oth = nf_reject_ip_tcphdr_get(oldskb, &_oth, hook); @@ -266,14 +265,12 @@ void nf_send_reset(struct net *net, struct sock *sk, struct sk_buff *oldskb, nskb->mark = IP4_REPLY_MARK(net, oldskb->mark); skb_reserve(nskb, LL_MAX_HEADER); - niph = nf_reject_iphdr_put(nskb, oldskb, IPPROTO_TCP, - ip4_dst_hoplimit(skb_dst(nskb))); + nf_reject_iphdr_put(nskb, oldskb, IPPROTO_TCP, + ip4_dst_hoplimit(skb_dst(nskb))); nf_reject_ip_tcphdr_put(nskb, oldskb, oth); if (ip_route_me_harder(net, sk, nskb, RTN_UNSPEC)) goto free_nskb; - niph = ip_hdr(nskb); - /* "Never happens" */ if (nskb->len > dst_mtu(skb_dst(nskb))) goto free_nskb; @@ -290,6 +287,7 @@ void nf_send_reset(struct net *net, struct sock *sk, struct sk_buff *oldskb, */ if (nf_bridge_info_exists(oldskb)) { struct ethhdr *oeth = eth_hdr(oldskb); + struct iphdr *niph = ip_hdr(nskb); struct net_device *br_indev; br_indev = nf_bridge_get_physindev(oldskb, net); diff --git a/net/ipv4/netfilter/nft_dup_ipv4.c b/net/ipv4/netfilter/nft_dup_ipv4.c index a522c3a3be52..ef5dd88107dd 100644 --- a/net/ipv4/netfilter/nft_dup_ipv4.c +++ b/net/ipv4/netfilter/nft_dup_ipv4.c @@ -40,13 +40,13 @@ static int nft_dup_ipv4_init(const struct nft_ctx *ctx, if (tb[NFTA_DUP_SREG_ADDR] == NULL) return -EINVAL; - err = nft_parse_register_load(tb[NFTA_DUP_SREG_ADDR], &priv->sreg_addr, + err = nft_parse_register_load(ctx, tb[NFTA_DUP_SREG_ADDR], &priv->sreg_addr, sizeof(struct in_addr)); if (err < 0) return err; if (tb[NFTA_DUP_SREG_DEV]) - err = nft_parse_register_load(tb[NFTA_DUP_SREG_DEV], + err = nft_parse_register_load(ctx, tb[NFTA_DUP_SREG_DEV], &priv->sreg_dev, sizeof(int)); return err; diff --git a/net/ipv4/netfilter/nft_fib_ipv4.c b/net/ipv4/netfilter/nft_fib_ipv4.c index 9eee535c64dd..00da1332bbf1 100644 --- a/net/ipv4/netfilter/nft_fib_ipv4.c +++ b/net/ipv4/netfilter/nft_fib_ipv4.c @@ -10,6 +10,7 @@ #include <net/netfilter/nf_tables.h> #include <net/netfilter/nft_fib.h> +#include <net/inet_dscp.h> #include <net/ip_fib.h> #include <net/route.h> @@ -22,8 +23,6 @@ static __be32 get_saddr(__be32 addr) return addr; } -#define DSCP_BITS 0xfc - void nft_fib4_eval_type(const struct nft_expr *expr, struct nft_regs *regs, const struct nft_pktinfo *pkt) { @@ -110,7 +109,7 @@ void nft_fib4_eval(const struct nft_expr *expr, struct nft_regs *regs, if (priv->flags & NFTA_FIB_F_MARK) fl4.flowi4_mark = pkt->skb->mark; - fl4.flowi4_tos = iph->tos & DSCP_BITS; + fl4.flowi4_tos = iph->tos & INET_DSCP_MASK; if (priv->flags & NFTA_FIB_F_DADDR) { fl4.daddr = iph->daddr; diff --git a/net/ipv4/nexthop.c b/net/ipv4/nexthop.c index 535856b0f0ed..93aaea0006ba 100644 --- a/net/ipv4/nexthop.c +++ b/net/ipv4/nexthop.c @@ -865,15 +865,18 @@ out: } static int nla_put_nh_group(struct sk_buff *skb, struct nexthop *nh, - u32 op_flags) + u32 op_flags, u32 *resp_op_flags) { struct nh_group *nhg = rtnl_dereference(nh->nh_grp); struct nexthop_grp *p; size_t len = nhg->num_nh * sizeof(*p); struct nlattr *nla; u16 group_type = 0; + u16 weight; int i; + *resp_op_flags |= NHA_OP_FLAG_RESP_GRP_RESVD_0; + if (nhg->hash_threshold) group_type = NEXTHOP_GRP_TYPE_MPATH; else if (nhg->resilient) @@ -888,9 +891,13 @@ static int nla_put_nh_group(struct sk_buff *skb, struct nexthop *nh, p = nla_data(nla); for (i = 0; i < nhg->num_nh; ++i) { - p->id = nhg->nh_entries[i].nh->id; - p->weight = nhg->nh_entries[i].weight - 1; - p += 1; + weight = nhg->nh_entries[i].weight - 1; + + *p++ = (struct nexthop_grp) { + .id = nhg->nh_entries[i].nh->id, + .weight = weight, + .weight_high = weight >> 8, + }; } if (nhg->resilient && nla_put_nh_group_res(skb, nhg)) @@ -933,10 +940,12 @@ static int nh_fill_node(struct sk_buff *skb, struct nexthop *nh, if (nh->is_group) { struct nh_group *nhg = rtnl_dereference(nh->nh_grp); + u32 resp_op_flags = 0; if (nhg->fdb_nh && nla_put_flag(skb, NHA_FDB)) goto nla_put_failure; - if (nla_put_nh_group(skb, nh, op_flags)) + if (nla_put_nh_group(skb, nh, op_flags, &resp_op_flags) || + nla_put_u32(skb, NHA_OP_FLAGS, resp_op_flags)) goto nla_put_failure; goto out; } @@ -1049,7 +1058,9 @@ static size_t nh_nlmsg_size(struct nexthop *nh) sz += nla_total_size(4); /* NHA_ID */ if (nh->is_group) - sz += nh_nlmsg_size_grp(nh); + sz += nh_nlmsg_size_grp(nh) + + nla_total_size(4) + /* NHA_OP_FLAGS */ + 0; else sz += nh_nlmsg_size_single(nh); @@ -1079,8 +1090,7 @@ static void nexthop_notify(int event, struct nexthop *nh, struct nl_info *info) info->nlh, gfp_any()); return; errout: - if (err < 0) - rtnl_set_sk_err(info->nl_net, RTNLGRP_NEXTHOP, err); + rtnl_set_sk_err(info->nl_net, RTNLGRP_NEXTHOP, err); } static unsigned long nh_res_bucket_used_time(const struct nh_res_bucket *bucket) @@ -1200,8 +1210,7 @@ static void nexthop_bucket_notify(struct nh_res_table *res_table, rtnl_notify(skb, nh->net, 0, RTNLGRP_NEXTHOP, NULL, GFP_KERNEL); return; errout: - if (err < 0) - rtnl_set_sk_err(nh->net, RTNLGRP_NEXTHOP, err); + rtnl_set_sk_err(nh->net, RTNLGRP_NEXTHOP, err); } static bool valid_group_nh(struct nexthop *nh, unsigned int npaths, @@ -1279,11 +1288,14 @@ static int nh_check_attr_group(struct net *net, nhg = nla_data(tb[NHA_GROUP]); for (i = 0; i < len; ++i) { - if (nhg[i].resvd1 || nhg[i].resvd2) { - NL_SET_ERR_MSG(extack, "Reserved fields in nexthop_grp must be 0"); + if (nhg[i].resvd2) { + NL_SET_ERR_MSG(extack, "Reserved field in nexthop_grp must be 0"); return -EINVAL; } - if (nhg[i].weight > 254) { + if (nexthop_grp_weight(&nhg[i]) == 0) { + /* 0xffff got passed in, representing weight of 0x10000, + * which is too heavy. + */ NL_SET_ERR_MSG(extack, "Invalid value for weight"); return -EINVAL; } @@ -1879,9 +1891,9 @@ static void nh_res_table_cancel_upkeep(struct nh_res_table *res_table) static void nh_res_group_rebalance(struct nh_group *nhg, struct nh_res_table *res_table) { - int prev_upper_bound = 0; - int total = 0; - int w = 0; + u16 prev_upper_bound = 0; + u32 total = 0; + u32 w = 0; int i; INIT_LIST_HEAD(&res_table->uw_nh_entries); @@ -1891,11 +1903,12 @@ static void nh_res_group_rebalance(struct nh_group *nhg, for (i = 0; i < nhg->num_nh; ++i) { struct nh_grp_entry *nhge = &nhg->nh_entries[i]; - int upper_bound; + u16 upper_bound; + u64 btw; w += nhge->weight; - upper_bound = DIV_ROUND_CLOSEST(res_table->num_nh_buckets * w, - total); + btw = ((u64)res_table->num_nh_buckets) * w; + upper_bound = DIV_ROUND_CLOSEST_ULL(btw, total); nhge->res.wants_buckets = upper_bound - prev_upper_bound; prev_upper_bound = upper_bound; @@ -1961,8 +1974,8 @@ static void replace_nexthop_grp_res(struct nh_group *oldg, static void nh_hthr_group_rebalance(struct nh_group *nhg) { - int total = 0; - int w = 0; + u32 total = 0; + u32 w = 0; int i; for (i = 0; i < nhg->num_nh; ++i) @@ -1970,7 +1983,7 @@ static void nh_hthr_group_rebalance(struct nh_group *nhg) for (i = 0; i < nhg->num_nh; ++i) { struct nh_grp_entry *nhge = &nhg->nh_entries[i]; - int upper_bound; + u32 upper_bound; w += nhge->weight; upper_bound = DIV_ROUND_CLOSEST_ULL((u64)w << 31, total) - 1; @@ -2712,7 +2725,8 @@ static struct nexthop *nexthop_create_group(struct net *net, goto out_no_nh; } nhg->nh_entries[i].nh = nhe; - nhg->nh_entries[i].weight = entry[i].weight + 1; + nhg->nh_entries[i].weight = nexthop_grp_weight(&entry[i]); + list_add(&nhg->nh_entries[i].nh_list, &nhe->grp_list); nhg->nh_entries[i].nh_parent = nh; } diff --git a/net/ipv4/ping.c b/net/ipv4/ping.c index 823306487a82..619ddc087957 100644 --- a/net/ipv4/ping.c +++ b/net/ipv4/ping.c @@ -946,7 +946,7 @@ static enum skb_drop_reason __ping_queue_rcv_skb(struct sock *sk, pr_debug("ping_queue_rcv_skb(sk=%p,sk->num=%d,skb=%p)\n", inet_sk(sk), inet_sk(sk)->inet_num, skb); if (sock_queue_rcv_skb_reason(sk, skb, &reason) < 0) { - kfree_skb_reason(skb, reason); + sk_skb_reason_drop(sk, skb, reason); pr_debug("ping_queue_rcv_skb -> failed\n"); return reason; } diff --git a/net/ipv4/proc.c b/net/ipv4/proc.c index 6c4664c681ca..40053a02bae1 100644 --- a/net/ipv4/proc.c +++ b/net/ipv4/proc.c @@ -44,7 +44,7 @@ #include <net/sock.h> #include <net/raw.h> -#define TCPUDP_MIB_MAX max_t(u32, UDP_MIB_MAX, TCP_MIB_MAX) +#define TCPUDP_MIB_MAX MAX_T(u32, UDP_MIB_MAX, TCP_MIB_MAX) /* * Report socket allocation statistics [mea@utu.fi] diff --git a/net/ipv4/raw.c b/net/ipv4/raw.c index 4cb43401e0e0..474dfd263c8b 100644 --- a/net/ipv4/raw.c +++ b/net/ipv4/raw.c @@ -301,7 +301,7 @@ static int raw_rcv_skb(struct sock *sk, struct sk_buff *skb) ipv4_pktinfo_prepare(sk, skb, true); if (sock_queue_rcv_skb_reason(sk, skb, &reason) < 0) { - kfree_skb_reason(skb, reason); + sk_skb_reason_drop(sk, skb, reason); return NET_RX_DROP; } @@ -312,7 +312,7 @@ int raw_rcv(struct sock *sk, struct sk_buff *skb) { if (!xfrm4_policy_check(sk, XFRM_POLICY_IN, skb)) { atomic_inc(&sk->sk_drops); - kfree_skb_reason(skb, SKB_DROP_REASON_XFRM_POLICY); + sk_skb_reason_drop(sk, skb, SKB_DROP_REASON_XFRM_POLICY); return NET_RX_DROP; } nf_reset_ct(skb); @@ -360,7 +360,7 @@ static int raw_send_hdrinc(struct sock *sk, struct flowi4 *fl4, skb->protocol = htons(ETH_P_IP); skb->priority = READ_ONCE(sk->sk_priority); skb->mark = sockc->mark; - skb->tstamp = sockc->transmit_time; + skb_set_delivery_type_by_clockid(skb, sockc->transmit_time, sk->sk_clockid); skb_dst_set(skb, &rt->dst); *rtp = NULL; diff --git a/net/ipv4/route.c b/net/ipv4/route.c index b3073d1c8f8f..723ac9181558 100644 --- a/net/ipv4/route.c +++ b/net/ipv4/route.c @@ -512,7 +512,7 @@ static void __build_flow_key(const struct net *net, struct flowi4 *fl4, sk->sk_protocol; } - flowi4_init_output(fl4, oif, mark, tos & IPTOS_RT_MASK, scope, + flowi4_init_output(fl4, oif, mark, tos & INET_DSCP_MASK, scope, prot, flow_flags, iph->daddr, iph->saddr, 0, 0, sock_net_uid(net, sk)); } @@ -541,7 +541,7 @@ static void build_sk_flow_key(struct flowi4 *fl4, const struct sock *sk) if (inet_opt && inet_opt->opt.srr) daddr = inet_opt->opt.faddr; flowi4_init_output(fl4, sk->sk_bound_dev_if, READ_ONCE(sk->sk_mark), - ip_sock_rt_tos(sk) & IPTOS_RT_MASK, + ip_sock_rt_tos(sk), ip_sock_rt_scope(sk), inet_test_bit(HDRINCL, sk) ? IPPROTO_RAW : sk->sk_protocol, @@ -1263,7 +1263,7 @@ void ip_rt_get_source(u8 *addr, struct sk_buff *skb, struct rtable *rt) struct flowi4 fl4 = { .daddr = iph->daddr, .saddr = iph->saddr, - .flowi4_tos = RT_TOS(iph->tos), + .flowi4_tos = iph->tos & INET_DSCP_MASK, .flowi4_oif = rt->dst.dev->ifindex, .flowi4_iif = skb->dev->ifindex, .flowi4_mark = skb->mark, @@ -1481,7 +1481,6 @@ static bool rt_cache_route(struct fib_nh_common *nhc, struct rtable *rt) struct uncached_list { spinlock_t lock; struct list_head head; - struct list_head quarantine; }; static DEFINE_PER_CPU_ALIGNED(struct uncached_list, rt_uncached_list); @@ -1532,7 +1531,7 @@ void rt_flush_dev(struct net_device *dev) rt->dst.dev = blackhole_netdev; netdev_ref_replace(dev, blackhole_netdev, &rt->dst.dev_tracker, GFP_ATOMIC); - list_move(&rt->dst.rt_uncached, &ul->quarantine); + list_del_init(&rt->dst.rt_uncached); } spin_unlock_bh(&ul->lock); } @@ -1924,7 +1923,7 @@ static u32 fib_multipath_custom_hash_outer(const struct net *net, hash_keys.ports.dst = keys.ports.dst; *p_has_inner = !!(keys.control.flags & FLOW_DIS_ENCAPSULATION); - return flow_hash_from_keys(&hash_keys); + return fib_multipath_hash_from_keys(net, &hash_keys); } static u32 fib_multipath_custom_hash_inner(const struct net *net, @@ -1973,7 +1972,7 @@ static u32 fib_multipath_custom_hash_inner(const struct net *net, if (hash_fields & FIB_MULTIPATH_HASH_FIELD_INNER_DST_PORT) hash_keys.ports.dst = keys.ports.dst; - return flow_hash_from_keys(&hash_keys); + return fib_multipath_hash_from_keys(net, &hash_keys); } static u32 fib_multipath_custom_hash_skb(const struct net *net, @@ -2010,7 +2009,7 @@ static u32 fib_multipath_custom_hash_fl4(const struct net *net, if (hash_fields & FIB_MULTIPATH_HASH_FIELD_DST_PORT) hash_keys.ports.dst = fl4->fl4_dport; - return flow_hash_from_keys(&hash_keys); + return fib_multipath_hash_from_keys(net, &hash_keys); } /* if skb is set it will be used and fl4 can be NULL */ @@ -2031,7 +2030,7 @@ int fib_multipath_hash(const struct net *net, const struct flowi4 *fl4, hash_keys.addrs.v4addrs.src = fl4->saddr; hash_keys.addrs.v4addrs.dst = fl4->daddr; } - mhash = flow_hash_from_keys(&hash_keys); + mhash = fib_multipath_hash_from_keys(net, &hash_keys); break; case 1: /* skb is currently provided only when forwarding */ @@ -2065,7 +2064,7 @@ int fib_multipath_hash(const struct net *net, const struct flowi4 *fl4, hash_keys.ports.dst = fl4->fl4_dport; hash_keys.basic.ip_proto = fl4->flowi4_proto; } - mhash = flow_hash_from_keys(&hash_keys); + mhash = fib_multipath_hash_from_keys(net, &hash_keys); break; case 2: memset(&hash_keys, 0, sizeof(hash_keys)); @@ -2096,7 +2095,7 @@ int fib_multipath_hash(const struct net *net, const struct flowi4 *fl4, hash_keys.addrs.v4addrs.src = fl4->saddr; hash_keys.addrs.v4addrs.dst = fl4->daddr; } - mhash = flow_hash_from_keys(&hash_keys); + mhash = fib_multipath_hash_from_keys(net, &hash_keys); break; case 3: if (skb) @@ -2161,7 +2160,7 @@ int ip_route_use_hint(struct sk_buff *skb, __be32 daddr, __be32 saddr, if (rt->rt_type != RTN_LOCAL) goto skip_validate_source; - tos &= IPTOS_RT_MASK; + tos &= INET_DSCP_MASK; err = fib_validate_source(skb, saddr, daddr, tos, 0, dev, in_dev, &tag); if (err < 0) goto martian_source; @@ -2471,7 +2470,7 @@ int ip_route_input_noref(struct sk_buff *skb, __be32 daddr, __be32 saddr, struct fib_result res; int err; - tos &= IPTOS_RT_MASK; + tos &= INET_DSCP_MASK; rcu_read_lock(); err = ip_route_input_rcu(skb, daddr, saddr, tos, dev, &res); rcu_read_unlock(); @@ -2619,7 +2618,7 @@ struct rtable *ip_route_output_key_hash(struct net *net, struct flowi4 *fl4, struct rtable *rth; fl4->flowi4_iif = LOOPBACK_IFINDEX; - fl4->flowi4_tos &= IPTOS_RT_MASK; + fl4->flowi4_tos &= INET_DSCP_MASK; rcu_read_lock(); rth = ip_route_output_key_hash_rcu(net, fl4, &res, skb); @@ -2868,9 +2867,9 @@ EXPORT_SYMBOL_GPL(ip_route_output_flow); /* called with rcu_read_lock held */ static int rt_fill_info(struct net *net, __be32 dst, __be32 src, - struct rtable *rt, u32 table_id, struct flowi4 *fl4, - struct sk_buff *skb, u32 portid, u32 seq, - unsigned int flags) + struct rtable *rt, u32 table_id, dscp_t dscp, + struct flowi4 *fl4, struct sk_buff *skb, u32 portid, + u32 seq, unsigned int flags) { struct rtmsg *r; struct nlmsghdr *nlh; @@ -2886,7 +2885,7 @@ static int rt_fill_info(struct net *net, __be32 dst, __be32 src, r->rtm_family = AF_INET; r->rtm_dst_len = 32; r->rtm_src_len = 0; - r->rtm_tos = fl4 ? fl4->flowi4_tos : 0; + r->rtm_tos = inet_dscp_to_dsfield(dscp); r->rtm_table = table_id < 256 ? table_id : RT_TABLE_COMPAT; if (nla_put_u32(skb, RTA_TABLE, table_id)) goto nla_put_failure; @@ -3036,7 +3035,7 @@ static int fnhe_dump_bucket(struct net *net, struct sk_buff *skb, goto next; err = rt_fill_info(net, fnhe->fnhe_daddr, 0, rt, - table_id, NULL, skb, + table_id, 0, NULL, skb, NETLINK_CB(cb->skb).portid, cb->nlh->nlmsg_seq, flags); if (err) @@ -3262,7 +3261,7 @@ static int inet_rtm_getroute(struct sk_buff *in_skb, struct nlmsghdr *nlh, fl4.daddr = dst; fl4.saddr = src; - fl4.flowi4_tos = rtm->rtm_tos & IPTOS_RT_MASK; + fl4.flowi4_tos = rtm->rtm_tos & INET_DSCP_MASK; fl4.flowi4_oif = tb[RTA_OIF] ? nla_get_u32(tb[RTA_OIF]) : 0; fl4.flowi4_mark = mark; fl4.flowi4_uid = uid; @@ -3287,7 +3286,7 @@ static int inet_rtm_getroute(struct sk_buff *in_skb, struct nlmsghdr *nlh, skb->dev = dev; skb->mark = mark; err = ip_route_input_rcu(skb, dst, src, - rtm->rtm_tos & IPTOS_RT_MASK, dev, + rtm->rtm_tos & INET_DSCP_MASK, dev, &res); rt = skb_rtable(skb); @@ -3332,7 +3331,7 @@ static int inet_rtm_getroute(struct sk_buff *in_skb, struct nlmsghdr *nlh, fri.tb_id = table_id; fri.dst = res.prefix; fri.dst_len = res.prefixlen; - fri.dscp = inet_dsfield_to_dscp(fl4.flowi4_tos); + fri.dscp = res.dscp; fri.type = rt->rt_type; fri.offload = 0; fri.trap = 0; @@ -3359,8 +3358,8 @@ static int inet_rtm_getroute(struct sk_buff *in_skb, struct nlmsghdr *nlh, err = fib_dump_info(skb, NETLINK_CB(in_skb).portid, nlh->nlmsg_seq, RTM_NEWROUTE, &fri, 0); } else { - err = rt_fill_info(net, dst, src, rt, table_id, &fl4, skb, - NETLINK_CB(in_skb).portid, + err = rt_fill_info(net, dst, src, rt, table_id, res.dscp, &fl4, + skb, NETLINK_CB(in_skb).portid, nlh->nlmsg_seq, 0); } if (err < 0) @@ -3389,7 +3388,7 @@ static int ip_rt_gc_min_interval __read_mostly = HZ / 2; static int ip_rt_gc_elasticity __read_mostly = 8; static int ip_min_valid_pmtu __read_mostly = IPV4_MIN_MTU; -static int ipv4_sysctl_rtcache_flush(struct ctl_table *__ctl, int write, +static int ipv4_sysctl_rtcache_flush(const struct ctl_table *__ctl, int write, void *buffer, size_t *lenp, loff_t *ppos) { struct net *net = (struct net *)__ctl->extra1; @@ -3661,7 +3660,6 @@ int __init ip_rt_init(void) struct uncached_list *ul = &per_cpu(rt_uncached_list, cpu); INIT_LIST_HEAD(&ul->head); - INIT_LIST_HEAD(&ul->quarantine); spin_lock_init(&ul->lock); } #ifdef CONFIG_IP_ROUTE_CLASSID diff --git a/net/ipv4/syncookies.c b/net/ipv4/syncookies.c index b61d36810fe3..1948d15f1f28 100644 --- a/net/ipv4/syncookies.c +++ b/net/ipv4/syncookies.c @@ -496,6 +496,6 @@ out: out_free: reqsk_free(req); out_drop: - kfree_skb_reason(skb, reason); + sk_skb_reason_drop(sk, skb, reason); return NULL; } diff --git a/net/ipv4/sysctl_net_ipv4.c b/net/ipv4/sysctl_net_ipv4.c index 162a0a3b6ba5..a79b2a52ce01 100644 --- a/net/ipv4/sysctl_net_ipv4.c +++ b/net/ipv4/sysctl_net_ipv4.c @@ -62,7 +62,7 @@ static void set_local_port_range(struct net *net, unsigned int low, unsigned int } /* Validate changes from /proc interface. */ -static int ipv4_local_port_range(struct ctl_table *table, int write, +static int ipv4_local_port_range(const struct ctl_table *table, int write, void *buffer, size_t *lenp, loff_t *ppos) { struct net *net = table->data; @@ -96,7 +96,7 @@ static int ipv4_local_port_range(struct ctl_table *table, int write, } /* Validate changes from /proc interface. */ -static int ipv4_privileged_ports(struct ctl_table *table, int write, +static int ipv4_privileged_ports(const struct ctl_table *table, int write, void *buffer, size_t *lenp, loff_t *ppos) { struct net *net = container_of(table->data, struct net, @@ -130,7 +130,8 @@ static int ipv4_privileged_ports(struct ctl_table *table, int write, return ret; } -static void inet_get_ping_group_range_table(struct ctl_table *table, kgid_t *low, kgid_t *high) +static void inet_get_ping_group_range_table(const struct ctl_table *table, + kgid_t *low, kgid_t *high) { kgid_t *data = table->data; struct net *net = @@ -145,7 +146,8 @@ static void inet_get_ping_group_range_table(struct ctl_table *table, kgid_t *low } /* Update system visible IP port range */ -static void set_ping_group_range(struct ctl_table *table, kgid_t low, kgid_t high) +static void set_ping_group_range(const struct ctl_table *table, + kgid_t low, kgid_t high) { kgid_t *data = table->data; struct net *net = @@ -157,7 +159,7 @@ static void set_ping_group_range(struct ctl_table *table, kgid_t low, kgid_t hig } /* Validate changes from /proc interface. */ -static int ipv4_ping_group_range(struct ctl_table *table, int write, +static int ipv4_ping_group_range(const struct ctl_table *table, int write, void *buffer, size_t *lenp, loff_t *ppos) { struct user_namespace *user_ns = current_user_ns(); @@ -192,7 +194,7 @@ static int ipv4_ping_group_range(struct ctl_table *table, int write, return ret; } -static int ipv4_fwd_update_priority(struct ctl_table *table, int write, +static int ipv4_fwd_update_priority(const struct ctl_table *table, int write, void *buffer, size_t *lenp, loff_t *ppos) { struct net *net; @@ -208,7 +210,7 @@ static int ipv4_fwd_update_priority(struct ctl_table *table, int write, return ret; } -static int proc_tcp_congestion_control(struct ctl_table *ctl, int write, +static int proc_tcp_congestion_control(const struct ctl_table *ctl, int write, void *buffer, size_t *lenp, loff_t *ppos) { struct net *net = container_of(ctl->data, struct net, @@ -228,7 +230,7 @@ static int proc_tcp_congestion_control(struct ctl_table *ctl, int write, return ret; } -static int proc_tcp_available_congestion_control(struct ctl_table *ctl, +static int proc_tcp_available_congestion_control(const struct ctl_table *ctl, int write, void *buffer, size_t *lenp, loff_t *ppos) { @@ -244,7 +246,7 @@ static int proc_tcp_available_congestion_control(struct ctl_table *ctl, return ret; } -static int proc_allowed_congestion_control(struct ctl_table *ctl, +static int proc_allowed_congestion_control(const struct ctl_table *ctl, int write, void *buffer, size_t *lenp, loff_t *ppos) { @@ -281,7 +283,7 @@ static int sscanf_key(char *buf, __le32 *key) return ret; } -static int proc_tcp_fastopen_key(struct ctl_table *table, int write, +static int proc_tcp_fastopen_key(const struct ctl_table *table, int write, void *buffer, size_t *lenp, loff_t *ppos) { struct net *net = container_of(table->data, struct net, @@ -352,7 +354,7 @@ bad_key: return ret; } -static int proc_tfo_blackhole_detect_timeout(struct ctl_table *table, +static int proc_tfo_blackhole_detect_timeout(const struct ctl_table *table, int write, void *buffer, size_t *lenp, loff_t *ppos) { @@ -367,7 +369,7 @@ static int proc_tfo_blackhole_detect_timeout(struct ctl_table *table, return ret; } -static int proc_tcp_available_ulp(struct ctl_table *ctl, +static int proc_tcp_available_ulp(const struct ctl_table *ctl, int write, void *buffer, size_t *lenp, loff_t *ppos) { @@ -384,7 +386,7 @@ static int proc_tcp_available_ulp(struct ctl_table *ctl, return ret; } -static int proc_tcp_ehash_entries(struct ctl_table *table, int write, +static int proc_tcp_ehash_entries(const struct ctl_table *table, int write, void *buffer, size_t *lenp, loff_t *ppos) { struct net *net = container_of(table->data, struct net, @@ -408,7 +410,7 @@ static int proc_tcp_ehash_entries(struct ctl_table *table, int write, return proc_dointvec(&tbl, write, buffer, lenp, ppos); } -static int proc_udp_hash_entries(struct ctl_table *table, int write, +static int proc_udp_hash_entries(const struct ctl_table *table, int write, void *buffer, size_t *lenp, loff_t *ppos) { struct net *net = container_of(table->data, struct net, @@ -432,7 +434,7 @@ static int proc_udp_hash_entries(struct ctl_table *table, int write, } #ifdef CONFIG_IP_ROUTE_MULTIPATH -static int proc_fib_multipath_hash_policy(struct ctl_table *table, int write, +static int proc_fib_multipath_hash_policy(const struct ctl_table *table, int write, void *buffer, size_t *lenp, loff_t *ppos) { @@ -447,7 +449,7 @@ static int proc_fib_multipath_hash_policy(struct ctl_table *table, int write, return ret; } -static int proc_fib_multipath_hash_fields(struct ctl_table *table, int write, +static int proc_fib_multipath_hash_fields(const struct ctl_table *table, int write, void *buffer, size_t *lenp, loff_t *ppos) { @@ -462,6 +464,61 @@ static int proc_fib_multipath_hash_fields(struct ctl_table *table, int write, return ret; } + +static u32 proc_fib_multipath_hash_rand_seed __ro_after_init; + +static void proc_fib_multipath_hash_init_rand_seed(void) +{ + get_random_bytes(&proc_fib_multipath_hash_rand_seed, + sizeof(proc_fib_multipath_hash_rand_seed)); +} + +static void proc_fib_multipath_hash_set_seed(struct net *net, u32 user_seed) +{ + struct sysctl_fib_multipath_hash_seed new = { + .user_seed = user_seed, + .mp_seed = (user_seed ? user_seed : + proc_fib_multipath_hash_rand_seed), + }; + + WRITE_ONCE(net->ipv4.sysctl_fib_multipath_hash_seed, new); +} + +static int proc_fib_multipath_hash_seed(const struct ctl_table *table, int write, + void *buffer, size_t *lenp, + loff_t *ppos) +{ + struct sysctl_fib_multipath_hash_seed *mphs; + struct net *net = table->data; + struct ctl_table tmp; + u32 user_seed; + int ret; + + mphs = &net->ipv4.sysctl_fib_multipath_hash_seed; + user_seed = mphs->user_seed; + + tmp = *table; + tmp.data = &user_seed; + + ret = proc_douintvec_minmax(&tmp, write, buffer, lenp, ppos); + + if (write && ret == 0) { + proc_fib_multipath_hash_set_seed(net, user_seed); + call_netevent_notifiers(NETEVENT_IPV4_MPATH_HASH_UPDATE, net); + } + + return ret; +} +#else + +static void proc_fib_multipath_hash_init_rand_seed(void) +{ +} + +static void proc_fib_multipath_hash_set_seed(struct net *net, u32 user_seed) +{ +} + #endif static struct ctl_table ipv4_table[] = { @@ -544,22 +601,6 @@ static struct ctl_table ipv4_table[] = { .proc_handler = proc_tcp_available_ulp, }, { - .procname = "icmp_msgs_per_sec", - .data = &sysctl_icmp_msgs_per_sec, - .maxlen = sizeof(int), - .mode = 0644, - .proc_handler = proc_dointvec_minmax, - .extra1 = SYSCTL_ZERO, - }, - { - .procname = "icmp_msgs_burst", - .data = &sysctl_icmp_msgs_burst, - .maxlen = sizeof(int), - .mode = 0644, - .proc_handler = proc_dointvec_minmax, - .extra1 = SYSCTL_ZERO, - }, - { .procname = "udp_mem", .data = &sysctl_udp_mem, .maxlen = sizeof(sysctl_udp_mem), @@ -645,6 +686,22 @@ static struct ctl_table ipv4_net_table[] = { .proc_handler = proc_dointvec }, { + .procname = "icmp_msgs_per_sec", + .data = &init_net.ipv4.sysctl_icmp_msgs_per_sec, + .maxlen = sizeof(int), + .mode = 0644, + .proc_handler = proc_dointvec_minmax, + .extra1 = SYSCTL_ZERO, + }, + { + .procname = "icmp_msgs_burst", + .data = &init_net.ipv4.sysctl_icmp_msgs_burst, + .maxlen = sizeof(int), + .mode = 0644, + .proc_handler = proc_dointvec_minmax, + .extra1 = SYSCTL_ZERO, + }, + { .procname = "ping_group_range", .data = &init_net.ipv4.ping_group_range.range, .maxlen = sizeof(gid_t)*2, @@ -1070,6 +1127,13 @@ static struct ctl_table ipv4_net_table[] = { .extra1 = SYSCTL_ONE, .extra2 = &fib_multipath_hash_fields_all_mask, }, + { + .procname = "fib_multipath_hash_seed", + .data = &init_net, + .maxlen = sizeof(u32), + .mode = 0644, + .proc_handler = proc_fib_multipath_hash_seed, + }, #endif { .procname = "ip_unprivileged_port_start", @@ -1501,6 +1565,14 @@ static struct ctl_table ipv4_net_table[] = { .proc_handler = proc_dou8vec_minmax, .extra1 = SYSCTL_ONE, }, + { + .procname = "tcp_rto_min_us", + .data = &init_net.ipv4.sysctl_tcp_rto_min_us, + .maxlen = sizeof(int), + .mode = 0644, + .proc_handler = proc_dointvec_minmax, + .extra1 = SYSCTL_ONE, + }, }; static __net_init int ipv4_sysctl_init_net(struct net *net) @@ -1540,6 +1612,8 @@ static __net_init int ipv4_sysctl_init_net(struct net *net) if (!net->ipv4.sysctl_local_reserved_ports) goto err_ports; + proc_fib_multipath_hash_set_seed(net, 0); + return 0; err_ports: @@ -1574,6 +1648,8 @@ static __init int sysctl_ipv4_init(void) if (!hdr) return -ENOMEM; + proc_fib_multipath_hash_init_rand_seed(); + if (register_pernet_subsys(&ipv4_sysctl_ops)) { unregister_net_sysctl_table(hdr); return -ENOMEM; diff --git a/net/ipv4/tcp.c b/net/ipv4/tcp.c index e6790ea74877..4f77bd862e95 100644 --- a/net/ipv4/tcp.c +++ b/net/ipv4/tcp.c @@ -282,8 +282,11 @@ #include <asm/ioctls.h> #include <net/busy_poll.h> #include <net/hotdata.h> +#include <trace/events/tcp.h> #include <net/rps.h> +#include "../core/devmem.h" + /* Track pending CMSGs. */ enum { TCP_CMSG_INQ = 1, @@ -420,6 +423,7 @@ void tcp_init_sock(struct sock *sk) { struct inet_connection_sock *icsk = inet_csk(sk); struct tcp_sock *tp = tcp_sk(sk); + int rto_min_us; tp->out_of_order_queue = RB_ROOT; sk->tcp_rtx_queue = RB_ROOT; @@ -428,7 +432,8 @@ void tcp_init_sock(struct sock *sk) INIT_LIST_HEAD(&tp->tsorted_sent_queue); icsk->icsk_rto = TCP_TIMEOUT_INIT; - icsk->icsk_rto_min = TCP_RTO_MIN; + rto_min_us = READ_ONCE(sock_net(sk)->ipv4.sysctl_tcp_rto_min_us); + icsk->icsk_rto_min = usecs_to_jiffies(rto_min_us); icsk->icsk_delack_max = TCP_DELACK_MAX; tp->mdev_us = jiffies_to_usecs(TCP_TIMEOUT_INIT); minmax_reset(&tp->rtt_min, tcp_jiffies32, ~0U); @@ -468,6 +473,7 @@ void tcp_init_sock(struct sock *sk) set_bit(SOCK_SUPPORT_ZC, &sk->sk_socket->flags); sk_sockets_allocated_inc(sk); + xa_init_flags(&sk->sk_user_frags, XA_FLAGS_ALLOC1); } EXPORT_SYMBOL(tcp_init_sock); @@ -598,7 +604,7 @@ __poll_t tcp_poll(struct file *file, struct socket *sock, poll_table *wait) */ mask |= EPOLLOUT | EPOLLWRNORM; } - /* This barrier is coupled with smp_wmb() in tcp_reset() */ + /* This barrier is coupled with smp_wmb() in tcp_done_with_error() */ smp_rmb(); if (READ_ONCE(sk->sk_err) || !skb_queue_empty_lockless(&sk->sk_error_queue)) @@ -2157,6 +2163,9 @@ static int tcp_zerocopy_receive(struct sock *sk, skb = tcp_recv_skb(sk, seq, &offset); } + if (!skb_frags_readable(skb)) + break; + if (TCP_SKB_CB(skb)->has_rxtstamp) { tcp_update_recv_tstamps(skb, tss); zc->msg_flags |= TCP_CMSG_TS; @@ -2174,6 +2183,9 @@ static int tcp_zerocopy_receive(struct sock *sk, break; } page = skb_frag_page(frags); + if (WARN_ON_ONCE(!page)) + break; + prefetchw(page); pages[pages_to_map++] = page; length += PAGE_SIZE; @@ -2232,6 +2244,7 @@ void tcp_recv_timestamp(struct msghdr *msg, const struct sock *sk, struct scm_timestamping_internal *tss) { int new_tstamp = sock_flag(sk, SOCK_TSTAMP_NEW); + u32 tsflags = READ_ONCE(sk->sk_tsflags); bool has_timestamping = false; if (tss->ts[0].tv_sec || tss->ts[0].tv_nsec) { @@ -2271,14 +2284,18 @@ void tcp_recv_timestamp(struct msghdr *msg, const struct sock *sk, } } - if (READ_ONCE(sk->sk_tsflags) & SOF_TIMESTAMPING_SOFTWARE) + if (tsflags & SOF_TIMESTAMPING_SOFTWARE && + (tsflags & SOF_TIMESTAMPING_RX_SOFTWARE || + !(tsflags & SOF_TIMESTAMPING_OPT_RX_FILTER))) has_timestamping = true; else tss->ts[0] = (struct timespec64) {0}; } if (tss->ts[2].tv_sec || tss->ts[2].tv_nsec) { - if (READ_ONCE(sk->sk_tsflags) & SOF_TIMESTAMPING_RAW_HARDWARE) + if (tsflags & SOF_TIMESTAMPING_RAW_HARDWARE && + (tsflags & SOF_TIMESTAMPING_RX_HARDWARE || + !(tsflags & SOF_TIMESTAMPING_OPT_RX_FILTER))) has_timestamping = true; else tss->ts[2] = (struct timespec64) {0}; @@ -2314,6 +2331,220 @@ static int tcp_inq_hint(struct sock *sk) return inq; } +/* batch __xa_alloc() calls and reduce xa_lock()/xa_unlock() overhead. */ +struct tcp_xa_pool { + u8 max; /* max <= MAX_SKB_FRAGS */ + u8 idx; /* idx <= max */ + __u32 tokens[MAX_SKB_FRAGS]; + netmem_ref netmems[MAX_SKB_FRAGS]; +}; + +static void tcp_xa_pool_commit_locked(struct sock *sk, struct tcp_xa_pool *p) +{ + int i; + + /* Commit part that has been copied to user space. */ + for (i = 0; i < p->idx; i++) + __xa_cmpxchg(&sk->sk_user_frags, p->tokens[i], XA_ZERO_ENTRY, + (__force void *)p->netmems[i], GFP_KERNEL); + /* Rollback what has been pre-allocated and is no longer needed. */ + for (; i < p->max; i++) + __xa_erase(&sk->sk_user_frags, p->tokens[i]); + + p->max = 0; + p->idx = 0; +} + +static void tcp_xa_pool_commit(struct sock *sk, struct tcp_xa_pool *p) +{ + if (!p->max) + return; + + xa_lock_bh(&sk->sk_user_frags); + + tcp_xa_pool_commit_locked(sk, p); + + xa_unlock_bh(&sk->sk_user_frags); +} + +static int tcp_xa_pool_refill(struct sock *sk, struct tcp_xa_pool *p, + unsigned int max_frags) +{ + int err, k; + + if (p->idx < p->max) + return 0; + + xa_lock_bh(&sk->sk_user_frags); + + tcp_xa_pool_commit_locked(sk, p); + + for (k = 0; k < max_frags; k++) { + err = __xa_alloc(&sk->sk_user_frags, &p->tokens[k], + XA_ZERO_ENTRY, xa_limit_31b, GFP_KERNEL); + if (err) + break; + } + + xa_unlock_bh(&sk->sk_user_frags); + + p->max = k; + p->idx = 0; + return k ? 0 : err; +} + +/* On error, returns the -errno. On success, returns number of bytes sent to the + * user. May not consume all of @remaining_len. + */ +static int tcp_recvmsg_dmabuf(struct sock *sk, const struct sk_buff *skb, + unsigned int offset, struct msghdr *msg, + int remaining_len) +{ + struct dmabuf_cmsg dmabuf_cmsg = { 0 }; + struct tcp_xa_pool tcp_xa_pool; + unsigned int start; + int i, copy, n; + int sent = 0; + int err = 0; + + tcp_xa_pool.max = 0; + tcp_xa_pool.idx = 0; + do { + start = skb_headlen(skb); + + if (skb_frags_readable(skb)) { + err = -ENODEV; + goto out; + } + + /* Copy header. */ + copy = start - offset; + if (copy > 0) { + copy = min(copy, remaining_len); + + n = copy_to_iter(skb->data + offset, copy, + &msg->msg_iter); + if (n != copy) { + err = -EFAULT; + goto out; + } + + offset += copy; + remaining_len -= copy; + + /* First a dmabuf_cmsg for # bytes copied to user + * buffer. + */ + memset(&dmabuf_cmsg, 0, sizeof(dmabuf_cmsg)); + dmabuf_cmsg.frag_size = copy; + err = put_cmsg(msg, SOL_SOCKET, SO_DEVMEM_LINEAR, + sizeof(dmabuf_cmsg), &dmabuf_cmsg); + if (err || msg->msg_flags & MSG_CTRUNC) { + msg->msg_flags &= ~MSG_CTRUNC; + if (!err) + err = -ETOOSMALL; + goto out; + } + + sent += copy; + + if (remaining_len == 0) + goto out; + } + + /* after that, send information of dmabuf pages through a + * sequence of cmsg + */ + for (i = 0; i < skb_shinfo(skb)->nr_frags; i++) { + skb_frag_t *frag = &skb_shinfo(skb)->frags[i]; + struct net_iov *niov; + u64 frag_offset; + int end; + + /* !skb_frags_readable() should indicate that ALL the + * frags in this skb are dmabuf net_iovs. We're checking + * for that flag above, but also check individual frags + * here. If the tcp stack is not setting + * skb_frags_readable() correctly, we still don't want + * to crash here. + */ + if (!skb_frag_net_iov(frag)) { + net_err_ratelimited("Found non-dmabuf skb with net_iov"); + err = -ENODEV; + goto out; + } + + niov = skb_frag_net_iov(frag); + end = start + skb_frag_size(frag); + copy = end - offset; + + if (copy > 0) { + copy = min(copy, remaining_len); + + frag_offset = net_iov_virtual_addr(niov) + + skb_frag_off(frag) + offset - + start; + dmabuf_cmsg.frag_offset = frag_offset; + dmabuf_cmsg.frag_size = copy; + err = tcp_xa_pool_refill(sk, &tcp_xa_pool, + skb_shinfo(skb)->nr_frags - i); + if (err) + goto out; + + /* Will perform the exchange later */ + dmabuf_cmsg.frag_token = tcp_xa_pool.tokens[tcp_xa_pool.idx]; + dmabuf_cmsg.dmabuf_id = net_iov_binding_id(niov); + + offset += copy; + remaining_len -= copy; + + err = put_cmsg(msg, SOL_SOCKET, + SO_DEVMEM_DMABUF, + sizeof(dmabuf_cmsg), + &dmabuf_cmsg); + if (err || msg->msg_flags & MSG_CTRUNC) { + msg->msg_flags &= ~MSG_CTRUNC; + if (!err) + err = -ETOOSMALL; + goto out; + } + + atomic_long_inc(&niov->pp_ref_count); + tcp_xa_pool.netmems[tcp_xa_pool.idx++] = skb_frag_netmem(frag); + + sent += copy; + + if (remaining_len == 0) + goto out; + } + start = end; + } + + tcp_xa_pool_commit(sk, &tcp_xa_pool); + if (!remaining_len) + goto out; + + /* if remaining_len is not satisfied yet, we need to go to the + * next frag in the frag_list to satisfy remaining_len. + */ + skb = skb_shinfo(skb)->frag_list ?: skb->next; + + offset = offset - start; + } while (skb); + + if (remaining_len) { + err = -EFAULT; + goto out; + } + +out: + tcp_xa_pool_commit(sk, &tcp_xa_pool); + if (!sent) + sent = err; + + return sent; +} + /* * This routine copies from a sock struct into the user buffer. * @@ -2327,6 +2558,7 @@ static int tcp_recvmsg_locked(struct sock *sk, struct msghdr *msg, size_t len, int *cmsg_flags) { struct tcp_sock *tp = tcp_sk(sk); + int last_copied_dmabuf = -1; /* uninitialized */ int copied = 0; u32 peek_seq; u32 *seq; @@ -2506,15 +2738,44 @@ found_ok_skb: } if (!(flags & MSG_TRUNC)) { - err = skb_copy_datagram_msg(skb, offset, msg, used); - if (err) { - /* Exception. Bailout! */ - if (!copied) - copied = -EFAULT; + if (last_copied_dmabuf != -1 && + last_copied_dmabuf != !skb_frags_readable(skb)) break; + + if (skb_frags_readable(skb)) { + err = skb_copy_datagram_msg(skb, offset, msg, + used); + if (err) { + /* Exception. Bailout! */ + if (!copied) + copied = -EFAULT; + break; + } + } else { + if (!(flags & MSG_SOCK_DEVMEM)) { + /* dmabuf skbs can only be received + * with the MSG_SOCK_DEVMEM flag. + */ + if (!copied) + copied = -EFAULT; + + break; + } + + err = tcp_recvmsg_dmabuf(sk, skb, offset, msg, + used); + if (err <= 0) { + if (!copied) + copied = -EFAULT; + + break; + } + used = err; } } + last_copied_dmabuf = !skb_frags_readable(skb); + WRITE_ONCE(*seq, *seq + used); copied += used; len -= used; @@ -2830,7 +3091,7 @@ void __tcp_close(struct sock *sk, long timeout) NET_INC_STATS(sock_net(sk), LINUX_MIB_TCPABORTONCLOSE); tcp_set_state(sk, TCP_CLOSE); tcp_send_active_reset(sk, sk->sk_allocation, - SK_RST_REASON_NOT_SPECIFIED); + SK_RST_REASON_TCP_ABORT_ON_CLOSE); } else if (sock_flag(sk, SOCK_LINGER) && !sk->sk_lingertime) { /* Check zero linger _after_ checking for unread data. */ sk->sk_prot->disconnect(sk, 0); @@ -2905,7 +3166,7 @@ adjudge_to_death: if (READ_ONCE(tp->linger2) < 0) { tcp_set_state(sk, TCP_CLOSE); tcp_send_active_reset(sk, GFP_ATOMIC, - SK_RST_REASON_NOT_SPECIFIED); + SK_RST_REASON_TCP_ABORT_ON_LINGER); __NET_INC_STATS(sock_net(sk), LINUX_MIB_TCPABORTONLINGER); } else { @@ -2924,7 +3185,7 @@ adjudge_to_death: if (tcp_check_oom(sk, 0)) { tcp_set_state(sk, TCP_CLOSE); tcp_send_active_reset(sk, GFP_ATOMIC, - SK_RST_REASON_NOT_SPECIFIED); + SK_RST_REASON_TCP_ABORT_ON_MEMORY); __NET_INC_STATS(sock_net(sk), LINUX_MIB_TCPABORTONMEMORY); } else if (!check_net(sock_net(sk))) { @@ -3022,13 +3283,16 @@ int tcp_disconnect(struct sock *sk, int flags) inet_csk_listen_stop(sk); } else if (unlikely(tp->repair)) { WRITE_ONCE(sk->sk_err, ECONNABORTED); - } else if (tcp_need_reset(old_state) || - (tp->snd_nxt != tp->write_seq && - (1 << old_state) & (TCPF_CLOSING | TCPF_LAST_ACK))) { + } else if (tcp_need_reset(old_state)) { + tcp_send_active_reset(sk, gfp_any(), SK_RST_REASON_TCP_STATE); + WRITE_ONCE(sk->sk_err, ECONNRESET); + } else if (tp->snd_nxt != tp->write_seq && + (1 << old_state) & (TCPF_CLOSING | TCPF_LAST_ACK)) { /* The last check adjusts for discrepancy of Linux wrt. RFC * states */ - tcp_send_active_reset(sk, gfp_any(), SK_RST_REASON_NOT_SPECIFIED); + tcp_send_active_reset(sk, gfp_any(), + SK_RST_REASON_TCP_DISCONNECT_WITH_DATA); WRITE_ONCE(sk->sk_err, ECONNRESET); } else if (old_state == TCP_SYN_SENT) WRITE_ONCE(sk->sk_err, ECONNRESET); @@ -3086,7 +3350,7 @@ int tcp_disconnect(struct sock *sk, int flags) icsk->icsk_ack.rcv_mss = TCP_MIN_MSS; memset(&tp->rx_opt, 0, sizeof(tp->rx_opt)); __sk_dst_reset(sk); - dst_release(xchg((__force struct dst_entry **)&sk->sk_rx_dst, NULL)); + dst_release(unrcu_pointer(xchg(&sk->sk_rx_dst, NULL))); tcp_saved_syn_free(tp); tp->compressed_ack = 0; tp->segs_in = 0; @@ -4461,7 +4725,7 @@ int tcp_md5_hash_key(struct tcp_sigpool *hp, EXPORT_SYMBOL(tcp_md5_hash_key); /* Called with rcu_read_lock() */ -enum skb_drop_reason +static enum skb_drop_reason tcp_inbound_md5_hash(const struct sock *sk, const struct sk_buff *skb, const void *saddr, const void *daddr, int family, int l3index, const __u8 *hash_location) @@ -4481,7 +4745,7 @@ tcp_inbound_md5_hash(const struct sock *sk, const struct sk_buff *skb, if (!key && hash_location) { NET_INC_STATS(sock_net(sk), LINUX_MIB_TCPMD5UNEXPECTED); - tcp_hash_fail("Unexpected MD5 Hash found", family, skb, ""); + trace_tcp_hash_md5_unexpected(sk, skb); return SKB_DROP_REASON_TCP_MD5UNEXPECTED; } @@ -4496,29 +4760,90 @@ tcp_inbound_md5_hash(const struct sock *sk, const struct sk_buff *skb, NULL, skb); if (genhash || memcmp(hash_location, newhash, 16) != 0) { NET_INC_STATS(sock_net(sk), LINUX_MIB_TCPMD5FAILURE); - if (family == AF_INET) { - tcp_hash_fail("MD5 Hash failed", AF_INET, skb, "%s L3 index %d", - genhash ? "tcp_v4_calc_md5_hash failed" - : "", l3index); - } else { - if (genhash) { - tcp_hash_fail("MD5 Hash failed", - AF_INET6, skb, "L3 index %d", - l3index); - } else { - tcp_hash_fail("MD5 Hash mismatch", - AF_INET6, skb, "L3 index %d", - l3index); - } - } + trace_tcp_hash_md5_mismatch(sk, skb); return SKB_DROP_REASON_TCP_MD5FAILURE; } return SKB_NOT_DROPPED_YET; } -EXPORT_SYMBOL(tcp_inbound_md5_hash); +#else +static inline enum skb_drop_reason +tcp_inbound_md5_hash(const struct sock *sk, const struct sk_buff *skb, + const void *saddr, const void *daddr, + int family, int l3index, const __u8 *hash_location) +{ + return SKB_NOT_DROPPED_YET; +} #endif +/* Called with rcu_read_lock() */ +enum skb_drop_reason +tcp_inbound_hash(struct sock *sk, const struct request_sock *req, + const struct sk_buff *skb, + const void *saddr, const void *daddr, + int family, int dif, int sdif) +{ + const struct tcphdr *th = tcp_hdr(skb); + const struct tcp_ao_hdr *aoh; + const __u8 *md5_location; + int l3index; + + /* Invalid option or two times meet any of auth options */ + if (tcp_parse_auth_options(th, &md5_location, &aoh)) { + trace_tcp_hash_bad_header(sk, skb); + return SKB_DROP_REASON_TCP_AUTH_HDR; + } + + if (req) { + if (tcp_rsk_used_ao(req) != !!aoh) { + u8 keyid, rnext, maclen; + + if (aoh) { + keyid = aoh->keyid; + rnext = aoh->rnext_keyid; + maclen = tcp_ao_hdr_maclen(aoh); + } else { + keyid = rnext = maclen = 0; + } + + NET_INC_STATS(sock_net(sk), LINUX_MIB_TCPAOBAD); + trace_tcp_ao_handshake_failure(sk, skb, keyid, rnext, maclen); + return SKB_DROP_REASON_TCP_AOFAILURE; + } + } + + /* sdif set, means packet ingressed via a device + * in an L3 domain and dif is set to the l3mdev + */ + l3index = sdif ? dif : 0; + + /* Fast path: unsigned segments */ + if (likely(!md5_location && !aoh)) { + /* Drop if there's TCP-MD5 or TCP-AO key with any rcvid/sndid + * for the remote peer. On TCP-AO established connection + * the last key is impossible to remove, so there's + * always at least one current_key. + */ + if (tcp_ao_required(sk, saddr, family, l3index, true)) { + trace_tcp_hash_ao_required(sk, skb); + return SKB_DROP_REASON_TCP_AONOTFOUND; + } + if (unlikely(tcp_md5_do_lookup(sk, l3index, saddr, family))) { + NET_INC_STATS(sock_net(sk), LINUX_MIB_TCPMD5NOTFOUND); + trace_tcp_hash_md5_required(sk, skb); + return SKB_DROP_REASON_TCP_MD5NOTFOUND; + } + return SKB_NOT_DROPPED_YET; + } + + if (aoh) + return tcp_inbound_ao_hash(sk, skb, family, req, l3index, aoh); + + return tcp_inbound_md5_hash(sk, skb, saddr, daddr, family, + l3index, md5_location); +} +EXPORT_SYMBOL_GPL(tcp_inbound_hash); + void tcp_done(struct sock *sk) { struct request_sock *req; @@ -4573,6 +4898,13 @@ int tcp_abort(struct sock *sk, int err) /* Don't race with userspace socket closes such as tcp_close. */ lock_sock(sk); + /* Avoid closing the same socket twice. */ + if (sk->sk_state == TCP_CLOSE) { + if (!has_current_bpf_ctx()) + release_sock(sk); + return -ENOENT; + } + if (sk->sk_state == TCP_LISTEN) { tcp_set_state(sk, TCP_CLOSE); inet_csk_listen_stop(sk); @@ -4582,20 +4914,13 @@ int tcp_abort(struct sock *sk, int err) local_bh_disable(); bh_lock_sock(sk); - if (!sock_flag(sk, SOCK_DEAD)) { - WRITE_ONCE(sk->sk_err, err); - /* This barrier is coupled with smp_rmb() in tcp_poll() */ - smp_wmb(); - sk_error_report(sk); - if (tcp_need_reset(sk->sk_state)) - tcp_send_active_reset(sk, GFP_ATOMIC, - SK_RST_REASON_NOT_SPECIFIED); - tcp_done(sk); - } + if (tcp_need_reset(sk->sk_state)) + tcp_send_active_reset(sk, GFP_ATOMIC, + SK_RST_REASON_TCP_STATE); + tcp_done_with_error(sk, err); bh_unlock_sock(sk); local_bh_enable(); - tcp_write_queue_purge(sk); if (!has_current_bpf_ctx()) release_sock(sk); return 0; diff --git a/net/ipv4/tcp_ao.c b/net/ipv4/tcp_ao.c index 09c0fa6756b7..db6516092daf 100644 --- a/net/ipv4/tcp_ao.c +++ b/net/ipv4/tcp_ao.c @@ -16,6 +16,7 @@ #include <net/tcp.h> #include <net/ipv6.h> #include <net/icmp.h> +#include <trace/events/tcp.h> DEFINE_STATIC_KEY_DEFERRED_FALSE(tcp_ao_needed, HZ); @@ -266,32 +267,49 @@ static void tcp_ao_key_free_rcu(struct rcu_head *head) kfree_sensitive(key); } -void tcp_ao_destroy_sock(struct sock *sk, bool twsk) +static void tcp_ao_info_free_rcu(struct rcu_head *head) { - struct tcp_ao_info *ao; + struct tcp_ao_info *ao = container_of(head, struct tcp_ao_info, rcu); struct tcp_ao_key *key; struct hlist_node *n; + hlist_for_each_entry_safe(key, n, &ao->head, node) { + hlist_del(&key->node); + tcp_sigpool_release(key->tcp_sigpool_id); + kfree_sensitive(key); + } + kfree(ao); + static_branch_slow_dec_deferred(&tcp_ao_needed); +} + +static void tcp_ao_sk_omem_free(struct sock *sk, struct tcp_ao_info *ao) +{ + size_t total_ao_sk_mem = 0; + struct tcp_ao_key *key; + + hlist_for_each_entry(key, &ao->head, node) + total_ao_sk_mem += tcp_ao_sizeof_key(key); + atomic_sub(total_ao_sk_mem, &sk->sk_omem_alloc); +} + +void tcp_ao_destroy_sock(struct sock *sk, bool twsk) +{ + struct tcp_ao_info *ao; + if (twsk) { ao = rcu_dereference_protected(tcp_twsk(sk)->ao_info, 1); - tcp_twsk(sk)->ao_info = NULL; + rcu_assign_pointer(tcp_twsk(sk)->ao_info, NULL); } else { ao = rcu_dereference_protected(tcp_sk(sk)->ao_info, 1); - tcp_sk(sk)->ao_info = NULL; + rcu_assign_pointer(tcp_sk(sk)->ao_info, NULL); } if (!ao || !refcount_dec_and_test(&ao->refcnt)) return; - hlist_for_each_entry_safe(key, n, &ao->head, node) { - hlist_del_rcu(&key->node); - if (!twsk) - atomic_sub(tcp_ao_sizeof_key(key), &sk->sk_omem_alloc); - call_rcu(&key->rcu, tcp_ao_key_free_rcu); - } - - kfree_rcu(ao, rcu); - static_branch_slow_dec_deferred(&tcp_ao_needed); + if (!twsk) + tcp_ao_sk_omem_free(sk, ao); + call_rcu(&ao->rcu, tcp_ao_info_free_rcu); } void tcp_ao_time_wait(struct tcp_timewait_sock *tcptw, struct tcp_sock *tp) @@ -884,17 +902,16 @@ tcp_ao_verify_hash(const struct sock *sk, const struct sk_buff *skb, const struct tcp_ao_hdr *aoh, struct tcp_ao_key *key, u8 *traffic_key, u8 *phash, u32 sne, int l3index) { - u8 maclen = aoh->length - sizeof(struct tcp_ao_hdr); const struct tcphdr *th = tcp_hdr(skb); + u8 maclen = tcp_ao_hdr_maclen(aoh); void *hash_buf = NULL; if (maclen != tcp_ao_maclen(key)) { NET_INC_STATS(sock_net(sk), LINUX_MIB_TCPAOBAD); atomic64_inc(&info->counters.pkt_bad); atomic64_inc(&key->pkt_bad); - tcp_hash_fail("AO hash wrong length", family, skb, - "%u != %d L3index: %d", maclen, - tcp_ao_maclen(key), l3index); + trace_tcp_ao_wrong_maclen(sk, skb, aoh->keyid, + aoh->rnext_keyid, maclen); return SKB_DROP_REASON_TCP_AOFAILURE; } @@ -909,8 +926,8 @@ tcp_ao_verify_hash(const struct sock *sk, const struct sk_buff *skb, NET_INC_STATS(sock_net(sk), LINUX_MIB_TCPAOBAD); atomic64_inc(&info->counters.pkt_bad); atomic64_inc(&key->pkt_bad); - tcp_hash_fail("AO hash mismatch", family, skb, - "L3index: %d", l3index); + trace_tcp_ao_mismatch(sk, skb, aoh->keyid, + aoh->rnext_keyid, maclen); kfree(hash_buf); return SKB_DROP_REASON_TCP_AOFAILURE; } @@ -927,6 +944,7 @@ tcp_inbound_ao_hash(struct sock *sk, const struct sk_buff *skb, int l3index, const struct tcp_ao_hdr *aoh) { const struct tcphdr *th = tcp_hdr(skb); + u8 maclen = tcp_ao_hdr_maclen(aoh); u8 *phash = (u8 *)(aoh + 1); /* hash goes just after the header */ struct tcp_ao_info *info; enum skb_drop_reason ret; @@ -939,8 +957,8 @@ tcp_inbound_ao_hash(struct sock *sk, const struct sk_buff *skb, info = rcu_dereference(tcp_sk(sk)->ao_info); if (!info) { NET_INC_STATS(sock_net(sk), LINUX_MIB_TCPAOKEYNOTFOUND); - tcp_hash_fail("AO key not found", family, skb, - "keyid: %u L3index: %d", aoh->keyid, l3index); + trace_tcp_ao_key_not_found(sk, skb, aoh->keyid, + aoh->rnext_keyid, maclen); return SKB_DROP_REASON_TCP_AOUNEXPECTED; } @@ -981,6 +999,9 @@ tcp_inbound_ao_hash(struct sock *sk, const struct sk_buff *skb, current_key = READ_ONCE(info->current_key); /* Key rotation: the peer asks us to use new key (RNext) */ if (unlikely(aoh->rnext_keyid != current_key->sndid)) { + trace_tcp_ao_rnext_request(sk, skb, current_key->sndid, + aoh->rnext_keyid, + tcp_ao_hdr_maclen(aoh)); /* If the key is not found we do nothing. */ key = tcp_ao_established_key(info, aoh->rnext_keyid, -1); if (key) @@ -1046,8 +1067,8 @@ verify_hash: key_not_found: NET_INC_STATS(sock_net(sk), LINUX_MIB_TCPAOKEYNOTFOUND); atomic64_inc(&info->counters.key_not_found); - tcp_hash_fail("Requested by the peer AO key id not found", - family, skb, "L3index: %d", l3index); + trace_tcp_ao_key_not_found(sk, skb, aoh->keyid, + aoh->rnext_keyid, maclen); return SKB_DROP_REASON_TCP_AOKEYNOTFOUND; } diff --git a/net/ipv4/tcp_bpf.c b/net/ipv4/tcp_bpf.c index 53b0d62fd2c2..e7658c5d6b79 100644 --- a/net/ipv4/tcp_bpf.c +++ b/net/ipv4/tcp_bpf.c @@ -30,7 +30,7 @@ void tcp_eat_skb(struct sock *sk, struct sk_buff *skb) } static int bpf_tcp_ingress(struct sock *sk, struct sk_psock *psock, - struct sk_msg *msg, u32 apply_bytes, int flags) + struct sk_msg *msg, u32 apply_bytes) { bool apply = apply_bytes; struct scatterlist *sge; @@ -167,7 +167,7 @@ int tcp_bpf_sendmsg_redir(struct sock *sk, bool ingress, if (unlikely(!psock)) return -EPIPE; - ret = ingress ? bpf_tcp_ingress(sk, psock, msg, bytes, flags) : + ret = ingress ? bpf_tcp_ingress(sk, psock, msg, bytes) : tcp_bpf_push_locked(sk, msg, bytes, flags, false); sk_psock_put(sk, psock); return ret; @@ -577,7 +577,7 @@ out_err: err = sk_stream_error(sk, msg->msg_flags, err); release_sock(sk); sk_psock_put(sk, psock); - return copied ? copied : err; + return copied > 0 ? copied : err; } enum { diff --git a/net/ipv4/tcp_cong.c b/net/ipv4/tcp_cong.c index 28ffcfbeef14..0306d257fa64 100644 --- a/net/ipv4/tcp_cong.c +++ b/net/ipv4/tcp_cong.c @@ -46,8 +46,7 @@ void tcp_set_ca_state(struct sock *sk, const u8 ca_state) } /* Must be called with rcu lock held */ -static struct tcp_congestion_ops *tcp_ca_find_autoload(struct net *net, - const char *name) +static struct tcp_congestion_ops *tcp_ca_find_autoload(const char *name) { struct tcp_congestion_ops *ca = tcp_ca_find(name); @@ -178,7 +177,7 @@ int tcp_update_congestion_control(struct tcp_congestion_ops *ca, struct tcp_cong return ret; } -u32 tcp_ca_get_key_by_name(struct net *net, const char *name, bool *ecn_ca) +u32 tcp_ca_get_key_by_name(const char *name, bool *ecn_ca) { const struct tcp_congestion_ops *ca; u32 key = TCP_CA_UNSPEC; @@ -186,7 +185,7 @@ u32 tcp_ca_get_key_by_name(struct net *net, const char *name, bool *ecn_ca) might_sleep(); rcu_read_lock(); - ca = tcp_ca_find_autoload(net, name); + ca = tcp_ca_find_autoload(name); if (ca) { key = ca->key; *ecn_ca = ca->flags & TCP_CONG_NEEDS_ECN; @@ -203,9 +202,10 @@ char *tcp_ca_get_name_by_key(u32 key, char *buffer) rcu_read_lock(); ca = tcp_ca_find_key(key); - if (ca) - ret = strncpy(buffer, ca->name, - TCP_CA_NAME_MAX); + if (ca) { + strscpy(buffer, ca->name, TCP_CA_NAME_MAX); + ret = buffer; + } rcu_read_unlock(); return ret; @@ -283,7 +283,7 @@ int tcp_set_default_congestion_control(struct net *net, const char *name) int ret; rcu_read_lock(); - ca = tcp_ca_find_autoload(net, name); + ca = tcp_ca_find_autoload(name); if (!ca) { ret = -ENOENT; } else if (!bpf_try_module_get(ca, ca->owner)) { @@ -338,7 +338,7 @@ void tcp_get_default_congestion_control(struct net *net, char *name) rcu_read_lock(); ca = rcu_dereference(net->ipv4.tcp_congestion_control); - strncpy(name, ca->name, TCP_CA_NAME_MAX); + strscpy(name, ca->name, TCP_CA_NAME_MAX); rcu_read_unlock(); } @@ -421,7 +421,7 @@ int tcp_set_congestion_control(struct sock *sk, const char *name, bool load, if (!load) ca = tcp_ca_find(name); else - ca = tcp_ca_find_autoload(sock_net(sk), name); + ca = tcp_ca_find_autoload(name); /* No change asking for existing value */ if (ca == icsk->icsk_ca_ops) { diff --git a/net/ipv4/tcp_fastopen.c b/net/ipv4/tcp_fastopen.c index 8ed54e7334a9..0f523cbfe329 100644 --- a/net/ipv4/tcp_fastopen.c +++ b/net/ipv4/tcp_fastopen.c @@ -49,7 +49,7 @@ void tcp_fastopen_ctx_destroy(struct net *net) { struct tcp_fastopen_context *ctxt; - ctxt = xchg((__force struct tcp_fastopen_context **)&net->ipv4.tcp_fastopen_ctx, NULL); + ctxt = unrcu_pointer(xchg(&net->ipv4.tcp_fastopen_ctx, NULL)); if (ctxt) call_rcu(&ctxt->rcu, tcp_fastopen_ctx_free); @@ -80,9 +80,10 @@ int tcp_fastopen_reset_cipher(struct net *net, struct sock *sk, if (sk) { q = &inet_csk(sk)->icsk_accept_queue.fastopenq; - octx = xchg((__force struct tcp_fastopen_context **)&q->ctx, ctx); + octx = unrcu_pointer(xchg(&q->ctx, RCU_INITIALIZER(ctx))); } else { - octx = xchg((__force struct tcp_fastopen_context **)&net->ipv4.tcp_fastopen_ctx, ctx); + octx = unrcu_pointer(xchg(&net->ipv4.tcp_fastopen_ctx, + RCU_INITIALIZER(ctx))); } if (octx) diff --git a/net/ipv4/tcp_htcp.c b/net/ipv4/tcp_htcp.c index 52b1f2665dfa..81b96331b2bb 100644 --- a/net/ipv4/tcp_htcp.c +++ b/net/ipv4/tcp_htcp.c @@ -185,7 +185,7 @@ static inline void htcp_alpha_update(struct htcp *ca) u32 scale = (HZ << 3) / (10 * minRTT); /* clamping ratio to interval [0.5,10]<<3 */ - scale = min(max(scale, 1U << 2), 10U << 3); + scale = clamp(scale, 1U << 2, 10U << 3); factor = (factor << 3) / scale; if (!factor) factor = 1; diff --git a/net/ipv4/tcp_input.c b/net/ipv4/tcp_input.c index 01d208e0eef3..9f314dfa1490 100644 --- a/net/ipv4/tcp_input.c +++ b/net/ipv4/tcp_input.c @@ -238,9 +238,14 @@ static void tcp_measure_rcv_mss(struct sock *sk, const struct sk_buff *skb) */ if (unlikely(len != icsk->icsk_ack.rcv_mss)) { u64 val = (u64)skb->len << TCP_RMEM_TO_WIN_SCALE; + u8 old_ratio = tcp_sk(sk)->scaling_ratio; do_div(val, skb->truesize); tcp_sk(sk)->scaling_ratio = val ? val : 1; + + if (old_ratio != tcp_sk(sk)->scaling_ratio) + WRITE_ONCE(tcp_sk(sk)->window_clamp, + tcp_win_from_space(sk, sk->sk_rcvbuf)); } icsk->icsk_ack.rcv_mss = min_t(unsigned int, len, tcp_sk(sk)->advmss); @@ -2129,8 +2134,16 @@ void tcp_clear_retrans(struct tcp_sock *tp) static inline void tcp_init_undo(struct tcp_sock *tp) { tp->undo_marker = tp->snd_una; + /* Retransmission still in flight may cause DSACKs later. */ - tp->undo_retrans = tp->retrans_out ? : -1; + /* First, account for regular retransmits in flight: */ + tp->undo_retrans = tp->retrans_out; + /* Next, account for TLP retransmits in flight: */ + if (tp->tlp_high_seq && tp->tlp_retrans) + tp->undo_retrans++; + /* Finally, avoid 0, because undo_retrans==0 means "can undo now": */ + if (!tp->undo_retrans) + tp->undo_retrans = -1; } static bool tcp_is_rack(const struct sock *sk) @@ -2209,6 +2222,7 @@ void tcp_enter_loss(struct sock *sk) tcp_set_ca_state(sk, TCP_CA_Loss); tp->high_seq = tp->snd_nxt; + tp->tlp_high_seq = 0; tcp_ecn_queue_cwr(tp); /* F-RTO RFC5682 sec 3.1 step 1: retransmit SND.UNA if no previous @@ -2782,13 +2796,37 @@ static void tcp_mtup_probe_success(struct sock *sk) NET_INC_STATS(sock_net(sk), LINUX_MIB_TCPMTUPSUCCESS); } +/* Sometimes we deduce that packets have been dropped due to reasons other than + * congestion, like path MTU reductions or failed client TFO attempts. In these + * cases we call this function to retransmit as many packets as cwnd allows, + * without reducing cwnd. Given that retransmits will set retrans_stamp to a + * non-zero value (and may do so in a later calling context due to TSQ), we + * also enter CA_Loss so that we track when all retransmitted packets are ACKed + * and clear retrans_stamp when that happens (to ensure later recurring RTOs + * are using the correct retrans_stamp and don't declare ETIMEDOUT + * prematurely). + */ +static void tcp_non_congestion_loss_retransmit(struct sock *sk) +{ + const struct inet_connection_sock *icsk = inet_csk(sk); + struct tcp_sock *tp = tcp_sk(sk); + + if (icsk->icsk_ca_state != TCP_CA_Loss) { + tp->high_seq = tp->snd_nxt; + tp->snd_ssthresh = tcp_current_ssthresh(sk); + tp->prior_ssthresh = 0; + tp->undo_marker = 0; + tcp_set_ca_state(sk, TCP_CA_Loss); + } + tcp_xmit_retransmit_queue(sk); +} + /* Do a simple retransmit without using the backoff mechanisms in * tcp_timer. This is used for path mtu discovery. * The socket is already locked here. */ void tcp_simple_retransmit(struct sock *sk) { - const struct inet_connection_sock *icsk = inet_csk(sk); struct tcp_sock *tp = tcp_sk(sk); struct sk_buff *skb; int mss; @@ -2828,14 +2866,7 @@ void tcp_simple_retransmit(struct sock *sk) * in network, but units changed and effective * cwnd/ssthresh really reduced now. */ - if (icsk->icsk_ca_state != TCP_CA_Loss) { - tp->high_seq = tp->snd_nxt; - tp->snd_ssthresh = tcp_current_ssthresh(sk); - tp->prior_ssthresh = 0; - tp->undo_marker = 0; - tcp_set_ca_state(sk, TCP_CA_Loss); - } - tcp_xmit_retransmit_queue(sk); + tcp_non_congestion_loss_retransmit(sk); } EXPORT_SYMBOL(tcp_simple_retransmit); @@ -3060,7 +3091,7 @@ static void tcp_fastretrans_alert(struct sock *sk, const u32 prior_snd_una, return; if (tcp_try_undo_dsack(sk)) - tcp_try_keep_open(sk); + tcp_try_to_open(sk, flag); tcp_identify_packet_loss(sk, ack_flag); if (icsk->icsk_ca_state != TCP_CA_Recovery) { @@ -3578,8 +3609,10 @@ static void tcp_snd_sne_update(struct tcp_sock *tp, u32 ack) ao = rcu_dereference_protected(tp->ao_info, lockdep_sock_is_held((struct sock *)tp)); - if (ao && ack < tp->snd_una) + if (ao && ack < tp->snd_una) { ao->snd_sne++; + trace_tcp_ao_snd_sne_update((struct sock *)tp, ao->snd_sne); + } #endif } @@ -3604,8 +3637,10 @@ static void tcp_rcv_sne_update(struct tcp_sock *tp, u32 seq) ao = rcu_dereference_protected(tp->ao_info, lockdep_sock_is_held((struct sock *)tp)); - if (ao && seq < tp->rcv_nxt) + if (ao && seq < tp->rcv_nxt) { ao->rcv_sne++; + trace_tcp_ao_rcv_sne_update((struct sock *)tp, ao->rcv_sne); + } #endif } @@ -4207,6 +4242,13 @@ void tcp_parse_options(const struct net *net, */ break; #endif +#ifdef CONFIG_TCP_AO + case TCPOPT_AO: + /* TCP AO has already been checked + * (see tcp_inbound_ao_hash()). + */ + break; +#endif case TCPOPT_FASTOPEN: tcp_parse_fastopen_option( opsize - TCPOLEN_FASTOPEN_BASE, @@ -4436,9 +4478,26 @@ static enum skb_drop_reason tcp_sequence(const struct tcp_sock *tp, return SKB_NOT_DROPPED_YET; } + +void tcp_done_with_error(struct sock *sk, int err) +{ + /* This barrier is coupled with smp_rmb() in tcp_poll() */ + WRITE_ONCE(sk->sk_err, err); + smp_wmb(); + + tcp_write_queue_purge(sk); + tcp_done(sk); + + if (!sock_flag(sk, SOCK_DEAD)) + sk_error_report(sk); +} +EXPORT_SYMBOL(tcp_done_with_error); + /* When we get a reset we do this. */ void tcp_reset(struct sock *sk, struct sk_buff *skb) { + int err; + trace_tcp_receive_reset(sk); /* mptcp can't tell us to ignore reset pkts, @@ -4450,24 +4509,17 @@ void tcp_reset(struct sock *sk, struct sk_buff *skb) /* We want the right error as BSD sees it (and indeed as we do). */ switch (sk->sk_state) { case TCP_SYN_SENT: - WRITE_ONCE(sk->sk_err, ECONNREFUSED); + err = ECONNREFUSED; break; case TCP_CLOSE_WAIT: - WRITE_ONCE(sk->sk_err, EPIPE); + err = EPIPE; break; case TCP_CLOSE: return; default: - WRITE_ONCE(sk->sk_err, ECONNRESET); + err = ECONNRESET; } - /* This barrier is coupled with smp_rmb() in tcp_poll() */ - smp_wmb(); - - tcp_write_queue_purge(sk); - tcp_done(sk); - - if (!sock_flag(sk, SOCK_DEAD)) - sk_error_report(sk); + tcp_done_with_error(sk, err); } /* @@ -4803,10 +4855,7 @@ static bool tcp_try_coalesce(struct sock *sk, if (TCP_SKB_CB(from)->seq != TCP_SKB_CB(to)->end_seq) return false; - if (!mptcp_skb_can_collapse(to, from)) - return false; - - if (skb_cmp_decrypted(from, to)) + if (!tcp_skb_can_collapse_rx(to, from)) return false; if (!skb_try_coalesce(to, from, fragstolen, &delta)) @@ -4849,7 +4898,7 @@ static void tcp_drop_reason(struct sock *sk, struct sk_buff *skb, enum skb_drop_reason reason) { sk_drops_add(sk, skb); - kfree_skb_reason(skb, reason); + sk_skb_reason_drop(sk, skb, reason); } /* This one checks to see if we can put data from the @@ -5342,6 +5391,9 @@ restart: for (end_of_skbs = true; skb != NULL && skb != tail; skb = n) { n = tcp_skb_next(skb, list); + if (!skb_frags_readable(skb)) + goto skip_this; + /* No new bits? It is possible on ofo queue. */ if (!before(start, TCP_SKB_CB(skb)->end_seq)) { skb = tcp_collapse_one(sk, skb, list, root); @@ -5362,17 +5414,20 @@ restart: break; } - if (n && n != tail && mptcp_skb_can_collapse(skb, n) && + if (n && n != tail && skb_frags_readable(n) && + tcp_skb_can_collapse_rx(skb, n) && TCP_SKB_CB(skb)->end_seq != TCP_SKB_CB(n)->seq) { end_of_skbs = false; break; } +skip_this: /* Decided to skip this, advance start seq. */ start = TCP_SKB_CB(skb)->end_seq; } if (end_of_skbs || - (TCP_SKB_CB(skb)->tcp_flags & (TCPHDR_SYN | TCPHDR_FIN))) + (TCP_SKB_CB(skb)->tcp_flags & (TCPHDR_SYN | TCPHDR_FIN)) || + !skb_frags_readable(skb)) return; __skb_queue_head_init(&tmp); @@ -5413,10 +5468,9 @@ restart: skb = tcp_collapse_one(sk, skb, list, root); if (!skb || skb == tail || - !mptcp_skb_can_collapse(nskb, skb) || - (TCP_SKB_CB(skb)->tcp_flags & (TCPHDR_SYN | TCPHDR_FIN))) - goto end; - if (skb_cmp_decrypted(skb, nskb)) + !tcp_skb_can_collapse_rx(nskb, skb) || + (TCP_SKB_CB(skb)->tcp_flags & (TCPHDR_SYN | TCPHDR_FIN)) || + !skb_frags_readable(skb)) goto end; } } @@ -5956,6 +6010,11 @@ static bool tcp_validate_incoming(struct sock *sk, struct sk_buff *skb, * RFC 5961 4.2 : Send a challenge ack */ if (th->syn) { + if (sk->sk_state == TCP_SYN_RECV && sk->sk_socket && th->ack && + TCP_SKB_CB(skb)->seq + 1 == TCP_SKB_CB(skb)->end_seq && + TCP_SKB_CB(skb)->seq + 1 == tp->rcv_nxt && + TCP_SKB_CB(skb)->ack_seq == tp->snd_nxt) + goto pass; syn_challenge: if (syn_inerr) TCP_INC_STATS(sock_net(sk), TCP_MIB_INERRS); @@ -5965,6 +6024,7 @@ syn_challenge: goto discard; } +pass: bpf_skops_parse_hdr(sk, skb); return true; @@ -6295,8 +6355,7 @@ static bool tcp_rcv_fastopen_synack(struct sock *sk, struct sk_buff *synack, tp->fastopen_client_fail = TFO_DATA_NOT_ACKED; skb_rbtree_walk_from(data) tcp_mark_skb_lost(sk, data); - tcp_xmit_retransmit_queue(sk); - tp->retrans_stamp = 0; + tcp_non_congestion_loss_retransmit(sk); NET_INC_STATS(sock_net(sk), LINUX_MIB_TCPFASTOPENACTIVEFAIL); return true; @@ -6982,31 +7041,6 @@ static void tcp_openreq_init(struct request_sock *req, #endif } -struct request_sock *inet_reqsk_alloc(const struct request_sock_ops *ops, - struct sock *sk_listener, - bool attach_listener) -{ - struct request_sock *req = reqsk_alloc(ops, sk_listener, - attach_listener); - - if (req) { - struct inet_request_sock *ireq = inet_rsk(req); - - ireq->ireq_opt = NULL; -#if IS_ENABLED(CONFIG_IPV6) - ireq->pktopts = NULL; -#endif - atomic64_set(&ireq->ir_cookie, 0); - ireq->ireq_state = TCP_NEW_SYN_RECV; - write_pnet(&ireq->ireq_net, sock_net(sk_listener)); - ireq->ireq_family = sk_listener->sk_family; - req->timeout = TCP_TIMEOUT_INIT; - } - - return req; -} -EXPORT_SYMBOL(inet_reqsk_alloc); - /* * Return true if a syncookie should be sent */ @@ -7257,7 +7291,12 @@ int tcp_conn_request(struct request_sock_ops *rsk_ops, tcp_rsk(req)->tfo_listener = false; if (!want_cookie) { req->timeout = tcp_timeout_init((struct sock *)req); - inet_csk_reqsk_queue_hash_add(sk, req, req->timeout); + if (unlikely(!inet_csk_reqsk_queue_hash_add(sk, req, + req->timeout))) { + reqsk_free(req); + return 0; + } + } af_ops->send_synack(sk, dst, &fl, req, &foc, !want_cookie ? TCP_SYNACK_NORMAL : diff --git a/net/ipv4/tcp_ipv4.c b/net/ipv4/tcp_ipv4.c index b710958393e6..5afe5e57c89b 100644 --- a/net/ipv4/tcp_ipv4.c +++ b/net/ipv4/tcp_ipv4.c @@ -79,6 +79,7 @@ #include <linux/seq_file.h> #include <linux/inetdevice.h> #include <linux/btf_ids.h> +#include <linux/skbuff_ref.h> #include <crypto/hash.h> #include <linux/scatterlist.h> @@ -93,7 +94,11 @@ static int tcp_v4_md5_hash_hdr(char *md5_hash, const struct tcp_md5sig_key *key, struct inet_hashinfo tcp_hashinfo; EXPORT_SYMBOL(tcp_hashinfo); -static DEFINE_PER_CPU(struct sock *, ipv4_tcp_sk); +static DEFINE_PER_CPU(struct sock_bh_locked, ipv4_tcp_sk) = { + .bh_lock = INIT_LOCAL_LOCK(bh_lock), +}; + +static DEFINE_MUTEX(tcp_exit_batch_mutex); static u32 tcp_v4_init_seq(const struct sk_buff *skb) { @@ -114,6 +119,10 @@ int tcp_twsk_unique(struct sock *sk, struct sock *sktw, void *twp) const struct inet_timewait_sock *tw = inet_twsk(sktw); const struct tcp_timewait_sock *tcptw = tcp_twsk(sktw); struct tcp_sock *tp = tcp_sk(sk); + int ts_recent_stamp; + + if (READ_ONCE(tw->tw_substate) == TCP_FIN_WAIT2) + reuse = 0; if (reuse == 2) { /* Still does not detect *everything* that goes through @@ -152,10 +161,11 @@ int tcp_twsk_unique(struct sock *sk, struct sock *sktw, void *twp) If TW bucket has been already destroyed we fall back to VJ's scheme and use initial timestamp retrieved from peer table. */ - if (tcptw->tw_ts_recent_stamp && + ts_recent_stamp = READ_ONCE(tcptw->tw_ts_recent_stamp); + if (ts_recent_stamp && (!twp || (reuse && time_after32(ktime_get_seconds(), - tcptw->tw_ts_recent_stamp)))) { - /* inet_twsk_hashdance() sets sk_refcnt after putting twsk + ts_recent_stamp)))) { + /* inet_twsk_hashdance_schedule() sets sk_refcnt after putting twsk * and releasing the bucket lock. */ if (unlikely(!refcount_inc_not_zero(&sktw->sk_refcnt))) @@ -178,8 +188,8 @@ int tcp_twsk_unique(struct sock *sk, struct sock *sktw, void *twp) if (!seq) seq = 1; WRITE_ONCE(tp->write_seq, seq); - tp->rx_opt.ts_recent = tcptw->tw_ts_recent; - tp->rx_opt.ts_recent_stamp = tcptw->tw_ts_recent_stamp; + tp->rx_opt.ts_recent = READ_ONCE(tcptw->tw_ts_recent); + tp->rx_opt.ts_recent_stamp = ts_recent_stamp; } return 1; @@ -611,15 +621,10 @@ int tcp_v4_err(struct sk_buff *skb, u32 info) ip_icmp_error(sk, skb, err, th->dest, info, (u8 *)th); - if (!sock_owned_by_user(sk)) { - WRITE_ONCE(sk->sk_err, err); - - sk_error_report(sk); - - tcp_done(sk); - } else { + if (!sock_owned_by_user(sk)) + tcp_done_with_error(sk, err); + else WRITE_ONCE(sk->sk_err_soft, err); - } goto out; } @@ -885,7 +890,9 @@ static void tcp_v4_send_reset(const struct sock *sk, struct sk_buff *skb, arg.tos = ip_hdr(skb)->tos; arg.uid = sock_net_uid(net, sk && sk_fullsock(sk) ? sk : NULL); local_bh_disable(); - ctl_sk = this_cpu_read(ipv4_tcp_sk); + local_lock_nested_bh(&ipv4_tcp_sk.bh_lock); + ctl_sk = this_cpu_read(ipv4_tcp_sk.sock); + sock_net_set(ctl_sk, net); if (sk) { ctl_sk->sk_mark = (sk->sk_state == TCP_TIME_WAIT) ? @@ -910,6 +917,7 @@ static void tcp_v4_send_reset(const struct sock *sk, struct sk_buff *skb, sock_net_set(ctl_sk, &init_net); __TCP_INC_STATS(net, TCP_MIB_OUTSEGS); __TCP_INC_STATS(net, TCP_MIB_OUTRSTS); + local_unlock_nested_bh(&ipv4_tcp_sk.bh_lock); local_bh_enable(); #ifdef CONFIG_TCP_MD5SIG @@ -1005,7 +1013,8 @@ static void tcp_v4_send_ack(const struct sock *sk, arg.tos = tos; arg.uid = sock_net_uid(net, sk_fullsock(sk) ? sk : NULL); local_bh_disable(); - ctl_sk = this_cpu_read(ipv4_tcp_sk); + local_lock_nested_bh(&ipv4_tcp_sk.bh_lock); + ctl_sk = this_cpu_read(ipv4_tcp_sk.sock); sock_net_set(ctl_sk, net); ctl_sk->sk_mark = (sk->sk_state == TCP_TIME_WAIT) ? inet_twsk(sk)->tw_mark : READ_ONCE(sk->sk_mark); @@ -1020,6 +1029,7 @@ static void tcp_v4_send_ack(const struct sock *sk, sock_net_set(ctl_sk, &init_net); __TCP_INC_STATS(net, TCP_MIB_OUTSEGS); + local_unlock_nested_bh(&ipv4_tcp_sk.bh_lock); local_bh_enable(); } @@ -1057,19 +1067,17 @@ static void tcp_v4_timewait_ack(struct sock *sk, struct sk_buff *skb) #else if (0) { #endif -#ifdef CONFIG_TCP_MD5SIG - } else if (static_branch_unlikely(&tcp_md5_needed.key)) { + } else if (static_branch_tcp_md5()) { key.md5_key = tcp_twsk_md5_key(tcptw); if (key.md5_key) key.type = TCP_KEY_MD5; -#endif } tcp_v4_send_ack(sk, skb, - tcptw->tw_snd_nxt, tcptw->tw_rcv_nxt, + tcptw->tw_snd_nxt, READ_ONCE(tcptw->tw_rcv_nxt), tcptw->tw_rcv_wnd >> tw->tw_rcv_wscale, tcp_tw_tsval(tcptw), - tcptw->tw_ts_recent, + READ_ONCE(tcptw->tw_ts_recent), tw->tw_bound_dev_if, &key, tw->tw_transparent ? IP_REPLY_ARG_NOSRCCHECK : 0, tw->tw_tos, @@ -1131,8 +1139,7 @@ static void tcp_v4_reqsk_send_ack(const struct sock *sk, struct sk_buff *skb, #else if (0) { #endif -#ifdef CONFIG_TCP_MD5SIG - } else if (static_branch_unlikely(&tcp_md5_needed.key)) { + } else if (static_branch_tcp_md5()) { const union tcp_md5_addr *addr; int l3index; @@ -1141,7 +1148,6 @@ static void tcp_v4_reqsk_send_ack(const struct sock *sk, struct sk_buff *skb, key.md5_key = tcp_md5_do_lookup(sk, l3index, addr, AF_INET); if (key.md5_key) key.type = TCP_KEY_MD5; -#endif } tcp_v4_send_ack(sk, skb, seq, @@ -1939,7 +1945,7 @@ int tcp_v4_do_rcv(struct sock *sk, struct sk_buff *skb) reset: tcp_v4_send_reset(rsk, skb, sk_rst_convert_drop_reason(reason)); discard: - kfree_skb_reason(skb, reason); + sk_skb_reason_drop(sk, skb, reason); /* Be careful here. If this function gets more complicated and * gcc suffers from register pressure on the x86, sk (in %ebx) * might be destroyed here. This current version compiles correctly, @@ -2049,8 +2055,7 @@ bool tcp_add_backlog(struct sock *sk, struct sk_buff *skb, TCP_SKB_CB(skb)->tcp_flags) & TCPHDR_ACK) || ((TCP_SKB_CB(tail)->tcp_flags ^ TCP_SKB_CB(skb)->tcp_flags) & (TCPHDR_ECE | TCPHDR_CWR)) || - !mptcp_skb_can_collapse(tail, skb) || - skb_cmp_decrypted(tail, skb) || + !tcp_skb_can_collapse_rx(tail, skb) || thtail->doff != th->doff || memcmp(thtail + 1, th + 1, hdrlen - sizeof(*th))) goto no_coalesce; @@ -2176,8 +2181,8 @@ int tcp_v4_rcv(struct sk_buff *skb) int dif = inet_iif(skb); const struct iphdr *iph; const struct tcphdr *th; + struct sock *sk = NULL; bool refcounted; - struct sock *sk; int ret; u32 isn; @@ -2376,7 +2381,7 @@ bad_packet: discard_it: SKB_DR_OR(drop_reason, NOT_SPECIFIED); /* Discard frame. */ - kfree_skb_reason(skb, drop_reason); + sk_skb_reason_drop(sk, skb, drop_reason); return 0; discard_and_relse: @@ -2508,10 +2513,25 @@ static void tcp_md5sig_info_free_rcu(struct rcu_head *head) } #endif +static void tcp_release_user_frags(struct sock *sk) +{ +#ifdef CONFIG_PAGE_POOL + unsigned long index; + void *netmem; + + xa_for_each(&sk->sk_user_frags, index, netmem) + WARN_ON_ONCE(!napi_pp_put_page((__force netmem_ref)netmem)); +#endif +} + void tcp_v4_destroy_sock(struct sock *sk) { struct tcp_sock *tp = tcp_sk(sk); + tcp_release_user_frags(sk); + + xa_destroy(&sk->sk_user_frags); + trace_tcp_destroy_sock(sk); tcp_clear_xmit_timers(sk); @@ -2944,7 +2964,7 @@ static void get_timewait4_sock(const struct inet_timewait_sock *tw, seq_printf(f, "%4d: %08X:%04X %08X:%04X" " %02X %08X:%08X %02X:%08lX %08X %5d %8d %d %d %pK", - i, src, srcp, dest, destp, tw->tw_substate, 0, 0, + i, src, srcp, dest, destp, READ_ONCE(tw->tw_substate), 0, 0, 3, jiffies_delta_to_clock_t(delta), 0, 0, 0, 0, refcount_read(&tw->tw_refcnt), tw); } @@ -3506,6 +3526,7 @@ static int __net_init tcp_sk_init(struct net *net) net->ipv4.sysctl_tcp_shrink_window = 0; net->ipv4.sysctl_tcp_pingpong_thresh = 1; + net->ipv4.sysctl_tcp_rto_min_us = jiffies_to_usecs(TCP_RTO_MIN); return 0; } @@ -3514,6 +3535,16 @@ static void __net_exit tcp_sk_exit_batch(struct list_head *net_exit_list) { struct net *net; + /* make sure concurrent calls to tcp_sk_exit_batch from net_cleanup_work + * and failed setup_net error unwinding path are serialized. + * + * tcp_twsk_purge() handles twsk in any dead netns, not just those in + * net_exit_list, the thread that dismantles a particular twsk must + * do so without other thread progressing to refcount_dec_and_test() of + * tcp_death_row.tw_refcount. + */ + mutex_lock(&tcp_exit_batch_mutex); + tcp_twsk_purge(net_exit_list); list_for_each_entry(net, net_exit_list, exit_list) { @@ -3521,6 +3552,8 @@ static void __net_exit tcp_sk_exit_batch(struct list_head *net_exit_list) WARN_ON_ONCE(!refcount_dec_and_test(&net->ipv4.tcp_death_row.tw_refcount)); tcp_fastopen_ctx_destroy(net); } + + mutex_unlock(&tcp_exit_batch_mutex); } static struct pernet_operations __net_initdata tcp_sk_ops = { @@ -3620,7 +3653,9 @@ void __init tcp_v4_init(void) */ inet_sk(sk)->pmtudisc = IP_PMTUDISC_DO; - per_cpu(ipv4_tcp_sk, cpu) = sk; + sk->sk_clockid = CLOCK_MONOTONIC; + + per_cpu(ipv4_tcp_sk.sock, cpu) = sk; } if (register_pernet_subsys(&tcp_sk_ops)) panic("Failed to create the TCP control socket.\n"); diff --git a/net/ipv4/tcp_metrics.c b/net/ipv4/tcp_metrics.c index e93df98de3f4..95669935494e 100644 --- a/net/ipv4/tcp_metrics.c +++ b/net/ipv4/tcp_metrics.c @@ -617,8 +617,13 @@ static struct genl_family tcp_metrics_nl_family; static const struct nla_policy tcp_metrics_nl_policy[TCP_METRICS_ATTR_MAX + 1] = { [TCP_METRICS_ATTR_ADDR_IPV4] = { .type = NLA_U32, }, - [TCP_METRICS_ATTR_ADDR_IPV6] = { .type = NLA_BINARY, - .len = sizeof(struct in6_addr), }, + [TCP_METRICS_ATTR_ADDR_IPV6] = + NLA_POLICY_EXACT_LEN(sizeof(struct in6_addr)), + + [TCP_METRICS_ATTR_SADDR_IPV4] = { .type = NLA_U32, }, + [TCP_METRICS_ATTR_SADDR_IPV6] = + NLA_POLICY_EXACT_LEN(sizeof(struct in6_addr)), + /* Following attributes are not received for GET/DEL, * we keep them for reference */ @@ -810,8 +815,6 @@ static int __parse_nl_addr(struct genl_info *info, struct inetpeer_addr *addr, if (a) { struct in6_addr in6; - if (nla_len(a) != sizeof(struct in6_addr)) - return -EINVAL; in6 = nla_get_in6_addr(a); inetpeer_set_addr_v6(addr, &in6); if (hash) diff --git a/net/ipv4/tcp_minisocks.c b/net/ipv4/tcp_minisocks.c index 538c06f95918..bb1fe1ba867a 100644 --- a/net/ipv4/tcp_minisocks.c +++ b/net/ipv4/tcp_minisocks.c @@ -52,16 +52,17 @@ tcp_timewait_check_oow_rate_limit(struct inet_timewait_sock *tw, return TCP_TW_SUCCESS; } -static void twsk_rcv_nxt_update(struct tcp_timewait_sock *tcptw, u32 seq) +static void twsk_rcv_nxt_update(struct tcp_timewait_sock *tcptw, u32 seq, + u32 rcv_nxt) { #ifdef CONFIG_TCP_AO struct tcp_ao_info *ao; ao = rcu_dereference(tcptw->ao_info); - if (unlikely(ao && seq < tcptw->tw_rcv_nxt)) + if (unlikely(ao && seq < rcv_nxt)) WRITE_ONCE(ao->rcv_sne, ao->rcv_sne + 1); #endif - tcptw->tw_rcv_nxt = seq; + WRITE_ONCE(tcptw->tw_rcv_nxt, seq); } /* @@ -98,43 +99,46 @@ enum tcp_tw_status tcp_timewait_state_process(struct inet_timewait_sock *tw, struct sk_buff *skb, const struct tcphdr *th, u32 *tw_isn) { - struct tcp_options_received tmp_opt; struct tcp_timewait_sock *tcptw = tcp_twsk((struct sock *)tw); + u32 rcv_nxt = READ_ONCE(tcptw->tw_rcv_nxt); + struct tcp_options_received tmp_opt; bool paws_reject = false; + int ts_recent_stamp; tmp_opt.saw_tstamp = 0; - if (th->doff > (sizeof(*th) >> 2) && tcptw->tw_ts_recent_stamp) { + ts_recent_stamp = READ_ONCE(tcptw->tw_ts_recent_stamp); + if (th->doff > (sizeof(*th) >> 2) && ts_recent_stamp) { tcp_parse_options(twsk_net(tw), skb, &tmp_opt, 0, NULL); if (tmp_opt.saw_tstamp) { if (tmp_opt.rcv_tsecr) tmp_opt.rcv_tsecr -= tcptw->tw_ts_offset; - tmp_opt.ts_recent = tcptw->tw_ts_recent; - tmp_opt.ts_recent_stamp = tcptw->tw_ts_recent_stamp; + tmp_opt.ts_recent = READ_ONCE(tcptw->tw_ts_recent); + tmp_opt.ts_recent_stamp = ts_recent_stamp; paws_reject = tcp_paws_reject(&tmp_opt, th->rst); } } - if (tw->tw_substate == TCP_FIN_WAIT2) { + if (READ_ONCE(tw->tw_substate) == TCP_FIN_WAIT2) { /* Just repeat all the checks of tcp_rcv_state_process() */ /* Out of window, send ACK */ if (paws_reject || !tcp_in_window(TCP_SKB_CB(skb)->seq, TCP_SKB_CB(skb)->end_seq, - tcptw->tw_rcv_nxt, - tcptw->tw_rcv_nxt + tcptw->tw_rcv_wnd)) + rcv_nxt, + rcv_nxt + tcptw->tw_rcv_wnd)) return tcp_timewait_check_oow_rate_limit( tw, skb, LINUX_MIB_TCPACKSKIPPEDFINWAIT2); if (th->rst) goto kill; - if (th->syn && !before(TCP_SKB_CB(skb)->seq, tcptw->tw_rcv_nxt)) + if (th->syn && !before(TCP_SKB_CB(skb)->seq, rcv_nxt)) return TCP_TW_RST; /* Dup ACK? */ if (!th->ack || - !after(TCP_SKB_CB(skb)->end_seq, tcptw->tw_rcv_nxt) || + !after(TCP_SKB_CB(skb)->end_seq, rcv_nxt) || TCP_SKB_CB(skb)->end_seq == TCP_SKB_CB(skb)->seq) { inet_twsk_put(tw); return TCP_TW_SUCCESS; @@ -144,16 +148,19 @@ tcp_timewait_state_process(struct inet_timewait_sock *tw, struct sk_buff *skb, * reset. */ if (!th->fin || - TCP_SKB_CB(skb)->end_seq != tcptw->tw_rcv_nxt + 1) + TCP_SKB_CB(skb)->end_seq != rcv_nxt + 1) return TCP_TW_RST; /* FIN arrived, enter true time-wait state. */ - tw->tw_substate = TCP_TIME_WAIT; - twsk_rcv_nxt_update(tcptw, TCP_SKB_CB(skb)->end_seq); + WRITE_ONCE(tw->tw_substate, TCP_TIME_WAIT); + twsk_rcv_nxt_update(tcptw, TCP_SKB_CB(skb)->end_seq, + rcv_nxt); if (tmp_opt.saw_tstamp) { - tcptw->tw_ts_recent_stamp = ktime_get_seconds(); - tcptw->tw_ts_recent = tmp_opt.rcv_tsval; + WRITE_ONCE(tcptw->tw_ts_recent_stamp, + ktime_get_seconds()); + WRITE_ONCE(tcptw->tw_ts_recent, + tmp_opt.rcv_tsval); } inet_twsk_reschedule(tw, TCP_TIMEWAIT_LEN); @@ -178,7 +185,7 @@ tcp_timewait_state_process(struct inet_timewait_sock *tw, struct sk_buff *skb, */ if (!paws_reject && - (TCP_SKB_CB(skb)->seq == tcptw->tw_rcv_nxt && + (TCP_SKB_CB(skb)->seq == rcv_nxt && (TCP_SKB_CB(skb)->seq == TCP_SKB_CB(skb)->end_seq || th->rst))) { /* In window segment, it may be only reset or bare ack. */ @@ -197,8 +204,10 @@ kill: } if (tmp_opt.saw_tstamp) { - tcptw->tw_ts_recent = tmp_opt.rcv_tsval; - tcptw->tw_ts_recent_stamp = ktime_get_seconds(); + WRITE_ONCE(tcptw->tw_ts_recent, + tmp_opt.rcv_tsval); + WRITE_ONCE(tcptw->tw_ts_recent_stamp, + ktime_get_seconds()); } inet_twsk_put(tw); @@ -223,9 +232,9 @@ kill: */ if (th->syn && !th->rst && !th->ack && !paws_reject && - (after(TCP_SKB_CB(skb)->seq, tcptw->tw_rcv_nxt) || + (after(TCP_SKB_CB(skb)->seq, rcv_nxt) || (tmp_opt.saw_tstamp && - (s32)(tcptw->tw_ts_recent - tmp_opt.rcv_tsval) < 0))) { + (s32)(READ_ONCE(tcptw->tw_ts_recent) - tmp_opt.rcv_tsval) < 0))) { u32 isn = tcptw->tw_snd_nxt + 65535 + 2; if (isn == 0) isn++; @@ -339,17 +348,10 @@ void tcp_time_wait(struct sock *sk, int state, int timeo) if (state == TCP_TIME_WAIT) timeo = TCP_TIMEWAIT_LEN; - /* tw_timer is pinned, so we need to make sure BH are disabled - * in following section, otherwise timer handler could run before - * we complete the initialization. - */ - local_bh_disable(); - inet_twsk_schedule(tw, timeo); /* Linkage updates. * Note that access to tw after this point is illegal. */ - inet_twsk_hashdance(tw, sk, net->ipv4.tcp_death_row.hashinfo); - local_bh_enable(); + inet_twsk_hashdance_schedule(tw, sk, net->ipv4.tcp_death_row.hashinfo, timeo); } else { /* Sorry, if we're out of memory, just CLOSE this * socket up. We've got bigger problems than @@ -515,9 +517,6 @@ struct sock *tcp_create_openreq_child(const struct sock *sk, const struct tcp_sock *oldtp; struct tcp_sock *newtp; u32 seq; -#ifdef CONFIG_TCP_AO - struct tcp_ao_key *ao_key; -#endif if (!newsk) return NULL; @@ -608,10 +607,14 @@ struct sock *tcp_create_openreq_child(const struct sock *sk, #endif #ifdef CONFIG_TCP_AO newtp->ao_info = NULL; - ao_key = treq->af_specific->ao_lookup(sk, req, - tcp_rsk(req)->ao_keyid, -1); - if (ao_key) - newtp->tcp_header_len += tcp_ao_len_aligned(ao_key); + + if (tcp_rsk_used_ao(req)) { + struct tcp_ao_key *ao_key; + + ao_key = treq->af_specific->ao_lookup(sk, req, tcp_rsk(req)->ao_keyid, -1); + if (ao_key) + newtp->tcp_header_len += tcp_ao_len_aligned(ao_key); + } #endif if (skb->len >= TCP_MSS_DEFAULT + newtp->tcp_header_len) newicsk->icsk_ack.last_seg_size = skb->len - newtp->tcp_header_len; @@ -625,6 +628,8 @@ struct sock *tcp_create_openreq_child(const struct sock *sk, __TCP_INC_STATS(sock_net(sk), TCP_MIB_PASSIVEOPENS); + xa_init_flags(&newsk->sk_user_frags, XA_FLAGS_ALLOC1); + return newsk; } EXPORT_SYMBOL(tcp_create_openreq_child); diff --git a/net/ipv4/tcp_offload.c b/net/ipv4/tcp_offload.c index 4b791e74529e..e4ad3311e148 100644 --- a/net/ipv4/tcp_offload.c +++ b/net/ipv4/tcp_offload.c @@ -140,6 +140,9 @@ struct sk_buff *tcp_gso_segment(struct sk_buff *skb, if (thlen < sizeof(*th)) goto out; + if (unlikely(skb_checksum_start(skb) != skb_transport_header(skb))) + goto out; + if (!pskb_may_pull(skb, thlen)) goto out; diff --git a/net/ipv4/tcp_output.c b/net/ipv4/tcp_output.c index 95618d0e78e4..4fd746bd4d54 100644 --- a/net/ipv4/tcp_output.c +++ b/net/ipv4/tcp_output.c @@ -1301,7 +1301,7 @@ static int __tcp_transmit_skb(struct sock *sk, struct sk_buff *skb, tp = tcp_sk(sk); prior_wstamp = tp->tcp_wstamp_ns; tp->tcp_wstamp_ns = max(tp->tcp_wstamp_ns, tp->tcp_clock_cache); - skb_set_delivery_time(skb, tp->tcp_wstamp_ns, true); + skb_set_delivery_time(skb, tp->tcp_wstamp_ns, SKB_CLOCK_MONOTONIC); if (clone_it) { oskb = skb; @@ -1655,7 +1655,7 @@ int tcp_fragment(struct sock *sk, enum tcp_queue tcp_queue, skb_split(skb, buff, len); - skb_set_delivery_time(buff, skb->tstamp, true); + skb_set_delivery_time(buff, skb->tstamp, SKB_CLOCK_MONOTONIC); tcp_fragment_tstamp(skb, buff); old_factor = tcp_skb_pcount(skb); @@ -2344,7 +2344,8 @@ static bool tcp_can_coalesce_send_queue_head(struct sock *sk, int len) if (unlikely(TCP_SKB_CB(skb)->eor) || tcp_has_tx_tstamp(skb) || - !skb_pure_zcopy_same(skb, next)) + !skb_pure_zcopy_same(skb, next) || + skb_frags_readable(skb) != skb_frags_readable(next)) return false; len -= skb->len; @@ -2764,7 +2765,7 @@ static bool tcp_write_xmit(struct sock *sk, unsigned int mss_now, int nonagle, if (unlikely(tp->repair) && tp->repair_queue == TCP_SEND_QUEUE) { /* "skb_mstamp_ns" is used as a start point for the retransmit timer */ tp->tcp_wstamp_ns = tp->tcp_clock_cache; - skb_set_delivery_time(skb, tp->tcp_wstamp_ns, true); + skb_set_delivery_time(skb, tp->tcp_wstamp_ns, SKB_CLOCK_MONOTONIC); list_move_tail(&skb->tcp_tsorted_anchor, &tp->tsorted_sent_queue); tcp_init_tso_segs(skb, mss_now); goto repair; /* Skip network transmission */ @@ -3264,6 +3265,8 @@ static bool tcp_can_collapse(const struct sock *sk, const struct sk_buff *skb) return false; if (skb_cloned(skb)) return false; + if (!skb_frags_readable(skb)) + return false; /* Some heuristics for collapsing over SACK'd could be invented */ if (TCP_SKB_CB(skb)->sacked & TCPCB_SACKED_ACKED) return false; @@ -3649,7 +3652,7 @@ void tcp_send_active_reset(struct sock *sk, gfp_t priority, /* skb of trace_tcp_send_reset() keeps the skb that caused RST, * skb here is different to the troublesome skb, so use NULL */ - trace_tcp_send_reset(sk, NULL, SK_RST_REASON_NOT_SPECIFIED); + trace_tcp_send_reset(sk, NULL, reason); } /* Send a crossed SYN-ACK during socket establishment. @@ -3752,11 +3755,11 @@ struct sk_buff *tcp_make_synack(const struct sock *sk, struct dst_entry *dst, #ifdef CONFIG_SYN_COOKIES if (unlikely(synack_type == TCP_SYNACK_COOKIE && ireq->tstamp_ok)) skb_set_delivery_time(skb, cookie_init_timestamp(req, now), - true); + SKB_CLOCK_MONOTONIC); else #endif { - skb_set_delivery_time(skb, now, true); + skb_set_delivery_time(skb, now, SKB_CLOCK_MONOTONIC); if (!tcp_rsk(req)->snt_synack) /* Timestamp first SYNACK */ tcp_rsk(req)->snt_synack = tcp_skb_timestamp_us(skb); } @@ -3768,6 +3771,7 @@ struct sk_buff *tcp_make_synack(const struct sock *sk, struct dst_entry *dst, #ifdef CONFIG_TCP_AO struct tcp_ao_key *ao_key = NULL; u8 keyid = tcp_rsk(req)->ao_keyid; + u8 rnext = tcp_rsk(req)->ao_rcv_next; ao_key = tcp_sk(sk)->af_specific->ao_lookup(sk, req_to_sk(req), keyid, -1); @@ -3777,6 +3781,7 @@ struct sk_buff *tcp_make_synack(const struct sock *sk, struct dst_entry *dst, * ao_keyid (RFC5925 RNextKeyID), so let's keep it simple here. */ if (unlikely(!ao_key)) { + trace_tcp_ao_synack_no_key(sk, keyid, rnext); rcu_read_unlock(); kfree_skb(skb); net_warn_ratelimited("TCP-AO: the keyid %u from SYN packet is not present - not sending SYNACK\n", @@ -3843,7 +3848,7 @@ struct sk_buff *tcp_make_synack(const struct sock *sk, struct dst_entry *dst, bpf_skops_write_hdr_opt((struct sock *)sk, skb, req, syn_skb, synack_type, &opts); - skb_set_delivery_time(skb, now, true); + skb_set_delivery_time(skb, now, SKB_CLOCK_MONOTONIC); tcp_add_tx_delay(skb, tp); return skb; @@ -4027,7 +4032,7 @@ static int tcp_send_syn_data(struct sock *sk, struct sk_buff *syn) err = tcp_transmit_skb(sk, syn_data, 1, sk->sk_allocation); - skb_set_delivery_time(syn, syn_data->skb_mstamp_ns, true); + skb_set_delivery_time(syn, syn_data->skb_mstamp_ns, SKB_CLOCK_MONOTONIC); /* Now full SYN+DATA was cloned and sent (or not), * remove the SYN from the original skb (syn_data) @@ -4163,16 +4168,9 @@ EXPORT_SYMBOL(tcp_connect); u32 tcp_delack_max(const struct sock *sk) { - const struct dst_entry *dst = __sk_dst_get(sk); - u32 delack_max = inet_csk(sk)->icsk_delack_max; + u32 delack_from_rto_min = max(tcp_rto_min(sk), 2) - 1; - if (dst && dst_metric_locked(dst, RTAX_RTO_MIN)) { - u32 rto_min = dst_metric_rtt(dst, RTAX_RTO_MIN); - u32 delack_from_rto_min = max_t(int, 1, rto_min - 1); - - delack_max = min_t(u32, delack_max, delack_from_rto_min); - } - return delack_max; + return min(inet_csk(sk)->icsk_delack_max, delack_from_rto_min); } /* Send out a delayed ack, the caller does the policy checking diff --git a/net/ipv4/tcp_sigpool.c b/net/ipv4/tcp_sigpool.c index 8512cb09ebc0..d8a4f192873a 100644 --- a/net/ipv4/tcp_sigpool.c +++ b/net/ipv4/tcp_sigpool.c @@ -10,7 +10,14 @@ #include <net/tcp.h> static size_t __scratch_size; -static DEFINE_PER_CPU(void __rcu *, sigpool_scratch); +struct sigpool_scratch { + local_lock_t bh_lock; + void __rcu *pad; +}; + +static DEFINE_PER_CPU(struct sigpool_scratch, sigpool_scratch) = { + .bh_lock = INIT_LOCAL_LOCK(bh_lock), +}; struct sigpool_entry { struct crypto_ahash *hash; @@ -72,7 +79,7 @@ static int sigpool_reserve_scratch(size_t size) break; } - old_scratch = rcu_replace_pointer(per_cpu(sigpool_scratch, cpu), + old_scratch = rcu_replace_pointer(per_cpu(sigpool_scratch.pad, cpu), scratch, lockdep_is_held(&cpool_mutex)); if (!cpu_online(cpu) || !old_scratch) { kfree(old_scratch); @@ -93,7 +100,7 @@ static void sigpool_scratch_free(void) int cpu; for_each_possible_cpu(cpu) - kfree(rcu_replace_pointer(per_cpu(sigpool_scratch, cpu), + kfree(rcu_replace_pointer(per_cpu(sigpool_scratch.pad, cpu), NULL, lockdep_is_held(&cpool_mutex))); __scratch_size = 0; } @@ -277,7 +284,8 @@ int tcp_sigpool_start(unsigned int id, struct tcp_sigpool *c) __cond_acquires(RC /* Pairs with tcp_sigpool_reserve_scratch(), scratch area is * valid (allocated) until tcp_sigpool_end(). */ - c->scratch = rcu_dereference_bh(*this_cpu_ptr(&sigpool_scratch)); + local_lock_nested_bh(&sigpool_scratch.bh_lock); + c->scratch = rcu_dereference_bh(*this_cpu_ptr(&sigpool_scratch.pad)); return 0; } EXPORT_SYMBOL_GPL(tcp_sigpool_start); @@ -286,6 +294,7 @@ void tcp_sigpool_end(struct tcp_sigpool *c) __releases(RCU_BH) { struct crypto_ahash *hash = crypto_ahash_reqtfm(c->req); + local_unlock_nested_bh(&sigpool_scratch.bh_lock); rcu_read_unlock_bh(); ahash_request_free(c->req); crypto_free_ahash(hash); diff --git a/net/ipv4/tcp_timer.c b/net/ipv4/tcp_timer.c index 5bfd76a31af6..79064580c8c0 100644 --- a/net/ipv4/tcp_timer.c +++ b/net/ipv4/tcp_timer.c @@ -74,11 +74,7 @@ u32 tcp_clamp_probe0_to_user_timeout(const struct sock *sk, u32 when) static void tcp_write_err(struct sock *sk) { - WRITE_ONCE(sk->sk_err, READ_ONCE(sk->sk_err_soft) ? : ETIMEDOUT); - sk_error_report(sk); - - tcp_write_queue_purge(sk); - tcp_done(sk); + tcp_done_with_error(sk, READ_ONCE(sk->sk_err_soft) ? : ETIMEDOUT); __NET_INC_STATS(sock_net(sk), LINUX_MIB_TCPABORTONTIMEOUT); } @@ -129,7 +125,7 @@ static int tcp_out_of_resources(struct sock *sk, bool do_reset) do_reset = true; if (do_reset) tcp_send_active_reset(sk, GFP_ATOMIC, - SK_RST_REASON_NOT_SPECIFIED); + SK_RST_REASON_TCP_ABORT_ON_MEMORY); tcp_done(sk); __NET_INC_STATS(sock_net(sk), LINUX_MIB_TCPABORTONMEMORY); return 1; @@ -286,6 +282,7 @@ static int tcp_write_timeout(struct sock *sk) expired = retransmits_timed_out(sk, retry_until, READ_ONCE(icsk->icsk_user_timeout)); tcp_fastopen_active_detect_blackhole(sk, expired); + mptcp_active_detect_blackhole(sk, expired); if (BPF_SOCK_OPS_TEST_FLAG(tp, BPF_SOCK_OPS_RTO_CB_FLAG)) tcp_call_bpf_3arg(sk, BPF_SOCK_OPS_RTO_CB, @@ -483,15 +480,26 @@ static bool tcp_rtx_probe0_timed_out(const struct sock *sk, const struct sk_buff *skb, u32 rtx_delta) { + const struct inet_connection_sock *icsk = inet_csk(sk); + u32 user_timeout = READ_ONCE(icsk->icsk_user_timeout); const struct tcp_sock *tp = tcp_sk(sk); - const int timeout = TCP_RTO_MAX * 2; + int timeout = TCP_RTO_MAX * 2; s32 rcv_delta; + if (user_timeout) { + /* If user application specified a TCP_USER_TIMEOUT, + * it does not want win 0 packets to 'reset the timer' + * while retransmits are not making progress. + */ + if (rtx_delta > user_timeout) + return true; + timeout = min_t(u32, timeout, msecs_to_jiffies(user_timeout)); + } /* Note: timer interrupt might have been delayed by at least one jiffy, * and tp->rcv_tstamp might very well have been written recently. * rcv_delta can thus be negative. */ - rcv_delta = inet_csk(sk)->icsk_timeout - tp->rcv_tstamp; + rcv_delta = icsk->icsk_timeout - tp->rcv_tstamp; if (rcv_delta <= timeout) return false; @@ -536,8 +544,6 @@ void tcp_retransmit_timer(struct sock *sk) if (WARN_ON_ONCE(!skb)) return; - tp->tlp_high_seq = 0; - if (!tp->snd_wnd && !sock_flag(sk, SOCK_DEAD) && !((1 << sk->sk_state) & (TCPF_SYN_SENT | TCPF_SYN_RECV))) { /* Receiver dastardly shrinks window. Our retransmits @@ -774,7 +780,7 @@ static void tcp_keepalive_timer (struct timer_list *t) goto out; } } - tcp_send_active_reset(sk, GFP_ATOMIC, SK_RST_REASON_NOT_SPECIFIED); + tcp_send_active_reset(sk, GFP_ATOMIC, SK_RST_REASON_TCP_STATE); goto death; } @@ -802,7 +808,7 @@ static void tcp_keepalive_timer (struct timer_list *t) (user_timeout == 0 && icsk->icsk_probes_out >= keepalive_probes(tp))) { tcp_send_active_reset(sk, GFP_ATOMIC, - SK_RST_REASON_NOT_SPECIFIED); + SK_RST_REASON_TCP_KEEPALIVE_TIMEOUT); tcp_write_err(sk); goto out; } diff --git a/net/ipv4/udp.c b/net/ipv4/udp.c index 189c9113fe9a..8accbf4cb295 100644 --- a/net/ipv4/udp.c +++ b/net/ipv4/udp.c @@ -115,6 +115,7 @@ #include <net/addrconf.h> #include <net/udp_tunnel.h> #include <net/gro.h> +#include <net/inet_dscp.h> #if IS_ENABLED(CONFIG_IPV6) #include <net/ipv6_stubs.h> #endif @@ -326,6 +327,8 @@ found: goto fail_unlock; } + sock_set_flag(sk, SOCK_RCU_FREE); + sk_add_node_rcu(sk, &hslot->head); hslot->count++; sock_prot_inuse_add(sock_net(sk), sk->sk_prot, 1); @@ -342,7 +345,7 @@ found: hslot2->count++; spin_unlock(&hslot2->lock); } - sock_set_flag(sk, SOCK_RCU_FREE); + error = 0; fail_unlock: spin_unlock_bh(&hslot->lock); @@ -363,7 +366,7 @@ int udp_v4_get_port(struct sock *sk, unsigned short snum) return udp_lib_get_port(sk, snum, hash2_nulladdr); } -static int compute_score(struct sock *sk, struct net *net, +static int compute_score(struct sock *sk, const struct net *net, __be32 saddr, __be16 sport, __be32 daddr, unsigned short hnum, int dif, int sdif) @@ -418,7 +421,7 @@ u32 udp_ehashfn(const struct net *net, const __be32 laddr, const __u16 lport, } /* called with rcu_read_lock() */ -static struct sock *udp4_lib_lookup2(struct net *net, +static struct sock *udp4_lib_lookup2(const struct net *net, __be32 saddr, __be16 sport, __be32 daddr, unsigned int hnum, int dif, int sdif, @@ -478,7 +481,7 @@ rescore: /* UDP is nearly always wildcards out the wazoo, it makes no sense to try * harder than this. -DaveM */ -struct sock *__udp4_lib_lookup(struct net *net, __be32 saddr, +struct sock *__udp4_lib_lookup(const struct net *net, __be32 saddr, __be16 sport, __be32 daddr, __be16 dport, int dif, int sdif, struct udp_table *udptable, struct sk_buff *skb) { @@ -559,7 +562,7 @@ struct sock *udp4_lib_lookup_skb(const struct sk_buff *skb, * Does increment socket refcount. */ #if IS_ENABLED(CONFIG_NF_TPROXY_IPV4) || IS_ENABLED(CONFIG_NF_SOCKET_IPV4) -struct sock *udp4_lib_lookup(struct net *net, __be32 saddr, __be16 sport, +struct sock *udp4_lib_lookup(const struct net *net, __be32 saddr, __be16 sport, __be32 daddr, __be16 dport, int dif) { struct sock *sk; @@ -938,8 +941,7 @@ static int udp_send_skb(struct sk_buff *skb, struct flowi4 *fl4, kfree_skb(skb); return -EINVAL; } - if (skb->ip_summed != CHECKSUM_PARTIAL || is_udplite || - dst_xfrm(skb_dst(skb))) { + if (is_udplite || dst_xfrm(skb_dst(skb))) { kfree_skb(skb); return -EIO; } @@ -2074,7 +2076,7 @@ static int __udp_queue_rcv_skb(struct sock *sk, struct sk_buff *skb) } UDP_INC_STATS(sock_net(sk), UDP_MIB_INERRORS, is_udplite); trace_udp_fail_queue_rcv_skb(rc, sk, skb); - kfree_skb_reason(skb, drop_reason); + sk_skb_reason_drop(sk, skb, drop_reason); return -1; } @@ -2196,7 +2198,7 @@ csum_error: drop: __UDP_INC_STATS(sock_net(sk), UDP_MIB_INERRORS, is_udplite); atomic_inc(&sk->sk_drops); - kfree_skb_reason(skb, drop_reason); + sk_skb_reason_drop(sk, skb, drop_reason); return -1; } @@ -2230,7 +2232,7 @@ bool udp_sk_rx_dst_set(struct sock *sk, struct dst_entry *dst) struct dst_entry *old; if (dst_hold_safe(dst)) { - old = xchg((__force struct dst_entry **)&sk->sk_rx_dst, dst); + old = unrcu_pointer(xchg(&sk->sk_rx_dst, RCU_INITIALIZER(dst))); dst_release(old); return old != dst; } @@ -2383,7 +2385,7 @@ static int udp_unicast_rcv_skb(struct sock *sk, struct sk_buff *skb, int __udp4_lib_rcv(struct sk_buff *skb, struct udp_table *udptable, int proto) { - struct sock *sk; + struct sock *sk = NULL; struct udphdr *uh; unsigned short ulen; struct rtable *rt = skb_rtable(skb); @@ -2460,7 +2462,7 @@ no_sk: * Hmm. We got an UDP packet to a port to which we * don't wanna listen. Ignore it. */ - kfree_skb_reason(skb, drop_reason); + sk_skb_reason_drop(sk, skb, drop_reason); return 0; short_packet: @@ -2485,7 +2487,7 @@ csum_error: __UDP_INC_STATS(net, UDP_MIB_CSUMERRORS, proto == IPPROTO_UDPLITE); drop: __UDP_INC_STATS(net, UDP_MIB_INERRORS, proto == IPPROTO_UDPLITE); - kfree_skb_reason(skb, drop_reason); + sk_skb_reason_drop(sk, skb, drop_reason); return 0; } @@ -2617,7 +2619,7 @@ int udp_v4_early_demux(struct sk_buff *skb) if (!inet_sk(sk)->inet_daddr && in_dev) return ip_mc_validate_source(skb, iph->daddr, iph->saddr, - iph->tos & IPTOS_RT_MASK, + iph->tos & INET_DSCP_MASK, skb->dev, in_dev, &itag); } return 0; diff --git a/net/ipv4/udp_offload.c b/net/ipv4/udp_offload.c index 59448a2dbf2c..d842303587af 100644 --- a/net/ipv4/udp_offload.c +++ b/net/ipv4/udp_offload.c @@ -278,6 +278,17 @@ struct sk_buff *__udp_gso_segment(struct sk_buff *gso_skb, if (gso_skb->len <= sizeof(*uh) + mss) return ERR_PTR(-EINVAL); + if (unlikely(skb_checksum_start(gso_skb) != + skb_transport_header(gso_skb) && + !(skb_shinfo(gso_skb)->gso_type & SKB_GSO_FRAGLIST))) + return ERR_PTR(-EINVAL); + + /* We don't know if egress device can segment and checksum the packet + * when IPv6 extension headers are present. Fall back to software GSO. + */ + if (gso_skb->ip_summed != CHECKSUM_PARTIAL) + features &= ~(NETIF_F_GSO_UDP_L4 | NETIF_F_CSUM_MASK); + if (skb_gso_ok(gso_skb, features | NETIF_F_GSO_ROBUST)) { /* Packet is from an untrusted source, reset gso_segs. */ skb_shinfo(gso_skb)->gso_segs = DIV_ROUND_UP(gso_skb->len - sizeof(*uh), @@ -357,6 +368,14 @@ struct sk_buff *__udp_gso_segment(struct sk_buff *gso_skb, else uh->check = gso_make_checksum(seg, ~check) ? : CSUM_MANGLED_0; + /* On the TX path, CHECKSUM_NONE and CHECKSUM_UNNECESSARY have the same + * meaning. However, check for bad offloads in the GSO stack expects the + * latter, if the checksum was calculated in software. To vouch for the + * segment skbs we actually need to set it on the gso_skb. + */ + if (gso_skb->ip_summed == CHECKSUM_NONE) + gso_skb->ip_summed = CHECKSUM_UNNECESSARY; + /* update refcount for the packet */ if (copy_dtor) { int delta = sum_truesize - gso_skb->truesize; diff --git a/net/ipv4/udp_tunnel_core.c b/net/ipv4/udp_tunnel_core.c index e4e0fa869fa4..619a53eb672d 100644 --- a/net/ipv4/udp_tunnel_core.c +++ b/net/ipv4/udp_tunnel_core.c @@ -6,6 +6,7 @@ #include <net/dst_metadata.h> #include <net/udp.h> #include <net/udp_tunnel.h> +#include <net/inet_dscp.h> int udp_sock_create4(struct net *net, struct udp_port_cfg *cfg, struct socket **sockp) @@ -232,7 +233,7 @@ struct rtable *udp_tunnel_dst_lookup(struct sk_buff *skb, fl4.saddr = key->u.ipv4.src; fl4.fl4_dport = dport; fl4.fl4_sport = sport; - fl4.flowi4_tos = RT_TOS(tos); + fl4.flowi4_tos = tos & INET_DSCP_MASK; fl4.flowi4_flags = key->flow_flags; rt = ip_route_output_key(net, &fl4); diff --git a/net/ipv6/Kconfig b/net/ipv6/Kconfig index 08d4b7132d4c..1c9c686d9522 100644 --- a/net/ipv6/Kconfig +++ b/net/ipv6/Kconfig @@ -323,6 +323,7 @@ config IPV6_RPL_LWTUNNEL bool "IPv6: RPL Source Routing Header support" depends on IPV6 select LWTUNNEL + select DST_CACHE help Support for RFC6554 RPL Source Routing Header using the lightweight tunnels mechanism. diff --git a/net/ipv6/addrconf.c b/net/ipv6/addrconf.c index 5c424a0e7232..d680beb91b0a 100644 --- a/net/ipv6/addrconf.c +++ b/net/ipv6/addrconf.c @@ -92,8 +92,6 @@ #include <linux/export.h> #include <linux/ioam6.h> -#define INFINITY_LIFE_TIME 0xFFFFFFFF - #define IPV6_MAX_STRLEN \ sizeof("ffff:ffff:ffff:ffff:ffff:ffff:255.255.255.255") @@ -239,6 +237,7 @@ static struct ipv6_devconf ipv6_devconf __read_mostly = { .ioam6_id_wide = IOAM6_DEFAULT_IF_ID_WIDE, .ndisc_evict_nocarrier = 1, .ra_honor_pio_life = 0, + .ra_honor_pio_pflag = 0, }; static struct ipv6_devconf ipv6_devconf_dflt __read_mostly = { @@ -302,6 +301,7 @@ static struct ipv6_devconf ipv6_devconf_dflt __read_mostly = { .ioam6_id_wide = IOAM6_DEFAULT_IF_ID_WIDE, .ndisc_evict_nocarrier = 1, .ra_honor_pio_life = 0, + .ra_honor_pio_pflag = 0, }; /* Check if link is ready: is it up and is a valid qdisc available */ @@ -863,7 +863,7 @@ static void addrconf_forward_change(struct net *net, __s32 newf) } } -static int addrconf_fixup_forwarding(struct ctl_table *table, int *p, int newf) +static int addrconf_fixup_forwarding(const struct ctl_table *table, int *p, int newf) { struct net *net; int old; @@ -931,7 +931,7 @@ static void addrconf_linkdown_change(struct net *net, __s32 newf) } } -static int addrconf_fixup_linkdown(struct ctl_table *table, int *p, int newf) +static int addrconf_fixup_linkdown(const struct ctl_table *table, int *p, int newf) { struct net *net; int old; @@ -1873,7 +1873,8 @@ int ipv6_dev_get_saddr(struct net *net, const struct net_device *dst_dev, master, &dst, scores, hiscore_idx); - if (scores[hiscore_idx].ifa) + if (scores[hiscore_idx].ifa && + scores[hiscore_idx].scopedist >= 0) goto out; } @@ -2761,6 +2762,7 @@ void addrconf_prefix_rcv(struct net_device *dev, u8 *opt, int len, bool sllao) u32 addr_flags = 0; struct inet6_dev *in6_dev; struct net *net = dev_net(dev); + bool ignore_autoconf = false; pinfo = (struct prefix_info *) opt; @@ -2863,7 +2865,8 @@ void addrconf_prefix_rcv(struct net_device *dev, u8 *opt, int len, bool sllao) /* Try to figure out our local address for this prefix */ - if (pinfo->autoconf && in6_dev->cnf.autoconf) { + ignore_autoconf = READ_ONCE(in6_dev->cnf.ra_honor_pio_pflag) && pinfo->preferpd; + if (pinfo->autoconf && in6_dev->cnf.autoconf && !ignore_autoconf) { struct in6_addr addr; bool tokenized = false, dev_addr_generated = false; @@ -5616,8 +5619,7 @@ static void inet6_ifa_notify(int event, struct inet6_ifaddr *ifa) rtnl_notify(skb, net, 0, RTNLGRP_IPV6_IFADDR, NULL, GFP_ATOMIC); return; errout: - if (err < 0) - rtnl_set_sk_err(net, RTNLGRP_IPV6_IFADDR, err); + rtnl_set_sk_err(net, RTNLGRP_IPV6_IFADDR, err); } static void ipv6_store_devconf(const struct ipv6_devconf *cnf, @@ -6172,8 +6174,7 @@ void inet6_ifinfo_notify(int event, struct inet6_dev *idev) rtnl_notify(skb, net, 0, RTNLGRP_IPV6_IFINFO, NULL, GFP_ATOMIC); return; errout: - if (err < 0) - rtnl_set_sk_err(net, RTNLGRP_IPV6_IFINFO, err); + rtnl_set_sk_err(net, RTNLGRP_IPV6_IFINFO, err); } static inline size_t inet6_prefix_nlmsg_size(void) @@ -6240,8 +6241,7 @@ static void inet6_prefix_notify(int event, struct inet6_dev *idev, rtnl_notify(skb, net, 0, RTNLGRP_IPV6_PREFIX, NULL, GFP_ATOMIC); return; errout: - if (err < 0) - rtnl_set_sk_err(net, RTNLGRP_IPV6_PREFIX, err); + rtnl_set_sk_err(net, RTNLGRP_IPV6_PREFIX, err); } static void __ipv6_ifa_notify(int event, struct inet6_ifaddr *ifp) @@ -6308,7 +6308,7 @@ static void ipv6_ifa_notify(int event, struct inet6_ifaddr *ifp) #ifdef CONFIG_SYSCTL -static int addrconf_sysctl_forward(struct ctl_table *ctl, int write, +static int addrconf_sysctl_forward(const struct ctl_table *ctl, int write, void *buffer, size_t *lenp, loff_t *ppos) { int *valp = ctl->data; @@ -6333,7 +6333,7 @@ static int addrconf_sysctl_forward(struct ctl_table *ctl, int write, return ret; } -static int addrconf_sysctl_mtu(struct ctl_table *ctl, int write, +static int addrconf_sysctl_mtu(const struct ctl_table *ctl, int write, void *buffer, size_t *lenp, loff_t *ppos) { struct inet6_dev *idev = ctl->extra1; @@ -6378,7 +6378,7 @@ static void addrconf_disable_change(struct net *net, __s32 newf) } } -static int addrconf_disable_ipv6(struct ctl_table *table, int *p, int newf) +static int addrconf_disable_ipv6(const struct ctl_table *table, int *p, int newf) { struct net *net = (struct net *)table->extra2; int old; @@ -6404,7 +6404,7 @@ static int addrconf_disable_ipv6(struct ctl_table *table, int *p, int newf) return 0; } -static int addrconf_sysctl_disable(struct ctl_table *ctl, int write, +static int addrconf_sysctl_disable(const struct ctl_table *ctl, int write, void *buffer, size_t *lenp, loff_t *ppos) { int *valp = ctl->data; @@ -6429,7 +6429,7 @@ static int addrconf_sysctl_disable(struct ctl_table *ctl, int write, return ret; } -static int addrconf_sysctl_proxy_ndp(struct ctl_table *ctl, int write, +static int addrconf_sysctl_proxy_ndp(const struct ctl_table *ctl, int write, void *buffer, size_t *lenp, loff_t *ppos) { int *valp = ctl->data; @@ -6470,7 +6470,7 @@ static int addrconf_sysctl_proxy_ndp(struct ctl_table *ctl, int write, return ret; } -static int addrconf_sysctl_addr_gen_mode(struct ctl_table *ctl, int write, +static int addrconf_sysctl_addr_gen_mode(const struct ctl_table *ctl, int write, void *buffer, size_t *lenp, loff_t *ppos) { @@ -6533,7 +6533,7 @@ out: return ret; } -static int addrconf_sysctl_stable_secret(struct ctl_table *ctl, int write, +static int addrconf_sysctl_stable_secret(const struct ctl_table *ctl, int write, void *buffer, size_t *lenp, loff_t *ppos) { @@ -6601,7 +6601,7 @@ out: } static -int addrconf_sysctl_ignore_routes_with_linkdown(struct ctl_table *ctl, +int addrconf_sysctl_ignore_routes_with_linkdown(const struct ctl_table *ctl, int write, void *buffer, size_t *lenp, loff_t *ppos) @@ -6669,7 +6669,7 @@ void addrconf_disable_policy_idev(struct inet6_dev *idev, int val) } static -int addrconf_disable_policy(struct ctl_table *ctl, int *valp, int val) +int addrconf_disable_policy(const struct ctl_table *ctl, int *valp, int val) { struct net *net = (struct net *)ctl->extra2; struct inet6_dev *idev; @@ -6701,7 +6701,7 @@ int addrconf_disable_policy(struct ctl_table *ctl, int *valp, int val) return 0; } -static int addrconf_sysctl_disable_policy(struct ctl_table *ctl, int write, +static int addrconf_sysctl_disable_policy(const struct ctl_table *ctl, int write, void *buffer, size_t *lenp, loff_t *ppos) { int *valp = ctl->data; @@ -6925,6 +6925,15 @@ static const struct ctl_table addrconf_sysctl[] = { .extra1 = SYSCTL_ZERO, .extra2 = SYSCTL_ONE, }, + { + .procname = "ra_honor_pio_pflag", + .data = &ipv6_devconf.ra_honor_pio_pflag, + .maxlen = sizeof(u8), + .mode = 0644, + .proc_handler = proc_dou8vec_minmax, + .extra1 = SYSCTL_ZERO, + .extra2 = SYSCTL_ONE, + }, #ifdef CONFIG_IPV6_ROUTER_PREF { .procname = "accept_ra_rtr_pref", diff --git a/net/ipv6/af_inet6.c b/net/ipv6/af_inet6.c index 8041dc181bd4..ba69b86f1c7d 100644 --- a/net/ipv6/af_inet6.c +++ b/net/ipv6/af_inet6.c @@ -509,7 +509,7 @@ void inet6_cleanup_sock(struct sock *sk) /* Free tx options */ - opt = xchg((__force struct ipv6_txoptions **)&np->opt, NULL); + opt = unrcu_pointer(xchg(&np->opt, NULL)); if (opt) { atomic_sub(opt->tot_len, &sk->sk_omem_alloc); txopt_put(opt); @@ -708,6 +708,7 @@ const struct proto_ops inet6_stream_ops = { .splice_eof = inet_splice_eof, .sendmsg_locked = tcp_sendmsg_locked, .splice_read = tcp_splice_read, + .set_peek_off = sk_set_peek_off, .read_sock = tcp_read_sock, .read_skb = tcp_read_skb, .peek_len = tcp_peek_len, @@ -1060,6 +1061,7 @@ static const struct ipv6_stub ipv6_stub_impl = { .nd_tbl = &nd_tbl, .ipv6_fragment = ip6_fragment, .ipv6_dev_find = ipv6_dev_find, + .ip6_xmit = ip6_xmit, }; static const struct ipv6_bpf_stub ipv6_bpf_stub_impl = { diff --git a/net/ipv6/esp6.c b/net/ipv6/esp6.c index 34a9a5b9ed00..b2400c226a32 100644 --- a/net/ipv6/esp6.c +++ b/net/ipv6/esp6.c @@ -132,7 +132,8 @@ static void esp_ssg_unref(struct xfrm_state *x, void *tmp, struct sk_buff *skb) */ if (req->src != req->dst) for (sg = sg_next(req->src); sg; sg = sg_next(sg)) - skb_page_unref(sg_page(sg), skb->pp_recycle); + skb_page_unref(page_to_netmem(sg_page(sg)), + skb->pp_recycle); } #ifdef CONFIG_INET6_ESPINTCP @@ -256,8 +257,7 @@ static int esp_output_tail_tcp(struct xfrm_state *x, struct sk_buff *skb) #else static int esp_output_tail_tcp(struct xfrm_state *x, struct sk_buff *skb) { - kfree_skb(skb); - + WARN_ON(1); return -EOPNOTSUPP; } #endif diff --git a/net/ipv6/esp6_offload.c b/net/ipv6/esp6_offload.c index 527b7caddbc6..919ebfabbe4e 100644 --- a/net/ipv6/esp6_offload.c +++ b/net/ipv6/esp6_offload.c @@ -83,6 +83,13 @@ static struct sk_buff *esp6_gro_receive(struct list_head *head, x = xfrm_state_lookup(dev_net(skb->dev), skb->mark, (xfrm_address_t *)&ipv6_hdr(skb)->daddr, spi, IPPROTO_ESP, AF_INET6); + + if (unlikely(x && x->dir && x->dir != XFRM_SA_DIR_IN)) { + /* non-offload path will record the error and audit log */ + xfrm_state_put(x); + x = NULL; + } + if (!x) goto out_reset; diff --git a/net/ipv6/fib6_rules.c b/net/ipv6/fib6_rules.c index 9e254de7462f..04a9ed5e8310 100644 --- a/net/ipv6/fib6_rules.c +++ b/net/ipv6/fib6_rules.c @@ -27,6 +27,7 @@ struct fib6_rule { struct rt6key src; struct rt6key dst; dscp_t dscp; + u8 dscp_full:1; /* DSCP or TOS selector */ }; static bool fib6_rule_matchall(const struct fib_rule *rule) @@ -345,6 +346,20 @@ INDIRECT_CALLABLE_SCOPE int fib6_rule_match(struct fib_rule *rule, return 1; } +static int fib6_nl2rule_dscp(const struct nlattr *nla, struct fib6_rule *rule6, + struct netlink_ext_ack *extack) +{ + if (rule6->dscp) { + NL_SET_ERR_MSG(extack, "Cannot specify both TOS and DSCP"); + return -EINVAL; + } + + rule6->dscp = inet_dsfield_to_dscp(nla_get_u8(nla) << 2); + rule6->dscp_full = true; + + return 0; +} + static int fib6_rule_configure(struct fib_rule *rule, struct sk_buff *skb, struct fib_rule_hdr *frh, struct nlattr **tb, @@ -361,6 +376,9 @@ static int fib6_rule_configure(struct fib_rule *rule, struct sk_buff *skb, } rule6->dscp = inet_dsfield_to_dscp(frh->tos); + if (tb[FRA_DSCP] && fib6_nl2rule_dscp(tb[FRA_DSCP], rule6, extack) < 0) + goto errout; + if (rule->action == FR_ACT_TO_TBL && !rule->l3mdev) { if (rule->table == RT6_TABLE_UNSPEC) { NL_SET_ERR_MSG(extack, "Invalid table"); @@ -413,9 +431,19 @@ static int fib6_rule_compare(struct fib_rule *rule, struct fib_rule_hdr *frh, if (frh->dst_len && (rule6->dst.plen != frh->dst_len)) return 0; - if (frh->tos && inet_dscp_to_dsfield(rule6->dscp) != frh->tos) + if (frh->tos && + (rule6->dscp_full || + inet_dscp_to_dsfield(rule6->dscp) != frh->tos)) return 0; + if (tb[FRA_DSCP]) { + dscp_t dscp; + + dscp = inet_dsfield_to_dscp(nla_get_u8(tb[FRA_DSCP]) << 2); + if (!rule6->dscp_full || rule6->dscp != dscp) + return 0; + } + if (frh->src_len && nla_memcmp(tb[FRA_SRC], &rule6->src.addr, sizeof(struct in6_addr))) return 0; @@ -434,7 +462,15 @@ static int fib6_rule_fill(struct fib_rule *rule, struct sk_buff *skb, frh->dst_len = rule6->dst.plen; frh->src_len = rule6->src.plen; - frh->tos = inet_dscp_to_dsfield(rule6->dscp); + + if (rule6->dscp_full) { + frh->tos = 0; + if (nla_put_u8(skb, FRA_DSCP, + inet_dscp_to_dsfield(rule6->dscp) >> 2)) + goto nla_put_failure; + } else { + frh->tos = inet_dscp_to_dsfield(rule6->dscp); + } if ((rule6->dst.plen && nla_put_in6_addr(skb, FRA_DST, &rule6->dst.addr)) || @@ -450,7 +486,8 @@ nla_put_failure: static size_t fib6_rule_nlmsg_payload(struct fib_rule *rule) { return nla_total_size(16) /* dst */ - + nla_total_size(16); /* src */ + + nla_total_size(16) /* src */ + + nla_total_size(1); /* dscp */ } static void fib6_rule_flush_cache(struct fib_rules_ops *ops) diff --git a/net/ipv6/icmp.c b/net/ipv6/icmp.c index 7b31674644ef..071b0bc1179d 100644 --- a/net/ipv6/icmp.c +++ b/net/ipv6/icmp.c @@ -175,14 +175,16 @@ static bool icmpv6_mask_allow(struct net *net, int type) return false; } -static bool icmpv6_global_allow(struct net *net, int type) +static bool icmpv6_global_allow(struct net *net, int type, + bool *apply_ratelimit) { if (icmpv6_mask_allow(net, type)) return true; - if (icmp_global_allow()) + if (icmp_global_allow(net)) { + *apply_ratelimit = true; return true; - + } __ICMP_INC_STATS(net, ICMP_MIB_RATELIMITGLOBAL); return false; } @@ -191,13 +193,13 @@ static bool icmpv6_global_allow(struct net *net, int type) * Check the ICMP output rate limit */ static bool icmpv6_xrlim_allow(struct sock *sk, u8 type, - struct flowi6 *fl6) + struct flowi6 *fl6, bool apply_ratelimit) { struct net *net = sock_net(sk); struct dst_entry *dst; bool res = false; - if (icmpv6_mask_allow(net, type)) + if (!apply_ratelimit) return true; /* @@ -228,6 +230,8 @@ static bool icmpv6_xrlim_allow(struct sock *sk, u8 type, if (!res) __ICMP6_INC_STATS(net, ip6_dst_idev(dst), ICMP6_MIB_RATELIMITHOST); + else + icmp_global_consume(net); dst_release(dst); return res; } @@ -452,6 +456,7 @@ void icmp6_send(struct sk_buff *skb, u8 type, u8 code, __u32 info, struct net *net; struct ipv6_pinfo *np; const struct in6_addr *saddr = NULL; + bool apply_ratelimit = false; struct dst_entry *dst; struct icmp6hdr tmp_hdr; struct flowi6 fl6; @@ -533,11 +538,12 @@ void icmp6_send(struct sk_buff *skb, u8 type, u8 code, __u32 info, return; } - /* Needed by both icmp_global_allow and icmpv6_xmit_lock */ + /* Needed by both icmpv6_global_allow and icmpv6_xmit_lock */ local_bh_disable(); /* Check global sysctl_icmp_msgs_per_sec ratelimit */ - if (!(skb->dev->flags & IFF_LOOPBACK) && !icmpv6_global_allow(net, type)) + if (!(skb->dev->flags & IFF_LOOPBACK) && + !icmpv6_global_allow(net, type, &apply_ratelimit)) goto out_bh_enable; mip6_addr_swap(skb, parm); @@ -575,7 +581,7 @@ void icmp6_send(struct sk_buff *skb, u8 type, u8 code, __u32 info, np = inet6_sk(sk); - if (!icmpv6_xrlim_allow(sk, type, &fl6)) + if (!icmpv6_xrlim_allow(sk, type, &fl6, apply_ratelimit)) goto out; tmp_hdr.icmp6_type = type; @@ -717,6 +723,7 @@ static enum skb_drop_reason icmpv6_echo_reply(struct sk_buff *skb) struct ipv6_pinfo *np; const struct in6_addr *saddr = NULL; struct icmp6hdr *icmph = icmp6_hdr(skb); + bool apply_ratelimit = false; struct icmp6hdr tmp_hdr; struct flowi6 fl6; struct icmpv6_msg msg; @@ -781,8 +788,9 @@ static enum skb_drop_reason icmpv6_echo_reply(struct sk_buff *skb) goto out; /* Check the ratelimit */ - if ((!(skb->dev->flags & IFF_LOOPBACK) && !icmpv6_global_allow(net, ICMPV6_ECHO_REPLY)) || - !icmpv6_xrlim_allow(sk, ICMPV6_ECHO_REPLY, &fl6)) + if ((!(skb->dev->flags & IFF_LOOPBACK) && + !icmpv6_global_allow(net, ICMPV6_ECHO_REPLY, &apply_ratelimit)) || + !icmpv6_xrlim_allow(sk, ICMPV6_ECHO_REPLY, &fl6, apply_ratelimit)) goto out_dst_release; idev = __in6_dev_get(skb->dev); diff --git a/net/ipv6/ila/ila.h b/net/ipv6/ila/ila.h index ad5f6f6ba333..85b92917849b 100644 --- a/net/ipv6/ila/ila.h +++ b/net/ipv6/ila/ila.h @@ -108,6 +108,7 @@ int ila_lwt_init(void); void ila_lwt_fini(void); int ila_xlat_init_net(struct net *net); +void ila_xlat_pre_exit_net(struct net *net); void ila_xlat_exit_net(struct net *net); int ila_xlat_nl_cmd_add_mapping(struct sk_buff *skb, struct genl_info *info); diff --git a/net/ipv6/ila/ila_main.c b/net/ipv6/ila/ila_main.c index 69caed07315f..976c78efbae1 100644 --- a/net/ipv6/ila/ila_main.c +++ b/net/ipv6/ila/ila_main.c @@ -71,6 +71,11 @@ ila_xlat_init_fail: return err; } +static __net_exit void ila_pre_exit_net(struct net *net) +{ + ila_xlat_pre_exit_net(net); +} + static __net_exit void ila_exit_net(struct net *net) { ila_xlat_exit_net(net); @@ -78,6 +83,7 @@ static __net_exit void ila_exit_net(struct net *net) static struct pernet_operations ila_net_ops = { .init = ila_init_net, + .pre_exit = ila_pre_exit_net, .exit = ila_exit_net, .id = &ila_net_id, .size = sizeof(struct ila_net), diff --git a/net/ipv6/ila/ila_xlat.c b/net/ipv6/ila/ila_xlat.c index 67e8c9440977..534a4498e280 100644 --- a/net/ipv6/ila/ila_xlat.c +++ b/net/ipv6/ila/ila_xlat.c @@ -619,6 +619,15 @@ int ila_xlat_init_net(struct net *net) return 0; } +void ila_xlat_pre_exit_net(struct net *net) +{ + struct ila_net *ilan = net_generic(net, ila_net_id); + + if (ilan->xlat.hooks_registered) + nf_unregister_net_hooks(net, ila_nf_hook_ops, + ARRAY_SIZE(ila_nf_hook_ops)); +} + void ila_xlat_exit_net(struct net *net) { struct ila_net *ilan = net_generic(net, ila_net_id); @@ -626,10 +635,6 @@ void ila_xlat_exit_net(struct net *net) rhashtable_free_and_destroy(&ilan->xlat.rhash_table, ila_free_cb, NULL); free_bucket_spinlocks(ilan->xlat.locks); - - if (ilan->xlat.hooks_registered) - nf_unregister_net_hooks(net, ila_nf_hook_ops, - ARRAY_SIZE(ila_nf_hook_ops)); } static int ila_xlat_addr(struct sk_buff *skb, bool sir2ila) diff --git a/net/ipv6/inet6_hashtables.c b/net/ipv6/inet6_hashtables.c index 6db71bb1cd30..9ec05e354baa 100644 --- a/net/ipv6/inet6_hashtables.c +++ b/net/ipv6/inet6_hashtables.c @@ -46,7 +46,7 @@ EXPORT_SYMBOL_GPL(inet6_ehashfn); * * The sockhash lock must be held as a reader here. */ -struct sock *__inet6_lookup_established(struct net *net, +struct sock *__inet6_lookup_established(const struct net *net, struct inet_hashinfo *hashinfo, const struct in6_addr *saddr, const __be16 sport, @@ -89,7 +89,7 @@ found: } EXPORT_SYMBOL(__inet6_lookup_established); -static inline int compute_score(struct sock *sk, struct net *net, +static inline int compute_score(struct sock *sk, const struct net *net, const unsigned short hnum, const struct in6_addr *daddr, const int dif, const int sdif) @@ -126,7 +126,7 @@ static inline int compute_score(struct sock *sk, struct net *net, * Return: NULL if sk doesn't have SO_REUSEPORT set, otherwise a pointer to * the selected sock or an error. */ -struct sock *inet6_lookup_reuseport(struct net *net, struct sock *sk, +struct sock *inet6_lookup_reuseport(const struct net *net, struct sock *sk, struct sk_buff *skb, int doff, const struct in6_addr *saddr, __be16 sport, @@ -147,7 +147,7 @@ struct sock *inet6_lookup_reuseport(struct net *net, struct sock *sk, EXPORT_SYMBOL_GPL(inet6_lookup_reuseport); /* called with rcu_read_lock() */ -static struct sock *inet6_lhash2_lookup(struct net *net, +static struct sock *inet6_lhash2_lookup(const struct net *net, struct inet_listen_hashbucket *ilb2, struct sk_buff *skb, int doff, const struct in6_addr *saddr, @@ -174,7 +174,7 @@ static struct sock *inet6_lhash2_lookup(struct net *net, return result; } -struct sock *inet6_lookup_run_sk_lookup(struct net *net, +struct sock *inet6_lookup_run_sk_lookup(const struct net *net, int protocol, struct sk_buff *skb, int doff, const struct in6_addr *saddr, @@ -199,7 +199,7 @@ struct sock *inet6_lookup_run_sk_lookup(struct net *net, } EXPORT_SYMBOL_GPL(inet6_lookup_run_sk_lookup); -struct sock *inet6_lookup_listener(struct net *net, +struct sock *inet6_lookup_listener(const struct net *net, struct inet_hashinfo *hashinfo, struct sk_buff *skb, int doff, const struct in6_addr *saddr, @@ -243,7 +243,8 @@ done: } EXPORT_SYMBOL_GPL(inet6_lookup_listener); -struct sock *inet6_lookup(struct net *net, struct inet_hashinfo *hashinfo, +struct sock *inet6_lookup(const struct net *net, + struct inet_hashinfo *hashinfo, struct sk_buff *skb, int doff, const struct in6_addr *saddr, const __be16 sport, const struct in6_addr *daddr, const __be16 dport, diff --git a/net/ipv6/ioam6_iptunnel.c b/net/ipv6/ioam6_iptunnel.c index bf7120ecea1e..beb6b4cfc551 100644 --- a/net/ipv6/ioam6_iptunnel.c +++ b/net/ipv6/ioam6_iptunnel.c @@ -42,8 +42,10 @@ struct ioam6_lwt { struct ioam6_lwt_freq freq; atomic_t pkt_cnt; u8 mode; + bool has_tunsrc; + struct in6_addr tunsrc; struct in6_addr tundst; - struct ioam6_lwt_encap tuninfo; + struct ioam6_lwt_encap tuninfo; }; static const struct netlink_range_validation freq_range = { @@ -72,8 +74,10 @@ static const struct nla_policy ioam6_iptunnel_policy[IOAM6_IPTUNNEL_MAX + 1] = { [IOAM6_IPTUNNEL_MODE] = NLA_POLICY_RANGE(NLA_U8, IOAM6_IPTUNNEL_MODE_MIN, IOAM6_IPTUNNEL_MODE_MAX), + [IOAM6_IPTUNNEL_SRC] = NLA_POLICY_EXACT_LEN(sizeof(struct in6_addr)), [IOAM6_IPTUNNEL_DST] = NLA_POLICY_EXACT_LEN(sizeof(struct in6_addr)), - [IOAM6_IPTUNNEL_TRACE] = NLA_POLICY_EXACT_LEN(sizeof(struct ioam6_trace_hdr)), + [IOAM6_IPTUNNEL_TRACE] = NLA_POLICY_EXACT_LEN( + sizeof(struct ioam6_trace_hdr)), }; static bool ioam6_validate_trace_hdr(struct ioam6_trace_hdr *trace) @@ -85,7 +89,7 @@ static bool ioam6_validate_trace_hdr(struct ioam6_trace_hdr *trace) trace->type.bit12 | trace->type.bit13 | trace->type.bit14 | trace->type.bit15 | trace->type.bit16 | trace->type.bit17 | trace->type.bit18 | trace->type.bit19 | trace->type.bit20 | - trace->type.bit21) + trace->type.bit21 | trace->type.bit23) return false; trace->nodelen = 0; @@ -143,6 +147,11 @@ static int ioam6_build_state(struct net *net, struct nlattr *nla, else mode = nla_get_u8(tb[IOAM6_IPTUNNEL_MODE]); + if (tb[IOAM6_IPTUNNEL_SRC] && mode == IOAM6_IPTUNNEL_MODE_INLINE) { + NL_SET_ERR_MSG(extack, "no tunnel src expected with this mode"); + return -EINVAL; + } + if (!tb[IOAM6_IPTUNNEL_DST] && mode != IOAM6_IPTUNNEL_MODE_INLINE) { NL_SET_ERR_MSG(extack, "this mode needs a tunnel destination"); return -EINVAL; @@ -167,19 +176,40 @@ static int ioam6_build_state(struct net *net, struct nlattr *nla, ilwt = ioam6_lwt_state(lwt); err = dst_cache_init(&ilwt->cache, GFP_ATOMIC); - if (err) { - kfree(lwt); - return err; - } + if (err) + goto free_lwt; atomic_set(&ilwt->pkt_cnt, 0); ilwt->freq.k = freq_k; ilwt->freq.n = freq_n; ilwt->mode = mode; - if (tb[IOAM6_IPTUNNEL_DST]) + + if (!tb[IOAM6_IPTUNNEL_SRC]) { + ilwt->has_tunsrc = false; + } else { + ilwt->has_tunsrc = true; + ilwt->tunsrc = nla_get_in6_addr(tb[IOAM6_IPTUNNEL_SRC]); + + if (ipv6_addr_any(&ilwt->tunsrc)) { + NL_SET_ERR_MSG_ATTR(extack, tb[IOAM6_IPTUNNEL_SRC], + "invalid tunnel source address"); + err = -EINVAL; + goto free_cache; + } + } + + if (tb[IOAM6_IPTUNNEL_DST]) { ilwt->tundst = nla_get_in6_addr(tb[IOAM6_IPTUNNEL_DST]); + if (ipv6_addr_any(&ilwt->tundst)) { + NL_SET_ERR_MSG_ATTR(extack, tb[IOAM6_IPTUNNEL_DST], + "invalid tunnel dest address"); + err = -EINVAL; + goto free_cache; + } + } + tuninfo = ioam6_lwt_info(lwt); tuninfo->eh.hdrlen = ((sizeof(*tuninfo) + len_aligned) >> 3) - 1; tuninfo->pad[0] = IPV6_TLV_PADN; @@ -201,6 +231,11 @@ static int ioam6_build_state(struct net *net, struct nlattr *nla, *ts = lwt; return 0; +free_cache: + dst_cache_destroy(&ilwt->cache); +free_lwt: + kfree(lwt); + return err; } static int ioam6_do_fill(struct net *net, struct sk_buff *skb) @@ -256,6 +291,8 @@ static int ioam6_do_inline(struct net *net, struct sk_buff *skb, static int ioam6_do_encap(struct net *net, struct sk_buff *skb, struct ioam6_lwt_encap *tuninfo, + bool has_tunsrc, + struct in6_addr *tunsrc, struct in6_addr *tundst) { struct dst_entry *dst = skb_dst(skb); @@ -285,8 +322,12 @@ static int ioam6_do_encap(struct net *net, struct sk_buff *skb, hdr->nexthdr = NEXTHDR_HOP; hdr->payload_len = cpu_to_be16(skb->len - sizeof(*hdr)); hdr->daddr = *tundst; - ipv6_dev_get_saddr(net, dst->dev, &hdr->daddr, - IPV6_PREFER_SRC_PUBLIC, &hdr->saddr); + + if (has_tunsrc) + memcpy(&hdr->saddr, tunsrc, sizeof(*tunsrc)); + else + ipv6_dev_get_saddr(net, dst->dev, &hdr->daddr, + IPV6_PREFER_SRC_PUBLIC, &hdr->saddr); skb_postpush_rcsum(skb, hdr, len); @@ -328,7 +369,9 @@ do_inline: case IOAM6_IPTUNNEL_MODE_ENCAP: do_encap: /* Encapsulation (ip6ip6) */ - err = ioam6_do_encap(net, skb, &ilwt->tuninfo, &ilwt->tundst); + err = ioam6_do_encap(net, skb, &ilwt->tuninfo, + ilwt->has_tunsrc, &ilwt->tunsrc, + &ilwt->tundst); if (unlikely(err)) goto drop; @@ -414,6 +457,13 @@ static int ioam6_fill_encap_info(struct sk_buff *skb, goto ret; if (ilwt->mode != IOAM6_IPTUNNEL_MODE_INLINE) { + if (ilwt->has_tunsrc) { + err = nla_put_in6_addr(skb, IOAM6_IPTUNNEL_SRC, + &ilwt->tunsrc); + if (err) + goto ret; + } + err = nla_put_in6_addr(skb, IOAM6_IPTUNNEL_DST, &ilwt->tundst); if (err) goto ret; @@ -435,8 +485,12 @@ static int ioam6_encap_nlsize(struct lwtunnel_state *lwtstate) nla_total_size(sizeof(ilwt->mode)) + nla_total_size(sizeof(ilwt->tuninfo.traceh)); - if (ilwt->mode != IOAM6_IPTUNNEL_MODE_INLINE) + if (ilwt->mode != IOAM6_IPTUNNEL_MODE_INLINE) { + if (ilwt->has_tunsrc) + nlsize += nla_total_size(sizeof(ilwt->tunsrc)); + nlsize += nla_total_size(sizeof(ilwt->tundst)); + } return nlsize; } @@ -451,17 +505,21 @@ static int ioam6_encap_cmp(struct lwtunnel_state *a, struct lwtunnel_state *b) return (ilwt_a->freq.k != ilwt_b->freq.k || ilwt_a->freq.n != ilwt_b->freq.n || ilwt_a->mode != ilwt_b->mode || + ilwt_a->has_tunsrc != ilwt_b->has_tunsrc || (ilwt_a->mode != IOAM6_IPTUNNEL_MODE_INLINE && !ipv6_addr_equal(&ilwt_a->tundst, &ilwt_b->tundst)) || + (ilwt_a->mode != IOAM6_IPTUNNEL_MODE_INLINE && + ilwt_a->has_tunsrc && + !ipv6_addr_equal(&ilwt_a->tunsrc, &ilwt_b->tunsrc)) || trace_a->namespace_id != trace_b->namespace_id); } static const struct lwtunnel_encap_ops ioam6_iptun_ops = { .build_state = ioam6_build_state, .destroy_state = ioam6_destroy_state, - .output = ioam6_output, + .output = ioam6_output, .fill_encap = ioam6_fill_encap_info, - .get_encap_size = ioam6_encap_nlsize, + .get_encap_size = ioam6_encap_nlsize, .cmp_encap = ioam6_encap_cmp, .owner = THIS_MODULE, }; diff --git a/net/ipv6/ip6_fib.c b/net/ipv6/ip6_fib.c index 83e4f9855ae1..eb111d20615c 100644 --- a/net/ipv6/ip6_fib.c +++ b/net/ipv6/ip6_fib.c @@ -987,7 +987,7 @@ static void __fib6_drop_pcpu_from(struct fib6_nh *fib6_nh, if (pcpu_rt && rcu_access_pointer(pcpu_rt->from) == match) { struct fib6_info *from; - from = xchg((__force struct fib6_info **)&pcpu_rt->from, NULL); + from = unrcu_pointer(xchg(&pcpu_rt->from, NULL)); fib6_info_release(from); } } diff --git a/net/ipv6/ip6_gre.c b/net/ipv6/ip6_gre.c index 3942bd2ade78..235808cfec70 100644 --- a/net/ipv6/ip6_gre.c +++ b/net/ipv6/ip6_gre.c @@ -1471,7 +1471,7 @@ static void ip6gre_tnl_init_features(struct net_device *dev) { struct ip6_tnl *nt = netdev_priv(dev); - dev->features |= GRE6_FEATURES | NETIF_F_LLTX; + dev->features |= GRE6_FEATURES; dev->hw_features |= GRE6_FEATURES; /* TCP offload with GRE SEQ is not supported, nor can we support 2 @@ -1485,6 +1485,8 @@ static void ip6gre_tnl_init_features(struct net_device *dev) dev->features |= NETIF_F_GSO_SOFTWARE; dev->hw_features |= NETIF_F_GSO_SOFTWARE; + + dev->lltx = true; } static int ip6gre_tunnel_init_common(struct net_device *dev) @@ -1619,8 +1621,7 @@ static int __net_init ip6gre_init_net(struct net *net) /* FB netdevice is special: we have one, and only one per netns. * Allowing to move it to another netns is clearly unsafe. */ - ign->fb_tunnel_dev->features |= NETIF_F_NETNS_LOCAL; - + ign->fb_tunnel_dev->netns_local = true; ip6gre_fb_tunnel_init(ign->fb_tunnel_dev); ign->fb_tunnel_dev->rtnl_link_ops = &ip6gre_link_ops; diff --git a/net/ipv6/ip6_input.c b/net/ipv6/ip6_input.c index 133610a49da6..70c0e16c0ae6 100644 --- a/net/ipv6/ip6_input.c +++ b/net/ipv6/ip6_input.c @@ -111,9 +111,8 @@ static void ip6_list_rcv_finish(struct net *net, struct sock *sk, { struct sk_buff *skb, *next, *hint = NULL; struct dst_entry *curr_dst = NULL; - struct list_head sublist; + LIST_HEAD(sublist); - INIT_LIST_HEAD(&sublist); list_for_each_entry_safe(skb, next, head, list) { struct dst_entry *dst; @@ -327,9 +326,8 @@ void ipv6_list_rcv(struct list_head *head, struct packet_type *pt, struct net_device *curr_dev = NULL; struct net *curr_net = NULL; struct sk_buff *skb, *next; - struct list_head sublist; + LIST_HEAD(sublist); - INIT_LIST_HEAD(&sublist); list_for_each_entry_safe(skb, next, head, list) { struct net_device *dev = skb->dev; struct net *net = dev_net(dev); diff --git a/net/ipv6/ip6_output.c b/net/ipv6/ip6_output.c index 27d8725445e3..f26841f1490f 100644 --- a/net/ipv6/ip6_output.c +++ b/net/ipv6/ip6_output.c @@ -70,11 +70,15 @@ static int ip6_finish_output2(struct net *net, struct sock *sk, struct sk_buff * /* Be paranoid, rather than too clever. */ if (unlikely(hh_len > skb_headroom(skb)) && dev->header_ops) { + /* Make sure idev stays alive */ + rcu_read_lock(); skb = skb_expand_head(skb, hh_len); if (!skb) { IP6_INC_STATS(net, idev, IPSTATS_MIB_OUTDISCARDS); + rcu_read_unlock(); return -ENOMEM; } + rcu_read_unlock(); } hdr = ipv6_hdr(skb); @@ -283,11 +287,15 @@ int ip6_xmit(const struct sock *sk, struct sk_buff *skb, struct flowi6 *fl6, head_room += opt->opt_nflen + opt->opt_flen; if (unlikely(head_room > skb_headroom(skb))) { + /* Make sure idev stays alive */ + rcu_read_lock(); skb = skb_expand_head(skb, head_room); if (!skb) { IP6_INC_STATS(net, idev, IPSTATS_MIB_OUTDISCARDS); + rcu_read_unlock(); return -ENOBUFS; } + rcu_read_unlock(); } if (opt) { @@ -859,7 +867,7 @@ int ip6_fragment(struct net *net, struct sock *sk, struct sk_buff *skb, struct rt6_info *rt = dst_rt6_info(skb_dst(skb)); struct ipv6_pinfo *np = skb->sk && !dev_recursion_level() ? inet6_sk(skb->sk) : NULL; - bool mono_delivery_time = skb->mono_delivery_time; + u8 tstamp_type = skb->tstamp_type; struct ip6_frag_state state; unsigned int mtu, hlen, nexthdr_offset; ktime_t tstamp = skb->tstamp; @@ -955,7 +963,7 @@ int ip6_fragment(struct net *net, struct sock *sk, struct sk_buff *skb, if (iter.frag) ip6_fraglist_prepare(skb, &iter); - skb_set_delivery_time(skb, tstamp, mono_delivery_time); + skb_set_delivery_time(skb, tstamp, tstamp_type); err = output(net, sk, skb); if (!err) IP6_INC_STATS(net, ip6_dst_idev(&rt->dst), @@ -1016,7 +1024,7 @@ slow_path: /* * Put this fragment into the sending queue. */ - skb_set_delivery_time(frag, tstamp, mono_delivery_time); + skb_set_delivery_time(frag, tstamp, tstamp_type); err = output(net, sk, frag); if (err) goto fail; @@ -1124,6 +1132,7 @@ static int ip6_dst_lookup_tail(struct net *net, const struct sock *sk, from = rt ? rcu_dereference(rt->from) : NULL; err = ip6_route_get_saddr(net, from, &fl6->daddr, sk ? READ_ONCE(inet6_sk(sk)->srcprefs) : 0, + fl6->flowi6_l3mdev, &fl6->saddr); rcu_read_unlock(); @@ -1924,7 +1933,10 @@ struct sk_buff *__ip6_make_skb(struct sock *sk, skb->priority = READ_ONCE(sk->sk_priority); skb->mark = cork->base.mark; - skb->tstamp = cork->base.transmit_time; + if (sk_is_tcp(sk)) + skb_set_delivery_time(skb, cork->base.transmit_time, SKB_CLOCK_MONOTONIC); + else + skb_set_delivery_type_by_clockid(skb, cork->base.transmit_time, sk->sk_clockid); ip6_cork_steal_dst(skb, cork); IP6_INC_STATS(net, rt->rt6i_idev, IPSTATS_MIB_OUTREQUESTS); @@ -1952,6 +1964,7 @@ int ip6_send_skb(struct sk_buff *skb) struct rt6_info *rt = dst_rt6_info(skb_dst(skb)); int err; + rcu_read_lock(); err = ip6_local_out(net, skb->sk, skb); if (err) { if (err > 0) @@ -1961,6 +1974,7 @@ int ip6_send_skb(struct sk_buff *skb) IPSTATS_MIB_OUTDISCARDS); } + rcu_read_unlock(); return err; } diff --git a/net/ipv6/ip6_tunnel.c b/net/ipv6/ip6_tunnel.c index 9dee0c127955..b60e13c42bca 100644 --- a/net/ipv6/ip6_tunnel.c +++ b/net/ipv6/ip6_tunnel.c @@ -53,6 +53,7 @@ #include <net/net_namespace.h> #include <net/netns/generic.h> #include <net/dst_metadata.h> +#include <net/inet_dscp.h> MODULE_AUTHOR("Ville Nuorvala"); MODULE_DESCRIPTION("IPv6 tunneling device"); @@ -608,7 +609,8 @@ ip4ip6_err(struct sk_buff *skb, struct inet6_skb_parm *opt, /* Try to guess incoming interface */ rt = ip_route_output_ports(dev_net(skb->dev), &fl4, NULL, eiph->saddr, - 0, 0, 0, IPPROTO_IPIP, RT_TOS(eiph->tos), 0); + 0, 0, 0, IPPROTO_IPIP, + eiph->tos & INET_DSCP_MASK, 0); if (IS_ERR(rt)) goto out; @@ -619,7 +621,8 @@ ip4ip6_err(struct sk_buff *skb, struct inet6_skb_parm *opt, if (rt->rt_flags & RTCF_LOCAL) { rt = ip_route_output_ports(dev_net(skb->dev), &fl4, NULL, eiph->daddr, eiph->saddr, 0, 0, - IPPROTO_IPIP, RT_TOS(eiph->tos), 0); + IPPROTO_IPIP, + eiph->tos & INET_DSCP_MASK, 0); if (IS_ERR(rt) || rt->dst.dev->type != ARPHRD_TUNNEL6) { if (!IS_ERR(rt)) ip_rt_put(rt); @@ -1507,7 +1510,8 @@ static void ip6_tnl_link_config(struct ip6_tnl *t) tdev = __dev_get_by_index(t->net, p->link); if (tdev) { - dev->hard_header_len = tdev->hard_header_len + t_hlen; + dev->needed_headroom = tdev->hard_header_len + + tdev->needed_headroom + t_hlen; mtu = min_t(unsigned int, tdev->mtu, IP6_MAX_MTU); mtu = mtu - t_hlen; @@ -1731,7 +1735,9 @@ ip6_tnl_siocdevprivate(struct net_device *dev, struct ifreq *ifr, int ip6_tnl_change_mtu(struct net_device *dev, int new_mtu) { struct ip6_tnl *tnl = netdev_priv(dev); + int t_hlen; + t_hlen = tnl->hlen + sizeof(struct ipv6hdr); if (tnl->parms.proto == IPPROTO_IPV6) { if (new_mtu < IPV6_MIN_MTU) return -EINVAL; @@ -1740,10 +1746,10 @@ int ip6_tnl_change_mtu(struct net_device *dev, int new_mtu) return -EINVAL; } if (tnl->parms.proto == IPPROTO_IPV6 || tnl->parms.proto == 0) { - if (new_mtu > IP6_MAX_MTU - dev->hard_header_len) + if (new_mtu > IP6_MAX_MTU - dev->hard_header_len - t_hlen) return -EINVAL; } else { - if (new_mtu > IP_MAX_MTU - dev->hard_header_len) + if (new_mtu > IP_MAX_MTU - dev->hard_header_len - t_hlen) return -EINVAL; } WRITE_ONCE(dev->mtu, new_mtu); @@ -1846,7 +1852,7 @@ static void ip6_tnl_dev_setup(struct net_device *dev) dev->type = ARPHRD_TUNNEL6; dev->flags |= IFF_NOARP; dev->addr_len = sizeof(struct in6_addr); - dev->features |= NETIF_F_LLTX; + dev->lltx = true; dev->pcpu_stat_type = NETDEV_PCPU_STAT_TSTATS; netif_keep_dst(dev); @@ -1887,12 +1893,11 @@ ip6_tnl_dev_init_gen(struct net_device *dev) t_hlen = t->hlen + sizeof(struct ipv6hdr); dev->type = ARPHRD_TUNNEL6; - dev->hard_header_len = LL_MAX_HEADER + t_hlen; dev->mtu = ETH_DATA_LEN - t_hlen; if (!(t->parms.flags & IP6_TNL_F_IGN_ENCAP_LIMIT)) dev->mtu -= 8; dev->min_mtu = ETH_MIN_MTU; - dev->max_mtu = IP6_MAX_MTU - dev->hard_header_len; + dev->max_mtu = IP6_MAX_MTU - dev->hard_header_len - t_hlen; netdev_hold(dev, &t->dev_tracker, GFP_KERNEL); netdev_lockdep_set_classes(dev); @@ -2256,7 +2261,7 @@ static int __net_init ip6_tnl_init_net(struct net *net) /* FB netdevice is special: we have one, and only one per netns. * Allowing to move it to another netns is clearly unsafe. */ - ip6n->fb_tnl_dev->features |= NETIF_F_NETNS_LOCAL; + ip6n->fb_tnl_dev->netns_local = true; err = ip6_fb_tnl_dev_init(ip6n->fb_tnl_dev); if (err < 0) diff --git a/net/ipv6/ip6mr.c b/net/ipv6/ip6mr.c index dd342e6ecf3f..2ce4ae0d8dc3 100644 --- a/net/ipv6/ip6mr.c +++ b/net/ipv6/ip6mr.c @@ -640,7 +640,7 @@ static void reg_vif_setup(struct net_device *dev) dev->flags = IFF_NOARP; dev->netdev_ops = ®_vif_netdev_ops; dev->needs_free_netdev = true; - dev->features |= NETIF_F_NETNS_LOCAL; + dev->netns_local = true; } static struct net_device *ip6mr_reg_vif(struct net *net, struct mr_table *mrt) @@ -2431,8 +2431,7 @@ static void mr6_netlink_event(struct mr_table *mrt, struct mfc6_cache *mfc, errout: kfree_skb(skb); - if (err < 0) - rtnl_set_sk_err(net, RTNLGRP_IPV6_MROUTE, err); + rtnl_set_sk_err(net, RTNLGRP_IPV6_MROUTE, err); } static size_t mrt6msg_netlink_msgsize(size_t payloadlen) diff --git a/net/ipv6/ipv6_sockglue.c b/net/ipv6/ipv6_sockglue.c index d4c28ec1bc51..1e225e6489ea 100644 --- a/net/ipv6/ipv6_sockglue.c +++ b/net/ipv6/ipv6_sockglue.c @@ -111,8 +111,7 @@ struct ipv6_txoptions *ipv6_update_options(struct sock *sk, icsk->icsk_sync_mss(sk, icsk->icsk_pmtu_cookie); } } - opt = xchg((__force struct ipv6_txoptions **)&inet6_sk(sk)->opt, - opt); + opt = unrcu_pointer(xchg(&inet6_sk(sk)->opt, RCU_INITIALIZER(opt))); sk_dst_reset(sk); return opt; @@ -986,7 +985,7 @@ int ipv6_setsockopt(struct sock *sk, int level, int optname, sockptr_t optval, int err; if (level == SOL_IP && sk->sk_type != SOCK_RAW) - return udp_prot.setsockopt(sk, level, optname, optval, optlen); + return ip_setsockopt(sk, level, optname, optval, optlen); if (level != SOL_IPV6) return -ENOPROTOOPT; @@ -1476,7 +1475,7 @@ int ipv6_getsockopt(struct sock *sk, int level, int optname, int err; if (level == SOL_IP && sk->sk_type != SOCK_RAW) - return udp_prot.getsockopt(sk, level, optname, optval, optlen); + return ip_getsockopt(sk, level, optname, optval, optlen); if (level != SOL_IPV6) return -ENOPROTOOPT; diff --git a/net/ipv6/mcast.c b/net/ipv6/mcast.c index 7ba01d8cfbae..b244dbf61d5f 100644 --- a/net/ipv6/mcast.c +++ b/net/ipv6/mcast.c @@ -586,7 +586,8 @@ int ip6_mc_msfget(struct sock *sk, struct group_filter *gsf, const struct in6_addr *group; struct ipv6_mc_socklist *pmc; struct ip6_sf_socklist *psl; - int i, count, copycount; + unsigned int count; + int i, copycount; group = &((struct sockaddr_in6 *)&gsf->gf_group)->sin6_addr; @@ -610,7 +611,7 @@ int ip6_mc_msfget(struct sock *sk, struct group_filter *gsf, psl = sock_dereference(pmc->sflist, sk); count = psl ? psl->sl_count : 0; - copycount = count < gsf->gf_numsrc ? count : gsf->gf_numsrc; + copycount = min(count, gsf->gf_numsrc); gsf->gf_numsrc = count; for (i = 0; i < copycount; i++) { struct sockaddr_in6 *psin6; diff --git a/net/ipv6/ndisc.c b/net/ipv6/ndisc.c index d914b23256ce..aba94a348673 100644 --- a/net/ipv6/ndisc.c +++ b/net/ipv6/ndisc.c @@ -200,9 +200,9 @@ static inline int ndisc_is_useropt(const struct net_device *dev, return opt->nd_opt_type == ND_OPT_PREFIX_INFO || opt->nd_opt_type == ND_OPT_RDNSS || opt->nd_opt_type == ND_OPT_DNSSL || + opt->nd_opt_type == ND_OPT_6CO || opt->nd_opt_type == ND_OPT_CAPTIVE_PORTAL || - opt->nd_opt_type == ND_OPT_PREF64 || - ndisc_ops_is_useropt(dev, opt->nd_opt_type); + opt->nd_opt_type == ND_OPT_PREF64; } static struct nd_opt_hdr *ndisc_next_useropt(const struct net_device *dev, @@ -227,6 +227,7 @@ struct ndisc_options *ndisc_parse_options(const struct net_device *dev, return NULL; memset(ndopts, 0, sizeof(*ndopts)); while (opt_len) { + bool unknown = false; int l; if (opt_len < sizeof(struct nd_opt_hdr)) return NULL; @@ -262,22 +263,23 @@ struct ndisc_options *ndisc_parse_options(const struct net_device *dev, break; #endif default: - if (ndisc_is_useropt(dev, nd_opt)) { - ndopts->nd_useropts_end = nd_opt; - if (!ndopts->nd_useropts) - ndopts->nd_useropts = nd_opt; - } else { - /* - * Unknown options must be silently ignored, - * to accommodate future extension to the - * protocol. - */ - ND_PRINTK(2, notice, - "%s: ignored unsupported option; type=%d, len=%d\n", - __func__, - nd_opt->nd_opt_type, - nd_opt->nd_opt_len); - } + unknown = true; + } + if (ndisc_is_useropt(dev, nd_opt)) { + ndopts->nd_useropts_end = nd_opt; + if (!ndopts->nd_useropts) + ndopts->nd_useropts = nd_opt; + } else if (unknown) { + /* + * Unknown options must be silently ignored, + * to accommodate future extension to the + * protocol. + */ + ND_PRINTK(2, notice, + "%s: ignored unsupported option; type=%d, len=%d\n", + __func__, + nd_opt->nd_opt_type, + nd_opt->nd_opt_len); } next_opt: opt_len -= l; @@ -1936,13 +1938,13 @@ static struct notifier_block ndisc_netdev_notifier = { }; #ifdef CONFIG_SYSCTL -static void ndisc_warn_deprecated_sysctl(struct ctl_table *ctl, +static void ndisc_warn_deprecated_sysctl(const struct ctl_table *ctl, const char *func, const char *dev_name) { static char warncomm[TASK_COMM_LEN]; static int warned; if (strcmp(warncomm, current->comm) && warned < 5) { - strcpy(warncomm, current->comm); + strscpy(warncomm, current->comm); pr_warn("process `%s' is using deprecated sysctl (%s) net.ipv6.neigh.%s.%s - use net.ipv6.neigh.%s.%s_ms instead\n", warncomm, func, dev_name, ctl->procname, @@ -1951,7 +1953,7 @@ static void ndisc_warn_deprecated_sysctl(struct ctl_table *ctl, } } -int ndisc_ifinfo_sysctl_change(struct ctl_table *ctl, int write, void *buffer, +int ndisc_ifinfo_sysctl_change(const struct ctl_table *ctl, int write, void *buffer, size_t *lenp, loff_t *ppos) { struct net_device *dev = ctl->extra1; diff --git a/net/ipv6/netfilter.c b/net/ipv6/netfilter.c index 5d989d803009..581ce055bf52 100644 --- a/net/ipv6/netfilter.c +++ b/net/ipv6/netfilter.c @@ -127,7 +127,7 @@ int br_ip6_fragment(struct net *net, struct sock *sk, struct sk_buff *skb, struct sk_buff *)) { int frag_max_size = BR_INPUT_SKB_CB(skb)->frag_max_size; - bool mono_delivery_time = skb->mono_delivery_time; + u8 tstamp_type = skb->tstamp_type; ktime_t tstamp = skb->tstamp; struct ip6_frag_state state; u8 *prevhdr, nexthdr = 0; @@ -193,7 +193,7 @@ int br_ip6_fragment(struct net *net, struct sock *sk, struct sk_buff *skb, if (iter.frag) ip6_fraglist_prepare(skb, &iter); - skb_set_delivery_time(skb, tstamp, mono_delivery_time); + skb_set_delivery_time(skb, tstamp, tstamp_type); err = output(net, sk, data, skb); if (err || !iter.frag) break; @@ -226,7 +226,7 @@ slow_path: goto blackhole; } - skb_set_delivery_time(skb2, tstamp, mono_delivery_time); + skb_set_delivery_time(skb2, tstamp, tstamp_type); err = output(net, sk, data, skb2); if (err) goto blackhole; diff --git a/net/ipv6/netfilter/ip6_tables.c b/net/ipv6/netfilter/ip6_tables.c index 131f7bb2110d..7d5602950ae7 100644 --- a/net/ipv6/netfilter/ip6_tables.c +++ b/net/ipv6/netfilter/ip6_tables.c @@ -1773,7 +1773,7 @@ int ip6t_register_table(struct net *net, const struct xt_table *table, goto out_free; } - ops = kmemdup(template_ops, sizeof(*ops) * num_ops, GFP_KERNEL); + ops = kmemdup_array(template_ops, num_ops, sizeof(*ops), GFP_KERNEL); if (!ops) { ret = -ENOMEM; goto out_free; diff --git a/net/ipv6/netfilter/ip6table_nat.c b/net/ipv6/netfilter/ip6table_nat.c index 52cf104e3478..e119d4f090cc 100644 --- a/net/ipv6/netfilter/ip6table_nat.c +++ b/net/ipv6/netfilter/ip6table_nat.c @@ -147,23 +147,27 @@ static struct pernet_operations ip6table_nat_net_ops = { static int __init ip6table_nat_init(void) { - int ret = xt_register_template(&nf_nat_ipv6_table, - ip6table_nat_table_init); + int ret; + /* net->gen->ptr[ip6table_nat_net_id] must be allocated + * before calling ip6t_nat_register_lookups(). + */ + ret = register_pernet_subsys(&ip6table_nat_net_ops); if (ret < 0) return ret; - ret = register_pernet_subsys(&ip6table_nat_net_ops); + ret = xt_register_template(&nf_nat_ipv6_table, + ip6table_nat_table_init); if (ret) - xt_unregister_template(&nf_nat_ipv6_table); + unregister_pernet_subsys(&ip6table_nat_net_ops); return ret; } static void __exit ip6table_nat_exit(void) { - unregister_pernet_subsys(&ip6table_nat_net_ops); xt_unregister_template(&nf_nat_ipv6_table); + unregister_pernet_subsys(&ip6table_nat_net_ops); } module_init(ip6table_nat_init); diff --git a/net/ipv6/netfilter/nf_conntrack_reasm.c b/net/ipv6/netfilter/nf_conntrack_reasm.c index 5e1b50c6a44d..4120e67a8ce6 100644 --- a/net/ipv6/netfilter/nf_conntrack_reasm.c +++ b/net/ipv6/netfilter/nf_conntrack_reasm.c @@ -154,6 +154,10 @@ static struct frag_queue *fq_find(struct net *net, __be32 id, u32 user, }; struct inet_frag_queue *q; + if (!(ipv6_addr_type(&hdr->daddr) & (IPV6_ADDR_MULTICAST | + IPV6_ADDR_LINKLOCAL))) + key.iif = 0; + q = inet_frag_find(nf_frag->fqdir, &key); if (!q) return NULL; @@ -263,7 +267,7 @@ static int nf_ct_frag6_queue(struct frag_queue *fq, struct sk_buff *skb, fq->iif = dev->ifindex; fq->q.stamp = skb->tstamp; - fq->q.mono_delivery_time = skb->mono_delivery_time; + fq->q.tstamp_type = skb->tstamp_type; fq->q.meat += skb->len; fq->ecn |= ecn; if (payload_len > fq->q.max_size) diff --git a/net/ipv6/netfilter/nf_reject_ipv6.c b/net/ipv6/netfilter/nf_reject_ipv6.c index dedee264b8f6..7db0437140bf 100644 --- a/net/ipv6/netfilter/nf_reject_ipv6.c +++ b/net/ipv6/netfilter/nf_reject_ipv6.c @@ -223,33 +223,23 @@ void nf_reject_ip6_tcphdr_put(struct sk_buff *nskb, const struct tcphdr *oth, unsigned int otcplen) { struct tcphdr *tcph; - int needs_ack; skb_reset_transport_header(nskb); - tcph = skb_put(nskb, sizeof(struct tcphdr)); + tcph = skb_put_zero(nskb, sizeof(struct tcphdr)); /* Truncate to length (no data) */ tcph->doff = sizeof(struct tcphdr)/4; tcph->source = oth->dest; tcph->dest = oth->source; if (oth->ack) { - needs_ack = 0; tcph->seq = oth->ack_seq; - tcph->ack_seq = 0; } else { - needs_ack = 1; tcph->ack_seq = htonl(ntohl(oth->seq) + oth->syn + oth->fin + otcplen - (oth->doff<<2)); - tcph->seq = 0; + tcph->ack = 1; } - /* Reset flags */ - ((u_int8_t *)tcph)[13] = 0; tcph->rst = 1; - tcph->ack = needs_ack; - tcph->window = 0; - tcph->urg_ptr = 0; - tcph->check = 0; /* Adjust TCP checksum */ tcph->check = csum_ipv6_magic(&ipv6_hdr(nskb)->saddr, @@ -283,7 +273,6 @@ void nf_send_reset6(struct net *net, struct sock *sk, struct sk_buff *oldskb, const struct tcphdr *otcph; unsigned int otcplen, hh_len; const struct ipv6hdr *oip6h = ipv6_hdr(oldskb); - struct ipv6hdr *ip6h; struct dst_entry *dst = NULL; struct flowi6 fl6; @@ -339,8 +328,7 @@ void nf_send_reset6(struct net *net, struct sock *sk, struct sk_buff *oldskb, nskb->mark = fl6.flowi6_mark; skb_reserve(nskb, hh_len + dst->header_len); - ip6h = nf_reject_ip6hdr_put(nskb, oldskb, IPPROTO_TCP, - ip6_dst_hoplimit(dst)); + nf_reject_ip6hdr_put(nskb, oldskb, IPPROTO_TCP, ip6_dst_hoplimit(dst)); nf_reject_ip6_tcphdr_put(nskb, oldskb, otcph, otcplen); nf_ct_attach(nskb, oldskb); @@ -355,6 +343,7 @@ void nf_send_reset6(struct net *net, struct sock *sk, struct sk_buff *oldskb, */ if (nf_bridge_info_exists(oldskb)) { struct ethhdr *oeth = eth_hdr(oldskb); + struct ipv6hdr *ip6h = ipv6_hdr(nskb); struct net_device *br_indev; br_indev = nf_bridge_get_physindev(oldskb, net); diff --git a/net/ipv6/netfilter/nft_dup_ipv6.c b/net/ipv6/netfilter/nft_dup_ipv6.c index c82f3fdd4a65..492a811828a7 100644 --- a/net/ipv6/netfilter/nft_dup_ipv6.c +++ b/net/ipv6/netfilter/nft_dup_ipv6.c @@ -38,13 +38,13 @@ static int nft_dup_ipv6_init(const struct nft_ctx *ctx, if (tb[NFTA_DUP_SREG_ADDR] == NULL) return -EINVAL; - err = nft_parse_register_load(tb[NFTA_DUP_SREG_ADDR], &priv->sreg_addr, + err = nft_parse_register_load(ctx, tb[NFTA_DUP_SREG_ADDR], &priv->sreg_addr, sizeof(struct in6_addr)); if (err < 0) return err; if (tb[NFTA_DUP_SREG_DEV]) - err = nft_parse_register_load(tb[NFTA_DUP_SREG_DEV], + err = nft_parse_register_load(ctx, tb[NFTA_DUP_SREG_DEV], &priv->sreg_dev, sizeof(int)); return err; diff --git a/net/ipv6/proc.c b/net/ipv6/proc.c index 6d1d9221649d..752327b10dde 100644 --- a/net/ipv6/proc.c +++ b/net/ipv6/proc.c @@ -27,7 +27,7 @@ #include <net/ipv6.h> #define MAX4(a, b, c, d) \ - max_t(u32, max_t(u32, a, b), max_t(u32, c, d)) + MAX_T(u32, MAX_T(u32, a, b), MAX_T(u32, c, d)) #define SNMP_MIB_MAX MAX4(UDP_MIB_MAX, TCP_MIB_MAX, \ IPSTATS_MIB_MAX, ICMP_MIB_MAX) diff --git a/net/ipv6/raw.c b/net/ipv6/raw.c index 2eedf255600b..608fa9d05b55 100644 --- a/net/ipv6/raw.c +++ b/net/ipv6/raw.c @@ -362,14 +362,14 @@ static inline int rawv6_rcv_skb(struct sock *sk, struct sk_buff *skb) if ((raw6_sk(sk)->checksum || rcu_access_pointer(sk->sk_filter)) && skb_checksum_complete(skb)) { atomic_inc(&sk->sk_drops); - kfree_skb_reason(skb, SKB_DROP_REASON_SKB_CSUM); + sk_skb_reason_drop(sk, skb, SKB_DROP_REASON_SKB_CSUM); return NET_RX_DROP; } /* Charge it to the socket. */ skb_dst_drop(skb); if (sock_queue_rcv_skb_reason(sk, skb, &reason) < 0) { - kfree_skb_reason(skb, reason); + sk_skb_reason_drop(sk, skb, reason); return NET_RX_DROP; } @@ -390,7 +390,7 @@ int rawv6_rcv(struct sock *sk, struct sk_buff *skb) if (!xfrm6_policy_check(sk, XFRM_POLICY_IN, skb)) { atomic_inc(&sk->sk_drops); - kfree_skb_reason(skb, SKB_DROP_REASON_XFRM_POLICY); + sk_skb_reason_drop(sk, skb, SKB_DROP_REASON_XFRM_POLICY); return NET_RX_DROP; } nf_reset_ct(skb); @@ -415,7 +415,7 @@ int rawv6_rcv(struct sock *sk, struct sk_buff *skb) if (inet_test_bit(HDRINCL, sk)) { if (skb_checksum_complete(skb)) { atomic_inc(&sk->sk_drops); - kfree_skb_reason(skb, SKB_DROP_REASON_SKB_CSUM); + sk_skb_reason_drop(sk, skb, SKB_DROP_REASON_SKB_CSUM); return NET_RX_DROP; } } @@ -621,7 +621,7 @@ static int rawv6_send_hdrinc(struct sock *sk, struct msghdr *msg, int length, skb->protocol = htons(ETH_P_IPV6); skb->priority = READ_ONCE(sk->sk_priority); skb->mark = sockc->mark; - skb->tstamp = sockc->transmit_time; + skb_set_delivery_type_by_clockid(skb, sockc->transmit_time, sk->sk_clockid); skb_put(skb, length); skb_reset_network_header(skb); diff --git a/net/ipv6/reassembly.c b/net/ipv6/reassembly.c index 327caca64257..a48be617a8ab 100644 --- a/net/ipv6/reassembly.c +++ b/net/ipv6/reassembly.c @@ -198,7 +198,7 @@ static int ip6_frag_queue(struct frag_queue *fq, struct sk_buff *skb, fq->iif = dev->ifindex; fq->q.stamp = skb->tstamp; - fq->q.mono_delivery_time = skb->mono_delivery_time; + fq->q.tstamp_type = skb->tstamp_type; fq->q.meat += skb->len; fq->ecn |= ecn; add_frag_mem_limit(fq->q.fqdir, skb->truesize); diff --git a/net/ipv6/route.c b/net/ipv6/route.c index 8d72ca0b086d..b4251915585f 100644 --- a/net/ipv6/route.c +++ b/net/ipv6/route.c @@ -131,7 +131,6 @@ static struct fib6_info *rt6_get_route_info(struct net *net, struct uncached_list { spinlock_t lock; struct list_head head; - struct list_head quarantine; }; static DEFINE_PER_CPU_ALIGNED(struct uncached_list, rt6_uncached_list); @@ -175,7 +174,7 @@ static void rt6_uncached_list_flush_dev(struct net_device *dev) struct net_device *rt_dev = rt->dst.dev; bool handled = false; - if (rt_idev->dev == dev) { + if (rt_idev && rt_idev->dev == dev) { rt->rt6i_idev = in6_dev_get(blackhole_netdev); in6_dev_put(rt_idev); handled = true; @@ -189,8 +188,7 @@ static void rt6_uncached_list_flush_dev(struct net_device *dev) handled = true; } if (handled) - list_move(&rt->dst.rt_uncached, - &ul->quarantine); + list_del_init(&rt->dst.rt_uncached); } spin_unlock_bh(&ul->lock); } @@ -368,7 +366,7 @@ static void ip6_dst_destroy(struct dst_entry *dst) in6_dev_put(idev); } - from = xchg((__force struct fib6_info **)&rt->from, NULL); + from = unrcu_pointer(xchg(&rt->from, NULL)); fib6_info_release(from); } @@ -1440,7 +1438,7 @@ static struct rt6_info *rt6_make_pcpu_route(struct net *net, if (res->f6i->fib6_destroying) { struct fib6_info *from; - from = xchg((__force struct fib6_info **)&pcpu_rt->from, NULL); + from = unrcu_pointer(xchg(&pcpu_rt->from, NULL)); fib6_info_release(from); } @@ -1469,7 +1467,7 @@ static void rt6_remove_exception(struct rt6_exception_bucket *bucket, /* purge completely the exception to allow releasing the held resources: * some [sk] cache may keep the dst around for unlimited time */ - from = xchg((__force struct fib6_info **)&rt6_ex->rt6i->from, NULL); + from = unrcu_pointer(xchg(&rt6_ex->rt6i->from, NULL)); fib6_info_release(from); dst_dev_put(&rt6_ex->rt6i->dst); @@ -2376,7 +2374,7 @@ static u32 rt6_multipath_custom_hash_outer(const struct net *net, hash_keys.ports.dst = keys.ports.dst; *p_has_inner = !!(keys.control.flags & FLOW_DIS_ENCAPSULATION); - return flow_hash_from_keys(&hash_keys); + return fib_multipath_hash_from_keys(net, &hash_keys); } static u32 rt6_multipath_custom_hash_inner(const struct net *net, @@ -2425,7 +2423,7 @@ static u32 rt6_multipath_custom_hash_inner(const struct net *net, if (hash_fields & FIB_MULTIPATH_HASH_FIELD_INNER_DST_PORT) hash_keys.ports.dst = keys.ports.dst; - return flow_hash_from_keys(&hash_keys); + return fib_multipath_hash_from_keys(net, &hash_keys); } static u32 rt6_multipath_custom_hash_skb(const struct net *net, @@ -2464,7 +2462,7 @@ static u32 rt6_multipath_custom_hash_fl6(const struct net *net, if (hash_fields & FIB_MULTIPATH_HASH_FIELD_DST_PORT) hash_keys.ports.dst = fl6->fl6_dport; - return flow_hash_from_keys(&hash_keys); + return fib_multipath_hash_from_keys(net, &hash_keys); } /* if skb is set it will be used and fl6 can be NULL */ @@ -2486,7 +2484,7 @@ u32 rt6_multipath_hash(const struct net *net, const struct flowi6 *fl6, hash_keys.tags.flow_label = (__force u32)flowi6_get_flowlabel(fl6); hash_keys.basic.ip_proto = fl6->flowi6_proto; } - mhash = flow_hash_from_keys(&hash_keys); + mhash = fib_multipath_hash_from_keys(net, &hash_keys); break; case 1: if (skb) { @@ -2518,7 +2516,7 @@ u32 rt6_multipath_hash(const struct net *net, const struct flowi6 *fl6, hash_keys.ports.dst = fl6->fl6_dport; hash_keys.basic.ip_proto = fl6->flowi6_proto; } - mhash = flow_hash_from_keys(&hash_keys); + mhash = fib_multipath_hash_from_keys(net, &hash_keys); break; case 2: memset(&hash_keys, 0, sizeof(hash_keys)); @@ -2555,7 +2553,7 @@ u32 rt6_multipath_hash(const struct net *net, const struct flowi6 *fl6, hash_keys.tags.flow_label = (__force u32)flowi6_get_flowlabel(fl6); hash_keys.basic.ip_proto = fl6->flowi6_proto; } - mhash = flow_hash_from_keys(&hash_keys); + mhash = fib_multipath_hash_from_keys(net, &hash_keys); break; case 3: if (skb) @@ -3764,7 +3762,7 @@ static struct fib6_info *ip6_route_info_create(struct fib6_config *cfg, if (!rt) goto out; - rt->fib6_metrics = ip_fib_metrics_init(net, cfg->fc_mx, cfg->fc_mx_len, + rt->fib6_metrics = ip_fib_metrics_init(cfg->fc_mx, cfg->fc_mx_len, extack); if (IS_ERR(rt->fib6_metrics)) { err = PTR_ERR(rt->fib6_metrics); @@ -5689,7 +5687,7 @@ static int rt6_fill_node(struct net *net, struct sk_buff *skb, goto nla_put_failure; } else if (dest) { struct in6_addr saddr_buf; - if (ip6_route_get_saddr(net, rt, dest, 0, &saddr_buf) == 0 && + if (ip6_route_get_saddr(net, rt, dest, 0, 0, &saddr_buf) == 0 && nla_put_in6_addr(skb, RTA_PREFSRC, &saddr_buf)) goto nla_put_failure; } @@ -6195,8 +6193,7 @@ void inet6_rt_notify(int event, struct fib6_info *rt, struct nl_info *info, info->nlh, gfp_any()); return; errout: - if (err < 0) - rtnl_set_sk_err(net, RTNLGRP_IPV6_ROUTE, err); + rtnl_set_sk_err(net, RTNLGRP_IPV6_ROUTE, err); } void fib6_rt_update(struct net *net, struct fib6_info *rt, @@ -6222,8 +6219,7 @@ void fib6_rt_update(struct net *net, struct fib6_info *rt, info->nlh, gfp_any()); return; errout: - if (err < 0) - rtnl_set_sk_err(net, RTNLGRP_IPV6_ROUTE, err); + rtnl_set_sk_err(net, RTNLGRP_IPV6_ROUTE, err); } void fib6_info_hw_flags_set(struct net *net, struct fib6_info *f6i, @@ -6336,7 +6332,7 @@ static int rt6_stats_seq_show(struct seq_file *seq, void *v) #ifdef CONFIG_SYSCTL -static int ipv6_sysctl_rtcache_flush(struct ctl_table *ctl, int write, +static int ipv6_sysctl_rtcache_flush(const struct ctl_table *ctl, int write, void *buffer, size_t *lenp, loff_t *ppos) { struct net *net; @@ -6758,7 +6754,6 @@ int __init ip6_route_init(void) struct uncached_list *ul = per_cpu_ptr(&rt6_uncached_list, cpu); INIT_LIST_HEAD(&ul->head); - INIT_LIST_HEAD(&ul->quarantine); spin_lock_init(&ul->lock); } diff --git a/net/ipv6/rpl_iptunnel.c b/net/ipv6/rpl_iptunnel.c index 2c83b7586422..db3c19a42e1c 100644 --- a/net/ipv6/rpl_iptunnel.c +++ b/net/ipv6/rpl_iptunnel.c @@ -263,10 +263,8 @@ static int rpl_input(struct sk_buff *skb) rlwt = rpl_lwt_lwtunnel(orig_dst->lwtstate); err = rpl_do_srh(skb, rlwt); - if (unlikely(err)) { - kfree_skb(skb); - return err; - } + if (unlikely(err)) + goto drop; local_bh_disable(); dst = dst_cache_get(&rlwt->cache); @@ -286,9 +284,13 @@ static int rpl_input(struct sk_buff *skb) err = skb_cow_head(skb, LL_RESERVED_SPACE(dst->dev)); if (unlikely(err)) - return err; + goto drop; return dst_input(skb); + +drop: + kfree_skb(skb); + return err; } static int nla_put_rpl_srh(struct sk_buff *skb, int attrtype, diff --git a/net/ipv6/seg6.c b/net/ipv6/seg6.c index a31521e270f7..180da19c148c 100644 --- a/net/ipv6/seg6.c +++ b/net/ipv6/seg6.c @@ -21,9 +21,7 @@ #include <net/genetlink.h> #include <linux/seg6.h> #include <linux/seg6_genl.h> -#ifdef CONFIG_IPV6_SEG6_HMAC #include <net/seg6_hmac.h> -#endif bool seg6_validate_srh(struct ipv6_sr_hdr *srh, int len, bool reduced) { @@ -437,13 +435,11 @@ static int __net_init seg6_net_init(struct net *net) net->ipv6.seg6_data = sdata; -#ifdef CONFIG_IPV6_SEG6_HMAC if (seg6_hmac_net_init(net)) { kfree(rcu_dereference_raw(sdata->tun_src)); kfree(sdata); return -ENOMEM; } -#endif return 0; } @@ -452,9 +448,7 @@ static void __net_exit seg6_net_exit(struct net *net) { struct seg6_pernet_data *sdata = seg6_pernet(net); -#ifdef CONFIG_IPV6_SEG6_HMAC seg6_hmac_net_exit(net); -#endif kfree(rcu_dereference_raw(sdata->tun_src)); kfree(sdata); @@ -520,41 +514,28 @@ int __init seg6_init(void) if (err) goto out_unregister_pernet; -#ifdef CONFIG_IPV6_SEG6_LWTUNNEL err = seg6_iptunnel_init(); if (err) goto out_unregister_genl; err = seg6_local_init(); - if (err) { - seg6_iptunnel_exit(); - goto out_unregister_genl; - } -#endif + if (err) + goto out_unregister_iptun; -#ifdef CONFIG_IPV6_SEG6_HMAC err = seg6_hmac_init(); if (err) - goto out_unregister_iptun; -#endif + goto out_unregister_seg6; pr_info("Segment Routing with IPv6\n"); out: return err; -#ifdef CONFIG_IPV6_SEG6_HMAC -out_unregister_iptun: -#ifdef CONFIG_IPV6_SEG6_LWTUNNEL +out_unregister_seg6: seg6_local_exit(); +out_unregister_iptun: seg6_iptunnel_exit(); -#endif -#endif -#ifdef CONFIG_IPV6_SEG6_LWTUNNEL out_unregister_genl: -#endif -#if IS_ENABLED(CONFIG_IPV6_SEG6_LWTUNNEL) || IS_ENABLED(CONFIG_IPV6_SEG6_HMAC) genl_unregister_family(&seg6_genl_family); -#endif out_unregister_pernet: unregister_pernet_subsys(&ip6_segments_ops); goto out; @@ -562,13 +543,9 @@ out_unregister_pernet: void seg6_exit(void) { -#ifdef CONFIG_IPV6_SEG6_HMAC seg6_hmac_exit(); -#endif -#ifdef CONFIG_IPV6_SEG6_LWTUNNEL seg6_local_exit(); seg6_iptunnel_exit(); -#endif genl_unregister_family(&seg6_genl_family); unregister_pernet_subsys(&ip6_segments_ops); } diff --git a/net/ipv6/seg6_local.c b/net/ipv6/seg6_local.c index c434940131b1..c74705ead984 100644 --- a/net/ipv6/seg6_local.c +++ b/net/ipv6/seg6_local.c @@ -1380,7 +1380,9 @@ drop: return err; } -DEFINE_PER_CPU(struct seg6_bpf_srh_state, seg6_bpf_srh_states); +DEFINE_PER_CPU(struct seg6_bpf_srh_state, seg6_bpf_srh_states) = { + .bh_lock = INIT_LOCAL_LOCK(bh_lock), +}; bool seg6_bpf_has_valid_srh(struct sk_buff *skb) { @@ -1388,6 +1390,7 @@ bool seg6_bpf_has_valid_srh(struct sk_buff *skb) this_cpu_ptr(&seg6_bpf_srh_states); struct ipv6_sr_hdr *srh = srh_state->srh; + lockdep_assert_held(&srh_state->bh_lock); if (unlikely(srh == NULL)) return false; @@ -1408,8 +1411,7 @@ bool seg6_bpf_has_valid_srh(struct sk_buff *skb) static int input_action_end_bpf(struct sk_buff *skb, struct seg6_local_lwt *slwt) { - struct seg6_bpf_srh_state *srh_state = - this_cpu_ptr(&seg6_bpf_srh_states); + struct seg6_bpf_srh_state *srh_state; struct ipv6_sr_hdr *srh; int ret; @@ -1420,10 +1422,14 @@ static int input_action_end_bpf(struct sk_buff *skb, } advance_nextseg(srh, &ipv6_hdr(skb)->daddr); - /* preempt_disable is needed to protect the per-CPU buffer srh_state, - * which is also accessed by the bpf_lwt_seg6_* helpers + /* The access to the per-CPU buffer srh_state is protected by running + * always in softirq context (with disabled BH). On PREEMPT_RT the + * required locking is provided by the following local_lock_nested_bh() + * statement. It is also accessed by the bpf_lwt_seg6_* helpers via + * bpf_prog_run_save_cb(). */ - preempt_disable(); + local_lock_nested_bh(&seg6_bpf_srh_states.bh_lock); + srh_state = this_cpu_ptr(&seg6_bpf_srh_states); srh_state->srh = srh; srh_state->hdrlen = srh->hdrlen << 3; srh_state->valid = true; @@ -1446,15 +1452,15 @@ static int input_action_end_bpf(struct sk_buff *skb, if (srh_state->srh && !seg6_bpf_has_valid_srh(skb)) goto drop; + local_unlock_nested_bh(&seg6_bpf_srh_states.bh_lock); - preempt_enable(); if (ret != BPF_REDIRECT) seg6_lookup_nexthop(skb, NULL, 0); return dst_input(skb); drop: - preempt_enable(); + local_unlock_nested_bh(&seg6_bpf_srh_states.bh_lock); kfree_skb(skb); return -EINVAL; } diff --git a/net/ipv6/sit.c b/net/ipv6/sit.c index 83b195f09561..39bd8951bfca 100644 --- a/net/ipv6/sit.c +++ b/net/ipv6/sit.c @@ -51,6 +51,7 @@ #include <net/dsfield.h> #include <net/net_namespace.h> #include <net/netns/generic.h> +#include <net/inet_dscp.h> /* This version of net/ipv6/sit.c is cloned of net/ipv4/ip_gre.c @@ -935,8 +936,8 @@ static netdev_tx_t ipip6_tunnel_xmit(struct sk_buff *skb, } flowi4_init_output(&fl4, tunnel->parms.link, tunnel->fwmark, - RT_TOS(tos), RT_SCOPE_UNIVERSE, IPPROTO_IPV6, - 0, dst, tiph->saddr, 0, 0, + tos & INET_DSCP_MASK, RT_SCOPE_UNIVERSE, + IPPROTO_IPV6, 0, dst, tiph->saddr, 0, 0, sock_net_uid(tunnel->net, NULL)); rt = dst_cache_get_ip4(&tunnel->dst_cache, &fl4.saddr); @@ -1111,7 +1112,7 @@ static void ipip6_tunnel_bind_dev(struct net_device *dev) iph->daddr, iph->saddr, 0, 0, IPPROTO_IPV6, - RT_TOS(iph->tos), + iph->tos & INET_DSCP_MASK, tunnel->parms.link); if (!IS_ERR(rt)) { @@ -1435,7 +1436,7 @@ static void ipip6_tunnel_setup(struct net_device *dev) dev->flags = IFF_NOARP; netif_keep_dst(dev); dev->addr_len = 4; - dev->features |= NETIF_F_LLTX; + dev->lltx = true; dev->features |= SIT_FEATURES; dev->hw_features |= SIT_FEATURES; dev->pcpu_stat_type = NETDEV_PCPU_STAT_TSTATS; @@ -1855,7 +1856,7 @@ static int __net_init sit_init_net(struct net *net) /* FB netdevice is special: we have one, and only one per netns. * Allowing to move it to another netns is clearly unsafe. */ - sitn->fb_tunnel_dev->features |= NETIF_F_NETNS_LOCAL; + sitn->fb_tunnel_dev->netns_local = true; err = register_netdev(sitn->fb_tunnel_dev); if (err) diff --git a/net/ipv6/syncookies.c b/net/ipv6/syncookies.c index bfad1e89b6a6..9d83eadd308b 100644 --- a/net/ipv6/syncookies.c +++ b/net/ipv6/syncookies.c @@ -275,6 +275,6 @@ out: out_free: reqsk_free(req); out_drop: - kfree_skb_reason(skb, reason); + sk_skb_reason_drop(sk, skb, reason); return NULL; } diff --git a/net/ipv6/sysctl_net_ipv6.c b/net/ipv6/sysctl_net_ipv6.c index c060285ff47f..d2cd33e2698d 100644 --- a/net/ipv6/sysctl_net_ipv6.c +++ b/net/ipv6/sysctl_net_ipv6.c @@ -30,7 +30,7 @@ static u32 rt6_multipath_hash_fields_all_mask = static u32 ioam6_id_max = IOAM6_DEFAULT_ID; static u64 ioam6_id_wide_max = IOAM6_DEFAULT_ID_WIDE; -static int proc_rt6_multipath_hash_policy(struct ctl_table *table, int write, +static int proc_rt6_multipath_hash_policy(const struct ctl_table *table, int write, void *buffer, size_t *lenp, loff_t *ppos) { struct net *net; @@ -46,7 +46,7 @@ static int proc_rt6_multipath_hash_policy(struct ctl_table *table, int write, } static int -proc_rt6_multipath_hash_fields(struct ctl_table *table, int write, void *buffer, +proc_rt6_multipath_hash_fields(const struct ctl_table *table, int write, void *buffer, size_t *lenp, loff_t *ppos) { struct net *net; diff --git a/net/ipv6/tcp_ipv6.c b/net/ipv6/tcp_ipv6.c index 729faf8bd366..d71ab4e1efe1 100644 --- a/net/ipv6/tcp_ipv6.c +++ b/net/ipv6/tcp_ipv6.c @@ -490,14 +490,10 @@ static int tcp_v6_err(struct sk_buff *skb, struct inet6_skb_parm *opt, ipv6_icmp_error(sk, skb, err, th->dest, ntohl(info), (u8 *)th); - if (!sock_owned_by_user(sk)) { - WRITE_ONCE(sk->sk_err, err); - sk_error_report(sk); /* Wake people up to see the error (see connect in sock.c) */ - - tcp_done(sk); - } else { + if (!sock_owned_by_user(sk)) + tcp_done_with_error(sk, err); + else WRITE_ONCE(sk->sk_err_soft, err); - } goto out; case TCP_LISTEN: break; @@ -975,7 +971,7 @@ static void tcp_v6_send_response(const struct sock *sk, struct sk_buff *skb, u32 mark = inet_twsk(sk)->tw_mark; else mark = READ_ONCE(sk->sk_mark); - skb_set_delivery_time(buff, tcp_transmit_time(sk), true); + skb_set_delivery_time(buff, tcp_transmit_time(sk), SKB_CLOCK_MONOTONIC); } if (txhash) { /* autoflowlabel/skb_get_hash_flowi6 rely on buff->hash */ @@ -1197,12 +1193,13 @@ static void tcp_v6_timewait_ack(struct sock *sk, struct sk_buff *skb) #endif } - tcp_v6_send_ack(sk, skb, tcptw->tw_snd_nxt, tcptw->tw_rcv_nxt, + tcp_v6_send_ack(sk, skb, tcptw->tw_snd_nxt, + READ_ONCE(tcptw->tw_rcv_nxt), tcptw->tw_rcv_wnd >> tw->tw_rcv_wscale, tcp_tw_tsval(tcptw), - tcptw->tw_ts_recent, tw->tw_bound_dev_if, &key, - tw->tw_tclass, cpu_to_be32(tw->tw_flowlabel), tw->tw_priority, - tw->tw_txhash); + READ_ONCE(tcptw->tw_ts_recent), tw->tw_bound_dev_if, + &key, tw->tw_tclass, cpu_to_be32(tw->tw_flowlabel), + tw->tw_priority, tw->tw_txhash); #ifdef CONFIG_TCP_AO out: @@ -1678,7 +1675,7 @@ reset: discard: if (opt_skb) __kfree_skb(opt_skb); - kfree_skb_reason(skb, reason); + sk_skb_reason_drop(sk, skb, reason); return 0; csum_err: reason = SKB_DROP_REASON_TCP_CSUM; @@ -1751,8 +1748,8 @@ INDIRECT_CALLABLE_SCOPE int tcp_v6_rcv(struct sk_buff *skb) int dif = inet6_iif(skb); const struct tcphdr *th; const struct ipv6hdr *hdr; + struct sock *sk = NULL; bool refcounted; - struct sock *sk; int ret; u32 isn; struct net *net = dev_net(skb->dev); @@ -1944,7 +1941,7 @@ bad_packet: discard_it: SKB_DR_OR(drop_reason, NOT_SPECIFIED); - kfree_skb_reason(skb, drop_reason); + sk_skb_reason_drop(sk, skb, drop_reason); return 0; discard_and_relse: @@ -2262,7 +2259,7 @@ static void get_timewait6_sock(struct seq_file *seq, src->s6_addr32[2], src->s6_addr32[3], srcp, dest->s6_addr32[0], dest->s6_addr32[1], dest->s6_addr32[2], dest->s6_addr32[3], destp, - tw->tw_substate, 0, 0, + READ_ONCE(tw->tw_substate), 0, 0, 3, jiffies_delta_to_clock_t(delta), 0, 0, 0, 0, refcount_read(&tw->tw_refcnt), tw); } @@ -2383,8 +2380,14 @@ static struct inet_protosw tcpv6_protosw = { static int __net_init tcpv6_net_init(struct net *net) { - return inet_ctl_sock_create(&net->ipv6.tcp_sk, PF_INET6, - SOCK_RAW, IPPROTO_TCP, net); + int res; + + res = inet_ctl_sock_create(&net->ipv6.tcp_sk, PF_INET6, + SOCK_RAW, IPPROTO_TCP, net); + if (!res) + net->ipv6.tcp_sk->sk_clockid = CLOCK_MONOTONIC; + + return res; } static void __net_exit tcpv6_net_exit(struct net *net) diff --git a/net/ipv6/udp.c b/net/ipv6/udp.c index c81a07ac0463..52dfbb2ff1a8 100644 --- a/net/ipv6/udp.c +++ b/net/ipv6/udp.c @@ -46,7 +46,6 @@ #include <net/tcp_states.h> #include <net/ip6_checksum.h> #include <net/ip6_tunnel.h> -#include <trace/events/udp.h> #include <net/xfrm.h> #include <net/inet_hashtables.h> #include <net/inet6_hashtables.h> @@ -115,7 +114,7 @@ void udp_v6_rehash(struct sock *sk) udp_lib_rehash(sk, new_hash); } -static int compute_score(struct sock *sk, struct net *net, +static int compute_score(struct sock *sk, const struct net *net, const struct in6_addr *saddr, __be16 sport, const struct in6_addr *daddr, unsigned short hnum, int dif, int sdif) @@ -161,7 +160,7 @@ static int compute_score(struct sock *sk, struct net *net, } /* called with rcu_read_lock() */ -static struct sock *udp6_lib_lookup2(struct net *net, +static struct sock *udp6_lib_lookup2(const struct net *net, const struct in6_addr *saddr, __be16 sport, const struct in6_addr *daddr, unsigned int hnum, int dif, int sdif, struct udp_hslot *hslot2, @@ -218,7 +217,7 @@ rescore: } /* rcu_read_lock() must be held */ -struct sock *__udp6_lib_lookup(struct net *net, +struct sock *__udp6_lib_lookup(const struct net *net, const struct in6_addr *saddr, __be16 sport, const struct in6_addr *daddr, __be16 dport, int dif, int sdif, struct udp_table *udptable, @@ -301,7 +300,7 @@ struct sock *udp6_lib_lookup_skb(const struct sk_buff *skb, * Does increment socket refcount. */ #if IS_ENABLED(CONFIG_NF_TPROXY_IPV6) || IS_ENABLED(CONFIG_NF_SOCKET_IPV6) -struct sock *udp6_lib_lookup(struct net *net, const struct in6_addr *saddr, __be16 sport, +struct sock *udp6_lib_lookup(const struct net *net, const struct in6_addr *saddr, __be16 sport, const struct in6_addr *daddr, __be16 dport, int dif) { struct sock *sk; @@ -673,7 +672,7 @@ static int __udpv6_queue_rcv_skb(struct sock *sk, struct sk_buff *skb) } UDP6_INC_STATS(sock_net(sk), UDP_MIB_INERRORS, is_udplite); trace_udp_fail_queue_rcv_skb(rc, sk, skb); - kfree_skb_reason(skb, drop_reason); + sk_skb_reason_drop(sk, skb, drop_reason); return -1; } @@ -776,7 +775,7 @@ csum_error: drop: __UDP6_INC_STATS(sock_net(sk), UDP_MIB_INERRORS, is_udplite); atomic_inc(&sk->sk_drops); - kfree_skb_reason(skb, drop_reason); + sk_skb_reason_drop(sk, skb, drop_reason); return -1; } @@ -940,8 +939,8 @@ int __udp6_lib_rcv(struct sk_buff *skb, struct udp_table *udptable, enum skb_drop_reason reason = SKB_DROP_REASON_NOT_SPECIFIED; const struct in6_addr *saddr, *daddr; struct net *net = dev_net(skb->dev); + struct sock *sk = NULL; struct udphdr *uh; - struct sock *sk; bool refcounted; u32 ulen = 0; @@ -1033,7 +1032,7 @@ no_sk: __UDP6_INC_STATS(net, UDP_MIB_NOPORTS, proto == IPPROTO_UDPLITE); icmpv6_send(skb, ICMPV6_DEST_UNREACH, ICMPV6_PORT_UNREACH, 0); - kfree_skb_reason(skb, reason); + sk_skb_reason_drop(sk, skb, reason); return 0; short_packet: @@ -1054,7 +1053,7 @@ csum_error: __UDP6_INC_STATS(net, UDP_MIB_CSUMERRORS, proto == IPPROTO_UDPLITE); discard: __UDP6_INC_STATS(net, UDP_MIB_INERRORS, proto == IPPROTO_UDPLITE); - kfree_skb_reason(skb, reason); + sk_skb_reason_drop(sk, skb, reason); return 0; } @@ -1257,8 +1256,7 @@ static int udp_v6_send_skb(struct sk_buff *skb, struct flowi6 *fl6, kfree_skb(skb); return -EINVAL; } - if (skb->ip_summed != CHECKSUM_PARTIAL || is_udplite || - dst_xfrm(skb_dst(skb))) { + if (is_udplite || dst_xfrm(skb_dst(skb))) { kfree_skb(skb); return -EIO; } diff --git a/net/ipv6/xfrm6_policy.c b/net/ipv6/xfrm6_policy.c index 2f1ea5f999a2..b1d81c4270ab 100644 --- a/net/ipv6/xfrm6_policy.c +++ b/net/ipv6/xfrm6_policy.c @@ -290,8 +290,14 @@ int __init xfrm6_init(void) ret = register_pernet_subsys(&xfrm6_net_ops); if (ret) goto out_protocol; + + ret = xfrm_nat_keepalive_init(AF_INET6); + if (ret) + goto out_nat_keepalive; out: return ret; +out_nat_keepalive: + unregister_pernet_subsys(&xfrm6_net_ops); out_protocol: xfrm6_protocol_fini(); out_state: @@ -303,6 +309,7 @@ out_policy: void xfrm6_fini(void) { + xfrm_nat_keepalive_fini(AF_INET6); unregister_pernet_subsys(&xfrm6_net_ops); xfrm6_protocol_fini(); xfrm6_policy_fini(); diff --git a/net/iucv/af_iucv.c b/net/iucv/af_iucv.c index c3b0b610b0aa..c00323fa9eb6 100644 --- a/net/iucv/af_iucv.c +++ b/net/iucv/af_iucv.c @@ -335,8 +335,8 @@ static void iucv_sever_path(struct sock *sk, int with_user_data) struct iucv_sock *iucv = iucv_sk(sk); struct iucv_path *path = iucv->path; - if (iucv->path) { - iucv->path = NULL; + /* Whoever resets the path pointer, must sever and free it. */ + if (xchg(&iucv->path, NULL)) { if (with_user_data) { low_nmcpy(user_data, iucv->src_name); high_nmcpy(user_data, iucv->dst_name); diff --git a/net/iucv/iucv.c b/net/iucv/iucv.c index b7bf34a5eb37..d3e9efab7f4b 100644 --- a/net/iucv/iucv.c +++ b/net/iucv/iucv.c @@ -62,7 +62,7 @@ #define IUCV_IPNORPY 0x10 #define IUCV_IPALL 0x80 -static int iucv_bus_match(struct device *dev, struct device_driver *drv) +static int iucv_bus_match(struct device *dev, const struct device_driver *drv) { return 0; } @@ -86,13 +86,15 @@ struct device *iucv_alloc_device(const struct attribute_group **attrs, { struct device *dev; va_list vargs; + char buf[20]; int rc; dev = kzalloc(sizeof(*dev), GFP_KERNEL); if (!dev) goto out_error; va_start(vargs, fmt); - rc = dev_set_name(dev, fmt, vargs); + vsnprintf(buf, sizeof(buf), fmt, vargs); + rc = dev_set_name(dev, "%s", buf); va_end(vargs); if (rc) goto out_error; diff --git a/net/kcm/kcmsock.c b/net/kcm/kcmsock.c index 2f191e50d4fc..d4118c796290 100644 --- a/net/kcm/kcmsock.c +++ b/net/kcm/kcmsock.c @@ -755,6 +755,7 @@ static int kcm_sendmsg(struct socket *sock, struct msghdr *msg, size_t len) !(msg->msg_flags & MSG_MORE) : !!(msg->msg_flags & MSG_EOR); int err = -EPIPE; + mutex_lock(&kcm->tx_mutex); lock_sock(sk); /* Per tcp_sendmsg this should be in poll */ @@ -926,6 +927,7 @@ partial_message: KCM_STATS_ADD(kcm->stats.tx_bytes, copied); release_sock(sk); + mutex_unlock(&kcm->tx_mutex); return copied; out_error: @@ -951,6 +953,7 @@ out_error: sk->sk_write_space(sk); release_sock(sk); + mutex_unlock(&kcm->tx_mutex); return err; } @@ -1204,6 +1207,7 @@ static void init_kcm_sock(struct kcm_sock *kcm, struct kcm_mux *mux) spin_unlock_bh(&mux->lock); INIT_WORK(&kcm->tx_work, kcm_tx_work); + mutex_init(&kcm->tx_mutex); spin_lock_bh(&mux->rx_lock); kcm_rcv_ready(kcm); diff --git a/net/l2tp/l2tp_core.c b/net/l2tp/l2tp_core.c index 88a34db265d8..3eec23ac5ab1 100644 --- a/net/l2tp/l2tp_core.c +++ b/net/l2tp/l2tp_core.c @@ -39,7 +39,6 @@ #include <linux/ip.h> #include <linux/udp.h> #include <linux/l2tp.h> -#include <linux/hash.h> #include <linux/sort.h> #include <linux/file.h> #include <linux/nsproxy.h> @@ -61,7 +60,6 @@ #include <linux/atomic.h> #include "l2tp_core.h" -#include "trace.h" #define CREATE_TRACE_POINTS #include "trace.h" @@ -88,6 +86,11 @@ /* Default trace flags */ #define L2TP_DEFAULT_DEBUG_FLAGS 0 +#define L2TP_DEPTH_NESTING 2 +#if L2TP_DEPTH_NESTING == SINGLE_DEPTH_NESTING +#error "L2TP requires its own lockdep subclass" +#endif + /* Private data stored for received packets in the skb. */ struct l2tp_skb_cb { @@ -107,99 +110,106 @@ struct l2tp_net { /* Lock for write access to l2tp_tunnel_idr */ spinlock_t l2tp_tunnel_idr_lock; struct idr l2tp_tunnel_idr; - struct hlist_head l2tp_session_hlist[L2TP_HASH_SIZE_2]; - /* Lock for write access to l2tp_session_hlist */ - spinlock_t l2tp_session_hlist_lock; + /* Lock for write access to l2tp_v[23]_session_idr/htable */ + spinlock_t l2tp_session_idr_lock; + struct idr l2tp_v2_session_idr; + struct idr l2tp_v3_session_idr; + struct hlist_head l2tp_v3_session_htable[16]; }; -#if IS_ENABLED(CONFIG_IPV6) -static bool l2tp_sk_is_v6(struct sock *sk) +static u32 l2tp_v2_session_key(u16 tunnel_id, u16 session_id) { - return sk->sk_family == PF_INET6 && - !ipv6_addr_v4mapped(&sk->sk_v6_daddr); + return ((u32)tunnel_id) << 16 | session_id; } -#endif -static inline struct l2tp_net *l2tp_pernet(const struct net *net) +static unsigned long l2tp_v3_session_hashkey(struct sock *sk, u32 session_id) { - return net_generic(net, l2tp_net_id); + return ((unsigned long)sk) + session_id; } -/* Session hash global list for L2TPv3. - * The session_id SHOULD be random according to RFC3931, but several - * L2TP implementations use incrementing session_ids. So we do a real - * hash on the session_id, rather than a simple bitmask. - */ -static inline struct hlist_head * -l2tp_session_id_hash_2(struct l2tp_net *pn, u32 session_id) +#if IS_ENABLED(CONFIG_IPV6) +static bool l2tp_sk_is_v6(struct sock *sk) { - return &pn->l2tp_session_hlist[hash_32(session_id, L2TP_HASH_BITS_2)]; + return sk->sk_family == PF_INET6 && + !ipv6_addr_v4mapped(&sk->sk_v6_daddr); } +#endif -/* Session hash list. - * The session_id SHOULD be random according to RFC2661, but several - * L2TP implementations (Cisco and Microsoft) use incrementing - * session_ids. So we do a real hash on the session_id, rather than a - * simple bitmask. - */ -static inline struct hlist_head * -l2tp_session_id_hash(struct l2tp_tunnel *tunnel, u32 session_id) +static struct l2tp_net *l2tp_pernet(const struct net *net) { - return &tunnel->session_hlist[hash_32(session_id, L2TP_HASH_BITS)]; + return net_generic(net, l2tp_net_id); } static void l2tp_tunnel_free(struct l2tp_tunnel *tunnel) { + struct sock *sk = tunnel->sock; + trace_free_tunnel(tunnel); - sock_put(tunnel->sock); - /* the tunnel is freed in the socket destructor */ + + if (sk) { + /* Disable udp encapsulation */ + switch (tunnel->encap) { + case L2TP_ENCAPTYPE_UDP: + /* No longer an encapsulation socket. See net/ipv4/udp.c */ + WRITE_ONCE(udp_sk(sk)->encap_type, 0); + udp_sk(sk)->encap_rcv = NULL; + udp_sk(sk)->encap_destroy = NULL; + break; + case L2TP_ENCAPTYPE_IP: + break; + } + + tunnel->sock = NULL; + sock_put(sk); + } + + kfree_rcu(tunnel, rcu); } static void l2tp_session_free(struct l2tp_session *session) { trace_free_session(session); if (session->tunnel) - l2tp_tunnel_dec_refcount(session->tunnel); - kfree(session); + l2tp_tunnel_put(session->tunnel); + kfree_rcu(session, rcu); } -struct l2tp_tunnel *l2tp_sk_to_tunnel(struct sock *sk) +struct l2tp_tunnel *l2tp_sk_to_tunnel(const struct sock *sk) { - struct l2tp_tunnel *tunnel = sk->sk_user_data; + const struct net *net = sock_net(sk); + unsigned long tunnel_id, tmp; + struct l2tp_tunnel *tunnel; + struct l2tp_net *pn; - if (tunnel) - if (WARN_ON(tunnel->magic != L2TP_TUNNEL_MAGIC)) - return NULL; + rcu_read_lock_bh(); + pn = l2tp_pernet(net); + idr_for_each_entry_ul(&pn->l2tp_tunnel_idr, tunnel, tmp, tunnel_id) { + if (tunnel && + tunnel->sock == sk && + refcount_inc_not_zero(&tunnel->ref_count)) { + rcu_read_unlock_bh(); + return tunnel; + } + } + rcu_read_unlock_bh(); - return tunnel; + return NULL; } EXPORT_SYMBOL_GPL(l2tp_sk_to_tunnel); -void l2tp_tunnel_inc_refcount(struct l2tp_tunnel *tunnel) -{ - refcount_inc(&tunnel->ref_count); -} -EXPORT_SYMBOL_GPL(l2tp_tunnel_inc_refcount); - -void l2tp_tunnel_dec_refcount(struct l2tp_tunnel *tunnel) +void l2tp_tunnel_put(struct l2tp_tunnel *tunnel) { if (refcount_dec_and_test(&tunnel->ref_count)) l2tp_tunnel_free(tunnel); } -EXPORT_SYMBOL_GPL(l2tp_tunnel_dec_refcount); +EXPORT_SYMBOL_GPL(l2tp_tunnel_put); -void l2tp_session_inc_refcount(struct l2tp_session *session) -{ - refcount_inc(&session->ref_count); -} -EXPORT_SYMBOL_GPL(l2tp_session_inc_refcount); - -void l2tp_session_dec_refcount(struct l2tp_session *session) +void l2tp_session_put(struct l2tp_session *session) { if (refcount_dec_and_test(&session->ref_count)) l2tp_session_free(session); } -EXPORT_SYMBOL_GPL(l2tp_session_dec_refcount); +EXPORT_SYMBOL_GPL(l2tp_session_put); /* Lookup a tunnel. A new reference is held on the returned tunnel. */ struct l2tp_tunnel *l2tp_tunnel_get(const struct net *net, u32 tunnel_id) @@ -219,92 +229,202 @@ struct l2tp_tunnel *l2tp_tunnel_get(const struct net *net, u32 tunnel_id) } EXPORT_SYMBOL_GPL(l2tp_tunnel_get); -struct l2tp_tunnel *l2tp_tunnel_get_nth(const struct net *net, int nth) +struct l2tp_tunnel *l2tp_tunnel_get_next(const struct net *net, unsigned long *key) { struct l2tp_net *pn = l2tp_pernet(net); - unsigned long tunnel_id, tmp; - struct l2tp_tunnel *tunnel; - int count = 0; + struct l2tp_tunnel *tunnel = NULL; rcu_read_lock_bh(); - idr_for_each_entry_ul(&pn->l2tp_tunnel_idr, tunnel, tmp, tunnel_id) { - if (tunnel && ++count > nth && - refcount_inc_not_zero(&tunnel->ref_count)) { +again: + tunnel = idr_get_next_ul(&pn->l2tp_tunnel_idr, key); + if (tunnel) { + if (refcount_inc_not_zero(&tunnel->ref_count)) { rcu_read_unlock_bh(); return tunnel; } + (*key)++; + goto again; } rcu_read_unlock_bh(); return NULL; } -EXPORT_SYMBOL_GPL(l2tp_tunnel_get_nth); +EXPORT_SYMBOL_GPL(l2tp_tunnel_get_next); -struct l2tp_session *l2tp_tunnel_get_session(struct l2tp_tunnel *tunnel, - u32 session_id) +struct l2tp_session *l2tp_v3_session_get(const struct net *net, struct sock *sk, u32 session_id) { - struct hlist_head *session_list; + const struct l2tp_net *pn = l2tp_pernet(net); struct l2tp_session *session; - session_list = l2tp_session_id_hash(tunnel, session_id); - rcu_read_lock_bh(); - hlist_for_each_entry_rcu(session, session_list, hlist) - if (session->session_id == session_id) { - l2tp_session_inc_refcount(session); - rcu_read_unlock_bh(); + session = idr_find(&pn->l2tp_v3_session_idr, session_id); + if (session && !hash_hashed(&session->hlist) && + refcount_inc_not_zero(&session->ref_count)) { + rcu_read_unlock_bh(); + return session; + } - return session; + /* If we get here and session is non-NULL, the session_id + * collides with one in another tunnel. If sk is non-NULL, + * find the session matching sk. + */ + if (session && sk) { + unsigned long key = l2tp_v3_session_hashkey(sk, session->session_id); + + hash_for_each_possible_rcu(pn->l2tp_v3_session_htable, session, + hlist, key) { + /* session->tunnel may be NULL if another thread is in + * l2tp_session_register and has added an item to + * l2tp_v3_session_htable but hasn't yet added the + * session to its tunnel's session_list. + */ + struct l2tp_tunnel *tunnel = READ_ONCE(session->tunnel); + + if (session->session_id == session_id && + tunnel && tunnel->sock == sk && + refcount_inc_not_zero(&session->ref_count)) { + rcu_read_unlock_bh(); + return session; + } } + } rcu_read_unlock_bh(); return NULL; } -EXPORT_SYMBOL_GPL(l2tp_tunnel_get_session); +EXPORT_SYMBOL_GPL(l2tp_v3_session_get); -struct l2tp_session *l2tp_session_get(const struct net *net, u32 session_id) +struct l2tp_session *l2tp_v2_session_get(const struct net *net, u16 tunnel_id, u16 session_id) { - struct hlist_head *session_list; + u32 session_key = l2tp_v2_session_key(tunnel_id, session_id); + const struct l2tp_net *pn = l2tp_pernet(net); struct l2tp_session *session; - session_list = l2tp_session_id_hash_2(l2tp_pernet(net), session_id); + rcu_read_lock_bh(); + session = idr_find(&pn->l2tp_v2_session_idr, session_key); + if (session && refcount_inc_not_zero(&session->ref_count)) { + rcu_read_unlock_bh(); + return session; + } + rcu_read_unlock_bh(); + + return NULL; +} +EXPORT_SYMBOL_GPL(l2tp_v2_session_get); + +struct l2tp_session *l2tp_session_get(const struct net *net, struct sock *sk, int pver, + u32 tunnel_id, u32 session_id) +{ + if (pver == L2TP_HDR_VER_2) + return l2tp_v2_session_get(net, tunnel_id, session_id); + else + return l2tp_v3_session_get(net, sk, session_id); +} +EXPORT_SYMBOL_GPL(l2tp_session_get); + +static struct l2tp_session *l2tp_v2_session_get_next(const struct net *net, + u16 tid, + unsigned long *key) +{ + struct l2tp_net *pn = l2tp_pernet(net); + struct l2tp_session *session = NULL; + + /* Start searching within the range of the tid */ + if (*key == 0) + *key = l2tp_v2_session_key(tid, 0); rcu_read_lock_bh(); - hlist_for_each_entry_rcu(session, session_list, global_hlist) - if (session->session_id == session_id) { - l2tp_session_inc_refcount(session); - rcu_read_unlock_bh(); +again: + session = idr_get_next_ul(&pn->l2tp_v2_session_idr, key); + if (session) { + struct l2tp_tunnel *tunnel = READ_ONCE(session->tunnel); + /* ignore sessions with id 0 as they are internal for pppol2tp */ + if (session->session_id == 0) { + (*key)++; + goto again; + } + + if (tunnel->tunnel_id == tid && + refcount_inc_not_zero(&session->ref_count)) { + rcu_read_unlock_bh(); return session; } + + (*key)++; + if (tunnel->tunnel_id == tid) + goto again; + } rcu_read_unlock_bh(); return NULL; } -EXPORT_SYMBOL_GPL(l2tp_session_get); -struct l2tp_session *l2tp_session_get_nth(struct l2tp_tunnel *tunnel, int nth) +static struct l2tp_session *l2tp_v3_session_get_next(const struct net *net, + u32 tid, struct sock *sk, + unsigned long *key) { - int hash; - struct l2tp_session *session; - int count = 0; + struct l2tp_net *pn = l2tp_pernet(net); + struct l2tp_session *session = NULL; rcu_read_lock_bh(); - for (hash = 0; hash < L2TP_HASH_SIZE; hash++) { - hlist_for_each_entry_rcu(session, &tunnel->session_hlist[hash], hlist) { - if (++count > nth) { - l2tp_session_inc_refcount(session); +again: + session = idr_get_next_ul(&pn->l2tp_v3_session_idr, key); + if (session && !hash_hashed(&session->hlist)) { + struct l2tp_tunnel *tunnel = READ_ONCE(session->tunnel); + + if (tunnel && tunnel->tunnel_id == tid && + refcount_inc_not_zero(&session->ref_count)) { + rcu_read_unlock_bh(); + return session; + } + + (*key)++; + goto again; + } + + /* If we get here and session is non-NULL, the IDR entry may be one + * where the session_id collides with one in another tunnel. Check + * session_htable for a match. There can only be one session of a given + * ID per tunnel so we can return as soon as a match is found. + */ + if (session && hash_hashed(&session->hlist)) { + unsigned long hkey = l2tp_v3_session_hashkey(sk, session->session_id); + u32 sid = session->session_id; + + hash_for_each_possible_rcu(pn->l2tp_v3_session_htable, session, + hlist, hkey) { + struct l2tp_tunnel *tunnel = READ_ONCE(session->tunnel); + + if (session->session_id == sid && + tunnel && tunnel->tunnel_id == tid && + refcount_inc_not_zero(&session->ref_count)) { rcu_read_unlock_bh(); return session; } } + + /* If no match found, the colliding session ID isn't in our + * tunnel so try the next session ID. + */ + (*key)++; + goto again; } rcu_read_unlock_bh(); return NULL; } -EXPORT_SYMBOL_GPL(l2tp_session_get_nth); + +struct l2tp_session *l2tp_session_get_next(const struct net *net, struct sock *sk, int pver, + u32 tunnel_id, unsigned long *key) +{ + if (pver == L2TP_HDR_VER_2) + return l2tp_v2_session_get_next(net, tunnel_id, key); + else + return l2tp_v3_session_get_next(net, tunnel_id, sk, key); +} +EXPORT_SYMBOL_GPL(l2tp_session_get_next); /* Lookup a session by interface name. * This is very inefficient but is only used by management interfaces. @@ -313,86 +433,190 @@ struct l2tp_session *l2tp_session_get_by_ifname(const struct net *net, const char *ifname) { struct l2tp_net *pn = l2tp_pernet(net); - int hash; + unsigned long tunnel_id, tmp; struct l2tp_session *session; + struct l2tp_tunnel *tunnel; rcu_read_lock_bh(); - for (hash = 0; hash < L2TP_HASH_SIZE_2; hash++) { - hlist_for_each_entry_rcu(session, &pn->l2tp_session_hlist[hash], global_hlist) { - if (!strcmp(session->ifname, ifname)) { - l2tp_session_inc_refcount(session); - rcu_read_unlock_bh(); - - return session; + idr_for_each_entry_ul(&pn->l2tp_tunnel_idr, tunnel, tmp, tunnel_id) { + if (tunnel) { + list_for_each_entry_rcu(session, &tunnel->session_list, list) { + if (!strcmp(session->ifname, ifname)) { + refcount_inc(&session->ref_count); + rcu_read_unlock_bh(); + + return session; + } } } } - rcu_read_unlock_bh(); return NULL; } EXPORT_SYMBOL_GPL(l2tp_session_get_by_ifname); +static void l2tp_session_coll_list_add(struct l2tp_session_coll_list *clist, + struct l2tp_session *session) +{ + refcount_inc(&session->ref_count); + WARN_ON_ONCE(session->coll_list); + session->coll_list = clist; + spin_lock(&clist->lock); + list_add(&session->clist, &clist->list); + spin_unlock(&clist->lock); +} + +static int l2tp_session_collision_add(struct l2tp_net *pn, + struct l2tp_session *session1, + struct l2tp_session *session2) +{ + struct l2tp_session_coll_list *clist; + + lockdep_assert_held(&pn->l2tp_session_idr_lock); + + if (!session2) + return -EEXIST; + + /* If existing session is in IP-encap tunnel, refuse new session */ + if (session2->tunnel->encap == L2TP_ENCAPTYPE_IP) + return -EEXIST; + + clist = session2->coll_list; + if (!clist) { + /* First collision. Allocate list to manage the collided sessions + * and add the existing session to the list. + */ + clist = kmalloc(sizeof(*clist), GFP_ATOMIC); + if (!clist) + return -ENOMEM; + + spin_lock_init(&clist->lock); + INIT_LIST_HEAD(&clist->list); + refcount_set(&clist->ref_count, 1); + l2tp_session_coll_list_add(clist, session2); + } + + /* If existing session isn't already in the session hlist, add it. */ + if (!hash_hashed(&session2->hlist)) + hash_add_rcu(pn->l2tp_v3_session_htable, &session2->hlist, + session2->hlist_key); + + /* Add new session to the hlist and collision list */ + hash_add_rcu(pn->l2tp_v3_session_htable, &session1->hlist, + session1->hlist_key); + refcount_inc(&clist->ref_count); + l2tp_session_coll_list_add(clist, session1); + + return 0; +} + +static void l2tp_session_collision_del(struct l2tp_net *pn, + struct l2tp_session *session) +{ + struct l2tp_session_coll_list *clist = session->coll_list; + unsigned long session_key = session->session_id; + struct l2tp_session *session2; + + lockdep_assert_held(&pn->l2tp_session_idr_lock); + + hash_del_rcu(&session->hlist); + + if (clist) { + /* Remove session from its collision list. If there + * are other sessions with the same ID, replace this + * session's IDR entry with that session, otherwise + * remove the IDR entry. If this is the last session, + * the collision list data is freed. + */ + spin_lock(&clist->lock); + list_del_init(&session->clist); + session2 = list_first_entry_or_null(&clist->list, struct l2tp_session, clist); + if (session2) { + void *old = idr_replace(&pn->l2tp_v3_session_idr, session2, session_key); + + WARN_ON_ONCE(IS_ERR_VALUE(old)); + } else { + void *removed = idr_remove(&pn->l2tp_v3_session_idr, session_key); + + WARN_ON_ONCE(removed != session); + } + session->coll_list = NULL; + spin_unlock(&clist->lock); + if (refcount_dec_and_test(&clist->ref_count)) + kfree(clist); + l2tp_session_put(session); + } +} + int l2tp_session_register(struct l2tp_session *session, struct l2tp_tunnel *tunnel) { - struct l2tp_session *session_walk; - struct hlist_head *g_head; - struct hlist_head *head; - struct l2tp_net *pn; + struct l2tp_net *pn = l2tp_pernet(tunnel->l2tp_net); + struct l2tp_session *other_session = NULL; + void *old = NULL; + u32 session_key; int err; - head = l2tp_session_id_hash(tunnel, session->session_id); + spin_lock_bh(&tunnel->list_lock); + spin_lock_bh(&pn->l2tp_session_idr_lock); - spin_lock_bh(&tunnel->hlist_lock); if (!tunnel->acpt_newsess) { err = -ENODEV; - goto err_tlock; + goto out; } - hlist_for_each_entry(session_walk, head, hlist) - if (session_walk->session_id == session->session_id) { - err = -EEXIST; - goto err_tlock; - } - if (tunnel->version == L2TP_HDR_VER_3) { - pn = l2tp_pernet(tunnel->l2tp_net); - g_head = l2tp_session_id_hash_2(pn, session->session_id); - - spin_lock_bh(&pn->l2tp_session_hlist_lock); - + session_key = session->session_id; + err = idr_alloc_u32(&pn->l2tp_v3_session_idr, NULL, + &session_key, session_key, GFP_ATOMIC); /* IP encap expects session IDs to be globally unique, while - * UDP encap doesn't. + * UDP encap doesn't. This isn't per the RFC, which says that + * sessions are identified only by the session ID, but is to + * support existing userspace which depends on it. */ - hlist_for_each_entry(session_walk, g_head, global_hlist) - if (session_walk->session_id == session->session_id && - (session_walk->tunnel->encap == L2TP_ENCAPTYPE_IP || - tunnel->encap == L2TP_ENCAPTYPE_IP)) { - err = -EEXIST; - goto err_tlock_pnlock; - } - - l2tp_tunnel_inc_refcount(tunnel); - hlist_add_head_rcu(&session->global_hlist, g_head); - - spin_unlock_bh(&pn->l2tp_session_hlist_lock); + if (err == -ENOSPC && tunnel->encap == L2TP_ENCAPTYPE_UDP) { + other_session = idr_find(&pn->l2tp_v3_session_idr, + session_key); + err = l2tp_session_collision_add(pn, session, + other_session); + } } else { - l2tp_tunnel_inc_refcount(tunnel); + session_key = l2tp_v2_session_key(tunnel->tunnel_id, + session->session_id); + err = idr_alloc_u32(&pn->l2tp_v2_session_idr, NULL, + &session_key, session_key, GFP_ATOMIC); } - hlist_add_head_rcu(&session->hlist, head); - spin_unlock_bh(&tunnel->hlist_lock); + if (err) { + if (err == -ENOSPC) + err = -EEXIST; + goto out; + } - trace_register_session(session); + refcount_inc(&tunnel->ref_count); + WRITE_ONCE(session->tunnel, tunnel); + list_add_rcu(&session->list, &tunnel->session_list); - return 0; + /* this makes session available to lockless getters */ + if (tunnel->version == L2TP_HDR_VER_3) { + if (!other_session) + old = idr_replace(&pn->l2tp_v3_session_idr, session, session_key); + } else { + old = idr_replace(&pn->l2tp_v2_session_idr, session, session_key); + } -err_tlock_pnlock: - spin_unlock_bh(&pn->l2tp_session_hlist_lock); -err_tlock: - spin_unlock_bh(&tunnel->hlist_lock); + /* old should be NULL, unless something removed or modified + * the IDR entry after our idr_alloc_32 above (which shouldn't + * happen). + */ + WARN_ON_ONCE(old); +out: + spin_unlock_bh(&pn->l2tp_session_idr_lock); + spin_unlock_bh(&tunnel->list_lock); + + if (!err) + trace_register_session(session); return err; } @@ -693,7 +917,8 @@ void l2tp_recv_common(struct l2tp_session *session, struct sk_buff *skb, if (!session->lns_mode && !session->send_seq) { trace_session_seqnum_lns_enable(session); session->send_seq = 1; - l2tp_session_set_header_len(session, tunnel->version); + l2tp_session_set_header_len(session, tunnel->version, + tunnel->encap); } } else { /* No sequence numbers. @@ -714,7 +939,8 @@ void l2tp_recv_common(struct l2tp_session *session, struct sk_buff *skb, if (!session->lns_mode && session->send_seq) { trace_session_seqnum_lns_disable(session); session->send_seq = 0; - l2tp_session_set_header_len(session, tunnel->version); + l2tp_session_set_header_len(session, tunnel->version, + tunnel->encap); } else if (session->send_seq) { pr_debug_ratelimited("%s: recv data has no seq numbers when required. Discarding.\n", session->name); @@ -785,19 +1011,14 @@ static void l2tp_session_queue_purge(struct l2tp_session *session) } } -/* Internal UDP receive frame. Do the real work of receiving an L2TP data frame - * here. The skb is not on a list when we get here. - * Returns 0 if the packet was a data packet and was successfully passed on. - * Returns 1 if the packet was not a good data packet and could not be - * forwarded. All such packets are passed up to userspace to deal with. - */ -static int l2tp_udp_recv_core(struct l2tp_tunnel *tunnel, struct sk_buff *skb) +/* UDP encapsulation receive handler. See net/ipv4/udp.c for details. */ +int l2tp_udp_encap_recv(struct sock *sk, struct sk_buff *skb) { struct l2tp_session *session = NULL; - struct l2tp_tunnel *orig_tunnel = tunnel; + struct l2tp_tunnel *tunnel = NULL; + struct net *net = sock_net(sk); unsigned char *ptr, *optr; u16 hdrflags; - u32 tunnel_id, session_id; u16 version; int length; @@ -807,11 +1028,8 @@ static int l2tp_udp_recv_core(struct l2tp_tunnel *tunnel, struct sk_buff *skb) __skb_pull(skb, sizeof(struct udphdr)); /* Short packet? */ - if (!pskb_may_pull(skb, L2TP_HDR_SIZE_MAX)) { - pr_debug_ratelimited("%s: recv short packet (len=%d)\n", - tunnel->name, skb->len); - goto invalid; - } + if (!pskb_may_pull(skb, L2TP_HDR_SIZE_MAX)) + goto pass; /* Point to L2TP header */ optr = skb->data; @@ -834,6 +1052,8 @@ static int l2tp_udp_recv_core(struct l2tp_tunnel *tunnel, struct sk_buff *skb) ptr += 2; if (version == L2TP_HDR_VER_2) { + u16 tunnel_id, session_id; + /* If length is present, skip it */ if (hdrflags & L2TP_HDRFLAG_L) ptr += 2; @@ -841,59 +1061,42 @@ static int l2tp_udp_recv_core(struct l2tp_tunnel *tunnel, struct sk_buff *skb) /* Extract tunnel and session ID */ tunnel_id = ntohs(*(__be16 *)ptr); ptr += 2; - - if (tunnel_id != tunnel->tunnel_id) { - /* We are receiving trafic for another tunnel, probably - * because we have several tunnels between the same - * IP/port quadruple, look it up. - */ - struct l2tp_tunnel *alt_tunnel; - - alt_tunnel = l2tp_tunnel_get(tunnel->l2tp_net, tunnel_id); - if (!alt_tunnel) - goto pass; - tunnel = alt_tunnel; - } - session_id = ntohs(*(__be16 *)ptr); ptr += 2; + + session = l2tp_v2_session_get(net, tunnel_id, session_id); } else { + u32 session_id; + ptr += 2; /* skip reserved bits */ - tunnel_id = tunnel->tunnel_id; session_id = ntohl(*(__be32 *)ptr); ptr += 4; - } - /* Check protocol version */ - if (version != tunnel->version) { - pr_debug_ratelimited("%s: recv protocol version mismatch: got %d expected %d\n", - tunnel->name, version, tunnel->version); - goto invalid; + session = l2tp_v3_session_get(net, sk, session_id); } - /* Find the session context */ - session = l2tp_tunnel_get_session(tunnel, session_id); if (!session || !session->recv_skb) { if (session) - l2tp_session_dec_refcount(session); + l2tp_session_put(session); /* Not found? Pass to userspace to deal with */ - pr_debug_ratelimited("%s: no session found (%u/%u). Passing up.\n", - tunnel->name, tunnel_id, session_id); goto pass; } - if (tunnel->version == L2TP_HDR_VER_3 && + tunnel = session->tunnel; + + /* Check protocol version */ + if (version != tunnel->version) + goto invalid; + + if (version == L2TP_HDR_VER_3 && l2tp_v3_ensure_opt_in_linear(session, skb, &ptr, &optr)) { - l2tp_session_dec_refcount(session); + l2tp_session_put(session); goto invalid; } l2tp_recv_common(session, skb, ptr, optr, hdrflags, length); - l2tp_session_dec_refcount(session); - - if (tunnel != orig_tunnel) - l2tp_tunnel_dec_refcount(tunnel); + l2tp_session_put(session); return 0; @@ -904,51 +1107,14 @@ pass: /* Put UDP header back */ __skb_push(skb, sizeof(struct udphdr)); - if (tunnel != orig_tunnel) - l2tp_tunnel_dec_refcount(tunnel); - - return 1; -} - -/* UDP encapsulation receive and error receive handlers. - * See net/ipv4/udp.c for details. - * - * Note that these functions are called from inside an - * RCU-protected region, but without the socket being locked. - * - * Hence we use rcu_dereference_sk_user_data to access the - * tunnel data structure rather the usual l2tp_sk_to_tunnel - * accessor function. - */ -int l2tp_udp_encap_recv(struct sock *sk, struct sk_buff *skb) -{ - struct l2tp_tunnel *tunnel; - - tunnel = rcu_dereference_sk_user_data(sk); - if (!tunnel) - goto pass_up; - if (WARN_ON(tunnel->magic != L2TP_TUNNEL_MAGIC)) - goto pass_up; - - if (l2tp_udp_recv_core(tunnel, skb)) - goto pass_up; - - return 0; - -pass_up: return 1; } EXPORT_SYMBOL_GPL(l2tp_udp_encap_recv); +/* UDP encapsulation receive error handler. See net/ipv4/udp.c for details. */ static void l2tp_udp_encap_err_recv(struct sock *sk, struct sk_buff *skb, int err, __be16 port, u32 info, u8 *payload) { - struct l2tp_tunnel *tunnel; - - tunnel = rcu_dereference_sk_user_data(sk); - if (!tunnel || tunnel->fd < 0) - return; - sk->sk_err = err; sk_error_report(sk); @@ -1085,7 +1251,13 @@ static int l2tp_xmit_core(struct l2tp_session *session, struct sk_buff *skb, uns IPCB(skb)->flags &= ~(IPSKB_XFRM_TUNNEL_SIZE | IPSKB_XFRM_TRANSFORMED | IPSKB_REROUTED); nf_reset_ct(skb); - bh_lock_sock_nested(sk); + /* L2TP uses its own lockdep subclass to avoid lockdep splats caused by + * nested socket calls on the same lockdep socket class. This can + * happen when data from a user socket is routed over l2tp, which uses + * another userspace socket. + */ + spin_lock_nested(&sk->sk_lock.slock, L2TP_DEPTH_NESTING); + if (sock_owned_by_user(sk)) { kfree_skb(skb); ret = NET_XMIT_DROP; @@ -1137,7 +1309,7 @@ static int l2tp_xmit_core(struct l2tp_session *session, struct sk_buff *skb, uns ret = l2tp_xmit_queue(tunnel, skb, &inet->cork.fl); out_unlock: - bh_unlock_sock(sk); + spin_unlock(&sk->sk_lock.slock); return ret; } @@ -1168,66 +1340,38 @@ EXPORT_SYMBOL_GPL(l2tp_xmit_skb); * Tinnel and session create/destroy. *****************************************************************************/ -/* Tunnel socket destruct hook. - * The tunnel context is deleted only when all session sockets have been - * closed. - */ -static void l2tp_tunnel_destruct(struct sock *sk) -{ - struct l2tp_tunnel *tunnel = l2tp_sk_to_tunnel(sk); - - if (!tunnel) - goto end; - - /* Disable udp encapsulation */ - switch (tunnel->encap) { - case L2TP_ENCAPTYPE_UDP: - /* No longer an encapsulation socket. See net/ipv4/udp.c */ - WRITE_ONCE(udp_sk(sk)->encap_type, 0); - udp_sk(sk)->encap_rcv = NULL; - udp_sk(sk)->encap_destroy = NULL; - break; - case L2TP_ENCAPTYPE_IP: - break; - } - - /* Remove hooks into tunnel socket */ - write_lock_bh(&sk->sk_callback_lock); - sk->sk_destruct = tunnel->old_sk_destruct; - sk->sk_user_data = NULL; - write_unlock_bh(&sk->sk_callback_lock); - - /* Call the original destructor */ - if (sk->sk_destruct) - (*sk->sk_destruct)(sk); - - kfree_rcu(tunnel, rcu); -end: - return; -} - -/* Remove an l2tp session from l2tp_core's hash lists. */ +/* Remove an l2tp session from l2tp_core's lists. */ static void l2tp_session_unhash(struct l2tp_session *session) { struct l2tp_tunnel *tunnel = session->tunnel; - /* Remove the session from core hashes */ if (tunnel) { - /* Remove from the per-tunnel hash */ - spin_lock_bh(&tunnel->hlist_lock); - hlist_del_init_rcu(&session->hlist); - spin_unlock_bh(&tunnel->hlist_lock); - - /* For L2TPv3 we have a per-net hash: remove from there, too */ - if (tunnel->version != L2TP_HDR_VER_2) { - struct l2tp_net *pn = l2tp_pernet(tunnel->l2tp_net); - - spin_lock_bh(&pn->l2tp_session_hlist_lock); - hlist_del_init_rcu(&session->global_hlist); - spin_unlock_bh(&pn->l2tp_session_hlist_lock); + struct l2tp_net *pn = l2tp_pernet(tunnel->l2tp_net); + struct l2tp_session *removed = session; + + spin_lock_bh(&tunnel->list_lock); + spin_lock_bh(&pn->l2tp_session_idr_lock); + + /* Remove from the per-tunnel list */ + list_del_init(&session->list); + + /* Remove from per-net IDR */ + if (tunnel->version == L2TP_HDR_VER_3) { + if (hash_hashed(&session->hlist)) + l2tp_session_collision_del(pn, session); + else + removed = idr_remove(&pn->l2tp_v3_session_idr, + session->session_id); + } else { + u32 session_key = l2tp_v2_session_key(tunnel->tunnel_id, + session->session_id); + removed = idr_remove(&pn->l2tp_v2_session_idr, + session_key); } + WARN_ON_ONCE(removed && removed != session); - synchronize_rcu(); + spin_unlock_bh(&pn->l2tp_session_idr_lock); + spin_unlock_bh(&tunnel->list_lock); } } @@ -1236,37 +1380,24 @@ static void l2tp_session_unhash(struct l2tp_session *session) static void l2tp_tunnel_closeall(struct l2tp_tunnel *tunnel) { struct l2tp_session *session; - int hash; - spin_lock_bh(&tunnel->hlist_lock); + spin_lock_bh(&tunnel->list_lock); tunnel->acpt_newsess = false; - for (hash = 0; hash < L2TP_HASH_SIZE; hash++) { -again: - hlist_for_each_entry_rcu(session, &tunnel->session_hlist[hash], hlist) { - hlist_del_init_rcu(&session->hlist); - - spin_unlock_bh(&tunnel->hlist_lock); - l2tp_session_delete(session); - spin_lock_bh(&tunnel->hlist_lock); - - /* Now restart from the beginning of this hash - * chain. We always remove a session from the - * list so we are guaranteed to make forward - * progress. - */ - goto again; - } - } - spin_unlock_bh(&tunnel->hlist_lock); + list_for_each_entry(session, &tunnel->session_list, list) + l2tp_session_delete(session); + spin_unlock_bh(&tunnel->list_lock); } /* Tunnel socket destroy hook for UDP encapsulation */ static void l2tp_udp_encap_destroy(struct sock *sk) { - struct l2tp_tunnel *tunnel = l2tp_sk_to_tunnel(sk); + struct l2tp_tunnel *tunnel; - if (tunnel) + tunnel = l2tp_sk_to_tunnel(sk); + if (tunnel) { l2tp_tunnel_delete(tunnel); + l2tp_tunnel_put(tunnel); + } } static void l2tp_tunnel_remove(struct net *net, struct l2tp_tunnel *tunnel) @@ -1300,10 +1431,10 @@ static void l2tp_tunnel_del_work(struct work_struct *work) l2tp_tunnel_remove(tunnel->l2tp_net, tunnel); /* drop initial ref */ - l2tp_tunnel_dec_refcount(tunnel); + l2tp_tunnel_put(tunnel); /* drop workqueue ref */ - l2tp_tunnel_dec_refcount(tunnel); + l2tp_tunnel_put(tunnel); } /* Create a socket for the tunnel, if one isn't set up by @@ -1449,10 +1580,10 @@ int l2tp_tunnel_create(int fd, int version, u32 tunnel_id, u32 peer_tunnel_id, tunnel->tunnel_id = tunnel_id; tunnel->peer_tunnel_id = peer_tunnel_id; - tunnel->magic = L2TP_TUNNEL_MAGIC; sprintf(&tunnel->name[0], "tunl %u", tunnel_id); - spin_lock_init(&tunnel->hlist_lock); + spin_lock_init(&tunnel->list_lock); tunnel->acpt_newsess = true; + INIT_LIST_HEAD(&tunnel->session_list); tunnel->encap = encap; @@ -1462,8 +1593,6 @@ int l2tp_tunnel_create(int fd, int version, u32 tunnel_id, u32 peer_tunnel_id, /* Init delete workqueue struct */ INIT_WORK(&tunnel->del_work, l2tp_tunnel_del_work); - INIT_LIST_HEAD(&tunnel->list); - err = 0; err: if (tunnelp) @@ -1476,6 +1605,8 @@ EXPORT_SYMBOL_GPL(l2tp_tunnel_create); static int l2tp_validate_socket(const struct sock *sk, const struct net *net, enum l2tp_encap_type encap) { + struct l2tp_tunnel *tunnel; + if (!net_eq(sock_net(sk), net)) return -EINVAL; @@ -1489,9 +1620,15 @@ static int l2tp_validate_socket(const struct sock *sk, const struct net *net, (encap == L2TP_ENCAPTYPE_IP && sk->sk_protocol != IPPROTO_L2TP)) return -EPROTONOSUPPORT; - if (sk->sk_user_data) + if (encap == L2TP_ENCAPTYPE_UDP && sk->sk_user_data) return -EBUSY; + tunnel = l2tp_sk_to_tunnel(sk); + if (tunnel) { + l2tp_tunnel_put(tunnel); + return -EBUSY; + } + return 0; } @@ -1529,12 +1666,10 @@ int l2tp_tunnel_register(struct l2tp_tunnel *tunnel, struct net *net, ret = l2tp_validate_socket(sk, net, tunnel->encap); if (ret < 0) goto err_inval_sock; - rcu_assign_sk_user_data(sk, tunnel); write_unlock_bh(&sk->sk_callback_lock); if (tunnel->encap == L2TP_ENCAPTYPE_UDP) { struct udp_tunnel_sock_cfg udp_cfg = { - .sk_user_data = tunnel, .encap_type = UDP_ENCAP_L2TPINUDP, .encap_rcv = l2tp_udp_encap_recv, .encap_err_rcv = l2tp_udp_encap_err_recv, @@ -1544,8 +1679,6 @@ int l2tp_tunnel_register(struct l2tp_tunnel *tunnel, struct net *net, setup_udp_tunnel_sock(net, sock, &udp_cfg); } - tunnel->old_sk_destruct = sk->sk_destruct; - sk->sk_destruct = &l2tp_tunnel_destruct; sk->sk_allocation = GFP_ATOMIC; release_sock(sk); @@ -1584,7 +1717,7 @@ void l2tp_tunnel_delete(struct l2tp_tunnel *tunnel) { if (!test_and_set_bit(0, &tunnel->dead)) { trace_delete_tunnel(tunnel); - l2tp_tunnel_inc_refcount(tunnel); + refcount_inc(&tunnel->ref_count); queue_work(l2tp_wq, &tunnel->del_work); } } @@ -1592,23 +1725,37 @@ EXPORT_SYMBOL_GPL(l2tp_tunnel_delete); void l2tp_session_delete(struct l2tp_session *session) { - if (test_and_set_bit(0, &session->dead)) - return; + if (!test_and_set_bit(0, &session->dead)) { + trace_delete_session(session); + refcount_inc(&session->ref_count); + queue_work(l2tp_wq, &session->del_work); + } +} +EXPORT_SYMBOL_GPL(l2tp_session_delete); + +/* Workqueue session deletion function */ +static void l2tp_session_del_work(struct work_struct *work) +{ + struct l2tp_session *session = container_of(work, struct l2tp_session, + del_work); - trace_delete_session(session); l2tp_session_unhash(session); l2tp_session_queue_purge(session); if (session->session_close) (*session->session_close)(session); - l2tp_session_dec_refcount(session); + /* drop initial ref */ + l2tp_session_put(session); + + /* drop workqueue ref */ + l2tp_session_put(session); } -EXPORT_SYMBOL_GPL(l2tp_session_delete); /* We come here whenever a session's send_seq, cookie_len or * l2specific_type parameters are set. */ -void l2tp_session_set_header_len(struct l2tp_session *session, int version) +void l2tp_session_set_header_len(struct l2tp_session *session, int version, + enum l2tp_encap_type encap) { if (version == L2TP_HDR_VER_2) { session->hdr_len = 6; @@ -1617,7 +1764,7 @@ void l2tp_session_set_header_len(struct l2tp_session *session, int version) } else { session->hdr_len = 4 + session->cookie_len; session->hdr_len += l2tp_get_l2specific_len(session); - if (session->tunnel->encap == L2TP_ENCAPTYPE_UDP) + if (encap == L2TP_ENCAPTYPE_UDP) session->hdr_len += 4; } } @@ -1631,7 +1778,6 @@ struct l2tp_session *l2tp_session_create(int priv_size, struct l2tp_tunnel *tunn session = kzalloc(sizeof(*session) + priv_size, GFP_KERNEL); if (session) { session->magic = L2TP_SESSION_MAGIC; - session->tunnel = tunnel; session->session_id = session_id; session->peer_session_id = peer_session_id; @@ -1651,8 +1797,11 @@ struct l2tp_session *l2tp_session_create(int priv_size, struct l2tp_tunnel *tunn skb_queue_head_init(&session->reorder_q); + session->hlist_key = l2tp_v3_session_hashkey(tunnel->sock, session->session_id); INIT_HLIST_NODE(&session->hlist); - INIT_HLIST_NODE(&session->global_hlist); + INIT_LIST_HEAD(&session->clist); + INIT_LIST_HEAD(&session->list); + INIT_WORK(&session->del_work, l2tp_session_del_work); if (cfg) { session->pwtype = cfg->pw_type; @@ -1667,7 +1816,7 @@ struct l2tp_session *l2tp_session_create(int priv_size, struct l2tp_tunnel *tunn memcpy(&session->peer_cookie[0], &cfg->peer_cookie[0], cfg->peer_cookie_len); } - l2tp_session_set_header_len(session, tunnel->version); + l2tp_session_set_header_len(session, tunnel->version, tunnel->encap); refcount_set(&session->ref_count, 1); @@ -1685,25 +1834,22 @@ EXPORT_SYMBOL_GPL(l2tp_session_create); static __net_init int l2tp_init_net(struct net *net) { struct l2tp_net *pn = net_generic(net, l2tp_net_id); - int hash; idr_init(&pn->l2tp_tunnel_idr); spin_lock_init(&pn->l2tp_tunnel_idr_lock); - for (hash = 0; hash < L2TP_HASH_SIZE_2; hash++) - INIT_HLIST_HEAD(&pn->l2tp_session_hlist[hash]); - - spin_lock_init(&pn->l2tp_session_hlist_lock); + idr_init(&pn->l2tp_v2_session_idr); + idr_init(&pn->l2tp_v3_session_idr); + spin_lock_init(&pn->l2tp_session_idr_lock); return 0; } -static __net_exit void l2tp_exit_net(struct net *net) +static __net_exit void l2tp_pre_exit_net(struct net *net) { struct l2tp_net *pn = l2tp_pernet(net); struct l2tp_tunnel *tunnel = NULL; unsigned long tunnel_id, tmp; - int hash; rcu_read_lock_bh(); idr_for_each_entry_ul(&pn->l2tp_tunnel_idr, tunnel, tmp, tunnel_id) { @@ -1712,18 +1858,34 @@ static __net_exit void l2tp_exit_net(struct net *net) } rcu_read_unlock_bh(); - if (l2tp_wq) - flush_workqueue(l2tp_wq); - rcu_barrier(); + if (l2tp_wq) { + /* Run all TUNNEL_DELETE work items just queued. */ + __flush_workqueue(l2tp_wq); + + /* Each TUNNEL_DELETE work item will queue a SESSION_DELETE + * work item for each session in the tunnel. Flush the + * workqueue again to process these. + */ + __flush_workqueue(l2tp_wq); + } +} + +static __net_exit void l2tp_exit_net(struct net *net) +{ + struct l2tp_net *pn = l2tp_pernet(net); - for (hash = 0; hash < L2TP_HASH_SIZE_2; hash++) - WARN_ON_ONCE(!hlist_empty(&pn->l2tp_session_hlist[hash])); + WARN_ON_ONCE(!idr_is_empty(&pn->l2tp_v2_session_idr)); + idr_destroy(&pn->l2tp_v2_session_idr); + WARN_ON_ONCE(!idr_is_empty(&pn->l2tp_v3_session_idr)); + idr_destroy(&pn->l2tp_v3_session_idr); + WARN_ON_ONCE(!idr_is_empty(&pn->l2tp_tunnel_idr)); idr_destroy(&pn->l2tp_tunnel_idr); } static struct pernet_operations l2tp_net_ops = { .init = l2tp_init_net, .exit = l2tp_exit_net, + .pre_exit = l2tp_pre_exit_net, .id = &l2tp_net_id, .size = sizeof(struct l2tp_net), }; diff --git a/net/l2tp/l2tp_core.h b/net/l2tp/l2tp_core.h index 91ebf0a3f499..ffd8ced3a51f 100644 --- a/net/l2tp/l2tp_core.h +++ b/net/l2tp/l2tp_core.h @@ -16,17 +16,8 @@ #endif /* Random numbers used for internal consistency checks of tunnel and session structures */ -#define L2TP_TUNNEL_MAGIC 0x42114DDA #define L2TP_SESSION_MAGIC 0x0C04EB7D -/* Per tunnel session hash table size */ -#define L2TP_HASH_BITS 4 -#define L2TP_HASH_SIZE BIT(L2TP_HASH_BITS) - -/* System-wide session hash table size */ -#define L2TP_HASH_BITS_2 8 -#define L2TP_HASH_SIZE_2 BIT(L2TP_HASH_BITS_2) - struct sk_buff; struct l2tp_stats { @@ -61,15 +52,21 @@ struct l2tp_session_cfg { char *ifname; }; +struct l2tp_session_coll_list { + spinlock_t lock; /* for access to list */ + struct list_head list; + refcount_t ref_count; +}; + /* Represents a session (pseudowire) instance. * Tracks runtime state including cookies, dataplane packet sequencing, and IO statistics. - * Is linked into a per-tunnel session hashlist; and in the case of an L2TPv3 session into - * an additional per-net ("global") hashlist. + * Is linked into a per-tunnel session list and a per-net ("global") IDR tree. */ #define L2TP_SESSION_NAME_MAX 32 struct l2tp_session { int magic; /* should be L2TP_SESSION_MAGIC */ long dead; + struct rcu_head rcu; struct l2tp_tunnel *tunnel; /* back pointer to tunnel context */ u32 session_id; @@ -88,8 +85,12 @@ struct l2tp_session { u32 nr_oos; /* NR of last OOS packet */ int nr_oos_count; /* for OOS recovery */ int nr_oos_count_max; - struct hlist_node hlist; /* hash list node */ + struct list_head list; /* per-tunnel list node */ refcount_t ref_count; + struct hlist_node hlist; /* per-net session hlist */ + unsigned long hlist_key; /* key for session hlist */ + struct l2tp_session_coll_list *coll_list; /* session collision list */ + struct list_head clist; /* for coll_list */ char name[L2TP_SESSION_NAME_MAX]; /* for logging */ char ifname[IFNAMSIZ]; @@ -102,7 +103,7 @@ struct l2tp_session { int reorder_skip; /* set if skip to next nr */ enum l2tp_pwtype pwtype; struct l2tp_stats stats; - struct hlist_node global_hlist; /* global hash list node */ + struct work_struct del_work; /* Session receive handler for data packets. * Each pseudowire implementation should implement this callback in order to @@ -114,7 +115,7 @@ struct l2tp_session { /* Session close handler. * Each pseudowire implementation may implement this callback in order to carry * out pseudowire-specific shutdown actions. - * The callback is called by core after unhashing the session and purging its + * The callback is called by core after unlisting the session and purging its * reorder queue. */ void (*session_close)(struct l2tp_session *session); @@ -150,22 +151,19 @@ struct l2tp_tunnel_cfg { /* Represents a tunnel instance. * Tracks runtime state including IO statistics. * Holds the tunnel socket (either passed from userspace or directly created by the kernel). - * Maintains a hashlist of sessions belonging to the tunnel instance. + * Maintains a list of sessions belonging to the tunnel instance. * Is linked into a per-net list of tunnels. */ #define L2TP_TUNNEL_NAME_MAX 20 struct l2tp_tunnel { - int magic; /* Should be L2TP_TUNNEL_MAGIC */ - unsigned long dead; struct rcu_head rcu; - spinlock_t hlist_lock; /* write-protection for session_hlist */ + spinlock_t list_lock; /* write-protection for session_list */ bool acpt_newsess; /* indicates whether this tunnel accepts - * new sessions. Protected by hlist_lock. + * new sessions. Protected by list_lock. */ - struct hlist_head session_hlist[L2TP_HASH_SIZE]; - /* hashed list of sessions, hashed by id */ + struct list_head session_list; /* list of sessions */ u32 tunnel_id; u32 peer_tunnel_id; int version; /* 2=>L2TPv2, 3=>L2TPv3 */ @@ -174,11 +172,9 @@ struct l2tp_tunnel { enum l2tp_encap_type encap; struct l2tp_stats stats; - struct list_head list; /* list node on per-namespace list of tunnels */ struct net *l2tp_net; /* the net we belong to */ refcount_t ref_count; - void (*old_sk_destruct)(struct sock *sk); struct sock *sock; /* parent socket */ int fd; /* parent fd, if tunnel socket was created * by userspace @@ -213,22 +209,22 @@ static inline void *l2tp_session_priv(struct l2tp_session *session) } /* Tunnel and session refcounts */ -void l2tp_tunnel_inc_refcount(struct l2tp_tunnel *tunnel); -void l2tp_tunnel_dec_refcount(struct l2tp_tunnel *tunnel); -void l2tp_session_inc_refcount(struct l2tp_session *session); -void l2tp_session_dec_refcount(struct l2tp_session *session); +void l2tp_tunnel_put(struct l2tp_tunnel *tunnel); +void l2tp_session_put(struct l2tp_session *session); /* Tunnel and session lookup. * These functions take a reference on the instances they return, so * the caller must ensure that the reference is dropped appropriately. */ struct l2tp_tunnel *l2tp_tunnel_get(const struct net *net, u32 tunnel_id); -struct l2tp_tunnel *l2tp_tunnel_get_nth(const struct net *net, int nth); -struct l2tp_session *l2tp_tunnel_get_session(struct l2tp_tunnel *tunnel, - u32 session_id); - -struct l2tp_session *l2tp_session_get(const struct net *net, u32 session_id); -struct l2tp_session *l2tp_session_get_nth(struct l2tp_tunnel *tunnel, int nth); +struct l2tp_tunnel *l2tp_tunnel_get_next(const struct net *net, unsigned long *key); + +struct l2tp_session *l2tp_v3_session_get(const struct net *net, struct sock *sk, u32 session_id); +struct l2tp_session *l2tp_v2_session_get(const struct net *net, u16 tunnel_id, u16 session_id); +struct l2tp_session *l2tp_session_get(const struct net *net, struct sock *sk, int pver, + u32 tunnel_id, u32 session_id); +struct l2tp_session *l2tp_session_get_next(const struct net *net, struct sock *sk, int pver, + u32 tunnel_id, unsigned long *key); struct l2tp_session *l2tp_session_get_by_ifname(const struct net *net, const char *ifname); @@ -261,7 +257,8 @@ void l2tp_recv_common(struct l2tp_session *session, struct sk_buff *skb, int l2tp_udp_encap_recv(struct sock *sk, struct sk_buff *skb); /* Transmit path helpers for sending packets over the tunnel socket. */ -void l2tp_session_set_header_len(struct l2tp_session *session, int version); +void l2tp_session_set_header_len(struct l2tp_session *session, int version, + enum l2tp_encap_type encap); int l2tp_xmit_skb(struct l2tp_session *session, struct sk_buff *skb); /* Pseudowire management. @@ -274,10 +271,7 @@ void l2tp_nl_unregister_ops(enum l2tp_pwtype pw_type); /* IOCTL helper for IP encap modules. */ int l2tp_ioctl(struct sock *sk, int cmd, int *karg); -/* Extract the tunnel structure from a socket's sk_user_data pointer, - * validating the tunnel magic feather. - */ -struct l2tp_tunnel *l2tp_sk_to_tunnel(struct sock *sk); +struct l2tp_tunnel *l2tp_sk_to_tunnel(const struct sock *sk); static inline int l2tp_get_l2specific_len(struct l2tp_session *session) { diff --git a/net/l2tp/l2tp_debugfs.c b/net/l2tp/l2tp_debugfs.c index 4595b56d175d..2d0c8275a3a8 100644 --- a/net/l2tp/l2tp_debugfs.c +++ b/net/l2tp/l2tp_debugfs.c @@ -34,8 +34,8 @@ static struct dentry *rootdir; struct l2tp_dfs_seq_data { struct net *net; netns_tracker ns_tracker; - int tunnel_idx; /* current tunnel */ - int session_idx; /* index of session within current tunnel */ + unsigned long tkey; /* lookup key of current tunnel */ + unsigned long skey; /* lookup key of current session */ struct l2tp_tunnel *tunnel; struct l2tp_session *session; /* NULL means get next tunnel */ }; @@ -44,23 +44,25 @@ static void l2tp_dfs_next_tunnel(struct l2tp_dfs_seq_data *pd) { /* Drop reference taken during previous invocation */ if (pd->tunnel) - l2tp_tunnel_dec_refcount(pd->tunnel); + l2tp_tunnel_put(pd->tunnel); - pd->tunnel = l2tp_tunnel_get_nth(pd->net, pd->tunnel_idx); - pd->tunnel_idx++; + pd->tunnel = l2tp_tunnel_get_next(pd->net, &pd->tkey); + pd->tkey++; } static void l2tp_dfs_next_session(struct l2tp_dfs_seq_data *pd) { /* Drop reference taken during previous invocation */ if (pd->session) - l2tp_session_dec_refcount(pd->session); + l2tp_session_put(pd->session); - pd->session = l2tp_session_get_nth(pd->tunnel, pd->session_idx); - pd->session_idx++; + pd->session = l2tp_session_get_next(pd->net, pd->tunnel->sock, + pd->tunnel->version, + pd->tunnel->tunnel_id, &pd->skey); + pd->skey++; if (!pd->session) { - pd->session_idx = 0; + pd->skey = 0; l2tp_dfs_next_tunnel(pd); } } @@ -109,11 +111,11 @@ static void l2tp_dfs_seq_stop(struct seq_file *p, void *v) * or l2tp_dfs_next_tunnel(). */ if (pd->session) { - l2tp_session_dec_refcount(pd->session); + l2tp_session_put(pd->session); pd->session = NULL; } if (pd->tunnel) { - l2tp_tunnel_dec_refcount(pd->tunnel); + l2tp_tunnel_put(pd->tunnel); pd->tunnel = NULL; } } @@ -123,17 +125,14 @@ static void l2tp_dfs_seq_tunnel_show(struct seq_file *m, void *v) struct l2tp_tunnel *tunnel = v; struct l2tp_session *session; int session_count = 0; - int hash; rcu_read_lock_bh(); - for (hash = 0; hash < L2TP_HASH_SIZE; hash++) { - hlist_for_each_entry_rcu(session, &tunnel->session_hlist[hash], hlist) { - /* Session ID of zero is a dummy/reserved value used by pppol2tp */ - if (session->session_id == 0) - continue; + list_for_each_entry_rcu(session, &tunnel->session_list, list) { + /* Session ID of zero is a dummy/reserved value used by pppol2tp */ + if (session->session_id == 0) + continue; - session_count++; - } + session_count++; } rcu_read_unlock_bh(); diff --git a/net/l2tp/l2tp_eth.c b/net/l2tp/l2tp_eth.c index 8ba00ad433c2..d692b902e120 100644 --- a/net/l2tp/l2tp_eth.c +++ b/net/l2tp/l2tp_eth.c @@ -72,31 +72,19 @@ static netdev_tx_t l2tp_eth_dev_xmit(struct sk_buff *skb, struct net_device *dev unsigned int len = skb->len; int ret = l2tp_xmit_skb(session, skb); - if (likely(ret == NET_XMIT_SUCCESS)) { - DEV_STATS_ADD(dev, tx_bytes, len); - DEV_STATS_INC(dev, tx_packets); - } else { + if (likely(ret == NET_XMIT_SUCCESS)) + dev_sw_netstats_tx_add(dev, 1, len); + else DEV_STATS_INC(dev, tx_dropped); - } - return NETDEV_TX_OK; -} -static void l2tp_eth_get_stats64(struct net_device *dev, - struct rtnl_link_stats64 *stats) -{ - stats->tx_bytes = DEV_STATS_READ(dev, tx_bytes); - stats->tx_packets = DEV_STATS_READ(dev, tx_packets); - stats->tx_dropped = DEV_STATS_READ(dev, tx_dropped); - stats->rx_bytes = DEV_STATS_READ(dev, rx_bytes); - stats->rx_packets = DEV_STATS_READ(dev, rx_packets); - stats->rx_errors = DEV_STATS_READ(dev, rx_errors); + return NETDEV_TX_OK; } static const struct net_device_ops l2tp_eth_netdev_ops = { .ndo_init = l2tp_eth_dev_init, .ndo_uninit = l2tp_eth_dev_uninit, .ndo_start_xmit = l2tp_eth_dev_xmit, - .ndo_get_stats64 = l2tp_eth_get_stats64, + .ndo_get_stats64 = dev_get_tstats64, .ndo_set_mac_address = eth_mac_addr, }; @@ -109,9 +97,10 @@ static void l2tp_eth_dev_setup(struct net_device *dev) SET_NETDEV_DEVTYPE(dev, &l2tpeth_type); ether_setup(dev); dev->priv_flags &= ~IFF_TX_SKB_SHARING; - dev->features |= NETIF_F_LLTX; + dev->lltx = true; dev->netdev_ops = &l2tp_eth_netdev_ops; dev->needs_free_netdev = true; + dev->pcpu_stat_type = NETDEV_PCPU_STAT_TSTATS; } static void l2tp_eth_dev_recv(struct l2tp_session *session, struct sk_buff *skb, int data_len) @@ -138,12 +127,11 @@ static void l2tp_eth_dev_recv(struct l2tp_session *session, struct sk_buff *skb, if (!dev) goto error_rcu; - if (dev_forward_skb(dev, skb) == NET_RX_SUCCESS) { - DEV_STATS_INC(dev, rx_packets); - DEV_STATS_ADD(dev, rx_bytes, data_len); - } else { + if (dev_forward_skb(dev, skb) == NET_RX_SUCCESS) + dev_sw_netstats_rx_add(dev, data_len); + else DEV_STATS_INC(dev, rx_errors); - } + rcu_read_unlock(); return; @@ -283,7 +271,7 @@ static int l2tp_eth_create(struct net *net, struct l2tp_tunnel *tunnel, spriv = l2tp_session_priv(session); - l2tp_session_inc_refcount(session); + refcount_inc(&session->ref_count); rtnl_lock(); @@ -301,7 +289,7 @@ static int l2tp_eth_create(struct net *net, struct l2tp_tunnel *tunnel, if (rc < 0) { rtnl_unlock(); l2tp_session_delete(session); - l2tp_session_dec_refcount(session); + l2tp_session_put(session); free_netdev(dev); return rc; @@ -312,17 +300,17 @@ static int l2tp_eth_create(struct net *net, struct l2tp_tunnel *tunnel, rtnl_unlock(); - l2tp_session_dec_refcount(session); + l2tp_session_put(session); __module_get(THIS_MODULE); return 0; err_sess_dev: - l2tp_session_dec_refcount(session); + l2tp_session_put(session); free_netdev(dev); err_sess: - kfree(session); + l2tp_session_put(session); err: return rc; } diff --git a/net/l2tp/l2tp_ip.c b/net/l2tp/l2tp_ip.c index 19c8cc5289d5..4bc24fddfd52 100644 --- a/net/l2tp/l2tp_ip.c +++ b/net/l2tp/l2tp_ip.c @@ -22,9 +22,19 @@ #include <net/tcp_states.h> #include <net/protocol.h> #include <net/xfrm.h> +#include <net/net_namespace.h> +#include <net/netns/generic.h> #include "l2tp_core.h" +/* per-net private data for this module */ +static unsigned int l2tp_ip_net_id; +struct l2tp_ip_net { + rwlock_t l2tp_ip_lock; + struct hlist_head l2tp_ip_table; + struct hlist_head l2tp_ip_bind_table; +}; + struct l2tp_ip_sock { /* inet_sock has to be the first member of l2tp_ip_sock */ struct inet_sock inet; @@ -33,21 +43,23 @@ struct l2tp_ip_sock { u32 peer_conn_id; }; -static DEFINE_RWLOCK(l2tp_ip_lock); -static struct hlist_head l2tp_ip_table; -static struct hlist_head l2tp_ip_bind_table; - -static inline struct l2tp_ip_sock *l2tp_ip_sk(const struct sock *sk) +static struct l2tp_ip_sock *l2tp_ip_sk(const struct sock *sk) { return (struct l2tp_ip_sock *)sk; } +static struct l2tp_ip_net *l2tp_ip_pernet(const struct net *net) +{ + return net_generic(net, l2tp_ip_net_id); +} + static struct sock *__l2tp_ip_bind_lookup(const struct net *net, __be32 laddr, __be32 raddr, int dif, u32 tunnel_id) { + struct l2tp_ip_net *pn = l2tp_ip_pernet(net); struct sock *sk; - sk_for_each_bound(sk, &l2tp_ip_bind_table) { + sk_for_each_bound(sk, &pn->l2tp_ip_bind_table) { const struct l2tp_ip_sock *l2tp = l2tp_ip_sk(sk); const struct inet_sock *inet = inet_sk(sk); int bound_dev_if; @@ -113,6 +125,7 @@ found: static int l2tp_ip_recv(struct sk_buff *skb) { struct net *net = dev_net(skb->dev); + struct l2tp_ip_net *pn; struct sock *sk; u32 session_id; u32 tunnel_id; @@ -121,6 +134,8 @@ static int l2tp_ip_recv(struct sk_buff *skb) struct l2tp_tunnel *tunnel = NULL; struct iphdr *iph; + pn = l2tp_ip_pernet(net); + if (!pskb_may_pull(skb, 4)) goto discard; @@ -140,7 +155,7 @@ static int l2tp_ip_recv(struct sk_buff *skb) } /* Ok, this is a data packet. Lookup the session. */ - session = l2tp_session_get(net, session_id); + session = l2tp_v3_session_get(net, NULL, session_id); if (!session) goto discard; @@ -152,7 +167,7 @@ static int l2tp_ip_recv(struct sk_buff *skb) goto discard_sess; l2tp_recv_common(session, skb, ptr, optr, 0, skb->len); - l2tp_session_dec_refcount(session); + l2tp_session_put(session); return 0; @@ -167,15 +182,15 @@ pass_up: tunnel_id = ntohl(*(__be32 *)&skb->data[4]); iph = (struct iphdr *)skb_network_header(skb); - read_lock_bh(&l2tp_ip_lock); + read_lock_bh(&pn->l2tp_ip_lock); sk = __l2tp_ip_bind_lookup(net, iph->daddr, iph->saddr, inet_iif(skb), tunnel_id); if (!sk) { - read_unlock_bh(&l2tp_ip_lock); + read_unlock_bh(&pn->l2tp_ip_lock); goto discard; } sock_hold(sk); - read_unlock_bh(&l2tp_ip_lock); + read_unlock_bh(&pn->l2tp_ip_lock); if (!xfrm4_policy_check(sk, XFRM_POLICY_IN, skb)) goto discard_put; @@ -185,7 +200,7 @@ pass_up: return sk_receive_skb(sk, skb, 1); discard_sess: - l2tp_session_dec_refcount(session); + l2tp_session_put(session); goto discard; discard_put: @@ -198,21 +213,25 @@ discard: static int l2tp_ip_hash(struct sock *sk) { + struct l2tp_ip_net *pn = l2tp_ip_pernet(sock_net(sk)); + if (sk_unhashed(sk)) { - write_lock_bh(&l2tp_ip_lock); - sk_add_node(sk, &l2tp_ip_table); - write_unlock_bh(&l2tp_ip_lock); + write_lock_bh(&pn->l2tp_ip_lock); + sk_add_node(sk, &pn->l2tp_ip_table); + write_unlock_bh(&pn->l2tp_ip_lock); } return 0; } static void l2tp_ip_unhash(struct sock *sk) { + struct l2tp_ip_net *pn = l2tp_ip_pernet(sock_net(sk)); + if (sk_unhashed(sk)) return; - write_lock_bh(&l2tp_ip_lock); + write_lock_bh(&pn->l2tp_ip_lock); sk_del_node_init(sk); - write_unlock_bh(&l2tp_ip_lock); + write_unlock_bh(&pn->l2tp_ip_lock); } static int l2tp_ip_open(struct sock *sk) @@ -226,23 +245,26 @@ static int l2tp_ip_open(struct sock *sk) static void l2tp_ip_close(struct sock *sk, long timeout) { - write_lock_bh(&l2tp_ip_lock); + struct l2tp_ip_net *pn = l2tp_ip_pernet(sock_net(sk)); + + write_lock_bh(&pn->l2tp_ip_lock); hlist_del_init(&sk->sk_bind_node); sk_del_node_init(sk); - write_unlock_bh(&l2tp_ip_lock); + write_unlock_bh(&pn->l2tp_ip_lock); sk_common_release(sk); } static void l2tp_ip_destroy_sock(struct sock *sk) { - struct l2tp_tunnel *tunnel = l2tp_sk_to_tunnel(sk); - struct sk_buff *skb; + struct l2tp_tunnel *tunnel; - while ((skb = __skb_dequeue_tail(&sk->sk_write_queue)) != NULL) - kfree_skb(skb); + __skb_queue_purge(&sk->sk_write_queue); - if (tunnel) + tunnel = l2tp_sk_to_tunnel(sk); + if (tunnel) { l2tp_tunnel_delete(tunnel); + l2tp_tunnel_put(tunnel); + } } static int l2tp_ip_bind(struct sock *sk, struct sockaddr *uaddr, int addr_len) @@ -250,6 +272,7 @@ static int l2tp_ip_bind(struct sock *sk, struct sockaddr *uaddr, int addr_len) struct inet_sock *inet = inet_sk(sk); struct sockaddr_l2tpip *addr = (struct sockaddr_l2tpip *)uaddr; struct net *net = sock_net(sk); + struct l2tp_ip_net *pn; int ret; int chk_addr_ret; @@ -280,10 +303,11 @@ static int l2tp_ip_bind(struct sock *sk, struct sockaddr *uaddr, int addr_len) if (chk_addr_ret == RTN_MULTICAST || chk_addr_ret == RTN_BROADCAST) inet->inet_saddr = 0; /* Use device */ - write_lock_bh(&l2tp_ip_lock); + pn = l2tp_ip_pernet(net); + write_lock_bh(&pn->l2tp_ip_lock); if (__l2tp_ip_bind_lookup(net, addr->l2tp_addr.s_addr, 0, sk->sk_bound_dev_if, addr->l2tp_conn_id)) { - write_unlock_bh(&l2tp_ip_lock); + write_unlock_bh(&pn->l2tp_ip_lock); ret = -EADDRINUSE; goto out; } @@ -291,9 +315,9 @@ static int l2tp_ip_bind(struct sock *sk, struct sockaddr *uaddr, int addr_len) sk_dst_reset(sk); l2tp_ip_sk(sk)->conn_id = addr->l2tp_conn_id; - sk_add_bind_node(sk, &l2tp_ip_bind_table); + sk_add_bind_node(sk, &pn->l2tp_ip_bind_table); sk_del_node_init(sk); - write_unlock_bh(&l2tp_ip_lock); + write_unlock_bh(&pn->l2tp_ip_lock); ret = 0; sock_reset_flag(sk, SOCK_ZAPPED); @@ -307,6 +331,7 @@ out: static int l2tp_ip_connect(struct sock *sk, struct sockaddr *uaddr, int addr_len) { struct sockaddr_l2tpip *lsa = (struct sockaddr_l2tpip *)uaddr; + struct l2tp_ip_net *pn = l2tp_ip_pernet(sock_net(sk)); int rc; if (addr_len < sizeof(*lsa)) @@ -329,10 +354,10 @@ static int l2tp_ip_connect(struct sock *sk, struct sockaddr *uaddr, int addr_len l2tp_ip_sk(sk)->peer_conn_id = lsa->l2tp_conn_id; - write_lock_bh(&l2tp_ip_lock); + write_lock_bh(&pn->l2tp_ip_lock); hlist_del_init(&sk->sk_bind_node); - sk_add_bind_node(sk, &l2tp_ip_bind_table); - write_unlock_bh(&l2tp_ip_lock); + sk_add_bind_node(sk, &pn->l2tp_ip_bind_table); + write_unlock_bh(&pn->l2tp_ip_lock); out_sk: release_sock(sk); @@ -637,25 +662,58 @@ static struct net_protocol l2tp_ip_protocol __read_mostly = { .handler = l2tp_ip_recv, }; +static __net_init int l2tp_ip_init_net(struct net *net) +{ + struct l2tp_ip_net *pn = net_generic(net, l2tp_ip_net_id); + + rwlock_init(&pn->l2tp_ip_lock); + INIT_HLIST_HEAD(&pn->l2tp_ip_table); + INIT_HLIST_HEAD(&pn->l2tp_ip_bind_table); + return 0; +} + +static __net_exit void l2tp_ip_exit_net(struct net *net) +{ + struct l2tp_ip_net *pn = l2tp_ip_pernet(net); + + write_lock_bh(&pn->l2tp_ip_lock); + WARN_ON_ONCE(hlist_count_nodes(&pn->l2tp_ip_table) != 0); + WARN_ON_ONCE(hlist_count_nodes(&pn->l2tp_ip_bind_table) != 0); + write_unlock_bh(&pn->l2tp_ip_lock); +} + +static struct pernet_operations l2tp_ip_net_ops = { + .init = l2tp_ip_init_net, + .exit = l2tp_ip_exit_net, + .id = &l2tp_ip_net_id, + .size = sizeof(struct l2tp_ip_net), +}; + static int __init l2tp_ip_init(void) { int err; pr_info("L2TP IP encapsulation support (L2TPv3)\n"); + err = register_pernet_device(&l2tp_ip_net_ops); + if (err) + goto out; + err = proto_register(&l2tp_ip_prot, 1); if (err != 0) - goto out; + goto out1; err = inet_add_protocol(&l2tp_ip_protocol, IPPROTO_L2TP); if (err) - goto out1; + goto out2; inet_register_protosw(&l2tp_ip_protosw); return 0; -out1: +out2: proto_unregister(&l2tp_ip_prot); +out1: + unregister_pernet_device(&l2tp_ip_net_ops); out: return err; } @@ -665,6 +723,7 @@ static void __exit l2tp_ip_exit(void) inet_unregister_protosw(&l2tp_ip_protosw); inet_del_protocol(&l2tp_ip_protocol, IPPROTO_L2TP); proto_unregister(&l2tp_ip_prot); + unregister_pernet_device(&l2tp_ip_net_ops); } module_init(l2tp_ip_init); diff --git a/net/l2tp/l2tp_ip6.c b/net/l2tp/l2tp_ip6.c index 8780ec64f376..f4c1da070826 100644 --- a/net/l2tp/l2tp_ip6.c +++ b/net/l2tp/l2tp_ip6.c @@ -22,6 +22,8 @@ #include <net/tcp_states.h> #include <net/protocol.h> #include <net/xfrm.h> +#include <net/net_namespace.h> +#include <net/netns/generic.h> #include <net/transp_v6.h> #include <net/addrconf.h> @@ -29,6 +31,14 @@ #include "l2tp_core.h" +/* per-net private data for this module */ +static unsigned int l2tp_ip6_net_id; +struct l2tp_ip6_net { + rwlock_t l2tp_ip6_lock; + struct hlist_head l2tp_ip6_table; + struct hlist_head l2tp_ip6_bind_table; +}; + struct l2tp_ip6_sock { /* inet_sock has to be the first member of l2tp_ip6_sock */ struct inet_sock inet; @@ -39,23 +49,25 @@ struct l2tp_ip6_sock { struct ipv6_pinfo inet6; }; -static DEFINE_RWLOCK(l2tp_ip6_lock); -static struct hlist_head l2tp_ip6_table; -static struct hlist_head l2tp_ip6_bind_table; - -static inline struct l2tp_ip6_sock *l2tp_ip6_sk(const struct sock *sk) +static struct l2tp_ip6_sock *l2tp_ip6_sk(const struct sock *sk) { return (struct l2tp_ip6_sock *)sk; } +static struct l2tp_ip6_net *l2tp_ip6_pernet(const struct net *net) +{ + return net_generic(net, l2tp_ip6_net_id); +} + static struct sock *__l2tp_ip6_bind_lookup(const struct net *net, const struct in6_addr *laddr, const struct in6_addr *raddr, int dif, u32 tunnel_id) { + struct l2tp_ip6_net *pn = l2tp_ip6_pernet(net); struct sock *sk; - sk_for_each_bound(sk, &l2tp_ip6_bind_table) { + sk_for_each_bound(sk, &pn->l2tp_ip6_bind_table) { const struct in6_addr *sk_laddr = inet6_rcv_saddr(sk); const struct in6_addr *sk_raddr = &sk->sk_v6_daddr; const struct l2tp_ip6_sock *l2tp = l2tp_ip6_sk(sk); @@ -123,6 +135,7 @@ found: static int l2tp_ip6_recv(struct sk_buff *skb) { struct net *net = dev_net(skb->dev); + struct l2tp_ip6_net *pn; struct sock *sk; u32 session_id; u32 tunnel_id; @@ -131,6 +144,8 @@ static int l2tp_ip6_recv(struct sk_buff *skb) struct l2tp_tunnel *tunnel = NULL; struct ipv6hdr *iph; + pn = l2tp_ip6_pernet(net); + if (!pskb_may_pull(skb, 4)) goto discard; @@ -150,7 +165,7 @@ static int l2tp_ip6_recv(struct sk_buff *skb) } /* Ok, this is a data packet. Lookup the session. */ - session = l2tp_session_get(net, session_id); + session = l2tp_v3_session_get(net, NULL, session_id); if (!session) goto discard; @@ -162,7 +177,7 @@ static int l2tp_ip6_recv(struct sk_buff *skb) goto discard_sess; l2tp_recv_common(session, skb, ptr, optr, 0, skb->len); - l2tp_session_dec_refcount(session); + l2tp_session_put(session); return 0; @@ -177,15 +192,15 @@ pass_up: tunnel_id = ntohl(*(__be32 *)&skb->data[4]); iph = ipv6_hdr(skb); - read_lock_bh(&l2tp_ip6_lock); + read_lock_bh(&pn->l2tp_ip6_lock); sk = __l2tp_ip6_bind_lookup(net, &iph->daddr, &iph->saddr, inet6_iif(skb), tunnel_id); if (!sk) { - read_unlock_bh(&l2tp_ip6_lock); + read_unlock_bh(&pn->l2tp_ip6_lock); goto discard; } sock_hold(sk); - read_unlock_bh(&l2tp_ip6_lock); + read_unlock_bh(&pn->l2tp_ip6_lock); if (!xfrm6_policy_check(sk, XFRM_POLICY_IN, skb)) goto discard_put; @@ -195,7 +210,7 @@ pass_up: return sk_receive_skb(sk, skb, 1); discard_sess: - l2tp_session_dec_refcount(session); + l2tp_session_put(session); goto discard; discard_put: @@ -208,21 +223,25 @@ discard: static int l2tp_ip6_hash(struct sock *sk) { + struct l2tp_ip6_net *pn = l2tp_ip6_pernet(sock_net(sk)); + if (sk_unhashed(sk)) { - write_lock_bh(&l2tp_ip6_lock); - sk_add_node(sk, &l2tp_ip6_table); - write_unlock_bh(&l2tp_ip6_lock); + write_lock_bh(&pn->l2tp_ip6_lock); + sk_add_node(sk, &pn->l2tp_ip6_table); + write_unlock_bh(&pn->l2tp_ip6_lock); } return 0; } static void l2tp_ip6_unhash(struct sock *sk) { + struct l2tp_ip6_net *pn = l2tp_ip6_pernet(sock_net(sk)); + if (sk_unhashed(sk)) return; - write_lock_bh(&l2tp_ip6_lock); + write_lock_bh(&pn->l2tp_ip6_lock); sk_del_node_init(sk); - write_unlock_bh(&l2tp_ip6_lock); + write_unlock_bh(&pn->l2tp_ip6_lock); } static int l2tp_ip6_open(struct sock *sk) @@ -236,24 +255,29 @@ static int l2tp_ip6_open(struct sock *sk) static void l2tp_ip6_close(struct sock *sk, long timeout) { - write_lock_bh(&l2tp_ip6_lock); + struct l2tp_ip6_net *pn = l2tp_ip6_pernet(sock_net(sk)); + + write_lock_bh(&pn->l2tp_ip6_lock); hlist_del_init(&sk->sk_bind_node); sk_del_node_init(sk); - write_unlock_bh(&l2tp_ip6_lock); + write_unlock_bh(&pn->l2tp_ip6_lock); sk_common_release(sk); } static void l2tp_ip6_destroy_sock(struct sock *sk) { - struct l2tp_tunnel *tunnel = l2tp_sk_to_tunnel(sk); + struct l2tp_tunnel *tunnel; lock_sock(sk); ip6_flush_pending_frames(sk); release_sock(sk); - if (tunnel) + tunnel = l2tp_sk_to_tunnel(sk); + if (tunnel) { l2tp_tunnel_delete(tunnel); + l2tp_tunnel_put(tunnel); + } } static int l2tp_ip6_bind(struct sock *sk, struct sockaddr *uaddr, int addr_len) @@ -262,11 +286,14 @@ static int l2tp_ip6_bind(struct sock *sk, struct sockaddr *uaddr, int addr_len) struct ipv6_pinfo *np = inet6_sk(sk); struct sockaddr_l2tpip6 *addr = (struct sockaddr_l2tpip6 *)uaddr; struct net *net = sock_net(sk); + struct l2tp_ip6_net *pn; __be32 v4addr = 0; int bound_dev_if; int addr_type; int err; + pn = l2tp_ip6_pernet(net); + if (addr->l2tp_family != AF_INET6) return -EINVAL; if (addr_len < sizeof(*addr)) @@ -324,10 +351,10 @@ static int l2tp_ip6_bind(struct sock *sk, struct sockaddr *uaddr, int addr_len) } rcu_read_unlock(); - write_lock_bh(&l2tp_ip6_lock); + write_lock_bh(&pn->l2tp_ip6_lock); if (__l2tp_ip6_bind_lookup(net, &addr->l2tp_addr, NULL, bound_dev_if, addr->l2tp_conn_id)) { - write_unlock_bh(&l2tp_ip6_lock); + write_unlock_bh(&pn->l2tp_ip6_lock); err = -EADDRINUSE; goto out_unlock; } @@ -340,9 +367,9 @@ static int l2tp_ip6_bind(struct sock *sk, struct sockaddr *uaddr, int addr_len) l2tp_ip6_sk(sk)->conn_id = addr->l2tp_conn_id; - sk_add_bind_node(sk, &l2tp_ip6_bind_table); + sk_add_bind_node(sk, &pn->l2tp_ip6_bind_table); sk_del_node_init(sk); - write_unlock_bh(&l2tp_ip6_lock); + write_unlock_bh(&pn->l2tp_ip6_lock); sock_reset_flag(sk, SOCK_ZAPPED); release_sock(sk); @@ -364,6 +391,7 @@ static int l2tp_ip6_connect(struct sock *sk, struct sockaddr *uaddr, struct in6_addr *daddr; int addr_type; int rc; + struct l2tp_ip6_net *pn; if (addr_len < sizeof(*lsa)) return -EINVAL; @@ -395,10 +423,11 @@ static int l2tp_ip6_connect(struct sock *sk, struct sockaddr *uaddr, l2tp_ip6_sk(sk)->peer_conn_id = lsa->l2tp_conn_id; - write_lock_bh(&l2tp_ip6_lock); + pn = l2tp_ip6_pernet(sock_net(sk)); + write_lock_bh(&pn->l2tp_ip6_lock); hlist_del_init(&sk->sk_bind_node); - sk_add_bind_node(sk, &l2tp_ip6_bind_table); - write_unlock_bh(&l2tp_ip6_lock); + sk_add_bind_node(sk, &pn->l2tp_ip6_bind_table); + write_unlock_bh(&pn->l2tp_ip6_lock); out_sk: release_sock(sk); @@ -765,25 +794,58 @@ static struct inet6_protocol l2tp_ip6_protocol __read_mostly = { .handler = l2tp_ip6_recv, }; +static __net_init int l2tp_ip6_init_net(struct net *net) +{ + struct l2tp_ip6_net *pn = net_generic(net, l2tp_ip6_net_id); + + rwlock_init(&pn->l2tp_ip6_lock); + INIT_HLIST_HEAD(&pn->l2tp_ip6_table); + INIT_HLIST_HEAD(&pn->l2tp_ip6_bind_table); + return 0; +} + +static __net_exit void l2tp_ip6_exit_net(struct net *net) +{ + struct l2tp_ip6_net *pn = l2tp_ip6_pernet(net); + + write_lock_bh(&pn->l2tp_ip6_lock); + WARN_ON_ONCE(hlist_count_nodes(&pn->l2tp_ip6_table) != 0); + WARN_ON_ONCE(hlist_count_nodes(&pn->l2tp_ip6_bind_table) != 0); + write_unlock_bh(&pn->l2tp_ip6_lock); +} + +static struct pernet_operations l2tp_ip6_net_ops = { + .init = l2tp_ip6_init_net, + .exit = l2tp_ip6_exit_net, + .id = &l2tp_ip6_net_id, + .size = sizeof(struct l2tp_ip6_net), +}; + static int __init l2tp_ip6_init(void) { int err; pr_info("L2TP IP encapsulation support for IPv6 (L2TPv3)\n"); + err = register_pernet_device(&l2tp_ip6_net_ops); + if (err) + goto out; + err = proto_register(&l2tp_ip6_prot, 1); if (err != 0) - goto out; + goto out1; err = inet6_add_protocol(&l2tp_ip6_protocol, IPPROTO_L2TP); if (err) - goto out1; + goto out2; inet6_register_protosw(&l2tp_ip6_protosw); return 0; -out1: +out2: proto_unregister(&l2tp_ip6_prot); +out1: + unregister_pernet_device(&l2tp_ip6_net_ops); out: return err; } @@ -793,6 +855,7 @@ static void __exit l2tp_ip6_exit(void) inet6_unregister_protosw(&l2tp_ip6_protosw); inet6_del_protocol(&l2tp_ip6_protocol, IPPROTO_L2TP); proto_unregister(&l2tp_ip6_prot); + unregister_pernet_device(&l2tp_ip6_net_ops); } module_init(l2tp_ip6_init); diff --git a/net/l2tp/l2tp_netlink.c b/net/l2tp/l2tp_netlink.c index a901fd14fe3b..284f1dec1b56 100644 --- a/net/l2tp/l2tp_netlink.c +++ b/net/l2tp/l2tp_netlink.c @@ -61,8 +61,9 @@ static struct l2tp_session *l2tp_nl_session_get(struct genl_info *info) session_id = nla_get_u32(info->attrs[L2TP_ATTR_SESSION_ID]); tunnel = l2tp_tunnel_get(net, tunnel_id); if (tunnel) { - session = l2tp_tunnel_get_session(tunnel, session_id); - l2tp_tunnel_dec_refcount(tunnel); + session = l2tp_session_get(net, tunnel->sock, tunnel->version, + tunnel_id, session_id); + l2tp_tunnel_put(tunnel); } } @@ -241,7 +242,7 @@ static int l2tp_nl_cmd_tunnel_create(struct sk_buff *skb, struct genl_info *info if (ret < 0) goto out; - l2tp_tunnel_inc_refcount(tunnel); + refcount_inc(&tunnel->ref_count); ret = l2tp_tunnel_register(tunnel, net, &cfg); if (ret < 0) { kfree(tunnel); @@ -249,7 +250,7 @@ static int l2tp_nl_cmd_tunnel_create(struct sk_buff *skb, struct genl_info *info } ret = l2tp_tunnel_notify(&l2tp_nl_family, info, tunnel, L2TP_CMD_TUNNEL_CREATE); - l2tp_tunnel_dec_refcount(tunnel); + l2tp_tunnel_put(tunnel); out: return ret; @@ -279,7 +280,7 @@ static int l2tp_nl_cmd_tunnel_delete(struct sk_buff *skb, struct genl_info *info l2tp_tunnel_delete(tunnel); - l2tp_tunnel_dec_refcount(tunnel); + l2tp_tunnel_put(tunnel); out: return ret; @@ -307,7 +308,7 @@ static int l2tp_nl_cmd_tunnel_modify(struct sk_buff *skb, struct genl_info *info ret = l2tp_tunnel_notify(&l2tp_nl_family, info, tunnel, L2TP_CMD_TUNNEL_MODIFY); - l2tp_tunnel_dec_refcount(tunnel); + l2tp_tunnel_put(tunnel); out: return ret; @@ -478,42 +479,48 @@ static int l2tp_nl_cmd_tunnel_get(struct sk_buff *skb, struct genl_info *info) if (ret < 0) goto err_nlmsg_tunnel; - l2tp_tunnel_dec_refcount(tunnel); + l2tp_tunnel_put(tunnel); return genlmsg_unicast(net, msg, info->snd_portid); err_nlmsg_tunnel: - l2tp_tunnel_dec_refcount(tunnel); + l2tp_tunnel_put(tunnel); err_nlmsg: nlmsg_free(msg); err: return ret; } +struct l2tp_nl_cb_data { + unsigned long tkey; + unsigned long skey; +}; + static int l2tp_nl_cmd_tunnel_dump(struct sk_buff *skb, struct netlink_callback *cb) { - int ti = cb->args[0]; + struct l2tp_nl_cb_data *cbd = (void *)&cb->ctx[0]; + unsigned long key = cbd->tkey; struct l2tp_tunnel *tunnel; struct net *net = sock_net(skb->sk); for (;;) { - tunnel = l2tp_tunnel_get_nth(net, ti); + tunnel = l2tp_tunnel_get_next(net, &key); if (!tunnel) goto out; if (l2tp_nl_tunnel_send(skb, NETLINK_CB(cb->skb).portid, cb->nlh->nlmsg_seq, NLM_F_MULTI, tunnel, L2TP_CMD_TUNNEL_GET) < 0) { - l2tp_tunnel_dec_refcount(tunnel); + l2tp_tunnel_put(tunnel); goto out; } - l2tp_tunnel_dec_refcount(tunnel); + l2tp_tunnel_put(tunnel); - ti++; + key++; } out: - cb->args[0] = ti; + cbd->tkey = key; return skb->len; } @@ -635,16 +642,17 @@ static int l2tp_nl_cmd_session_create(struct sk_buff *skb, struct genl_info *inf &cfg); if (ret >= 0) { - session = l2tp_tunnel_get_session(tunnel, session_id); + session = l2tp_session_get(net, tunnel->sock, tunnel->version, + tunnel_id, session_id); if (session) { ret = l2tp_session_notify(&l2tp_nl_family, info, session, L2TP_CMD_SESSION_CREATE); - l2tp_session_dec_refcount(session); + l2tp_session_put(session); } } out_tunnel: - l2tp_tunnel_dec_refcount(tunnel); + l2tp_tunnel_put(tunnel); out: return ret; } @@ -669,7 +677,7 @@ static int l2tp_nl_cmd_session_delete(struct sk_buff *skb, struct genl_info *inf if (l2tp_nl_cmd_ops[pw_type] && l2tp_nl_cmd_ops[pw_type]->session_delete) l2tp_nl_cmd_ops[pw_type]->session_delete(session); - l2tp_session_dec_refcount(session); + l2tp_session_put(session); out: return ret; @@ -690,8 +698,10 @@ static int l2tp_nl_cmd_session_modify(struct sk_buff *skb, struct genl_info *inf session->recv_seq = nla_get_u8(info->attrs[L2TP_ATTR_RECV_SEQ]); if (info->attrs[L2TP_ATTR_SEND_SEQ]) { + struct l2tp_tunnel *tunnel = session->tunnel; + session->send_seq = nla_get_u8(info->attrs[L2TP_ATTR_SEND_SEQ]); - l2tp_session_set_header_len(session, session->tunnel->version); + l2tp_session_set_header_len(session, tunnel->version, tunnel->encap); } if (info->attrs[L2TP_ATTR_LNS_MODE]) @@ -703,7 +713,7 @@ static int l2tp_nl_cmd_session_modify(struct sk_buff *skb, struct genl_info *inf ret = l2tp_session_notify(&l2tp_nl_family, info, session, L2TP_CMD_SESSION_MODIFY); - l2tp_session_dec_refcount(session); + l2tp_session_put(session); out: return ret; @@ -814,57 +824,59 @@ static int l2tp_nl_cmd_session_get(struct sk_buff *skb, struct genl_info *info) ret = genlmsg_unicast(genl_info_net(info), msg, info->snd_portid); - l2tp_session_dec_refcount(session); + l2tp_session_put(session); return ret; err_ref_msg: nlmsg_free(msg); err_ref: - l2tp_session_dec_refcount(session); + l2tp_session_put(session); err: return ret; } static int l2tp_nl_cmd_session_dump(struct sk_buff *skb, struct netlink_callback *cb) { + struct l2tp_nl_cb_data *cbd = (void *)&cb->ctx[0]; struct net *net = sock_net(skb->sk); struct l2tp_session *session; struct l2tp_tunnel *tunnel = NULL; - int ti = cb->args[0]; - int si = cb->args[1]; + unsigned long tkey = cbd->tkey; + unsigned long skey = cbd->skey; for (;;) { if (!tunnel) { - tunnel = l2tp_tunnel_get_nth(net, ti); + tunnel = l2tp_tunnel_get_next(net, &tkey); if (!tunnel) goto out; } - session = l2tp_session_get_nth(tunnel, si); + session = l2tp_session_get_next(net, tunnel->sock, tunnel->version, + tunnel->tunnel_id, &skey); if (!session) { - ti++; - l2tp_tunnel_dec_refcount(tunnel); + tkey++; + l2tp_tunnel_put(tunnel); tunnel = NULL; - si = 0; + skey = 0; continue; } if (l2tp_nl_session_send(skb, NETLINK_CB(cb->skb).portid, cb->nlh->nlmsg_seq, NLM_F_MULTI, session, L2TP_CMD_SESSION_GET) < 0) { - l2tp_session_dec_refcount(session); - l2tp_tunnel_dec_refcount(tunnel); + l2tp_session_put(session); + l2tp_tunnel_put(tunnel); break; } - l2tp_session_dec_refcount(session); + l2tp_session_put(session); - si++; + skey++; } out: - cb->args[0] = ti; - cb->args[1] = si; + cbd->tkey = tkey; + cbd->skey = skey; return skb->len; } diff --git a/net/l2tp/l2tp_ppp.c b/net/l2tp/l2tp_ppp.c index 6146e4e67bbb..53baf2dd5d5d 100644 --- a/net/l2tp/l2tp_ppp.c +++ b/net/l2tp/l2tp_ppp.c @@ -119,7 +119,6 @@ struct pppol2tp_session { struct mutex sk_lock; /* Protects .sk */ struct sock __rcu *sk; /* Pointer to the session PPPoX socket */ struct sock *__sk; /* Copy of .sk, for cleanup */ - struct rcu_head rcu; /* For asynchronous release */ }; static int pppol2tp_xmit(struct ppp_channel *chan, struct sk_buff *skb); @@ -150,27 +149,23 @@ static struct sock *pppol2tp_session_get_sock(struct l2tp_session *session) /* Helpers to obtain tunnel/session contexts from sockets. */ -static inline struct l2tp_session *pppol2tp_sock_to_session(struct sock *sk) +static struct l2tp_session *pppol2tp_sock_to_session(struct sock *sk) { struct l2tp_session *session; if (!sk) return NULL; - sock_hold(sk); - session = (struct l2tp_session *)(sk->sk_user_data); - if (!session) { - sock_put(sk); - goto out; - } - if (WARN_ON(session->magic != L2TP_SESSION_MAGIC)) { - session = NULL; - sock_put(sk); - goto out; + rcu_read_lock(); + session = rcu_dereference_sk_user_data(sk); + if (session && refcount_inc_not_zero(&session->ref_count)) { + rcu_read_unlock(); + WARN_ON_ONCE(session->magic != L2TP_SESSION_MAGIC); + return session; } + rcu_read_unlock(); -out: - return session; + return NULL; } /***************************************************************************** @@ -318,12 +313,12 @@ static int pppol2tp_sendmsg(struct socket *sock, struct msghdr *m, l2tp_xmit_skb(session, skb); local_bh_enable(); - sock_put(sk); + l2tp_session_put(session); return total_len; error_put_sess: - sock_put(sk); + l2tp_session_put(session); error: return error; } @@ -377,12 +372,12 @@ static int pppol2tp_xmit(struct ppp_channel *chan, struct sk_buff *skb) l2tp_xmit_skb(session, skb); local_bh_enable(); - sock_put(sk); + l2tp_session_put(session); return 1; abort_put_sess: - sock_put(sk); + l2tp_session_put(session); abort: /* Free the original skb */ kfree_skb(skb); @@ -393,29 +388,32 @@ abort: * Session (and tunnel control) socket create/destroy. *****************************************************************************/ -static void pppol2tp_put_sk(struct rcu_head *head) -{ - struct pppol2tp_session *ps; - - ps = container_of(head, typeof(*ps), rcu); - sock_put(ps->__sk); -} - /* Really kill the session socket. (Called from sock_put() if * refcnt == 0.) */ static void pppol2tp_session_destruct(struct sock *sk) { - struct l2tp_session *session = sk->sk_user_data; - skb_queue_purge(&sk->sk_receive_queue); skb_queue_purge(&sk->sk_write_queue); +} - if (session) { - sk->sk_user_data = NULL; - if (WARN_ON(session->magic != L2TP_SESSION_MAGIC)) - return; - l2tp_session_dec_refcount(session); +static void pppol2tp_session_close(struct l2tp_session *session) +{ + struct pppol2tp_session *ps; + + ps = l2tp_session_priv(session); + mutex_lock(&ps->sk_lock); + ps->__sk = rcu_dereference_protected(ps->sk, + lockdep_is_held(&ps->sk_lock)); + RCU_INIT_POINTER(ps->sk, NULL); + mutex_unlock(&ps->sk_lock); + if (ps->__sk) { + /* detach socket */ + rcu_assign_sk_user_data(ps->__sk, NULL); + sock_put(ps->__sk); + + /* drop ref taken when we referenced socket via sk_user_data */ + l2tp_session_put(session); } } @@ -444,30 +442,13 @@ static int pppol2tp_release(struct socket *sock) session = pppol2tp_sock_to_session(sk); if (session) { - struct pppol2tp_session *ps; - l2tp_session_delete(session); - - ps = l2tp_session_priv(session); - mutex_lock(&ps->sk_lock); - ps->__sk = rcu_dereference_protected(ps->sk, - lockdep_is_held(&ps->sk_lock)); - RCU_INIT_POINTER(ps->sk, NULL); - mutex_unlock(&ps->sk_lock); - call_rcu(&ps->rcu, pppol2tp_put_sk); - - /* Rely on the sock_put() call at the end of the function for - * dropping the reference held by pppol2tp_sock_to_session(). - * The last reference will be dropped by pppol2tp_put_sk(). - */ + /* drop ref taken by pppol2tp_sock_to_session */ + l2tp_session_put(session); } release_sock(sk); - /* This will delete the session context via - * pppol2tp_session_destruct() if the socket's refcnt drops to - * zero. - */ sock_put(sk); return 0; @@ -506,6 +487,7 @@ static int pppol2tp_create(struct net *net, struct socket *sock, int kern) goto out; sock_init_data(sock, sk); + sock_set_flag(sk, SOCK_RCU_FREE); sock->state = SS_UNCONNECTED; sock->ops = &pppol2tp_ops; @@ -542,6 +524,7 @@ static void pppol2tp_session_init(struct l2tp_session *session) struct pppol2tp_session *ps; session->recv_skb = pppol2tp_recv; + session->session_close = pppol2tp_session_close; if (IS_ENABLED(CONFIG_L2TP_DEBUGFS)) session->show = pppol2tp_show; @@ -685,7 +668,7 @@ static struct l2tp_tunnel *pppol2tp_tunnel_get(struct net *net, if (error < 0) return ERR_PTR(error); - l2tp_tunnel_inc_refcount(tunnel); + refcount_inc(&tunnel->ref_count); error = l2tp_tunnel_register(tunnel, net, &tcfg); if (error < 0) { kfree(tunnel); @@ -701,7 +684,7 @@ static struct l2tp_tunnel *pppol2tp_tunnel_get(struct net *net, /* Error if socket is not prepped */ if (!tunnel->sock) { - l2tp_tunnel_dec_refcount(tunnel); + l2tp_tunnel_put(tunnel); return ERR_PTR(-ENOENT); } } @@ -753,7 +736,8 @@ static int pppol2tp_connect(struct socket *sock, struct sockaddr *uservaddr, if (tunnel->peer_tunnel_id == 0) tunnel->peer_tunnel_id = info.peer_tunnel_id; - session = l2tp_tunnel_get_session(tunnel, info.session_id); + session = l2tp_session_get(sock_net(sk), tunnel->sock, tunnel->version, + info.tunnel_id, info.session_id); if (session) { drop_refcnt = true; @@ -786,18 +770,20 @@ static int pppol2tp_connect(struct socket *sock, struct sockaddr *uservaddr, goto end; } + drop_refcnt = true; + pppol2tp_session_init(session); ps = l2tp_session_priv(session); - l2tp_session_inc_refcount(session); + refcount_inc(&session->ref_count); mutex_lock(&ps->sk_lock); error = l2tp_session_register(session, tunnel); if (error < 0) { mutex_unlock(&ps->sk_lock); - kfree(session); + l2tp_session_put(session); goto end; } - drop_refcnt = true; + new_session = true; } @@ -829,12 +815,13 @@ static int pppol2tp_connect(struct socket *sock, struct sockaddr *uservaddr, out_no_ppp: /* This is how we get the session context from the socket. */ - sk->sk_user_data = session; + sock_hold(sk); + rcu_assign_sk_user_data(sk, session); rcu_assign_pointer(ps->sk, sk); mutex_unlock(&ps->sk_lock); /* Keep the reference we've grabbed on the session: sk doesn't expect - * the session to disappear. pppol2tp_session_destruct() is responsible + * the session to disappear. pppol2tp_session_close() is responsible * for dropping it. */ drop_refcnt = false; @@ -849,8 +836,8 @@ end: l2tp_tunnel_delete(tunnel); } if (drop_refcnt) - l2tp_session_dec_refcount(session); - l2tp_tunnel_dec_refcount(tunnel); + l2tp_session_put(session); + l2tp_tunnel_put(tunnel); release_sock(sk); return error; @@ -890,7 +877,7 @@ static int pppol2tp_session_create(struct net *net, struct l2tp_tunnel *tunnel, return 0; err_sess: - kfree(session); + l2tp_session_put(session); err: return error; } @@ -1001,7 +988,7 @@ static int pppol2tp_getname(struct socket *sock, struct sockaddr *uaddr, error = len; - sock_put(sk); + l2tp_session_put(session); end: return error; } @@ -1045,17 +1032,18 @@ static int pppol2tp_tunnel_copy_stats(struct pppol2tp_ioc_stats *stats, /* If session_id is set, search the corresponding session in the * context of this tunnel and record the session's statistics. */ - session = l2tp_tunnel_get_session(tunnel, stats->session_id); + session = l2tp_session_get(tunnel->l2tp_net, tunnel->sock, tunnel->version, + tunnel->tunnel_id, stats->session_id); if (!session) return -EBADR; if (session->pwtype != L2TP_PWTYPE_PPP) { - l2tp_session_dec_refcount(session); + l2tp_session_put(session); return -EBADR; } pppol2tp_copy_stats(stats, &session->stats); - l2tp_session_dec_refcount(session); + l2tp_session_put(session); return 0; } @@ -1203,7 +1191,8 @@ static int pppol2tp_session_setsockopt(struct sock *sk, po->chan.hdrlen = val ? PPPOL2TP_L2TP_HDR_SIZE_SEQ : PPPOL2TP_L2TP_HDR_SIZE_NOSEQ; } - l2tp_session_set_header_len(session, session->tunnel->version); + l2tp_session_set_header_len(session, session->tunnel->version, + session->tunnel->encap); break; case PPPOL2TP_SO_LNSMODE: @@ -1272,7 +1261,7 @@ static int pppol2tp_setsockopt(struct socket *sock, int level, int optname, err = pppol2tp_session_setsockopt(sk, session, optname, val); } - sock_put(sk); + l2tp_session_put(session); end: return err; } @@ -1393,7 +1382,7 @@ static int pppol2tp_getsockopt(struct socket *sock, int level, int optname, err = 0; end_put_sess: - sock_put(sk); + l2tp_session_put(session); end: return err; } @@ -1404,14 +1393,12 @@ end: * L2TPv2, we dump only L2TPv2 tunnels and sessions here. *****************************************************************************/ -static unsigned int pppol2tp_net_id; - #ifdef CONFIG_PROC_FS struct pppol2tp_seq_data { struct seq_net_private p; - int tunnel_idx; /* current tunnel */ - int session_idx; /* index of session within current tunnel */ + unsigned long tkey; /* lookup key of current tunnel */ + unsigned long skey; /* lookup key of current session */ struct l2tp_tunnel *tunnel; struct l2tp_session *session; /* NULL means get next tunnel */ }; @@ -1420,17 +1407,17 @@ static void pppol2tp_next_tunnel(struct net *net, struct pppol2tp_seq_data *pd) { /* Drop reference taken during previous invocation */ if (pd->tunnel) - l2tp_tunnel_dec_refcount(pd->tunnel); + l2tp_tunnel_put(pd->tunnel); for (;;) { - pd->tunnel = l2tp_tunnel_get_nth(net, pd->tunnel_idx); - pd->tunnel_idx++; + pd->tunnel = l2tp_tunnel_get_next(net, &pd->tkey); + pd->tkey++; /* Only accept L2TPv2 tunnels */ if (!pd->tunnel || pd->tunnel->version == 2) return; - l2tp_tunnel_dec_refcount(pd->tunnel); + l2tp_tunnel_put(pd->tunnel); } } @@ -1438,13 +1425,15 @@ static void pppol2tp_next_session(struct net *net, struct pppol2tp_seq_data *pd) { /* Drop reference taken during previous invocation */ if (pd->session) - l2tp_session_dec_refcount(pd->session); + l2tp_session_put(pd->session); - pd->session = l2tp_session_get_nth(pd->tunnel, pd->session_idx); - pd->session_idx++; + pd->session = l2tp_session_get_next(net, pd->tunnel->sock, + pd->tunnel->version, + pd->tunnel->tunnel_id, &pd->skey); + pd->skey++; if (!pd->session) { - pd->session_idx = 0; + pd->skey = 0; pppol2tp_next_tunnel(net, pd); } } @@ -1496,11 +1485,11 @@ static void pppol2tp_seq_stop(struct seq_file *p, void *v) * or pppol2tp_next_tunnel(). */ if (pd->session) { - l2tp_session_dec_refcount(pd->session); + l2tp_session_put(pd->session); pd->session = NULL; } if (pd->tunnel) { - l2tp_tunnel_dec_refcount(pd->tunnel); + l2tp_tunnel_put(pd->tunnel); pd->tunnel = NULL; } } @@ -1511,7 +1500,7 @@ static void pppol2tp_seq_tunnel_show(struct seq_file *m, void *v) seq_printf(m, "\nTUNNEL '%s', %c %d\n", tunnel->name, - (tunnel == tunnel->sock->sk_user_data) ? 'Y' : 'N', + tunnel->sock ? 'Y' : 'N', refcount_read(&tunnel->ref_count) - 1); seq_printf(m, " %08x %ld/%ld/%ld %ld/%ld/%ld\n", 0, @@ -1639,7 +1628,6 @@ static __net_exit void pppol2tp_exit_net(struct net *net) static struct pernet_operations pppol2tp_net_ops = { .init = pppol2tp_init_net, .exit = pppol2tp_exit_net, - .id = &pppol2tp_net_id, }; /***************************************************************************** diff --git a/net/llc/llc_c_st.c b/net/llc/llc_c_st.c index 2467573b5f84..1c267db304df 100644 --- a/net/llc/llc_c_st.c +++ b/net/llc/llc_c_st.c @@ -42,7 +42,7 @@ static const llc_conn_action_t llc_common_actions_1[] = { [5] = NULL, }; -static struct llc_conn_state_trans llc_common_state_trans_1 = { +static const struct llc_conn_state_trans llc_common_state_trans_1 = { .ev = llc_conn_ev_disc_req, .next_state = LLC_CONN_STATE_D_CONN, .ev_qualifiers = NONE, @@ -59,7 +59,7 @@ static const llc_conn_action_t llc_common_actions_2[] = { [5] = NULL, }; -static struct llc_conn_state_trans llc_common_state_trans_2 = { +static const struct llc_conn_state_trans llc_common_state_trans_2 = { .ev = llc_conn_ev_rst_req, .next_state = LLC_CONN_STATE_RESET, .ev_qualifiers = NONE, @@ -79,7 +79,7 @@ static const llc_conn_action_t llc_common_actions_3[] = { [8] = NULL, }; -static struct llc_conn_state_trans llc_common_state_trans_3 = { +static const struct llc_conn_state_trans llc_common_state_trans_3 = { .ev = llc_conn_ev_rx_sabme_cmd_pbit_set_x, .next_state = LLC_CONN_STATE_NORMAL, .ev_qualifiers = NONE, @@ -95,7 +95,7 @@ static const llc_conn_action_t llc_common_actions_4[] = { [4] = NULL, }; -static struct llc_conn_state_trans llc_common_state_trans_4 = { +static const struct llc_conn_state_trans llc_common_state_trans_4 = { .ev = llc_conn_ev_rx_disc_cmd_pbit_set_x, .next_state = LLC_CONN_STATE_ADM, .ev_qualifiers = NONE, @@ -114,7 +114,7 @@ static const llc_conn_action_t llc_common_actions_5[] = { [7] = NULL, }; -static struct llc_conn_state_trans llc_common_state_trans_5 = { +static const struct llc_conn_state_trans llc_common_state_trans_5 = { .ev = llc_conn_ev_rx_frmr_rsp_fbit_set_x, .next_state = LLC_CONN_STATE_RESET, .ev_qualifiers = NONE, @@ -129,7 +129,7 @@ static const llc_conn_action_t llc_common_actions_6[] = { [3] = NULL, }; -static struct llc_conn_state_trans llc_common_state_trans_6 = { +static const struct llc_conn_state_trans llc_common_state_trans_6 = { .ev = llc_conn_ev_rx_dm_rsp_fbit_set_x, .next_state = LLC_CONN_STATE_ADM, .ev_qualifiers = NONE, @@ -145,7 +145,7 @@ static const llc_conn_action_t llc_common_actions_7a[] = { [4] = NULL, }; -static struct llc_conn_state_trans llc_common_state_trans_7a = { +static const struct llc_conn_state_trans llc_common_state_trans_7a = { .ev = llc_conn_ev_rx_zzz_cmd_pbit_set_x_inval_nr, .next_state = LLC_CONN_STATE_ERROR, .ev_qualifiers = NONE, @@ -161,7 +161,7 @@ static const llc_conn_action_t llc_common_actions_7b[] = { [4] = NULL, }; -static struct llc_conn_state_trans llc_common_state_trans_7b = { +static const struct llc_conn_state_trans llc_common_state_trans_7b = { .ev = llc_conn_ev_rx_i_cmd_pbit_set_x_inval_ns, .next_state = LLC_CONN_STATE_ERROR, .ev_qualifiers = NONE, @@ -177,7 +177,7 @@ static const llc_conn_action_t llc_common_actions_8a[] = { [4] = NULL, }; -static struct llc_conn_state_trans llc_common_state_trans_8a = { +static const struct llc_conn_state_trans llc_common_state_trans_8a = { .ev = llc_conn_ev_rx_zzz_rsp_fbit_set_x_inval_nr, .next_state = LLC_CONN_STATE_ERROR, .ev_qualifiers = NONE, @@ -193,7 +193,7 @@ static const llc_conn_action_t llc_common_actions_8b[] = { [4] = NULL, }; -static struct llc_conn_state_trans llc_common_state_trans_8b = { +static const struct llc_conn_state_trans llc_common_state_trans_8b = { .ev = llc_conn_ev_rx_i_rsp_fbit_set_x_inval_ns, .next_state = LLC_CONN_STATE_ERROR, .ev_qualifiers = NONE, @@ -209,7 +209,7 @@ static const llc_conn_action_t llc_common_actions_8c[] = { [4] = NULL, }; -static struct llc_conn_state_trans llc_common_state_trans_8c = { +static const struct llc_conn_state_trans llc_common_state_trans_8c = { .ev = llc_conn_ev_rx_bad_pdu, .next_state = LLC_CONN_STATE_ERROR, .ev_qualifiers = NONE, @@ -225,7 +225,7 @@ static const llc_conn_action_t llc_common_actions_9[] = { [4] = NULL, }; -static struct llc_conn_state_trans llc_common_state_trans_9 = { +static const struct llc_conn_state_trans llc_common_state_trans_9 = { .ev = llc_conn_ev_rx_ua_rsp_fbit_set_x, .next_state = LLC_CONN_STATE_ERROR, .ev_qualifiers = NONE, @@ -247,7 +247,7 @@ static const llc_conn_action_t llc_common_actions_10[] = { [4] = NULL, }; -static struct llc_conn_state_trans llc_common_state_trans_10 = { +static const struct llc_conn_state_trans llc_common_state_trans_10 = { .ev = llc_conn_ev_rx_xxx_rsp_fbit_set_1, .next_state = LLC_CONN_STATE_ERROR, .ev_qualifiers = llc_common_ev_qfyrs_10, @@ -270,7 +270,7 @@ static const llc_conn_action_t llc_common_actions_11a[] = { [5] = NULL, }; -static struct llc_conn_state_trans llc_common_state_trans_11a = { +static const struct llc_conn_state_trans llc_common_state_trans_11a = { .ev = llc_conn_ev_p_tmr_exp, .next_state = LLC_CONN_STATE_RESET, .ev_qualifiers = llc_common_ev_qfyrs_11a, @@ -292,7 +292,7 @@ static const llc_conn_action_t llc_common_actions_11b[] = { [5] = NULL, }; -static struct llc_conn_state_trans llc_common_state_trans_11b = { +static const struct llc_conn_state_trans llc_common_state_trans_11b = { .ev = llc_conn_ev_ack_tmr_exp, .next_state = LLC_CONN_STATE_RESET, .ev_qualifiers = llc_common_ev_qfyrs_11b, @@ -314,7 +314,7 @@ static const llc_conn_action_t llc_common_actions_11c[] = { [5] = NULL, }; -static struct llc_conn_state_trans llc_common_state_trans_11c = { +static const struct llc_conn_state_trans llc_common_state_trans_11c = { .ev = llc_conn_ev_rej_tmr_exp, .next_state = LLC_CONN_STATE_RESET, .ev_qualifiers = llc_common_ev_qfyrs_11c, @@ -336,7 +336,7 @@ static const llc_conn_action_t llc_common_actions_11d[] = { [5] = NULL, }; -static struct llc_conn_state_trans llc_common_state_trans_11d = { +static const struct llc_conn_state_trans llc_common_state_trans_11d = { .ev = llc_conn_ev_busy_tmr_exp, .next_state = LLC_CONN_STATE_RESET, .ev_qualifiers = llc_common_ev_qfyrs_11d, @@ -347,7 +347,7 @@ static struct llc_conn_state_trans llc_common_state_trans_11d = { * Common dummy state transition; must be last entry for all state * transition groups - it'll be on .bss, so will be zeroed. */ -static struct llc_conn_state_trans llc_common_state_trans_end; +static const struct llc_conn_state_trans llc_common_state_trans_end; /* LLC_CONN_STATE_ADM transitions */ /* State transitions for LLC_CONN_EV_CONN_REQ event */ @@ -359,7 +359,7 @@ static const llc_conn_action_t llc_adm_actions_1[] = { [4] = NULL, }; -static struct llc_conn_state_trans llc_adm_state_trans_1 = { +static const struct llc_conn_state_trans llc_adm_state_trans_1 = { .ev = llc_conn_ev_conn_req, .next_state = LLC_CONN_STATE_SETUP, .ev_qualifiers = NONE, @@ -378,7 +378,7 @@ static const llc_conn_action_t llc_adm_actions_2[] = { [7] = NULL, }; -static struct llc_conn_state_trans llc_adm_state_trans_2 = { +static const struct llc_conn_state_trans llc_adm_state_trans_2 = { .ev = llc_conn_ev_rx_sabme_cmd_pbit_set_x, .next_state = LLC_CONN_STATE_NORMAL, .ev_qualifiers = NONE, @@ -392,7 +392,7 @@ static const llc_conn_action_t llc_adm_actions_3[] = { [2] = NULL, }; -static struct llc_conn_state_trans llc_adm_state_trans_3 = { +static const struct llc_conn_state_trans llc_adm_state_trans_3 = { .ev = llc_conn_ev_rx_disc_cmd_pbit_set_x, .next_state = LLC_CONN_STATE_ADM, .ev_qualifiers = NONE, @@ -406,7 +406,7 @@ static const llc_conn_action_t llc_adm_actions_4[] = { [2] = NULL, }; -static struct llc_conn_state_trans llc_adm_state_trans_4 = { +static const struct llc_conn_state_trans llc_adm_state_trans_4 = { .ev = llc_conn_ev_rx_xxx_cmd_pbit_set_1, .next_state = LLC_CONN_STATE_ADM, .ev_qualifiers = NONE, @@ -419,7 +419,7 @@ static const llc_conn_action_t llc_adm_actions_5[] = { [1] = NULL, }; -static struct llc_conn_state_trans llc_adm_state_trans_5 = { +static const struct llc_conn_state_trans llc_adm_state_trans_5 = { .ev = llc_conn_ev_rx_any_frame, .next_state = LLC_CONN_OUT_OF_SVC, .ev_qualifiers = NONE, @@ -430,7 +430,7 @@ static struct llc_conn_state_trans llc_adm_state_trans_5 = { * Array of pointers; * one to each transition */ -static struct llc_conn_state_trans *llc_adm_state_transitions[] = { +static const struct llc_conn_state_trans *llc_adm_state_transitions[] = { [0] = &llc_adm_state_trans_1, /* Request */ [1] = &llc_common_state_trans_end, [2] = &llc_common_state_trans_end, /* local_busy */ @@ -453,7 +453,7 @@ static const llc_conn_action_t llc_setup_actions_1[] = { [4] = NULL, }; -static struct llc_conn_state_trans llc_setup_state_trans_1 = { +static const struct llc_conn_state_trans llc_setup_state_trans_1 = { .ev = llc_conn_ev_rx_sabme_cmd_pbit_set_x, .next_state = LLC_CONN_STATE_SETUP, .ev_qualifiers = NONE, @@ -477,7 +477,7 @@ static const llc_conn_action_t llc_setup_actions_2[] = { [6] = NULL, }; -static struct llc_conn_state_trans llc_setup_state_trans_2 = { +static const struct llc_conn_state_trans llc_setup_state_trans_2 = { .ev = llc_conn_ev_rx_ua_rsp_fbit_set_x, .next_state = LLC_CONN_STATE_NORMAL, .ev_qualifiers = llc_setup_ev_qfyrs_2, @@ -498,7 +498,7 @@ static const llc_conn_action_t llc_setup_actions_3[] = { [3] = NULL, }; -static struct llc_conn_state_trans llc_setup_state_trans_3 = { +static const struct llc_conn_state_trans llc_setup_state_trans_3 = { .ev = llc_conn_ev_ack_tmr_exp, .next_state = LLC_CONN_STATE_NORMAL, .ev_qualifiers = llc_setup_ev_qfyrs_3, @@ -519,7 +519,7 @@ static const llc_conn_action_t llc_setup_actions_4[] = { [4] = NULL, }; -static struct llc_conn_state_trans llc_setup_state_trans_4 = { +static const struct llc_conn_state_trans llc_setup_state_trans_4 = { .ev = llc_conn_ev_rx_disc_cmd_pbit_set_x, .next_state = LLC_CONN_STATE_ADM, .ev_qualifiers = llc_setup_ev_qfyrs_4, @@ -539,7 +539,7 @@ static const llc_conn_action_t llc_setup_actions_5[] = { [3] = NULL, }; -static struct llc_conn_state_trans llc_setup_state_trans_5 = { +static const struct llc_conn_state_trans llc_setup_state_trans_5 = { .ev = llc_conn_ev_rx_dm_rsp_fbit_set_x, .next_state = LLC_CONN_STATE_ADM, .ev_qualifiers = llc_setup_ev_qfyrs_5, @@ -560,7 +560,7 @@ static const llc_conn_action_t llc_setup_actions_7[] = { [3] = NULL, }; -static struct llc_conn_state_trans llc_setup_state_trans_7 = { +static const struct llc_conn_state_trans llc_setup_state_trans_7 = { .ev = llc_conn_ev_ack_tmr_exp, .next_state = LLC_CONN_STATE_SETUP, .ev_qualifiers = llc_setup_ev_qfyrs_7, @@ -581,7 +581,7 @@ static const llc_conn_action_t llc_setup_actions_8[] = { [2] = NULL, }; -static struct llc_conn_state_trans llc_setup_state_trans_8 = { +static const struct llc_conn_state_trans llc_setup_state_trans_8 = { .ev = llc_conn_ev_ack_tmr_exp, .next_state = LLC_CONN_STATE_ADM, .ev_qualifiers = llc_setup_ev_qfyrs_8, @@ -592,7 +592,7 @@ static struct llc_conn_state_trans llc_setup_state_trans_8 = { * Array of pointers; * one to each transition */ -static struct llc_conn_state_trans *llc_setup_state_transitions[] = { +static const struct llc_conn_state_trans *llc_setup_state_transitions[] = { [0] = &llc_common_state_trans_end, /* Request */ [1] = &llc_common_state_trans_end, /* local busy */ [2] = &llc_common_state_trans_end, /* init_pf_cycle */ @@ -622,7 +622,7 @@ static const llc_conn_action_t llc_normal_actions_1[] = { [2] = NULL, }; -static struct llc_conn_state_trans llc_normal_state_trans_1 = { +static const struct llc_conn_state_trans llc_normal_state_trans_1 = { .ev = llc_conn_ev_data_req, .next_state = LLC_CONN_STATE_NORMAL, .ev_qualifiers = llc_normal_ev_qfyrs_1, @@ -643,7 +643,7 @@ static const llc_conn_action_t llc_normal_actions_2[] = { [2] = NULL, }; -static struct llc_conn_state_trans llc_normal_state_trans_2 = { +static const struct llc_conn_state_trans llc_normal_state_trans_2 = { .ev = llc_conn_ev_data_req, .next_state = LLC_CONN_STATE_NORMAL, .ev_qualifiers = llc_normal_ev_qfyrs_2, @@ -660,7 +660,7 @@ static const llc_conn_ev_qfyr_t llc_normal_ev_qfyrs_2_1[] = { /* just one member, NULL, .bss zeroes it */ static const llc_conn_action_t llc_normal_actions_2_1[1]; -static struct llc_conn_state_trans llc_normal_state_trans_2_1 = { +static const struct llc_conn_state_trans llc_normal_state_trans_2_1 = { .ev = llc_conn_ev_data_req, .next_state = LLC_CONN_STATE_NORMAL, .ev_qualifiers = llc_normal_ev_qfyrs_2_1, @@ -680,7 +680,7 @@ static const llc_conn_action_t llc_normal_actions_3[] = { [3] = NULL, }; -static struct llc_conn_state_trans llc_normal_state_trans_3 = { +static const struct llc_conn_state_trans llc_normal_state_trans_3 = { .ev = llc_conn_ev_local_busy_detected, .next_state = LLC_CONN_STATE_BUSY, .ev_qualifiers = llc_normal_ev_qfyrs_3, @@ -700,7 +700,7 @@ static const llc_conn_action_t llc_normal_actions_4[] = { [3] = NULL, }; -static struct llc_conn_state_trans llc_normal_state_trans_4 = { +static const struct llc_conn_state_trans llc_normal_state_trans_4 = { .ev = llc_conn_ev_local_busy_detected, .next_state = LLC_CONN_STATE_BUSY, .ev_qualifiers = llc_normal_ev_qfyrs_4, @@ -723,7 +723,7 @@ static const llc_conn_action_t llc_normal_actions_5a[] = { [6] = NULL, }; -static struct llc_conn_state_trans llc_normal_state_trans_5a = { +static const struct llc_conn_state_trans llc_normal_state_trans_5a = { .ev = llc_conn_ev_rx_i_cmd_pbit_set_0_unexpd_ns, .next_state = LLC_CONN_STATE_REJ, .ev_qualifiers = llc_normal_ev_qfyrs_5a, @@ -746,7 +746,7 @@ static const llc_conn_action_t llc_normal_actions_5b[] = { [6] = NULL, }; -static struct llc_conn_state_trans llc_normal_state_trans_5b = { +static const struct llc_conn_state_trans llc_normal_state_trans_5b = { .ev = llc_conn_ev_rx_i_rsp_fbit_set_0_unexpd_ns, .next_state = LLC_CONN_STATE_REJ, .ev_qualifiers = llc_normal_ev_qfyrs_5b, @@ -769,7 +769,7 @@ static const llc_conn_action_t llc_normal_actions_5c[] = { [6] = NULL, }; -static struct llc_conn_state_trans llc_normal_state_trans_5c = { +static const struct llc_conn_state_trans llc_normal_state_trans_5c = { .ev = llc_conn_ev_rx_i_rsp_fbit_set_1_unexpd_ns, .next_state = LLC_CONN_STATE_REJ, .ev_qualifiers = llc_normal_ev_qfyrs_5c, @@ -790,7 +790,7 @@ static const llc_conn_action_t llc_normal_actions_6a[] = { [4] = NULL, }; -static struct llc_conn_state_trans llc_normal_state_trans_6a = { +static const struct llc_conn_state_trans llc_normal_state_trans_6a = { .ev = llc_conn_ev_rx_i_cmd_pbit_set_0_unexpd_ns, .next_state = LLC_CONN_STATE_REJ, .ev_qualifiers = llc_normal_ev_qfyrs_6a, @@ -811,7 +811,7 @@ static const llc_conn_action_t llc_normal_actions_6b[] = { [4] = NULL, }; -static struct llc_conn_state_trans llc_normal_state_trans_6b = { +static const struct llc_conn_state_trans llc_normal_state_trans_6b = { .ev = llc_conn_ev_rx_i_rsp_fbit_set_0_unexpd_ns, .next_state = LLC_CONN_STATE_REJ, .ev_qualifiers = llc_normal_ev_qfyrs_6b, @@ -827,7 +827,7 @@ static const llc_conn_action_t llc_normal_actions_7[] = { [4] = NULL, }; -static struct llc_conn_state_trans llc_normal_state_trans_7 = { +static const struct llc_conn_state_trans llc_normal_state_trans_7 = { .ev = llc_conn_ev_rx_i_cmd_pbit_set_1_unexpd_ns, .next_state = LLC_CONN_STATE_REJ, .ev_qualifiers = NONE, @@ -850,7 +850,7 @@ static const llc_conn_action_t llc_normal_actions_8[] = { [6] = NULL, }; -static struct llc_conn_state_trans llc_normal_state_trans_8a = { +static const struct llc_conn_state_trans llc_normal_state_trans_8a = { .ev = llc_conn_ev_rx_i_rsp_fbit_set_x, .next_state = LLC_CONN_STATE_NORMAL, .ev_qualifiers = llc_normal_ev_qfyrs_8a, @@ -863,7 +863,7 @@ static const llc_conn_ev_qfyr_t llc_normal_ev_qfyrs_8b[] = { [1] = NULL, }; -static struct llc_conn_state_trans llc_normal_state_trans_8b = { +static const struct llc_conn_state_trans llc_normal_state_trans_8b = { .ev = llc_conn_ev_rx_i_cmd_pbit_set_0, .next_state = LLC_CONN_STATE_NORMAL, .ev_qualifiers = llc_normal_ev_qfyrs_8b, @@ -884,7 +884,7 @@ static const llc_conn_action_t llc_normal_actions_9a[] = { [4] = NULL, }; -static struct llc_conn_state_trans llc_normal_state_trans_9a = { +static const struct llc_conn_state_trans llc_normal_state_trans_9a = { .ev = llc_conn_ev_rx_i_rsp_fbit_set_0, .next_state = LLC_CONN_STATE_NORMAL, .ev_qualifiers = llc_normal_ev_qfyrs_9a, @@ -905,7 +905,7 @@ static const llc_conn_action_t llc_normal_actions_9b[] = { [4] = NULL, }; -static struct llc_conn_state_trans llc_normal_state_trans_9b = { +static const struct llc_conn_state_trans llc_normal_state_trans_9b = { .ev = llc_conn_ev_rx_i_cmd_pbit_set_0, .next_state = LLC_CONN_STATE_NORMAL, .ev_qualifiers = llc_normal_ev_qfyrs_9b, @@ -922,7 +922,7 @@ static const llc_conn_action_t llc_normal_actions_10[] = { [5] = NULL, }; -static struct llc_conn_state_trans llc_normal_state_trans_10 = { +static const struct llc_conn_state_trans llc_normal_state_trans_10 = { .ev = llc_conn_ev_rx_i_cmd_pbit_set_1, .next_state = LLC_CONN_STATE_NORMAL, .ev_qualifiers = NONE, @@ -937,7 +937,7 @@ static const llc_conn_action_t llc_normal_actions_11a[] = { [3] = NULL, }; -static struct llc_conn_state_trans llc_normal_state_trans_11a = { +static const struct llc_conn_state_trans llc_normal_state_trans_11a = { .ev = llc_conn_ev_rx_rr_cmd_pbit_set_0, .next_state = LLC_CONN_STATE_NORMAL, .ev_qualifiers = NONE, @@ -952,7 +952,7 @@ static const llc_conn_action_t llc_normal_actions_11b[] = { [3] = NULL, }; -static struct llc_conn_state_trans llc_normal_state_trans_11b = { +static const struct llc_conn_state_trans llc_normal_state_trans_11b = { .ev = llc_conn_ev_rx_rr_rsp_fbit_set_0, .next_state = LLC_CONN_STATE_NORMAL, .ev_qualifiers = NONE, @@ -973,7 +973,7 @@ static const llc_conn_action_t llc_normal_actions_11c[] = { [4] = NULL, }; -static struct llc_conn_state_trans llc_normal_state_trans_11c = { +static const struct llc_conn_state_trans llc_normal_state_trans_11c = { .ev = llc_conn_ev_rx_rr_rsp_fbit_set_1, .next_state = LLC_CONN_STATE_NORMAL, .ev_qualifiers = llc_normal_ev_qfyrs_11c, @@ -990,7 +990,7 @@ static const llc_conn_action_t llc_normal_actions_12[] = { [5] = NULL, }; -static struct llc_conn_state_trans llc_normal_state_trans_12 = { +static const struct llc_conn_state_trans llc_normal_state_trans_12 = { .ev = llc_conn_ev_rx_rr_cmd_pbit_set_1, .next_state = LLC_CONN_STATE_NORMAL, .ev_qualifiers = NONE, @@ -1005,7 +1005,7 @@ static const llc_conn_action_t llc_normal_actions_13a[] = { [3] = NULL, }; -static struct llc_conn_state_trans llc_normal_state_trans_13a = { +static const struct llc_conn_state_trans llc_normal_state_trans_13a = { .ev = llc_conn_ev_rx_rnr_cmd_pbit_set_0, .next_state = LLC_CONN_STATE_NORMAL, .ev_qualifiers = NONE, @@ -1020,7 +1020,7 @@ static const llc_conn_action_t llc_normal_actions_13b[] = { [3] = NULL, }; -static struct llc_conn_state_trans llc_normal_state_trans_13b = { +static const struct llc_conn_state_trans llc_normal_state_trans_13b = { .ev = llc_conn_ev_rx_rnr_rsp_fbit_set_0, .next_state = LLC_CONN_STATE_NORMAL, .ev_qualifiers = NONE, @@ -1040,7 +1040,7 @@ static const llc_conn_action_t llc_normal_actions_13c[] = { [3] = NULL, }; -static struct llc_conn_state_trans llc_normal_state_trans_13c = { +static const struct llc_conn_state_trans llc_normal_state_trans_13c = { .ev = llc_conn_ev_rx_rnr_rsp_fbit_set_1, .next_state = LLC_CONN_STATE_NORMAL, .ev_qualifiers = llc_normal_ev_qfyrs_13c, @@ -1057,7 +1057,7 @@ static const llc_conn_action_t llc_normal_actions_14[] = { [5] = NULL, }; -static struct llc_conn_state_trans llc_normal_state_trans_14 = { +static const struct llc_conn_state_trans llc_normal_state_trans_14 = { .ev = llc_conn_ev_rx_rnr_cmd_pbit_set_1, .next_state = LLC_CONN_STATE_NORMAL, .ev_qualifiers = NONE, @@ -1080,7 +1080,7 @@ static const llc_conn_action_t llc_normal_actions_15a[] = { [6] = NULL, }; -static struct llc_conn_state_trans llc_normal_state_trans_15a = { +static const struct llc_conn_state_trans llc_normal_state_trans_15a = { .ev = llc_conn_ev_rx_rej_cmd_pbit_set_0, .next_state = LLC_CONN_STATE_NORMAL, .ev_qualifiers = llc_normal_ev_qfyrs_15a, @@ -1103,7 +1103,7 @@ static const llc_conn_action_t llc_normal_actions_15b[] = { [6] = NULL, }; -static struct llc_conn_state_trans llc_normal_state_trans_15b = { +static const struct llc_conn_state_trans llc_normal_state_trans_15b = { .ev = llc_conn_ev_rx_rej_rsp_fbit_set_x, .next_state = LLC_CONN_STATE_NORMAL, .ev_qualifiers = llc_normal_ev_qfyrs_15b, @@ -1125,7 +1125,7 @@ static const llc_conn_action_t llc_normal_actions_16a[] = { [5] = NULL, }; -static struct llc_conn_state_trans llc_normal_state_trans_16a = { +static const struct llc_conn_state_trans llc_normal_state_trans_16a = { .ev = llc_conn_ev_rx_rej_cmd_pbit_set_0, .next_state = LLC_CONN_STATE_NORMAL, .ev_qualifiers = llc_normal_ev_qfyrs_16a, @@ -1147,7 +1147,7 @@ static const llc_conn_action_t llc_normal_actions_16b[] = { [5] = NULL, }; -static struct llc_conn_state_trans llc_normal_state_trans_16b = { +static const struct llc_conn_state_trans llc_normal_state_trans_16b = { .ev = llc_conn_ev_rx_rej_rsp_fbit_set_0, .next_state = LLC_CONN_STATE_NORMAL, .ev_qualifiers = llc_normal_ev_qfyrs_16b, @@ -1164,7 +1164,7 @@ static const llc_conn_action_t llc_normal_actions_17[] = { [5] = NULL, }; -static struct llc_conn_state_trans llc_normal_state_trans_17 = { +static const struct llc_conn_state_trans llc_normal_state_trans_17 = { .ev = llc_conn_ev_rx_rej_cmd_pbit_set_1, .next_state = LLC_CONN_STATE_NORMAL, .ev_qualifiers = NONE, @@ -1183,7 +1183,7 @@ static const llc_conn_action_t llc_normal_actions_18[] = { [2] = NULL, }; -static struct llc_conn_state_trans llc_normal_state_trans_18 = { +static const struct llc_conn_state_trans llc_normal_state_trans_18 = { .ev = llc_conn_ev_init_p_f_cycle, .next_state = LLC_CONN_STATE_NORMAL, .ev_qualifiers = llc_normal_ev_qfyrs_18, @@ -1205,7 +1205,7 @@ static const llc_conn_action_t llc_normal_actions_19[] = { [5] = NULL, }; -static struct llc_conn_state_trans llc_normal_state_trans_19 = { +static const struct llc_conn_state_trans llc_normal_state_trans_19 = { .ev = llc_conn_ev_p_tmr_exp, .next_state = LLC_CONN_STATE_AWAIT, .ev_qualifiers = llc_normal_ev_qfyrs_19, @@ -1228,7 +1228,7 @@ static const llc_conn_action_t llc_normal_actions_20a[] = { [5] = NULL, }; -static struct llc_conn_state_trans llc_normal_state_trans_20a = { +static const struct llc_conn_state_trans llc_normal_state_trans_20a = { .ev = llc_conn_ev_ack_tmr_exp, .next_state = LLC_CONN_STATE_AWAIT, .ev_qualifiers = llc_normal_ev_qfyrs_20a, @@ -1251,7 +1251,7 @@ static const llc_conn_action_t llc_normal_actions_20b[] = { [5] = NULL, }; -static struct llc_conn_state_trans llc_normal_state_trans_20b = { +static const struct llc_conn_state_trans llc_normal_state_trans_20b = { .ev = llc_conn_ev_busy_tmr_exp, .next_state = LLC_CONN_STATE_AWAIT, .ev_qualifiers = llc_normal_ev_qfyrs_20b, @@ -1270,7 +1270,7 @@ static const llc_conn_action_t llc_normal_actions_21[] = { [2] = NULL, }; -static struct llc_conn_state_trans llc_normal_state_trans_21 = { +static const struct llc_conn_state_trans llc_normal_state_trans_21 = { .ev = llc_conn_ev_tx_buffer_full, .next_state = LLC_CONN_STATE_NORMAL, .ev_qualifiers = llc_normal_ev_qfyrs_21, @@ -1281,7 +1281,7 @@ static struct llc_conn_state_trans llc_normal_state_trans_21 = { * Array of pointers; * one to each transition */ -static struct llc_conn_state_trans *llc_normal_state_transitions[] = { +static const struct llc_conn_state_trans *llc_normal_state_transitions[] = { [0] = &llc_normal_state_trans_1, /* Requests */ [1] = &llc_normal_state_trans_2, [2] = &llc_normal_state_trans_2_1, @@ -1354,7 +1354,7 @@ static const llc_conn_action_t llc_busy_actions_1[] = { [2] = NULL, }; -static struct llc_conn_state_trans llc_busy_state_trans_1 = { +static const struct llc_conn_state_trans llc_busy_state_trans_1 = { .ev = llc_conn_ev_data_req, .next_state = LLC_CONN_STATE_BUSY, .ev_qualifiers = llc_busy_ev_qfyrs_1, @@ -1374,7 +1374,7 @@ static const llc_conn_action_t llc_busy_actions_2[] = { [2] = NULL, }; -static struct llc_conn_state_trans llc_busy_state_trans_2 = { +static const struct llc_conn_state_trans llc_busy_state_trans_2 = { .ev = llc_conn_ev_data_req, .next_state = LLC_CONN_STATE_BUSY, .ev_qualifiers = llc_busy_ev_qfyrs_2, @@ -1391,7 +1391,7 @@ static const llc_conn_ev_qfyr_t llc_busy_ev_qfyrs_2_1[] = { /* just one member, NULL, .bss zeroes it */ static const llc_conn_action_t llc_busy_actions_2_1[1]; -static struct llc_conn_state_trans llc_busy_state_trans_2_1 = { +static const struct llc_conn_state_trans llc_busy_state_trans_2_1 = { .ev = llc_conn_ev_data_req, .next_state = LLC_CONN_STATE_BUSY, .ev_qualifiers = llc_busy_ev_qfyrs_2_1, @@ -1411,7 +1411,7 @@ static const llc_conn_action_t llc_busy_actions_3[] = { [2] = NULL, }; -static struct llc_conn_state_trans llc_busy_state_trans_3 = { +static const struct llc_conn_state_trans llc_busy_state_trans_3 = { .ev = llc_conn_ev_local_busy_cleared, .next_state = LLC_CONN_STATE_REJ, .ev_qualifiers = llc_busy_ev_qfyrs_3, @@ -1431,7 +1431,7 @@ static const llc_conn_action_t llc_busy_actions_4[] = { [2] = NULL, }; -static struct llc_conn_state_trans llc_busy_state_trans_4 = { +static const struct llc_conn_state_trans llc_busy_state_trans_4 = { .ev = llc_conn_ev_local_busy_cleared, .next_state = LLC_CONN_STATE_REJ, .ev_qualifiers = llc_busy_ev_qfyrs_4, @@ -1450,7 +1450,7 @@ static const llc_conn_action_t llc_busy_actions_5[] = { [1] = NULL, }; -static struct llc_conn_state_trans llc_busy_state_trans_5 = { +static const struct llc_conn_state_trans llc_busy_state_trans_5 = { .ev = llc_conn_ev_local_busy_cleared, .next_state = LLC_CONN_STATE_NORMAL, .ev_qualifiers = llc_busy_ev_qfyrs_5, @@ -1469,7 +1469,7 @@ static const llc_conn_action_t llc_busy_actions_6[] = { [1] = NULL, }; -static struct llc_conn_state_trans llc_busy_state_trans_6 = { +static const struct llc_conn_state_trans llc_busy_state_trans_6 = { .ev = llc_conn_ev_local_busy_cleared, .next_state = LLC_CONN_STATE_NORMAL, .ev_qualifiers = llc_busy_ev_qfyrs_6, @@ -1488,7 +1488,7 @@ static const llc_conn_action_t llc_busy_actions_7[] = { [1] = NULL, }; -static struct llc_conn_state_trans llc_busy_state_trans_7 = { +static const struct llc_conn_state_trans llc_busy_state_trans_7 = { .ev = llc_conn_ev_local_busy_cleared, .next_state = LLC_CONN_STATE_REJ, .ev_qualifiers = llc_busy_ev_qfyrs_7, @@ -1507,7 +1507,7 @@ static const llc_conn_action_t llc_busy_actions_8[] = { [1] = NULL, }; -static struct llc_conn_state_trans llc_busy_state_trans_8 = { +static const struct llc_conn_state_trans llc_busy_state_trans_8 = { .ev = llc_conn_ev_local_busy_cleared, .next_state = LLC_CONN_STATE_REJ, .ev_qualifiers = llc_busy_ev_qfyrs_8, @@ -1529,7 +1529,7 @@ static const llc_conn_action_t llc_busy_actions_9a[] = { [5] = NULL, }; -static struct llc_conn_state_trans llc_busy_state_trans_9a = { +static const struct llc_conn_state_trans llc_busy_state_trans_9a = { .ev = llc_conn_ev_rx_i_rsp_fbit_set_x_unexpd_ns, .next_state = LLC_CONN_STATE_BUSY, .ev_qualifiers = llc_busy_ev_qfyrs_9a, @@ -1551,7 +1551,7 @@ static const llc_conn_action_t llc_busy_actions_9b[] = { [5] = NULL, }; -static struct llc_conn_state_trans llc_busy_state_trans_9b = { +static const struct llc_conn_state_trans llc_busy_state_trans_9b = { .ev = llc_conn_ev_rx_i_cmd_pbit_set_0_unexpd_ns, .next_state = LLC_CONN_STATE_BUSY, .ev_qualifiers = llc_busy_ev_qfyrs_9b, @@ -1571,7 +1571,7 @@ static const llc_conn_action_t llc_busy_actions_10a[] = { [3] = NULL, }; -static struct llc_conn_state_trans llc_busy_state_trans_10a = { +static const struct llc_conn_state_trans llc_busy_state_trans_10a = { .ev = llc_conn_ev_rx_i_rsp_fbit_set_0_unexpd_ns, .next_state = LLC_CONN_STATE_BUSY, .ev_qualifiers = llc_busy_ev_qfyrs_10a, @@ -1591,7 +1591,7 @@ static const llc_conn_action_t llc_busy_actions_10b[] = { [3] = NULL, }; -static struct llc_conn_state_trans llc_busy_state_trans_10b = { +static const struct llc_conn_state_trans llc_busy_state_trans_10b = { .ev = llc_conn_ev_rx_i_cmd_pbit_set_0_unexpd_ns, .next_state = LLC_CONN_STATE_BUSY, .ev_qualifiers = llc_busy_ev_qfyrs_10b, @@ -1606,7 +1606,7 @@ static const llc_conn_action_t llc_busy_actions_11[] = { [3] = NULL, }; -static struct llc_conn_state_trans llc_busy_state_trans_11 = { +static const struct llc_conn_state_trans llc_busy_state_trans_11 = { .ev = llc_conn_ev_rx_i_cmd_pbit_set_1_unexpd_ns, .next_state = LLC_CONN_STATE_BUSY, .ev_qualifiers = NONE, @@ -1624,7 +1624,7 @@ static const llc_conn_action_t llc_busy_actions_12[] = { [6] = NULL, }; -static struct llc_conn_state_trans llc_busy_state_trans_12 = { +static const struct llc_conn_state_trans llc_busy_state_trans_12 = { .ev = llc_conn_ev_rx_i_cmd_pbit_set_1, .next_state = LLC_CONN_STATE_BUSY, .ev_qualifiers = NONE, @@ -1649,7 +1649,7 @@ static const llc_conn_action_t llc_busy_actions_13a[] = { [8] = NULL, }; -static struct llc_conn_state_trans llc_busy_state_trans_13a = { +static const struct llc_conn_state_trans llc_busy_state_trans_13a = { .ev = llc_conn_ev_rx_i_rsp_fbit_set_x, .next_state = LLC_CONN_STATE_BUSY, .ev_qualifiers = llc_busy_ev_qfyrs_13a, @@ -1674,7 +1674,7 @@ static const llc_conn_action_t llc_busy_actions_13b[] = { [8] = NULL, }; -static struct llc_conn_state_trans llc_busy_state_trans_13b = { +static const struct llc_conn_state_trans llc_busy_state_trans_13b = { .ev = llc_conn_ev_rx_i_cmd_pbit_set_0, .next_state = LLC_CONN_STATE_BUSY, .ev_qualifiers = llc_busy_ev_qfyrs_13b, @@ -1697,7 +1697,7 @@ static const llc_conn_action_t llc_busy_actions_14a[] = { [6] = NULL, }; -static struct llc_conn_state_trans llc_busy_state_trans_14a = { +static const struct llc_conn_state_trans llc_busy_state_trans_14a = { .ev = llc_conn_ev_rx_i_rsp_fbit_set_0, .next_state = LLC_CONN_STATE_BUSY, .ev_qualifiers = llc_busy_ev_qfyrs_14a, @@ -1720,7 +1720,7 @@ static const llc_conn_action_t llc_busy_actions_14b[] = { [6] = NULL, }; -static struct llc_conn_state_trans llc_busy_state_trans_14b = { +static const struct llc_conn_state_trans llc_busy_state_trans_14b = { .ev = llc_conn_ev_rx_i_cmd_pbit_set_0, .next_state = LLC_CONN_STATE_BUSY, .ev_qualifiers = llc_busy_ev_qfyrs_14b, @@ -1735,7 +1735,7 @@ static const llc_conn_action_t llc_busy_actions_15a[] = { [3] = NULL, }; -static struct llc_conn_state_trans llc_busy_state_trans_15a = { +static const struct llc_conn_state_trans llc_busy_state_trans_15a = { .ev = llc_conn_ev_rx_rr_cmd_pbit_set_0, .next_state = LLC_CONN_STATE_BUSY, .ev_qualifiers = NONE, @@ -1750,7 +1750,7 @@ static const llc_conn_action_t llc_busy_actions_15b[] = { [3] = NULL, }; -static struct llc_conn_state_trans llc_busy_state_trans_15b = { +static const struct llc_conn_state_trans llc_busy_state_trans_15b = { .ev = llc_conn_ev_rx_rr_rsp_fbit_set_0, .next_state = LLC_CONN_STATE_BUSY, .ev_qualifiers = NONE, @@ -1770,7 +1770,7 @@ static const llc_conn_action_t llc_busy_actions_15c[] = { [3] = NULL, }; -static struct llc_conn_state_trans llc_busy_state_trans_15c = { +static const struct llc_conn_state_trans llc_busy_state_trans_15c = { .ev = llc_conn_ev_rx_rr_rsp_fbit_set_1, .next_state = LLC_CONN_STATE_BUSY, .ev_qualifiers = llc_busy_ev_qfyrs_15c, @@ -1785,7 +1785,7 @@ static const llc_conn_action_t llc_busy_actions_16[] = { [3] = NULL, }; -static struct llc_conn_state_trans llc_busy_state_trans_16 = { +static const struct llc_conn_state_trans llc_busy_state_trans_16 = { .ev = llc_conn_ev_rx_rr_cmd_pbit_set_1, .next_state = LLC_CONN_STATE_BUSY, .ev_qualifiers = NONE, @@ -1800,7 +1800,7 @@ static const llc_conn_action_t llc_busy_actions_17a[] = { [3] = NULL, }; -static struct llc_conn_state_trans llc_busy_state_trans_17a = { +static const struct llc_conn_state_trans llc_busy_state_trans_17a = { .ev = llc_conn_ev_rx_rnr_cmd_pbit_set_0, .next_state = LLC_CONN_STATE_BUSY, .ev_qualifiers = NONE, @@ -1815,7 +1815,7 @@ static const llc_conn_action_t llc_busy_actions_17b[] = { [3] = NULL, }; -static struct llc_conn_state_trans llc_busy_state_trans_17b = { +static const struct llc_conn_state_trans llc_busy_state_trans_17b = { .ev = llc_conn_ev_rx_rnr_rsp_fbit_set_0, .next_state = LLC_CONN_STATE_BUSY, .ev_qualifiers = NONE, @@ -1835,7 +1835,7 @@ static const llc_conn_action_t llc_busy_actions_17c[] = { [3] = NULL, }; -static struct llc_conn_state_trans llc_busy_state_trans_17c = { +static const struct llc_conn_state_trans llc_busy_state_trans_17c = { .ev = llc_conn_ev_rx_rnr_rsp_fbit_set_1, .next_state = LLC_CONN_STATE_BUSY, .ev_qualifiers = llc_busy_ev_qfyrs_17c, @@ -1850,7 +1850,7 @@ static const llc_conn_action_t llc_busy_actions_18[] = { [3] = NULL, }; -static struct llc_conn_state_trans llc_busy_state_trans_18 = { +static const struct llc_conn_state_trans llc_busy_state_trans_18 = { .ev = llc_conn_ev_rx_rnr_cmd_pbit_set_1, .next_state = LLC_CONN_STATE_BUSY, .ev_qualifiers = NONE, @@ -1872,7 +1872,7 @@ static const llc_conn_action_t llc_busy_actions_19a[] = { [5] = NULL, }; -static struct llc_conn_state_trans llc_busy_state_trans_19a = { +static const struct llc_conn_state_trans llc_busy_state_trans_19a = { .ev = llc_conn_ev_rx_rej_cmd_pbit_set_0, .next_state = LLC_CONN_STATE_BUSY, .ev_qualifiers = llc_busy_ev_qfyrs_19a, @@ -1894,7 +1894,7 @@ static const llc_conn_action_t llc_busy_actions_19b[] = { [5] = NULL, }; -static struct llc_conn_state_trans llc_busy_state_trans_19b = { +static const struct llc_conn_state_trans llc_busy_state_trans_19b = { .ev = llc_conn_ev_rx_rej_rsp_fbit_set_x, .next_state = LLC_CONN_STATE_BUSY, .ev_qualifiers = llc_busy_ev_qfyrs_19b, @@ -1915,7 +1915,7 @@ static const llc_conn_action_t llc_busy_actions_20a[] = { [4] = NULL, }; -static struct llc_conn_state_trans llc_busy_state_trans_20a = { +static const struct llc_conn_state_trans llc_busy_state_trans_20a = { .ev = llc_conn_ev_rx_rej_cmd_pbit_set_0, .next_state = LLC_CONN_STATE_BUSY, .ev_qualifiers = llc_busy_ev_qfyrs_20a, @@ -1936,7 +1936,7 @@ static const llc_conn_action_t llc_busy_actions_20b[] = { [4] = NULL, }; -static struct llc_conn_state_trans llc_busy_state_trans_20b = { +static const struct llc_conn_state_trans llc_busy_state_trans_20b = { .ev = llc_conn_ev_rx_rej_rsp_fbit_set_0, .next_state = LLC_CONN_STATE_BUSY, .ev_qualifiers = llc_busy_ev_qfyrs_20b, @@ -1953,7 +1953,7 @@ static const llc_conn_action_t llc_busy_actions_21[] = { [5] = NULL, }; -static struct llc_conn_state_trans llc_busy_state_trans_21 = { +static const struct llc_conn_state_trans llc_busy_state_trans_21 = { .ev = llc_conn_ev_rx_rej_cmd_pbit_set_1, .next_state = LLC_CONN_STATE_BUSY, .ev_qualifiers = NONE, @@ -1972,7 +1972,7 @@ static const llc_conn_action_t llc_busy_actions_22[] = { [2] = NULL, }; -static struct llc_conn_state_trans llc_busy_state_trans_22 = { +static const struct llc_conn_state_trans llc_busy_state_trans_22 = { .ev = llc_conn_ev_init_p_f_cycle, .next_state = LLC_CONN_STATE_BUSY, .ev_qualifiers = llc_busy_ev_qfyrs_22, @@ -1993,7 +1993,7 @@ static const llc_conn_action_t llc_busy_actions_23[] = { [4] = NULL, }; -static struct llc_conn_state_trans llc_busy_state_trans_23 = { +static const struct llc_conn_state_trans llc_busy_state_trans_23 = { .ev = llc_conn_ev_p_tmr_exp, .next_state = LLC_CONN_STATE_AWAIT_BUSY, .ev_qualifiers = llc_busy_ev_qfyrs_23, @@ -2015,7 +2015,7 @@ static const llc_conn_action_t llc_busy_actions_24a[] = { [4] = NULL, }; -static struct llc_conn_state_trans llc_busy_state_trans_24a = { +static const struct llc_conn_state_trans llc_busy_state_trans_24a = { .ev = llc_conn_ev_ack_tmr_exp, .next_state = LLC_CONN_STATE_AWAIT_BUSY, .ev_qualifiers = llc_busy_ev_qfyrs_24a, @@ -2037,7 +2037,7 @@ static const llc_conn_action_t llc_busy_actions_24b[] = { [4] = NULL, }; -static struct llc_conn_state_trans llc_busy_state_trans_24b = { +static const struct llc_conn_state_trans llc_busy_state_trans_24b = { .ev = llc_conn_ev_busy_tmr_exp, .next_state = LLC_CONN_STATE_AWAIT_BUSY, .ev_qualifiers = llc_busy_ev_qfyrs_24b, @@ -2060,7 +2060,7 @@ static const llc_conn_action_t llc_busy_actions_25[] = { [5] = NULL, }; -static struct llc_conn_state_trans llc_busy_state_trans_25 = { +static const struct llc_conn_state_trans llc_busy_state_trans_25 = { .ev = llc_conn_ev_rej_tmr_exp, .next_state = LLC_CONN_STATE_AWAIT_BUSY, .ev_qualifiers = llc_busy_ev_qfyrs_25, @@ -2079,7 +2079,7 @@ static const llc_conn_action_t llc_busy_actions_26[] = { [1] = NULL, }; -static struct llc_conn_state_trans llc_busy_state_trans_26 = { +static const struct llc_conn_state_trans llc_busy_state_trans_26 = { .ev = llc_conn_ev_rej_tmr_exp, .next_state = LLC_CONN_STATE_BUSY, .ev_qualifiers = llc_busy_ev_qfyrs_26, @@ -2090,7 +2090,7 @@ static struct llc_conn_state_trans llc_busy_state_trans_26 = { * Array of pointers; * one to each transition */ -static struct llc_conn_state_trans *llc_busy_state_transitions[] = { +static const struct llc_conn_state_trans *llc_busy_state_transitions[] = { [0] = &llc_common_state_trans_1, /* Request */ [1] = &llc_common_state_trans_2, [2] = &llc_busy_state_trans_1, @@ -2166,7 +2166,7 @@ static const llc_conn_action_t llc_reject_actions_1[] = { [1] = NULL, }; -static struct llc_conn_state_trans llc_reject_state_trans_1 = { +static const struct llc_conn_state_trans llc_reject_state_trans_1 = { .ev = llc_conn_ev_data_req, .next_state = LLC_CONN_STATE_REJ, .ev_qualifiers = llc_reject_ev_qfyrs_1, @@ -2185,7 +2185,7 @@ static const llc_conn_action_t llc_reject_actions_2[] = { [1] = NULL, }; -static struct llc_conn_state_trans llc_reject_state_trans_2 = { +static const struct llc_conn_state_trans llc_reject_state_trans_2 = { .ev = llc_conn_ev_data_req, .next_state = LLC_CONN_STATE_REJ, .ev_qualifiers = llc_reject_ev_qfyrs_2, @@ -2202,7 +2202,7 @@ static const llc_conn_ev_qfyr_t llc_reject_ev_qfyrs_2_1[] = { /* just one member, NULL, .bss zeroes it */ static const llc_conn_action_t llc_reject_actions_2_1[1]; -static struct llc_conn_state_trans llc_reject_state_trans_2_1 = { +static const struct llc_conn_state_trans llc_reject_state_trans_2_1 = { .ev = llc_conn_ev_data_req, .next_state = LLC_CONN_STATE_REJ, .ev_qualifiers = llc_reject_ev_qfyrs_2_1, @@ -2222,7 +2222,7 @@ static const llc_conn_action_t llc_reject_actions_3[] = { [2] = NULL, }; -static struct llc_conn_state_trans llc_reject_state_trans_3 = { +static const struct llc_conn_state_trans llc_reject_state_trans_3 = { .ev = llc_conn_ev_local_busy_detected, .next_state = LLC_CONN_STATE_BUSY, .ev_qualifiers = llc_reject_ev_qfyrs_3, @@ -2241,7 +2241,7 @@ static const llc_conn_action_t llc_reject_actions_4[] = { [2] = NULL, }; -static struct llc_conn_state_trans llc_reject_state_trans_4 = { +static const struct llc_conn_state_trans llc_reject_state_trans_4 = { .ev = llc_conn_ev_local_busy_detected, .next_state = LLC_CONN_STATE_BUSY, .ev_qualifiers = llc_reject_ev_qfyrs_4, @@ -2256,7 +2256,7 @@ static const llc_conn_action_t llc_reject_actions_5a[] = { [3] = NULL, }; -static struct llc_conn_state_trans llc_reject_state_trans_5a = { +static const struct llc_conn_state_trans llc_reject_state_trans_5a = { .ev = llc_conn_ev_rx_i_cmd_pbit_set_0_unexpd_ns, .next_state = LLC_CONN_STATE_REJ, .ev_qualifiers = NONE, @@ -2271,7 +2271,7 @@ static const llc_conn_action_t llc_reject_actions_5b[] = { [3] = NULL, }; -static struct llc_conn_state_trans llc_reject_state_trans_5b = { +static const struct llc_conn_state_trans llc_reject_state_trans_5b = { .ev = llc_conn_ev_rx_i_rsp_fbit_set_0_unexpd_ns, .next_state = LLC_CONN_STATE_REJ, .ev_qualifiers = NONE, @@ -2291,7 +2291,7 @@ static const llc_conn_action_t llc_reject_actions_5c[] = { [3] = NULL, }; -static struct llc_conn_state_trans llc_reject_state_trans_5c = { +static const struct llc_conn_state_trans llc_reject_state_trans_5c = { .ev = llc_conn_ev_rx_i_rsp_fbit_set_1_unexpd_ns, .next_state = LLC_CONN_STATE_REJ, .ev_qualifiers = llc_reject_ev_qfyrs_5c, @@ -2305,7 +2305,7 @@ static const llc_conn_action_t llc_reject_actions_6[] = { [2] = NULL, }; -static struct llc_conn_state_trans llc_reject_state_trans_6 = { +static const struct llc_conn_state_trans llc_reject_state_trans_6 = { .ev = llc_conn_ev_rx_i_cmd_pbit_set_1_unexpd_ns, .next_state = LLC_CONN_STATE_REJ, .ev_qualifiers = NONE, @@ -2330,7 +2330,7 @@ static const llc_conn_action_t llc_reject_actions_7a[] = { }; -static struct llc_conn_state_trans llc_reject_state_trans_7a = { +static const struct llc_conn_state_trans llc_reject_state_trans_7a = { .ev = llc_conn_ev_rx_i_rsp_fbit_set_x, .next_state = LLC_CONN_STATE_NORMAL, .ev_qualifiers = llc_reject_ev_qfyrs_7a, @@ -2354,7 +2354,7 @@ static const llc_conn_action_t llc_reject_actions_7b[] = { [7] = NULL, }; -static struct llc_conn_state_trans llc_reject_state_trans_7b = { +static const struct llc_conn_state_trans llc_reject_state_trans_7b = { .ev = llc_conn_ev_rx_i_cmd_pbit_set_0, .next_state = LLC_CONN_STATE_NORMAL, .ev_qualifiers = llc_reject_ev_qfyrs_7b, @@ -2376,7 +2376,7 @@ static const llc_conn_action_t llc_reject_actions_8a[] = { [5] = NULL, }; -static struct llc_conn_state_trans llc_reject_state_trans_8a = { +static const struct llc_conn_state_trans llc_reject_state_trans_8a = { .ev = llc_conn_ev_rx_i_rsp_fbit_set_0, .next_state = LLC_CONN_STATE_NORMAL, .ev_qualifiers = llc_reject_ev_qfyrs_8a, @@ -2398,7 +2398,7 @@ static const llc_conn_action_t llc_reject_actions_8b[] = { [5] = NULL, }; -static struct llc_conn_state_trans llc_reject_state_trans_8b = { +static const struct llc_conn_state_trans llc_reject_state_trans_8b = { .ev = llc_conn_ev_rx_i_cmd_pbit_set_0, .next_state = LLC_CONN_STATE_NORMAL, .ev_qualifiers = llc_reject_ev_qfyrs_8b, @@ -2415,7 +2415,7 @@ static const llc_conn_action_t llc_reject_actions_9[] = { [5] = NULL, }; -static struct llc_conn_state_trans llc_reject_state_trans_9 = { +static const struct llc_conn_state_trans llc_reject_state_trans_9 = { .ev = llc_conn_ev_rx_i_cmd_pbit_set_1, .next_state = LLC_CONN_STATE_NORMAL, .ev_qualifiers = NONE, @@ -2430,7 +2430,7 @@ static const llc_conn_action_t llc_reject_actions_10a[] = { [3] = NULL, }; -static struct llc_conn_state_trans llc_reject_state_trans_10a = { +static const struct llc_conn_state_trans llc_reject_state_trans_10a = { .ev = llc_conn_ev_rx_rr_cmd_pbit_set_0, .next_state = LLC_CONN_STATE_REJ, .ev_qualifiers = NONE, @@ -2445,7 +2445,7 @@ static const llc_conn_action_t llc_reject_actions_10b[] = { [3] = NULL, }; -static struct llc_conn_state_trans llc_reject_state_trans_10b = { +static const struct llc_conn_state_trans llc_reject_state_trans_10b = { .ev = llc_conn_ev_rx_rr_rsp_fbit_set_0, .next_state = LLC_CONN_STATE_REJ, .ev_qualifiers = NONE, @@ -2465,7 +2465,7 @@ static const llc_conn_action_t llc_reject_actions_10c[] = { [3] = NULL, }; -static struct llc_conn_state_trans llc_reject_state_trans_10c = { +static const struct llc_conn_state_trans llc_reject_state_trans_10c = { .ev = llc_conn_ev_rx_rr_rsp_fbit_set_1, .next_state = LLC_CONN_STATE_REJ, .ev_qualifiers = llc_reject_ev_qfyrs_10c, @@ -2480,7 +2480,7 @@ static const llc_conn_action_t llc_reject_actions_11[] = { [3] = NULL, }; -static struct llc_conn_state_trans llc_reject_state_trans_11 = { +static const struct llc_conn_state_trans llc_reject_state_trans_11 = { .ev = llc_conn_ev_rx_rr_cmd_pbit_set_1, .next_state = LLC_CONN_STATE_REJ, .ev_qualifiers = NONE, @@ -2495,7 +2495,7 @@ static const llc_conn_action_t llc_reject_actions_12a[] = { [3] = NULL, }; -static struct llc_conn_state_trans llc_reject_state_trans_12a = { +static const struct llc_conn_state_trans llc_reject_state_trans_12a = { .ev = llc_conn_ev_rx_rnr_cmd_pbit_set_0, .next_state = LLC_CONN_STATE_REJ, .ev_qualifiers = NONE, @@ -2510,7 +2510,7 @@ static const llc_conn_action_t llc_reject_actions_12b[] = { [3] = NULL, }; -static struct llc_conn_state_trans llc_reject_state_trans_12b = { +static const struct llc_conn_state_trans llc_reject_state_trans_12b = { .ev = llc_conn_ev_rx_rnr_rsp_fbit_set_0, .next_state = LLC_CONN_STATE_REJ, .ev_qualifiers = NONE, @@ -2530,7 +2530,7 @@ static const llc_conn_action_t llc_reject_actions_12c[] = { [3] = NULL, }; -static struct llc_conn_state_trans llc_reject_state_trans_12c = { +static const struct llc_conn_state_trans llc_reject_state_trans_12c = { .ev = llc_conn_ev_rx_rnr_rsp_fbit_set_1, .next_state = LLC_CONN_STATE_REJ, .ev_qualifiers = llc_reject_ev_qfyrs_12c, @@ -2545,7 +2545,7 @@ static const llc_conn_action_t llc_reject_actions_13[] = { [3] = NULL, }; -static struct llc_conn_state_trans llc_reject_state_trans_13 = { +static const struct llc_conn_state_trans llc_reject_state_trans_13 = { .ev = llc_conn_ev_rx_rnr_cmd_pbit_set_1, .next_state = LLC_CONN_STATE_REJ, .ev_qualifiers = NONE, @@ -2567,7 +2567,7 @@ static const llc_conn_action_t llc_reject_actions_14a[] = { [5] = NULL, }; -static struct llc_conn_state_trans llc_reject_state_trans_14a = { +static const struct llc_conn_state_trans llc_reject_state_trans_14a = { .ev = llc_conn_ev_rx_rej_cmd_pbit_set_0, .next_state = LLC_CONN_STATE_REJ, .ev_qualifiers = llc_reject_ev_qfyrs_14a, @@ -2589,7 +2589,7 @@ static const llc_conn_action_t llc_reject_actions_14b[] = { [5] = NULL, }; -static struct llc_conn_state_trans llc_reject_state_trans_14b = { +static const struct llc_conn_state_trans llc_reject_state_trans_14b = { .ev = llc_conn_ev_rx_rej_rsp_fbit_set_x, .next_state = LLC_CONN_STATE_REJ, .ev_qualifiers = llc_reject_ev_qfyrs_14b, @@ -2610,7 +2610,7 @@ static const llc_conn_action_t llc_reject_actions_15a[] = { [4] = NULL, }; -static struct llc_conn_state_trans llc_reject_state_trans_15a = { +static const struct llc_conn_state_trans llc_reject_state_trans_15a = { .ev = llc_conn_ev_rx_rej_cmd_pbit_set_0, .next_state = LLC_CONN_STATE_REJ, .ev_qualifiers = llc_reject_ev_qfyrs_15a, @@ -2631,7 +2631,7 @@ static const llc_conn_action_t llc_reject_actions_15b[] = { [4] = NULL, }; -static struct llc_conn_state_trans llc_reject_state_trans_15b = { +static const struct llc_conn_state_trans llc_reject_state_trans_15b = { .ev = llc_conn_ev_rx_rej_rsp_fbit_set_0, .next_state = LLC_CONN_STATE_REJ, .ev_qualifiers = llc_reject_ev_qfyrs_15b, @@ -2647,7 +2647,7 @@ static const llc_conn_action_t llc_reject_actions_16[] = { [4] = NULL, }; -static struct llc_conn_state_trans llc_reject_state_trans_16 = { +static const struct llc_conn_state_trans llc_reject_state_trans_16 = { .ev = llc_conn_ev_rx_rej_cmd_pbit_set_1, .next_state = LLC_CONN_STATE_REJ, .ev_qualifiers = NONE, @@ -2666,7 +2666,7 @@ static const llc_conn_action_t llc_reject_actions_17[] = { [2] = NULL, }; -static struct llc_conn_state_trans llc_reject_state_trans_17 = { +static const struct llc_conn_state_trans llc_reject_state_trans_17 = { .ev = llc_conn_ev_init_p_f_cycle, .next_state = LLC_CONN_STATE_REJ, .ev_qualifiers = llc_reject_ev_qfyrs_17, @@ -2688,7 +2688,7 @@ static const llc_conn_action_t llc_reject_actions_18[] = { [4] = NULL, }; -static struct llc_conn_state_trans llc_reject_state_trans_18 = { +static const struct llc_conn_state_trans llc_reject_state_trans_18 = { .ev = llc_conn_ev_rej_tmr_exp, .next_state = LLC_CONN_STATE_REJ, .ev_qualifiers = llc_reject_ev_qfyrs_18, @@ -2710,7 +2710,7 @@ static const llc_conn_action_t llc_reject_actions_19[] = { [5] = NULL, }; -static struct llc_conn_state_trans llc_reject_state_trans_19 = { +static const struct llc_conn_state_trans llc_reject_state_trans_19 = { .ev = llc_conn_ev_p_tmr_exp, .next_state = LLC_CONN_STATE_AWAIT_REJ, .ev_qualifiers = llc_reject_ev_qfyrs_19, @@ -2733,7 +2733,7 @@ static const llc_conn_action_t llc_reject_actions_20a[] = { [5] = NULL, }; -static struct llc_conn_state_trans llc_reject_state_trans_20a = { +static const struct llc_conn_state_trans llc_reject_state_trans_20a = { .ev = llc_conn_ev_ack_tmr_exp, .next_state = LLC_CONN_STATE_AWAIT_REJ, .ev_qualifiers = llc_reject_ev_qfyrs_20a, @@ -2756,7 +2756,7 @@ static const llc_conn_action_t llc_reject_actions_20b[] = { [5] = NULL, }; -static struct llc_conn_state_trans llc_reject_state_trans_20b = { +static const struct llc_conn_state_trans llc_reject_state_trans_20b = { .ev = llc_conn_ev_busy_tmr_exp, .next_state = LLC_CONN_STATE_AWAIT_REJ, .ev_qualifiers = llc_reject_ev_qfyrs_20b, @@ -2767,7 +2767,7 @@ static struct llc_conn_state_trans llc_reject_state_trans_20b = { * Array of pointers; * one to each transition */ -static struct llc_conn_state_trans *llc_reject_state_transitions[] = { +static const struct llc_conn_state_trans *llc_reject_state_transitions[] = { [0] = &llc_common_state_trans_1, /* Request */ [1] = &llc_common_state_trans_2, [2] = &llc_common_state_trans_end, @@ -2834,7 +2834,7 @@ static const llc_conn_ev_qfyr_t llc_await_ev_qfyrs_1_0[] = { /* just one member, NULL, .bss zeroes it */ static const llc_conn_action_t llc_await_actions_1_0[1]; -static struct llc_conn_state_trans llc_await_state_trans_1_0 = { +static const struct llc_conn_state_trans llc_await_state_trans_1_0 = { .ev = llc_conn_ev_data_req, .next_state = LLC_CONN_STATE_AWAIT, .ev_qualifiers = llc_await_ev_qfyrs_1_0, @@ -2848,7 +2848,7 @@ static const llc_conn_action_t llc_await_actions_1[] = { [2] = NULL, }; -static struct llc_conn_state_trans llc_await_state_trans_1 = { +static const struct llc_conn_state_trans llc_await_state_trans_1 = { .ev = llc_conn_ev_local_busy_detected, .next_state = LLC_CONN_STATE_AWAIT_BUSY, .ev_qualifiers = NONE, @@ -2867,7 +2867,7 @@ static const llc_conn_action_t llc_await_actions_2[] = { [7] = NULL, }; -static struct llc_conn_state_trans llc_await_state_trans_2 = { +static const struct llc_conn_state_trans llc_await_state_trans_2 = { .ev = llc_conn_ev_rx_i_rsp_fbit_set_1_unexpd_ns, .next_state = LLC_CONN_STATE_REJ, .ev_qualifiers = NONE, @@ -2883,7 +2883,7 @@ static const llc_conn_action_t llc_await_actions_3a[] = { [4] = NULL, }; -static struct llc_conn_state_trans llc_await_state_trans_3a = { +static const struct llc_conn_state_trans llc_await_state_trans_3a = { .ev = llc_conn_ev_rx_i_cmd_pbit_set_0_unexpd_ns, .next_state = LLC_CONN_STATE_AWAIT_REJ, .ev_qualifiers = NONE, @@ -2899,7 +2899,7 @@ static const llc_conn_action_t llc_await_actions_3b[] = { [4] = NULL, }; -static struct llc_conn_state_trans llc_await_state_trans_3b = { +static const struct llc_conn_state_trans llc_await_state_trans_3b = { .ev = llc_conn_ev_rx_i_rsp_fbit_set_0_unexpd_ns, .next_state = LLC_CONN_STATE_AWAIT_REJ, .ev_qualifiers = NONE, @@ -2916,7 +2916,7 @@ static const llc_conn_action_t llc_await_actions_4[] = { [5] = NULL, }; -static struct llc_conn_state_trans llc_await_state_trans_4 = { +static const struct llc_conn_state_trans llc_await_state_trans_4 = { .ev = llc_conn_ev_rx_i_cmd_pbit_set_1_unexpd_ns, .next_state = LLC_CONN_STATE_AWAIT_REJ, .ev_qualifiers = NONE, @@ -2935,7 +2935,7 @@ static const llc_conn_action_t llc_await_actions_5[] = { [7] = NULL, }; -static struct llc_conn_state_trans llc_await_state_trans_5 = { +static const struct llc_conn_state_trans llc_await_state_trans_5 = { .ev = llc_conn_ev_rx_i_rsp_fbit_set_1, .next_state = LLC_CONN_STATE_NORMAL, .ev_qualifiers = NONE, @@ -2952,7 +2952,7 @@ static const llc_conn_action_t llc_await_actions_6a[] = { [5] = NULL, }; -static struct llc_conn_state_trans llc_await_state_trans_6a = { +static const struct llc_conn_state_trans llc_await_state_trans_6a = { .ev = llc_conn_ev_rx_i_rsp_fbit_set_0, .next_state = LLC_CONN_STATE_AWAIT, .ev_qualifiers = NONE, @@ -2969,7 +2969,7 @@ static const llc_conn_action_t llc_await_actions_6b[] = { [5] = NULL, }; -static struct llc_conn_state_trans llc_await_state_trans_6b = { +static const struct llc_conn_state_trans llc_await_state_trans_6b = { .ev = llc_conn_ev_rx_i_cmd_pbit_set_0, .next_state = LLC_CONN_STATE_AWAIT, .ev_qualifiers = NONE, @@ -2986,7 +2986,7 @@ static const llc_conn_action_t llc_await_actions_7[] = { [5] = NULL, }; -static struct llc_conn_state_trans llc_await_state_trans_7 = { +static const struct llc_conn_state_trans llc_await_state_trans_7 = { .ev = llc_conn_ev_rx_i_cmd_pbit_set_1, .next_state = LLC_CONN_STATE_AWAIT, .ev_qualifiers = NONE, @@ -3003,7 +3003,7 @@ static const llc_conn_action_t llc_await_actions_8a[] = { [5] = NULL, }; -static struct llc_conn_state_trans llc_await_state_trans_8a = { +static const struct llc_conn_state_trans llc_await_state_trans_8a = { .ev = llc_conn_ev_rx_rr_rsp_fbit_set_1, .next_state = LLC_CONN_STATE_NORMAL, .ev_qualifiers = NONE, @@ -3020,7 +3020,7 @@ static const llc_conn_action_t llc_await_actions_8b[] = { [5] = NULL, }; -static struct llc_conn_state_trans llc_await_state_trans_8b = { +static const struct llc_conn_state_trans llc_await_state_trans_8b = { .ev = llc_conn_ev_rx_rej_rsp_fbit_set_1, .next_state = LLC_CONN_STATE_NORMAL, .ev_qualifiers = NONE, @@ -3035,7 +3035,7 @@ static const llc_conn_action_t llc_await_actions_9a[] = { [3] = NULL, }; -static struct llc_conn_state_trans llc_await_state_trans_9a = { +static const struct llc_conn_state_trans llc_await_state_trans_9a = { .ev = llc_conn_ev_rx_rr_cmd_pbit_set_0, .next_state = LLC_CONN_STATE_AWAIT, .ev_qualifiers = NONE, @@ -3050,7 +3050,7 @@ static const llc_conn_action_t llc_await_actions_9b[] = { [3] = NULL, }; -static struct llc_conn_state_trans llc_await_state_trans_9b = { +static const struct llc_conn_state_trans llc_await_state_trans_9b = { .ev = llc_conn_ev_rx_rr_rsp_fbit_set_0, .next_state = LLC_CONN_STATE_AWAIT, .ev_qualifiers = NONE, @@ -3065,7 +3065,7 @@ static const llc_conn_action_t llc_await_actions_9c[] = { [3] = NULL, }; -static struct llc_conn_state_trans llc_await_state_trans_9c = { +static const struct llc_conn_state_trans llc_await_state_trans_9c = { .ev = llc_conn_ev_rx_rej_cmd_pbit_set_0, .next_state = LLC_CONN_STATE_AWAIT, .ev_qualifiers = NONE, @@ -3080,7 +3080,7 @@ static const llc_conn_action_t llc_await_actions_9d[] = { [3] = NULL, }; -static struct llc_conn_state_trans llc_await_state_trans_9d = { +static const struct llc_conn_state_trans llc_await_state_trans_9d = { .ev = llc_conn_ev_rx_rej_rsp_fbit_set_0, .next_state = LLC_CONN_STATE_AWAIT, .ev_qualifiers = NONE, @@ -3096,7 +3096,7 @@ static const llc_conn_action_t llc_await_actions_10a[] = { [4] = NULL, }; -static struct llc_conn_state_trans llc_await_state_trans_10a = { +static const struct llc_conn_state_trans llc_await_state_trans_10a = { .ev = llc_conn_ev_rx_rr_cmd_pbit_set_1, .next_state = LLC_CONN_STATE_AWAIT, .ev_qualifiers = NONE, @@ -3112,7 +3112,7 @@ static const llc_conn_action_t llc_await_actions_10b[] = { [4] = NULL, }; -static struct llc_conn_state_trans llc_await_state_trans_10b = { +static const struct llc_conn_state_trans llc_await_state_trans_10b = { .ev = llc_conn_ev_rx_rej_cmd_pbit_set_1, .next_state = LLC_CONN_STATE_AWAIT, .ev_qualifiers = NONE, @@ -3128,7 +3128,7 @@ static const llc_conn_action_t llc_await_actions_11[] = { [4] = NULL, }; -static struct llc_conn_state_trans llc_await_state_trans_11 = { +static const struct llc_conn_state_trans llc_await_state_trans_11 = { .ev = llc_conn_ev_rx_rnr_rsp_fbit_set_1, .next_state = LLC_CONN_STATE_NORMAL, .ev_qualifiers = NONE, @@ -3143,7 +3143,7 @@ static const llc_conn_action_t llc_await_actions_12a[] = { [3] = NULL, }; -static struct llc_conn_state_trans llc_await_state_trans_12a = { +static const struct llc_conn_state_trans llc_await_state_trans_12a = { .ev = llc_conn_ev_rx_rnr_cmd_pbit_set_0, .next_state = LLC_CONN_STATE_AWAIT, .ev_qualifiers = NONE, @@ -3158,7 +3158,7 @@ static const llc_conn_action_t llc_await_actions_12b[] = { [3] = NULL, }; -static struct llc_conn_state_trans llc_await_state_trans_12b = { +static const struct llc_conn_state_trans llc_await_state_trans_12b = { .ev = llc_conn_ev_rx_rnr_rsp_fbit_set_0, .next_state = LLC_CONN_STATE_AWAIT, .ev_qualifiers = NONE, @@ -3174,7 +3174,7 @@ static const llc_conn_action_t llc_await_actions_13[] = { [4] = NULL, }; -static struct llc_conn_state_trans llc_await_state_trans_13 = { +static const struct llc_conn_state_trans llc_await_state_trans_13 = { .ev = llc_conn_ev_rx_rnr_cmd_pbit_set_1, .next_state = LLC_CONN_STATE_AWAIT, .ev_qualifiers = NONE, @@ -3194,7 +3194,7 @@ static const llc_conn_action_t llc_await_actions_14[] = { [3] = NULL, }; -static struct llc_conn_state_trans llc_await_state_trans_14 = { +static const struct llc_conn_state_trans llc_await_state_trans_14 = { .ev = llc_conn_ev_p_tmr_exp, .next_state = LLC_CONN_STATE_AWAIT, .ev_qualifiers = llc_await_ev_qfyrs_14, @@ -3205,7 +3205,7 @@ static struct llc_conn_state_trans llc_await_state_trans_14 = { * Array of pointers; * one to each transition */ -static struct llc_conn_state_trans *llc_await_state_transitions[] = { +static const struct llc_conn_state_trans *llc_await_state_transitions[] = { [0] = &llc_common_state_trans_1, /* Request */ [1] = &llc_common_state_trans_2, [2] = &llc_await_state_trans_1_0, @@ -3263,7 +3263,7 @@ static const llc_conn_ev_qfyr_t llc_await_busy_ev_qfyrs_1_0[] = { /* just one member, NULL, .bss zeroes it */ static const llc_conn_action_t llc_await_busy_actions_1_0[1]; -static struct llc_conn_state_trans llc_await_busy_state_trans_1_0 = { +static const struct llc_conn_state_trans llc_await_busy_state_trans_1_0 = { .ev = llc_conn_ev_data_req, .next_state = LLC_CONN_STATE_AWAIT_BUSY, .ev_qualifiers = llc_await_busy_ev_qfyrs_1_0, @@ -3282,7 +3282,7 @@ static const llc_conn_action_t llc_await_busy_actions_1[] = { [2] = NULL, }; -static struct llc_conn_state_trans llc_await_busy_state_trans_1 = { +static const struct llc_conn_state_trans llc_await_busy_state_trans_1 = { .ev = llc_conn_ev_local_busy_cleared, .next_state = LLC_CONN_STATE_AWAIT_REJ, .ev_qualifiers = llc_await_busy_ev_qfyrs_1, @@ -3300,7 +3300,7 @@ static const llc_conn_action_t llc_await_busy_actions_2[] = { [1] = NULL, }; -static struct llc_conn_state_trans llc_await_busy_state_trans_2 = { +static const struct llc_conn_state_trans llc_await_busy_state_trans_2 = { .ev = llc_conn_ev_local_busy_cleared, .next_state = LLC_CONN_STATE_AWAIT, .ev_qualifiers = llc_await_busy_ev_qfyrs_2, @@ -3318,7 +3318,7 @@ static const llc_conn_action_t llc_await_busy_actions_3[] = { [1] = NULL, }; -static struct llc_conn_state_trans llc_await_busy_state_trans_3 = { +static const struct llc_conn_state_trans llc_await_busy_state_trans_3 = { .ev = llc_conn_ev_local_busy_cleared, .next_state = LLC_CONN_STATE_AWAIT_REJ, .ev_qualifiers = llc_await_busy_ev_qfyrs_3, @@ -3337,7 +3337,7 @@ static const llc_conn_action_t llc_await_busy_actions_4[] = { [7] = NULL, }; -static struct llc_conn_state_trans llc_await_busy_state_trans_4 = { +static const struct llc_conn_state_trans llc_await_busy_state_trans_4 = { .ev = llc_conn_ev_rx_i_rsp_fbit_set_1_unexpd_ns, .next_state = LLC_CONN_STATE_BUSY, .ev_qualifiers = NONE, @@ -3353,7 +3353,7 @@ static const llc_conn_action_t llc_await_busy_actions_5a[] = { [4] = NULL, }; -static struct llc_conn_state_trans llc_await_busy_state_trans_5a = { +static const struct llc_conn_state_trans llc_await_busy_state_trans_5a = { .ev = llc_conn_ev_rx_i_cmd_pbit_set_0_unexpd_ns, .next_state = LLC_CONN_STATE_AWAIT_BUSY, .ev_qualifiers = NONE, @@ -3369,7 +3369,7 @@ static const llc_conn_action_t llc_await_busy_actions_5b[] = { [4] = NULL, }; -static struct llc_conn_state_trans llc_await_busy_state_trans_5b = { +static const struct llc_conn_state_trans llc_await_busy_state_trans_5b = { .ev = llc_conn_ev_rx_i_rsp_fbit_set_0_unexpd_ns, .next_state = LLC_CONN_STATE_AWAIT_BUSY, .ev_qualifiers = NONE, @@ -3385,7 +3385,7 @@ static const llc_conn_action_t llc_await_busy_actions_6[] = { [4] = NULL, }; -static struct llc_conn_state_trans llc_await_busy_state_trans_6 = { +static const struct llc_conn_state_trans llc_await_busy_state_trans_6 = { .ev = llc_conn_ev_rx_i_cmd_pbit_set_1_unexpd_ns, .next_state = LLC_CONN_STATE_AWAIT_BUSY, .ev_qualifiers = NONE, @@ -3406,7 +3406,7 @@ static const llc_conn_action_t llc_await_busy_actions_7[] = { [9] = NULL, }; -static struct llc_conn_state_trans llc_await_busy_state_trans_7 = { +static const struct llc_conn_state_trans llc_await_busy_state_trans_7 = { .ev = llc_conn_ev_rx_i_rsp_fbit_set_1, .next_state = LLC_CONN_STATE_BUSY, .ev_qualifiers = NONE, @@ -3424,7 +3424,7 @@ static const llc_conn_action_t llc_await_busy_actions_8a[] = { [6] = NULL, }; -static struct llc_conn_state_trans llc_await_busy_state_trans_8a = { +static const struct llc_conn_state_trans llc_await_busy_state_trans_8a = { .ev = llc_conn_ev_rx_i_rsp_fbit_set_0, .next_state = LLC_CONN_STATE_AWAIT_BUSY, .ev_qualifiers = NONE, @@ -3442,7 +3442,7 @@ static const llc_conn_action_t llc_await_busy_actions_8b[] = { [6] = NULL, }; -static struct llc_conn_state_trans llc_await_busy_state_trans_8b = { +static const struct llc_conn_state_trans llc_await_busy_state_trans_8b = { .ev = llc_conn_ev_rx_i_cmd_pbit_set_0, .next_state = LLC_CONN_STATE_AWAIT_BUSY, .ev_qualifiers = NONE, @@ -3460,7 +3460,7 @@ static const llc_conn_action_t llc_await_busy_actions_9[] = { [6] = NULL, }; -static struct llc_conn_state_trans llc_await_busy_state_trans_9 = { +static const struct llc_conn_state_trans llc_await_busy_state_trans_9 = { .ev = llc_conn_ev_rx_i_cmd_pbit_set_1, .next_state = LLC_CONN_STATE_AWAIT_BUSY, .ev_qualifiers = NONE, @@ -3477,7 +3477,7 @@ static const llc_conn_action_t llc_await_busy_actions_10a[] = { [5] = NULL, }; -static struct llc_conn_state_trans llc_await_busy_state_trans_10a = { +static const struct llc_conn_state_trans llc_await_busy_state_trans_10a = { .ev = llc_conn_ev_rx_rr_rsp_fbit_set_1, .next_state = LLC_CONN_STATE_BUSY, .ev_qualifiers = NONE, @@ -3494,7 +3494,7 @@ static const llc_conn_action_t llc_await_busy_actions_10b[] = { [5] = NULL, }; -static struct llc_conn_state_trans llc_await_busy_state_trans_10b = { +static const struct llc_conn_state_trans llc_await_busy_state_trans_10b = { .ev = llc_conn_ev_rx_rej_rsp_fbit_set_1, .next_state = LLC_CONN_STATE_BUSY, .ev_qualifiers = NONE, @@ -3509,7 +3509,7 @@ static const llc_conn_action_t llc_await_busy_actions_11a[] = { [3] = NULL, }; -static struct llc_conn_state_trans llc_await_busy_state_trans_11a = { +static const struct llc_conn_state_trans llc_await_busy_state_trans_11a = { .ev = llc_conn_ev_rx_rr_cmd_pbit_set_0, .next_state = LLC_CONN_STATE_AWAIT_BUSY, .ev_qualifiers = NONE, @@ -3524,7 +3524,7 @@ static const llc_conn_action_t llc_await_busy_actions_11b[] = { [3] = NULL, }; -static struct llc_conn_state_trans llc_await_busy_state_trans_11b = { +static const struct llc_conn_state_trans llc_await_busy_state_trans_11b = { .ev = llc_conn_ev_rx_rr_rsp_fbit_set_0, .next_state = LLC_CONN_STATE_AWAIT_BUSY, .ev_qualifiers = NONE, @@ -3539,7 +3539,7 @@ static const llc_conn_action_t llc_await_busy_actions_11c[] = { [3] = NULL, }; -static struct llc_conn_state_trans llc_await_busy_state_trans_11c = { +static const struct llc_conn_state_trans llc_await_busy_state_trans_11c = { .ev = llc_conn_ev_rx_rej_cmd_pbit_set_0, .next_state = LLC_CONN_STATE_AWAIT_BUSY, .ev_qualifiers = NONE, @@ -3554,7 +3554,7 @@ static const llc_conn_action_t llc_await_busy_actions_11d[] = { [3] = NULL, }; -static struct llc_conn_state_trans llc_await_busy_state_trans_11d = { +static const struct llc_conn_state_trans llc_await_busy_state_trans_11d = { .ev = llc_conn_ev_rx_rej_rsp_fbit_set_0, .next_state = LLC_CONN_STATE_AWAIT_BUSY, .ev_qualifiers = NONE, @@ -3570,7 +3570,7 @@ static const llc_conn_action_t llc_await_busy_actions_12a[] = { [4] = NULL, }; -static struct llc_conn_state_trans llc_await_busy_state_trans_12a = { +static const struct llc_conn_state_trans llc_await_busy_state_trans_12a = { .ev = llc_conn_ev_rx_rr_cmd_pbit_set_1, .next_state = LLC_CONN_STATE_AWAIT_BUSY, .ev_qualifiers = NONE, @@ -3586,7 +3586,7 @@ static const llc_conn_action_t llc_await_busy_actions_12b[] = { [4] = NULL, }; -static struct llc_conn_state_trans llc_await_busy_state_trans_12b = { +static const struct llc_conn_state_trans llc_await_busy_state_trans_12b = { .ev = llc_conn_ev_rx_rej_cmd_pbit_set_1, .next_state = LLC_CONN_STATE_AWAIT_BUSY, .ev_qualifiers = NONE, @@ -3602,7 +3602,7 @@ static const llc_conn_action_t llc_await_busy_actions_13[] = { [4] = NULL, }; -static struct llc_conn_state_trans llc_await_busy_state_trans_13 = { +static const struct llc_conn_state_trans llc_await_busy_state_trans_13 = { .ev = llc_conn_ev_rx_rnr_rsp_fbit_set_1, .next_state = LLC_CONN_STATE_BUSY, .ev_qualifiers = NONE, @@ -3617,7 +3617,7 @@ static const llc_conn_action_t llc_await_busy_actions_14a[] = { [3] = NULL, }; -static struct llc_conn_state_trans llc_await_busy_state_trans_14a = { +static const struct llc_conn_state_trans llc_await_busy_state_trans_14a = { .ev = llc_conn_ev_rx_rnr_cmd_pbit_set_0, .next_state = LLC_CONN_STATE_AWAIT_BUSY, .ev_qualifiers = NONE, @@ -3632,7 +3632,7 @@ static const llc_conn_action_t llc_await_busy_actions_14b[] = { [3] = NULL, }; -static struct llc_conn_state_trans llc_await_busy_state_trans_14b = { +static const struct llc_conn_state_trans llc_await_busy_state_trans_14b = { .ev = llc_conn_ev_rx_rnr_rsp_fbit_set_0, .next_state = LLC_CONN_STATE_AWAIT_BUSY, .ev_qualifiers = NONE, @@ -3648,7 +3648,7 @@ static const llc_conn_action_t llc_await_busy_actions_15[] = { [4] = NULL, }; -static struct llc_conn_state_trans llc_await_busy_state_trans_15 = { +static const struct llc_conn_state_trans llc_await_busy_state_trans_15 = { .ev = llc_conn_ev_rx_rnr_cmd_pbit_set_1, .next_state = LLC_CONN_STATE_AWAIT_BUSY, .ev_qualifiers = NONE, @@ -3668,7 +3668,7 @@ static const llc_conn_action_t llc_await_busy_actions_16[] = { [3] = NULL, }; -static struct llc_conn_state_trans llc_await_busy_state_trans_16 = { +static const struct llc_conn_state_trans llc_await_busy_state_trans_16 = { .ev = llc_conn_ev_p_tmr_exp, .next_state = LLC_CONN_STATE_AWAIT_BUSY, .ev_qualifiers = llc_await_busy_ev_qfyrs_16, @@ -3679,7 +3679,7 @@ static struct llc_conn_state_trans llc_await_busy_state_trans_16 = { * Array of pointers; * one to each transition */ -static struct llc_conn_state_trans *llc_await_busy_state_transitions[] = { +static const struct llc_conn_state_trans *llc_await_busy_state_transitions[] = { [0] = &llc_common_state_trans_1, /* Request */ [1] = &llc_common_state_trans_2, [2] = &llc_await_busy_state_trans_1_0, @@ -3739,7 +3739,7 @@ static const llc_conn_ev_qfyr_t llc_await_reject_ev_qfyrs_1_0[] = { /* just one member, NULL, .bss zeroes it */ static const llc_conn_action_t llc_await_reject_actions_1_0[1]; -static struct llc_conn_state_trans llc_await_reject_state_trans_1_0 = { +static const struct llc_conn_state_trans llc_await_reject_state_trans_1_0 = { .ev = llc_conn_ev_data_req, .next_state = LLC_CONN_STATE_AWAIT_REJ, .ev_qualifiers = llc_await_reject_ev_qfyrs_1_0, @@ -3753,7 +3753,7 @@ static const llc_conn_action_t llc_await_rejct_actions_1[] = { [2] = NULL }; -static struct llc_conn_state_trans llc_await_rejct_state_trans_1 = { +static const struct llc_conn_state_trans llc_await_rejct_state_trans_1 = { .ev = llc_conn_ev_local_busy_detected, .next_state = LLC_CONN_STATE_AWAIT_BUSY, .ev_qualifiers = NONE, @@ -3767,7 +3767,7 @@ static const llc_conn_action_t llc_await_rejct_actions_2a[] = { [2] = NULL }; -static struct llc_conn_state_trans llc_await_rejct_state_trans_2a = { +static const struct llc_conn_state_trans llc_await_rejct_state_trans_2a = { .ev = llc_conn_ev_rx_i_cmd_pbit_set_0_unexpd_ns, .next_state = LLC_CONN_STATE_AWAIT_REJ, .ev_qualifiers = NONE, @@ -3781,7 +3781,7 @@ static const llc_conn_action_t llc_await_rejct_actions_2b[] = { [2] = NULL }; -static struct llc_conn_state_trans llc_await_rejct_state_trans_2b = { +static const struct llc_conn_state_trans llc_await_rejct_state_trans_2b = { .ev = llc_conn_ev_rx_i_rsp_fbit_set_0_unexpd_ns, .next_state = LLC_CONN_STATE_AWAIT_REJ, .ev_qualifiers = NONE, @@ -3796,7 +3796,7 @@ static const llc_conn_action_t llc_await_rejct_actions_3[] = { [3] = NULL }; -static struct llc_conn_state_trans llc_await_rejct_state_trans_3 = { +static const struct llc_conn_state_trans llc_await_rejct_state_trans_3 = { .ev = llc_conn_ev_rx_i_cmd_pbit_set_1_unexpd_ns, .next_state = LLC_CONN_STATE_AWAIT_REJ, .ev_qualifiers = NONE, @@ -3816,7 +3816,7 @@ static const llc_conn_action_t llc_await_rejct_actions_4[] = { [8] = NULL, }; -static struct llc_conn_state_trans llc_await_rejct_state_trans_4 = { +static const struct llc_conn_state_trans llc_await_rejct_state_trans_4 = { .ev = llc_conn_ev_rx_i_rsp_fbit_set_1, .next_state = LLC_CONN_STATE_NORMAL, .ev_qualifiers = NONE, @@ -3834,7 +3834,7 @@ static const llc_conn_action_t llc_await_rejct_actions_5a[] = { [6] = NULL, }; -static struct llc_conn_state_trans llc_await_rejct_state_trans_5a = { +static const struct llc_conn_state_trans llc_await_rejct_state_trans_5a = { .ev = llc_conn_ev_rx_i_rsp_fbit_set_0, .next_state = LLC_CONN_STATE_AWAIT, .ev_qualifiers = NONE, @@ -3852,7 +3852,7 @@ static const llc_conn_action_t llc_await_rejct_actions_5b[] = { [6] = NULL, }; -static struct llc_conn_state_trans llc_await_rejct_state_trans_5b = { +static const struct llc_conn_state_trans llc_await_rejct_state_trans_5b = { .ev = llc_conn_ev_rx_i_cmd_pbit_set_0, .next_state = LLC_CONN_STATE_AWAIT, .ev_qualifiers = NONE, @@ -3870,7 +3870,7 @@ static const llc_conn_action_t llc_await_rejct_actions_6[] = { [6] = NULL, }; -static struct llc_conn_state_trans llc_await_rejct_state_trans_6 = { +static const struct llc_conn_state_trans llc_await_rejct_state_trans_6 = { .ev = llc_conn_ev_rx_i_cmd_pbit_set_1, .next_state = LLC_CONN_STATE_AWAIT, .ev_qualifiers = NONE, @@ -3887,7 +3887,7 @@ static const llc_conn_action_t llc_await_rejct_actions_7a[] = { [5] = NULL, }; -static struct llc_conn_state_trans llc_await_rejct_state_trans_7a = { +static const struct llc_conn_state_trans llc_await_rejct_state_trans_7a = { .ev = llc_conn_ev_rx_rr_rsp_fbit_set_1, .next_state = LLC_CONN_STATE_REJ, .ev_qualifiers = NONE, @@ -3904,7 +3904,7 @@ static const llc_conn_action_t llc_await_rejct_actions_7b[] = { [5] = NULL, }; -static struct llc_conn_state_trans llc_await_rejct_state_trans_7b = { +static const struct llc_conn_state_trans llc_await_rejct_state_trans_7b = { .ev = llc_conn_ev_rx_rej_rsp_fbit_set_1, .next_state = LLC_CONN_STATE_REJ, .ev_qualifiers = NONE, @@ -3921,7 +3921,7 @@ static const llc_conn_action_t llc_await_rejct_actions_7c[] = { [5] = NULL, }; -static struct llc_conn_state_trans llc_await_rejct_state_trans_7c = { +static const struct llc_conn_state_trans llc_await_rejct_state_trans_7c = { .ev = llc_conn_ev_rx_i_rsp_fbit_set_1_unexpd_ns, .next_state = LLC_CONN_STATE_REJ, .ev_qualifiers = NONE, @@ -3936,7 +3936,7 @@ static const llc_conn_action_t llc_await_rejct_actions_8a[] = { [3] = NULL, }; -static struct llc_conn_state_trans llc_await_rejct_state_trans_8a = { +static const struct llc_conn_state_trans llc_await_rejct_state_trans_8a = { .ev = llc_conn_ev_rx_rr_cmd_pbit_set_0, .next_state = LLC_CONN_STATE_AWAIT_REJ, .ev_qualifiers = NONE, @@ -3951,7 +3951,7 @@ static const llc_conn_action_t llc_await_rejct_actions_8b[] = { [3] = NULL, }; -static struct llc_conn_state_trans llc_await_rejct_state_trans_8b = { +static const struct llc_conn_state_trans llc_await_rejct_state_trans_8b = { .ev = llc_conn_ev_rx_rr_rsp_fbit_set_0, .next_state = LLC_CONN_STATE_AWAIT_REJ, .ev_qualifiers = NONE, @@ -3966,7 +3966,7 @@ static const llc_conn_action_t llc_await_rejct_actions_8c[] = { [3] = NULL, }; -static struct llc_conn_state_trans llc_await_rejct_state_trans_8c = { +static const struct llc_conn_state_trans llc_await_rejct_state_trans_8c = { .ev = llc_conn_ev_rx_rej_cmd_pbit_set_0, .next_state = LLC_CONN_STATE_AWAIT_REJ, .ev_qualifiers = NONE, @@ -3981,7 +3981,7 @@ static const llc_conn_action_t llc_await_rejct_actions_8d[] = { [3] = NULL, }; -static struct llc_conn_state_trans llc_await_rejct_state_trans_8d = { +static const struct llc_conn_state_trans llc_await_rejct_state_trans_8d = { .ev = llc_conn_ev_rx_rej_rsp_fbit_set_0, .next_state = LLC_CONN_STATE_AWAIT_REJ, .ev_qualifiers = NONE, @@ -3997,7 +3997,7 @@ static const llc_conn_action_t llc_await_rejct_actions_9a[] = { [4] = NULL, }; -static struct llc_conn_state_trans llc_await_rejct_state_trans_9a = { +static const struct llc_conn_state_trans llc_await_rejct_state_trans_9a = { .ev = llc_conn_ev_rx_rr_cmd_pbit_set_1, .next_state = LLC_CONN_STATE_AWAIT_REJ, .ev_qualifiers = NONE, @@ -4013,7 +4013,7 @@ static const llc_conn_action_t llc_await_rejct_actions_9b[] = { [4] = NULL, }; -static struct llc_conn_state_trans llc_await_rejct_state_trans_9b = { +static const struct llc_conn_state_trans llc_await_rejct_state_trans_9b = { .ev = llc_conn_ev_rx_rej_cmd_pbit_set_1, .next_state = LLC_CONN_STATE_AWAIT_REJ, .ev_qualifiers = NONE, @@ -4029,7 +4029,7 @@ static const llc_conn_action_t llc_await_rejct_actions_10[] = { [4] = NULL, }; -static struct llc_conn_state_trans llc_await_rejct_state_trans_10 = { +static const struct llc_conn_state_trans llc_await_rejct_state_trans_10 = { .ev = llc_conn_ev_rx_rnr_rsp_fbit_set_1, .next_state = LLC_CONN_STATE_REJ, .ev_qualifiers = NONE, @@ -4044,7 +4044,7 @@ static const llc_conn_action_t llc_await_rejct_actions_11a[] = { [3] = NULL, }; -static struct llc_conn_state_trans llc_await_rejct_state_trans_11a = { +static const struct llc_conn_state_trans llc_await_rejct_state_trans_11a = { .ev = llc_conn_ev_rx_rnr_cmd_pbit_set_0, .next_state = LLC_CONN_STATE_AWAIT_REJ, .ev_qualifiers = NONE, @@ -4059,7 +4059,7 @@ static const llc_conn_action_t llc_await_rejct_actions_11b[] = { [3] = NULL, }; -static struct llc_conn_state_trans llc_await_rejct_state_trans_11b = { +static const struct llc_conn_state_trans llc_await_rejct_state_trans_11b = { .ev = llc_conn_ev_rx_rnr_rsp_fbit_set_0, .next_state = LLC_CONN_STATE_AWAIT_REJ, .ev_qualifiers = NONE, @@ -4075,7 +4075,7 @@ static const llc_conn_action_t llc_await_rejct_actions_12[] = { [4] = NULL, }; -static struct llc_conn_state_trans llc_await_rejct_state_trans_12 = { +static const struct llc_conn_state_trans llc_await_rejct_state_trans_12 = { .ev = llc_conn_ev_rx_rnr_cmd_pbit_set_1, .next_state = LLC_CONN_STATE_AWAIT_REJ, .ev_qualifiers = NONE, @@ -4095,7 +4095,7 @@ static const llc_conn_action_t llc_await_rejct_actions_13[] = { [3] = NULL, }; -static struct llc_conn_state_trans llc_await_rejct_state_trans_13 = { +static const struct llc_conn_state_trans llc_await_rejct_state_trans_13 = { .ev = llc_conn_ev_p_tmr_exp, .next_state = LLC_CONN_STATE_AWAIT_REJ, .ev_qualifiers = llc_await_rejct_ev_qfyrs_13, @@ -4106,7 +4106,7 @@ static struct llc_conn_state_trans llc_await_rejct_state_trans_13 = { * Array of pointers; * one to each transition */ -static struct llc_conn_state_trans *llc_await_rejct_state_transitions[] = { +static const struct llc_conn_state_trans *llc_await_rejct_state_transitions[] = { [0] = &llc_await_reject_state_trans_1_0, [1] = &llc_common_state_trans_1, /* requests */ [2] = &llc_common_state_trans_2, @@ -4171,7 +4171,7 @@ static const llc_conn_action_t llc_d_conn_actions_1[] = { [4] = NULL, }; -static struct llc_conn_state_trans llc_d_conn_state_trans_1 = { +static const struct llc_conn_state_trans llc_d_conn_state_trans_1 = { .ev = llc_conn_ev_rx_sabme_cmd_pbit_set_x, .next_state = LLC_CONN_STATE_ADM, .ev_qualifiers = llc_d_conn_ev_qfyrs_1, @@ -4194,7 +4194,7 @@ static const llc_conn_action_t llc_d_conn_actions_1_1[] = { [3] = NULL, }; -static struct llc_conn_state_trans llc_d_conn_state_trans_1_1 = { +static const struct llc_conn_state_trans llc_d_conn_state_trans_1_1 = { .ev = llc_conn_ev_rx_sabme_cmd_pbit_set_x, .next_state = LLC_CONN_STATE_ADM, .ev_qualifiers = llc_d_conn_ev_qfyrs_1_1, @@ -4218,7 +4218,7 @@ static const llc_conn_action_t llc_d_conn_actions_2[] = { [3] = NULL, }; -static struct llc_conn_state_trans llc_d_conn_state_trans_2 = { +static const struct llc_conn_state_trans llc_d_conn_state_trans_2 = { .ev = llc_conn_ev_rx_ua_rsp_fbit_set_x, .next_state = LLC_CONN_STATE_ADM, .ev_qualifiers = llc_d_conn_ev_qfyrs_2, @@ -4241,7 +4241,7 @@ static const llc_conn_action_t llc_d_conn_actions_2_1[] = { [2] = NULL, }; -static struct llc_conn_state_trans llc_d_conn_state_trans_2_1 = { +static const struct llc_conn_state_trans llc_d_conn_state_trans_2_1 = { .ev = llc_conn_ev_rx_ua_rsp_fbit_set_x, .next_state = LLC_CONN_STATE_ADM, .ev_qualifiers = llc_d_conn_ev_qfyrs_2_1, @@ -4254,7 +4254,7 @@ static const llc_conn_action_t llc_d_conn_actions_3[] = { [1] = NULL, }; -static struct llc_conn_state_trans llc_d_conn_state_trans_3 = { +static const struct llc_conn_state_trans llc_d_conn_state_trans_3 = { .ev = llc_conn_ev_rx_disc_cmd_pbit_set_x, .next_state = LLC_CONN_STATE_D_CONN, .ev_qualifiers = NONE, @@ -4277,7 +4277,7 @@ static const llc_conn_action_t llc_d_conn_actions_4[] = { [3] = NULL, }; -static struct llc_conn_state_trans llc_d_conn_state_trans_4 = { +static const struct llc_conn_state_trans llc_d_conn_state_trans_4 = { .ev = llc_conn_ev_rx_dm_rsp_fbit_set_x, .next_state = LLC_CONN_STATE_ADM, .ev_qualifiers = llc_d_conn_ev_qfyrs_4, @@ -4299,7 +4299,7 @@ static const llc_conn_action_t llc_d_conn_actions_4_1[] = { [2] = NULL, }; -static struct llc_conn_state_trans llc_d_conn_state_trans_4_1 = { +static const struct llc_conn_state_trans llc_d_conn_state_trans_4_1 = { .ev = llc_conn_ev_rx_dm_rsp_fbit_set_x, .next_state = LLC_CONN_STATE_ADM, .ev_qualifiers = llc_d_conn_ev_qfyrs_4_1, @@ -4318,7 +4318,7 @@ static const llc_conn_ev_qfyr_t llc_d_conn_ev_qfyrs_5[] = { /* just one member, NULL, .bss zeroes it */ static const llc_conn_action_t llc_d_conn_actions_5[1]; -static struct llc_conn_state_trans llc_d_conn_state_trans_5 = { +static const struct llc_conn_state_trans llc_d_conn_state_trans_5 = { .ev = llc_conn_ev_data_req, .next_state = LLC_CONN_STATE_D_CONN, .ev_qualifiers = llc_d_conn_ev_qfyrs_5, @@ -4338,7 +4338,7 @@ static const llc_conn_action_t llc_d_conn_actions_6[] = { [3] = NULL, }; -static struct llc_conn_state_trans llc_d_conn_state_trans_6 = { +static const struct llc_conn_state_trans llc_d_conn_state_trans_6 = { .ev = llc_conn_ev_ack_tmr_exp, .next_state = LLC_CONN_STATE_D_CONN, .ev_qualifiers = llc_d_conn_ev_qfyrs_6, @@ -4359,7 +4359,7 @@ static const llc_conn_action_t llc_d_conn_actions_7[] = { [2] = NULL, }; -static struct llc_conn_state_trans llc_d_conn_state_trans_7 = { +static const struct llc_conn_state_trans llc_d_conn_state_trans_7 = { .ev = llc_conn_ev_ack_tmr_exp, .next_state = LLC_CONN_STATE_ADM, .ev_qualifiers = llc_d_conn_ev_qfyrs_7, @@ -4379,7 +4379,7 @@ static const llc_conn_action_t llc_d_conn_actions_8[] = { [1] = NULL, }; -static struct llc_conn_state_trans llc_d_conn_state_trans_8 = { +static const struct llc_conn_state_trans llc_d_conn_state_trans_8 = { .ev = llc_conn_ev_ack_tmr_exp, .next_state = LLC_CONN_STATE_ADM, .ev_qualifiers = llc_d_conn_ev_qfyrs_8, @@ -4390,7 +4390,7 @@ static struct llc_conn_state_trans llc_d_conn_state_trans_8 = { * Array of pointers; * one to each transition */ -static struct llc_conn_state_trans *llc_d_conn_state_transitions[] = { +static const struct llc_conn_state_trans *llc_d_conn_state_transitions[] = { [0] = &llc_d_conn_state_trans_5, /* Request */ [1] = &llc_common_state_trans_end, [2] = &llc_common_state_trans_end, /* Local busy */ @@ -4419,7 +4419,7 @@ static const llc_conn_action_t llc_rst_actions_1[] = { [4] = NULL, }; -static struct llc_conn_state_trans llc_rst_state_trans_1 = { +static const struct llc_conn_state_trans llc_rst_state_trans_1 = { .ev = llc_conn_ev_rx_sabme_cmd_pbit_set_x, .next_state = LLC_CONN_STATE_RESET, .ev_qualifiers = NONE, @@ -4447,7 +4447,7 @@ static const llc_conn_action_t llc_rst_actions_2[] = { [7] = NULL, }; -static struct llc_conn_state_trans llc_rst_state_trans_2 = { +static const struct llc_conn_state_trans llc_rst_state_trans_2 = { .ev = llc_conn_ev_rx_ua_rsp_fbit_set_x, .next_state = LLC_CONN_STATE_NORMAL, .ev_qualifiers = llc_rst_ev_qfyrs_2, @@ -4475,7 +4475,7 @@ static const llc_conn_action_t llc_rst_actions_2_1[] = { [7] = NULL, }; -static struct llc_conn_state_trans llc_rst_state_trans_2_1 = { +static const struct llc_conn_state_trans llc_rst_state_trans_2_1 = { .ev = llc_conn_ev_rx_ua_rsp_fbit_set_x, .next_state = LLC_CONN_STATE_NORMAL, .ev_qualifiers = llc_rst_ev_qfyrs_2_1, @@ -4495,7 +4495,7 @@ static const llc_conn_action_t llc_rst_actions_3[] = { [2] = NULL, }; -static struct llc_conn_state_trans llc_rst_state_trans_3 = { +static const struct llc_conn_state_trans llc_rst_state_trans_3 = { .ev = llc_conn_ev_ack_tmr_exp, .next_state = LLC_CONN_STATE_NORMAL, .ev_qualifiers = llc_rst_ev_qfyrs_3, @@ -4518,7 +4518,7 @@ static const llc_conn_action_t llc_rst_actions_4[] = { [4] = NULL, }; -static struct llc_conn_state_trans llc_rst_state_trans_4 = { +static const struct llc_conn_state_trans llc_rst_state_trans_4 = { .ev = llc_conn_ev_rx_disc_cmd_pbit_set_x, .next_state = LLC_CONN_STATE_ADM, .ev_qualifiers = llc_rst_ev_qfyrs_4, @@ -4541,7 +4541,7 @@ static const llc_conn_action_t llc_rst_actions_4_1[] = { [3] = NULL, }; -static struct llc_conn_state_trans llc_rst_state_trans_4_1 = { +static const struct llc_conn_state_trans llc_rst_state_trans_4_1 = { .ev = llc_conn_ev_rx_disc_cmd_pbit_set_x, .next_state = LLC_CONN_STATE_ADM, .ev_qualifiers = llc_rst_ev_qfyrs_4_1, @@ -4564,7 +4564,7 @@ static const llc_conn_action_t llc_rst_actions_5[] = { [3] = NULL, }; -static struct llc_conn_state_trans llc_rst_state_trans_5 = { +static const struct llc_conn_state_trans llc_rst_state_trans_5 = { .ev = llc_conn_ev_rx_dm_rsp_fbit_set_x, .next_state = LLC_CONN_STATE_ADM, .ev_qualifiers = llc_rst_ev_qfyrs_5, @@ -4586,7 +4586,7 @@ static const llc_conn_action_t llc_rst_actions_5_1[] = { [2] = NULL, }; -static struct llc_conn_state_trans llc_rst_state_trans_5_1 = { +static const struct llc_conn_state_trans llc_rst_state_trans_5_1 = { .ev = llc_conn_ev_rx_dm_rsp_fbit_set_x, .next_state = LLC_CONN_STATE_ADM, .ev_qualifiers = llc_rst_ev_qfyrs_5_1, @@ -4602,7 +4602,7 @@ static const llc_conn_ev_qfyr_t llc_rst_ev_qfyrs_6[] = { /* just one member, NULL, .bss zeroes it */ static const llc_conn_action_t llc_rst_actions_6[1]; -static struct llc_conn_state_trans llc_rst_state_trans_6 = { +static const struct llc_conn_state_trans llc_rst_state_trans_6 = { .ev = llc_conn_ev_data_req, .next_state = LLC_CONN_STATE_RESET, .ev_qualifiers = llc_rst_ev_qfyrs_6, @@ -4623,7 +4623,7 @@ static const llc_conn_action_t llc_rst_actions_7[] = { [3] = NULL, }; -static struct llc_conn_state_trans llc_rst_state_trans_7 = { +static const struct llc_conn_state_trans llc_rst_state_trans_7 = { .ev = llc_conn_ev_ack_tmr_exp, .next_state = LLC_CONN_STATE_RESET, .ev_qualifiers = llc_rst_ev_qfyrs_7, @@ -4644,7 +4644,7 @@ static const llc_conn_action_t llc_rst_actions_8[] = { [2] = NULL, }; -static struct llc_conn_state_trans llc_rst_state_trans_8 = { +static const struct llc_conn_state_trans llc_rst_state_trans_8 = { .ev = llc_conn_ev_ack_tmr_exp, .next_state = LLC_CONN_STATE_ADM, .ev_qualifiers = llc_rst_ev_qfyrs_8, @@ -4665,7 +4665,7 @@ static const llc_conn_action_t llc_rst_actions_8_1[] = { [2] = NULL, }; -static struct llc_conn_state_trans llc_rst_state_trans_8_1 = { +static const struct llc_conn_state_trans llc_rst_state_trans_8_1 = { .ev = llc_conn_ev_ack_tmr_exp, .next_state = LLC_CONN_STATE_ADM, .ev_qualifiers = llc_rst_ev_qfyrs_8_1, @@ -4676,7 +4676,7 @@ static struct llc_conn_state_trans llc_rst_state_trans_8_1 = { * Array of pointers; * one to each transition */ -static struct llc_conn_state_trans *llc_rst_state_transitions[] = { +static const struct llc_conn_state_trans *llc_rst_state_transitions[] = { [0] = &llc_rst_state_trans_6, /* Request */ [1] = &llc_common_state_trans_end, [2] = &llc_common_state_trans_end, /* Local busy */ @@ -4710,7 +4710,7 @@ static const llc_conn_action_t llc_error_actions_1[] = { [8] = NULL, }; -static struct llc_conn_state_trans llc_error_state_trans_1 = { +static const struct llc_conn_state_trans llc_error_state_trans_1 = { .ev = llc_conn_ev_rx_sabme_cmd_pbit_set_x, .next_state = LLC_CONN_STATE_NORMAL, .ev_qualifiers = NONE, @@ -4726,7 +4726,7 @@ static const llc_conn_action_t llc_error_actions_2[] = { [4] = NULL, }; -static struct llc_conn_state_trans llc_error_state_trans_2 = { +static const struct llc_conn_state_trans llc_error_state_trans_2 = { .ev = llc_conn_ev_rx_disc_cmd_pbit_set_x, .next_state = LLC_CONN_STATE_ADM, .ev_qualifiers = NONE, @@ -4741,7 +4741,7 @@ static const llc_conn_action_t llc_error_actions_3[] = { [3] = NULL, }; -static struct llc_conn_state_trans llc_error_state_trans_3 = { +static const struct llc_conn_state_trans llc_error_state_trans_3 = { .ev = llc_conn_ev_rx_dm_rsp_fbit_set_x, .next_state = LLC_CONN_STATE_ADM, .ev_qualifiers = NONE, @@ -4757,7 +4757,7 @@ static const llc_conn_action_t llc_error_actions_4[] = { [4] = NULL, }; -static struct llc_conn_state_trans llc_error_state_trans_4 = { +static const struct llc_conn_state_trans llc_error_state_trans_4 = { .ev = llc_conn_ev_rx_frmr_rsp_fbit_set_x, .next_state = LLC_CONN_STATE_RESET, .ev_qualifiers = NONE, @@ -4770,7 +4770,7 @@ static const llc_conn_action_t llc_error_actions_5[] = { [1] = NULL, }; -static struct llc_conn_state_trans llc_error_state_trans_5 = { +static const struct llc_conn_state_trans llc_error_state_trans_5 = { .ev = llc_conn_ev_rx_xxx_cmd_pbit_set_x, .next_state = LLC_CONN_STATE_ERROR, .ev_qualifiers = NONE, @@ -4778,7 +4778,7 @@ static struct llc_conn_state_trans llc_error_state_trans_5 = { }; /* State transitions for LLC_CONN_EV_RX_XXX_RSP_Fbit_SET_X event */ -static struct llc_conn_state_trans llc_error_state_trans_6 = { +static const struct llc_conn_state_trans llc_error_state_trans_6 = { .ev = llc_conn_ev_rx_xxx_rsp_fbit_set_x, .next_state = LLC_CONN_STATE_ERROR, .ev_qualifiers = NONE, @@ -4798,7 +4798,7 @@ static const llc_conn_action_t llc_error_actions_7[] = { [3] = NULL, }; -static struct llc_conn_state_trans llc_error_state_trans_7 = { +static const struct llc_conn_state_trans llc_error_state_trans_7 = { .ev = llc_conn_ev_ack_tmr_exp, .next_state = LLC_CONN_STATE_ERROR, .ev_qualifiers = llc_error_ev_qfyrs_7, @@ -4820,7 +4820,7 @@ static const llc_conn_action_t llc_error_actions_8[] = { [5] = NULL, }; -static struct llc_conn_state_trans llc_error_state_trans_8 = { +static const struct llc_conn_state_trans llc_error_state_trans_8 = { .ev = llc_conn_ev_ack_tmr_exp, .next_state = LLC_CONN_STATE_RESET, .ev_qualifiers = llc_error_ev_qfyrs_8, @@ -4836,7 +4836,7 @@ static const llc_conn_ev_qfyr_t llc_error_ev_qfyrs_9[] = { /* just one member, NULL, .bss zeroes it */ static const llc_conn_action_t llc_error_actions_9[1]; -static struct llc_conn_state_trans llc_error_state_trans_9 = { +static const struct llc_conn_state_trans llc_error_state_trans_9 = { .ev = llc_conn_ev_data_req, .next_state = LLC_CONN_STATE_ERROR, .ev_qualifiers = llc_error_ev_qfyrs_9, @@ -4847,7 +4847,7 @@ static struct llc_conn_state_trans llc_error_state_trans_9 = { * Array of pointers; * one to each transition */ -static struct llc_conn_state_trans *llc_error_state_transitions[] = { +static const struct llc_conn_state_trans *llc_error_state_transitions[] = { [0] = &llc_error_state_trans_9, /* Request */ [1] = &llc_common_state_trans_end, [2] = &llc_common_state_trans_end, /* Local busy */ @@ -4873,7 +4873,7 @@ static const llc_conn_action_t llc_temp_actions_1[] = { [3] = NULL, }; -static struct llc_conn_state_trans llc_temp_state_trans_1 = { +static const struct llc_conn_state_trans llc_temp_state_trans_1 = { .ev = llc_conn_ev_disc_req, .next_state = LLC_CONN_STATE_ADM, .ev_qualifiers = NONE, @@ -4884,7 +4884,7 @@ static struct llc_conn_state_trans llc_temp_state_trans_1 = { * Array of pointers; * one to each transition */ -static struct llc_conn_state_trans *llc_temp_state_transitions[] = { +static const struct llc_conn_state_trans *llc_temp_state_transitions[] = { [0] = &llc_temp_state_trans_1, /* requests */ [1] = &llc_common_state_trans_end, [2] = &llc_common_state_trans_end, /* local busy */ diff --git a/net/llc/llc_conn.c b/net/llc/llc_conn.c index 0a3f5e0bec00..afc6974eafda 100644 --- a/net/llc/llc_conn.c +++ b/net/llc/llc_conn.c @@ -34,10 +34,10 @@ static int llc_find_offset(int state, int ev_type); static void llc_conn_send_pdus(struct sock *sk); static int llc_conn_service(struct sock *sk, struct sk_buff *skb); static int llc_exec_conn_trans_actions(struct sock *sk, - struct llc_conn_state_trans *trans, + const struct llc_conn_state_trans *trans, struct sk_buff *ev); -static struct llc_conn_state_trans *llc_qualify_conn_ev(struct sock *sk, - struct sk_buff *skb); +static const struct llc_conn_state_trans *llc_qualify_conn_ev(struct sock *sk, + struct sk_buff *skb); /* Offset table on connection states transition diagram */ static int llc_offset_table[NBR_CONN_STATES][NBR_CONN_EV]; @@ -356,9 +356,9 @@ static void llc_conn_send_pdus(struct sock *sk) */ static int llc_conn_service(struct sock *sk, struct sk_buff *skb) { - int rc = 1; + const struct llc_conn_state_trans *trans; struct llc_sock *llc = llc_sk(sk); - struct llc_conn_state_trans *trans; + int rc = 1; if (llc->state > NBR_CONN_STATES) goto out; @@ -384,10 +384,10 @@ out: * This function finds transition that matches with happened event. * Returns pointer to found transition on success, %NULL otherwise. */ -static struct llc_conn_state_trans *llc_qualify_conn_ev(struct sock *sk, - struct sk_buff *skb) +static const struct llc_conn_state_trans *llc_qualify_conn_ev(struct sock *sk, + struct sk_buff *skb) { - struct llc_conn_state_trans **next_trans; + const struct llc_conn_state_trans **next_trans; const llc_conn_ev_qfyr_t *next_qualifier; struct llc_conn_state_ev *ev = llc_conn_ev(skb); struct llc_sock *llc = llc_sk(sk); @@ -432,7 +432,7 @@ static struct llc_conn_state_trans *llc_qualify_conn_ev(struct sock *sk, * success, 1 to indicate failure of at least one action. */ static int llc_exec_conn_trans_actions(struct sock *sk, - struct llc_conn_state_trans *trans, + const struct llc_conn_state_trans *trans, struct sk_buff *skb) { int rc = 0; @@ -635,8 +635,8 @@ u8 llc_data_accept_state(u8 state) */ static u16 __init llc_find_next_offset(struct llc_conn_state *state, u16 offset) { + const struct llc_conn_state_trans **next_trans; u16 cnt = 0; - struct llc_conn_state_trans **next_trans; for (next_trans = state->transitions + offset; (*next_trans)->ev; next_trans++) diff --git a/net/llc/llc_s_st.c b/net/llc/llc_s_st.c index 308c616883a4..acccc827c562 100644 --- a/net/llc/llc_s_st.c +++ b/net/llc/llc_s_st.c @@ -24,7 +24,7 @@ * last entry for this state * all members are zeros, .bss zeroes it */ -static struct llc_sap_state_trans llc_sap_state_trans_end; +static const struct llc_sap_state_trans llc_sap_state_trans_end; /* state LLC_SAP_STATE_INACTIVE transition for * LLC_SAP_EV_ACTIVATION_REQ event @@ -34,14 +34,14 @@ static const llc_sap_action_t llc_sap_inactive_state_actions_1[] = { [1] = NULL, }; -static struct llc_sap_state_trans llc_sap_inactive_state_trans_1 = { +static const struct llc_sap_state_trans llc_sap_inactive_state_trans_1 = { .ev = llc_sap_ev_activation_req, .next_state = LLC_SAP_STATE_ACTIVE, .ev_actions = llc_sap_inactive_state_actions_1, }; /* array of pointers; one to each transition */ -static struct llc_sap_state_trans *llc_sap_inactive_state_transitions[] = { +static const struct llc_sap_state_trans *llc_sap_inactive_state_transitions[] = { [0] = &llc_sap_inactive_state_trans_1, [1] = &llc_sap_state_trans_end, }; @@ -52,7 +52,7 @@ static const llc_sap_action_t llc_sap_active_state_actions_1[] = { [1] = NULL, }; -static struct llc_sap_state_trans llc_sap_active_state_trans_1 = { +static const struct llc_sap_state_trans llc_sap_active_state_trans_1 = { .ev = llc_sap_ev_rx_ui, .next_state = LLC_SAP_STATE_ACTIVE, .ev_actions = llc_sap_active_state_actions_1, @@ -64,7 +64,7 @@ static const llc_sap_action_t llc_sap_active_state_actions_2[] = { [1] = NULL, }; -static struct llc_sap_state_trans llc_sap_active_state_trans_2 = { +static const struct llc_sap_state_trans llc_sap_active_state_trans_2 = { .ev = llc_sap_ev_unitdata_req, .next_state = LLC_SAP_STATE_ACTIVE, .ev_actions = llc_sap_active_state_actions_2, @@ -76,7 +76,7 @@ static const llc_sap_action_t llc_sap_active_state_actions_3[] = { [1] = NULL, }; -static struct llc_sap_state_trans llc_sap_active_state_trans_3 = { +static const struct llc_sap_state_trans llc_sap_active_state_trans_3 = { .ev = llc_sap_ev_xid_req, .next_state = LLC_SAP_STATE_ACTIVE, .ev_actions = llc_sap_active_state_actions_3, @@ -88,7 +88,7 @@ static const llc_sap_action_t llc_sap_active_state_actions_4[] = { [1] = NULL, }; -static struct llc_sap_state_trans llc_sap_active_state_trans_4 = { +static const struct llc_sap_state_trans llc_sap_active_state_trans_4 = { .ev = llc_sap_ev_rx_xid_c, .next_state = LLC_SAP_STATE_ACTIVE, .ev_actions = llc_sap_active_state_actions_4, @@ -100,7 +100,7 @@ static const llc_sap_action_t llc_sap_active_state_actions_5[] = { [1] = NULL, }; -static struct llc_sap_state_trans llc_sap_active_state_trans_5 = { +static const struct llc_sap_state_trans llc_sap_active_state_trans_5 = { .ev = llc_sap_ev_rx_xid_r, .next_state = LLC_SAP_STATE_ACTIVE, .ev_actions = llc_sap_active_state_actions_5, @@ -112,7 +112,7 @@ static const llc_sap_action_t llc_sap_active_state_actions_6[] = { [1] = NULL, }; -static struct llc_sap_state_trans llc_sap_active_state_trans_6 = { +static const struct llc_sap_state_trans llc_sap_active_state_trans_6 = { .ev = llc_sap_ev_test_req, .next_state = LLC_SAP_STATE_ACTIVE, .ev_actions = llc_sap_active_state_actions_6, @@ -124,7 +124,7 @@ static const llc_sap_action_t llc_sap_active_state_actions_7[] = { [1] = NULL, }; -static struct llc_sap_state_trans llc_sap_active_state_trans_7 = { +static const struct llc_sap_state_trans llc_sap_active_state_trans_7 = { .ev = llc_sap_ev_rx_test_c, .next_state = LLC_SAP_STATE_ACTIVE, .ev_actions = llc_sap_active_state_actions_7 @@ -136,7 +136,7 @@ static const llc_sap_action_t llc_sap_active_state_actions_8[] = { [1] = NULL, }; -static struct llc_sap_state_trans llc_sap_active_state_trans_8 = { +static const struct llc_sap_state_trans llc_sap_active_state_trans_8 = { .ev = llc_sap_ev_rx_test_r, .next_state = LLC_SAP_STATE_ACTIVE, .ev_actions = llc_sap_active_state_actions_8, @@ -150,14 +150,14 @@ static const llc_sap_action_t llc_sap_active_state_actions_9[] = { [1] = NULL, }; -static struct llc_sap_state_trans llc_sap_active_state_trans_9 = { +static const struct llc_sap_state_trans llc_sap_active_state_trans_9 = { .ev = llc_sap_ev_deactivation_req, .next_state = LLC_SAP_STATE_INACTIVE, .ev_actions = llc_sap_active_state_actions_9 }; /* array of pointers; one to each transition */ -static struct llc_sap_state_trans *llc_sap_active_state_transitions[] = { +static const struct llc_sap_state_trans *llc_sap_active_state_transitions[] = { [0] = &llc_sap_active_state_trans_2, [1] = &llc_sap_active_state_trans_1, [2] = &llc_sap_active_state_trans_3, diff --git a/net/llc/llc_sap.c b/net/llc/llc_sap.c index 116c0e479183..6cd03c2ae7d5 100644 --- a/net/llc/llc_sap.c +++ b/net/llc/llc_sap.c @@ -114,12 +114,12 @@ void llc_sap_rtn_pdu(struct llc_sap *sap, struct sk_buff *skb) * Returns the pointer to found transition on success or %NULL for * failure. */ -static struct llc_sap_state_trans *llc_find_sap_trans(struct llc_sap *sap, - struct sk_buff *skb) +static const struct llc_sap_state_trans *llc_find_sap_trans(struct llc_sap *sap, + struct sk_buff *skb) { int i = 0; - struct llc_sap_state_trans *rc = NULL; - struct llc_sap_state_trans **next_trans; + const struct llc_sap_state_trans *rc = NULL; + const struct llc_sap_state_trans **next_trans; struct llc_sap_state *curr_state = &llc_sap_state_table[sap->state - 1]; /* * Search thru events for this state until list exhausted or until @@ -143,7 +143,7 @@ static struct llc_sap_state_trans *llc_find_sap_trans(struct llc_sap *sap, * Returns 0 for success and 1 for failure of at least one action. */ static int llc_exec_sap_trans_actions(struct llc_sap *sap, - struct llc_sap_state_trans *trans, + const struct llc_sap_state_trans *trans, struct sk_buff *skb) { int rc = 0; @@ -166,8 +166,8 @@ static int llc_exec_sap_trans_actions(struct llc_sap *sap, */ static int llc_sap_next_state(struct llc_sap *sap, struct sk_buff *skb) { + const struct llc_sap_state_trans *trans; int rc = 1; - struct llc_sap_state_trans *trans; if (sap->state > LLC_NR_SAP_STATES) goto out; diff --git a/net/mac80211/agg-rx.c b/net/mac80211/agg-rx.c index 9bffac7a4974..fe7eab4b681b 100644 --- a/net/mac80211/agg-rx.c +++ b/net/mac80211/agg-rx.c @@ -207,20 +207,7 @@ static void ieee80211_send_addba_resp(struct sta_info *sta, u8 *da, u16 tid, return; skb_reserve(skb, local->hw.extra_tx_headroom); - mgmt = skb_put_zero(skb, 24); - memcpy(mgmt->da, da, ETH_ALEN); - memcpy(mgmt->sa, sdata->vif.addr, ETH_ALEN); - if (sdata->vif.type == NL80211_IFTYPE_AP || - sdata->vif.type == NL80211_IFTYPE_AP_VLAN || - sdata->vif.type == NL80211_IFTYPE_MESH_POINT) - memcpy(mgmt->bssid, sdata->vif.addr, ETH_ALEN); - else if (sdata->vif.type == NL80211_IFTYPE_STATION) - memcpy(mgmt->bssid, sdata->vif.cfg.ap_addr, ETH_ALEN); - else if (sdata->vif.type == NL80211_IFTYPE_ADHOC) - memcpy(mgmt->bssid, sdata->u.ibss.bssid, ETH_ALEN); - - mgmt->frame_control = cpu_to_le16(IEEE80211_FTYPE_MGMT | - IEEE80211_STYPE_ACTION); + mgmt = ieee80211_mgmt_ba(skb, da, sdata); skb_put(skb, 1 + sizeof(mgmt->u.action.u.addba_resp)); mgmt->u.action.category = WLAN_CATEGORY_BACK; diff --git a/net/mac80211/agg-tx.c b/net/mac80211/agg-tx.c index 21d55dc539f6..1c18b862ef8c 100644 --- a/net/mac80211/agg-tx.c +++ b/net/mac80211/agg-tx.c @@ -74,20 +74,7 @@ static void ieee80211_send_addba_request(struct ieee80211_sub_if_data *sdata, return; skb_reserve(skb, local->hw.extra_tx_headroom); - mgmt = skb_put_zero(skb, 24); - memcpy(mgmt->da, da, ETH_ALEN); - memcpy(mgmt->sa, sdata->vif.addr, ETH_ALEN); - if (sdata->vif.type == NL80211_IFTYPE_AP || - sdata->vif.type == NL80211_IFTYPE_AP_VLAN || - sdata->vif.type == NL80211_IFTYPE_MESH_POINT) - memcpy(mgmt->bssid, sdata->vif.addr, ETH_ALEN); - else if (sdata->vif.type == NL80211_IFTYPE_STATION) - memcpy(mgmt->bssid, sdata->vif.cfg.ap_addr, ETH_ALEN); - else if (sdata->vif.type == NL80211_IFTYPE_ADHOC) - memcpy(mgmt->bssid, sdata->u.ibss.bssid, ETH_ALEN); - - mgmt->frame_control = cpu_to_le16(IEEE80211_FTYPE_MGMT | - IEEE80211_STYPE_ACTION); + mgmt = ieee80211_mgmt_ba(skb, da, sdata); skb_put(skb, 1 + sizeof(mgmt->u.action.u.addba_req)); @@ -616,7 +603,9 @@ int ieee80211_start_tx_ba_session(struct ieee80211_sta *pubsta, u16 tid, return -EINVAL; if (!pubsta->deflink.ht_cap.ht_supported && - sta->sdata->vif.bss_conf.chanreq.oper.chan->band != NL80211_BAND_6GHZ) + !pubsta->deflink.vht_cap.vht_supported && + !pubsta->deflink.he_cap.has_he && + !pubsta->deflink.eht_cap.has_eht) return -EINVAL; if (WARN_ON_ONCE(!local->ops->ampdu_action)) diff --git a/net/mac80211/airtime.c b/net/mac80211/airtime.c index fdf8b658fede..c61df637232a 100644 --- a/net/mac80211/airtime.c +++ b/net/mac80211/airtime.c @@ -55,10 +55,21 @@ #define HE_DURATION_S(shift, streams, gi, bps) \ (HE_DURATION(streams, gi, bps) >> shift) +/* gi in HE/EHT is identical. It matches enum nl80211_eht_gi as well */ +#define EHT_GI_08 HE_GI_08 +#define EHT_GI_16 HE_GI_16 +#define EHT_GI_32 HE_GI_32 + +#define EHT_DURATION(streams, gi, bps) \ + HE_DURATION(streams, gi, bps) +#define EHT_DURATION_S(shift, streams, gi, bps) \ + HE_DURATION_S(shift, streams, gi, bps) + #define BW_20 0 #define BW_40 1 #define BW_80 2 #define BW_160 3 +#define BW_320 4 /* * Define group sort order: HT40 -> SGI -> #streams @@ -68,17 +79,26 @@ #define IEEE80211_VHT_STREAM_GROUPS 8 /* BW(=4) * SGI(=2) */ #define IEEE80211_HE_MAX_STREAMS 8 +#define IEEE80211_HE_STREAM_GROUPS 12 /* BW(=4) * GI(=3) */ + +#define IEEE80211_EHT_MAX_STREAMS 8 +#define IEEE80211_EHT_STREAM_GROUPS 15 /* BW(=5) * GI(=3) */ #define IEEE80211_HT_GROUPS_NB (IEEE80211_MAX_STREAMS * \ IEEE80211_HT_STREAM_GROUPS) #define IEEE80211_VHT_GROUPS_NB (IEEE80211_MAX_STREAMS * \ IEEE80211_VHT_STREAM_GROUPS) +#define IEEE80211_HE_GROUPS_NB (IEEE80211_HE_MAX_STREAMS * \ + IEEE80211_HE_STREAM_GROUPS) +#define IEEE80211_EHT_GROUPS_NB (IEEE80211_EHT_MAX_STREAMS * \ + IEEE80211_EHT_STREAM_GROUPS) #define IEEE80211_HT_GROUP_0 0 #define IEEE80211_VHT_GROUP_0 (IEEE80211_HT_GROUP_0 + IEEE80211_HT_GROUPS_NB) #define IEEE80211_HE_GROUP_0 (IEEE80211_VHT_GROUP_0 + IEEE80211_VHT_GROUPS_NB) +#define IEEE80211_EHT_GROUP_0 (IEEE80211_HE_GROUP_0 + IEEE80211_HE_GROUPS_NB) -#define MCS_GROUP_RATES 12 +#define MCS_GROUP_RATES 14 #define HT_GROUP_IDX(_streams, _sgi, _ht40) \ IEEE80211_HT_GROUP_0 + \ @@ -203,6 +223,69 @@ #define HE_GROUP(_streams, _gi, _bw) \ __HE_GROUP(_streams, _gi, _bw, \ HE_GROUP_SHIFT(_streams, _gi, _bw)) + +#define EHT_BW2VBPS(_bw, r5, r4, r3, r2, r1) \ + ((_bw) == BW_320 ? r5 : BW2VBPS(_bw, r4, r3, r2, r1)) + +#define EHT_GROUP_IDX(_streams, _gi, _bw) \ + (IEEE80211_EHT_GROUP_0 + \ + IEEE80211_EHT_MAX_STREAMS * 3 * (_bw) + \ + IEEE80211_EHT_MAX_STREAMS * (_gi) + \ + (_streams) - 1) + +#define __EHT_GROUP(_streams, _gi, _bw, _s) \ + [EHT_GROUP_IDX(_streams, _gi, _bw)] = { \ + .shift = _s, \ + .duration = { \ + EHT_DURATION_S(_s, _streams, _gi, \ + EHT_BW2VBPS(_bw, 1960, 980, 490, 234, 117)), \ + EHT_DURATION_S(_s, _streams, _gi, \ + EHT_BW2VBPS(_bw, 3920, 1960, 980, 468, 234)), \ + EHT_DURATION_S(_s, _streams, _gi, \ + EHT_BW2VBPS(_bw, 5880, 2937, 1470, 702, 351)), \ + EHT_DURATION_S(_s, _streams, _gi, \ + EHT_BW2VBPS(_bw, 7840, 3920, 1960, 936, 468)), \ + EHT_DURATION_S(_s, _streams, _gi, \ + EHT_BW2VBPS(_bw, 11760, 5880, 2940, 1404, 702)), \ + EHT_DURATION_S(_s, _streams, _gi, \ + EHT_BW2VBPS(_bw, 15680, 7840, 3920, 1872, 936)), \ + EHT_DURATION_S(_s, _streams, _gi, \ + EHT_BW2VBPS(_bw, 17640, 8820, 4410, 2106, 1053)), \ + EHT_DURATION_S(_s, _streams, _gi, \ + EHT_BW2VBPS(_bw, 19600, 9800, 4900, 2340, 1170)), \ + EHT_DURATION_S(_s, _streams, _gi, \ + EHT_BW2VBPS(_bw, 23520, 11760, 5880, 2808, 1404)), \ + EHT_DURATION_S(_s, _streams, _gi, \ + EHT_BW2VBPS(_bw, 26133, 13066, 6533, 3120, 1560)), \ + EHT_DURATION_S(_s, _streams, _gi, \ + EHT_BW2VBPS(_bw, 29400, 14700, 7350, 3510, 1755)), \ + EHT_DURATION_S(_s, _streams, _gi, \ + EHT_BW2VBPS(_bw, 32666, 16333, 8166, 3900, 1950)), \ + EHT_DURATION_S(_s, _streams, _gi, \ + EHT_BW2VBPS(_bw, 35280, 17640, 8820, 4212, 2106)), \ + EHT_DURATION_S(_s, _streams, _gi, \ + EHT_BW2VBPS(_bw, 39200, 19600, 9800, 4680, 2340)) \ + } \ +} + +#define EHT_GROUP_SHIFT(_streams, _gi, _bw) \ + GROUP_SHIFT(EHT_DURATION(_streams, _gi, \ + EHT_BW2VBPS(_bw, 1960, 980, 490, 234, 117))) + +#define EHT_GROUP(_streams, _gi, _bw) \ + __EHT_GROUP(_streams, _gi, _bw, \ + EHT_GROUP_SHIFT(_streams, _gi, _bw)) + +#define EHT_GROUP_RANGE(_gi, _bw) \ + EHT_GROUP(1, _gi, _bw), \ + EHT_GROUP(2, _gi, _bw), \ + EHT_GROUP(3, _gi, _bw), \ + EHT_GROUP(4, _gi, _bw), \ + EHT_GROUP(5, _gi, _bw), \ + EHT_GROUP(6, _gi, _bw), \ + EHT_GROUP(7, _gi, _bw), \ + EHT_GROUP(8, _gi, _bw) + struct mcs_group { u8 shift; u16 duration[MCS_GROUP_RATES]; @@ -376,6 +459,26 @@ static const struct mcs_group airtime_mcs_groups[] = { HE_GROUP(6, HE_GI_32, BW_160), HE_GROUP(7, HE_GI_32, BW_160), HE_GROUP(8, HE_GI_32, BW_160), + + EHT_GROUP_RANGE(EHT_GI_08, BW_20), + EHT_GROUP_RANGE(EHT_GI_16, BW_20), + EHT_GROUP_RANGE(EHT_GI_32, BW_20), + + EHT_GROUP_RANGE(EHT_GI_08, BW_40), + EHT_GROUP_RANGE(EHT_GI_16, BW_40), + EHT_GROUP_RANGE(EHT_GI_32, BW_40), + + EHT_GROUP_RANGE(EHT_GI_08, BW_80), + EHT_GROUP_RANGE(EHT_GI_16, BW_80), + EHT_GROUP_RANGE(EHT_GI_32, BW_80), + + EHT_GROUP_RANGE(EHT_GI_08, BW_160), + EHT_GROUP_RANGE(EHT_GI_16, BW_160), + EHT_GROUP_RANGE(EHT_GI_32, BW_160), + + EHT_GROUP_RANGE(EHT_GI_08, BW_320), + EHT_GROUP_RANGE(EHT_GI_16, BW_320), + EHT_GROUP_RANGE(EHT_GI_32, BW_320), }; static u32 @@ -422,6 +525,9 @@ static u32 ieee80211_get_rate_duration(struct ieee80211_hw *hw, case RATE_INFO_BW_160: bw = BW_160; break; + case RATE_INFO_BW_320: + bw = BW_320; + break; default: WARN_ON_ONCE(1); return 0; @@ -443,14 +549,27 @@ static u32 ieee80211_get_rate_duration(struct ieee80211_hw *hw, idx = status->rate_idx; group = HE_GROUP_IDX(streams, status->he_gi, bw); break; + case RX_ENC_EHT: + streams = status->nss; + idx = status->rate_idx; + group = EHT_GROUP_IDX(streams, status->eht.gi, bw); + break; default: WARN_ON_ONCE(1); return 0; } - if (WARN_ON_ONCE((status->encoding != RX_ENC_HE && streams > 4) || - (status->encoding == RX_ENC_HE && streams > 8))) - return 0; + switch (status->encoding) { + case RX_ENC_EHT: + case RX_ENC_HE: + if (WARN_ON_ONCE(streams > 8)) + return 0; + break; + default: + if (WARN_ON_ONCE(streams > 4)) + return 0; + break; + } if (idx >= MCS_GROUP_RATES) return 0; @@ -517,7 +636,9 @@ static bool ieee80211_fill_rate_info(struct ieee80211_hw *hw, stat->nss = ri->nss; stat->rate_idx = ri->mcs; - if (ri->flags & RATE_INFO_FLAGS_HE_MCS) + if (ri->flags & RATE_INFO_FLAGS_EHT_MCS) + stat->encoding = RX_ENC_EHT; + else if (ri->flags & RATE_INFO_FLAGS_HE_MCS) stat->encoding = RX_ENC_HE; else if (ri->flags & RATE_INFO_FLAGS_VHT_MCS) stat->encoding = RX_ENC_VHT; @@ -529,7 +650,14 @@ static bool ieee80211_fill_rate_info(struct ieee80211_hw *hw, if (ri->flags & RATE_INFO_FLAGS_SHORT_GI) stat->enc_flags |= RX_ENC_FLAG_SHORT_GI; - stat->he_gi = ri->he_gi; + switch (stat->encoding) { + case RX_ENC_EHT: + stat->eht.gi = ri->eht_gi; + break; + default: + stat->he_gi = ri->he_gi; + break; + } if (stat->encoding != RX_ENC_LEGACY) return true; diff --git a/net/mac80211/cfg.c b/net/mac80211/cfg.c index 83ad6c9709fe..847304a3a29a 100644 --- a/net/mac80211/cfg.c +++ b/net/mac80211/cfg.c @@ -114,7 +114,7 @@ static int ieee80211_set_mon_options(struct ieee80211_sub_if_data *sdata, /* apply all changes now - no failures allowed */ - if (monitor_sdata) + if (monitor_sdata && ieee80211_hw_check(&local->hw, WANT_MONITOR_VIF)) ieee80211_set_mu_mimo_follow(monitor_sdata, params); if (params->flags) { @@ -263,7 +263,7 @@ static int ieee80211_start_p2p_device(struct wiphy *wiphy, lockdep_assert_wiphy(sdata->local->hw.wiphy); - ret = ieee80211_check_combinations(sdata, NULL, 0, 0); + ret = ieee80211_check_combinations(sdata, NULL, 0, 0, -1); if (ret < 0) return ret; @@ -285,7 +285,7 @@ static int ieee80211_start_nan(struct wiphy *wiphy, lockdep_assert_wiphy(sdata->local->hw.wiphy); - ret = ieee80211_check_combinations(sdata, NULL, 0, 0); + ret = ieee80211_check_combinations(sdata, NULL, 0, 0, -1); if (ret < 0) return ret; @@ -742,9 +742,6 @@ static int ieee80211_get_key(struct wiphy *wiphy, struct net_device *dev, break; } - params.key = key->conf.key; - params.key_len = key->conf.keylen; - callback(cookie, ¶ms); err = 0; @@ -1379,6 +1376,11 @@ static int ieee80211_start_ap(struct wiphy *wiphy, struct net_device *dev, (IEEE80211_EHT_PHY_CAP7_MU_BEAMFORMER_80MHZ | IEEE80211_EHT_PHY_CAP7_MU_BEAMFORMER_160MHZ | IEEE80211_EHT_PHY_CAP7_MU_BEAMFORMER_320MHZ); + link_conf->eht_80mhz_full_bw_ul_mumimo = + params->eht_cap->fixed.phy_cap_info[7] & + (IEEE80211_EHT_PHY_CAP7_NON_OFDMA_UL_MU_MIMO_80MHZ | + IEEE80211_EHT_PHY_CAP7_NON_OFDMA_UL_MU_MIMO_160MHZ | + IEEE80211_EHT_PHY_CAP7_NON_OFDMA_UL_MU_MIMO_320MHZ); } else { link_conf->eht_su_beamformer = false; link_conf->eht_su_beamformee = false; @@ -1610,11 +1612,7 @@ static int ieee80211_stop_ap(struct wiphy *wiphy, struct net_device *dev, /* abort any running channel switch or color change */ link_conf->csa_active = false; link_conf->color_change_active = false; - if (sdata->csa_blocked_queues) { - ieee80211_wake_vif_queues(local, sdata, - IEEE80211_QUEUE_STOP_REASON_CSA); - sdata->csa_blocked_queues = false; - } + ieee80211_vif_unblock_queues_csa(sdata); ieee80211_free_next_beacon(link); @@ -1664,12 +1662,12 @@ static int ieee80211_stop_ap(struct wiphy *wiphy, struct net_device *dev, ieee80211_link_info_change_notify(sdata, link, BSS_CHANGED_BEACON_ENABLED); - if (sdata->wdev.cac_started) { + if (sdata->wdev.links[link_id].cac_started) { chandef = link_conf->chanreq.oper; wiphy_delayed_work_cancel(wiphy, &link->dfs_cac_timer_work); cfg80211_cac_event(sdata->dev, &chandef, NL80211_RADAR_CAC_ABORTED, - GFP_KERNEL); + GFP_KERNEL, link_id); } drv_stop_ap(sdata->local, sdata, link_conf); @@ -1809,11 +1807,17 @@ static void sta_apply_mesh_params(struct ieee80211_local *local, #endif } +enum sta_link_apply_mode { + STA_LINK_MODE_NEW, + STA_LINK_MODE_STA_MODIFY, + STA_LINK_MODE_LINK_MODIFY, +}; + static int sta_link_apply_parameters(struct ieee80211_local *local, - struct sta_info *sta, bool new_link, + struct sta_info *sta, + enum sta_link_apply_mode mode, struct link_station_parameters *params) { - int ret = 0; struct ieee80211_supported_band *sband; struct ieee80211_sub_if_data *sdata = sta->sdata; u32 link_id = params->link_id < 0 ? 0 : params->link_id; @@ -1822,18 +1826,29 @@ static int sta_link_apply_parameters(struct ieee80211_local *local, struct link_sta_info *link_sta = rcu_dereference_protected(sta->link[link_id], lockdep_is_held(&local->hw.wiphy->mtx)); - - /* - * If there are no changes, then accept a link that exist, - * unless it's a new link. - */ - if (params->link_id >= 0 && !new_link && - !params->link_mac && !params->txpwr_set && - !params->supported_rates_len && - !params->ht_capa && !params->vht_capa && - !params->he_capa && !params->eht_capa && - !params->opmode_notif_used) - return 0; + bool changes = params->link_mac || + params->txpwr_set || + params->supported_rates_len || + params->ht_capa || + params->vht_capa || + params->he_capa || + params->eht_capa || + params->opmode_notif_used; + + switch (mode) { + case STA_LINK_MODE_NEW: + if (!params->link_mac) + return -EINVAL; + break; + case STA_LINK_MODE_LINK_MODIFY: + break; + case STA_LINK_MODE_STA_MODIFY: + if (params->link_id >= 0) + break; + if (!changes) + return 0; + break; + } if (!link || !link_sta) return -EINVAL; @@ -1843,18 +1858,18 @@ static int sta_link_apply_parameters(struct ieee80211_local *local, return -EINVAL; if (params->link_mac) { - if (new_link) { + if (mode == STA_LINK_MODE_NEW) { memcpy(link_sta->addr, params->link_mac, ETH_ALEN); memcpy(link_sta->pub->addr, params->link_mac, ETH_ALEN); } else if (!ether_addr_equal(link_sta->addr, params->link_mac)) { return -EINVAL; } - } else if (new_link) { - return -EINVAL; } if (params->txpwr_set) { + int ret; + link_sta->pub->txpwr.type = params->txpwr.type; if (params->txpwr.type == NL80211_TX_POWER_LIMITED) link_sta->pub->txpwr.power = params->txpwr.power; @@ -1907,7 +1922,7 @@ static int sta_link_apply_parameters(struct ieee80211_local *local, ieee80211_sta_init_nss(link_sta); - return ret; + return 0; } static int sta_apply_parameters(struct ieee80211_local *local, @@ -2023,7 +2038,7 @@ static int sta_apply_parameters(struct ieee80211_local *local, if (params->listen_interval >= 0) sta->listen_interval = params->listen_interval; - ret = sta_link_apply_parameters(local, sta, false, + ret = sta_link_apply_parameters(local, sta, STA_LINK_MODE_STA_MODIFY, ¶ms->link_sta_params); if (ret) return ret; @@ -3038,6 +3053,9 @@ static int ieee80211_set_tx_power(struct wiphy *wiphy, sdata = IEEE80211_WDEV_TO_SUB_IF(wdev); if (sdata->vif.type == NL80211_IFTYPE_MONITOR) { + if (!ieee80211_hw_check(&local->hw, WANT_MONITOR_VIF)) + return -EOPNOTSUPP; + sdata = wiphy_dereference(local->hw.wiphy, local->monitor_sdata); if (!sdata) @@ -3100,7 +3118,7 @@ static int ieee80211_set_tx_power(struct wiphy *wiphy, if (has_monitor) { sdata = wiphy_dereference(local->hw.wiphy, local->monitor_sdata); - if (sdata) { + if (sdata && ieee80211_hw_check(&local->hw, WANT_MONITOR_VIF)) { sdata->deflink.user_power_level = local->user_power_level; if (txp_type != sdata->vif.bss_conf.txpower_type) update_txp_type = true; @@ -3444,55 +3462,58 @@ static int ieee80211_set_bitrate_mask(struct wiphy *wiphy, static int ieee80211_start_radar_detection(struct wiphy *wiphy, struct net_device *dev, struct cfg80211_chan_def *chandef, - u32 cac_time_ms) + u32 cac_time_ms, int link_id) { struct ieee80211_sub_if_data *sdata = IEEE80211_DEV_TO_SUB_IF(dev); struct ieee80211_chan_req chanreq = { .oper = *chandef }; struct ieee80211_local *local = sdata->local; + struct ieee80211_link_data *link_data; int err; lockdep_assert_wiphy(local->hw.wiphy); - if (!list_empty(&local->roc_list) || local->scanning) { - err = -EBUSY; - goto out_unlock; - } + if (!list_empty(&local->roc_list) || local->scanning) + return -EBUSY; + + link_data = sdata_dereference(sdata->link[link_id], sdata); + if (!link_data) + return -ENOLINK; /* whatever, but channel contexts should not complain about that one */ - sdata->deflink.smps_mode = IEEE80211_SMPS_OFF; - sdata->deflink.needed_rx_chains = local->rx_chains; + link_data->smps_mode = IEEE80211_SMPS_OFF; + link_data->needed_rx_chains = local->rx_chains; - err = ieee80211_link_use_channel(&sdata->deflink, &chanreq, + err = ieee80211_link_use_channel(link_data, &chanreq, IEEE80211_CHANCTX_SHARED); if (err) - goto out_unlock; + return err; - wiphy_delayed_work_queue(wiphy, &sdata->deflink.dfs_cac_timer_work, + wiphy_delayed_work_queue(wiphy, &link_data->dfs_cac_timer_work, msecs_to_jiffies(cac_time_ms)); - out_unlock: - return err; + return 0; } static void ieee80211_end_cac(struct wiphy *wiphy, - struct net_device *dev) + struct net_device *dev, unsigned int link_id) { struct ieee80211_sub_if_data *sdata = IEEE80211_DEV_TO_SUB_IF(dev); struct ieee80211_local *local = sdata->local; + struct ieee80211_link_data *link_data; lockdep_assert_wiphy(local->hw.wiphy); list_for_each_entry(sdata, &local->interfaces, list) { - /* it might be waiting for the local->mtx, but then - * by the time it gets it, sdata->wdev.cac_started - * will no longer be true - */ + link_data = sdata_dereference(sdata->link[link_id], sdata); + if (!link_data) + continue; + wiphy_delayed_work_cancel(wiphy, - &sdata->deflink.dfs_cac_timer_work); + &link_data->dfs_cac_timer_work); - if (sdata->wdev.cac_started) { - ieee80211_link_release_channel(&sdata->deflink); - sdata->wdev.cac_started = false; + if (sdata->wdev.links[link_id].cac_started) { + ieee80211_link_release_channel(link_data); + sdata->wdev.links[link_id].cac_started = false; } } } @@ -3638,10 +3659,10 @@ void ieee80211_csa_finish(struct ieee80211_vif *vif, unsigned int link_id) continue; wiphy_work_queue(iter->local->hw.wiphy, - &iter->deflink.csa_finalize_work); + &iter->deflink.csa.finalize_work); } } - wiphy_work_queue(local->hw.wiphy, &link_data->csa_finalize_work); + wiphy_work_queue(local->hw.wiphy, &link_data->csa.finalize_work); rcu_read_unlock(); } @@ -3728,7 +3749,7 @@ static int __ieee80211_csa_finalize(struct ieee80211_link_data *link_data) } if (!cfg80211_chandef_identical(&link_conf->chanreq.oper, - &link_data->csa_chanreq.oper)) + &link_data->csa.chanreq.oper)) return -EINVAL; link_conf->csa_active = false; @@ -3739,17 +3760,13 @@ static int __ieee80211_csa_finalize(struct ieee80211_link_data *link_data) ieee80211_link_info_change_notify(sdata, link_data, changed); - if (sdata->csa_blocked_queues) { - ieee80211_wake_vif_queues(local, sdata, - IEEE80211_QUEUE_STOP_REASON_CSA); - sdata->csa_blocked_queues = false; - } + ieee80211_vif_unblock_queues_csa(sdata); err = drv_post_channel_switch(link_data); if (err) return err; - cfg80211_ch_switch_notify(sdata->dev, &link_data->csa_chanreq.oper, + cfg80211_ch_switch_notify(sdata->dev, &link_data->csa.chanreq.oper, link_data->link_id); return 0; @@ -3770,7 +3787,7 @@ static void ieee80211_csa_finalize(struct ieee80211_link_data *link_data) void ieee80211_csa_finalize_work(struct wiphy *wiphy, struct wiphy_work *work) { struct ieee80211_link_data *link = - container_of(work, struct ieee80211_link_data, csa_finalize_work); + container_of(work, struct ieee80211_link_data, csa.finalize_work); struct ieee80211_sub_if_data *sdata = link->sdata; struct ieee80211_local *local = sdata->local; @@ -3951,7 +3968,7 @@ __ieee80211_channel_switch(struct wiphy *wiphy, struct net_device *dev, if (!list_empty(&local->roc_list) || local->scanning) return -EBUSY; - if (sdata->wdev.cac_started) + if (sdata->wdev.links[link_id].cac_started) return -EBUSY; if (WARN_ON(link_id >= IEEE80211_MLD_MAX_NUM_LINKS)) @@ -4001,7 +4018,7 @@ __ieee80211_channel_switch(struct wiphy *wiphy, struct net_device *dev, goto out; /* if reservation is invalid then this will fail */ - err = ieee80211_check_combinations(sdata, NULL, chanctx->mode, 0); + err = ieee80211_check_combinations(sdata, NULL, chanctx->mode, 0, -1); if (err) { ieee80211_link_unreserve_chanctx(link_data); goto out; @@ -4017,23 +4034,19 @@ __ieee80211_channel_switch(struct wiphy *wiphy, struct net_device *dev, goto out; } - link_data->csa_chanreq = chanreq; + link_data->csa.chanreq = chanreq; link_conf->csa_active = true; - if (params->block_tx && - !ieee80211_hw_check(&local->hw, HANDLES_QUIET_CSA)) { - ieee80211_stop_vif_queues(local, sdata, - IEEE80211_QUEUE_STOP_REASON_CSA); - sdata->csa_blocked_queues = true; - } + if (params->block_tx) + ieee80211_vif_block_queues_csa(sdata); cfg80211_ch_switch_started_notify(sdata->dev, - &link_data->csa_chanreq.oper, link_id, + &link_data->csa.chanreq.oper, link_id, params->count, params->block_tx); if (changed) { ieee80211_link_info_change_notify(sdata, link_data, changed); - drv_channel_switch_beacon(sdata, &link_data->csa_chanreq.oper); + drv_channel_switch_beacon(sdata, &link_data->csa.chanreq.oper); } else { /* if the beacon didn't change, we can finalize immediately */ ieee80211_csa_finalize(link_data); @@ -4979,13 +4992,17 @@ static void ieee80211_del_intf_link(struct wiphy *wiphy, ieee80211_vif_set_links(sdata, wdev->valid_links, 0); } -static int sta_add_link_station(struct ieee80211_local *local, - struct ieee80211_sub_if_data *sdata, - struct link_station_parameters *params) +static int +ieee80211_add_link_station(struct wiphy *wiphy, struct net_device *dev, + struct link_station_parameters *params) { + struct ieee80211_sub_if_data *sdata = IEEE80211_DEV_TO_SUB_IF(dev); + struct ieee80211_local *local = wiphy_priv(wiphy); struct sta_info *sta; int ret; + lockdep_assert_wiphy(local->hw.wiphy); + sta = sta_info_get_bss(sdata, params->mld_mac); if (!sta) return -ENOENT; @@ -5000,7 +5017,7 @@ static int sta_add_link_station(struct ieee80211_local *local, if (ret) return ret; - ret = sta_link_apply_parameters(local, sta, true, params); + ret = sta_link_apply_parameters(local, sta, STA_LINK_MODE_NEW, params); if (ret) { ieee80211_sta_free_link(sta, params->link_id); return ret; @@ -5011,23 +5028,15 @@ static int sta_add_link_station(struct ieee80211_local *local, } static int -ieee80211_add_link_station(struct wiphy *wiphy, struct net_device *dev, +ieee80211_mod_link_station(struct wiphy *wiphy, struct net_device *dev, struct link_station_parameters *params) { struct ieee80211_sub_if_data *sdata = IEEE80211_DEV_TO_SUB_IF(dev); struct ieee80211_local *local = wiphy_priv(wiphy); - - lockdep_assert_wiphy(sdata->local->hw.wiphy); - - return sta_add_link_station(local, sdata, params); -} - -static int sta_mod_link_station(struct ieee80211_local *local, - struct ieee80211_sub_if_data *sdata, - struct link_station_parameters *params) -{ struct sta_info *sta; + lockdep_assert_wiphy(local->hw.wiphy); + sta = sta_info_get_bss(sdata, params->mld_mac); if (!sta) return -ENOENT; @@ -5035,26 +5044,19 @@ static int sta_mod_link_station(struct ieee80211_local *local, if (!(sta->sta.valid_links & BIT(params->link_id))) return -EINVAL; - return sta_link_apply_parameters(local, sta, false, params); + return sta_link_apply_parameters(local, sta, STA_LINK_MODE_LINK_MODIFY, + params); } static int -ieee80211_mod_link_station(struct wiphy *wiphy, struct net_device *dev, - struct link_station_parameters *params) +ieee80211_del_link_station(struct wiphy *wiphy, struct net_device *dev, + struct link_station_del_parameters *params) { struct ieee80211_sub_if_data *sdata = IEEE80211_DEV_TO_SUB_IF(dev); - struct ieee80211_local *local = wiphy_priv(wiphy); + struct sta_info *sta; lockdep_assert_wiphy(sdata->local->hw.wiphy); - return sta_mod_link_station(local, sdata, params); -} - -static int sta_del_link_station(struct ieee80211_sub_if_data *sdata, - struct link_station_del_parameters *params) -{ - struct sta_info *sta; - sta = sta_info_get_bss(sdata, params->mld_mac); if (!sta) return -ENOENT; @@ -5071,17 +5073,6 @@ static int sta_del_link_station(struct ieee80211_sub_if_data *sdata, return 0; } -static int -ieee80211_del_link_station(struct wiphy *wiphy, struct net_device *dev, - struct link_station_del_parameters *params) -{ - struct ieee80211_sub_if_data *sdata = IEEE80211_DEV_TO_SUB_IF(dev); - - lockdep_assert_wiphy(sdata->local->hw.wiphy); - - return sta_del_link_station(sdata, params); -} - static int ieee80211_set_hw_timestamp(struct wiphy *wiphy, struct net_device *dev, struct cfg80211_set_hw_timestamp *hwts) @@ -5222,4 +5213,5 @@ const struct cfg80211_ops mac80211_config_ops = { .del_link_station = ieee80211_del_link_station, .set_hw_timestamp = ieee80211_set_hw_timestamp, .set_ttlm = ieee80211_set_ttlm, + .get_radio_mask = ieee80211_get_radio_mask, }; diff --git a/net/mac80211/chan.c b/net/mac80211/chan.c index 380695fdc32f..cca6d14084d2 100644 --- a/net/mac80211/chan.c +++ b/net/mac80211/chan.c @@ -47,24 +47,29 @@ int ieee80211_chanctx_refcount(struct ieee80211_local *local, ieee80211_chanctx_num_reserved(local, ctx); } -static int ieee80211_num_chanctx(struct ieee80211_local *local) +static int ieee80211_num_chanctx(struct ieee80211_local *local, int radio_idx) { struct ieee80211_chanctx *ctx; int num = 0; lockdep_assert_wiphy(local->hw.wiphy); - list_for_each_entry(ctx, &local->chanctx_list, list) + list_for_each_entry(ctx, &local->chanctx_list, list) { + if (radio_idx >= 0 && ctx->conf.radio_idx != radio_idx) + continue; num++; + } return num; } -static bool ieee80211_can_create_new_chanctx(struct ieee80211_local *local) +static bool ieee80211_can_create_new_chanctx(struct ieee80211_local *local, + int radio_idx) { lockdep_assert_wiphy(local->hw.wiphy); - return ieee80211_num_chanctx(local) < ieee80211_max_num_channels(local); + return ieee80211_num_chanctx(local, radio_idx) < + ieee80211_max_num_channels(local, radio_idx); } static struct ieee80211_chanctx * @@ -281,7 +286,9 @@ ieee80211_get_max_required_bw(struct ieee80211_link_data *link) enum nl80211_chan_width max_bw = NL80211_CHAN_WIDTH_20_NOHT; struct sta_info *sta; - list_for_each_entry_rcu(sta, &sdata->local->sta_list, list) { + lockdep_assert_wiphy(sdata->local->hw.wiphy); + + list_for_each_entry(sta, &sdata->local->sta_list, list) { if (sdata != sta->sdata && !(sta->sdata->bss && sta->sdata->bss == sdata->bss)) continue; @@ -295,17 +302,24 @@ ieee80211_get_max_required_bw(struct ieee80211_link_data *link) static enum nl80211_chan_width ieee80211_get_chanctx_max_required_bw(struct ieee80211_local *local, struct ieee80211_chanctx *ctx, - struct ieee80211_link_data *rsvd_for) + struct ieee80211_link_data *rsvd_for, + bool check_reserved) { struct ieee80211_sub_if_data *sdata; struct ieee80211_link_data *link; enum nl80211_chan_width max_bw = NL80211_CHAN_WIDTH_20_NOHT; + if (WARN_ON(check_reserved && rsvd_for)) + return ctx->conf.def.width; + for_each_sdata_link(local, link) { enum nl80211_chan_width width = NL80211_CHAN_WIDTH_20_NOHT; - if (link != rsvd_for && - rcu_access_pointer(link->conf->chanctx_conf) != &ctx->conf) + if (check_reserved) { + if (link->reserved_chanctx != ctx) + continue; + } else if (link != rsvd_for && + rcu_access_pointer(link->conf->chanctx_conf) != &ctx->conf) continue; switch (link->sdata->vif.type) { @@ -359,7 +373,8 @@ ieee80211_get_chanctx_max_required_bw(struct ieee80211_local *local, static u32 _ieee80211_recalc_chanctx_min_def(struct ieee80211_local *local, struct ieee80211_chanctx *ctx, - struct ieee80211_link_data *rsvd_for) + struct ieee80211_link_data *rsvd_for, + bool check_reserved) { enum nl80211_chan_width max_bw; struct cfg80211_chan_def min_def; @@ -379,7 +394,8 @@ _ieee80211_recalc_chanctx_min_def(struct ieee80211_local *local, return 0; } - max_bw = ieee80211_get_chanctx_max_required_bw(local, ctx, rsvd_for); + max_bw = ieee80211_get_chanctx_max_required_bw(local, ctx, rsvd_for, + check_reserved); /* downgrade chandef up to max_bw */ min_def = ctx->conf.def; @@ -396,12 +412,9 @@ _ieee80211_recalc_chanctx_min_def(struct ieee80211_local *local, return IEEE80211_CHANCTX_CHANGE_MIN_WIDTH; } -/* calling this function is assuming that station vif is updated to - * lates changes by calling ieee80211_link_update_chanreq - */ static void ieee80211_chan_bw_change(struct ieee80211_local *local, struct ieee80211_chanctx *ctx, - bool narrowed) + bool reserved, bool narrowed) { struct sta_info *sta; struct ieee80211_supported_band *sband = @@ -418,13 +431,17 @@ static void ieee80211_chan_bw_change(struct ieee80211_local *local, continue; for (link_id = 0; link_id < ARRAY_SIZE(sta->sdata->link); link_id++) { - struct ieee80211_bss_conf *link_conf = - rcu_dereference(sdata->vif.link_conf[link_id]); + struct ieee80211_link_data *link = + rcu_dereference(sdata->link[link_id]); + struct ieee80211_bss_conf *link_conf; + struct cfg80211_chan_def *new_chandef; struct link_sta_info *link_sta; - if (!link_conf) + if (!link) continue; + link_conf = link->conf; + if (rcu_access_pointer(link_conf->chanctx_conf) != &ctx->conf) continue; @@ -432,7 +449,13 @@ static void ieee80211_chan_bw_change(struct ieee80211_local *local, if (!link_sta) continue; - new_sta_bw = ieee80211_sta_cur_vht_bw(link_sta); + if (reserved) + new_chandef = &link->reserved.oper; + else + new_chandef = &link_conf->chanreq.oper; + + new_sta_bw = _ieee80211_sta_cur_vht_bw(link_sta, + new_chandef); /* nothing change */ if (new_sta_bw == link_sta->pub->bandwidth) @@ -458,20 +481,22 @@ static void ieee80211_chan_bw_change(struct ieee80211_local *local, */ void ieee80211_recalc_chanctx_min_def(struct ieee80211_local *local, struct ieee80211_chanctx *ctx, - struct ieee80211_link_data *rsvd_for) + struct ieee80211_link_data *rsvd_for, + bool check_reserved) { - u32 changed = _ieee80211_recalc_chanctx_min_def(local, ctx, rsvd_for); + u32 changed = _ieee80211_recalc_chanctx_min_def(local, ctx, rsvd_for, + check_reserved); if (!changed) return; /* check is BW narrowed */ - ieee80211_chan_bw_change(local, ctx, true); + ieee80211_chan_bw_change(local, ctx, false, true); drv_change_chanctx(local, ctx, changed); /* check is BW wider */ - ieee80211_chan_bw_change(local, ctx, false); + ieee80211_chan_bw_change(local, ctx, false, false); } static void _ieee80211_change_chanctx(struct ieee80211_local *local, @@ -505,10 +530,10 @@ static void _ieee80211_change_chanctx(struct ieee80211_local *local, * due to maybe not returning from it, e.g in case new context was added * first time with all parameters up to date. */ - ieee80211_chan_bw_change(local, old_ctx, true); + ieee80211_chan_bw_change(local, old_ctx, false, true); if (ieee80211_chanreq_identical(&ctx_req, chanreq)) { - ieee80211_recalc_chanctx_min_def(local, ctx, rsvd_for); + ieee80211_recalc_chanctx_min_def(local, ctx, rsvd_for, false); return; } @@ -529,14 +554,14 @@ static void _ieee80211_change_chanctx(struct ieee80211_local *local, ctx->conf.ap = chanreq->ap; /* check if min chanctx also changed */ - changed |= _ieee80211_recalc_chanctx_min_def(local, ctx, rsvd_for); + changed |= _ieee80211_recalc_chanctx_min_def(local, ctx, rsvd_for, false); ieee80211_add_wbrf(local, &ctx->conf.def); drv_change_chanctx(local, ctx, changed); /* check if BW is wider */ - ieee80211_chan_bw_change(local, old_ctx, false); + ieee80211_chan_bw_change(local, old_ctx, false, false); } static void ieee80211_change_chanctx(struct ieee80211_local *local, @@ -638,7 +663,8 @@ ieee80211_chanctx_radar_required(struct ieee80211_local *local, static struct ieee80211_chanctx * ieee80211_alloc_chanctx(struct ieee80211_local *local, const struct ieee80211_chan_req *chanreq, - enum ieee80211_chanctx_mode mode) + enum ieee80211_chanctx_mode mode, + int radio_idx) { struct ieee80211_chanctx *ctx; @@ -656,7 +682,9 @@ ieee80211_alloc_chanctx(struct ieee80211_local *local, ctx->conf.rx_chains_dynamic = 1; ctx->mode = mode; ctx->conf.radar_enabled = false; - _ieee80211_recalc_chanctx_min_def(local, ctx, NULL); + ctx->conf.radio_idx = radio_idx; + ctx->radar_detected = false; + _ieee80211_recalc_chanctx_min_def(local, ctx, NULL, false); return ctx; } @@ -689,14 +717,15 @@ static struct ieee80211_chanctx * ieee80211_new_chanctx(struct ieee80211_local *local, const struct ieee80211_chan_req *chanreq, enum ieee80211_chanctx_mode mode, - bool assign_on_failure) + bool assign_on_failure, + int radio_idx) { struct ieee80211_chanctx *ctx; int err; lockdep_assert_wiphy(local->hw.wiphy); - ctx = ieee80211_alloc_chanctx(local, chanreq, mode); + ctx = ieee80211_alloc_chanctx(local, chanreq, mode, radio_idx); if (!ctx) return ERR_PTR(-ENOMEM); @@ -775,13 +804,24 @@ void ieee80211_recalc_chanctx_chantype(struct ieee80211_local *local, /* TDLS peers can sometimes affect the chandef width */ list_for_each_entry(sta, &local->sta_list, list) { + struct ieee80211_sub_if_data *sdata = sta->sdata; struct ieee80211_chan_req tdls_chanreq = {}; + int tdls_link_id; + if (!sta->uploaded || !test_sta_flag(sta, WLAN_STA_TDLS_WIDER_BW) || !test_sta_flag(sta, WLAN_STA_AUTHORIZED) || !sta->tdls_chandef.chan) continue; + tdls_link_id = ieee80211_tdls_sta_link_id(sta); + link = sdata_dereference(sdata->link[tdls_link_id], sdata); + if (!link) + continue; + + if (rcu_access_pointer(link->conf->chanctx_conf) != conf) + continue; + tdls_chanreq.oper = sta->tdls_chandef; /* note this always fills and returns &tmp if compat */ @@ -838,7 +878,7 @@ static int ieee80211_assign_link_chanctx(struct ieee80211_link_data *link, if (new_ctx) { /* recalc considering the link we'll use it for now */ - ieee80211_recalc_chanctx_min_def(local, new_ctx, link); + ieee80211_recalc_chanctx_min_def(local, new_ctx, link, false); ret = drv_assign_vif_chanctx(local, sdata, link->conf, new_ctx); if (assign_on_failure || !ret) { @@ -861,12 +901,12 @@ static int ieee80211_assign_link_chanctx(struct ieee80211_link_data *link, ieee80211_recalc_chanctx_chantype(local, curr_ctx); ieee80211_recalc_smps_chanctx(local, curr_ctx); ieee80211_recalc_radar_chanctx(local, curr_ctx); - ieee80211_recalc_chanctx_min_def(local, curr_ctx, NULL); + ieee80211_recalc_chanctx_min_def(local, curr_ctx, NULL, false); } if (new_ctx && ieee80211_chanctx_num_assigned(local, new_ctx) > 0) { ieee80211_recalc_txpower(sdata, false); - ieee80211_recalc_chanctx_min_def(local, new_ctx, NULL); + ieee80211_recalc_chanctx_min_def(local, new_ctx, NULL, false); } if (conf) { @@ -1053,6 +1093,107 @@ int ieee80211_link_unreserve_chanctx(struct ieee80211_link_data *link) return 0; } +static struct ieee80211_chanctx * +ieee80211_replace_chanctx(struct ieee80211_local *local, + const struct ieee80211_chan_req *chanreq, + enum ieee80211_chanctx_mode mode, + struct ieee80211_chanctx *curr_ctx) +{ + struct ieee80211_chanctx *new_ctx, *ctx; + struct wiphy *wiphy = local->hw.wiphy; + const struct wiphy_radio *radio; + + if (!curr_ctx || (curr_ctx->replace_state == + IEEE80211_CHANCTX_WILL_BE_REPLACED) || + !list_empty(&curr_ctx->reserved_links)) { + /* + * Another link already requested this context for a + * reservation. Find another one hoping all links assigned + * to it will also switch soon enough. + * + * TODO: This needs a little more work as some cases + * (more than 2 chanctx capable devices) may fail which could + * otherwise succeed provided some channel context juggling was + * performed. + * + * Consider ctx1..3, link1..6, each ctx has 2 links. link1 and + * link2 from ctx1 request new different chandefs starting 2 + * in-place reserations with ctx4 and ctx5 replacing ctx1 and + * ctx2 respectively. Next link5 and link6 from ctx3 reserve + * ctx4. If link3 and link4 remain on ctx2 as they are then this + * fails unless `replace_ctx` from ctx5 is replaced with ctx3. + */ + list_for_each_entry(ctx, &local->chanctx_list, list) { + if (ctx->replace_state != + IEEE80211_CHANCTX_REPLACE_NONE) + continue; + + if (!list_empty(&ctx->reserved_links)) + continue; + + if (ctx->conf.radio_idx >= 0) { + radio = &wiphy->radio[ctx->conf.radio_idx]; + if (!cfg80211_radio_chandef_valid(radio, &chanreq->oper)) + continue; + } + + curr_ctx = ctx; + break; + } + } + + /* + * If that's true then all available contexts already have reservations + * and cannot be used. + */ + if (!curr_ctx || (curr_ctx->replace_state == + IEEE80211_CHANCTX_WILL_BE_REPLACED) || + !list_empty(&curr_ctx->reserved_links)) + return ERR_PTR(-EBUSY); + + new_ctx = ieee80211_alloc_chanctx(local, chanreq, mode, -1); + if (!new_ctx) + return ERR_PTR(-ENOMEM); + + new_ctx->replace_ctx = curr_ctx; + new_ctx->replace_state = IEEE80211_CHANCTX_REPLACES_OTHER; + + curr_ctx->replace_ctx = new_ctx; + curr_ctx->replace_state = IEEE80211_CHANCTX_WILL_BE_REPLACED; + + list_add_rcu(&new_ctx->list, &local->chanctx_list); + + return new_ctx; +} + +static bool +ieee80211_find_available_radio(struct ieee80211_local *local, + const struct ieee80211_chan_req *chanreq, + int *radio_idx) +{ + struct wiphy *wiphy = local->hw.wiphy; + const struct wiphy_radio *radio; + int i; + + *radio_idx = -1; + if (!wiphy->n_radio) + return true; + + for (i = 0; i < wiphy->n_radio; i++) { + radio = &wiphy->radio[i]; + if (!cfg80211_radio_chandef_valid(radio, &chanreq->oper)) + continue; + + if (!ieee80211_can_create_new_chanctx(local, i)) + continue; + + *radio_idx = i; + return true; + } + + return false; +} + int ieee80211_link_reserve_chanctx(struct ieee80211_link_data *link, const struct ieee80211_chan_req *chanreq, enum ieee80211_chanctx_mode mode, @@ -1060,7 +1201,8 @@ int ieee80211_link_reserve_chanctx(struct ieee80211_link_data *link, { struct ieee80211_sub_if_data *sdata = link->sdata; struct ieee80211_local *local = sdata->local; - struct ieee80211_chanctx *new_ctx, *curr_ctx, *ctx; + struct ieee80211_chanctx *new_ctx, *curr_ctx; + int radio_idx; lockdep_assert_wiphy(local->hw.wiphy); @@ -1070,76 +1212,15 @@ int ieee80211_link_reserve_chanctx(struct ieee80211_link_data *link, new_ctx = ieee80211_find_reservation_chanctx(local, chanreq, mode); if (!new_ctx) { - if (ieee80211_can_create_new_chanctx(local)) { + if (ieee80211_can_create_new_chanctx(local, -1) && + ieee80211_find_available_radio(local, chanreq, &radio_idx)) new_ctx = ieee80211_new_chanctx(local, chanreq, mode, - false); - if (IS_ERR(new_ctx)) - return PTR_ERR(new_ctx); - } else { - if (!curr_ctx || - (curr_ctx->replace_state == - IEEE80211_CHANCTX_WILL_BE_REPLACED) || - !list_empty(&curr_ctx->reserved_links)) { - /* - * Another link already requested this context - * for a reservation. Find another one hoping - * all links assigned to it will also switch - * soon enough. - * - * TODO: This needs a little more work as some - * cases (more than 2 chanctx capable devices) - * may fail which could otherwise succeed - * provided some channel context juggling was - * performed. - * - * Consider ctx1..3, link1..6, each ctx has 2 - * links. link1 and link2 from ctx1 request new - * different chandefs starting 2 in-place - * reserations with ctx4 and ctx5 replacing - * ctx1 and ctx2 respectively. Next link5 and - * link6 from ctx3 reserve ctx4. If link3 and - * link4 remain on ctx2 as they are then this - * fails unless `replace_ctx` from ctx5 is - * replaced with ctx3. - */ - list_for_each_entry(ctx, &local->chanctx_list, - list) { - if (ctx->replace_state != - IEEE80211_CHANCTX_REPLACE_NONE) - continue; - - if (!list_empty(&ctx->reserved_links)) - continue; - - curr_ctx = ctx; - break; - } - } - - /* - * If that's true then all available contexts already - * have reservations and cannot be used. - */ - if (!curr_ctx || - (curr_ctx->replace_state == - IEEE80211_CHANCTX_WILL_BE_REPLACED) || - !list_empty(&curr_ctx->reserved_links)) - return -EBUSY; - - new_ctx = ieee80211_alloc_chanctx(local, chanreq, mode); - if (!new_ctx) - return -ENOMEM; - - new_ctx->replace_ctx = curr_ctx; - new_ctx->replace_state = - IEEE80211_CHANCTX_REPLACES_OTHER; - - curr_ctx->replace_ctx = new_ctx; - curr_ctx->replace_state = - IEEE80211_CHANCTX_WILL_BE_REPLACED; - - list_add_rcu(&new_ctx->list, &local->chanctx_list); - } + false, radio_idx); + else + new_ctx = ieee80211_replace_chanctx(local, chanreq, + mode, curr_ctx); + if (IS_ERR(new_ctx)) + return PTR_ERR(new_ctx); } list_add(&link->reserved_chanctx_list, &new_ctx->reserved_links); @@ -1162,11 +1243,11 @@ ieee80211_link_chanctx_reservation_complete(struct ieee80211_link_data *link) case NL80211_IFTYPE_MESH_POINT: case NL80211_IFTYPE_OCB: wiphy_work_queue(sdata->local->hw.wiphy, - &link->csa_finalize_work); + &link->csa.finalize_work); break; case NL80211_IFTYPE_STATION: wiphy_delayed_work_queue(sdata->local->hw.wiphy, - &link->u.mgd.chswitch_work, 0); + &link->u.mgd.csa.switch_work, 0); break; case NL80211_IFTYPE_UNSPECIFIED: case NL80211_IFTYPE_AP_VLAN: @@ -1279,7 +1360,7 @@ ieee80211_link_use_reserved_reassign(struct ieee80211_link_data *link) if (ieee80211_chanctx_refcount(local, old_ctx) == 0) ieee80211_free_chanctx(local, old_ctx, false); - ieee80211_recalc_chanctx_min_def(local, new_ctx, NULL); + ieee80211_recalc_chanctx_min_def(local, new_ctx, NULL, false); ieee80211_recalc_smps_chanctx(local, new_ctx); ieee80211_recalc_radar_chanctx(local, new_ctx); @@ -1545,6 +1626,31 @@ static int ieee80211_vif_use_reserved_switch(struct ieee80211_local *local) goto err; } + /* update station rate control and min width before switch */ + list_for_each_entry(ctx, &local->chanctx_list, list) { + struct ieee80211_link_data *link; + + if (ctx->replace_state != IEEE80211_CHANCTX_REPLACES_OTHER) + continue; + + if (WARN_ON(!ctx->replace_ctx)) { + err = -EINVAL; + goto err; + } + + list_for_each_entry(link, &ctx->reserved_links, + reserved_chanctx_list) { + if (!ieee80211_link_has_in_place_reservation(link)) + continue; + + ieee80211_chan_bw_change(local, + ieee80211_link_get_chanctx(link), + true, true); + } + + ieee80211_recalc_chanctx_min_def(local, ctx, NULL, true); + } + /* * All necessary vifs are ready. Perform the switch now depending on * reservations and driver capabilities. @@ -1612,7 +1718,7 @@ static int ieee80211_vif_use_reserved_switch(struct ieee80211_local *local) ieee80211_recalc_chanctx_chantype(local, ctx); ieee80211_recalc_smps_chanctx(local, ctx); ieee80211_recalc_radar_chanctx(local, ctx); - ieee80211_recalc_chanctx_min_def(local, ctx, NULL); + ieee80211_recalc_chanctx_min_def(local, ctx, NULL, false); list_for_each_entry_safe(link, link_tmp, &ctx->reserved_links, reserved_chanctx_list) { @@ -1625,6 +1731,7 @@ static int ieee80211_vif_use_reserved_switch(struct ieee80211_local *local) link->reserved_chanctx = NULL; ieee80211_link_chanctx_reservation_complete(link); + ieee80211_chan_bw_change(local, ctx, false, false); } /* @@ -1745,6 +1852,7 @@ int _ieee80211_link_use_channel(struct ieee80211_link_data *link, struct ieee80211_chanctx *ctx; u8 radar_detect_width = 0; bool reserved = false; + int radio_idx; int ret; lockdep_assert_wiphy(local->hw.wiphy); @@ -1765,7 +1873,7 @@ int _ieee80211_link_use_channel(struct ieee80211_link_data *link, link->radar_required = ret; ret = ieee80211_check_combinations(sdata, &chanreq->oper, mode, - radar_detect_width); + radar_detect_width, -1); if (ret < 0) goto out; @@ -1775,9 +1883,11 @@ int _ieee80211_link_use_channel(struct ieee80211_link_data *link, /* Note: context is now reserved */ if (ctx) reserved = true; + else if (!ieee80211_find_available_radio(local, chanreq, &radio_idx)) + ctx = ERR_PTR(-EBUSY); else ctx = ieee80211_new_chanctx(local, chanreq, mode, - assign_on_failure); + assign_on_failure, radio_idx); if (IS_ERR(ctx)) { ret = PTR_ERR(ctx); goto out; diff --git a/net/mac80211/debugfs.c b/net/mac80211/debugfs.c index 98310188f330..02b5476a4376 100644 --- a/net/mac80211/debugfs.c +++ b/net/mac80211/debugfs.c @@ -483,7 +483,6 @@ static const char *hw_flag_names[] = { FLAG(REPORTS_LOW_ACK), FLAG(SUPPORTS_TX_FRAG), FLAG(SUPPORTS_TDLS_BUFFER_STA), - FLAG(DEAUTH_NEED_MGD_TX_PREP), FLAG(DOESNT_SUPPORT_QOS_NDP), FLAG(BUFF_MMPDU_TXQ), FLAG(SUPPORTS_VHT_EXT_NSS_BW), diff --git a/net/mac80211/driver-ops.c b/net/mac80211/driver-ops.c index 254d745832cb..fe868b521622 100644 --- a/net/mac80211/driver-ops.c +++ b/net/mac80211/driver-ops.c @@ -33,7 +33,7 @@ int drv_start(struct ieee80211_local *local) return ret; } -void drv_stop(struct ieee80211_local *local) +void drv_stop(struct ieee80211_local *local, bool suspend) { might_sleep(); lockdep_assert_wiphy(local->hw.wiphy); @@ -41,8 +41,8 @@ void drv_stop(struct ieee80211_local *local) if (WARN_ON(!local->started)) return; - trace_drv_stop(local); - local->ops->stop(&local->hw); + trace_drv_stop(local, suspend); + local->ops->stop(&local->hw, suspend); trace_drv_return_void(local); /* sync away all work on the tasklet before clearing started */ diff --git a/net/mac80211/driver-ops.h b/net/mac80211/driver-ops.h index 5d078c0a2323..d382d9729e85 100644 --- a/net/mac80211/driver-ops.h +++ b/net/mac80211/driver-ops.h @@ -88,7 +88,7 @@ static inline int drv_get_et_sset_count(struct ieee80211_sub_if_data *sdata, } int drv_start(struct ieee80211_local *local); -void drv_stop(struct ieee80211_local *local); +void drv_stop(struct ieee80211_local *local, bool suspend); #ifdef CONFIG_PM static inline int drv_suspend(struct ieee80211_local *local, @@ -1150,6 +1150,9 @@ drv_pre_channel_switch(struct ieee80211_sub_if_data *sdata, if (!check_sdata_in_driver(sdata)) return -EIO; + if (!ieee80211_vif_link_active(&sdata->vif, ch_switch->link_id)) + return 0; + trace_drv_pre_channel_switch(local, sdata, ch_switch); if (local->ops->pre_channel_switch) ret = local->ops->pre_channel_switch(&local->hw, &sdata->vif, @@ -1171,6 +1174,9 @@ drv_post_channel_switch(struct ieee80211_link_data *link) if (!check_sdata_in_driver(sdata)) return -EIO; + if (!ieee80211_vif_link_active(&sdata->vif, link->link_id)) + return 0; + trace_drv_post_channel_switch(local, sdata); if (local->ops->post_channel_switch) ret = local->ops->post_channel_switch(&local->hw, &sdata->vif, @@ -1191,6 +1197,9 @@ drv_abort_channel_switch(struct ieee80211_link_data *link) if (!check_sdata_in_driver(sdata)) return; + if (!ieee80211_vif_link_active(&sdata->vif, link->link_id)) + return; + trace_drv_abort_channel_switch(local, sdata); if (local->ops->abort_channel_switch) @@ -1210,6 +1219,9 @@ drv_channel_switch_rx_beacon(struct ieee80211_sub_if_data *sdata, if (!check_sdata_in_driver(sdata)) return; + if (!ieee80211_vif_link_active(&sdata->vif, ch_switch->link_id)) + return; + trace_drv_channel_switch_rx_beacon(local, sdata, ch_switch); if (local->ops->channel_switch_rx_beacon) local->ops->channel_switch_rx_beacon(&local->hw, &sdata->vif, diff --git a/net/mac80211/ht.c b/net/mac80211/ht.c index d7e8cf8e48b7..1c2b7dd8976a 100644 --- a/net/mac80211/ht.c +++ b/net/mac80211/ht.c @@ -467,20 +467,7 @@ void ieee80211_send_delba(struct ieee80211_sub_if_data *sdata, return; skb_reserve(skb, local->hw.extra_tx_headroom); - mgmt = skb_put_zero(skb, 24); - memcpy(mgmt->da, da, ETH_ALEN); - memcpy(mgmt->sa, sdata->vif.addr, ETH_ALEN); - if (sdata->vif.type == NL80211_IFTYPE_AP || - sdata->vif.type == NL80211_IFTYPE_AP_VLAN || - sdata->vif.type == NL80211_IFTYPE_MESH_POINT) - memcpy(mgmt->bssid, sdata->vif.addr, ETH_ALEN); - else if (sdata->vif.type == NL80211_IFTYPE_STATION) - memcpy(mgmt->bssid, sdata->deflink.u.mgd.bssid, ETH_ALEN); - else if (sdata->vif.type == NL80211_IFTYPE_ADHOC) - memcpy(mgmt->bssid, sdata->u.ibss.bssid, ETH_ALEN); - - mgmt->frame_control = cpu_to_le16(IEEE80211_FTYPE_MGMT | - IEEE80211_STYPE_ACTION); + mgmt = ieee80211_mgmt_ba(skb, da, sdata); skb_put(skb, 1 + sizeof(mgmt->u.action.u.delba)); diff --git a/net/mac80211/ibss.c b/net/mac80211/ibss.c index 7ace5cdc6c26..3f74bbceeca5 100644 --- a/net/mac80211/ibss.c +++ b/net/mac80211/ibss.c @@ -9,7 +9,7 @@ * Copyright 2009, Johannes Berg <johannes@sipsolutions.net> * Copyright 2013-2014 Intel Mobile Communications GmbH * Copyright(c) 2016 Intel Deutschland GmbH - * Copyright(c) 2018-2023 Intel Corporation + * Copyright(c) 2018-2024 Intel Corporation */ #include <linux/delay.h> @@ -533,12 +533,12 @@ int ieee80211_ibss_finish_csa(struct ieee80211_sub_if_data *sdata, u64 *changed) IEEE80211_PRIVACY(ifibss->privacy)); /* XXX: should not really modify cfg80211 data */ if (cbss) { - cbss->channel = sdata->deflink.csa_chanreq.oper.chan; + cbss->channel = sdata->deflink.csa.chanreq.oper.chan; cfg80211_put_bss(sdata->local->hw.wiphy, cbss); } } - ifibss->chandef = sdata->deflink.csa_chanreq.oper; + ifibss->chandef = sdata->deflink.csa.chanreq.oper; /* generate the beacon */ return ieee80211_ibss_csa_beacon(sdata, NULL, changed); @@ -785,7 +785,8 @@ ieee80211_ibss_process_chanswitch(struct ieee80211_sub_if_data *sdata, err = ieee80211_parse_ch_switch_ie(sdata, elems, ifibss->chandef.chan->band, vht_cap_info, &conn, - ifibss->bssid, &csa_ie); + ifibss->bssid, false, + &csa_ie); /* can't switch to destination channel, fail */ if (err < 0) goto disconnect; @@ -1745,7 +1746,7 @@ int ieee80211_ibss_join(struct ieee80211_sub_if_data *sdata, IEEE80211_CHANCTX_SHARED : IEEE80211_CHANCTX_EXCLUSIVE; ret = ieee80211_check_combinations(sdata, ¶ms->chandef, chanmode, - radar_detect_width); + radar_detect_width, -1); if (ret < 0) return ret; diff --git a/net/mac80211/ieee80211_i.h b/net/mac80211/ieee80211_i.h index 3cedfdc9099b..4f0390918b60 100644 --- a/net/mac80211/ieee80211_i.h +++ b/net/mac80211/ieee80211_i.h @@ -26,6 +26,7 @@ #include <linux/idr.h> #include <linux/rhashtable.h> #include <linux/rbtree.h> +#include <kunit/visibility.h> #include <net/ieee80211_radiotap.h> #include <net/cfg80211.h> #include <net/mac80211.h> @@ -892,6 +893,8 @@ struct ieee80211_chanctx { struct ieee80211_chan_req req; struct ieee80211_chanctx_conf conf; + + bool radar_detected; }; struct mac80211_qos_map { @@ -974,10 +977,15 @@ struct ieee80211_link_data_managed { bool disable_wmm_tracking; bool operating_11g_mode; - bool csa_waiting_bcn; - bool csa_ignored_same_chan; - bool csa_blocked_tx; - struct wiphy_delayed_work chswitch_work; + struct { + struct wiphy_delayed_work switch_work; + struct cfg80211_chan_def ap_chandef; + struct ieee80211_parsed_tpe tpe; + unsigned long time; + bool waiting_bcn; + bool ignored_same_chan; + bool blocked_tx; + } csa; struct wiphy_work request_smps_work; /* used to reconfigure hardware SM PS */ @@ -1036,11 +1044,13 @@ struct ieee80211_link_data { struct ieee80211_key __rcu *default_mgmt_key; struct ieee80211_key __rcu *default_beacon_key; - struct wiphy_work csa_finalize_work; bool operating_11g_mode; - struct ieee80211_chan_req csa_chanreq; + struct { + struct wiphy_work finalize_work; + struct ieee80211_chan_req chanreq; + } csa; struct wiphy_work color_change_finalize_work; struct delayed_work color_collision_detect_work; @@ -1708,7 +1718,6 @@ struct ieee802_11_elems { const struct ieee80211_he_spr *he_spr; const struct ieee80211_mu_edca_param_set *mu_edca_param_set; const struct ieee80211_he_6ghz_capa *he_6ghz_capa; - const struct ieee80211_tx_pwr_env *tx_pwr_env[IEEE80211_TPE_MAX_IE_COUNT]; const u8 *uora_element; const u8 *mesh_id; const u8 *peering; @@ -1746,6 +1755,10 @@ struct ieee802_11_elems { const struct ieee80211_bandwidth_indication *bandwidth_indication; const struct ieee80211_ttlm_elem *ttlm[IEEE80211_TTLM_MAX_CNT]; + /* not the order in the psd values is per element, not per chandef */ + struct ieee80211_parsed_tpe tpe; + struct ieee80211_parsed_tpe csa_tpe; + /* length of them, respectively */ u8 ext_capab_len; u8 ssid_len; @@ -1764,8 +1777,6 @@ struct ieee802_11_elems { u8 perr_len; u8 country_elem_len; u8 bssid_index_len; - u8 tx_pwr_env_len[IEEE80211_TPE_MAX_IE_COUNT]; - u8 tx_pwr_env_num; u8 eht_cap_len; /* mult-link element can be de-fragmented and thus u8 is not sufficient */ @@ -1813,6 +1824,9 @@ ieee80211_have_rx_timestamp(struct ieee80211_rx_status *status) void ieee80211_vif_inc_num_mcast(struct ieee80211_sub_if_data *sdata); void ieee80211_vif_dec_num_mcast(struct ieee80211_sub_if_data *sdata); +void ieee80211_vif_block_queues_csa(struct ieee80211_sub_if_data *sdata); +void ieee80211_vif_unblock_queues_csa(struct ieee80211_sub_if_data *sdata); + /* This function returns the number of multicast stations connected to this * interface. It returns -1 if that number is not tracked, that is for netdevs * not in AP or AP_VLAN mode or when using 4addr. @@ -1970,6 +1984,7 @@ void ieee80211_offchannel_stop_vifs(struct ieee80211_local *local); void ieee80211_offchannel_return(struct ieee80211_local *local); void ieee80211_roc_setup(struct ieee80211_local *local); void ieee80211_start_next_roc(struct ieee80211_local *local); +void ieee80211_reconfig_roc(struct ieee80211_local *local); void ieee80211_roc_purge(struct ieee80211_local *local, struct ieee80211_sub_if_data *sdata); int ieee80211_remain_on_channel(struct wiphy *wiphy, struct wireless_dev *wdev, @@ -2058,8 +2073,6 @@ void __ieee80211_subif_start_xmit(struct sk_buff *skb, u32 info_flags, u32 ctrl_flags, u64 *cookie); -void ieee80211_purge_tx_queue(struct ieee80211_hw *hw, - struct sk_buff_head *skbs); struct sk_buff * ieee80211_build_data_template(struct ieee80211_sub_if_data *sdata, struct sk_buff *skb, u32 info_flags); @@ -2122,6 +2135,29 @@ void ieee80211_process_addba_request(struct ieee80211_local *local, struct ieee80211_mgmt *mgmt, size_t len); +static inline struct ieee80211_mgmt * +ieee80211_mgmt_ba(struct sk_buff *skb, const u8 *da, + struct ieee80211_sub_if_data *sdata) +{ + struct ieee80211_mgmt *mgmt = skb_put_zero(skb, 24); + + ether_addr_copy(mgmt->da, da); + ether_addr_copy(mgmt->sa, sdata->vif.addr); + + if (sdata->vif.type == NL80211_IFTYPE_AP || + sdata->vif.type == NL80211_IFTYPE_AP_VLAN || + sdata->vif.type == NL80211_IFTYPE_MESH_POINT) + ether_addr_copy(mgmt->bssid, sdata->vif.addr); + else if (sdata->vif.type == NL80211_IFTYPE_STATION) + ether_addr_copy(mgmt->bssid, sdata->vif.cfg.ap_addr); + else if (sdata->vif.type == NL80211_IFTYPE_ADHOC) + ether_addr_copy(mgmt->bssid, sdata->u.ibss.bssid); + + mgmt->frame_control = cpu_to_le16(IEEE80211_FTYPE_MGMT | + IEEE80211_STYPE_ACTION); + return mgmt; +} + int __ieee80211_stop_tx_ba_session(struct sta_info *sta, u16 tid, enum ieee80211_agg_stop_reason reason); void ieee80211_start_tx_ba_cb(struct sta_info *sta, int tid, @@ -2144,9 +2180,21 @@ ieee80211_vht_cap_ie_to_sta_vht_cap(struct ieee80211_sub_if_data *sdata, const struct ieee80211_vht_cap *vht_cap_ie2, struct link_sta_info *link_sta); enum ieee80211_sta_rx_bandwidth -ieee80211_sta_cap_rx_bw(struct link_sta_info *link_sta); +_ieee80211_sta_cap_rx_bw(struct link_sta_info *link_sta, + struct cfg80211_chan_def *chandef); +static inline enum ieee80211_sta_rx_bandwidth +ieee80211_sta_cap_rx_bw(struct link_sta_info *link_sta) +{ + return _ieee80211_sta_cap_rx_bw(link_sta, NULL); +} enum ieee80211_sta_rx_bandwidth -ieee80211_sta_cur_vht_bw(struct link_sta_info *link_sta); +_ieee80211_sta_cur_vht_bw(struct link_sta_info *link_sta, + struct cfg80211_chan_def *chandef); +static inline enum ieee80211_sta_rx_bandwidth +ieee80211_sta_cur_vht_bw(struct link_sta_info *link_sta) +{ + return _ieee80211_sta_cur_vht_bw(link_sta, NULL); +} void ieee80211_sta_init_nss(struct link_sta_info *link_sta); enum ieee80211_sta_rx_bandwidth ieee80211_chan_width_to_rx_bw(enum nl80211_chan_width width); @@ -2204,6 +2252,8 @@ void ieee80211_process_measurement_req(struct ieee80211_sub_if_data *sdata, * @conn: contains information about own capabilities and restrictions * to decide which channel switch announcements can be accepted * @bssid: the currently connected bssid (for reporting) + * @unprot_action: whether the frame was an unprotected frame or not, + * used for reporting * @csa_ie: parsed 802.11 csa elements on count, mode, chandef and mesh ttl. * All of them will be filled with if success only. * Return: 0 on success, <0 on error and >0 if there is nothing to parse. @@ -2213,12 +2263,12 @@ int ieee80211_parse_ch_switch_ie(struct ieee80211_sub_if_data *sdata, enum nl80211_band current_band, u32 vht_cap_info, struct ieee80211_conn_settings *conn, - u8 *bssid, + u8 *bssid, bool unprot_action, struct ieee80211_csa_ie *csa_ie); /* Suspend/resume and hw reconfiguration */ int ieee80211_reconfig(struct ieee80211_local *local); -void ieee80211_stop_device(struct ieee80211_local *local); +void ieee80211_stop_device(struct ieee80211_local *local, bool suspend); int __ieee80211_suspend(struct ieee80211_hw *hw, struct cfg80211_wowlan *wowlan); @@ -2245,6 +2295,7 @@ int ieee80211_frame_duration(enum nl80211_band band, size_t len, void ieee80211_regulatory_limit_wmm_params(struct ieee80211_sub_if_data *sdata, struct ieee80211_tx_queue_params *qparam, int ac); +void ieee80211_clear_tpe(struct ieee80211_parsed_tpe *tpe); void ieee80211_set_wmm_default(struct ieee80211_link_data *link, bool bss_notify, bool enable_qos); void ieee80211_xmit(struct ieee80211_sub_if_data *sdata, @@ -2595,11 +2646,13 @@ void ieee80211_recalc_smps_chanctx(struct ieee80211_local *local, struct ieee80211_chanctx *chanctx); void ieee80211_recalc_chanctx_min_def(struct ieee80211_local *local, struct ieee80211_chanctx *ctx, - struct ieee80211_link_data *rsvd_for); + struct ieee80211_link_data *rsvd_for, + bool check_reserved); bool ieee80211_is_radar_required(struct ieee80211_local *local); void ieee80211_dfs_cac_timer_work(struct wiphy *wiphy, struct wiphy_work *work); -void ieee80211_dfs_cac_cancel(struct ieee80211_local *local); +void ieee80211_dfs_cac_cancel(struct ieee80211_local *local, + struct ieee80211_chanctx *chanctx); void ieee80211_dfs_radar_detected_work(struct wiphy *wiphy, struct wiphy_work *work); int ieee80211_send_action_csa(struct ieee80211_sub_if_data *sdata, @@ -2610,8 +2663,9 @@ void ieee80211_recalc_dtim(struct ieee80211_local *local, int ieee80211_check_combinations(struct ieee80211_sub_if_data *sdata, const struct cfg80211_chan_def *chandef, enum ieee80211_chanctx_mode chanmode, - u8 radar_detect); -int ieee80211_max_num_channels(struct ieee80211_local *local); + u8 radar_detect, int radio_idx); +int ieee80211_max_num_channels(struct ieee80211_local *local, int radio_idx); +u32 ieee80211_get_radio_mask(struct wiphy *wiphy, struct net_device *dev); void ieee80211_recalc_chanctx_chantype(struct ieee80211_local *local, struct ieee80211_chanctx *ctx); @@ -2683,6 +2737,11 @@ void ieee80211_remove_wbrf(struct ieee80211_local *local, struct cfg80211_chan_d #define VISIBLE_IF_MAC80211_KUNIT ieee80211_rx_result ieee80211_drop_unencrypted_mgmt(struct ieee80211_rx_data *rx); +int ieee80211_calc_chandef_subchan_offset(const struct cfg80211_chan_def *ap, + u8 n_partial_subchans); +void ieee80211_rearrange_tpe_psd(struct ieee80211_parsed_tpe_psd *psd, + const struct cfg80211_chan_def *ap, + const struct cfg80211_chan_def *used); #else #define EXPORT_SYMBOL_IF_MAC80211_KUNIT(sym) #define VISIBLE_IF_MAC80211_KUNIT static diff --git a/net/mac80211/iface.c b/net/mac80211/iface.c index b935bb5d8ed1..6ef0990d3d29 100644 --- a/net/mac80211/iface.c +++ b/net/mac80211/iface.c @@ -397,7 +397,7 @@ static int ieee80211_check_concurrent_iface(struct ieee80211_sub_if_data *sdata, } } - return ieee80211_check_combinations(sdata, NULL, 0, 0); + return ieee80211_check_combinations(sdata, NULL, 0, 0, -1); } static int ieee80211_check_queues(struct ieee80211_sub_if_data *sdata, @@ -462,6 +462,7 @@ static void ieee80211_do_stop(struct ieee80211_sub_if_data *sdata, bool going_do { struct ieee80211_local *local = sdata->local; unsigned long flags; + struct sk_buff_head freeq; struct sk_buff *skb, *tmp; u32 hw_reconf_flags = 0; int i, flushed; @@ -543,26 +544,22 @@ static void ieee80211_do_stop(struct ieee80211_sub_if_data *sdata, bool going_do sdata->vif.bss_conf.csa_active = false; if (sdata->vif.type == NL80211_IFTYPE_STATION) - sdata->deflink.u.mgd.csa_waiting_bcn = false; - if (sdata->csa_blocked_queues) { - ieee80211_wake_vif_queues(local, sdata, - IEEE80211_QUEUE_STOP_REASON_CSA); - sdata->csa_blocked_queues = false; - } + sdata->deflink.u.mgd.csa.waiting_bcn = false; + ieee80211_vif_unblock_queues_csa(sdata); - wiphy_work_cancel(local->hw.wiphy, &sdata->deflink.csa_finalize_work); + wiphy_work_cancel(local->hw.wiphy, &sdata->deflink.csa.finalize_work); wiphy_work_cancel(local->hw.wiphy, &sdata->deflink.color_change_finalize_work); wiphy_delayed_work_cancel(local->hw.wiphy, &sdata->deflink.dfs_cac_timer_work); - if (sdata->wdev.cac_started) { + if (sdata->wdev.links[0].cac_started) { chandef = sdata->vif.bss_conf.chanreq.oper; WARN_ON(local->suspended); ieee80211_link_release_channel(&sdata->deflink); cfg80211_cac_event(sdata->dev, &chandef, NL80211_RADAR_CAC_ABORTED, - GFP_KERNEL); + GFP_KERNEL, 0); } if (sdata->vif.type == NL80211_IFTYPE_AP) { @@ -641,18 +638,32 @@ static void ieee80211_do_stop(struct ieee80211_sub_if_data *sdata, bool going_do skb_queue_purge(&sdata->status_queue); } + /* + * Since ieee80211_free_txskb() may issue __dev_queue_xmit() + * which should be called with interrupts enabled, reclamation + * is done in two phases: + */ + __skb_queue_head_init(&freeq); + + /* unlink from local queues... */ spin_lock_irqsave(&local->queue_stop_reason_lock, flags); for (i = 0; i < IEEE80211_MAX_QUEUES; i++) { skb_queue_walk_safe(&local->pending[i], skb, tmp) { struct ieee80211_tx_info *info = IEEE80211_SKB_CB(skb); if (info->control.vif == &sdata->vif) { __skb_unlink(skb, &local->pending[i]); - ieee80211_free_txskb(&local->hw, skb); + __skb_queue_tail(&freeq, skb); } } } spin_unlock_irqrestore(&local->queue_stop_reason_lock, flags); + /* ... and perform actual reclamation with interrupts enabled. */ + skb_queue_walk_safe(&freeq, skb, tmp) { + __skb_unlink(skb, &freeq); + ieee80211_free_txskb(&local->hw, skb); + } + if (sdata->vif.type == NL80211_IFTYPE_AP_VLAN) ieee80211_txq_remove_vlan(local, sdata); @@ -693,8 +704,12 @@ static void ieee80211_do_stop(struct ieee80211_sub_if_data *sdata, bool going_do fallthrough; default: - if (going_down) - drv_remove_interface(local, sdata); + if (!going_down) + break; + drv_remove_interface(local, sdata); + + /* Clear private driver data to prevent reuse */ + memset(sdata->vif.drv_priv, 0, local->hw.vif_data_size); } ieee80211_recalc_ps(local); @@ -703,7 +718,7 @@ static void ieee80211_do_stop(struct ieee80211_sub_if_data *sdata, bool going_do wiphy_delayed_work_flush(local->hw.wiphy, &local->scan_work); if (local->open_count == 0) { - ieee80211_stop_device(local); + ieee80211_stop_device(local, false); /* no reconfiguring after stop! */ return; @@ -816,12 +831,6 @@ static void ieee80211_uninit(struct net_device *dev) ieee80211_teardown_sdata(IEEE80211_DEV_TO_SUB_IF(dev)); } -static void -ieee80211_get_stats64(struct net_device *dev, struct rtnl_link_stats64 *stats) -{ - dev_fetch_sw_netstats(stats, dev->tstats); -} - static int ieee80211_netdev_setup_tc(struct net_device *dev, enum tc_setup_type type, void *type_data) { @@ -838,7 +847,6 @@ static const struct net_device_ops ieee80211_dataif_ops = { .ndo_start_xmit = ieee80211_subif_start_xmit, .ndo_set_rx_mode = ieee80211_set_multicast_list, .ndo_set_mac_address = ieee80211_change_mac, - .ndo_get_stats64 = ieee80211_get_stats64, .ndo_setup_tc = ieee80211_netdev_setup_tc, }; @@ -878,7 +886,6 @@ static const struct net_device_ops ieee80211_monitorif_ops = { .ndo_set_rx_mode = ieee80211_set_multicast_list, .ndo_set_mac_address = ieee80211_change_mac, .ndo_select_queue = ieee80211_monitor_select_queue, - .ndo_get_stats64 = ieee80211_get_stats64, }; static int ieee80211_netdev_fill_forward_path(struct net_device_path_ctx *ctx, @@ -946,7 +953,6 @@ static const struct net_device_ops ieee80211_dataif_8023_ops = { .ndo_start_xmit = ieee80211_subif_start_xmit_8023, .ndo_set_rx_mode = ieee80211_set_multicast_list, .ndo_set_mac_address = ieee80211_change_mac, - .ndo_get_stats64 = ieee80211_get_stats64, .ndo_fill_forward_path = ieee80211_netdev_fill_forward_path, .ndo_setup_tc = ieee80211_netdev_setup_tc, }; @@ -1446,7 +1452,7 @@ int ieee80211_do_open(struct wireless_dev *wdev, bool coming_up) drv_remove_interface(local, sdata); err_stop: if (!local->open_count) - drv_stop(local); + drv_stop(local, false); err_del_bss: sdata->bss = NULL; if (sdata->vif.type == NL80211_IFTYPE_AP_VLAN) @@ -1456,11 +1462,6 @@ int ieee80211_do_open(struct wireless_dev *wdev, bool coming_up) return res; } -static void ieee80211_if_free(struct net_device *dev) -{ - free_percpu(dev->tstats); -} - static void ieee80211_if_setup(struct net_device *dev) { ether_setup(dev); @@ -1468,7 +1469,6 @@ static void ieee80211_if_setup(struct net_device *dev) dev->priv_flags |= IFF_NO_QUEUE; dev->netdev_ops = &ieee80211_dataif_ops; dev->needs_free_netdev = true; - dev->priv_destructor = ieee80211_if_free; } static void ieee80211_iface_process_skb(struct ieee80211_local *local, @@ -2099,11 +2099,7 @@ int ieee80211_if_add(struct ieee80211_local *local, const char *name, dev_net_set(ndev, wiphy_net(local->hw.wiphy)); - ndev->tstats = netdev_alloc_pcpu_stats(struct pcpu_sw_netstats); - if (!ndev->tstats) { - free_netdev(ndev); - return -ENOMEM; - } + ndev->pcpu_stat_type = NETDEV_PCPU_STAT_TSTATS; ndev->needed_headroom = local->tx_headroom + 4*6 /* four MAC addresses */ @@ -2116,7 +2112,6 @@ int ieee80211_if_add(struct ieee80211_local *local, const char *name, ret = dev_alloc_name(ndev, ndev->name); if (ret < 0) { - ieee80211_if_free(ndev); free_netdev(ndev); return ret; } @@ -2361,3 +2356,26 @@ void ieee80211_vif_dec_num_mcast(struct ieee80211_sub_if_data *sdata) else if (sdata->vif.type == NL80211_IFTYPE_AP_VLAN) atomic_dec(&sdata->u.vlan.num_mcast_sta); } + +void ieee80211_vif_block_queues_csa(struct ieee80211_sub_if_data *sdata) +{ + struct ieee80211_local *local = sdata->local; + + if (ieee80211_hw_check(&local->hw, HANDLES_QUIET_CSA)) + return; + + ieee80211_stop_vif_queues(local, sdata, + IEEE80211_QUEUE_STOP_REASON_CSA); + sdata->csa_blocked_queues = true; +} + +void ieee80211_vif_unblock_queues_csa(struct ieee80211_sub_if_data *sdata) +{ + struct ieee80211_local *local = sdata->local; + + if (sdata->csa_blocked_queues) { + ieee80211_wake_vif_queues(local, sdata, + IEEE80211_QUEUE_STOP_REASON_CSA); + sdata->csa_blocked_queues = false; + } +} diff --git a/net/mac80211/link.c b/net/mac80211/link.c index af0321408a97..0bbac64d5fa0 100644 --- a/net/mac80211/link.c +++ b/net/mac80211/link.c @@ -37,7 +37,7 @@ void ieee80211_link_init(struct ieee80211_sub_if_data *sdata, link_conf->link_id = link_id; link_conf->vif = &sdata->vif; - wiphy_work_init(&link->csa_finalize_work, + wiphy_work_init(&link->csa.finalize_work, ieee80211_csa_finalize_work); wiphy_work_init(&link->color_change_finalize_work, ieee80211_color_change_finalize_work); @@ -74,7 +74,19 @@ void ieee80211_link_stop(struct ieee80211_link_data *link) cancel_delayed_work_sync(&link->color_collision_detect_work); wiphy_work_cancel(link->sdata->local->hw.wiphy, - &link->csa_finalize_work); + &link->color_change_finalize_work); + wiphy_work_cancel(link->sdata->local->hw.wiphy, + &link->csa.finalize_work); + + if (link->sdata->wdev.links[link->link_id].cac_started) { + wiphy_delayed_work_cancel(link->sdata->local->hw.wiphy, + &link->dfs_cac_timer_work); + cfg80211_cac_event(link->sdata->dev, + &link->conf->chanreq.oper, + NL80211_RADAR_CAC_ABORTED, + GFP_KERNEL, link->link_id); + } + ieee80211_link_release_channel(link); } @@ -359,6 +371,18 @@ static int _ieee80211_set_active_links(struct ieee80211_sub_if_data *sdata, ieee80211_teardown_tdls_peers(link); __ieee80211_link_release_channel(link, true); + + /* + * If CSA is (still) active while the link is deactivated, + * just schedule the channel switch work for the time we + * had previously calculated, and we'll take the process + * from there. + */ + if (link->conf->csa_active) + wiphy_delayed_work_queue(local->hw.wiphy, + &link->u.mgd.csa.switch_work, + link->u.mgd.csa.time - + jiffies); } list_for_each_entry(sta, &local->sta_list, list) { diff --git a/net/mac80211/main.c b/net/mac80211/main.c index 1132dea0e290..89084690350f 100644 --- a/net/mac80211/main.c +++ b/net/mac80211/main.c @@ -148,7 +148,7 @@ static u32 ieee80211_calc_hw_conf_chan(struct ieee80211_local *local, offchannel_flag ^= local->hw.conf.flags & IEEE80211_CONF_OFFCHANNEL; /* force it also for scanning, since drivers might config differently */ - if (offchannel_flag || local->scanning || + if (offchannel_flag || local->scanning || local->in_reconfig || !cfg80211_chandef_identical(&local->hw.conf.chandef, &chandef)) { local->hw.conf.chandef = chandef; changed |= IEEE80211_CONF_CHANGE_CHANNEL; @@ -337,6 +337,8 @@ void ieee80211_bss_info_change_notify(struct ieee80211_sub_if_data *sdata, might_sleep(); + WARN_ON_ONCE(ieee80211_vif_is_mld(&sdata->vif)); + if (!changed || sdata->vif.type == NL80211_IFTYPE_AP_VLAN) return; @@ -369,7 +371,6 @@ void ieee80211_bss_info_change_notify(struct ieee80211_sub_if_data *sdata, if (changed & ~BSS_CHANGED_VIF_CFG_FLAGS) { u64 ch = changed & ~BSS_CHANGED_VIF_CFG_FLAGS; - /* FIXME: should be for each link */ trace_drv_link_info_changed(local, sdata, &sdata->vif.bss_conf, changed); if (local->ops->link_info_changed) @@ -423,6 +424,7 @@ u64 ieee80211_reset_erp_info(struct ieee80211_sub_if_data *sdata) BSS_CHANGED_ERP_SLOT; } +/* context: requires softirqs disabled */ void ieee80211_handle_queued_frames(struct ieee80211_local *local) { struct sk_buff *skb; @@ -1049,9 +1051,9 @@ static int ieee80211_init_cipher_suites(struct ieee80211_local *local) return 0; /* Driver provides cipher suites, but we need to exclude WEP */ - suites = kmemdup(local->hw.wiphy->cipher_suites, - sizeof(u32) * local->hw.wiphy->n_cipher_suites, - GFP_KERNEL); + suites = kmemdup_array(local->hw.wiphy->cipher_suites, + local->hw.wiphy->n_cipher_suites, + sizeof(u32), GFP_KERNEL); if (!suites) return -ENOMEM; @@ -1089,6 +1091,27 @@ static int ieee80211_init_cipher_suites(struct ieee80211_local *local) return 0; } +static bool +ieee80211_ifcomb_check(const struct ieee80211_iface_combination *c, int n_comb) +{ + int i, j; + + for (i = 0; i < n_comb; i++, c++) { + /* DFS is not supported with multi-channel combinations yet */ + if (c->radar_detect_widths && + c->num_different_channels > 1) + return false; + + /* mac80211 doesn't support more than one IBSS interface */ + for (j = 0; j < c->n_limits; j++) + if ((c->limits[j].types & BIT(NL80211_IFTYPE_ADHOC)) && + c->limits[j].max > 1) + return false; + } + + return true; +} + int ieee80211_register_hw(struct ieee80211_hw *hw) { struct ieee80211_local *local = hw_to_local(hw); @@ -1159,9 +1182,6 @@ int ieee80211_register_hw(struct ieee80211_hw *hw) if (WARN_ON(!ieee80211_hw_check(hw, AP_LINK_PS))) return -EINVAL; - - if (WARN_ON(ieee80211_hw_check(hw, DEAUTH_NEED_MGD_TX_PREP))) - return -EINVAL; } #ifdef CONFIG_PM @@ -1178,17 +1198,20 @@ int ieee80211_register_hw(struct ieee80211_hw *hw) if (comb->num_different_channels > 1) return -EINVAL; } - } else { - /* DFS is not supported with multi-channel combinations yet */ - for (i = 0; i < local->hw.wiphy->n_iface_combinations; i++) { - const struct ieee80211_iface_combination *comb; + } - comb = &local->hw.wiphy->iface_combinations[i]; + if (hw->wiphy->n_radio) { + for (i = 0; i < hw->wiphy->n_radio; i++) { + const struct wiphy_radio *radio = &hw->wiphy->radio[i]; - if (comb->radar_detect_widths && - comb->num_different_channels > 1) + if (!ieee80211_ifcomb_check(radio->iface_combinations, + radio->n_iface_combinations)) return -EINVAL; } + } else { + if (!ieee80211_ifcomb_check(hw->wiphy->iface_combinations, + hw->wiphy->n_iface_combinations)) + return -EINVAL; } /* Only HW csum features are currently compatible with mac80211 */ @@ -1318,18 +1341,6 @@ int ieee80211_register_hw(struct ieee80211_hw *hw) hw->wiphy->interface_modes |= BIT(NL80211_IFTYPE_MONITOR); hw->wiphy->software_iftypes |= BIT(NL80211_IFTYPE_MONITOR); - /* mac80211 doesn't support more than one IBSS interface right now */ - for (i = 0; i < hw->wiphy->n_iface_combinations; i++) { - const struct ieee80211_iface_combination *c; - int j; - - c = &hw->wiphy->iface_combinations[i]; - - for (j = 0; j < c->n_limits; j++) - if ((c->limits[j].types & BIT(NL80211_IFTYPE_ADHOC)) && - c->limits[j].max > 1) - return -EINVAL; - } local->int_scan_req = kzalloc(sizeof(*local->int_scan_req) + sizeof(void *) * channels, GFP_KERNEL); diff --git a/net/mac80211/mesh.c b/net/mac80211/mesh.c index 6d4510221c98..f94e4be0be12 100644 --- a/net/mac80211/mesh.c +++ b/net/mac80211/mesh.c @@ -1312,7 +1312,7 @@ ieee80211_mesh_process_chnswitch(struct ieee80211_sub_if_data *sdata, memset(¶ms, 0, sizeof(params)); err = ieee80211_parse_ch_switch_ie(sdata, elems, sband->band, vht_cap_info, &conn, - sdata->vif.addr, + sdata->vif.addr, false, &csa_ie); if (err < 0) return false; diff --git a/net/mac80211/mesh_pathtbl.c b/net/mac80211/mesh_pathtbl.c index c0a5c75cddcb..30c0d89203af 100644 --- a/net/mac80211/mesh_pathtbl.c +++ b/net/mac80211/mesh_pathtbl.c @@ -580,7 +580,7 @@ void mesh_fast_tx_cache(struct ieee80211_sub_if_data *sdata, prev = rhashtable_lookup_get_insert_fast(&cache->rht, &entry->rhash, fast_tx_rht_params); - if (unlikely(IS_ERR(prev))) { + if (IS_ERR(prev)) { kfree(entry); goto unlock_cache; } diff --git a/net/mac80211/mlme.c b/net/mac80211/mlme.c index a5f2d3cfe60d..735e78adb0db 100644 --- a/net/mac80211/mlme.c +++ b/net/mac80211/mlme.c @@ -606,11 +606,218 @@ static bool ieee80211_chandef_usable(struct ieee80211_sub_if_data *sdata, return true; } +static int ieee80211_chandef_num_subchans(const struct cfg80211_chan_def *c) +{ + if (c->width == NL80211_CHAN_WIDTH_80P80) + return 4 + 4; + + return nl80211_chan_width_to_mhz(c->width) / 20; +} + +static int ieee80211_chandef_num_widths(const struct cfg80211_chan_def *c) +{ + switch (c->width) { + case NL80211_CHAN_WIDTH_20: + case NL80211_CHAN_WIDTH_20_NOHT: + return 1; + case NL80211_CHAN_WIDTH_40: + return 2; + case NL80211_CHAN_WIDTH_80P80: + case NL80211_CHAN_WIDTH_80: + return 3; + case NL80211_CHAN_WIDTH_160: + return 4; + case NL80211_CHAN_WIDTH_320: + return 5; + default: + WARN_ON(1); + return 0; + } +} + +VISIBLE_IF_MAC80211_KUNIT int +ieee80211_calc_chandef_subchan_offset(const struct cfg80211_chan_def *ap, + u8 n_partial_subchans) +{ + int n = ieee80211_chandef_num_subchans(ap); + struct cfg80211_chan_def tmp = *ap; + int offset = 0; + + /* + * Given a chandef (in this context, it's the AP's) and a number + * of subchannels that we want to look at ('n_partial_subchans'), + * calculate the offset in number of subchannels between the full + * and the subset with the desired width. + */ + + /* same number of subchannels means no offset, obviously */ + if (n == n_partial_subchans) + return 0; + + /* don't WARN - misconfigured APs could cause this if their N > width */ + if (n < n_partial_subchans) + return 0; + + while (ieee80211_chandef_num_subchans(&tmp) > n_partial_subchans) { + u32 prev = tmp.center_freq1; + + ieee80211_chandef_downgrade(&tmp, NULL); + + /* + * if center_freq moved up, half the original channels + * are gone now but were below, so increase offset + */ + if (prev < tmp.center_freq1) + offset += ieee80211_chandef_num_subchans(&tmp); + } + + /* + * 80+80 with secondary 80 below primary - four subchannels for it + * (we cannot downgrade *to* 80+80, so no need to consider 'tmp') + */ + if (ap->width == NL80211_CHAN_WIDTH_80P80 && + ap->center_freq2 < ap->center_freq1) + offset += 4; + + return offset; +} +EXPORT_SYMBOL_IF_MAC80211_KUNIT(ieee80211_calc_chandef_subchan_offset); + +VISIBLE_IF_MAC80211_KUNIT void +ieee80211_rearrange_tpe_psd(struct ieee80211_parsed_tpe_psd *psd, + const struct cfg80211_chan_def *ap, + const struct cfg80211_chan_def *used) +{ + u8 needed = ieee80211_chandef_num_subchans(used); + u8 have = ieee80211_chandef_num_subchans(ap); + u8 tmp[IEEE80211_TPE_PSD_ENTRIES_320MHZ]; + u8 offset; + + if (!psd->valid) + return; + + /* if N is zero, all defaults were used, no point in rearranging */ + if (!psd->n) + goto out; + + BUILD_BUG_ON(sizeof(tmp) != sizeof(psd->power)); + + /* + * This assumes that 'N' is consistent with the HE channel, as + * it should be (otherwise the AP is broken). + * + * In psd->power we have values in the order 0..N, 0..K, where + * N+K should cover the entire channel per 'ap', but even if it + * doesn't then we've pre-filled 'unlimited' as defaults. + * + * But this is all the wrong order, we want to have them in the + * order of the 'used' channel. + * + * So for example, we could have a 320 MHz EHT AP, which has the + * HE channel as 80 MHz (e.g. due to puncturing, which doesn't + * seem to be considered for the TPE), as follows: + * + * EHT 320: | | | | | | | | | | | | | | | | | + * HE 80: | | | | | + * used 160: | | | | | | | | | + * + * N entries: |--|--|--|--| + * K entries: |--|--|--|--|--|--|--|--| |--|--|--|--| + * power idx: 4 5 6 7 8 9 10 11 0 1 2 3 12 13 14 15 + * full chan: 0 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 + * used chan: 0 1 2 3 4 5 6 7 + * + * The idx in the power array ('power idx') is like this since it + * comes directly from the element's N and K entries in their + * element order, and those are this way for HE compatibility. + * + * Rearrange them as desired here, first by putting them into the + * 'full chan' order, and then selecting the necessary subset for + * the 'used chan'. + */ + + /* first reorder according to AP channel */ + offset = ieee80211_calc_chandef_subchan_offset(ap, psd->n); + for (int i = 0; i < have; i++) { + if (i < offset) + tmp[i] = psd->power[i + psd->n]; + else if (i < offset + psd->n) + tmp[i] = psd->power[i - offset]; + else + tmp[i] = psd->power[i]; + } + + /* + * and then select the subset for the used channel + * (set everything to defaults first in case a driver is confused) + */ + memset(psd->power, IEEE80211_TPE_PSD_NO_LIMIT, sizeof(psd->power)); + offset = ieee80211_calc_chandef_subchan_offset(ap, needed); + for (int i = 0; i < needed; i++) + psd->power[i] = tmp[offset + i]; + +out: + /* limit, but don't lie if there are defaults in the data */ + if (needed < psd->count) + psd->count = needed; +} +EXPORT_SYMBOL_IF_MAC80211_KUNIT(ieee80211_rearrange_tpe_psd); + +static void ieee80211_rearrange_tpe(struct ieee80211_parsed_tpe *tpe, + const struct cfg80211_chan_def *ap, + const struct cfg80211_chan_def *used) +{ + /* ignore this completely for narrow/invalid channels */ + if (!ieee80211_chandef_num_subchans(ap) || + !ieee80211_chandef_num_subchans(used)) { + ieee80211_clear_tpe(tpe); + return; + } + + for (int i = 0; i < 2; i++) { + int needed_pwr_count; + + ieee80211_rearrange_tpe_psd(&tpe->psd_local[i], ap, used); + ieee80211_rearrange_tpe_psd(&tpe->psd_reg_client[i], ap, used); + + /* limit this to the widths we actually need */ + needed_pwr_count = ieee80211_chandef_num_widths(used); + if (needed_pwr_count < tpe->max_local[i].count) + tpe->max_local[i].count = needed_pwr_count; + if (needed_pwr_count < tpe->max_reg_client[i].count) + tpe->max_reg_client[i].count = needed_pwr_count; + } +} + +/* + * The AP part of the channel request is used to distinguish settings + * to the device used for wider bandwidth OFDMA. This is used in the + * channel context code to assign two channel contexts even if they're + * both for the same channel, if the AP bandwidths are incompatible. + * If not EHT (or driver override) then ap.chan == NULL indicates that + * there's no wider BW OFDMA used. + */ +static void ieee80211_set_chanreq_ap(struct ieee80211_sub_if_data *sdata, + struct ieee80211_chan_req *chanreq, + struct ieee80211_conn_settings *conn, + struct cfg80211_chan_def *ap_chandef) +{ + chanreq->ap.chan = NULL; + + if (conn->mode < IEEE80211_CONN_MODE_EHT) + return; + if (sdata->vif.driver_flags & IEEE80211_VIF_IGNORE_OFDMA_WIDER_BW) + return; + + chanreq->ap = *ap_chandef; +} + static struct ieee802_11_elems * ieee80211_determine_chan_mode(struct ieee80211_sub_if_data *sdata, struct ieee80211_conn_settings *conn, struct cfg80211_bss *cbss, int link_id, - struct ieee80211_chan_req *chanreq) + struct ieee80211_chan_req *chanreq, + struct cfg80211_chan_def *ap_chandef) { const struct cfg80211_bss_ies *ies = rcu_dereference(cbss->ies); struct ieee80211_bss *bss = (void *)cbss->priv; @@ -623,7 +830,6 @@ ieee80211_determine_chan_mode(struct ieee80211_sub_if_data *sdata, }; struct ieee802_11_elems *elems; struct ieee80211_supported_band *sband; - struct cfg80211_chan_def ap_chandef; enum ieee80211_conn_mode ap_mode; int ret; @@ -634,7 +840,7 @@ again: return ERR_PTR(-ENOMEM); ap_mode = ieee80211_determine_ap_chan(sdata, channel, bss->vht_cap_info, - elems, false, conn, &ap_chandef); + elems, false, conn, ap_chandef); /* this should be impossible since parsing depends on our mode */ if (WARN_ON(ap_mode > conn->mode)) { @@ -701,14 +907,9 @@ again: break; } - chanreq->oper = ap_chandef; + chanreq->oper = *ap_chandef; - /* wider-bandwidth OFDMA is only done in EHT */ - if (conn->mode >= IEEE80211_CONN_MODE_EHT && - !(sdata->vif.driver_flags & IEEE80211_VIF_IGNORE_OFDMA_WIDER_BW)) - chanreq->ap = ap_chandef; - else - chanreq->ap.chan = NULL; + ieee80211_set_chanreq_ap(sdata, chanreq, conn, ap_chandef); while (!ieee80211_chandef_usable(sdata, &chanreq->oper, IEEE80211_CHAN_DISABLED)) { @@ -738,7 +939,7 @@ again: IEEE80211_CONN_BW_LIMIT_160); } - if (chanreq->oper.width != ap_chandef.width || ap_mode != conn->mode) + if (chanreq->oper.width != ap_chandef->width || ap_mode != conn->mode) sdata_info(sdata, "regulatory prevented using AP config, downgraded\n"); @@ -790,6 +991,7 @@ static int ieee80211_config_bw(struct ieee80211_link_data *link, struct ieee80211_channel *channel = link->conf->chanreq.oper.chan; struct ieee80211_sub_if_data *sdata = link->sdata; struct ieee80211_chan_req chanreq = {}; + struct cfg80211_chan_def ap_chandef; enum ieee80211_conn_mode ap_mode; u32 vht_cap_info = 0; u16 ht_opmode; @@ -805,7 +1007,7 @@ static int ieee80211_config_bw(struct ieee80211_link_data *link, ap_mode = ieee80211_determine_ap_chan(sdata, channel, vht_cap_info, elems, true, &link->u.mgd.conn, - &chanreq.ap); + &ap_chandef); if (ap_mode != link->u.mgd.conn.mode) { link_info(link, @@ -815,10 +1017,9 @@ static int ieee80211_config_bw(struct ieee80211_link_data *link, return -EINVAL; } - chanreq.oper = chanreq.ap; - if (link->u.mgd.conn.mode < IEEE80211_CONN_MODE_EHT || - sdata->vif.driver_flags & IEEE80211_VIF_IGNORE_OFDMA_WIDER_BW) - chanreq.ap.chan = NULL; + chanreq.oper = ap_chandef; + ieee80211_set_chanreq_ap(sdata, &chanreq, &link->u.mgd.conn, + &ap_chandef); /* * if HT operation mode changed store the new one - @@ -843,6 +1044,16 @@ static int ieee80211_config_bw(struct ieee80211_link_data *link, ieee80211_min_bw_limit_from_chandef(&chanreq.oper)) ieee80211_chandef_downgrade(&chanreq.oper, NULL); + if (ap_chandef.chan->band == NL80211_BAND_6GHZ && + link->u.mgd.conn.mode >= IEEE80211_CONN_MODE_HE) { + ieee80211_rearrange_tpe(&elems->tpe, &ap_chandef, + &chanreq.oper); + if (memcmp(&link->conf->tpe, &elems->tpe, sizeof(elems->tpe))) { + link->conf->tpe = elems->tpe; + *changed |= BSS_CHANGED_TPE; + } + } + if (ieee80211_chanreq_identical(&chanreq, &link->conf->chanreq)) return 0; @@ -1020,7 +1231,7 @@ static bool ieee80211_add_vht_ie(struct ieee80211_sub_if_data *sdata, bool disable_mu_mimo = false; struct ieee80211_sub_if_data *other; - list_for_each_entry_rcu(other, &local->interfaces, list) { + list_for_each_entry(other, &local->interfaces, list) { if (other->vif.bss_conf.mu_mimo_owner) { disable_mu_mimo = true; break; @@ -1862,12 +2073,12 @@ void ieee80211_send_4addr_nullfunc(struct ieee80211_local *local, } /* spectrum management related things */ -static void ieee80211_chswitch_work(struct wiphy *wiphy, - struct wiphy_work *work) +static void ieee80211_csa_switch_work(struct wiphy *wiphy, + struct wiphy_work *work) { struct ieee80211_link_data *link = container_of(work, struct ieee80211_link_data, - u.mgd.chswitch_work.work); + u.mgd.csa.switch_work.work); struct ieee80211_sub_if_data *sdata = link->sdata; struct ieee80211_local *local = sdata->local; struct ieee80211_if_managed *ifmgd = &sdata->u.mgd; @@ -1885,6 +2096,18 @@ static void ieee80211_chswitch_work(struct wiphy *wiphy, return; /* + * If the link isn't active (now), we cannot wait for beacons, won't + * have a reserved chanctx, etc. Just switch over the chandef and + * update cfg80211 directly. + */ + if (!ieee80211_vif_link_active(&sdata->vif, link->link_id)) { + link->conf->chanreq = link->csa.chanreq; + cfg80211_ch_switch_notify(sdata->dev, &link->csa.chanreq.oper, + link->link_id); + return; + } + + /* * using reservation isn't immediate as it may be deferred until later * with multi-vif. once reservation is complete it will re-schedule the * work with no reserved_chanctx so verify chandef to check if it @@ -1902,9 +2125,9 @@ static void ieee80211_chswitch_work(struct wiphy *wiphy, ret = ieee80211_link_use_reserved_context(link); if (ret) { - sdata_info(sdata, - "failed to use reserved channel context, disconnecting (err=%d)\n", - ret); + link_info(link, + "failed to use reserved channel context, disconnecting (err=%d)\n", + ret); wiphy_work_queue(sdata->local->hw.wiphy, &ifmgd->csa_connection_drop_work); } @@ -1912,15 +2135,29 @@ static void ieee80211_chswitch_work(struct wiphy *wiphy, } if (!ieee80211_chanreq_identical(&link->conf->chanreq, - &link->csa_chanreq)) { - sdata_info(sdata, - "failed to finalize channel switch, disconnecting\n"); + &link->csa.chanreq)) { + link_info(link, + "failed to finalize channel switch, disconnecting\n"); wiphy_work_queue(sdata->local->hw.wiphy, &ifmgd->csa_connection_drop_work); return; } - link->u.mgd.csa_waiting_bcn = true; + link->u.mgd.csa.waiting_bcn = true; + + /* apply new TPE restrictions immediately on the new channel */ + if (link->u.mgd.csa.ap_chandef.chan->band == NL80211_BAND_6GHZ && + link->u.mgd.conn.mode >= IEEE80211_CONN_MODE_HE) { + ieee80211_rearrange_tpe(&link->u.mgd.csa.tpe, + &link->u.mgd.csa.ap_chandef, + &link->conf->chanreq.oper); + if (memcmp(&link->conf->tpe, &link->u.mgd.csa.tpe, + sizeof(link->u.mgd.csa.tpe))) { + link->conf->tpe = link->u.mgd.csa.tpe; + ieee80211_link_info_change_notify(sdata, link, + BSS_CHANGED_TPE); + } + } ieee80211_sta_reset_beacon_monitor(sdata); ieee80211_sta_reset_conn_monitor(sdata); @@ -1929,7 +2166,6 @@ static void ieee80211_chswitch_work(struct wiphy *wiphy, static void ieee80211_chswitch_post_beacon(struct ieee80211_link_data *link) { struct ieee80211_sub_if_data *sdata = link->sdata; - struct ieee80211_local *local = sdata->local; struct ieee80211_if_managed *ifmgd = &sdata->u.mgd; int ret; @@ -1937,26 +2173,22 @@ static void ieee80211_chswitch_post_beacon(struct ieee80211_link_data *link) WARN_ON(!link->conf->csa_active); - if (sdata->csa_blocked_queues) { - ieee80211_wake_vif_queues(local, sdata, - IEEE80211_QUEUE_STOP_REASON_CSA); - sdata->csa_blocked_queues = false; - } + ieee80211_vif_unblock_queues_csa(sdata); link->conf->csa_active = false; - link->u.mgd.csa_blocked_tx = false; - link->u.mgd.csa_waiting_bcn = false; + link->u.mgd.csa.blocked_tx = false; + link->u.mgd.csa.waiting_bcn = false; ret = drv_post_channel_switch(link); if (ret) { - sdata_info(sdata, - "driver post channel switch failed, disconnecting\n"); + link_info(link, + "driver post channel switch failed, disconnecting\n"); wiphy_work_queue(sdata->local->hw.wiphy, &ifmgd->csa_connection_drop_work); return; } - cfg80211_ch_switch_notify(sdata->dev, &link->reserved.oper, + cfg80211_ch_switch_notify(sdata->dev, &link->conf->chanreq.oper, link->link_id); } @@ -1971,7 +2203,8 @@ void ieee80211_chswitch_done(struct ieee80211_vif *vif, bool success, if (!success) { sdata_info(sdata, - "driver channel switch failed, disconnecting\n"); + "driver channel switch failed (link %d), disconnecting\n", + link_id); wiphy_work_queue(sdata->local->hw.wiphy, &sdata->u.mgd.csa_connection_drop_work); } else { @@ -1984,7 +2217,7 @@ void ieee80211_chswitch_done(struct ieee80211_vif *vif, bool success, } wiphy_delayed_work_queue(sdata->local->hw.wiphy, - &link->u.mgd.chswitch_work, 0); + &link->u.mgd.csa.switch_work, 0); } rcu_read_unlock(); @@ -2004,126 +2237,308 @@ ieee80211_sta_abort_chanswitch(struct ieee80211_link_data *link) ieee80211_link_unreserve_chanctx(link); - if (sdata->csa_blocked_queues) { - ieee80211_wake_vif_queues(local, sdata, - IEEE80211_QUEUE_STOP_REASON_CSA); - sdata->csa_blocked_queues = false; - } + ieee80211_vif_unblock_queues_csa(sdata); link->conf->csa_active = false; - link->u.mgd.csa_blocked_tx = false; + link->u.mgd.csa.blocked_tx = false; drv_abort_channel_switch(link); } +struct sta_csa_rnr_iter_data { + struct ieee80211_link_data *link; + struct ieee80211_channel *chan; + u8 mld_id; +}; + +static enum cfg80211_rnr_iter_ret +ieee80211_sta_csa_rnr_iter(void *_data, u8 type, + const struct ieee80211_neighbor_ap_info *info, + const u8 *tbtt_info, u8 tbtt_info_len) +{ + struct sta_csa_rnr_iter_data *data = _data; + struct ieee80211_link_data *link = data->link; + struct ieee80211_sub_if_data *sdata = link->sdata; + struct ieee80211_if_managed *ifmgd = &sdata->u.mgd; + const struct ieee80211_tbtt_info_ge_11 *ti; + enum nl80211_band band; + unsigned int center_freq; + int link_id; + + if (type != IEEE80211_TBTT_INFO_TYPE_TBTT) + return RNR_ITER_CONTINUE; + + if (tbtt_info_len < sizeof(*ti)) + return RNR_ITER_CONTINUE; + + ti = (const void *)tbtt_info; + + if (ti->mld_params.mld_id != data->mld_id) + return RNR_ITER_CONTINUE; + + link_id = le16_get_bits(ti->mld_params.params, + IEEE80211_RNR_MLD_PARAMS_LINK_ID); + if (link_id != data->link->link_id) + return RNR_ITER_CONTINUE; + + /* we found the entry for our link! */ + + /* this AP is confused, it had this right before ... just disconnect */ + if (!ieee80211_operating_class_to_band(info->op_class, &band)) { + link_info(link, + "AP now has invalid operating class in RNR, disconnect\n"); + wiphy_work_queue(sdata->local->hw.wiphy, + &ifmgd->csa_connection_drop_work); + return RNR_ITER_BREAK; + } + + center_freq = ieee80211_channel_to_frequency(info->channel, band); + data->chan = ieee80211_get_channel(sdata->local->hw.wiphy, center_freq); + + return RNR_ITER_BREAK; +} + +static void +ieee80211_sta_other_link_csa_disappeared(struct ieee80211_link_data *link, + struct ieee802_11_elems *elems) +{ + struct ieee80211_sub_if_data *sdata = link->sdata; + struct ieee80211_if_managed *ifmgd = &sdata->u.mgd; + struct sta_csa_rnr_iter_data data = { + .link = link, + }; + + /* + * If we get here, we see a beacon from another link without + * CSA still being reported for it, so now we have to check + * if the CSA was aborted or completed. This may not even be + * perfectly possible if the CSA was only done for changing + * the puncturing, but in that case if the link in inactive + * we don't really care, and if it's an active link (or when + * it's activated later) we'll get a beacon and adjust. + */ + + if (WARN_ON(!elems->ml_basic)) + return; + + data.mld_id = ieee80211_mle_get_mld_id((const void *)elems->ml_basic); + + /* + * So in order to do this, iterate the RNR element(s) and see + * what channel is reported now. + */ + cfg80211_iter_rnr(elems->ie_start, elems->total_len, + ieee80211_sta_csa_rnr_iter, &data); + + if (!data.chan) { + link_info(link, + "couldn't find (valid) channel in RNR for CSA, disconnect\n"); + wiphy_work_queue(sdata->local->hw.wiphy, + &ifmgd->csa_connection_drop_work); + return; + } + + /* + * If it doesn't match the CSA, then assume it aborted. This + * may erroneously detect that it was _not_ aborted when it + * was in fact aborted, but only changed the bandwidth or the + * puncturing configuration, but we don't have enough data to + * detect that. + */ + if (data.chan != link->csa.chanreq.oper.chan) + ieee80211_sta_abort_chanswitch(link); +} + +enum ieee80211_csa_source { + IEEE80211_CSA_SOURCE_BEACON, + IEEE80211_CSA_SOURCE_OTHER_LINK, + IEEE80211_CSA_SOURCE_PROT_ACTION, + IEEE80211_CSA_SOURCE_UNPROT_ACTION, +}; + static void ieee80211_sta_process_chanswitch(struct ieee80211_link_data *link, u64 timestamp, u32 device_timestamp, - struct ieee802_11_elems *elems, - bool beacon) + struct ieee802_11_elems *full_elems, + struct ieee802_11_elems *csa_elems, + enum ieee80211_csa_source source) { struct ieee80211_sub_if_data *sdata = link->sdata; struct ieee80211_local *local = sdata->local; struct ieee80211_if_managed *ifmgd = &sdata->u.mgd; - struct cfg80211_bss *cbss = link->conf->bss; + struct ieee80211_chanctx *chanctx = NULL; struct ieee80211_chanctx_conf *conf; - struct ieee80211_chanctx *chanctx; - enum nl80211_band current_band; - struct ieee80211_csa_ie csa_ie; + struct ieee80211_csa_ie csa_ie = {}; struct ieee80211_channel_switch ch_switch = { .link_id = link->link_id, + .timestamp = timestamp, + .device_timestamp = device_timestamp, }; - struct ieee80211_bss *bss; - unsigned long timeout; + unsigned long now; int res; lockdep_assert_wiphy(local->hw.wiphy); - if (!cbss) - return; + if (csa_elems) { + struct cfg80211_bss *cbss = link->conf->bss; + enum nl80211_band current_band; + struct ieee80211_bss *bss; - current_band = cbss->channel->band; - bss = (void *)cbss->priv; - res = ieee80211_parse_ch_switch_ie(sdata, elems, current_band, - bss->vht_cap_info, - &link->u.mgd.conn, - link->u.mgd.bssid, &csa_ie); + if (WARN_ON(!cbss)) + return; - if (!res) { - ch_switch.timestamp = timestamp; - ch_switch.device_timestamp = device_timestamp; - ch_switch.block_tx = csa_ie.mode; - ch_switch.chandef = csa_ie.chanreq.oper; - ch_switch.count = csa_ie.count; - ch_switch.delay = csa_ie.max_switch_time; + current_band = cbss->channel->band; + bss = (void *)cbss->priv; + + res = ieee80211_parse_ch_switch_ie(sdata, csa_elems, + current_band, + bss->vht_cap_info, + &link->u.mgd.conn, + link->u.mgd.bssid, + source == IEEE80211_CSA_SOURCE_UNPROT_ACTION, + &csa_ie); + if (res == 0) { + ch_switch.block_tx = csa_ie.mode; + ch_switch.chandef = csa_ie.chanreq.oper; + ch_switch.count = csa_ie.count; + ch_switch.delay = csa_ie.max_switch_time; + } + + link->u.mgd.csa.tpe = csa_elems->csa_tpe; + } else { + /* + * If there was no per-STA profile for this link, we + * get called with csa_elems == NULL. This of course means + * there are no CSA elements, so set res=1 indicating + * no more CSA. + */ + res = 1; } - if (res < 0) + if (res < 0) { + /* ignore this case, not a protected frame */ + if (source == IEEE80211_CSA_SOURCE_UNPROT_ACTION) + return; goto drop_connection; + } if (link->conf->csa_active) { - /* already processing - disregard action frames */ - if (!beacon) + switch (source) { + case IEEE80211_CSA_SOURCE_PROT_ACTION: + case IEEE80211_CSA_SOURCE_UNPROT_ACTION: + /* already processing - disregard action frames */ return; + case IEEE80211_CSA_SOURCE_BEACON: + if (link->u.mgd.csa.waiting_bcn) { + ieee80211_chswitch_post_beacon(link); + /* + * If the CSA is still present after the switch + * we need to consider it as a new CSA (possibly + * to self). This happens by not returning here + * so we'll get to the check below. + */ + } else if (res) { + ieee80211_sta_abort_chanswitch(link); + return; + } else { + drv_channel_switch_rx_beacon(sdata, &ch_switch); + return; + } + break; + case IEEE80211_CSA_SOURCE_OTHER_LINK: + /* active link: we want to see the beacon to continue */ + if (ieee80211_vif_link_active(&sdata->vif, + link->link_id)) + return; - if (link->u.mgd.csa_waiting_bcn) { - ieee80211_chswitch_post_beacon(link); - /* - * If the CSA IE is still present in the beacon after - * the switch, we need to consider it as a new CSA - * (possibly to self) - this happens by not returning - * here so we'll get to the check below. - */ - } else if (res) { - ieee80211_sta_abort_chanswitch(link); - return; - } else { - drv_channel_switch_rx_beacon(sdata, &ch_switch); + /* switch work ran, so just complete the process */ + if (link->u.mgd.csa.waiting_bcn) { + ieee80211_chswitch_post_beacon(link); + /* + * If the CSA is still present after the switch + * we need to consider it as a new CSA (possibly + * to self). This happens by not returning here + * so we'll get to the check below. + */ + break; + } + + /* link still has CSA but we already know, do nothing */ + if (!res) + return; + + /* check in the RNR if the CSA aborted */ + ieee80211_sta_other_link_csa_disappeared(link, + full_elems); return; } } - /* nothing to do at all - no active CSA nor a new one */ - if (res) + /* no active CSA nor a new one */ + if (res) { + /* + * However, we may have stopped queues when receiving a public + * action frame that couldn't be protected, if it had the quiet + * bit set. This is a trade-off, we want to be quiet as soon as + * possible, but also don't trust the public action frame much, + * as it can't be protected. + */ + if (unlikely(link->u.mgd.csa.blocked_tx)) { + link->u.mgd.csa.blocked_tx = false; + ieee80211_vif_unblock_queues_csa(sdata); + } return; + } + + /* + * We don't really trust public action frames, but block queues (go to + * quiet mode) for them anyway, we should get a beacon soon to either + * know what the CSA really is, or figure out the public action frame + * was actually an attack. + */ + if (source == IEEE80211_CSA_SOURCE_UNPROT_ACTION) { + if (csa_ie.mode) { + link->u.mgd.csa.blocked_tx = true; + ieee80211_vif_block_queues_csa(sdata); + } + return; + } if (link->conf->chanreq.oper.chan->band != csa_ie.chanreq.oper.chan->band) { - sdata_info(sdata, - "AP %pM switches to different band (%d MHz, width:%d, CF1/2: %d/%d MHz), disconnecting\n", - link->u.mgd.bssid, - csa_ie.chanreq.oper.chan->center_freq, - csa_ie.chanreq.oper.width, - csa_ie.chanreq.oper.center_freq1, - csa_ie.chanreq.oper.center_freq2); + link_info(link, + "AP %pM switches to different band (%d MHz, width:%d, CF1/2: %d/%d MHz), disconnecting\n", + link->u.mgd.bssid, + csa_ie.chanreq.oper.chan->center_freq, + csa_ie.chanreq.oper.width, + csa_ie.chanreq.oper.center_freq1, + csa_ie.chanreq.oper.center_freq2); goto drop_connection; } if (!cfg80211_chandef_usable(local->hw.wiphy, &csa_ie.chanreq.oper, IEEE80211_CHAN_DISABLED)) { - sdata_info(sdata, - "AP %pM switches to unsupported channel " - "(%d.%03d MHz, width:%d, CF1/2: %d.%03d/%d MHz), " - "disconnecting\n", - link->u.mgd.bssid, - csa_ie.chanreq.oper.chan->center_freq, - csa_ie.chanreq.oper.chan->freq_offset, - csa_ie.chanreq.oper.width, - csa_ie.chanreq.oper.center_freq1, - csa_ie.chanreq.oper.freq1_offset, - csa_ie.chanreq.oper.center_freq2); + link_info(link, + "AP %pM switches to unsupported channel (%d.%03d MHz, width:%d, CF1/2: %d.%03d/%d MHz), disconnecting\n", + link->u.mgd.bssid, + csa_ie.chanreq.oper.chan->center_freq, + csa_ie.chanreq.oper.chan->freq_offset, + csa_ie.chanreq.oper.width, + csa_ie.chanreq.oper.center_freq1, + csa_ie.chanreq.oper.freq1_offset, + csa_ie.chanreq.oper.center_freq2); goto drop_connection; } if (cfg80211_chandef_identical(&csa_ie.chanreq.oper, &link->conf->chanreq.oper) && - (!csa_ie.mode || !beacon)) { - if (link->u.mgd.csa_ignored_same_chan) + (!csa_ie.mode || source != IEEE80211_CSA_SOURCE_BEACON)) { + if (link->u.mgd.csa.ignored_same_chan) return; - sdata_info(sdata, - "AP %pM tries to chanswitch to same channel, ignore\n", - link->u.mgd.bssid); - link->u.mgd.csa_ignored_same_chan = true; + link_info(link, + "AP %pM tries to chanswitch to same channel, ignore\n", + link->u.mgd.bssid); + link->u.mgd.csa.ignored_same_chan = true; return; } @@ -2138,64 +2553,78 @@ ieee80211_sta_process_chanswitch(struct ieee80211_link_data *link, conf = rcu_dereference_protected(link->conf->chanctx_conf, lockdep_is_held(&local->hw.wiphy->mtx)); - if (!conf) { - sdata_info(sdata, - "no channel context assigned to vif?, disconnecting\n"); + if (ieee80211_vif_link_active(&sdata->vif, link->link_id) && !conf) { + link_info(link, + "no channel context assigned to vif?, disconnecting\n"); goto drop_connection; } - chanctx = container_of(conf, struct ieee80211_chanctx, conf); + if (conf) + chanctx = container_of(conf, struct ieee80211_chanctx, conf); if (!ieee80211_hw_check(&local->hw, CHANCTX_STA_CSA)) { - sdata_info(sdata, - "driver doesn't support chan-switch with channel contexts\n"); + link_info(link, + "driver doesn't support chan-switch with channel contexts\n"); goto drop_connection; } if (drv_pre_channel_switch(sdata, &ch_switch)) { - sdata_info(sdata, - "preparing for channel switch failed, disconnecting\n"); + link_info(link, + "preparing for channel switch failed, disconnecting\n"); goto drop_connection; } - res = ieee80211_link_reserve_chanctx(link, &csa_ie.chanreq, - chanctx->mode, false); - if (res) { - sdata_info(sdata, - "failed to reserve channel context for channel switch, disconnecting (err=%d)\n", - res); - goto drop_connection; + link->u.mgd.csa.ap_chandef = csa_ie.chanreq.ap; + + link->csa.chanreq.oper = csa_ie.chanreq.oper; + ieee80211_set_chanreq_ap(sdata, &link->csa.chanreq, &link->u.mgd.conn, + &csa_ie.chanreq.ap); + + if (chanctx) { + res = ieee80211_link_reserve_chanctx(link, &link->csa.chanreq, + chanctx->mode, false); + if (res) { + link_info(link, + "failed to reserve channel context for channel switch, disconnecting (err=%d)\n", + res); + goto drop_connection; + } } link->conf->csa_active = true; - link->csa_chanreq = csa_ie.chanreq; - link->u.mgd.csa_ignored_same_chan = false; + link->u.mgd.csa.ignored_same_chan = false; link->u.mgd.beacon_crc_valid = false; - link->u.mgd.csa_blocked_tx = csa_ie.mode; + link->u.mgd.csa.blocked_tx = csa_ie.mode; - if (csa_ie.mode && - !ieee80211_hw_check(&local->hw, HANDLES_QUIET_CSA)) { - ieee80211_stop_vif_queues(local, sdata, - IEEE80211_QUEUE_STOP_REASON_CSA); - sdata->csa_blocked_queues = true; - } + if (csa_ie.mode) + ieee80211_vif_block_queues_csa(sdata); cfg80211_ch_switch_started_notify(sdata->dev, &csa_ie.chanreq.oper, link->link_id, csa_ie.count, csa_ie.mode); - if (local->ops->channel_switch) { - /* use driver's channel switch callback */ + /* we may have to handle timeout for deactivated link in software */ + now = jiffies; + link->u.mgd.csa.time = now + + TU_TO_JIFFIES((max_t(int, csa_ie.count, 1) - 1) * + link->conf->beacon_int); + + if (ieee80211_vif_link_active(&sdata->vif, link->link_id) && + local->ops->channel_switch) { + /* + * Use driver's channel switch callback, the driver will + * later call ieee80211_chswitch_done(). It may deactivate + * the link as well, we handle that elsewhere and queue + * the csa.switch_work for the calculated time then. + */ drv_channel_switch(local, sdata, &ch_switch); return; } /* channel switch handled in software */ - timeout = TU_TO_JIFFIES((max_t(int, csa_ie.count, 1) - 1) * - cbss->beacon_interval); wiphy_delayed_work_queue(local->hw.wiphy, - &link->u.mgd.chswitch_work, - timeout); + &link->u.mgd.csa.switch_work, + link->u.mgd.csa.time - now); return; drop_connection: /* @@ -2206,7 +2635,7 @@ ieee80211_sta_process_chanswitch(struct ieee80211_link_data *link, * reset when the disconnection worker runs. */ link->conf->csa_active = true; - link->u.mgd.csa_blocked_tx = csa_ie.mode; + link->u.mgd.csa.blocked_tx = csa_ie.mode; sdata->csa_blocked_queues = csa_ie.mode && !ieee80211_hw_check(&local->hw, HANDLES_QUIET_CSA); @@ -2610,11 +3039,11 @@ void ieee80211_dfs_cac_timer_work(struct wiphy *wiphy, struct wiphy_work *work) lockdep_assert_wiphy(sdata->local->hw.wiphy); - if (sdata->wdev.cac_started) { + if (sdata->wdev.links[link->link_id].cac_started) { ieee80211_link_release_channel(link); cfg80211_cac_event(sdata->dev, &chandef, NL80211_RADAR_CAC_FINISHED, - GFP_KERNEL); + GFP_KERNEL, link->link_id); } } @@ -3093,6 +3522,8 @@ static void ieee80211_set_disassoc(struct ieee80211_sub_if_data *sdata, u64 changed = 0; struct ieee80211_prep_tx_info info = { .subtype = stype, + .was_assoc = true, + .link_id = ffs(sdata->vif.active_links) - 1, }; lockdep_assert_wiphy(local->hw.wiphy); @@ -3141,29 +3572,7 @@ static void ieee80211_set_disassoc(struct ieee80211_sub_if_data *sdata, /* deauthenticate/disassociate now */ if (tx || frame_buf) { - /* - * In multi channel scenarios guarantee that the virtual - * interface is granted immediate airtime to transmit the - * deauthentication frame by calling mgd_prepare_tx, if the - * driver requested so. - */ - if (ieee80211_hw_check(&local->hw, DEAUTH_NEED_MGD_TX_PREP)) { - for (link_id = 0; link_id < ARRAY_SIZE(sdata->link); - link_id++) { - struct ieee80211_link_data *link; - - link = sdata_dereference(sdata->link[link_id], - sdata); - if (!link) - continue; - if (link->u.mgd.have_beacon) - break; - } - if (link_id == IEEE80211_MLD_MAX_NUM_LINKS) { - info.link_id = ffs(sdata->vif.active_links) - 1; - drv_mgd_prepare_tx(sdata->local, sdata, &info); - } - } + drv_mgd_prepare_tx(sdata->local, sdata, &info); ieee80211_send_deauth_disassoc(sdata, sdata->vif.cfg.ap_addr, sdata->vif.cfg.ap_addr, stype, @@ -3260,14 +3669,10 @@ static void ieee80211_set_disassoc(struct ieee80211_sub_if_data *sdata, } sdata->vif.bss_conf.csa_active = false; - sdata->deflink.u.mgd.csa_blocked_tx = false; - sdata->deflink.u.mgd.csa_waiting_bcn = false; - sdata->deflink.u.mgd.csa_ignored_same_chan = false; - if (sdata->csa_blocked_queues) { - ieee80211_wake_vif_queues(local, sdata, - IEEE80211_QUEUE_STOP_REASON_CSA); - sdata->csa_blocked_queues = false; - } + sdata->deflink.u.mgd.csa.blocked_tx = false; + sdata->deflink.u.mgd.csa.waiting_bcn = false; + sdata->deflink.u.mgd.csa.ignored_same_chan = false; + ieee80211_vif_unblock_queues_csa(sdata); /* existing TX TSPEC sessions no longer exist */ memset(ifmgd->tx_tspec, 0, sizeof(ifmgd->tx_tspec)); @@ -3275,9 +3680,7 @@ static void ieee80211_set_disassoc(struct ieee80211_sub_if_data *sdata, sdata->vif.bss_conf.power_type = IEEE80211_REG_UNSET_AP; sdata->vif.bss_conf.pwr_reduction = 0; - sdata->vif.bss_conf.tx_pwr_env_num = 0; - memset(sdata->vif.bss_conf.tx_pwr_env, 0, - sizeof(sdata->vif.bss_conf.tx_pwr_env)); + ieee80211_clear_tpe(&sdata->vif.bss_conf.tpe); sdata->vif.cfg.eml_cap = 0; sdata->vif.cfg.eml_med_sync_delay = 0; @@ -3287,8 +3690,17 @@ static void ieee80211_set_disassoc(struct ieee80211_sub_if_data *sdata, sizeof(sdata->u.mgd.ttlm_info)); wiphy_delayed_work_cancel(sdata->local->hw.wiphy, &ifmgd->ttlm_work); + memset(&sdata->vif.neg_ttlm, 0, sizeof(sdata->vif.neg_ttlm)); wiphy_delayed_work_cancel(sdata->local->hw.wiphy, &ifmgd->neg_ttlm_timeout_work); + + sdata->u.mgd.removed_links = 0; + wiphy_delayed_work_cancel(sdata->local->hw.wiphy, + &sdata->u.mgd.ml_reconf_work); + + wiphy_work_cancel(sdata->local->hw.wiphy, + &ifmgd->teardown_ttlm_work); + ieee80211_vif_set_links(sdata, 0, 0); ifmgd->mcast_seq_last = IEEE80211_SN_MODULO; @@ -3592,7 +4004,7 @@ static void __ieee80211_disconnect(struct ieee80211_sub_if_data *sdata) if (WARN_ON_ONCE(!link)) continue; - if (link->u.mgd.csa_blocked_tx) + if (link->u.mgd.csa.blocked_tx) continue; tx = true; @@ -3629,13 +4041,9 @@ static void __ieee80211_disconnect(struct ieee80211_sub_if_data *sdata) tx, frame_buf); /* the other links will be destroyed */ sdata->vif.bss_conf.csa_active = false; - sdata->deflink.u.mgd.csa_waiting_bcn = false; - sdata->deflink.u.mgd.csa_blocked_tx = false; - if (sdata->csa_blocked_queues) { - ieee80211_wake_vif_queues(local, sdata, - IEEE80211_QUEUE_STOP_REASON_CSA); - sdata->csa_blocked_queues = false; - } + sdata->deflink.u.mgd.csa.waiting_bcn = false; + sdata->deflink.u.mgd.csa.blocked_tx = false; + ieee80211_vif_unblock_queues_csa(sdata); ieee80211_report_disconnect(sdata, frame_buf, sizeof(frame_buf), tx, WLAN_REASON_DISASSOC_DUE_TO_INACTIVITY, @@ -4308,7 +4716,7 @@ static bool ieee80211_assoc_config_link(struct ieee80211_link_data *link, ((assoc_data->wmm && !elems->wmm_param) || (link->u.mgd.conn.mode >= IEEE80211_CONN_MODE_HT && (!elems->ht_cap_elem || !elems->ht_operation)) || - (link->u.mgd.conn.mode >= IEEE80211_CONN_MODE_VHT && + (is_5ghz && link->u.mgd.conn.mode >= IEEE80211_CONN_MODE_VHT && (!elems->vht_cap_elem || !elems->vht_operation)))) { const struct cfg80211_bss_ies *ies; struct ieee802_11_elems *bss_elems; @@ -4356,19 +4764,22 @@ static bool ieee80211_assoc_config_link(struct ieee80211_link_data *link, sdata_info(sdata, "AP bug: HT operation missing from AssocResp\n"); } - if (!elems->vht_cap_elem && bss_elems->vht_cap_elem && - link->u.mgd.conn.mode >= IEEE80211_CONN_MODE_VHT) { - elems->vht_cap_elem = bss_elems->vht_cap_elem; - sdata_info(sdata, - "AP bug: VHT capa missing from AssocResp\n"); - } - if (!elems->vht_operation && bss_elems->vht_operation && - link->u.mgd.conn.mode >= IEEE80211_CONN_MODE_VHT) { - elems->vht_operation = bss_elems->vht_operation; - sdata_info(sdata, - "AP bug: VHT operation missing from AssocResp\n"); - } + if (is_5ghz) { + if (!elems->vht_cap_elem && bss_elems->vht_cap_elem && + link->u.mgd.conn.mode >= IEEE80211_CONN_MODE_VHT) { + elems->vht_cap_elem = bss_elems->vht_cap_elem; + sdata_info(sdata, + "AP bug: VHT capa missing from AssocResp\n"); + } + + if (!elems->vht_operation && bss_elems->vht_operation && + link->u.mgd.conn.mode >= IEEE80211_CONN_MODE_VHT) { + elems->vht_operation = bss_elems->vht_operation; + sdata_info(sdata, + "AP bug: VHT operation missing from AssocResp\n"); + } + } kfree(bss_elems); } @@ -4445,40 +4856,12 @@ static bool ieee80211_assoc_config_link(struct ieee80211_link_data *link, if (elems->he_operation && link->u.mgd.conn.mode >= IEEE80211_CONN_MODE_HE && elems->he_cap) { - const struct ieee80211_he_6ghz_oper *he_6ghz_oper; - ieee80211_he_cap_ie_to_sta_he_cap(sdata, sband, elems->he_cap, elems->he_cap_len, elems->he_6ghz_capa, link_sta); - he_6ghz_oper = ieee80211_he_6ghz_oper(elems->he_operation); - - if (is_6ghz && he_6ghz_oper) { - switch (u8_get_bits(he_6ghz_oper->control, - IEEE80211_HE_6GHZ_OPER_CTRL_REG_INFO)) { - case IEEE80211_6GHZ_CTRL_REG_LPI_AP: - case IEEE80211_6GHZ_CTRL_REG_INDOOR_LPI_AP: - bss_conf->power_type = IEEE80211_REG_LPI_AP; - break; - case IEEE80211_6GHZ_CTRL_REG_SP_AP: - case IEEE80211_6GHZ_CTRL_REG_INDOOR_SP_AP: - bss_conf->power_type = IEEE80211_REG_SP_AP; - break; - case IEEE80211_6GHZ_CTRL_REG_VLP_AP: - bss_conf->power_type = IEEE80211_REG_VLP_AP; - break; - default: - bss_conf->power_type = IEEE80211_REG_UNSET_AP; - break; - } - } else if (is_6ghz) { - link_info(link, - "HE 6 GHz operation missing (on %d MHz), expect issues\n", - bss_conf->chanreq.oper.chan->center_freq); - } - bss_conf->he_support = link_sta->pub->he_cap.has_he; if (elems->rsnx && elems->rsnx_len && (elems->rsnx[0] & WLAN_RSNX_CAPA_PROTECTED_TWT) && @@ -5020,6 +5403,23 @@ ieee80211_determine_our_sta_mode_assoc(struct ieee80211_sub_if_data *sdata, conn->bw_limit, tmp.bw_limit); } +static enum ieee80211_ap_reg_power +ieee80211_ap_power_type(u8 control) +{ + switch (u8_get_bits(control, IEEE80211_HE_6GHZ_OPER_CTRL_REG_INFO)) { + case IEEE80211_6GHZ_CTRL_REG_LPI_AP: + case IEEE80211_6GHZ_CTRL_REG_INDOOR_LPI_AP: + return IEEE80211_REG_LPI_AP; + case IEEE80211_6GHZ_CTRL_REG_SP_AP: + case IEEE80211_6GHZ_CTRL_REG_INDOOR_SP_AP: + return IEEE80211_REG_SP_AP; + case IEEE80211_6GHZ_CTRL_REG_VLP_AP: + return IEEE80211_REG_VLP_AP; + default: + return IEEE80211_REG_UNSET_AP; + } +} + static int ieee80211_prep_channel(struct ieee80211_sub_if_data *sdata, struct ieee80211_link_data *link, int link_id, @@ -5029,15 +5429,15 @@ static int ieee80211_prep_channel(struct ieee80211_sub_if_data *sdata, struct ieee80211_local *local = sdata->local; bool is_6ghz = cbss->channel->band == NL80211_BAND_6GHZ; struct ieee80211_chan_req chanreq = {}; + struct cfg80211_chan_def ap_chandef; struct ieee802_11_elems *elems; int ret; - u32 i; lockdep_assert_wiphy(local->hw.wiphy); rcu_read_lock(); elems = ieee80211_determine_chan_mode(sdata, conn, cbss, link_id, - &chanreq); + &chanreq, &ap_chandef); if (IS_ERR(elems)) { rcu_read_unlock(); @@ -5052,26 +5452,23 @@ static int ieee80211_prep_channel(struct ieee80211_sub_if_data *sdata, } if (link && is_6ghz && conn->mode >= IEEE80211_CONN_MODE_HE) { - struct ieee80211_bss_conf *bss_conf; - u8 j = 0; - - bss_conf = link->conf; + const struct ieee80211_he_6ghz_oper *he_6ghz_oper; if (elems->pwr_constr_elem) - bss_conf->pwr_reduction = *elems->pwr_constr_elem; + link->conf->pwr_reduction = *elems->pwr_constr_elem; - BUILD_BUG_ON(ARRAY_SIZE(bss_conf->tx_pwr_env) != - ARRAY_SIZE(elems->tx_pwr_env)); - - for (i = 0; i < elems->tx_pwr_env_num; i++) { - if (elems->tx_pwr_env_len[i] > sizeof(bss_conf->tx_pwr_env[j])) - continue; + he_6ghz_oper = ieee80211_he_6ghz_oper(elems->he_operation); + if (he_6ghz_oper) + link->conf->power_type = + ieee80211_ap_power_type(he_6ghz_oper->control); + else + link_info(link, + "HE 6 GHz operation missing (on %d MHz), expect issues\n", + cbss->channel->center_freq); - bss_conf->tx_pwr_env_num++; - memcpy(&bss_conf->tx_pwr_env[j], elems->tx_pwr_env[i], - elems->tx_pwr_env_len[i]); - j++; - } + link->conf->tpe = elems->tpe; + ieee80211_rearrange_tpe(&link->conf->tpe, &ap_chandef, + &chanreq.oper); } rcu_read_unlock(); /* the element data was RCU protected so no longer valid anyway */ @@ -6150,13 +6547,140 @@ static void ieee80211_process_adv_ttlm(struct ieee80211_sub_if_data *sdata, } } +static void +ieee80211_mgd_check_cross_link_csa(struct ieee80211_sub_if_data *sdata, + int reporting_link_id, + struct ieee802_11_elems *elems) +{ + const struct element *sta_profiles[IEEE80211_MLD_MAX_NUM_LINKS] = {}; + ssize_t sta_profiles_len[IEEE80211_MLD_MAX_NUM_LINKS] = {}; + const struct element *sub; + const u8 *subelems; + size_t subelems_len; + u8 common_size; + int link_id; + + if (!ieee80211_mle_size_ok((u8 *)elems->ml_basic, elems->ml_basic_len)) + return; + + common_size = ieee80211_mle_common_size((u8 *)elems->ml_basic); + subelems = (u8 *)elems->ml_basic + common_size; + subelems_len = elems->ml_basic_len - common_size; + + for_each_element_id(sub, IEEE80211_MLE_SUBELEM_PER_STA_PROFILE, + subelems, subelems_len) { + struct ieee80211_mle_per_sta_profile *prof = (void *)sub->data; + struct ieee80211_link_data *link; + ssize_t len; + + if (!ieee80211_mle_basic_sta_prof_size_ok(sub->data, + sub->datalen)) + continue; + + link_id = le16_get_bits(prof->control, + IEEE80211_MLE_STA_CONTROL_LINK_ID); + /* need a valid link ID, but also not our own, both AP bugs */ + if (link_id == reporting_link_id || + link_id >= IEEE80211_MLD_MAX_NUM_LINKS) + continue; + + link = sdata_dereference(sdata->link[link_id], sdata); + if (!link) + continue; + + len = cfg80211_defragment_element(sub, subelems, subelems_len, + NULL, 0, + IEEE80211_MLE_SUBELEM_FRAGMENT); + if (WARN_ON(len < 0)) + continue; + + sta_profiles[link_id] = sub; + sta_profiles_len[link_id] = len; + } + + for (link_id = 0; link_id < IEEE80211_MLD_MAX_NUM_LINKS; link_id++) { + struct ieee80211_mle_per_sta_profile *prof; + struct ieee802_11_elems *prof_elems; + struct ieee80211_link_data *link; + ssize_t len; + + if (link_id == reporting_link_id) + continue; + + link = sdata_dereference(sdata->link[link_id], sdata); + if (!link) + continue; + + if (!sta_profiles[link_id]) { + prof_elems = NULL; + goto handle; + } + + /* we can defragment in-place, won't use the buffer again */ + len = cfg80211_defragment_element(sta_profiles[link_id], + subelems, subelems_len, + (void *)sta_profiles[link_id], + sta_profiles_len[link_id], + IEEE80211_MLE_SUBELEM_FRAGMENT); + if (WARN_ON(len != sta_profiles_len[link_id])) + continue; + + prof = (void *)sta_profiles[link_id]; + prof_elems = ieee802_11_parse_elems(prof->variable + + (prof->sta_info_len - 1), + len - + (prof->sta_info_len - 1), + false, NULL); + + /* memory allocation failed - let's hope that's transient */ + if (!prof_elems) + continue; + +handle: + /* + * FIXME: the timings here are obviously incorrect, + * but only older Intel drivers seem to care, and + * those don't have MLO. If you really need this, + * the problem is having to calculate it with the + * TSF offset etc. The device_timestamp is still + * correct, of course. + */ + ieee80211_sta_process_chanswitch(link, 0, 0, elems, prof_elems, + IEEE80211_CSA_SOURCE_OTHER_LINK); + kfree(prof_elems); + } +} + +static bool ieee80211_mgd_ssid_mismatch(struct ieee80211_sub_if_data *sdata, + const struct ieee802_11_elems *elems) +{ + struct ieee80211_vif_cfg *cfg = &sdata->vif.cfg; + static u8 zero_ssid[IEEE80211_MAX_SSID_LEN]; + + if (!elems->ssid) + return false; + + /* hidden SSID: zero length */ + if (elems->ssid_len == 0) + return false; + + if (elems->ssid_len != cfg->ssid_len) + return true; + + /* hidden SSID: zeroed out */ + if (!memcmp(elems->ssid, zero_ssid, elems->ssid_len)) + return false; + + return memcmp(elems->ssid, cfg->ssid, cfg->ssid_len); +} + static void ieee80211_rx_mgmt_beacon(struct ieee80211_link_data *link, struct ieee80211_hdr *hdr, size_t len, struct ieee80211_rx_status *rx_status) { struct ieee80211_sub_if_data *sdata = link->sdata; struct ieee80211_if_managed *ifmgd = &sdata->u.mgd; - struct ieee80211_bss_conf *bss_conf = &sdata->vif.bss_conf; + struct ieee80211_bss_conf *bss_conf = link->conf; struct ieee80211_vif_cfg *vif_cfg = &sdata->vif.cfg; struct ieee80211_mgmt *mgmt = (void *) hdr; size_t baselen; @@ -6200,7 +6724,7 @@ static void ieee80211_rx_mgmt_beacon(struct ieee80211_link_data *link, parse_params.len = len - baselen; rcu_read_lock(); - chanctx_conf = rcu_dereference(link->conf->chanctx_conf); + chanctx_conf = rcu_dereference(bss_conf->chanctx_conf); if (!chanctx_conf) { rcu_read_unlock(); return; @@ -6230,11 +6754,11 @@ static void ieee80211_rx_mgmt_beacon(struct ieee80211_link_data *link, ifmgd->assoc_data->need_beacon = false; if (ieee80211_hw_check(&local->hw, TIMING_BEACON_ONLY) && !ieee80211_is_s1g_beacon(hdr->frame_control)) { - link->conf->sync_tsf = + bss_conf->sync_tsf = le64_to_cpu(mgmt->u.beacon.timestamp); - link->conf->sync_device_ts = + bss_conf->sync_device_ts = rx_status->device_timestamp; - link->conf->sync_dtim_count = elems->dtim_count; + bss_conf->sync_dtim_count = elems->dtim_count; } if (elems->mbssid_config_ie) @@ -6258,7 +6782,7 @@ static void ieee80211_rx_mgmt_beacon(struct ieee80211_link_data *link, } if (!ifmgd->associated || - !ieee80211_rx_our_beacon(bssid, link->conf->bss)) + !ieee80211_rx_our_beacon(bssid, bss_conf->bss)) return; bssid = link->u.mgd.bssid; @@ -6285,12 +6809,21 @@ static void ieee80211_rx_mgmt_beacon(struct ieee80211_link_data *link, */ if (!ieee80211_is_s1g_beacon(hdr->frame_control)) ncrc = crc32_be(0, (void *)&mgmt->u.beacon.beacon_int, 4); - parse_params.bss = link->conf->bss; + parse_params.bss = bss_conf->bss; parse_params.filter = care_about_ies; parse_params.crc = ncrc; elems = ieee802_11_parse_elems_full(&parse_params); if (!elems) return; + + if (rx_status->flag & RX_FLAG_DECRYPTED && + ieee80211_mgd_ssid_mismatch(sdata, elems)) { + sdata_info(sdata, "SSID mismatch for AP %pM, disconnect\n", + sdata->vif.cfg.ap_addr); + __ieee80211_disconnect(sdata); + return; + } + ncrc = elems->crc; if (ieee80211_hw_check(&local->hw, PS_NULLFUNC_STACK) && @@ -6357,11 +6890,11 @@ static void ieee80211_rx_mgmt_beacon(struct ieee80211_link_data *link, */ if (ieee80211_hw_check(&local->hw, TIMING_BEACON_ONLY) && !ieee80211_is_s1g_beacon(hdr->frame_control)) { - link->conf->sync_tsf = + bss_conf->sync_tsf = le64_to_cpu(mgmt->u.beacon.timestamp); - link->conf->sync_device_ts = + bss_conf->sync_device_ts = rx_status->device_timestamp; - link->conf->sync_dtim_count = elems->dtim_count; + bss_conf->sync_dtim_count = elems->dtim_count; } if ((ncrc == link->u.mgd.beacon_crc && link->u.mgd.beacon_crc_valid) || @@ -6374,7 +6907,11 @@ static void ieee80211_rx_mgmt_beacon(struct ieee80211_link_data *link, ieee80211_sta_process_chanswitch(link, rx_status->mactime, rx_status->device_timestamp, - elems, true); + elems, elems, + IEEE80211_CSA_SOURCE_BEACON); + + /* note that after this elems->ml_basic can no longer be used fully */ + ieee80211_mgd_check_cross_link_csa(sdata, rx_status->link_id, elems); if (!link->u.mgd.disable_wmm_tracking && ieee80211_sta_wmm_params(local, link, elems->wmm_param, @@ -6420,10 +6957,10 @@ static void ieee80211_rx_mgmt_beacon(struct ieee80211_link_data *link, goto free; } - if (WARN_ON(!link->conf->chanreq.oper.chan)) + if (WARN_ON(!bss_conf->chanreq.oper.chan)) goto free; - sband = local->hw.wiphy->bands[link->conf->chanreq.oper.chan->band]; + sband = local->hw.wiphy->bands[bss_conf->chanreq.oper.chan->band]; changed |= ieee80211_recalc_twt_req(sdata, sband, link, link_sta, elems); @@ -6834,7 +7371,7 @@ static void ieee80211_teardown_ttlm_work(struct wiphy *wiphy, u16 new_dormant_links; struct ieee80211_sub_if_data *sdata = container_of(work, struct ieee80211_sub_if_data, - u.mgd.neg_ttlm_timeout_work.work); + u.mgd.teardown_ttlm_work); if (!sdata->vif.neg_ttlm.valid) return; @@ -6908,6 +7445,7 @@ void ieee80211_sta_rx_queued_mgmt(struct ieee80211_sub_if_data *sdata, { struct ieee80211_link_data *link = &sdata->deflink; struct ieee80211_rx_status *rx_status; + struct ieee802_11_elems *elems; struct ieee80211_mgmt *mgmt; u16 fc; int ies_len; @@ -6951,9 +7489,8 @@ void ieee80211_sta_rx_queued_mgmt(struct ieee80211_sub_if_data *sdata, !ether_addr_equal(mgmt->bssid, sdata->vif.cfg.ap_addr)) break; - if (mgmt->u.action.category == WLAN_CATEGORY_SPECTRUM_MGMT) { - struct ieee802_11_elems *elems; - + switch (mgmt->u.action.category) { + case WLAN_CATEGORY_SPECTRUM_MGMT: ies_len = skb->len - offsetof(struct ieee80211_mgmt, u.action.u.chan_switch.variable); @@ -6966,15 +7503,20 @@ void ieee80211_sta_rx_queued_mgmt(struct ieee80211_sub_if_data *sdata, mgmt->u.action.u.chan_switch.variable, ies_len, true, NULL); - if (elems && !elems->parse_error) + if (elems && !elems->parse_error) { + enum ieee80211_csa_source src = + IEEE80211_CSA_SOURCE_PROT_ACTION; + ieee80211_sta_process_chanswitch(link, rx_status->mactime, rx_status->device_timestamp, - elems, false); + elems, elems, + src); + } kfree(elems); - } else if (mgmt->u.action.category == WLAN_CATEGORY_PUBLIC) { - struct ieee802_11_elems *elems; - + break; + case WLAN_CATEGORY_PUBLIC: + case WLAN_CATEGORY_PROTECTED_DUAL_OF_ACTION: ies_len = skb->len - offsetof(struct ieee80211_mgmt, u.action.u.ext_chan_switch.variable); @@ -6991,6 +7533,14 @@ void ieee80211_sta_rx_queued_mgmt(struct ieee80211_sub_if_data *sdata, ies_len, true, NULL); if (elems && !elems->parse_error) { + enum ieee80211_csa_source src; + + if (mgmt->u.action.category == + WLAN_CATEGORY_PROTECTED_DUAL_OF_ACTION) + src = IEEE80211_CSA_SOURCE_PROT_ACTION; + else + src = IEEE80211_CSA_SOURCE_UNPROT_ACTION; + /* for the handling code pretend it was an IE */ elems->ext_chansw_ie = &mgmt->u.action.u.ext_chan_switch.data; @@ -6998,10 +7548,12 @@ void ieee80211_sta_rx_queued_mgmt(struct ieee80211_sub_if_data *sdata, ieee80211_sta_process_chanswitch(link, rx_status->mactime, rx_status->device_timestamp, - elems, false); + elems, elems, + src); } kfree(elems); + break; } break; } @@ -7112,6 +7664,7 @@ static int ieee80211_do_assoc(struct ieee80211_sub_if_data *sdata) lockdep_assert_wiphy(sdata->local->hw.wiphy); assoc_data->tries++; + assoc_data->comeback = false; if (assoc_data->tries > IEEE80211_ASSOC_MAX_TRIES) { sdata_info(sdata, "association with %pM timed out\n", assoc_data->ap_addr); @@ -7321,7 +7874,7 @@ static void ieee80211_sta_bcn_mon_timer(struct timer_list *t) return; if (sdata->vif.bss_conf.csa_active && - !sdata->deflink.u.mgd.csa_waiting_bcn) + !sdata->deflink.u.mgd.csa.waiting_bcn) return; if (sdata->vif.driver_flags & IEEE80211_VIF_BEACON_FILTER) @@ -7345,7 +7898,7 @@ static void ieee80211_sta_conn_mon_timer(struct timer_list *t) return; if (sdata->vif.bss_conf.csa_active && - !sdata->deflink.u.mgd.csa_waiting_bcn) + !sdata->deflink.u.mgd.csa.waiting_bcn) return; sta = sta_info_get(sdata, sdata->vif.cfg.ap_addr); @@ -7556,8 +8109,10 @@ void ieee80211_mgd_setup_link(struct ieee80211_link_data *link) else link->u.mgd.req_smps = IEEE80211_SMPS_OFF; - wiphy_delayed_work_init(&link->u.mgd.chswitch_work, - ieee80211_chswitch_work); + wiphy_delayed_work_init(&link->u.mgd.csa.switch_work, + ieee80211_csa_switch_work); + + ieee80211_clear_tpe(&link->conf->tpe); if (sdata->u.mgd.assoc_data) ether_addr_copy(link->conf->addr, @@ -8686,7 +9241,7 @@ void ieee80211_mgd_stop_link(struct ieee80211_link_data *link) wiphy_work_cancel(link->sdata->local->hw.wiphy, &link->u.mgd.recalc_smps); wiphy_delayed_work_cancel(link->sdata->local->hw.wiphy, - &link->u.mgd.chswitch_work); + &link->u.mgd.csa.switch_work); } void ieee80211_mgd_stop(struct ieee80211_sub_if_data *sdata) @@ -8704,15 +9259,8 @@ void ieee80211_mgd_stop(struct ieee80211_sub_if_data *sdata) &ifmgd->beacon_connection_loss_work); wiphy_work_cancel(sdata->local->hw.wiphy, &ifmgd->csa_connection_drop_work); - wiphy_work_cancel(sdata->local->hw.wiphy, - &ifmgd->teardown_ttlm_work); wiphy_delayed_work_cancel(sdata->local->hw.wiphy, &ifmgd->tdls_peer_del_work); - wiphy_delayed_work_cancel(sdata->local->hw.wiphy, - &ifmgd->ml_reconf_work); - wiphy_delayed_work_cancel(sdata->local->hw.wiphy, &ifmgd->ttlm_work); - wiphy_delayed_work_cancel(sdata->local->hw.wiphy, - &ifmgd->neg_ttlm_timeout_work); if (ifmgd->assoc_data) ieee80211_destroy_assoc_data(sdata, ASSOC_TIMEOUT); diff --git a/net/mac80211/offchannel.c b/net/mac80211/offchannel.c index 65e1e9e971fd..29fab7ae47b4 100644 --- a/net/mac80211/offchannel.c +++ b/net/mac80211/offchannel.c @@ -8,7 +8,7 @@ * Copyright 2006-2007 Jiri Benc <jbenc@suse.cz> * Copyright 2007, Michael Wu <flamingice@sourmilk.net> * Copyright 2009 Johannes Berg <johannes@sipsolutions.net> - * Copyright (C) 2019, 2022-2023 Intel Corporation + * Copyright (C) 2019, 2022-2024 Intel Corporation */ #include <linux/export.h> #include <net/mac80211.h> @@ -413,6 +413,39 @@ void ieee80211_start_next_roc(struct ieee80211_local *local) } } +void ieee80211_reconfig_roc(struct ieee80211_local *local) +{ + struct ieee80211_roc_work *roc, *tmp; + + /* + * In the software implementation can just continue with the + * interruption due to reconfig, roc_work is still queued if + * needed. + */ + if (!local->ops->remain_on_channel) + return; + + /* flush work so nothing from the driver is still pending */ + wiphy_work_flush(local->hw.wiphy, &local->hw_roc_start); + wiphy_work_flush(local->hw.wiphy, &local->hw_roc_done); + + list_for_each_entry_safe(roc, tmp, &local->roc_list, list) { + if (!roc->started) + break; + + if (!roc->hw_begun) { + /* it didn't start in HW yet, so we can restart it */ + roc->started = false; + continue; + } + + /* otherwise destroy it and tell userspace */ + ieee80211_roc_notify_destroy(roc); + } + + ieee80211_start_next_roc(local); +} + static void __ieee80211_roc_work(struct ieee80211_local *local) { struct ieee80211_roc_work *roc; @@ -964,6 +997,7 @@ int ieee80211_mgmt_tx(struct wiphy *wiphy, struct wireless_dev *wdev, } IEEE80211_SKB_CB(skb)->flags = flags; + IEEE80211_SKB_CB(skb)->control.flags |= IEEE80211_TX_CTRL_DONT_USE_RATE_MASK; skb->dev = sdata->dev; diff --git a/net/mac80211/parse.c b/net/mac80211/parse.c index 055a60e90979..279c5143b335 100644 --- a/net/mac80211/parse.c +++ b/net/mac80211/parse.c @@ -187,6 +187,84 @@ ieee80211_parse_extension_element(u32 *crc, *crc = crc32_be(*crc, (void *)elem, elem->datalen + 2); } +static void ieee80211_parse_tpe(struct ieee80211_parsed_tpe *tpe, + const u8 *data, u8 len) +{ + const struct ieee80211_tx_pwr_env *env = (const void *)data; + u8 count, interpret, category; + u8 *out, N, *cnt_out = NULL, *N_out = NULL; + + if (!ieee80211_valid_tpe_element(data, len)) + return; + + count = u8_get_bits(env->info, IEEE80211_TX_PWR_ENV_INFO_COUNT); + interpret = u8_get_bits(env->info, IEEE80211_TX_PWR_ENV_INFO_INTERPRET); + category = u8_get_bits(env->info, IEEE80211_TX_PWR_ENV_INFO_CATEGORY); + + switch (interpret) { + case IEEE80211_TPE_LOCAL_EIRP: + out = tpe->max_local[category].power; + cnt_out = &tpe->max_local[category].count; + tpe->max_local[category].valid = true; + break; + case IEEE80211_TPE_REG_CLIENT_EIRP: + out = tpe->max_reg_client[category].power; + cnt_out = &tpe->max_reg_client[category].count; + tpe->max_reg_client[category].valid = true; + break; + case IEEE80211_TPE_LOCAL_EIRP_PSD: + out = tpe->psd_local[category].power; + cnt_out = &tpe->psd_local[category].count; + N_out = &tpe->psd_local[category].n; + tpe->psd_local[category].valid = true; + break; + case IEEE80211_TPE_REG_CLIENT_EIRP_PSD: + out = tpe->psd_reg_client[category].power; + cnt_out = &tpe->psd_reg_client[category].count; + N_out = &tpe->psd_reg_client[category].n; + tpe->psd_reg_client[category].valid = true; + break; + } + + switch (interpret) { + case IEEE80211_TPE_LOCAL_EIRP: + case IEEE80211_TPE_REG_CLIENT_EIRP: + /* count was validated <= 3, plus 320 MHz */ + BUILD_BUG_ON(IEEE80211_TPE_EIRP_ENTRIES_320MHZ < 5); + memcpy(out, env->variable, count + 1); + *cnt_out = count + 1; + /* separately take 320 MHz if present */ + if (count == 3 && len > sizeof(*env) + count + 1) { + out[4] = env->variable[4]; + *cnt_out = 5; + } + break; + case IEEE80211_TPE_LOCAL_EIRP_PSD: + case IEEE80211_TPE_REG_CLIENT_EIRP_PSD: + if (!count) { + memset(out, env->variable[0], + IEEE80211_TPE_PSD_ENTRIES_320MHZ); + *cnt_out = IEEE80211_TPE_PSD_ENTRIES_320MHZ; + break; + } + + N = 1 << (count - 1); + memcpy(out, env->variable, N); + *cnt_out = N; + *N_out = N; + + if (len > sizeof(*env) + N) { + int K = u8_get_bits(env->variable[N], + IEEE80211_TX_PWR_ENV_EXT_COUNT); + + K = min(K, IEEE80211_TPE_PSD_ENTRIES_320MHZ - N); + memcpy(out + N, env->variable + N + 1, K); + (*cnt_out) += K; + } + break; + } +} + static u32 _ieee802_11_parse_elems_full(struct ieee80211_elems_parse_params *params, struct ieee80211_elems_parse *elems_parse, @@ -529,6 +607,13 @@ _ieee802_11_parse_elems_full(struct ieee80211_elems_parse_params *params, elem_parse_failed = IEEE80211_PARSE_ERR_BAD_ELEM_SIZE; } + + subelem = cfg80211_find_ext_elem(WLAN_EID_TX_POWER_ENVELOPE, + pos, elen); + if (subelem) + ieee80211_parse_tpe(&elems->csa_tpe, + subelem->data + 1, + subelem->datalen - 1); break; case WLAN_EID_COUNTRY: elems->country_elem = pos; @@ -593,16 +678,9 @@ _ieee802_11_parse_elems_full(struct ieee80211_elems_parse_params *params, elems->rsnx_len = elen; break; case WLAN_EID_TX_POWER_ENVELOPE: - if (elen < 1 || - elen > sizeof(struct ieee80211_tx_pwr_env)) + if (params->mode < IEEE80211_CONN_MODE_HE) break; - - if (elems->tx_pwr_env_num >= ARRAY_SIZE(elems->tx_pwr_env)) - break; - - elems->tx_pwr_env[elems->tx_pwr_env_num] = (void *)pos; - elems->tx_pwr_env_len[elems->tx_pwr_env_num] = elen; - elems->tx_pwr_env_num++; + ieee80211_parse_tpe(&elems->tpe, pos, elen); break; case WLAN_EID_EXTENSION: ieee80211_parse_extension_element(calc_crc ? @@ -889,6 +967,10 @@ ieee802_11_parse_elems_full(struct ieee80211_elems_parse_params *params) elems->ie_start = params->start; elems->total_len = params->len; + /* set all TPE entries to unlimited (but invalid) */ + ieee80211_clear_tpe(&elems->tpe); + ieee80211_clear_tpe(&elems->csa_tpe); + nontransmitted_profile = elems_parse->scratch_pos; nontransmitted_profile_len = ieee802_11_find_bssid_profile(params->start, params->len, diff --git a/net/mac80211/pm.c b/net/mac80211/pm.c index c1fa26e09479..7be52345f218 100644 --- a/net/mac80211/pm.c +++ b/net/mac80211/pm.c @@ -1,7 +1,7 @@ // SPDX-License-Identifier: GPL-2.0 /* * Portions - * Copyright (C) 2020-2021, 2023 Intel Corporation + * Copyright (C) 2020-2021, 2023-2024 Intel Corporation */ #include <net/mac80211.h> #include <net/rtnetlink.h> @@ -32,7 +32,7 @@ int __ieee80211_suspend(struct ieee80211_hw *hw, struct cfg80211_wowlan *wowlan) ieee80211_scan_cancel(local); - ieee80211_dfs_cac_cancel(local); + ieee80211_dfs_cac_cancel(local, NULL); ieee80211_roc_purge(local, NULL); @@ -171,7 +171,7 @@ int __ieee80211_suspend(struct ieee80211_hw *hw, struct cfg80211_wowlan *wowlan) WARN_ON(!list_empty(&local->chanctx_list)); /* stop hardware - this must stop RX */ - ieee80211_stop_device(local); + ieee80211_stop_device(local, true); suspend: local->suspended = true; diff --git a/net/mac80211/rate.c b/net/mac80211/rate.c index 4dc1def69548..3dc9752188d5 100644 --- a/net/mac80211/rate.c +++ b/net/mac80211/rate.c @@ -890,7 +890,7 @@ void ieee80211_get_tx_rates(struct ieee80211_vif *vif, if (ieee80211_is_tx_data(skb)) rate_control_apply_mask(sdata, sta, sband, dest, max_rates); - if (!(info->control.flags & IEEE80211_TX_CTRL_SCAN_TX)) + if (!(info->control.flags & IEEE80211_TX_CTRL_DONT_USE_RATE_MASK)) mask = sdata->rc_rateidx_mask[info->band]; if (dest[0].idx < 0) diff --git a/net/mac80211/rc80211_minstrel_ht_debugfs.c b/net/mac80211/rc80211_minstrel_ht_debugfs.c index 25b8a67a63a4..85149c774505 100644 --- a/net/mac80211/rc80211_minstrel_ht_debugfs.c +++ b/net/mac80211/rc80211_minstrel_ht_debugfs.c @@ -187,7 +187,6 @@ static const struct file_operations minstrel_ht_stat_fops = { .open = minstrel_ht_stats_open, .read = minstrel_stats_read, .release = minstrel_stats_release, - .llseek = no_llseek, }; static char * @@ -323,7 +322,6 @@ static const struct file_operations minstrel_ht_stat_csv_fops = { .open = minstrel_ht_stats_csv_open, .read = minstrel_stats_read, .release = minstrel_stats_release, - .llseek = no_llseek, }; void diff --git a/net/mac80211/rx.c b/net/mac80211/rx.c index 4914692750e5..59ad24a71141 100644 --- a/net/mac80211/rx.c +++ b/net/mac80211/rx.c @@ -3358,6 +3358,7 @@ static void ieee80211_rx_check_bss_color_collision(struct ieee80211_rx_data *rx) { struct ieee80211_mgmt *mgmt = (void *)rx->skb->data; + struct ieee80211_bss_conf *bss_conf; const struct element *ie; size_t baselen; @@ -3368,7 +3369,9 @@ ieee80211_rx_check_bss_color_collision(struct ieee80211_rx_data *rx) if (ieee80211_hw_check(&rx->local->hw, DETECTS_COLOR_COLLISION)) return; - if (rx->link->conf->csa_active) + bss_conf = rx->link->conf; + if (bss_conf->csa_active || bss_conf->color_change_active || + !bss_conf->he_bss_color.enabled) return; baselen = mgmt->u.beacon.variable - rx->skb->data; @@ -3380,7 +3383,6 @@ ieee80211_rx_check_bss_color_collision(struct ieee80211_rx_data *rx) rx->skb->len - baselen); if (ie && ie->datalen >= sizeof(struct ieee80211_he_operation) && ie->datalen >= ieee80211_he_oper_size(ie->data + 1)) { - struct ieee80211_bss_conf *bss_conf = rx->link->conf; const struct ieee80211_he_operation *he_oper; u8 color; @@ -3617,6 +3619,7 @@ ieee80211_rx_h_action(struct ieee80211_rx_data *rx) break; case WLAN_CATEGORY_PUBLIC: + case WLAN_CATEGORY_PROTECTED_DUAL_OF_ACTION: if (len < IEEE80211_MIN_ACTION_SIZE + 1) goto invalid; if (sdata->vif.type != NL80211_IFTYPE_STATION) diff --git a/net/mac80211/scan.c b/net/mac80211/scan.c index b5f2df61c7f6..adb88c06b598 100644 --- a/net/mac80211/scan.c +++ b/net/mac80211/scan.c @@ -504,7 +504,7 @@ static void __ieee80211_scan_completed(struct ieee80211_hw *hw, bool aborted) * the scan was in progress; if there was none this will * just be a no-op for the particular interface. */ - list_for_each_entry_rcu(sdata, &local->interfaces, list) { + list_for_each_entry(sdata, &local->interfaces, list) { if (ieee80211_sdata_running(sdata)) wiphy_work_queue(sdata->local->hw.wiphy, &sdata->work); } @@ -575,6 +575,7 @@ static bool __ieee80211_can_leave_ch(struct ieee80211_sub_if_data *sdata) { struct ieee80211_local *local = sdata->local; struct ieee80211_sub_if_data *sdata_iter; + unsigned int link_id; lockdep_assert_wiphy(local->hw.wiphy); @@ -585,8 +586,9 @@ static bool __ieee80211_can_leave_ch(struct ieee80211_sub_if_data *sdata) return false; list_for_each_entry(sdata_iter, &local->interfaces, list) { - if (sdata_iter->wdev.cac_started) - return false; + for_each_valid_link(&sdata_iter->wdev, link_id) + if (sdata_iter->wdev.links[link_id].cac_started) + return false; } return true; @@ -649,7 +651,7 @@ static void ieee80211_send_scan_probe_req(struct ieee80211_sub_if_data *sdata, cpu_to_le16(IEEE80211_SN_TO_SEQ(sn)); } IEEE80211_SKB_CB(skb)->flags |= tx_flags; - IEEE80211_SKB_CB(skb)->control.flags |= IEEE80211_TX_CTRL_SCAN_TX; + IEEE80211_SKB_CB(skb)->control.flags |= IEEE80211_TX_CTRL_DONT_USE_RATE_MASK; ieee80211_tx_skb_tid_band(sdata, skb, 7, channel->band); } } @@ -1013,10 +1015,8 @@ set_channel: */ if ((chan->flags & (IEEE80211_CHAN_NO_IR | IEEE80211_CHAN_RADAR)) || !scan_req->n_ssids) { - *next_delay = msecs_to_jiffies(scan_req->duration) > - IEEE80211_PASSIVE_CHANNEL_TIME ? - msecs_to_jiffies(scan_req->duration) : - IEEE80211_PASSIVE_CHANNEL_TIME; + *next_delay = max(msecs_to_jiffies(scan_req->duration), + IEEE80211_PASSIVE_CHANNEL_TIME); local->next_scan_state = SCAN_DECISION; if (scan_req->n_ssids) set_bit(SCAN_BEACON_WAIT, &local->scanning); diff --git a/net/mac80211/spectmgmt.c b/net/mac80211/spectmgmt.c index b2de4c6fb808..073ff9e0f397 100644 --- a/net/mac80211/spectmgmt.c +++ b/net/mac80211/spectmgmt.c @@ -9,7 +9,7 @@ * Copyright 2007, Michael Wu <flamingice@sourmilk.net> * Copyright 2007-2008, Intel Corporation * Copyright 2008, Johannes Berg <johannes@sipsolutions.net> - * Copyright (C) 2018, 2020, 2022-2023 Intel Corporation + * Copyright (C) 2018, 2020, 2022-2024 Intel Corporation */ #include <linux/ieee80211.h> @@ -223,7 +223,7 @@ int ieee80211_parse_ch_switch_ie(struct ieee80211_sub_if_data *sdata, enum nl80211_band current_band, u32 vht_cap_info, struct ieee80211_conn_settings *conn, - u8 *bssid, + u8 *bssid, bool unprot_action, struct ieee80211_csa_ie *csa_ie) { enum nl80211_band new_band = current_band; @@ -258,8 +258,10 @@ int ieee80211_parse_ch_switch_ie(struct ieee80211_sub_if_data *sdata, if (!ieee80211_operating_class_to_band(new_op_class, &new_band)) { new_op_class = 0; - sdata_info(sdata, "cannot understand ECSA IE operating class, %d, ignoring\n", - ext_chansw_elem->new_operating_class); + if (!unprot_action) + sdata_info(sdata, + "cannot understand ECSA IE operating class, %d, ignoring\n", + ext_chansw_elem->new_operating_class); } else { new_chan_no = ext_chansw_elem->new_ch_num; csa_ie->count = ext_chansw_elem->count; @@ -293,9 +295,10 @@ int ieee80211_parse_ch_switch_ie(struct ieee80211_sub_if_data *sdata, new_freq = ieee80211_channel_to_frequency(new_chan_no, new_band); new_chan = ieee80211_get_channel(sdata->local->hw.wiphy, new_freq); if (!new_chan || new_chan->flags & IEEE80211_CHAN_DISABLED) { - sdata_info(sdata, - "BSS %pM switches to unsupported channel (%d MHz), disconnecting\n", - bssid, new_freq); + if (!unprot_action) + sdata_info(sdata, + "BSS %pM switches to unsupported channel (%d MHz), disconnecting\n", + bssid, new_freq); return -EINVAL; } @@ -340,6 +343,9 @@ int ieee80211_parse_ch_switch_ie(struct ieee80211_sub_if_data *sdata, break; } + /* capture the AP configuration */ + csa_ie->chanreq.ap = csa_ie->chanreq.oper; + /* parse one of the Elements to build a new chandef */ memset(&new_chandef, 0, sizeof(new_chandef)); new_chandef.chan = new_chan; @@ -368,6 +374,9 @@ int ieee80211_parse_ch_switch_ie(struct ieee80211_sub_if_data *sdata, /* if data is there validate the bandwidth & use it */ if (new_chandef.chan) { + /* capture the AP chandef before (potential) downgrading */ + csa_ie->chanreq.ap = new_chandef; + if (conn->bw_limit < IEEE80211_CONN_BW_LIMIT_320 && new_chandef.width == NL80211_CHAN_WIDTH_320) ieee80211_chandef_downgrade(&new_chandef, NULL); diff --git a/net/mac80211/sta_info.h b/net/mac80211/sta_info.h index bd5e2f7146f6..9195d5a2de0a 100644 --- a/net/mac80211/sta_info.h +++ b/net/mac80211/sta_info.h @@ -727,6 +727,12 @@ struct sta_info { struct ieee80211_sta sta; }; +static inline int ieee80211_tdls_sta_link_id(struct sta_info *sta) +{ + /* TDLS STA can only have a single link */ + return sta->sta.valid_links ? __ffs(sta->sta.valid_links) : 0; +} + static inline enum nl80211_plink_state sta_plink_state(struct sta_info *sta) { #ifdef CONFIG_MAC80211_MESH diff --git a/net/mac80211/status.c b/net/mac80211/status.c index dd8f857a1fbc..d1cf987de13b 100644 --- a/net/mac80211/status.c +++ b/net/mac80211/status.c @@ -1301,3 +1301,4 @@ void ieee80211_purge_tx_queue(struct ieee80211_hw *hw, while ((skb = __skb_dequeue(skbs))) ieee80211_free_txskb(hw, skb); } +EXPORT_SYMBOL(ieee80211_purge_tx_queue); diff --git a/net/mac80211/tests/Makefile b/net/mac80211/tests/Makefile index 4fdaf3feaca3..511dfa226699 100644 --- a/net/mac80211/tests/Makefile +++ b/net/mac80211/tests/Makefile @@ -1,3 +1,3 @@ -mac80211-tests-y += module.o elems.o mfp.o +mac80211-tests-y += module.o elems.o mfp.o tpe.o obj-$(CONFIG_MAC80211_KUNIT_TEST) += mac80211-tests.o diff --git a/net/mac80211/tests/tpe.c b/net/mac80211/tests/tpe.c new file mode 100644 index 000000000000..dd63303a2985 --- /dev/null +++ b/net/mac80211/tests/tpe.c @@ -0,0 +1,284 @@ +// SPDX-License-Identifier: GPL-2.0-only +/* + * KUnit tests for TPE element handling + * + * Copyright (C) 2024 Intel Corporation + */ +#include <kunit/test.h> +#include "../ieee80211_i.h" + +MODULE_IMPORT_NS(EXPORTED_FOR_KUNIT_TESTING); + +static struct ieee80211_channel chan6g_1 = { + .band = NL80211_BAND_6GHZ, + .center_freq = 5955, +}; + +static struct ieee80211_channel chan6g_33 = { + .band = NL80211_BAND_6GHZ, + .center_freq = 6115, +}; + +static struct ieee80211_channel chan6g_61 = { + .band = NL80211_BAND_6GHZ, + .center_freq = 6255, +}; + +static const struct subchan_test_case { + const char *desc; + struct cfg80211_chan_def c; + u8 n; + int expect; +} subchan_offset_cases[] = { + { + .desc = "identical 20 MHz", + .c.width = NL80211_CHAN_WIDTH_20, + .c.chan = &chan6g_1, + .c.center_freq1 = 5955, + .n = 1, + .expect = 0, + }, + { + .desc = "identical 40 MHz", + .c.width = NL80211_CHAN_WIDTH_40, + .c.chan = &chan6g_1, + .c.center_freq1 = 5965, + .n = 2, + .expect = 0, + }, + { + .desc = "identical 80+80 MHz", + /* not really is valid? doesn't matter for the test */ + .c.width = NL80211_CHAN_WIDTH_80P80, + .c.chan = &chan6g_1, + .c.center_freq1 = 5985, + .c.center_freq2 = 6225, + .n = 16, + .expect = 0, + }, + { + .desc = "identical 320 MHz", + .c.width = NL80211_CHAN_WIDTH_320, + .c.chan = &chan6g_1, + .c.center_freq1 = 6105, + .n = 16, + .expect = 0, + }, + { + .desc = "lower 160 MHz of 320 MHz", + .c.width = NL80211_CHAN_WIDTH_320, + .c.chan = &chan6g_1, + .c.center_freq1 = 6105, + .n = 8, + .expect = 0, + }, + { + .desc = "upper 160 MHz of 320 MHz", + .c.width = NL80211_CHAN_WIDTH_320, + .c.chan = &chan6g_61, + .c.center_freq1 = 6105, + .n = 8, + .expect = 8, + }, + { + .desc = "upper 160 MHz of 320 MHz, go to 40", + .c.width = NL80211_CHAN_WIDTH_320, + .c.chan = &chan6g_61, + .c.center_freq1 = 6105, + .n = 2, + .expect = 8 + 4 + 2, + }, + { + .desc = "secondary 80 above primary in 80+80 MHz", + /* not really is valid? doesn't matter for the test */ + .c.width = NL80211_CHAN_WIDTH_80P80, + .c.chan = &chan6g_1, + .c.center_freq1 = 5985, + .c.center_freq2 = 6225, + .n = 4, + .expect = 0, + }, + { + .desc = "secondary 80 below primary in 80+80 MHz", + /* not really is valid? doesn't matter for the test */ + .c.width = NL80211_CHAN_WIDTH_80P80, + .c.chan = &chan6g_61, + .c.center_freq1 = 6225, + .c.center_freq2 = 5985, + .n = 4, + .expect = 4, + }, + { + .desc = "secondary 80 below primary in 80+80 MHz, go to 20", + /* not really is valid? doesn't matter for the test */ + .c.width = NL80211_CHAN_WIDTH_80P80, + .c.chan = &chan6g_61, + .c.center_freq1 = 6225, + .c.center_freq2 = 5985, + .n = 1, + .expect = 7, + }, +}; + +KUNIT_ARRAY_PARAM_DESC(subchan_offset, subchan_offset_cases, desc); + +static void subchan_offset(struct kunit *test) +{ + const struct subchan_test_case *params = test->param_value; + int offset; + + KUNIT_ASSERT_EQ(test, cfg80211_chandef_valid(¶ms->c), true); + + offset = ieee80211_calc_chandef_subchan_offset(¶ms->c, params->n); + + KUNIT_EXPECT_EQ(test, params->expect, offset); +} + +static const struct psd_reorder_test_case { + const char *desc; + struct cfg80211_chan_def ap, used; + struct ieee80211_parsed_tpe_psd psd, out; +} psd_reorder_cases[] = { + { + .desc = "no changes, 320 MHz", + + .ap.width = NL80211_CHAN_WIDTH_320, + .ap.chan = &chan6g_1, + .ap.center_freq1 = 6105, + + .used.width = NL80211_CHAN_WIDTH_320, + .used.chan = &chan6g_1, + .used.center_freq1 = 6105, + + .psd.valid = true, + .psd.count = 16, + .psd.n = 8, + .psd.power = { 0, 1, 2, 3, 4, 5, 6, 7, 8, 9, 10, 11, 12, 13, 14, 15 }, + + .out.valid = true, + .out.count = 16, + .out.n = 8, + .out.power = { 0, 1, 2, 3, 4, 5, 6, 7, 8, 9, 10, 11, 12, 13, 14, 15 }, + }, + { + .desc = "no changes, 320 MHz, 160 MHz used, n=0", + + .ap.width = NL80211_CHAN_WIDTH_320, + .ap.chan = &chan6g_1, + .ap.center_freq1 = 6105, + + .used.width = NL80211_CHAN_WIDTH_160, + .used.chan = &chan6g_1, + .used.center_freq1 = 6025, + + .psd.valid = true, + .psd.count = 16, + .psd.n = 0, + .psd.power = { 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, }, + + .out.valid = true, + .out.count = 8, + .out.n = 0, + .out.power = { 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, }, + }, + { + .desc = "320 MHz, HE is 80, used 160, all lower", + + .ap.width = NL80211_CHAN_WIDTH_320, + .ap.chan = &chan6g_1, + .ap.center_freq1 = 6105, + + .used.width = NL80211_CHAN_WIDTH_160, + .used.chan = &chan6g_1, + .used.center_freq1 = 6025, + + .psd.valid = true, + .psd.count = 16, + .psd.n = 4, + .psd.power = { 0, 1, 2, 3, 4, 5, 6, 7, 8, 9, 10, 11, 12, 13, 14, 15 }, + + .out.valid = true, + .out.count = 8, + .out.n = 4, + .out.power = { 0, 1, 2, 3, 4, 5, 6, 7, 127, 127, 127, 127, 127, 127, 127, 127}, + }, + { + .desc = "320 MHz, HE is 80, used 160, all upper", + /* + * EHT: | | | | | | | | | | | | | | | | | + * HE: | | | | | + * used: | | | | | | | | | + */ + + .ap.width = NL80211_CHAN_WIDTH_320, + .ap.chan = &chan6g_61, + .ap.center_freq1 = 6105, + + .used.width = NL80211_CHAN_WIDTH_160, + .used.chan = &chan6g_61, + .used.center_freq1 = 6185, + + .psd.valid = true, + .psd.count = 16, + .psd.n = 4, + .psd.power = { 0, 1, 2, 3, 4, 5, 6, 7, 8, 9, 10, 11, 12, 13, 14, 15 }, + + .out.valid = true, + .out.count = 8, + .out.n = 4, + .out.power = { 12, 13, 14, 15, 0, 1, 2, 3, 127, 127, 127, 127, 127, 127, 127, 127}, + }, + { + .desc = "320 MHz, HE is 80, used 160, split", + /* + * EHT: | | | | | | | | | | | | | | | | | + * HE: | | | | | + * used: | | | | | | | | | + */ + + .ap.width = NL80211_CHAN_WIDTH_320, + .ap.chan = &chan6g_33, + .ap.center_freq1 = 6105, + + .used.width = NL80211_CHAN_WIDTH_160, + .used.chan = &chan6g_33, + .used.center_freq1 = 6185, + + .psd.valid = true, + .psd.count = 16, + .psd.n = 4, + .psd.power = { 0, 1, 2, 3, 4, 5, 6, 7, 8, 9, 10, 11, 12, 13, 14, 15 }, + + .out.valid = true, + .out.count = 8, + .out.n = 4, + .out.power = { 0, 1, 2, 3, 12, 13, 14, 15, 127, 127, 127, 127, 127, 127, 127, 127}, + }, +}; + +KUNIT_ARRAY_PARAM_DESC(psd_reorder, psd_reorder_cases, desc); + +static void psd_reorder(struct kunit *test) +{ + const struct psd_reorder_test_case *params = test->param_value; + struct ieee80211_parsed_tpe_psd tmp = params->psd; + + KUNIT_ASSERT_EQ(test, cfg80211_chandef_valid(¶ms->ap), true); + KUNIT_ASSERT_EQ(test, cfg80211_chandef_valid(¶ms->used), true); + + ieee80211_rearrange_tpe_psd(&tmp, ¶ms->ap, ¶ms->used); + KUNIT_EXPECT_MEMEQ(test, &tmp, ¶ms->out, sizeof(tmp)); +} + +static struct kunit_case tpe_test_cases[] = { + KUNIT_CASE_PARAM(subchan_offset, subchan_offset_gen_params), + KUNIT_CASE_PARAM(psd_reorder, psd_reorder_gen_params), + {} +}; + +static struct kunit_suite tpe = { + .name = "mac80211-tpe", + .test_cases = tpe_test_cases, +}; + +kunit_test_suite(tpe); diff --git a/net/mac80211/trace.h b/net/mac80211/trace.h index b26aacfbc622..dc498cd8cd91 100644 --- a/net/mac80211/trace.h +++ b/net/mac80211/trace.h @@ -328,9 +328,18 @@ TRACE_EVENT(drv_set_wakeup, TP_printk(LOCAL_PR_FMT " enabled:%d", LOCAL_PR_ARG, __entry->enabled) ); -DEFINE_EVENT(local_only_evt, drv_stop, - TP_PROTO(struct ieee80211_local *local), - TP_ARGS(local) +TRACE_EVENT(drv_stop, + TP_PROTO(struct ieee80211_local *local, bool suspend), + TP_ARGS(local, suspend), + TP_STRUCT__entry( + LOCAL_ENTRY + __field(bool, suspend) + ), + TP_fast_assign( + LOCAL_ASSIGN; + __entry->suspend = suspend; + ), + TP_printk(LOCAL_PR_FMT " suspend:%d", LOCAL_PR_ARG, __entry->suspend) ); DEFINE_EVENT(local_sdata_addr_evt, drv_add_interface, diff --git a/net/mac80211/tx.c b/net/mac80211/tx.c index f861d99e5f05..a9ee86982259 100644 --- a/net/mac80211/tx.c +++ b/net/mac80211/tx.c @@ -699,7 +699,7 @@ ieee80211_tx_h_rate_ctrl(struct ieee80211_tx_data *tx) txrc.skb = tx->skb; txrc.reported_rate.idx = -1; - if (unlikely(info->control.flags & IEEE80211_TX_CTRL_SCAN_TX)) { + if (unlikely(info->control.flags & IEEE80211_TX_CTRL_DONT_USE_RATE_MASK)) { txrc.rate_idx_mask = ~0; } else { txrc.rate_idx_mask = tx->sdata->rc_rateidx_mask[info->band]; @@ -1768,7 +1768,7 @@ static bool __ieee80211_tx(struct ieee80211_local *local, break; } sdata = rcu_dereference(local->monitor_sdata); - if (sdata) { + if (sdata && ieee80211_hw_check(&local->hw, WANT_MONITOR_VIF)) { vif = &sdata->vif; info->hw_queue = vif->hw_queue[skb_get_queue_mapping(skb)]; @@ -2774,8 +2774,7 @@ static struct sk_buff *ieee80211_build_hdr(struct ieee80211_sub_if_data *sdata, if (tdls_peer) { /* For TDLS only one link can be valid with peer STA */ - int tdls_link_id = sta->sta.valid_links ? - __ffs(sta->sta.valid_links) : 0; + int tdls_link_id = ieee80211_tdls_sta_link_id(sta); struct ieee80211_link_data *link; /* DA SA BSSID */ @@ -3101,8 +3100,7 @@ void ieee80211_check_fast_xmit(struct sta_info *sta) case NL80211_IFTYPE_STATION: if (test_sta_flag(sta, WLAN_STA_TDLS_PEER)) { /* For TDLS only one link can be valid with peer STA */ - int tdls_link_id = sta->sta.valid_links ? - __ffs(sta->sta.valid_links) : 0; + int tdls_link_id = ieee80211_tdls_sta_link_id(sta); struct ieee80211_link_data *link; /* DA SA BSSID */ @@ -3959,7 +3957,8 @@ begin: break; } tx.sdata = rcu_dereference(local->monitor_sdata); - if (tx.sdata) { + if (tx.sdata && + ieee80211_hw_check(&local->hw, WANT_MONITOR_VIF)) { vif = &tx.sdata->vif; info->hw_queue = vif->hw_queue[skb_get_queue_mapping(skb)]; @@ -5349,8 +5348,10 @@ ieee80211_beacon_get_ap(struct ieee80211_hw *hw, if (beacon->tail) skb_put_data(skb, beacon->tail, beacon->tail_len); - if (ieee80211_beacon_protect(skb, local, sdata, link) < 0) + if (ieee80211_beacon_protect(skb, local, sdata, link) < 0) { + dev_kfree_skb(skb); return NULL; + } ieee80211_beacon_get_finish(hw, vif, link, offs, beacon, skb, chanctx_conf, csa_off_base); diff --git a/net/mac80211/util.c b/net/mac80211/util.c index 963ed75deb76..f94faa86ba8a 100644 --- a/net/mac80211/util.c +++ b/net/mac80211/util.c @@ -751,7 +751,9 @@ static void __iterate_interfaces(struct ieee80211_local *local, struct ieee80211_sub_if_data *sdata; bool active_only = iter_flags & IEEE80211_IFACE_ITER_ACTIVE; - list_for_each_entry_rcu(sdata, &local->interfaces, list) { + list_for_each_entry_rcu(sdata, &local->interfaces, list, + lockdep_is_held(&local->iflist_mtx) || + lockdep_is_held(&local->hw.wiphy->mtx)) { switch (sdata->vif.type) { case NL80211_IFTYPE_MONITOR: if (!(sdata->u.mntr.flags & MONITOR_FLAG_ACTIVE)) @@ -776,7 +778,7 @@ static void __iterate_interfaces(struct ieee80211_local *local, sdata = rcu_dereference_check(local->monitor_sdata, lockdep_is_held(&local->iflist_mtx) || lockdep_is_held(&local->hw.wiphy->mtx)); - if (sdata && + if (sdata && ieee80211_hw_check(&local->hw, WANT_MONITOR_VIF) && (iter_flags & IEEE80211_IFACE_ITER_RESUME_ALL || !active_only || sdata->flags & IEEE80211_SDATA_IN_DRIVER)) iterator(data, sdata->vif.addr, &sdata->vif); @@ -833,7 +835,8 @@ static void __iterate_stations(struct ieee80211_local *local, { struct sta_info *sta; - list_for_each_entry_rcu(sta, &local->sta_list, list) { + list_for_each_entry_rcu(sta, &local->sta_list, list, + lockdep_is_held(&local->hw.wiphy->mtx)) { if (!sta->uploaded) continue; @@ -854,6 +857,19 @@ void ieee80211_iterate_stations_atomic(struct ieee80211_hw *hw, } EXPORT_SYMBOL_GPL(ieee80211_iterate_stations_atomic); +void ieee80211_iterate_stations_mtx(struct ieee80211_hw *hw, + void (*iterator)(void *data, + struct ieee80211_sta *sta), + void *data) +{ + struct ieee80211_local *local = hw_to_local(hw); + + lockdep_assert_wiphy(local->hw.wiphy); + + __iterate_stations(local, iterator, data); +} +EXPORT_SYMBOL_GPL(ieee80211_iterate_stations_mtx); + struct ieee80211_vif *wdev_to_ieee80211_vif(struct wireless_dev *wdev) { struct ieee80211_sub_if_data *sdata = IEEE80211_WDEV_TO_SUB_IF(wdev); @@ -1565,9 +1581,11 @@ u32 ieee80211_sta_get_rates(struct ieee80211_sub_if_data *sdata, return supp_rates; } -void ieee80211_stop_device(struct ieee80211_local *local) +void ieee80211_stop_device(struct ieee80211_local *local, bool suspend) { + local_bh_disable(); ieee80211_handle_queued_frames(local); + local_bh_enable(); ieee80211_led_radio(local, false); ieee80211_mod_tpt_led_trig(local, 0, IEEE80211_TPT_LEDTRIG_FL_RADIO); @@ -1576,7 +1594,7 @@ void ieee80211_stop_device(struct ieee80211_local *local) flush_workqueue(local->workqueue); wiphy_work_flush(local->hw.wiphy, NULL); - drv_stop(local); + drv_stop(local, suspend); } static void ieee80211_flush_completed_scan(struct ieee80211_local *local, @@ -2177,8 +2195,7 @@ int ieee80211_reconfig(struct ieee80211_local *local) local->in_reconfig = false; barrier(); - /* Restart deferred ROCs */ - ieee80211_start_next_roc(local); + ieee80211_reconfig_roc(local); /* Requeue all works */ list_for_each_entry(sdata, &local->interfaces, list) @@ -2335,7 +2352,7 @@ void ieee80211_recalc_min_chandef(struct ieee80211_sub_if_data *sdata, chanctx = container_of(chanctx_conf, struct ieee80211_chanctx, conf); - ieee80211_recalc_chanctx_min_def(local, chanctx, NULL); + ieee80211_recalc_chanctx_min_def(local, chanctx, NULL, false); } } @@ -3450,28 +3467,44 @@ u64 ieee80211_calculate_rx_timestamp(struct ieee80211_local *local, return ts; } -void ieee80211_dfs_cac_cancel(struct ieee80211_local *local) +/* Cancel CAC for the interfaces under the specified @local. If @ctx is + * also provided, only the interfaces using that ctx will be canceled. + */ +void ieee80211_dfs_cac_cancel(struct ieee80211_local *local, + struct ieee80211_chanctx *ctx) { struct ieee80211_sub_if_data *sdata; struct cfg80211_chan_def chandef; + struct ieee80211_link_data *link; + struct ieee80211_chanctx_conf *chanctx_conf; + unsigned int link_id; lockdep_assert_wiphy(local->hw.wiphy); list_for_each_entry(sdata, &local->interfaces, list) { - /* it might be waiting for the local->mtx, but then - * by the time it gets it, sdata->wdev.cac_started - * will no longer be true - */ - wiphy_delayed_work_cancel(local->hw.wiphy, - &sdata->deflink.dfs_cac_timer_work); - - if (sdata->wdev.cac_started) { - chandef = sdata->vif.bss_conf.chanreq.oper; - ieee80211_link_release_channel(&sdata->deflink); - cfg80211_cac_event(sdata->dev, - &chandef, + for (link_id = 0; link_id < IEEE80211_MLD_MAX_NUM_LINKS; + link_id++) { + link = sdata_dereference(sdata->link[link_id], + sdata); + if (!link) + continue; + + chanctx_conf = sdata_dereference(link->conf->chanctx_conf, + sdata); + if (ctx && &ctx->conf != chanctx_conf) + continue; + + wiphy_delayed_work_cancel(local->hw.wiphy, + &link->dfs_cac_timer_work); + + if (!sdata->wdev.links[link_id].cac_started) + continue; + + chandef = link->conf->chanreq.oper; + ieee80211_link_release_channel(link); + cfg80211_cac_event(sdata->dev, &chandef, NL80211_RADAR_CAC_ABORTED, - GFP_KERNEL); + GFP_KERNEL, link_id); } } } @@ -3481,9 +3514,8 @@ void ieee80211_dfs_radar_detected_work(struct wiphy *wiphy, { struct ieee80211_local *local = container_of(work, struct ieee80211_local, radar_detected_work); - struct cfg80211_chan_def chandef = local->hw.conf.chandef; + struct cfg80211_chan_def chandef; struct ieee80211_chanctx *ctx; - int num_chanctx = 0; lockdep_assert_wiphy(local->hw.wiphy); @@ -3491,25 +3523,46 @@ void ieee80211_dfs_radar_detected_work(struct wiphy *wiphy, if (ctx->replace_state == IEEE80211_CHANCTX_REPLACES_OTHER) continue; - num_chanctx++; + if (!ctx->radar_detected) + continue; + + ctx->radar_detected = false; + chandef = ctx->conf.def; + + ieee80211_dfs_cac_cancel(local, ctx); + cfg80211_radar_event(local->hw.wiphy, &chandef, GFP_KERNEL); } +} - ieee80211_dfs_cac_cancel(local); +static void +ieee80211_radar_mark_chan_ctx_iterator(struct ieee80211_hw *hw, + struct ieee80211_chanctx_conf *chanctx_conf, + void *data) +{ + struct ieee80211_chanctx *ctx = + container_of(chanctx_conf, struct ieee80211_chanctx, + conf); - if (num_chanctx > 1) - /* XXX: multi-channel is not supported yet */ - WARN_ON(1); - else - cfg80211_radar_event(local->hw.wiphy, &chandef, GFP_KERNEL); + if (ctx->replace_state == IEEE80211_CHANCTX_REPLACES_OTHER) + return; + + if (data && data != chanctx_conf) + return; + + ctx->radar_detected = true; } -void ieee80211_radar_detected(struct ieee80211_hw *hw) +void ieee80211_radar_detected(struct ieee80211_hw *hw, + struct ieee80211_chanctx_conf *chanctx_conf) { struct ieee80211_local *local = hw_to_local(hw); trace_api_radar_detected(local); + ieee80211_iter_chan_contexts_atomic(hw, ieee80211_radar_mark_chan_ctx_iterator, + chanctx_conf); + wiphy_work_queue(hw->wiphy, &local->radar_detected_work); } EXPORT_SYMBOL(ieee80211_radar_detected); @@ -3935,19 +3988,103 @@ static u8 ieee80211_chanctx_radar_detect(struct ieee80211_local *local, return radar_detect; } +static u32 +__ieee80211_get_radio_mask(struct ieee80211_sub_if_data *sdata) +{ + struct ieee80211_bss_conf *link_conf; + struct ieee80211_chanctx_conf *conf; + unsigned int link_id; + u32 mask = 0; + + for_each_vif_active_link(&sdata->vif, link_conf, link_id) { + conf = sdata_dereference(link_conf->chanctx_conf, sdata); + if (!conf || conf->radio_idx < 0) + continue; + + mask |= BIT(conf->radio_idx); + } + + return mask; +} + +u32 ieee80211_get_radio_mask(struct wiphy *wiphy, struct net_device *dev) +{ + struct ieee80211_sub_if_data *sdata = IEEE80211_DEV_TO_SUB_IF(dev); + + return __ieee80211_get_radio_mask(sdata); +} + +static bool +ieee80211_sdata_uses_radio(struct ieee80211_sub_if_data *sdata, int radio_idx) +{ + if (radio_idx < 0) + return true; + + return __ieee80211_get_radio_mask(sdata) & BIT(radio_idx); +} + +static int +ieee80211_fill_ifcomb_params(struct ieee80211_local *local, + struct iface_combination_params *params, + const struct cfg80211_chan_def *chandef, + struct ieee80211_sub_if_data *sdata) +{ + struct ieee80211_sub_if_data *sdata_iter; + struct ieee80211_chanctx *ctx; + int total = !!sdata; + + list_for_each_entry(ctx, &local->chanctx_list, list) { + if (ctx->replace_state == IEEE80211_CHANCTX_WILL_BE_REPLACED) + continue; + + if (params->radio_idx >= 0 && + ctx->conf.radio_idx != params->radio_idx) + continue; + + params->radar_detect |= + ieee80211_chanctx_radar_detect(local, ctx); + + if (chandef && ctx->mode != IEEE80211_CHANCTX_EXCLUSIVE && + cfg80211_chandef_compatible(chandef, &ctx->conf.def)) + continue; + + params->num_different_channels++; + } + + list_for_each_entry(sdata_iter, &local->interfaces, list) { + struct wireless_dev *wdev_iter; + + wdev_iter = &sdata_iter->wdev; + + if (sdata_iter == sdata || + !ieee80211_sdata_running(sdata_iter) || + cfg80211_iftype_allowed(local->hw.wiphy, + wdev_iter->iftype, 0, 1)) + continue; + + if (!ieee80211_sdata_uses_radio(sdata_iter, params->radio_idx)) + continue; + + params->iftype_num[wdev_iter->iftype]++; + total++; + } + + return total; +} + int ieee80211_check_combinations(struct ieee80211_sub_if_data *sdata, const struct cfg80211_chan_def *chandef, enum ieee80211_chanctx_mode chanmode, - u8 radar_detect) + u8 radar_detect, int radio_idx) { + bool shared = chanmode == IEEE80211_CHANCTX_SHARED; struct ieee80211_local *local = sdata->local; - struct ieee80211_sub_if_data *sdata_iter; enum nl80211_iftype iftype = sdata->wdev.iftype; - struct ieee80211_chanctx *ctx; - int total = 1; struct iface_combination_params params = { .radar_detect = radar_detect, + .radio_idx = radio_idx, }; + int total; lockdep_assert_wiphy(local->hw.wiphy); @@ -3984,37 +4121,9 @@ int ieee80211_check_combinations(struct ieee80211_sub_if_data *sdata, if (iftype != NL80211_IFTYPE_UNSPECIFIED) params.iftype_num[iftype] = 1; - list_for_each_entry(ctx, &local->chanctx_list, list) { - if (ctx->replace_state == IEEE80211_CHANCTX_WILL_BE_REPLACED) - continue; - params.radar_detect |= - ieee80211_chanctx_radar_detect(local, ctx); - if (ctx->mode == IEEE80211_CHANCTX_EXCLUSIVE) { - params.num_different_channels++; - continue; - } - if (chandef && chanmode == IEEE80211_CHANCTX_SHARED && - cfg80211_chandef_compatible(chandef, - &ctx->conf.def)) - continue; - params.num_different_channels++; - } - - list_for_each_entry_rcu(sdata_iter, &local->interfaces, list) { - struct wireless_dev *wdev_iter; - - wdev_iter = &sdata_iter->wdev; - - if (sdata_iter == sdata || - !ieee80211_sdata_running(sdata_iter) || - cfg80211_iftype_allowed(local->hw.wiphy, - wdev_iter->iftype, 0, 1)) - continue; - - params.iftype_num[wdev_iter->iftype]++; - total++; - } - + total = ieee80211_fill_ifcomb_params(local, ¶ms, + shared ? chandef : NULL, + sdata); if (total == 1 && !params.radar_detect) return 0; @@ -4031,28 +4140,17 @@ ieee80211_iter_max_chans(const struct ieee80211_iface_combination *c, c->num_different_channels); } -int ieee80211_max_num_channels(struct ieee80211_local *local) +int ieee80211_max_num_channels(struct ieee80211_local *local, int radio_idx) { - struct ieee80211_sub_if_data *sdata; - struct ieee80211_chanctx *ctx; u32 max_num_different_channels = 1; int err; - struct iface_combination_params params = {0}; + struct iface_combination_params params = { + .radio_idx = radio_idx, + }; lockdep_assert_wiphy(local->hw.wiphy); - list_for_each_entry(ctx, &local->chanctx_list, list) { - if (ctx->replace_state == IEEE80211_CHANCTX_WILL_BE_REPLACED) - continue; - - params.num_different_channels++; - - params.radar_detect |= - ieee80211_chanctx_radar_detect(local, ctx); - } - - list_for_each_entry_rcu(sdata, &local->interfaces, list) - params.iftype_num[sdata->wdev.iftype]++; + ieee80211_fill_ifcomb_params(local, ¶ms, NULL, NULL); err = cfg80211_iter_combinations(local->hw.wiphy, ¶ms, ieee80211_iter_max_chans, @@ -4340,3 +4438,28 @@ ieee80211_min_bw_limit_from_chandef(struct cfg80211_chan_def *chandef) return IEEE80211_CONN_BW_LIMIT_20; } } + +void ieee80211_clear_tpe(struct ieee80211_parsed_tpe *tpe) +{ + for (int i = 0; i < 2; i++) { + tpe->max_local[i].valid = false; + memset(tpe->max_local[i].power, + IEEE80211_TPE_MAX_TX_PWR_NO_CONSTRAINT, + sizeof(tpe->max_local[i].power)); + + tpe->max_reg_client[i].valid = false; + memset(tpe->max_reg_client[i].power, + IEEE80211_TPE_MAX_TX_PWR_NO_CONSTRAINT, + sizeof(tpe->max_reg_client[i].power)); + + tpe->psd_local[i].valid = false; + memset(tpe->psd_local[i].power, + IEEE80211_TPE_PSD_NO_LIMIT, + sizeof(tpe->psd_local[i].power)); + + tpe->psd_reg_client[i].valid = false; + memset(tpe->psd_reg_client[i].power, + IEEE80211_TPE_PSD_NO_LIMIT, + sizeof(tpe->psd_reg_client[i].power)); + } +} diff --git a/net/mac80211/vht.c b/net/mac80211/vht.c index 642891cafbaf..bf6ef45af757 100644 --- a/net/mac80211/vht.c +++ b/net/mac80211/vht.c @@ -351,7 +351,8 @@ ieee80211_vht_cap_ie_to_sta_vht_cap(struct ieee80211_sub_if_data *sdata, /* FIXME: move this to some better location - parses HE/EHT now */ enum ieee80211_sta_rx_bandwidth -ieee80211_sta_cap_rx_bw(struct link_sta_info *link_sta) +_ieee80211_sta_cap_rx_bw(struct link_sta_info *link_sta, + struct cfg80211_chan_def *chandef) { unsigned int link_id = link_sta->link_id; struct ieee80211_sub_if_data *sdata = link_sta->sta->sdata; @@ -361,44 +362,43 @@ ieee80211_sta_cap_rx_bw(struct link_sta_info *link_sta) u32 cap_width; if (he_cap->has_he) { - struct ieee80211_bss_conf *link_conf; - enum ieee80211_sta_rx_bandwidth ret; + enum nl80211_band band; u8 info; - rcu_read_lock(); - link_conf = rcu_dereference(sdata->vif.link_conf[link_id]); + if (chandef) { + band = chandef->chan->band; + } else { + struct ieee80211_bss_conf *link_conf; + + rcu_read_lock(); + link_conf = rcu_dereference(sdata->vif.link_conf[link_id]); + band = link_conf->chanreq.oper.chan->band; + rcu_read_unlock(); + } - if (eht_cap->has_eht && - link_conf->chanreq.oper.chan->band == NL80211_BAND_6GHZ) { + if (eht_cap->has_eht && band == NL80211_BAND_6GHZ) { info = eht_cap->eht_cap_elem.phy_cap_info[0]; - if (info & IEEE80211_EHT_PHY_CAP0_320MHZ_IN_6GHZ) { - ret = IEEE80211_STA_RX_BW_320; - goto out; - } + if (info & IEEE80211_EHT_PHY_CAP0_320MHZ_IN_6GHZ) + return IEEE80211_STA_RX_BW_320; } info = he_cap->he_cap_elem.phy_cap_info[0]; - if (link_conf->chanreq.oper.chan->band == NL80211_BAND_2GHZ) { + if (band == NL80211_BAND_2GHZ) { if (info & IEEE80211_HE_PHY_CAP0_CHANNEL_WIDTH_SET_40MHZ_IN_2G) - ret = IEEE80211_STA_RX_BW_40; - else - ret = IEEE80211_STA_RX_BW_20; - goto out; + return IEEE80211_STA_RX_BW_40; + return IEEE80211_STA_RX_BW_20; } if (info & IEEE80211_HE_PHY_CAP0_CHANNEL_WIDTH_SET_160MHZ_IN_5G || info & IEEE80211_HE_PHY_CAP0_CHANNEL_WIDTH_SET_80PLUS80_MHZ_IN_5G) - ret = IEEE80211_STA_RX_BW_160; - else if (info & IEEE80211_HE_PHY_CAP0_CHANNEL_WIDTH_SET_40MHZ_80MHZ_IN_5G) - ret = IEEE80211_STA_RX_BW_80; - else - ret = IEEE80211_STA_RX_BW_20; -out: - rcu_read_unlock(); + return IEEE80211_STA_RX_BW_160; - return ret; + if (info & IEEE80211_HE_PHY_CAP0_CHANNEL_WIDTH_SET_40MHZ_80MHZ_IN_5G) + return IEEE80211_STA_RX_BW_80; + + return IEEE80211_STA_RX_BW_20; } if (!vht_cap->vht_supported) @@ -503,22 +503,29 @@ ieee80211_chan_width_to_rx_bw(enum nl80211_chan_width width) /* FIXME: rename/move - this deals with everything not just VHT */ enum ieee80211_sta_rx_bandwidth -ieee80211_sta_cur_vht_bw(struct link_sta_info *link_sta) +_ieee80211_sta_cur_vht_bw(struct link_sta_info *link_sta, + struct cfg80211_chan_def *chandef) { struct sta_info *sta = link_sta->sta; - struct ieee80211_bss_conf *link_conf; enum nl80211_chan_width bss_width; enum ieee80211_sta_rx_bandwidth bw; - rcu_read_lock(); - link_conf = rcu_dereference(sta->sdata->vif.link_conf[link_sta->link_id]); - if (WARN_ON(!link_conf)) - bss_width = NL80211_CHAN_WIDTH_20_NOHT; - else + if (chandef) { + bss_width = chandef->width; + } else { + struct ieee80211_bss_conf *link_conf; + + rcu_read_lock(); + link_conf = rcu_dereference(sta->sdata->vif.link_conf[link_sta->link_id]); + if (WARN_ON_ONCE(!link_conf)) { + rcu_read_unlock(); + return IEEE80211_STA_RX_BW_20; + } bss_width = link_conf->chanreq.oper.width; - rcu_read_unlock(); + rcu_read_unlock(); + } - bw = ieee80211_sta_cap_rx_bw(link_sta); + bw = _ieee80211_sta_cap_rx_bw(link_sta, chandef); bw = min(bw, link_sta->cur_max_bandwidth); /* Don't consider AP's bandwidth for TDLS peers, section 11.23.1 of diff --git a/net/mac802154/main.c b/net/mac802154/main.c index 9ab7396668d2..21b7c3b280b4 100644 --- a/net/mac802154/main.c +++ b/net/mac802154/main.c @@ -161,8 +161,10 @@ void ieee802154_configure_durations(struct wpan_phy *phy, } phy->symbol_duration = duration; - phy->lifs_period = (IEEE802154_LIFS_PERIOD * phy->symbol_duration) / NSEC_PER_SEC; - phy->sifs_period = (IEEE802154_SIFS_PERIOD * phy->symbol_duration) / NSEC_PER_SEC; + phy->lifs_period = + (IEEE802154_LIFS_PERIOD * phy->symbol_duration) / NSEC_PER_USEC; + phy->sifs_period = + (IEEE802154_SIFS_PERIOD * phy->symbol_duration) / NSEC_PER_USEC; } EXPORT_SYMBOL(ieee802154_configure_durations); @@ -184,10 +186,10 @@ static void ieee802154_setup_wpan_phy_pib(struct wpan_phy *wpan_phy) * Should be done when all drivers sets this value. */ - wpan_phy->lifs_period = - (IEEE802154_LIFS_PERIOD * wpan_phy->symbol_duration) / 1000; - wpan_phy->sifs_period = - (IEEE802154_SIFS_PERIOD * wpan_phy->symbol_duration) / 1000; + wpan_phy->lifs_period = (IEEE802154_LIFS_PERIOD * + wpan_phy->symbol_duration) / NSEC_PER_USEC; + wpan_phy->sifs_period = (IEEE802154_SIFS_PERIOD * + wpan_phy->symbol_duration) / NSEC_PER_USEC; } int ieee802154_register_hw(struct ieee802154_hw *hw) diff --git a/net/mac802154/tx.c b/net/mac802154/tx.c index 2a6f1ed763c9..6fbed5bb5c3e 100644 --- a/net/mac802154/tx.c +++ b/net/mac802154/tx.c @@ -34,8 +34,8 @@ void ieee802154_xmit_sync_worker(struct work_struct *work) if (res) goto err_tx; - dev->stats.tx_packets++; - dev->stats.tx_bytes += skb->len; + DEV_STATS_INC(dev, tx_packets); + DEV_STATS_ADD(dev, tx_bytes, skb->len); ieee802154_xmit_complete(&local->hw, skb, false); @@ -90,8 +90,8 @@ ieee802154_tx(struct ieee802154_local *local, struct sk_buff *skb) if (ret) goto err_wake_netif_queue; - dev->stats.tx_packets++; - dev->stats.tx_bytes += len; + DEV_STATS_INC(dev, tx_packets); + DEV_STATS_ADD(dev, tx_bytes, len); } else { local->tx_skb = skb; queue_work(local->workqueue, &local->sync_tx_work); diff --git a/net/mctp/af_mctp.c b/net/mctp/af_mctp.c index de52a9191da0..43288b408fde 100644 --- a/net/mctp/af_mctp.c +++ b/net/mctp/af_mctp.c @@ -486,6 +486,9 @@ static int mctp_ioctl_droptag(struct mctp_sock *msk, bool tagv2, tag = ctl.tag & MCTP_TAG_MASK; rc = -EINVAL; + if (ctl.peer_addr == MCTP_ADDR_NULL) + ctl.peer_addr = MCTP_ADDR_ANY; + spin_lock_irqsave(&net->mctp.keys_lock, flags); hlist_for_each_entry_safe(key, tmp, &msk->keys, sklist) { /* we do an irqsave here, even though we know the irq state, diff --git a/net/mctp/test/route-test.c b/net/mctp/test/route-test.c index 77e5dd422258..8551dab1d1e6 100644 --- a/net/mctp/test/route-test.c +++ b/net/mctp/test/route-test.c @@ -366,7 +366,7 @@ static void mctp_test_route_input_sk(struct kunit *test) skb2 = skb_recv_datagram(sock->sk, MSG_DONTWAIT, &rc); KUNIT_EXPECT_NOT_ERR_OR_NULL(test, skb2); - KUNIT_EXPECT_EQ(test, skb->len, 1); + KUNIT_EXPECT_EQ(test, skb2->len, 1); skb_free_datagram(sock->sk, skb2); diff --git a/net/mpls/af_mpls.c b/net/mpls/af_mpls.c index 2dc7a908a6bb..aba983531ed3 100644 --- a/net/mpls/af_mpls.c +++ b/net/mpls/af_mpls.c @@ -1201,8 +1201,7 @@ static void mpls_netconf_notify_devconf(struct net *net, int event, rtnl_notify(skb, net, 0, RTNLGRP_MPLS_NETCONF, NULL, GFP_KERNEL); return; errout: - if (err < 0) - rtnl_set_sk_err(net, RTNLGRP_MPLS_NETCONF, err); + rtnl_set_sk_err(net, RTNLGRP_MPLS_NETCONF, err); } static const struct nla_policy devconf_mpls_policy[NETCONFA_MAX + 1] = { @@ -1347,7 +1346,7 @@ static int mpls_netconf_dump_devconf(struct sk_buff *skb, #define MPLS_PERDEV_SYSCTL_OFFSET(field) \ (&((struct mpls_dev *)0)->field) -static int mpls_conf_proc(struct ctl_table *ctl, int write, +static int mpls_conf_proc(const struct ctl_table *ctl, int write, void *buffer, size_t *lenp, loff_t *ppos) { int oval = *(int *)ctl->data; @@ -2278,8 +2277,7 @@ static void rtmsg_lfib(int event, u32 label, struct mpls_route *rt, return; errout: - if (err < 0) - rtnl_set_sk_err(net, RTNLGRP_MPLS_ROUTE, err); + rtnl_set_sk_err(net, RTNLGRP_MPLS_ROUTE, err); } static int mpls_valid_getroute_req(struct sk_buff *skb, @@ -2600,7 +2598,7 @@ nolabels: return -ENOMEM; } -static int mpls_platform_labels(struct ctl_table *table, int write, +static int mpls_platform_labels(const struct ctl_table *table, int write, void *buffer, size_t *lenp, loff_t *ppos) { struct net *net = table->data; diff --git a/net/mpls/mpls_iptunnel.c b/net/mpls/mpls_iptunnel.c index 4385fd3b13be..6e73da94af7f 100644 --- a/net/mpls/mpls_iptunnel.c +++ b/net/mpls/mpls_iptunnel.c @@ -106,7 +106,7 @@ static int mpls_xmit(struct sk_buff *skb) hh_len = 0; /* Ensure there is enough space for the headers in the skb */ - if (skb_cow(skb, hh_len + new_header_size)) + if (skb_cow_head(skb, hh_len + new_header_size)) goto drop; skb_set_inner_protocol(skb, skb->protocol); diff --git a/net/mptcp/ctrl.c b/net/mptcp/ctrl.c index 98b1dd498ff6..38d8121331d4 100644 --- a/net/mptcp/ctrl.c +++ b/net/mptcp/ctrl.c @@ -12,6 +12,7 @@ #include <net/netns/generic.h> #include "protocol.h" +#include "mib.h" #define MPTCP_SYSCTL_PATH "net/mptcp" @@ -27,8 +28,11 @@ struct mptcp_pernet { #endif unsigned int add_addr_timeout; + unsigned int blackhole_timeout; unsigned int close_timeout; unsigned int stale_loss_cnt; + atomic_t active_disable_times; + unsigned long active_disable_stamp; u8 mptcp_enabled; u8 checksum_enabled; u8 allow_join_initial_addr_port; @@ -87,6 +91,8 @@ static void mptcp_pernet_set_defaults(struct mptcp_pernet *pernet) { pernet->mptcp_enabled = 1; pernet->add_addr_timeout = TCP_RTO_MAX; + pernet->blackhole_timeout = 3600; + atomic_set(&pernet->active_disable_times, 0); pernet->close_timeout = TCP_TIMEWAIT_LEN; pernet->checksum_enabled = 0; pernet->allow_join_initial_addr_port = 1; @@ -113,7 +119,7 @@ static int mptcp_set_scheduler(const struct net *net, const char *name) return ret; } -static int proc_scheduler(struct ctl_table *ctl, int write, +static int proc_scheduler(const struct ctl_table *ctl, int write, void *buffer, size_t *lenp, loff_t *ppos) { const struct net *net = current->nsproxy->net_ns; @@ -133,7 +139,7 @@ static int proc_scheduler(struct ctl_table *ctl, int write, return ret; } -static int proc_available_schedulers(struct ctl_table *ctl, +static int proc_available_schedulers(const struct ctl_table *ctl, int write, void *buffer, size_t *lenp, loff_t *ppos) { @@ -151,6 +157,20 @@ static int proc_available_schedulers(struct ctl_table *ctl, return ret; } +static int proc_blackhole_detect_timeout(const struct ctl_table *table, + int write, void *buffer, size_t *lenp, + loff_t *ppos) +{ + struct mptcp_pernet *pernet = mptcp_get_pernet(current->nsproxy->net_ns); + int ret; + + ret = proc_dointvec_minmax(table, write, buffer, lenp, ppos); + if (write && ret == 0) + atomic_set(&pernet->active_disable_times, 0); + + return ret; +} + static struct ctl_table mptcp_sysctl_table[] = { { .procname = "enabled", @@ -217,6 +237,13 @@ static struct ctl_table mptcp_sysctl_table[] = { .mode = 0644, .proc_handler = proc_dointvec_jiffies, }, + { + .procname = "blackhole_timeout", + .maxlen = sizeof(unsigned int), + .mode = 0644, + .proc_handler = proc_blackhole_detect_timeout, + .extra1 = SYSCTL_ZERO, + }, }; static int mptcp_pernet_new_table(struct net *net, struct mptcp_pernet *pernet) @@ -240,6 +267,7 @@ static int mptcp_pernet_new_table(struct net *net, struct mptcp_pernet *pernet) table[6].data = &pernet->scheduler; /* table[7] is for available_schedulers which is read-only info */ table[8].data = &pernet->close_timeout; + table[9].data = &pernet->blackhole_timeout; hdr = register_net_sysctl_sz(net, MPTCP_SYSCTL_PATH, table, ARRAY_SIZE(mptcp_sysctl_table)); @@ -277,6 +305,111 @@ static void mptcp_pernet_del_table(struct mptcp_pernet *pernet) {} #endif /* CONFIG_SYSCTL */ +/* The following code block is to deal with middle box issues with MPTCP, + * similar to what is done with TFO. + * The proposed solution is to disable active MPTCP globally when SYN+MPC are + * dropped, while SYN without MPC aren't. In this case, active side MPTCP is + * disabled globally for 1hr at first. Then if it happens again, it is disabled + * for 2h, then 4h, 8h, ... + * The timeout is reset back to 1hr when a successful active MPTCP connection is + * fully established. + */ + +/* Disable active MPTCP and record current jiffies and active_disable_times */ +void mptcp_active_disable(struct sock *sk) +{ + struct net *net = sock_net(sk); + struct mptcp_pernet *pernet; + + pernet = mptcp_get_pernet(net); + + if (!READ_ONCE(pernet->blackhole_timeout)) + return; + + /* Paired with READ_ONCE() in mptcp_active_should_disable() */ + WRITE_ONCE(pernet->active_disable_stamp, jiffies); + + /* Paired with smp_rmb() in mptcp_active_should_disable(). + * We want pernet->active_disable_stamp to be updated first. + */ + smp_mb__before_atomic(); + atomic_inc(&pernet->active_disable_times); + + MPTCP_INC_STATS(net, MPTCP_MIB_BLACKHOLE); +} + +/* Calculate timeout for MPTCP active disable + * Return true if we are still in the active MPTCP disable period + * Return false if timeout already expired and we should use active MPTCP + */ +bool mptcp_active_should_disable(struct sock *ssk) +{ + struct net *net = sock_net(ssk); + unsigned int blackhole_timeout; + struct mptcp_pernet *pernet; + unsigned long timeout; + int disable_times; + int multiplier; + + pernet = mptcp_get_pernet(net); + blackhole_timeout = READ_ONCE(pernet->blackhole_timeout); + + if (!blackhole_timeout) + return false; + + disable_times = atomic_read(&pernet->active_disable_times); + if (!disable_times) + return false; + + /* Paired with smp_mb__before_atomic() in mptcp_active_disable() */ + smp_rmb(); + + /* Limit timeout to max: 2^6 * initial timeout */ + multiplier = 1 << min(disable_times - 1, 6); + + /* Paired with the WRITE_ONCE() in mptcp_active_disable(). */ + timeout = READ_ONCE(pernet->active_disable_stamp) + + multiplier * blackhole_timeout * HZ; + + return time_before(jiffies, timeout); +} + +/* Enable active MPTCP and reset active_disable_times if needed */ +void mptcp_active_enable(struct sock *sk) +{ + struct mptcp_pernet *pernet = mptcp_get_pernet(sock_net(sk)); + + if (atomic_read(&pernet->active_disable_times)) { + struct dst_entry *dst = sk_dst_get(sk); + + if (dst && dst->dev && (dst->dev->flags & IFF_LOOPBACK)) + atomic_set(&pernet->active_disable_times, 0); + } +} + +/* Check the number of retransmissions, and fallback to TCP if needed */ +void mptcp_active_detect_blackhole(struct sock *ssk, bool expired) +{ + struct mptcp_subflow_context *subflow; + u32 timeouts; + + if (!sk_is_mptcp(ssk)) + return; + + timeouts = inet_csk(ssk)->icsk_retransmits; + subflow = mptcp_subflow_ctx(ssk); + + if (subflow->request_mptcp && ssk->sk_state == TCP_SYN_SENT) { + if (timeouts == 2 || (timeouts < 2 && expired)) { + MPTCP_INC_STATS(sock_net(ssk), MPTCP_MIB_MPCAPABLEACTIVEDROP); + subflow->mpc_drop = 1; + mptcp_subflow_early_fallback(mptcp_sk(subflow->conn), subflow); + } else { + subflow->mpc_drop = 0; + } + } +} + static int __net_init mptcp_net_init(struct net *net) { struct mptcp_pernet *pernet = mptcp_get_pernet(net); diff --git a/net/mptcp/diag.c b/net/mptcp/diag.c index 3ae46b545d2c..2d3efb405437 100644 --- a/net/mptcp/diag.c +++ b/net/mptcp/diag.c @@ -94,7 +94,7 @@ static size_t subflow_get_info_size(const struct sock *sk) nla_total_size(4) + /* MPTCP_SUBFLOW_ATTR_RELWRITE_SEQ */ nla_total_size_64bit(8) + /* MPTCP_SUBFLOW_ATTR_MAP_SEQ */ nla_total_size(4) + /* MPTCP_SUBFLOW_ATTR_MAP_SFSEQ */ - nla_total_size(2) + /* MPTCP_SUBFLOW_ATTR_SSN_OFFSET */ + nla_total_size(4) + /* MPTCP_SUBFLOW_ATTR_SSN_OFFSET */ nla_total_size(2) + /* MPTCP_SUBFLOW_ATTR_MAP_DATALEN */ nla_total_size(4) + /* MPTCP_SUBFLOW_ATTR_FLAGS */ nla_total_size(1) + /* MPTCP_SUBFLOW_ATTR_ID_REM */ diff --git a/net/mptcp/fastopen.c b/net/mptcp/fastopen.c index ad28da655f8b..a29ff901df75 100644 --- a/net/mptcp/fastopen.c +++ b/net/mptcp/fastopen.c @@ -68,12 +68,12 @@ void __mptcp_fastopen_gen_msk_ackseq(struct mptcp_sock *msk, struct mptcp_subflo skb = skb_peek_tail(&sk->sk_receive_queue); if (skb) { WARN_ON_ONCE(MPTCP_SKB_CB(skb)->end_seq); - pr_debug("msk %p moving seq %llx -> %llx end_seq %llx -> %llx", sk, + pr_debug("msk %p moving seq %llx -> %llx end_seq %llx -> %llx\n", sk, MPTCP_SKB_CB(skb)->map_seq, MPTCP_SKB_CB(skb)->map_seq + msk->ack_seq, MPTCP_SKB_CB(skb)->end_seq, MPTCP_SKB_CB(skb)->end_seq + msk->ack_seq); MPTCP_SKB_CB(skb)->map_seq += msk->ack_seq; MPTCP_SKB_CB(skb)->end_seq += msk->ack_seq; } - pr_debug("msk=%p ack_seq=%llx", msk, msk->ack_seq); + pr_debug("msk=%p ack_seq=%llx\n", msk, msk->ack_seq); } diff --git a/net/mptcp/mib.c b/net/mptcp/mib.c index c30405e76833..38c2efc82b94 100644 --- a/net/mptcp/mib.c +++ b/net/mptcp/mib.c @@ -15,14 +15,22 @@ static const struct snmp_mib mptcp_snmp_list[] = { SNMP_MIB_ITEM("MPCapableACKRX", MPTCP_MIB_MPCAPABLEPASSIVEACK), SNMP_MIB_ITEM("MPCapableFallbackACK", MPTCP_MIB_MPCAPABLEPASSIVEFALLBACK), SNMP_MIB_ITEM("MPCapableFallbackSYNACK", MPTCP_MIB_MPCAPABLEACTIVEFALLBACK), + SNMP_MIB_ITEM("MPCapableSYNTXDrop", MPTCP_MIB_MPCAPABLEACTIVEDROP), + SNMP_MIB_ITEM("MPCapableSYNTXDisabled", MPTCP_MIB_MPCAPABLEACTIVEDISABLED), SNMP_MIB_ITEM("MPFallbackTokenInit", MPTCP_MIB_TOKENFALLBACKINIT), SNMP_MIB_ITEM("MPTCPRetrans", MPTCP_MIB_RETRANSSEGS), SNMP_MIB_ITEM("MPJoinNoTokenFound", MPTCP_MIB_JOINNOTOKEN), SNMP_MIB_ITEM("MPJoinSynRx", MPTCP_MIB_JOINSYNRX), + SNMP_MIB_ITEM("MPJoinSynBackupRx", MPTCP_MIB_JOINSYNBACKUPRX), SNMP_MIB_ITEM("MPJoinSynAckRx", MPTCP_MIB_JOINSYNACKRX), + SNMP_MIB_ITEM("MPJoinSynAckBackupRx", MPTCP_MIB_JOINSYNACKBACKUPRX), SNMP_MIB_ITEM("MPJoinSynAckHMacFailure", MPTCP_MIB_JOINSYNACKMAC), SNMP_MIB_ITEM("MPJoinAckRx", MPTCP_MIB_JOINACKRX), SNMP_MIB_ITEM("MPJoinAckHMacFailure", MPTCP_MIB_JOINACKMAC), + SNMP_MIB_ITEM("MPJoinSynTx", MPTCP_MIB_JOINSYNTX), + SNMP_MIB_ITEM("MPJoinSynTxCreatSkErr", MPTCP_MIB_JOINSYNTXCREATSKERR), + SNMP_MIB_ITEM("MPJoinSynTxBindErr", MPTCP_MIB_JOINSYNTXBINDERR), + SNMP_MIB_ITEM("MPJoinSynTxConnectErr", MPTCP_MIB_JOINSYNTXCONNECTERR), SNMP_MIB_ITEM("DSSNotMatching", MPTCP_MIB_DSSNOMATCH), SNMP_MIB_ITEM("InfiniteMapTx", MPTCP_MIB_INFINITEMAPTX), SNMP_MIB_ITEM("InfiniteMapRx", MPTCP_MIB_INFINITEMAPRX), @@ -67,6 +75,7 @@ static const struct snmp_mib mptcp_snmp_list[] = { SNMP_MIB_ITEM("RcvWndConflictUpdate", MPTCP_MIB_RCVWNDCONFLICTUPDATE), SNMP_MIB_ITEM("RcvWndConflict", MPTCP_MIB_RCVWNDCONFLICT), SNMP_MIB_ITEM("MPCurrEstab", MPTCP_MIB_CURRESTAB), + SNMP_MIB_ITEM("Blackhole", MPTCP_MIB_BLACKHOLE), SNMP_MIB_SENTINEL }; diff --git a/net/mptcp/mib.h b/net/mptcp/mib.h index 2704afd0dfe4..c8ffe18a8722 100644 --- a/net/mptcp/mib.h +++ b/net/mptcp/mib.h @@ -10,14 +10,22 @@ enum linux_mptcp_mib_field { MPTCP_MIB_MPCAPABLEPASSIVEACK, /* Received third ACK with MP_CAPABLE */ MPTCP_MIB_MPCAPABLEPASSIVEFALLBACK,/* Server-side fallback during 3-way handshake */ MPTCP_MIB_MPCAPABLEACTIVEFALLBACK, /* Client-side fallback during 3-way handshake */ + MPTCP_MIB_MPCAPABLEACTIVEDROP, /* Client-side fallback due to a MPC drop */ + MPTCP_MIB_MPCAPABLEACTIVEDISABLED, /* Client-side disabled due to past issues */ MPTCP_MIB_TOKENFALLBACKINIT, /* Could not init/allocate token */ MPTCP_MIB_RETRANSSEGS, /* Segments retransmitted at the MPTCP-level */ MPTCP_MIB_JOINNOTOKEN, /* Received MP_JOIN but the token was not found */ MPTCP_MIB_JOINSYNRX, /* Received a SYN + MP_JOIN */ + MPTCP_MIB_JOINSYNBACKUPRX, /* Received a SYN + MP_JOIN + backup flag */ MPTCP_MIB_JOINSYNACKRX, /* Received a SYN/ACK + MP_JOIN */ + MPTCP_MIB_JOINSYNACKBACKUPRX, /* Received a SYN/ACK + MP_JOIN + backup flag */ MPTCP_MIB_JOINSYNACKMAC, /* HMAC was wrong on SYN/ACK + MP_JOIN */ MPTCP_MIB_JOINACKRX, /* Received an ACK + MP_JOIN */ MPTCP_MIB_JOINACKMAC, /* HMAC was wrong on ACK + MP_JOIN */ + MPTCP_MIB_JOINSYNTX, /* Sending a SYN + MP_JOIN */ + MPTCP_MIB_JOINSYNTXCREATSKERR, /* Not able to create a socket when sending a SYN + MP_JOIN */ + MPTCP_MIB_JOINSYNTXBINDERR, /* Not able to bind() the address when sending a SYN + MP_JOIN */ + MPTCP_MIB_JOINSYNTXCONNECTERR, /* Not able to connect() when sending a SYN + MP_JOIN */ MPTCP_MIB_DSSNOMATCH, /* Received a new mapping that did not match the previous one */ MPTCP_MIB_INFINITEMAPTX, /* Sent an infinite mapping */ MPTCP_MIB_INFINITEMAPRX, /* Received an infinite mapping */ @@ -68,6 +76,7 @@ enum linux_mptcp_mib_field { */ MPTCP_MIB_RCVWNDCONFLICT, /* Conflict with while updating msk rcv wnd */ MPTCP_MIB_CURRESTAB, /* Current established MPTCP connections */ + MPTCP_MIB_BLACKHOLE, /* A blackhole has been detected */ __MPTCP_MIB_MAX }; diff --git a/net/mptcp/options.c b/net/mptcp/options.c index 8e8dcfbc2993..370c3836b771 100644 --- a/net/mptcp/options.c +++ b/net/mptcp/options.c @@ -117,7 +117,7 @@ static void mptcp_parse_option(const struct sk_buff *skb, mp_opt->suboptions |= OPTION_MPTCP_CSUMREQD; ptr += 2; } - pr_debug("MP_CAPABLE version=%x, flags=%x, optlen=%d sndr=%llu, rcvr=%llu len=%d csum=%u", + pr_debug("MP_CAPABLE version=%x, flags=%x, optlen=%d sndr=%llu, rcvr=%llu len=%d csum=%u\n", version, flags, opsize, mp_opt->sndr_key, mp_opt->rcvr_key, mp_opt->data_len, mp_opt->csum); break; @@ -131,7 +131,7 @@ static void mptcp_parse_option(const struct sk_buff *skb, ptr += 4; mp_opt->nonce = get_unaligned_be32(ptr); ptr += 4; - pr_debug("MP_JOIN bkup=%u, id=%u, token=%u, nonce=%u", + pr_debug("MP_JOIN bkup=%u, id=%u, token=%u, nonce=%u\n", mp_opt->backup, mp_opt->join_id, mp_opt->token, mp_opt->nonce); } else if (opsize == TCPOLEN_MPTCP_MPJ_SYNACK) { @@ -142,19 +142,19 @@ static void mptcp_parse_option(const struct sk_buff *skb, ptr += 8; mp_opt->nonce = get_unaligned_be32(ptr); ptr += 4; - pr_debug("MP_JOIN bkup=%u, id=%u, thmac=%llu, nonce=%u", + pr_debug("MP_JOIN bkup=%u, id=%u, thmac=%llu, nonce=%u\n", mp_opt->backup, mp_opt->join_id, mp_opt->thmac, mp_opt->nonce); } else if (opsize == TCPOLEN_MPTCP_MPJ_ACK) { mp_opt->suboptions |= OPTION_MPTCP_MPJ_ACK; ptr += 2; memcpy(mp_opt->hmac, ptr, MPTCPOPT_HMAC_LEN); - pr_debug("MP_JOIN hmac"); + pr_debug("MP_JOIN hmac\n"); } break; case MPTCPOPT_DSS: - pr_debug("DSS"); + pr_debug("DSS\n"); ptr++; /* we must clear 'mpc_map' be able to detect MP_CAPABLE @@ -169,7 +169,7 @@ static void mptcp_parse_option(const struct sk_buff *skb, mp_opt->ack64 = (flags & MPTCP_DSS_ACK64) != 0; mp_opt->use_ack = (flags & MPTCP_DSS_HAS_ACK); - pr_debug("data_fin=%d dsn64=%d use_map=%d ack64=%d use_ack=%d", + pr_debug("data_fin=%d dsn64=%d use_map=%d ack64=%d use_ack=%d\n", mp_opt->data_fin, mp_opt->dsn64, mp_opt->use_map, mp_opt->ack64, mp_opt->use_ack); @@ -207,7 +207,7 @@ static void mptcp_parse_option(const struct sk_buff *skb, ptr += 4; } - pr_debug("data_ack=%llu", mp_opt->data_ack); + pr_debug("data_ack=%llu\n", mp_opt->data_ack); } if (mp_opt->use_map) { @@ -231,7 +231,7 @@ static void mptcp_parse_option(const struct sk_buff *skb, ptr += 2; } - pr_debug("data_seq=%llu subflow_seq=%u data_len=%u csum=%d:%u", + pr_debug("data_seq=%llu subflow_seq=%u data_len=%u csum=%d:%u\n", mp_opt->data_seq, mp_opt->subflow_seq, mp_opt->data_len, !!(mp_opt->suboptions & OPTION_MPTCP_CSUMREQD), mp_opt->csum); @@ -293,7 +293,7 @@ static void mptcp_parse_option(const struct sk_buff *skb, mp_opt->ahmac = get_unaligned_be64(ptr); ptr += 8; } - pr_debug("ADD_ADDR%s: id=%d, ahmac=%llu, echo=%d, port=%d", + pr_debug("ADD_ADDR%s: id=%d, ahmac=%llu, echo=%d, port=%d\n", (mp_opt->addr.family == AF_INET6) ? "6" : "", mp_opt->addr.id, mp_opt->ahmac, mp_opt->echo, ntohs(mp_opt->addr.port)); break; @@ -309,7 +309,7 @@ static void mptcp_parse_option(const struct sk_buff *skb, mp_opt->rm_list.nr = opsize - TCPOLEN_MPTCP_RM_ADDR_BASE; for (i = 0; i < mp_opt->rm_list.nr; i++) mp_opt->rm_list.ids[i] = *ptr++; - pr_debug("RM_ADDR: rm_list_nr=%d", mp_opt->rm_list.nr); + pr_debug("RM_ADDR: rm_list_nr=%d\n", mp_opt->rm_list.nr); break; case MPTCPOPT_MP_PRIO: @@ -318,7 +318,7 @@ static void mptcp_parse_option(const struct sk_buff *skb, mp_opt->suboptions |= OPTION_MPTCP_PRIO; mp_opt->backup = *ptr++ & MPTCP_PRIO_BKUP; - pr_debug("MP_PRIO: prio=%d", mp_opt->backup); + pr_debug("MP_PRIO: prio=%d\n", mp_opt->backup); break; case MPTCPOPT_MP_FASTCLOSE: @@ -329,7 +329,7 @@ static void mptcp_parse_option(const struct sk_buff *skb, mp_opt->rcvr_key = get_unaligned_be64(ptr); ptr += 8; mp_opt->suboptions |= OPTION_MPTCP_FASTCLOSE; - pr_debug("MP_FASTCLOSE: recv_key=%llu", mp_opt->rcvr_key); + pr_debug("MP_FASTCLOSE: recv_key=%llu\n", mp_opt->rcvr_key); break; case MPTCPOPT_RST: @@ -343,7 +343,7 @@ static void mptcp_parse_option(const struct sk_buff *skb, flags = *ptr++; mp_opt->reset_transient = flags & MPTCP_RST_TRANSIENT; mp_opt->reset_reason = *ptr; - pr_debug("MP_RST: transient=%u reason=%u", + pr_debug("MP_RST: transient=%u reason=%u\n", mp_opt->reset_transient, mp_opt->reset_reason); break; @@ -354,7 +354,7 @@ static void mptcp_parse_option(const struct sk_buff *skb, ptr += 2; mp_opt->suboptions |= OPTION_MPTCP_FAIL; mp_opt->fail_seq = get_unaligned_be64(ptr); - pr_debug("MP_FAIL: data_seq=%llu", mp_opt->fail_seq); + pr_debug("MP_FAIL: data_seq=%llu\n", mp_opt->fail_seq); break; default: @@ -417,7 +417,7 @@ bool mptcp_syn_options(struct sock *sk, const struct sk_buff *skb, *size = TCPOLEN_MPTCP_MPC_SYN; return true; } else if (subflow->request_join) { - pr_debug("remote_token=%u, nonce=%u", subflow->remote_token, + pr_debug("remote_token=%u, nonce=%u\n", subflow->remote_token, subflow->local_nonce); opts->suboptions = OPTION_MPTCP_MPJ_SYN; opts->join_id = subflow->local_id; @@ -500,7 +500,7 @@ static bool mptcp_established_options_mp(struct sock *sk, struct sk_buff *skb, *size = TCPOLEN_MPTCP_MPC_ACK; } - pr_debug("subflow=%p, local_key=%llu, remote_key=%llu map_len=%d", + pr_debug("subflow=%p, local_key=%llu, remote_key=%llu map_len=%d\n", subflow, subflow->local_key, subflow->remote_key, data_len); @@ -509,7 +509,7 @@ static bool mptcp_established_options_mp(struct sock *sk, struct sk_buff *skb, opts->suboptions = OPTION_MPTCP_MPJ_ACK; memcpy(opts->hmac, subflow->hmac, MPTCPOPT_HMAC_LEN); *size = TCPOLEN_MPTCP_MPJ_ACK; - pr_debug("subflow=%p", subflow); + pr_debug("subflow=%p\n", subflow); /* we can use the full delegate action helper only from BH context * If we are in process context - sk is flushing the backlog at @@ -675,7 +675,7 @@ static bool mptcp_established_options_add_addr(struct sock *sk, struct sk_buff * *size = len; if (drop_other_suboptions) { - pr_debug("drop other suboptions"); + pr_debug("drop other suboptions\n"); opts->suboptions = 0; /* note that e.g. DSS could have written into the memory @@ -695,7 +695,7 @@ static bool mptcp_established_options_add_addr(struct sock *sk, struct sk_buff * } else { MPTCP_INC_STATS(sock_net(sk), MPTCP_MIB_ECHOADDTX); } - pr_debug("addr_id=%d, ahmac=%llu, echo=%d, port=%d", + pr_debug("addr_id=%d, ahmac=%llu, echo=%d, port=%d\n", opts->addr.id, opts->ahmac, echo, ntohs(opts->addr.port)); return true; @@ -726,7 +726,7 @@ static bool mptcp_established_options_rm_addr(struct sock *sk, opts->rm_list = rm_list; for (i = 0; i < opts->rm_list.nr; i++) - pr_debug("rm_list_ids[%d]=%d", i, opts->rm_list.ids[i]); + pr_debug("rm_list_ids[%d]=%d\n", i, opts->rm_list.ids[i]); MPTCP_ADD_STATS(sock_net(sk), MPTCP_MIB_RMADDRTX, opts->rm_list.nr); return true; } @@ -752,7 +752,7 @@ static bool mptcp_established_options_mp_prio(struct sock *sk, opts->suboptions |= OPTION_MPTCP_PRIO; opts->backup = subflow->request_bkup; - pr_debug("prio=%d", opts->backup); + pr_debug("prio=%d\n", opts->backup); return true; } @@ -794,7 +794,7 @@ static bool mptcp_established_options_fastclose(struct sock *sk, opts->suboptions |= OPTION_MPTCP_FASTCLOSE; opts->rcvr_key = READ_ONCE(msk->remote_key); - pr_debug("FASTCLOSE key=%llu", opts->rcvr_key); + pr_debug("FASTCLOSE key=%llu\n", opts->rcvr_key); MPTCP_INC_STATS(sock_net(sk), MPTCP_MIB_MPFASTCLOSETX); return true; } @@ -816,7 +816,7 @@ static bool mptcp_established_options_mp_fail(struct sock *sk, opts->suboptions |= OPTION_MPTCP_FAIL; opts->fail_seq = subflow->map_seq; - pr_debug("MP_FAIL fail_seq=%llu", opts->fail_seq); + pr_debug("MP_FAIL fail_seq=%llu\n", opts->fail_seq); MPTCP_INC_STATS(sock_net(sk), MPTCP_MIB_MPFAILTX); return true; @@ -904,16 +904,16 @@ bool mptcp_synack_options(const struct request_sock *req, unsigned int *size, opts->csum_reqd = subflow_req->csum_reqd; opts->allow_join_id0 = subflow_req->allow_join_id0; *size = TCPOLEN_MPTCP_MPC_SYNACK; - pr_debug("subflow_req=%p, local_key=%llu", + pr_debug("subflow_req=%p, local_key=%llu\n", subflow_req, subflow_req->local_key); return true; } else if (subflow_req->mp_join) { opts->suboptions = OPTION_MPTCP_MPJ_SYNACK; - opts->backup = subflow_req->backup; + opts->backup = subflow_req->request_bkup; opts->join_id = subflow_req->local_id; opts->thmac = subflow_req->thmac; opts->nonce = subflow_req->local_nonce; - pr_debug("req=%p, bkup=%u, id=%u, thmac=%llu, nonce=%u", + pr_debug("req=%p, bkup=%u, id=%u, thmac=%llu, nonce=%u\n", subflow_req, opts->backup, opts->join_id, opts->thmac, opts->nonce); *size = TCPOLEN_MPTCP_MPJ_SYNACK; @@ -958,7 +958,8 @@ static bool check_fully_established(struct mptcp_sock *msk, struct sock *ssk, if (subflow->remote_key_valid && (((mp_opt->suboptions & OPTION_MPTCP_DSS) && mp_opt->use_ack) || - ((mp_opt->suboptions & OPTION_MPTCP_ADD_ADDR) && !mp_opt->echo))) { + ((mp_opt->suboptions & OPTION_MPTCP_ADD_ADDR) && + (!mp_opt->echo || subflow->mp_join)))) { /* subflows are fully established as soon as we get any * additional ack, including ADD_ADDR. */ diff --git a/net/mptcp/pm.c b/net/mptcp/pm.c index 55406720c607..620264c75dc2 100644 --- a/net/mptcp/pm.c +++ b/net/mptcp/pm.c @@ -19,7 +19,7 @@ int mptcp_pm_announce_addr(struct mptcp_sock *msk, { u8 add_addr = READ_ONCE(msk->pm.addr_signal); - pr_debug("msk=%p, local_id=%d, echo=%d", msk, addr->id, echo); + pr_debug("msk=%p, local_id=%d, echo=%d\n", msk, addr->id, echo); lockdep_assert_held(&msk->pm.lock); @@ -45,7 +45,7 @@ int mptcp_pm_remove_addr(struct mptcp_sock *msk, const struct mptcp_rm_list *rm_ { u8 rm_addr = READ_ONCE(msk->pm.addr_signal); - pr_debug("msk=%p, rm_list_nr=%d", msk, rm_list->nr); + pr_debug("msk=%p, rm_list_nr=%d\n", msk, rm_list->nr); if (rm_addr) { MPTCP_ADD_STATS(sock_net((struct sock *)msk), @@ -60,23 +60,13 @@ int mptcp_pm_remove_addr(struct mptcp_sock *msk, const struct mptcp_rm_list *rm_ return 0; } -int mptcp_pm_remove_subflow(struct mptcp_sock *msk, const struct mptcp_rm_list *rm_list) -{ - pr_debug("msk=%p, rm_list_nr=%d", msk, rm_list->nr); - - spin_lock_bh(&msk->pm.lock); - mptcp_pm_nl_rm_subflow_received(msk, rm_list); - spin_unlock_bh(&msk->pm.lock); - return 0; -} - /* path manager event handlers */ void mptcp_pm_new_connection(struct mptcp_sock *msk, const struct sock *ssk, int server_side) { struct mptcp_pm_data *pm = &msk->pm; - pr_debug("msk=%p, token=%u side=%d", msk, READ_ONCE(msk->token), server_side); + pr_debug("msk=%p, token=%u side=%d\n", msk, READ_ONCE(msk->token), server_side); WRITE_ONCE(pm->server_side, server_side); mptcp_event(MPTCP_EVENT_CREATED, msk, ssk, GFP_ATOMIC); @@ -100,7 +90,7 @@ bool mptcp_pm_allow_new_subflow(struct mptcp_sock *msk) subflows_max = mptcp_pm_get_subflows_max(msk); - pr_debug("msk=%p subflows=%d max=%d allow=%d", msk, pm->subflows, + pr_debug("msk=%p subflows=%d max=%d allow=%d\n", msk, pm->subflows, subflows_max, READ_ONCE(pm->accept_subflow)); /* try to avoid acquiring the lock below */ @@ -124,7 +114,7 @@ bool mptcp_pm_allow_new_subflow(struct mptcp_sock *msk) static bool mptcp_pm_schedule_work(struct mptcp_sock *msk, enum mptcp_pm_status new_status) { - pr_debug("msk=%p status=%x new=%lx", msk, msk->pm.status, + pr_debug("msk=%p status=%x new=%lx\n", msk, msk->pm.status, BIT(new_status)); if (msk->pm.status & BIT(new_status)) return false; @@ -139,7 +129,7 @@ void mptcp_pm_fully_established(struct mptcp_sock *msk, const struct sock *ssk) struct mptcp_pm_data *pm = &msk->pm; bool announce = false; - pr_debug("msk=%p", msk); + pr_debug("msk=%p\n", msk); spin_lock_bh(&pm->lock); @@ -163,14 +153,14 @@ void mptcp_pm_fully_established(struct mptcp_sock *msk, const struct sock *ssk) void mptcp_pm_connection_closed(struct mptcp_sock *msk) { - pr_debug("msk=%p", msk); + pr_debug("msk=%p\n", msk); } void mptcp_pm_subflow_established(struct mptcp_sock *msk) { struct mptcp_pm_data *pm = &msk->pm; - pr_debug("msk=%p", msk); + pr_debug("msk=%p\n", msk); if (!READ_ONCE(pm->work_pending)) return; @@ -222,7 +212,7 @@ void mptcp_pm_add_addr_received(const struct sock *ssk, struct mptcp_sock *msk = mptcp_sk(subflow->conn); struct mptcp_pm_data *pm = &msk->pm; - pr_debug("msk=%p remote_id=%d accept=%d", msk, addr->id, + pr_debug("msk=%p remote_id=%d accept=%d\n", msk, addr->id, READ_ONCE(pm->accept_addr)); mptcp_event_addr_announced(ssk, addr); @@ -236,7 +226,9 @@ void mptcp_pm_add_addr_received(const struct sock *ssk, } else { __MPTCP_INC_STATS(sock_net((struct sock *)msk), MPTCP_MIB_ADDADDRDROP); } - } else if (!READ_ONCE(pm->accept_addr)) { + /* id0 should not have a different address */ + } else if ((addr->id == 0 && !mptcp_pm_nl_is_init_remote_addr(msk, addr)) || + (addr->id > 0 && !READ_ONCE(pm->accept_addr))) { mptcp_pm_announce_addr(msk, addr, true); mptcp_pm_add_addr_send_ack(msk); } else if (mptcp_pm_schedule_work(msk, MPTCP_PM_ADD_ADDR_RECEIVED)) { @@ -253,7 +245,7 @@ void mptcp_pm_add_addr_echoed(struct mptcp_sock *msk, { struct mptcp_pm_data *pm = &msk->pm; - pr_debug("msk=%p", msk); + pr_debug("msk=%p\n", msk); spin_lock_bh(&pm->lock); @@ -277,7 +269,7 @@ void mptcp_pm_rm_addr_received(struct mptcp_sock *msk, struct mptcp_pm_data *pm = &msk->pm; u8 i; - pr_debug("msk=%p remote_ids_nr=%d", msk, rm_list->nr); + pr_debug("msk=%p remote_ids_nr=%d\n", msk, rm_list->nr); for (i = 0; i < rm_list->nr; i++) mptcp_event_addr_removed(msk, rm_list->ids[i]); @@ -309,19 +301,19 @@ void mptcp_pm_mp_fail_received(struct sock *sk, u64 fail_seq) struct mptcp_subflow_context *subflow = mptcp_subflow_ctx(sk); struct mptcp_sock *msk = mptcp_sk(subflow->conn); - pr_debug("fail_seq=%llu", fail_seq); + pr_debug("fail_seq=%llu\n", fail_seq); if (!READ_ONCE(msk->allow_infinite_fallback)) return; if (!subflow->fail_tout) { - pr_debug("send MP_FAIL response and infinite map"); + pr_debug("send MP_FAIL response and infinite map\n"); subflow->send_mp_fail = 1; subflow->send_infinite_map = 1; tcp_send_ack(sk); } else { - pr_debug("MP_FAIL response received"); + pr_debug("MP_FAIL response received\n"); WRITE_ONCE(subflow->fail_tout, 0); } } @@ -426,18 +418,16 @@ int mptcp_pm_get_local_id(struct mptcp_sock *msk, struct sock_common *skc) return mptcp_pm_nl_get_local_id(msk, &skc_local); } -int mptcp_pm_get_flags_and_ifindex_by_id(struct mptcp_sock *msk, unsigned int id, - u8 *flags, int *ifindex) +bool mptcp_pm_is_backup(struct mptcp_sock *msk, struct sock_common *skc) { - *flags = 0; - *ifindex = 0; + struct mptcp_addr_info skc_local; - if (!id) - return 0; + mptcp_local_address((struct sock_common *)skc, &skc_local); if (mptcp_pm_is_userspace(msk)) - return mptcp_userspace_pm_get_flags_and_ifindex_by_id(msk, id, flags, ifindex); - return mptcp_pm_nl_get_flags_and_ifindex_by_id(msk, id, flags, ifindex); + return mptcp_userspace_pm_is_backup(msk, &skc_local); + + return mptcp_pm_nl_is_backup(msk, &skc_local); } int mptcp_pm_get_addr(struct sk_buff *skb, struct genl_info *info) diff --git a/net/mptcp/pm_netlink.c b/net/mptcp/pm_netlink.c index ea9e5817b9e9..64fe0e7d87d7 100644 --- a/net/mptcp/pm_netlink.c +++ b/net/mptcp/pm_netlink.c @@ -130,12 +130,15 @@ static bool lookup_subflow_by_daddr(const struct list_head *list, { struct mptcp_subflow_context *subflow; struct mptcp_addr_info cur; - struct sock_common *skc; list_for_each_entry(subflow, list, node) { - skc = (struct sock_common *)mptcp_subflow_tcp_sock(subflow); + struct sock *ssk = mptcp_subflow_tcp_sock(subflow); - remote_address(skc, &cur); + if (!((1 << inet_sk_state_load(ssk)) & + (TCPF_ESTABLISHED | TCPF_SYN_SENT | TCPF_SYN_RECV))) + continue; + + remote_address((struct sock_common *)ssk, &cur); if (mptcp_addresses_equal(&cur, daddr, daddr->port)) return true; } @@ -143,11 +146,13 @@ static bool lookup_subflow_by_daddr(const struct list_head *list, return false; } -static struct mptcp_pm_addr_entry * +static bool select_local_address(const struct pm_nl_pernet *pernet, - const struct mptcp_sock *msk) + const struct mptcp_sock *msk, + struct mptcp_pm_local *new_local) { - struct mptcp_pm_addr_entry *entry, *ret = NULL; + struct mptcp_pm_addr_entry *entry; + bool found = false; msk_owned_by_me(msk); @@ -159,17 +164,23 @@ select_local_address(const struct pm_nl_pernet *pernet, if (!test_bit(entry->addr.id, msk->pm.id_avail_bitmap)) continue; - ret = entry; + new_local->addr = entry->addr; + new_local->flags = entry->flags; + new_local->ifindex = entry->ifindex; + found = true; break; } rcu_read_unlock(); - return ret; + + return found; } -static struct mptcp_pm_addr_entry * -select_signal_address(struct pm_nl_pernet *pernet, const struct mptcp_sock *msk) +static bool +select_signal_address(struct pm_nl_pernet *pernet, const struct mptcp_sock *msk, + struct mptcp_pm_local *new_local) { - struct mptcp_pm_addr_entry *entry, *ret = NULL; + struct mptcp_pm_addr_entry *entry; + bool found = false; rcu_read_lock(); /* do not keep any additional per socket state, just signal @@ -184,11 +195,15 @@ select_signal_address(struct pm_nl_pernet *pernet, const struct mptcp_sock *msk) if (!(entry->flags & MPTCP_PM_ADDR_FLAG_SIGNAL)) continue; - ret = entry; + new_local->addr = entry->addr; + new_local->flags = entry->flags; + new_local->ifindex = entry->ifindex; + found = true; break; } rcu_read_unlock(); - return ret; + + return found; } unsigned int mptcp_pm_get_add_addr_signal_max(const struct mptcp_sock *msk) @@ -279,7 +294,7 @@ static void mptcp_pm_add_timer(struct timer_list *timer) struct mptcp_sock *msk = entry->sock; struct sock *sk = (struct sock *)msk; - pr_debug("msk=%p", msk); + pr_debug("msk=%p\n", msk); if (!msk) return; @@ -298,7 +313,7 @@ static void mptcp_pm_add_timer(struct timer_list *timer) spin_lock_bh(&msk->pm.lock); if (!mptcp_pm_should_add_signal_addr(msk)) { - pr_debug("retransmit ADD_ADDR id=%d", entry->addr.id); + pr_debug("retransmit ADD_ADDR id=%d\n", entry->addr.id); mptcp_pm_announce_addr(msk, &entry->addr, false); mptcp_pm_add_addr_send_ack(msk); entry->retrans_times++; @@ -323,15 +338,21 @@ mptcp_pm_del_add_timer(struct mptcp_sock *msk, { struct mptcp_pm_add_entry *entry; struct sock *sk = (struct sock *)msk; + struct timer_list *add_timer = NULL; spin_lock_bh(&msk->pm.lock); entry = mptcp_lookup_anno_list_by_saddr(msk, addr); - if (entry && (!check_id || entry->addr.id == addr->id)) + if (entry && (!check_id || entry->addr.id == addr->id)) { entry->retrans_times = ADD_ADDR_RETRANS_MAX; + add_timer = &entry->add_timer; + } + if (!check_id && entry) + list_del(&entry->list); spin_unlock_bh(&msk->pm.lock); - if (entry && (!check_id || entry->addr.id == addr->id)) - sk_stop_timer_sync(sk, &entry->add_timer); + /* no lock, because sk_stop_timer_sync() is calling del_timer_sync() */ + if (add_timer) + sk_stop_timer_sync(sk, add_timer); return entry; } @@ -348,7 +369,7 @@ bool mptcp_pm_alloc_anno_list(struct mptcp_sock *msk, add_entry = mptcp_lookup_anno_list_by_saddr(msk, addr); if (add_entry) { - if (mptcp_pm_is_kernel(msk)) + if (WARN_ON_ONCE(mptcp_pm_is_kernel(msk))) return false; sk_reset_timer(sk, &add_entry->add_timer, @@ -379,7 +400,7 @@ void mptcp_pm_free_anno_list(struct mptcp_sock *msk) struct sock *sk = (struct sock *)msk; LIST_HEAD(free_list); - pr_debug("msk=%p", msk); + pr_debug("msk=%p\n", msk); spin_lock_bh(&msk->pm.lock); list_splice_init(&msk->pm.anno_list, &free_list); @@ -465,13 +486,12 @@ static void __mptcp_pm_send_ack(struct mptcp_sock *msk, struct mptcp_subflow_con struct sock *ssk = mptcp_subflow_tcp_sock(subflow); bool slow; - pr_debug("send ack for %s", + pr_debug("send ack for %s\n", prio ? "mp_prio" : (mptcp_pm_should_add_signal(msk) ? "add_addr" : "rm_addr")); slow = lock_sock_fast(ssk); if (prio) { subflow->send_mp_prio = 1; - subflow->backup = backup; subflow->request_bkup = backup; } @@ -514,10 +534,11 @@ __lookup_addr(struct pm_nl_pernet *pernet, const struct mptcp_addr_info *info) static void mptcp_pm_create_subflow_or_signal_addr(struct mptcp_sock *msk) { struct sock *sk = (struct sock *)msk; - struct mptcp_pm_addr_entry *local; unsigned int add_addr_signal_max; + bool signal_and_subflow = false; unsigned int local_addr_max; struct pm_nl_pernet *pernet; + struct mptcp_pm_local local; unsigned int subflows_max; pernet = pm_nl_get_pernet(sock_net(sk)); @@ -556,8 +577,6 @@ static void mptcp_pm_create_subflow_or_signal_addr(struct mptcp_sock *msk) /* check first for announce */ if (msk->pm.add_addr_signaled < add_addr_signal_max) { - local = select_signal_address(pernet, msk); - /* due to racing events on both ends we can reach here while * previous add address is still running: if we invoke now * mptcp_pm_announce_addr(), that will fail and the @@ -568,16 +587,30 @@ static void mptcp_pm_create_subflow_or_signal_addr(struct mptcp_sock *msk) if (msk->pm.addr_signal & BIT(MPTCP_ADD_ADDR_SIGNAL)) return; - if (local) { - if (mptcp_pm_alloc_anno_list(msk, &local->addr)) { - __clear_bit(local->addr.id, msk->pm.id_avail_bitmap); - msk->pm.add_addr_signaled++; - mptcp_pm_announce_addr(msk, &local->addr, false); - mptcp_pm_nl_addr_send_ack(msk); - } - } + if (!select_signal_address(pernet, msk, &local)) + goto subflow; + + /* If the alloc fails, we are on memory pressure, not worth + * continuing, and trying to create subflows. + */ + if (!mptcp_pm_alloc_anno_list(msk, &local.addr)) + return; + + __clear_bit(local.addr.id, msk->pm.id_avail_bitmap); + msk->pm.add_addr_signaled++; + + /* Special case for ID0: set the correct ID */ + if (local.addr.id == msk->mpc_endpoint_id) + local.addr.id = 0; + + mptcp_pm_announce_addr(msk, &local.addr, false); + mptcp_pm_nl_addr_send_ack(msk); + + if (local.flags & MPTCP_PM_ADDR_FLAG_SUBFLOW) + signal_and_subflow = true; } +subflow: /* check if should create a new subflow */ while (msk->pm.local_addr_used < local_addr_max && msk->pm.subflows < subflows_max) { @@ -585,21 +618,28 @@ static void mptcp_pm_create_subflow_or_signal_addr(struct mptcp_sock *msk) bool fullmesh; int i, nr; - local = select_local_address(pernet, msk); - if (!local) + if (signal_and_subflow) + signal_and_subflow = false; + else if (!select_local_address(pernet, msk, &local)) break; - fullmesh = !!(local->flags & MPTCP_PM_ADDR_FLAG_FULLMESH); + fullmesh = !!(local.flags & MPTCP_PM_ADDR_FLAG_FULLMESH); - msk->pm.local_addr_used++; - __clear_bit(local->addr.id, msk->pm.id_avail_bitmap); - nr = fill_remote_addresses_vec(msk, &local->addr, fullmesh, addrs); + __clear_bit(local.addr.id, msk->pm.id_avail_bitmap); + + /* Special case for ID0: set the correct ID */ + if (local.addr.id == msk->mpc_endpoint_id) + local.addr.id = 0; + else /* local_addr_used is not decr for ID 0 */ + msk->pm.local_addr_used++; + + nr = fill_remote_addresses_vec(msk, &local.addr, fullmesh, addrs); if (nr == 0) continue; spin_unlock_bh(&msk->pm.lock); for (i = 0; i < nr; i++) - __mptcp_subflow_connect(sk, &local->addr, &addrs[i]); + __mptcp_subflow_connect(sk, &local, &addrs[i]); spin_lock_bh(&msk->pm.lock); } mptcp_pm_nl_check_work_pending(msk); @@ -620,10 +660,11 @@ static void mptcp_pm_nl_subflow_established(struct mptcp_sock *msk) */ static unsigned int fill_local_addresses_vec(struct mptcp_sock *msk, struct mptcp_addr_info *remote, - struct mptcp_addr_info *addrs) + struct mptcp_pm_local *locals) { struct sock *sk = (struct sock *)msk; struct mptcp_pm_addr_entry *entry; + struct mptcp_addr_info mpc_addr; struct pm_nl_pernet *pernet; unsigned int subflows_max; int i = 0; @@ -631,6 +672,8 @@ static unsigned int fill_local_addresses_vec(struct mptcp_sock *msk, pernet = pm_nl_get_pernet_from_msk(msk); subflows_max = mptcp_pm_get_subflows_max(msk); + mptcp_local_address((struct sock_common *)msk, &mpc_addr); + rcu_read_lock(); list_for_each_entry_rcu(entry, &pernet->local_addr_list, list) { if (!(entry->flags & MPTCP_PM_ADDR_FLAG_FULLMESH)) @@ -640,8 +683,16 @@ static unsigned int fill_local_addresses_vec(struct mptcp_sock *msk, continue; if (msk->pm.subflows < subflows_max) { + locals[i].addr = entry->addr; + locals[i].flags = entry->flags; + locals[i].ifindex = entry->ifindex; + + /* Special case for ID0: set the correct ID */ + if (mptcp_addresses_equal(&locals[i].addr, &mpc_addr, locals[i].addr.port)) + locals[i].addr.id = 0; + msk->pm.subflows++; - addrs[i++] = entry->addr; + i++; } } rcu_read_unlock(); @@ -650,21 +701,19 @@ static unsigned int fill_local_addresses_vec(struct mptcp_sock *msk, * 'IPADDRANY' local address */ if (!i) { - struct mptcp_addr_info local; - - memset(&local, 0, sizeof(local)); - local.family = + memset(&locals[i], 0, sizeof(locals[i])); + locals[i].addr.family = #if IS_ENABLED(CONFIG_MPTCP_IPV6) remote->family == AF_INET6 && ipv6_addr_v4mapped(&remote->addr6) ? AF_INET : #endif remote->family; - if (!mptcp_pm_addr_families_match(sk, &local, remote)) + if (!mptcp_pm_addr_families_match(sk, &locals[i].addr, remote)) return 0; msk->pm.subflows++; - addrs[i++] = local; + i++; } return i; @@ -672,7 +721,7 @@ static unsigned int fill_local_addresses_vec(struct mptcp_sock *msk, static void mptcp_pm_nl_add_addr_received(struct mptcp_sock *msk) { - struct mptcp_addr_info addrs[MPTCP_PM_ADDR_MAX]; + struct mptcp_pm_local locals[MPTCP_PM_ADDR_MAX]; struct sock *sk = (struct sock *)msk; unsigned int add_addr_accept_max; struct mptcp_addr_info remote; @@ -683,7 +732,7 @@ static void mptcp_pm_nl_add_addr_received(struct mptcp_sock *msk) add_addr_accept_max = mptcp_pm_get_add_addr_accept_max(msk); subflows_max = mptcp_pm_get_subflows_max(msk); - pr_debug("accepted %d:%d remote family %d", + pr_debug("accepted %d:%d remote family %d\n", msk->pm.add_addr_accepted, add_addr_accept_max, msk->pm.remote.family); @@ -701,24 +750,35 @@ static void mptcp_pm_nl_add_addr_received(struct mptcp_sock *msk) /* connect to the specified remote address, using whatever * local address the routing configuration will pick. */ - nr = fill_local_addresses_vec(msk, &remote, addrs); + nr = fill_local_addresses_vec(msk, &remote, locals); if (nr == 0) return; spin_unlock_bh(&msk->pm.lock); for (i = 0; i < nr; i++) - if (__mptcp_subflow_connect(sk, &addrs[i], &remote) == 0) + if (__mptcp_subflow_connect(sk, &locals[i], &remote) == 0) sf_created = true; spin_lock_bh(&msk->pm.lock); if (sf_created) { - msk->pm.add_addr_accepted++; + /* add_addr_accepted is not decr for ID 0 */ + if (remote.id) + msk->pm.add_addr_accepted++; if (msk->pm.add_addr_accepted >= add_addr_accept_max || msk->pm.subflows >= subflows_max) WRITE_ONCE(msk->pm.accept_addr, false); } } +bool mptcp_pm_nl_is_init_remote_addr(struct mptcp_sock *msk, + const struct mptcp_addr_info *remote) +{ + struct mptcp_addr_info mpc_remote; + + remote_address((struct sock_common *)msk, &mpc_remote); + return mptcp_addresses_equal(&mpc_remote, remote, remote->port); +} + void mptcp_pm_nl_addr_send_ack(struct mptcp_sock *msk) { struct mptcp_subflow_context *subflow; @@ -730,9 +790,12 @@ void mptcp_pm_nl_addr_send_ack(struct mptcp_sock *msk) !mptcp_pm_should_rm_signal(msk)) return; - subflow = list_first_entry_or_null(&msk->conn_list, typeof(*subflow), node); - if (subflow) - mptcp_pm_send_ack(msk, subflow, false, false); + mptcp_for_each_subflow(msk, subflow) { + if (__mptcp_subflow_active(subflow)) { + mptcp_pm_send_ack(msk, subflow, false, false); + break; + } + } } int mptcp_pm_nl_mp_prio_send_ack(struct mptcp_sock *msk, @@ -742,7 +805,7 @@ int mptcp_pm_nl_mp_prio_send_ack(struct mptcp_sock *msk, { struct mptcp_subflow_context *subflow; - pr_debug("bkup=%d", bkup); + pr_debug("bkup=%d\n", bkup); mptcp_for_each_subflow(msk, subflow) { struct sock *ssk = mptcp_subflow_tcp_sock(subflow); @@ -765,11 +828,6 @@ int mptcp_pm_nl_mp_prio_send_ack(struct mptcp_sock *msk, return -EINVAL; } -static bool mptcp_local_id_match(const struct mptcp_sock *msk, u8 local_id, u8 id) -{ - return local_id == id || (!local_id && msk->mpc_endpoint_id == id); -} - static void mptcp_pm_nl_rm_addr_or_subflow(struct mptcp_sock *msk, const struct mptcp_rm_list *rm_list, enum linux_mptcp_mib_field rm_type) @@ -778,7 +836,7 @@ static void mptcp_pm_nl_rm_addr_or_subflow(struct mptcp_sock *msk, struct sock *sk = (struct sock *)msk; u8 i; - pr_debug("%s rm_list_nr %d", + pr_debug("%s rm_list_nr %d\n", rm_type == MPTCP_MIB_RMADDR ? "address" : "subflow", rm_list->nr); msk_owned_by_me(msk); @@ -802,12 +860,14 @@ static void mptcp_pm_nl_rm_addr_or_subflow(struct mptcp_sock *msk, int how = RCV_SHUTDOWN | SEND_SHUTDOWN; u8 id = subflow_get_local_id(subflow); + if (inet_sk_state_load(ssk) == TCP_CLOSE) + continue; if (rm_type == MPTCP_MIB_RMADDR && remote_id != rm_id) continue; - if (rm_type == MPTCP_MIB_RMSUBFLOW && !mptcp_local_id_match(msk, id, rm_id)) + if (rm_type == MPTCP_MIB_RMSUBFLOW && id != rm_id) continue; - pr_debug(" -> %s rm_list_ids[%d]=%u local_id=%u remote_id=%u mpc_id=%u", + pr_debug(" -> %s rm_list_ids[%d]=%u local_id=%u remote_id=%u mpc_id=%u\n", rm_type == MPTCP_MIB_RMADDR ? "address" : "subflow", i, rm_id, id, remote_id, msk->mpc_endpoint_id); spin_unlock_bh(&msk->pm.lock); @@ -817,25 +877,27 @@ static void mptcp_pm_nl_rm_addr_or_subflow(struct mptcp_sock *msk, mptcp_close_ssk(sk, ssk, subflow); spin_lock_bh(&msk->pm.lock); - removed = true; + removed |= subflow->request_join; if (rm_type == MPTCP_MIB_RMSUBFLOW) __MPTCP_INC_STATS(sock_net(sk), rm_type); } - if (rm_type == MPTCP_MIB_RMSUBFLOW) - __set_bit(rm_id ? rm_id : msk->mpc_endpoint_id, msk->pm.id_avail_bitmap); - else if (rm_type == MPTCP_MIB_RMADDR) + + if (rm_type == MPTCP_MIB_RMADDR) __MPTCP_INC_STATS(sock_net(sk), rm_type); + if (!removed) continue; if (!mptcp_pm_is_kernel(msk)) continue; - if (rm_type == MPTCP_MIB_RMADDR) { - msk->pm.add_addr_accepted--; - WRITE_ONCE(msk->pm.accept_addr, true); - } else if (rm_type == MPTCP_MIB_RMSUBFLOW) { - msk->pm.local_addr_used--; + if (rm_type == MPTCP_MIB_RMADDR && rm_id && + !WARN_ON_ONCE(msk->pm.add_addr_accepted == 0)) { + /* Note: if the subflow has been closed before, this + * add_addr_accepted counter will not be decremented. + */ + if (--msk->pm.add_addr_accepted < mptcp_pm_get_add_addr_accept_max(msk)) + WRITE_ONCE(msk->pm.accept_addr, true); } } } @@ -845,8 +907,8 @@ static void mptcp_pm_nl_rm_addr_received(struct mptcp_sock *msk) mptcp_pm_nl_rm_addr_or_subflow(msk, &msk->pm.rm_list_rx, MPTCP_MIB_RMADDR); } -void mptcp_pm_nl_rm_subflow_received(struct mptcp_sock *msk, - const struct mptcp_rm_list *rm_list) +static void mptcp_pm_nl_rm_subflow_received(struct mptcp_sock *msk, + const struct mptcp_rm_list *rm_list) { mptcp_pm_nl_rm_addr_or_subflow(msk, rm_list, MPTCP_MIB_RMSUBFLOW); } @@ -862,7 +924,7 @@ void mptcp_pm_nl_work(struct mptcp_sock *msk) spin_lock_bh(&msk->pm.lock); - pr_debug("msk=%p status=%x", msk, pm->status); + pr_debug("msk=%p status=%x\n", msk, pm->status); if (pm->status & BIT(MPTCP_PM_ADD_ADDR_RECEIVED)) { pm->status &= ~BIT(MPTCP_PM_ADD_ADDR_RECEIVED); mptcp_pm_nl_add_addr_received(msk); @@ -1102,6 +1164,24 @@ int mptcp_pm_nl_get_local_id(struct mptcp_sock *msk, struct mptcp_addr_info *skc return ret; } +bool mptcp_pm_nl_is_backup(struct mptcp_sock *msk, struct mptcp_addr_info *skc) +{ + struct pm_nl_pernet *pernet = pm_nl_get_pernet_from_msk(msk); + struct mptcp_pm_addr_entry *entry; + bool backup = false; + + rcu_read_lock(); + list_for_each_entry_rcu(entry, &pernet->local_addr_list, list) { + if (mptcp_addresses_equal(&entry->addr, skc, entry->addr.port)) { + backup = !!(entry->flags & MPTCP_PM_ADDR_FLAG_BACKUP); + break; + } + } + rcu_read_unlock(); + + return backup; +} + #define MPTCP_PM_CMD_GRP_OFFSET 0 #define MPTCP_PM_EV_GRP_OFFSET 1 @@ -1262,20 +1342,27 @@ static struct pm_nl_pernet *genl_info_pm_nl(struct genl_info *info) return pm_nl_get_pernet(genl_info_net(info)); } -static int mptcp_nl_add_subflow_or_signal_addr(struct net *net) +static int mptcp_nl_add_subflow_or_signal_addr(struct net *net, + struct mptcp_addr_info *addr) { struct mptcp_sock *msk; long s_slot = 0, s_num = 0; while ((msk = mptcp_token_iter_next(net, &s_slot, &s_num)) != NULL) { struct sock *sk = (struct sock *)msk; + struct mptcp_addr_info mpc_addr; if (!READ_ONCE(msk->fully_established) || mptcp_pm_is_userspace(msk)) goto next; + /* if the endp linked to the init sf is re-added with a != ID */ + mptcp_local_address((struct sock_common *)msk, &mpc_addr); + lock_sock(sk); spin_lock_bh(&msk->pm.lock); + if (mptcp_addresses_equal(addr, &mpc_addr, addr->port)) + msk->mpc_endpoint_id = addr->id; mptcp_pm_create_subflow_or_signal_addr(msk); spin_unlock_bh(&msk->pm.lock); release_sock(sk); @@ -1311,8 +1398,8 @@ int mptcp_pm_nl_add_addr_doit(struct sk_buff *skb, struct genl_info *info) if (ret < 0) return ret; - if (addr.addr.port && !(addr.flags & MPTCP_PM_ADDR_FLAG_SIGNAL)) { - GENL_SET_ERR_MSG(info, "flags must have signal when using port"); + if (addr.addr.port && !address_use_port(&addr)) { + GENL_SET_ERR_MSG(info, "flags must have signal and not subflow when using port"); return -EINVAL; } @@ -1348,7 +1435,7 @@ int mptcp_pm_nl_add_addr_doit(struct sk_buff *skb, struct genl_info *info) goto out_free; } - mptcp_nl_add_subflow_or_signal_addr(sock_net(skb->sk)); + mptcp_nl_add_subflow_or_signal_addr(sock_net(skb->sk), &entry->addr); return 0; out_free: @@ -1356,24 +1443,6 @@ out_free: return ret; } -int mptcp_pm_nl_get_flags_and_ifindex_by_id(struct mptcp_sock *msk, unsigned int id, - u8 *flags, int *ifindex) -{ - struct mptcp_pm_addr_entry *entry; - struct sock *sk = (struct sock *)msk; - struct net *net = sock_net(sk); - - rcu_read_lock(); - entry = __lookup_addr_by_id(pm_nl_get_pernet(net), id); - if (entry) { - *flags = entry->flags; - *ifindex = entry->ifindex; - } - rcu_read_unlock(); - - return 0; -} - static bool remove_anno_list_by_saddr(struct mptcp_sock *msk, const struct mptcp_addr_info *addr) { @@ -1381,7 +1450,6 @@ static bool remove_anno_list_by_saddr(struct mptcp_sock *msk, entry = mptcp_pm_del_add_timer(msk, addr, false); if (entry) { - list_del(&entry->list); kfree(entry); return true; } @@ -1389,6 +1457,12 @@ static bool remove_anno_list_by_saddr(struct mptcp_sock *msk, return false; } +static u8 mptcp_endp_get_local_id(struct mptcp_sock *msk, + const struct mptcp_addr_info *addr) +{ + return msk->mpc_endpoint_id == addr->id ? 0 : addr->id; +} + static bool mptcp_pm_remove_anno_addr(struct mptcp_sock *msk, const struct mptcp_addr_info *addr, bool force) @@ -1396,28 +1470,38 @@ static bool mptcp_pm_remove_anno_addr(struct mptcp_sock *msk, struct mptcp_rm_list list = { .nr = 0 }; bool ret; - list.ids[list.nr++] = addr->id; + list.ids[list.nr++] = mptcp_endp_get_local_id(msk, addr); ret = remove_anno_list_by_saddr(msk, addr); if (ret || force) { spin_lock_bh(&msk->pm.lock); + if (ret) { + __set_bit(addr->id, msk->pm.id_avail_bitmap); + msk->pm.add_addr_signaled--; + } mptcp_pm_remove_addr(msk, &list); spin_unlock_bh(&msk->pm.lock); } return ret; } +static void __mark_subflow_endp_available(struct mptcp_sock *msk, u8 id) +{ + /* If it was marked as used, and not ID 0, decrement local_addr_used */ + if (!__test_and_set_bit(id ? : msk->mpc_endpoint_id, msk->pm.id_avail_bitmap) && + id && !WARN_ON_ONCE(msk->pm.local_addr_used == 0)) + msk->pm.local_addr_used--; +} + static int mptcp_nl_remove_subflow_and_signal_addr(struct net *net, const struct mptcp_pm_addr_entry *entry) { const struct mptcp_addr_info *addr = &entry->addr; - struct mptcp_rm_list list = { .nr = 0 }; + struct mptcp_rm_list list = { .nr = 1 }; long s_slot = 0, s_num = 0; struct mptcp_sock *msk; - pr_debug("remove_id=%d", addr->id); - - list.ids[list.nr++] = addr->id; + pr_debug("remove_id=%d\n", addr->id); while ((msk = mptcp_token_iter_next(net, &s_slot, &s_num)) != NULL) { struct sock *sk = (struct sock *)msk; @@ -1435,8 +1519,22 @@ static int mptcp_nl_remove_subflow_and_signal_addr(struct net *net, remove_subflow = lookup_subflow_by_saddr(&msk->conn_list, addr); mptcp_pm_remove_anno_addr(msk, addr, remove_subflow && !(entry->flags & MPTCP_PM_ADDR_FLAG_IMPLICIT)); - if (remove_subflow) - mptcp_pm_remove_subflow(msk, &list); + + list.ids[0] = mptcp_endp_get_local_id(msk, addr); + if (remove_subflow) { + spin_lock_bh(&msk->pm.lock); + mptcp_pm_nl_rm_subflow_received(msk, &list); + spin_unlock_bh(&msk->pm.lock); + } + + if (entry->flags & MPTCP_PM_ADDR_FLAG_SUBFLOW) { + spin_lock_bh(&msk->pm.lock); + __mark_subflow_endp_available(msk, list.ids[0]); + spin_unlock_bh(&msk->pm.lock); + } + + if (msk->mpc_endpoint_id == entry->addr.id) + msk->mpc_endpoint_id = 0; release_sock(sk); next: @@ -1471,6 +1569,7 @@ static int mptcp_nl_remove_id_zero_address(struct net *net, spin_lock_bh(&msk->pm.lock); mptcp_pm_remove_addr(msk, &list); mptcp_pm_nl_rm_subflow_received(msk, &list); + __mark_subflow_endp_available(msk, 0); spin_unlock_bh(&msk->pm.lock); release_sock(sk); @@ -1530,52 +1629,67 @@ int mptcp_pm_nl_del_addr_doit(struct sk_buff *skb, struct genl_info *info) return ret; } +/* Called from the userspace PM only */ void mptcp_pm_remove_addrs(struct mptcp_sock *msk, struct list_head *rm_list) { struct mptcp_rm_list alist = { .nr = 0 }; struct mptcp_pm_addr_entry *entry; + int anno_nr = 0; list_for_each_entry(entry, rm_list, list) { - if ((remove_anno_list_by_saddr(msk, &entry->addr) || - lookup_subflow_by_saddr(&msk->conn_list, &entry->addr)) && - alist.nr < MPTCP_RM_IDS_MAX) - alist.ids[alist.nr++] = entry->addr.id; + if (alist.nr >= MPTCP_RM_IDS_MAX) + break; + + /* only delete if either announced or matching a subflow */ + if (remove_anno_list_by_saddr(msk, &entry->addr)) + anno_nr++; + else if (!lookup_subflow_by_saddr(&msk->conn_list, + &entry->addr)) + continue; + + alist.ids[alist.nr++] = entry->addr.id; } if (alist.nr) { spin_lock_bh(&msk->pm.lock); + msk->pm.add_addr_signaled -= anno_nr; mptcp_pm_remove_addr(msk, &alist); spin_unlock_bh(&msk->pm.lock); } } -static void mptcp_pm_remove_addrs_and_subflows(struct mptcp_sock *msk, - struct list_head *rm_list) +/* Called from the in-kernel PM only */ +static void mptcp_pm_flush_addrs_and_subflows(struct mptcp_sock *msk, + struct list_head *rm_list) { struct mptcp_rm_list alist = { .nr = 0 }, slist = { .nr = 0 }; struct mptcp_pm_addr_entry *entry; list_for_each_entry(entry, rm_list, list) { - if (lookup_subflow_by_saddr(&msk->conn_list, &entry->addr) && - slist.nr < MPTCP_RM_IDS_MAX) - slist.ids[slist.nr++] = entry->addr.id; + if (slist.nr < MPTCP_RM_IDS_MAX && + lookup_subflow_by_saddr(&msk->conn_list, &entry->addr)) + slist.ids[slist.nr++] = mptcp_endp_get_local_id(msk, &entry->addr); - if (remove_anno_list_by_saddr(msk, &entry->addr) && - alist.nr < MPTCP_RM_IDS_MAX) - alist.ids[alist.nr++] = entry->addr.id; + if (alist.nr < MPTCP_RM_IDS_MAX && + remove_anno_list_by_saddr(msk, &entry->addr)) + alist.ids[alist.nr++] = mptcp_endp_get_local_id(msk, &entry->addr); } + spin_lock_bh(&msk->pm.lock); if (alist.nr) { - spin_lock_bh(&msk->pm.lock); + msk->pm.add_addr_signaled -= alist.nr; mptcp_pm_remove_addr(msk, &alist); - spin_unlock_bh(&msk->pm.lock); } if (slist.nr) - mptcp_pm_remove_subflow(msk, &slist); + mptcp_pm_nl_rm_subflow_received(msk, &slist); + /* Reset counters: maybe some subflows have been removed before */ + bitmap_fill(msk->pm.id_avail_bitmap, MPTCP_PM_MAX_ADDR_ID + 1); + msk->pm.local_addr_used = 0; + spin_unlock_bh(&msk->pm.lock); } -static void mptcp_nl_remove_addrs_list(struct net *net, - struct list_head *rm_list) +static void mptcp_nl_flush_addrs_list(struct net *net, + struct list_head *rm_list) { long s_slot = 0, s_num = 0; struct mptcp_sock *msk; @@ -1588,7 +1702,7 @@ static void mptcp_nl_remove_addrs_list(struct net *net, if (!mptcp_pm_is_userspace(msk)) { lock_sock(sk); - mptcp_pm_remove_addrs_and_subflows(msk, rm_list); + mptcp_pm_flush_addrs_and_subflows(msk, rm_list); release_sock(sk); } @@ -1629,7 +1743,7 @@ int mptcp_pm_nl_flush_addrs_doit(struct sk_buff *skb, struct genl_info *info) pernet->next_id = 1; bitmap_zero(pernet->id_bitmap, MPTCP_PM_MAX_ADDR_ID + 1); spin_unlock_bh(&pernet->lock); - mptcp_nl_remove_addrs_list(sock_net(skb->sk), &free_list); + mptcp_nl_flush_addrs_list(sock_net(skb->sk), &free_list); synchronize_rcu(); __flush_addrs(&free_list); return 0; @@ -1855,10 +1969,11 @@ static void mptcp_pm_nl_fullmesh(struct mptcp_sock *msk, { struct mptcp_rm_list list = { .nr = 0 }; - list.ids[list.nr++] = addr->id; + list.ids[list.nr++] = mptcp_endp_get_local_id(msk, addr); spin_lock_bh(&msk->pm.lock); mptcp_pm_nl_rm_subflow_received(msk, &list); + __mark_subflow_endp_available(msk, list.ids[0]); mptcp_pm_create_subflow_or_signal_addr(msk); spin_unlock_bh(&msk->pm.lock); } diff --git a/net/mptcp/pm_userspace.c b/net/mptcp/pm_userspace.c index f0a4590506c6..2cceded3a83a 100644 --- a/net/mptcp/pm_userspace.c +++ b/net/mptcp/pm_userspace.c @@ -119,23 +119,6 @@ mptcp_userspace_pm_lookup_addr_by_id(struct mptcp_sock *msk, unsigned int id) return NULL; } -int mptcp_userspace_pm_get_flags_and_ifindex_by_id(struct mptcp_sock *msk, - unsigned int id, - u8 *flags, int *ifindex) -{ - struct mptcp_pm_addr_entry *match; - - spin_lock_bh(&msk->pm.lock); - match = mptcp_userspace_pm_lookup_addr_by_id(msk, id); - spin_unlock_bh(&msk->pm.lock); - if (match) { - *flags = match->flags; - *ifindex = match->ifindex; - } - - return 0; -} - int mptcp_userspace_pm_get_local_id(struct mptcp_sock *msk, struct mptcp_addr_info *skc) { @@ -165,6 +148,24 @@ int mptcp_userspace_pm_get_local_id(struct mptcp_sock *msk, return mptcp_userspace_pm_append_new_local_addr(msk, &new_entry, true); } +bool mptcp_userspace_pm_is_backup(struct mptcp_sock *msk, + struct mptcp_addr_info *skc) +{ + struct mptcp_pm_addr_entry *entry; + bool backup = false; + + spin_lock_bh(&msk->pm.lock); + list_for_each_entry(entry, &msk->pm.userspace_pm_local_addr_list, list) { + if (mptcp_addresses_equal(&entry->addr, skc, false)) { + backup = !!(entry->flags & MPTCP_PM_ADDR_FLAG_BACKUP); + break; + } + } + spin_unlock_bh(&msk->pm.lock); + + return backup; +} + int mptcp_pm_nl_announce_doit(struct sk_buff *skb, struct genl_info *info) { struct nlattr *token = info->attrs[MPTCP_PM_ATTR_TOKEN]; @@ -334,8 +335,9 @@ int mptcp_pm_nl_subflow_create_doit(struct sk_buff *skb, struct genl_info *info) struct nlattr *raddr = info->attrs[MPTCP_PM_ATTR_ADDR_REMOTE]; struct nlattr *token = info->attrs[MPTCP_PM_ATTR_TOKEN]; struct nlattr *laddr = info->attrs[MPTCP_PM_ATTR_ADDR]; - struct mptcp_pm_addr_entry local = { 0 }; + struct mptcp_pm_addr_entry entry = { 0 }; struct mptcp_addr_info addr_r; + struct mptcp_pm_local local; struct mptcp_sock *msk; int err = -EINVAL; struct sock *sk; @@ -361,18 +363,18 @@ int mptcp_pm_nl_subflow_create_doit(struct sk_buff *skb, struct genl_info *info) goto create_err; } - err = mptcp_pm_parse_entry(laddr, info, true, &local); + err = mptcp_pm_parse_entry(laddr, info, true, &entry); if (err < 0) { NL_SET_ERR_MSG_ATTR(info->extack, laddr, "error parsing local addr"); goto create_err; } - if (local.flags & MPTCP_PM_ADDR_FLAG_SIGNAL) { + if (entry.flags & MPTCP_PM_ADDR_FLAG_SIGNAL) { GENL_SET_ERR_MSG(info, "invalid addr flags"); err = -EINVAL; goto create_err; } - local.flags |= MPTCP_PM_ADDR_FLAG_SUBFLOW; + entry.flags |= MPTCP_PM_ADDR_FLAG_SUBFLOW; err = mptcp_pm_parse_addr(raddr, info, &addr_r); if (err < 0) { @@ -380,27 +382,29 @@ int mptcp_pm_nl_subflow_create_doit(struct sk_buff *skb, struct genl_info *info) goto create_err; } - if (!mptcp_pm_addr_families_match(sk, &local.addr, &addr_r)) { + if (!mptcp_pm_addr_families_match(sk, &entry.addr, &addr_r)) { GENL_SET_ERR_MSG(info, "families mismatch"); err = -EINVAL; goto create_err; } - err = mptcp_userspace_pm_append_new_local_addr(msk, &local, false); + err = mptcp_userspace_pm_append_new_local_addr(msk, &entry, false); if (err < 0) { GENL_SET_ERR_MSG(info, "did not match address and id"); goto create_err; } - lock_sock(sk); - - err = __mptcp_subflow_connect(sk, &local.addr, &addr_r); + local.addr = entry.addr; + local.flags = entry.flags; + local.ifindex = entry.ifindex; + lock_sock(sk); + err = __mptcp_subflow_connect(sk, &local, &addr_r); release_sock(sk); spin_lock_bh(&msk->pm.lock); if (err) - mptcp_userspace_pm_delete_local_addr(msk, &local); + mptcp_userspace_pm_delete_local_addr(msk, &entry); else msk->pm.subflows++; spin_unlock_bh(&msk->pm.lock); diff --git a/net/mptcp/protocol.c b/net/mptcp/protocol.c index bb7dca8aa2d9..c2317919fc14 100644 --- a/net/mptcp/protocol.c +++ b/net/mptcp/protocol.c @@ -139,7 +139,7 @@ static bool mptcp_try_coalesce(struct sock *sk, struct sk_buff *to, !skb_try_coalesce(to, from, &fragstolen, &delta)) return false; - pr_debug("colesced seq %llx into %llx new len %d new end seq %llx", + pr_debug("colesced seq %llx into %llx new len %d new end seq %llx\n", MPTCP_SKB_CB(from)->map_seq, MPTCP_SKB_CB(to)->map_seq, to->len, MPTCP_SKB_CB(from)->end_seq); MPTCP_SKB_CB(to)->end_seq = MPTCP_SKB_CB(from)->end_seq; @@ -217,7 +217,7 @@ static void mptcp_data_queue_ofo(struct mptcp_sock *msk, struct sk_buff *skb) end_seq = MPTCP_SKB_CB(skb)->end_seq; max_seq = atomic64_read(&msk->rcv_wnd_sent); - pr_debug("msk=%p seq=%llx limit=%llx empty=%d", msk, seq, max_seq, + pr_debug("msk=%p seq=%llx limit=%llx empty=%d\n", msk, seq, max_seq, RB_EMPTY_ROOT(&msk->out_of_order_queue)); if (after64(end_seq, max_seq)) { /* out of window */ @@ -350,8 +350,10 @@ static bool __mptcp_move_skb(struct mptcp_sock *msk, struct sock *ssk, skb_orphan(skb); /* try to fetch required memory from subflow */ - if (!mptcp_rmem_schedule(sk, ssk, skb->truesize)) + if (!mptcp_rmem_schedule(sk, ssk, skb->truesize)) { + MPTCP_INC_STATS(sock_net(sk), MPTCP_MIB_RCVPRUNED); goto drop; + } has_rxtstamp = TCP_SKB_CB(skb)->has_rxtstamp; @@ -641,7 +643,7 @@ static bool __mptcp_move_skbs_from_subflow(struct mptcp_sock *msk, } } - pr_debug("msk=%p ssk=%p", msk, ssk); + pr_debug("msk=%p ssk=%p\n", msk, ssk); tp = tcp_sk(ssk); do { u32 map_remaining, offset; @@ -722,7 +724,7 @@ static bool __mptcp_ofo_queue(struct mptcp_sock *msk) u64 end_seq; p = rb_first(&msk->out_of_order_queue); - pr_debug("msk=%p empty=%d", msk, RB_EMPTY_ROOT(&msk->out_of_order_queue)); + pr_debug("msk=%p empty=%d\n", msk, RB_EMPTY_ROOT(&msk->out_of_order_queue)); while (p) { skb = rb_to_skb(p); if (after64(MPTCP_SKB_CB(skb)->map_seq, msk->ack_seq)) @@ -744,7 +746,7 @@ static bool __mptcp_ofo_queue(struct mptcp_sock *msk) int delta = msk->ack_seq - MPTCP_SKB_CB(skb)->map_seq; /* skip overlapping data, if any */ - pr_debug("uncoalesced seq=%llx ack seq=%llx delta=%d", + pr_debug("uncoalesced seq=%llx ack seq=%llx delta=%d\n", MPTCP_SKB_CB(skb)->map_seq, msk->ack_seq, delta); MPTCP_SKB_CB(skb)->offset += delta; @@ -844,10 +846,8 @@ void mptcp_data_ready(struct sock *sk, struct sock *ssk) sk_rbuf = ssk_rbuf; /* over limit? can't append more skbs to msk, Also, no need to wake-up*/ - if (__mptcp_rmem(sk) > sk_rbuf) { - MPTCP_INC_STATS(sock_net(sk), MPTCP_MIB_RCVPRUNED); + if (__mptcp_rmem(sk) > sk_rbuf) return; - } /* Wake-up the reader only for in-sequence data */ mptcp_data_lock(sk); @@ -1240,7 +1240,7 @@ static int mptcp_sendmsg_frag(struct sock *sk, struct sock *ssk, size_t copy; int i; - pr_debug("msk=%p ssk=%p sending dfrag at seq=%llu len=%u already sent=%u", + pr_debug("msk=%p ssk=%p sending dfrag at seq=%llu len=%u already sent=%u\n", msk, ssk, dfrag->data_seq, dfrag->data_len, info->sent); if (WARN_ON_ONCE(info->sent > info->limit || @@ -1341,7 +1341,7 @@ alloc_skb: mpext->use_map = 1; mpext->dsn64 = 1; - pr_debug("data_seq=%llu subflow_seq=%u data_len=%u dsn64=%d", + pr_debug("data_seq=%llu subflow_seq=%u data_len=%u dsn64=%d\n", mpext->data_seq, mpext->subflow_seq, mpext->data_len, mpext->dsn64); @@ -1422,13 +1422,15 @@ struct sock *mptcp_subflow_get_send(struct mptcp_sock *msk) } mptcp_for_each_subflow(msk, subflow) { + bool backup = subflow->backup || subflow->request_bkup; + trace_mptcp_subflow_get_send(subflow); ssk = mptcp_subflow_tcp_sock(subflow); if (!mptcp_subflow_active(subflow)) continue; tout = max(tout, mptcp_timeout_from_subflow(subflow)); - nr_active += !subflow->backup; + nr_active += !backup; pace = subflow->avg_pacing_rate; if (unlikely(!pace)) { /* init pacing rate from socket */ @@ -1439,9 +1441,9 @@ struct sock *mptcp_subflow_get_send(struct mptcp_sock *msk) } linger_time = div_u64((u64)READ_ONCE(ssk->sk_wmem_queued) << 32, pace); - if (linger_time < send_info[subflow->backup].linger_time) { - send_info[subflow->backup].ssk = ssk; - send_info[subflow->backup].linger_time = linger_time; + if (linger_time < send_info[backup].linger_time) { + send_info[backup].ssk = ssk; + send_info[backup].linger_time = linger_time; } } __mptcp_set_timeout(sk, tout); @@ -1890,7 +1892,7 @@ static int mptcp_sendmsg(struct sock *sk, struct msghdr *msg, size_t len) if (!msk->first_pending) WRITE_ONCE(msk->first_pending, dfrag); } - pr_debug("msk=%p dfrag at seq=%llu len=%u sent=%u new=%d", msk, + pr_debug("msk=%p dfrag at seq=%llu len=%u sent=%u new=%d\n", msk, dfrag->data_seq, dfrag->data_len, dfrag->already_sent, !dfrag_collapsed); @@ -2040,13 +2042,13 @@ static void mptcp_rcv_space_adjust(struct mptcp_sock *msk, int copied) do_div(grow, msk->rcvq_space.space); rcvwin += (grow << 1); - rcvbuf = min_t(u64, __tcp_space_from_win(scaling_ratio, rcvwin), + rcvbuf = min_t(u64, mptcp_space_from_win(sk, rcvwin), READ_ONCE(sock_net(sk)->ipv4.sysctl_tcp_rmem[2])); if (rcvbuf > sk->sk_rcvbuf) { u32 window_clamp; - window_clamp = __tcp_win_from_space(scaling_ratio, rcvbuf); + window_clamp = mptcp_win_from_space(sk, rcvbuf); WRITE_ONCE(sk->sk_rcvbuf, rcvbuf); /* Make subflows follow along. If we do not do this, we @@ -2202,7 +2204,7 @@ static int mptcp_recvmsg(struct sock *sk, struct msghdr *msg, size_t len, if (skb_queue_empty(&msk->receive_queue) && __mptcp_move_skbs(msk)) continue; - /* only the master socket status is relevant here. The exit + /* only the MPTCP socket status is relevant here. The exit * conditions mirror closely tcp_recvmsg() */ if (copied >= target) @@ -2246,7 +2248,7 @@ static int mptcp_recvmsg(struct sock *sk, struct msghdr *msg, size_t len, } } - pr_debug("block timeout %ld", timeo); + pr_debug("block timeout %ld\n", timeo); sk_wait_data(sk, &timeo, NULL); } @@ -2262,7 +2264,7 @@ out_err: } } - pr_debug("msk=%p rx queue empty=%d:%d copied=%d", + pr_debug("msk=%p rx queue empty=%d:%d copied=%d\n", msk, skb_queue_empty_lockless(&sk->sk_receive_queue), skb_queue_empty(&msk->receive_queue), copied); if (!(flags & MSG_PEEK)) @@ -2324,7 +2326,7 @@ struct sock *mptcp_subflow_get_retrans(struct mptcp_sock *msk) continue; } - if (subflow->backup) { + if (subflow->backup || subflow->request_bkup) { if (!backup) backup = ssk; continue; @@ -2506,6 +2508,12 @@ out: void mptcp_close_ssk(struct sock *sk, struct sock *ssk, struct mptcp_subflow_context *subflow) { + /* The first subflow can already be closed and still in the list */ + if (subflow->close_event_done) + return; + + subflow->close_event_done = true; + if (sk->sk_state == TCP_ESTABLISHED) mptcp_event(MPTCP_EVENT_SUB_CLOSED, mptcp_sk(sk), ssk, GFP_KERNEL); @@ -2531,8 +2539,11 @@ static void __mptcp_close_subflow(struct sock *sk) mptcp_for_each_subflow_safe(msk, subflow, tmp) { struct sock *ssk = mptcp_subflow_tcp_sock(subflow); + int ssk_state = inet_sk_state_load(ssk); - if (inet_sk_state_load(ssk) != TCP_CLOSE) + if (ssk_state != TCP_CLOSE && + (ssk_state != TCP_CLOSE_WAIT || + inet_sk_state_load(sk) != TCP_ESTABLISHED)) continue; /* 'subflow_data_ready' will re-sched once rx queue is empty */ @@ -2712,7 +2723,7 @@ static void mptcp_mp_fail_no_response(struct mptcp_sock *msk) if (!ssk) return; - pr_debug("MP_FAIL doesn't respond, reset the subflow"); + pr_debug("MP_FAIL doesn't respond, reset the subflow\n"); slow = lock_sock_fast(ssk); mptcp_subflow_reset(ssk); @@ -2886,7 +2897,7 @@ void mptcp_subflow_shutdown(struct sock *sk, struct sock *ssk, int how) break; default: if (__mptcp_check_fallback(mptcp_sk(sk))) { - pr_debug("Fallback"); + pr_debug("Fallback\n"); ssk->sk_shutdown |= how; tcp_shutdown(ssk, how); @@ -2896,7 +2907,7 @@ void mptcp_subflow_shutdown(struct sock *sk, struct sock *ssk, int how) WRITE_ONCE(mptcp_sk(sk)->snd_una, mptcp_sk(sk)->snd_nxt); mptcp_schedule_work(sk); } else { - pr_debug("Sending DATA_FIN on subflow %p", ssk); + pr_debug("Sending DATA_FIN on subflow %p\n", ssk); tcp_send_ack(ssk); if (!mptcp_rtx_timer_pending(sk)) mptcp_reset_rtx_timer(sk); @@ -2962,7 +2973,7 @@ static void mptcp_check_send_data_fin(struct sock *sk) struct mptcp_subflow_context *subflow; struct mptcp_sock *msk = mptcp_sk(sk); - pr_debug("msk=%p snd_data_fin_enable=%d pending=%d snd_nxt=%llu write_seq=%llu", + pr_debug("msk=%p snd_data_fin_enable=%d pending=%d snd_nxt=%llu write_seq=%llu\n", msk, msk->snd_data_fin_enable, !!mptcp_send_head(sk), msk->snd_nxt, msk->write_seq); @@ -2986,7 +2997,7 @@ static void __mptcp_wr_shutdown(struct sock *sk) { struct mptcp_sock *msk = mptcp_sk(sk); - pr_debug("msk=%p snd_data_fin_enable=%d shutdown=%x state=%d pending=%d", + pr_debug("msk=%p snd_data_fin_enable=%d shutdown=%x state=%d pending=%d\n", msk, msk->snd_data_fin_enable, sk->sk_shutdown, sk->sk_state, !!mptcp_send_head(sk)); @@ -3001,7 +3012,7 @@ static void __mptcp_destroy_sock(struct sock *sk) { struct mptcp_sock *msk = mptcp_sk(sk); - pr_debug("msk=%p", msk); + pr_debug("msk=%p\n", msk); might_sleep(); @@ -3109,7 +3120,7 @@ cleanup: mptcp_set_state(sk, TCP_CLOSE); sock_hold(sk); - pr_debug("msk=%p state=%d", sk, sk->sk_state); + pr_debug("msk=%p state=%d\n", sk, sk->sk_state); if (msk->token) mptcp_event(MPTCP_EVENT_CLOSED, msk, NULL, GFP_KERNEL); @@ -3526,7 +3537,7 @@ void mptcp_subflow_process_delegated(struct sock *ssk, long status) static int mptcp_hash(struct sock *sk) { /* should never be called, - * we hash the TCP subflows not the master socket + * we hash the TCP subflows not the MPTCP socket */ WARN_ON_ONCE(1); return 0; @@ -3541,7 +3552,7 @@ static int mptcp_get_port(struct sock *sk, unsigned short snum) { struct mptcp_sock *msk = mptcp_sk(sk); - pr_debug("msk=%p, ssk=%p", msk, msk->first); + pr_debug("msk=%p, ssk=%p\n", msk, msk->first); if (WARN_ON_ONCE(!msk->first)) return -EINVAL; @@ -3558,7 +3569,7 @@ void mptcp_finish_connect(struct sock *ssk) sk = subflow->conn; msk = mptcp_sk(sk); - pr_debug("msk=%p, token=%u", sk, subflow->token); + pr_debug("msk=%p, token=%u\n", sk, subflow->token); subflow->map_seq = subflow->iasn; subflow->map_subflow_seq = 1; @@ -3587,7 +3598,7 @@ bool mptcp_finish_join(struct sock *ssk) struct sock *parent = (void *)msk; bool ret = true; - pr_debug("msk=%p, subflow=%p", msk, subflow); + pr_debug("msk=%p, subflow=%p\n", msk, subflow); /* mptcp socket already closing? */ if (!mptcp_is_fully_established(parent)) { @@ -3633,7 +3644,7 @@ err_prohibited: static void mptcp_shutdown(struct sock *sk, int how) { - pr_debug("sk=%p, how=%d", sk, how); + pr_debug("sk=%p, how=%d\n", sk, how); if ((how & SEND_SHUTDOWN) && mptcp_close_state(sk)) __mptcp_wr_shutdown(sk); @@ -3706,13 +3717,6 @@ static int mptcp_ioctl(struct sock *sk, int cmd, int *karg) return 0; } -static void mptcp_subflow_early_fallback(struct mptcp_sock *msk, - struct mptcp_subflow_context *subflow) -{ - subflow->request_mptcp = 0; - __mptcp_do_fallback(msk); -} - static int mptcp_connect(struct sock *sk, struct sockaddr *uaddr, int addr_len) { struct mptcp_subflow_context *subflow; @@ -3733,9 +3737,14 @@ static int mptcp_connect(struct sock *sk, struct sockaddr *uaddr, int addr_len) if (rcu_access_pointer(tcp_sk(ssk)->md5sig_info)) mptcp_subflow_early_fallback(msk, subflow); #endif - if (subflow->request_mptcp && mptcp_token_new_connect(ssk)) { - MPTCP_INC_STATS(sock_net(ssk), MPTCP_MIB_TOKENFALLBACKINIT); - mptcp_subflow_early_fallback(msk, subflow); + if (subflow->request_mptcp) { + if (mptcp_active_should_disable(sk)) { + MPTCP_INC_STATS(sock_net(ssk), MPTCP_MIB_MPCAPABLEACTIVEDISABLED); + mptcp_subflow_early_fallback(msk, subflow); + } else if (mptcp_token_new_connect(ssk) < 0) { + MPTCP_INC_STATS(sock_net(ssk), MPTCP_MIB_TOKENFALLBACKINIT); + mptcp_subflow_early_fallback(msk, subflow); + } } WRITE_ONCE(msk->write_seq, subflow->idsn); @@ -3854,7 +3863,7 @@ static int mptcp_listen(struct socket *sock, int backlog) struct sock *ssk; int err; - pr_debug("msk=%p", msk); + pr_debug("msk=%p\n", msk); lock_sock(sk); @@ -3893,7 +3902,7 @@ static int mptcp_stream_accept(struct socket *sock, struct socket *newsock, struct mptcp_sock *msk = mptcp_sk(sock->sk); struct sock *ssk, *newsk; - pr_debug("msk=%p", msk); + pr_debug("msk=%p\n", msk); /* Buggy applications can call accept on socket states other then LISTEN * but no need to allocate the first subflow just to error out. @@ -3902,12 +3911,12 @@ static int mptcp_stream_accept(struct socket *sock, struct socket *newsock, if (!ssk) return -EINVAL; - pr_debug("ssk=%p, listener=%p", ssk, mptcp_subflow_ctx(ssk)); + pr_debug("ssk=%p, listener=%p\n", ssk, mptcp_subflow_ctx(ssk)); newsk = inet_csk_accept(ssk, arg); if (!newsk) return arg->err; - pr_debug("newsk=%p, subflow is mptcp=%d", newsk, sk_is_mptcp(newsk)); + pr_debug("newsk=%p, subflow is mptcp=%d\n", newsk, sk_is_mptcp(newsk)); if (sk_is_mptcp(newsk)) { struct mptcp_subflow_context *subflow; struct sock *new_mptcp_sock; @@ -4000,7 +4009,7 @@ static __poll_t mptcp_poll(struct file *file, struct socket *sock, sock_poll_wait(file, sock, wait); state = inet_sk_state_load(sk); - pr_debug("msk=%p state=%d flags=%lx", msk, state, msk->flags); + pr_debug("msk=%p state=%d flags=%lx\n", msk, state, msk->flags); if (state == TCP_LISTEN) { struct sock *ssk = READ_ONCE(msk->first); diff --git a/net/mptcp/protocol.h b/net/mptcp/protocol.h index 7aa47e2dd52b..74417aae08d0 100644 --- a/net/mptcp/protocol.h +++ b/net/mptcp/protocol.h @@ -236,6 +236,12 @@ struct mptcp_pm_data { struct mptcp_rm_list rm_list_rx; }; +struct mptcp_pm_local { + struct mptcp_addr_info addr; + u8 flags; + int ifindex; +}; + struct mptcp_pm_addr_entry { struct list_head list; struct mptcp_addr_info addr; @@ -386,6 +392,11 @@ static inline int mptcp_win_from_space(const struct sock *sk, int space) return __tcp_win_from_space(mptcp_sk(sk)->scaling_ratio, space); } +static inline int mptcp_space_from_win(const struct sock *sk, int win) +{ + return __tcp_space_from_win(mptcp_sk(sk)->scaling_ratio, win); +} + static inline int __mptcp_space(const struct sock *sk) { return mptcp_win_from_space(sk, READ_ONCE(sk->sk_rcvbuf) - __mptcp_rmem(sk)); @@ -443,6 +454,7 @@ struct mptcp_subflow_request_sock { u16 mp_capable : 1, mp_join : 1, backup : 1, + request_bkup : 1, csum_reqd : 1, allow_join_id0 : 1; u8 local_id; @@ -518,7 +530,9 @@ struct mptcp_subflow_context { stale : 1, /* unable to snd/rcv data, do not use for xmit */ valid_csum_seen : 1, /* at least one csum validated */ is_mptfo : 1, /* subflow is doing TFO */ - __unused : 10; + close_event_done : 1, /* has done the post-closed part */ + mpc_drop : 1, /* the MPC option has been dropped in a rtx */ + __unused : 8; bool data_avail; bool scheduled; u32 remote_nonce; @@ -684,6 +698,11 @@ unsigned int mptcp_stale_loss_cnt(const struct net *net); unsigned int mptcp_close_timeout(const struct sock *sk); int mptcp_get_pm_type(const struct net *net); const char *mptcp_get_scheduler(const struct net *net); + +void mptcp_active_disable(struct sock *sk); +bool mptcp_active_should_disable(struct sock *ssk); +void mptcp_active_enable(struct sock *sk); + void mptcp_get_available_schedulers(char *buf, size_t maxlen); void __mptcp_subflow_fully_established(struct mptcp_sock *msk, struct mptcp_subflow_context *subflow, @@ -712,7 +731,7 @@ bool mptcp_addresses_equal(const struct mptcp_addr_info *a, void mptcp_local_address(const struct sock_common *skc, struct mptcp_addr_info *addr); /* called with sk socket lock held */ -int __mptcp_subflow_connect(struct sock *sk, const struct mptcp_addr_info *loc, +int __mptcp_subflow_connect(struct sock *sk, const struct mptcp_pm_local *local, const struct mptcp_addr_info *remote); int mptcp_subflow_create_socket(struct sock *sk, unsigned short family, struct socket **new_sock); @@ -986,6 +1005,8 @@ void mptcp_pm_add_addr_received(const struct sock *ssk, void mptcp_pm_add_addr_echoed(struct mptcp_sock *msk, const struct mptcp_addr_info *addr); void mptcp_pm_add_addr_send_ack(struct mptcp_sock *msk); +bool mptcp_pm_nl_is_init_remote_addr(struct mptcp_sock *msk, + const struct mptcp_addr_info *remote); void mptcp_pm_nl_addr_send_ack(struct mptcp_sock *msk); void mptcp_pm_rm_addr_received(struct mptcp_sock *msk, const struct mptcp_rm_list *rm_list); @@ -1005,14 +1026,6 @@ mptcp_pm_del_add_timer(struct mptcp_sock *msk, struct mptcp_pm_add_entry * mptcp_lookup_anno_list_by_saddr(const struct mptcp_sock *msk, const struct mptcp_addr_info *addr); -int mptcp_pm_get_flags_and_ifindex_by_id(struct mptcp_sock *msk, - unsigned int id, - u8 *flags, int *ifindex); -int mptcp_pm_nl_get_flags_and_ifindex_by_id(struct mptcp_sock *msk, unsigned int id, - u8 *flags, int *ifindex); -int mptcp_userspace_pm_get_flags_and_ifindex_by_id(struct mptcp_sock *msk, - unsigned int id, - u8 *flags, int *ifindex); int mptcp_pm_set_flags(struct sk_buff *skb, struct genl_info *info); int mptcp_pm_nl_set_flags(struct sk_buff *skb, struct genl_info *info); int mptcp_userspace_pm_set_flags(struct sk_buff *skb, struct genl_info *info); @@ -1020,7 +1033,6 @@ int mptcp_pm_announce_addr(struct mptcp_sock *msk, const struct mptcp_addr_info *addr, bool echo); int mptcp_pm_remove_addr(struct mptcp_sock *msk, const struct mptcp_rm_list *rm_list); -int mptcp_pm_remove_subflow(struct mptcp_sock *msk, const struct mptcp_rm_list *rm_list); void mptcp_pm_remove_addrs(struct mptcp_sock *msk, struct list_head *rm_list); void mptcp_free_local_addr_list(struct mptcp_sock *msk); @@ -1103,6 +1115,9 @@ bool mptcp_pm_rm_addr_signal(struct mptcp_sock *msk, unsigned int remaining, int mptcp_pm_get_local_id(struct mptcp_sock *msk, struct sock_common *skc); int mptcp_pm_nl_get_local_id(struct mptcp_sock *msk, struct mptcp_addr_info *skc); int mptcp_userspace_pm_get_local_id(struct mptcp_sock *msk, struct mptcp_addr_info *skc); +bool mptcp_pm_is_backup(struct mptcp_sock *msk, struct sock_common *skc); +bool mptcp_pm_nl_is_backup(struct mptcp_sock *msk, struct mptcp_addr_info *skc); +bool mptcp_userspace_pm_is_backup(struct mptcp_sock *msk, struct mptcp_addr_info *skc); int mptcp_pm_dump_addr(struct sk_buff *msg, struct netlink_callback *cb); int mptcp_pm_nl_dump_addr(struct sk_buff *msg, struct netlink_callback *cb); @@ -1124,8 +1139,6 @@ static inline u8 subflow_get_local_id(const struct mptcp_subflow_context *subflo void __init mptcp_pm_nl_init(void); void mptcp_pm_nl_work(struct mptcp_sock *msk); -void mptcp_pm_nl_rm_subflow_received(struct mptcp_sock *msk, - const struct mptcp_rm_list *rm_list); unsigned int mptcp_pm_get_add_addr_signal_max(const struct mptcp_sock *msk); unsigned int mptcp_pm_get_add_addr_accept_max(const struct mptcp_sock *msk); unsigned int mptcp_pm_get_subflows_max(const struct mptcp_sock *msk); @@ -1145,7 +1158,6 @@ static inline void mptcp_pm_close_subflow(struct mptcp_sock *msk) spin_unlock_bh(&msk->pm.lock); } -void mptcp_sockopt_sync(struct mptcp_sock *msk, struct sock *ssk); void mptcp_sockopt_sync_locked(struct mptcp_sock *msk, struct sock *ssk); static inline struct mptcp_ext *mptcp_get_ext(const struct sk_buff *skb) @@ -1171,7 +1183,7 @@ static inline bool mptcp_check_fallback(const struct sock *sk) static inline void __mptcp_do_fallback(struct mptcp_sock *msk) { if (__mptcp_check_fallback(msk)) { - pr_debug("TCP fallback already done (msk=%p)", msk); + pr_debug("TCP fallback already done (msk=%p)\n", msk); return; } set_bit(MPTCP_FALLBACK_DONE, &msk->flags); @@ -1207,7 +1219,15 @@ static inline void mptcp_do_fallback(struct sock *ssk) } } -#define pr_fallback(a) pr_debug("%s:fallback to TCP (msk=%p)", __func__, a) +#define pr_fallback(a) pr_debug("%s:fallback to TCP (msk=%p)\n", __func__, a) + +static inline void mptcp_subflow_early_fallback(struct mptcp_sock *msk, + struct mptcp_subflow_context *subflow) +{ + pr_fallback(msk); + subflow->request_mptcp = 0; + __mptcp_do_fallback(msk); +} static inline bool mptcp_check_infinite_map(struct sk_buff *skb) { diff --git a/net/mptcp/sched.c b/net/mptcp/sched.c index 4a7fd0508ad2..78ed508ebc1b 100644 --- a/net/mptcp/sched.c +++ b/net/mptcp/sched.c @@ -86,7 +86,7 @@ int mptcp_register_scheduler(struct mptcp_sched_ops *sched) list_add_tail_rcu(&sched->list, &mptcp_sched_list); spin_unlock(&mptcp_sched_list_lock); - pr_debug("%s registered", sched->name); + pr_debug("%s registered\n", sched->name); return 0; } @@ -118,7 +118,7 @@ int mptcp_init_sched(struct mptcp_sock *msk, if (msk->sched->init) msk->sched->init(msk); - pr_debug("sched=%s", msk->sched->name); + pr_debug("sched=%s\n", msk->sched->name); return 0; } diff --git a/net/mptcp/sockopt.c b/net/mptcp/sockopt.c index f9a4fb17b5b7..505445a9598f 100644 --- a/net/mptcp/sockopt.c +++ b/net/mptcp/sockopt.c @@ -873,7 +873,7 @@ int mptcp_setsockopt(struct sock *sk, int level, int optname, struct mptcp_sock *msk = mptcp_sk(sk); struct sock *ssk; - pr_debug("msk=%p", msk); + pr_debug("msk=%p\n", msk); if (level == SOL_SOCKET) return mptcp_setsockopt_sol_socket(msk, optname, optval, optlen); @@ -1453,7 +1453,7 @@ int mptcp_getsockopt(struct sock *sk, int level, int optname, struct mptcp_sock *msk = mptcp_sk(sk); struct sock *ssk; - pr_debug("msk=%p", msk); + pr_debug("msk=%p\n", msk); /* @@ the meaning of setsockopt() when the socket is connected and * there are multiple subflows is not yet defined. It is up to the @@ -1579,7 +1579,7 @@ int mptcp_set_rcvlowat(struct sock *sk, int val) if (sk->sk_userlocks & SOCK_RCVBUF_LOCK) return 0; - space = __tcp_space_from_win(mptcp_sk(sk)->scaling_ratio, val); + space = mptcp_space_from_win(sk, val); if (space <= sk->sk_rcvbuf) return 0; diff --git a/net/mptcp/subflow.c b/net/mptcp/subflow.c index 612c38570a64..1040b3b9696b 100644 --- a/net/mptcp/subflow.c +++ b/net/mptcp/subflow.c @@ -39,7 +39,7 @@ static void subflow_req_destructor(struct request_sock *req) { struct mptcp_subflow_request_sock *subflow_req = mptcp_subflow_rsk(req); - pr_debug("subflow_req=%p", subflow_req); + pr_debug("subflow_req=%p\n", subflow_req); if (subflow_req->msk) sock_put((struct sock *)subflow_req->msk); @@ -100,6 +100,7 @@ static struct mptcp_sock *subflow_token_join_request(struct request_sock *req) return NULL; } subflow_req->local_id = local_id; + subflow_req->request_bkup = mptcp_pm_is_backup(msk, (struct sock_common *)req); return msk; } @@ -145,7 +146,7 @@ static int subflow_check_req(struct request_sock *req, struct mptcp_options_received mp_opt; bool opt_mp_capable, opt_mp_join; - pr_debug("subflow_req=%p, listener=%p", subflow_req, listener); + pr_debug("subflow_req=%p, listener=%p\n", subflow_req, listener); #ifdef CONFIG_TCP_MD5SIG /* no MPTCP if MD5SIG is enabled on this socket or we may run out of @@ -168,6 +169,9 @@ static int subflow_check_req(struct request_sock *req, return 0; } else if (opt_mp_join) { SUBFLOW_REQ_INC_STATS(req, MPTCP_MIB_JOINSYNRX); + + if (mp_opt.backup) + SUBFLOW_REQ_INC_STATS(req, MPTCP_MIB_JOINSYNBACKUPRX); } if (opt_mp_capable && listener->request_mptcp) { @@ -217,7 +221,7 @@ again: } if (subflow_use_different_sport(subflow_req->msk, sk_listener)) { - pr_debug("syn inet_sport=%d %d", + pr_debug("syn inet_sport=%d %d\n", ntohs(inet_sk(sk_listener)->inet_sport), ntohs(inet_sk((struct sock *)subflow_req->msk)->inet_sport)); if (!mptcp_pm_sport_in_anno_list(subflow_req->msk, sk_listener)) { @@ -239,7 +243,7 @@ again: subflow_init_req_cookie_join_save(subflow_req, skb); } - pr_debug("token=%u, remote_nonce=%u msk=%p", subflow_req->token, + pr_debug("token=%u, remote_nonce=%u msk=%p\n", subflow_req->token, subflow_req->remote_nonce, subflow_req->msk); } @@ -523,7 +527,7 @@ static void subflow_finish_connect(struct sock *sk, const struct sk_buff *skb) subflow->rel_write_seq = 1; subflow->conn_finished = 1; subflow->ssn_offset = TCP_SKB_CB(skb)->seq; - pr_debug("subflow=%p synack seq=%x", subflow, subflow->ssn_offset); + pr_debug("subflow=%p synack seq=%x\n", subflow, subflow->ssn_offset); mptcp_get_options(skb, &mp_opt); if (subflow->request_mptcp) { @@ -542,6 +546,7 @@ static void subflow_finish_connect(struct sock *sk, const struct sk_buff *skb) subflow->mp_capable = 1; MPTCP_INC_STATS(sock_net(sk), MPTCP_MIB_MPCAPABLEACTIVEACK); mptcp_finish_connect(sk); + mptcp_active_enable(parent); mptcp_propagate_state(parent, sk, subflow, &mp_opt); } else if (subflow->request_join) { u8 hmac[SHA256_DIGEST_SIZE]; @@ -555,7 +560,7 @@ static void subflow_finish_connect(struct sock *sk, const struct sk_buff *skb) subflow->thmac = mp_opt.thmac; subflow->remote_nonce = mp_opt.nonce; WRITE_ONCE(subflow->remote_id, mp_opt.join_id); - pr_debug("subflow=%p, thmac=%llu, remote_nonce=%u backup=%d", + pr_debug("subflow=%p, thmac=%llu, remote_nonce=%u backup=%d\n", subflow, subflow->thmac, subflow->remote_nonce, subflow->backup); @@ -577,13 +582,19 @@ static void subflow_finish_connect(struct sock *sk, const struct sk_buff *skb) subflow->mp_join = 1; MPTCP_INC_STATS(sock_net(sk), MPTCP_MIB_JOINSYNACKRX); + if (subflow->backup) + MPTCP_INC_STATS(sock_net(sk), MPTCP_MIB_JOINSYNACKBACKUPRX); + if (subflow_use_different_dport(msk, sk)) { - pr_debug("synack inet_dport=%d %d", + pr_debug("synack inet_dport=%d %d\n", ntohs(inet_sk(sk)->inet_dport), ntohs(inet_sk(parent)->inet_dport)); MPTCP_INC_STATS(sock_net(sk), MPTCP_MIB_JOINPORTSYNACKRX); } } else if (mptcp_check_fallback(sk)) { + /* It looks like MPTCP is blocked, while TCP is not */ + if (subflow->mpc_drop) + mptcp_active_disable(parent); fallback: mptcp_propagate_state(parent, sk, subflow, NULL); } @@ -614,6 +625,8 @@ static int subflow_chk_local_id(struct sock *sk) return err; subflow_set_local_id(subflow, err); + subflow->request_bkup = mptcp_pm_is_backup(msk, (struct sock_common *)sk); + return 0; } @@ -646,7 +659,7 @@ static int subflow_v4_conn_request(struct sock *sk, struct sk_buff *skb) { struct mptcp_subflow_context *subflow = mptcp_subflow_ctx(sk); - pr_debug("subflow=%p", subflow); + pr_debug("subflow=%p\n", subflow); /* Never answer to SYNs sent to broadcast or multicast */ if (skb_rtable(skb)->rt_flags & (RTCF_BROADCAST | RTCF_MULTICAST)) @@ -677,7 +690,7 @@ static int subflow_v6_conn_request(struct sock *sk, struct sk_buff *skb) { struct mptcp_subflow_context *subflow = mptcp_subflow_ctx(sk); - pr_debug("subflow=%p", subflow); + pr_debug("subflow=%p\n", subflow); if (skb->protocol == htons(ETH_P_IP)) return subflow_v4_conn_request(sk, skb); @@ -798,7 +811,7 @@ static struct sock *subflow_syn_recv_sock(const struct sock *sk, struct mptcp_sock *owner; struct sock *child; - pr_debug("listener=%p, req=%p, conn=%p", listener, req, listener->conn); + pr_debug("listener=%p, req=%p, conn=%p\n", listener, req, listener->conn); /* After child creation we must look for MPC even when options * are not parsed @@ -889,7 +902,7 @@ create_child: ctx->conn = (struct sock *)owner; if (subflow_use_different_sport(owner, sk)) { - pr_debug("ack inet_sport=%d %d", + pr_debug("ack inet_sport=%d %d\n", ntohs(inet_sk(sk)->inet_sport), ntohs(inet_sk((struct sock *)owner)->inet_sport)); if (!mptcp_pm_sport_in_anno_list(owner, sk)) { @@ -952,7 +965,7 @@ enum mapping_status { static void dbg_bad_map(struct mptcp_subflow_context *subflow, u32 ssn) { - pr_debug("Bad mapping: ssn=%d map_seq=%d map_data_len=%d", + pr_debug("Bad mapping: ssn=%d map_seq=%d map_data_len=%d\n", ssn, subflow->map_subflow_seq, subflow->map_data_len); } @@ -1112,7 +1125,7 @@ static enum mapping_status get_mapping_status(struct sock *ssk, data_len = mpext->data_len; if (data_len == 0) { - pr_debug("infinite mapping received"); + pr_debug("infinite mapping received\n"); MPTCP_INC_STATS(sock_net(ssk), MPTCP_MIB_INFINITEMAPRX); subflow->map_data_len = 0; return MAPPING_INVALID; @@ -1124,7 +1137,7 @@ static enum mapping_status get_mapping_status(struct sock *ssk, if (data_len == 1) { bool updated = mptcp_update_rcv_data_fin(msk, mpext->data_seq, mpext->dsn64); - pr_debug("DATA_FIN with no payload seq=%llu", mpext->data_seq); + pr_debug("DATA_FIN with no payload seq=%llu\n", mpext->data_seq); if (subflow->map_valid) { /* A DATA_FIN might arrive in a DSS * option before the previous mapping @@ -1150,7 +1163,7 @@ static enum mapping_status get_mapping_status(struct sock *ssk, data_fin_seq &= GENMASK_ULL(31, 0); mptcp_update_rcv_data_fin(msk, data_fin_seq, mpext->dsn64); - pr_debug("DATA_FIN with mapping seq=%llu dsn64=%d", + pr_debug("DATA_FIN with mapping seq=%llu dsn64=%d\n", data_fin_seq, mpext->dsn64); /* Adjust for DATA_FIN using 1 byte of sequence space */ @@ -1196,7 +1209,7 @@ static enum mapping_status get_mapping_status(struct sock *ssk, if (unlikely(subflow->map_csum_reqd != csum_reqd)) return MAPPING_INVALID; - pr_debug("new map seq=%llu subflow_seq=%u data_len=%u csum=%d:%u", + pr_debug("new map seq=%llu subflow_seq=%u data_len=%u csum=%d:%u\n", subflow->map_seq, subflow->map_subflow_seq, subflow->map_data_len, subflow->map_csum_reqd, subflow->map_data_csum); @@ -1221,14 +1234,22 @@ static void mptcp_subflow_discard_data(struct sock *ssk, struct sk_buff *skb, { struct mptcp_subflow_context *subflow = mptcp_subflow_ctx(ssk); bool fin = TCP_SKB_CB(skb)->tcp_flags & TCPHDR_FIN; - u32 incr; + struct tcp_sock *tp = tcp_sk(ssk); + u32 offset, incr, avail_len; + + offset = tp->copied_seq - TCP_SKB_CB(skb)->seq; + if (WARN_ON_ONCE(offset > skb->len)) + goto out; - incr = limit >= skb->len ? skb->len + fin : limit; + avail_len = skb->len - offset; + incr = limit >= avail_len ? avail_len + fin : limit; - pr_debug("discarding=%d len=%d seq=%d", incr, skb->len, - subflow->map_subflow_seq); + pr_debug("discarding=%d len=%d offset=%d seq=%d\n", incr, skb->len, + offset, subflow->map_subflow_seq); MPTCP_INC_STATS(sock_net(ssk), MPTCP_MIB_DUPDATA); tcp_sk(ssk)->copied_seq += incr; + +out: if (!before(tcp_sk(ssk)->copied_seq, TCP_SKB_CB(skb)->end_seq)) sk_eat_skb(ssk, skb); if (mptcp_subflow_get_map_offset(subflow) >= subflow->map_data_len) @@ -1238,12 +1259,16 @@ static void mptcp_subflow_discard_data(struct sock *ssk, struct sk_buff *skb, /* sched mptcp worker to remove the subflow if no more data is pending */ static void subflow_sched_work_if_closed(struct mptcp_sock *msk, struct sock *ssk) { - if (likely(ssk->sk_state != TCP_CLOSE)) + struct sock *sk = (struct sock *)msk; + + if (likely(ssk->sk_state != TCP_CLOSE && + (ssk->sk_state != TCP_CLOSE_WAIT || + inet_sk_state_load(sk) != TCP_ESTABLISHED))) return; if (skb_queue_empty(&ssk->sk_receive_queue) && !test_and_set_bit(MPTCP_WORK_CLOSE_SUBFLOW, &msk->flags)) - mptcp_schedule_work((struct sock *)msk); + mptcp_schedule_work(sk); } static bool subflow_can_fallback(struct mptcp_subflow_context *subflow) @@ -1320,7 +1345,7 @@ static bool subflow_check_data_avail(struct sock *ssk) old_ack = READ_ONCE(msk->ack_seq); ack_seq = mptcp_subflow_get_mapped_dsn(subflow); - pr_debug("msk ack_seq=%llx subflow ack_seq=%llx", old_ack, + pr_debug("msk ack_seq=%llx subflow ack_seq=%llx\n", old_ack, ack_seq); if (unlikely(before64(ack_seq, old_ack))) { mptcp_subflow_discard_data(ssk, skb, old_ack - ack_seq); @@ -1392,7 +1417,7 @@ bool mptcp_subflow_data_available(struct sock *sk) subflow->map_valid = 0; WRITE_ONCE(subflow->data_avail, false); - pr_debug("Done with mapping: seq=%u data_len=%u", + pr_debug("Done with mapping: seq=%u data_len=%u\n", subflow->map_subflow_seq, subflow->map_data_len); } @@ -1502,7 +1527,7 @@ void mptcpv6_handle_mapped(struct sock *sk, bool mapped) target = mapped ? &subflow_v6m_specific : subflow_default_af_ops(sk); - pr_debug("subflow=%p family=%d ops=%p target=%p mapped=%d", + pr_debug("subflow=%p family=%d ops=%p target=%p mapped=%d\n", subflow, sk->sk_family, icsk->icsk_af_ops, target, mapped); if (likely(icsk->icsk_af_ops == target)) @@ -1544,28 +1569,31 @@ void mptcp_info2sockaddr(const struct mptcp_addr_info *info, #endif } -int __mptcp_subflow_connect(struct sock *sk, const struct mptcp_addr_info *loc, +int __mptcp_subflow_connect(struct sock *sk, const struct mptcp_pm_local *local, const struct mptcp_addr_info *remote) { struct mptcp_sock *msk = mptcp_sk(sk); struct mptcp_subflow_context *subflow; + int local_id = local->addr.id; struct sockaddr_storage addr; int remote_id = remote->id; - int local_id = loc->id; int err = -ENOTCONN; struct socket *sf; struct sock *ssk; u32 remote_token; int addrlen; - int ifindex; - u8 flags; + /* The userspace PM sent the request too early? */ if (!mptcp_is_fully_established(sk)) goto err_out; - err = mptcp_subflow_create_socket(sk, loc->family, &sf); - if (err) + err = mptcp_subflow_create_socket(sk, local->addr.family, &sf); + if (err) { + MPTCP_INC_STATS(sock_net(sk), MPTCP_MIB_JOINSYNTXCREATSKERR); + pr_debug("msk=%p local=%d remote=%d create sock error: %d\n", + msk, local_id, remote_id, err); goto err_out; + } ssk = sf->sk; subflow = mptcp_subflow_ctx(ssk); @@ -1573,42 +1601,61 @@ int __mptcp_subflow_connect(struct sock *sk, const struct mptcp_addr_info *loc, get_random_bytes(&subflow->local_nonce, sizeof(u32)); } while (!subflow->local_nonce); - if (local_id) + /* if 'IPADDRANY', the ID will be set later, after the routing */ + if (local->addr.family == AF_INET) { + if (!local->addr.addr.s_addr) + local_id = -1; +#if IS_ENABLED(CONFIG_MPTCP_IPV6) + } else if (sk->sk_family == AF_INET6) { + if (ipv6_addr_any(&local->addr.addr6)) + local_id = -1; +#endif + } + + if (local_id >= 0) subflow_set_local_id(subflow, local_id); - mptcp_pm_get_flags_and_ifindex_by_id(msk, local_id, - &flags, &ifindex); subflow->remote_key_valid = 1; subflow->remote_key = READ_ONCE(msk->remote_key); subflow->local_key = READ_ONCE(msk->local_key); subflow->token = msk->token; - mptcp_info2sockaddr(loc, &addr, ssk->sk_family); + mptcp_info2sockaddr(&local->addr, &addr, ssk->sk_family); addrlen = sizeof(struct sockaddr_in); #if IS_ENABLED(CONFIG_MPTCP_IPV6) if (addr.ss_family == AF_INET6) addrlen = sizeof(struct sockaddr_in6); #endif - ssk->sk_bound_dev_if = ifindex; + ssk->sk_bound_dev_if = local->ifindex; err = kernel_bind(sf, (struct sockaddr *)&addr, addrlen); - if (err) + if (err) { + MPTCP_INC_STATS(sock_net(sk), MPTCP_MIB_JOINSYNTXBINDERR); + pr_debug("msk=%p local=%d remote=%d bind error: %d\n", + msk, local_id, remote_id, err); goto failed; + } mptcp_crypto_key_sha(subflow->remote_key, &remote_token, NULL); - pr_debug("msk=%p remote_token=%u local_id=%d remote_id=%d", msk, + pr_debug("msk=%p remote_token=%u local_id=%d remote_id=%d\n", msk, remote_token, local_id, remote_id); subflow->remote_token = remote_token; WRITE_ONCE(subflow->remote_id, remote_id); subflow->request_join = 1; - subflow->request_bkup = !!(flags & MPTCP_PM_ADDR_FLAG_BACKUP); + subflow->request_bkup = !!(local->flags & MPTCP_PM_ADDR_FLAG_BACKUP); subflow->subflow_id = msk->subflow_id++; mptcp_info2sockaddr(remote, &addr, ssk->sk_family); sock_hold(ssk); list_add_tail(&subflow->node, &msk->conn_list); err = kernel_connect(sf, (struct sockaddr *)&addr, addrlen, O_NONBLOCK); - if (err && err != -EINPROGRESS) + if (err && err != -EINPROGRESS) { + MPTCP_INC_STATS(sock_net(sk), MPTCP_MIB_JOINSYNTXCONNECTERR); + pr_debug("msk=%p local=%d remote=%d connect error: %d\n", + msk, local_id, remote_id, err); goto failed_unlink; + } + + MPTCP_INC_STATS(sock_net(sk), MPTCP_MIB_JOINSYNTX); /* discard the subflow socket */ mptcp_sock_graft(ssk, sk->sk_socket); @@ -1719,7 +1766,7 @@ int mptcp_subflow_create_socket(struct sock *sk, unsigned short family, mptcp_sockopt_sync_locked(mptcp_sk(sk), sf->sk); release_sock(sf->sk); - /* the newly created socket really belongs to the owning MPTCP master + /* the newly created socket really belongs to the owning MPTCP * socket, even if for additional subflows the allocation is performed * by a kernel workqueue. Adjust inode references, so that the * procfs/diag interfaces really show this one belonging to the correct @@ -1730,7 +1777,7 @@ int mptcp_subflow_create_socket(struct sock *sk, unsigned short family, SOCK_INODE(sf)->i_gid = SOCK_INODE(sk->sk_socket)->i_gid; subflow = mptcp_subflow_ctx(sf->sk); - pr_debug("subflow=%p", subflow); + pr_debug("subflow=%p\n", subflow); *new_sock = sf; sock_hold(sk); @@ -1759,7 +1806,7 @@ static struct mptcp_subflow_context *subflow_create_ctx(struct sock *sk, INIT_LIST_HEAD(&ctx->node); INIT_LIST_HEAD(&ctx->delegated_node); - pr_debug("subflow=%p", ctx); + pr_debug("subflow=%p\n", ctx); ctx->tcp_sock = sk; WRITE_ONCE(ctx->local_id, -1); @@ -1910,7 +1957,7 @@ static int subflow_ulp_init(struct sock *sk) goto out; } - pr_debug("subflow=%p, family=%d", ctx, sk->sk_family); + pr_debug("subflow=%p, family=%d\n", ctx, sk->sk_family); tp->is_mptcp = 1; ctx->icsk_af_ops = icsk->icsk_af_ops; @@ -2005,6 +2052,7 @@ static void subflow_ulp_clone(const struct request_sock *req, new_ctx->fully_established = 1; new_ctx->remote_key_valid = 1; new_ctx->backup = subflow_req->backup; + new_ctx->request_bkup = subflow_req->request_bkup; WRITE_ONCE(new_ctx->remote_id, subflow_req->remote_id); new_ctx->token = subflow_req->token; new_ctx->thmac = subflow_req->thmac; diff --git a/net/netfilter/Makefile b/net/netfilter/Makefile index 614815a3ed73..f0aa4d7ef499 100644 --- a/net/netfilter/Makefile +++ b/net/netfilter/Makefile @@ -142,8 +142,13 @@ obj-$(CONFIG_NFT_FWD_NETDEV) += nft_fwd_netdev.o # flow table infrastructure obj-$(CONFIG_NF_FLOW_TABLE) += nf_flow_table.o nf_flow_table-objs := nf_flow_table_core.o nf_flow_table_ip.o \ - nf_flow_table_offload.o + nf_flow_table_offload.o nf_flow_table_xdp.o nf_flow_table-$(CONFIG_NF_FLOW_TABLE_PROCFS) += nf_flow_table_procfs.o +ifeq ($(CONFIG_NF_FLOW_TABLE),m) +nf_flow_table-$(CONFIG_DEBUG_INFO_BTF_MODULES) += nf_flow_table_bpf.o +else ifeq ($(CONFIG_NF_FLOW_TABLE),y) +nf_flow_table-$(CONFIG_DEBUG_INFO_BTF) += nf_flow_table_bpf.o +endif obj-$(CONFIG_NF_FLOW_TABLE_INET) += nf_flow_table_inet.o diff --git a/net/netfilter/core.c b/net/netfilter/core.c index b00fc285b334..b9f551f02c81 100644 --- a/net/netfilter/core.c +++ b/net/netfilter/core.c @@ -655,11 +655,9 @@ void nf_hook_slow_list(struct list_head *head, struct nf_hook_state *state, const struct nf_hook_entries *e) { struct sk_buff *skb, *next; - struct list_head sublist; + LIST_HEAD(sublist); int ret; - INIT_LIST_HEAD(&sublist); - list_for_each_entry_safe(skb, next, head, list) { skb_list_del_init(skb); ret = nf_hook_slow(skb, state, e, 0); diff --git a/net/netfilter/ipvs/ip_vs_ctl.c b/net/netfilter/ipvs/ip_vs_ctl.c index b6d0dcf3a5c3..dc6ddc4abbe2 100644 --- a/net/netfilter/ipvs/ip_vs_ctl.c +++ b/net/netfilter/ipvs/ip_vs_ctl.c @@ -1459,18 +1459,18 @@ ip_vs_add_service(struct netns_ipvs *ipvs, struct ip_vs_service_user_kern *u, if (ret < 0) goto out_err; - /* Bind the ct retriever */ - RCU_INIT_POINTER(svc->pe, pe); - pe = NULL; - /* Update the virtual service counters */ if (svc->port == FTPPORT) atomic_inc(&ipvs->ftpsvc_counter); else if (svc->port == 0) atomic_inc(&ipvs->nullsvc_counter); - if (svc->pe && svc->pe->conn_out) + if (pe && pe->conn_out) atomic_inc(&ipvs->conn_out_counter); + /* Bind the ct retriever */ + RCU_INIT_POINTER(svc->pe, pe); + pe = NULL; + /* Count only IPv4 services for old get/setsockopt interface */ if (svc->af == AF_INET) ipvs->num_services++; @@ -1846,7 +1846,7 @@ static int ip_vs_zero_all(struct netns_ipvs *ipvs) #ifdef CONFIG_SYSCTL static int -proc_do_defense_mode(struct ctl_table *table, int write, +proc_do_defense_mode(const struct ctl_table *table, int write, void *buffer, size_t *lenp, loff_t *ppos) { struct netns_ipvs *ipvs = table->extra2; @@ -1873,7 +1873,7 @@ proc_do_defense_mode(struct ctl_table *table, int write, } static int -proc_do_sync_threshold(struct ctl_table *table, int write, +proc_do_sync_threshold(const struct ctl_table *table, int write, void *buffer, size_t *lenp, loff_t *ppos) { struct netns_ipvs *ipvs = table->extra2; @@ -1901,7 +1901,7 @@ proc_do_sync_threshold(struct ctl_table *table, int write, } static int -proc_do_sync_ports(struct ctl_table *table, int write, +proc_do_sync_ports(const struct ctl_table *table, int write, void *buffer, size_t *lenp, loff_t *ppos) { int *valp = table->data; @@ -1924,7 +1924,8 @@ proc_do_sync_ports(struct ctl_table *table, int write, return rc; } -static int ipvs_proc_est_cpumask_set(struct ctl_table *table, void *buffer) +static int ipvs_proc_est_cpumask_set(const struct ctl_table *table, + void *buffer) { struct netns_ipvs *ipvs = table->extra2; cpumask_var_t *valp = table->data; @@ -1962,8 +1963,8 @@ out: return ret; } -static int ipvs_proc_est_cpumask_get(struct ctl_table *table, void *buffer, - size_t size) +static int ipvs_proc_est_cpumask_get(const struct ctl_table *table, + void *buffer, size_t size) { struct netns_ipvs *ipvs = table->extra2; cpumask_var_t *valp = table->data; @@ -1983,7 +1984,7 @@ static int ipvs_proc_est_cpumask_get(struct ctl_table *table, void *buffer, return ret; } -static int ipvs_proc_est_cpulist(struct ctl_table *table, int write, +static int ipvs_proc_est_cpulist(const struct ctl_table *table, int write, void *buffer, size_t *lenp, loff_t *ppos) { int ret; @@ -2010,7 +2011,7 @@ static int ipvs_proc_est_cpulist(struct ctl_table *table, int write, return ret; } -static int ipvs_proc_est_nice(struct ctl_table *table, int write, +static int ipvs_proc_est_nice(const struct ctl_table *table, int write, void *buffer, size_t *lenp, loff_t *ppos) { struct netns_ipvs *ipvs = table->extra2; @@ -2040,7 +2041,7 @@ static int ipvs_proc_est_nice(struct ctl_table *table, int write, return ret; } -static int ipvs_proc_run_estimation(struct ctl_table *table, int write, +static int ipvs_proc_run_estimation(const struct ctl_table *table, int write, void *buffer, size_t *lenp, loff_t *ppos) { struct netns_ipvs *ipvs = table->extra2; diff --git a/net/netfilter/ipvs/ip_vs_proto_sctp.c b/net/netfilter/ipvs/ip_vs_proto_sctp.c index 1e689c714127..83e452916403 100644 --- a/net/netfilter/ipvs/ip_vs_proto_sctp.c +++ b/net/netfilter/ipvs/ip_vs_proto_sctp.c @@ -126,7 +126,7 @@ sctp_snat_handler(struct sk_buff *skb, struct ip_vs_protocol *pp, if (sctph->source != cp->vport || payload_csum || skb->ip_summed == CHECKSUM_PARTIAL) { sctph->source = cp->vport; - if (!skb_is_gso(skb) || !skb_is_gso_sctp(skb)) + if (!skb_is_gso(skb)) sctp_nat_csum(skb, sctph, sctphoff); } else { skb->ip_summed = CHECKSUM_UNNECESSARY; @@ -175,7 +175,7 @@ sctp_dnat_handler(struct sk_buff *skb, struct ip_vs_protocol *pp, (skb->ip_summed == CHECKSUM_PARTIAL && !(skb_dst(skb)->dev->features & NETIF_F_SCTP_CRC))) { sctph->dest = cp->dport; - if (!skb_is_gso(skb) || !skb_is_gso_sctp(skb)) + if (!skb_is_gso(skb)) sctp_nat_csum(skb, sctph, sctphoff); } else if (skb->ip_summed != CHECKSUM_PARTIAL) { skb->ip_summed = CHECKSUM_UNNECESSARY; diff --git a/net/netfilter/nf_conncount.c b/net/netfilter/nf_conncount.c index 8715617b02fe..4890af4dc263 100644 --- a/net/netfilter/nf_conncount.c +++ b/net/netfilter/nf_conncount.c @@ -321,7 +321,6 @@ insert_tree(struct net *net, struct nf_conncount_rb *rbconn; struct nf_conncount_tuple *conn; unsigned int count = 0, gc_count = 0; - u8 keylen = data->keylen; bool do_gc = true; spin_lock_bh(&nf_conncount_locks[hash]); @@ -333,7 +332,7 @@ restart: rbconn = rb_entry(*rbnode, struct nf_conncount_rb, node); parent = *rbnode; - diff = key_diff(key, rbconn->key, keylen); + diff = key_diff(key, rbconn->key, data->keylen); if (diff < 0) { rbnode = &((*rbnode)->rb_left); } else if (diff > 0) { @@ -378,7 +377,7 @@ restart: conn->tuple = *tuple; conn->zone = *zone; - memcpy(rbconn->key, key, sizeof(u32) * keylen); + memcpy(rbconn->key, key, sizeof(u32) * data->keylen); nf_conncount_list_init(&rbconn->list); list_add(&conn->node, &rbconn->list.head); @@ -403,7 +402,6 @@ count_tree(struct net *net, struct rb_node *parent; struct nf_conncount_rb *rbconn; unsigned int hash; - u8 keylen = data->keylen; hash = jhash2(key, data->keylen, conncount_rnd) % CONNCOUNT_SLOTS; root = &data->root[hash]; @@ -414,7 +412,7 @@ count_tree(struct net *net, rbconn = rb_entry(parent, struct nf_conncount_rb, node); - diff = key_diff(key, rbconn->key, keylen); + diff = key_diff(key, rbconn->key, data->keylen); if (diff < 0) { parent = rcu_dereference_raw(parent->rb_left); } else if (diff > 0) { @@ -524,11 +522,10 @@ unsigned int nf_conncount_count(struct net *net, } EXPORT_SYMBOL_GPL(nf_conncount_count); -struct nf_conncount_data *nf_conncount_init(struct net *net, unsigned int family, - unsigned int keylen) +struct nf_conncount_data *nf_conncount_init(struct net *net, unsigned int keylen) { struct nf_conncount_data *data; - int ret, i; + int i; if (keylen % sizeof(u32) || keylen / sizeof(u32) > MAX_KEYLEN || @@ -541,12 +538,6 @@ struct nf_conncount_data *nf_conncount_init(struct net *net, unsigned int family if (!data) return ERR_PTR(-ENOMEM); - ret = nf_ct_netns_get(net, family); - if (ret < 0) { - kfree(data); - return ERR_PTR(ret); - } - for (i = 0; i < ARRAY_SIZE(data->root); ++i) data->root[i] = RB_ROOT; @@ -583,13 +574,11 @@ static void destroy_tree(struct rb_root *r) } } -void nf_conncount_destroy(struct net *net, unsigned int family, - struct nf_conncount_data *data) +void nf_conncount_destroy(struct net *net, struct nf_conncount_data *data) { unsigned int i; cancel_work_sync(&data->gc_work); - nf_ct_netns_put(net, family); for (i = 0; i < ARRAY_SIZE(data->root); ++i) destroy_tree(&data->root[i]); diff --git a/net/netfilter/nf_conntrack_bpf.c b/net/netfilter/nf_conntrack_bpf.c index d2492d050fe6..4a136fc3a9c0 100644 --- a/net/netfilter/nf_conntrack_bpf.c +++ b/net/netfilter/nf_conntrack_bpf.c @@ -32,7 +32,9 @@ * -EINVAL - Passed NULL for bpf_tuple pointer * -EINVAL - opts->reserved is not 0 * -EINVAL - netns_id is less than -1 - * -EINVAL - opts__sz isn't NF_BPF_CT_OPTS_SZ (12) + * -EINVAL - opts__sz isn't NF_BPF_CT_OPTS_SZ (16) or 12 + * -EINVAL - opts->ct_zone_id set when + opts__sz isn't NF_BPF_CT_OPTS_SZ (16) * -EPROTO - l4proto isn't one of IPPROTO_TCP or IPPROTO_UDP * -ENONET - No network namespace found for netns_id * -ENOENT - Conntrack lookup could not find entry for tuple @@ -42,6 +44,8 @@ * Values: * IPPROTO_TCP, IPPROTO_UDP * @dir: - connection tracking tuple direction. + * @ct_zone_id - connection tracking zone id. + * @ct_zone_dir - connection tracking zone direction. * @reserved - Reserved member, will be reused for more options in future * Values: * 0 @@ -51,11 +55,13 @@ struct bpf_ct_opts { s32 error; u8 l4proto; u8 dir; - u8 reserved[2]; + u16 ct_zone_id; + u8 ct_zone_dir; + u8 reserved[3]; }; enum { - NF_BPF_CT_OPTS_SZ = 12, + NF_BPF_CT_OPTS_SZ = 16, }; static int bpf_nf_ct_tuple_parse(struct bpf_sock_tuple *bpf_tuple, @@ -104,12 +110,21 @@ __bpf_nf_ct_alloc_entry(struct net *net, struct bpf_sock_tuple *bpf_tuple, u32 timeout) { struct nf_conntrack_tuple otuple, rtuple; + struct nf_conntrack_zone ct_zone; struct nf_conn *ct; int err; - if (!opts || !bpf_tuple || opts->reserved[0] || opts->reserved[1] || - opts_len != NF_BPF_CT_OPTS_SZ) + if (!opts || !bpf_tuple) return ERR_PTR(-EINVAL); + if (!(opts_len == NF_BPF_CT_OPTS_SZ || opts_len == 12)) + return ERR_PTR(-EINVAL); + if (opts_len == NF_BPF_CT_OPTS_SZ) { + if (opts->reserved[0] || opts->reserved[1] || opts->reserved[2]) + return ERR_PTR(-EINVAL); + } else { + if (opts->ct_zone_id) + return ERR_PTR(-EINVAL); + } if (unlikely(opts->netns_id < BPF_F_CURRENT_NETNS)) return ERR_PTR(-EINVAL); @@ -130,7 +145,16 @@ __bpf_nf_ct_alloc_entry(struct net *net, struct bpf_sock_tuple *bpf_tuple, return ERR_PTR(-ENONET); } - ct = nf_conntrack_alloc(net, &nf_ct_zone_dflt, &otuple, &rtuple, + if (opts_len == NF_BPF_CT_OPTS_SZ) { + if (opts->ct_zone_dir == 0) + opts->ct_zone_dir = NF_CT_DEFAULT_ZONE_DIR; + nf_ct_zone_init(&ct_zone, + opts->ct_zone_id, opts->ct_zone_dir, 0); + } else { + ct_zone = nf_ct_zone_dflt; + } + + ct = nf_conntrack_alloc(net, &ct_zone, &otuple, &rtuple, GFP_ATOMIC); if (IS_ERR(ct)) goto out; @@ -152,12 +176,21 @@ static struct nf_conn *__bpf_nf_ct_lookup(struct net *net, { struct nf_conntrack_tuple_hash *hash; struct nf_conntrack_tuple tuple; + struct nf_conntrack_zone ct_zone; struct nf_conn *ct; int err; - if (!opts || !bpf_tuple || opts->reserved[0] || opts->reserved[1] || - opts_len != NF_BPF_CT_OPTS_SZ) + if (!opts || !bpf_tuple) return ERR_PTR(-EINVAL); + if (!(opts_len == NF_BPF_CT_OPTS_SZ || opts_len == 12)) + return ERR_PTR(-EINVAL); + if (opts_len == NF_BPF_CT_OPTS_SZ) { + if (opts->reserved[0] || opts->reserved[1] || opts->reserved[2]) + return ERR_PTR(-EINVAL); + } else { + if (opts->ct_zone_id) + return ERR_PTR(-EINVAL); + } if (unlikely(opts->l4proto != IPPROTO_TCP && opts->l4proto != IPPROTO_UDP)) return ERR_PTR(-EPROTO); if (unlikely(opts->netns_id < BPF_F_CURRENT_NETNS)) @@ -174,7 +207,16 @@ static struct nf_conn *__bpf_nf_ct_lookup(struct net *net, return ERR_PTR(-ENONET); } - hash = nf_conntrack_find_get(net, &nf_ct_zone_dflt, &tuple); + if (opts_len == NF_BPF_CT_OPTS_SZ) { + if (opts->ct_zone_dir == 0) + opts->ct_zone_dir = NF_CT_DEFAULT_ZONE_DIR; + nf_ct_zone_init(&ct_zone, + opts->ct_zone_id, opts->ct_zone_dir, 0); + } else { + ct_zone = nf_ct_zone_dflt; + } + + hash = nf_conntrack_find_get(net, &ct_zone, &tuple); if (opts->netns_id >= 0) put_net(net); if (!hash) @@ -245,7 +287,7 @@ __bpf_kfunc_start_defs(); * @opts - Additional options for allocation (documented above) * Cannot be NULL * @opts__sz - Length of the bpf_ct_opts structure - * Must be NF_BPF_CT_OPTS_SZ (12) + * Must be NF_BPF_CT_OPTS_SZ (16) or 12 */ __bpf_kfunc struct nf_conn___init * bpf_xdp_ct_alloc(struct xdp_md *xdp_ctx, struct bpf_sock_tuple *bpf_tuple, @@ -279,7 +321,7 @@ bpf_xdp_ct_alloc(struct xdp_md *xdp_ctx, struct bpf_sock_tuple *bpf_tuple, * @opts - Additional options for lookup (documented above) * Cannot be NULL * @opts__sz - Length of the bpf_ct_opts structure - * Must be NF_BPF_CT_OPTS_SZ (12) + * Must be NF_BPF_CT_OPTS_SZ (16) or 12 */ __bpf_kfunc struct nf_conn * bpf_xdp_ct_lookup(struct xdp_md *xdp_ctx, struct bpf_sock_tuple *bpf_tuple, @@ -312,7 +354,7 @@ bpf_xdp_ct_lookup(struct xdp_md *xdp_ctx, struct bpf_sock_tuple *bpf_tuple, * @opts - Additional options for allocation (documented above) * Cannot be NULL * @opts__sz - Length of the bpf_ct_opts structure - * Must be NF_BPF_CT_OPTS_SZ (12) + * Must be NF_BPF_CT_OPTS_SZ (16) or 12 */ __bpf_kfunc struct nf_conn___init * bpf_skb_ct_alloc(struct __sk_buff *skb_ctx, struct bpf_sock_tuple *bpf_tuple, @@ -347,7 +389,7 @@ bpf_skb_ct_alloc(struct __sk_buff *skb_ctx, struct bpf_sock_tuple *bpf_tuple, * @opts - Additional options for lookup (documented above) * Cannot be NULL * @opts__sz - Length of the bpf_ct_opts structure - * Must be NF_BPF_CT_OPTS_SZ (12) + * Must be NF_BPF_CT_OPTS_SZ (16) or 12 */ __bpf_kfunc struct nf_conn * bpf_skb_ct_lookup(struct __sk_buff *skb_ctx, struct bpf_sock_tuple *bpf_tuple, diff --git a/net/netfilter/nf_conntrack_core.c b/net/netfilter/nf_conntrack_core.c index 7ac20750c127..9db3e2b0b1c3 100644 --- a/net/netfilter/nf_conntrack_core.c +++ b/net/netfilter/nf_conntrack_core.c @@ -988,6 +988,56 @@ static void __nf_conntrack_insert_prepare(struct nf_conn *ct) tstamp->start = ktime_get_real_ns(); } +/** + * nf_ct_match_reverse - check if ct1 and ct2 refer to identical flow + * @ct1: conntrack in hash table to check against + * @ct2: merge candidate + * + * returns true if ct1 and ct2 happen to refer to the same flow, but + * in opposing directions, i.e. + * ct1: a:b -> c:d + * ct2: c:d -> a:b + * for both directions. If so, @ct2 should not have been created + * as the skb should have been picked up as ESTABLISHED flow. + * But ct1 was not yet committed to hash table before skb that created + * ct2 had arrived. + * + * Note we don't compare netns because ct entries in different net + * namespace cannot clash to begin with. + * + * @return: true if ct1 and ct2 are identical when swapping origin/reply. + */ +static bool +nf_ct_match_reverse(const struct nf_conn *ct1, const struct nf_conn *ct2) +{ + u16 id1, id2; + + if (!nf_ct_tuple_equal(&ct1->tuplehash[IP_CT_DIR_ORIGINAL].tuple, + &ct2->tuplehash[IP_CT_DIR_REPLY].tuple)) + return false; + + if (!nf_ct_tuple_equal(&ct1->tuplehash[IP_CT_DIR_REPLY].tuple, + &ct2->tuplehash[IP_CT_DIR_ORIGINAL].tuple)) + return false; + + id1 = nf_ct_zone_id(nf_ct_zone(ct1), IP_CT_DIR_ORIGINAL); + id2 = nf_ct_zone_id(nf_ct_zone(ct2), IP_CT_DIR_REPLY); + if (id1 != id2) + return false; + + id1 = nf_ct_zone_id(nf_ct_zone(ct1), IP_CT_DIR_REPLY); + id2 = nf_ct_zone_id(nf_ct_zone(ct2), IP_CT_DIR_ORIGINAL); + + return id1 == id2; +} + +static int nf_ct_can_merge(const struct nf_conn *ct, + const struct nf_conn *loser_ct) +{ + return nf_ct_match(ct, loser_ct) || + nf_ct_match_reverse(ct, loser_ct); +} + /* caller must hold locks to prevent concurrent changes */ static int __nf_ct_resolve_clash(struct sk_buff *skb, struct nf_conntrack_tuple_hash *h) @@ -999,11 +1049,7 @@ static int __nf_ct_resolve_clash(struct sk_buff *skb, loser_ct = nf_ct_get(skb, &ctinfo); - if (nf_ct_is_dying(ct)) - return NF_DROP; - - if (((ct->status & IPS_NAT_DONE_MASK) == 0) || - nf_ct_match(ct, loser_ct)) { + if (nf_ct_can_merge(ct, loser_ct)) { struct net *net = nf_ct_net(ct); nf_conntrack_get(&ct->ct_general); @@ -1090,7 +1136,7 @@ static int nf_ct_resolve_clash_harder(struct sk_buff *skb, u32 repl_idx) * A conntrack entry can be inserted to the connection tracking table * if there is no existing entry with an identical tuple. * - * If there is one, @skb (and the assocated, unconfirmed conntrack) has + * If there is one, @skb (and the associated, unconfirmed conntrack) has * to be dropped. In case @skb is retransmitted, next conntrack lookup * will find the already-existing entry. * @@ -1722,7 +1768,7 @@ init_conntrack(struct net *net, struct nf_conn *tmpl, ct = __nf_conntrack_alloc(net, zone, tuple, &repl_tuple, GFP_ATOMIC, hash); if (IS_ERR(ct)) - return (struct nf_conntrack_tuple_hash *)ct; + return ERR_CAST(ct); if (!nf_ct_add_synproxy(ct, tmpl)) { nf_conntrack_free(ct); @@ -2151,80 +2197,6 @@ static void nf_conntrack_attach(struct sk_buff *nskb, const struct sk_buff *skb) nf_conntrack_get(skb_nfct(nskb)); } -static int __nf_conntrack_update(struct net *net, struct sk_buff *skb, - struct nf_conn *ct, - enum ip_conntrack_info ctinfo) -{ - const struct nf_nat_hook *nat_hook; - struct nf_conntrack_tuple_hash *h; - struct nf_conntrack_tuple tuple; - unsigned int status; - int dataoff; - u16 l3num; - u8 l4num; - - l3num = nf_ct_l3num(ct); - - dataoff = get_l4proto(skb, skb_network_offset(skb), l3num, &l4num); - if (dataoff <= 0) - return NF_DROP; - - if (!nf_ct_get_tuple(skb, skb_network_offset(skb), dataoff, l3num, - l4num, net, &tuple)) - return NF_DROP; - - if (ct->status & IPS_SRC_NAT) { - memcpy(tuple.src.u3.all, - ct->tuplehash[IP_CT_DIR_ORIGINAL].tuple.src.u3.all, - sizeof(tuple.src.u3.all)); - tuple.src.u.all = - ct->tuplehash[IP_CT_DIR_ORIGINAL].tuple.src.u.all; - } - - if (ct->status & IPS_DST_NAT) { - memcpy(tuple.dst.u3.all, - ct->tuplehash[IP_CT_DIR_ORIGINAL].tuple.dst.u3.all, - sizeof(tuple.dst.u3.all)); - tuple.dst.u.all = - ct->tuplehash[IP_CT_DIR_ORIGINAL].tuple.dst.u.all; - } - - h = nf_conntrack_find_get(net, nf_ct_zone(ct), &tuple); - if (!h) - return NF_ACCEPT; - - /* Store status bits of the conntrack that is clashing to re-do NAT - * mangling according to what it has been done already to this packet. - */ - status = ct->status; - - nf_ct_put(ct); - ct = nf_ct_tuplehash_to_ctrack(h); - nf_ct_set(skb, ct, ctinfo); - - nat_hook = rcu_dereference(nf_nat_hook); - if (!nat_hook) - return NF_ACCEPT; - - if (status & IPS_SRC_NAT) { - unsigned int verdict = nat_hook->manip_pkt(skb, ct, - NF_NAT_MANIP_SRC, - IP_CT_DIR_ORIGINAL); - if (verdict != NF_ACCEPT) - return verdict; - } - - if (status & IPS_DST_NAT) { - unsigned int verdict = nat_hook->manip_pkt(skb, ct, - NF_NAT_MANIP_DST, - IP_CT_DIR_ORIGINAL); - if (verdict != NF_ACCEPT) - return verdict; - } - - return NF_ACCEPT; -} - /* This packet is coming from userspace via nf_queue, complete the packet * processing after the helper invocation in nf_confirm(). */ @@ -2288,17 +2260,6 @@ static int nf_conntrack_update(struct net *net, struct sk_buff *skb) if (!ct) return NF_ACCEPT; - if (!nf_ct_is_confirmed(ct)) { - int ret = __nf_conntrack_update(net, skb, ct, ctinfo); - - if (ret != NF_ACCEPT) - return ret; - - ct = nf_ct_get(skb, &ctinfo); - if (!ct) - return NF_ACCEPT; - } - return nf_confirm_cthelper(skb, ct, ctinfo); } diff --git a/net/netfilter/nf_conntrack_netlink.c b/net/netfilter/nf_conntrack_netlink.c index 3b846cbdc050..6a1239433830 100644 --- a/net/netfilter/nf_conntrack_netlink.c +++ b/net/netfilter/nf_conntrack_netlink.c @@ -382,7 +382,7 @@ nla_put_failure: #define ctnetlink_dump_secctx(a, b) (0) #endif -#ifdef CONFIG_NF_CONNTRACK_LABELS +#ifdef CONFIG_NF_CONNTRACK_EVENTS static inline int ctnetlink_label_size(const struct nf_conn *ct) { struct nf_conn_labels *labels = nf_ct_labels_find(ct); @@ -391,6 +391,7 @@ static inline int ctnetlink_label_size(const struct nf_conn *ct) return 0; return nla_total_size(sizeof(labels->bits)); } +#endif static int ctnetlink_dump_labels(struct sk_buff *skb, const struct nf_conn *ct) @@ -411,10 +412,6 @@ ctnetlink_dump_labels(struct sk_buff *skb, const struct nf_conn *ct) return 0; } -#else -#define ctnetlink_dump_labels(a, b) (0) -#define ctnetlink_label_size(a) (0) -#endif #define master_tuple(ct) &(ct->master->tuplehash[IP_CT_DIR_ORIGINAL].tuple) @@ -652,7 +649,6 @@ static size_t ctnetlink_proto_size(const struct nf_conn *ct) return len + len4; } -#endif static inline size_t ctnetlink_acct_size(const struct nf_conn *ct) { @@ -690,6 +686,7 @@ static inline size_t ctnetlink_timestamp_size(const struct nf_conn *ct) return 0; #endif } +#endif #ifdef CONFIG_NF_CONNTRACK_EVENTS static size_t ctnetlink_nlmsg_size(const struct nf_conn *ct) @@ -1579,9 +1576,6 @@ static int ctnetlink_flush_conntrack(struct net *net, }; if (ctnetlink_needs_filter(family, cda)) { - if (cda[CTA_FILTER]) - return -EOPNOTSUPP; - filter = ctnetlink_alloc_filter(cda, family); if (IS_ERR(filter)) return PTR_ERR(filter); @@ -1610,14 +1604,14 @@ static int ctnetlink_del_conntrack(struct sk_buff *skb, if (err < 0) return err; - if (cda[CTA_TUPLE_ORIG]) + if (cda[CTA_TUPLE_ORIG] && !cda[CTA_FILTER]) err = ctnetlink_parse_tuple(cda, &tuple, CTA_TUPLE_ORIG, family, &zone); - else if (cda[CTA_TUPLE_REPLY]) + else if (cda[CTA_TUPLE_REPLY] && !cda[CTA_FILTER]) err = ctnetlink_parse_tuple(cda, &tuple, CTA_TUPLE_REPLY, family, &zone); else { - u_int8_t u3 = info->nfmsg->version ? family : AF_UNSPEC; + u8 u3 = info->nfmsg->version || cda[CTA_FILTER] ? family : AF_UNSPEC; return ctnetlink_flush_conntrack(info->net, cda, NETLINK_CB(skb).portid, @@ -3420,7 +3414,8 @@ static int ctnetlink_del_expect(struct sk_buff *skb, if (cda[CTA_EXPECT_ID]) { __be32 id = nla_get_be32(cda[CTA_EXPECT_ID]); - if (ntohl(id) != (u32)(unsigned long)exp) { + + if (id != nf_expect_get_id(exp)) { nf_ct_expect_put(exp); return -ENOENT; } diff --git a/net/netfilter/nf_conntrack_standalone.c b/net/netfilter/nf_conntrack_standalone.c index 6c40bdf8b05a..7d4f0fa8b609 100644 --- a/net/netfilter/nf_conntrack_standalone.c +++ b/net/netfilter/nf_conntrack_standalone.c @@ -524,7 +524,7 @@ EXPORT_SYMBOL_GPL(nf_conntrack_count); static unsigned int nf_conntrack_htable_size_user __read_mostly; static int -nf_conntrack_hash_sysctl(struct ctl_table *table, int write, +nf_conntrack_hash_sysctl(const struct ctl_table *table, int write, void *buffer, size_t *lenp, loff_t *ppos) { int ret; diff --git a/net/netfilter/nf_flow_table_bpf.c b/net/netfilter/nf_flow_table_bpf.c new file mode 100644 index 000000000000..4a5f5195f2d2 --- /dev/null +++ b/net/netfilter/nf_flow_table_bpf.c @@ -0,0 +1,121 @@ +// SPDX-License-Identifier: GPL-2.0-only +/* Unstable Flow Table Helpers for XDP hook + * + * These are called from the XDP programs. + * Note that it is allowed to break compatibility for these functions since + * the interface they are exposed through to BPF programs is explicitly + * unstable. + */ + +#include <linux/kernel.h> +#include <linux/init.h> +#include <linux/module.h> +#include <net/netfilter/nf_flow_table.h> +#include <linux/bpf.h> +#include <linux/btf.h> +#include <net/xdp.h> + +/* bpf_flowtable_opts - options for bpf flowtable helpers + * @error: out parameter, set for any encountered error + */ +struct bpf_flowtable_opts { + s32 error; +}; + +enum { + NF_BPF_FLOWTABLE_OPTS_SZ = 4, +}; + +__diag_push(); +__diag_ignore_all("-Wmissing-prototypes", + "Global functions as their definitions will be in nf_flow_table BTF"); + +__bpf_kfunc_start_defs(); + +static struct flow_offload_tuple_rhash * +bpf_xdp_flow_tuple_lookup(struct net_device *dev, + struct flow_offload_tuple *tuple, __be16 proto) +{ + struct flow_offload_tuple_rhash *tuplehash; + struct nf_flowtable *nf_flow_table; + struct flow_offload *nf_flow; + + nf_flow_table = nf_flowtable_by_dev(dev); + if (!nf_flow_table) + return ERR_PTR(-ENOENT); + + tuplehash = flow_offload_lookup(nf_flow_table, tuple); + if (!tuplehash) + return ERR_PTR(-ENOENT); + + nf_flow = container_of(tuplehash, struct flow_offload, + tuplehash[tuplehash->tuple.dir]); + flow_offload_refresh(nf_flow_table, nf_flow, false); + + return tuplehash; +} + +__bpf_kfunc struct flow_offload_tuple_rhash * +bpf_xdp_flow_lookup(struct xdp_md *ctx, struct bpf_fib_lookup *fib_tuple, + struct bpf_flowtable_opts *opts, u32 opts_len) +{ + struct xdp_buff *xdp = (struct xdp_buff *)ctx; + struct flow_offload_tuple tuple = { + .iifidx = fib_tuple->ifindex, + .l3proto = fib_tuple->family, + .l4proto = fib_tuple->l4_protocol, + .src_port = fib_tuple->sport, + .dst_port = fib_tuple->dport, + }; + struct flow_offload_tuple_rhash *tuplehash; + __be16 proto; + + if (opts_len != NF_BPF_FLOWTABLE_OPTS_SZ) { + opts->error = -EINVAL; + return NULL; + } + + switch (fib_tuple->family) { + case AF_INET: + tuple.src_v4.s_addr = fib_tuple->ipv4_src; + tuple.dst_v4.s_addr = fib_tuple->ipv4_dst; + proto = htons(ETH_P_IP); + break; + case AF_INET6: + tuple.src_v6 = *(struct in6_addr *)&fib_tuple->ipv6_src; + tuple.dst_v6 = *(struct in6_addr *)&fib_tuple->ipv6_dst; + proto = htons(ETH_P_IPV6); + break; + default: + opts->error = -EAFNOSUPPORT; + return NULL; + } + + tuplehash = bpf_xdp_flow_tuple_lookup(xdp->rxq->dev, &tuple, proto); + if (IS_ERR(tuplehash)) { + opts->error = PTR_ERR(tuplehash); + return NULL; + } + + return tuplehash; +} + +__diag_pop() + +__bpf_kfunc_end_defs(); + +BTF_KFUNCS_START(nf_ft_kfunc_set) +BTF_ID_FLAGS(func, bpf_xdp_flow_lookup, KF_TRUSTED_ARGS | KF_RET_NULL) +BTF_KFUNCS_END(nf_ft_kfunc_set) + +static const struct btf_kfunc_id_set nf_flow_kfunc_set = { + .owner = THIS_MODULE, + .set = &nf_ft_kfunc_set, +}; + +int nf_flow_register_bpf(void) +{ + return register_btf_kfunc_id_set(BPF_PROG_TYPE_XDP, + &nf_flow_kfunc_set); +} +EXPORT_SYMBOL_GPL(nf_flow_register_bpf); diff --git a/net/netfilter/nf_flow_table_core.c b/net/netfilter/nf_flow_table_core.c index 5c1ff07eaee0..df72b0376970 100644 --- a/net/netfilter/nf_flow_table_core.c +++ b/net/netfilter/nf_flow_table_core.c @@ -670,8 +670,14 @@ static int __init nf_flow_table_module_init(void) if (ret) goto out_offload; + ret = nf_flow_register_bpf(); + if (ret) + goto out_bpf; + return 0; +out_bpf: + nf_flow_table_offload_exit(); out_offload: unregister_pernet_subsys(&nf_flow_table_net_ops); return ret; diff --git a/net/netfilter/nf_flow_table_inet.c b/net/netfilter/nf_flow_table_inet.c index 6eef15648b7b..b0f199171932 100644 --- a/net/netfilter/nf_flow_table_inet.c +++ b/net/netfilter/nf_flow_table_inet.c @@ -17,6 +17,9 @@ nf_flow_offload_inet_hook(void *priv, struct sk_buff *skb, switch (skb->protocol) { case htons(ETH_P_8021Q): + if (!pskb_may_pull(skb, skb_mac_offset(skb) + sizeof(*veth))) + return NF_ACCEPT; + veth = (struct vlan_ethhdr *)skb_mac_header(skb); proto = veth->h_vlan_encapsulated_proto; break; diff --git a/net/netfilter/nf_flow_table_ip.c b/net/netfilter/nf_flow_table_ip.c index c2c005234dcd..98edcaa37b38 100644 --- a/net/netfilter/nf_flow_table_ip.c +++ b/net/netfilter/nf_flow_table_ip.c @@ -281,6 +281,9 @@ static bool nf_flow_skb_encap_protocol(struct sk_buff *skb, __be16 proto, switch (skb->protocol) { case htons(ETH_P_8021Q): + if (!pskb_may_pull(skb, skb_mac_offset(skb) + sizeof(*veth))) + return false; + veth = (struct vlan_ethhdr *)skb_mac_header(skb); if (veth->h_vlan_encapsulated_proto == proto) { *offset += VLAN_HLEN; diff --git a/net/netfilter/nf_flow_table_offload.c b/net/netfilter/nf_flow_table_offload.c index a010b25076ca..e06bc36f49fe 100644 --- a/net/netfilter/nf_flow_table_offload.c +++ b/net/netfilter/nf_flow_table_offload.c @@ -841,8 +841,8 @@ static int nf_flow_offload_tuple(struct nf_flowtable *flowtable, struct list_head *block_cb_list) { struct flow_cls_offload cls_flow = {}; + struct netlink_ext_ack extack = {}; struct flow_block_cb *block_cb; - struct netlink_ext_ack extack; __be16 proto = ETH_P_ALL; int err, i = 0; @@ -1192,7 +1192,7 @@ int nf_flow_table_offload_setup(struct nf_flowtable *flowtable, int err; if (!nf_flowtable_hw_offload(flowtable)) - return 0; + return nf_flow_offload_xdp_setup(flowtable, dev, cmd); if (dev->netdev_ops->ndo_setup_tc) err = nf_flow_table_offload_cmd(&bo, flowtable, dev, cmd, diff --git a/net/netfilter/nf_flow_table_xdp.c b/net/netfilter/nf_flow_table_xdp.c new file mode 100644 index 000000000000..e1252d042699 --- /dev/null +++ b/net/netfilter/nf_flow_table_xdp.c @@ -0,0 +1,147 @@ +// SPDX-License-Identifier: GPL-2.0-only +#include <linux/kernel.h> +#include <linux/module.h> +#include <linux/netfilter.h> +#include <linux/rhashtable.h> +#include <linux/netdevice.h> +#include <net/flow_offload.h> +#include <net/netfilter/nf_flow_table.h> + +struct flow_offload_xdp_ft { + struct list_head head; + struct nf_flowtable *ft; + struct rcu_head rcuhead; +}; + +struct flow_offload_xdp { + struct hlist_node hnode; + unsigned long net_device_addr; + struct list_head head; +}; + +#define NF_XDP_HT_BITS 4 +static DEFINE_HASHTABLE(nf_xdp_hashtable, NF_XDP_HT_BITS); +static DEFINE_MUTEX(nf_xdp_hashtable_lock); + +/* caller must hold rcu read lock */ +struct nf_flowtable *nf_flowtable_by_dev(const struct net_device *dev) +{ + unsigned long key = (unsigned long)dev; + struct flow_offload_xdp *iter; + + hash_for_each_possible_rcu(nf_xdp_hashtable, iter, hnode, key) { + if (key == iter->net_device_addr) { + struct flow_offload_xdp_ft *ft_elem; + + /* The user is supposed to insert a given net_device + * just into a single nf_flowtable so we always return + * the first element here. + */ + ft_elem = list_first_or_null_rcu(&iter->head, + struct flow_offload_xdp_ft, + head); + return ft_elem ? ft_elem->ft : NULL; + } + } + + return NULL; +} + +static int nf_flowtable_by_dev_insert(struct nf_flowtable *ft, + const struct net_device *dev) +{ + struct flow_offload_xdp *iter, *elem = NULL; + unsigned long key = (unsigned long)dev; + struct flow_offload_xdp_ft *ft_elem; + + ft_elem = kzalloc(sizeof(*ft_elem), GFP_KERNEL_ACCOUNT); + if (!ft_elem) + return -ENOMEM; + + ft_elem->ft = ft; + + mutex_lock(&nf_xdp_hashtable_lock); + + hash_for_each_possible(nf_xdp_hashtable, iter, hnode, key) { + if (key == iter->net_device_addr) { + elem = iter; + break; + } + } + + if (!elem) { + elem = kzalloc(sizeof(*elem), GFP_KERNEL_ACCOUNT); + if (!elem) + goto err_unlock; + + elem->net_device_addr = key; + INIT_LIST_HEAD(&elem->head); + hash_add_rcu(nf_xdp_hashtable, &elem->hnode, key); + } + list_add_tail_rcu(&ft_elem->head, &elem->head); + + mutex_unlock(&nf_xdp_hashtable_lock); + + return 0; + +err_unlock: + mutex_unlock(&nf_xdp_hashtable_lock); + kfree(ft_elem); + + return -ENOMEM; +} + +static void nf_flowtable_by_dev_remove(struct nf_flowtable *ft, + const struct net_device *dev) +{ + struct flow_offload_xdp *iter, *elem = NULL; + unsigned long key = (unsigned long)dev; + + mutex_lock(&nf_xdp_hashtable_lock); + + hash_for_each_possible(nf_xdp_hashtable, iter, hnode, key) { + if (key == iter->net_device_addr) { + elem = iter; + break; + } + } + + if (elem) { + struct flow_offload_xdp_ft *ft_elem, *ft_next; + + list_for_each_entry_safe(ft_elem, ft_next, &elem->head, head) { + if (ft_elem->ft == ft) { + list_del_rcu(&ft_elem->head); + kfree_rcu(ft_elem, rcuhead); + } + } + + if (list_empty(&elem->head)) + hash_del_rcu(&elem->hnode); + else + elem = NULL; + } + + mutex_unlock(&nf_xdp_hashtable_lock); + + if (elem) { + synchronize_rcu(); + kfree(elem); + } +} + +int nf_flow_offload_xdp_setup(struct nf_flowtable *flowtable, + struct net_device *dev, + enum flow_block_command cmd) +{ + switch (cmd) { + case FLOW_BLOCK_BIND: + return nf_flowtable_by_dev_insert(flowtable, dev); + case FLOW_BLOCK_UNBIND: + nf_flowtable_by_dev_remove(flowtable, dev); + return 0; + } + + WARN_ON_ONCE(1); + return 0; +} diff --git a/net/netfilter/nf_hooks_lwtunnel.c b/net/netfilter/nf_hooks_lwtunnel.c index 7cdb59bb4459..2d890dd04ff8 100644 --- a/net/netfilter/nf_hooks_lwtunnel.c +++ b/net/netfilter/nf_hooks_lwtunnel.c @@ -28,7 +28,7 @@ static inline int nf_hooks_lwtunnel_set(int enable) } #ifdef CONFIG_SYSCTL -int nf_hooks_lwtunnel_sysctl_handler(struct ctl_table *table, int write, +int nf_hooks_lwtunnel_sysctl_handler(const struct ctl_table *table, int write, void *buffer, size_t *lenp, loff_t *ppos) { int proc_nf_hooks_lwtunnel_enabled = 0; @@ -117,4 +117,7 @@ void netfilter_lwtunnel_fini(void) { unregister_pernet_subsys(&nf_lwtunnel_net_ops); } +#else +int __init netfilter_lwtunnel_init(void) { return 0; } +void netfilter_lwtunnel_fini(void) {} #endif /* CONFIG_SYSCTL */ diff --git a/net/netfilter/nf_log.c b/net/netfilter/nf_log.c index 769fd7680fac..6dd0de33eebd 100644 --- a/net/netfilter/nf_log.c +++ b/net/netfilter/nf_log.c @@ -408,7 +408,7 @@ static struct ctl_table nf_log_sysctl_ftable[] = { }, }; -static int nf_log_proc_dostring(struct ctl_table *table, int write, +static int nf_log_proc_dostring(const struct ctl_table *table, int write, void *buffer, size_t *lenp, loff_t *ppos) { const struct nf_logger *logger; diff --git a/net/netfilter/nf_nat_core.c b/net/netfilter/nf_nat_core.c index 016c816d91cb..4085c436e306 100644 --- a/net/netfilter/nf_nat_core.c +++ b/net/netfilter/nf_nat_core.c @@ -183,7 +183,35 @@ hash_by_src(const struct net *net, return reciprocal_scale(hash, nf_nat_htable_size); } -/* Is this tuple already taken? (not by us) */ +/** + * nf_nat_used_tuple - check if proposed nat tuple clashes with existing entry + * @tuple: proposed NAT binding + * @ignored_conntrack: our (unconfirmed) conntrack entry + * + * A conntrack entry can be inserted to the connection tracking table + * if there is no existing entry with an identical tuple in either direction. + * + * Example: + * INITIATOR -> NAT/PAT -> RESPONDER + * + * INITIATOR passes through NAT/PAT ("us") and SNAT is done (saddr rewrite). + * Then, later, NAT/PAT itself also connects to RESPONDER. + * + * This will not work if the SNAT done earlier has same IP:PORT source pair. + * + * Conntrack table has: + * ORIGINAL: $IP_INITIATOR:$SPORT -> $IP_RESPONDER:$DPORT + * REPLY: $IP_RESPONDER:$DPORT -> $IP_NAT:$SPORT + * + * and new locally originating connection wants: + * ORIGINAL: $IP_NAT:$SPORT -> $IP_RESPONDER:$DPORT + * REPLY: $IP_RESPONDER:$DPORT -> $IP_NAT:$SPORT + * + * ... which would mean incoming packets cannot be distinguished between + * the existing and the newly added entry (identical IP_CT_DIR_REPLY tuple). + * + * @return: true if the proposed NAT mapping collides with an existing entry. + */ static int nf_nat_used_tuple(const struct nf_conntrack_tuple *tuple, const struct nf_conn *ignored_conntrack) @@ -200,6 +228,94 @@ nf_nat_used_tuple(const struct nf_conntrack_tuple *tuple, return nf_conntrack_tuple_taken(&reply, ignored_conntrack); } +static bool nf_nat_allow_clash(const struct nf_conn *ct) +{ + return nf_ct_l4proto_find(nf_ct_protonum(ct))->allow_clash; +} + +/** + * nf_nat_used_tuple_new - check if to-be-inserted conntrack collides with existing entry + * @tuple: proposed NAT binding + * @ignored_ct: our (unconfirmed) conntrack entry + * + * Same as nf_nat_used_tuple, but also check for rare clash in reverse + * direction. Should be called only when @tuple has not been altered, i.e. + * @ignored_conntrack will not be subject to NAT. + * + * @return: true if the proposed NAT mapping collides with existing entry. + */ +static noinline bool +nf_nat_used_tuple_new(const struct nf_conntrack_tuple *tuple, + const struct nf_conn *ignored_ct) +{ + static const unsigned long uses_nat = IPS_NAT_MASK | IPS_SEQ_ADJUST_BIT; + const struct nf_conntrack_tuple_hash *thash; + const struct nf_conntrack_zone *zone; + struct nf_conn *ct; + bool taken = true; + struct net *net; + + if (!nf_nat_used_tuple(tuple, ignored_ct)) + return false; + + if (!nf_nat_allow_clash(ignored_ct)) + return true; + + /* Initial choice clashes with existing conntrack. + * Check for (rare) reverse collision. + * + * This can happen when new packets are received in both directions + * at the exact same time on different CPUs. + * + * Without SMP, first packet creates new conntrack entry and second + * packet is resolved as established reply packet. + * + * With parallel processing, both packets could be picked up as + * new and both get their own ct entry allocated. + * + * If ignored_conntrack and colliding ct are not subject to NAT then + * pretend the tuple is available and let later clash resolution + * handle this at insertion time. + * + * Without it, the 'reply' packet has its source port rewritten + * by nat engine. + */ + if (READ_ONCE(ignored_ct->status) & uses_nat) + return true; + + net = nf_ct_net(ignored_ct); + zone = nf_ct_zone(ignored_ct); + + thash = nf_conntrack_find_get(net, zone, tuple); + if (unlikely(!thash)) /* clashing entry went away */ + return false; + + ct = nf_ct_tuplehash_to_ctrack(thash); + + /* NB: IP_CT_DIR_ORIGINAL should be impossible because + * nf_nat_used_tuple() handles origin collisions. + * + * Handle remote chance other CPU confirmed its ct right after. + */ + if (thash->tuple.dst.dir != IP_CT_DIR_REPLY) + goto out; + + /* clashing connection subject to NAT? Retry with new tuple. */ + if (READ_ONCE(ct->status) & uses_nat) + goto out; + + if (nf_ct_tuple_equal(&ct->tuplehash[IP_CT_DIR_ORIGINAL].tuple, + &ignored_ct->tuplehash[IP_CT_DIR_REPLY].tuple) && + nf_ct_tuple_equal(&ct->tuplehash[IP_CT_DIR_REPLY].tuple, + &ignored_ct->tuplehash[IP_CT_DIR_ORIGINAL].tuple)) { + taken = false; + goto out; + } +out: + nf_ct_put(ct); + return taken; +} + static bool nf_nat_may_kill(struct nf_conn *ct, unsigned long flags) { static const unsigned long flags_refuse = IPS_FIXED_TIMEOUT | @@ -611,7 +727,7 @@ get_unique_tuple(struct nf_conntrack_tuple *tuple, !(range->flags & NF_NAT_RANGE_PROTO_RANDOM_ALL)) { /* try the original tuple first */ if (nf_in_range(orig_tuple, range)) { - if (!nf_nat_used_tuple(orig_tuple, ct)) { + if (!nf_nat_used_tuple_new(orig_tuple, ct)) { *tuple = *orig_tuple; return; } @@ -1104,7 +1220,7 @@ int nf_nat_register_fn(struct net *net, u8 pf, const struct nf_hook_ops *ops, if (!nat_proto_net->nat_hook_ops) { WARN_ON(nat_proto_net->users != 0); - nat_ops = kmemdup(orig_nat_ops, sizeof(*orig_nat_ops) * ops_count, GFP_KERNEL); + nat_ops = kmemdup_array(orig_nat_ops, ops_count, sizeof(*orig_nat_ops), GFP_KERNEL); if (!nat_ops) { mutex_unlock(&nf_nat_proto_mutex); return -ENOMEM; @@ -1208,7 +1324,6 @@ static const struct nf_nat_hook nat_hook = { #ifdef CONFIG_XFRM .decode_session = __nf_nat_decode_session, #endif - .manip_pkt = nf_nat_manip_pkt, .remove_nat_bysrc = nf_nat_cleanup_conntrack, }; diff --git a/net/netfilter/nf_tables_api.c b/net/netfilter/nf_tables_api.c index be3b4c90d2ed..a24fe62650a7 100644 --- a/net/netfilter/nf_tables_api.c +++ b/net/netfilter/nf_tables_api.c @@ -146,6 +146,8 @@ static void nft_ctx_init(struct nft_ctx *ctx, ctx->report = nlmsg_report(nlh); ctx->flags = nlh->nlmsg_flags; ctx->seq = nlh->nlmsg_seq; + + bitmap_zero(ctx->reg_inited, NFT_REG32_NUM); } static struct nft_trans *nft_trans_alloc_gfp(const struct nft_ctx *ctx, @@ -153,14 +155,18 @@ static struct nft_trans *nft_trans_alloc_gfp(const struct nft_ctx *ctx, { struct nft_trans *trans; - trans = kzalloc(sizeof(struct nft_trans) + size, gfp); + trans = kzalloc(size, gfp); if (trans == NULL) return NULL; INIT_LIST_HEAD(&trans->list); - INIT_LIST_HEAD(&trans->binding_list); trans->msg_type = msg_type; - trans->ctx = *ctx; + + trans->net = ctx->net; + trans->table = ctx->table; + trans->seq = ctx->seq; + trans->flags = ctx->flags; + trans->report = ctx->report; return trans; } @@ -171,10 +177,26 @@ static struct nft_trans *nft_trans_alloc(const struct nft_ctx *ctx, return nft_trans_alloc_gfp(ctx, msg_type, size, GFP_KERNEL); } +static struct nft_trans_binding *nft_trans_get_binding(struct nft_trans *trans) +{ + switch (trans->msg_type) { + case NFT_MSG_NEWCHAIN: + case NFT_MSG_NEWSET: + return container_of(trans, struct nft_trans_binding, nft_trans); + } + + return NULL; +} + static void nft_trans_list_del(struct nft_trans *trans) { + struct nft_trans_binding *trans_binding; + list_del(&trans->list); - list_del(&trans->binding_list); + + trans_binding = nft_trans_get_binding(trans); + if (trans_binding) + list_del(&trans_binding->binding_list); } static void nft_trans_destroy(struct nft_trans *trans) @@ -236,7 +258,7 @@ static void __nft_chain_trans_bind(const struct nft_ctx *ctx, nft_trans_chain_bound(trans) = bind; break; case NFT_MSG_NEWRULE: - if (trans->ctx.chain == chain) + if (nft_trans_rule_chain(trans) == chain) nft_trans_rule_bound(trans) = bind; break; } @@ -372,21 +394,31 @@ static void nf_tables_unregister_hook(struct net *net, static void nft_trans_commit_list_add_tail(struct net *net, struct nft_trans *trans) { struct nftables_pernet *nft_net = nft_pernet(net); + struct nft_trans_binding *binding; + struct nft_trans_set *trans_set; + + list_add_tail(&trans->list, &nft_net->commit_list); + + binding = nft_trans_get_binding(trans); + if (!binding) + return; switch (trans->msg_type) { case NFT_MSG_NEWSET: + trans_set = nft_trans_container_set(trans); + if (!nft_trans_set_update(trans) && nft_set_is_anonymous(nft_trans_set(trans))) - list_add_tail(&trans->binding_list, &nft_net->binding_list); + list_add_tail(&binding->binding_list, &nft_net->binding_list); + + list_add_tail(&trans_set->list_trans_newset, &nft_net->commit_set_list); break; case NFT_MSG_NEWCHAIN: if (!nft_trans_chain_update(trans) && nft_chain_binding(nft_trans_chain(trans))) - list_add_tail(&trans->binding_list, &nft_net->binding_list); + list_add_tail(&binding->binding_list, &nft_net->binding_list); break; } - - list_add_tail(&trans->list, &nft_net->commit_list); } static int nft_trans_table_add(struct nft_ctx *ctx, int msg_type) @@ -416,11 +448,28 @@ static int nft_deltable(struct nft_ctx *ctx) return err; } -static struct nft_trans *nft_trans_chain_add(struct nft_ctx *ctx, int msg_type) +static struct nft_trans * +nft_trans_alloc_chain(const struct nft_ctx *ctx, int msg_type) { + struct nft_trans_chain *trans_chain; struct nft_trans *trans; trans = nft_trans_alloc(ctx, msg_type, sizeof(struct nft_trans_chain)); + if (!trans) + return NULL; + + trans_chain = nft_trans_container_chain(trans); + INIT_LIST_HEAD(&trans_chain->nft_trans_binding.binding_list); + trans_chain->chain = ctx->chain; + + return trans; +} + +static struct nft_trans *nft_trans_chain_add(struct nft_ctx *ctx, int msg_type) +{ + struct nft_trans *trans; + + trans = nft_trans_alloc_chain(ctx, msg_type); if (trans == NULL) return ERR_PTR(-ENOMEM); @@ -432,7 +481,6 @@ static struct nft_trans *nft_trans_chain_add(struct nft_ctx *ctx, int msg_type) ntohl(nla_get_be32(ctx->nla[NFTA_CHAIN_ID])); } } - nft_trans_chain(trans) = ctx->chain; nft_trans_commit_list_add_tail(ctx->net, trans); return trans; @@ -505,6 +553,7 @@ static struct nft_trans *nft_trans_rule_add(struct nft_ctx *ctx, int msg_type, ntohl(nla_get_be32(ctx->nla[NFTA_RULE_ID])); } nft_trans_rule(trans) = rule; + nft_trans_rule_chain(trans) = ctx->chain; nft_trans_commit_list_add_tail(ctx->net, trans); return trans; @@ -560,12 +609,17 @@ static int __nft_trans_set_add(const struct nft_ctx *ctx, int msg_type, struct nft_set *set, const struct nft_set_desc *desc) { + struct nft_trans_set *trans_set; struct nft_trans *trans; trans = nft_trans_alloc(ctx, msg_type, sizeof(struct nft_trans_set)); if (trans == NULL) return -ENOMEM; + trans_set = nft_trans_container_set(trans); + INIT_LIST_HEAD(&trans_set->nft_trans_binding.binding_list); + INIT_LIST_HEAD(&trans_set->list_trans_newset); + if (msg_type == NFT_MSG_NEWSET && ctx->nla[NFTA_SET_ID] && !desc) { nft_trans_set_id(trans) = ntohl(nla_get_be32(ctx->nla[NFTA_SET_ID])); @@ -1217,11 +1271,11 @@ static bool nft_table_pending_update(const struct nft_ctx *ctx) return true; list_for_each_entry(trans, &nft_net->commit_list, list) { - if (trans->ctx.table == ctx->table && + if (trans->table == ctx->table && ((trans->msg_type == NFT_MSG_NEWCHAIN && nft_trans_chain_update(trans)) || (trans->msg_type == NFT_MSG_DELCHAIN && - nft_is_base_chain(trans->ctx.chain)))) + nft_is_base_chain(nft_trans_chain(trans))))) return true; } @@ -1615,15 +1669,15 @@ static int nf_tables_deltable(struct sk_buff *skb, const struct nfnl_info *info, return nft_flush_table(&ctx); } -static void nf_tables_table_destroy(struct nft_ctx *ctx) +static void nf_tables_table_destroy(struct nft_table *table) { - if (WARN_ON(ctx->table->use > 0)) + if (WARN_ON(table->use > 0)) return; - rhltable_destroy(&ctx->table->chains_ht); - kfree(ctx->table->name); - kfree(ctx->table->udata); - kfree(ctx->table); + rhltable_destroy(&table->chains_ht); + kfree(table->name); + kfree(table->udata); + kfree(table); } void nft_register_chain_type(const struct nft_chain_type *ctype) @@ -1795,7 +1849,7 @@ static int nft_dump_basechain_hook(struct sk_buff *skb, int family, if (!hook_list) hook_list = &basechain->hook_list; - list_for_each_entry(hook, hook_list, list) { + list_for_each_entry_rcu(hook, hook_list, list) { if (!first) first = hook; @@ -2049,18 +2103,19 @@ static struct nft_stats __percpu *nft_stats_alloc(const struct nlattr *attr) return newstats; } -static void nft_chain_stats_replace(struct nft_trans *trans) +static void nft_chain_stats_replace(struct nft_trans_chain *trans) { - struct nft_base_chain *chain = nft_base_chain(trans->ctx.chain); + const struct nft_trans *t = &trans->nft_trans_binding.nft_trans; + struct nft_base_chain *chain = nft_base_chain(trans->chain); - if (!nft_trans_chain_stats(trans)) + if (!trans->stats) return; - nft_trans_chain_stats(trans) = - rcu_replace_pointer(chain->stats, nft_trans_chain_stats(trans), - lockdep_commit_lock_is_held(trans->ctx.net)); + trans->stats = + rcu_replace_pointer(chain->stats, trans->stats, + lockdep_commit_lock_is_held(t->net)); - if (!nft_trans_chain_stats(trans)) + if (!trans->stats) static_branch_inc(&nft_counters_enabled); } @@ -2078,9 +2133,9 @@ static void nf_tables_chain_free_chain_rules(struct nft_chain *chain) kvfree(chain->blob_next); } -void nf_tables_chain_destroy(struct nft_ctx *ctx) +void nf_tables_chain_destroy(struct nft_chain *chain) { - struct nft_chain *chain = ctx->chain; + const struct nft_table *table = chain->table; struct nft_hook *hook, *next; if (WARN_ON(chain->use > 0)) @@ -2092,7 +2147,7 @@ void nf_tables_chain_destroy(struct nft_ctx *ctx) if (nft_is_base_chain(chain)) { struct nft_base_chain *basechain = nft_base_chain(chain); - if (nft_base_chain_netdev(ctx->family, basechain->ops.hooknum)) { + if (nft_base_chain_netdev(table->family, basechain->ops.hooknum)) { list_for_each_entry_safe(hook, next, &basechain->hook_list, list) { list_del_rcu(&hook->list); @@ -2581,7 +2636,7 @@ err_chain_add: err_trans: nft_use_dec_restore(&table->use); err_destroy_chain: - nf_tables_chain_destroy(ctx); + nf_tables_chain_destroy(chain); return err; } @@ -2698,8 +2753,7 @@ static int nf_tables_updchain(struct nft_ctx *ctx, u8 genmask, u8 policy, } err = -ENOMEM; - trans = nft_trans_alloc(ctx, NFT_MSG_NEWCHAIN, - sizeof(struct nft_trans_chain)); + trans = nft_trans_alloc_chain(ctx, NFT_MSG_NEWCHAIN); if (trans == NULL) goto err_trans; @@ -2725,7 +2779,7 @@ static int nf_tables_updchain(struct nft_ctx *ctx, u8 genmask, u8 policy, err = -EEXIST; list_for_each_entry(tmp, &nft_net->commit_list, list) { if (tmp->msg_type == NFT_MSG_NEWCHAIN && - tmp->ctx.table == table && + tmp->table == table && nft_trans_chain_update(tmp) && nft_trans_chain_name(tmp) && strcmp(name, nft_trans_chain_name(tmp)) == 0) { @@ -2774,13 +2828,11 @@ static struct nft_chain *nft_chain_lookup_byid(const struct net *net, struct nft_trans *trans; list_for_each_entry(trans, &nft_net->commit_list, list) { - struct nft_chain *chain = trans->ctx.chain; - if (trans->msg_type == NFT_MSG_NEWCHAIN && - chain->table == table && + nft_trans_chain(trans)->table == table && id == nft_trans_chain_id(trans) && - nft_active_genmask(chain, genmask)) - return chain; + nft_active_genmask(nft_trans_chain(trans), genmask)) + return nft_trans_chain(trans); } return ERR_PTR(-ENOENT); } @@ -2915,8 +2967,7 @@ static int nft_delchain_hook(struct nft_ctx *ctx, list_move(&hook->list, &chain_del_list); } - trans = nft_trans_alloc(ctx, NFT_MSG_DELCHAIN, - sizeof(struct nft_trans_chain)); + trans = nft_trans_alloc_chain(ctx, NFT_MSG_DELCHAIN); if (!trans) { err = -ENOMEM; goto err_chain_del_hook; @@ -3823,10 +3874,18 @@ static void nf_tables_rule_release(const struct nft_ctx *ctx, struct nft_rule *r nf_tables_rule_destroy(ctx, rule); } +/** nft_chain_validate - loop detection and hook validation + * + * @ctx: context containing call depth and base chain + * @chain: chain to validate + * + * Walk through the rules of the given chain and chase all jumps/gotos + * and set lookups until either the jump limit is hit or all reachable + * chains have been validated. + */ int nft_chain_validate(const struct nft_ctx *ctx, const struct nft_chain *chain) { struct nft_expr *expr, *last; - const struct nft_data *data; struct nft_rule *rule; int err; @@ -3844,7 +3903,10 @@ int nft_chain_validate(const struct nft_ctx *ctx, const struct nft_chain *chain) if (!expr->ops->validate) continue; - err = expr->ops->validate(ctx, expr, &data); + /* This may call nft_chain_validate() recursively, + * callers that do so must increment ctx->level. + */ + err = expr->ops->validate(ctx, expr); if (err < 0) return err; } @@ -4188,7 +4250,7 @@ static struct nft_rule *nft_rule_lookup_byid(const struct net *net, list_for_each_entry(trans, &nft_net->commit_list, list) { if (trans->msg_type == NFT_MSG_NEWRULE && - trans->ctx.chain == chain && + nft_trans_rule_chain(trans) == chain && id == nft_trans_rule_id(trans)) return nft_trans_rule(trans); } @@ -4430,17 +4492,16 @@ static struct nft_set *nft_set_lookup_byid(const struct net *net, { struct nftables_pernet *nft_net = nft_pernet(net); u32 id = ntohl(nla_get_be32(nla)); - struct nft_trans *trans; + struct nft_trans_set *trans; - list_for_each_entry(trans, &nft_net->commit_list, list) { - if (trans->msg_type == NFT_MSG_NEWSET) { - struct nft_set *set = nft_trans_set(trans); + /* its likely the id we need is at the tail, not at start */ + list_for_each_entry_reverse(trans, &nft_net->commit_set_list, list_trans_newset) { + struct nft_set *set = trans->set; - if (id == nft_trans_set_id(trans) && - set->table == table && - nft_active_genmask(set, genmask)) - return set; - } + if (id == trans->set_id && + set->table == table && + nft_active_genmask(set, genmask)) + return set; } return ERR_PTR(-ENOENT); } @@ -4532,7 +4593,7 @@ int nf_msecs_to_jiffies64(const struct nlattr *nla, u64 *result) return -ERANGE; ms *= NSEC_PER_MSEC; - *result = nsecs_to_jiffies64(ms); + *result = nsecs_to_jiffies64(ms) ? : !!ms; return 0; } @@ -5633,12 +5694,8 @@ const struct nft_set_ext_type nft_set_ext_types[] = { .align = __alignof__(u8), }, [NFT_SET_EXT_TIMEOUT] = { - .len = sizeof(u64), - .align = __alignof__(u64), - }, - [NFT_SET_EXT_EXPIRATION] = { - .len = sizeof(u64), - .align = __alignof__(u64), + .len = sizeof(struct nft_timeout), + .align = __alignof__(struct nft_timeout), }, [NFT_SET_EXT_USERDATA] = { .len = sizeof(struct nft_userdata), @@ -5740,8 +5797,7 @@ static int nf_tables_fill_setelem(struct sk_buff *skb, if (nft_set_ext_exists(ext, NFT_SET_EXT_DATA) && nft_data_dump(skb, NFTA_SET_ELEM_DATA, nft_set_ext_data(ext), - set->dtype == NFT_DATA_VERDICT ? NFT_DATA_VERDICT : NFT_DATA_VALUE, - set->dlen) < 0) + nft_set_datatype(set), set->dlen) < 0) goto nla_put_failure; if (nft_set_ext_exists(ext, NFT_SET_EXT_EXPRESSIONS) && @@ -5758,25 +5814,32 @@ static int nf_tables_fill_setelem(struct sk_buff *skb, htonl(*nft_set_ext_flags(ext)))) goto nla_put_failure; - if (nft_set_ext_exists(ext, NFT_SET_EXT_TIMEOUT) && - nla_put_be64(skb, NFTA_SET_ELEM_TIMEOUT, - nf_jiffies64_to_msecs(*nft_set_ext_timeout(ext)), - NFTA_SET_ELEM_PAD)) - goto nla_put_failure; + if (nft_set_ext_exists(ext, NFT_SET_EXT_TIMEOUT)) { + u64 timeout = READ_ONCE(nft_set_ext_timeout(ext)->timeout); + u64 set_timeout = READ_ONCE(set->timeout); + __be64 msecs = 0; + + if (set_timeout != timeout) { + msecs = nf_jiffies64_to_msecs(timeout); + if (nla_put_be64(skb, NFTA_SET_ELEM_TIMEOUT, msecs, + NFTA_SET_ELEM_PAD)) + goto nla_put_failure; + } - if (nft_set_ext_exists(ext, NFT_SET_EXT_EXPIRATION)) { - u64 expires, now = get_jiffies_64(); + if (timeout > 0) { + u64 expires, now = get_jiffies_64(); - expires = *nft_set_ext_expiration(ext); - if (time_before64(now, expires)) - expires -= now; - else - expires = 0; + expires = READ_ONCE(nft_set_ext_timeout(ext)->expiration); + if (time_before64(now, expires)) + expires -= now; + else + expires = 0; - if (nla_put_be64(skb, NFTA_SET_ELEM_EXPIRATION, - nf_jiffies64_to_msecs(expires), - NFTA_SET_ELEM_PAD)) - goto nla_put_failure; + if (nla_put_be64(skb, NFTA_SET_ELEM_EXPIRATION, + nf_jiffies64_to_msecs(expires), + NFTA_SET_ELEM_PAD)) + goto nla_put_failure; + } } if (nft_set_ext_exists(ext, NFT_SET_EXT_USERDATA)) { @@ -6439,13 +6502,14 @@ struct nft_elem_priv *nft_set_elem_init(const struct nft_set *set, nft_set_ext_data(ext), data, set->dlen) < 0) goto err_ext_check; - if (nft_set_ext_exists(ext, NFT_SET_EXT_EXPIRATION)) { - *nft_set_ext_expiration(ext) = get_jiffies_64() + expiration; + if (nft_set_ext_exists(ext, NFT_SET_EXT_TIMEOUT)) { + nft_set_ext_timeout(ext)->timeout = timeout; + if (expiration == 0) - *nft_set_ext_expiration(ext) += timeout; + expiration = timeout; + + nft_set_ext_timeout(ext)->expiration = get_jiffies_64() + expiration; } - if (nft_set_ext_exists(ext, NFT_SET_EXT_TIMEOUT)) - *nft_set_ext_timeout(ext) = timeout; return elem; @@ -6620,7 +6684,7 @@ static int nft_setelem_catchall_insert(const struct net *net, } } - catchall = kmalloc(sizeof(*catchall), GFP_KERNEL); + catchall = kmalloc(sizeof(*catchall), GFP_KERNEL_ACCOUNT); if (!catchall) return -ENOMEM; @@ -6788,6 +6852,7 @@ static int nft_add_set_elem(struct nft_ctx *ctx, struct nft_set *set, struct nft_data_desc desc; enum nft_registers dreg; struct nft_trans *trans; + u8 update_flags; u64 expiration; u64 timeout; int err, i; @@ -6856,17 +6921,23 @@ static int nft_add_set_elem(struct nft_ctx *ctx, struct nft_set *set, return err; } else if (set->flags & NFT_SET_TIMEOUT && !(flags & NFT_SET_ELEM_INTERVAL_END)) { - timeout = READ_ONCE(set->timeout); + timeout = set->timeout; } expiration = 0; if (nla[NFTA_SET_ELEM_EXPIRATION] != NULL) { if (!(set->flags & NFT_SET_TIMEOUT)) return -EINVAL; + if (timeout == 0) + return -EOPNOTSUPP; + err = nf_msecs_to_jiffies64(nla[NFTA_SET_ELEM_EXPIRATION], &expiration); if (err) return err; + + if (expiration > timeout) + return -ERANGE; } if (nla[NFTA_SET_ELEM_EXPR]) { @@ -6952,16 +7023,10 @@ static int nft_add_set_elem(struct nft_ctx *ctx, struct nft_set *set, goto err_parse_key_end; } - if (timeout > 0) { - err = nft_set_ext_add(&tmpl, NFT_SET_EXT_EXPIRATION); + if (set->flags & NFT_SET_TIMEOUT) { + err = nft_set_ext_add(&tmpl, NFT_SET_EXT_TIMEOUT); if (err < 0) goto err_parse_key_end; - - if (timeout != READ_ONCE(set->timeout)) { - err = nft_set_ext_add(&tmpl, NFT_SET_EXT_TIMEOUT); - if (err < 0) - goto err_parse_key_end; - } } if (num_exprs) { @@ -7099,8 +7164,30 @@ static int nft_add_set_elem(struct nft_ctx *ctx, struct nft_set *set, nft_set_ext_exists(ext2, NFT_SET_EXT_OBJREF) && *nft_set_ext_obj(ext) != *nft_set_ext_obj(ext2))) goto err_element_clash; - else if (!(nlmsg_flags & NLM_F_EXCL)) + else if (!(nlmsg_flags & NLM_F_EXCL)) { err = 0; + if (nft_set_ext_exists(ext2, NFT_SET_EXT_TIMEOUT)) { + update_flags = 0; + if (timeout != nft_set_ext_timeout(ext2)->timeout) { + nft_trans_elem_timeout(trans) = timeout; + if (expiration == 0) + expiration = timeout; + + update_flags |= NFT_TRANS_UPD_TIMEOUT; + } + if (expiration) { + nft_trans_elem_expiration(trans) = expiration; + update_flags |= NFT_TRANS_UPD_EXPIRATION; + } + + if (update_flags) { + nft_trans_elem_priv(trans) = elem_priv; + nft_trans_elem_update_flags(trans) = update_flags; + nft_trans_commit_list_add_tail(ctx->net, trans); + goto err_elem_free; + } + } + } } else if (err == -ENOTEMPTY) { /* ENOTEMPTY reports overlapping between this element * and an existing one. @@ -7966,6 +8053,19 @@ cont: return skb->len; } +static int nf_tables_dumpreset_obj(struct sk_buff *skb, + struct netlink_callback *cb) +{ + struct nftables_pernet *nft_net = nft_pernet(sock_net(skb->sk)); + int ret; + + mutex_lock(&nft_net->commit_mutex); + ret = nf_tables_dump_obj(skb, cb); + mutex_unlock(&nft_net->commit_mutex); + + return ret; +} + static int nf_tables_dump_obj_start(struct netlink_callback *cb) { struct nft_obj_dump_ctx *ctx = (void *)cb->ctx; @@ -7982,12 +8082,18 @@ static int nf_tables_dump_obj_start(struct netlink_callback *cb) if (nla[NFTA_OBJ_TYPE]) ctx->type = ntohl(nla_get_be32(nla[NFTA_OBJ_TYPE])); - if (NFNL_MSG_TYPE(cb->nlh->nlmsg_type) == NFT_MSG_GETOBJ_RESET) - ctx->reset = true; - return 0; } +static int nf_tables_dumpreset_obj_start(struct netlink_callback *cb) +{ + struct nft_obj_dump_ctx *ctx = (void *)cb->ctx; + + ctx->reset = true; + + return nf_tables_dump_obj_start(cb); +} + static int nf_tables_dump_obj_done(struct netlink_callback *cb) { struct nft_obj_dump_ctx *ctx = (void *)cb->ctx; @@ -7998,8 +8104,9 @@ static int nf_tables_dump_obj_done(struct netlink_callback *cb) } /* called with rcu_read_lock held */ -static int nf_tables_getobj(struct sk_buff *skb, const struct nfnl_info *info, - const struct nlattr * const nla[]) +static struct sk_buff * +nf_tables_getobj_single(u32 portid, const struct nfnl_info *info, + const struct nlattr * const nla[], bool reset) { struct netlink_ext_ack *extack = info->extack; u8 genmask = nft_genmask_cur(info->net); @@ -8008,72 +8115,109 @@ static int nf_tables_getobj(struct sk_buff *skb, const struct nfnl_info *info, struct net *net = info->net; struct nft_object *obj; struct sk_buff *skb2; - bool reset = false; u32 objtype; int err; - if (info->nlh->nlmsg_flags & NLM_F_DUMP) { - struct netlink_dump_control c = { - .start = nf_tables_dump_obj_start, - .dump = nf_tables_dump_obj, - .done = nf_tables_dump_obj_done, - .module = THIS_MODULE, - .data = (void *)nla, - }; - - return nft_netlink_dump_start_rcu(info->sk, skb, info->nlh, &c); - } - if (!nla[NFTA_OBJ_NAME] || !nla[NFTA_OBJ_TYPE]) - return -EINVAL; + return ERR_PTR(-EINVAL); table = nft_table_lookup(net, nla[NFTA_OBJ_TABLE], family, genmask, 0); if (IS_ERR(table)) { NL_SET_BAD_ATTR(extack, nla[NFTA_OBJ_TABLE]); - return PTR_ERR(table); + return ERR_CAST(table); } objtype = ntohl(nla_get_be32(nla[NFTA_OBJ_TYPE])); obj = nft_obj_lookup(net, table, nla[NFTA_OBJ_NAME], objtype, genmask); if (IS_ERR(obj)) { NL_SET_BAD_ATTR(extack, nla[NFTA_OBJ_NAME]); - return PTR_ERR(obj); + return ERR_CAST(obj); } skb2 = alloc_skb(NLMSG_GOODSIZE, GFP_ATOMIC); if (!skb2) - return -ENOMEM; + return ERR_PTR(-ENOMEM); + + err = nf_tables_fill_obj_info(skb2, net, portid, + info->nlh->nlmsg_seq, NFT_MSG_NEWOBJ, 0, + family, table, obj, reset); + if (err < 0) { + kfree_skb(skb2); + return ERR_PTR(err); + } - if (NFNL_MSG_TYPE(info->nlh->nlmsg_type) == NFT_MSG_GETOBJ_RESET) - reset = true; + return skb2; +} - if (reset) { - const struct nftables_pernet *nft_net; - char *buf; +static int nf_tables_getobj(struct sk_buff *skb, const struct nfnl_info *info, + const struct nlattr * const nla[]) +{ + u32 portid = NETLINK_CB(skb).portid; + struct sk_buff *skb2; - nft_net = nft_pernet(net); - buf = kasprintf(GFP_ATOMIC, "%s:%u", table->name, nft_net->base_seq); + if (info->nlh->nlmsg_flags & NLM_F_DUMP) { + struct netlink_dump_control c = { + .start = nf_tables_dump_obj_start, + .dump = nf_tables_dump_obj, + .done = nf_tables_dump_obj_done, + .module = THIS_MODULE, + .data = (void *)nla, + }; - audit_log_nfcfg(buf, - family, - 1, - AUDIT_NFT_OP_OBJ_RESET, - GFP_ATOMIC); - kfree(buf); + return nft_netlink_dump_start_rcu(info->sk, skb, info->nlh, &c); } - err = nf_tables_fill_obj_info(skb2, net, NETLINK_CB(skb).portid, - info->nlh->nlmsg_seq, NFT_MSG_NEWOBJ, 0, - family, table, obj, reset); - if (err < 0) - goto err_fill_obj_info; + skb2 = nf_tables_getobj_single(portid, info, nla, false); + if (IS_ERR(skb2)) + return PTR_ERR(skb2); - return nfnetlink_unicast(skb2, net, NETLINK_CB(skb).portid); + return nfnetlink_unicast(skb2, info->net, portid); +} -err_fill_obj_info: - kfree_skb(skb2); - return err; +static int nf_tables_getobj_reset(struct sk_buff *skb, + const struct nfnl_info *info, + const struct nlattr * const nla[]) +{ + struct nftables_pernet *nft_net = nft_pernet(info->net); + u32 portid = NETLINK_CB(skb).portid; + struct net *net = info->net; + struct sk_buff *skb2; + char *buf; + + if (info->nlh->nlmsg_flags & NLM_F_DUMP) { + struct netlink_dump_control c = { + .start = nf_tables_dumpreset_obj_start, + .dump = nf_tables_dumpreset_obj, + .done = nf_tables_dump_obj_done, + .module = THIS_MODULE, + .data = (void *)nla, + }; + + return nft_netlink_dump_start_rcu(info->sk, skb, info->nlh, &c); + } + + if (!try_module_get(THIS_MODULE)) + return -EINVAL; + rcu_read_unlock(); + mutex_lock(&nft_net->commit_mutex); + skb2 = nf_tables_getobj_single(portid, info, nla, true); + mutex_unlock(&nft_net->commit_mutex); + rcu_read_lock(); + module_put(THIS_MODULE); + + if (IS_ERR(skb2)) + return PTR_ERR(skb2); + + buf = kasprintf(GFP_ATOMIC, "%.*s:%u", + nla_len(nla[NFTA_OBJ_TABLE]), + (char *)nla_data(nla[NFTA_OBJ_TABLE]), + nft_net->base_seq); + audit_log_nfcfg(buf, info->nfmsg->nfgen_family, 1, + AUDIT_NFT_OP_OBJ_RESET, GFP_ATOMIC); + kfree(buf); + + return nfnetlink_unicast(skb2, net, portid); } static void nft_obj_destroy(const struct nft_ctx *ctx, struct nft_object *obj) @@ -9063,7 +9207,7 @@ static void nf_tables_flowtable_destroy(struct nft_flowtable *flowtable) flowtable->data.type->setup(&flowtable->data, hook->ops.dev, FLOW_BLOCK_UNBIND); list_del_rcu(&hook->list); - kfree(hook); + kfree_rcu(hook, rcu); } kfree(flowtable->name); module_put(flowtable->data.type->owner); @@ -9356,7 +9500,7 @@ static const struct nfnl_callback nf_tables_cb[NFT_MSG_MAX] = { .policy = nft_obj_policy, }, [NFT_MSG_GETOBJ_RESET] = { - .call = nf_tables_getobj, + .call = nf_tables_getobj_reset, .type = NFNL_CB_RCU, .attr_count = NFTA_OBJ_MAX, .policy = nft_obj_policy, @@ -9418,51 +9562,53 @@ static int nf_tables_validate(struct net *net) * * We defer the drop policy until the transaction has been finalized. */ -static void nft_chain_commit_drop_policy(struct nft_trans *trans) +static void nft_chain_commit_drop_policy(struct nft_trans_chain *trans) { struct nft_base_chain *basechain; - if (nft_trans_chain_policy(trans) != NF_DROP) + if (trans->policy != NF_DROP) return; - if (!nft_is_base_chain(trans->ctx.chain)) + if (!nft_is_base_chain(trans->chain)) return; - basechain = nft_base_chain(trans->ctx.chain); + basechain = nft_base_chain(trans->chain); basechain->policy = NF_DROP; } -static void nft_chain_commit_update(struct nft_trans *trans) +static void nft_chain_commit_update(struct nft_trans_chain *trans) { + struct nft_table *table = trans->nft_trans_binding.nft_trans.table; struct nft_base_chain *basechain; - if (nft_trans_chain_name(trans)) { - rhltable_remove(&trans->ctx.table->chains_ht, - &trans->ctx.chain->rhlhead, + if (trans->name) { + rhltable_remove(&table->chains_ht, + &trans->chain->rhlhead, nft_chain_ht_params); - swap(trans->ctx.chain->name, nft_trans_chain_name(trans)); - rhltable_insert_key(&trans->ctx.table->chains_ht, - trans->ctx.chain->name, - &trans->ctx.chain->rhlhead, + swap(trans->chain->name, trans->name); + rhltable_insert_key(&table->chains_ht, + trans->chain->name, + &trans->chain->rhlhead, nft_chain_ht_params); } - if (!nft_is_base_chain(trans->ctx.chain)) + if (!nft_is_base_chain(trans->chain)) return; nft_chain_stats_replace(trans); - basechain = nft_base_chain(trans->ctx.chain); + basechain = nft_base_chain(trans->chain); - switch (nft_trans_chain_policy(trans)) { + switch (trans->policy) { case NF_DROP: case NF_ACCEPT: - basechain->policy = nft_trans_chain_policy(trans); + basechain->policy = trans->policy; break; } } -static void nft_obj_commit_update(struct nft_trans *trans) +static void nft_obj_commit_update(const struct nft_ctx *ctx, + struct nft_trans *trans) { struct nft_object *newobj; struct nft_object *obj; @@ -9474,15 +9620,21 @@ static void nft_obj_commit_update(struct nft_trans *trans) return; obj->ops->update(obj, newobj); - nft_obj_destroy(&trans->ctx, newobj); + nft_obj_destroy(ctx, newobj); } static void nft_commit_release(struct nft_trans *trans) { + struct nft_ctx ctx = { + .net = trans->net, + }; + + nft_ctx_update(&ctx, trans); + switch (trans->msg_type) { case NFT_MSG_DELTABLE: case NFT_MSG_DESTROYTABLE: - nf_tables_table_destroy(&trans->ctx); + nf_tables_table_destroy(trans->table); break; case NFT_MSG_NEWCHAIN: free_percpu(nft_trans_chain_stats(trans)); @@ -9493,25 +9645,25 @@ static void nft_commit_release(struct nft_trans *trans) if (nft_trans_chain_update(trans)) nft_hooks_destroy(&nft_trans_chain_hooks(trans)); else - nf_tables_chain_destroy(&trans->ctx); + nf_tables_chain_destroy(nft_trans_chain(trans)); break; case NFT_MSG_DELRULE: case NFT_MSG_DESTROYRULE: - nf_tables_rule_destroy(&trans->ctx, nft_trans_rule(trans)); + nf_tables_rule_destroy(&ctx, nft_trans_rule(trans)); break; case NFT_MSG_DELSET: case NFT_MSG_DESTROYSET: - nft_set_destroy(&trans->ctx, nft_trans_set(trans)); + nft_set_destroy(&ctx, nft_trans_set(trans)); break; case NFT_MSG_DELSETELEM: case NFT_MSG_DESTROYSETELEM: - nf_tables_set_elem_destroy(&trans->ctx, + nf_tables_set_elem_destroy(&ctx, nft_trans_elem_set(trans), nft_trans_elem_priv(trans)); break; case NFT_MSG_DELOBJ: case NFT_MSG_DESTROYOBJ: - nft_obj_destroy(&trans->ctx, nft_trans_obj(trans)); + nft_obj_destroy(&ctx, nft_trans_obj(trans)); break; case NFT_MSG_DELFLOWTABLE: case NFT_MSG_DESTROYFLOWTABLE: @@ -9523,7 +9675,7 @@ static void nft_commit_release(struct nft_trans *trans) } if (trans->put_net) - put_net(trans->ctx.net); + put_net(trans->net); kfree(trans); } @@ -9642,10 +9794,10 @@ static void nf_tables_commit_chain_prepare_cancel(struct net *net) struct nft_trans *trans, *next; list_for_each_entry_safe(trans, next, &nft_net->commit_list, list) { - struct nft_chain *chain = trans->ctx.chain; - if (trans->msg_type == NFT_MSG_NEWRULE || trans->msg_type == NFT_MSG_DELRULE) { + struct nft_chain *chain = nft_trans_rule_chain(trans); + kvfree(chain->blob_next); chain->blob_next = NULL; } @@ -10003,7 +10155,7 @@ static void nf_tables_commit_release(struct net *net) trans = list_last_entry(&nft_net->commit_list, struct nft_trans, list); - get_net(trans->ctx.net); + get_net(trans->net); WARN_ON_ONCE(trans->put_net); trans->put_net = true; @@ -10147,12 +10299,15 @@ static void nft_gc_seq_end(struct nftables_pernet *nft_net, unsigned int gc_seq) static int nf_tables_commit(struct net *net, struct sk_buff *skb) { struct nftables_pernet *nft_net = nft_pernet(net); + const struct nlmsghdr *nlh = nlmsg_hdr(skb); + struct nft_trans_binding *trans_binding; struct nft_trans *trans, *next; unsigned int base_seq, gc_seq; LIST_HEAD(set_update_list); struct nft_trans_elem *te; struct nft_chain *chain; struct nft_table *table; + struct nft_ctx ctx; LIST_HEAD(adl); int err; @@ -10161,7 +10316,10 @@ static int nf_tables_commit(struct net *net, struct sk_buff *skb) return 0; } - list_for_each_entry(trans, &nft_net->binding_list, binding_list) { + nft_ctx_init(&ctx, net, skb, nlh, NFPROTO_UNSPEC, NULL, NULL, NULL); + + list_for_each_entry(trans_binding, &nft_net->binding_list, binding_list) { + trans = &trans_binding->nft_trans; switch (trans->msg_type) { case NFT_MSG_NEWSET: if (!nft_trans_set_update(trans) && @@ -10179,6 +10337,9 @@ static int nf_tables_commit(struct net *net, struct sk_buff *skb) return -EINVAL; } break; + default: + WARN_ONCE(1, "Unhandled bind type %d", trans->msg_type); + break; } } @@ -10194,9 +10355,10 @@ static int nf_tables_commit(struct net *net, struct sk_buff *skb) /* 1. Allocate space for next generation rules_gen_X[] */ list_for_each_entry_safe(trans, next, &nft_net->commit_list, list) { + struct nft_table *table = trans->table; int ret; - ret = nf_tables_commit_audit_alloc(&adl, trans->ctx.table); + ret = nf_tables_commit_audit_alloc(&adl, table); if (ret) { nf_tables_commit_chain_prepare_cancel(net); nf_tables_commit_audit_free(&adl); @@ -10204,7 +10366,7 @@ static int nf_tables_commit(struct net *net, struct sk_buff *skb) } if (trans->msg_type == NFT_MSG_NEWRULE || trans->msg_type == NFT_MSG_DELRULE) { - chain = trans->ctx.chain; + chain = nft_trans_rule_chain(trans); ret = nf_tables_commit_chain_prepare(net, chain); if (ret < 0) { @@ -10237,70 +10399,71 @@ static int nf_tables_commit(struct net *net, struct sk_buff *skb) net->nft.gencursor = nft_gencursor_next(net); list_for_each_entry_safe(trans, next, &nft_net->commit_list, list) { - nf_tables_commit_audit_collect(&adl, trans->ctx.table, - trans->msg_type); + struct nft_table *table = trans->table; + + nft_ctx_update(&ctx, trans); + + nf_tables_commit_audit_collect(&adl, table, trans->msg_type); switch (trans->msg_type) { case NFT_MSG_NEWTABLE: if (nft_trans_table_update(trans)) { - if (!(trans->ctx.table->flags & __NFT_TABLE_F_UPDATE)) { + if (!(table->flags & __NFT_TABLE_F_UPDATE)) { nft_trans_destroy(trans); break; } - if (trans->ctx.table->flags & NFT_TABLE_F_DORMANT) - nf_tables_table_disable(net, trans->ctx.table); + if (table->flags & NFT_TABLE_F_DORMANT) + nf_tables_table_disable(net, table); - trans->ctx.table->flags &= ~__NFT_TABLE_F_UPDATE; + table->flags &= ~__NFT_TABLE_F_UPDATE; } else { - nft_clear(net, trans->ctx.table); + nft_clear(net, table); } - nf_tables_table_notify(&trans->ctx, NFT_MSG_NEWTABLE); + nf_tables_table_notify(&ctx, NFT_MSG_NEWTABLE); nft_trans_destroy(trans); break; case NFT_MSG_DELTABLE: case NFT_MSG_DESTROYTABLE: - list_del_rcu(&trans->ctx.table->list); - nf_tables_table_notify(&trans->ctx, trans->msg_type); + list_del_rcu(&table->list); + nf_tables_table_notify(&ctx, trans->msg_type); break; case NFT_MSG_NEWCHAIN: if (nft_trans_chain_update(trans)) { - nft_chain_commit_update(trans); - nf_tables_chain_notify(&trans->ctx, NFT_MSG_NEWCHAIN, + nft_chain_commit_update(nft_trans_container_chain(trans)); + nf_tables_chain_notify(&ctx, NFT_MSG_NEWCHAIN, &nft_trans_chain_hooks(trans)); list_splice(&nft_trans_chain_hooks(trans), &nft_trans_basechain(trans)->hook_list); /* trans destroyed after rcu grace period */ } else { - nft_chain_commit_drop_policy(trans); - nft_clear(net, trans->ctx.chain); - nf_tables_chain_notify(&trans->ctx, NFT_MSG_NEWCHAIN, NULL); + nft_chain_commit_drop_policy(nft_trans_container_chain(trans)); + nft_clear(net, nft_trans_chain(trans)); + nf_tables_chain_notify(&ctx, NFT_MSG_NEWCHAIN, NULL); nft_trans_destroy(trans); } break; case NFT_MSG_DELCHAIN: case NFT_MSG_DESTROYCHAIN: if (nft_trans_chain_update(trans)) { - nf_tables_chain_notify(&trans->ctx, NFT_MSG_DELCHAIN, + nf_tables_chain_notify(&ctx, NFT_MSG_DELCHAIN, &nft_trans_chain_hooks(trans)); - if (!(trans->ctx.table->flags & NFT_TABLE_F_DORMANT)) { + if (!(table->flags & NFT_TABLE_F_DORMANT)) { nft_netdev_unregister_hooks(net, &nft_trans_chain_hooks(trans), true); } } else { - nft_chain_del(trans->ctx.chain); - nf_tables_chain_notify(&trans->ctx, NFT_MSG_DELCHAIN, + nft_chain_del(nft_trans_chain(trans)); + nf_tables_chain_notify(&ctx, NFT_MSG_DELCHAIN, NULL); - nf_tables_unregister_hook(trans->ctx.net, - trans->ctx.table, - trans->ctx.chain); + nf_tables_unregister_hook(ctx.net, ctx.table, + nft_trans_chain(trans)); } break; case NFT_MSG_NEWRULE: - nft_clear(trans->ctx.net, nft_trans_rule(trans)); - nf_tables_rule_notify(&trans->ctx, - nft_trans_rule(trans), + nft_clear(net, nft_trans_rule(trans)); + nf_tables_rule_notify(&ctx, nft_trans_rule(trans), NFT_MSG_NEWRULE); - if (trans->ctx.chain->flags & NFT_CHAIN_HW_OFFLOAD) + if (nft_trans_rule_chain(trans)->flags & NFT_CHAIN_HW_OFFLOAD) nft_flow_rule_destroy(nft_trans_flow_rule(trans)); nft_trans_destroy(trans); @@ -10308,17 +10471,16 @@ static int nf_tables_commit(struct net *net, struct sk_buff *skb) case NFT_MSG_DELRULE: case NFT_MSG_DESTROYRULE: list_del_rcu(&nft_trans_rule(trans)->list); - nf_tables_rule_notify(&trans->ctx, - nft_trans_rule(trans), + nf_tables_rule_notify(&ctx, nft_trans_rule(trans), trans->msg_type); - nft_rule_expr_deactivate(&trans->ctx, - nft_trans_rule(trans), + nft_rule_expr_deactivate(&ctx, nft_trans_rule(trans), NFT_TRANS_COMMIT); - if (trans->ctx.chain->flags & NFT_CHAIN_HW_OFFLOAD) + if (nft_trans_rule_chain(trans)->flags & NFT_CHAIN_HW_OFFLOAD) nft_flow_rule_destroy(nft_trans_flow_rule(trans)); break; case NFT_MSG_NEWSET: + list_del(&nft_trans_container_set(trans)->list_trans_newset); if (nft_trans_set_update(trans)) { struct nft_set *set = nft_trans_set(trans); @@ -10334,9 +10496,9 @@ static int nf_tables_commit(struct net *net, struct sk_buff *skb) */ if (nft_set_is_anonymous(nft_trans_set(trans)) && !list_empty(&nft_trans_set(trans)->bindings)) - nft_use_dec(&trans->ctx.table->use); + nft_use_dec(&table->use); } - nf_tables_set_notify(&trans->ctx, nft_trans_set(trans), + nf_tables_set_notify(&ctx, nft_trans_set(trans), NFT_MSG_NEWSET, GFP_KERNEL); nft_trans_destroy(trans); break; @@ -10344,14 +10506,29 @@ static int nf_tables_commit(struct net *net, struct sk_buff *skb) case NFT_MSG_DESTROYSET: nft_trans_set(trans)->dead = 1; list_del_rcu(&nft_trans_set(trans)->list); - nf_tables_set_notify(&trans->ctx, nft_trans_set(trans), + nf_tables_set_notify(&ctx, nft_trans_set(trans), trans->msg_type, GFP_KERNEL); break; case NFT_MSG_NEWSETELEM: - te = (struct nft_trans_elem *)trans->data; + te = nft_trans_container_elem(trans); + + if (te->update_flags) { + const struct nft_set_ext *ext = + nft_set_elem_ext(te->set, te->elem_priv); + + if (te->update_flags & NFT_TRANS_UPD_TIMEOUT) { + WRITE_ONCE(nft_set_ext_timeout(ext)->timeout, + te->timeout); + } + if (te->update_flags & NFT_TRANS_UPD_EXPIRATION) { + WRITE_ONCE(nft_set_ext_timeout(ext)->expiration, + get_jiffies_64() + te->expiration); + } + } else { + nft_setelem_activate(net, te->set, te->elem_priv); + } - nft_setelem_activate(net, te->set, te->elem_priv); - nf_tables_setelem_notify(&trans->ctx, te->set, + nf_tables_setelem_notify(&ctx, te->set, te->elem_priv, NFT_MSG_NEWSETELEM); if (te->set->ops->commit && @@ -10363,9 +10540,9 @@ static int nf_tables_commit(struct net *net, struct sk_buff *skb) break; case NFT_MSG_DELSETELEM: case NFT_MSG_DESTROYSETELEM: - te = (struct nft_trans_elem *)trans->data; + te = nft_trans_container_elem(trans); - nf_tables_setelem_notify(&trans->ctx, te->set, + nf_tables_setelem_notify(&ctx, te->set, te->elem_priv, trans->msg_type); nft_setelem_remove(net, te->set, te->elem_priv); @@ -10381,13 +10558,13 @@ static int nf_tables_commit(struct net *net, struct sk_buff *skb) break; case NFT_MSG_NEWOBJ: if (nft_trans_obj_update(trans)) { - nft_obj_commit_update(trans); - nf_tables_obj_notify(&trans->ctx, + nft_obj_commit_update(&ctx, trans); + nf_tables_obj_notify(&ctx, nft_trans_obj(trans), NFT_MSG_NEWOBJ); } else { nft_clear(net, nft_trans_obj(trans)); - nf_tables_obj_notify(&trans->ctx, + nf_tables_obj_notify(&ctx, nft_trans_obj(trans), NFT_MSG_NEWOBJ); nft_trans_destroy(trans); @@ -10396,14 +10573,14 @@ static int nf_tables_commit(struct net *net, struct sk_buff *skb) case NFT_MSG_DELOBJ: case NFT_MSG_DESTROYOBJ: nft_obj_del(nft_trans_obj(trans)); - nf_tables_obj_notify(&trans->ctx, nft_trans_obj(trans), + nf_tables_obj_notify(&ctx, nft_trans_obj(trans), trans->msg_type); break; case NFT_MSG_NEWFLOWTABLE: if (nft_trans_flowtable_update(trans)) { nft_trans_flowtable(trans)->data.flags = nft_trans_flowtable_flags(trans); - nf_tables_flowtable_notify(&trans->ctx, + nf_tables_flowtable_notify(&ctx, nft_trans_flowtable(trans), &nft_trans_flowtable_hooks(trans), NFT_MSG_NEWFLOWTABLE); @@ -10411,7 +10588,7 @@ static int nf_tables_commit(struct net *net, struct sk_buff *skb) &nft_trans_flowtable(trans)->hook_list); } else { nft_clear(net, nft_trans_flowtable(trans)); - nf_tables_flowtable_notify(&trans->ctx, + nf_tables_flowtable_notify(&ctx, nft_trans_flowtable(trans), NULL, NFT_MSG_NEWFLOWTABLE); @@ -10421,7 +10598,7 @@ static int nf_tables_commit(struct net *net, struct sk_buff *skb) case NFT_MSG_DELFLOWTABLE: case NFT_MSG_DESTROYFLOWTABLE: if (nft_trans_flowtable_update(trans)) { - nf_tables_flowtable_notify(&trans->ctx, + nf_tables_flowtable_notify(&ctx, nft_trans_flowtable(trans), &nft_trans_flowtable_hooks(trans), trans->msg_type); @@ -10429,7 +10606,7 @@ static int nf_tables_commit(struct net *net, struct sk_buff *skb) &nft_trans_flowtable_hooks(trans)); } else { list_del_rcu(&nft_trans_flowtable(trans)->list); - nf_tables_flowtable_notify(&trans->ctx, + nf_tables_flowtable_notify(&ctx, nft_trans_flowtable(trans), NULL, trans->msg_type); @@ -10471,28 +10648,32 @@ static void nf_tables_module_autoload(struct net *net) static void nf_tables_abort_release(struct nft_trans *trans) { + struct nft_ctx ctx = { }; + + nft_ctx_update(&ctx, trans); + switch (trans->msg_type) { case NFT_MSG_NEWTABLE: - nf_tables_table_destroy(&trans->ctx); + nf_tables_table_destroy(trans->table); break; case NFT_MSG_NEWCHAIN: if (nft_trans_chain_update(trans)) nft_hooks_destroy(&nft_trans_chain_hooks(trans)); else - nf_tables_chain_destroy(&trans->ctx); + nf_tables_chain_destroy(nft_trans_chain(trans)); break; case NFT_MSG_NEWRULE: - nf_tables_rule_destroy(&trans->ctx, nft_trans_rule(trans)); + nf_tables_rule_destroy(&ctx, nft_trans_rule(trans)); break; case NFT_MSG_NEWSET: - nft_set_destroy(&trans->ctx, nft_trans_set(trans)); + nft_set_destroy(&ctx, nft_trans_set(trans)); break; case NFT_MSG_NEWSETELEM: nft_set_elem_destroy(nft_trans_elem_set(trans), nft_trans_elem_priv(trans), true); break; case NFT_MSG_NEWOBJ: - nft_obj_destroy(&trans->ctx, nft_trans_obj(trans)); + nft_obj_destroy(&ctx, nft_trans_obj(trans)); break; case NFT_MSG_NEWFLOWTABLE: if (nft_trans_flowtable_update(trans)) @@ -10524,6 +10705,9 @@ static int __nf_tables_abort(struct net *net, enum nfnl_abort_action action) struct nft_trans *trans, *next; LIST_HEAD(set_update_list); struct nft_trans_elem *te; + struct nft_ctx ctx = { + .net = net, + }; int err = 0; if (action == NFNL_ABORT_VALIDATE && @@ -10532,37 +10716,41 @@ static int __nf_tables_abort(struct net *net, enum nfnl_abort_action action) list_for_each_entry_safe_reverse(trans, next, &nft_net->commit_list, list) { + struct nft_table *table = trans->table; + + nft_ctx_update(&ctx, trans); + switch (trans->msg_type) { case NFT_MSG_NEWTABLE: if (nft_trans_table_update(trans)) { - if (!(trans->ctx.table->flags & __NFT_TABLE_F_UPDATE)) { + if (!(table->flags & __NFT_TABLE_F_UPDATE)) { nft_trans_destroy(trans); break; } - if (trans->ctx.table->flags & __NFT_TABLE_F_WAS_DORMANT) { - nf_tables_table_disable(net, trans->ctx.table); - trans->ctx.table->flags |= NFT_TABLE_F_DORMANT; - } else if (trans->ctx.table->flags & __NFT_TABLE_F_WAS_AWAKEN) { - trans->ctx.table->flags &= ~NFT_TABLE_F_DORMANT; + if (table->flags & __NFT_TABLE_F_WAS_DORMANT) { + nf_tables_table_disable(net, table); + table->flags |= NFT_TABLE_F_DORMANT; + } else if (table->flags & __NFT_TABLE_F_WAS_AWAKEN) { + table->flags &= ~NFT_TABLE_F_DORMANT; } - if (trans->ctx.table->flags & __NFT_TABLE_F_WAS_ORPHAN) { - trans->ctx.table->flags &= ~NFT_TABLE_F_OWNER; - trans->ctx.table->nlpid = 0; + if (table->flags & __NFT_TABLE_F_WAS_ORPHAN) { + table->flags &= ~NFT_TABLE_F_OWNER; + table->nlpid = 0; } - trans->ctx.table->flags &= ~__NFT_TABLE_F_UPDATE; + table->flags &= ~__NFT_TABLE_F_UPDATE; nft_trans_destroy(trans); } else { - list_del_rcu(&trans->ctx.table->list); + list_del_rcu(&table->list); } break; case NFT_MSG_DELTABLE: case NFT_MSG_DESTROYTABLE: - nft_clear(trans->ctx.net, trans->ctx.table); + nft_clear(trans->net, table); nft_trans_destroy(trans); break; case NFT_MSG_NEWCHAIN: if (nft_trans_chain_update(trans)) { - if (!(trans->ctx.table->flags & NFT_TABLE_F_DORMANT)) { + if (!(table->flags & NFT_TABLE_F_DORMANT)) { nft_netdev_unregister_hooks(net, &nft_trans_chain_hooks(trans), true); @@ -10575,11 +10763,10 @@ static int __nf_tables_abort(struct net *net, enum nfnl_abort_action action) nft_trans_destroy(trans); break; } - nft_use_dec_restore(&trans->ctx.table->use); - nft_chain_del(trans->ctx.chain); - nf_tables_unregister_hook(trans->ctx.net, - trans->ctx.table, - trans->ctx.chain); + nft_use_dec_restore(&table->use); + nft_chain_del(nft_trans_chain(trans)); + nf_tables_unregister_hook(trans->net, table, + nft_trans_chain(trans)); } break; case NFT_MSG_DELCHAIN: @@ -10588,8 +10775,8 @@ static int __nf_tables_abort(struct net *net, enum nfnl_abort_action action) list_splice(&nft_trans_chain_hooks(trans), &nft_trans_basechain(trans)->hook_list); } else { - nft_use_inc_restore(&trans->ctx.table->use); - nft_clear(trans->ctx.net, trans->ctx.chain); + nft_use_inc_restore(&table->use); + nft_clear(trans->net, nft_trans_chain(trans)); } nft_trans_destroy(trans); break; @@ -10598,30 +10785,31 @@ static int __nf_tables_abort(struct net *net, enum nfnl_abort_action action) nft_trans_destroy(trans); break; } - nft_use_dec_restore(&trans->ctx.chain->use); + nft_use_dec_restore(&nft_trans_rule_chain(trans)->use); list_del_rcu(&nft_trans_rule(trans)->list); - nft_rule_expr_deactivate(&trans->ctx, + nft_rule_expr_deactivate(&ctx, nft_trans_rule(trans), NFT_TRANS_ABORT); - if (trans->ctx.chain->flags & NFT_CHAIN_HW_OFFLOAD) + if (nft_trans_rule_chain(trans)->flags & NFT_CHAIN_HW_OFFLOAD) nft_flow_rule_destroy(nft_trans_flow_rule(trans)); break; case NFT_MSG_DELRULE: case NFT_MSG_DESTROYRULE: - nft_use_inc_restore(&trans->ctx.chain->use); - nft_clear(trans->ctx.net, nft_trans_rule(trans)); - nft_rule_expr_activate(&trans->ctx, nft_trans_rule(trans)); - if (trans->ctx.chain->flags & NFT_CHAIN_HW_OFFLOAD) + nft_use_inc_restore(&nft_trans_rule_chain(trans)->use); + nft_clear(trans->net, nft_trans_rule(trans)); + nft_rule_expr_activate(&ctx, nft_trans_rule(trans)); + if (nft_trans_rule_chain(trans)->flags & NFT_CHAIN_HW_OFFLOAD) nft_flow_rule_destroy(nft_trans_flow_rule(trans)); nft_trans_destroy(trans); break; case NFT_MSG_NEWSET: + list_del(&nft_trans_container_set(trans)->list_trans_newset); if (nft_trans_set_update(trans)) { nft_trans_destroy(trans); break; } - nft_use_dec_restore(&trans->ctx.table->use); + nft_use_dec_restore(&table->use); if (nft_trans_set_bound(trans)) { nft_trans_destroy(trans); break; @@ -10631,20 +10819,24 @@ static int __nf_tables_abort(struct net *net, enum nfnl_abort_action action) break; case NFT_MSG_DELSET: case NFT_MSG_DESTROYSET: - nft_use_inc_restore(&trans->ctx.table->use); - nft_clear(trans->ctx.net, nft_trans_set(trans)); + nft_use_inc_restore(&table->use); + nft_clear(trans->net, nft_trans_set(trans)); if (nft_trans_set(trans)->flags & (NFT_SET_MAP | NFT_SET_OBJECT)) - nft_map_activate(&trans->ctx, nft_trans_set(trans)); + nft_map_activate(&ctx, nft_trans_set(trans)); nft_trans_destroy(trans); break; case NFT_MSG_NEWSETELEM: - if (nft_trans_elem_set_bound(trans)) { + if (nft_trans_elem_update_flags(trans) || + nft_trans_elem_set_bound(trans)) { nft_trans_destroy(trans); break; } - te = (struct nft_trans_elem *)trans->data; - nft_setelem_remove(net, te->set, te->elem_priv); + te = nft_trans_container_elem(trans); + if (!te->set->ops->abort || + nft_setelem_is_catchall(te->set, te->elem_priv)) + nft_setelem_remove(net, te->set, te->elem_priv); + if (!nft_setelem_is_catchall(te->set, te->elem_priv)) atomic_dec(&te->set->nelems); @@ -10656,7 +10848,7 @@ static int __nf_tables_abort(struct net *net, enum nfnl_abort_action action) break; case NFT_MSG_DELSETELEM: case NFT_MSG_DESTROYSETELEM: - te = (struct nft_trans_elem *)trans->data; + te = nft_trans_container_elem(trans); if (!nft_setelem_active_next(net, te->set, te->elem_priv)) { nft_setelem_data_activate(net, te->set, te->elem_priv); @@ -10674,17 +10866,17 @@ static int __nf_tables_abort(struct net *net, enum nfnl_abort_action action) break; case NFT_MSG_NEWOBJ: if (nft_trans_obj_update(trans)) { - nft_obj_destroy(&trans->ctx, nft_trans_obj_newobj(trans)); + nft_obj_destroy(&ctx, nft_trans_obj_newobj(trans)); nft_trans_destroy(trans); } else { - nft_use_dec_restore(&trans->ctx.table->use); + nft_use_dec_restore(&table->use); nft_obj_del(nft_trans_obj(trans)); } break; case NFT_MSG_DELOBJ: case NFT_MSG_DESTROYOBJ: - nft_use_inc_restore(&trans->ctx.table->use); - nft_clear(trans->ctx.net, nft_trans_obj(trans)); + nft_use_inc_restore(&table->use); + nft_clear(trans->net, nft_trans_obj(trans)); nft_trans_destroy(trans); break; case NFT_MSG_NEWFLOWTABLE: @@ -10692,7 +10884,7 @@ static int __nf_tables_abort(struct net *net, enum nfnl_abort_action action) nft_unregister_flowtable_net_hooks(net, &nft_trans_flowtable_hooks(trans)); } else { - nft_use_dec_restore(&trans->ctx.table->use); + nft_use_dec_restore(&table->use); list_del_rcu(&nft_trans_flowtable(trans)->list); nft_unregister_flowtable_net_hooks(net, &nft_trans_flowtable(trans)->hook_list); @@ -10704,14 +10896,16 @@ static int __nf_tables_abort(struct net *net, enum nfnl_abort_action action) list_splice(&nft_trans_flowtable_hooks(trans), &nft_trans_flowtable(trans)->hook_list); } else { - nft_use_inc_restore(&trans->ctx.table->use); - nft_clear(trans->ctx.net, nft_trans_flowtable(trans)); + nft_use_inc_restore(&table->use); + nft_clear(trans->net, nft_trans_flowtable(trans)); } nft_trans_destroy(trans); break; } } + WARN_ON_ONCE(!list_empty(&nft_net->commit_set_list)); + nft_set_abort_update(&set_update_list); synchronize_rcu(); @@ -10810,150 +11004,6 @@ int nft_chain_validate_hooks(const struct nft_chain *chain, } EXPORT_SYMBOL_GPL(nft_chain_validate_hooks); -/* - * Loop detection - walk through the ruleset beginning at the destination chain - * of a new jump until either the source chain is reached (loop) or all - * reachable chains have been traversed. - * - * The loop check is performed whenever a new jump verdict is added to an - * expression or verdict map or a verdict map is bound to a new chain. - */ - -static int nf_tables_check_loops(const struct nft_ctx *ctx, - const struct nft_chain *chain); - -static int nft_check_loops(const struct nft_ctx *ctx, - const struct nft_set_ext *ext) -{ - const struct nft_data *data; - int ret; - - data = nft_set_ext_data(ext); - switch (data->verdict.code) { - case NFT_JUMP: - case NFT_GOTO: - ret = nf_tables_check_loops(ctx, data->verdict.chain); - break; - default: - ret = 0; - break; - } - - return ret; -} - -static int nf_tables_loop_check_setelem(const struct nft_ctx *ctx, - struct nft_set *set, - const struct nft_set_iter *iter, - struct nft_elem_priv *elem_priv) -{ - const struct nft_set_ext *ext = nft_set_elem_ext(set, elem_priv); - - if (!nft_set_elem_active(ext, iter->genmask)) - return 0; - - if (nft_set_ext_exists(ext, NFT_SET_EXT_FLAGS) && - *nft_set_ext_flags(ext) & NFT_SET_ELEM_INTERVAL_END) - return 0; - - return nft_check_loops(ctx, ext); -} - -static int nft_set_catchall_loops(const struct nft_ctx *ctx, - struct nft_set *set) -{ - u8 genmask = nft_genmask_next(ctx->net); - struct nft_set_elem_catchall *catchall; - struct nft_set_ext *ext; - int ret = 0; - - list_for_each_entry_rcu(catchall, &set->catchall_list, list) { - ext = nft_set_elem_ext(set, catchall->elem); - if (!nft_set_elem_active(ext, genmask)) - continue; - - ret = nft_check_loops(ctx, ext); - if (ret < 0) - return ret; - } - - return ret; -} - -static int nf_tables_check_loops(const struct nft_ctx *ctx, - const struct nft_chain *chain) -{ - const struct nft_rule *rule; - const struct nft_expr *expr, *last; - struct nft_set *set; - struct nft_set_binding *binding; - struct nft_set_iter iter; - - if (ctx->chain == chain) - return -ELOOP; - - if (fatal_signal_pending(current)) - return -EINTR; - - list_for_each_entry(rule, &chain->rules, list) { - nft_rule_for_each_expr(expr, last, rule) { - struct nft_immediate_expr *priv; - const struct nft_data *data; - int err; - - if (strcmp(expr->ops->type->name, "immediate")) - continue; - - priv = nft_expr_priv(expr); - if (priv->dreg != NFT_REG_VERDICT) - continue; - - data = &priv->data; - switch (data->verdict.code) { - case NFT_JUMP: - case NFT_GOTO: - err = nf_tables_check_loops(ctx, - data->verdict.chain); - if (err < 0) - return err; - break; - default: - break; - } - } - } - - list_for_each_entry(set, &ctx->table->sets, list) { - if (!nft_is_active_next(ctx->net, set)) - continue; - if (!(set->flags & NFT_SET_MAP) || - set->dtype != NFT_DATA_VERDICT) - continue; - - list_for_each_entry(binding, &set->bindings, list) { - if (!(binding->flags & NFT_SET_MAP) || - binding->chain != chain) - continue; - - iter.genmask = nft_genmask_next(ctx->net); - iter.type = NFT_ITER_UPDATE; - iter.skip = 0; - iter.count = 0; - iter.err = 0; - iter.fn = nf_tables_loop_check_setelem; - - set->ops->walk(ctx, set, &iter); - if (!iter.err) - iter.err = nft_set_catchall_loops(ctx, set); - - if (iter.err < 0) - return iter.err; - } - } - - return 0; -} - /** * nft_parse_u32_check - fetch u32 attribute and check for maximum value * @@ -11032,10 +11082,11 @@ static int nft_validate_register_load(enum nft_registers reg, unsigned int len) return 0; } -int nft_parse_register_load(const struct nlattr *attr, u8 *sreg, u32 len) +int nft_parse_register_load(const struct nft_ctx *ctx, + const struct nlattr *attr, u8 *sreg, u32 len) { - u32 reg; - int err; + int err, invalid_reg; + u32 reg, next_register; err = nft_parse_register(attr, ®); if (err < 0) @@ -11045,11 +11096,36 @@ int nft_parse_register_load(const struct nlattr *attr, u8 *sreg, u32 len) if (err < 0) return err; + next_register = DIV_ROUND_UP(len, NFT_REG32_SIZE) + reg; + + /* Can't happen: nft_validate_register_load() should have failed */ + if (WARN_ON_ONCE(next_register > NFT_REG32_NUM)) + return -EINVAL; + + /* find first register that did not see an earlier store. */ + invalid_reg = find_next_zero_bit(ctx->reg_inited, NFT_REG32_NUM, reg); + + /* invalid register within the range that we're loading from? */ + if (invalid_reg < next_register) + return -ENODATA; + *sreg = reg; return 0; } EXPORT_SYMBOL_GPL(nft_parse_register_load); +static void nft_saw_register_store(const struct nft_ctx *__ctx, + int reg, unsigned int len) +{ + unsigned int registers = DIV_ROUND_UP(len, NFT_REG32_SIZE); + struct nft_ctx *ctx = (struct nft_ctx *)__ctx; + + if (WARN_ON_ONCE(len == 0 || reg < 0)) + return; + + bitmap_set(ctx->reg_inited, reg, registers); +} + static int nft_validate_register_store(const struct nft_ctx *ctx, enum nft_registers reg, const struct nft_data *data, @@ -11066,13 +11142,16 @@ static int nft_validate_register_store(const struct nft_ctx *ctx, if (data != NULL && (data->verdict.code == NFT_GOTO || data->verdict.code == NFT_JUMP)) { - err = nf_tables_check_loops(ctx, data->verdict.chain); + err = nft_chain_validate(ctx, data->verdict.chain); if (err < 0) return err; } - return 0; + break; default: + if (type != NFT_DATA_VALUE) + return -EINVAL; + if (reg < NFT_REG_1 * NFT_REG_SIZE / NFT_REG32_SIZE) return -EINVAL; if (len == 0) @@ -11081,10 +11160,11 @@ static int nft_validate_register_store(const struct nft_ctx *ctx, sizeof_field(struct nft_regs, data)) return -ERANGE; - if (data != NULL && type != NFT_DATA_VALUE) - return -EINVAL; - return 0; + break; } + + nft_saw_register_store(ctx, reg, len); + return 0; } int nft_parse_register_store(const struct nft_ctx *ctx, @@ -11365,7 +11445,7 @@ int __nft_release_basechain(struct nft_ctx *ctx) } nft_chain_del(ctx->chain); nft_use_dec(&ctx->table->use); - nf_tables_chain_destroy(ctx); + nf_tables_chain_destroy(ctx->chain); return 0; } @@ -11440,12 +11520,11 @@ static void __nft_release_table(struct net *net, struct nft_table *table) nft_obj_destroy(&ctx, obj); } list_for_each_entry_safe(chain, nc, &table->chains, list) { - ctx.chain = chain; nft_chain_del(chain); nft_use_dec(&table->use); - nf_tables_chain_destroy(&ctx); + nf_tables_chain_destroy(chain); } - nf_tables_table_destroy(&ctx); + nf_tables_table_destroy(table); } static void __nft_release_tables(struct net *net) @@ -11483,8 +11562,7 @@ static int nft_rcv_nl_event(struct notifier_block *this, unsigned long event, gc_seq = nft_gc_seq_begin(nft_net); - if (!list_empty(&nf_tables_destroy_list)) - nf_tables_trans_destroy_flush_work(); + nf_tables_trans_destroy_flush_work(); again: list_for_each_entry(table, &nft_net->tables, list) { if (nft_table_has_owner(table) && @@ -11526,6 +11604,7 @@ static int __net_init nf_tables_init_net(struct net *net) INIT_LIST_HEAD(&nft_net->tables); INIT_LIST_HEAD(&nft_net->commit_list); + INIT_LIST_HEAD(&nft_net->commit_set_list); INIT_LIST_HEAD(&nft_net->binding_list); INIT_LIST_HEAD(&nft_net->module_list); INIT_LIST_HEAD(&nft_net->notify_list); @@ -11556,6 +11635,7 @@ static void __net_exit nf_tables_exit_net(struct net *net) gc_seq = nft_gc_seq_begin(nft_net); WARN_ON_ONCE(!list_empty(&nft_net->commit_list)); + WARN_ON_ONCE(!list_empty(&nft_net->commit_set_list)); if (!list_empty(&nft_net->module_list)) nf_tables_module_autoload_cleanup(net); @@ -11588,6 +11668,14 @@ static int __init nf_tables_module_init(void) { int err; + BUILD_BUG_ON(offsetof(struct nft_trans_table, nft_trans) != 0); + BUILD_BUG_ON(offsetof(struct nft_trans_chain, nft_trans_binding.nft_trans) != 0); + BUILD_BUG_ON(offsetof(struct nft_trans_rule, nft_trans) != 0); + BUILD_BUG_ON(offsetof(struct nft_trans_set, nft_trans_binding.nft_trans) != 0); + BUILD_BUG_ON(offsetof(struct nft_trans_elem, nft_trans) != 0); + BUILD_BUG_ON(offsetof(struct nft_trans_obj, nft_trans) != 0); + BUILD_BUG_ON(offsetof(struct nft_trans_flowtable, nft_trans) != 0); + err = register_pernet_subsys(&nf_tables_net_ops); if (err < 0) return err; diff --git a/net/netfilter/nf_tables_core.c b/net/netfilter/nf_tables_core.c index a48d5f0e2f3e..75598520b0fa 100644 --- a/net/netfilter/nf_tables_core.c +++ b/net/netfilter/nf_tables_core.c @@ -256,7 +256,7 @@ nft_do_chain(struct nft_pktinfo *pkt, void *priv) const struct net *net = nft_net(pkt); const struct nft_expr *expr, *last; const struct nft_rule_dp *rule; - struct nft_regs regs = {}; + struct nft_regs regs; unsigned int stackptr = 0; struct nft_jumpstack jumpstack[NFT_JUMP_STACK_SIZE]; bool genbit = READ_ONCE(net->nft.gencursor); diff --git a/net/netfilter/nf_tables_offload.c b/net/netfilter/nf_tables_offload.c index 12ab78fa5d84..64675f1c7f29 100644 --- a/net/netfilter/nf_tables_offload.c +++ b/net/netfilter/nf_tables_offload.c @@ -513,38 +513,38 @@ static void nft_flow_rule_offload_abort(struct net *net, int err = 0; list_for_each_entry_continue_reverse(trans, &nft_net->commit_list, list) { - if (trans->ctx.family != NFPROTO_NETDEV) + if (trans->table->family != NFPROTO_NETDEV) continue; switch (trans->msg_type) { case NFT_MSG_NEWCHAIN: - if (!(trans->ctx.chain->flags & NFT_CHAIN_HW_OFFLOAD) || + if (!(nft_trans_chain(trans)->flags & NFT_CHAIN_HW_OFFLOAD) || nft_trans_chain_update(trans)) continue; - err = nft_flow_offload_chain(trans->ctx.chain, NULL, + err = nft_flow_offload_chain(nft_trans_chain(trans), NULL, FLOW_BLOCK_UNBIND); break; case NFT_MSG_DELCHAIN: - if (!(trans->ctx.chain->flags & NFT_CHAIN_HW_OFFLOAD)) + if (!(nft_trans_chain(trans)->flags & NFT_CHAIN_HW_OFFLOAD)) continue; - err = nft_flow_offload_chain(trans->ctx.chain, NULL, + err = nft_flow_offload_chain(nft_trans_chain(trans), NULL, FLOW_BLOCK_BIND); break; case NFT_MSG_NEWRULE: - if (!(trans->ctx.chain->flags & NFT_CHAIN_HW_OFFLOAD)) + if (!(nft_trans_rule_chain(trans)->flags & NFT_CHAIN_HW_OFFLOAD)) continue; - err = nft_flow_offload_rule(trans->ctx.chain, + err = nft_flow_offload_rule(nft_trans_rule_chain(trans), nft_trans_rule(trans), NULL, FLOW_CLS_DESTROY); break; case NFT_MSG_DELRULE: - if (!(trans->ctx.chain->flags & NFT_CHAIN_HW_OFFLOAD)) + if (!(nft_trans_rule_chain(trans)->flags & NFT_CHAIN_HW_OFFLOAD)) continue; - err = nft_flow_offload_rule(trans->ctx.chain, + err = nft_flow_offload_rule(nft_trans_rule_chain(trans), nft_trans_rule(trans), nft_trans_flow_rule(trans), FLOW_CLS_REPLACE); @@ -564,46 +564,46 @@ int nft_flow_rule_offload_commit(struct net *net) u8 policy; list_for_each_entry(trans, &nft_net->commit_list, list) { - if (trans->ctx.family != NFPROTO_NETDEV) + if (trans->table->family != NFPROTO_NETDEV) continue; switch (trans->msg_type) { case NFT_MSG_NEWCHAIN: - if (!(trans->ctx.chain->flags & NFT_CHAIN_HW_OFFLOAD) || + if (!(nft_trans_chain(trans)->flags & NFT_CHAIN_HW_OFFLOAD) || nft_trans_chain_update(trans)) continue; policy = nft_trans_chain_policy(trans); - err = nft_flow_offload_chain(trans->ctx.chain, &policy, + err = nft_flow_offload_chain(nft_trans_chain(trans), &policy, FLOW_BLOCK_BIND); break; case NFT_MSG_DELCHAIN: - if (!(trans->ctx.chain->flags & NFT_CHAIN_HW_OFFLOAD)) + if (!(nft_trans_chain(trans)->flags & NFT_CHAIN_HW_OFFLOAD)) continue; policy = nft_trans_chain_policy(trans); - err = nft_flow_offload_chain(trans->ctx.chain, &policy, + err = nft_flow_offload_chain(nft_trans_chain(trans), &policy, FLOW_BLOCK_UNBIND); break; case NFT_MSG_NEWRULE: - if (!(trans->ctx.chain->flags & NFT_CHAIN_HW_OFFLOAD)) + if (!(nft_trans_rule_chain(trans)->flags & NFT_CHAIN_HW_OFFLOAD)) continue; - if (trans->ctx.flags & NLM_F_REPLACE || - !(trans->ctx.flags & NLM_F_APPEND)) { + if (trans->flags & NLM_F_REPLACE || + !(trans->flags & NLM_F_APPEND)) { err = -EOPNOTSUPP; break; } - err = nft_flow_offload_rule(trans->ctx.chain, + err = nft_flow_offload_rule(nft_trans_rule_chain(trans), nft_trans_rule(trans), nft_trans_flow_rule(trans), FLOW_CLS_REPLACE); break; case NFT_MSG_DELRULE: - if (!(trans->ctx.chain->flags & NFT_CHAIN_HW_OFFLOAD)) + if (!(nft_trans_rule_chain(trans)->flags & NFT_CHAIN_HW_OFFLOAD)) continue; - err = nft_flow_offload_rule(trans->ctx.chain, + err = nft_flow_offload_rule(nft_trans_rule_chain(trans), nft_trans_rule(trans), NULL, FLOW_CLS_DESTROY); break; diff --git a/net/netfilter/nf_tables_trace.c b/net/netfilter/nf_tables_trace.c index a83637e3f455..580c55268f65 100644 --- a/net/netfilter/nf_tables_trace.c +++ b/net/netfilter/nf_tables_trace.c @@ -317,7 +317,7 @@ void nft_trace_init(struct nft_traceinfo *info, const struct nft_pktinfo *pkt, net_get_random_once(&trace_key, sizeof(trace_key)); info->skbid = (u32)siphash_3u32(hash32_ptr(skb), - skb_get_hash(skb), + skb_get_hash_net(nft_net(pkt), skb), skb->skb_iif, &trace_key); } diff --git a/net/netfilter/nfnetlink.c b/net/netfilter/nfnetlink.c index 4abf660c7baf..7784ec094097 100644 --- a/net/netfilter/nfnetlink.c +++ b/net/netfilter/nfnetlink.c @@ -402,33 +402,35 @@ replay_abort: { nfnl_unlock(subsys_id); netlink_ack(oskb, nlh, -EOPNOTSUPP, NULL); - return kfree_skb(skb); + return consume_skb(skb); } } if (!ss->valid_genid || !ss->commit || !ss->abort) { nfnl_unlock(subsys_id); netlink_ack(oskb, nlh, -EOPNOTSUPP, NULL); - return kfree_skb(skb); + return consume_skb(skb); } if (!try_module_get(ss->owner)) { nfnl_unlock(subsys_id); netlink_ack(oskb, nlh, -EOPNOTSUPP, NULL); - return kfree_skb(skb); + return consume_skb(skb); } if (!ss->valid_genid(net, genid)) { module_put(ss->owner); nfnl_unlock(subsys_id); netlink_ack(oskb, nlh, -ERESTART, NULL); - return kfree_skb(skb); + return consume_skb(skb); } nfnl_unlock(subsys_id); - if (nlh->nlmsg_flags & NLM_F_ACK) + if (nlh->nlmsg_flags & NLM_F_ACK) { + memset(&extack, 0, sizeof(extack)); nfnl_err_add(&err_list, nlh, 0, &extack); + } while (skb->len >= nlmsg_total_size(0)) { int msglen, type; @@ -565,7 +567,7 @@ done: if (status & NFNL_BATCH_REPLAY) { ss->abort(net, oskb, NFNL_ABORT_AUTOLOAD); nfnl_err_reset(&err_list); - kfree_skb(skb); + consume_skb(skb); module_put(ss->owner); goto replay; } else if (status == NFNL_BATCH_DONE) { @@ -577,6 +579,7 @@ done: ss->abort(net, oskb, NFNL_ABORT_NONE); netlink_ack(oskb, nlmsg_hdr(oskb), err, NULL); } else if (nlh->nlmsg_flags & NLM_F_ACK) { + memset(&extack, 0, sizeof(extack)); nfnl_err_add(&err_list, nlh, 0, &extack); } } else { @@ -590,7 +593,7 @@ done: err = ss->abort(net, oskb, abort_action); if (err == -EAGAIN) { nfnl_err_reset(&err_list); - kfree_skb(skb); + consume_skb(skb); module_put(ss->owner); status |= NFNL_BATCH_FAILURE; goto replay_abort; @@ -598,7 +601,7 @@ done: } nfnl_err_deliver(&err_list, oskb); - kfree_skb(skb); + consume_skb(skb); module_put(ss->owner); } diff --git a/net/netfilter/nfnetlink_cttimeout.c b/net/netfilter/nfnetlink_cttimeout.c index f466af4f8531..eab4f476b47f 100644 --- a/net/netfilter/nfnetlink_cttimeout.c +++ b/net/netfilter/nfnetlink_cttimeout.c @@ -366,8 +366,7 @@ static int cttimeout_default_set(struct sk_buff *skb, __u8 l4num; int ret; - if (!cda[CTA_TIMEOUT_L3PROTO] || - !cda[CTA_TIMEOUT_L4PROTO] || + if (!cda[CTA_TIMEOUT_L4PROTO] || !cda[CTA_TIMEOUT_DATA]) return -EINVAL; diff --git a/net/netfilter/nfnetlink_queue.c b/net/netfilter/nfnetlink_queue.c index f1c31757e496..d2773ce9b585 100644 --- a/net/netfilter/nfnetlink_queue.c +++ b/net/netfilter/nfnetlink_queue.c @@ -325,7 +325,7 @@ static void nf_reinject(struct nf_queue_entry *entry, unsigned int verdict) hooks = nf_hook_entries_head(net, pf, entry->state.hook); i = entry->hook_index; - if (WARN_ON_ONCE(!hooks || i >= hooks->num_hook_entries)) { + if (!hooks || i >= hooks->num_hook_entries) { kfree_skb_reason(skb, SKB_DROP_REASON_NETFILTER_DROP); nf_queue_entry_free(entry); return; @@ -540,6 +540,14 @@ nla_put_failure: return -1; } +static int nf_queue_checksum_help(struct sk_buff *entskb) +{ + if (skb_csum_is_sctp(entskb)) + return skb_crc32c_csum_help(entskb); + + return skb_checksum_help(entskb); +} + static struct sk_buff * nfqnl_build_packet_message(struct net *net, struct nfqnl_instance *queue, struct nf_queue_entry *entry, @@ -602,7 +610,7 @@ nfqnl_build_packet_message(struct net *net, struct nfqnl_instance *queue, case NFQNL_COPY_PACKET: if (!(queue->flags & NFQA_CFG_F_GSO) && entskb->ip_summed == CHECKSUM_PARTIAL && - skb_checksum_help(entskb)) + nf_queue_checksum_help(entskb)) return NULL; data_len = READ_ONCE(queue->copy_range); @@ -820,10 +828,41 @@ static bool nf_ct_drop_unconfirmed(const struct nf_queue_entry *entry) { #if IS_ENABLED(CONFIG_NF_CONNTRACK) static const unsigned long flags = IPS_CONFIRMED | IPS_DYING; - const struct nf_conn *ct = (void *)skb_nfct(entry->skb); + struct nf_conn *ct = (void *)skb_nfct(entry->skb); + unsigned long status; + unsigned int use; + + if (!ct) + return false; - if (ct && ((ct->status & flags) == IPS_DYING)) + status = READ_ONCE(ct->status); + if ((status & flags) == IPS_DYING) return true; + + if (status & IPS_CONFIRMED) + return false; + + /* in some cases skb_clone() can occur after initial conntrack + * pickup, but conntrack assumes exclusive skb->_nfct ownership for + * unconfirmed entries. + * + * This happens for br_netfilter and with ip multicast routing. + * We can't be solved with serialization here because one clone could + * have been queued for local delivery. + */ + use = refcount_read(&ct->ct_general.use); + if (likely(use == 1)) + return false; + + /* Can't decrement further? Exclusive ownership. */ + if (!refcount_dec_not_one(&ct->ct_general.use)) + return false; + + skb_set_nfct(entry->skb, 0); + /* No nf_ct_put(): we already decremented .use and it cannot + * drop down to 0. + */ + return true; #endif return false; } @@ -983,7 +1022,7 @@ nfqnl_enqueue_packet(struct nf_queue_entry *entry, unsigned int queuenum) break; } - if ((queue->flags & NFQA_CFG_F_GSO) || !skb_is_gso(skb)) + if (!skb_is_gso(skb) || ((queue->flags & NFQA_CFG_F_GSO) && !skb_is_gso_sctp(skb))) return __nfqnl_enqueue_packet(net, queue, entry); nf_bridge_adjust_skb_data(skb); diff --git a/net/netfilter/nft_bitwise.c b/net/netfilter/nft_bitwise.c index ca857afbf061..7de95674fd8c 100644 --- a/net/netfilter/nft_bitwise.c +++ b/net/netfilter/nft_bitwise.c @@ -171,7 +171,7 @@ static int nft_bitwise_init(const struct nft_ctx *ctx, priv->len = len; - err = nft_parse_register_load(tb[NFTA_BITWISE_SREG], &priv->sreg, + err = nft_parse_register_load(ctx, tb[NFTA_BITWISE_SREG], &priv->sreg, priv->len); if (err < 0) return err; @@ -365,7 +365,7 @@ static int nft_bitwise_fast_init(const struct nft_ctx *ctx, struct nft_bitwise_fast_expr *priv = nft_expr_priv(expr); int err; - err = nft_parse_register_load(tb[NFTA_BITWISE_SREG], &priv->sreg, + err = nft_parse_register_load(ctx, tb[NFTA_BITWISE_SREG], &priv->sreg, sizeof(u32)); if (err < 0) return err; diff --git a/net/netfilter/nft_byteorder.c b/net/netfilter/nft_byteorder.c index f6e791a68101..2f82a444d21b 100644 --- a/net/netfilter/nft_byteorder.c +++ b/net/netfilter/nft_byteorder.c @@ -139,7 +139,7 @@ static int nft_byteorder_init(const struct nft_ctx *ctx, priv->len = len; - err = nft_parse_register_load(tb[NFTA_BYTEORDER_SREG], &priv->sreg, + err = nft_parse_register_load(ctx, tb[NFTA_BYTEORDER_SREG], &priv->sreg, priv->len); if (err < 0) return err; diff --git a/net/netfilter/nft_cmp.c b/net/netfilter/nft_cmp.c index cd4652259095..2605f43737bc 100644 --- a/net/netfilter/nft_cmp.c +++ b/net/netfilter/nft_cmp.c @@ -83,7 +83,7 @@ static int nft_cmp_init(const struct nft_ctx *ctx, const struct nft_expr *expr, if (err < 0) return err; - err = nft_parse_register_load(tb[NFTA_CMP_SREG], &priv->sreg, desc.len); + err = nft_parse_register_load(ctx, tb[NFTA_CMP_SREG], &priv->sreg, desc.len); if (err < 0) return err; @@ -222,7 +222,7 @@ static int nft_cmp_fast_init(const struct nft_ctx *ctx, if (err < 0) return err; - err = nft_parse_register_load(tb[NFTA_CMP_SREG], &priv->sreg, desc.len); + err = nft_parse_register_load(ctx, tb[NFTA_CMP_SREG], &priv->sreg, desc.len); if (err < 0) return err; @@ -323,7 +323,7 @@ static int nft_cmp16_fast_init(const struct nft_ctx *ctx, if (err < 0) return err; - err = nft_parse_register_load(tb[NFTA_CMP_SREG], &priv->sreg, desc.len); + err = nft_parse_register_load(ctx, tb[NFTA_CMP_SREG], &priv->sreg, desc.len); if (err < 0) return err; diff --git a/net/netfilter/nft_compat.c b/net/netfilter/nft_compat.c index d3d11dede545..7ca4f0d21fe2 100644 --- a/net/netfilter/nft_compat.c +++ b/net/netfilter/nft_compat.c @@ -350,8 +350,7 @@ nla_put_failure: } static int nft_target_validate(const struct nft_ctx *ctx, - const struct nft_expr *expr, - const struct nft_data **data) + const struct nft_expr *expr) { struct xt_target *target = expr->ops->data; unsigned int hook_mask = 0; @@ -536,7 +535,7 @@ nft_match_large_init(const struct nft_ctx *ctx, const struct nft_expr *expr, struct xt_match *m = expr->ops->data; int ret; - priv->info = kmalloc(XT_ALIGN(m->matchsize), GFP_KERNEL); + priv->info = kmalloc(XT_ALIGN(m->matchsize), GFP_KERNEL_ACCOUNT); if (!priv->info) return -ENOMEM; @@ -611,8 +610,7 @@ static int nft_match_large_dump(struct sk_buff *skb, } static int nft_match_validate(const struct nft_ctx *ctx, - const struct nft_expr *expr, - const struct nft_data **data) + const struct nft_expr *expr) { struct xt_match *match = expr->ops->data; unsigned int hook_mask = 0; @@ -810,7 +808,7 @@ nft_match_select_ops(const struct nft_ctx *ctx, goto err; } - ops = kzalloc(sizeof(struct nft_expr_ops), GFP_KERNEL); + ops = kzalloc(sizeof(struct nft_expr_ops), GFP_KERNEL_ACCOUNT); if (!ops) { err = -ENOMEM; goto err; @@ -900,7 +898,7 @@ nft_target_select_ops(const struct nft_ctx *ctx, goto err; } - ops = kzalloc(sizeof(struct nft_expr_ops), GFP_KERNEL); + ops = kzalloc(sizeof(struct nft_expr_ops), GFP_KERNEL_ACCOUNT); if (!ops) { err = -ENOMEM; goto err; diff --git a/net/netfilter/nft_counter.c b/net/netfilter/nft_counter.c index 291ed2026367..cc7325329496 100644 --- a/net/netfilter/nft_counter.c +++ b/net/netfilter/nft_counter.c @@ -8,7 +8,7 @@ #include <linux/kernel.h> #include <linux/init.h> #include <linux/module.h> -#include <linux/seqlock.h> +#include <linux/u64_stats_sync.h> #include <linux/netlink.h> #include <linux/netfilter.h> #include <linux/netfilter/nf_tables.h> @@ -17,6 +17,11 @@ #include <net/netfilter/nf_tables_offload.h> struct nft_counter { + u64_stats_t bytes; + u64_stats_t packets; +}; + +struct nft_counter_tot { s64 bytes; s64 packets; }; @@ -25,25 +30,24 @@ struct nft_counter_percpu_priv { struct nft_counter __percpu *counter; }; -static DEFINE_PER_CPU(seqcount_t, nft_counter_seq); +static DEFINE_PER_CPU(struct u64_stats_sync, nft_counter_sync); static inline void nft_counter_do_eval(struct nft_counter_percpu_priv *priv, struct nft_regs *regs, const struct nft_pktinfo *pkt) { + struct u64_stats_sync *nft_sync; struct nft_counter *this_cpu; - seqcount_t *myseq; local_bh_disable(); this_cpu = this_cpu_ptr(priv->counter); - myseq = this_cpu_ptr(&nft_counter_seq); - - write_seqcount_begin(myseq); + nft_sync = this_cpu_ptr(&nft_counter_sync); - this_cpu->bytes += pkt->skb->len; - this_cpu->packets++; + u64_stats_update_begin(nft_sync); + u64_stats_add(&this_cpu->bytes, pkt->skb->len); + u64_stats_inc(&this_cpu->packets); + u64_stats_update_end(nft_sync); - write_seqcount_end(myseq); local_bh_enable(); } @@ -66,17 +70,16 @@ static int nft_counter_do_init(const struct nlattr * const tb[], if (cpu_stats == NULL) return -ENOMEM; - preempt_disable(); - this_cpu = this_cpu_ptr(cpu_stats); + this_cpu = raw_cpu_ptr(cpu_stats); if (tb[NFTA_COUNTER_PACKETS]) { - this_cpu->packets = - be64_to_cpu(nla_get_be64(tb[NFTA_COUNTER_PACKETS])); + u64_stats_set(&this_cpu->packets, + be64_to_cpu(nla_get_be64(tb[NFTA_COUNTER_PACKETS]))); } if (tb[NFTA_COUNTER_BYTES]) { - this_cpu->bytes = - be64_to_cpu(nla_get_be64(tb[NFTA_COUNTER_BYTES])); + u64_stats_set(&this_cpu->bytes, + be64_to_cpu(nla_get_be64(tb[NFTA_COUNTER_BYTES]))); } - preempt_enable(); + priv->counter = cpu_stats; return 0; } @@ -104,35 +107,41 @@ static void nft_counter_obj_destroy(const struct nft_ctx *ctx, } static void nft_counter_reset(struct nft_counter_percpu_priv *priv, - struct nft_counter *total) + struct nft_counter_tot *total) { + struct u64_stats_sync *nft_sync; struct nft_counter *this_cpu; local_bh_disable(); this_cpu = this_cpu_ptr(priv->counter); - this_cpu->packets -= total->packets; - this_cpu->bytes -= total->bytes; + nft_sync = this_cpu_ptr(&nft_counter_sync); + + u64_stats_update_begin(nft_sync); + u64_stats_add(&this_cpu->packets, -total->packets); + u64_stats_add(&this_cpu->bytes, -total->bytes); + u64_stats_update_end(nft_sync); + local_bh_enable(); } static void nft_counter_fetch(struct nft_counter_percpu_priv *priv, - struct nft_counter *total) + struct nft_counter_tot *total) { struct nft_counter *this_cpu; - const seqcount_t *myseq; u64 bytes, packets; unsigned int seq; int cpu; memset(total, 0, sizeof(*total)); for_each_possible_cpu(cpu) { - myseq = per_cpu_ptr(&nft_counter_seq, cpu); + struct u64_stats_sync *nft_sync = per_cpu_ptr(&nft_counter_sync, cpu); + this_cpu = per_cpu_ptr(priv->counter, cpu); do { - seq = read_seqcount_begin(myseq); - bytes = this_cpu->bytes; - packets = this_cpu->packets; - } while (read_seqcount_retry(myseq, seq)); + seq = u64_stats_fetch_begin(nft_sync); + bytes = u64_stats_read(&this_cpu->bytes); + packets = u64_stats_read(&this_cpu->packets); + } while (u64_stats_fetch_retry(nft_sync, seq)); total->bytes += bytes; total->packets += packets; @@ -143,7 +152,7 @@ static int nft_counter_do_dump(struct sk_buff *skb, struct nft_counter_percpu_priv *priv, bool reset) { - struct nft_counter total; + struct nft_counter_tot total; nft_counter_fetch(priv, &total); @@ -232,7 +241,7 @@ static int nft_counter_clone(struct nft_expr *dst, const struct nft_expr *src, g struct nft_counter_percpu_priv *priv_clone = nft_expr_priv(dst); struct nft_counter __percpu *cpu_stats; struct nft_counter *this_cpu; - struct nft_counter total; + struct nft_counter_tot total; nft_counter_fetch(priv, &total); @@ -240,11 +249,9 @@ static int nft_counter_clone(struct nft_expr *dst, const struct nft_expr *src, g if (cpu_stats == NULL) return -ENOMEM; - preempt_disable(); - this_cpu = this_cpu_ptr(cpu_stats); - this_cpu->packets = total.packets; - this_cpu->bytes = total.bytes; - preempt_enable(); + this_cpu = raw_cpu_ptr(cpu_stats); + u64_stats_set(&this_cpu->packets, total.packets); + u64_stats_set(&this_cpu->bytes, total.bytes); priv_clone->counter = cpu_stats; return 0; @@ -262,18 +269,18 @@ static void nft_counter_offload_stats(struct nft_expr *expr, const struct flow_stats *stats) { struct nft_counter_percpu_priv *priv = nft_expr_priv(expr); + struct u64_stats_sync *nft_sync; struct nft_counter *this_cpu; - seqcount_t *myseq; - preempt_disable(); + local_bh_disable(); this_cpu = this_cpu_ptr(priv->counter); - myseq = this_cpu_ptr(&nft_counter_seq); + nft_sync = this_cpu_ptr(&nft_counter_sync); - write_seqcount_begin(myseq); - this_cpu->packets += stats->pkts; - this_cpu->bytes += stats->bytes; - write_seqcount_end(myseq); - preempt_enable(); + u64_stats_update_begin(nft_sync); + u64_stats_add(&this_cpu->packets, stats->pkts); + u64_stats_add(&this_cpu->bytes, stats->bytes); + u64_stats_update_end(nft_sync); + local_bh_enable(); } void nft_counter_init_seqcount(void) @@ -281,7 +288,7 @@ void nft_counter_init_seqcount(void) int cpu; for_each_possible_cpu(cpu) - seqcount_init(per_cpu_ptr(&nft_counter_seq, cpu)); + u64_stats_init(per_cpu_ptr(&nft_counter_sync, cpu)); } struct nft_expr_type nft_counter_type; diff --git a/net/netfilter/nft_ct.c b/net/netfilter/nft_ct.c index 452ed94c3a4d..67a41cd2baaf 100644 --- a/net/netfilter/nft_ct.c +++ b/net/netfilter/nft_ct.c @@ -606,7 +606,7 @@ static int nft_ct_set_init(const struct nft_ctx *ctx, } priv->len = len; - err = nft_parse_register_load(tb[NFTA_CT_SREG], &priv->sreg, len); + err = nft_parse_register_load(ctx, tb[NFTA_CT_SREG], &priv->sreg, len); if (err < 0) goto err1; diff --git a/net/netfilter/nft_dup_netdev.c b/net/netfilter/nft_dup_netdev.c index e5739a59ebf1..0573f96ce079 100644 --- a/net/netfilter/nft_dup_netdev.c +++ b/net/netfilter/nft_dup_netdev.c @@ -40,7 +40,7 @@ static int nft_dup_netdev_init(const struct nft_ctx *ctx, if (tb[NFTA_DUP_SREG_DEV] == NULL) return -EINVAL; - return nft_parse_register_load(tb[NFTA_DUP_SREG_DEV], &priv->sreg_dev, + return nft_parse_register_load(ctx, tb[NFTA_DUP_SREG_DEV], &priv->sreg_dev, sizeof(int)); } diff --git a/net/netfilter/nft_dynset.c b/net/netfilter/nft_dynset.c index b4ada3ab2167..88922e0e8e83 100644 --- a/net/netfilter/nft_dynset.c +++ b/net/netfilter/nft_dynset.c @@ -56,7 +56,7 @@ static struct nft_elem_priv *nft_dynset_new(struct nft_set *set, if (!atomic_add_unless(&set->nelems, 1, set->size)) return NULL; - timeout = priv->timeout ? : set->timeout; + timeout = priv->timeout ? : READ_ONCE(set->timeout); elem_priv = nft_set_elem_init(set, &priv->tmpl, ®s->data[priv->sreg_key], NULL, ®s->data[priv->sreg_data], @@ -94,9 +94,10 @@ void nft_dynset_eval(const struct nft_expr *expr, if (set->ops->update(set, ®s->data[priv->sreg_key], nft_dynset_new, expr, regs, &ext)) { if (priv->op == NFT_DYNSET_OP_UPDATE && - nft_set_ext_exists(ext, NFT_SET_EXT_EXPIRATION)) { - timeout = priv->timeout ? : set->timeout; - *nft_set_ext_expiration(ext) = get_jiffies_64() + timeout; + nft_set_ext_exists(ext, NFT_SET_EXT_TIMEOUT) && + READ_ONCE(nft_set_ext_timeout(ext)->timeout) != 0) { + timeout = priv->timeout ? : READ_ONCE(set->timeout); + WRITE_ONCE(nft_set_ext_timeout(ext)->expiration, get_jiffies_64() + timeout); } nft_set_elem_update_expr(ext, regs, pkt); @@ -215,7 +216,7 @@ static int nft_dynset_init(const struct nft_ctx *ctx, return err; } - err = nft_parse_register_load(tb[NFTA_DYNSET_SREG_KEY], &priv->sreg_key, + err = nft_parse_register_load(ctx, tb[NFTA_DYNSET_SREG_KEY], &priv->sreg_key, set->klen); if (err < 0) return err; @@ -226,7 +227,7 @@ static int nft_dynset_init(const struct nft_ctx *ctx, if (set->dtype == NFT_DATA_VERDICT) return -EOPNOTSUPP; - err = nft_parse_register_load(tb[NFTA_DYNSET_SREG_DATA], + err = nft_parse_register_load(ctx, tb[NFTA_DYNSET_SREG_DATA], &priv->sreg_data, set->dlen); if (err < 0) return err; @@ -312,12 +313,9 @@ static int nft_dynset_init(const struct nft_ctx *ctx, if (priv->num_exprs) nft_dynset_ext_add_expr(priv); - if (set->flags & NFT_SET_TIMEOUT) { - if (timeout || set->timeout) { - nft_set_ext_add(&priv->tmpl, NFT_SET_EXT_TIMEOUT); - nft_set_ext_add(&priv->tmpl, NFT_SET_EXT_EXPIRATION); - } - } + if (set->flags & NFT_SET_TIMEOUT && + (timeout || READ_ONCE(set->timeout))) + nft_set_ext_add(&priv->tmpl, NFT_SET_EXT_TIMEOUT); priv->timeout = timeout; diff --git a/net/netfilter/nft_exthdr.c b/net/netfilter/nft_exthdr.c index 6eb571d0c3fd..6bfd33516241 100644 --- a/net/netfilter/nft_exthdr.c +++ b/net/netfilter/nft_exthdr.c @@ -588,7 +588,7 @@ static int nft_exthdr_tcp_set_init(const struct nft_ctx *ctx, priv->flags = flags; priv->op = op; - return nft_parse_register_load(tb[NFTA_EXTHDR_SREG], &priv->sreg, + return nft_parse_register_load(ctx, tb[NFTA_EXTHDR_SREG], &priv->sreg, priv->len); } diff --git a/net/netfilter/nft_fib.c b/net/netfilter/nft_fib.c index b58f62195ff3..96e02a83c045 100644 --- a/net/netfilter/nft_fib.c +++ b/net/netfilter/nft_fib.c @@ -26,8 +26,7 @@ const struct nla_policy nft_fib_policy[NFTA_FIB_MAX + 1] = { }; EXPORT_SYMBOL(nft_fib_policy); -int nft_fib_validate(const struct nft_ctx *ctx, const struct nft_expr *expr, - const struct nft_data **data) +int nft_fib_validate(const struct nft_ctx *ctx, const struct nft_expr *expr) { const struct nft_fib *priv = nft_expr_priv(expr); unsigned int hooks; diff --git a/net/netfilter/nft_flow_offload.c b/net/netfilter/nft_flow_offload.c index ab9576098701..2f732fae5a83 100644 --- a/net/netfilter/nft_flow_offload.c +++ b/net/netfilter/nft_flow_offload.c @@ -9,6 +9,7 @@ #include <linux/netfilter/nf_conntrack_common.h> #include <linux/netfilter/nf_tables.h> #include <net/ip.h> /* for ipv4 options. */ +#include <net/inet_dscp.h> #include <net/netfilter/nf_tables.h> #include <net/netfilter/nf_tables_core.h> #include <net/netfilter/nf_conntrack_core.h> @@ -235,7 +236,7 @@ static int nft_flow_route(const struct nft_pktinfo *pkt, fl.u.ip4.saddr = ct->tuplehash[!dir].tuple.src.u3.ip; fl.u.ip4.flowi4_oif = nft_in(pkt)->ifindex; fl.u.ip4.flowi4_iif = this_dst->dev->ifindex; - fl.u.ip4.flowi4_tos = RT_TOS(ip_hdr(pkt->skb)->tos); + fl.u.ip4.flowi4_tos = ip_hdr(pkt->skb)->tos & INET_DSCP_MASK; fl.u.ip4.flowi4_mark = pkt->skb->mark; fl.u.ip4.flowi4_flags = FLOWI_FLAG_ANYSRC; break; @@ -380,8 +381,7 @@ out: } static int nft_flow_offload_validate(const struct nft_ctx *ctx, - const struct nft_expr *expr, - const struct nft_data **data) + const struct nft_expr *expr) { unsigned int hook_mask = (1 << NF_INET_FORWARD); diff --git a/net/netfilter/nft_fwd_netdev.c b/net/netfilter/nft_fwd_netdev.c index 358e742afad7..152a9fb4d23a 100644 --- a/net/netfilter/nft_fwd_netdev.c +++ b/net/netfilter/nft_fwd_netdev.c @@ -52,7 +52,7 @@ static int nft_fwd_netdev_init(const struct nft_ctx *ctx, if (tb[NFTA_FWD_SREG_DEV] == NULL) return -EINVAL; - return nft_parse_register_load(tb[NFTA_FWD_SREG_DEV], &priv->sreg_dev, + return nft_parse_register_load(ctx, tb[NFTA_FWD_SREG_DEV], &priv->sreg_dev, sizeof(int)); } @@ -178,12 +178,12 @@ static int nft_fwd_neigh_init(const struct nft_ctx *ctx, return -EOPNOTSUPP; } - err = nft_parse_register_load(tb[NFTA_FWD_SREG_DEV], &priv->sreg_dev, + err = nft_parse_register_load(ctx, tb[NFTA_FWD_SREG_DEV], &priv->sreg_dev, sizeof(int)); if (err < 0) return err; - return nft_parse_register_load(tb[NFTA_FWD_SREG_ADDR], &priv->sreg_addr, + return nft_parse_register_load(ctx, tb[NFTA_FWD_SREG_ADDR], &priv->sreg_addr, addr_len); } @@ -204,8 +204,7 @@ nla_put_failure: } static int nft_fwd_validate(const struct nft_ctx *ctx, - const struct nft_expr *expr, - const struct nft_data **data) + const struct nft_expr *expr) { return nft_chain_validate_hooks(ctx->chain, (1 << NF_NETDEV_INGRESS) | (1 << NF_NETDEV_EGRESS)); diff --git a/net/netfilter/nft_hash.c b/net/netfilter/nft_hash.c index 92d47e469204..5d034bbb6913 100644 --- a/net/netfilter/nft_hash.c +++ b/net/netfilter/nft_hash.c @@ -51,7 +51,8 @@ static void nft_symhash_eval(const struct nft_expr *expr, struct sk_buff *skb = pkt->skb; u32 h; - h = reciprocal_scale(__skb_get_hash_symmetric(skb), priv->modulus); + h = reciprocal_scale(__skb_get_hash_symmetric_net(nft_net(pkt), skb), + priv->modulus); regs->data[priv->dreg] = h + priv->offset; } @@ -91,7 +92,7 @@ static int nft_jhash_init(const struct nft_ctx *ctx, priv->len = len; - err = nft_parse_register_load(tb[NFTA_HASH_SREG], &priv->sreg, len); + err = nft_parse_register_load(ctx, tb[NFTA_HASH_SREG], &priv->sreg, len); if (err < 0) return err; diff --git a/net/netfilter/nft_immediate.c b/net/netfilter/nft_immediate.c index 6475c7abc1fe..02ee5fb69871 100644 --- a/net/netfilter/nft_immediate.c +++ b/net/netfilter/nft_immediate.c @@ -221,7 +221,7 @@ static void nft_immediate_destroy(const struct nft_ctx *ctx, list_del(&rule->list); nf_tables_rule_destroy(&chain_ctx, rule); } - nf_tables_chain_destroy(&chain_ctx); + nf_tables_chain_destroy(chain); break; default: break; @@ -244,8 +244,7 @@ nla_put_failure: } static int nft_immediate_validate(const struct nft_ctx *ctx, - const struct nft_expr *expr, - const struct nft_data **d) + const struct nft_expr *expr) { const struct nft_immediate_expr *priv = nft_expr_priv(expr); struct nft_ctx *pctx = (struct nft_ctx *)ctx; diff --git a/net/netfilter/nft_log.c b/net/netfilter/nft_log.c index 5defe6e4fd98..e35588137995 100644 --- a/net/netfilter/nft_log.c +++ b/net/netfilter/nft_log.c @@ -163,7 +163,7 @@ static int nft_log_init(const struct nft_ctx *ctx, nla = tb[NFTA_LOG_PREFIX]; if (nla != NULL) { - priv->prefix = kmalloc(nla_len(nla) + 1, GFP_KERNEL); + priv->prefix = kmalloc(nla_len(nla) + 1, GFP_KERNEL_ACCOUNT); if (priv->prefix == NULL) return -ENOMEM; nla_strscpy(priv->prefix, nla, nla_len(nla) + 1); diff --git a/net/netfilter/nft_lookup.c b/net/netfilter/nft_lookup.c index b314ca728a29..63ef832b8aa7 100644 --- a/net/netfilter/nft_lookup.c +++ b/net/netfilter/nft_lookup.c @@ -113,7 +113,7 @@ static int nft_lookup_init(const struct nft_ctx *ctx, if (IS_ERR(set)) return PTR_ERR(set); - err = nft_parse_register_load(tb[NFTA_LOOKUP_SREG], &priv->sreg, + err = nft_parse_register_load(ctx, tb[NFTA_LOOKUP_SREG], &priv->sreg, set->klen); if (err < 0) return err; @@ -132,7 +132,8 @@ static int nft_lookup_init(const struct nft_ctx *ctx, return -EINVAL; err = nft_parse_register_store(ctx, tb[NFTA_LOOKUP_DREG], - &priv->dreg, NULL, set->dtype, + &priv->dreg, NULL, + nft_set_datatype(set), set->dlen); if (err < 0) return err; @@ -205,8 +206,7 @@ nla_put_failure: } static int nft_lookup_validate(const struct nft_ctx *ctx, - const struct nft_expr *expr, - const struct nft_data **d) + const struct nft_expr *expr) { const struct nft_lookup *priv = nft_expr_priv(expr); struct nft_set_iter iter; diff --git a/net/netfilter/nft_masq.c b/net/netfilter/nft_masq.c index 8a14aaca93bb..868bd4d73555 100644 --- a/net/netfilter/nft_masq.c +++ b/net/netfilter/nft_masq.c @@ -27,8 +27,7 @@ static const struct nla_policy nft_masq_policy[NFTA_MASQ_MAX + 1] = { }; static int nft_masq_validate(const struct nft_ctx *ctx, - const struct nft_expr *expr, - const struct nft_data **data) + const struct nft_expr *expr) { int err; @@ -52,13 +51,13 @@ static int nft_masq_init(const struct nft_ctx *ctx, priv->flags = ntohl(nla_get_be32(tb[NFTA_MASQ_FLAGS])); if (tb[NFTA_MASQ_REG_PROTO_MIN]) { - err = nft_parse_register_load(tb[NFTA_MASQ_REG_PROTO_MIN], + err = nft_parse_register_load(ctx, tb[NFTA_MASQ_REG_PROTO_MIN], &priv->sreg_proto_min, plen); if (err < 0) return err; if (tb[NFTA_MASQ_REG_PROTO_MAX]) { - err = nft_parse_register_load(tb[NFTA_MASQ_REG_PROTO_MAX], + err = nft_parse_register_load(ctx, tb[NFTA_MASQ_REG_PROTO_MAX], &priv->sreg_proto_max, plen); if (err < 0) diff --git a/net/netfilter/nft_meta.c b/net/netfilter/nft_meta.c index 9139ce38ea7b..05cd1e6e6a2f 100644 --- a/net/netfilter/nft_meta.c +++ b/net/netfilter/nft_meta.c @@ -581,8 +581,7 @@ static int nft_meta_get_validate_xfrm(const struct nft_ctx *ctx) } static int nft_meta_get_validate(const struct nft_ctx *ctx, - const struct nft_expr *expr, - const struct nft_data **data) + const struct nft_expr *expr) { const struct nft_meta *priv = nft_expr_priv(expr); @@ -600,8 +599,7 @@ static int nft_meta_get_validate(const struct nft_ctx *ctx, } int nft_meta_set_validate(const struct nft_ctx *ctx, - const struct nft_expr *expr, - const struct nft_data **data) + const struct nft_expr *expr) { struct nft_meta *priv = nft_expr_priv(expr); unsigned int hooks; @@ -657,7 +655,7 @@ int nft_meta_set_init(const struct nft_ctx *ctx, } priv->len = len; - err = nft_parse_register_load(tb[NFTA_META_SREG], &priv->sreg, len); + err = nft_parse_register_load(ctx, tb[NFTA_META_SREG], &priv->sreg, len); if (err < 0) return err; @@ -954,7 +952,7 @@ static int nft_secmark_obj_init(const struct nft_ctx *ctx, if (tb[NFTA_SECMARK_CTX] == NULL) return -EINVAL; - priv->ctx = nla_strdup(tb[NFTA_SECMARK_CTX], GFP_KERNEL); + priv->ctx = nla_strdup(tb[NFTA_SECMARK_CTX], GFP_KERNEL_ACCOUNT); if (!priv->ctx) return -ENOMEM; diff --git a/net/netfilter/nft_nat.c b/net/netfilter/nft_nat.c index 808f5802c270..6e21f72c5b57 100644 --- a/net/netfilter/nft_nat.c +++ b/net/netfilter/nft_nat.c @@ -137,8 +137,7 @@ static const struct nla_policy nft_nat_policy[NFTA_NAT_MAX + 1] = { }; static int nft_nat_validate(const struct nft_ctx *ctx, - const struct nft_expr *expr, - const struct nft_data **data) + const struct nft_expr *expr) { struct nft_nat *priv = nft_expr_priv(expr); int err; @@ -214,13 +213,13 @@ static int nft_nat_init(const struct nft_ctx *ctx, const struct nft_expr *expr, priv->family = family; if (tb[NFTA_NAT_REG_ADDR_MIN]) { - err = nft_parse_register_load(tb[NFTA_NAT_REG_ADDR_MIN], + err = nft_parse_register_load(ctx, tb[NFTA_NAT_REG_ADDR_MIN], &priv->sreg_addr_min, alen); if (err < 0) return err; if (tb[NFTA_NAT_REG_ADDR_MAX]) { - err = nft_parse_register_load(tb[NFTA_NAT_REG_ADDR_MAX], + err = nft_parse_register_load(ctx, tb[NFTA_NAT_REG_ADDR_MAX], &priv->sreg_addr_max, alen); if (err < 0) @@ -234,13 +233,13 @@ static int nft_nat_init(const struct nft_ctx *ctx, const struct nft_expr *expr, plen = sizeof_field(struct nf_nat_range, min_proto.all); if (tb[NFTA_NAT_REG_PROTO_MIN]) { - err = nft_parse_register_load(tb[NFTA_NAT_REG_PROTO_MIN], + err = nft_parse_register_load(ctx, tb[NFTA_NAT_REG_PROTO_MIN], &priv->sreg_proto_min, plen); if (err < 0) return err; if (tb[NFTA_NAT_REG_PROTO_MAX]) { - err = nft_parse_register_load(tb[NFTA_NAT_REG_PROTO_MAX], + err = nft_parse_register_load(ctx, tb[NFTA_NAT_REG_PROTO_MAX], &priv->sreg_proto_max, plen); if (err < 0) diff --git a/net/netfilter/nft_numgen.c b/net/netfilter/nft_numgen.c index 7d29db7c2ac0..bd058babfc82 100644 --- a/net/netfilter/nft_numgen.c +++ b/net/netfilter/nft_numgen.c @@ -66,7 +66,7 @@ static int nft_ng_inc_init(const struct nft_ctx *ctx, if (priv->offset + priv->modulus - 1 < priv->offset) return -EOVERFLOW; - priv->counter = kmalloc(sizeof(*priv->counter), GFP_KERNEL); + priv->counter = kmalloc(sizeof(*priv->counter), GFP_KERNEL_ACCOUNT); if (!priv->counter) return -ENOMEM; diff --git a/net/netfilter/nft_objref.c b/net/netfilter/nft_objref.c index 509011b1ef59..09da7a3f9f96 100644 --- a/net/netfilter/nft_objref.c +++ b/net/netfilter/nft_objref.c @@ -143,7 +143,7 @@ static int nft_objref_map_init(const struct nft_ctx *ctx, if (!(set->flags & NFT_SET_OBJECT)) return -EINVAL; - err = nft_parse_register_load(tb[NFTA_OBJREF_SET_SREG], &priv->sreg, + err = nft_parse_register_load(ctx, tb[NFTA_OBJREF_SET_SREG], &priv->sreg, set->klen); if (err < 0) return err; diff --git a/net/netfilter/nft_osf.c b/net/netfilter/nft_osf.c index 7fec57ff736f..1c0b493ef0a9 100644 --- a/net/netfilter/nft_osf.c +++ b/net/netfilter/nft_osf.c @@ -108,8 +108,7 @@ nla_put_failure: } static int nft_osf_validate(const struct nft_ctx *ctx, - const struct nft_expr *expr, - const struct nft_data **data) + const struct nft_expr *expr) { unsigned int hooks; diff --git a/net/netfilter/nft_payload.c b/net/netfilter/nft_payload.c index 50429cbd42da..330609a76fb2 100644 --- a/net/netfilter/nft_payload.c +++ b/net/netfilter/nft_payload.c @@ -981,7 +981,7 @@ static int nft_payload_set_init(const struct nft_ctx *ctx, } priv->csum_type = csum_type; - return nft_parse_register_load(tb[NFTA_PAYLOAD_SREG], &priv->sreg, + return nft_parse_register_load(ctx, tb[NFTA_PAYLOAD_SREG], &priv->sreg, priv->len); } diff --git a/net/netfilter/nft_queue.c b/net/netfilter/nft_queue.c index b2b8127c8d43..344fe311878f 100644 --- a/net/netfilter/nft_queue.c +++ b/net/netfilter/nft_queue.c @@ -69,8 +69,7 @@ static void nft_queue_sreg_eval(const struct nft_expr *expr, } static int nft_queue_validate(const struct nft_ctx *ctx, - const struct nft_expr *expr, - const struct nft_data **data) + const struct nft_expr *expr) { static const unsigned int supported_hooks = ((1 << NF_INET_PRE_ROUTING) | (1 << NF_INET_LOCAL_IN) | @@ -136,7 +135,7 @@ static int nft_queue_sreg_init(const struct nft_ctx *ctx, struct nft_queue *priv = nft_expr_priv(expr); int err; - err = nft_parse_register_load(tb[NFTA_QUEUE_SREG_QNUM], + err = nft_parse_register_load(ctx, tb[NFTA_QUEUE_SREG_QNUM], &priv->sreg_qnum, sizeof(u32)); if (err < 0) return err; diff --git a/net/netfilter/nft_range.c b/net/netfilter/nft_range.c index 51ae64cd268f..ea382f7bbd78 100644 --- a/net/netfilter/nft_range.c +++ b/net/netfilter/nft_range.c @@ -83,7 +83,7 @@ static int nft_range_init(const struct nft_ctx *ctx, const struct nft_expr *expr goto err2; } - err = nft_parse_register_load(tb[NFTA_RANGE_SREG], &priv->sreg, + err = nft_parse_register_load(ctx, tb[NFTA_RANGE_SREG], &priv->sreg, desc_from.len); if (err < 0) goto err2; diff --git a/net/netfilter/nft_redir.c b/net/netfilter/nft_redir.c index a58bd8d291ff..95eedad85c83 100644 --- a/net/netfilter/nft_redir.c +++ b/net/netfilter/nft_redir.c @@ -27,8 +27,7 @@ static const struct nla_policy nft_redir_policy[NFTA_REDIR_MAX + 1] = { }; static int nft_redir_validate(const struct nft_ctx *ctx, - const struct nft_expr *expr, - const struct nft_data **data) + const struct nft_expr *expr) { int err; @@ -51,13 +50,13 @@ static int nft_redir_init(const struct nft_ctx *ctx, plen = sizeof_field(struct nf_nat_range, min_proto.all); if (tb[NFTA_REDIR_REG_PROTO_MIN]) { - err = nft_parse_register_load(tb[NFTA_REDIR_REG_PROTO_MIN], + err = nft_parse_register_load(ctx, tb[NFTA_REDIR_REG_PROTO_MIN], &priv->sreg_proto_min, plen); if (err < 0) return err; if (tb[NFTA_REDIR_REG_PROTO_MAX]) { - err = nft_parse_register_load(tb[NFTA_REDIR_REG_PROTO_MAX], + err = nft_parse_register_load(ctx, tb[NFTA_REDIR_REG_PROTO_MAX], &priv->sreg_proto_max, plen); if (err < 0) diff --git a/net/netfilter/nft_reject.c b/net/netfilter/nft_reject.c index ed2e668474d6..196a92c7ea09 100644 --- a/net/netfilter/nft_reject.c +++ b/net/netfilter/nft_reject.c @@ -24,8 +24,7 @@ const struct nla_policy nft_reject_policy[NFTA_REJECT_MAX + 1] = { EXPORT_SYMBOL_GPL(nft_reject_policy); int nft_reject_validate(const struct nft_ctx *ctx, - const struct nft_expr *expr, - const struct nft_data **data) + const struct nft_expr *expr) { return nft_chain_validate_hooks(ctx->chain, (1 << NF_INET_LOCAL_IN) | diff --git a/net/netfilter/nft_reject_inet.c b/net/netfilter/nft_reject_inet.c index 973fa31a9dd6..49020e67304a 100644 --- a/net/netfilter/nft_reject_inet.c +++ b/net/netfilter/nft_reject_inet.c @@ -61,8 +61,7 @@ static void nft_reject_inet_eval(const struct nft_expr *expr, } static int nft_reject_inet_validate(const struct nft_ctx *ctx, - const struct nft_expr *expr, - const struct nft_data **data) + const struct nft_expr *expr) { return nft_chain_validate_hooks(ctx->chain, (1 << NF_INET_LOCAL_IN) | diff --git a/net/netfilter/nft_reject_netdev.c b/net/netfilter/nft_reject_netdev.c index 7865cd8b11bb..2558ce1505d9 100644 --- a/net/netfilter/nft_reject_netdev.c +++ b/net/netfilter/nft_reject_netdev.c @@ -145,8 +145,7 @@ out: } static int nft_reject_netdev_validate(const struct nft_ctx *ctx, - const struct nft_expr *expr, - const struct nft_data **data) + const struct nft_expr *expr) { return nft_chain_validate_hooks(ctx->chain, (1 << NF_NETDEV_INGRESS)); } diff --git a/net/netfilter/nft_rt.c b/net/netfilter/nft_rt.c index 14d88394bcb7..dc50b9a5bd68 100644 --- a/net/netfilter/nft_rt.c +++ b/net/netfilter/nft_rt.c @@ -160,8 +160,7 @@ nla_put_failure: return -1; } -static int nft_rt_validate(const struct nft_ctx *ctx, const struct nft_expr *expr, - const struct nft_data **data) +static int nft_rt_validate(const struct nft_ctx *ctx, const struct nft_expr *expr) { const struct nft_rt *priv = nft_expr_priv(expr); unsigned int hooks; diff --git a/net/netfilter/nft_set_pipapo.c b/net/netfilter/nft_set_pipapo.c index 15a236bebb46..7be342b495f5 100644 --- a/net/netfilter/nft_set_pipapo.c +++ b/net/netfilter/nft_set_pipapo.c @@ -434,7 +434,7 @@ bool nft_pipapo_lookup(const struct net *net, const struct nft_set *set, res_map = scratch->map + (map_index ? m->bsize_max : 0); fill_map = scratch->map + (map_index ? 0 : m->bsize_max); - memset(res_map, 0xff, m->bsize_max * sizeof(*res_map)); + pipapo_resmap_init(m, res_map); nft_pipapo_for_each_field(f, i, m) { bool last = i == m->field_count - 1; @@ -542,7 +542,7 @@ static struct nft_pipapo_elem *pipapo_get(const struct net *net, goto out; } - memset(res_map, 0xff, m->bsize_max * sizeof(*res_map)); + pipapo_resmap_init(m, res_map); nft_pipapo_for_each_field(f, i, m) { bool last = i == m->field_count - 1; @@ -663,7 +663,7 @@ static int pipapo_realloc_mt(struct nft_pipapo_field *f, check_add_overflow(rules, extra, &rules_alloc)) return -EOVERFLOW; - new_mt = kvmalloc_array(rules_alloc, sizeof(*new_mt), GFP_KERNEL); + new_mt = kvmalloc_array(rules_alloc, sizeof(*new_mt), GFP_KERNEL_ACCOUNT); if (!new_mt) return -ENOMEM; @@ -936,7 +936,7 @@ static void pipapo_lt_bits_adjust(struct nft_pipapo_field *f) return; } - new_lt = kvzalloc(lt_size + NFT_PIPAPO_ALIGN_HEADROOM, GFP_KERNEL); + new_lt = kvzalloc(lt_size + NFT_PIPAPO_ALIGN_HEADROOM, GFP_KERNEL_ACCOUNT); if (!new_lt) return; @@ -1212,7 +1212,7 @@ static int pipapo_realloc_scratch(struct nft_pipapo_match *clone, scratch = kzalloc_node(struct_size(scratch, map, bsize_max * 2) + NFT_PIPAPO_ALIGN_HEADROOM, - GFP_KERNEL, cpu_to_node(i)); + GFP_KERNEL_ACCOUNT, cpu_to_node(i)); if (!scratch) { /* On failure, there's no need to undo previous * allocations: this means that some scratch maps have @@ -1427,7 +1427,7 @@ static struct nft_pipapo_match *pipapo_clone(struct nft_pipapo_match *old) struct nft_pipapo_match *new; int i; - new = kmalloc(struct_size(new, f, old->field_count), GFP_KERNEL); + new = kmalloc(struct_size(new, f, old->field_count), GFP_KERNEL_ACCOUNT); if (!new) return NULL; @@ -1457,7 +1457,7 @@ static struct nft_pipapo_match *pipapo_clone(struct nft_pipapo_match *old) new_lt = kvzalloc(src->groups * NFT_PIPAPO_BUCKETS(src->bb) * src->bsize * sizeof(*dst->lt) + NFT_PIPAPO_ALIGN_HEADROOM, - GFP_KERNEL); + GFP_KERNEL_ACCOUNT); if (!new_lt) goto out_lt; @@ -1470,7 +1470,8 @@ static struct nft_pipapo_match *pipapo_clone(struct nft_pipapo_match *old) if (src->rules > 0) { dst->mt = kvmalloc_array(src->rules_alloc, - sizeof(*src->mt), GFP_KERNEL); + sizeof(*src->mt), + GFP_KERNEL_ACCOUNT); if (!dst->mt) goto out_mt; diff --git a/net/netfilter/nft_set_pipapo.h b/net/netfilter/nft_set_pipapo.h index 0d2e40e10f7f..4a2ff85ce1c4 100644 --- a/net/netfilter/nft_set_pipapo.h +++ b/net/netfilter/nft_set_pipapo.h @@ -278,4 +278,25 @@ static u64 pipapo_estimate_size(const struct nft_set_desc *desc) return size; } +/** + * pipapo_resmap_init() - Initialise result map before first use + * @m: Matching data, including mapping table + * @res_map: Result map + * + * Initialize all bits covered by the first field to one, so that after + * the first step, only the matching bits of the first bit group remain. + * + * If other fields have a large bitmap, set remainder of res_map to 0. + */ +static inline void pipapo_resmap_init(const struct nft_pipapo_match *m, unsigned long *res_map) +{ + const struct nft_pipapo_field *f = m->f; + int i; + + for (i = 0; i < f->bsize; i++) + res_map[i] = ULONG_MAX; + + for (i = f->bsize; i < m->bsize_max; i++) + res_map[i] = 0ul; +} #endif /* _NFT_SET_PIPAPO_H */ diff --git a/net/netfilter/nft_set_pipapo_avx2.c b/net/netfilter/nft_set_pipapo_avx2.c index d08407d589ea..b8d3c3213efe 100644 --- a/net/netfilter/nft_set_pipapo_avx2.c +++ b/net/netfilter/nft_set_pipapo_avx2.c @@ -1036,6 +1036,7 @@ nothing: /** * nft_pipapo_avx2_lookup_slow() - Fallback function for uncommon field sizes + * @mdata: Matching data, including mapping table * @map: Previous match result, used as initial bitmap * @fill: Destination bitmap to be filled with current match result * @f: Field, containing lookup and mapping tables @@ -1051,7 +1052,8 @@ nothing: * Return: -1 on no match, rule index of match if @last, otherwise first long * word index to be checked next (i.e. first filled word). */ -static int nft_pipapo_avx2_lookup_slow(unsigned long *map, unsigned long *fill, +static int nft_pipapo_avx2_lookup_slow(const struct nft_pipapo_match *mdata, + unsigned long *map, unsigned long *fill, const struct nft_pipapo_field *f, int offset, const u8 *pkt, bool first, bool last) @@ -1060,7 +1062,7 @@ static int nft_pipapo_avx2_lookup_slow(unsigned long *map, unsigned long *fill, int i, ret = -1, b; if (first) - memset(map, 0xff, bsize * sizeof(*map)); + pipapo_resmap_init(mdata, map); for (i = offset; i < bsize; i++) { if (f->bb == 8) @@ -1137,8 +1139,14 @@ bool nft_pipapo_avx2_lookup(const struct net *net, const struct nft_set *set, bool map_index; int i, ret = 0; - if (unlikely(!irq_fpu_usable())) - return nft_pipapo_lookup(net, set, key, ext); + local_bh_disable(); + + if (unlikely(!irq_fpu_usable())) { + bool fallback_res = nft_pipapo_lookup(net, set, key, ext); + + local_bh_enable(); + return fallback_res; + } m = rcu_dereference(priv->match); @@ -1153,6 +1161,7 @@ bool nft_pipapo_avx2_lookup(const struct net *net, const struct nft_set *set, scratch = *raw_cpu_ptr(m->scratch); if (unlikely(!scratch)) { kernel_fpu_end(); + local_bh_enable(); return false; } @@ -1186,7 +1195,7 @@ next_match: } else if (f->groups == 16) { NFT_SET_PIPAPO_AVX2_LOOKUP(8, 16); } else { - ret = nft_pipapo_avx2_lookup_slow(res, fill, f, + ret = nft_pipapo_avx2_lookup_slow(m, res, fill, f, ret, rp, first, last); } @@ -1202,7 +1211,7 @@ next_match: } else if (f->groups == 32) { NFT_SET_PIPAPO_AVX2_LOOKUP(4, 32); } else { - ret = nft_pipapo_avx2_lookup_slow(res, fill, f, + ret = nft_pipapo_avx2_lookup_slow(m, res, fill, f, ret, rp, first, last); } @@ -1233,6 +1242,7 @@ out: if (i % 2) scratch->map_index = !map_index; kernel_fpu_end(); + local_bh_enable(); return ret >= 0; } diff --git a/net/netfilter/nft_socket.c b/net/netfilter/nft_socket.c index f30163e2ca62..f5da0c1775f2 100644 --- a/net/netfilter/nft_socket.c +++ b/net/netfilter/nft_socket.c @@ -9,7 +9,8 @@ struct nft_socket { enum nft_socket_keys key:8; - u8 level; + u8 level; /* cgroupv2 level to extract */ + u8 level_user; /* cgroupv2 level provided by userspace */ u8 len; union { u8 dreg; @@ -53,6 +54,28 @@ nft_sock_get_eval_cgroupv2(u32 *dest, struct sock *sk, const struct nft_pktinfo memcpy(dest, &cgid, sizeof(u64)); return true; } + +/* process context only, uses current->nsproxy. */ +static noinline int nft_socket_cgroup_subtree_level(void) +{ + struct cgroup *cgrp = cgroup_get_from_path("/"); + int level; + + if (IS_ERR(cgrp)) + return PTR_ERR(cgrp); + + level = cgrp->level; + + cgroup_put(cgrp); + + if (WARN_ON_ONCE(level > 255)) + return -ERANGE; + + if (WARN_ON_ONCE(level < 0)) + return -EINVAL; + + return level; +} #endif static struct sock *nft_socket_do_lookup(const struct nft_pktinfo *pkt) @@ -110,13 +133,13 @@ static void nft_socket_eval(const struct nft_expr *expr, *dest = READ_ONCE(sk->sk_mark); } else { regs->verdict.code = NFT_BREAK; - return; + goto out_put_sk; } break; case NFT_SOCKET_WILDCARD: if (!sk_fullsock(sk)) { regs->verdict.code = NFT_BREAK; - return; + goto out_put_sk; } nft_socket_wildcard(pkt, regs, sk, dest); break; @@ -124,7 +147,7 @@ static void nft_socket_eval(const struct nft_expr *expr, case NFT_SOCKET_CGROUPV2: if (!nft_sock_get_eval_cgroupv2(dest, sk, pkt, priv->level)) { regs->verdict.code = NFT_BREAK; - return; + goto out_put_sk; } break; #endif @@ -133,6 +156,7 @@ static void nft_socket_eval(const struct nft_expr *expr, regs->verdict.code = NFT_BREAK; } +out_put_sk: if (sk != skb->sk) sock_gen_put(sk); } @@ -173,9 +197,10 @@ static int nft_socket_init(const struct nft_ctx *ctx, case NFT_SOCKET_MARK: len = sizeof(u32); break; -#ifdef CONFIG_CGROUPS +#ifdef CONFIG_SOCK_CGROUP_DATA case NFT_SOCKET_CGROUPV2: { unsigned int level; + int err; if (!tb[NFTA_SOCKET_LEVEL]) return -EINVAL; @@ -184,6 +209,17 @@ static int nft_socket_init(const struct nft_ctx *ctx, if (level > 255) return -EOPNOTSUPP; + err = nft_socket_cgroup_subtree_level(); + if (err < 0) + return err; + + priv->level_user = level; + + level += err; + /* Implies a giant cgroup tree */ + if (WARN_ON_ONCE(level > 255)) + return -EOPNOTSUPP; + priv->level = level; len = sizeof(u64); break; @@ -208,7 +244,7 @@ static int nft_socket_dump(struct sk_buff *skb, if (nft_dump_register(skb, NFTA_SOCKET_DREG, priv->dreg)) return -1; if (priv->key == NFT_SOCKET_CGROUPV2 && - nla_put_be32(skb, NFTA_SOCKET_LEVEL, htonl(priv->level))) + nla_put_be32(skb, NFTA_SOCKET_LEVEL, htonl(priv->level_user))) return -1; return 0; } @@ -239,8 +275,7 @@ static bool nft_socket_reduce(struct nft_regs_track *track, } static int nft_socket_validate(const struct nft_ctx *ctx, - const struct nft_expr *expr, - const struct nft_data **data) + const struct nft_expr *expr) { if (ctx->family != NFPROTO_IPV4 && ctx->family != NFPROTO_IPV6 && diff --git a/net/netfilter/nft_synproxy.c b/net/netfilter/nft_synproxy.c index 1d737f89dfc1..5d3e51825985 100644 --- a/net/netfilter/nft_synproxy.c +++ b/net/netfilter/nft_synproxy.c @@ -248,8 +248,7 @@ static void nft_synproxy_eval(const struct nft_expr *expr, } static int nft_synproxy_validate(const struct nft_ctx *ctx, - const struct nft_expr *expr, - const struct nft_data **data) + const struct nft_expr *expr) { if (ctx->family != NFPROTO_IPV4 && ctx->family != NFPROTO_IPV6 && diff --git a/net/netfilter/nft_tproxy.c b/net/netfilter/nft_tproxy.c index 71412adb73d4..50481280abd2 100644 --- a/net/netfilter/nft_tproxy.c +++ b/net/netfilter/nft_tproxy.c @@ -254,14 +254,14 @@ static int nft_tproxy_init(const struct nft_ctx *ctx, } if (tb[NFTA_TPROXY_REG_ADDR]) { - err = nft_parse_register_load(tb[NFTA_TPROXY_REG_ADDR], + err = nft_parse_register_load(ctx, tb[NFTA_TPROXY_REG_ADDR], &priv->sreg_addr, alen); if (err < 0) return err; } if (tb[NFTA_TPROXY_REG_PORT]) { - err = nft_parse_register_load(tb[NFTA_TPROXY_REG_PORT], + err = nft_parse_register_load(ctx, tb[NFTA_TPROXY_REG_PORT], &priv->sreg_port, sizeof(u16)); if (err < 0) return err; @@ -313,8 +313,7 @@ static int nft_tproxy_dump(struct sk_buff *skb, } static int nft_tproxy_validate(const struct nft_ctx *ctx, - const struct nft_expr *expr, - const struct nft_data **data) + const struct nft_expr *expr) { if (ctx->family != NFPROTO_IPV4 && ctx->family != NFPROTO_IPV6 && diff --git a/net/netfilter/nft_tunnel.c b/net/netfilter/nft_tunnel.c index 60a76e6e348e..5c6ed68cc6e0 100644 --- a/net/netfilter/nft_tunnel.c +++ b/net/netfilter/nft_tunnel.c @@ -509,13 +509,14 @@ static int nft_tunnel_obj_init(const struct nft_ctx *ctx, return err; } - md = metadata_dst_alloc(priv->opts.len, METADATA_IP_TUNNEL, GFP_KERNEL); + md = metadata_dst_alloc(priv->opts.len, METADATA_IP_TUNNEL, + GFP_KERNEL_ACCOUNT); if (!md) return -ENOMEM; memcpy(&md->u.tun_info, &info, sizeof(info)); #ifdef CONFIG_DST_CACHE - err = dst_cache_init(&md->u.tun_info.dst_cache, GFP_KERNEL); + err = dst_cache_init(&md->u.tun_info.dst_cache, GFP_KERNEL_ACCOUNT); if (err < 0) { metadata_dst_free(md); return err; diff --git a/net/netfilter/nft_xfrm.c b/net/netfilter/nft_xfrm.c index 1c866757db55..8a07b46cc8fb 100644 --- a/net/netfilter/nft_xfrm.c +++ b/net/netfilter/nft_xfrm.c @@ -229,8 +229,7 @@ static int nft_xfrm_get_dump(struct sk_buff *skb, return 0; } -static int nft_xfrm_validate(const struct nft_ctx *ctx, const struct nft_expr *expr, - const struct nft_data **data) +static int nft_xfrm_validate(const struct nft_ctx *ctx, const struct nft_expr *expr) { const struct nft_xfrm *priv = nft_expr_priv(expr); unsigned int hooks; diff --git a/net/netfilter/xt_connlimit.c b/net/netfilter/xt_connlimit.c index 5d04ef80a61d..0e762277bcf8 100644 --- a/net/netfilter/xt_connlimit.c +++ b/net/netfilter/xt_connlimit.c @@ -86,6 +86,7 @@ static int connlimit_mt_check(const struct xt_mtchk_param *par) { struct xt_connlimit_info *info = par->matchinfo; unsigned int keylen; + int ret; keylen = sizeof(u32); if (par->family == NFPROTO_IPV6) @@ -93,8 +94,17 @@ static int connlimit_mt_check(const struct xt_mtchk_param *par) else keylen += sizeof(struct in_addr); + ret = nf_ct_netns_get(par->net, par->family); + if (ret < 0) { + pr_info_ratelimited("cannot load conntrack support for proto=%u\n", + par->family); + return ret; + } + /* init private data */ - info->data = nf_conncount_init(par->net, par->family, keylen); + info->data = nf_conncount_init(par->net, keylen); + if (IS_ERR(info->data)) + nf_ct_netns_put(par->net, par->family); return PTR_ERR_OR_ZERO(info->data); } @@ -103,7 +113,8 @@ static void connlimit_mt_destroy(const struct xt_mtdtor_param *par) { const struct xt_connlimit_info *info = par->matchinfo; - nf_conncount_destroy(par->net, par->family, info->data); + nf_conncount_destroy(par->net, info->data); + nf_ct_netns_put(par->net, par->family); } static struct xt_match connlimit_mt_reg __read_mostly = { diff --git a/net/netfilter/xt_recent.c b/net/netfilter/xt_recent.c index ef93e0d3bee0..588a5e6ad899 100644 --- a/net/netfilter/xt_recent.c +++ b/net/netfilter/xt_recent.c @@ -59,9 +59,9 @@ MODULE_PARM_DESC(ip_list_gid, "default owning group of /proc/net/xt_recent/* fil /* retained for backwards compatibility */ static unsigned int ip_pkt_list_tot __read_mostly; module_param(ip_pkt_list_tot, uint, 0400); -MODULE_PARM_DESC(ip_pkt_list_tot, "number of packets per IP address to remember (max. 255)"); +MODULE_PARM_DESC(ip_pkt_list_tot, "number of packets per IP address to remember (max. 65535)"); -#define XT_RECENT_MAX_NSTAMPS 256 +#define XT_RECENT_MAX_NSTAMPS 65536 struct recent_entry { struct list_head list; @@ -69,7 +69,7 @@ struct recent_entry { union nf_inet_addr addr; u_int16_t family; u_int8_t ttl; - u_int8_t index; + u_int16_t index; u_int16_t nstamps; unsigned long stamps[]; }; @@ -80,7 +80,7 @@ struct recent_table { union nf_inet_addr mask; unsigned int refcnt; unsigned int entries; - u8 nstamps_max_mask; + u_int16_t nstamps_max_mask; struct list_head lru_list; struct list_head iphash[]; }; diff --git a/net/netlink/af_netlink.c b/net/netlink/af_netlink.c index fa9c090cf629..0b7a89db3ab7 100644 --- a/net/netlink/af_netlink.c +++ b/net/netlink/af_netlink.c @@ -636,8 +636,7 @@ static struct proto netlink_proto = { }; static int __netlink_create(struct net *net, struct socket *sock, - struct mutex *dump_cb_mutex, int protocol, - int kern) + int protocol, int kern) { struct sock *sk; struct netlink_sock *nlk; @@ -655,7 +654,6 @@ static int __netlink_create(struct net *net, struct socket *sock, lockdep_set_class_and_name(&nlk->nl_cb_mutex, nlk_cb_mutex_keys + protocol, nlk_cb_mutex_key_strings[protocol]); - nlk->dump_cb_mutex = dump_cb_mutex; init_waitqueue_head(&nlk->wait); sk->sk_destruct = netlink_sock_destruct; @@ -667,7 +665,6 @@ static int netlink_create(struct net *net, struct socket *sock, int protocol, int kern) { struct module *module = NULL; - struct mutex *cb_mutex; struct netlink_sock *nlk; int (*bind)(struct net *net, int group); void (*unbind)(struct net *net, int group); @@ -696,7 +693,6 @@ static int netlink_create(struct net *net, struct socket *sock, int protocol, module = nl_table[protocol].module; else err = -EPROTONOSUPPORT; - cb_mutex = nl_table[protocol].cb_mutex; bind = nl_table[protocol].bind; unbind = nl_table[protocol].unbind; release = nl_table[protocol].release; @@ -705,7 +701,7 @@ static int netlink_create(struct net *net, struct socket *sock, int protocol, if (err < 0) goto out; - err = __netlink_create(net, sock, cb_mutex, protocol, kern); + err = __netlink_create(net, sock, protocol, kern); if (err < 0) goto out_module; @@ -2016,7 +2012,6 @@ __netlink_kernel_create(struct net *net, int unit, struct module *module, struct sock *sk; struct netlink_sock *nlk; struct listeners *listeners = NULL; - struct mutex *cb_mutex = cfg ? cfg->cb_mutex : NULL; unsigned int groups; BUG_ON(!nl_table); @@ -2027,7 +2022,7 @@ __netlink_kernel_create(struct net *net, int unit, struct module *module, if (sock_create_lite(PF_NETLINK, SOCK_DGRAM, unit, &sock)) return NULL; - if (__netlink_create(net, sock, cb_mutex, unit, 1) < 0) + if (__netlink_create(net, sock, unit, 1) < 0) goto out_sock_release_nosk; sk = sock->sk; @@ -2055,7 +2050,6 @@ __netlink_kernel_create(struct net *net, int unit, struct module *module, if (!nl_table[unit].registered) { nl_table[unit].groups = groups; rcu_assign_pointer(nl_table[unit].listeners, listeners); - nl_table[unit].cb_mutex = cb_mutex; nl_table[unit].module = module; if (cfg) { nl_table[unit].bind = cfg->bind; @@ -2326,17 +2320,9 @@ static int netlink_dump(struct sock *sk, bool lock_taken) netlink_skb_set_owner_r(skb, sk); if (nlk->dump_done_errno > 0) { - struct mutex *extra_mutex = nlk->dump_cb_mutex; - cb->extack = &extack; - if (cb->flags & RTNL_FLAG_DUMP_UNLOCKED) - extra_mutex = NULL; - if (extra_mutex) - mutex_lock(extra_mutex); nlk->dump_done_errno = cb->dump(skb, cb); - if (extra_mutex) - mutex_unlock(extra_mutex); /* EMSGSIZE plus something already in the skb means * that there's more to dump but current skb has filled up. diff --git a/net/netlink/af_netlink.h b/net/netlink/af_netlink.h index 9751e29d4bbb..5b0e4e62ab8b 100644 --- a/net/netlink/af_netlink.h +++ b/net/netlink/af_netlink.h @@ -41,7 +41,6 @@ struct netlink_sock { struct netlink_callback cb; struct mutex nl_cb_mutex; - struct mutex *dump_cb_mutex; void (*netlink_rcv)(struct sk_buff *skb); int (*netlink_bind)(struct net *net, int group); void (*netlink_unbind)(struct net *net, int group); diff --git a/net/netrom/nr_route.c b/net/netrom/nr_route.c index bd2b17b219ae..2b5e246b8d9a 100644 --- a/net/netrom/nr_route.c +++ b/net/netrom/nr_route.c @@ -189,7 +189,7 @@ static int __must_check nr_add_node(ax25_address *nr, const char *mnemonic, } nr_node->callsign = *nr; - strcpy(nr_node->mnemonic, mnemonic); + strscpy(nr_node->mnemonic, mnemonic); nr_node->which = 0; nr_node->count = 1; @@ -214,7 +214,7 @@ static int __must_check nr_add_node(ax25_address *nr, const char *mnemonic, nr_node_lock(nr_node); if (quality != 0) - strcpy(nr_node->mnemonic, mnemonic); + strscpy(nr_node->mnemonic, mnemonic); for (found = 0, i = 0; i < nr_node->count; i++) { if (nr_node->routes[i].neighbour == nr_neigh) { diff --git a/net/openvswitch/Kconfig b/net/openvswitch/Kconfig index 29a7081858cd..2535f3f9f462 100644 --- a/net/openvswitch/Kconfig +++ b/net/openvswitch/Kconfig @@ -10,6 +10,7 @@ config OPENVSWITCH (NF_CONNTRACK && ((!NF_DEFRAG_IPV6 || NF_DEFRAG_IPV6) && \ (!NF_NAT || NF_NAT) && \ (!NETFILTER_CONNCOUNT || NETFILTER_CONNCOUNT))) + depends on PSAMPLE || !PSAMPLE select LIBCRC32C select MPLS select NET_MPLS_GSO diff --git a/net/openvswitch/actions.c b/net/openvswitch/actions.c index 964225580824..16e260014684 100644 --- a/net/openvswitch/actions.c +++ b/net/openvswitch/actions.c @@ -24,6 +24,11 @@ #include <net/checksum.h> #include <net/dsfield.h> #include <net/mpls.h> + +#if IS_ENABLED(CONFIG_PSAMPLE) +#include <net/psample.h> +#endif + #include <net/sctp/checksum.h> #include "datapath.h" @@ -232,14 +237,18 @@ static int pop_vlan(struct sk_buff *skb, struct sw_flow_key *key) static int push_vlan(struct sk_buff *skb, struct sw_flow_key *key, const struct ovs_action_push_vlan *vlan) { + int err; + if (skb_vlan_tag_present(skb)) { invalidate_flow_key(key); } else { key->eth.vlan.tci = vlan->vlan_tci; key->eth.vlan.tpid = vlan->vlan_tpid; } - return skb_vlan_push(skb, vlan->vlan_tpid, - ntohs(vlan->vlan_tci) & ~VLAN_CFI_MASK); + err = skb_vlan_push(skb, vlan->vlan_tpid, + ntohs(vlan->vlan_tci) & ~VLAN_CFI_MASK); + skb_reset_mac_len(skb); + return err; } /* 'src' is already properly masked. */ @@ -1043,12 +1052,15 @@ static int sample(struct datapath *dp, struct sk_buff *skb, struct nlattr *sample_arg; int rem = nla_len(attr); const struct sample_arg *arg; + u32 init_probability; bool clone_flow_key; + int err; /* The first action is always 'OVS_SAMPLE_ATTR_ARG'. */ sample_arg = nla_data(attr); arg = nla_data(sample_arg); actions = nla_next(sample_arg, &rem); + init_probability = OVS_CB(skb)->probability; if ((arg->probability != U32_MAX) && (!arg->probability || get_random_u32() > arg->probability)) { @@ -1057,9 +1069,16 @@ static int sample(struct datapath *dp, struct sk_buff *skb, return 0; } + OVS_CB(skb)->probability = arg->probability; + clone_flow_key = !arg->exec; - return clone_execute(dp, skb, key, 0, actions, rem, last, - clone_flow_key); + err = clone_execute(dp, skb, key, 0, actions, rem, last, + clone_flow_key); + + if (!last) + OVS_CB(skb)->probability = init_probability; + + return err; } /* When 'last' is true, clone() should always consume the 'skb'. @@ -1299,6 +1318,44 @@ static int execute_dec_ttl(struct sk_buff *skb, struct sw_flow_key *key) return 0; } +#if IS_ENABLED(CONFIG_PSAMPLE) +static void execute_psample(struct datapath *dp, struct sk_buff *skb, + const struct nlattr *attr) +{ + struct psample_group psample_group = {}; + struct psample_metadata md = {}; + const struct nlattr *a; + u32 rate; + int rem; + + nla_for_each_attr(a, nla_data(attr), nla_len(attr), rem) { + switch (nla_type(a)) { + case OVS_PSAMPLE_ATTR_GROUP: + psample_group.group_num = nla_get_u32(a); + break; + + case OVS_PSAMPLE_ATTR_COOKIE: + md.user_cookie = nla_data(a); + md.user_cookie_len = nla_len(a); + break; + } + } + + psample_group.net = ovs_dp_get_net(dp); + md.in_ifindex = OVS_CB(skb)->input_vport->dev->ifindex; + md.trunc_size = skb->len - OVS_CB(skb)->cutlen; + md.rate_as_probability = 1; + + rate = OVS_CB(skb)->probability ? OVS_CB(skb)->probability : U32_MAX; + + psample_sample_packet(&psample_group, skb, rate, &md); +} +#else +static void execute_psample(struct datapath *dp, struct sk_buff *skb, + const struct nlattr *attr) +{} +#endif + /* Execute a list of actions against 'skb'. */ static int do_execute_actions(struct datapath *dp, struct sk_buff *skb, struct sw_flow_key *key, @@ -1502,6 +1559,15 @@ static int do_execute_actions(struct datapath *dp, struct sk_buff *skb, ovs_kfree_skb_reason(skb, reason); return 0; } + + case OVS_ACTION_ATTR_PSAMPLE: + execute_psample(dp, skb, a); + OVS_CB(skb)->cutlen = 0; + if (nla_is_last(a, rem)) { + consume_skb(skb); + return 0; + } + break; } if (unlikely(err)) { diff --git a/net/openvswitch/conntrack.c b/net/openvswitch/conntrack.c index 2928c142a2dd..3bb4810234aa 100644 --- a/net/openvswitch/conntrack.c +++ b/net/openvswitch/conntrack.c @@ -168,8 +168,13 @@ static u32 ovs_ct_get_mark(const struct nf_conn *ct) static void ovs_ct_get_labels(const struct nf_conn *ct, struct ovs_key_ct_labels *labels) { - struct nf_conn_labels *cl = ct ? nf_ct_labels_find(ct) : NULL; + struct nf_conn_labels *cl = NULL; + if (ct) { + if (ct->master && !nf_ct_is_confirmed(ct)) + ct = ct->master; + cl = nf_ct_labels_find(ct); + } if (cl) memcpy(labels, cl->bits, OVS_CT_LABELS_LEN); else @@ -674,6 +679,8 @@ static int ovs_ct_nat(struct net *net, struct sw_flow_key *key, action |= BIT(NF_NAT_MANIP_DST); err = nf_ct_nat(skb, ct, ctinfo, &action, &info->range, info->commit); + if (err != NF_ACCEPT) + return err; if (action & BIT(NF_NAT_MANIP_SRC)) ovs_nat_update_key(key, skb, NF_NAT_MANIP_SRC); @@ -692,6 +699,22 @@ static int ovs_ct_nat(struct net *net, struct sw_flow_key *key, } #endif +static int verdict_to_errno(unsigned int verdict) +{ + switch (verdict & NF_VERDICT_MASK) { + case NF_ACCEPT: + return 0; + case NF_DROP: + return -EINVAL; + case NF_STOLEN: + return -EINPROGRESS; + default: + break; + } + + return -EINVAL; +} + /* Pass 'skb' through conntrack in 'net', using zone configured in 'info', if * not done already. Update key with new CT state after passing the packet * through conntrack. @@ -730,7 +753,7 @@ static int __ovs_ct_lookup(struct net *net, struct sw_flow_key *key, err = nf_conntrack_in(skb, &state); if (err != NF_ACCEPT) - return -ENOENT; + return verdict_to_errno(err); /* Clear CT state NAT flags to mark that we have not yet done * NAT after the nf_conntrack_in() call. We can actually clear @@ -757,9 +780,12 @@ static int __ovs_ct_lookup(struct net *net, struct sw_flow_key *key, * the key->ct_state. */ if (info->nat && !(key->ct_state & OVS_CS_F_NAT_MASK) && - (nf_ct_is_confirmed(ct) || info->commit) && - ovs_ct_nat(net, key, info, skb, ct, ctinfo) != NF_ACCEPT) { - return -EINVAL; + (nf_ct_is_confirmed(ct) || info->commit)) { + int err = ovs_ct_nat(net, key, info, skb, ct, ctinfo); + + err = verdict_to_errno(err); + if (err) + return err; } /* Userspace may decide to perform a ct lookup without a helper @@ -790,9 +816,12 @@ static int __ovs_ct_lookup(struct net *net, struct sw_flow_key *key, * - When committing an unconfirmed connection. */ if ((nf_ct_is_confirmed(ct) ? !cached || add_helper : - info->commit) && - nf_ct_helper(skb, ct, ctinfo, info->family) != NF_ACCEPT) { - return -EINVAL; + info->commit)) { + int err = nf_ct_helper(skb, ct, ctinfo, info->family); + + err = verdict_to_errno(err); + if (err) + return err; } if (nf_ct_protonum(ct) == IPPROTO_TCP && @@ -996,10 +1025,9 @@ static int ovs_ct_commit(struct net *net, struct sw_flow_key *key, /* This will take care of sending queued events even if the connection * is already confirmed. */ - if (nf_conntrack_confirm(skb) != NF_ACCEPT) - return -EINVAL; + err = nf_conntrack_confirm(skb); - return 0; + return verdict_to_errno(err); } /* Returns 0 on success, -EINPROGRESS if 'skb' is stolen, or other nonzero @@ -1034,6 +1062,10 @@ int ovs_ct_execute(struct net *net, struct sk_buff *skb, else err = ovs_ct_lookup(net, key, info, skb); + /* conntrack core returned NF_STOLEN */ + if (err == -EINPROGRESS) + return err; + skb_push_rcsum(skb, nh_ofs); if (err) ovs_kfree_skb_reason(skb, OVS_DROP_CONNTRACK); @@ -1336,11 +1368,8 @@ bool ovs_ct_verify(struct net *net, enum ovs_key_attr attr) attr == OVS_KEY_ATTR_CT_MARK) return true; if (IS_ENABLED(CONFIG_NF_CONNTRACK_LABELS) && - attr == OVS_KEY_ATTR_CT_LABELS) { - struct ovs_net *ovs_net = net_generic(net, ovs_net_id); - - return ovs_net->xt_label; - } + attr == OVS_KEY_ATTR_CT_LABELS) + return true; return false; } @@ -1349,6 +1378,7 @@ int ovs_ct_copy_action(struct net *net, const struct nlattr *attr, const struct sw_flow_key *key, struct sw_flow_actions **sfa, bool log) { + unsigned int n_bits = sizeof(struct ovs_key_ct_labels) * BITS_PER_BYTE; struct ovs_conntrack_info ct_info; const char *helper = NULL; u16 family; @@ -1377,6 +1407,12 @@ int ovs_ct_copy_action(struct net *net, const struct nlattr *attr, return -ENOMEM; } + if (nf_connlabels_get(net, n_bits - 1)) { + nf_ct_tmpl_free(ct_info.ct); + OVS_NLERR(log, "Failed to set connlabel length"); + return -EOPNOTSUPP; + } + if (ct_info.timeout[0]) { if (nf_ct_set_timeout(net, ct_info.ct, family, key->ip.proto, ct_info.timeout)) @@ -1545,6 +1581,7 @@ static void __ovs_ct_free_action(struct ovs_conntrack_info *ct_info) if (ct_info->ct) { if (ct_info->timeout[0]) nf_ct_destroy_timeout(ct_info->ct); + nf_connlabels_put(nf_ct_net(ct_info->ct)); nf_ct_tmpl_free(ct_info->ct); } } @@ -1571,8 +1608,7 @@ static int ovs_ct_limit_init(struct net *net, struct ovs_net *ovs_net) for (i = 0; i < CT_LIMIT_HASH_BUCKETS; i++) INIT_HLIST_HEAD(&ovs_net->ct_limit_info->limits[i]); - ovs_net->ct_limit_info->data = - nf_conncount_init(net, NFPROTO_INET, sizeof(u32)); + ovs_net->ct_limit_info->data = nf_conncount_init(net, sizeof(u32)); if (IS_ERR(ovs_net->ct_limit_info->data)) { err = PTR_ERR(ovs_net->ct_limit_info->data); @@ -1589,7 +1625,7 @@ static void ovs_ct_limit_exit(struct net *net, struct ovs_net *ovs_net) const struct ovs_ct_limit_info *info = ovs_net->ct_limit_info; int i; - nf_conncount_destroy(net, NFPROTO_INET, info->data); + nf_conncount_destroy(net, info->data); for (i = 0; i < CT_LIMIT_HASH_BUCKETS; ++i) { struct hlist_head *head = &info->limits[i]; struct ovs_ct_limit *ct_limit; @@ -1970,17 +2006,9 @@ struct genl_family dp_ct_limit_genl_family __ro_after_init = { int ovs_ct_init(struct net *net) { - unsigned int n_bits = sizeof(struct ovs_key_ct_labels) * BITS_PER_BYTE; +#if IS_ENABLED(CONFIG_NETFILTER_CONNCOUNT) struct ovs_net *ovs_net = net_generic(net, ovs_net_id); - if (nf_connlabels_get(net, n_bits - 1)) { - ovs_net->xt_label = false; - OVS_NLERR(true, "Failed to set connlabel length"); - } else { - ovs_net->xt_label = true; - } - -#if IS_ENABLED(CONFIG_NETFILTER_CONNCOUNT) return ovs_ct_limit_init(net, ovs_net); #else return 0; @@ -1989,12 +2017,9 @@ int ovs_ct_init(struct net *net) void ovs_ct_exit(struct net *net) { +#if IS_ENABLED(CONFIG_NETFILTER_CONNCOUNT) struct ovs_net *ovs_net = net_generic(net, ovs_net_id); -#if IS_ENABLED(CONFIG_NETFILTER_CONNCOUNT) ovs_ct_limit_exit(net, ovs_net); #endif - - if (ovs_net->xt_label) - nf_connlabels_put(net); } diff --git a/net/openvswitch/datapath.c b/net/openvswitch/datapath.c index 99d72543abd3..78d9961fcd44 100644 --- a/net/openvswitch/datapath.c +++ b/net/openvswitch/datapath.c @@ -2706,7 +2706,7 @@ static struct pernet_operations ovs_net_ops = { }; static const char * const ovs_drop_reasons[] = { -#define S(x) (#x), +#define S(x) [(x) & ~SKB_DROP_REASON_SUBSYS_MASK] = (#x), OVS_DROP_REASONS(S) #undef S }; diff --git a/net/openvswitch/datapath.h b/net/openvswitch/datapath.h index 0cd29971a907..365b9bb7f546 100644 --- a/net/openvswitch/datapath.h +++ b/net/openvswitch/datapath.h @@ -115,12 +115,15 @@ struct datapath { * fragmented. * @acts_origlen: The netlink size of the flow actions applied to this skb. * @cutlen: The number of bytes from the packet end to be removed. + * @probability: The sampling probability that was applied to this skb; 0 means + * no sampling has occurred; U32_MAX means 100% probability. */ struct ovs_skb_cb { struct vport *input_vport; u16 mru; u16 acts_origlen; u32 cutlen; + u32 probability; }; #define OVS_CB(skb) ((struct ovs_skb_cb *)(skb)->cb) @@ -157,9 +160,6 @@ struct ovs_net { #if IS_ENABLED(CONFIG_NETFILTER_CONNCOUNT) struct ovs_ct_limit_info *ct_limit_info; #endif - - /* Module reference for configuring conntrack. */ - bool xt_label; }; /** diff --git a/net/openvswitch/flow_netlink.c b/net/openvswitch/flow_netlink.c index f224d9bcea5e..729ef582a3a8 100644 --- a/net/openvswitch/flow_netlink.c +++ b/net/openvswitch/flow_netlink.c @@ -64,6 +64,7 @@ static bool actions_may_change_flow(const struct nlattr *actions) case OVS_ACTION_ATTR_TRUNC: case OVS_ACTION_ATTR_USERSPACE: case OVS_ACTION_ATTR_DROP: + case OVS_ACTION_ATTR_PSAMPLE: break; case OVS_ACTION_ATTR_CT: @@ -2409,7 +2410,7 @@ static void ovs_nla_free_nested_actions(const struct nlattr *actions, int len) /* Whenever new actions are added, the need to update this * function should be considered. */ - BUILD_BUG_ON(OVS_ACTION_ATTR_MAX != 24); + BUILD_BUG_ON(OVS_ACTION_ATTR_MAX != 25); if (!actions) return; @@ -2490,7 +2491,7 @@ static struct nlattr *reserve_sfa_size(struct sw_flow_actions **sfa, acts = nla_alloc_flow_actions(new_acts_size); if (IS_ERR(acts)) - return (void *)acts; + return ERR_CAST(acts); memcpy(acts->actions, (*sfa)->actions, (*sfa)->actions_len); acts->actions_len = (*sfa)->actions_len; @@ -3157,6 +3158,28 @@ static int validate_and_copy_check_pkt_len(struct net *net, return 0; } +static int validate_psample(const struct nlattr *attr) +{ + static const struct nla_policy policy[OVS_PSAMPLE_ATTR_MAX + 1] = { + [OVS_PSAMPLE_ATTR_GROUP] = { .type = NLA_U32 }, + [OVS_PSAMPLE_ATTR_COOKIE] = { + .type = NLA_BINARY, + .len = OVS_PSAMPLE_COOKIE_MAX_SIZE, + }, + }; + struct nlattr *a[OVS_PSAMPLE_ATTR_MAX + 1]; + int err; + + if (!IS_ENABLED(CONFIG_PSAMPLE)) + return -EOPNOTSUPP; + + err = nla_parse_nested(a, OVS_PSAMPLE_ATTR_MAX, attr, policy, NULL); + if (err) + return err; + + return a[OVS_PSAMPLE_ATTR_GROUP] ? 0 : -EINVAL; +} + static int copy_action(const struct nlattr *from, struct sw_flow_actions **sfa, bool log) { @@ -3212,6 +3235,7 @@ static int __ovs_nla_copy_actions(struct net *net, const struct nlattr *attr, [OVS_ACTION_ATTR_ADD_MPLS] = sizeof(struct ovs_action_add_mpls), [OVS_ACTION_ATTR_DEC_TTL] = (u32)-1, [OVS_ACTION_ATTR_DROP] = sizeof(u32), + [OVS_ACTION_ATTR_PSAMPLE] = (u32)-1, }; const struct ovs_action_push_vlan *vlan; int type = nla_type(a); @@ -3490,6 +3514,12 @@ static int __ovs_nla_copy_actions(struct net *net, const struct nlattr *attr, return -EINVAL; break; + case OVS_ACTION_ATTR_PSAMPLE: + err = validate_psample(a); + if (err) + return err; + break; + default: OVS_NLERR(log, "Unknown Action type %d", type); return -EINVAL; diff --git a/net/openvswitch/vport-internal_dev.c b/net/openvswitch/vport-internal_dev.c index 74c88a6baa43..5858d65ea1a9 100644 --- a/net/openvswitch/vport-internal_dev.c +++ b/net/openvswitch/vport-internal_dev.c @@ -85,7 +85,6 @@ static const struct net_device_ops internal_dev_netdev_ops = { .ndo_stop = internal_dev_stop, .ndo_start_xmit = internal_dev_xmit, .ndo_set_mac_address = eth_mac_addr, - .ndo_get_stats64 = dev_get_tstats64, }; static struct rtnl_link_ops internal_dev_link_ops __read_mostly = { @@ -103,19 +102,20 @@ static void do_setup(struct net_device *netdev) netdev->priv_flags &= ~IFF_TX_SKB_SHARING; netdev->priv_flags |= IFF_LIVE_ADDR_CHANGE | IFF_OPENVSWITCH | IFF_NO_QUEUE; + netdev->lltx = true; netdev->needs_free_netdev = true; netdev->priv_destructor = NULL; netdev->ethtool_ops = &internal_dev_ethtool_ops; netdev->rtnl_link_ops = &internal_dev_link_ops; - netdev->features = NETIF_F_LLTX | NETIF_F_SG | NETIF_F_FRAGLIST | - NETIF_F_HIGHDMA | NETIF_F_HW_CSUM | - NETIF_F_GSO_SOFTWARE | NETIF_F_GSO_ENCAP_ALL; + netdev->features = NETIF_F_SG | NETIF_F_FRAGLIST | NETIF_F_HIGHDMA | + NETIF_F_HW_CSUM | NETIF_F_GSO_SOFTWARE | + NETIF_F_GSO_ENCAP_ALL; netdev->vlan_features = netdev->features; netdev->hw_enc_features = netdev->features; netdev->features |= NETIF_F_HW_VLAN_CTAG_TX | NETIF_F_HW_VLAN_STAG_TX; - netdev->hw_features = netdev->features & ~NETIF_F_LLTX; + netdev->hw_features = netdev->features; eth_hw_addr_random(netdev); } @@ -140,11 +140,7 @@ static struct vport *internal_dev_create(const struct vport_parms *parms) err = -ENOMEM; goto error_free_vport; } - vport->dev->tstats = netdev_alloc_pcpu_stats(struct pcpu_sw_netstats); - if (!vport->dev->tstats) { - err = -ENOMEM; - goto error_free_netdev; - } + dev->pcpu_stat_type = NETDEV_PCPU_STAT_TSTATS; dev_net_set(vport->dev, ovs_dp_get_net(vport->dp)); dev->ifindex = parms->desired_ifindex; @@ -153,7 +149,7 @@ static struct vport *internal_dev_create(const struct vport_parms *parms) /* Restrict bridge port to current netns. */ if (vport->port_no == OVSP_LOCAL) - vport->dev->features |= NETIF_F_NETNS_LOCAL; + vport->dev->netns_local = true; rtnl_lock(); err = register_netdevice(vport->dev); @@ -169,8 +165,6 @@ static struct vport *internal_dev_create(const struct vport_parms *parms) error_unlock: rtnl_unlock(); - free_percpu(dev->tstats); -error_free_netdev: free_netdev(dev); error_free_vport: ovs_vport_free(vport); @@ -186,7 +180,6 @@ static void internal_dev_destroy(struct vport *vport) /* unregister_netdevice() waits for an RCU grace period. */ unregister_netdevice(vport->dev); - free_percpu(vport->dev->tstats); rtnl_unlock(); } diff --git a/net/openvswitch/vport.c b/net/openvswitch/vport.c index 972ae01a70f7..8732f6e51ae5 100644 --- a/net/openvswitch/vport.c +++ b/net/openvswitch/vport.c @@ -500,6 +500,7 @@ int ovs_vport_receive(struct vport *vport, struct sk_buff *skb, OVS_CB(skb)->input_vport = vport; OVS_CB(skb)->mru = 0; OVS_CB(skb)->cutlen = 0; + OVS_CB(skb)->probability = 0; if (unlikely(dev_net(skb->dev) != ovs_dp_get_net(vport->dp))) { u32 mark; diff --git a/net/packet/af_packet.c b/net/packet/af_packet.c index ea3ebc160e25..a705ec214254 100644 --- a/net/packet/af_packet.c +++ b/net/packet/af_packet.c @@ -538,6 +538,61 @@ static void *packet_current_frame(struct packet_sock *po, return packet_lookup_frame(po, rb, rb->head, status); } +static u16 vlan_get_tci(struct sk_buff *skb, struct net_device *dev) +{ + u8 *skb_orig_data = skb->data; + int skb_orig_len = skb->len; + struct vlan_hdr vhdr, *vh; + unsigned int header_len; + + if (!dev) + return 0; + + /* In the SOCK_DGRAM scenario, skb data starts at the network + * protocol, which is after the VLAN headers. The outer VLAN + * header is at the hard_header_len offset in non-variable + * length link layer headers. If it's a VLAN device, the + * min_header_len should be used to exclude the VLAN header + * size. + */ + if (dev->min_header_len == dev->hard_header_len) + header_len = dev->hard_header_len; + else if (is_vlan_dev(dev)) + header_len = dev->min_header_len; + else + return 0; + + skb_push(skb, skb->data - skb_mac_header(skb)); + vh = skb_header_pointer(skb, header_len, sizeof(vhdr), &vhdr); + if (skb_orig_data != skb->data) { + skb->data = skb_orig_data; + skb->len = skb_orig_len; + } + if (unlikely(!vh)) + return 0; + + return ntohs(vh->h_vlan_TCI); +} + +static __be16 vlan_get_protocol_dgram(struct sk_buff *skb) +{ + __be16 proto = skb->protocol; + + if (unlikely(eth_type_vlan(proto))) { + u8 *skb_orig_data = skb->data; + int skb_orig_len = skb->len; + + skb_push(skb, skb->data - skb_mac_header(skb)); + proto = __vlan_get_protocol(skb, proto, NULL); + if (skb_orig_data != skb->data) { + skb->data = skb_orig_data; + skb->len = skb_orig_len; + } + } + + return proto; +} + static void prb_del_retire_blk_timer(struct tpacket_kbdq_core *pkc) { del_timer_sync(&pkc->retire_blk_timer); @@ -1007,10 +1062,16 @@ static void prb_clear_rxhash(struct tpacket_kbdq_core *pkc, static void prb_fill_vlan_info(struct tpacket_kbdq_core *pkc, struct tpacket3_hdr *ppd) { + struct packet_sock *po = container_of(pkc, struct packet_sock, rx_ring.prb_bdqc); + if (skb_vlan_tag_present(pkc->skb)) { ppd->hv1.tp_vlan_tci = skb_vlan_tag_get(pkc->skb); ppd->hv1.tp_vlan_tpid = ntohs(pkc->skb->vlan_proto); ppd->tp_status = TP_STATUS_VLAN_VALID | TP_STATUS_VLAN_TPID_VALID; + } else if (unlikely(po->sk.sk_type == SOCK_DGRAM && eth_type_vlan(pkc->skb->protocol))) { + ppd->hv1.tp_vlan_tci = vlan_get_tci(pkc->skb, pkc->skb->dev); + ppd->hv1.tp_vlan_tpid = ntohs(pkc->skb->protocol); + ppd->tp_status = TP_STATUS_VLAN_VALID | TP_STATUS_VLAN_TPID_VALID; } else { ppd->hv1.tp_vlan_tci = 0; ppd->hv1.tp_vlan_tpid = 0; @@ -2056,8 +2117,7 @@ retry: skb->dev = dev; skb->priority = READ_ONCE(sk->sk_priority); skb->mark = READ_ONCE(sk->sk_mark); - skb->tstamp = sockc.transmit_time; - + skb_set_delivery_type_by_clockid(skb, sockc.transmit_time, sk->sk_clockid); skb_setup_tx_timestamp(skb, sockc.tsflags); if (unlikely(extra_len == 4)) @@ -2122,7 +2182,7 @@ static int packet_rcv(struct sk_buff *skb, struct net_device *dev, struct packet_type *pt, struct net_device *orig_dev) { enum skb_drop_reason drop_reason = SKB_CONSUMED; - struct sock *sk; + struct sock *sk = NULL; struct sockaddr_ll *sll; struct packet_sock *po; u8 *skb_head = skb->data; @@ -2156,7 +2216,7 @@ static int packet_rcv(struct sk_buff *skb, struct net_device *dev, } } - snaplen = skb->len; + snaplen = skb_frags_readable(skb) ? skb->len : skb_headlen(skb); res = run_filter(skb, sk, snaplen); if (!res) @@ -2227,7 +2287,7 @@ drop_n_restore: skb->len = skb_len; } drop: - kfree_skb_reason(skb, drop_reason); + sk_skb_reason_drop(sk, skb, drop_reason); return 0; } @@ -2235,7 +2295,7 @@ static int tpacket_rcv(struct sk_buff *skb, struct net_device *dev, struct packet_type *pt, struct net_device *orig_dev) { enum skb_drop_reason drop_reason = SKB_CONSUMED; - struct sock *sk; + struct sock *sk = NULL; struct packet_sock *po; struct sockaddr_ll *sll; union tpacket_uhdr h; @@ -2276,7 +2336,7 @@ static int tpacket_rcv(struct sk_buff *skb, struct net_device *dev, } } - snaplen = skb->len; + snaplen = skb_frags_readable(skb) ? skb->len : skb_headlen(skb); res = run_filter(skb, sk, snaplen); if (!res) @@ -2428,6 +2488,10 @@ static int tpacket_rcv(struct sk_buff *skb, struct net_device *dev, h.h2->tp_vlan_tci = skb_vlan_tag_get(skb); h.h2->tp_vlan_tpid = ntohs(skb->vlan_proto); status |= TP_STATUS_VLAN_VALID | TP_STATUS_VLAN_TPID_VALID; + } else if (unlikely(sk->sk_type == SOCK_DGRAM && eth_type_vlan(skb->protocol))) { + h.h2->tp_vlan_tci = vlan_get_tci(skb, skb->dev); + h.h2->tp_vlan_tpid = ntohs(skb->protocol); + status |= TP_STATUS_VLAN_VALID | TP_STATUS_VLAN_TPID_VALID; } else { h.h2->tp_vlan_tci = 0; h.h2->tp_vlan_tpid = 0; @@ -2457,7 +2521,8 @@ static int tpacket_rcv(struct sk_buff *skb, struct net_device *dev, sll->sll_halen = dev_parse_header(skb, sll->sll_addr); sll->sll_family = AF_PACKET; sll->sll_hatype = dev->type; - sll->sll_protocol = skb->protocol; + sll->sll_protocol = (sk->sk_type == SOCK_DGRAM) ? + vlan_get_protocol_dgram(skb) : skb->protocol; sll->sll_pkttype = skb->pkt_type; if (unlikely(packet_sock_flag(po, PACKET_SOCK_ORIGDEV))) sll->sll_ifindex = orig_dev->ifindex; @@ -2495,7 +2560,7 @@ drop_n_restore: skb->len = skb_len; } drop: - kfree_skb_reason(skb, drop_reason); + sk_skb_reason_drop(sk, skb, drop_reason); return 0; drop_n_account: @@ -2504,7 +2569,7 @@ drop_n_account: drop_reason = SKB_DROP_REASON_PACKET_SOCK_ERROR; sk->sk_data_ready(sk); - kfree_skb_reason(copy_skb, drop_reason); + sk_skb_reason_drop(sk, copy_skb, drop_reason); goto drop_n_restore; } @@ -2584,7 +2649,7 @@ static int tpacket_fill_skb(struct packet_sock *po, struct sk_buff *skb, skb->dev = dev; skb->priority = READ_ONCE(po->sk.sk_priority); skb->mark = READ_ONCE(po->sk.sk_mark); - skb->tstamp = sockc->transmit_time; + skb_set_delivery_type_by_clockid(skb, sockc->transmit_time, po->sk.sk_clockid); skb_setup_tx_timestamp(skb, sockc->tsflags); skb_zcopy_set_nouarg(skb, ph.raw); @@ -3062,7 +3127,7 @@ static int packet_snd(struct socket *sock, struct msghdr *msg, size_t len) skb->dev = dev; skb->priority = READ_ONCE(sk->sk_priority); skb->mark = sockc.mark; - skb->tstamp = sockc.transmit_time; + skb_set_delivery_type_by_clockid(skb, sockc.transmit_time, sk->sk_clockid); if (unlikely(extra_len == 4)) skb->no_fcs = 1; @@ -3482,7 +3547,8 @@ static int packet_recvmsg(struct socket *sock, struct msghdr *msg, size_t len, /* Original length was stored in sockaddr_ll fields */ origlen = PACKET_SKB_CB(skb)->sa.origlen; sll->sll_family = AF_PACKET; - sll->sll_protocol = skb->protocol; + sll->sll_protocol = (sock->type == SOCK_DGRAM) ? + vlan_get_protocol_dgram(skb) : skb->protocol; } sock_recv_cmsgs(msg, sk, skb); @@ -3539,6 +3605,21 @@ static int packet_recvmsg(struct socket *sock, struct msghdr *msg, size_t len, aux.tp_vlan_tci = skb_vlan_tag_get(skb); aux.tp_vlan_tpid = ntohs(skb->vlan_proto); aux.tp_status |= TP_STATUS_VLAN_VALID | TP_STATUS_VLAN_TPID_VALID; + } else if (unlikely(sock->type == SOCK_DGRAM && eth_type_vlan(skb->protocol))) { + struct sockaddr_ll *sll = &PACKET_SKB_CB(skb)->sa.ll; + struct net_device *dev; + + rcu_read_lock(); + dev = dev_get_by_index_rcu(sock_net(sk), sll->sll_ifindex); + if (dev) { + aux.tp_vlan_tci = vlan_get_tci(skb, dev); + aux.tp_vlan_tpid = ntohs(skb->protocol); + aux.tp_status |= TP_STATUS_VLAN_VALID | TP_STATUS_VLAN_TPID_VALID; + } else { + aux.tp_vlan_tci = 0; + aux.tp_vlan_tpid = 0; + } + rcu_read_unlock(); } else { aux.tp_vlan_tci = 0; aux.tp_vlan_tpid = 0; diff --git a/net/phonet/sysctl.c b/net/phonet/sysctl.c index 82fc22467a09..463a74a27d3e 100644 --- a/net/phonet/sysctl.c +++ b/net/phonet/sysctl.c @@ -48,7 +48,7 @@ void phonet_get_local_port_range(int *min, int *max) } while (read_seqretry(&local_port_range_lock, seq)); } -static int proc_local_port_range(struct ctl_table *table, int write, +static int proc_local_port_range(const struct ctl_table *table, int write, void *buffer, size_t *lenp, loff_t *ppos) { int ret; diff --git a/net/psample/psample.c b/net/psample/psample.c index a5d9b8446f77..a0ddae8a65f9 100644 --- a/net/psample/psample.c +++ b/net/psample/psample.c @@ -360,8 +360,9 @@ static int psample_tunnel_meta_len(struct ip_tunnel_info *tun_info) } #endif -void psample_sample_packet(struct psample_group *group, struct sk_buff *skb, - u32 sample_rate, const struct psample_metadata *md) +void psample_sample_packet(struct psample_group *group, + const struct sk_buff *skb, u32 sample_rate, + const struct psample_metadata *md) { ktime_t tstamp = ktime_get_real(); int out_ifindex = md->out_ifindex; @@ -376,6 +377,10 @@ void psample_sample_packet(struct psample_group *group, struct sk_buff *skb, void *data; int ret; + if (!genl_has_listeners(&psample_nl_family, group->net, + PSAMPLE_NL_MCGRP_SAMPLE)) + return; + meta_len = (in_ifindex ? nla_total_size(sizeof(u16)) : 0) + (out_ifindex ? nla_total_size(sizeof(u16)) : 0) + (md->out_tc_valid ? nla_total_size(sizeof(u16)) : 0) + @@ -386,7 +391,9 @@ void psample_sample_packet(struct psample_group *group, struct sk_buff *skb, nla_total_size(sizeof(u32)) + /* group_num */ nla_total_size(sizeof(u32)) + /* seq */ nla_total_size_64bit(sizeof(u64)) + /* timestamp */ - nla_total_size(sizeof(u16)); /* protocol */ + nla_total_size(sizeof(u16)) + /* protocol */ + (md->user_cookie_len ? + nla_total_size(md->user_cookie_len) : 0); /* user cookie */ #ifdef CONFIG_INET tun_info = skb_tunnel_info(skb); @@ -486,6 +493,14 @@ void psample_sample_packet(struct psample_group *group, struct sk_buff *skb, } #endif + if (md->user_cookie && md->user_cookie_len && + nla_put(nl_skb, PSAMPLE_ATTR_USER_COOKIE, md->user_cookie_len, + md->user_cookie)) + goto error; + + if (md->rate_as_probability) + nla_put_flag(nl_skb, PSAMPLE_ATTR_SAMPLE_PROBABILITY); + genlmsg_end(nl_skb, data); genlmsg_multicast_netns(&psample_nl_family, group->net, nl_skb, 0, PSAMPLE_NL_MCGRP_SAMPLE, GFP_ATOMIC); diff --git a/net/qrtr/af_qrtr.c b/net/qrtr/af_qrtr.c index 41ece61eb57a..00c51cf693f3 100644 --- a/net/qrtr/af_qrtr.c +++ b/net/qrtr/af_qrtr.c @@ -884,7 +884,7 @@ static int qrtr_bcast_enqueue(struct qrtr_node *node, struct sk_buff *skb, mutex_lock(&qrtr_node_lock); list_for_each_entry(node, &qrtr_all_nodes, item) { - skbn = skb_clone(skb, GFP_KERNEL); + skbn = pskb_copy(skb, GFP_KERNEL); if (!skbn) break; skb_set_owner_w(skbn, skb->sk); diff --git a/net/qrtr/ns.c b/net/qrtr/ns.c index 654a3cc0d347..3de9350cbf30 100644 --- a/net/qrtr/ns.c +++ b/net/qrtr/ns.c @@ -132,8 +132,8 @@ static int service_announce_new(struct sockaddr_qrtr *dest, return kernel_sendmsg(qrtr_ns.sock, &msg, &iv, 1, sizeof(pkt)); } -static int service_announce_del(struct sockaddr_qrtr *dest, - struct qrtr_server *srv) +static void service_announce_del(struct sockaddr_qrtr *dest, + struct qrtr_server *srv) { struct qrtr_ctrl_pkt pkt; struct msghdr msg = { }; @@ -157,10 +157,10 @@ static int service_announce_del(struct sockaddr_qrtr *dest, msg.msg_namelen = sizeof(*dest); ret = kernel_sendmsg(qrtr_ns.sock, &msg, &iv, 1, sizeof(pkt)); - if (ret < 0) + if (ret < 0 && ret != -ENODEV) pr_err("failed to announce del service\n"); - return ret; + return; } static void lookup_notify(struct sockaddr_qrtr *to, struct qrtr_server *srv, @@ -188,7 +188,7 @@ static void lookup_notify(struct sockaddr_qrtr *to, struct qrtr_server *srv, msg.msg_namelen = sizeof(*to); ret = kernel_sendmsg(qrtr_ns.sock, &msg, &iv, 1, sizeof(pkt)); - if (ret < 0) + if (ret < 0 && ret != -ENODEV) pr_err("failed to send lookup notification\n"); } @@ -207,6 +207,9 @@ static int announce_servers(struct sockaddr_qrtr *sq) xa_for_each(&node->servers, index, srv) { ret = service_announce_new(sq, srv); if (ret < 0) { + if (ret == -ENODEV) + continue; + pr_err("failed to announce new service\n"); return ret; } @@ -369,7 +372,7 @@ static int ctrl_cmd_bye(struct sockaddr_qrtr *from) msg.msg_namelen = sizeof(sq); ret = kernel_sendmsg(qrtr_ns.sock, &msg, &iv, 1, sizeof(pkt)); - if (ret < 0) { + if (ret < 0 && ret != -ENODEV) { pr_err("failed to send bye cmd\n"); return ret; } @@ -443,7 +446,7 @@ static int ctrl_cmd_del_client(struct sockaddr_qrtr *from, msg.msg_namelen = sizeof(sq); ret = kernel_sendmsg(qrtr_ns.sock, &msg, &iv, 1, sizeof(pkt)); - if (ret < 0) { + if (ret < 0 && ret != -ENODEV) { pr_err("failed to send del client cmd\n"); return ret; } diff --git a/net/rds/Kconfig b/net/rds/Kconfig index 75cd696963b2..f007730aa2bb 100644 --- a/net/rds/Kconfig +++ b/net/rds/Kconfig @@ -26,3 +26,12 @@ config RDS_DEBUG bool "RDS debugging messages" depends on RDS default n + +config GCOV_PROFILE_RDS + bool "Enable GCOV profiling on RDS" + depends on GCOV_KERNEL + help + Enable GCOV profiling on RDS for checking which functions/lines + are executed. + + If unsure, say N. diff --git a/net/rds/Makefile b/net/rds/Makefile index 8fdc118e2927..3af1ca1d965c 100644 --- a/net/rds/Makefile +++ b/net/rds/Makefile @@ -15,3 +15,8 @@ rds_tcp-y := tcp.o tcp_connect.o tcp_listen.o tcp_recv.o \ tcp_send.o tcp_stats.o ccflags-$(CONFIG_RDS_DEBUG) := -DRDS_DEBUG + +# for GCOV coverage profiling +ifdef CONFIG_GCOV_PROFILE_RDS +GCOV_PROFILE := y +endif diff --git a/net/rds/ib.h b/net/rds/ib.h index 2ba71102b1f1..8ef3178ed4d6 100644 --- a/net/rds/ib.h +++ b/net/rds/ib.h @@ -369,9 +369,6 @@ int rds_ib_conn_alloc(struct rds_connection *conn, gfp_t gfp); void rds_ib_conn_free(void *arg); int rds_ib_conn_path_connect(struct rds_conn_path *cp); void rds_ib_conn_path_shutdown(struct rds_conn_path *cp); -void rds_ib_state_change(struct sock *sk); -int rds_ib_listen_init(void); -void rds_ib_listen_stop(void); __printf(2, 3) void __rds_ib_conn_error(struct rds_connection *conn, const char *, ...); int rds_ib_cm_handle_connect(struct rdma_cm_id *cm_id, @@ -402,7 +399,6 @@ void rds_ib_inc_free(struct rds_incoming *inc); int rds_ib_inc_copy_to_user(struct rds_incoming *inc, struct iov_iter *to); void rds_ib_recv_cqe_handler(struct rds_ib_connection *ic, struct ib_wc *wc, struct rds_ib_ack_state *state); -void rds_ib_recv_tasklet_fn(unsigned long data); void rds_ib_recv_init_ring(struct rds_ib_connection *ic); void rds_ib_recv_clear_ring(struct rds_ib_connection *ic); void rds_ib_recv_init_ack(struct rds_ib_connection *ic); diff --git a/net/rds/tcp.c b/net/rds/tcp.c index d8111ac83bb6..351ac1747224 100644 --- a/net/rds/tcp.c +++ b/net/rds/tcp.c @@ -61,7 +61,7 @@ static atomic_t rds_tcp_unloading = ATOMIC_INIT(0); static struct kmem_cache *rds_tcp_conn_slab; -static int rds_tcp_skbuf_handler(struct ctl_table *ctl, int write, +static int rds_tcp_skbuf_handler(const struct ctl_table *ctl, int write, void *buffer, size_t *lenp, loff_t *fpos); static int rds_tcp_min_sndbuf = SOCK_MIN_SNDBUF; @@ -682,7 +682,7 @@ static void rds_tcp_sysctl_reset(struct net *net) spin_unlock_irq(&rds_tcp_conn_lock); } -static int rds_tcp_skbuf_handler(struct ctl_table *ctl, int write, +static int rds_tcp_skbuf_handler(const struct ctl_table *ctl, int write, void *buffer, size_t *lenp, loff_t *fpos) { struct net *net = current->nsproxy->net_ns; @@ -719,9 +719,7 @@ static int __init rds_tcp_init(void) { int ret; - rds_tcp_conn_slab = kmem_cache_create("rds_tcp_connection", - sizeof(struct rds_tcp_connection), - 0, 0, NULL); + rds_tcp_conn_slab = KMEM_CACHE(rds_tcp_connection, 0); if (!rds_tcp_conn_slab) { ret = -ENOMEM; goto out; diff --git a/net/rds/tcp_recv.c b/net/rds/tcp_recv.c index c00f04a1a534..7997a19d1da3 100644 --- a/net/rds/tcp_recv.c +++ b/net/rds/tcp_recv.c @@ -337,9 +337,7 @@ out: int rds_tcp_recv_init(void) { - rds_tcp_incoming_slab = kmem_cache_create("rds_tcp_incoming", - sizeof(struct rds_tcp_incoming), - 0, 0, NULL); + rds_tcp_incoming_slab = KMEM_CACHE(rds_tcp_incoming, 0); if (!rds_tcp_incoming_slab) return -ENOMEM; return 0; diff --git a/net/rfkill/core.c b/net/rfkill/core.c index c3feb4f49d09..7d3e82e4c2fc 100644 --- a/net/rfkill/core.c +++ b/net/rfkill/core.c @@ -539,18 +539,14 @@ bool rfkill_get_global_sw_state(const enum rfkill_type type) #endif bool rfkill_set_hw_state_reason(struct rfkill *rfkill, - bool blocked, unsigned long reason) + bool blocked, + enum rfkill_hard_block_reasons reason) { unsigned long flags; bool ret, prev; BUG_ON(!rfkill); - if (WARN(reason & - ~(RFKILL_HARD_BLOCK_SIGNAL | RFKILL_HARD_BLOCK_NOT_OWNER), - "hw_state reason not supported: 0x%lx", reason)) - return blocked; - spin_lock_irqsave(&rfkill->lock, flags); prev = !!(rfkill->hard_block_reasons & reason); if (blocked) { @@ -1398,7 +1394,6 @@ static const struct file_operations rfkill_fops = { .release = rfkill_fop_release, .unlocked_ioctl = rfkill_fop_ioctl, .compat_ioctl = compat_ptr_ioctl, - .llseek = no_llseek, }; #define RFKILL_NAME "rfkill" diff --git a/net/rfkill/rfkill-gpio.c b/net/rfkill/rfkill-gpio.c index 84529886c2e6..c268c2b011f4 100644 --- a/net/rfkill/rfkill-gpio.c +++ b/net/rfkill/rfkill-gpio.c @@ -3,6 +3,7 @@ * Copyright (c) 2011, NVIDIA Corporation. */ +#include <linux/dmi.h> #include <linux/init.h> #include <linux/kernel.h> #include <linux/module.h> @@ -72,6 +73,20 @@ static int rfkill_gpio_acpi_probe(struct device *dev, return devm_acpi_dev_add_driver_gpios(dev, acpi_rfkill_default_gpios); } +/* List of DMI matches for devices on which rfkill-gpio should not load, + * to avoid firmware bugs. + */ +static const struct dmi_system_id rfkill_gpio_deny_table[] = { + { + /* Lenovo Yoga Tab 3 Pro YT3-X90, bogus "BCM4752" device in DSDT */ + .matches = { + DMI_MATCH(DMI_SYS_VENDOR, "Intel Corporation"), + DMI_MATCH(DMI_PRODUCT_VERSION, "Blade3-10A-001"), + }, + }, + { } +}; + static int rfkill_gpio_probe(struct platform_device *pdev) { struct rfkill_gpio_data *rfkill; @@ -81,6 +96,9 @@ static int rfkill_gpio_probe(struct platform_device *pdev) const char *type_name; int ret; + if (dmi_check_system(rfkill_gpio_deny_table)) + return -ENODEV; + rfkill = devm_kzalloc(&pdev->dev, sizeof(*rfkill), GFP_KERNEL); if (!rfkill) return -ENOMEM; diff --git a/net/rxrpc/ar-internal.h b/net/rxrpc/ar-internal.h index 08de24658f4f..80d682f89b23 100644 --- a/net/rxrpc/ar-internal.h +++ b/net/rxrpc/ar-internal.h @@ -856,7 +856,6 @@ bool rxrpc_new_incoming_call(struct rxrpc_local *local, struct rxrpc_connection *conn, struct sockaddr_rxrpc *peer_srx, struct sk_buff *skb); -void rxrpc_accept_incoming_calls(struct rxrpc_local *); int rxrpc_user_charge_accept(struct rxrpc_sock *, unsigned long); /* @@ -969,7 +968,6 @@ void rxrpc_connect_client_calls(struct rxrpc_local *local); void rxrpc_expose_client_call(struct rxrpc_call *); void rxrpc_disconnect_client_call(struct rxrpc_bundle *, struct rxrpc_call *); void rxrpc_deactivate_bundle(struct rxrpc_bundle *bundle); -void rxrpc_put_client_conn(struct rxrpc_connection *, enum rxrpc_conn_trace); void rxrpc_discard_expired_client_conns(struct rxrpc_local *local); void rxrpc_clean_up_local_conns(struct rxrpc_local *); diff --git a/net/sched/act_api.c b/net/sched/act_api.c index 2520708b06a1..2714c4ed928e 100644 --- a/net/sched/act_api.c +++ b/net/sched/act_api.c @@ -62,7 +62,7 @@ static void tcf_set_action_cookie(struct tc_cookie __rcu **old_cookie, { struct tc_cookie *old; - old = xchg((__force struct tc_cookie **)old_cookie, new_cookie); + old = unrcu_pointer(xchg(old_cookie, RCU_INITIALIZER(new_cookie))); if (old) call_rcu(&old->rcu, tcf_free_cookie_rcu); } diff --git a/net/sched/act_bpf.c b/net/sched/act_bpf.c index 0e3cf11ae5fc..396b576390d0 100644 --- a/net/sched/act_bpf.c +++ b/net/sched/act_bpf.c @@ -54,8 +54,8 @@ TC_INDIRECT_SCOPE int tcf_bpf_act(struct sk_buff *skb, bpf_compute_data_pointers(skb); filter_res = bpf_prog_run(filter, skb); } - if (unlikely(!skb->tstamp && skb->mono_delivery_time)) - skb->mono_delivery_time = 0; + if (unlikely(!skb->tstamp && skb->tstamp_type)) + skb->tstamp_type = SKB_CLOCK_REALTIME; if (skb_sk_is_prefetched(skb) && filter_res != TC_ACT_OK) skb_orphan(skb); diff --git a/net/sched/act_ct.c b/net/sched/act_ct.c index 2a96d9c1db65..2197eb625658 100644 --- a/net/sched/act_ct.c +++ b/net/sched/act_ct.c @@ -60,7 +60,7 @@ struct tcf_ct_flow_table { static const struct rhashtable_params zones_params = { .head_offset = offsetof(struct tcf_ct_flow_table, node), .key_offset = offsetof(struct tcf_ct_flow_table, key), - .key_len = sizeof_field(struct tcf_ct_flow_table, key), + .key_len = offsetofend(struct zones_ht_key, zone), .automatic_shrinking = true, }; @@ -944,6 +944,8 @@ static int tcf_ct_act_nat(struct sk_buff *skb, action |= BIT(NF_NAT_MANIP_DST); err = nf_ct_nat(skb, ct, ctinfo, &action, range, commit); + if (err != NF_ACCEPT) + return err & NF_VERDICT_MASK; if (action & BIT(NF_NAT_MANIP_SRC)) tc_skb_cb(skb)->post_ct_snat = 1; @@ -1035,7 +1037,7 @@ TC_INDIRECT_SCOPE int tcf_ct_act(struct sk_buff *skb, const struct tc_action *a, state.pf = family; err = nf_conntrack_in(skb, &state); if (err != NF_ACCEPT) - goto out_push; + goto nf_error; } do_nat: @@ -1047,7 +1049,7 @@ do_nat: err = tcf_ct_act_nat(skb, ct, ctinfo, p->ct_action, &p->range, commit); if (err != NF_ACCEPT) - goto drop; + goto nf_error; if (!nf_ct_is_confirmed(ct) && commit && p->helper && !nfct_help(ct)) { err = __nf_ct_try_assign_helper(ct, p->tmpl, GFP_ATOMIC); @@ -1061,8 +1063,9 @@ do_nat: } if (nf_ct_is_confirmed(ct) ? ((!cached && !skip_add) || add_helper) : commit) { - if (nf_ct_helper(skb, ct, ctinfo, family) != NF_ACCEPT) - goto drop; + err = nf_ct_helper(skb, ct, ctinfo, family); + if (err != NF_ACCEPT) + goto nf_error; } if (commit) { @@ -1075,8 +1078,17 @@ do_nat: /* This will take care of sending queued events * even if the connection is already confirmed. */ - if (nf_conntrack_confirm(skb) != NF_ACCEPT) - goto drop; + err = nf_conntrack_confirm(skb); + if (err != NF_ACCEPT) + goto nf_error; + + /* The ct may be dropped if a clash has been resolved, + * so it's necessary to retrieve it from skb again to + * prevent UAF. + */ + ct = nf_ct_get(skb, &ctinfo); + if (!ct) + skip_add = true; } if (!skip_add) @@ -1100,6 +1112,21 @@ out_frag: drop: tcf_action_inc_drop_qstats(&c->common); return TC_ACT_SHOT; + +nf_error: + /* some verdicts store extra data in upper bits, such + * as errno or queue number. + */ + switch (err & NF_VERDICT_MASK) { + case NF_DROP: + goto drop; + case NF_STOLEN: + tcf_action_inc_drop_qstats(&c->common); + return TC_ACT_CONSUMED; + default: + DEBUG_NET_WARN_ON_ONCE(1); + goto drop; + } } static const struct nla_policy ct_policy[TCA_CT_MAX + 1] = { diff --git a/net/sched/act_sample.c b/net/sched/act_sample.c index a69b53d54039..2ceb4d141b71 100644 --- a/net/sched/act_sample.c +++ b/net/sched/act_sample.c @@ -167,7 +167,9 @@ TC_INDIRECT_SCOPE int tcf_sample_act(struct sk_buff *skb, { struct tcf_sample *s = to_sample(a); struct psample_group *psample_group; + u8 cookie_data[TC_COOKIE_MAX_SIZE]; struct psample_metadata md = {}; + struct tc_cookie *user_cookie; int retval; tcf_lastuse_update(&s->tcf_tm); @@ -189,6 +191,16 @@ TC_INDIRECT_SCOPE int tcf_sample_act(struct sk_buff *skb, if (skb_at_tc_ingress(skb) && tcf_sample_dev_ok_push(skb->dev)) skb_push(skb, skb->mac_len); + rcu_read_lock(); + user_cookie = rcu_dereference(a->user_cookie); + if (user_cookie) { + memcpy(cookie_data, user_cookie->data, + user_cookie->len); + md.user_cookie = cookie_data; + md.user_cookie_len = user_cookie->len; + } + rcu_read_unlock(); + md.trunc_size = s->truncate ? s->trunc_size : skb->len; psample_sample_packet(psample_group, skb, s->rate, &md); diff --git a/net/sched/act_skbmod.c b/net/sched/act_skbmod.c index cd0accaf844a..dc0229693461 100644 --- a/net/sched/act_skbmod.c +++ b/net/sched/act_skbmod.c @@ -246,7 +246,7 @@ static int tcf_skbmod_dump(struct sk_buff *skb, struct tc_action *a, memset(&opt, 0, sizeof(opt)); opt.index = d->tcf_index; - opt.refcnt = refcount_read(&d->tcf_refcnt) - ref, + opt.refcnt = refcount_read(&d->tcf_refcnt) - ref; opt.bindcnt = atomic_read(&d->tcf_bindcnt) - bind; spin_lock_bh(&d->tcf_lock); opt.action = d->tcf_action; diff --git a/net/sched/act_vlan.c b/net/sched/act_vlan.c index 22f4b1e8ade9..383bf18b6862 100644 --- a/net/sched/act_vlan.c +++ b/net/sched/act_vlan.c @@ -96,6 +96,7 @@ out: if (skb_at_tc_ingress(skb)) skb_pull_rcsum(skb, skb->mac_len); + skb_reset_mac_len(skb); return action; drop: diff --git a/net/sched/cls_bpf.c b/net/sched/cls_bpf.c index 5e83e890f6a4..1941ebec23ff 100644 --- a/net/sched/cls_bpf.c +++ b/net/sched/cls_bpf.c @@ -104,8 +104,8 @@ TC_INDIRECT_SCOPE int cls_bpf_classify(struct sk_buff *skb, bpf_compute_data_pointers(skb); filter_res = bpf_prog_run(prog->filter, skb); } - if (unlikely(!skb->tstamp && skb->mono_delivery_time)) - skb->mono_delivery_time = 0; + if (unlikely(!skb->tstamp && skb->tstamp_type)) + skb->tstamp_type = SKB_CLOCK_REALTIME; if (prog->exts_integrated) { res->class = 0; diff --git a/net/sched/cls_flower.c b/net/sched/cls_flower.c index fd9a6f20b60b..e280c27cb9f9 100644 --- a/net/sched/cls_flower.c +++ b/net/sched/cls_flower.c @@ -41,6 +41,16 @@ #define TCA_FLOWER_KEY_CT_FLAGS_MASK \ (TCA_FLOWER_KEY_CT_FLAGS_MAX - 1) +#define TCA_FLOWER_KEY_FLAGS_POLICY_MASK \ + (TCA_FLOWER_KEY_FLAGS_IS_FRAGMENT | \ + TCA_FLOWER_KEY_FLAGS_FRAG_IS_FIRST) + +#define TCA_FLOWER_KEY_ENC_FLAGS_POLICY_MASK \ + (TCA_FLOWER_KEY_FLAGS_TUNNEL_CSUM | \ + TCA_FLOWER_KEY_FLAGS_TUNNEL_DONT_FRAGMENT | \ + TCA_FLOWER_KEY_FLAGS_TUNNEL_OAM | \ + TCA_FLOWER_KEY_FLAGS_TUNNEL_CRIT_OPT) + struct fl_flow_key { struct flow_dissector_key_meta meta; struct flow_dissector_key_control control; @@ -669,8 +679,10 @@ static const struct nla_policy fl_policy[TCA_FLOWER_MAX + 1] = { [TCA_FLOWER_KEY_ENC_UDP_SRC_PORT_MASK] = { .type = NLA_U16 }, [TCA_FLOWER_KEY_ENC_UDP_DST_PORT] = { .type = NLA_U16 }, [TCA_FLOWER_KEY_ENC_UDP_DST_PORT_MASK] = { .type = NLA_U16 }, - [TCA_FLOWER_KEY_FLAGS] = { .type = NLA_U32 }, - [TCA_FLOWER_KEY_FLAGS_MASK] = { .type = NLA_U32 }, + [TCA_FLOWER_KEY_FLAGS] = NLA_POLICY_MASK(NLA_BE32, + TCA_FLOWER_KEY_FLAGS_POLICY_MASK), + [TCA_FLOWER_KEY_FLAGS_MASK] = NLA_POLICY_MASK(NLA_BE32, + TCA_FLOWER_KEY_FLAGS_POLICY_MASK), [TCA_FLOWER_KEY_ICMPV4_TYPE] = { .type = NLA_U8 }, [TCA_FLOWER_KEY_ICMPV4_TYPE_MASK] = { .type = NLA_U8 }, [TCA_FLOWER_KEY_ICMPV4_CODE] = { .type = NLA_U8 }, @@ -732,6 +744,10 @@ static const struct nla_policy fl_policy[TCA_FLOWER_MAX + 1] = { [TCA_FLOWER_KEY_SPI_MASK] = { .type = NLA_U32 }, [TCA_FLOWER_L2_MISS] = NLA_POLICY_MAX(NLA_U8, 1), [TCA_FLOWER_KEY_CFM] = { .type = NLA_NESTED }, + [TCA_FLOWER_KEY_ENC_FLAGS] = NLA_POLICY_MASK(NLA_BE32, + TCA_FLOWER_KEY_ENC_FLAGS_POLICY_MASK), + [TCA_FLOWER_KEY_ENC_FLAGS_MASK] = NLA_POLICY_MASK(NLA_BE32, + TCA_FLOWER_KEY_ENC_FLAGS_POLICY_MASK), }; static const struct nla_policy @@ -1155,19 +1171,29 @@ static void fl_set_key_flag(u32 flower_key, u32 flower_mask, } } -static int fl_set_key_flags(struct nlattr **tb, u32 *flags_key, - u32 *flags_mask, struct netlink_ext_ack *extack) +static int fl_set_key_flags(struct nlattr *tca_opts, struct nlattr **tb, + bool encap, u32 *flags_key, u32 *flags_mask, + struct netlink_ext_ack *extack) { + int fl_key, fl_mask; u32 key, mask; + if (encap) { + fl_key = TCA_FLOWER_KEY_ENC_FLAGS; + fl_mask = TCA_FLOWER_KEY_ENC_FLAGS_MASK; + } else { + fl_key = TCA_FLOWER_KEY_FLAGS; + fl_mask = TCA_FLOWER_KEY_FLAGS_MASK; + } + /* mask is mandatory for flags */ - if (!tb[TCA_FLOWER_KEY_FLAGS_MASK]) { + if (NL_REQ_ATTR_CHECK(extack, tca_opts, tb, fl_mask)) { NL_SET_ERR_MSG(extack, "Missing flags mask"); return -EINVAL; } - key = be32_to_cpu(nla_get_be32(tb[TCA_FLOWER_KEY_FLAGS])); - mask = be32_to_cpu(nla_get_be32(tb[TCA_FLOWER_KEY_FLAGS_MASK])); + key = be32_to_cpu(nla_get_be32(tb[fl_key])); + mask = be32_to_cpu(nla_get_be32(tb[fl_mask])); *flags_key = 0; *flags_mask = 0; @@ -1178,6 +1204,21 @@ static int fl_set_key_flags(struct nlattr **tb, u32 *flags_key, TCA_FLOWER_KEY_FLAGS_FRAG_IS_FIRST, FLOW_DIS_FIRST_FRAG); + fl_set_key_flag(key, mask, flags_key, flags_mask, + TCA_FLOWER_KEY_FLAGS_TUNNEL_CSUM, + FLOW_DIS_F_TUNNEL_CSUM); + + fl_set_key_flag(key, mask, flags_key, flags_mask, + TCA_FLOWER_KEY_FLAGS_TUNNEL_DONT_FRAGMENT, + FLOW_DIS_F_TUNNEL_DONT_FRAGMENT); + + fl_set_key_flag(key, mask, flags_key, flags_mask, + TCA_FLOWER_KEY_FLAGS_TUNNEL_OAM, FLOW_DIS_F_TUNNEL_OAM); + + fl_set_key_flag(key, mask, flags_key, flags_mask, + TCA_FLOWER_KEY_FLAGS_TUNNEL_CRIT_OPT, + FLOW_DIS_F_TUNNEL_CRIT_OPT); + return 0; } @@ -1825,9 +1866,9 @@ static int fl_set_key_cfm(struct nlattr **tb, return 0; } -static int fl_set_key(struct net *net, struct nlattr **tb, - struct fl_flow_key *key, struct fl_flow_key *mask, - struct netlink_ext_ack *extack) +static int fl_set_key(struct net *net, struct nlattr *tca_opts, + struct nlattr **tb, struct fl_flow_key *key, + struct fl_flow_key *mask, struct netlink_ext_ack *extack) { __be16 ethertype; int ret = 0; @@ -2059,9 +2100,18 @@ static int fl_set_key(struct net *net, struct nlattr **tb, if (ret) return ret; - if (tb[TCA_FLOWER_KEY_FLAGS]) - ret = fl_set_key_flags(tb, &key->control.flags, + if (tb[TCA_FLOWER_KEY_FLAGS]) { + ret = fl_set_key_flags(tca_opts, tb, false, + &key->control.flags, &mask->control.flags, extack); + if (ret) + return ret; + } + + if (tb[TCA_FLOWER_KEY_ENC_FLAGS]) + ret = fl_set_key_flags(tca_opts, tb, true, + &key->enc_control.flags, + &mask->enc_control.flags, extack); return ret; } @@ -2152,7 +2202,8 @@ static void fl_init_dissector(struct flow_dissector *dissector, FL_KEY_SET_IF_MASKED(mask, keys, cnt, FLOW_DISSECTOR_KEY_ENC_IPV6_ADDRS, enc_ipv6); if (FL_KEY_IS_MASKED(mask, enc_ipv4) || - FL_KEY_IS_MASKED(mask, enc_ipv6)) + FL_KEY_IS_MASKED(mask, enc_ipv6) || + FL_KEY_IS_MASKED(mask, enc_control)) FL_KEY_SET(keys, cnt, FLOW_DISSECTOR_KEY_ENC_CONTROL, enc_control); FL_KEY_SET_IF_MASKED(mask, keys, cnt, @@ -2310,6 +2361,7 @@ static int fl_change(struct net *net, struct sk_buff *in_skb, { struct cls_fl_head *head = fl_head_dereference(tp); bool rtnl_held = !(flags & TCA_ACT_FLAGS_NO_RTNL); + struct nlattr *tca_opts = tca[TCA_OPTIONS]; struct cls_fl_filter *fold = *arg; bool bound_to_filter = false; struct cls_fl_filter *fnew; @@ -2318,7 +2370,7 @@ static int fl_change(struct net *net, struct sk_buff *in_skb, bool in_ht; int err; - if (!tca[TCA_OPTIONS]) { + if (!tca_opts) { err = -EINVAL; goto errout_fold; } @@ -2336,7 +2388,7 @@ static int fl_change(struct net *net, struct sk_buff *in_skb, } err = nla_parse_nested_deprecated(tb, TCA_FLOWER_MAX, - tca[TCA_OPTIONS], fl_policy, NULL); + tca_opts, fl_policy, NULL); if (err < 0) goto errout_tb; @@ -2412,7 +2464,7 @@ static int fl_change(struct net *net, struct sk_buff *in_skb, bound_to_filter = true; } - err = fl_set_key(net, tb, &fnew->key, &mask->key, extack); + err = fl_set_key(net, tca_opts, tb, &fnew->key, &mask->key, extack); if (err) goto unbind_filter; @@ -2752,18 +2804,19 @@ static void *fl_tmplt_create(struct net *net, struct tcf_chain *chain, struct nlattr **tca, struct netlink_ext_ack *extack) { + struct nlattr *tca_opts = tca[TCA_OPTIONS]; struct fl_flow_tmplt *tmplt; struct nlattr **tb; int err; - if (!tca[TCA_OPTIONS]) + if (!tca_opts) return ERR_PTR(-EINVAL); tb = kcalloc(TCA_FLOWER_MAX + 1, sizeof(struct nlattr *), GFP_KERNEL); if (!tb) return ERR_PTR(-ENOBUFS); err = nla_parse_nested_deprecated(tb, TCA_FLOWER_MAX, - tca[TCA_OPTIONS], fl_policy, NULL); + tca_opts, fl_policy, NULL); if (err) goto errout_tb; @@ -2773,7 +2826,8 @@ static void *fl_tmplt_create(struct net *net, struct tcf_chain *chain, goto errout_tb; } tmplt->chain = chain; - err = fl_set_key(net, tb, &tmplt->dummy_key, &tmplt->mask, extack); + err = fl_set_key(net, tca_opts, tb, &tmplt->dummy_key, + &tmplt->mask, extack); if (err) goto errout_tmplt; @@ -3049,12 +3103,22 @@ static void fl_get_key_flag(u32 dissector_key, u32 dissector_mask, } } -static int fl_dump_key_flags(struct sk_buff *skb, u32 flags_key, u32 flags_mask) +static int fl_dump_key_flags(struct sk_buff *skb, bool encap, + u32 flags_key, u32 flags_mask) { - u32 key, mask; + int fl_key, fl_mask; __be32 _key, _mask; + u32 key, mask; int err; + if (encap) { + fl_key = TCA_FLOWER_KEY_ENC_FLAGS; + fl_mask = TCA_FLOWER_KEY_ENC_FLAGS_MASK; + } else { + fl_key = TCA_FLOWER_KEY_FLAGS; + fl_mask = TCA_FLOWER_KEY_FLAGS_MASK; + } + if (!memchr_inv(&flags_mask, 0, sizeof(flags_mask))) return 0; @@ -3067,14 +3131,29 @@ static int fl_dump_key_flags(struct sk_buff *skb, u32 flags_key, u32 flags_mask) TCA_FLOWER_KEY_FLAGS_FRAG_IS_FIRST, FLOW_DIS_FIRST_FRAG); + fl_get_key_flag(flags_key, flags_mask, &key, &mask, + TCA_FLOWER_KEY_FLAGS_TUNNEL_CSUM, + FLOW_DIS_F_TUNNEL_CSUM); + + fl_get_key_flag(flags_key, flags_mask, &key, &mask, + TCA_FLOWER_KEY_FLAGS_TUNNEL_DONT_FRAGMENT, + FLOW_DIS_F_TUNNEL_DONT_FRAGMENT); + + fl_get_key_flag(flags_key, flags_mask, &key, &mask, + TCA_FLOWER_KEY_FLAGS_TUNNEL_OAM, FLOW_DIS_F_TUNNEL_OAM); + + fl_get_key_flag(flags_key, flags_mask, &key, &mask, + TCA_FLOWER_KEY_FLAGS_TUNNEL_CRIT_OPT, + FLOW_DIS_F_TUNNEL_CRIT_OPT); + _key = cpu_to_be32(key); _mask = cpu_to_be32(mask); - err = nla_put(skb, TCA_FLOWER_KEY_FLAGS, 4, &_key); + err = nla_put(skb, fl_key, 4, &_key); if (err) return err; - return nla_put(skb, TCA_FLOWER_KEY_FLAGS_MASK, 4, &_mask); + return nla_put(skb, fl_mask, 4, &_mask); } static int fl_dump_key_geneve_opt(struct sk_buff *skb, @@ -3581,7 +3660,8 @@ static int fl_dump_key(struct sk_buff *skb, struct net *net, if (fl_dump_key_ct(skb, &key->ct, &mask->ct)) goto nla_put_failure; - if (fl_dump_key_flags(skb, key->control.flags, mask->control.flags)) + if (fl_dump_key_flags(skb, false, key->control.flags, + mask->control.flags)) goto nla_put_failure; if (fl_dump_key_val(skb, &key->hash.hash, TCA_FLOWER_KEY_HASH, @@ -3592,6 +3672,10 @@ static int fl_dump_key(struct sk_buff *skb, struct net *net, if (fl_dump_key_cfm(skb, &key->cfm, &mask->cfm)) goto nla_put_failure; + if (fl_dump_key_flags(skb, true, key->enc_control.flags, + mask->enc_control.flags)) + goto nla_put_failure; + return 0; nla_put_failure: diff --git a/net/sched/sch_cake.c b/net/sched/sch_cake.c index 9602dafe32e6..f2f9b75008bb 100644 --- a/net/sched/sch_cake.c +++ b/net/sched/sch_cake.c @@ -361,8 +361,24 @@ static const u8 besteffort[] = { static const u8 normal_order[] = {0, 1, 2, 3, 4, 5, 6, 7}; static const u8 bulk_order[] = {1, 0, 2, 3}; +/* There is a big difference in timing between the accurate values placed in the + * cache and the approximations given by a single Newton step for small count + * values, particularly when stepping from count 1 to 2 or vice versa. Hence, + * these values are calculated using eight Newton steps, using the + * implementation below. Above 16, a single Newton step gives sufficient + * accuracy in either direction, given the precision stored. + * + * The magnitude of the error when stepping up to count 2 is such as to give the + * value that *should* have been produced at count 4. + */ + #define REC_INV_SQRT_CACHE (16) -static u32 cobalt_rec_inv_sqrt_cache[REC_INV_SQRT_CACHE] = {0}; +static const u32 inv_sqrt_cache[REC_INV_SQRT_CACHE] = { + ~0, ~0, 3037000500, 2479700525, + 2147483647, 1920767767, 1753413056, 1623345051, + 1518500250, 1431655765, 1358187914, 1294981364, + 1239850263, 1191209601, 1147878294, 1108955788 +}; /* http://en.wikipedia.org/wiki/Methods_of_computing_square_roots * new_invsqrt = (invsqrt / 2) * (3 - count * invsqrt^2) @@ -388,47 +404,14 @@ static void cobalt_newton_step(struct cobalt_vars *vars) static void cobalt_invsqrt(struct cobalt_vars *vars) { if (vars->count < REC_INV_SQRT_CACHE) - vars->rec_inv_sqrt = cobalt_rec_inv_sqrt_cache[vars->count]; + vars->rec_inv_sqrt = inv_sqrt_cache[vars->count]; else cobalt_newton_step(vars); } -/* There is a big difference in timing between the accurate values placed in - * the cache and the approximations given by a single Newton step for small - * count values, particularly when stepping from count 1 to 2 or vice versa. - * Above 16, a single Newton step gives sufficient accuracy in either - * direction, given the precision stored. - * - * The magnitude of the error when stepping up to count 2 is such as to give - * the value that *should* have been produced at count 4. - */ - -static void cobalt_cache_init(void) -{ - struct cobalt_vars v; - - memset(&v, 0, sizeof(v)); - v.rec_inv_sqrt = ~0U; - cobalt_rec_inv_sqrt_cache[0] = v.rec_inv_sqrt; - - for (v.count = 1; v.count < REC_INV_SQRT_CACHE; v.count++) { - cobalt_newton_step(&v); - cobalt_newton_step(&v); - cobalt_newton_step(&v); - cobalt_newton_step(&v); - - cobalt_rec_inv_sqrt_cache[v.count] = v.rec_inv_sqrt; - } -} - static void cobalt_vars_init(struct cobalt_vars *vars) { memset(vars, 0, sizeof(*vars)); - - if (!cobalt_rec_inv_sqrt_cache[0]) { - cobalt_cache_init(); - cobalt_rec_inv_sqrt_cache[0] = ~0; - } } /* CoDel control_law is t + interval/sqrt(count) @@ -786,12 +769,15 @@ skip_hash: * queue, accept the collision, update the host tags. */ q->way_collisions++; - if (q->flows[outer_hash + k].set == CAKE_SET_BULK) { - q->hosts[q->flows[reduced_hash].srchost].srchost_bulk_flow_count--; - q->hosts[q->flows[reduced_hash].dsthost].dsthost_bulk_flow_count--; - } allocate_src = cake_dsrc(flow_mode); allocate_dst = cake_ddst(flow_mode); + + if (q->flows[outer_hash + k].set == CAKE_SET_BULK) { + if (allocate_src) + q->hosts[q->flows[reduced_hash].srchost].srchost_bulk_flow_count--; + if (allocate_dst) + q->hosts[q->flows[reduced_hash].dsthost].dsthost_bulk_flow_count--; + } found: /* reserve queue for future packets in same flow */ reduced_hash = outer_hash + k; diff --git a/net/sched/sch_fq.c b/net/sched/sch_fq.c index 238974725679..19a49af5a9e5 100644 --- a/net/sched/sch_fq.c +++ b/net/sched/sch_fq.c @@ -663,7 +663,9 @@ begin: pband = &q->band_flows[q->band_nr]; pband->credit = min(pband->credit + pband->quantum, pband->quantum); - goto begin; + if (pband->credit > 0) + goto begin; + retry = 0; } if (q->time_next_delayed_flow != ~0ULL) qdisc_watchdog_schedule_range_ns(&q->watchdog, diff --git a/net/sched/sch_generic.c b/net/sched/sch_generic.c index e22ff003d52e..2af24547a82c 100644 --- a/net/sched/sch_generic.c +++ b/net/sched/sch_generic.c @@ -633,6 +633,7 @@ EXPORT_SYMBOL_GPL(netif_carrier_event); static int noop_enqueue(struct sk_buff *skb, struct Qdisc *qdisc, struct sk_buff **to_free) { + dev_core_stats_tx_dropped_inc(skb->dev); __qdisc_drop(skb, to_free); return NET_XMIT_CN; } diff --git a/net/sched/sch_ingress.c b/net/sched/sch_ingress.c index c2ef9dcf91d2..cc6051d4f2ef 100644 --- a/net/sched/sch_ingress.c +++ b/net/sched/sch_ingress.c @@ -91,7 +91,7 @@ static int ingress_init(struct Qdisc *sch, struct nlattr *opt, entry = tcx_entry_fetch_or_create(dev, true, &created); if (!entry) return -ENOMEM; - tcx_miniq_set_active(entry, true); + tcx_miniq_inc(entry); mini_qdisc_pair_init(&q->miniqp, sch, &tcx_entry(entry)->miniq); if (created) tcx_entry_update(dev, entry, true); @@ -121,7 +121,7 @@ static void ingress_destroy(struct Qdisc *sch) tcf_block_put_ext(q->block, sch, &q->block_info); if (entry) { - tcx_miniq_set_active(entry, false); + tcx_miniq_dec(entry); if (!tcx_entry_is_active(entry)) { tcx_entry_update(dev, NULL, true); tcx_entry_free(entry); @@ -257,7 +257,7 @@ static int clsact_init(struct Qdisc *sch, struct nlattr *opt, entry = tcx_entry_fetch_or_create(dev, true, &created); if (!entry) return -ENOMEM; - tcx_miniq_set_active(entry, true); + tcx_miniq_inc(entry); mini_qdisc_pair_init(&q->miniqp_ingress, sch, &tcx_entry(entry)->miniq); if (created) tcx_entry_update(dev, entry, true); @@ -276,7 +276,7 @@ static int clsact_init(struct Qdisc *sch, struct nlattr *opt, entry = tcx_entry_fetch_or_create(dev, false, &created); if (!entry) return -ENOMEM; - tcx_miniq_set_active(entry, true); + tcx_miniq_inc(entry); mini_qdisc_pair_init(&q->miniqp_egress, sch, &tcx_entry(entry)->miniq); if (created) tcx_entry_update(dev, entry, false); @@ -302,7 +302,7 @@ static void clsact_destroy(struct Qdisc *sch) tcf_block_put_ext(q->egress_block, sch, &q->egress_block_info); if (ingress_entry) { - tcx_miniq_set_active(ingress_entry, false); + tcx_miniq_dec(ingress_entry); if (!tcx_entry_is_active(ingress_entry)) { tcx_entry_update(dev, NULL, true); tcx_entry_free(ingress_entry); @@ -310,7 +310,7 @@ static void clsact_destroy(struct Qdisc *sch) } if (egress_entry) { - tcx_miniq_set_active(egress_entry, false); + tcx_miniq_dec(egress_entry); if (!tcx_entry_is_active(egress_entry)) { tcx_entry_update(dev, NULL, false); tcx_entry_free(egress_entry); diff --git a/net/sched/sch_netem.c b/net/sched/sch_netem.c index edc72962ae63..39382ee1e331 100644 --- a/net/sched/sch_netem.c +++ b/net/sched/sch_netem.c @@ -446,12 +446,10 @@ static int netem_enqueue(struct sk_buff *skb, struct Qdisc *sch, struct netem_sched_data *q = qdisc_priv(sch); /* We don't fill cb now as skb_unshare() may invalidate it */ struct netem_skb_cb *cb; - struct sk_buff *skb2; + struct sk_buff *skb2 = NULL; struct sk_buff *segs = NULL; unsigned int prev_len = qdisc_pkt_len(skb); int count = 1; - int rc = NET_XMIT_SUCCESS; - int rc_drop = NET_XMIT_DROP; /* Do not fool qdisc_drop_all() */ skb->prev = NULL; @@ -480,19 +478,11 @@ static int netem_enqueue(struct sk_buff *skb, struct Qdisc *sch, skb_orphan_partial(skb); /* - * If we need to duplicate packet, then re-insert at top of the - * qdisc tree, since parent queuer expects that only one - * skb will be queued. + * If we need to duplicate packet, then clone it before + * original is modified. */ - if (count > 1 && (skb2 = skb_clone(skb, GFP_ATOMIC)) != NULL) { - struct Qdisc *rootq = qdisc_root_bh(sch); - u32 dupsave = q->duplicate; /* prevent duplicating a dup... */ - - q->duplicate = 0; - rootq->enqueue(skb2, rootq, to_free); - q->duplicate = dupsave; - rc_drop = NET_XMIT_SUCCESS; - } + if (count > 1) + skb2 = skb_clone(skb, GFP_ATOMIC); /* * Randomized packet corruption. @@ -504,7 +494,8 @@ static int netem_enqueue(struct sk_buff *skb, struct Qdisc *sch, if (skb_is_gso(skb)) { skb = netem_segment(skb, sch, to_free); if (!skb) - return rc_drop; + goto finish_segs; + segs = skb->next; skb_mark_not_on_list(skb); qdisc_skb_cb(skb)->pkt_len = skb->len; @@ -530,7 +521,24 @@ static int netem_enqueue(struct sk_buff *skb, struct Qdisc *sch, /* re-link segs, so that qdisc_drop_all() frees them all */ skb->next = segs; qdisc_drop_all(skb, sch, to_free); - return rc_drop; + if (skb2) + __qdisc_drop(skb2, to_free); + return NET_XMIT_DROP; + } + + /* + * If doing duplication then re-insert at top of the + * qdisc tree, since parent queuer expects that only one + * skb will be queued. + */ + if (skb2) { + struct Qdisc *rootq = qdisc_root_bh(sch); + u32 dupsave = q->duplicate; /* prevent duplicating a dup... */ + + q->duplicate = 0; + rootq->enqueue(skb2, rootq, to_free); + q->duplicate = dupsave; + skb2 = NULL; } qdisc_qstats_backlog_inc(sch, skb); @@ -601,9 +609,12 @@ static int netem_enqueue(struct sk_buff *skb, struct Qdisc *sch, } finish_segs: + if (skb2) + __qdisc_drop(skb2, to_free); + if (segs) { unsigned int len, last_len; - int nb; + int rc, nb; len = skb ? skb->len : 0; nb = skb ? 1 : 0; @@ -731,11 +742,10 @@ deliver: err = qdisc_enqueue(skb, q->qdisc, &to_free); kfree_skb_list(to_free); - if (err != NET_XMIT_SUCCESS && - net_xmit_drop_count(err)) { - qdisc_qstats_drop(sch); - qdisc_tree_reduce_backlog(sch, 1, - pkt_len); + if (err != NET_XMIT_SUCCESS) { + if (net_xmit_drop_count(err)) + qdisc_qstats_drop(sch); + qdisc_tree_reduce_backlog(sch, 1, pkt_len); } goto tfifo_dequeue; } diff --git a/net/sched/sch_taprio.c b/net/sched/sch_taprio.c index b284a06b5a75..8498d0606b24 100644 --- a/net/sched/sch_taprio.c +++ b/net/sched/sch_taprio.c @@ -1610,7 +1610,7 @@ static int taprio_parse_clockid(struct Qdisc *sch, struct nlattr **tb, if (FULL_OFFLOAD_IS_ENABLED(q->flags)) { const struct ethtool_ops *ops = dev->ethtool_ops; - struct ethtool_ts_info info = { + struct kernel_ethtool_ts_info info = { .cmd = ETHTOOL_GET_TS_INFO, .phc_index = -1, }; @@ -1952,7 +1952,9 @@ static int taprio_change(struct Qdisc *sch, struct nlattr *opt, goto unlock; } - rcu_assign_pointer(q->admin_sched, new_admin); + /* Not going to race against advance_sched(), but still */ + admin = rcu_replace_pointer(q->admin_sched, new_admin, + lockdep_rtnl_is_held()); if (admin) call_rcu(&admin->rcu, taprio_free_sched_cb); } else { diff --git a/net/sctp/input.c b/net/sctp/input.c index 17fcaa9b0df9..a8a254a5008e 100644 --- a/net/sctp/input.c +++ b/net/sctp/input.c @@ -735,15 +735,19 @@ static int __sctp_hash_endpoint(struct sctp_endpoint *ep) struct sock *sk = ep->base.sk; struct net *net = sock_net(sk); struct sctp_hashbucket *head; + int err = 0; ep->hashent = sctp_ep_hashfn(net, ep->base.bind_addr.port); head = &sctp_ep_hashtable[ep->hashent]; + write_lock(&head->lock); if (sk->sk_reuseport) { bool any = sctp_is_ep_boundall(sk); struct sctp_endpoint *ep2; struct list_head *list; - int cnt = 0, err = 1; + int cnt = 0; + + err = 1; list_for_each(list, &ep->base.bind_addr.address_list) cnt++; @@ -761,24 +765,24 @@ static int __sctp_hash_endpoint(struct sctp_endpoint *ep) if (!err) { err = reuseport_add_sock(sk, sk2, any); if (err) - return err; + goto out; break; } else if (err < 0) { - return err; + goto out; } } if (err) { err = reuseport_alloc(sk, any); if (err) - return err; + goto out; } } - write_lock(&head->lock); hlist_add_head(&ep->node, &head->chain); +out: write_unlock(&head->lock); - return 0; + return err; } /* Add an endpoint to the hash. Local BH-safe. */ @@ -803,10 +807,9 @@ static void __sctp_unhash_endpoint(struct sctp_endpoint *ep) head = &sctp_ep_hashtable[ep->hashent]; + write_lock(&head->lock); if (rcu_access_pointer(sk->sk_reuseport_cb)) reuseport_detach_sock(sk); - - write_lock(&head->lock); hlist_del_init(&ep->node); write_unlock(&head->lock); } diff --git a/net/sctp/protocol.c b/net/sctp/protocol.c index 5a7436a13b74..39ca5403d4d7 100644 --- a/net/sctp/protocol.c +++ b/net/sctp/protocol.c @@ -44,6 +44,7 @@ #include <net/inet_common.h> #include <net/inet_ecn.h> #include <net/udp_tunnel.h> +#include <net/inet_dscp.h> #define MAX_SCTP_PORT_HASH_ENTRIES (64 * 1024) @@ -435,7 +436,7 @@ static void sctp_v4_get_dst(struct sctp_transport *t, union sctp_addr *saddr, fl4->fl4_dport = daddr->v4.sin_port; fl4->flowi4_proto = IPPROTO_SCTP; if (asoc) { - fl4->flowi4_tos = RT_TOS(tos); + fl4->flowi4_tos = tos & INET_DSCP_MASK; fl4->flowi4_scope = ip_sock_rt_scope(asoc->base.sk); fl4->flowi4_oif = asoc->base.sk->sk_bound_dev_if; fl4->fl4_sport = htons(asoc->base.bind_addr.port); diff --git a/net/sctp/sm_statefuns.c b/net/sctp/sm_statefuns.c index 5adf0c0a6c1a..7d315a18612b 100644 --- a/net/sctp/sm_statefuns.c +++ b/net/sctp/sm_statefuns.c @@ -2260,12 +2260,6 @@ enum sctp_disposition sctp_sf_do_5_2_4_dupcook( } } - /* Update socket peer label if first association. */ - if (security_sctp_assoc_request(new_asoc, chunk->head_skb ?: chunk->skb)) { - sctp_association_free(new_asoc); - return sctp_sf_pdiscard(net, ep, asoc, type, arg, commands); - } - /* Set temp so that it won't be added into hashtable */ new_asoc->temp = 1; @@ -2274,6 +2268,22 @@ enum sctp_disposition sctp_sf_do_5_2_4_dupcook( */ action = sctp_tietags_compare(new_asoc, asoc); + /* In cases C and E the association doesn't enter the ESTABLISHED + * state, so there is no need to call security_sctp_assoc_request(). + */ + switch (action) { + case 'A': /* Association restart. */ + case 'B': /* Collision case B. */ + case 'D': /* Collision case D. */ + /* Update socket peer label if first association. */ + if (security_sctp_assoc_request((struct sctp_association *)asoc, + chunk->head_skb ?: chunk->skb)) { + sctp_association_free(new_asoc); + return sctp_sf_pdiscard(net, ep, asoc, type, arg, commands); + } + break; + } + switch (action) { case 'A': /* Association restart. */ retval = sctp_sf_do_dupcook_a(net, ep, asoc, chunk, commands, diff --git a/net/sctp/socket.c b/net/sctp/socket.c index c009383369b2..32f76f1298da 100644 --- a/net/sctp/socket.c +++ b/net/sctp/socket.c @@ -4834,10 +4834,14 @@ int sctp_inet_connect(struct socket *sock, struct sockaddr *uaddr, return sctp_connect(sock->sk, uaddr, addr_len, flags); } -/* FIXME: Write comments. */ +/* Only called when shutdown a listening SCTP socket. */ static int sctp_disconnect(struct sock *sk, int flags) { - return -EOPNOTSUPP; /* STUB */ + if (!sctp_style(sk, TCP)) + return -EOPNOTSUPP; + + sk->sk_shutdown |= RCV_SHUTDOWN; + return 0; } /* 4.1.4 accept() - TCP Style Syntax @@ -4866,7 +4870,8 @@ static struct sock *sctp_accept(struct sock *sk, struct proto_accept_arg *arg) goto out; } - if (!sctp_sstate(sk, LISTENING)) { + if (!sctp_sstate(sk, LISTENING) || + (sk->sk_shutdown & RCV_SHUTDOWN)) { error = -EINVAL; goto out; } @@ -9393,7 +9398,8 @@ static int sctp_wait_for_accept(struct sock *sk, long timeo) } err = -EINVAL; - if (!sctp_sstate(sk, LISTENING)) + if (!sctp_sstate(sk, LISTENING) || + (sk->sk_shutdown & RCV_SHUTDOWN)) break; err = 0; diff --git a/net/sctp/sysctl.c b/net/sctp/sysctl.c index 61c6f3027e7f..e5a5af343c4c 100644 --- a/net/sctp/sysctl.c +++ b/net/sctp/sysctl.c @@ -43,19 +43,19 @@ static unsigned long max_autoclose_max = (MAX_SCHEDULE_TIMEOUT / HZ > UINT_MAX) ? UINT_MAX : MAX_SCHEDULE_TIMEOUT / HZ; -static int proc_sctp_do_hmac_alg(struct ctl_table *ctl, int write, +static int proc_sctp_do_hmac_alg(const struct ctl_table *ctl, int write, void *buffer, size_t *lenp, loff_t *ppos); -static int proc_sctp_do_rto_min(struct ctl_table *ctl, int write, +static int proc_sctp_do_rto_min(const struct ctl_table *ctl, int write, void *buffer, size_t *lenp, loff_t *ppos); -static int proc_sctp_do_rto_max(struct ctl_table *ctl, int write, void *buffer, +static int proc_sctp_do_rto_max(const struct ctl_table *ctl, int write, void *buffer, size_t *lenp, loff_t *ppos); -static int proc_sctp_do_udp_port(struct ctl_table *ctl, int write, void *buffer, +static int proc_sctp_do_udp_port(const struct ctl_table *ctl, int write, void *buffer, size_t *lenp, loff_t *ppos); -static int proc_sctp_do_alpha_beta(struct ctl_table *ctl, int write, +static int proc_sctp_do_alpha_beta(const struct ctl_table *ctl, int write, void *buffer, size_t *lenp, loff_t *ppos); -static int proc_sctp_do_auth(struct ctl_table *ctl, int write, +static int proc_sctp_do_auth(const struct ctl_table *ctl, int write, void *buffer, size_t *lenp, loff_t *ppos); -static int proc_sctp_do_probe_interval(struct ctl_table *ctl, int write, +static int proc_sctp_do_probe_interval(const struct ctl_table *ctl, int write, void *buffer, size_t *lenp, loff_t *ppos); static struct ctl_table sctp_table[] = { @@ -384,7 +384,7 @@ static struct ctl_table sctp_net_table[] = { }, }; -static int proc_sctp_do_hmac_alg(struct ctl_table *ctl, int write, +static int proc_sctp_do_hmac_alg(const struct ctl_table *ctl, int write, void *buffer, size_t *lenp, loff_t *ppos) { struct net *net = current->nsproxy->net_ns; @@ -429,7 +429,7 @@ static int proc_sctp_do_hmac_alg(struct ctl_table *ctl, int write, return ret; } -static int proc_sctp_do_rto_min(struct ctl_table *ctl, int write, +static int proc_sctp_do_rto_min(const struct ctl_table *ctl, int write, void *buffer, size_t *lenp, loff_t *ppos) { struct net *net = current->nsproxy->net_ns; @@ -457,7 +457,7 @@ static int proc_sctp_do_rto_min(struct ctl_table *ctl, int write, return ret; } -static int proc_sctp_do_rto_max(struct ctl_table *ctl, int write, +static int proc_sctp_do_rto_max(const struct ctl_table *ctl, int write, void *buffer, size_t *lenp, loff_t *ppos) { struct net *net = current->nsproxy->net_ns; @@ -485,7 +485,7 @@ static int proc_sctp_do_rto_max(struct ctl_table *ctl, int write, return ret; } -static int proc_sctp_do_alpha_beta(struct ctl_table *ctl, int write, +static int proc_sctp_do_alpha_beta(const struct ctl_table *ctl, int write, void *buffer, size_t *lenp, loff_t *ppos) { if (write) @@ -495,7 +495,7 @@ static int proc_sctp_do_alpha_beta(struct ctl_table *ctl, int write, return proc_dointvec_minmax(ctl, write, buffer, lenp, ppos); } -static int proc_sctp_do_auth(struct ctl_table *ctl, int write, +static int proc_sctp_do_auth(const struct ctl_table *ctl, int write, void *buffer, size_t *lenp, loff_t *ppos) { struct net *net = current->nsproxy->net_ns; @@ -524,7 +524,7 @@ static int proc_sctp_do_auth(struct ctl_table *ctl, int write, return ret; } -static int proc_sctp_do_udp_port(struct ctl_table *ctl, int write, +static int proc_sctp_do_udp_port(const struct ctl_table *ctl, int write, void *buffer, size_t *lenp, loff_t *ppos) { struct net *net = current->nsproxy->net_ns; @@ -565,7 +565,7 @@ static int proc_sctp_do_udp_port(struct ctl_table *ctl, int write, return ret; } -static int proc_sctp_do_probe_interval(struct ctl_table *ctl, int write, +static int proc_sctp_do_probe_interval(const struct ctl_table *ctl, int write, void *buffer, size_t *lenp, loff_t *ppos) { struct net *net = current->nsproxy->net_ns; diff --git a/net/smc/Makefile b/net/smc/Makefile index 2c510d543058..60f1c87d5212 100644 --- a/net/smc/Makefile +++ b/net/smc/Makefile @@ -4,6 +4,6 @@ obj-$(CONFIG_SMC) += smc.o obj-$(CONFIG_SMC_DIAG) += smc_diag.o smc-y := af_smc.o smc_pnet.o smc_ib.o smc_clc.o smc_core.o smc_wr.o smc_llc.o smc-y += smc_cdc.o smc_tx.o smc_rx.o smc_close.o smc_ism.o smc_netlink.o smc_stats.o -smc-y += smc_tracepoint.o +smc-y += smc_tracepoint.o smc_inet.o smc-$(CONFIG_SYSCTL) += smc_sysctl.o smc-$(CONFIG_SMC_LO) += smc_loopback.o diff --git a/net/smc/af_smc.c b/net/smc/af_smc.c index c5f98c6b2561..0316217b7687 100644 --- a/net/smc/af_smc.c +++ b/net/smc/af_smc.c @@ -54,6 +54,7 @@ #include "smc_tracepoint.h" #include "smc_sysctl.h" #include "smc_loopback.h" +#include "smc_inet.h" static DEFINE_MUTEX(smc_server_lgr_pending); /* serialize link group * creation on server @@ -170,15 +171,15 @@ static bool smc_hs_congested(const struct sock *sk) return false; } -static struct smc_hashinfo smc_v4_hashinfo = { +struct smc_hashinfo smc_v4_hashinfo = { .lock = __RW_LOCK_UNLOCKED(smc_v4_hashinfo.lock), }; -static struct smc_hashinfo smc_v6_hashinfo = { +struct smc_hashinfo smc_v6_hashinfo = { .lock = __RW_LOCK_UNLOCKED(smc_v6_hashinfo.lock), }; -static int smc_hash_sk(struct sock *sk) +int smc_hash_sk(struct sock *sk) { struct smc_hashinfo *h = sk->sk_prot->h.smc_hash; struct hlist_head *head; @@ -193,7 +194,7 @@ static int smc_hash_sk(struct sock *sk) return 0; } -static void smc_unhash_sk(struct sock *sk) +void smc_unhash_sk(struct sock *sk) { struct smc_hashinfo *h = sk->sk_prot->h.smc_hash; @@ -207,7 +208,7 @@ static void smc_unhash_sk(struct sock *sk) * work which we didn't do because of user hold the sock_lock in the * BH context */ -static void smc_release_cb(struct sock *sk) +void smc_release_cb(struct sock *sk) { struct smc_sock *smc = smc_sk(sk); @@ -307,7 +308,7 @@ static int __smc_release(struct smc_sock *smc) return rc; } -static int smc_release(struct socket *sock) +int smc_release(struct socket *sock) { struct sock *sk = sock->sk; struct smc_sock *smc; @@ -361,25 +362,15 @@ static void smc_destruct(struct sock *sk) return; } -static struct sock *smc_sock_alloc(struct net *net, struct socket *sock, - int protocol) +void smc_sk_init(struct net *net, struct sock *sk, int protocol) { - struct smc_sock *smc; - struct proto *prot; - struct sock *sk; - - prot = (protocol == SMCPROTO_SMC6) ? &smc_proto6 : &smc_proto; - sk = sk_alloc(net, PF_SMC, GFP_KERNEL, prot, 0); - if (!sk) - return NULL; + struct smc_sock *smc = smc_sk(sk); - sock_init_data(sock, sk); /* sets sk_refcnt to 1 */ sk->sk_state = SMC_INIT; sk->sk_destruct = smc_destruct; sk->sk_protocol = protocol; WRITE_ONCE(sk->sk_sndbuf, 2 * READ_ONCE(net->smc.sysctl_wmem)); WRITE_ONCE(sk->sk_rcvbuf, 2 * READ_ONCE(net->smc.sysctl_rmem)); - smc = smc_sk(sk); INIT_WORK(&smc->tcp_listen_work, smc_tcp_listen_work); INIT_WORK(&smc->connect_work, smc_connect_work); INIT_DELAYED_WORK(&smc->conn.tx_work, smc_tx_work); @@ -389,12 +380,30 @@ static struct sock *smc_sock_alloc(struct net *net, struct socket *sock, sk->sk_prot->hash(sk); mutex_init(&smc->clcsock_release_lock); smc_init_saved_callbacks(smc); + smc->limit_smc_hs = net->smc.limit_smc_hs; + smc->use_fallback = false; /* assume rdma capability first */ + smc->fallback_rsn = 0; +} + +static struct sock *smc_sock_alloc(struct net *net, struct socket *sock, + int protocol) +{ + struct proto *prot; + struct sock *sk; + + prot = (protocol == SMCPROTO_SMC6) ? &smc_proto6 : &smc_proto; + sk = sk_alloc(net, PF_SMC, GFP_KERNEL, prot, 0); + if (!sk) + return NULL; + + sock_init_data(sock, sk); /* sets sk_refcnt to 1 */ + smc_sk_init(net, sk, protocol); return sk; } -static int smc_bind(struct socket *sock, struct sockaddr *uaddr, - int addr_len) +int smc_bind(struct socket *sock, struct sockaddr *uaddr, + int addr_len) { struct sockaddr_in *addr = (struct sockaddr_in *)uaddr; struct sock *sk = sock->sk; @@ -1457,10 +1466,6 @@ connect_abort: static int smc_connect_check_aclc(struct smc_init_info *ini, struct smc_clc_msg_accept_confirm *aclc) { - if (aclc->hdr.typev1 != SMC_TYPE_R && - aclc->hdr.typev1 != SMC_TYPE_D) - return SMC_CLC_DECL_MODEUNSUPP; - if (aclc->hdr.version >= SMC_V2) { if ((aclc->hdr.typev1 == SMC_TYPE_R && !smcr_indicated(ini->smc_type_v2)) || @@ -1514,10 +1519,6 @@ static int __smc_connect(struct smc_sock *smc) ini->smcd_version &= ~SMC_V1; ini->smcr_version = 0; ini->smc_type_v1 = SMC_TYPE_N; - if (!ini->smcd_version) { - rc = SMC_CLC_DECL_GETVLANERR; - goto fallback; - } } rc = smc_find_proposal_devices(smc, ini); @@ -1623,8 +1624,8 @@ out: release_sock(&smc->sk); } -static int smc_connect(struct socket *sock, struct sockaddr *addr, - int alen, int flags) +int smc_connect(struct socket *sock, struct sockaddr *addr, + int alen, int flags) { struct sock *sk = sock->sk; struct smc_sock *smc; @@ -2605,7 +2606,7 @@ out: read_unlock_bh(&listen_clcsock->sk_callback_lock); } -static int smc_listen(struct socket *sock, int backlog) +int smc_listen(struct socket *sock, int backlog) { struct sock *sk = sock->sk; struct smc_sock *smc; @@ -2670,8 +2671,8 @@ out: return rc; } -static int smc_accept(struct socket *sock, struct socket *new_sock, - struct proto_accept_arg *arg) +int smc_accept(struct socket *sock, struct socket *new_sock, + struct proto_accept_arg *arg) { struct sock *sk = sock->sk, *nsk; DECLARE_WAITQUEUE(wait, current); @@ -2740,8 +2741,8 @@ out: return rc; } -static int smc_getname(struct socket *sock, struct sockaddr *addr, - int peer) +int smc_getname(struct socket *sock, struct sockaddr *addr, + int peer) { struct smc_sock *smc; @@ -2754,7 +2755,7 @@ static int smc_getname(struct socket *sock, struct sockaddr *addr, return smc->clcsock->ops->getname(smc->clcsock, addr, peer); } -static int smc_sendmsg(struct socket *sock, struct msghdr *msg, size_t len) +int smc_sendmsg(struct socket *sock, struct msghdr *msg, size_t len) { struct sock *sk = sock->sk; struct smc_sock *smc; @@ -2792,8 +2793,8 @@ out: return rc; } -static int smc_recvmsg(struct socket *sock, struct msghdr *msg, size_t len, - int flags) +int smc_recvmsg(struct socket *sock, struct msghdr *msg, size_t len, + int flags) { struct sock *sk = sock->sk; struct smc_sock *smc; @@ -2842,8 +2843,8 @@ static __poll_t smc_accept_poll(struct sock *parent) return mask; } -static __poll_t smc_poll(struct file *file, struct socket *sock, - poll_table *wait) +__poll_t smc_poll(struct file *file, struct socket *sock, + poll_table *wait) { struct sock *sk = sock->sk; struct smc_sock *smc; @@ -2895,7 +2896,7 @@ static __poll_t smc_poll(struct file *file, struct socket *sock, return mask; } -static int smc_shutdown(struct socket *sock, int how) +int smc_shutdown(struct socket *sock, int how) { struct sock *sk = sock->sk; bool do_shutdown = true; @@ -3035,8 +3036,8 @@ static int __smc_setsockopt(struct socket *sock, int level, int optname, return rc; } -static int smc_setsockopt(struct socket *sock, int level, int optname, - sockptr_t optval, unsigned int optlen) +int smc_setsockopt(struct socket *sock, int level, int optname, + sockptr_t optval, unsigned int optlen) { struct sock *sk = sock->sk; struct smc_sock *smc; @@ -3122,8 +3123,8 @@ out: return rc; } -static int smc_getsockopt(struct socket *sock, int level, int optname, - char __user *optval, int __user *optlen) +int smc_getsockopt(struct socket *sock, int level, int optname, + char __user *optval, int __user *optlen) { struct smc_sock *smc; int rc; @@ -3148,8 +3149,8 @@ static int smc_getsockopt(struct socket *sock, int level, int optname, return rc; } -static int smc_ioctl(struct socket *sock, unsigned int cmd, - unsigned long arg) +int smc_ioctl(struct socket *sock, unsigned int cmd, + unsigned long arg) { union smc_host_cursor cons, urg; struct smc_connection *conn; @@ -3235,9 +3236,9 @@ static int smc_ioctl(struct socket *sock, unsigned int cmd, * Note that subsequent recv() calls have to wait till all splice() processing * completed. */ -static ssize_t smc_splice_read(struct socket *sock, loff_t *ppos, - struct pipe_inode_info *pipe, size_t len, - unsigned int flags) +ssize_t smc_splice_read(struct socket *sock, loff_t *ppos, + struct pipe_inode_info *pipe, size_t len, + unsigned int flags) { struct sock *sk = sock->sk; struct smc_sock *smc; @@ -3303,6 +3304,29 @@ static const struct proto_ops smc_sock_ops = { .splice_read = smc_splice_read, }; +int smc_create_clcsk(struct net *net, struct sock *sk, int family) +{ + struct smc_sock *smc = smc_sk(sk); + int rc; + + rc = sock_create_kern(net, family, SOCK_STREAM, IPPROTO_TCP, + &smc->clcsock); + if (rc) + return rc; + + /* smc_clcsock_release() does not wait smc->clcsock->sk's + * destruction; its sk_state might not be TCP_CLOSE after + * smc->sk is close()d, and TCP timers can be fired later, + * which need net ref. + */ + sk = smc->clcsock->sk; + __netns_tracker_free(net, &sk->ns_tracker, false); + sk->sk_net_refcnt = 1; + get_net_track(net, &sk->ns_tracker, GFP_KERNEL); + sock_inuse_add(net, 1); + return 0; +} + static int __smc_create(struct net *net, struct socket *sock, int protocol, int kern, struct socket *clcsock) { @@ -3328,35 +3352,15 @@ static int __smc_create(struct net *net, struct socket *sock, int protocol, /* create internal TCP socket for CLC handshake and fallback */ smc = smc_sk(sk); - smc->use_fallback = false; /* assume rdma capability first */ - smc->fallback_rsn = 0; - - /* default behavior from limit_smc_hs in every net namespace */ - smc->limit_smc_hs = net->smc.limit_smc_hs; rc = 0; - if (!clcsock) { - rc = sock_create_kern(net, family, SOCK_STREAM, IPPROTO_TCP, - &smc->clcsock); - if (rc) { - sk_common_release(sk); - goto out; - } - - /* smc_clcsock_release() does not wait smc->clcsock->sk's - * destruction; its sk_state might not be TCP_CLOSE after - * smc->sk is close()d, and TCP timers can be fired later, - * which need net ref. - */ - sk = smc->clcsock->sk; - __netns_tracker_free(net, &sk->ns_tracker, false); - sk->sk_net_refcnt = 1; - get_net_track(net, &sk->ns_tracker, GFP_KERNEL); - sock_inuse_add(net, 1); - } else { + if (clcsock) smc->clcsock = clcsock; - } + else + rc = smc_create_clcsk(net, sk, family); + if (rc) + sk_common_release(sk); out: return rc; } @@ -3565,10 +3569,15 @@ static int __init smc_init(void) pr_err("%s: tcp_ulp_register fails with %d\n", __func__, rc); goto out_lo; } - + rc = smc_inet_init(); + if (rc) { + pr_err("%s: smc_inet_init fails with %d\n", __func__, rc); + goto out_ulp; + } static_branch_enable(&tcp_have_smc); return 0; - +out_ulp: + tcp_unregister_ulp(&smc_ulp_ops); out_lo: smc_loopback_exit(); out_ib: @@ -3605,6 +3614,7 @@ out_pernet_subsys: static void __exit smc_exit(void) { static_branch_disable(&tcp_have_smc); + smc_inet_exit(); tcp_unregister_ulp(&smc_ulp_ops); sock_unregister(PF_SMC); smc_core_exit(); @@ -3632,4 +3642,9 @@ MODULE_DESCRIPTION("smc socket address family"); MODULE_LICENSE("GPL"); MODULE_ALIAS_NETPROTO(PF_SMC); MODULE_ALIAS_TCP_ULP("smc"); +/* 256 for IPPROTO_SMC and 1 for SOCK_STREAM */ +MODULE_ALIAS_NET_PF_PROTO_TYPE(PF_INET, 256, 1); +#if IS_ENABLED(CONFIG_IPV6) +MODULE_ALIAS_NET_PF_PROTO_TYPE(PF_INET6, 256, 1); +#endif /* CONFIG_IPV6 */ MODULE_ALIAS_GENL_FAMILY(SMC_GENL_FAMILY_NAME); diff --git a/net/smc/smc.h b/net/smc/smc.h index 18c8b7870198..ad77d6b6b8d3 100644 --- a/net/smc/smc.h +++ b/net/smc/smc.h @@ -34,6 +34,44 @@ extern struct proto smc_proto; extern struct proto smc_proto6; +extern struct smc_hashinfo smc_v4_hashinfo; +extern struct smc_hashinfo smc_v6_hashinfo; + +int smc_hash_sk(struct sock *sk); +void smc_unhash_sk(struct sock *sk); +void smc_release_cb(struct sock *sk); + +int smc_release(struct socket *sock); +int smc_bind(struct socket *sock, struct sockaddr *uaddr, + int addr_len); +int smc_connect(struct socket *sock, struct sockaddr *addr, + int alen, int flags); +int smc_accept(struct socket *sock, struct socket *new_sock, + struct proto_accept_arg *arg); +int smc_getname(struct socket *sock, struct sockaddr *addr, + int peer); +__poll_t smc_poll(struct file *file, struct socket *sock, + poll_table *wait); +int smc_ioctl(struct socket *sock, unsigned int cmd, + unsigned long arg); +int smc_listen(struct socket *sock, int backlog); +int smc_shutdown(struct socket *sock, int how); +int smc_setsockopt(struct socket *sock, int level, int optname, + sockptr_t optval, unsigned int optlen); +int smc_getsockopt(struct socket *sock, int level, int optname, + char __user *optval, int __user *optlen); +int smc_sendmsg(struct socket *sock, struct msghdr *msg, size_t len); +int smc_recvmsg(struct socket *sock, struct msghdr *msg, size_t len, + int flags); +ssize_t smc_splice_read(struct socket *sock, loff_t *ppos, + struct pipe_inode_info *pipe, size_t len, + unsigned int flags); + +/* smc sock initialization */ +void smc_sk_init(struct net *net, struct sock *sk, int protocol); +/* clcsock initialization */ +int smc_create_clcsk(struct net *net, struct sock *sk, int family); + #ifdef ATOMIC64_INIT #define KERNEL_HAS_ATOMIC64 #endif @@ -246,6 +284,9 @@ struct smc_connection { struct smc_sock { /* smc sock container */ struct sock sk; +#if IS_ENABLED(CONFIG_IPV6) + struct ipv6_pinfo *pinet6; +#endif struct socket *clcsock; /* internal tcp socket */ void (*clcsk_state_change)(struct sock *sk); /* original stat_change fct. */ diff --git a/net/smc/smc_clc.h b/net/smc/smc_clc.h index 467effb50cd6..5625fda2960b 100644 --- a/net/smc/smc_clc.h +++ b/net/smc/smc_clc.h @@ -145,6 +145,8 @@ struct smc_clc_v2_extension { ); u8 user_eids[][SMC_MAX_EID_LEN]; }; +static_assert(offsetof(struct smc_clc_v2_extension, user_eids) == sizeof(struct smc_clc_v2_extension_fixed), + "struct member likely outside of struct_group_tagged()"); struct smc_clc_msg_proposal_prefix { /* prefix part of clc proposal message*/ __be32 outgoing_subnet; /* subnet mask */ @@ -169,6 +171,8 @@ struct smc_clc_smcd_v2_extension { ); struct smc_clc_smcd_gid_chid gidchid[]; }; +static_assert(offsetof(struct smc_clc_smcd_v2_extension, gidchid) == sizeof(struct smc_clc_smcd_v2_extension_fixed), + "struct member likely outside of struct_group_tagged()"); struct smc_clc_msg_proposal { /* clc proposal message sent by Linux */ struct smc_clc_msg_hdr hdr; diff --git a/net/smc/smc_core.c b/net/smc/smc_core.c index fafdb97adfad..4e694860ece4 100644 --- a/net/smc/smc_core.c +++ b/net/smc/smc_core.c @@ -221,6 +221,35 @@ static void smc_lgr_unregister_conn(struct smc_connection *conn) write_unlock_bh(&lgr->conns_lock); } +static void smc_lgr_buf_list_add(struct smc_link_group *lgr, + bool is_rmb, + struct list_head *buf_list, + struct smc_buf_desc *buf_desc) +{ + list_add(&buf_desc->list, buf_list); + if (is_rmb) { + lgr->alloc_rmbs += buf_desc->len; + lgr->alloc_rmbs += + lgr->is_smcd ? sizeof(struct smcd_cdc_msg) : 0; + } else { + lgr->alloc_sndbufs += buf_desc->len; + } +} + +static void smc_lgr_buf_list_del(struct smc_link_group *lgr, + bool is_rmb, + struct smc_buf_desc *buf_desc) +{ + list_del(&buf_desc->list); + if (is_rmb) { + lgr->alloc_rmbs -= buf_desc->len; + lgr->alloc_rmbs -= + lgr->is_smcd ? sizeof(struct smcd_cdc_msg) : 0; + } else { + lgr->alloc_sndbufs -= buf_desc->len; + } +} + int smc_nl_get_sys_info(struct sk_buff *skb, struct netlink_callback *cb) { struct smc_nl_dmp_ctx *cb_ctx = smc_nl_dmp_ctx(cb); @@ -363,6 +392,10 @@ static int smc_nl_fill_lgr(struct smc_link_group *lgr, smc_target[SMC_MAX_PNETID_LEN] = 0; if (nla_put_string(skb, SMC_NLA_LGR_R_PNETID, smc_target)) goto errattr; + if (nla_put_uint(skb, SMC_NLA_LGR_R_SNDBUF_ALLOC, lgr->alloc_sndbufs)) + goto errattr; + if (nla_put_uint(skb, SMC_NLA_LGR_R_RMB_ALLOC, lgr->alloc_rmbs)) + goto errattr; if (lgr->smc_version > SMC_V1) { v2_attrs = nla_nest_start(skb, SMC_NLA_LGR_R_V2_COMMON); if (!v2_attrs) @@ -541,6 +574,10 @@ static int smc_nl_fill_smcd_lgr(struct smc_link_group *lgr, goto errattr; if (nla_put_u32(skb, SMC_NLA_LGR_D_CHID, smc_ism_get_chid(lgr->smcd))) goto errattr; + if (nla_put_uint(skb, SMC_NLA_LGR_D_SNDBUF_ALLOC, lgr->alloc_sndbufs)) + goto errattr; + if (nla_put_uint(skb, SMC_NLA_LGR_D_DMB_ALLOC, lgr->alloc_rmbs)) + goto errattr; memcpy(smc_pnet, lgr->smcd->pnetid, SMC_MAX_PNETID_LEN); smc_pnet[SMC_MAX_PNETID_LEN] = 0; if (nla_put_string(skb, SMC_NLA_LGR_D_PNETID, smc_pnet)) @@ -1138,7 +1175,7 @@ static void smcr_buf_unuse(struct smc_buf_desc *buf_desc, bool is_rmb, lock = is_rmb ? &lgr->rmbs_lock : &lgr->sndbufs_lock; down_write(lock); - list_del(&buf_desc->list); + smc_lgr_buf_list_del(lgr, is_rmb, buf_desc); up_write(lock); smc_buf_free(lgr, is_rmb, buf_desc); @@ -1166,22 +1203,30 @@ static void smcd_buf_detach(struct smc_connection *conn) static void smc_buf_unuse(struct smc_connection *conn, struct smc_link_group *lgr) { + struct smc_sock *smc = container_of(conn, struct smc_sock, conn); + bool is_smcd = lgr->is_smcd; + int bufsize; + if (conn->sndbuf_desc) { - if (!lgr->is_smcd && conn->sndbuf_desc->is_vm) { + bufsize = conn->sndbuf_desc->len; + if (!is_smcd && conn->sndbuf_desc->is_vm) { smcr_buf_unuse(conn->sndbuf_desc, false, lgr); } else { - memzero_explicit(conn->sndbuf_desc->cpu_addr, conn->sndbuf_desc->len); + memzero_explicit(conn->sndbuf_desc->cpu_addr, bufsize); WRITE_ONCE(conn->sndbuf_desc->used, 0); } + SMC_STAT_RMB_SIZE(smc, is_smcd, false, false, bufsize); } if (conn->rmb_desc) { - if (!lgr->is_smcd) { + bufsize = conn->rmb_desc->len; + if (!is_smcd) { smcr_buf_unuse(conn->rmb_desc, true, lgr); } else { - memzero_explicit(conn->rmb_desc->cpu_addr, - conn->rmb_desc->len + sizeof(struct smcd_cdc_msg)); + bufsize += sizeof(struct smcd_cdc_msg); + memzero_explicit(conn->rmb_desc->cpu_addr, bufsize); WRITE_ONCE(conn->rmb_desc->used, 0); } + SMC_STAT_RMB_SIZE(smc, is_smcd, true, false, bufsize); } } @@ -1377,7 +1422,7 @@ static void __smc_lgr_free_bufs(struct smc_link_group *lgr, bool is_rmb) buf_list = &lgr->sndbufs[i]; list_for_each_entry_safe(buf_desc, bf_desc, buf_list, list) { - list_del(&buf_desc->list); + smc_lgr_buf_list_del(lgr, is_rmb, buf_desc); smc_buf_free(lgr, is_rmb, buf_desc); } } @@ -2006,7 +2051,7 @@ out: } #define SMCD_DMBE_SIZES 6 /* 0 -> 16KB, 1 -> 32KB, .. 6 -> 1MB */ -#define SMCR_RMBE_SIZES 5 /* 0 -> 16KB, 1 -> 32KB, .. 5 -> 512KB */ +#define SMCR_RMBE_SIZES 15 /* 0 -> 16KB, 1 -> 32KB, .. 15 -> 512MB */ /* convert the RMB size into the compressed notation (minimum 16K, see * SMCD/R_DMBE_SIZES. @@ -2015,7 +2060,6 @@ out: */ static u8 smc_compress_bufsize(int size, bool is_smcd, bool is_rmb) { - const unsigned int max_scat = SG_MAX_SINGLE_ALLOC * PAGE_SIZE; u8 compressed; if (size <= SMC_BUF_MIN_SIZE) @@ -2025,9 +2069,11 @@ static u8 smc_compress_bufsize(int size, bool is_smcd, bool is_rmb) compressed = min_t(u8, ilog2(size) + 1, is_smcd ? SMCD_DMBE_SIZES : SMCR_RMBE_SIZES); +#ifdef CONFIG_ARCH_NO_SG_CHAIN if (!is_smcd && is_rmb) /* RMBs are backed by & limited to max size of scatterlists */ - compressed = min_t(u8, compressed, ilog2(max_scat >> 14)); + compressed = min_t(u8, compressed, ilog2((SG_MAX_SINGLE_ALLOC * PAGE_SIZE) >> 14)); +#endif return compressed; } @@ -2249,7 +2295,7 @@ int smcr_buf_reg_lgr(struct smc_link *lnk) } static struct smc_buf_desc *smcr_new_buf_create(struct smc_link_group *lgr, - bool is_rmb, int bufsize) + int bufsize) { struct smc_buf_desc *buf_desc; @@ -2389,7 +2435,7 @@ static int __smc_buf_create(struct smc_sock *smc, bool is_smcd, bool is_rmb) buf_desc = smc_buf_get_slot(bufsize_comp, lock, buf_list); if (buf_desc) { buf_desc->is_dma_need_sync = 0; - SMC_STAT_RMB_SIZE(smc, is_smcd, is_rmb, bufsize); + SMC_STAT_RMB_SIZE(smc, is_smcd, is_rmb, true, bufsize); SMC_STAT_BUF_REUSE(smc, is_smcd, is_rmb); break; /* found reusable slot */ } @@ -2397,7 +2443,7 @@ static int __smc_buf_create(struct smc_sock *smc, bool is_smcd, bool is_rmb) if (is_smcd) buf_desc = smcd_new_buf_create(lgr, is_rmb, bufsize); else - buf_desc = smcr_new_buf_create(lgr, is_rmb, bufsize); + buf_desc = smcr_new_buf_create(lgr, bufsize); if (PTR_ERR(buf_desc) == -ENOMEM) break; @@ -2410,10 +2456,10 @@ static int __smc_buf_create(struct smc_sock *smc, bool is_smcd, bool is_rmb) } SMC_STAT_RMB_ALLOC(smc, is_smcd, is_rmb); - SMC_STAT_RMB_SIZE(smc, is_smcd, is_rmb, bufsize); + SMC_STAT_RMB_SIZE(smc, is_smcd, is_rmb, true, bufsize); buf_desc->used = 1; down_write(lock); - list_add(&buf_desc->list, buf_list); + smc_lgr_buf_list_add(lgr, is_rmb, buf_list, buf_desc); up_write(lock); break; /* found */ } @@ -2495,7 +2541,8 @@ create_rmb: rc = __smc_buf_create(smc, is_smcd, true); if (rc && smc->conn.sndbuf_desc) { down_write(&smc->conn.lgr->sndbufs_lock); - list_del(&smc->conn.sndbuf_desc->list); + smc_lgr_buf_list_del(smc->conn.lgr, false, + smc->conn.sndbuf_desc); up_write(&smc->conn.lgr->sndbufs_lock); smc_buf_free(smc->conn.lgr, false, smc->conn.sndbuf_desc); smc->conn.sndbuf_desc = NULL; diff --git a/net/smc/smc_core.h b/net/smc/smc_core.h index d93cf51dbd7c..0db4e5f79ac4 100644 --- a/net/smc/smc_core.h +++ b/net/smc/smc_core.h @@ -281,6 +281,8 @@ struct smc_link_group { struct rw_semaphore sndbufs_lock; /* protects tx buffers */ struct list_head rmbs[SMC_RMBE_SIZES]; /* rx buffers */ struct rw_semaphore rmbs_lock; /* protects rx buffers */ + u64 alloc_sndbufs; /* stats of tx buffers */ + u64 alloc_rmbs; /* stats of rx buffers */ u8 id[SMC_LGR_ID_SIZE]; /* unique lgr id */ struct delayed_work free_work; /* delayed freeing of an lgr */ diff --git a/net/smc/smc_inet.c b/net/smc/smc_inet.c new file mode 100644 index 000000000000..a5b2041600f9 --- /dev/null +++ b/net/smc/smc_inet.c @@ -0,0 +1,165 @@ +// SPDX-License-Identifier: GPL-2.0-only +/* + * Shared Memory Communications over RDMA (SMC-R) and RoCE + * + * Definitions for the IPPROTO_SMC (socket related) + * + * Copyright IBM Corp. 2016, 2018 + * Copyright (c) 2024, Alibaba Inc. + * + * Author: D. Wythe <alibuda@linux.alibaba.com> + */ + +#include <net/protocol.h> +#include <net/sock.h> + +#include "smc_inet.h" +#include "smc.h" + +static int smc_inet_init_sock(struct sock *sk); + +static struct proto smc_inet_prot = { + .name = "INET_SMC", + .owner = THIS_MODULE, + .init = smc_inet_init_sock, + .hash = smc_hash_sk, + .unhash = smc_unhash_sk, + .release_cb = smc_release_cb, + .obj_size = sizeof(struct smc_sock), + .h.smc_hash = &smc_v4_hashinfo, + .slab_flags = SLAB_TYPESAFE_BY_RCU, +}; + +static const struct proto_ops smc_inet_stream_ops = { + .family = PF_INET, + .owner = THIS_MODULE, + .release = smc_release, + .bind = smc_bind, + .connect = smc_connect, + .socketpair = sock_no_socketpair, + .accept = smc_accept, + .getname = smc_getname, + .poll = smc_poll, + .ioctl = smc_ioctl, + .listen = smc_listen, + .shutdown = smc_shutdown, + .setsockopt = smc_setsockopt, + .getsockopt = smc_getsockopt, + .sendmsg = smc_sendmsg, + .recvmsg = smc_recvmsg, + .mmap = sock_no_mmap, + .splice_read = smc_splice_read, +}; + +static struct inet_protosw smc_inet_protosw = { + .type = SOCK_STREAM, + .protocol = IPPROTO_SMC, + .prot = &smc_inet_prot, + .ops = &smc_inet_stream_ops, + .flags = INET_PROTOSW_ICSK, +}; + +#if IS_ENABLED(CONFIG_IPV6) +struct smc6_sock { + struct smc_sock smc; + struct ipv6_pinfo inet6; +}; + +static struct proto smc_inet6_prot = { + .name = "INET6_SMC", + .owner = THIS_MODULE, + .init = smc_inet_init_sock, + .hash = smc_hash_sk, + .unhash = smc_unhash_sk, + .release_cb = smc_release_cb, + .obj_size = sizeof(struct smc6_sock), + .h.smc_hash = &smc_v6_hashinfo, + .slab_flags = SLAB_TYPESAFE_BY_RCU, + .ipv6_pinfo_offset = offsetof(struct smc6_sock, inet6), +}; + +static const struct proto_ops smc_inet6_stream_ops = { + .family = PF_INET6, + .owner = THIS_MODULE, + .release = smc_release, + .bind = smc_bind, + .connect = smc_connect, + .socketpair = sock_no_socketpair, + .accept = smc_accept, + .getname = smc_getname, + .poll = smc_poll, + .ioctl = smc_ioctl, + .listen = smc_listen, + .shutdown = smc_shutdown, + .setsockopt = smc_setsockopt, + .getsockopt = smc_getsockopt, + .sendmsg = smc_sendmsg, + .recvmsg = smc_recvmsg, + .mmap = sock_no_mmap, + .splice_read = smc_splice_read, +}; + +static struct inet_protosw smc_inet6_protosw = { + .type = SOCK_STREAM, + .protocol = IPPROTO_SMC, + .prot = &smc_inet6_prot, + .ops = &smc_inet6_stream_ops, + .flags = INET_PROTOSW_ICSK, +}; +#endif /* CONFIG_IPV6 */ + +static int smc_inet_init_sock(struct sock *sk) +{ + struct net *net = sock_net(sk); + + /* init common smc sock */ + smc_sk_init(net, sk, IPPROTO_SMC); + /* create clcsock */ + return smc_create_clcsk(net, sk, sk->sk_family); +} + +int __init smc_inet_init(void) +{ + int rc; + + rc = proto_register(&smc_inet_prot, 1); + if (rc) { + pr_err("%s: proto_register smc_inet_prot fails with %d\n", + __func__, rc); + return rc; + } + /* no return value */ + inet_register_protosw(&smc_inet_protosw); + +#if IS_ENABLED(CONFIG_IPV6) + rc = proto_register(&smc_inet6_prot, 1); + if (rc) { + pr_err("%s: proto_register smc_inet6_prot fails with %d\n", + __func__, rc); + goto out_inet6_prot; + } + rc = inet6_register_protosw(&smc_inet6_protosw); + if (rc) { + pr_err("%s: inet6_register_protosw smc_inet6_protosw fails with %d\n", + __func__, rc); + goto out_inet6_protosw; + } + return rc; +out_inet6_protosw: + proto_unregister(&smc_inet6_prot); +out_inet6_prot: + inet_unregister_protosw(&smc_inet_protosw); + proto_unregister(&smc_inet_prot); +#endif /* CONFIG_IPV6 */ + return rc; +} + +void smc_inet_exit(void) +{ +#if IS_ENABLED(CONFIG_IPV6) + inet6_unregister_protosw(&smc_inet6_protosw); + proto_unregister(&smc_inet6_prot); +#endif /* CONFIG_IPV6 */ + inet_unregister_protosw(&smc_inet_protosw); + proto_unregister(&smc_inet_prot); +} diff --git a/net/smc/smc_inet.h b/net/smc/smc_inet.h new file mode 100644 index 000000000000..a489c8a2b8ef --- /dev/null +++ b/net/smc/smc_inet.h @@ -0,0 +1,22 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +/* + * Shared Memory Communications over RDMA (SMC-R) and RoCE + * + * Definitions for the IPPROTO_SMC (socket related) + + * Copyright IBM Corp. 2016 + * Copyright (c) 2024, Alibaba Inc. + * + * Author: D. Wythe <alibuda@linux.alibaba.com> + */ +#ifndef __INET_SMC +#define __INET_SMC + +/* Initialize protocol registration on IPPROTO_SMC, + * @return 0 on success + */ +int smc_inet_init(void); + +void smc_inet_exit(void); + +#endif /* __INET_SMC */ diff --git a/net/smc/smc_loopback.h b/net/smc/smc_loopback.h index 6dd4292dae56..04dc6808d2e1 100644 --- a/net/smc/smc_loopback.h +++ b/net/smc/smc_loopback.h @@ -15,7 +15,6 @@ #define _SMC_LOOPBACK_H #include <linux/device.h> -#include <linux/err.h> #include <net/smc.h> #if IS_ENABLED(CONFIG_SMC_LO) diff --git a/net/smc/smc_pnet.c b/net/smc/smc_pnet.c index 2adb92b8c469..1dd362326c0a 100644 --- a/net/smc/smc_pnet.c +++ b/net/smc/smc_pnet.c @@ -887,9 +887,6 @@ int smc_pnet_net_init(struct net *net) smc_pnet_create_pnetids_list(net); - /* disable handshake limitation by default */ - net->smc.limit_smc_hs = 0; - return 0; } diff --git a/net/smc/smc_stats.c b/net/smc/smc_stats.c index ca14c0f3a07d..e71b17d1e21c 100644 --- a/net/smc/smc_stats.c +++ b/net/smc/smc_stats.c @@ -218,6 +218,12 @@ static int smc_nl_fill_stats_tech_data(struct sk_buff *skb, smc_tech->tx_bytes, SMC_NLA_STATS_PAD)) goto errattr; + if (nla_put_uint(skb, SMC_NLA_STATS_T_RX_RMB_USAGE, + smc_tech->rx_rmbuse)) + goto errattr; + if (nla_put_uint(skb, SMC_NLA_STATS_T_TX_RMB_USAGE, + smc_tech->tx_rmbuse)) + goto errattr; if (nla_put_u64_64bit(skb, SMC_NLA_STATS_T_RX_CNT, smc_tech->rx_cnt, SMC_NLA_STATS_PAD)) diff --git a/net/smc/smc_stats.h b/net/smc/smc_stats.h index 9d32058db2b5..571f9d9e7814 100644 --- a/net/smc/smc_stats.h +++ b/net/smc/smc_stats.h @@ -19,7 +19,7 @@ #include "smc_clc.h" -#define SMC_MAX_FBACK_RSN_CNT 30 +#define SMC_MAX_FBACK_RSN_CNT 36 enum { SMC_BUF_8K, @@ -79,6 +79,8 @@ struct smc_stats_tech { u64 tx_bytes; u64 rx_cnt; u64 tx_cnt; + u64 rx_rmbuse; + u64 tx_rmbuse; }; struct smc_stats { @@ -135,38 +137,46 @@ do { \ } \ while (0) -#define SMC_STAT_RMB_SIZE_SUB(_smc_stats, _tech, k, _len) \ +#define SMC_STAT_RMB_SIZE_SUB(_smc_stats, _tech, k, _is_add, _len) \ do { \ + typeof(_smc_stats) stats = (_smc_stats); \ + typeof(_is_add) is_a = (_is_add); \ typeof(_len) _l = (_len); \ typeof(_tech) t = (_tech); \ int _pos; \ int m = SMC_BUF_MAX - 1; \ if (_l <= 0) \ break; \ - _pos = fls((_l - 1) >> 13); \ - _pos = (_pos <= m) ? _pos : m; \ - this_cpu_inc((*(_smc_stats)).smc[t].k ## _rmbsize.buf[_pos]); \ + if (is_a) { \ + _pos = fls((_l - 1) >> 13); \ + _pos = (_pos <= m) ? _pos : m; \ + this_cpu_inc((*stats).smc[t].k ## _rmbsize.buf[_pos]); \ + this_cpu_add((*stats).smc[t].k ## _rmbuse, _l); \ + } else { \ + this_cpu_sub((*stats).smc[t].k ## _rmbuse, _l); \ + } \ } \ while (0) #define SMC_STAT_RMB_SUB(_smc_stats, type, t, key) \ this_cpu_inc((*(_smc_stats)).smc[t].rmb ## _ ## key.type ## _cnt) -#define SMC_STAT_RMB_SIZE(_smc, _is_smcd, _is_rx, _len) \ +#define SMC_STAT_RMB_SIZE(_smc, _is_smcd, _is_rx, _is_add, _len) \ do { \ struct net *_net = sock_net(&(_smc)->sk); \ struct smc_stats __percpu *_smc_stats = _net->smc.smc_stats; \ + typeof(_is_add) is_add = (_is_add); \ typeof(_is_smcd) is_d = (_is_smcd); \ typeof(_is_rx) is_r = (_is_rx); \ typeof(_len) l = (_len); \ if ((is_d) && (is_r)) \ - SMC_STAT_RMB_SIZE_SUB(_smc_stats, SMC_TYPE_D, rx, l); \ + SMC_STAT_RMB_SIZE_SUB(_smc_stats, SMC_TYPE_D, rx, is_add, l); \ if ((is_d) && !(is_r)) \ - SMC_STAT_RMB_SIZE_SUB(_smc_stats, SMC_TYPE_D, tx, l); \ + SMC_STAT_RMB_SIZE_SUB(_smc_stats, SMC_TYPE_D, tx, is_add, l); \ if (!(is_d) && (is_r)) \ - SMC_STAT_RMB_SIZE_SUB(_smc_stats, SMC_TYPE_R, rx, l); \ + SMC_STAT_RMB_SIZE_SUB(_smc_stats, SMC_TYPE_R, rx, is_add, l); \ if (!(is_d) && !(is_r)) \ - SMC_STAT_RMB_SIZE_SUB(_smc_stats, SMC_TYPE_R, tx, l); \ + SMC_STAT_RMB_SIZE_SUB(_smc_stats, SMC_TYPE_R, tx, is_add, l); \ } \ while (0) diff --git a/net/smc/smc_sysctl.c b/net/smc/smc_sysctl.c index 13f2bc092db1..2fab6456f765 100644 --- a/net/smc/smc_sysctl.c +++ b/net/smc/smc_sysctl.c @@ -90,6 +90,15 @@ static struct ctl_table smc_table[] = { .extra1 = &conns_per_lgr_min, .extra2 = &conns_per_lgr_max, }, + { + .procname = "limit_smc_hs", + .data = &init_net.smc.limit_smc_hs, + .maxlen = sizeof(int), + .mode = 0644, + .proc_handler = proc_dointvec_minmax, + .extra1 = SYSCTL_ZERO, + .extra2 = SYSCTL_ONE, + }, }; int __net_init smc_sysctl_net_init(struct net *net) @@ -121,6 +130,8 @@ int __net_init smc_sysctl_net_init(struct net *net) WRITE_ONCE(net->smc.sysctl_rmem, net_smc_rmem_init); net->smc.sysctl_max_links_per_lgr = SMC_LINKS_PER_LGR_MAX_PREFER; net->smc.sysctl_max_conns_per_lgr = SMC_CONN_PER_LGR_PREFER; + /* disable handshake limitation by default */ + net->smc.limit_smc_hs = 0; return 0; diff --git a/net/socket.c b/net/socket.c index e416920e9399..601ad74930ef 100644 --- a/net/socket.c +++ b/net/socket.c @@ -153,7 +153,6 @@ static void sock_show_fdinfo(struct seq_file *m, struct file *f) static const struct file_operations socket_file_ops = { .owner = THIS_MODULE, - .llseek = no_llseek, .read_iter = sock_read_iter, .write_iter = sock_write_iter, .poll = sock_poll, @@ -556,10 +555,10 @@ static struct socket *sockfd_lookup_light(int fd, int *err, int *fput_needed) struct socket *sock; *err = -EBADF; - if (f.file) { - sock = sock_from_file(f.file); + if (fd_file(f)) { + sock = sock_from_file(fd_file(f)); if (likely(sock)) { - *fput_needed = f.flags & FDPUT_FPUT; + *fput_needed = f.word & FDPUT_FPUT; return sock; } *err = -ENOTSOCK; @@ -946,11 +945,17 @@ void __sock_recv_timestamp(struct msghdr *msg, struct sock *sk, memset(&tss, 0, sizeof(tss)); tsflags = READ_ONCE(sk->sk_tsflags); - if ((tsflags & SOF_TIMESTAMPING_SOFTWARE) && + if ((tsflags & SOF_TIMESTAMPING_SOFTWARE && + (tsflags & SOF_TIMESTAMPING_RX_SOFTWARE || + skb_is_err_queue(skb) || + !(tsflags & SOF_TIMESTAMPING_OPT_RX_FILTER))) && ktime_to_timespec64_cond(skb->tstamp, tss.ts + 0)) empty = 0; if (shhwtstamps && - (tsflags & SOF_TIMESTAMPING_RAW_HARDWARE) && + (tsflags & SOF_TIMESTAMPING_RAW_HARDWARE && + (tsflags & SOF_TIMESTAMPING_RX_HARDWARE || + skb_is_err_queue(skb) || + !(tsflags & SOF_TIMESTAMPING_OPT_RX_FILTER))) && !skb_is_swtx_tstamp(skb, false_tstamp)) { if_index = 0; if (skb_shinfo(skb)->tx_flags & SKBTX_HW_TSTAMP_NETDEV) @@ -1822,6 +1827,20 @@ SYSCALL_DEFINE4(socketpair, int, family, int, type, int, protocol, return __sys_socketpair(family, type, protocol, usockvec); } +int __sys_bind_socket(struct socket *sock, struct sockaddr_storage *address, + int addrlen) +{ + int err; + + err = security_socket_bind(sock, (struct sockaddr *)address, + addrlen); + if (!err) + err = READ_ONCE(sock->ops)->bind(sock, + (struct sockaddr *)address, + addrlen); + return err; +} + /* * Bind a name to a socket. Nothing much to do here since it's * the protocol's responsibility to handle the local address. @@ -1839,15 +1858,8 @@ int __sys_bind(int fd, struct sockaddr __user *umyaddr, int addrlen) sock = sockfd_lookup_light(fd, &err, &fput_needed); if (sock) { err = move_addr_to_kernel(umyaddr, addrlen, &address); - if (!err) { - err = security_socket_bind(sock, - (struct sockaddr *)&address, - addrlen); - if (!err) - err = READ_ONCE(sock->ops)->bind(sock, - (struct sockaddr *) - &address, addrlen); - } + if (!err) + err = __sys_bind_socket(sock, &address, addrlen); fput_light(sock->file, fput_needed); } return err; @@ -1863,23 +1875,28 @@ SYSCALL_DEFINE3(bind, int, fd, struct sockaddr __user *, umyaddr, int, addrlen) * necessary for a listen, and if that works, we mark the socket as * ready for listening. */ +int __sys_listen_socket(struct socket *sock, int backlog) +{ + int somaxconn, err; + + somaxconn = READ_ONCE(sock_net(sock->sk)->core.sysctl_somaxconn); + if ((unsigned int)backlog > somaxconn) + backlog = somaxconn; + + err = security_socket_listen(sock, backlog); + if (!err) + err = READ_ONCE(sock->ops)->listen(sock, backlog); + return err; +} int __sys_listen(int fd, int backlog) { struct socket *sock; int err, fput_needed; - int somaxconn; sock = sockfd_lookup_light(fd, &err, &fput_needed); if (sock) { - somaxconn = READ_ONCE(sock_net(sock->sk)->core.sysctl_somaxconn); - if ((unsigned int)backlog > somaxconn) - backlog = somaxconn; - - err = security_socket_listen(sock, backlog); - if (!err) - err = READ_ONCE(sock->ops)->listen(sock, backlog); - + err = __sys_listen_socket(sock, backlog); fput_light(sock->file, fput_needed); } return err; @@ -1996,8 +2013,8 @@ int __sys_accept4(int fd, struct sockaddr __user *upeer_sockaddr, struct fd f; f = fdget(fd); - if (f.file) { - ret = __sys_accept4_file(f.file, upeer_sockaddr, + if (fd_file(f)) { + ret = __sys_accept4_file(fd_file(f), upeer_sockaddr, upeer_addrlen, flags); fdput(f); } @@ -2058,12 +2075,12 @@ int __sys_connect(int fd, struct sockaddr __user *uservaddr, int addrlen) struct fd f; f = fdget(fd); - if (f.file) { + if (fd_file(f)) { struct sockaddr_storage address; ret = move_addr_to_kernel(uservaddr, addrlen, &address); if (!ret) - ret = __sys_connect_file(f.file, &address, addrlen, 0); + ret = __sys_connect_file(fd_file(f), &address, addrlen, 0); fdput(f); } @@ -2350,7 +2367,7 @@ INDIRECT_CALLABLE_DECLARE(bool tcp_bpf_bypass_getsockopt(int level, int do_sock_getsockopt(struct socket *sock, bool compat, int level, int optname, sockptr_t optval, sockptr_t optlen) { - int max_optlen __maybe_unused; + int max_optlen __maybe_unused = 0; const struct proto_ops *ops; int err; @@ -2359,7 +2376,7 @@ int do_sock_getsockopt(struct socket *sock, bool compat, int level, return err; if (!compat) - max_optlen = BPF_CGROUP_GETSOCKOPT_MAX_OPTLEN(optlen); + copy_from_sockptr(&max_optlen, optlen, sizeof(int)); ops = READ_ONCE(sock->ops); if (level == SOL_SOCKET) { diff --git a/net/sunrpc/auth_gss/gss_krb5_keys.c b/net/sunrpc/auth_gss/gss_krb5_keys.c index 06d8ee0db000..4eb19c3a54c7 100644 --- a/net/sunrpc/auth_gss/gss_krb5_keys.c +++ b/net/sunrpc/auth_gss/gss_krb5_keys.c @@ -168,7 +168,7 @@ static int krb5_DK(const struct gss_krb5_enctype *gk5e, goto err_return; blocksize = crypto_sync_skcipher_blocksize(cipher); if (crypto_sync_skcipher_setkey(cipher, inkey->data, inkey->len)) - goto err_return; + goto err_free_cipher; ret = -ENOMEM; inblockdata = kmalloc(blocksize, gfp_mask); diff --git a/net/sunrpc/cache.c b/net/sunrpc/cache.c index 95ff74706104..1bd3e531b0e0 100644 --- a/net/sunrpc/cache.c +++ b/net/sunrpc/cache.c @@ -731,11 +731,10 @@ static bool cache_defer_req(struct cache_req *req, struct cache_head *item) static void cache_revisit_request(struct cache_head *item) { struct cache_deferred_req *dreq; - struct list_head pending; struct hlist_node *tmp; int hash = DFR_HASH(item); + LIST_HEAD(pending); - INIT_LIST_HEAD(&pending); spin_lock(&cache_defer_lock); hlist_for_each_entry_safe(dreq, tmp, &cache_defer_hash[hash], hash) @@ -756,10 +755,8 @@ static void cache_revisit_request(struct cache_head *item) void cache_clean_deferred(void *owner) { struct cache_deferred_req *dreq, *tmp; - struct list_head pending; + LIST_HEAD(pending); - - INIT_LIST_HEAD(&pending); spin_lock(&cache_defer_lock); list_for_each_entry_safe(dreq, tmp, &cache_defer_list, recent) { @@ -1085,9 +1082,8 @@ static void cache_dequeue(struct cache_detail *detail, struct cache_head *ch) { struct cache_queue *cq, *tmp; struct cache_request *cr; - struct list_head dequeued; + LIST_HEAD(dequeued); - INIT_LIST_HEAD(&dequeued); spin_lock(&queue_lock); list_for_each_entry_safe(cq, tmp, &detail->queue, list) if (!cq->reader) { @@ -1596,7 +1592,6 @@ static int cache_release_procfs(struct inode *inode, struct file *filp) } static const struct proc_ops cache_channel_proc_ops = { - .proc_lseek = no_llseek, .proc_read = cache_read_procfs, .proc_write = cache_write_procfs, .proc_poll = cache_poll_procfs, @@ -1662,7 +1657,6 @@ static const struct proc_ops cache_flush_proc_ops = { .proc_read = read_flush_procfs, .proc_write = write_flush_procfs, .proc_release = release_flush_procfs, - .proc_lseek = no_llseek, }; static void remove_cache_proc_entries(struct cache_detail *cd) @@ -1815,7 +1809,6 @@ static int cache_release_pipefs(struct inode *inode, struct file *filp) const struct file_operations cache_file_operations_pipefs = { .owner = THIS_MODULE, - .llseek = no_llseek, .read = cache_read_pipefs, .write = cache_write_pipefs, .poll = cache_poll_pipefs, @@ -1881,7 +1874,6 @@ const struct file_operations cache_flush_operations_pipefs = { .read = read_flush_pipefs, .write = write_flush_pipefs, .release = release_flush_pipefs, - .llseek = no_llseek, }; int sunrpc_cache_register_pipefs(struct dentry *parent, diff --git a/net/sunrpc/clnt.c b/net/sunrpc/clnt.c index cfd1b1bf7e35..0090162ee8c3 100644 --- a/net/sunrpc/clnt.c +++ b/net/sunrpc/clnt.c @@ -48,13 +48,8 @@ # define RPCDBG_FACILITY RPCDBG_CALL #endif -/* - * All RPC clients are linked into this list - */ - static DECLARE_WAIT_QUEUE_HEAD(destroy_wait); - static void call_start(struct rpc_task *task); static void call_reserve(struct rpc_task *task); static void call_reserveresult(struct rpc_task *task); @@ -546,7 +541,7 @@ struct rpc_clnt *rpc_create(struct rpc_create_args *args) .connect_timeout = args->connect_timeout, .reconnect_timeout = args->reconnect_timeout, }; - char servername[48]; + char servername[RPC_MAXNETNAMELEN]; struct rpc_clnt *clnt; int i; @@ -1893,12 +1888,6 @@ call_allocate(struct rpc_task *task) if (req->rq_buffer) return; - if (proc->p_proc != 0) { - BUG_ON(proc->p_arglen == 0); - if (proc->p_decode != NULL) - BUG_ON(proc->p_replen == 0); - } - /* * Calculate the size (in quads) of the RPC call * and reply headers, and convert both values @@ -2326,12 +2315,13 @@ call_transmit_status(struct rpc_task *task) task->tk_action = call_transmit; task->tk_status = 0; break; - case -ECONNREFUSED: case -EHOSTDOWN: case -ENETDOWN: case -EHOSTUNREACH: case -ENETUNREACH: case -EPERM: + break; + case -ECONNREFUSED: if (RPC_IS_SOFTCONN(task)) { if (!task->tk_msg.rpc_proc->p_proc) trace_xprt_ping(task->tk_xprt, diff --git a/net/sunrpc/rpc_pipe.c b/net/sunrpc/rpc_pipe.c index 910a5d850d04..7ce3721c06ca 100644 --- a/net/sunrpc/rpc_pipe.c +++ b/net/sunrpc/rpc_pipe.c @@ -385,7 +385,6 @@ rpc_pipe_ioctl(struct file *filp, unsigned int cmd, unsigned long arg) static const struct file_operations rpc_pipe_fops = { .owner = THIS_MODULE, - .llseek = no_llseek, .read = rpc_pipe_read, .write = rpc_pipe_write, .poll = rpc_pipe_poll, diff --git a/net/sunrpc/sched.c b/net/sunrpc/sched.c index 6debf4fd42d4..cef623ea1506 100644 --- a/net/sunrpc/sched.c +++ b/net/sunrpc/sched.c @@ -369,8 +369,10 @@ static void rpc_make_runnable(struct workqueue_struct *wq, if (RPC_IS_ASYNC(task)) { INIT_WORK(&task->u.tk_work, rpc_async_schedule); queue_work(wq, &task->u.tk_work); - } else + } else { + smp_mb__after_atomic(); wake_up_bit(&task->tk_runstate, RPC_TASK_QUEUED); + } } /* diff --git a/net/sunrpc/sunrpc.h b/net/sunrpc/sunrpc.h index d4a362c9e4b3..e3c6e3b63f0b 100644 --- a/net/sunrpc/sunrpc.h +++ b/net/sunrpc/sunrpc.h @@ -36,7 +36,11 @@ static inline int sock_is_loopback(struct sock *sk) return loopback; } +struct svc_serv; +struct svc_rqst; int rpc_clients_notifier_register(void); void rpc_clients_notifier_unregister(void); void auth_domain_cleanup(void); +void svc_sock_update_bufs(struct svc_serv *serv); +enum svc_auth_status svc_authenticate(struct svc_rqst *rqstp); #endif /* _NET_SUNRPC_SUNRPC_H */ diff --git a/net/sunrpc/svc.c b/net/sunrpc/svc.c index 2b4b1276d4e8..7e7f4e0390c7 100644 --- a/net/sunrpc/svc.c +++ b/net/sunrpc/svc.c @@ -32,6 +32,7 @@ #include <trace/events/sunrpc.h> #include "fail.h" +#include "sunrpc.h" #define RPCDBG_FACILITY RPCDBG_SVCDSP @@ -72,57 +73,100 @@ static struct svc_pool_map svc_pool_map = { static DEFINE_MUTEX(svc_pool_map_mutex);/* protects svc_pool_map.count only */ static int -param_set_pool_mode(const char *val, const struct kernel_param *kp) +__param_set_pool_mode(const char *val, struct svc_pool_map *m) { - int *ip = (int *)kp->arg; - struct svc_pool_map *m = &svc_pool_map; - int err; + int err, mode; mutex_lock(&svc_pool_map_mutex); - err = -EBUSY; - if (m->count) - goto out; - err = 0; if (!strncmp(val, "auto", 4)) - *ip = SVC_POOL_AUTO; + mode = SVC_POOL_AUTO; else if (!strncmp(val, "global", 6)) - *ip = SVC_POOL_GLOBAL; + mode = SVC_POOL_GLOBAL; else if (!strncmp(val, "percpu", 6)) - *ip = SVC_POOL_PERCPU; + mode = SVC_POOL_PERCPU; else if (!strncmp(val, "pernode", 7)) - *ip = SVC_POOL_PERNODE; + mode = SVC_POOL_PERNODE; else err = -EINVAL; + if (err) + goto out; + + if (m->count == 0) + m->mode = mode; + else if (mode != m->mode) + err = -EBUSY; out: mutex_unlock(&svc_pool_map_mutex); return err; } static int -param_get_pool_mode(char *buf, const struct kernel_param *kp) +param_set_pool_mode(const char *val, const struct kernel_param *kp) +{ + struct svc_pool_map *m = kp->arg; + + return __param_set_pool_mode(val, m); +} + +int sunrpc_set_pool_mode(const char *val) +{ + return __param_set_pool_mode(val, &svc_pool_map); +} +EXPORT_SYMBOL(sunrpc_set_pool_mode); + +/** + * sunrpc_get_pool_mode - get the current pool_mode for the host + * @buf: where to write the current pool_mode + * @size: size of @buf + * + * Grab the current pool_mode from the svc_pool_map and write + * the resulting string to @buf. Returns the number of characters + * written to @buf (a'la snprintf()). + */ +int +sunrpc_get_pool_mode(char *buf, size_t size) { - int *ip = (int *)kp->arg; + struct svc_pool_map *m = &svc_pool_map; - switch (*ip) + switch (m->mode) { case SVC_POOL_AUTO: - return sysfs_emit(buf, "auto\n"); + return snprintf(buf, size, "auto"); case SVC_POOL_GLOBAL: - return sysfs_emit(buf, "global\n"); + return snprintf(buf, size, "global"); case SVC_POOL_PERCPU: - return sysfs_emit(buf, "percpu\n"); + return snprintf(buf, size, "percpu"); case SVC_POOL_PERNODE: - return sysfs_emit(buf, "pernode\n"); + return snprintf(buf, size, "pernode"); default: - return sysfs_emit(buf, "%d\n", *ip); + return snprintf(buf, size, "%d", m->mode); } } +EXPORT_SYMBOL(sunrpc_get_pool_mode); + +static int +param_get_pool_mode(char *buf, const struct kernel_param *kp) +{ + char str[16]; + int len; + + len = sunrpc_get_pool_mode(str, ARRAY_SIZE(str)); + + /* Ensure we have room for newline and NUL */ + len = min_t(int, len, ARRAY_SIZE(str) - 2); + + /* tack on the newline */ + str[len] = '\n'; + str[len + 1] = '\0'; + + return sysfs_emit(buf, "%s", str); +} module_param_call(pool_mode, param_set_pool_mode, param_get_pool_mode, - &svc_pool_map.mode, 0644); + &svc_pool_map, 0644); /* * Detect best pool mapping mode heuristically, @@ -250,10 +294,8 @@ svc_pool_map_get(void) int npools = -1; mutex_lock(&svc_pool_map_mutex); - if (m->count++) { mutex_unlock(&svc_pool_map_mutex); - WARN_ON_ONCE(m->npools <= 1); return m->npools; } @@ -275,32 +317,21 @@ svc_pool_map_get(void) m->mode = SVC_POOL_GLOBAL; } m->npools = npools; - - if (npools == 1) - /* service is unpooled, so doesn't hold a reference */ - m->count--; - mutex_unlock(&svc_pool_map_mutex); return npools; } /* - * Drop a reference to the global map of cpus to pools, if - * pools were in use, i.e. if npools > 1. + * Drop a reference to the global map of cpus to pools. * When the last reference is dropped, the map data is - * freed; this allows the sysadmin to change the pool - * mode using the pool_mode module option without - * rebooting or re-loading sunrpc.ko. + * freed; this allows the sysadmin to change the pool. */ static void -svc_pool_map_put(int npools) +svc_pool_map_put(void) { struct svc_pool_map *m = &svc_pool_map; - if (npools <= 1) - return; mutex_lock(&svc_pool_map_mutex); - if (!--m->count) { kfree(m->to_pool); m->to_pool = NULL; @@ -308,7 +339,6 @@ svc_pool_map_put(int npools) m->pool_to = NULL; m->npools = 0; } - mutex_unlock(&svc_pool_map_mutex); } @@ -388,7 +418,7 @@ struct svc_pool *svc_pool_for_cpu(struct svc_serv *serv) return &serv->sv_pools[pidx % serv->sv_nrpools]; } -int svc_rpcb_setup(struct svc_serv *serv, struct net *net) +static int svc_rpcb_setup(struct svc_serv *serv, struct net *net) { int err; @@ -400,7 +430,6 @@ int svc_rpcb_setup(struct svc_serv *serv, struct net *net) svc_unregister(serv, net); return 0; } -EXPORT_SYMBOL_GPL(svc_rpcb_setup); void svc_rpcb_cleanup(struct svc_serv *serv, struct net *net) { @@ -411,10 +440,11 @@ EXPORT_SYMBOL_GPL(svc_rpcb_cleanup); static int svc_uses_rpcbind(struct svc_serv *serv) { - struct svc_program *progp; - unsigned int i; + unsigned int p, i; + + for (p = 0; p < serv->sv_nprogs; p++) { + struct svc_program *progp = &serv->sv_programs[p]; - for (progp = serv->sv_program; progp; progp = progp->pg_next) { for (i = 0; i < progp->pg_nvers; i++) { if (progp->pg_vers[i] == NULL) continue; @@ -451,7 +481,7 @@ __svc_init_bc(struct svc_serv *serv) * Create an RPC service */ static struct svc_serv * -__svc_create(struct svc_program *prog, struct svc_stat *stats, +__svc_create(struct svc_program *prog, int nprogs, struct svc_stat *stats, unsigned int bufsize, int npools, int (*threadfn)(void *data)) { struct svc_serv *serv; @@ -462,7 +492,8 @@ __svc_create(struct svc_program *prog, struct svc_stat *stats, if (!(serv = kzalloc(sizeof(*serv), GFP_KERNEL))) return NULL; serv->sv_name = prog->pg_name; - serv->sv_program = prog; + serv->sv_programs = prog; + serv->sv_nprogs = nprogs; serv->sv_stats = stats; if (bufsize > RPCSVC_MAXPAYLOAD) bufsize = RPCSVC_MAXPAYLOAD; @@ -470,17 +501,18 @@ __svc_create(struct svc_program *prog, struct svc_stat *stats, serv->sv_max_mesg = roundup(serv->sv_max_payload + PAGE_SIZE, PAGE_SIZE); serv->sv_threadfn = threadfn; xdrsize = 0; - while (prog) { - prog->pg_lovers = prog->pg_nvers-1; - for (vers=0; vers<prog->pg_nvers ; vers++) - if (prog->pg_vers[vers]) { - prog->pg_hivers = vers; - if (prog->pg_lovers > vers) - prog->pg_lovers = vers; - if (prog->pg_vers[vers]->vs_xdrsize > xdrsize) - xdrsize = prog->pg_vers[vers]->vs_xdrsize; + for (i = 0; i < nprogs; i++) { + struct svc_program *progp = &prog[i]; + + progp->pg_lovers = progp->pg_nvers-1; + for (vers = 0; vers < progp->pg_nvers ; vers++) + if (progp->pg_vers[vers]) { + progp->pg_hivers = vers; + if (progp->pg_lovers > vers) + progp->pg_lovers = vers; + if (progp->pg_vers[vers]->vs_xdrsize > xdrsize) + xdrsize = progp->pg_vers[vers]->vs_xdrsize; } - prog = prog->pg_next; } serv->sv_xdrsize = xdrsize; INIT_LIST_HEAD(&serv->sv_tempsocks); @@ -529,13 +561,14 @@ __svc_create(struct svc_program *prog, struct svc_stat *stats, struct svc_serv *svc_create(struct svc_program *prog, unsigned int bufsize, int (*threadfn)(void *data)) { - return __svc_create(prog, NULL, bufsize, 1, threadfn); + return __svc_create(prog, 1, NULL, bufsize, 1, threadfn); } EXPORT_SYMBOL_GPL(svc_create); /** * svc_create_pooled - Create an RPC service with pooled threads - * @prog: the RPC program the new service will handle + * @prog: Array of RPC programs the new service will handle + * @nprogs: Number of programs in the array * @stats: the stats struct if desired * @bufsize: maximum message size for @prog * @threadfn: a function to service RPC requests for @prog @@ -543,6 +576,7 @@ EXPORT_SYMBOL_GPL(svc_create); * Returns an instantiated struct svc_serv object or NULL. */ struct svc_serv *svc_create_pooled(struct svc_program *prog, + unsigned int nprogs, struct svc_stat *stats, unsigned int bufsize, int (*threadfn)(void *data)) @@ -550,12 +584,13 @@ struct svc_serv *svc_create_pooled(struct svc_program *prog, struct svc_serv *serv; unsigned int npools = svc_pool_map_get(); - serv = __svc_create(prog, stats, bufsize, npools, threadfn); + serv = __svc_create(prog, nprogs, stats, bufsize, npools, threadfn); if (!serv) goto out_err; + serv->sv_is_pooled = true; return serv; out_err: - svc_pool_map_put(npools); + svc_pool_map_put(); return NULL; } EXPORT_SYMBOL_GPL(svc_create_pooled); @@ -572,20 +607,21 @@ svc_destroy(struct svc_serv **servp) *servp = NULL; - dprintk("svc: svc_destroy(%s)\n", serv->sv_program->pg_name); + dprintk("svc: svc_destroy(%s)\n", serv->sv_programs->pg_name); timer_shutdown_sync(&serv->sv_temptimer); /* * Remaining transports at this point are not expected. */ WARN_ONCE(!list_empty(&serv->sv_permsocks), - "SVC: permsocks remain for %s\n", serv->sv_program->pg_name); + "SVC: permsocks remain for %s\n", serv->sv_programs->pg_name); WARN_ONCE(!list_empty(&serv->sv_tempsocks), - "SVC: tempsocks remain for %s\n", serv->sv_program->pg_name); + "SVC: tempsocks remain for %s\n", serv->sv_programs->pg_name); cache_clean_deferred(serv); - svc_pool_map_put(serv->sv_nrpools); + if (serv->sv_is_pooled) + svc_pool_map_put(); for (i = 0; i < serv->sv_nrpools; i++) { struct svc_pool *pool = &serv->sv_pools[i]; @@ -633,8 +669,21 @@ svc_release_buffer(struct svc_rqst *rqstp) put_page(rqstp->rq_pages[i]); } -struct svc_rqst * -svc_rqst_alloc(struct svc_serv *serv, struct svc_pool *pool, int node) +static void +svc_rqst_free(struct svc_rqst *rqstp) +{ + folio_batch_release(&rqstp->rq_fbatch); + svc_release_buffer(rqstp); + if (rqstp->rq_scratch_page) + put_page(rqstp->rq_scratch_page); + kfree(rqstp->rq_resp); + kfree(rqstp->rq_argp); + kfree(rqstp->rq_auth_data); + kfree_rcu(rqstp, rq_rcu_head); +} + +static struct svc_rqst * +svc_prepare_thread(struct svc_serv *serv, struct svc_pool *pool, int node) { struct svc_rqst *rqstp; @@ -662,27 +711,10 @@ svc_rqst_alloc(struct svc_serv *serv, struct svc_pool *pool, int node) if (!svc_init_buffer(rqstp, serv->sv_max_mesg, node)) goto out_enomem; - return rqstp; -out_enomem: - svc_rqst_free(rqstp); - return NULL; -} -EXPORT_SYMBOL_GPL(svc_rqst_alloc); - -static struct svc_rqst * -svc_prepare_thread(struct svc_serv *serv, struct svc_pool *pool, int node) -{ - struct svc_rqst *rqstp; + rqstp->rq_err = -EAGAIN; /* No error yet */ - rqstp = svc_rqst_alloc(serv, pool, node); - if (!rqstp) - return ERR_PTR(-ENOMEM); - - spin_lock_bh(&serv->sv_lock); serv->sv_nrthreads += 1; - spin_unlock_bh(&serv->sv_lock); - - atomic_inc(&pool->sp_nrthreads); + pool->sp_nrthreads += 1; /* Protected by whatever lock the service uses when calling * svc_set_num_threads() @@ -690,6 +722,10 @@ svc_prepare_thread(struct svc_serv *serv, struct svc_pool *pool, int node) list_add_rcu(&rqstp->rq_all, &pool->sp_all_threads); return rqstp; + +out_enomem: + svc_rqst_free(rqstp); + return NULL; } /** @@ -737,31 +773,22 @@ svc_pool_victim(struct svc_serv *serv, struct svc_pool *target_pool, struct svc_pool *pool; unsigned int i; -retry: pool = target_pool; - if (pool != NULL) { - if (atomic_inc_not_zero(&pool->sp_nrthreads)) - goto found_pool; - return NULL; - } else { + if (!pool) { for (i = 0; i < serv->sv_nrpools; i++) { pool = &serv->sv_pools[--(*state) % serv->sv_nrpools]; - if (atomic_inc_not_zero(&pool->sp_nrthreads)) - goto found_pool; + if (pool->sp_nrthreads) + break; } - return NULL; } -found_pool: - set_bit(SP_VICTIM_REMAINS, &pool->sp_flags); - set_bit(SP_NEED_VICTIM, &pool->sp_flags); - if (!atomic_dec_and_test(&pool->sp_nrthreads)) + if (pool && pool->sp_nrthreads) { + set_bit(SP_VICTIM_REMAINS, &pool->sp_flags); + set_bit(SP_NEED_VICTIM, &pool->sp_flags); return pool; - /* Nothing left in this pool any more */ - clear_bit(SP_NEED_VICTIM, &pool->sp_flags); - clear_bit(SP_VICTIM_REMAINS, &pool->sp_flags); - goto retry; + } + return NULL; } static int @@ -772,6 +799,7 @@ svc_start_kthreads(struct svc_serv *serv, struct svc_pool *pool, int nrservs) struct svc_pool *chosen_pool; unsigned int state = serv->sv_nrthreads-1; int node; + int err; do { nrservs--; @@ -779,8 +807,8 @@ svc_start_kthreads(struct svc_serv *serv, struct svc_pool *pool, int nrservs) node = svc_pool_map_get_node(chosen_pool->sp_id); rqstp = svc_prepare_thread(serv, chosen_pool, node); - if (IS_ERR(rqstp)) - return PTR_ERR(rqstp); + if (!rqstp) + return -ENOMEM; task = kthread_create_on_node(serv->sv_threadfn, rqstp, node, "%s", serv->sv_name); if (IS_ERR(task)) { @@ -794,6 +822,13 @@ svc_start_kthreads(struct svc_serv *serv, struct svc_pool *pool, int nrservs) svc_sock_update_bufs(serv); wake_up_process(task); + + wait_var_event(&rqstp->rq_err, rqstp->rq_err != -EAGAIN); + err = rqstp->rq_err; + if (err) { + svc_exit_thread(rqstp); + return err; + } } while (nrservs > 0); return 0; @@ -840,7 +875,7 @@ svc_set_num_threads(struct svc_serv *serv, struct svc_pool *pool, int nrservs) if (!pool) nrservs -= serv->sv_nrthreads; else - nrservs -= atomic_read(&pool->sp_nrthreads); + nrservs -= pool->sp_nrthreads; if (nrservs > 0) return svc_start_kthreads(serv, pool, nrservs); @@ -902,25 +937,21 @@ void svc_rqst_release_pages(struct svc_rqst *rqstp) } } -/* - * Called from a server thread as it's exiting. Caller must hold the "service - * mutex" for the service. +/** + * svc_exit_thread - finalise the termination of a sunrpc server thread + * @rqstp: the svc_rqst which represents the thread. + * + * When a thread started with svc_new_thread() exits it must call + * svc_exit_thread() as its last act. This must be done with the + * service mutex held. Normally this is held by a DIFFERENT thread, the + * one that is calling svc_set_num_threads() and which will wait for + * SP_VICTIM_REMAINS to be cleared before dropping the mutex. If the + * thread exits for any reason other than svc_thread_should_stop() + * returning %true (which indicated that svc_set_num_threads() is + * waiting for it to exit), then it must take the service mutex itself, + * which can only safely be done using mutex_try_lock(). */ void -svc_rqst_free(struct svc_rqst *rqstp) -{ - folio_batch_release(&rqstp->rq_fbatch); - svc_release_buffer(rqstp); - if (rqstp->rq_scratch_page) - put_page(rqstp->rq_scratch_page); - kfree(rqstp->rq_resp); - kfree(rqstp->rq_argp); - kfree(rqstp->rq_auth_data); - kfree_rcu(rqstp, rq_rcu_head); -} -EXPORT_SYMBOL_GPL(svc_rqst_free); - -void svc_exit_thread(struct svc_rqst *rqstp) { struct svc_serv *serv = rqstp->rq_server; @@ -928,11 +959,8 @@ svc_exit_thread(struct svc_rqst *rqstp) list_del_rcu(&rqstp->rq_all); - atomic_dec(&pool->sp_nrthreads); - - spin_lock_bh(&serv->sv_lock); + pool->sp_nrthreads -= 1; serv->sv_nrthreads -= 1; - spin_unlock_bh(&serv->sv_lock); svc_sock_update_bufs(serv); svc_rqst_free(rqstp); @@ -1067,6 +1095,7 @@ static int __svc_register(struct net *net, const char *progname, return error; } +static int svc_rpcbind_set_version(struct net *net, const struct svc_program *progp, u32 version, int family, @@ -1077,7 +1106,6 @@ int svc_rpcbind_set_version(struct net *net, version, family, proto, port); } -EXPORT_SYMBOL_GPL(svc_rpcbind_set_version); int svc_generic_rpcbind_set(struct net *net, const struct svc_program *progp, @@ -1125,15 +1153,16 @@ int svc_register(const struct svc_serv *serv, struct net *net, const int family, const unsigned short proto, const unsigned short port) { - struct svc_program *progp; - unsigned int i; + unsigned int p, i; int error = 0; WARN_ON_ONCE(proto == 0 && port == 0); if (proto == 0 && port == 0) return -EINVAL; - for (progp = serv->sv_program; progp; progp = progp->pg_next) { + for (p = 0; p < serv->sv_nprogs; p++) { + struct svc_program *progp = &serv->sv_programs[p]; + for (i = 0; i < progp->pg_nvers; i++) { error = progp->pg_rpcbind_set(net, progp, i, @@ -1185,13 +1214,14 @@ static void __svc_unregister(struct net *net, const u32 program, const u32 versi static void svc_unregister(const struct svc_serv *serv, struct net *net) { struct sighand_struct *sighand; - struct svc_program *progp; unsigned long flags; - unsigned int i; + unsigned int p, i; clear_thread_flag(TIF_SIGPENDING); - for (progp = serv->sv_program; progp; progp = progp->pg_next) { + for (p = 0; p < serv->sv_nprogs; p++) { + struct svc_program *progp = &serv->sv_programs[p]; + for (i = 0; i < progp->pg_nvers; i++) { if (progp->pg_vers[i] == NULL) continue; @@ -1297,7 +1327,7 @@ svc_process_common(struct svc_rqst *rqstp) struct svc_process_info process; enum svc_auth_status auth_res; unsigned int aoffset; - int rc; + int pr, rc; __be32 *p; /* Will be turned off only when NFSv4 Sessions are used */ @@ -1321,9 +1351,12 @@ svc_process_common(struct svc_rqst *rqstp) rqstp->rq_vers = be32_to_cpup(p++); rqstp->rq_proc = be32_to_cpup(p); - for (progp = serv->sv_program; progp; progp = progp->pg_next) + for (pr = 0; pr < serv->sv_nprogs; pr++) { + progp = &serv->sv_programs[pr]; + if (rqstp->rq_prog == progp->pg_prog) break; + } /* * Decode auth data, and add verifier to reply buffer. @@ -1495,6 +1528,14 @@ err_system_err: goto sendit; } +/* + * Drop request + */ +static void svc_drop(struct svc_rqst *rqstp) +{ + trace_svc_drop(rqstp); +} + /** * svc_process - Execute one RPC transaction * @rqstp: RPC transaction context @@ -1557,9 +1598,11 @@ out_drop: */ void svc_process_bc(struct rpc_rqst *req, struct svc_rqst *rqstp) { + struct rpc_timeout timeout = { + .to_increment = 0, + }; struct rpc_task *task; int proc_error; - struct rpc_timeout timeout; /* Build the svc_rqst used by the common processing routine */ rqstp->rq_xid = req->rq_xid; @@ -1612,6 +1655,7 @@ void svc_process_bc(struct rpc_rqst *req, struct svc_rqst *rqstp) timeout.to_initval = req->rq_xprt->timeout->to_initval; timeout.to_retries = req->rq_xprt->timeout->to_retries; } + timeout.to_maxval = timeout.to_initval; memcpy(&req->rq_snd_buf, &rqstp->rq_res, sizeof(req->rq_snd_buf)); task = rpc_run_bc_task(req, &timeout); diff --git a/net/sunrpc/svc_xprt.c b/net/sunrpc/svc_xprt.c index 49a3bea33f9d..43c57124de52 100644 --- a/net/sunrpc/svc_xprt.c +++ b/net/sunrpc/svc_xprt.c @@ -157,6 +157,7 @@ int svc_print_xprts(char *buf, int maxlen) */ void svc_xprt_deferred_close(struct svc_xprt *xprt) { + trace_svc_xprt_close(xprt); if (!test_and_set_bit(XPT_CLOSE, &xprt->xpt_flags)) svc_xprt_enqueue(xprt); } @@ -267,7 +268,7 @@ static int _svc_xprt_create(struct svc_serv *serv, const char *xprt_name, spin_unlock(&svc_xprt_class_lock); newxprt = xcl->xcl_ops->xpo_create(serv, net, sap, len, flags); if (IS_ERR(newxprt)) { - trace_svc_xprt_create_err(serv->sv_program->pg_name, + trace_svc_xprt_create_err(serv->sv_programs->pg_name, xcl->xcl_name, sap, len, newxprt); module_put(xcl->xcl_owner); @@ -904,15 +905,6 @@ void svc_recv(struct svc_rqst *rqstp) } EXPORT_SYMBOL_GPL(svc_recv); -/* - * Drop request - */ -void svc_drop(struct svc_rqst *rqstp) -{ - trace_svc_drop(rqstp); -} -EXPORT_SYMBOL_GPL(svc_drop); - /** * svc_send - Return reply to client * @rqstp: RPC transaction context @@ -1421,13 +1413,12 @@ static void *svc_pool_stats_start(struct seq_file *m, loff_t *pos) dprintk("svc_pool_stats_start, *pidx=%u\n", pidx); - if (!si->serv) - return NULL; - mutex_lock(si->mutex); if (!pidx) return SEQ_START_TOKEN; + if (!si->serv) + return NULL; return pidx > si->serv->sv_nrpools ? NULL : &si->serv->sv_pools[pidx - 1]; } @@ -1459,8 +1450,7 @@ static void svc_pool_stats_stop(struct seq_file *m, void *p) { struct svc_info *si = m->private; - if (si->serv) - mutex_unlock(si->mutex); + mutex_unlock(si->mutex); } static int svc_pool_stats_show(struct seq_file *m, void *p) diff --git a/net/sunrpc/svcauth.c b/net/sunrpc/svcauth.c index 1619211f0960..55b4d2874188 100644 --- a/net/sunrpc/svcauth.c +++ b/net/sunrpc/svcauth.c @@ -18,6 +18,7 @@ #include <linux/sunrpc/svcauth.h> #include <linux/err.h> #include <linux/hash.h> +#include <linux/user_namespace.h> #include <trace/events/sunrpc.h> @@ -98,7 +99,6 @@ enum svc_auth_status svc_authenticate(struct svc_rqst *rqstp) rqstp->rq_authop = aops; return aops->accept(rqstp); } -EXPORT_SYMBOL_GPL(svc_authenticate); /** * svc_set_client - Assign an appropriate 'auth_domain' as the client @@ -176,6 +176,33 @@ rpc_authflavor_t svc_auth_flavor(struct svc_rqst *rqstp) } EXPORT_SYMBOL_GPL(svc_auth_flavor); +/** + * svcauth_map_clnt_to_svc_cred_local - maps a generic cred + * to a svc_cred suitable for use in nfsd. + * @clnt: rpc_clnt associated with nfs client + * @cred: generic cred associated with nfs client + * @svc: returned svc_cred that is suitable for use in nfsd + */ +void svcauth_map_clnt_to_svc_cred_local(struct rpc_clnt *clnt, + const struct cred *cred, + struct svc_cred *svc) +{ + struct user_namespace *userns = clnt->cl_cred ? + clnt->cl_cred->user_ns : &init_user_ns; + + memset(svc, 0, sizeof(struct svc_cred)); + + svc->cr_uid = KUIDT_INIT(from_kuid_munged(userns, cred->fsuid)); + svc->cr_gid = KGIDT_INIT(from_kgid_munged(userns, cred->fsgid)); + svc->cr_flavor = clnt->cl_auth->au_flavor; + if (cred->group_info) + svc->cr_group_info = get_group_info(cred->group_info); + /* These aren't relevant for local (network is bypassed) */ + svc->cr_principal = NULL; + svc->cr_gss_mech = NULL; +} +EXPORT_SYMBOL_GPL(svcauth_map_clnt_to_svc_cred_local); + /************************************************** * 'auth_domains' are stored in a hash table indexed by name. * When the last reference to an 'auth_domain' is dropped, diff --git a/net/sunrpc/svcauth_unix.c b/net/sunrpc/svcauth_unix.c index 04b45588ae6f..8ca98b146ec8 100644 --- a/net/sunrpc/svcauth_unix.c +++ b/net/sunrpc/svcauth_unix.c @@ -697,7 +697,8 @@ svcauth_unix_set_client(struct svc_rqst *rqstp) rqstp->rq_auth_stat = rpc_autherr_badcred; ipm = ip_map_cached_get(xprt); if (ipm == NULL) - ipm = __ip_map_lookup(sn->ip_map_cache, rqstp->rq_server->sv_program->pg_class, + ipm = __ip_map_lookup(sn->ip_map_cache, + rqstp->rq_server->sv_programs->pg_class, &sin6->sin6_addr); if (ipm == NULL) diff --git a/net/sunrpc/svcsock.c b/net/sunrpc/svcsock.c index 6b3f01beb294..825ec5357691 100644 --- a/net/sunrpc/svcsock.c +++ b/net/sunrpc/svcsock.c @@ -1378,7 +1378,6 @@ void svc_sock_update_bufs(struct svc_serv *serv) set_bit(XPT_CHNGBUF, &svsk->sk_xprt.xpt_flags); spin_unlock_bh(&serv->sv_lock); } -EXPORT_SYMBOL_GPL(svc_sock_update_bufs); /* * Initialize socket for RPC use and create svc_sock struct diff --git a/net/sunrpc/sysctl.c b/net/sunrpc/sysctl.c index 5f3170a1c9bb..bdb587a72422 100644 --- a/net/sunrpc/sysctl.c +++ b/net/sunrpc/sysctl.c @@ -40,7 +40,7 @@ EXPORT_SYMBOL_GPL(nlm_debug); #if IS_ENABLED(CONFIG_SUNRPC_DEBUG) -static int proc_do_xprt(struct ctl_table *table, int write, +static int proc_do_xprt(const struct ctl_table *table, int write, void *buffer, size_t *lenp, loff_t *ppos) { char tmpbuf[256]; @@ -62,7 +62,7 @@ static int proc_do_xprt(struct ctl_table *table, int write, } static int -proc_dodebug(struct ctl_table *table, int write, void *buffer, size_t *lenp, +proc_dodebug(const struct ctl_table *table, int write, void *buffer, size_t *lenp, loff_t *ppos) { char tmpbuf[20], *s = NULL; diff --git a/net/sunrpc/xprtrdma/Makefile b/net/sunrpc/xprtrdma/Makefile index 55b21bae866d..3232aa23cdb4 100644 --- a/net/sunrpc/xprtrdma/Makefile +++ b/net/sunrpc/xprtrdma/Makefile @@ -1,7 +1,7 @@ # SPDX-License-Identifier: GPL-2.0 obj-$(CONFIG_SUNRPC_XPRT_RDMA) += rpcrdma.o -rpcrdma-y := transport.o rpc_rdma.o verbs.o frwr_ops.o \ +rpcrdma-y := transport.o rpc_rdma.o verbs.o frwr_ops.o ib_client.o \ svc_rdma.o svc_rdma_backchannel.o svc_rdma_transport.o \ svc_rdma_sendto.o svc_rdma_recvfrom.o svc_rdma_rw.o \ svc_rdma_pcl.o module.o diff --git a/net/sunrpc/xprtrdma/frwr_ops.c b/net/sunrpc/xprtrdma/frwr_ops.c index ffbf99894970..31434aeb8e29 100644 --- a/net/sunrpc/xprtrdma/frwr_ops.c +++ b/net/sunrpc/xprtrdma/frwr_ops.c @@ -54,7 +54,7 @@ static void frwr_cid_init(struct rpcrdma_ep *ep, cid->ci_completion_id = mr->mr_ibmr->res.id; } -static void frwr_mr_unmap(struct rpcrdma_xprt *r_xprt, struct rpcrdma_mr *mr) +static void frwr_mr_unmap(struct rpcrdma_mr *mr) { if (mr->mr_device) { trace_xprtrdma_mr_unmap(mr); @@ -73,7 +73,7 @@ void frwr_mr_release(struct rpcrdma_mr *mr) { int rc; - frwr_mr_unmap(mr->mr_xprt, mr); + frwr_mr_unmap(mr); rc = ib_dereg_mr(mr->mr_ibmr); if (rc) @@ -84,7 +84,7 @@ void frwr_mr_release(struct rpcrdma_mr *mr) static void frwr_mr_put(struct rpcrdma_mr *mr) { - frwr_mr_unmap(mr->mr_xprt, mr); + frwr_mr_unmap(mr); /* The MR is returned to the req's MR free list instead * of to the xprt's MR free list. No spinlock is needed. @@ -92,7 +92,8 @@ static void frwr_mr_put(struct rpcrdma_mr *mr) rpcrdma_mr_push(mr, &mr->mr_req->rl_free_mrs); } -/* frwr_reset - Place MRs back on the free list +/** + * frwr_reset - Place MRs back on @req's free list * @req: request to reset * * Used after a failed marshal. For FRWR, this means the MRs diff --git a/net/sunrpc/xprtrdma/ib_client.c b/net/sunrpc/xprtrdma/ib_client.c new file mode 100644 index 000000000000..8507cd4d8921 --- /dev/null +++ b/net/sunrpc/xprtrdma/ib_client.c @@ -0,0 +1,183 @@ +// SPDX-License-Identifier: GPL-2.0 OR BSD-3-Clause +/* + * Copyright (c) 2024 Oracle. All rights reserved. + */ + +/* #include <linux/module.h> +#include <linux/slab.h> */ +#include <linux/xarray.h> +#include <linux/types.h> +#include <linux/kref.h> +#include <linux/completion.h> + +#include <linux/sunrpc/svc_rdma.h> +#include <linux/sunrpc/rdma_rn.h> + +#include "xprt_rdma.h" +#include <trace/events/rpcrdma.h> + +/* Per-ib_device private data for rpcrdma */ +struct rpcrdma_device { + struct kref rd_kref; + unsigned long rd_flags; + struct ib_device *rd_device; + struct xarray rd_xa; + struct completion rd_done; +}; + +#define RPCRDMA_RD_F_REMOVING (0) + +static struct ib_client rpcrdma_ib_client; + +/* + * Listeners have no associated device, so we never register them. + * Note that ib_get_client_data() does not check if @device is + * NULL for us. + */ +static struct rpcrdma_device *rpcrdma_get_client_data(struct ib_device *device) +{ + if (!device) + return NULL; + return ib_get_client_data(device, &rpcrdma_ib_client); +} + +/** + * rpcrdma_rn_register - register to get device removal notifications + * @device: device to monitor + * @rn: notification object that wishes to be notified + * @done: callback to notify caller of device removal + * + * Returns zero on success. The callback in rn_done is guaranteed + * to be invoked when the device is removed, unless this notification + * is unregistered first. + * + * On failure, a negative errno is returned. + */ +int rpcrdma_rn_register(struct ib_device *device, + struct rpcrdma_notification *rn, + void (*done)(struct rpcrdma_notification *rn)) +{ + struct rpcrdma_device *rd = rpcrdma_get_client_data(device); + + if (!rd || test_bit(RPCRDMA_RD_F_REMOVING, &rd->rd_flags)) + return -ENETUNREACH; + + if (xa_alloc(&rd->rd_xa, &rn->rn_index, rn, xa_limit_32b, GFP_KERNEL) < 0) + return -ENOMEM; + kref_get(&rd->rd_kref); + rn->rn_done = done; + trace_rpcrdma_client_register(device, rn); + return 0; +} + +static void rpcrdma_rn_release(struct kref *kref) +{ + struct rpcrdma_device *rd = container_of(kref, struct rpcrdma_device, + rd_kref); + + trace_rpcrdma_client_completion(rd->rd_device); + complete(&rd->rd_done); +} + +/** + * rpcrdma_rn_unregister - stop device removal notifications + * @device: monitored device + * @rn: notification object that no longer wishes to be notified + */ +void rpcrdma_rn_unregister(struct ib_device *device, + struct rpcrdma_notification *rn) +{ + struct rpcrdma_device *rd = rpcrdma_get_client_data(device); + + if (!rd) + return; + + trace_rpcrdma_client_unregister(device, rn); + xa_erase(&rd->rd_xa, rn->rn_index); + kref_put(&rd->rd_kref, rpcrdma_rn_release); +} + +/** + * rpcrdma_add_one - ib_client device insertion callback + * @device: device about to be inserted + * + * Returns zero on success. xprtrdma private data has been allocated + * for this device. On failure, a negative errno is returned. + */ +static int rpcrdma_add_one(struct ib_device *device) +{ + struct rpcrdma_device *rd; + + rd = kzalloc(sizeof(*rd), GFP_KERNEL); + if (!rd) + return -ENOMEM; + + kref_init(&rd->rd_kref); + xa_init_flags(&rd->rd_xa, XA_FLAGS_ALLOC); + rd->rd_device = device; + init_completion(&rd->rd_done); + ib_set_client_data(device, &rpcrdma_ib_client, rd); + + trace_rpcrdma_client_add_one(device); + return 0; +} + +/** + * rpcrdma_remove_one - ib_client device removal callback + * @device: device about to be removed + * @client_data: this module's private per-device data + * + * Upon return, all transports associated with @device have divested + * themselves from IB hardware resources. + */ +static void rpcrdma_remove_one(struct ib_device *device, + void *client_data) +{ + struct rpcrdma_device *rd = client_data; + struct rpcrdma_notification *rn; + unsigned long index; + + trace_rpcrdma_client_remove_one(device); + + set_bit(RPCRDMA_RD_F_REMOVING, &rd->rd_flags); + xa_for_each(&rd->rd_xa, index, rn) + rn->rn_done(rn); + + /* + * Wait only if there are still outstanding notification + * registrants for this device. + */ + if (!refcount_dec_and_test(&rd->rd_kref.refcount)) { + trace_rpcrdma_client_wait_on(device); + wait_for_completion(&rd->rd_done); + } + + trace_rpcrdma_client_remove_one_done(device); + kfree(rd); +} + +static struct ib_client rpcrdma_ib_client = { + .name = "rpcrdma", + .add = rpcrdma_add_one, + .remove = rpcrdma_remove_one, +}; + +/** + * rpcrdma_ib_client_unregister - unregister ib_client for xprtrdma + * + * cel: watch for orphaned rpcrdma_device objects on module unload + */ +void rpcrdma_ib_client_unregister(void) +{ + ib_unregister_client(&rpcrdma_ib_client); +} + +/** + * rpcrdma_ib_client_register - register ib_client for rpcrdma + * + * Returns zero on success, or a negative errno. + */ +int rpcrdma_ib_client_register(void) +{ + return ib_register_client(&rpcrdma_ib_client); +} diff --git a/net/sunrpc/xprtrdma/module.c b/net/sunrpc/xprtrdma/module.c index 45c5b41ac8dc..697f571d4c01 100644 --- a/net/sunrpc/xprtrdma/module.c +++ b/net/sunrpc/xprtrdma/module.c @@ -11,6 +11,7 @@ #include <linux/module.h> #include <linux/init.h> #include <linux/sunrpc/svc_rdma.h> +#include <linux/sunrpc/rdma_rn.h> #include <asm/swab.h> @@ -30,21 +31,32 @@ static void __exit rpc_rdma_cleanup(void) { xprt_rdma_cleanup(); svc_rdma_cleanup(); + rpcrdma_ib_client_unregister(); } static int __init rpc_rdma_init(void) { int rc; + rc = rpcrdma_ib_client_register(); + if (rc) + goto out_rc; + rc = svc_rdma_init(); if (rc) - goto out; + goto out_ib_client; rc = xprt_rdma_init(); if (rc) - svc_rdma_cleanup(); + goto out_svc_rdma; -out: + return 0; + +out_svc_rdma: + svc_rdma_cleanup(); +out_ib_client: + rpcrdma_ib_client_unregister(); +out_rc: return rc; } diff --git a/net/sunrpc/xprtrdma/rpc_rdma.c b/net/sunrpc/xprtrdma/rpc_rdma.c index 190a4de239c8..1478c41c7e9d 100644 --- a/net/sunrpc/xprtrdma/rpc_rdma.c +++ b/net/sunrpc/xprtrdma/rpc_rdma.c @@ -1471,8 +1471,7 @@ void rpcrdma_reply_handler(struct rpcrdma_rep *rep) credits = 1; /* don't deadlock */ else if (credits > r_xprt->rx_ep->re_max_requests) credits = r_xprt->rx_ep->re_max_requests; - rpcrdma_post_recvs(r_xprt, credits + (buf->rb_bc_srv_max_requests << 1), - false); + rpcrdma_post_recvs(r_xprt, credits + (buf->rb_bc_srv_max_requests << 1)); if (buf->rb_credits != credits) rpcrdma_update_cwnd(r_xprt, credits); diff --git a/net/sunrpc/xprtrdma/svc_rdma.c b/net/sunrpc/xprtrdma/svc_rdma.c index 474f7a98fe9e..58ae6ec4f25b 100644 --- a/net/sunrpc/xprtrdma/svc_rdma.c +++ b/net/sunrpc/xprtrdma/svc_rdma.c @@ -74,7 +74,7 @@ enum { SVCRDMA_COUNTER_BUFSIZ = sizeof(unsigned long long), }; -static int svcrdma_counter_handler(struct ctl_table *table, int write, +static int svcrdma_counter_handler(const struct ctl_table *table, int write, void *buffer, size_t *lenp, loff_t *ppos) { struct percpu_counter *stat = (struct percpu_counter *)table->data; diff --git a/net/sunrpc/xprtrdma/svc_rdma_transport.c b/net/sunrpc/xprtrdma/svc_rdma_transport.c index 2b1c16b9547d..c3fbf0779d4a 100644 --- a/net/sunrpc/xprtrdma/svc_rdma_transport.c +++ b/net/sunrpc/xprtrdma/svc_rdma_transport.c @@ -65,6 +65,8 @@ static struct svcxprt_rdma *svc_rdma_create_xprt(struct svc_serv *serv, struct net *net, int node); +static int svc_rdma_listen_handler(struct rdma_cm_id *cma_id, + struct rdma_cm_event *event); static struct svc_xprt *svc_rdma_create(struct svc_serv *serv, struct net *net, struct sockaddr *sa, int salen, @@ -122,6 +124,41 @@ static void qp_event_handler(struct ib_event *event, void *context) } } +static struct rdma_cm_id * +svc_rdma_create_listen_id(struct net *net, struct sockaddr *sap, + void *context) +{ + struct rdma_cm_id *listen_id; + int ret; + + listen_id = rdma_create_id(net, svc_rdma_listen_handler, context, + RDMA_PS_TCP, IB_QPT_RC); + if (IS_ERR(listen_id)) + return listen_id; + + /* Allow both IPv4 and IPv6 sockets to bind a single port + * at the same time. + */ +#if IS_ENABLED(CONFIG_IPV6) + ret = rdma_set_afonly(listen_id, 1); + if (ret) + goto out_destroy; +#endif + ret = rdma_bind_addr(listen_id, sap); + if (ret) + goto out_destroy; + + ret = rdma_listen(listen_id, RPCRDMA_LISTEN_BACKLOG); + if (ret) + goto out_destroy; + + return listen_id; + +out_destroy: + rdma_destroy_id(listen_id); + return ERR_PTR(ret); +} + static struct svcxprt_rdma *svc_rdma_create_xprt(struct svc_serv *serv, struct net *net, int node) { @@ -247,17 +284,31 @@ static void handle_connect_req(struct rdma_cm_id *new_cma_id, * * Return values: * %0: Do not destroy @cma_id - * %1: Destroy @cma_id (never returned here) + * %1: Destroy @cma_id * * NB: There is never a DEVICE_REMOVAL event for INADDR_ANY listeners. */ static int svc_rdma_listen_handler(struct rdma_cm_id *cma_id, struct rdma_cm_event *event) { + struct sockaddr *sap = (struct sockaddr *)&cma_id->route.addr.src_addr; + struct svcxprt_rdma *cma_xprt = cma_id->context; + struct svc_xprt *cma_rdma = &cma_xprt->sc_xprt; + struct rdma_cm_id *listen_id; + switch (event->event) { case RDMA_CM_EVENT_CONNECT_REQUEST: handle_connect_req(cma_id, &event->param.conn); break; + case RDMA_CM_EVENT_ADDR_CHANGE: + listen_id = svc_rdma_create_listen_id(cma_rdma->xpt_net, + sap, cma_xprt); + if (IS_ERR(listen_id)) { + pr_err("Listener dead, address change failed for device %s\n", + cma_id->device->name); + } else + cma_xprt->sc_cm_id = listen_id; + return 1; default: break; } @@ -288,7 +339,6 @@ static int svc_rdma_cma_handler(struct rdma_cm_id *cma_id, svc_xprt_enqueue(xprt); break; case RDMA_CM_EVENT_DISCONNECTED: - case RDMA_CM_EVENT_DEVICE_REMOVAL: svc_xprt_deferred_close(xprt); break; default: @@ -307,7 +357,6 @@ static struct svc_xprt *svc_rdma_create(struct svc_serv *serv, { struct rdma_cm_id *listen_id; struct svcxprt_rdma *cma_xprt; - int ret; if (sa->sa_family != AF_INET && sa->sa_family != AF_INET6) return ERR_PTR(-EAFNOSUPPORT); @@ -317,30 +366,13 @@ static struct svc_xprt *svc_rdma_create(struct svc_serv *serv, set_bit(XPT_LISTENER, &cma_xprt->sc_xprt.xpt_flags); strcpy(cma_xprt->sc_xprt.xpt_remotebuf, "listener"); - listen_id = rdma_create_id(net, svc_rdma_listen_handler, cma_xprt, - RDMA_PS_TCP, IB_QPT_RC); + listen_id = svc_rdma_create_listen_id(net, sa, cma_xprt); if (IS_ERR(listen_id)) { - ret = PTR_ERR(listen_id); - goto err0; + kfree(cma_xprt); + return ERR_CAST(listen_id); } - - /* Allow both IPv4 and IPv6 sockets to bind a single port - * at the same time. - */ -#if IS_ENABLED(CONFIG_IPV6) - ret = rdma_set_afonly(listen_id, 1); - if (ret) - goto err1; -#endif - ret = rdma_bind_addr(listen_id, sa); - if (ret) - goto err1; cma_xprt->sc_cm_id = listen_id; - ret = rdma_listen(listen_id, RPCRDMA_LISTEN_BACKLOG); - if (ret) - goto err1; - /* * We need to use the address from the cm_id in case the * caller specified 0 for the port number. @@ -349,12 +381,16 @@ static struct svc_xprt *svc_rdma_create(struct svc_serv *serv, svc_xprt_set_local(&cma_xprt->sc_xprt, sa, salen); return &cma_xprt->sc_xprt; +} - err1: - rdma_destroy_id(listen_id); - err0: - kfree(cma_xprt); - return ERR_PTR(ret); +static void svc_rdma_xprt_done(struct rpcrdma_notification *rn) +{ + struct svcxprt_rdma *rdma = container_of(rn, struct svcxprt_rdma, + sc_rn); + struct rdma_cm_id *id = rdma->sc_cm_id; + + trace_svcrdma_device_removal(id); + svc_xprt_close(&rdma->sc_xprt); } /* @@ -398,6 +434,9 @@ static struct svc_xprt *svc_rdma_accept(struct svc_xprt *xprt) dev = newxprt->sc_cm_id->device; newxprt->sc_port_num = newxprt->sc_cm_id->port_num; + if (rpcrdma_rn_register(dev, &newxprt->sc_rn, svc_rdma_xprt_done)) + goto errout; + newxprt->sc_max_req_size = svcrdma_max_req_size; newxprt->sc_max_requests = svcrdma_max_requests; newxprt->sc_max_bc_requests = svcrdma_max_bc_requests; @@ -553,6 +592,7 @@ static void __svc_rdma_free(struct work_struct *work) { struct svcxprt_rdma *rdma = container_of(work, struct svcxprt_rdma, sc_work); + struct ib_device *device = rdma->sc_cm_id->device; /* This blocks until the Completion Queues are empty */ if (rdma->sc_qp && !IS_ERR(rdma->sc_qp)) @@ -581,6 +621,7 @@ static void __svc_rdma_free(struct work_struct *work) /* Destroy the CM ID */ rdma_destroy_id(rdma->sc_cm_id); + rpcrdma_rn_unregister(device, &rdma->sc_rn); kfree(rdma); } diff --git a/net/sunrpc/xprtrdma/verbs.c b/net/sunrpc/xprtrdma/verbs.c index 432557a553e7..63262ef0c2e3 100644 --- a/net/sunrpc/xprtrdma/verbs.c +++ b/net/sunrpc/xprtrdma/verbs.c @@ -49,14 +49,14 @@ * o buffer memory */ +#include <linux/bitops.h> #include <linux/interrupt.h> #include <linux/slab.h> #include <linux/sunrpc/addr.h> #include <linux/sunrpc/svc_rdma.h> #include <linux/log2.h> -#include <asm-generic/barrier.h> -#include <asm/bitops.h> +#include <asm/barrier.h> #include <rdma/ib_cm.h> @@ -69,13 +69,15 @@ static void rpcrdma_sendctx_put_locked(struct rpcrdma_xprt *r_xprt, struct rpcrdma_sendctx *sc); static int rpcrdma_reqs_setup(struct rpcrdma_xprt *r_xprt); static void rpcrdma_reqs_reset(struct rpcrdma_xprt *r_xprt); -static void rpcrdma_rep_destroy(struct rpcrdma_rep *rep); static void rpcrdma_reps_unmap(struct rpcrdma_xprt *r_xprt); static void rpcrdma_mrs_create(struct rpcrdma_xprt *r_xprt); static void rpcrdma_mrs_destroy(struct rpcrdma_xprt *r_xprt); static void rpcrdma_ep_get(struct rpcrdma_ep *ep); static int rpcrdma_ep_put(struct rpcrdma_ep *ep); static struct rpcrdma_regbuf * +rpcrdma_regbuf_alloc_node(size_t size, enum dma_data_direction direction, + int node); +static struct rpcrdma_regbuf * rpcrdma_regbuf_alloc(size_t size, enum dma_data_direction direction); static void rpcrdma_regbuf_dma_unmap(struct rpcrdma_regbuf *rb); static void rpcrdma_regbuf_free(struct rpcrdma_regbuf *rb); @@ -222,7 +224,6 @@ static void rpcrdma_update_cm_private(struct rpcrdma_ep *ep, static int rpcrdma_cm_event_handler(struct rdma_cm_id *id, struct rdma_cm_event *event) { - struct sockaddr *sap = (struct sockaddr *)&id->route.addr.dst_addr; struct rpcrdma_ep *ep = id->context; might_sleep(); @@ -241,14 +242,6 @@ rpcrdma_cm_event_handler(struct rdma_cm_id *id, struct rdma_cm_event *event) ep->re_async_rc = -ENETUNREACH; complete(&ep->re_done); return 0; - case RDMA_CM_EVENT_DEVICE_REMOVAL: - pr_info("rpcrdma: removing device %s for %pISpc\n", - ep->re_id->device->name, sap); - switch (xchg(&ep->re_connect_status, -ENODEV)) { - case 0: goto wake_connect_worker; - case 1: goto disconnected; - } - return 0; case RDMA_CM_EVENT_ADDR_CHANGE: ep->re_connect_status = -ENODEV; goto disconnected; @@ -284,6 +277,14 @@ disconnected: return 0; } +static void rpcrdma_ep_removal_done(struct rpcrdma_notification *rn) +{ + struct rpcrdma_ep *ep = container_of(rn, struct rpcrdma_ep, re_rn); + + trace_xprtrdma_device_removal(ep->re_id); + xprt_force_disconnect(ep->re_xprt); +} + static struct rdma_cm_id *rpcrdma_create_id(struct rpcrdma_xprt *r_xprt, struct rpcrdma_ep *ep) { @@ -323,6 +324,10 @@ static struct rdma_cm_id *rpcrdma_create_id(struct rpcrdma_xprt *r_xprt, if (rc) goto out; + rc = rpcrdma_rn_register(id->device, &ep->re_rn, rpcrdma_ep_removal_done); + if (rc) + goto out; + return id; out: @@ -350,6 +355,8 @@ static void rpcrdma_ep_destroy(struct kref *kref) ib_dealloc_pd(ep->re_pd); ep->re_pd = NULL; + rpcrdma_rn_unregister(ep->re_id->device, &ep->re_rn); + kfree(ep); module_put(THIS_MODULE); } @@ -505,7 +512,7 @@ int rpcrdma_xprt_connect(struct rpcrdma_xprt *r_xprt) * outstanding Receives. */ rpcrdma_ep_get(ep); - rpcrdma_post_recvs(r_xprt, 1, true); + rpcrdma_post_recvs(r_xprt, 1); rc = rdma_connect(ep->re_id, &ep->re_remote_cma); if (rc) @@ -897,6 +904,8 @@ static int rpcrdma_reqs_setup(struct rpcrdma_xprt *r_xprt) static void rpcrdma_req_reset(struct rpcrdma_req *req) { + struct rpcrdma_mr *mr; + /* Credits are valid for only one connection */ req->rl_slot.rq_cong = 0; @@ -906,7 +915,19 @@ static void rpcrdma_req_reset(struct rpcrdma_req *req) rpcrdma_regbuf_dma_unmap(req->rl_sendbuf); rpcrdma_regbuf_dma_unmap(req->rl_recvbuf); - frwr_reset(req); + /* The verbs consumer can't know the state of an MR on the + * req->rl_registered list unless a successful completion + * has occurred, so they cannot be re-used. + */ + while ((mr = rpcrdma_mr_pop(&req->rl_registered))) { + struct rpcrdma_buffer *buf = &mr->mr_xprt->rx_buf; + + spin_lock(&buf->rb_lock); + list_del(&mr->mr_all); + spin_unlock(&buf->rb_lock); + + frwr_mr_release(mr); + } } /* ASSUMPTION: the rb_allreqs list is stable for the duration, @@ -924,18 +945,20 @@ static void rpcrdma_reqs_reset(struct rpcrdma_xprt *r_xprt) } static noinline -struct rpcrdma_rep *rpcrdma_rep_create(struct rpcrdma_xprt *r_xprt, - bool temp) +struct rpcrdma_rep *rpcrdma_rep_create(struct rpcrdma_xprt *r_xprt) { struct rpcrdma_buffer *buf = &r_xprt->rx_buf; + struct rpcrdma_ep *ep = r_xprt->rx_ep; + struct ib_device *device = ep->re_id->device; struct rpcrdma_rep *rep; rep = kzalloc(sizeof(*rep), XPRTRDMA_GFP_FLAGS); if (rep == NULL) goto out; - rep->rr_rdmabuf = rpcrdma_regbuf_alloc(r_xprt->rx_ep->re_inline_recv, - DMA_FROM_DEVICE); + rep->rr_rdmabuf = rpcrdma_regbuf_alloc_node(ep->re_inline_recv, + DMA_FROM_DEVICE, + ibdev_to_node(device)); if (!rep->rr_rdmabuf) goto out_free; @@ -950,7 +973,6 @@ struct rpcrdma_rep *rpcrdma_rep_create(struct rpcrdma_xprt *r_xprt, rep->rr_recv_wr.wr_cqe = &rep->rr_cqe; rep->rr_recv_wr.sg_list = &rep->rr_rdmabuf->rg_iov; rep->rr_recv_wr.num_sge = 1; - rep->rr_temp = temp; spin_lock(&buf->rb_lock); list_add(&rep->rr_all, &buf->rb_all_reps); @@ -969,17 +991,6 @@ static void rpcrdma_rep_free(struct rpcrdma_rep *rep) kfree(rep); } -static void rpcrdma_rep_destroy(struct rpcrdma_rep *rep) -{ - struct rpcrdma_buffer *buf = &rep->rr_rxprt->rx_buf; - - spin_lock(&buf->rb_lock); - list_del(&rep->rr_all); - spin_unlock(&buf->rb_lock); - - rpcrdma_rep_free(rep); -} - static struct rpcrdma_rep *rpcrdma_rep_get_locked(struct rpcrdma_buffer *buf) { struct llist_node *node; @@ -1011,10 +1022,8 @@ static void rpcrdma_reps_unmap(struct rpcrdma_xprt *r_xprt) struct rpcrdma_buffer *buf = &r_xprt->rx_buf; struct rpcrdma_rep *rep; - list_for_each_entry(rep, &buf->rb_all_reps, rr_all) { + list_for_each_entry(rep, &buf->rb_all_reps, rr_all) rpcrdma_regbuf_dma_unmap(rep->rr_rdmabuf); - rep->rr_temp = true; /* Mark this rep for destruction */ - } } static void rpcrdma_reps_destroy(struct rpcrdma_buffer *buf) @@ -1231,14 +1240,15 @@ void rpcrdma_buffer_put(struct rpcrdma_buffer *buffers, struct rpcrdma_req *req) * or Replies they may be registered externally via frwr_map. */ static struct rpcrdma_regbuf * -rpcrdma_regbuf_alloc(size_t size, enum dma_data_direction direction) +rpcrdma_regbuf_alloc_node(size_t size, enum dma_data_direction direction, + int node) { struct rpcrdma_regbuf *rb; - rb = kmalloc(sizeof(*rb), XPRTRDMA_GFP_FLAGS); + rb = kmalloc_node(sizeof(*rb), XPRTRDMA_GFP_FLAGS, node); if (!rb) return NULL; - rb->rg_data = kmalloc(size, XPRTRDMA_GFP_FLAGS); + rb->rg_data = kmalloc_node(size, XPRTRDMA_GFP_FLAGS, node); if (!rb->rg_data) { kfree(rb); return NULL; @@ -1250,6 +1260,12 @@ rpcrdma_regbuf_alloc(size_t size, enum dma_data_direction direction) return rb; } +static struct rpcrdma_regbuf * +rpcrdma_regbuf_alloc(size_t size, enum dma_data_direction direction) +{ + return rpcrdma_regbuf_alloc_node(size, direction, NUMA_NO_NODE); +} + /** * rpcrdma_regbuf_realloc - re-allocate a SEND/RECV buffer * @rb: regbuf to reallocate @@ -1327,10 +1343,9 @@ static void rpcrdma_regbuf_free(struct rpcrdma_regbuf *rb) * rpcrdma_post_recvs - Refill the Receive Queue * @r_xprt: controlling transport instance * @needed: current credit grant - * @temp: mark Receive buffers to be deleted after one use * */ -void rpcrdma_post_recvs(struct rpcrdma_xprt *r_xprt, int needed, bool temp) +void rpcrdma_post_recvs(struct rpcrdma_xprt *r_xprt, int needed) { struct rpcrdma_buffer *buf = &r_xprt->rx_buf; struct rpcrdma_ep *ep = r_xprt->rx_ep; @@ -1344,8 +1359,7 @@ void rpcrdma_post_recvs(struct rpcrdma_xprt *r_xprt, int needed, bool temp) if (likely(ep->re_receive_count > needed)) goto out; needed -= ep->re_receive_count; - if (!temp) - needed += RPCRDMA_MAX_RECV_BATCH; + needed += RPCRDMA_MAX_RECV_BATCH; if (atomic_inc_return(&ep->re_receiving) > 1) goto out; @@ -1354,12 +1368,8 @@ void rpcrdma_post_recvs(struct rpcrdma_xprt *r_xprt, int needed, bool temp) wr = NULL; while (needed) { rep = rpcrdma_rep_get_locked(buf); - if (rep && rep->rr_temp) { - rpcrdma_rep_destroy(rep); - continue; - } if (!rep) - rep = rpcrdma_rep_create(r_xprt, temp); + rep = rpcrdma_rep_create(r_xprt); if (!rep) break; if (!rpcrdma_regbuf_dma_map(r_xprt, rep->rr_rdmabuf)) { diff --git a/net/sunrpc/xprtrdma/xprt_rdma.h b/net/sunrpc/xprtrdma/xprt_rdma.h index da409450dfc0..8147d2b41494 100644 --- a/net/sunrpc/xprtrdma/xprt_rdma.h +++ b/net/sunrpc/xprtrdma/xprt_rdma.h @@ -56,6 +56,7 @@ #include <linux/sunrpc/rpc_rdma_cid.h> /* completion IDs */ #include <linux/sunrpc/rpc_rdma.h> /* RPC/RDMA protocol */ #include <linux/sunrpc/xprtrdma.h> /* xprt parameters */ +#include <linux/sunrpc/rdma_rn.h> /* removal notifications */ #define RDMA_RESOLVE_TIMEOUT (5000) /* 5 seconds */ #define RDMA_CONNECT_RETRY_MAX (2) /* retries if no listener backlog */ @@ -92,6 +93,7 @@ struct rpcrdma_ep { struct rpcrdma_connect_private re_cm_private; struct rdma_conn_param re_remote_cma; + struct rpcrdma_notification re_rn; int re_receive_count; unsigned int re_max_requests; /* depends on device */ unsigned int re_inline_send; /* negotiated */ @@ -198,7 +200,6 @@ struct rpcrdma_rep { __be32 rr_proc; int rr_wc_flags; u32 rr_inv_rkey; - bool rr_temp; struct rpcrdma_regbuf *rr_rdmabuf; struct rpcrdma_xprt *rr_rxprt; struct rpc_rqst *rr_rqst; @@ -466,7 +467,7 @@ void rpcrdma_flush_disconnect(struct rpcrdma_xprt *r_xprt, struct ib_wc *wc); int rpcrdma_xprt_connect(struct rpcrdma_xprt *r_xprt); void rpcrdma_xprt_disconnect(struct rpcrdma_xprt *r_xprt); -void rpcrdma_post_recvs(struct rpcrdma_xprt *r_xprt, int needed, bool temp); +void rpcrdma_post_recvs(struct rpcrdma_xprt *r_xprt, int needed); /* * Buffer calls - xprtrdma/verbs.c diff --git a/net/sunrpc/xprtsock.c b/net/sunrpc/xprtsock.c index dfc353eea8ed..0e1691316f42 100644 --- a/net/sunrpc/xprtsock.c +++ b/net/sunrpc/xprtsock.c @@ -2441,6 +2441,13 @@ static void xs_tcp_setup_socket(struct work_struct *work) transport->srcport = 0; status = -EAGAIN; break; + case -EPERM: + /* Happens, for instance, if a BPF program is preventing + * the connect. Remap the error so upper layers can better + * deal with it. + */ + status = -ECONNREFUSED; + fallthrough; case -EINVAL: /* Happens, for instance, if the user specified a link * local IPv6 address without a scope-id. diff --git a/net/sysctl_net.c b/net/sysctl_net.c index f5017012a049..19e8048241ba 100644 --- a/net/sysctl_net.c +++ b/net/sysctl_net.c @@ -127,7 +127,7 @@ static void ensure_safe_net_sysctl(struct net *net, const char *path, pr_debug("Registering net sysctl (net %p): %s\n", net, path); ent = table; - for (size_t i = 0; i < table_size && ent->procname; ent++, i++) { + for (size_t i = 0; i < table_size; ent++, i++) { unsigned long addr; const char *where; @@ -165,17 +165,10 @@ struct ctl_table_header *register_net_sysctl_sz(struct net *net, struct ctl_table *table, size_t table_size) { - int count; - struct ctl_table *entry; - if (!net_eq(net, &init_net)) ensure_safe_net_sysctl(net, path, table, table_size); - entry = table; - for (count = 0 ; count < table_size && entry->procname; entry++, count++) - ; - - return __register_sysctl_table(&net->sysctls, path, table, count); + return __register_sysctl_table(&net->sysctls, path, table, table_size); } EXPORT_SYMBOL_GPL(register_net_sysctl_sz); diff --git a/net/tipc/bcast.c b/net/tipc/bcast.c index 593846d25214..114fef65f92e 100644 --- a/net/tipc/bcast.c +++ b/net/tipc/bcast.c @@ -320,8 +320,8 @@ static int tipc_mcast_send_sync(struct net *net, struct sk_buff *skb, { struct tipc_msg *hdr, *_hdr; struct sk_buff_head tmpq; + u16 cong_link_cnt = 0; struct sk_buff *_skb; - u16 cong_link_cnt; int rc = 0; /* Is a cluster supporting with new capabilities ? */ diff --git a/net/tipc/bearer.c b/net/tipc/bearer.c index 5a526ebafeb4..ae1ddbf71853 100644 --- a/net/tipc/bearer.c +++ b/net/tipc/bearer.c @@ -163,8 +163,12 @@ static int bearer_name_validate(const char *name, /* return bearer name components, if necessary */ if (name_parts) { - strcpy(name_parts->media_name, media_name); - strcpy(name_parts->if_name, if_name); + if (strscpy(name_parts->media_name, media_name, + TIPC_MAX_MEDIA_NAME) < 0) + return 0; + if (strscpy(name_parts->if_name, if_name, + TIPC_MAX_IF_NAME) < 0) + return 0; } return 1; } @@ -322,7 +326,7 @@ static int tipc_enable_bearer(struct net *net, const char *name, if (!b) return -ENOMEM; - strcpy(b->name, name); + strscpy(b->name, name); b->media = m; res = m->enable_media(net, b, attr); if (res) { diff --git a/net/tipc/core.h b/net/tipc/core.h index 7eccd97e0609..7f3fe3401c45 100644 --- a/net/tipc/core.h +++ b/net/tipc/core.h @@ -72,7 +72,6 @@ struct tipc_node; struct tipc_bearer; struct tipc_bc_base; struct tipc_link; -struct tipc_name_table; struct tipc_topsrv; struct tipc_monitor; #ifdef CONFIG_TIPC_CRYPTO diff --git a/net/tipc/link.c b/net/tipc/link.c index 0716eb5c8a31..5c2088a469ce 100644 --- a/net/tipc/link.c +++ b/net/tipc/link.c @@ -241,13 +241,6 @@ enum { LINK_SYNCHING = 0xc << 24 }; -/* Link FSM state checking routines - */ -static int link_is_up(struct tipc_link *l) -{ - return l->state & (LINK_ESTABLISHED | LINK_SYNCHING); -} - static int tipc_link_proto_rcv(struct tipc_link *l, struct sk_buff *skb, struct sk_buff_head *xmitq); static void tipc_link_build_proto_msg(struct tipc_link *l, int mtyp, bool probe, @@ -274,7 +267,7 @@ static void tipc_link_update_cwin(struct tipc_link *l, int released, */ bool tipc_link_is_up(struct tipc_link *l) { - return link_is_up(l); + return l->state & (LINK_ESTABLISHED | LINK_SYNCHING); } bool tipc_link_peer_is_down(struct tipc_link *l) @@ -1790,7 +1783,7 @@ int tipc_link_rcv(struct tipc_link *l, struct sk_buff *skb, rcv_nxt = l->rcv_nxt; win_lim = rcv_nxt + TIPC_MAX_LINK_WIN; - if (unlikely(!link_is_up(l))) { + if (unlikely(!tipc_link_is_up(l))) { if (l->state == LINK_ESTABLISHING) rc = TIPC_LINK_UP_EVT; kfree_skb(skb); @@ -1848,7 +1841,7 @@ static void tipc_link_build_proto_msg(struct tipc_link *l, int mtyp, bool probe, struct tipc_link *bcl = l->bc_rcvlink; struct tipc_msg *hdr; struct sk_buff *skb; - bool node_up = link_is_up(bcl); + bool node_up = tipc_link_is_up(bcl); u16 glen = 0, bc_rcvgap = 0; int dlen = 0; void *data; @@ -2163,7 +2156,7 @@ bool tipc_link_validate_msg(struct tipc_link *l, struct tipc_msg *hdr) if (session != curr_session) return false; /* Extra sanity check */ - if (!link_is_up(l) && msg_ack(hdr)) + if (!tipc_link_is_up(l) && msg_ack(hdr)) return false; if (!(l->peer_caps & TIPC_LINK_PROTO_SEQNO)) return true; @@ -2261,7 +2254,7 @@ static int tipc_link_proto_rcv(struct tipc_link *l, struct sk_buff *skb, } /* ACTIVATE_MSG serves as PEER_RESET if link is already down */ - if (mtyp == RESET_MSG || !link_is_up(l)) + if (mtyp == RESET_MSG || !tipc_link_is_up(l)) rc = tipc_link_fsm_evt(l, LINK_PEER_RESET_EVT); /* ACTIVATE_MSG takes up link if it was already locally reset */ @@ -2300,7 +2293,7 @@ static int tipc_link_proto_rcv(struct tipc_link *l, struct sk_buff *skb, if (msg_probe(hdr)) l->stats.recv_probes++; - if (!link_is_up(l)) { + if (!tipc_link_is_up(l)) { if (l->state == LINK_ESTABLISHING) rc = TIPC_LINK_UP_EVT; break; @@ -2387,7 +2380,7 @@ void tipc_link_bc_init_rcv(struct tipc_link *l, struct tipc_msg *hdr) int mtyp = msg_type(hdr); u16 peers_snd_nxt = msg_bc_snd_nxt(hdr); - if (link_is_up(l)) + if (tipc_link_is_up(l)) return; if (msg_user(hdr) == BCAST_PROTOCOL) { @@ -2415,7 +2408,7 @@ int tipc_link_bc_sync_rcv(struct tipc_link *l, struct tipc_msg *hdr, u16 peers_snd_nxt = msg_bc_snd_nxt(hdr); int rc = 0; - if (!link_is_up(l)) + if (!tipc_link_is_up(l)) return rc; if (!msg_peer_node_is_up(hdr)) @@ -2475,7 +2468,7 @@ int tipc_link_bc_ack_rcv(struct tipc_link *r, u16 acked, u16 gap, bool unused = false; int rc = 0; - if (!link_is_up(r) || !r->bc_peer_is_up) + if (!tipc_link_is_up(r) || !r->bc_peer_is_up) return 0; if (gap) { @@ -2873,7 +2866,7 @@ void tipc_link_set_tolerance(struct tipc_link *l, u32 tol, l->tolerance = tol; if (l->bc_rcvlink) l->bc_rcvlink->tolerance = tol; - if (link_is_up(l)) + if (tipc_link_is_up(l)) tipc_link_build_proto_msg(l, STATE_MSG, 0, 0, 0, tol, 0, xmitq); } diff --git a/net/tipc/monitor.c b/net/tipc/monitor.c index 77a3d016cade..e2f19627e43d 100644 --- a/net/tipc/monitor.c +++ b/net/tipc/monitor.c @@ -149,7 +149,7 @@ static int dom_size(int peers) while ((i * i) < peers) i++; - return i < MAX_MON_DOMAIN ? i : MAX_MON_DOMAIN; + return min(i, MAX_MON_DOMAIN); } static void map_set(u64 *up_map, int i, unsigned int v) diff --git a/net/tipc/socket.c b/net/tipc/socket.c index 2d58ecae4e21..65dcbb54f55d 100644 --- a/net/tipc/socket.c +++ b/net/tipc/socket.c @@ -657,7 +657,7 @@ static int tipc_release(struct socket *sock) } /** - * __tipc_bind - associate or disassocate TIPC name(s) with a socket + * __tipc_bind - associate or disassociate TIPC name(s) with a socket * @sock: socket structure * @skaddr: socket address describing name(s) and desired operation * @alen: size of socket address data structure @@ -1009,12 +1009,11 @@ static int tipc_send_group_anycast(struct socket *sock, struct msghdr *m, struct tipc_member *mbr = NULL; struct net *net = sock_net(sk); u32 node, port, exclude; - struct list_head dsts; + LIST_HEAD(dsts); int lookups = 0; int dstcnt, rc; bool cong; - INIT_LIST_HEAD(&dsts); ua->sa.type = msg_nametype(hdr); ua->scope = msg_lookup_scope(hdr); @@ -1161,10 +1160,9 @@ static int tipc_send_group_mcast(struct socket *sock, struct msghdr *m, struct tipc_group *grp = tsk->group; struct tipc_msg *hdr = &tsk->phdr; struct net *net = sock_net(sk); - struct list_head dsts; u32 dstcnt, exclude; + LIST_HEAD(dsts); - INIT_LIST_HEAD(&dsts); ua->sa.type = msg_nametype(hdr); ua->scope = msg_lookup_scope(hdr); exclude = tipc_group_exclude(grp); diff --git a/net/tipc/udp_media.c b/net/tipc/udp_media.c index b849a3d133a0..439f75539977 100644 --- a/net/tipc/udp_media.c +++ b/net/tipc/udp_media.c @@ -135,8 +135,11 @@ static int tipc_udp_addr2str(struct tipc_media_addr *a, char *buf, int size) snprintf(buf, size, "%pI4:%u", &ua->ipv4, ntohs(ua->port)); else if (ntohs(ua->proto) == ETH_P_IPV6) snprintf(buf, size, "%pI6:%u", &ua->ipv6, ntohs(ua->port)); - else + else { pr_err("Invalid UDP media address\n"); + return 1; + } + return 0; } diff --git a/net/tls/tls_device.c b/net/tls/tls_device.c index ab6e694f7bc2..dc063c2c7950 100644 --- a/net/tls/tls_device.c +++ b/net/tls/tls_device.c @@ -231,14 +231,10 @@ static void tls_device_resync_tx(struct sock *sk, struct tls_context *tls_ctx, u32 seq) { struct net_device *netdev; - struct sk_buff *skb; int err = 0; u8 *rcd_sn; - skb = tcp_write_queue_tail(sk); - if (skb) - TCP_SKB_CB(skb)->eor = 1; - + tcp_write_collapse_fence(sk); rcd_sn = tls_ctx->tx.rec_seq; trace_tls_device_tx_resync_send(sk, seq, rcd_sn); @@ -1067,7 +1063,6 @@ int tls_set_device_offload(struct sock *sk) struct tls_prot_info *prot; struct net_device *netdev; struct tls_context *ctx; - struct sk_buff *skb; char *iv, *rec_seq; int rc; @@ -1138,9 +1133,7 @@ int tls_set_device_offload(struct sock *sk) * SKBs where only part of the payload needs to be encrypted. * So mark the last skb in the write queue as end of record. */ - skb = tcp_write_queue_tail(sk); - if (skb) - TCP_SKB_CB(skb)->eor = 1; + tcp_write_collapse_fence(sk); /* Avoid offloading if the device is down * We don't want to offload new flows after diff --git a/net/tls/tls_main.c b/net/tls/tls_main.c index 90b7f253d363..6b4b9f2749a6 100644 --- a/net/tls/tls_main.c +++ b/net/tls/tls_main.c @@ -616,6 +616,7 @@ static int do_tls_setsockopt_conf(struct sock *sk, sockptr_t optval, struct tls_crypto_info *alt_crypto_info; struct tls_context *ctx = tls_get_ctx(sk); const struct tls_cipher_desc *cipher_desc; + union tls_crypto_context *crypto_ctx; int rc = 0; int conf; @@ -623,13 +624,15 @@ static int do_tls_setsockopt_conf(struct sock *sk, sockptr_t optval, return -EINVAL; if (tx) { - crypto_info = &ctx->crypto_send.info; + crypto_ctx = &ctx->crypto_send; alt_crypto_info = &ctx->crypto_recv.info; } else { - crypto_info = &ctx->crypto_recv.info; + crypto_ctx = &ctx->crypto_recv; alt_crypto_info = &ctx->crypto_send.info; } + crypto_info = &crypto_ctx->info; + /* Currently we don't support set crypto info more than one time */ if (TLS_CRYPTO_INFO_READY(crypto_info)) return -EBUSY; @@ -710,7 +713,7 @@ static int do_tls_setsockopt_conf(struct sock *sk, sockptr_t optval, return 0; err_crypto_info: - memzero_explicit(crypto_info, sizeof(union tls_crypto_context)); + memzero_explicit(crypto_ctx, sizeof(*crypto_ctx)); return rc; } diff --git a/net/tls/tls_sw.c b/net/tls/tls_sw.c index 305a412785f5..bbf26cc4f6ee 100644 --- a/net/tls/tls_sw.c +++ b/net/tls/tls_sw.c @@ -1201,7 +1201,7 @@ trim_sgl: if (!num_async) { goto send_end; - } else if (num_zc) { + } else if (num_zc || eor) { int err; /* Wait for pending encryptions to get completed */ diff --git a/net/unix/af_unix.c b/net/unix/af_unix.c index 5e695a9a609c..001ccc55ef0f 100644 --- a/net/unix/af_unix.c +++ b/net/unix/af_unix.c @@ -126,6 +126,81 @@ static spinlock_t bsd_socket_locks[UNIX_HASH_SIZE / 2]; * hash table is protected with spinlock. * each socket state is protected by separate spinlock. */ +#ifdef CONFIG_PROVE_LOCKING +#define cmp_ptr(l, r) (((l) > (r)) - ((l) < (r))) + +static int unix_table_lock_cmp_fn(const struct lockdep_map *a, + const struct lockdep_map *b) +{ + return cmp_ptr(a, b); +} + +static int unix_state_lock_cmp_fn(const struct lockdep_map *_a, + const struct lockdep_map *_b) +{ + const struct unix_sock *a, *b; + + a = container_of(_a, struct unix_sock, lock.dep_map); + b = container_of(_b, struct unix_sock, lock.dep_map); + + if (a->sk.sk_state == TCP_LISTEN) { + /* unix_stream_connect(): Before the 2nd unix_state_lock(), + * + * 1. a is TCP_LISTEN. + * 2. b is not a. + * 3. concurrent connect(b -> a) must fail. + * + * Except for 2. & 3., the b's state can be any possible + * value due to concurrent connect() or listen(). + * + * 2. is detected in debug_spin_lock_before(), and 3. cannot + * be expressed as lock_cmp_fn. + */ + switch (b->sk.sk_state) { + case TCP_CLOSE: + case TCP_ESTABLISHED: + case TCP_LISTEN: + return -1; + default: + /* Invalid case. */ + return 0; + } + } + + /* Should never happen. Just to be symmetric. */ + if (b->sk.sk_state == TCP_LISTEN) { + switch (b->sk.sk_state) { + case TCP_CLOSE: + case TCP_ESTABLISHED: + return 1; + default: + return 0; + } + } + + /* unix_state_double_lock(): ascending address order. */ + return cmp_ptr(a, b); +} + +static int unix_recvq_lock_cmp_fn(const struct lockdep_map *_a, + const struct lockdep_map *_b) +{ + const struct sock *a, *b; + + a = container_of(_a, struct sock, sk_receive_queue.lock.dep_map); + b = container_of(_b, struct sock, sk_receive_queue.lock.dep_map); + + /* unix_collect_skb(): listener -> embryo order. */ + if (a->sk_state == TCP_LISTEN && unix_sk(b)->listener == a) + return -1; + + /* Should never happen. Just to be symmetric. */ + if (b->sk_state == TCP_LISTEN && unix_sk(a)->listener == b) + return 1; + + return 0; +} +#endif static unsigned int unix_unbound_hash(struct sock *sk) { @@ -168,7 +243,7 @@ static void unix_table_double_lock(struct net *net, swap(hash1, hash2); spin_lock(&net->unx.table.locks[hash1]); - spin_lock_nested(&net->unx.table.locks[hash2], SINGLE_DEPTH_NESTING); + spin_lock(&net->unx.table.locks[hash2]); } static void unix_table_double_unlock(struct net *net, @@ -618,10 +693,7 @@ static void unix_release_sock(struct sock *sk, int embrion) unix_state_unlock(sk); #if IS_ENABLED(CONFIG_AF_UNIX_OOB) - if (u->oob_skb) { - kfree_skb(u->oob_skb); - u->oob_skb = NULL; - } + u->oob_skb = NULL; #endif wake_up_interruptible_all(&u->peer_wait); @@ -647,8 +719,8 @@ static void unix_release_sock(struct sock *sk, int embrion) while ((skb = skb_dequeue(&sk->sk_receive_queue)) != NULL) { if (state == TCP_LISTEN) unix_release_sock(skb->sk, 1); + /* passed fds are erased in the kfree_skb hook */ - UNIXCB(skb).consumed = skb->len; kfree_skb(skb); } @@ -676,14 +748,19 @@ static void unix_release_sock(struct sock *sk, int embrion) static void init_peercred(struct sock *sk) { + sk->sk_peer_pid = get_pid(task_tgid(current)); + sk->sk_peer_cred = get_current_cred(); +} + +static void update_peercred(struct sock *sk) +{ const struct cred *old_cred; struct pid *old_pid; spin_lock(&sk->sk_peer_lock); old_pid = sk->sk_peer_pid; old_cred = sk->sk_peer_cred; - sk->sk_peer_pid = get_pid(task_tgid(current)); - sk->sk_peer_cred = get_current_cred(); + init_peercred(sk); spin_unlock(&sk->sk_peer_lock); put_pid(old_pid); @@ -692,26 +769,12 @@ static void init_peercred(struct sock *sk) static void copy_peercred(struct sock *sk, struct sock *peersk) { - const struct cred *old_cred; - struct pid *old_pid; + lockdep_assert_held(&unix_sk(peersk)->lock); - if (sk < peersk) { - spin_lock(&sk->sk_peer_lock); - spin_lock_nested(&peersk->sk_peer_lock, SINGLE_DEPTH_NESTING); - } else { - spin_lock(&peersk->sk_peer_lock); - spin_lock_nested(&sk->sk_peer_lock, SINGLE_DEPTH_NESTING); - } - old_pid = sk->sk_peer_pid; - old_cred = sk->sk_peer_cred; - sk->sk_peer_pid = get_pid(peersk->sk_peer_pid); + spin_lock(&sk->sk_peer_lock); + sk->sk_peer_pid = get_pid(peersk->sk_peer_pid); sk->sk_peer_cred = get_cred(peersk->sk_peer_cred); - spin_unlock(&sk->sk_peer_lock); - spin_unlock(&peersk->sk_peer_lock); - - put_pid(old_pid); - put_cred(old_cred); } static int unix_listen(struct socket *sock, int backlog) @@ -735,7 +798,7 @@ static int unix_listen(struct socket *sock, int backlog) WRITE_ONCE(sk->sk_state, TCP_LISTEN); /* set credentials so connect can copy them */ - init_peercred(sk); + update_peercred(sk); err = 0; out_unlock: @@ -972,12 +1035,15 @@ static struct sock *unix_create1(struct net *net, struct socket *sock, int kern, sk->sk_write_space = unix_write_space; sk->sk_max_ack_backlog = READ_ONCE(net->unx.sysctl_max_dgram_qlen); sk->sk_destruct = unix_sock_destructor; + lock_set_cmp_fn(&sk->sk_receive_queue.lock, unix_recvq_lock_cmp_fn, NULL); + u = unix_sk(sk); u->listener = NULL; u->vertex = NULL; u->path.dentry = NULL; u->path.mnt = NULL; spin_lock_init(&u->lock); + lock_set_cmp_fn(&u->lock, unix_state_lock_cmp_fn, NULL); mutex_init(&u->iolock); /* single task reading lock */ mutex_init(&u->bindlock); /* single task binding lock */ init_waitqueue_head(&u->peer_wait); @@ -1326,11 +1392,12 @@ static void unix_state_double_lock(struct sock *sk1, struct sock *sk2) unix_state_lock(sk1); return; } + if (sk1 > sk2) swap(sk1, sk2); unix_state_lock(sk1); - unix_state_lock_nested(sk2, U_LOCK_SECOND); + unix_state_lock(sk2); } static void unix_state_double_unlock(struct sock *sk1, struct sock *sk2) @@ -1473,6 +1540,7 @@ static int unix_stream_connect(struct socket *sock, struct sockaddr *uaddr, struct unix_sock *u = unix_sk(sk), *newu, *otheru; struct net *net = sock_net(sk); struct sk_buff *skb = NULL; + unsigned char state; long timeo; int err; @@ -1523,7 +1591,6 @@ restart: goto out; } - /* Latch state of peer */ unix_state_lock(other); /* Apparently VFS overslept socket death. Retry. */ @@ -1553,37 +1620,21 @@ restart: goto restart; } - /* Latch our state. - - It is tricky place. We need to grab our state lock and cannot - drop lock on peer. It is dangerous because deadlock is - possible. Connect to self case and simultaneous - attempt to connect are eliminated by checking socket - state. other is TCP_LISTEN, if sk is TCP_LISTEN we - check this before attempt to grab lock. - - Well, and we have to recheck the state after socket locked. + /* self connect and simultaneous connect are eliminated + * by rejecting TCP_LISTEN socket to avoid deadlock. */ - switch (READ_ONCE(sk->sk_state)) { - case TCP_CLOSE: - /* This is ok... continue with connect */ - break; - case TCP_ESTABLISHED: - /* Socket is already connected */ - err = -EISCONN; - goto out_unlock; - default: - err = -EINVAL; + state = READ_ONCE(sk->sk_state); + if (unlikely(state != TCP_CLOSE)) { + err = state == TCP_ESTABLISHED ? -EISCONN : -EINVAL; goto out_unlock; } - unix_state_lock_nested(sk, U_LOCK_SECOND); + unix_state_lock(sk); - if (sk->sk_state != TCP_CLOSE) { + if (unlikely(sk->sk_state != TCP_CLOSE)) { + err = sk->sk_state == TCP_ESTABLISHED ? -EISCONN : -EINVAL; unix_state_unlock(sk); - unix_state_unlock(other); - sock_put(other); - goto restart; + goto out_unlock; } err = security_unix_stream_connect(sk, other, newsk); @@ -2172,13 +2223,9 @@ static int queue_oob(struct socket *sock, struct msghdr *msg, struct sock *other } maybe_add_creds(skb, sock, other); - skb_get(skb); - scm_stat_add(other, skb); spin_lock(&other->sk_receive_queue.lock); - if (ousk->oob_skb) - consume_skb(ousk->oob_skb); WRITE_ONCE(ousk->oob_skb, skb); __skb_queue_tail(&other->sk_receive_queue, skb); spin_unlock(&other->sk_receive_queue.lock); @@ -2586,8 +2633,6 @@ static int unix_stream_recv_urg(struct unix_stream_read_state *state) if (!(state->flags & MSG_PEEK)) WRITE_ONCE(u->oob_skb, NULL); - else - skb_get(oob_skb); spin_unlock(&sk->sk_receive_queue.lock); unix_state_unlock(sk); @@ -2597,8 +2642,6 @@ static int unix_stream_recv_urg(struct unix_stream_read_state *state) if (!(state->flags & MSG_PEEK)) UNIXCB(oob_skb).consumed += 1; - consume_skb(oob_skb); - mutex_unlock(&u->iolock); if (chunk < 0) @@ -2611,52 +2654,100 @@ static int unix_stream_recv_urg(struct unix_stream_read_state *state) static struct sk_buff *manage_oob(struct sk_buff *skb, struct sock *sk, int flags, int copied) { + struct sk_buff *read_skb = NULL, *unread_skb = NULL; struct unix_sock *u = unix_sk(sk); - if (!unix_skb_len(skb) && !(flags & MSG_PEEK)) { - skb_unlink(skb, &sk->sk_receive_queue); - consume_skb(skb); - skb = NULL; - } else { - struct sk_buff *unlinked_skb = NULL; + if (likely(unix_skb_len(skb) && skb != READ_ONCE(u->oob_skb))) + return skb; - spin_lock(&sk->sk_receive_queue.lock); + spin_lock(&sk->sk_receive_queue.lock); - if (skb == u->oob_skb) { - if (copied) { - skb = NULL; - } else if (!(flags & MSG_PEEK)) { - if (sock_flag(sk, SOCK_URGINLINE)) { - WRITE_ONCE(u->oob_skb, NULL); - consume_skb(skb); - } else { - __skb_unlink(skb, &sk->sk_receive_queue); - WRITE_ONCE(u->oob_skb, NULL); - unlinked_skb = skb; - skb = skb_peek(&sk->sk_receive_queue); - } - } else if (!sock_flag(sk, SOCK_URGINLINE)) { - skb = skb_peek_next(skb, &sk->sk_receive_queue); - } + if (!unix_skb_len(skb)) { + if (copied && (!u->oob_skb || skb == u->oob_skb)) { + skb = NULL; + } else if (flags & MSG_PEEK) { + skb = skb_peek_next(skb, &sk->sk_receive_queue); + } else { + read_skb = skb; + skb = skb_peek_next(skb, &sk->sk_receive_queue); + __skb_unlink(read_skb, &sk->sk_receive_queue); } - spin_unlock(&sk->sk_receive_queue.lock); + if (!skb) + goto unlock; + } - if (unlinked_skb) { - WARN_ON_ONCE(skb_unref(unlinked_skb)); - kfree_skb(unlinked_skb); + if (skb != u->oob_skb) + goto unlock; + + if (copied) { + skb = NULL; + } else if (!(flags & MSG_PEEK)) { + WRITE_ONCE(u->oob_skb, NULL); + + if (!sock_flag(sk, SOCK_URGINLINE)) { + __skb_unlink(skb, &sk->sk_receive_queue); + unread_skb = skb; + skb = skb_peek(&sk->sk_receive_queue); } + } else if (!sock_flag(sk, SOCK_URGINLINE)) { + skb = skb_peek_next(skb, &sk->sk_receive_queue); } + +unlock: + spin_unlock(&sk->sk_receive_queue.lock); + + consume_skb(read_skb); + kfree_skb(unread_skb); + return skb; } #endif static int unix_stream_read_skb(struct sock *sk, skb_read_actor_t recv_actor) { + struct unix_sock *u = unix_sk(sk); + struct sk_buff *skb; + int err; + if (unlikely(READ_ONCE(sk->sk_state) != TCP_ESTABLISHED)) return -ENOTCONN; - return unix_read_skb(sk, recv_actor); + mutex_lock(&u->iolock); + skb = skb_recv_datagram(sk, MSG_DONTWAIT, &err); + mutex_unlock(&u->iolock); + if (!skb) + return err; + +#if IS_ENABLED(CONFIG_AF_UNIX_OOB) + if (unlikely(skb == READ_ONCE(u->oob_skb))) { + bool drop = false; + + unix_state_lock(sk); + + if (sock_flag(sk, SOCK_DEAD)) { + unix_state_unlock(sk); + kfree_skb(skb); + return -ECONNRESET; + } + + spin_lock(&sk->sk_receive_queue.lock); + if (likely(skb == u->oob_skb)) { + WRITE_ONCE(u->oob_skb, NULL); + drop = true; + } + spin_unlock(&sk->sk_receive_queue.lock); + + unix_state_unlock(sk); + + if (drop) { + kfree_skb(skb); + return -EAGAIN; + } + } +#endif + + return recv_actor(sk, skb); } static int unix_stream_read_generic(struct unix_stream_read_state *state, @@ -2703,9 +2794,8 @@ static int unix_stream_read_generic(struct unix_stream_read_state *state, skip = max(sk_peek_offset(sk, flags), 0); do { - int chunk; - bool drop_skb; struct sk_buff *skb, *last; + int chunk; redo: unix_state_lock(sk); @@ -2801,11 +2891,7 @@ unlock: } chunk = min_t(unsigned int, unix_skb_len(skb) - skip, size); - skb_get(skb); chunk = state->recv_actor(skb, skip, chunk, state); - drop_skb = !unix_skb_len(skb); - /* skb is only safe to use if !drop_skb */ - consume_skb(skb); if (chunk < 0) { if (copied == 0) copied = -EFAULT; @@ -2814,18 +2900,6 @@ unlock: copied += chunk; size -= chunk; - if (drop_skb) { - /* the skb was touched by a concurrent reader; - * we should not expect anything from this skb - * anymore and assume it invalid - we can be - * sure it was dropped from the socket queue - * - * let's report a short read - */ - err = 0; - break; - } - /* Mark read part of skb as used */ if (!(flags & MSG_PEEK)) { UNIXCB(skb).consumed += chunk; @@ -3093,12 +3167,27 @@ static int unix_ioctl(struct socket *sock, unsigned int cmd, unsigned long arg) #if IS_ENABLED(CONFIG_AF_UNIX_OOB) case SIOCATMARK: { + struct unix_sock *u = unix_sk(sk); struct sk_buff *skb; int answ = 0; + mutex_lock(&u->iolock); + skb = skb_peek(&sk->sk_receive_queue); - if (skb && skb == READ_ONCE(unix_sk(sk)->oob_skb)) - answ = 1; + if (skb) { + struct sk_buff *oob_skb = READ_ONCE(u->oob_skb); + struct sk_buff *next_skb; + + next_skb = skb_peek_next(skb, &sk->sk_receive_queue); + + if (skb == oob_skb || + (!unix_skb_len(skb) && + (!oob_skb || next_skb == oob_skb))) + answ = 1; + } + + mutex_unlock(&u->iolock); + err = put_user(answ, (int __user *)arg); } break; @@ -3595,6 +3684,7 @@ static int __net_init unix_net_init(struct net *net) for (i = 0; i < UNIX_HASH_SIZE; i++) { spin_lock_init(&net->unx.table.locks[i]); + lock_set_cmp_fn(&net->unx.table.locks[i], unix_table_lock_cmp_fn, NULL); INIT_HLIST_HEAD(&net->unx.table.buckets[i]); } diff --git a/net/unix/diag.c b/net/unix/diag.c index 937edf4afed4..9138af8b465e 100644 --- a/net/unix/diag.c +++ b/net/unix/diag.c @@ -47,9 +47,7 @@ static int sk_diag_dump_peer(struct sock *sk, struct sk_buff *nlskb) peer = unix_peer_get(sk); if (peer) { - unix_state_lock(peer); ino = sock_i_ino(peer); - unix_state_unlock(peer); sock_put(peer); return nla_put_u32(nlskb, UNIX_DIAG_PEER, ino); @@ -75,20 +73,9 @@ static int sk_diag_dump_icons(struct sock *sk, struct sk_buff *nlskb) buf = nla_data(attr); i = 0; - skb_queue_walk(&sk->sk_receive_queue, skb) { - struct sock *req, *peer; - - req = skb->sk; - /* - * The state lock is outer for the same sk's - * queue lock. With the other's queue locked it's - * OK to lock the state. - */ - unix_state_lock_nested(req, U_LOCK_DIAG); - peer = unix_sk(req)->peer; - buf[i++] = (peer ? sock_i_ino(peer) : 0); - unix_state_unlock(req); - } + skb_queue_walk(&sk->sk_receive_queue, skb) + buf[i++] = sock_i_ino(unix_peer(skb->sk)); + spin_unlock(&sk->sk_receive_queue.lock); } @@ -180,22 +167,6 @@ out_nlmsg_trim: return -EMSGSIZE; } -static int sk_diag_dump(struct sock *sk, struct sk_buff *skb, struct unix_diag_req *req, - struct user_namespace *user_ns, - u32 portid, u32 seq, u32 flags) -{ - int sk_ino; - - unix_state_lock(sk); - sk_ino = sock_i_ino(sk); - unix_state_unlock(sk); - - if (!sk_ino) - return 0; - - return sk_diag_fill(sk, skb, req, user_ns, portid, seq, flags, sk_ino); -} - static int unix_diag_dump(struct sk_buff *skb, struct netlink_callback *cb) { struct net *net = sock_net(skb->sk); @@ -213,14 +184,22 @@ static int unix_diag_dump(struct sk_buff *skb, struct netlink_callback *cb) num = 0; spin_lock(&net->unx.table.locks[slot]); sk_for_each(sk, &net->unx.table.buckets[slot]) { + int sk_ino; + if (num < s_num) goto next; + if (!(req->udiag_states & (1 << READ_ONCE(sk->sk_state)))) goto next; - if (sk_diag_dump(sk, skb, req, sk_user_ns(skb->sk), + + sk_ino = sock_i_ino(sk); + if (!sk_ino) + goto next; + + if (sk_diag_fill(sk, skb, req, sk_user_ns(skb->sk), NETLINK_CB(cb->skb).portid, cb->nlh->nlmsg_seq, - NLM_F_MULTI) < 0) { + NLM_F_MULTI, sk_ino) < 0) { spin_unlock(&net->unx.table.locks[slot]); goto done; } diff --git a/net/unix/garbage.c b/net/unix/garbage.c index dfe94a90ece4..0068e758be4d 100644 --- a/net/unix/garbage.c +++ b/net/unix/garbage.c @@ -337,23 +337,6 @@ static bool unix_vertex_dead(struct unix_vertex *vertex) return true; } -enum unix_recv_queue_lock_class { - U_RECVQ_LOCK_NORMAL, - U_RECVQ_LOCK_EMBRYO, -}; - -static void unix_collect_queue(struct unix_sock *u, struct sk_buff_head *hitlist) -{ - skb_queue_splice_init(&u->sk.sk_receive_queue, hitlist); - -#if IS_ENABLED(CONFIG_AF_UNIX_OOB) - if (u->oob_skb) { - WARN_ON_ONCE(skb_unref(u->oob_skb)); - u->oob_skb = NULL; - } -#endif -} - static void unix_collect_skb(struct list_head *scc, struct sk_buff_head *hitlist) { struct unix_vertex *vertex; @@ -375,13 +358,12 @@ static void unix_collect_skb(struct list_head *scc, struct sk_buff_head *hitlist skb_queue_walk(queue, skb) { struct sk_buff_head *embryo_queue = &skb->sk->sk_receive_queue; - /* listener -> embryo order, the inversion never happens. */ - spin_lock_nested(&embryo_queue->lock, U_RECVQ_LOCK_EMBRYO); - unix_collect_queue(unix_sk(skb->sk), hitlist); + spin_lock(&embryo_queue->lock); + skb_queue_splice_init(embryo_queue, hitlist); spin_unlock(&embryo_queue->lock); } } else { - unix_collect_queue(u, hitlist); + skb_queue_splice_init(queue, hitlist); } spin_unlock(&queue->lock); @@ -476,6 +458,7 @@ prev_vertex: } if (vertex->index == vertex->scc_index) { + struct unix_vertex *v; struct list_head scc; bool scc_dead = true; @@ -486,15 +469,15 @@ prev_vertex: */ __list_cut_position(&scc, &vertex_stack, &vertex->scc_entry); - list_for_each_entry_reverse(vertex, &scc, scc_entry) { + list_for_each_entry_reverse(v, &scc, scc_entry) { /* Don't restart DFS from this vertex in unix_walk_scc(). */ - list_move_tail(&vertex->entry, &unix_visited_vertices); + list_move_tail(&v->entry, &unix_visited_vertices); /* Mark vertex as off-stack. */ - vertex->index = unix_vertex_grouped_index; + v->index = unix_vertex_grouped_index; if (scc_dead) - scc_dead = unix_vertex_dead(vertex); + scc_dead = unix_vertex_dead(v); } if (scc_dead) diff --git a/net/unix/unix_bpf.c b/net/unix/unix_bpf.c index bd84785bf8d6..bca2d86ba97d 100644 --- a/net/unix/unix_bpf.c +++ b/net/unix/unix_bpf.c @@ -54,6 +54,9 @@ static int unix_bpf_recvmsg(struct sock *sk, struct msghdr *msg, struct sk_psock *psock; int copied; + if (flags & MSG_OOB) + return -EOPNOTSUPP; + if (!len) return 0; diff --git a/net/vmw_vsock/af_vsock.c b/net/vmw_vsock/af_vsock.c index 4b040285aa78..35681adedd9a 100644 --- a/net/vmw_vsock/af_vsock.c +++ b/net/vmw_vsock/af_vsock.c @@ -112,6 +112,7 @@ #include <net/sock.h> #include <net/af_vsock.h> #include <uapi/linux/vm_sockets.h> +#include <uapi/asm-generic/ioctls.h> static int __vsock_bind(struct sock *sk, struct sockaddr_vm *addr); static void vsock_sk_destruct(struct sock *sk); @@ -1270,28 +1271,82 @@ out: return err; } +int __vsock_dgram_recvmsg(struct socket *sock, struct msghdr *msg, + size_t len, int flags) +{ + struct sock *sk = sock->sk; + struct vsock_sock *vsk = vsock_sk(sk); + + return vsk->transport->dgram_dequeue(vsk, msg, len, flags); +} + int vsock_dgram_recvmsg(struct socket *sock, struct msghdr *msg, size_t len, int flags) { #ifdef CONFIG_BPF_SYSCALL + struct sock *sk = sock->sk; const struct proto *prot; -#endif - struct vsock_sock *vsk; - struct sock *sk; - sk = sock->sk; - vsk = vsock_sk(sk); - -#ifdef CONFIG_BPF_SYSCALL prot = READ_ONCE(sk->sk_prot); if (prot != &vsock_proto) return prot->recvmsg(sk, msg, len, flags, NULL); #endif - return vsk->transport->dgram_dequeue(vsk, msg, len, flags); + return __vsock_dgram_recvmsg(sock, msg, len, flags); } EXPORT_SYMBOL_GPL(vsock_dgram_recvmsg); +static int vsock_do_ioctl(struct socket *sock, unsigned int cmd, + int __user *arg) +{ + struct sock *sk = sock->sk; + struct vsock_sock *vsk; + int ret; + + vsk = vsock_sk(sk); + + switch (cmd) { + case SIOCOUTQ: { + ssize_t n_bytes; + + if (!vsk->transport || !vsk->transport->unsent_bytes) { + ret = -EOPNOTSUPP; + break; + } + + if (sock_type_connectible(sk->sk_type) && sk->sk_state == TCP_LISTEN) { + ret = -EINVAL; + break; + } + + n_bytes = vsk->transport->unsent_bytes(vsk); + if (n_bytes < 0) { + ret = n_bytes; + break; + } + + ret = put_user(n_bytes, arg); + break; + } + default: + ret = -ENOIOCTLCMD; + } + + return ret; +} + +static int vsock_ioctl(struct socket *sock, unsigned int cmd, + unsigned long arg) +{ + int ret; + + lock_sock(sock->sk); + ret = vsock_do_ioctl(sock, cmd, (int __user *)arg); + release_sock(sock->sk); + + return ret; +} + static const struct proto_ops vsock_dgram_ops = { .family = PF_VSOCK, .owner = THIS_MODULE, @@ -1302,7 +1357,7 @@ static const struct proto_ops vsock_dgram_ops = { .accept = sock_no_accept, .getname = vsock_getname, .poll = vsock_poll, - .ioctl = sock_no_ioctl, + .ioctl = vsock_ioctl, .listen = sock_no_listen, .shutdown = vsock_shutdown, .sendmsg = vsock_dgram_sendmsg, @@ -2174,15 +2229,12 @@ out: } int -vsock_connectible_recvmsg(struct socket *sock, struct msghdr *msg, size_t len, - int flags) +__vsock_connectible_recvmsg(struct socket *sock, struct msghdr *msg, size_t len, + int flags) { struct sock *sk; struct vsock_sock *vsk; const struct vsock_transport *transport; -#ifdef CONFIG_BPF_SYSCALL - const struct proto *prot; -#endif int err; sk = sock->sk; @@ -2233,14 +2285,6 @@ vsock_connectible_recvmsg(struct socket *sock, struct msghdr *msg, size_t len, goto out; } -#ifdef CONFIG_BPF_SYSCALL - prot = READ_ONCE(sk->sk_prot); - if (prot != &vsock_proto) { - release_sock(sk); - return prot->recvmsg(sk, msg, len, flags, NULL); - } -#endif - if (sk->sk_type == SOCK_STREAM) err = __vsock_stream_recvmsg(sk, msg, len, flags); else @@ -2250,6 +2294,22 @@ out: release_sock(sk); return err; } + +int +vsock_connectible_recvmsg(struct socket *sock, struct msghdr *msg, size_t len, + int flags) +{ +#ifdef CONFIG_BPF_SYSCALL + struct sock *sk = sock->sk; + const struct proto *prot; + + prot = READ_ONCE(sk->sk_prot); + if (prot != &vsock_proto) + return prot->recvmsg(sk, msg, len, flags, NULL); +#endif + + return __vsock_connectible_recvmsg(sock, msg, len, flags); +} EXPORT_SYMBOL_GPL(vsock_connectible_recvmsg); static int vsock_set_rcvlowat(struct sock *sk, int val) @@ -2286,7 +2346,7 @@ static const struct proto_ops vsock_stream_ops = { .accept = vsock_accept, .getname = vsock_getname, .poll = vsock_poll, - .ioctl = sock_no_ioctl, + .ioctl = vsock_ioctl, .listen = vsock_listen, .shutdown = vsock_shutdown, .setsockopt = vsock_connectible_setsockopt, @@ -2308,7 +2368,7 @@ static const struct proto_ops vsock_seqpacket_ops = { .accept = vsock_accept, .getname = vsock_getname, .poll = vsock_poll, - .ioctl = sock_no_ioctl, + .ioctl = vsock_ioctl, .listen = vsock_listen, .shutdown = vsock_shutdown, .setsockopt = vsock_connectible_setsockopt, diff --git a/net/vmw_vsock/virtio_transport.c b/net/vmw_vsock/virtio_transport.c index 43d405298857..85e423921734 100644 --- a/net/vmw_vsock/virtio_transport.c +++ b/net/vmw_vsock/virtio_transport.c @@ -94,6 +94,63 @@ out_rcu: return ret; } +/* Caller need to hold vsock->tx_lock on vq */ +static int virtio_transport_send_skb(struct sk_buff *skb, struct virtqueue *vq, + struct virtio_vsock *vsock) +{ + int ret, in_sg = 0, out_sg = 0; + struct scatterlist **sgs; + + sgs = vsock->out_sgs; + sg_init_one(sgs[out_sg], virtio_vsock_hdr(skb), + sizeof(*virtio_vsock_hdr(skb))); + out_sg++; + + if (!skb_is_nonlinear(skb)) { + if (skb->len > 0) { + sg_init_one(sgs[out_sg], skb->data, skb->len); + out_sg++; + } + } else { + struct skb_shared_info *si; + int i; + + /* If skb is nonlinear, then its buffer must contain + * only header and nothing more. Data is stored in + * the fragged part. + */ + WARN_ON_ONCE(skb_headroom(skb) != sizeof(*virtio_vsock_hdr(skb))); + + si = skb_shinfo(skb); + + for (i = 0; i < si->nr_frags; i++) { + skb_frag_t *skb_frag = &si->frags[i]; + void *va; + + /* We will use 'page_to_virt()' for the userspace page + * here, because virtio or dma-mapping layers will call + * 'virt_to_phys()' later to fill the buffer descriptor. + * We don't touch memory at "virtual" address of this page. + */ + va = page_to_virt(skb_frag_page(skb_frag)); + sg_init_one(sgs[out_sg], + va + skb_frag_off(skb_frag), + skb_frag_size(skb_frag)); + out_sg++; + } + } + + ret = virtqueue_add_sgs(vq, sgs, out_sg, in_sg, skb, GFP_KERNEL); + /* Usually this means that there is no more space available in + * the vq + */ + if (ret < 0) + return ret; + + virtio_transport_deliver_tap_pkt(skb); + return 0; +} + static void virtio_transport_send_pkt_work(struct work_struct *work) { @@ -111,66 +168,22 @@ virtio_transport_send_pkt_work(struct work_struct *work) vq = vsock->vqs[VSOCK_VQ_TX]; for (;;) { - int ret, in_sg = 0, out_sg = 0; - struct scatterlist **sgs; struct sk_buff *skb; bool reply; + int ret; skb = virtio_vsock_skb_dequeue(&vsock->send_pkt_queue); if (!skb) break; reply = virtio_vsock_skb_reply(skb); - sgs = vsock->out_sgs; - sg_init_one(sgs[out_sg], virtio_vsock_hdr(skb), - sizeof(*virtio_vsock_hdr(skb))); - out_sg++; - - if (!skb_is_nonlinear(skb)) { - if (skb->len > 0) { - sg_init_one(sgs[out_sg], skb->data, skb->len); - out_sg++; - } - } else { - struct skb_shared_info *si; - int i; - - /* If skb is nonlinear, then its buffer must contain - * only header and nothing more. Data is stored in - * the fragged part. - */ - WARN_ON_ONCE(skb_headroom(skb) != sizeof(*virtio_vsock_hdr(skb))); - si = skb_shinfo(skb); - - for (i = 0; i < si->nr_frags; i++) { - skb_frag_t *skb_frag = &si->frags[i]; - void *va; - - /* We will use 'page_to_virt()' for the userspace page - * here, because virtio or dma-mapping layers will call - * 'virt_to_phys()' later to fill the buffer descriptor. - * We don't touch memory at "virtual" address of this page. - */ - va = page_to_virt(skb_frag_page(skb_frag)); - sg_init_one(sgs[out_sg], - va + skb_frag_off(skb_frag), - skb_frag_size(skb_frag)); - out_sg++; - } - } - - ret = virtqueue_add_sgs(vq, sgs, out_sg, in_sg, skb, GFP_KERNEL); - /* Usually this means that there is no more space available in - * the vq - */ + ret = virtio_transport_send_skb(skb, vq, vsock); if (ret < 0) { virtio_vsock_skb_queue_head(&vsock->send_pkt_queue, skb); break; } - virtio_transport_deliver_tap_pkt(skb); - if (reply) { struct virtqueue *rx_vq = vsock->vqs[VSOCK_VQ_RX]; int val; @@ -195,6 +208,28 @@ out: queue_work(virtio_vsock_workqueue, &vsock->rx_work); } +/* Caller need to hold RCU for vsock. + * Returns 0 if the packet is successfully put on the vq. + */ +static int virtio_transport_send_skb_fast_path(struct virtio_vsock *vsock, struct sk_buff *skb) +{ + struct virtqueue *vq = vsock->vqs[VSOCK_VQ_TX]; + int ret; + + /* Inside RCU, can't sleep! */ + ret = mutex_trylock(&vsock->tx_lock); + if (unlikely(ret == 0)) + return -EBUSY; + + ret = virtio_transport_send_skb(skb, vq, vsock); + if (ret == 0) + virtqueue_kick(vq); + + mutex_unlock(&vsock->tx_lock); + + return ret; +} + static int virtio_transport_send_pkt(struct sk_buff *skb) { @@ -218,11 +253,20 @@ virtio_transport_send_pkt(struct sk_buff *skb) goto out_rcu; } - if (virtio_vsock_skb_reply(skb)) - atomic_inc(&vsock->queued_replies); + /* If send_pkt_queue is empty, we can safely bypass this queue + * because packet order is maintained and (try) to put the packet + * on the virtqueue using virtio_transport_send_skb_fast_path. + * If this fails we simply put the packet on the intermediate + * queue and schedule the worker. + */ + if (!skb_queue_empty_lockless(&vsock->send_pkt_queue) || + virtio_transport_send_skb_fast_path(vsock, skb)) { + if (virtio_vsock_skb_reply(skb)) + atomic_inc(&vsock->queued_replies); - virtio_vsock_skb_queue_tail(&vsock->send_pkt_queue, skb); - queue_work(virtio_vsock_workqueue, &vsock->send_pkt_work); + virtio_vsock_skb_queue_tail(&vsock->send_pkt_queue, skb); + queue_work(virtio_vsock_workqueue, &vsock->send_pkt_work); + } out_rcu: rcu_read_unlock(); @@ -311,7 +355,7 @@ static void virtio_transport_tx_work(struct work_struct *work) virtqueue_disable_cb(vq); while ((skb = virtqueue_get_buf(vq, &len)) != NULL) { - consume_skb(skb); + virtio_transport_consume_skb_sent(skb, true); added = true; } } while (!virtqueue_enable_cb(vq)); @@ -540,6 +584,8 @@ static struct virtio_transport virtio_transport = { .notify_buffer_size = virtio_transport_notify_buffer_size, .notify_set_rcvlowat = virtio_transport_notify_set_rcvlowat, + .unsent_bytes = virtio_transport_unsent_bytes, + .read_skb = virtio_transport_read_skb, }, @@ -617,20 +663,14 @@ out: static int virtio_vsock_vqs_init(struct virtio_vsock *vsock) { struct virtio_device *vdev = vsock->vdev; - static const char * const names[] = { - "rx", - "tx", - "event", - }; - vq_callback_t *callbacks[] = { - virtio_vsock_rx_done, - virtio_vsock_tx_done, - virtio_vsock_event_done, + struct virtqueue_info vqs_info[] = { + { "rx", virtio_vsock_rx_done }, + { "tx", virtio_vsock_tx_done }, + { "event", virtio_vsock_event_done }, }; int ret; - ret = virtio_find_vqs(vdev, VSOCK_VQ_MAX, vsock->vqs, callbacks, names, - NULL); + ret = virtio_find_vqs(vdev, VSOCK_VQ_MAX, vsock->vqs, vqs_info, NULL); if (ret < 0) return ret; diff --git a/net/vmw_vsock/virtio_transport_common.c b/net/vmw_vsock/virtio_transport_common.c index 16ff976a86e3..884ee128851e 100644 --- a/net/vmw_vsock/virtio_transport_common.c +++ b/net/vmw_vsock/virtio_transport_common.c @@ -463,6 +463,26 @@ void virtio_transport_inc_tx_pkt(struct virtio_vsock_sock *vvs, struct sk_buff * } EXPORT_SYMBOL_GPL(virtio_transport_inc_tx_pkt); +void virtio_transport_consume_skb_sent(struct sk_buff *skb, bool consume) +{ + struct sock *s = skb->sk; + + if (s && skb->len) { + struct vsock_sock *vs = vsock_sk(s); + struct virtio_vsock_sock *vvs; + + vvs = vs->trans; + + spin_lock_bh(&vvs->tx_lock); + vvs->bytes_unsent -= skb->len; + spin_unlock_bh(&vvs->tx_lock); + } + + if (consume) + consume_skb(skb); +} +EXPORT_SYMBOL_GPL(virtio_transport_consume_skb_sent); + u32 virtio_transport_get_credit(struct virtio_vsock_sock *vvs, u32 credit) { u32 ret; @@ -475,6 +495,7 @@ u32 virtio_transport_get_credit(struct virtio_vsock_sock *vvs, u32 credit) if (ret > credit) ret = credit; vvs->tx_cnt += ret; + vvs->bytes_unsent += ret; spin_unlock_bh(&vvs->tx_lock); return ret; @@ -488,6 +509,7 @@ void virtio_transport_put_credit(struct virtio_vsock_sock *vvs, u32 credit) spin_lock_bh(&vvs->tx_lock); vvs->tx_cnt -= credit; + vvs->bytes_unsent -= credit; spin_unlock_bh(&vvs->tx_lock); } EXPORT_SYMBOL_GPL(virtio_transport_put_credit); @@ -1090,6 +1112,19 @@ void virtio_transport_destruct(struct vsock_sock *vsk) } EXPORT_SYMBOL_GPL(virtio_transport_destruct); +ssize_t virtio_transport_unsent_bytes(struct vsock_sock *vsk) +{ + struct virtio_vsock_sock *vvs = vsk->trans; + size_t ret; + + spin_lock_bh(&vvs->tx_lock); + ret = vvs->bytes_unsent; + spin_unlock_bh(&vvs->tx_lock); + + return ret; +} +EXPORT_SYMBOL_GPL(virtio_transport_unsent_bytes); + static int virtio_transport_reset(struct vsock_sock *vsk, struct sk_buff *skb) { diff --git a/net/vmw_vsock/vsock_bpf.c b/net/vmw_vsock/vsock_bpf.c index a3c97546ab84..c42c5cc18f32 100644 --- a/net/vmw_vsock/vsock_bpf.c +++ b/net/vmw_vsock/vsock_bpf.c @@ -64,9 +64,9 @@ static int __vsock_recvmsg(struct sock *sk, struct msghdr *msg, size_t len, int int err; if (sk->sk_type == SOCK_STREAM || sk->sk_type == SOCK_SEQPACKET) - err = vsock_connectible_recvmsg(sock, msg, len, flags); + err = __vsock_connectible_recvmsg(sock, msg, len, flags); else if (sk->sk_type == SOCK_DGRAM) - err = vsock_dgram_recvmsg(sock, msg, len, flags); + err = __vsock_dgram_recvmsg(sock, msg, len, flags); else err = -EPROTOTYPE; diff --git a/net/vmw_vsock/vsock_loopback.c b/net/vmw_vsock/vsock_loopback.c index 6dea6119f5b2..6e78927a598e 100644 --- a/net/vmw_vsock/vsock_loopback.c +++ b/net/vmw_vsock/vsock_loopback.c @@ -98,6 +98,8 @@ static struct virtio_transport loopback_transport = { .notify_buffer_size = virtio_transport_notify_buffer_size, .notify_set_rcvlowat = virtio_transport_notify_set_rcvlowat, + .unsent_bytes = virtio_transport_unsent_bytes, + .read_skb = virtio_transport_read_skb, }, @@ -123,6 +125,10 @@ static void vsock_loopback_work(struct work_struct *work) spin_unlock_bh(&vsock->pkt_queue.lock); while ((skb = __skb_dequeue(&pkts))) { + /* Decrement the bytes_unsent counter without deallocating skb + * It is freed by the receiver. + */ + virtio_transport_consume_skb_sent(skb, false); virtio_transport_deliver_tap_pkt(skb); virtio_transport_recv_pkt(&loopback_transport, skb); } diff --git a/net/wireless/chan.c b/net/wireless/chan.c index 3414b2c3abcc..e579d7e1425f 100644 --- a/net/wireless/chan.c +++ b/net/wireless/chan.c @@ -263,6 +263,37 @@ static int cfg80211_chandef_get_width(const struct cfg80211_chan_def *c) return nl80211_chan_width_to_mhz(c->width); } +static bool cfg80211_valid_center_freq(u32 center, + enum nl80211_chan_width width) +{ + int bw; + int step; + + /* We only do strict verification on 6 GHz */ + if (center < 5955 || center > 7115) + return true; + + bw = nl80211_chan_width_to_mhz(width); + if (bw < 0) + return false; + + /* Validate that the channels bw is entirely within the 6 GHz band */ + if (center - bw / 2 < 5945 || center + bw / 2 > 7125) + return false; + + /* With 320 MHz the permitted channels overlap */ + if (bw == 320) + step = 160; + else + step = bw; + + /* + * Valid channels are packed from lowest frequency towards higher ones. + * So test that the lower frequency alignes with one of these steps. + */ + return (center - bw / 2 - 5945) % step == 0; +} + bool cfg80211_chandef_valid(const struct cfg80211_chan_def *chandef) { u32 control_freq, oper_freq; @@ -374,6 +405,13 @@ bool cfg80211_chandef_valid(const struct cfg80211_chan_def *chandef) return false; } + if (!cfg80211_valid_center_freq(chandef->center_freq1, chandef->width)) + return false; + + if (chandef->width == NL80211_CHAN_WIDTH_80P80 && + !cfg80211_valid_center_freq(chandef->center_freq2, chandef->width)) + return false; + /* channel 14 is only for IEEE 802.11b */ if (chandef->center_freq1 == 2484 && chandef->width != NL80211_CHAN_WIDTH_20_NOHT) @@ -1145,7 +1183,8 @@ EXPORT_SYMBOL(cfg80211_chandef_dfs_cac_time); static bool cfg80211_secondary_chans_ok(struct wiphy *wiphy, u32 center_freq, u32 bandwidth, - u32 prohibited_flags, bool monitor) + u32 prohibited_flags, + u32 permitting_flags) { struct ieee80211_channel *c; u32 freq, start_freq, end_freq; @@ -1157,7 +1196,7 @@ static bool cfg80211_secondary_chans_ok(struct wiphy *wiphy, c = ieee80211_get_channel_khz(wiphy, freq); if (!c) return false; - if (monitor && c->flags & IEEE80211_CHAN_CAN_MONITOR) + if (c->flags & permitting_flags) continue; if (c->flags & prohibited_flags) return false; @@ -1221,7 +1260,8 @@ static bool cfg80211_edmg_usable(struct wiphy *wiphy, u8 edmg_channels, bool _cfg80211_chandef_usable(struct wiphy *wiphy, const struct cfg80211_chan_def *chandef, - u32 prohibited_flags, bool monitor) + u32 prohibited_flags, + u32 permitting_flags) { struct ieee80211_sta_ht_cap *ht_cap; struct ieee80211_sta_vht_cap *vht_cap; @@ -1383,22 +1423,23 @@ bool _cfg80211_chandef_usable(struct wiphy *wiphy, if (!cfg80211_secondary_chans_ok(wiphy, ieee80211_chandef_to_khz(chandef), - width, prohibited_flags, monitor)) + width, prohibited_flags, + permitting_flags)) return false; if (!chandef->center_freq2) return true; return cfg80211_secondary_chans_ok(wiphy, MHZ_TO_KHZ(chandef->center_freq2), - width, prohibited_flags, monitor); + width, prohibited_flags, + permitting_flags); } bool cfg80211_chandef_usable(struct wiphy *wiphy, const struct cfg80211_chan_def *chandef, u32 prohibited_flags) { - return _cfg80211_chandef_usable(wiphy, chandef, prohibited_flags, - false); + return _cfg80211_chandef_usable(wiphy, chandef, prohibited_flags, 0); } EXPORT_SYMBOL(cfg80211_chandef_usable); @@ -1520,49 +1561,50 @@ static bool cfg80211_ir_permissive_chan(struct wiphy *wiphy, static bool _cfg80211_reg_can_beacon(struct wiphy *wiphy, struct cfg80211_chan_def *chandef, enum nl80211_iftype iftype, - bool check_no_ir) + u32 prohibited_flags, + u32 permitting_flags) { - bool res; - u32 prohibited_flags = IEEE80211_CHAN_DISABLED; + bool res, check_radar; int dfs_required; - trace_cfg80211_reg_can_beacon(wiphy, chandef, iftype, check_no_ir); + trace_cfg80211_reg_can_beacon(wiphy, chandef, iftype, + prohibited_flags, + permitting_flags); - if (check_no_ir) - prohibited_flags |= IEEE80211_CHAN_NO_IR; + if (!_cfg80211_chandef_usable(wiphy, chandef, + IEEE80211_CHAN_DISABLED, 0)) + return false; dfs_required = cfg80211_chandef_dfs_required(wiphy, chandef, iftype); - if (dfs_required != 0) - prohibited_flags |= IEEE80211_CHAN_RADAR; + check_radar = dfs_required != 0; if (dfs_required > 0 && cfg80211_chandef_dfs_available(wiphy, chandef)) { /* We can skip IEEE80211_CHAN_NO_IR if chandef dfs available */ - prohibited_flags = IEEE80211_CHAN_DISABLED; + prohibited_flags &= ~IEEE80211_CHAN_NO_IR; + check_radar = false; } - res = cfg80211_chandef_usable(wiphy, chandef, prohibited_flags); + if (check_radar && + !_cfg80211_chandef_usable(wiphy, chandef, + IEEE80211_CHAN_RADAR, 0)) + return false; + + res = _cfg80211_chandef_usable(wiphy, chandef, + prohibited_flags, + permitting_flags); trace_cfg80211_return_bool(res); return res; } -bool cfg80211_reg_can_beacon(struct wiphy *wiphy, - struct cfg80211_chan_def *chandef, - enum nl80211_iftype iftype) -{ - return _cfg80211_reg_can_beacon(wiphy, chandef, iftype, true); -} -EXPORT_SYMBOL(cfg80211_reg_can_beacon); - -bool cfg80211_reg_can_beacon_relax(struct wiphy *wiphy, - struct cfg80211_chan_def *chandef, - enum nl80211_iftype iftype) +bool cfg80211_reg_check_beaconing(struct wiphy *wiphy, + struct cfg80211_chan_def *chandef, + struct cfg80211_beaconing_check_config *cfg) { struct cfg80211_registered_device *rdev = wiphy_to_rdev(wiphy); - bool check_no_ir; - - lockdep_assert_held(&rdev->wiphy.mtx); + u32 permitting_flags = 0; + bool check_no_ir = true; /* * Under certain conditions suggested by some regulatory bodies a @@ -1570,12 +1612,20 @@ bool cfg80211_reg_can_beacon_relax(struct wiphy *wiphy, * only if such relaxations are not enabled and the conditions are not * met. */ - check_no_ir = !cfg80211_ir_permissive_chan(wiphy, iftype, - chandef->chan); + if (cfg->relax) { + lockdep_assert_held(&rdev->wiphy.mtx); + check_no_ir = !cfg80211_ir_permissive_chan(wiphy, cfg->iftype, + chandef->chan); + } + + if (cfg->reg_power == IEEE80211_REG_VLP_AP) + permitting_flags |= IEEE80211_CHAN_ALLOW_6GHZ_VLP_AP; - return _cfg80211_reg_can_beacon(wiphy, chandef, iftype, check_no_ir); + return _cfg80211_reg_can_beacon(wiphy, chandef, cfg->iftype, + check_no_ir ? IEEE80211_CHAN_NO_IR : 0, + permitting_flags); } -EXPORT_SYMBOL(cfg80211_reg_can_beacon_relax); +EXPORT_SYMBOL(cfg80211_reg_check_beaconing); int cfg80211_set_monitor_channel(struct cfg80211_registered_device *rdev, struct cfg80211_chan_def *chandef) diff --git a/net/wireless/core.c b/net/wireless/core.c index 4b1f45e3070e..661adfc77644 100644 --- a/net/wireless/core.c +++ b/net/wireless/core.c @@ -165,11 +165,11 @@ int cfg80211_switch_netns(struct cfg80211_registered_device *rdev, list_for_each_entry(wdev, &rdev->wiphy.wdev_list, list) { if (!wdev->netdev) continue; - wdev->netdev->features &= ~NETIF_F_NETNS_LOCAL; + wdev->netdev->netns_local = false; err = dev_change_net_namespace(wdev->netdev, net, "wlan%d"); if (err) break; - wdev->netdev->features |= NETIF_F_NETNS_LOCAL; + wdev->netdev->netns_local = true; } if (err) { @@ -181,11 +181,11 @@ int cfg80211_switch_netns(struct cfg80211_registered_device *rdev, list) { if (!wdev->netdev) continue; - wdev->netdev->features &= ~NETIF_F_NETNS_LOCAL; + wdev->netdev->netns_local = false; err = dev_change_net_namespace(wdev->netdev, net, "wlan%d"); WARN_ON(err); - wdev->netdev->features |= NETIF_F_NETNS_LOCAL; + wdev->netdev->netns_local = true; } return err; @@ -421,6 +421,8 @@ static void cfg80211_wiphy_work(struct work_struct *work) rdev = container_of(work, struct cfg80211_registered_device, wiphy_work); + trace_wiphy_work_worker_start(&rdev->wiphy); + wiphy_lock(&rdev->wiphy); if (rdev->suspended) goto out; @@ -434,6 +436,7 @@ static void cfg80211_wiphy_work(struct work_struct *work) queue_work(system_unbound_wq, work); spin_unlock_irq(&rdev->wiphy_work_lock); + trace_wiphy_work_run(&rdev->wiphy, wk); wk->func(&rdev->wiphy, wk); } else { spin_unlock_irq(&rdev->wiphy_work_lock); @@ -1066,6 +1069,7 @@ void cfg80211_process_wiphy_works(struct cfg80211_registered_device *rdev, list_del_init(&wk->entry); spin_unlock_irqrestore(&rdev->wiphy_work_lock, flags); + trace_wiphy_work_run(&rdev->wiphy, wk); wk->func(&rdev->wiphy, wk); spin_lock_irqsave(&rdev->wiphy_work_lock, flags); @@ -1141,7 +1145,8 @@ void wiphy_unregister(struct wiphy *wiphy) flush_work(&rdev->background_cac_abort_wk); cfg80211_rdev_free_wowlan(rdev); - cfg80211_rdev_free_coalesce(rdev); + cfg80211_free_coalesce(rdev->coalesce); + rdev->coalesce = NULL; } EXPORT_SYMBOL(wiphy_unregister); @@ -1468,7 +1473,7 @@ static int cfg80211_netdev_notifier_call(struct notifier_block *nb, SET_NETDEV_DEVTYPE(dev, &wiphy_type); wdev->netdev = dev; /* can only change netns with wiphy */ - dev->features |= NETIF_F_NETNS_LOCAL; + dev->netns_local = true; cfg80211_init_wdev(wdev); break; @@ -1610,6 +1615,8 @@ void wiphy_work_queue(struct wiphy *wiphy, struct wiphy_work *work) struct cfg80211_registered_device *rdev = wiphy_to_rdev(wiphy); unsigned long flags; + trace_wiphy_work_queue(wiphy, work); + spin_lock_irqsave(&rdev->wiphy_work_lock, flags); if (list_empty(&work->entry)) list_add_tail(&work->entry, &rdev->wiphy_work_list); @@ -1626,6 +1633,8 @@ void wiphy_work_cancel(struct wiphy *wiphy, struct wiphy_work *work) lockdep_assert_held(&wiphy->mtx); + trace_wiphy_work_cancel(wiphy, work); + spin_lock_irqsave(&rdev->wiphy_work_lock, flags); if (!list_empty(&work->entry)) list_del_init(&work->entry); @@ -1639,6 +1648,8 @@ void wiphy_work_flush(struct wiphy *wiphy, struct wiphy_work *work) unsigned long flags; bool run; + trace_wiphy_work_flush(wiphy, work); + spin_lock_irqsave(&rdev->wiphy_work_lock, flags); run = !work || !list_empty(&work->entry); spin_unlock_irqrestore(&rdev->wiphy_work_lock, flags); @@ -1660,6 +1671,8 @@ void wiphy_delayed_work_queue(struct wiphy *wiphy, struct wiphy_delayed_work *dwork, unsigned long delay) { + trace_wiphy_delayed_work_queue(wiphy, &dwork->work, delay); + if (!delay) { del_timer(&dwork->timer); wiphy_work_queue(wiphy, &dwork->work); diff --git a/net/wireless/core.h b/net/wireless/core.h index 118f2f619828..3b3e3cd7027a 100644 --- a/net/wireless/core.h +++ b/net/wireless/core.h @@ -170,6 +170,12 @@ static inline int for_each_rdev_check_rtnl(void) if (for_each_rdev_check_rtnl()) {} else \ list_for_each_entry(rdev, &cfg80211_rdev_list, list) +enum bss_source_type { + BSS_SOURCE_DIRECT = 0, + BSS_SOURCE_MBSSID, + BSS_SOURCE_STA_PROFILE, +}; + struct cfg80211_internal_bss { struct list_head list; struct list_head hidden_list; @@ -191,6 +197,8 @@ struct cfg80211_internal_bss { */ u8 parent_bssid[ETH_ALEN] __aligned(2); + enum bss_source_type bss_source; + /* must be last because of priv member */ struct cfg80211_bss pub; }; @@ -494,7 +502,8 @@ bool cfg80211_wdev_on_sub_chan(struct wireless_dev *wdev, bool primary_only); bool _cfg80211_chandef_usable(struct wiphy *wiphy, const struct cfg80211_chan_def *chandef, - u32 prohibited_flags, bool monitor); + u32 prohibited_flags, + u32 permitting_flags); static inline unsigned int elapsed_jiffies_msecs(unsigned long start) { @@ -532,6 +541,10 @@ struct cfg80211_internal_bss * cfg80211_bss_update(struct cfg80211_registered_device *rdev, struct cfg80211_internal_bss *tmp, bool signal_valid, unsigned long ts); + +enum ieee80211_ap_reg_power +cfg80211_get_6ghz_power_type(const u8 *elems, size_t elems_len); + #ifdef CONFIG_CFG80211_DEVELOPER_WARNINGS #define CFG80211_DEV_WARN_ON(cond) WARN_ON(cond) #else diff --git a/net/wireless/ibss.c b/net/wireless/ibss.c index 9f02ee5f08be..1e3ed29f7cfc 100644 --- a/net/wireless/ibss.c +++ b/net/wireless/ibss.c @@ -3,7 +3,7 @@ * Some IBSS support code for cfg80211. * * Copyright 2009 Johannes Berg <johannes@sipsolutions.net> - * Copyright (C) 2020-2023 Intel Corporation + * Copyright (C) 2020-2024 Intel Corporation */ #include <linux/etherdevice.h> @@ -94,6 +94,9 @@ int __cfg80211_join_ibss(struct cfg80211_registered_device *rdev, lockdep_assert_held(&rdev->wiphy.mtx); + if (wdev->links[0].cac_started) + return -EBUSY; + if (wdev->u.ibss.ssid_len) return -EALREADY; diff --git a/net/wireless/lib80211.c b/net/wireless/lib80211.c index d66a913027e0..64c447040786 100644 --- a/net/wireless/lib80211.c +++ b/net/wireless/lib80211.c @@ -34,7 +34,7 @@ MODULE_LICENSE("GPL"); struct lib80211_crypto_alg { struct list_head list; - struct lib80211_crypto_ops *ops; + const struct lib80211_crypto_ops *ops; }; static LIST_HEAD(lib80211_crypto_algs); @@ -161,7 +161,7 @@ void lib80211_crypt_delayed_deinit(struct lib80211_crypt_info *info, } EXPORT_SYMBOL(lib80211_crypt_delayed_deinit); -int lib80211_register_crypto_ops(struct lib80211_crypto_ops *ops) +int lib80211_register_crypto_ops(const struct lib80211_crypto_ops *ops) { unsigned long flags; struct lib80211_crypto_alg *alg; @@ -183,7 +183,7 @@ int lib80211_register_crypto_ops(struct lib80211_crypto_ops *ops) } EXPORT_SYMBOL(lib80211_register_crypto_ops); -int lib80211_unregister_crypto_ops(struct lib80211_crypto_ops *ops) +int lib80211_unregister_crypto_ops(const struct lib80211_crypto_ops *ops) { struct lib80211_crypto_alg *alg; unsigned long flags; @@ -206,7 +206,7 @@ int lib80211_unregister_crypto_ops(struct lib80211_crypto_ops *ops) } EXPORT_SYMBOL(lib80211_unregister_crypto_ops); -struct lib80211_crypto_ops *lib80211_get_crypto_ops(const char *name) +const struct lib80211_crypto_ops *lib80211_get_crypto_ops(const char *name) { struct lib80211_crypto_alg *alg; unsigned long flags; @@ -234,7 +234,7 @@ static void lib80211_crypt_null_deinit(void *priv) { } -static struct lib80211_crypto_ops lib80211_crypt_null = { +static const struct lib80211_crypto_ops lib80211_crypt_null = { .name = "NULL", .init = lib80211_crypt_null_init, .deinit = lib80211_crypt_null_deinit, diff --git a/net/wireless/lib80211_crypt_ccmp.c b/net/wireless/lib80211_crypt_ccmp.c index cca5e1cf089e..5aad139130e1 100644 --- a/net/wireless/lib80211_crypt_ccmp.c +++ b/net/wireless/lib80211_crypt_ccmp.c @@ -418,7 +418,7 @@ static void lib80211_ccmp_print_stats(struct seq_file *m, void *priv) ccmp->dot11RSNAStatsCCMPDecryptErrors); } -static struct lib80211_crypto_ops lib80211_crypt_ccmp = { +static const struct lib80211_crypto_ops lib80211_crypt_ccmp = { .name = "CCMP", .init = lib80211_ccmp_init, .deinit = lib80211_ccmp_deinit, diff --git a/net/wireless/lib80211_crypt_tkip.c b/net/wireless/lib80211_crypt_tkip.c index 5c8cdf7681e3..63e68e5e121e 100644 --- a/net/wireless/lib80211_crypt_tkip.c +++ b/net/wireless/lib80211_crypt_tkip.c @@ -705,7 +705,7 @@ static void lib80211_tkip_print_stats(struct seq_file *m, void *priv) tkip->dot11RSNAStatsTKIPLocalMICFailures); } -static struct lib80211_crypto_ops lib80211_crypt_tkip = { +static const struct lib80211_crypto_ops lib80211_crypt_tkip = { .name = "TKIP", .init = lib80211_tkip_init, .deinit = lib80211_tkip_deinit, diff --git a/net/wireless/lib80211_crypt_wep.c b/net/wireless/lib80211_crypt_wep.c index 6ab9957b8f96..3b148c7bef85 100644 --- a/net/wireless/lib80211_crypt_wep.c +++ b/net/wireless/lib80211_crypt_wep.c @@ -226,7 +226,7 @@ static void lib80211_wep_print_stats(struct seq_file *m, void *priv) seq_printf(m, "key[%d] alg=WEP len=%d\n", wep->key_idx, wep->key_len); } -static struct lib80211_crypto_ops lib80211_crypt_wep = { +static const struct lib80211_crypto_ops lib80211_crypt_wep = { .name = "WEP", .init = lib80211_wep_init, .deinit = lib80211_wep_deinit, diff --git a/net/wireless/mesh.c b/net/wireless/mesh.c index 83306979fbe2..2c6654075ca9 100644 --- a/net/wireless/mesh.c +++ b/net/wireless/mesh.c @@ -1,7 +1,7 @@ // SPDX-License-Identifier: GPL-2.0 /* * Portions - * Copyright (C) 2022-2023 Intel Corporation + * Copyright (C) 2022-2024 Intel Corporation */ #include <linux/ieee80211.h> #include <linux/export.h> @@ -127,6 +127,9 @@ int __cfg80211_join_mesh(struct cfg80211_registered_device *rdev, if (!rdev->ops->join_mesh) return -EOPNOTSUPP; + if (wdev->links[0].cac_started) + return -EBUSY; + if (!setup->chandef.chan) { /* if no channel explicitly given, use preset channel */ setup->chandef = wdev->u.mesh.preset_chandef; diff --git a/net/wireless/mlme.c b/net/wireless/mlme.c index 4052041a19ea..4dac81854721 100644 --- a/net/wireless/mlme.c +++ b/net/wireless/mlme.c @@ -1110,26 +1110,28 @@ EXPORT_SYMBOL(__cfg80211_radar_event); void cfg80211_cac_event(struct net_device *netdev, const struct cfg80211_chan_def *chandef, - enum nl80211_radar_event event, gfp_t gfp) + enum nl80211_radar_event event, gfp_t gfp, + unsigned int link_id) { struct wireless_dev *wdev = netdev->ieee80211_ptr; struct wiphy *wiphy = wdev->wiphy; struct cfg80211_registered_device *rdev = wiphy_to_rdev(wiphy); unsigned long timeout; - /* not yet supported */ - if (wdev->valid_links) + if (WARN_ON(wdev->valid_links && + !(wdev->valid_links & BIT(link_id)))) return; - trace_cfg80211_cac_event(netdev, event); + trace_cfg80211_cac_event(netdev, event, link_id); - if (WARN_ON(!wdev->cac_started && event != NL80211_RADAR_CAC_STARTED)) + if (WARN_ON(!wdev->links[link_id].cac_started && + event != NL80211_RADAR_CAC_STARTED)) return; switch (event) { case NL80211_RADAR_CAC_FINISHED: - timeout = wdev->cac_start_time + - msecs_to_jiffies(wdev->cac_time_ms); + timeout = wdev->links[link_id].cac_start_time + + msecs_to_jiffies(wdev->links[link_id].cac_time_ms); WARN_ON(!time_after_eq(jiffies, timeout)); cfg80211_set_dfs_state(wiphy, chandef, NL80211_DFS_AVAILABLE); memcpy(&rdev->cac_done_chandef, chandef, @@ -1138,10 +1140,10 @@ void cfg80211_cac_event(struct net_device *netdev, cfg80211_sched_dfs_chan_update(rdev); fallthrough; case NL80211_RADAR_CAC_ABORTED: - wdev->cac_started = false; + wdev->links[link_id].cac_started = false; break; case NL80211_RADAR_CAC_STARTED: - wdev->cac_started = true; + wdev->links[link_id].cac_started = true; break; default: WARN_ON(1); diff --git a/net/wireless/nl80211.c b/net/wireless/nl80211.c index 3c0bca4238d3..9ab777e0bd4d 100644 --- a/net/wireless/nl80211.c +++ b/net/wireless/nl80211.c @@ -315,8 +315,7 @@ nl80211_pmsr_ftm_req_attr_policy[NL80211_PMSR_FTM_REQ_ATTR_MAX + 1] = { [NL80211_PMSR_FTM_REQ_ATTR_BURST_PERIOD] = { .type = NLA_U16 }, [NL80211_PMSR_FTM_REQ_ATTR_BURST_DURATION] = NLA_POLICY_MAX(NLA_U8, 15), - [NL80211_PMSR_FTM_REQ_ATTR_FTMS_PER_BURST] = - NLA_POLICY_MAX(NLA_U8, 31), + [NL80211_PMSR_FTM_REQ_ATTR_FTMS_PER_BURST] = { .type = NLA_U8 }, [NL80211_PMSR_FTM_REQ_ATTR_NUM_FTMR_RETRIES] = { .type = NLA_U8 }, [NL80211_PMSR_FTM_REQ_ATTR_REQUEST_LCI] = { .type = NLA_FLAG }, [NL80211_PMSR_FTM_REQ_ATTR_REQUEST_CIVICLOC] = { .type = NLA_FLAG }, @@ -468,6 +467,10 @@ static const struct netlink_range_validation nl80211_punct_bitmap_range = { .max = 0xffff, }; +static const struct netlink_range_validation q_range = { + .max = INT_MAX, +}; + static const struct nla_policy nl80211_policy[NUM_NL80211_ATTR] = { [0] = { .strict_start_type = NL80211_ATTR_HE_OBSS_PD }, [NL80211_ATTR_WIPHY] = { .type = NLA_U32 }, @@ -754,7 +757,7 @@ static const struct nla_policy nl80211_policy[NUM_NL80211_ATTR] = { [NL80211_ATTR_TXQ_LIMIT] = { .type = NLA_U32 }, [NL80211_ATTR_TXQ_MEMORY_LIMIT] = { .type = NLA_U32 }, - [NL80211_ATTR_TXQ_QUANTUM] = { .type = NLA_U32 }, + [NL80211_ATTR_TXQ_QUANTUM] = NLA_POLICY_FULL_RANGE(NLA_U32, &q_range), [NL80211_ATTR_HE_CAPABILITY] = NLA_POLICY_VALIDATE_FN(NLA_BINARY, validate_he_capa, NL80211_HE_MAX_CAPABILITY_LEN), @@ -1204,6 +1207,12 @@ static int nl80211_msg_put_channel(struct sk_buff *msg, struct wiphy *wiphy, if ((chan->flags & IEEE80211_CHAN_NO_6GHZ_AFC_CLIENT) && nla_put_flag(msg, NL80211_FREQUENCY_ATTR_NO_6GHZ_AFC_CLIENT)) goto nla_put_failure; + if ((chan->flags & IEEE80211_CHAN_CAN_MONITOR) && + nla_put_flag(msg, NL80211_FREQUENCY_ATTR_CAN_MONITOR)) + goto nla_put_failure; + if ((chan->flags & IEEE80211_CHAN_ALLOW_6GHZ_VLP_AP) && + nla_put_flag(msg, NL80211_FREQUENCY_ATTR_ALLOW_6GHZ_VLP_AP)) + goto nla_put_failure; } if (nla_put_u32(msg, NL80211_FREQUENCY_ATTR_MAX_TX_POWER, @@ -1622,71 +1631,87 @@ nla_put_failure: return -ENOBUFS; } -static int nl80211_put_iface_combinations(struct wiphy *wiphy, - struct sk_buff *msg, - bool large) +static int nl80211_put_ifcomb_data(struct sk_buff *msg, bool large, int idx, + const struct ieee80211_iface_combination *c, + u16 nested) { - struct nlattr *nl_combis; - int i, j; + struct nlattr *nl_combi, *nl_limits; + int i; - nl_combis = nla_nest_start_noflag(msg, - NL80211_ATTR_INTERFACE_COMBINATIONS); - if (!nl_combis) + nl_combi = nla_nest_start_noflag(msg, idx | nested); + if (!nl_combi) goto nla_put_failure; - for (i = 0; i < wiphy->n_iface_combinations; i++) { - const struct ieee80211_iface_combination *c; - struct nlattr *nl_combi, *nl_limits; + nl_limits = nla_nest_start_noflag(msg, NL80211_IFACE_COMB_LIMITS | + nested); + if (!nl_limits) + goto nla_put_failure; - c = &wiphy->iface_combinations[i]; + for (i = 0; i < c->n_limits; i++) { + struct nlattr *nl_limit; - nl_combi = nla_nest_start_noflag(msg, i + 1); - if (!nl_combi) + nl_limit = nla_nest_start_noflag(msg, i + 1); + if (!nl_limit) goto nla_put_failure; - - nl_limits = nla_nest_start_noflag(msg, - NL80211_IFACE_COMB_LIMITS); - if (!nl_limits) + if (nla_put_u32(msg, NL80211_IFACE_LIMIT_MAX, c->limits[i].max)) + goto nla_put_failure; + if (nl80211_put_iftypes(msg, NL80211_IFACE_LIMIT_TYPES, + c->limits[i].types)) goto nla_put_failure; + nla_nest_end(msg, nl_limit); + } - for (j = 0; j < c->n_limits; j++) { - struct nlattr *nl_limit; + nla_nest_end(msg, nl_limits); - nl_limit = nla_nest_start_noflag(msg, j + 1); - if (!nl_limit) - goto nla_put_failure; - if (nla_put_u32(msg, NL80211_IFACE_LIMIT_MAX, - c->limits[j].max)) - goto nla_put_failure; - if (nl80211_put_iftypes(msg, NL80211_IFACE_LIMIT_TYPES, - c->limits[j].types)) - goto nla_put_failure; - nla_nest_end(msg, nl_limit); - } + if (c->beacon_int_infra_match && + nla_put_flag(msg, NL80211_IFACE_COMB_STA_AP_BI_MATCH)) + goto nla_put_failure; + if (nla_put_u32(msg, NL80211_IFACE_COMB_NUM_CHANNELS, + c->num_different_channels) || + nla_put_u32(msg, NL80211_IFACE_COMB_MAXNUM, + c->max_interfaces)) + goto nla_put_failure; + if (large && + (nla_put_u32(msg, NL80211_IFACE_COMB_RADAR_DETECT_WIDTHS, + c->radar_detect_widths) || + nla_put_u32(msg, NL80211_IFACE_COMB_RADAR_DETECT_REGIONS, + c->radar_detect_regions))) + goto nla_put_failure; + if (c->beacon_int_min_gcd && + nla_put_u32(msg, NL80211_IFACE_COMB_BI_MIN_GCD, + c->beacon_int_min_gcd)) + goto nla_put_failure; - nla_nest_end(msg, nl_limits); + nla_nest_end(msg, nl_combi); - if (c->beacon_int_infra_match && - nla_put_flag(msg, NL80211_IFACE_COMB_STA_AP_BI_MATCH)) - goto nla_put_failure; - if (nla_put_u32(msg, NL80211_IFACE_COMB_NUM_CHANNELS, - c->num_different_channels) || - nla_put_u32(msg, NL80211_IFACE_COMB_MAXNUM, - c->max_interfaces)) - goto nla_put_failure; - if (large && - (nla_put_u32(msg, NL80211_IFACE_COMB_RADAR_DETECT_WIDTHS, - c->radar_detect_widths) || - nla_put_u32(msg, NL80211_IFACE_COMB_RADAR_DETECT_REGIONS, - c->radar_detect_regions))) - goto nla_put_failure; - if (c->beacon_int_min_gcd && - nla_put_u32(msg, NL80211_IFACE_COMB_BI_MIN_GCD, - c->beacon_int_min_gcd)) - goto nla_put_failure; + return 0; +nla_put_failure: + return -ENOBUFS; +} + +static int nl80211_put_iface_combinations(struct wiphy *wiphy, + struct sk_buff *msg, + int attr, int radio, + bool large, u16 nested) +{ + const struct ieee80211_iface_combination *c; + struct nlattr *nl_combis; + int i, n; + + nl_combis = nla_nest_start_noflag(msg, attr | nested); + if (!nl_combis) + goto nla_put_failure; - nla_nest_end(msg, nl_combi); + if (radio >= 0) { + c = wiphy->radio[0].iface_combinations; + n = wiphy->radio[0].n_iface_combinations; + } else { + c = wiphy->iface_combinations; + n = wiphy->n_iface_combinations; } + for (i = 0; i < n; i++) + if (nl80211_put_ifcomb_data(msg, large, i + 1, &c[i], nested)) + goto nla_put_failure; nla_nest_end(msg, nl_combis); @@ -2392,6 +2417,80 @@ fail: return -ENOBUFS; } +static int nl80211_put_radio(struct wiphy *wiphy, struct sk_buff *msg, int idx) +{ + const struct wiphy_radio *r = &wiphy->radio[idx]; + struct nlattr *radio, *freq; + int i; + + radio = nla_nest_start(msg, idx); + if (!radio) + return -ENOBUFS; + + if (nla_put_u32(msg, NL80211_WIPHY_RADIO_ATTR_INDEX, idx)) + goto nla_put_failure; + + for (i = 0; i < r->n_freq_range; i++) { + const struct wiphy_radio_freq_range *range = &r->freq_range[i]; + + freq = nla_nest_start(msg, NL80211_WIPHY_RADIO_ATTR_FREQ_RANGE); + if (!freq) + goto nla_put_failure; + + if (nla_put_u32(msg, NL80211_WIPHY_RADIO_FREQ_ATTR_START, + range->start_freq) || + nla_put_u32(msg, NL80211_WIPHY_RADIO_FREQ_ATTR_END, + range->end_freq)) + goto nla_put_failure; + + nla_nest_end(msg, freq); + } + + for (i = 0; i < r->n_iface_combinations; i++) + if (nl80211_put_ifcomb_data(msg, true, + NL80211_WIPHY_RADIO_ATTR_INTERFACE_COMBINATION, + &r->iface_combinations[i], + NLA_F_NESTED)) + goto nla_put_failure; + + nla_nest_end(msg, radio); + + return 0; + +nla_put_failure: + return -ENOBUFS; +} + +static int nl80211_put_radios(struct wiphy *wiphy, struct sk_buff *msg) +{ + struct nlattr *radios; + int i; + + if (!wiphy->n_radio) + return 0; + + radios = nla_nest_start(msg, NL80211_ATTR_WIPHY_RADIOS); + if (!radios) + return -ENOBUFS; + + for (i = 0; i < wiphy->n_radio; i++) + if (nl80211_put_radio(wiphy, msg, i)) + goto fail; + + nla_nest_end(msg, radios); + + if (nl80211_put_iface_combinations(wiphy, msg, + NL80211_ATTR_WIPHY_INTERFACE_COMBINATIONS, + -1, true, NLA_F_NESTED)) + return -ENOBUFS; + + return 0; + +fail: + nla_nest_cancel(msg, radios); + return -ENOBUFS; +} + struct nl80211_dump_wiphy_state { s64 filter_wiphy; long start; @@ -2687,7 +2786,9 @@ static int nl80211_send_wiphy(struct cfg80211_registered_device *rdev, goto nla_put_failure; if (nl80211_put_iface_combinations(&rdev->wiphy, msg, - state->split)) + NL80211_ATTR_INTERFACE_COMBINATIONS, + rdev->wiphy.n_radio ? 0 : -1, + state->split, 0)) goto nla_put_failure; state->split_start++; @@ -3001,6 +3102,12 @@ static int nl80211_send_wiphy(struct cfg80211_registered_device *rdev, rdev->wiphy.hw_timestamp_max_peers)) goto nla_put_failure; + state->split_start++; + break; + case 17: + if (nl80211_put_radios(&rdev->wiphy, msg)) + goto nla_put_failure; + /* done */ state->split_start = 0; break; @@ -3344,7 +3451,7 @@ static int _nl80211_parse_chandef(struct cfg80211_registered_device *rdev, if (!_cfg80211_chandef_usable(&rdev->wiphy, chandef, IEEE80211_CHAN_DISABLED, - monitor)) { + monitor ? IEEE80211_CHAN_CAN_MONITOR : 0)) { NL_SET_ERR_MSG(extack, "(extension) channel is disabled"); return -EINVAL; } @@ -3415,6 +3522,33 @@ static int __nl80211_set_channel(struct cfg80211_registered_device *rdev, if (chandef.chan != cur_chan) return -EBUSY; + /* only allow this for regular channel widths */ + switch (wdev->links[link_id].ap.chandef.width) { + case NL80211_CHAN_WIDTH_20_NOHT: + case NL80211_CHAN_WIDTH_20: + case NL80211_CHAN_WIDTH_40: + case NL80211_CHAN_WIDTH_80: + case NL80211_CHAN_WIDTH_80P80: + case NL80211_CHAN_WIDTH_160: + case NL80211_CHAN_WIDTH_320: + break; + default: + return -EINVAL; + } + + switch (chandef.width) { + case NL80211_CHAN_WIDTH_20_NOHT: + case NL80211_CHAN_WIDTH_20: + case NL80211_CHAN_WIDTH_40: + case NL80211_CHAN_WIDTH_80: + case NL80211_CHAN_WIDTH_80P80: + case NL80211_CHAN_WIDTH_160: + case NL80211_CHAN_WIDTH_320: + break; + default: + return -EINVAL; + } + result = rdev_set_ap_chanwidth(rdev, dev, link_id, &chandef); if (result) @@ -4451,10 +4585,7 @@ static void get_key_callback(void *c, struct key_params *params) struct nlattr *key; struct get_key_cookie *cookie = c; - if ((params->key && - nla_put(cookie->msg, NL80211_ATTR_KEY_DATA, - params->key_len, params->key)) || - (params->seq && + if ((params->seq && nla_put(cookie->msg, NL80211_ATTR_KEY_SEQ, params->seq_len, params->seq)) || (params->cipher && @@ -4466,10 +4597,7 @@ static void get_key_callback(void *c, struct key_params *params) if (!key) goto nla_put_failure; - if ((params->key && - nla_put(cookie->msg, NL80211_KEY_DATA, - params->key_len, params->key)) || - (params->seq && + if ((params->seq && nla_put(cookie->msg, NL80211_KEY_SEQ, params->seq_len, params->seq)) || (params->cipher && @@ -5924,6 +6052,7 @@ static int nl80211_validate_ap_phy_operation(struct cfg80211_ap_settings *params static int nl80211_start_ap(struct sk_buff *skb, struct genl_info *info) { struct cfg80211_registered_device *rdev = info->user_ptr[0]; + struct cfg80211_beaconing_check_config beacon_check = {}; unsigned int link_id = nl80211_link_id(info->attrs); struct net_device *dev = info->user_ptr[1]; struct wireless_dev *wdev = dev->ieee80211_ptr; @@ -5937,6 +6066,9 @@ static int nl80211_start_ap(struct sk_buff *skb, struct genl_info *info) if (!rdev->ops->start_ap) return -EOPNOTSUPP; + if (wdev->links[link_id].cac_started) + return -EBUSY; + if (wdev->links[link_id].ap.beacon_interval) return -EALREADY; @@ -6070,8 +6202,13 @@ static int nl80211_start_ap(struct sk_buff *skb, struct genl_info *info) goto out; } - if (!cfg80211_reg_can_beacon_relax(&rdev->wiphy, ¶ms->chandef, - wdev->iftype)) { + beacon_check.iftype = wdev->iftype; + beacon_check.relax = true; + beacon_check.reg_power = + cfg80211_get_6ghz_power_type(params->beacon.tail, + params->beacon.tail_len); + if (!cfg80211_reg_check_beaconing(&rdev->wiphy, ¶ms->chandef, + &beacon_check)) { err = -EINVAL; goto out; } @@ -6228,6 +6365,7 @@ out: static int nl80211_set_beacon(struct sk_buff *skb, struct genl_info *info) { struct cfg80211_registered_device *rdev = info->user_ptr[0]; + struct cfg80211_beaconing_check_config beacon_check = {}; unsigned int link_id = nl80211_link_id(info->attrs); struct net_device *dev = info->user_ptr[1]; struct wireless_dev *wdev = dev->ieee80211_ptr; @@ -6254,6 +6392,19 @@ static int nl80211_set_beacon(struct sk_buff *skb, struct genl_info *info) if (err) goto out; + /* recheck beaconing is permitted with possibly changed power type */ + beacon_check.iftype = wdev->iftype; + beacon_check.relax = true; + beacon_check.reg_power = + cfg80211_get_6ghz_power_type(params->beacon.tail, + params->beacon.tail_len); + if (!cfg80211_reg_check_beaconing(&rdev->wiphy, + &wdev->links[link_id].ap.chandef, + &beacon_check)) { + err = -EINVAL; + goto out; + } + attr = info->attrs[NL80211_ATTR_FILS_DISCOVERY]; if (attr) { err = nl80211_parse_fils_discovery(rdev, attr, @@ -9627,7 +9778,8 @@ nl80211_parse_sched_scan(struct wiphy *wiphy, struct wireless_dev *wdev, return ERR_PTR(-ENOMEM); if (n_ssids) - request->ssids = (void *)&request->channels[n_channels]; + request->ssids = (void *)request + + struct_size(request, channels, n_channels); request->n_ssids = n_ssids; if (ie_len) { if (n_ssids) @@ -9921,6 +10073,7 @@ static int nl80211_start_radar_detection(struct sk_buff *skb, struct cfg80211_registered_device *rdev = info->user_ptr[0]; struct net_device *dev = info->user_ptr[1]; struct wireless_dev *wdev = dev->ieee80211_ptr; + int link_id = nl80211_link_id(info->attrs); struct wiphy *wiphy = wdev->wiphy; struct cfg80211_chan_def chandef; enum nl80211_dfs_regions dfs_region; @@ -9929,6 +10082,17 @@ static int nl80211_start_radar_detection(struct sk_buff *skb, flush_delayed_work(&rdev->dfs_update_channels_wk); + switch (wdev->iftype) { + case NL80211_IFTYPE_AP: + case NL80211_IFTYPE_P2P_GO: + case NL80211_IFTYPE_MESH_POINT: + case NL80211_IFTYPE_ADHOC: + break; + default: + /* caution - see cfg80211_beaconing_iface_active() below */ + return -EINVAL; + } + wiphy_lock(wiphy); dfs_region = reg_get_dfs_region(wiphy); @@ -9959,12 +10123,20 @@ static int nl80211_start_radar_detection(struct sk_buff *skb, goto unlock; } - if (netif_carrier_ok(dev)) { - err = -EBUSY; - goto unlock; + if (cfg80211_beaconing_iface_active(wdev)) { + /* During MLO other link(s) can beacon, only the current link + * can not already beacon + */ + if (wdev->valid_links && + !wdev->links[link_id].ap.beacon_interval) { + /* nothing */ + } else { + err = -EBUSY; + goto unlock; + } } - if (wdev->cac_started) { + if (wdev->links[link_id].cac_started) { err = -EBUSY; goto unlock; } @@ -9984,12 +10156,26 @@ static int nl80211_start_radar_detection(struct sk_buff *skb, if (WARN_ON(!cac_time_ms)) cac_time_ms = IEEE80211_DFS_MIN_CAC_TIME_MS; - err = rdev_start_radar_detection(rdev, dev, &chandef, cac_time_ms); + err = rdev_start_radar_detection(rdev, dev, &chandef, cac_time_ms, + link_id); if (!err) { - wdev->links[0].ap.chandef = chandef; - wdev->cac_started = true; - wdev->cac_start_time = jiffies; - wdev->cac_time_ms = cac_time_ms; + switch (wdev->iftype) { + case NL80211_IFTYPE_AP: + case NL80211_IFTYPE_P2P_GO: + wdev->links[0].ap.chandef = chandef; + break; + case NL80211_IFTYPE_ADHOC: + wdev->u.ibss.chandef = chandef; + break; + case NL80211_IFTYPE_MESH_POINT: + wdev->u.mesh.chandef = chandef; + break; + default: + break; + } + wdev->links[link_id].cac_started = true; + wdev->links[link_id].cac_start_time = jiffies; + wdev->links[link_id].cac_time_ms = cac_time_ms; } unlock: wiphy_unlock(wiphy); @@ -10337,17 +10523,21 @@ static int nl80211_send_bss(struct sk_buff *msg, struct netlink_callback *cb, NL80211_BSS_CHAIN_SIGNAL)) goto nla_put_failure; - switch (rdev->wiphy.signal_type) { - case CFG80211_SIGNAL_TYPE_MBM: - if (nla_put_u32(msg, NL80211_BSS_SIGNAL_MBM, res->signal)) - goto nla_put_failure; - break; - case CFG80211_SIGNAL_TYPE_UNSPEC: - if (nla_put_u8(msg, NL80211_BSS_SIGNAL_UNSPEC, res->signal)) - goto nla_put_failure; - break; - default: - break; + if (intbss->bss_source != BSS_SOURCE_STA_PROFILE) { + switch (rdev->wiphy.signal_type) { + case CFG80211_SIGNAL_TYPE_MBM: + if (nla_put_u32(msg, NL80211_BSS_SIGNAL_MBM, + res->signal)) + goto nla_put_failure; + break; + case CFG80211_SIGNAL_TYPE_UNSPEC: + if (nla_put_u8(msg, NL80211_BSS_SIGNAL_UNSPEC, + res->signal)) + goto nla_put_failure; + break; + default: + break; + } } switch (wdev->iftype) { @@ -13861,9 +14051,8 @@ nla_put_failure: return -ENOBUFS; } -void cfg80211_rdev_free_coalesce(struct cfg80211_registered_device *rdev) +void cfg80211_free_coalesce(struct cfg80211_coalesce *coalesce) { - struct cfg80211_coalesce *coalesce = rdev->coalesce; int i, j; struct cfg80211_coalesce_rules *rule; @@ -13872,13 +14061,13 @@ void cfg80211_rdev_free_coalesce(struct cfg80211_registered_device *rdev) for (i = 0; i < coalesce->n_rules; i++) { rule = &coalesce->rules[i]; + if (!rule) + continue; for (j = 0; j < rule->n_patterns; j++) kfree(rule->patterns[j].mask); kfree(rule->patterns); } - kfree(coalesce->rules); kfree(coalesce); - rdev->coalesce = NULL; } static int nl80211_parse_coalesce_rule(struct cfg80211_registered_device *rdev, @@ -13976,17 +14165,16 @@ static int nl80211_set_coalesce(struct sk_buff *skb, struct genl_info *info) { struct cfg80211_registered_device *rdev = info->user_ptr[0]; const struct wiphy_coalesce_support *coalesce = rdev->wiphy.coalesce; - struct cfg80211_coalesce new_coalesce = {}; - struct cfg80211_coalesce *n_coalesce; - int err, rem_rule, n_rules = 0, i, j; + struct cfg80211_coalesce *new_coalesce; + int err, rem_rule, n_rules = 0, i; struct nlattr *rule; - struct cfg80211_coalesce_rules *tmp_rule; if (!rdev->wiphy.coalesce || !rdev->ops->set_coalesce) return -EOPNOTSUPP; if (!info->attrs[NL80211_ATTR_COALESCE_RULE]) { - cfg80211_rdev_free_coalesce(rdev); + cfg80211_free_coalesce(rdev->coalesce); + rdev->coalesce = NULL; rdev_set_coalesce(rdev, NULL); return 0; } @@ -13997,47 +14185,34 @@ static int nl80211_set_coalesce(struct sk_buff *skb, struct genl_info *info) if (n_rules > coalesce->n_rules) return -EINVAL; - new_coalesce.rules = kcalloc(n_rules, sizeof(new_coalesce.rules[0]), - GFP_KERNEL); - if (!new_coalesce.rules) + new_coalesce = kzalloc(struct_size(new_coalesce, rules, n_rules), + GFP_KERNEL); + if (!new_coalesce) return -ENOMEM; - new_coalesce.n_rules = n_rules; + new_coalesce->n_rules = n_rules; i = 0; nla_for_each_nested(rule, info->attrs[NL80211_ATTR_COALESCE_RULE], rem_rule) { err = nl80211_parse_coalesce_rule(rdev, rule, - &new_coalesce.rules[i]); + &new_coalesce->rules[i]); if (err) goto error; i++; } - err = rdev_set_coalesce(rdev, &new_coalesce); + err = rdev_set_coalesce(rdev, new_coalesce); if (err) goto error; - n_coalesce = kmemdup(&new_coalesce, sizeof(new_coalesce), GFP_KERNEL); - if (!n_coalesce) { - err = -ENOMEM; - goto error; - } - cfg80211_rdev_free_coalesce(rdev); - rdev->coalesce = n_coalesce; + cfg80211_free_coalesce(rdev->coalesce); + rdev->coalesce = new_coalesce; return 0; error: - for (i = 0; i < new_coalesce.n_rules; i++) { - tmp_rule = &new_coalesce.rules[i]; - if (!tmp_rule) - continue; - for (j = 0; j < tmp_rule->n_patterns; j++) - kfree(tmp_rule->patterns[j].mask); - kfree(tmp_rule->patterns); - } - kfree(new_coalesce.rules); + cfg80211_free_coalesce(new_coalesce); return err; } @@ -16356,10 +16531,10 @@ nl80211_set_ttlm(struct sk_buff *skb, struct genl_info *info) SELECTOR(__sel, NETDEV_UP_NOTMX, \ NL80211_FLAG_NEED_NETDEV_UP | \ NL80211_FLAG_NO_WIPHY_MTX) \ - SELECTOR(__sel, NETDEV_UP_NOTMX_NOMLO, \ + SELECTOR(__sel, NETDEV_UP_NOTMX_MLO, \ NL80211_FLAG_NEED_NETDEV_UP | \ NL80211_FLAG_NO_WIPHY_MTX | \ - NL80211_FLAG_MLO_UNSUPPORTED) \ + NL80211_FLAG_MLO_VALID_LINK_ID) \ SELECTOR(__sel, NETDEV_UP_CLEAR, \ NL80211_FLAG_NEED_NETDEV_UP | \ NL80211_FLAG_CLEAR_SKB) \ @@ -17254,7 +17429,7 @@ static const struct genl_small_ops nl80211_small_ops[] = { .flags = GENL_UNS_ADMIN_PERM, .internal_flags = IFLAGS(NL80211_FLAG_NEED_NETDEV_UP | NL80211_FLAG_NO_WIPHY_MTX | - NL80211_FLAG_MLO_UNSUPPORTED), + NL80211_FLAG_MLO_VALID_LINK_ID), }, { .cmd = NL80211_CMD_GET_PROTOCOL_FEATURES, diff --git a/net/wireless/nl80211.h b/net/wireless/nl80211.h index 6376f3a87f8a..ffaab9a92e5b 100644 --- a/net/wireless/nl80211.h +++ b/net/wireless/nl80211.h @@ -1,7 +1,7 @@ /* SPDX-License-Identifier: GPL-2.0 */ /* * Portions of this file - * Copyright (C) 2018, 2020-2022 Intel Corporation + * Copyright (C) 2018, 2020-2024 Intel Corporation */ #ifndef __NET_WIRELESS_NL80211_H #define __NET_WIRELESS_NL80211_H @@ -119,7 +119,7 @@ nl80211_radar_notify(struct cfg80211_registered_device *rdev, void nl80211_send_ap_stopped(struct wireless_dev *wdev, unsigned int link_id); -void cfg80211_rdev_free_coalesce(struct cfg80211_registered_device *rdev); +void cfg80211_free_coalesce(struct cfg80211_coalesce *coalesce); /* peer measurement */ int nl80211_pmsr_start(struct sk_buff *skb, struct genl_info *info); diff --git a/net/wireless/pmsr.c b/net/wireless/pmsr.c index c569c37da317..0396fa19bdf1 100644 --- a/net/wireless/pmsr.c +++ b/net/wireless/pmsr.c @@ -1,6 +1,6 @@ /* SPDX-License-Identifier: GPL-2.0 */ /* - * Copyright (C) 2018 - 2021, 2023 Intel Corporation + * Copyright (C) 2018 - 2021, 2023 - 2024 Intel Corporation */ #include <net/cfg80211.h> #include "core.h" @@ -148,6 +148,14 @@ static int pmsr_parse_ftm(struct cfg80211_registered_device *rdev, return -EINVAL; } + if (out->ftm.ftms_per_burst > 31 && !out->ftm.non_trigger_based && + !out->ftm.trigger_based) { + NL_SET_ERR_MSG_ATTR(info->extack, + tb[NL80211_PMSR_FTM_REQ_ATTR_FTMS_PER_BURST], + "FTM: FTMs per burst must be set lower than 31"); + return -ERANGE; + } + if ((out->ftm.trigger_based || out->ftm.non_trigger_based) && out->ftm.preamble != NL80211_PREAMBLE_HE) { NL_SET_ERR_MSG_ATTR(info->extack, diff --git a/net/wireless/rdev-ops.h b/net/wireless/rdev-ops.h index 755af47b88b9..f5adbf6b5c84 100644 --- a/net/wireless/rdev-ops.h +++ b/net/wireless/rdev-ops.h @@ -578,13 +578,11 @@ static inline int rdev_leave_ibss(struct cfg80211_registered_device *rdev, static inline int rdev_set_wiphy_params(struct cfg80211_registered_device *rdev, u32 changed) { - int ret; - - if (!rdev->ops->set_wiphy_params) - return -EOPNOTSUPP; + int ret = -EOPNOTSUPP; trace_rdev_set_wiphy_params(&rdev->wiphy, changed); - ret = rdev->ops->set_wiphy_params(&rdev->wiphy, changed); + if (rdev->ops->set_wiphy_params) + ret = rdev->ops->set_wiphy_params(&rdev->wiphy, changed); trace_rdev_return_int(&rdev->wiphy, ret); return ret; } @@ -1202,26 +1200,27 @@ static inline int rdev_start_radar_detection(struct cfg80211_registered_device *rdev, struct net_device *dev, struct cfg80211_chan_def *chandef, - u32 cac_time_ms) + u32 cac_time_ms, int link_id) { int ret = -EOPNOTSUPP; trace_rdev_start_radar_detection(&rdev->wiphy, dev, chandef, - cac_time_ms); + cac_time_ms, link_id); if (rdev->ops->start_radar_detection) ret = rdev->ops->start_radar_detection(&rdev->wiphy, dev, - chandef, cac_time_ms); + chandef, cac_time_ms, + link_id); trace_rdev_return_int(&rdev->wiphy, ret); return ret; } static inline void rdev_end_cac(struct cfg80211_registered_device *rdev, - struct net_device *dev) + struct net_device *dev, unsigned int link_id) { - trace_rdev_end_cac(&rdev->wiphy, dev); + trace_rdev_end_cac(&rdev->wiphy, dev, link_id); if (rdev->ops->end_cac) - rdev->ops->end_cac(&rdev->wiphy, dev); + rdev->ops->end_cac(&rdev->wiphy, dev, link_id); trace_rdev_return_void(&rdev->wiphy); } @@ -1425,13 +1424,11 @@ rdev_set_radar_background(struct cfg80211_registered_device *rdev, struct cfg80211_chan_def *chandef) { struct wiphy *wiphy = &rdev->wiphy; - int ret; - - if (!rdev->ops->set_radar_background) - return -EOPNOTSUPP; + int ret = -EOPNOTSUPP; trace_rdev_set_radar_background(wiphy, chandef); - ret = rdev->ops->set_radar_background(wiphy, chandef); + if (rdev->ops->set_radar_background) + ret = rdev->ops->set_radar_background(wiphy, chandef); trace_rdev_return_int(wiphy, ret); return ret; @@ -1468,13 +1465,11 @@ rdev_add_link_station(struct cfg80211_registered_device *rdev, struct net_device *dev, struct link_station_parameters *params) { - int ret; - - if (!rdev->ops->add_link_station) - return -EOPNOTSUPP; + int ret = -EOPNOTSUPP; trace_rdev_add_link_station(&rdev->wiphy, dev, params); - ret = rdev->ops->add_link_station(&rdev->wiphy, dev, params); + if (rdev->ops->add_link_station) + ret = rdev->ops->add_link_station(&rdev->wiphy, dev, params); trace_rdev_return_int(&rdev->wiphy, ret); return ret; } @@ -1484,13 +1479,11 @@ rdev_mod_link_station(struct cfg80211_registered_device *rdev, struct net_device *dev, struct link_station_parameters *params) { - int ret; - - if (!rdev->ops->mod_link_station) - return -EOPNOTSUPP; + int ret = -EOPNOTSUPP; trace_rdev_mod_link_station(&rdev->wiphy, dev, params); - ret = rdev->ops->mod_link_station(&rdev->wiphy, dev, params); + if (rdev->ops->mod_link_station) + ret = rdev->ops->mod_link_station(&rdev->wiphy, dev, params); trace_rdev_return_int(&rdev->wiphy, ret); return ret; } @@ -1500,13 +1493,11 @@ rdev_del_link_station(struct cfg80211_registered_device *rdev, struct net_device *dev, struct link_station_del_parameters *params) { - int ret; - - if (!rdev->ops->del_link_station) - return -EOPNOTSUPP; + int ret = -EOPNOTSUPP; trace_rdev_del_link_station(&rdev->wiphy, dev, params); - ret = rdev->ops->del_link_station(&rdev->wiphy, dev, params); + if (rdev->ops->del_link_station) + ret = rdev->ops->del_link_station(&rdev->wiphy, dev, params); trace_rdev_return_int(&rdev->wiphy, ret); return ret; } @@ -1517,13 +1508,11 @@ rdev_set_hw_timestamp(struct cfg80211_registered_device *rdev, struct cfg80211_set_hw_timestamp *hwts) { struct wiphy *wiphy = &rdev->wiphy; - int ret; - - if (!rdev->ops->set_hw_timestamp) - return -EOPNOTSUPP; + int ret = -EOPNOTSUPP; trace_rdev_set_hw_timestamp(wiphy, dev, hwts); - ret = rdev->ops->set_hw_timestamp(wiphy, dev, hwts); + if (rdev->ops->set_hw_timestamp) + ret = rdev->ops->set_hw_timestamp(wiphy, dev, hwts); trace_rdev_return_int(wiphy, ret); return ret; @@ -1535,15 +1524,25 @@ rdev_set_ttlm(struct cfg80211_registered_device *rdev, struct cfg80211_ttlm_params *params) { struct wiphy *wiphy = &rdev->wiphy; - int ret; - - if (!rdev->ops->set_ttlm) - return -EOPNOTSUPP; + int ret = -EOPNOTSUPP; trace_rdev_set_ttlm(wiphy, dev, params); - ret = rdev->ops->set_ttlm(wiphy, dev, params); + if (rdev->ops->set_ttlm) + ret = rdev->ops->set_ttlm(wiphy, dev, params); trace_rdev_return_int(wiphy, ret); return ret; } + +static inline u32 +rdev_get_radio_mask(struct cfg80211_registered_device *rdev, + struct net_device *dev) +{ + struct wiphy *wiphy = &rdev->wiphy; + + if (!rdev->ops->get_radio_mask) + return 0; + + return rdev->ops->get_radio_mask(wiphy, dev); +} #endif /* __CFG80211_RDEV_OPS */ diff --git a/net/wireless/reg.c b/net/wireless/reg.c index 3cef0021a3db..6489ba943a63 100644 --- a/net/wireless/reg.c +++ b/net/wireless/reg.c @@ -1600,6 +1600,8 @@ static u32 map_regdom_flags(u32 rd_flags) channel_flags |= IEEE80211_CHAN_NO_6GHZ_AFC_CLIENT; if (rd_flags & NL80211_RRF_PSD) channel_flags |= IEEE80211_CHAN_PSD; + if (rd_flags & NL80211_RRF_ALLOW_6GHZ_VLP_AP) + channel_flags |= IEEE80211_CHAN_ALLOW_6GHZ_VLP_AP; return channel_flags; } @@ -4227,6 +4229,8 @@ EXPORT_SYMBOL(regulatory_pre_cac_allowed); static void cfg80211_check_and_end_cac(struct cfg80211_registered_device *rdev) { struct wireless_dev *wdev; + unsigned int link_id; + /* If we finished CAC or received radar, we should end any * CAC running on the same channels. * the check !cfg80211_chandef_dfs_usable contain 2 options: @@ -4239,16 +4243,17 @@ static void cfg80211_check_and_end_cac(struct cfg80211_registered_device *rdev) list_for_each_entry(wdev, &rdev->wiphy.wdev_list, list) { struct cfg80211_chan_def *chandef; - if (!wdev->cac_started) - continue; + for_each_valid_link(wdev, link_id) { + if (!wdev->links[link_id].cac_started) + continue; - /* FIXME: radar detection is tied to link 0 for now */ - chandef = wdev_chandef(wdev, 0); - if (!chandef) - continue; + chandef = wdev_chandef(wdev, link_id); + if (!chandef) + continue; - if (!cfg80211_chandef_dfs_usable(&rdev->wiphy, chandef)) - rdev_end_cac(rdev, wdev->netdev); + if (!cfg80211_chandef_dfs_usable(&rdev->wiphy, chandef)) + rdev_end_cac(rdev, wdev->netdev, link_id); + } } } diff --git a/net/wireless/scan.c b/net/wireless/scan.c index 0222ede0feb6..59a90bf3c0d6 100644 --- a/net/wireless/scan.c +++ b/net/wireless/scan.c @@ -1604,7 +1604,7 @@ struct cfg80211_bss *__cfg80211_get_bss(struct wiphy *wiphy, } EXPORT_SYMBOL(__cfg80211_get_bss); -static void rb_insert_bss(struct cfg80211_registered_device *rdev, +static bool rb_insert_bss(struct cfg80211_registered_device *rdev, struct cfg80211_internal_bss *bss) { struct rb_node **p = &rdev->bss_tree.rb_node; @@ -1620,7 +1620,7 @@ static void rb_insert_bss(struct cfg80211_registered_device *rdev, if (WARN_ON(!cmp)) { /* will sort of leak this BSS */ - return; + return false; } if (cmp < 0) @@ -1631,6 +1631,7 @@ static void rb_insert_bss(struct cfg80211_registered_device *rdev, rb_link_node(&bss->rbn, parent, p); rb_insert_color(&bss->rbn, &rdev->bss_tree); + return true; } static struct cfg80211_internal_bss * @@ -1657,6 +1658,34 @@ rb_find_bss(struct cfg80211_registered_device *rdev, return NULL; } +static void cfg80211_insert_bss(struct cfg80211_registered_device *rdev, + struct cfg80211_internal_bss *bss) +{ + lockdep_assert_held(&rdev->bss_lock); + + if (!rb_insert_bss(rdev, bss)) + return; + list_add_tail(&bss->list, &rdev->bss_list); + rdev->bss_entries++; +} + +static void cfg80211_rehash_bss(struct cfg80211_registered_device *rdev, + struct cfg80211_internal_bss *bss) +{ + lockdep_assert_held(&rdev->bss_lock); + + rb_erase(&bss->rbn, &rdev->bss_tree); + if (!rb_insert_bss(rdev, bss)) { + list_del(&bss->list); + if (!list_empty(&bss->hidden_list)) + list_del_init(&bss->hidden_list); + if (!list_empty(&bss->pub.nontrans_list)) + list_del_init(&bss->pub.nontrans_list); + rdev->bss_entries--; + } + rdev->bss_generation++; +} + static bool cfg80211_combine_bsses(struct cfg80211_registered_device *rdev, struct cfg80211_internal_bss *new) { @@ -1881,6 +1910,7 @@ cfg80211_update_known_bss(struct cfg80211_registered_device *rdev, known->pub.bssid_index = new->pub.bssid_index; known->pub.use_for &= new->pub.use_for; known->pub.cannot_use_reasons = new->pub.cannot_use_reasons; + known->bss_source = new->bss_source; return true; } @@ -1969,9 +1999,7 @@ __cfg80211_bss_update(struct cfg80211_registered_device *rdev, bss_ref_get(rdev, bss_from_pub(tmp->pub.transmitted_bss)); } - list_add_tail(&new->list, &rdev->bss_list); - rdev->bss_entries++; - rb_insert_bss(rdev, new); + cfg80211_insert_bss(rdev, new); found = new; } @@ -1981,10 +2009,10 @@ __cfg80211_bss_update(struct cfg80211_registered_device *rdev, return found; free_ies: - ies = (void *)rcu_dereference(tmp->pub.beacon_ies); + ies = (void *)rcu_access_pointer(tmp->pub.beacon_ies); if (ies) kfree_rcu(ies, rcu_head); - ies = (void *)rcu_dereference(tmp->pub.proberesp_ies); + ies = (void *)rcu_access_pointer(tmp->pub.proberesp_ies); if (ies) kfree_rcu(ies, rcu_head); @@ -2122,11 +2150,7 @@ struct cfg80211_inform_single_bss_data { const u8 *ie; size_t ielen; - enum { - BSS_SOURCE_DIRECT = 0, - BSS_SOURCE_MBSSID, - BSS_SOURCE_STA_PROFILE, - } bss_source; + enum bss_source_type bss_source; /* Set if reporting bss_source != BSS_SOURCE_DIRECT */ struct cfg80211_bss *source_bss; u8 max_bssid_indicator; @@ -2136,38 +2160,53 @@ struct cfg80211_inform_single_bss_data { u64 cannot_use_reasons; }; -static bool cfg80211_6ghz_power_type_valid(const u8 *ie, size_t ielen, - const u32 flags) +enum ieee80211_ap_reg_power +cfg80211_get_6ghz_power_type(const u8 *elems, size_t elems_len) { - const struct element *tmp; + const struct ieee80211_he_6ghz_oper *he_6ghz_oper; struct ieee80211_he_operation *he_oper; + const struct element *tmp; - tmp = cfg80211_find_ext_elem(WLAN_EID_EXT_HE_OPERATION, ie, ielen); - if (tmp && tmp->datalen >= sizeof(*he_oper) + 1 && - tmp->datalen >= ieee80211_he_oper_size(tmp->data + 1)) { - const struct ieee80211_he_6ghz_oper *he_6ghz_oper; - - he_oper = (void *)&tmp->data[1]; - he_6ghz_oper = ieee80211_he_6ghz_oper(he_oper); - - if (!he_6ghz_oper) - return false; + tmp = cfg80211_find_ext_elem(WLAN_EID_EXT_HE_OPERATION, + elems, elems_len); + if (!tmp || tmp->datalen < sizeof(*he_oper) + 1 || + tmp->datalen < ieee80211_he_oper_size(tmp->data + 1)) + return IEEE80211_REG_UNSET_AP; + + he_oper = (void *)&tmp->data[1]; + he_6ghz_oper = ieee80211_he_6ghz_oper(he_oper); + + if (!he_6ghz_oper) + return IEEE80211_REG_UNSET_AP; + + switch (u8_get_bits(he_6ghz_oper->control, + IEEE80211_HE_6GHZ_OPER_CTRL_REG_INFO)) { + case IEEE80211_6GHZ_CTRL_REG_LPI_AP: + case IEEE80211_6GHZ_CTRL_REG_INDOOR_LPI_AP: + return IEEE80211_REG_LPI_AP; + case IEEE80211_6GHZ_CTRL_REG_SP_AP: + case IEEE80211_6GHZ_CTRL_REG_INDOOR_SP_AP: + return IEEE80211_REG_SP_AP; + case IEEE80211_6GHZ_CTRL_REG_VLP_AP: + return IEEE80211_REG_VLP_AP; + default: + return IEEE80211_REG_UNSET_AP; + } +} - switch (u8_get_bits(he_6ghz_oper->control, - IEEE80211_HE_6GHZ_OPER_CTRL_REG_INFO)) { - case IEEE80211_6GHZ_CTRL_REG_LPI_AP: - case IEEE80211_6GHZ_CTRL_REG_INDOOR_LPI_AP: - return true; - case IEEE80211_6GHZ_CTRL_REG_SP_AP: - case IEEE80211_6GHZ_CTRL_REG_INDOOR_SP_AP: - return !(flags & IEEE80211_CHAN_NO_6GHZ_AFC_CLIENT); - case IEEE80211_6GHZ_CTRL_REG_VLP_AP: - return !(flags & IEEE80211_CHAN_NO_6GHZ_VLP_CLIENT); - default: - return false; - } +static bool cfg80211_6ghz_power_type_valid(const u8 *elems, size_t elems_len, + const u32 flags) +{ + switch (cfg80211_get_6ghz_power_type(elems, elems_len)) { + case IEEE80211_REG_LPI_AP: + return true; + case IEEE80211_REG_SP_AP: + return !(flags & IEEE80211_CHAN_NO_6GHZ_AFC_CLIENT); + case IEEE80211_REG_VLP_AP: + return !(flags & IEEE80211_CHAN_NO_6GHZ_VLP_CLIENT); + default: + return false; } - return false; } /* Returned bss is reference counted and must be cleaned up appropriately. */ @@ -2226,6 +2265,7 @@ cfg80211_inform_single_bss_data(struct wiphy *wiphy, IEEE80211_MAX_CHAINS); tmp.pub.use_for = data->use_for; tmp.pub.cannot_use_reasons = data->cannot_use_reasons; + tmp.bss_source = data->bss_source; switch (data->bss_source) { case BSS_SOURCE_MBSSID: @@ -2865,6 +2905,9 @@ cfg80211_parse_ml_elem_sta_data(struct wiphy *wiphy, struct element *reporter_rnr = NULL; struct ieee80211_multi_link_elem *ml_elem; struct cfg80211_mle *mle; + const struct element *ssid_elem; + const u8 *ssid = NULL; + size_t ssid_len = 0; u16 control; u8 ml_common_len; u8 *new_ie = NULL; @@ -2919,6 +2962,13 @@ cfg80211_parse_ml_elem_sta_data(struct wiphy *wiphy, bss_change_count, gfp); + ssid_elem = cfg80211_find_elem(WLAN_EID_SSID, tx_data->ie, + tx_data->ielen); + if (ssid_elem) { + ssid = ssid_elem->data; + ssid_len = ssid_elem->datalen; + } + for (i = 0; i < ARRAY_SIZE(mle->sta_prof) && mle->sta_prof[i]; i++) { const struct ieee80211_neighbor_ap_info *ap_info; enum nl80211_band band; @@ -3000,6 +3050,23 @@ cfg80211_parse_ml_elem_sta_data(struct wiphy *wiphy, freq = ieee80211_channel_to_freq_khz(ap_info->channel, band); data.channel = ieee80211_get_channel_khz(wiphy, freq); + /* Skip if BSS entry generated from MBSSID or DIRECT source + * frame data available already. + */ + bss = cfg80211_get_bss(wiphy, data.channel, data.bssid, ssid, + ssid_len, IEEE80211_BSS_TYPE_ANY, + IEEE80211_PRIVACY_ANY); + if (bss) { + struct cfg80211_internal_bss *ibss = bss_from_pub(bss); + + if (data.capability == bss->capability && + ibss->bss_source != BSS_SOURCE_STA_PROFILE) { + cfg80211_put_bss(wiphy, bss); + continue; + } + cfg80211_put_bss(wiphy, bss); + } + if (use_for == NL80211_BSS_USE_FOR_MLD_LINK && !(wiphy->flags & WIPHY_FLAG_SUPPORTS_NSTR_NONPRIMARY)) { use_for = 0; @@ -3136,8 +3203,7 @@ cfg80211_inform_bss_frame_data(struct wiphy *wiphy, struct ieee80211_mgmt *mgmt, size_t len, gfp_t gfp) { - size_t min_hdr_len = offsetof(struct ieee80211_mgmt, - u.probe_resp.variable); + size_t min_hdr_len; struct ieee80211_ext *ext = NULL; enum cfg80211_bss_frame_type ftype; u16 beacon_interval; @@ -3160,10 +3226,16 @@ cfg80211_inform_bss_frame_data(struct wiphy *wiphy, if (ieee80211_is_s1g_beacon(mgmt->frame_control)) { ext = (void *) mgmt; - min_hdr_len = offsetof(struct ieee80211_ext, u.s1g_beacon); if (ieee80211_is_s1g_short_beacon(mgmt->frame_control)) min_hdr_len = offsetof(struct ieee80211_ext, u.s1g_short_beacon.variable); + else + min_hdr_len = offsetof(struct ieee80211_ext, + u.s1g_beacon.variable); + } else { + /* same for beacons */ + min_hdr_len = offsetof(struct ieee80211_mgmt, + u.probe_resp.variable); } if (WARN_ON(len < min_hdr_len)) @@ -3349,19 +3421,14 @@ void cfg80211_update_assoc_bss_entry(struct wireless_dev *wdev, if (!WARN_ON(!__cfg80211_unlink_bss(rdev, new))) rdev->bss_generation++; } - - rb_erase(&cbss->rbn, &rdev->bss_tree); - rb_insert_bss(rdev, cbss); - rdev->bss_generation++; + cfg80211_rehash_bss(rdev, cbss); list_for_each_entry_safe(nontrans_bss, tmp, &cbss->pub.nontrans_list, nontrans_list) { bss = bss_from_pub(nontrans_bss); bss->pub.channel = chan; - rb_erase(&bss->rbn, &rdev->bss_tree); - rb_insert_bss(rdev, bss); - rdev->bss_generation++; + cfg80211_rehash_bss(rdev, bss); } done: @@ -3425,8 +3492,8 @@ int cfg80211_wext_siwscan(struct net_device *dev, n_channels = ieee80211_get_num_supported_channels(wiphy); } - creq = kzalloc(sizeof(*creq) + sizeof(struct cfg80211_ssid) + - n_channels * sizeof(void *), + creq = kzalloc(struct_size(creq, channels, n_channels) + + sizeof(struct cfg80211_ssid), GFP_ATOMIC); if (!creq) return -ENOMEM; @@ -3434,7 +3501,7 @@ int cfg80211_wext_siwscan(struct net_device *dev, creq->wiphy = wiphy; creq->wdev = dev->ieee80211_ptr; /* SSIDs come after channels */ - creq->ssids = (void *)&creq->channels[n_channels]; + creq->ssids = (void *)creq + struct_size(creq, channels, n_channels); creq->n_channels = n_channels; creq->n_ssids = 1; creq->scan_start = jiffies; diff --git a/net/wireless/sme.c b/net/wireless/sme.c index a8ad55f11133..431da30817a6 100644 --- a/net/wireless/sme.c +++ b/net/wireless/sme.c @@ -5,7 +5,7 @@ * (for nl80211's connect() and wext) * * Copyright 2009 Johannes Berg <johannes@sipsolutions.net> - * Copyright (C) 2009, 2020, 2022-2023 Intel Corporation. All rights reserved. + * Copyright (C) 2009, 2020, 2022-2024 Intel Corporation. All rights reserved. * Copyright 2017 Intel Deutschland GmbH */ @@ -115,7 +115,8 @@ static int cfg80211_conn_scan(struct wireless_dev *wdev) n_channels = i; } request->n_channels = n_channels; - request->ssids = (void *)&request->channels[n_channels]; + request->ssids = (void *)request + + struct_size(request, channels, n_channels); request->n_ssids = 1; memcpy(request->ssids[0].ssid, wdev->conn->params.ssid, @@ -130,7 +131,7 @@ static int cfg80211_conn_scan(struct wireless_dev *wdev) rdev->scan_req = request; - err = rdev_scan(rdev, request); + err = cfg80211_scan(rdev); if (!err) { wdev->conn->state = CFG80211_CONN_SCANNING; nl80211_send_scan_start(rdev, wdev); @@ -1045,6 +1046,7 @@ void cfg80211_connect_done(struct net_device *dev, cfg80211_hold_bss( bss_from_pub(params->links[link].bss)); ev->cr.links[link].bss = params->links[link].bss; + ev->cr.links[link].status = params->links[link].status; if (params->links[link].addr) { ev->cr.links[link].addr = next; diff --git a/net/wireless/tests/chan.c b/net/wireless/tests/chan.c index d02258ac2dab..74bbee25085f 100644 --- a/net/wireless/tests/chan.c +++ b/net/wireless/tests/chan.c @@ -113,16 +113,16 @@ static const struct chandef_compat_case { }, }, { - .desc = "different primary 160 MHz", + .desc = "different primary 320 MHz", .c1 = { .width = NL80211_CHAN_WIDTH_320, .chan = &chan_6ghz_105, - .center_freq1 = 6475 + 150, + .center_freq1 = 6475 + 110, }, .c2 = { .width = NL80211_CHAN_WIDTH_320, .chan = &chan_6ghz_105, - .center_freq1 = 6475 - 10, + .center_freq1 = 6475 - 50, }, }, { @@ -131,12 +131,12 @@ static const struct chandef_compat_case { .c1 = { .width = NL80211_CHAN_WIDTH_160, .chan = &chan_6ghz_105, - .center_freq1 = 6475 + 70, + .center_freq1 = 6475 + 30, }, .c2 = { .width = NL80211_CHAN_WIDTH_320, .chan = &chan_6ghz_105, - .center_freq1 = 6475 - 10, + .center_freq1 = 6475 - 50, }, .compat = true, }, @@ -145,12 +145,12 @@ static const struct chandef_compat_case { .c1 = { .width = NL80211_CHAN_WIDTH_160, .chan = &chan_6ghz_105, - .center_freq1 = 6475 + 70, + .center_freq1 = 6475 + 30, }, .c2 = { .width = NL80211_CHAN_WIDTH_320, .chan = &chan_6ghz_105, - .center_freq1 = 6475 - 10, + .center_freq1 = 6475 - 50, .punctured = 0xf, }, .compat = true, @@ -160,13 +160,13 @@ static const struct chandef_compat_case { .c1 = { .width = NL80211_CHAN_WIDTH_160, .chan = &chan_6ghz_105, - .center_freq1 = 6475 + 70, + .center_freq1 = 6475 + 30, .punctured = 0xc0, }, .c2 = { .width = NL80211_CHAN_WIDTH_320, .chan = &chan_6ghz_105, - .center_freq1 = 6475 - 10, + .center_freq1 = 6475 - 50, .punctured = 0xc000, }, .compat = true, @@ -176,13 +176,13 @@ static const struct chandef_compat_case { .c1 = { .width = NL80211_CHAN_WIDTH_160, .chan = &chan_6ghz_105, - .center_freq1 = 6475 + 70, + .center_freq1 = 6475 + 30, .punctured = 0x80, }, .c2 = { .width = NL80211_CHAN_WIDTH_320, .chan = &chan_6ghz_105, - .center_freq1 = 6475 - 10, + .center_freq1 = 6475 - 50, .punctured = 0xc000, }, }, diff --git a/net/wireless/trace.h b/net/wireless/trace.h index 87986170d1b1..97c21b627791 100644 --- a/net/wireless/trace.h +++ b/net/wireless/trace.h @@ -243,6 +243,80 @@ } while (0) /************************************************************* + * wiphy work traces * + *************************************************************/ + +DECLARE_EVENT_CLASS(wiphy_work_event, + TP_PROTO(struct wiphy *wiphy, struct wiphy_work *work), + TP_ARGS(wiphy, work), + TP_STRUCT__entry( + WIPHY_ENTRY + __field(void *, instance) + __field(void *, func) + ), + TP_fast_assign( + WIPHY_ASSIGN; + __entry->instance = work; + __entry->func = work ? work->func : NULL; + ), + TP_printk(WIPHY_PR_FMT " instance=%p func=%pS", + WIPHY_PR_ARG, __entry->instance, __entry->func) +); + +DEFINE_EVENT(wiphy_work_event, wiphy_work_queue, + TP_PROTO(struct wiphy *wiphy, struct wiphy_work *work), + TP_ARGS(wiphy, work) +); + +DEFINE_EVENT(wiphy_work_event, wiphy_work_run, + TP_PROTO(struct wiphy *wiphy, struct wiphy_work *work), + TP_ARGS(wiphy, work) +); + +DEFINE_EVENT(wiphy_work_event, wiphy_work_cancel, + TP_PROTO(struct wiphy *wiphy, struct wiphy_work *work), + TP_ARGS(wiphy, work) +); + +DEFINE_EVENT(wiphy_work_event, wiphy_work_flush, + TP_PROTO(struct wiphy *wiphy, struct wiphy_work *work), + TP_ARGS(wiphy, work) +); + +TRACE_EVENT(wiphy_delayed_work_queue, + TP_PROTO(struct wiphy *wiphy, struct wiphy_work *work, + unsigned long delay), + TP_ARGS(wiphy, work, delay), + TP_STRUCT__entry( + WIPHY_ENTRY + __field(void *, instance) + __field(void *, func) + __field(unsigned long, delay) + ), + TP_fast_assign( + WIPHY_ASSIGN; + __entry->instance = work; + __entry->func = work->func; + __entry->delay = delay; + ), + TP_printk(WIPHY_PR_FMT " instance=%p func=%pS delay=%ld", + WIPHY_PR_ARG, __entry->instance, __entry->func, + __entry->delay) +); + +TRACE_EVENT(wiphy_work_worker_start, + TP_PROTO(struct wiphy *wiphy), + TP_ARGS(wiphy), + TP_STRUCT__entry( + WIPHY_ENTRY + ), + TP_fast_assign( + WIPHY_ASSIGN; + ), + TP_printk(WIPHY_PR_FMT, WIPHY_PR_ARG) +); + +/************************************************************* * rdev->ops traces * *************************************************************/ @@ -731,9 +805,22 @@ DEFINE_EVENT(wiphy_netdev_evt, rdev_flush_pmksa, TP_ARGS(wiphy, netdev) ); -DEFINE_EVENT(wiphy_netdev_evt, rdev_end_cac, - TP_PROTO(struct wiphy *wiphy, struct net_device *netdev), - TP_ARGS(wiphy, netdev) +TRACE_EVENT(rdev_end_cac, + TP_PROTO(struct wiphy *wiphy, struct net_device *netdev, + unsigned int link_id), + TP_ARGS(wiphy, netdev, link_id), + TP_STRUCT__entry( + WIPHY_ENTRY + NETDEV_ENTRY + __field(unsigned int, link_id) + ), + TP_fast_assign( + WIPHY_ASSIGN; + NETDEV_ASSIGN; + __entry->link_id = link_id; + ), + TP_printk(WIPHY_PR_FMT ", " NETDEV_PR_FMT ", link_id: %d", + WIPHY_PR_ARG, NETDEV_PR_ARG, __entry->link_id) ); DECLARE_EVENT_CLASS(station_add_change, @@ -2578,24 +2665,26 @@ TRACE_EVENT(rdev_external_auth, TRACE_EVENT(rdev_start_radar_detection, TP_PROTO(struct wiphy *wiphy, struct net_device *netdev, struct cfg80211_chan_def *chandef, - u32 cac_time_ms), - TP_ARGS(wiphy, netdev, chandef, cac_time_ms), + u32 cac_time_ms, int link_id), + TP_ARGS(wiphy, netdev, chandef, cac_time_ms, link_id), TP_STRUCT__entry( WIPHY_ENTRY NETDEV_ENTRY CHAN_DEF_ENTRY __field(u32, cac_time_ms) + __field(int, link_id) ), TP_fast_assign( WIPHY_ASSIGN; NETDEV_ASSIGN; CHAN_DEF_ASSIGN(chandef); __entry->cac_time_ms = cac_time_ms; + __entry->link_id = link_id; ), TP_printk(WIPHY_PR_FMT ", " NETDEV_PR_FMT ", " CHAN_DEF_PR_FMT - ", cac_time_ms=%u", + ", cac_time_ms=%u, link_id=%d", WIPHY_PR_ARG, NETDEV_PR_ARG, CHAN_DEF_PR_ARG, - __entry->cac_time_ms) + __entry->cac_time_ms, __entry->link_id) ); TRACE_EVENT(rdev_set_mcast_rate, @@ -2889,6 +2978,75 @@ DEFINE_EVENT(wiphy_wdev_link_evt, rdev_del_intf_link, TP_ARGS(wiphy, wdev, link_id) ); +TRACE_EVENT(rdev_del_link_station, + TP_PROTO(struct wiphy *wiphy, struct net_device *netdev, + struct link_station_del_parameters *params), + TP_ARGS(wiphy, netdev, params), + TP_STRUCT__entry( + WIPHY_ENTRY + NETDEV_ENTRY + __array(u8, mld_mac, 6) + __field(u32, link_id) + ), + TP_fast_assign( + WIPHY_ASSIGN; + NETDEV_ASSIGN; + memset(__entry->mld_mac, 0, 6); + if (params->mld_mac) + memcpy(__entry->mld_mac, params->mld_mac, 6); + __entry->link_id = params->link_id; + ), + TP_printk(WIPHY_PR_FMT ", " NETDEV_PR_FMT ", station mac: %pM" + ", link id: %u", + WIPHY_PR_ARG, NETDEV_PR_ARG, __entry->mld_mac, + __entry->link_id) +); + +TRACE_EVENT(rdev_set_hw_timestamp, + TP_PROTO(struct wiphy *wiphy, struct net_device *netdev, + struct cfg80211_set_hw_timestamp *hwts), + + TP_ARGS(wiphy, netdev, hwts), + + TP_STRUCT__entry( + WIPHY_ENTRY + NETDEV_ENTRY + MAC_ENTRY(macaddr) + __field(bool, enable) + ), + + TP_fast_assign( + WIPHY_ASSIGN; + NETDEV_ASSIGN; + MAC_ASSIGN(macaddr, hwts->macaddr); + __entry->enable = hwts->enable; + ), + + TP_printk(WIPHY_PR_FMT ", " NETDEV_PR_FMT ", mac %pM, enable: %u", + WIPHY_PR_ARG, NETDEV_PR_ARG, __entry->macaddr, + __entry->enable) +); + +TRACE_EVENT(rdev_set_ttlm, + TP_PROTO(struct wiphy *wiphy, struct net_device *netdev, + struct cfg80211_ttlm_params *params), + TP_ARGS(wiphy, netdev, params), + TP_STRUCT__entry( + WIPHY_ENTRY + NETDEV_ENTRY + __array(u8, dlink, sizeof(u16) * 8) + __array(u8, ulink, sizeof(u16) * 8) + ), + TP_fast_assign( + WIPHY_ASSIGN; + NETDEV_ASSIGN; + memcpy(__entry->dlink, params->dlink, sizeof(params->dlink)); + memcpy(__entry->ulink, params->ulink, sizeof(params->ulink)); + ), + TP_printk(WIPHY_PR_FMT ", " NETDEV_PR_FMT, + WIPHY_PR_ARG, NETDEV_PR_ARG) +); + /************************************************************* * cfg80211 exported functions traces * *************************************************************/ @@ -3246,23 +3404,26 @@ TRACE_EVENT(cfg80211_cqm_rssi_notify, TRACE_EVENT(cfg80211_reg_can_beacon, TP_PROTO(struct wiphy *wiphy, struct cfg80211_chan_def *chandef, - enum nl80211_iftype iftype, bool check_no_ir), - TP_ARGS(wiphy, chandef, iftype, check_no_ir), + enum nl80211_iftype iftype, u32 prohibited_flags, + u32 permitting_flags), + TP_ARGS(wiphy, chandef, iftype, prohibited_flags, permitting_flags), TP_STRUCT__entry( WIPHY_ENTRY CHAN_DEF_ENTRY __field(enum nl80211_iftype, iftype) - __field(bool, check_no_ir) + __field(u32, prohibited_flags) + __field(u32, permitting_flags) ), TP_fast_assign( WIPHY_ASSIGN; CHAN_DEF_ASSIGN(chandef); __entry->iftype = iftype; - __entry->check_no_ir = check_no_ir; + __entry->prohibited_flags = prohibited_flags; + __entry->permitting_flags = permitting_flags; ), - TP_printk(WIPHY_PR_FMT ", " CHAN_DEF_PR_FMT ", iftype=%d check_no_ir=%s", + TP_printk(WIPHY_PR_FMT ", " CHAN_DEF_PR_FMT ", iftype=%d prohibited_flags=0x%x permitting_flags=0x%x", WIPHY_PR_ARG, CHAN_DEF_PR_ARG, __entry->iftype, - BOOL_TO_STR(__entry->check_no_ir)) + __entry->prohibited_flags, __entry->permitting_flags) ); TRACE_EVENT(cfg80211_chandef_dfs_required, @@ -3337,18 +3498,21 @@ TRACE_EVENT(cfg80211_radar_event, ); TRACE_EVENT(cfg80211_cac_event, - TP_PROTO(struct net_device *netdev, enum nl80211_radar_event evt), - TP_ARGS(netdev, evt), + TP_PROTO(struct net_device *netdev, enum nl80211_radar_event evt, + unsigned int link_id), + TP_ARGS(netdev, evt, link_id), TP_STRUCT__entry( NETDEV_ENTRY __field(enum nl80211_radar_event, evt) + __field(unsigned int, link_id) ), TP_fast_assign( NETDEV_ASSIGN; __entry->evt = evt; + __entry->link_id = link_id; ), - TP_printk(NETDEV_PR_FMT ", event: %d", - NETDEV_PR_ARG, __entry->evt) + TP_printk(NETDEV_PR_FMT ", event: %d, link_id=%u", + NETDEV_PR_ARG, __entry->evt, __entry->link_id) ); DECLARE_EVENT_CLASS(cfg80211_rx_evt, @@ -3923,55 +4087,6 @@ DEFINE_EVENT(link_station_add_mod, rdev_mod_link_station, TP_ARGS(wiphy, netdev, params) ); -TRACE_EVENT(rdev_del_link_station, - TP_PROTO(struct wiphy *wiphy, struct net_device *netdev, - struct link_station_del_parameters *params), - TP_ARGS(wiphy, netdev, params), - TP_STRUCT__entry( - WIPHY_ENTRY - NETDEV_ENTRY - __array(u8, mld_mac, 6) - __field(u32, link_id) - ), - TP_fast_assign( - WIPHY_ASSIGN; - NETDEV_ASSIGN; - memset(__entry->mld_mac, 0, 6); - if (params->mld_mac) - memcpy(__entry->mld_mac, params->mld_mac, 6); - __entry->link_id = params->link_id; - ), - TP_printk(WIPHY_PR_FMT ", " NETDEV_PR_FMT ", station mac: %pM" - ", link id: %u", - WIPHY_PR_ARG, NETDEV_PR_ARG, __entry->mld_mac, - __entry->link_id) -); - -TRACE_EVENT(rdev_set_hw_timestamp, - TP_PROTO(struct wiphy *wiphy, struct net_device *netdev, - struct cfg80211_set_hw_timestamp *hwts), - - TP_ARGS(wiphy, netdev, hwts), - - TP_STRUCT__entry( - WIPHY_ENTRY - NETDEV_ENTRY - MAC_ENTRY(macaddr) - __field(bool, enable) - ), - - TP_fast_assign( - WIPHY_ASSIGN; - NETDEV_ASSIGN; - MAC_ASSIGN(macaddr, hwts->macaddr); - __entry->enable = hwts->enable; - ), - - TP_printk(WIPHY_PR_FMT ", " NETDEV_PR_FMT ", mac %pM, enable: %u", - WIPHY_PR_ARG, NETDEV_PR_ARG, __entry->macaddr, - __entry->enable) -); - TRACE_EVENT(cfg80211_links_removed, TP_PROTO(struct net_device *netdev, u16 link_mask), TP_ARGS(netdev, link_mask), @@ -3987,26 +4102,6 @@ TRACE_EVENT(cfg80211_links_removed, __entry->link_mask) ); -TRACE_EVENT(rdev_set_ttlm, - TP_PROTO(struct wiphy *wiphy, struct net_device *netdev, - struct cfg80211_ttlm_params *params), - TP_ARGS(wiphy, netdev, params), - TP_STRUCT__entry( - WIPHY_ENTRY - NETDEV_ENTRY - __array(u8, dlink, sizeof(u16) * 8) - __array(u8, ulink, sizeof(u16) * 8) - ), - TP_fast_assign( - WIPHY_ASSIGN; - NETDEV_ASSIGN; - memcpy(__entry->dlink, params->dlink, sizeof(params->dlink)); - memcpy(__entry->ulink, params->ulink, sizeof(params->ulink)); - ), - TP_printk(WIPHY_PR_FMT ", " NETDEV_PR_FMT, - WIPHY_PR_ARG, NETDEV_PR_ARG) -); - #endif /* !__RDEV_OPS_TRACE || TRACE_HEADER_MULTI_READ */ #undef TRACE_INCLUDE_PATH diff --git a/net/wireless/util.c b/net/wireless/util.c index 082c6f9c5416..f49b55724f83 100644 --- a/net/wireless/util.c +++ b/net/wireless/util.c @@ -998,10 +998,10 @@ unsigned int cfg80211_classify8021d(struct sk_buff *skb, * Diffserv Service Classes no update is needed: * - Standard: DF * - Low Priority Data: CS1 - * - Multimedia Streaming: AF31, AF32, AF33 * - Multimedia Conferencing: AF41, AF42, AF43 * - Network Control Traffic: CS7 * - Real-Time Interactive: CS4 + * - Signaling: CS5 */ switch (dscp >> 2) { case 10: @@ -1026,9 +1026,11 @@ unsigned int cfg80211_classify8021d(struct sk_buff *skb, /* Broadcasting video: CS3 */ ret = 4; break; - case 40: - /* Signaling: CS5 */ - ret = 5; + case 26: + case 28: + case 30: + /* Multimedia Streaming: AF31, AF32, AF33 */ + ret = 4; break; case 44: /* Voice Admit: VA */ @@ -1504,7 +1506,7 @@ static u32 cfg80211_calculate_bitrate_he(struct rate_info *rate) 5120, /* 0.833333... */ }; u32 rates_160M[3] = { 960777777, 907400000, 816666666 }; - u32 rates_969[3] = { 480388888, 453700000, 408333333 }; + u32 rates_996[3] = { 480388888, 453700000, 408333333 }; u32 rates_484[3] = { 229411111, 216666666, 195000000 }; u32 rates_242[3] = { 114711111, 108333333, 97500000 }; u32 rates_106[3] = { 40000000, 37777777, 34000000 }; @@ -1524,12 +1526,14 @@ static u32 cfg80211_calculate_bitrate_he(struct rate_info *rate) if (WARN_ON_ONCE(rate->nss < 1 || rate->nss > 8)) return 0; - if (rate->bw == RATE_INFO_BW_160) + if (rate->bw == RATE_INFO_BW_160 || + (rate->bw == RATE_INFO_BW_HE_RU && + rate->he_ru_alloc == NL80211_RATE_INFO_HE_RU_ALLOC_2x996)) result = rates_160M[rate->he_gi]; else if (rate->bw == RATE_INFO_BW_80 || (rate->bw == RATE_INFO_BW_HE_RU && rate->he_ru_alloc == NL80211_RATE_INFO_HE_RU_ALLOC_996)) - result = rates_969[rate->he_gi]; + result = rates_996[rate->he_gi]; else if (rate->bw == RATE_INFO_BW_40 || (rate->bw == RATE_INFO_BW_HE_RU && rate->he_ru_alloc == NL80211_RATE_INFO_HE_RU_ALLOC_484)) @@ -2305,13 +2309,16 @@ static int cfg80211_wdev_bi(struct wireless_dev *wdev) static void cfg80211_calculate_bi_data(struct wiphy *wiphy, u32 new_beacon_int, u32 *beacon_int_gcd, - bool *beacon_int_different) + bool *beacon_int_different, + int radio_idx) { + struct cfg80211_registered_device *rdev; struct wireless_dev *wdev; *beacon_int_gcd = 0; *beacon_int_different = false; + rdev = wiphy_to_rdev(wiphy); list_for_each_entry(wdev, &wiphy->wdev_list, list) { int wdev_bi; @@ -2319,6 +2326,11 @@ static void cfg80211_calculate_bi_data(struct wiphy *wiphy, u32 new_beacon_int, if (wdev->valid_links) continue; + /* skip wdevs not active on the given wiphy radio */ + if (radio_idx >= 0 && + !(rdev_get_radio_mask(rdev, wdev->netdev) & BIT(radio_idx))) + continue; + wdev_bi = cfg80211_wdev_bi(wdev); if (!wdev_bi) @@ -2366,14 +2378,19 @@ int cfg80211_iter_combinations(struct wiphy *wiphy, void *data), void *data) { + const struct wiphy_radio *radio = NULL; + const struct ieee80211_iface_combination *c, *cs; const struct ieee80211_regdomain *regdom; enum nl80211_dfs_regions region = 0; - int i, j, iftype; + int i, j, n, iftype; int num_interfaces = 0; u32 used_iftypes = 0; u32 beacon_int_gcd; bool beacon_int_different; + if (params->radio_idx >= 0) + radio = &wiphy->radio[params->radio_idx]; + /* * This is a bit strange, since the iteration used to rely only on * the data given by the driver, but here it now relies on context, @@ -2385,7 +2402,8 @@ int cfg80211_iter_combinations(struct wiphy *wiphy, * interfaces (while being brought up) and channel/radar data. */ cfg80211_calculate_bi_data(wiphy, params->new_beacon_int, - &beacon_int_gcd, &beacon_int_different); + &beacon_int_gcd, &beacon_int_different, + params->radio_idx); if (params->radar_detect) { rcu_read_lock(); @@ -2402,20 +2420,25 @@ int cfg80211_iter_combinations(struct wiphy *wiphy, used_iftypes |= BIT(iftype); } - for (i = 0; i < wiphy->n_iface_combinations; i++) { - const struct ieee80211_iface_combination *c; + if (radio) { + cs = radio->iface_combinations; + n = radio->n_iface_combinations; + } else { + cs = wiphy->iface_combinations; + n = wiphy->n_iface_combinations; + } + for (i = 0; i < n; i++) { struct ieee80211_iface_limit *limits; u32 all_iftypes = 0; - c = &wiphy->iface_combinations[i]; - + c = &cs[i]; if (num_interfaces > c->max_interfaces) continue; if (params->num_different_channels > c->num_different_channels) continue; - limits = kmemdup(c->limits, sizeof(limits[0]) * c->n_limits, - GFP_KERNEL); + limits = kmemdup_array(c->limits, c->n_limits, sizeof(*limits), + GFP_KERNEL); if (!limits) return -ENOMEM; @@ -2865,3 +2888,38 @@ cfg80211_get_iftype_ext_capa(struct wiphy *wiphy, enum nl80211_iftype type) return NULL; } EXPORT_SYMBOL(cfg80211_get_iftype_ext_capa); + +static bool +ieee80211_radio_freq_range_valid(const struct wiphy_radio *radio, + u32 freq, u32 width) +{ + const struct wiphy_radio_freq_range *r; + int i; + + for (i = 0; i < radio->n_freq_range; i++) { + r = &radio->freq_range[i]; + if (freq - width / 2 >= r->start_freq && + freq + width / 2 <= r->end_freq) + return true; + } + + return false; +} + +bool cfg80211_radio_chandef_valid(const struct wiphy_radio *radio, + const struct cfg80211_chan_def *chandef) +{ + u32 freq, width; + + freq = ieee80211_chandef_to_khz(chandef); + width = nl80211_chan_width_to_mhz(chandef->width); + if (!ieee80211_radio_freq_range_valid(radio, freq, width)) + return false; + + freq = MHZ_TO_KHZ(chandef->center_freq2); + if (freq && !ieee80211_radio_freq_range_valid(radio, freq, width)) + return false; + + return true; +} +EXPORT_SYMBOL(cfg80211_radio_chandef_valid); diff --git a/net/xdp/xdp_umem.c b/net/xdp/xdp_umem.c index caa340134b0e..9f76ca591d54 100644 --- a/net/xdp/xdp_umem.c +++ b/net/xdp/xdp_umem.c @@ -151,6 +151,7 @@ static int xdp_umem_account_pages(struct xdp_umem *umem) #define XDP_UMEM_FLAGS_VALID ( \ XDP_UMEM_UNALIGNED_CHUNK_FLAG | \ XDP_UMEM_TX_SW_CSUM | \ + XDP_UMEM_TX_METADATA_LEN | \ 0) static int xdp_umem_reg(struct xdp_umem *umem, struct xdp_umem_reg *mr) @@ -204,8 +205,11 @@ static int xdp_umem_reg(struct xdp_umem *umem, struct xdp_umem_reg *mr) if (headroom >= chunk_size - XDP_PACKET_HEADROOM) return -EINVAL; - if (mr->tx_metadata_len >= 256 || mr->tx_metadata_len % 8) - return -EINVAL; + if (mr->flags & XDP_UMEM_TX_METADATA_LEN) { + if (mr->tx_metadata_len >= 256 || mr->tx_metadata_len % 8) + return -EINVAL; + umem->tx_metadata_len = mr->tx_metadata_len; + } umem->size = size; umem->headroom = headroom; @@ -215,7 +219,6 @@ static int xdp_umem_reg(struct xdp_umem *umem, struct xdp_umem_reg *mr) umem->pgs = NULL; umem->user = NULL; umem->flags = mr->flags; - umem->tx_metadata_len = mr->tx_metadata_len; INIT_LIST_HEAD(&umem->xsk_dma_list); refcount_set(&umem->users, 1); diff --git a/net/xdp/xsk.c b/net/xdp/xsk.c index 7d1c0986f9bb..1140b2a120ca 100644 --- a/net/xdp/xsk.c +++ b/net/xdp/xsk.c @@ -35,8 +35,6 @@ #define TX_BATCH_SIZE 32 #define MAX_PER_SOCKET_BUDGET (TX_BATCH_SIZE) -static DEFINE_PER_CPU(struct list_head, xskmap_flush_list); - void xsk_set_rx_need_wakeup(struct xsk_buff_pool *pool) { if (pool->cached_need_wakeup & XDP_WAKEUP_RX) @@ -372,22 +370,23 @@ static int xsk_rcv(struct xdp_sock *xs, struct xdp_buff *xdp) int __xsk_map_redirect(struct xdp_sock *xs, struct xdp_buff *xdp) { - struct list_head *flush_list = this_cpu_ptr(&xskmap_flush_list); int err; err = xsk_rcv(xs, xdp); if (err) return err; - if (!xs->flush_node.prev) + if (!xs->flush_node.prev) { + struct list_head *flush_list = bpf_net_ctx_get_xskmap_flush_list(); + list_add(&xs->flush_node, flush_list); + } return 0; } -void __xsk_map_flush(void) +void __xsk_map_flush(struct list_head *flush_list) { - struct list_head *flush_list = this_cpu_ptr(&xskmap_flush_list); struct xdp_sock *xs, *tmp; list_for_each_entry_safe(xs, tmp, flush_list, flush_node) { @@ -396,16 +395,6 @@ void __xsk_map_flush(void) } } -#ifdef CONFIG_DEBUG_NET -bool xsk_map_check_flush(void) -{ - if (list_empty(this_cpu_ptr(&xskmap_flush_list))) - return false; - __xsk_map_flush(); - return true; -} -#endif - void xsk_tx_completed(struct xsk_buff_pool *pool, u32 nb_entries) { xskq_prod_submit_n(pool->cq, nb_entries); @@ -1331,14 +1320,6 @@ struct xdp_umem_reg_v1 { __u32 headroom; }; -struct xdp_umem_reg_v2 { - __u64 addr; /* Start of packet data area */ - __u64 len; /* Length of packet data area */ - __u32 chunk_size; - __u32 headroom; - __u32 flags; -}; - static int xsk_setsockopt(struct socket *sock, int level, int optname, sockptr_t optval, unsigned int optlen) { @@ -1382,10 +1363,19 @@ static int xsk_setsockopt(struct socket *sock, int level, int optname, if (optlen < sizeof(struct xdp_umem_reg_v1)) return -EINVAL; - else if (optlen < sizeof(struct xdp_umem_reg_v2)) - mr_size = sizeof(struct xdp_umem_reg_v1); else if (optlen < sizeof(mr)) - mr_size = sizeof(struct xdp_umem_reg_v2); + mr_size = sizeof(struct xdp_umem_reg_v1); + + BUILD_BUG_ON(sizeof(struct xdp_umem_reg_v1) >= sizeof(struct xdp_umem_reg)); + + /* Make sure the last field of the struct doesn't have + * uninitialized padding. All padding has to be explicit + * and has to be set to zero by the userspace to make + * struct xdp_umem_reg extensible in the future. + */ + BUILD_BUG_ON(offsetof(struct xdp_umem_reg, tx_metadata_len) + + sizeof_field(struct xdp_umem_reg, tx_metadata_len) != + sizeof(struct xdp_umem_reg)); if (copy_from_sockptr(&mr, optval, mr_size)) return -EFAULT; @@ -1772,7 +1762,7 @@ static struct pernet_operations xsk_net_ops = { static int __init xsk_init(void) { - int err, cpu; + int err; err = proto_register(&xsk_proto, 0 /* no slab */); if (err) @@ -1790,8 +1780,6 @@ static int __init xsk_init(void) if (err) goto out_pernet; - for_each_possible_cpu(cpu) - INIT_LIST_HEAD(&per_cpu(xskmap_flush_list, cpu)); return 0; out_pernet: diff --git a/net/xdp/xsk_buff_pool.c b/net/xdp/xsk_buff_pool.c index c0e0204b9630..521a2938e50a 100644 --- a/net/xdp/xsk_buff_pool.c +++ b/net/xdp/xsk_buff_pool.c @@ -211,6 +211,11 @@ int xp_assign_dev(struct xsk_buff_pool *pool, goto err_unreg_pool; } + if (dev_get_min_mp_channel_count(netdev)) { + err = -EBUSY; + goto err_unreg_pool; + } + bpf.command = XDP_SETUP_XSK_POOL; bpf.xsk.pool = pool; bpf.xsk.queue_id = queue_id; @@ -623,20 +628,31 @@ static u32 xp_alloc_reused(struct xsk_buff_pool *pool, struct xdp_buff **xdp, u3 return nb_entries; } -u32 xp_alloc_batch(struct xsk_buff_pool *pool, struct xdp_buff **xdp, u32 max) +static u32 xp_alloc_slow(struct xsk_buff_pool *pool, struct xdp_buff **xdp, + u32 max) { - u32 nb_entries1 = 0, nb_entries2; + int i; - if (unlikely(pool->dev && dma_dev_need_sync(pool->dev))) { + for (i = 0; i < max; i++) { struct xdp_buff *buff; - /* Slow path */ buff = xp_alloc(pool); - if (buff) - *xdp = buff; - return !!buff; + if (unlikely(!buff)) + return i; + *xdp = buff; + xdp++; } + return max; +} + +u32 xp_alloc_batch(struct xsk_buff_pool *pool, struct xdp_buff **xdp, u32 max) +{ + u32 nb_entries1 = 0, nb_entries2; + + if (unlikely(pool->dev && dma_dev_need_sync(pool->dev))) + return xp_alloc_slow(pool, xdp, max); + if (unlikely(pool->free_list_cnt)) { nb_entries1 = xp_alloc_reused(pool, xdp, max); if (nb_entries1 == max) @@ -656,9 +672,17 @@ EXPORT_SYMBOL(xp_alloc_batch); bool xp_can_alloc(struct xsk_buff_pool *pool, u32 count) { + u32 req_count, avail_count; + if (pool->free_list_cnt >= count) return true; - return xskq_cons_has_entries(pool->fq, count - pool->free_list_cnt); + + req_count = count - pool->free_list_cnt; + avail_count = xskq_cons_nb_entries(pool->fq, req_count); + if (!avail_count) + pool->fq->queue_empty_descs++; + + return avail_count >= req_count; } EXPORT_SYMBOL(xp_can_alloc); diff --git a/net/xdp/xsk_queue.h b/net/xdp/xsk_queue.h index 6f2d1621c992..406b20dfee8d 100644 --- a/net/xdp/xsk_queue.h +++ b/net/xdp/xsk_queue.h @@ -306,11 +306,6 @@ static inline u32 xskq_cons_nb_entries(struct xsk_queue *q, u32 max) return entries >= max ? max : entries; } -static inline bool xskq_cons_has_entries(struct xsk_queue *q, u32 cnt) -{ - return xskq_cons_nb_entries(q, cnt) >= cnt; -} - static inline bool xskq_cons_peek_addr_unchecked(struct xsk_queue *q, u64 *addr) { if (q->cached_prod == q->cached_cons) diff --git a/net/xfrm/Makefile b/net/xfrm/Makefile index 547cec77ba03..512e0b2f8514 100644 --- a/net/xfrm/Makefile +++ b/net/xfrm/Makefile @@ -13,7 +13,8 @@ endif obj-$(CONFIG_XFRM) := xfrm_policy.o xfrm_state.o xfrm_hash.o \ xfrm_input.o xfrm_output.o \ - xfrm_sysctl.o xfrm_replay.o xfrm_device.o + xfrm_sysctl.o xfrm_replay.o xfrm_device.o \ + xfrm_nat_keepalive.o obj-$(CONFIG_XFRM_STATISTICS) += xfrm_proc.o obj-$(CONFIG_XFRM_ALGO) += xfrm_algo.o obj-$(CONFIG_XFRM_USER) += xfrm_user.o diff --git a/net/xfrm/xfrm_compat.c b/net/xfrm/xfrm_compat.c index 703d4172c7d7..91357ccaf4af 100644 --- a/net/xfrm/xfrm_compat.c +++ b/net/xfrm/xfrm_compat.c @@ -131,6 +131,7 @@ static const struct nla_policy compat_policy[XFRMA_MAX+1] = { [XFRMA_IF_ID] = { .type = NLA_U32 }, [XFRMA_MTIMER_THRESH] = { .type = NLA_U32 }, [XFRMA_SA_DIR] = NLA_POLICY_RANGE(NLA_U8, XFRM_SA_DIR_IN, XFRM_SA_DIR_OUT), + [XFRMA_NAT_KEEPALIVE_INTERVAL] = { .type = NLA_U32 }, }; static struct nlmsghdr *xfrm_nlmsg_put_compat(struct sk_buff *skb, @@ -280,9 +281,10 @@ static int xfrm_xlate64_attr(struct sk_buff *dst, const struct nlattr *src) case XFRMA_IF_ID: case XFRMA_MTIMER_THRESH: case XFRMA_SA_DIR: + case XFRMA_NAT_KEEPALIVE_INTERVAL: return xfrm_nla_cpy(dst, src, nla_len(src)); default: - BUILD_BUG_ON(XFRMA_MAX != XFRMA_SA_DIR); + BUILD_BUG_ON(XFRMA_MAX != XFRMA_NAT_KEEPALIVE_INTERVAL); pr_warn_once("unsupported nla_type %d\n", src->nla_type); return -EOPNOTSUPP; } @@ -437,7 +439,7 @@ static int xfrm_xlate32_attr(void *dst, const struct nlattr *nla, int err; if (type > XFRMA_MAX) { - BUILD_BUG_ON(XFRMA_MAX != XFRMA_SA_DIR); + BUILD_BUG_ON(XFRMA_MAX != XFRMA_NAT_KEEPALIVE_INTERVAL); NL_SET_ERR_MSG(extack, "Bad attribute"); return -EOPNOTSUPP; } diff --git a/net/xfrm/xfrm_device.c b/net/xfrm/xfrm_device.c index 2455a76a1cff..f123b7c9ec82 100644 --- a/net/xfrm/xfrm_device.c +++ b/net/xfrm/xfrm_device.c @@ -261,9 +261,9 @@ int xfrm_dev_state_add(struct net *net, struct xfrm_state *x, is_packet_offload = xuo->flags & XFRM_OFFLOAD_PACKET; - /* We don't yet support UDP encapsulation and TFC padding. */ - if ((!is_packet_offload && x->encap) || x->tfcpad) { - NL_SET_ERR_MSG(extack, "Encapsulation and TFC padding can't be offloaded"); + /* We don't yet support TFC padding. */ + if (x->tfcpad) { + NL_SET_ERR_MSG(extack, "TFC padding can't be offloaded"); return -EINVAL; } @@ -328,12 +328,8 @@ int xfrm_dev_state_add(struct net *net, struct xfrm_state *x, /* User explicitly requested packet offload mode and configured * policy in addition to the XFRM state. So be civil to users, * and return an error instead of taking fallback path. - * - * This WARN_ON() can be seen as a documentation for driver - * authors to do not return -EOPNOTSUPP in packet offload mode. */ - WARN_ON(err == -EOPNOTSUPP && is_packet_offload); - if (err != -EOPNOTSUPP || is_packet_offload) { + if ((err != -EOPNOTSUPP && !is_packet_offload) || is_packet_offload) { NL_SET_ERR_MSG_WEAK(extack, "Device failed to offload this state"); return err; } diff --git a/net/xfrm/xfrm_input.c b/net/xfrm/xfrm_input.c index d2ea18dcb0cb..749e7eea99e4 100644 --- a/net/xfrm/xfrm_input.c +++ b/net/xfrm/xfrm_input.c @@ -471,14 +471,10 @@ int xfrm_input(struct sk_buff *skb, int nexthdr, __be32 spi, int encap_type) struct xfrm_offload *xo = xfrm_offload(skb); struct sec_path *sp; - if (encap_type < 0 || (xo && xo->flags & XFRM_GRO)) { + if (encap_type < 0 || (xo && (xo->flags & XFRM_GRO || encap_type == 0 || + encap_type == UDP_ENCAP_ESPINUDP))) { x = xfrm_input_state(skb); - if (unlikely(x->dir && x->dir != XFRM_SA_DIR_IN)) { - XFRM_INC_STATS(net, LINUX_MIB_XFRMINSTATEDIRERROR); - goto drop; - } - if (unlikely(x->km.state != XFRM_STATE_VALID)) { if (x->km.state == XFRM_STATE_ACQ) XFRM_INC_STATS(net, LINUX_MIB_XFRMACQUIREERROR); @@ -585,8 +581,11 @@ int xfrm_input(struct sk_buff *skb, int nexthdr, __be32 spi, int encap_type) } if (unlikely(x->dir && x->dir != XFRM_SA_DIR_IN)) { + secpath_reset(skb); XFRM_INC_STATS(net, LINUX_MIB_XFRMINSTATEDIRERROR); + xfrm_audit_state_notfound(skb, family, spi, seq); xfrm_state_put(x); + x = NULL; goto drop; } diff --git a/net/xfrm/xfrm_interface_core.c b/net/xfrm/xfrm_interface_core.c index e50e4bf993fa..98f1e2b67c76 100644 --- a/net/xfrm/xfrm_interface_core.c +++ b/net/xfrm/xfrm_interface_core.c @@ -769,7 +769,7 @@ static int xfrmi_dev_init(struct net_device *dev) if (err) return err; - dev->features |= NETIF_F_LLTX; + dev->lltx = true; dev->features |= XFRMI_FEATURES; dev->hw_features |= XFRMI_FEATURES; diff --git a/net/xfrm/xfrm_nat_keepalive.c b/net/xfrm/xfrm_nat_keepalive.c new file mode 100644 index 000000000000..82f0a301683f --- /dev/null +++ b/net/xfrm/xfrm_nat_keepalive.c @@ -0,0 +1,292 @@ +// SPDX-License-Identifier: GPL-2.0-only +/* + * xfrm_nat_keepalive.c + * + * (c) 2024 Eyal Birger <eyal.birger@gmail.com> + */ + +#include <net/inet_common.h> +#include <net/ip6_checksum.h> +#include <net/xfrm.h> + +static DEFINE_PER_CPU(struct sock *, nat_keepalive_sk_ipv4); +#if IS_ENABLED(CONFIG_IPV6) +static DEFINE_PER_CPU(struct sock *, nat_keepalive_sk_ipv6); +#endif + +struct nat_keepalive { + struct net *net; + u16 family; + xfrm_address_t saddr; + xfrm_address_t daddr; + __be16 encap_sport; + __be16 encap_dport; + __u32 smark; +}; + +static void nat_keepalive_init(struct nat_keepalive *ka, struct xfrm_state *x) +{ + ka->net = xs_net(x); + ka->family = x->props.family; + ka->saddr = x->props.saddr; + ka->daddr = x->id.daddr; + ka->encap_sport = x->encap->encap_sport; + ka->encap_dport = x->encap->encap_dport; + ka->smark = xfrm_smark_get(0, x); +} + +static int nat_keepalive_send_ipv4(struct sk_buff *skb, + struct nat_keepalive *ka) +{ + struct net *net = ka->net; + struct flowi4 fl4; + struct rtable *rt; + struct sock *sk; + __u8 tos = 0; + int err; + + flowi4_init_output(&fl4, 0 /* oif */, skb->mark, tos, + RT_SCOPE_UNIVERSE, IPPROTO_UDP, 0, + ka->daddr.a4, ka->saddr.a4, ka->encap_dport, + ka->encap_sport, sock_net_uid(net, NULL)); + + rt = ip_route_output_key(net, &fl4); + if (IS_ERR(rt)) + return PTR_ERR(rt); + + skb_dst_set(skb, &rt->dst); + + sk = *this_cpu_ptr(&nat_keepalive_sk_ipv4); + sock_net_set(sk, net); + err = ip_build_and_send_pkt(skb, sk, fl4.saddr, fl4.daddr, NULL, tos); + sock_net_set(sk, &init_net); + return err; +} + +#if IS_ENABLED(CONFIG_IPV6) +static int nat_keepalive_send_ipv6(struct sk_buff *skb, + struct nat_keepalive *ka, + struct udphdr *uh) +{ + struct net *net = ka->net; + struct dst_entry *dst; + struct flowi6 fl6; + struct sock *sk; + __wsum csum; + int err; + + csum = skb_checksum(skb, 0, skb->len, 0); + uh->check = csum_ipv6_magic(&ka->saddr.in6, &ka->daddr.in6, + skb->len, IPPROTO_UDP, csum); + if (uh->check == 0) + uh->check = CSUM_MANGLED_0; + + memset(&fl6, 0, sizeof(fl6)); + fl6.flowi6_mark = skb->mark; + fl6.saddr = ka->saddr.in6; + fl6.daddr = ka->daddr.in6; + fl6.flowi6_proto = IPPROTO_UDP; + fl6.fl6_sport = ka->encap_sport; + fl6.fl6_dport = ka->encap_dport; + + sk = *this_cpu_ptr(&nat_keepalive_sk_ipv6); + sock_net_set(sk, net); + dst = ipv6_stub->ipv6_dst_lookup_flow(net, sk, &fl6, NULL); + if (IS_ERR(dst)) + return PTR_ERR(dst); + + skb_dst_set(skb, dst); + err = ipv6_stub->ip6_xmit(sk, skb, &fl6, skb->mark, NULL, 0, 0); + sock_net_set(sk, &init_net); + return err; +} +#endif + +static void nat_keepalive_send(struct nat_keepalive *ka) +{ + const int nat_ka_hdrs_len = max(sizeof(struct iphdr), + sizeof(struct ipv6hdr)) + + sizeof(struct udphdr); + const u8 nat_ka_payload = 0xFF; + int err = -EAFNOSUPPORT; + struct sk_buff *skb; + struct udphdr *uh; + + skb = alloc_skb(nat_ka_hdrs_len + sizeof(nat_ka_payload), GFP_ATOMIC); + if (unlikely(!skb)) + return; + + skb_reserve(skb, nat_ka_hdrs_len); + + skb_put_u8(skb, nat_ka_payload); + + uh = skb_push(skb, sizeof(*uh)); + uh->source = ka->encap_sport; + uh->dest = ka->encap_dport; + uh->len = htons(skb->len); + uh->check = 0; + + skb->mark = ka->smark; + + switch (ka->family) { + case AF_INET: + err = nat_keepalive_send_ipv4(skb, ka); + break; +#if IS_ENABLED(CONFIG_IPV6) + case AF_INET6: + err = nat_keepalive_send_ipv6(skb, ka, uh); + break; +#endif + } + if (err) + kfree_skb(skb); +} + +struct nat_keepalive_work_ctx { + time64_t next_run; + time64_t now; +}; + +static int nat_keepalive_work_single(struct xfrm_state *x, int count, void *ptr) +{ + struct nat_keepalive_work_ctx *ctx = ptr; + bool send_keepalive = false; + struct nat_keepalive ka; + time64_t next_run; + u32 interval; + int delta; + + interval = x->nat_keepalive_interval; + if (!interval) + return 0; + + spin_lock(&x->lock); + + delta = (int)(ctx->now - x->lastused); + if (delta < interval) { + x->nat_keepalive_expiration = ctx->now + interval - delta; + next_run = x->nat_keepalive_expiration; + } else if (x->nat_keepalive_expiration > ctx->now) { + next_run = x->nat_keepalive_expiration; + } else { + next_run = ctx->now + interval; + nat_keepalive_init(&ka, x); + send_keepalive = true; + } + + spin_unlock(&x->lock); + + if (send_keepalive) + nat_keepalive_send(&ka); + + if (!ctx->next_run || next_run < ctx->next_run) + ctx->next_run = next_run; + return 0; +} + +static void nat_keepalive_work(struct work_struct *work) +{ + struct nat_keepalive_work_ctx ctx; + struct xfrm_state_walk walk; + struct net *net; + + ctx.next_run = 0; + ctx.now = ktime_get_real_seconds(); + + net = container_of(work, struct net, xfrm.nat_keepalive_work.work); + xfrm_state_walk_init(&walk, IPPROTO_ESP, NULL); + xfrm_state_walk(net, &walk, nat_keepalive_work_single, &ctx); + xfrm_state_walk_done(&walk, net); + if (ctx.next_run) + schedule_delayed_work(&net->xfrm.nat_keepalive_work, + (ctx.next_run - ctx.now) * HZ); +} + +static int nat_keepalive_sk_init(struct sock * __percpu *socks, + unsigned short family) +{ + struct sock *sk; + int err, i; + + for_each_possible_cpu(i) { + err = inet_ctl_sock_create(&sk, family, SOCK_RAW, IPPROTO_UDP, + &init_net); + if (err < 0) + goto err; + + *per_cpu_ptr(socks, i) = sk; + } + + return 0; +err: + for_each_possible_cpu(i) + inet_ctl_sock_destroy(*per_cpu_ptr(socks, i)); + return err; +} + +static void nat_keepalive_sk_fini(struct sock * __percpu *socks) +{ + int i; + + for_each_possible_cpu(i) + inet_ctl_sock_destroy(*per_cpu_ptr(socks, i)); +} + +void xfrm_nat_keepalive_state_updated(struct xfrm_state *x) +{ + struct net *net; + + if (!x->nat_keepalive_interval) + return; + + net = xs_net(x); + schedule_delayed_work(&net->xfrm.nat_keepalive_work, 0); +} + +int __net_init xfrm_nat_keepalive_net_init(struct net *net) +{ + INIT_DELAYED_WORK(&net->xfrm.nat_keepalive_work, nat_keepalive_work); + return 0; +} + +int xfrm_nat_keepalive_net_fini(struct net *net) +{ + cancel_delayed_work_sync(&net->xfrm.nat_keepalive_work); + return 0; +} + +int xfrm_nat_keepalive_init(unsigned short family) +{ + int err = -EAFNOSUPPORT; + + switch (family) { + case AF_INET: + err = nat_keepalive_sk_init(&nat_keepalive_sk_ipv4, PF_INET); + break; +#if IS_ENABLED(CONFIG_IPV6) + case AF_INET6: + err = nat_keepalive_sk_init(&nat_keepalive_sk_ipv6, PF_INET6); + break; +#endif + } + + if (err) + pr_err("xfrm nat keepalive init: failed to init err:%d\n", err); + return err; +} +EXPORT_SYMBOL_GPL(xfrm_nat_keepalive_init); + +void xfrm_nat_keepalive_fini(unsigned short family) +{ + switch (family) { + case AF_INET: + nat_keepalive_sk_fini(&nat_keepalive_sk_ipv4); + break; +#if IS_ENABLED(CONFIG_IPV6) + case AF_INET6: + nat_keepalive_sk_fini(&nat_keepalive_sk_ipv6); + break; +#endif + } +} +EXPORT_SYMBOL_GPL(xfrm_nat_keepalive_fini); diff --git a/net/xfrm/xfrm_policy.c b/net/xfrm/xfrm_policy.c index 66e07de2de35..914bac03b52a 100644 --- a/net/xfrm/xfrm_policy.c +++ b/net/xfrm/xfrm_policy.c @@ -45,6 +45,7 @@ #ifdef CONFIG_XFRM_ESPINTCP #include <net/espintcp.h> #endif +#include <net/inet_dscp.h> #include "xfrm_hash.h" @@ -109,7 +110,11 @@ struct xfrm_pol_inexact_node { * 4. saddr:any list from saddr tree * * This result set then needs to be searched for the policy with - * the lowest priority. If two results have same prio, youngest one wins. + * the lowest priority. If two candidates have the same priority, the + * struct xfrm_policy pos member with the lower number is used. + * + * This replicates previous single-list-search algorithm which would + * return first matching policy in the (ordered-by-priority) list. */ struct xfrm_pol_inexact_key { @@ -196,8 +201,6 @@ xfrm_policy_inexact_lookup_rcu(struct net *net, static struct xfrm_policy * xfrm_policy_insert_list(struct hlist_head *chain, struct xfrm_policy *policy, bool excl); -static void xfrm_policy_insert_inexact_list(struct hlist_head *chain, - struct xfrm_policy *policy); static bool xfrm_policy_find_inexact_candidates(struct xfrm_pol_inexact_candidates *cand, @@ -410,7 +413,6 @@ struct xfrm_policy *xfrm_policy_alloc(struct net *net, gfp_t gfp) if (policy) { write_pnet(&policy->xp_net, net); INIT_LIST_HEAD(&policy->walk.all); - INIT_HLIST_NODE(&policy->bydst_inexact_list); INIT_HLIST_NODE(&policy->bydst); INIT_HLIST_NODE(&policy->byidx); rwlock_init(&policy->lock); @@ -452,6 +454,8 @@ EXPORT_SYMBOL(xfrm_policy_destroy); static void xfrm_policy_kill(struct xfrm_policy *policy) { + xfrm_dev_policy_delete(policy); + write_lock_bh(&policy->lock); policy->walk.dead = 1; write_unlock_bh(&policy->lock); @@ -1226,26 +1230,31 @@ xfrm_policy_inexact_insert(struct xfrm_policy *policy, u8 dir, int excl) return ERR_PTR(-EEXIST); } - chain = &net->xfrm.policy_inexact[dir]; - xfrm_policy_insert_inexact_list(chain, policy); - if (delpol) __xfrm_policy_inexact_prune_bin(bin, false); return delpol; } +static bool xfrm_policy_is_dead_or_sk(const struct xfrm_policy *policy) +{ + int dir; + + if (policy->walk.dead) + return true; + + dir = xfrm_policy_id2dir(policy->index); + return dir >= XFRM_POLICY_MAX; +} + static void xfrm_hash_rebuild(struct work_struct *work) { struct net *net = container_of(work, struct net, xfrm.policy_hthresh.work); - unsigned int hmask; struct xfrm_policy *pol; struct xfrm_policy *policy; struct hlist_head *chain; - struct hlist_head *odst; struct hlist_node *newpos; - int i; int dir; unsigned seq; u8 lbits4, rbits4, lbits6, rbits6; @@ -1272,13 +1281,10 @@ static void xfrm_hash_rebuild(struct work_struct *work) struct xfrm_pol_inexact_bin *bin; u8 dbits, sbits; - if (policy->walk.dead) + if (xfrm_policy_is_dead_or_sk(policy)) continue; dir = xfrm_policy_id2dir(policy->index); - if (dir >= XFRM_POLICY_MAX) - continue; - if ((dir & XFRM_POLICY_MASK) == XFRM_POLICY_OUT) { if (policy->family == AF_INET) { dbits = rbits4; @@ -1309,23 +1315,7 @@ static void xfrm_hash_rebuild(struct work_struct *work) goto out_unlock; } - /* reset the bydst and inexact table in all directions */ for (dir = 0; dir < XFRM_POLICY_MAX; dir++) { - struct hlist_node *n; - - hlist_for_each_entry_safe(policy, n, - &net->xfrm.policy_inexact[dir], - bydst_inexact_list) { - hlist_del_rcu(&policy->bydst); - hlist_del_init(&policy->bydst_inexact_list); - } - - hmask = net->xfrm.policy_bydst[dir].hmask; - odst = net->xfrm.policy_bydst[dir].table; - for (i = hmask; i >= 0; i--) { - hlist_for_each_entry_safe(policy, n, odst + i, bydst) - hlist_del_rcu(&policy->bydst); - } if ((dir & XFRM_POLICY_MASK) == XFRM_POLICY_OUT) { /* dir out => dst = remote, src = local */ net->xfrm.policy_bydst[dir].dbits4 = rbits4; @@ -1343,14 +1333,13 @@ static void xfrm_hash_rebuild(struct work_struct *work) /* re-insert all policies by order of creation */ list_for_each_entry_reverse(policy, &net->xfrm.policy_all, walk.all) { - if (policy->walk.dead) + if (xfrm_policy_is_dead_or_sk(policy)) continue; - dir = xfrm_policy_id2dir(policy->index); - if (dir >= XFRM_POLICY_MAX) { - /* skip socket policies */ - continue; - } + + hlist_del_rcu(&policy->bydst); + newpos = NULL; + dir = xfrm_policy_id2dir(policy->index); chain = policy_hash_bysel(net, &policy->selector, policy->family, dir); @@ -1517,42 +1506,6 @@ static const struct rhashtable_params xfrm_pol_inexact_params = { .automatic_shrinking = true, }; -static void xfrm_policy_insert_inexact_list(struct hlist_head *chain, - struct xfrm_policy *policy) -{ - struct xfrm_policy *pol, *delpol = NULL; - struct hlist_node *newpos = NULL; - int i = 0; - - hlist_for_each_entry(pol, chain, bydst_inexact_list) { - if (pol->type == policy->type && - pol->if_id == policy->if_id && - !selector_cmp(&pol->selector, &policy->selector) && - xfrm_policy_mark_match(&policy->mark, pol) && - xfrm_sec_ctx_match(pol->security, policy->security) && - !WARN_ON(delpol)) { - delpol = pol; - if (policy->priority > pol->priority) - continue; - } else if (policy->priority >= pol->priority) { - newpos = &pol->bydst_inexact_list; - continue; - } - if (delpol) - break; - } - - if (newpos && policy->xdo.type != XFRM_DEV_OFFLOAD_PACKET) - hlist_add_behind_rcu(&policy->bydst_inexact_list, newpos); - else - hlist_add_head_rcu(&policy->bydst_inexact_list, chain); - - hlist_for_each_entry(pol, chain, bydst_inexact_list) { - pol->pos = i; - i++; - } -} - static struct xfrm_policy *xfrm_policy_insert_list(struct hlist_head *chain, struct xfrm_policy *policy, bool excl) @@ -1850,7 +1803,6 @@ again: __xfrm_policy_unlink(pol, dir); spin_unlock_bh(&net->xfrm.xfrm_policy_lock); - xfrm_dev_policy_delete(pol); cnt++; xfrm_audit_policy_delete(pol, 1, task_valid); xfrm_policy_kill(pol); @@ -1891,7 +1843,6 @@ again: __xfrm_policy_unlink(pol, dir); spin_unlock_bh(&net->xfrm.xfrm_policy_lock); - xfrm_dev_policy_delete(pol); cnt++; xfrm_audit_policy_delete(pol, 1, task_valid); xfrm_policy_kill(pol); @@ -2294,10 +2245,52 @@ out: return pol; } +static u32 xfrm_gen_pos_slow(struct net *net) +{ + struct xfrm_policy *policy; + u32 i = 0; + + /* oldest entry is last in list */ + list_for_each_entry_reverse(policy, &net->xfrm.policy_all, walk.all) { + if (!xfrm_policy_is_dead_or_sk(policy)) + policy->pos = ++i; + } + + return i; +} + +static u32 xfrm_gen_pos(struct net *net) +{ + const struct xfrm_policy *policy; + u32 i = 0; + + /* most recently added policy is at the head of the list */ + list_for_each_entry(policy, &net->xfrm.policy_all, walk.all) { + if (xfrm_policy_is_dead_or_sk(policy)) + continue; + + if (policy->pos == UINT_MAX) + return xfrm_gen_pos_slow(net); + + i = policy->pos + 1; + break; + } + + return i; +} + static void __xfrm_policy_link(struct xfrm_policy *pol, int dir) { struct net *net = xp_net(pol); + switch (dir) { + case XFRM_POLICY_IN: + case XFRM_POLICY_FWD: + case XFRM_POLICY_OUT: + pol->pos = xfrm_gen_pos(net); + break; + } + list_add(&pol->walk.all, &net->xfrm.policy_all); net->xfrm.policy_count[dir]++; xfrm_pol_hold(pol); @@ -2314,7 +2307,6 @@ static struct xfrm_policy *__xfrm_policy_unlink(struct xfrm_policy *pol, /* Socket policies are not hashed. */ if (!hlist_unhashed(&pol->bydst)) { hlist_del_rcu(&pol->bydst); - hlist_del_init(&pol->bydst_inexact_list); hlist_del(&pol->byidx); } @@ -2342,7 +2334,6 @@ int xfrm_policy_delete(struct xfrm_policy *pol, int dir) pol = __xfrm_policy_unlink(pol, dir); spin_unlock_bh(&net->xfrm.xfrm_policy_lock); if (pol) { - xfrm_dev_policy_delete(pol); xfrm_policy_kill(pol); return 0; } @@ -2562,7 +2553,7 @@ xfrm_tmpl_resolve(struct xfrm_policy **pols, int npols, const struct flowi *fl, static int xfrm_get_tos(const struct flowi *fl, int family) { if (family == AF_INET) - return IPTOS_RT_MASK & fl->u.ip4.flowi4_tos; + return fl->u.ip4.flowi4_tos & INET_DSCP_MASK; return 0; } @@ -3718,12 +3709,15 @@ int __xfrm_policy_check(struct sock *sk, int dir, struct sk_buff *skb, pol = xfrm_in_fwd_icmp(skb, &fl, family, if_id); if (!pol) { + const bool is_crypto_offload = sp && + (xfrm_input_state(skb)->xso.type == XFRM_DEV_OFFLOAD_CRYPTO); + if (net->xfrm.policy_default[dir] == XFRM_USERPOLICY_BLOCK) { XFRM_INC_STATS(net, LINUX_MIB_XFRMINNOPOLS); return 0; } - if (sp && secpath_has_nontransport(sp, 0, &xerr_idx)) { + if (sp && secpath_has_nontransport(sp, 0, &xerr_idx) && !is_crypto_offload) { xfrm_secpath_reject(xerr_idx, skb, &fl); XFRM_INC_STATS(net, LINUX_MIB_XFRMINNOPOLS); return 0; @@ -4284,8 +4278,14 @@ static int __net_init xfrm_net_init(struct net *net) if (rv < 0) goto out_sysctl; + rv = xfrm_nat_keepalive_net_init(net); + if (rv < 0) + goto out_nat_keepalive; + return 0; +out_nat_keepalive: + xfrm_sysctl_fini(net); out_sysctl: xfrm_policy_fini(net); out_policy: @@ -4298,6 +4298,7 @@ out_statistics: static void __net_exit xfrm_net_exit(struct net *net) { + xfrm_nat_keepalive_net_fini(net); xfrm_sysctl_fini(net); xfrm_policy_fini(net); xfrm_state_fini(net); @@ -4359,6 +4360,7 @@ void __init xfrm_init(void) #endif register_xfrm_state_bpf(); + xfrm_nat_keepalive_init(AF_INET); } #ifdef CONFIG_AUDITSYSCALL @@ -4427,63 +4429,50 @@ EXPORT_SYMBOL_GPL(xfrm_audit_policy_delete); #endif #ifdef CONFIG_XFRM_MIGRATE -static bool xfrm_migrate_selector_match(const struct xfrm_selector *sel_cmp, - const struct xfrm_selector *sel_tgt) -{ - if (sel_cmp->proto == IPSEC_ULPROTO_ANY) { - if (sel_tgt->family == sel_cmp->family && - xfrm_addr_equal(&sel_tgt->daddr, &sel_cmp->daddr, - sel_cmp->family) && - xfrm_addr_equal(&sel_tgt->saddr, &sel_cmp->saddr, - sel_cmp->family) && - sel_tgt->prefixlen_d == sel_cmp->prefixlen_d && - sel_tgt->prefixlen_s == sel_cmp->prefixlen_s) { - return true; - } - } else { - if (memcmp(sel_tgt, sel_cmp, sizeof(*sel_tgt)) == 0) { - return true; - } - } - return false; -} - static struct xfrm_policy *xfrm_migrate_policy_find(const struct xfrm_selector *sel, u8 dir, u8 type, struct net *net, u32 if_id) { - struct xfrm_policy *pol, *ret = NULL; - struct hlist_head *chain; - u32 priority = ~0U; + struct xfrm_policy *pol; + struct flowi fl; - spin_lock_bh(&net->xfrm.xfrm_policy_lock); - chain = policy_hash_direct(net, &sel->daddr, &sel->saddr, sel->family, dir); - hlist_for_each_entry(pol, chain, bydst) { - if ((if_id == 0 || pol->if_id == if_id) && - xfrm_migrate_selector_match(sel, &pol->selector) && - pol->type == type) { - ret = pol; - priority = ret->priority; - break; - } - } - chain = &net->xfrm.policy_inexact[dir]; - hlist_for_each_entry(pol, chain, bydst_inexact_list) { - if ((pol->priority >= priority) && ret) - break; + memset(&fl, 0, sizeof(fl)); - if ((if_id == 0 || pol->if_id == if_id) && - xfrm_migrate_selector_match(sel, &pol->selector) && - pol->type == type) { - ret = pol; + fl.flowi_proto = sel->proto; + + switch (sel->family) { + case AF_INET: + fl.u.ip4.saddr = sel->saddr.a4; + fl.u.ip4.daddr = sel->daddr.a4; + if (sel->proto == IPSEC_ULPROTO_ANY) break; - } + fl.u.flowi4_oif = sel->ifindex; + fl.u.ip4.fl4_sport = sel->sport; + fl.u.ip4.fl4_dport = sel->dport; + break; + case AF_INET6: + fl.u.ip6.saddr = sel->saddr.in6; + fl.u.ip6.daddr = sel->daddr.in6; + if (sel->proto == IPSEC_ULPROTO_ANY) + break; + fl.u.flowi6_oif = sel->ifindex; + fl.u.ip6.fl4_sport = sel->sport; + fl.u.ip6.fl4_dport = sel->dport; + break; + default: + return ERR_PTR(-EAFNOSUPPORT); } - xfrm_pol_hold(ret); + rcu_read_lock(); - spin_unlock_bh(&net->xfrm.xfrm_policy_lock); + pol = xfrm_policy_lookup_bytype(net, type, &fl, sel->family, dir, if_id); + if (IS_ERR_OR_NULL(pol)) + goto out_unlock; - return ret; + if (!xfrm_pol_hold_rcu(pol)) + pol = NULL; +out_unlock: + rcu_read_unlock(); + return pol; } static int migrate_tmpl_match(const struct xfrm_migrate *m, const struct xfrm_tmpl *t) @@ -4620,9 +4609,9 @@ int xfrm_migrate(const struct xfrm_selector *sel, u8 dir, u8 type, /* Stage 1 - find policy */ pol = xfrm_migrate_policy_find(sel, dir, type, net, if_id); - if (!pol) { + if (IS_ERR_OR_NULL(pol)) { NL_SET_ERR_MSG(extack, "Target policy not found"); - err = -ENOENT; + err = IS_ERR(pol) ? PTR_ERR(pol) : -ENOENT; goto out; } diff --git a/net/xfrm/xfrm_state.c b/net/xfrm/xfrm_state.c index 649bb739df0d..37478d36a8df 100644 --- a/net/xfrm/xfrm_state.c +++ b/net/xfrm/xfrm_state.c @@ -49,6 +49,7 @@ static struct kmem_cache *xfrm_state_cache __ro_after_init; static DECLARE_WORK(xfrm_state_gc_work, xfrm_state_gc_task); static HLIST_HEAD(xfrm_state_gc_list); +static HLIST_HEAD(xfrm_state_dev_gc_list); static inline bool xfrm_state_hold_rcu(struct xfrm_state __rcu *x) { @@ -214,6 +215,7 @@ static DEFINE_SPINLOCK(xfrm_state_afinfo_lock); static struct xfrm_state_afinfo __rcu *xfrm_state_afinfo[NPROTO]; static DEFINE_SPINLOCK(xfrm_state_gc_lock); +static DEFINE_SPINLOCK(xfrm_state_dev_gc_lock); int __xfrm_state_delete(struct xfrm_state *x); @@ -683,6 +685,41 @@ struct xfrm_state *xfrm_state_alloc(struct net *net) } EXPORT_SYMBOL(xfrm_state_alloc); +#ifdef CONFIG_XFRM_OFFLOAD +void xfrm_dev_state_delete(struct xfrm_state *x) +{ + struct xfrm_dev_offload *xso = &x->xso; + struct net_device *dev = READ_ONCE(xso->dev); + + if (dev) { + dev->xfrmdev_ops->xdo_dev_state_delete(x); + spin_lock_bh(&xfrm_state_dev_gc_lock); + hlist_add_head(&x->dev_gclist, &xfrm_state_dev_gc_list); + spin_unlock_bh(&xfrm_state_dev_gc_lock); + } +} +EXPORT_SYMBOL_GPL(xfrm_dev_state_delete); + +void xfrm_dev_state_free(struct xfrm_state *x) +{ + struct xfrm_dev_offload *xso = &x->xso; + struct net_device *dev = READ_ONCE(xso->dev); + + if (dev && dev->xfrmdev_ops) { + spin_lock_bh(&xfrm_state_dev_gc_lock); + if (!hlist_unhashed(&x->dev_gclist)) + hlist_del(&x->dev_gclist); + spin_unlock_bh(&xfrm_state_dev_gc_lock); + + if (dev->xfrmdev_ops->xdo_dev_state_free) + dev->xfrmdev_ops->xdo_dev_state_free(x); + WRITE_ONCE(xso->dev, NULL); + xso->type = XFRM_DEV_OFFLOAD_UNSPECIFIED; + netdev_put(dev, &xso->dev_tracker); + } +} +#endif + void __xfrm_state_destroy(struct xfrm_state *x, bool sync) { WARN_ON(x->km.state != XFRM_STATE_DEAD); @@ -715,6 +752,7 @@ int __xfrm_state_delete(struct xfrm_state *x) if (x->id.spi) hlist_del_rcu(&x->byspi); net->xfrm.state_num--; + xfrm_nat_keepalive_state_updated(x); spin_unlock(&net->xfrm.xfrm_state_lock); if (x->encap_sk) @@ -848,6 +886,9 @@ EXPORT_SYMBOL(xfrm_state_flush); int xfrm_dev_state_flush(struct net *net, struct net_device *dev, bool task_valid) { + struct xfrm_state *x; + struct hlist_node *tmp; + struct xfrm_dev_offload *xso; int i, err = 0, cnt = 0; spin_lock_bh(&net->xfrm.xfrm_state_lock); @@ -857,8 +898,6 @@ int xfrm_dev_state_flush(struct net *net, struct net_device *dev, bool task_vali err = -ESRCH; for (i = 0; i <= net->xfrm.state_hmask; i++) { - struct xfrm_state *x; - struct xfrm_dev_offload *xso; restart: hlist_for_each_entry(x, net->xfrm.state_bydst+i, bydst) { xso = &x->xso; @@ -868,6 +907,8 @@ restart: spin_unlock_bh(&net->xfrm.xfrm_state_lock); err = xfrm_state_delete(x); + xfrm_dev_state_free(x); + xfrm_audit_state_delete(x, err ? 0 : 1, task_valid); xfrm_state_put(x); @@ -884,6 +925,24 @@ restart: out: spin_unlock_bh(&net->xfrm.xfrm_state_lock); + + spin_lock_bh(&xfrm_state_dev_gc_lock); +restart_gc: + hlist_for_each_entry_safe(x, tmp, &xfrm_state_dev_gc_list, dev_gclist) { + xso = &x->xso; + + if (xso->dev == dev) { + spin_unlock_bh(&xfrm_state_dev_gc_lock); + xfrm_dev_state_free(x); + spin_lock_bh(&xfrm_state_dev_gc_lock); + goto restart_gc; + } + + } + spin_unlock_bh(&xfrm_state_dev_gc_lock); + + xfrm_flush_gc(); + return err; } EXPORT_SYMBOL(xfrm_dev_state_flush); @@ -1273,8 +1332,7 @@ found: xso->dev = xdo->dev; xso->real_dev = xdo->real_dev; xso->flags = XFRM_DEV_OFFLOAD_FLAG_ACQ; - netdev_tracker_alloc(xso->dev, &xso->dev_tracker, - GFP_ATOMIC); + netdev_hold(xso->dev, &xso->dev_tracker, GFP_ATOMIC); error = xso->dev->xfrmdev_ops->xdo_dev_state_add(x, NULL); if (error) { xso->dir = 0; @@ -1453,6 +1511,7 @@ static void __xfrm_state_insert(struct xfrm_state *x) net->xfrm.state_num++; xfrm_hash_grow_check(net, x->bydst.next != NULL); + xfrm_nat_keepalive_state_updated(x); } /* net->xfrm.xfrm_state_lock is held */ @@ -2871,6 +2930,21 @@ int __xfrm_init_state(struct xfrm_state *x, bool init_replay, bool offload, goto error; } + if (x->nat_keepalive_interval) { + if (x->dir != XFRM_SA_DIR_OUT) { + NL_SET_ERR_MSG(extack, "NAT keepalive is only supported for outbound SAs"); + err = -EINVAL; + goto error; + } + + if (!x->encap || x->encap->encap_type != UDP_ENCAP_ESPINUDP) { + NL_SET_ERR_MSG(extack, + "NAT keepalive is only supported for UDP encapsulation"); + err = -EINVAL; + goto error; + } + } + error: return err; } diff --git a/net/xfrm/xfrm_user.c b/net/xfrm/xfrm_user.c index e83c687bd64e..55f039ec3d59 100644 --- a/net/xfrm/xfrm_user.c +++ b/net/xfrm/xfrm_user.c @@ -833,6 +833,10 @@ static struct xfrm_state *xfrm_state_construct(struct net *net, if (attrs[XFRMA_SA_DIR]) x->dir = nla_get_u8(attrs[XFRMA_SA_DIR]); + if (attrs[XFRMA_NAT_KEEPALIVE_INTERVAL]) + x->nat_keepalive_interval = + nla_get_u32(attrs[XFRMA_NAT_KEEPALIVE_INTERVAL]); + err = __xfrm_init_state(x, false, attrs[XFRMA_OFFLOAD_DEV], extack); if (err) goto error; @@ -1288,6 +1292,13 @@ static int copy_to_user_state_extra(struct xfrm_state *x, } if (x->dir) ret = nla_put_u8(skb, XFRMA_SA_DIR, x->dir); + + if (x->nat_keepalive_interval) { + ret = nla_put_u32(skb, XFRMA_NAT_KEEPALIVE_INTERVAL, + x->nat_keepalive_interval); + if (ret) + goto out; + } out: return ret; } @@ -2455,7 +2466,6 @@ static int xfrm_get_policy(struct sk_buff *skb, struct nlmsghdr *nlh, NETLINK_CB(skb).portid); } } else { - xfrm_dev_policy_delete(xp); xfrm_audit_policy_delete(xp, err ? 0 : 1, true); if (err != 0) @@ -3165,6 +3175,7 @@ const struct nla_policy xfrma_policy[XFRMA_MAX+1] = { [XFRMA_IF_ID] = { .type = NLA_U32 }, [XFRMA_MTIMER_THRESH] = { .type = NLA_U32 }, [XFRMA_SA_DIR] = NLA_POLICY_RANGE(NLA_U8, XFRM_SA_DIR_IN, XFRM_SA_DIR_OUT), + [XFRMA_NAT_KEEPALIVE_INTERVAL] = { .type = NLA_U32 }, }; EXPORT_SYMBOL_GPL(xfrma_policy); @@ -3474,6 +3485,9 @@ static inline unsigned int xfrm_sa_len(struct xfrm_state *x) if (x->dir) l += nla_total_size(sizeof(x->dir)); + if (x->nat_keepalive_interval) + l += nla_total_size(sizeof(x->nat_keepalive_interval)); + return l; } |