diff options
Diffstat (limited to 'net')
318 files changed, 15693 insertions, 5543 deletions
diff --git a/net/802/Kconfig b/net/802/Kconfig index be33d27c8e69..80d4bf78905d 100644 --- a/net/802/Kconfig +++ b/net/802/Kconfig @@ -5,3 +5,6 @@ config STP config GARP tristate select STP + +config MRP + tristate diff --git a/net/802/Makefile b/net/802/Makefile index a30d6e385aed..37e654d6615e 100644 --- a/net/802/Makefile +++ b/net/802/Makefile @@ -11,3 +11,4 @@ obj-$(CONFIG_IPX) += p8022.o psnap.o p8023.o obj-$(CONFIG_ATALK) += p8022.o psnap.o obj-$(CONFIG_STP) += stp.o obj-$(CONFIG_GARP) += garp.o +obj-$(CONFIG_MRP) += mrp.o diff --git a/net/802/mrp.c b/net/802/mrp.c new file mode 100644 index 000000000000..a4cc3229952a --- /dev/null +++ b/net/802/mrp.c @@ -0,0 +1,895 @@ +/* + * IEEE 802.1Q Multiple Registration Protocol (MRP) + * + * Copyright (c) 2012 Massachusetts Institute of Technology + * + * Adapted from code in net/802/garp.c + * Copyright (c) 2008 Patrick McHardy <kaber@trash.net> + * + * 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. + */ +#include <linux/kernel.h> +#include <linux/timer.h> +#include <linux/skbuff.h> +#include <linux/netdevice.h> +#include <linux/etherdevice.h> +#include <linux/rtnetlink.h> +#include <linux/slab.h> +#include <linux/module.h> +#include <net/mrp.h> +#include <asm/unaligned.h> + +static unsigned int mrp_join_time __read_mostly = 200; +module_param(mrp_join_time, uint, 0644); +MODULE_PARM_DESC(mrp_join_time, "Join time in ms (default 200ms)"); +MODULE_LICENSE("GPL"); + +static const u8 +mrp_applicant_state_table[MRP_APPLICANT_MAX + 1][MRP_EVENT_MAX + 1] = { + [MRP_APPLICANT_VO] = { + [MRP_EVENT_NEW] = MRP_APPLICANT_VN, + [MRP_EVENT_JOIN] = MRP_APPLICANT_VP, + [MRP_EVENT_LV] = MRP_APPLICANT_VO, + [MRP_EVENT_TX] = MRP_APPLICANT_VO, + [MRP_EVENT_R_NEW] = MRP_APPLICANT_VO, + [MRP_EVENT_R_JOIN_IN] = MRP_APPLICANT_AO, + [MRP_EVENT_R_IN] = MRP_APPLICANT_VO, + [MRP_EVENT_R_JOIN_MT] = MRP_APPLICANT_VO, + [MRP_EVENT_R_MT] = MRP_APPLICANT_VO, + [MRP_EVENT_R_LV] = MRP_APPLICANT_VO, + [MRP_EVENT_R_LA] = MRP_APPLICANT_VO, + [MRP_EVENT_REDECLARE] = MRP_APPLICANT_VO, + [MRP_EVENT_PERIODIC] = MRP_APPLICANT_VO, + }, + [MRP_APPLICANT_VP] = { + [MRP_EVENT_NEW] = MRP_APPLICANT_VN, + [MRP_EVENT_JOIN] = MRP_APPLICANT_VP, + [MRP_EVENT_LV] = MRP_APPLICANT_VO, + [MRP_EVENT_TX] = MRP_APPLICANT_AA, + [MRP_EVENT_R_NEW] = MRP_APPLICANT_VP, + [MRP_EVENT_R_JOIN_IN] = MRP_APPLICANT_AP, + [MRP_EVENT_R_IN] = MRP_APPLICANT_VP, + [MRP_EVENT_R_JOIN_MT] = MRP_APPLICANT_VP, + [MRP_EVENT_R_MT] = MRP_APPLICANT_VP, + [MRP_EVENT_R_LV] = MRP_APPLICANT_VP, + [MRP_EVENT_R_LA] = MRP_APPLICANT_VP, + [MRP_EVENT_REDECLARE] = MRP_APPLICANT_VP, + [MRP_EVENT_PERIODIC] = MRP_APPLICANT_VP, + }, + [MRP_APPLICANT_VN] = { + [MRP_EVENT_NEW] = MRP_APPLICANT_VN, + [MRP_EVENT_JOIN] = MRP_APPLICANT_VN, + [MRP_EVENT_LV] = MRP_APPLICANT_LA, + [MRP_EVENT_TX] = MRP_APPLICANT_AN, + [MRP_EVENT_R_NEW] = MRP_APPLICANT_VN, + [MRP_EVENT_R_JOIN_IN] = MRP_APPLICANT_VN, + [MRP_EVENT_R_IN] = MRP_APPLICANT_VN, + [MRP_EVENT_R_JOIN_MT] = MRP_APPLICANT_VN, + [MRP_EVENT_R_MT] = MRP_APPLICANT_VN, + [MRP_EVENT_R_LV] = MRP_APPLICANT_VN, + [MRP_EVENT_R_LA] = MRP_APPLICANT_VN, + [MRP_EVENT_REDECLARE] = MRP_APPLICANT_VN, + [MRP_EVENT_PERIODIC] = MRP_APPLICANT_VN, + }, + [MRP_APPLICANT_AN] = { + [MRP_EVENT_NEW] = MRP_APPLICANT_AN, + [MRP_EVENT_JOIN] = MRP_APPLICANT_AN, + [MRP_EVENT_LV] = MRP_APPLICANT_LA, + [MRP_EVENT_TX] = MRP_APPLICANT_QA, + [MRP_EVENT_R_NEW] = MRP_APPLICANT_AN, + [MRP_EVENT_R_JOIN_IN] = MRP_APPLICANT_AN, + [MRP_EVENT_R_IN] = MRP_APPLICANT_AN, + [MRP_EVENT_R_JOIN_MT] = MRP_APPLICANT_AN, + [MRP_EVENT_R_MT] = MRP_APPLICANT_AN, + [MRP_EVENT_R_LV] = MRP_APPLICANT_VN, + [MRP_EVENT_R_LA] = MRP_APPLICANT_VN, + [MRP_EVENT_REDECLARE] = MRP_APPLICANT_VN, + [MRP_EVENT_PERIODIC] = MRP_APPLICANT_AN, + }, + [MRP_APPLICANT_AA] = { + [MRP_EVENT_NEW] = MRP_APPLICANT_VN, + [MRP_EVENT_JOIN] = MRP_APPLICANT_AA, + [MRP_EVENT_LV] = MRP_APPLICANT_LA, + [MRP_EVENT_TX] = MRP_APPLICANT_QA, + [MRP_EVENT_R_NEW] = MRP_APPLICANT_AA, + [MRP_EVENT_R_JOIN_IN] = MRP_APPLICANT_QA, + [MRP_EVENT_R_IN] = MRP_APPLICANT_AA, + [MRP_EVENT_R_JOIN_MT] = MRP_APPLICANT_AA, + [MRP_EVENT_R_MT] = MRP_APPLICANT_AA, + [MRP_EVENT_R_LV] = MRP_APPLICANT_VP, + [MRP_EVENT_R_LA] = MRP_APPLICANT_VP, + [MRP_EVENT_REDECLARE] = MRP_APPLICANT_VP, + [MRP_EVENT_PERIODIC] = MRP_APPLICANT_AA, + }, + [MRP_APPLICANT_QA] = { + [MRP_EVENT_NEW] = MRP_APPLICANT_VN, + [MRP_EVENT_JOIN] = MRP_APPLICANT_QA, + [MRP_EVENT_LV] = MRP_APPLICANT_LA, + [MRP_EVENT_TX] = MRP_APPLICANT_QA, + [MRP_EVENT_R_NEW] = MRP_APPLICANT_QA, + [MRP_EVENT_R_JOIN_IN] = MRP_APPLICANT_QA, + [MRP_EVENT_R_IN] = MRP_APPLICANT_QA, + [MRP_EVENT_R_JOIN_MT] = MRP_APPLICANT_AA, + [MRP_EVENT_R_MT] = MRP_APPLICANT_AA, + [MRP_EVENT_R_LV] = MRP_APPLICANT_VP, + [MRP_EVENT_R_LA] = MRP_APPLICANT_VP, + [MRP_EVENT_REDECLARE] = MRP_APPLICANT_VP, + [MRP_EVENT_PERIODIC] = MRP_APPLICANT_AA, + }, + [MRP_APPLICANT_LA] = { + [MRP_EVENT_NEW] = MRP_APPLICANT_VN, + [MRP_EVENT_JOIN] = MRP_APPLICANT_AA, + [MRP_EVENT_LV] = MRP_APPLICANT_LA, + [MRP_EVENT_TX] = MRP_APPLICANT_VO, + [MRP_EVENT_R_NEW] = MRP_APPLICANT_LA, + [MRP_EVENT_R_JOIN_IN] = MRP_APPLICANT_LA, + [MRP_EVENT_R_IN] = MRP_APPLICANT_LA, + [MRP_EVENT_R_JOIN_MT] = MRP_APPLICANT_LA, + [MRP_EVENT_R_MT] = MRP_APPLICANT_LA, + [MRP_EVENT_R_LV] = MRP_APPLICANT_LA, + [MRP_EVENT_R_LA] = MRP_APPLICANT_LA, + [MRP_EVENT_REDECLARE] = MRP_APPLICANT_LA, + [MRP_EVENT_PERIODIC] = MRP_APPLICANT_LA, + }, + [MRP_APPLICANT_AO] = { + [MRP_EVENT_NEW] = MRP_APPLICANT_VN, + [MRP_EVENT_JOIN] = MRP_APPLICANT_AP, + [MRP_EVENT_LV] = MRP_APPLICANT_AO, + [MRP_EVENT_TX] = MRP_APPLICANT_AO, + [MRP_EVENT_R_NEW] = MRP_APPLICANT_AO, + [MRP_EVENT_R_JOIN_IN] = MRP_APPLICANT_QO, + [MRP_EVENT_R_IN] = MRP_APPLICANT_AO, + [MRP_EVENT_R_JOIN_MT] = MRP_APPLICANT_AO, + [MRP_EVENT_R_MT] = MRP_APPLICANT_AO, + [MRP_EVENT_R_LV] = MRP_APPLICANT_VO, + [MRP_EVENT_R_LA] = MRP_APPLICANT_VO, + [MRP_EVENT_REDECLARE] = MRP_APPLICANT_VO, + [MRP_EVENT_PERIODIC] = MRP_APPLICANT_AO, + }, + [MRP_APPLICANT_QO] = { + [MRP_EVENT_NEW] = MRP_APPLICANT_VN, + [MRP_EVENT_JOIN] = MRP_APPLICANT_QP, + [MRP_EVENT_LV] = MRP_APPLICANT_QO, + [MRP_EVENT_TX] = MRP_APPLICANT_QO, + [MRP_EVENT_R_NEW] = MRP_APPLICANT_QO, + [MRP_EVENT_R_JOIN_IN] = MRP_APPLICANT_QO, + [MRP_EVENT_R_IN] = MRP_APPLICANT_QO, + [MRP_EVENT_R_JOIN_MT] = MRP_APPLICANT_AO, + [MRP_EVENT_R_MT] = MRP_APPLICANT_AO, + [MRP_EVENT_R_LV] = MRP_APPLICANT_VO, + [MRP_EVENT_R_LA] = MRP_APPLICANT_VO, + [MRP_EVENT_REDECLARE] = MRP_APPLICANT_VO, + [MRP_EVENT_PERIODIC] = MRP_APPLICANT_QO, + }, + [MRP_APPLICANT_AP] = { + [MRP_EVENT_NEW] = MRP_APPLICANT_VN, + [MRP_EVENT_JOIN] = MRP_APPLICANT_AP, + [MRP_EVENT_LV] = MRP_APPLICANT_AO, + [MRP_EVENT_TX] = MRP_APPLICANT_QA, + [MRP_EVENT_R_NEW] = MRP_APPLICANT_AP, + [MRP_EVENT_R_JOIN_IN] = MRP_APPLICANT_QP, + [MRP_EVENT_R_IN] = MRP_APPLICANT_AP, + [MRP_EVENT_R_JOIN_MT] = MRP_APPLICANT_AP, + [MRP_EVENT_R_MT] = MRP_APPLICANT_AP, + [MRP_EVENT_R_LV] = MRP_APPLICANT_VP, + [MRP_EVENT_R_LA] = MRP_APPLICANT_VP, + [MRP_EVENT_REDECLARE] = MRP_APPLICANT_VP, + [MRP_EVENT_PERIODIC] = MRP_APPLICANT_AP, + }, + [MRP_APPLICANT_QP] = { + [MRP_EVENT_NEW] = MRP_APPLICANT_VN, + [MRP_EVENT_JOIN] = MRP_APPLICANT_QP, + [MRP_EVENT_LV] = MRP_APPLICANT_QO, + [MRP_EVENT_TX] = MRP_APPLICANT_QP, + [MRP_EVENT_R_NEW] = MRP_APPLICANT_QP, + [MRP_EVENT_R_JOIN_IN] = MRP_APPLICANT_QP, + [MRP_EVENT_R_IN] = MRP_APPLICANT_QP, + [MRP_EVENT_R_JOIN_MT] = MRP_APPLICANT_AP, + [MRP_EVENT_R_MT] = MRP_APPLICANT_AP, + [MRP_EVENT_R_LV] = MRP_APPLICANT_VP, + [MRP_EVENT_R_LA] = MRP_APPLICANT_VP, + [MRP_EVENT_REDECLARE] = MRP_APPLICANT_VP, + [MRP_EVENT_PERIODIC] = MRP_APPLICANT_AP, + }, +}; + +static const u8 +mrp_tx_action_table[MRP_APPLICANT_MAX + 1] = { + [MRP_APPLICANT_VO] = MRP_TX_ACTION_S_IN_OPTIONAL, + [MRP_APPLICANT_VP] = MRP_TX_ACTION_S_JOIN_IN, + [MRP_APPLICANT_VN] = MRP_TX_ACTION_S_NEW, + [MRP_APPLICANT_AN] = MRP_TX_ACTION_S_NEW, + [MRP_APPLICANT_AA] = MRP_TX_ACTION_S_JOIN_IN, + [MRP_APPLICANT_QA] = MRP_TX_ACTION_S_JOIN_IN_OPTIONAL, + [MRP_APPLICANT_LA] = MRP_TX_ACTION_S_LV, + [MRP_APPLICANT_AO] = MRP_TX_ACTION_S_IN_OPTIONAL, + [MRP_APPLICANT_QO] = MRP_TX_ACTION_S_IN_OPTIONAL, + [MRP_APPLICANT_AP] = MRP_TX_ACTION_S_JOIN_IN, + [MRP_APPLICANT_QP] = MRP_TX_ACTION_S_IN_OPTIONAL, +}; + +static void mrp_attrvalue_inc(void *value, u8 len) +{ + u8 *v = (u8 *)value; + + /* Add 1 to the last byte. If it becomes zero, + * go to the previous byte and repeat. + */ + while (len > 0 && !++v[--len]) + ; +} + +static int mrp_attr_cmp(const struct mrp_attr *attr, + const void *value, u8 len, u8 type) +{ + if (attr->type != type) + return attr->type - type; + if (attr->len != len) + return attr->len - len; + return memcmp(attr->value, value, len); +} + +static struct mrp_attr *mrp_attr_lookup(const struct mrp_applicant *app, + const void *value, u8 len, u8 type) +{ + struct rb_node *parent = app->mad.rb_node; + struct mrp_attr *attr; + int d; + + while (parent) { + attr = rb_entry(parent, struct mrp_attr, node); + d = mrp_attr_cmp(attr, value, len, type); + if (d > 0) + parent = parent->rb_left; + else if (d < 0) + parent = parent->rb_right; + else + return attr; + } + return NULL; +} + +static struct mrp_attr *mrp_attr_create(struct mrp_applicant *app, + const void *value, u8 len, u8 type) +{ + struct rb_node *parent = NULL, **p = &app->mad.rb_node; + struct mrp_attr *attr; + int d; + + while (*p) { + parent = *p; + attr = rb_entry(parent, struct mrp_attr, node); + d = mrp_attr_cmp(attr, value, len, type); + if (d > 0) + p = &parent->rb_left; + else if (d < 0) + p = &parent->rb_right; + else { + /* The attribute already exists; re-use it. */ + return attr; + } + } + attr = kmalloc(sizeof(*attr) + len, GFP_ATOMIC); + if (!attr) + return attr; + attr->state = MRP_APPLICANT_VO; + attr->type = type; + attr->len = len; + memcpy(attr->value, value, len); + + rb_link_node(&attr->node, parent, p); + rb_insert_color(&attr->node, &app->mad); + return attr; +} + +static void mrp_attr_destroy(struct mrp_applicant *app, struct mrp_attr *attr) +{ + rb_erase(&attr->node, &app->mad); + kfree(attr); +} + +static int mrp_pdu_init(struct mrp_applicant *app) +{ + struct sk_buff *skb; + struct mrp_pdu_hdr *ph; + + skb = alloc_skb(app->dev->mtu + LL_RESERVED_SPACE(app->dev), + GFP_ATOMIC); + if (!skb) + return -ENOMEM; + + skb->dev = app->dev; + skb->protocol = app->app->pkttype.type; + skb_reserve(skb, LL_RESERVED_SPACE(app->dev)); + skb_reset_network_header(skb); + skb_reset_transport_header(skb); + + ph = (struct mrp_pdu_hdr *)__skb_put(skb, sizeof(*ph)); + ph->version = app->app->version; + + app->pdu = skb; + return 0; +} + +static int mrp_pdu_append_end_mark(struct mrp_applicant *app) +{ + __be16 *endmark; + + if (skb_tailroom(app->pdu) < sizeof(*endmark)) + return -1; + endmark = (__be16 *)__skb_put(app->pdu, sizeof(*endmark)); + put_unaligned(MRP_END_MARK, endmark); + return 0; +} + +static void mrp_pdu_queue(struct mrp_applicant *app) +{ + if (!app->pdu) + return; + + if (mrp_cb(app->pdu)->mh) + mrp_pdu_append_end_mark(app); + mrp_pdu_append_end_mark(app); + + dev_hard_header(app->pdu, app->dev, ntohs(app->app->pkttype.type), + app->app->group_address, app->dev->dev_addr, + app->pdu->len); + + skb_queue_tail(&app->queue, app->pdu); + app->pdu = NULL; +} + +static void mrp_queue_xmit(struct mrp_applicant *app) +{ + struct sk_buff *skb; + + while ((skb = skb_dequeue(&app->queue))) + dev_queue_xmit(skb); +} + +static int mrp_pdu_append_msg_hdr(struct mrp_applicant *app, + u8 attrtype, u8 attrlen) +{ + struct mrp_msg_hdr *mh; + + if (mrp_cb(app->pdu)->mh) { + if (mrp_pdu_append_end_mark(app) < 0) + return -1; + mrp_cb(app->pdu)->mh = NULL; + mrp_cb(app->pdu)->vah = NULL; + } + + if (skb_tailroom(app->pdu) < sizeof(*mh)) + return -1; + mh = (struct mrp_msg_hdr *)__skb_put(app->pdu, sizeof(*mh)); + mh->attrtype = attrtype; + mh->attrlen = attrlen; + mrp_cb(app->pdu)->mh = mh; + return 0; +} + +static int mrp_pdu_append_vecattr_hdr(struct mrp_applicant *app, + const void *firstattrvalue, u8 attrlen) +{ + struct mrp_vecattr_hdr *vah; + + if (skb_tailroom(app->pdu) < sizeof(*vah) + attrlen) + return -1; + vah = (struct mrp_vecattr_hdr *)__skb_put(app->pdu, + sizeof(*vah) + attrlen); + put_unaligned(0, &vah->lenflags); + memcpy(vah->firstattrvalue, firstattrvalue, attrlen); + mrp_cb(app->pdu)->vah = vah; + memcpy(mrp_cb(app->pdu)->attrvalue, firstattrvalue, attrlen); + return 0; +} + +static int mrp_pdu_append_vecattr_event(struct mrp_applicant *app, + const struct mrp_attr *attr, + enum mrp_vecattr_event vaevent) +{ + u16 len, pos; + u8 *vaevents; + int err; +again: + if (!app->pdu) { + err = mrp_pdu_init(app); + if (err < 0) + return err; + } + + /* If there is no Message header in the PDU, or the Message header is + * for a different attribute type, add an EndMark (if necessary) and a + * new Message header to the PDU. + */ + if (!mrp_cb(app->pdu)->mh || + mrp_cb(app->pdu)->mh->attrtype != attr->type || + mrp_cb(app->pdu)->mh->attrlen != attr->len) { + if (mrp_pdu_append_msg_hdr(app, attr->type, attr->len) < 0) + goto queue; + } + + /* If there is no VectorAttribute header for this Message in the PDU, + * or this attribute's value does not sequentially follow the previous + * attribute's value, add a new VectorAttribute header to the PDU. + */ + if (!mrp_cb(app->pdu)->vah || + memcmp(mrp_cb(app->pdu)->attrvalue, attr->value, attr->len)) { + if (mrp_pdu_append_vecattr_hdr(app, attr->value, attr->len) < 0) + goto queue; + } + + len = be16_to_cpu(get_unaligned(&mrp_cb(app->pdu)->vah->lenflags)); + pos = len % 3; + + /* Events are packed into Vectors in the PDU, three to a byte. Add a + * byte to the end of the Vector if necessary. + */ + if (!pos) { + if (skb_tailroom(app->pdu) < sizeof(u8)) + goto queue; + vaevents = (u8 *)__skb_put(app->pdu, sizeof(u8)); + } else { + vaevents = (u8 *)(skb_tail_pointer(app->pdu) - sizeof(u8)); + } + + switch (pos) { + case 0: + *vaevents = vaevent * (__MRP_VECATTR_EVENT_MAX * + __MRP_VECATTR_EVENT_MAX); + break; + case 1: + *vaevents += vaevent * __MRP_VECATTR_EVENT_MAX; + break; + case 2: + *vaevents += vaevent; + break; + default: + WARN_ON(1); + } + + /* Increment the length of the VectorAttribute in the PDU, as well as + * the value of the next attribute that would continue its Vector. + */ + put_unaligned(cpu_to_be16(++len), &mrp_cb(app->pdu)->vah->lenflags); + mrp_attrvalue_inc(mrp_cb(app->pdu)->attrvalue, attr->len); + + return 0; + +queue: + mrp_pdu_queue(app); + goto again; +} + +static void mrp_attr_event(struct mrp_applicant *app, + struct mrp_attr *attr, enum mrp_event event) +{ + enum mrp_applicant_state state; + + state = mrp_applicant_state_table[attr->state][event]; + if (state == MRP_APPLICANT_INVALID) { + WARN_ON(1); + return; + } + + if (event == MRP_EVENT_TX) { + /* When appending the attribute fails, don't update its state + * in order to retry at the next TX event. + */ + + switch (mrp_tx_action_table[attr->state]) { + case MRP_TX_ACTION_NONE: + case MRP_TX_ACTION_S_JOIN_IN_OPTIONAL: + case MRP_TX_ACTION_S_IN_OPTIONAL: + break; + case MRP_TX_ACTION_S_NEW: + if (mrp_pdu_append_vecattr_event( + app, attr, MRP_VECATTR_EVENT_NEW) < 0) + return; + break; + case MRP_TX_ACTION_S_JOIN_IN: + if (mrp_pdu_append_vecattr_event( + app, attr, MRP_VECATTR_EVENT_JOIN_IN) < 0) + return; + break; + case MRP_TX_ACTION_S_LV: + if (mrp_pdu_append_vecattr_event( + app, attr, MRP_VECATTR_EVENT_LV) < 0) + return; + /* As a pure applicant, sending a leave message + * implies that the attribute was unregistered and + * can be destroyed. + */ + mrp_attr_destroy(app, attr); + return; + default: + WARN_ON(1); + } + } + + attr->state = state; +} + +int mrp_request_join(const struct net_device *dev, + const struct mrp_application *appl, + const void *value, u8 len, u8 type) +{ + struct mrp_port *port = rtnl_dereference(dev->mrp_port); + struct mrp_applicant *app = rtnl_dereference( + port->applicants[appl->type]); + struct mrp_attr *attr; + + if (sizeof(struct mrp_skb_cb) + len > + FIELD_SIZEOF(struct sk_buff, cb)) + return -ENOMEM; + + spin_lock_bh(&app->lock); + attr = mrp_attr_create(app, value, len, type); + if (!attr) { + spin_unlock_bh(&app->lock); + return -ENOMEM; + } + mrp_attr_event(app, attr, MRP_EVENT_JOIN); + spin_unlock_bh(&app->lock); + return 0; +} +EXPORT_SYMBOL_GPL(mrp_request_join); + +void mrp_request_leave(const struct net_device *dev, + const struct mrp_application *appl, + const void *value, u8 len, u8 type) +{ + struct mrp_port *port = rtnl_dereference(dev->mrp_port); + struct mrp_applicant *app = rtnl_dereference( + port->applicants[appl->type]); + struct mrp_attr *attr; + + if (sizeof(struct mrp_skb_cb) + len > + FIELD_SIZEOF(struct sk_buff, cb)) + return; + + spin_lock_bh(&app->lock); + attr = mrp_attr_lookup(app, value, len, type); + if (!attr) { + spin_unlock_bh(&app->lock); + return; + } + mrp_attr_event(app, attr, MRP_EVENT_LV); + spin_unlock_bh(&app->lock); +} +EXPORT_SYMBOL_GPL(mrp_request_leave); + +static void mrp_mad_event(struct mrp_applicant *app, enum mrp_event event) +{ + struct rb_node *node, *next; + struct mrp_attr *attr; + + for (node = rb_first(&app->mad); + next = node ? rb_next(node) : NULL, node != NULL; + node = next) { + attr = rb_entry(node, struct mrp_attr, node); + mrp_attr_event(app, attr, event); + } +} + +static void mrp_join_timer_arm(struct mrp_applicant *app) +{ + unsigned long delay; + + delay = (u64)msecs_to_jiffies(mrp_join_time) * net_random() >> 32; + mod_timer(&app->join_timer, jiffies + delay); +} + +static void mrp_join_timer(unsigned long data) +{ + struct mrp_applicant *app = (struct mrp_applicant *)data; + + spin_lock(&app->lock); + mrp_mad_event(app, MRP_EVENT_TX); + mrp_pdu_queue(app); + spin_unlock(&app->lock); + + mrp_queue_xmit(app); + mrp_join_timer_arm(app); +} + +static int mrp_pdu_parse_end_mark(struct sk_buff *skb, int *offset) +{ + __be16 endmark; + + if (skb_copy_bits(skb, *offset, &endmark, sizeof(endmark)) < 0) + return -1; + if (endmark == MRP_END_MARK) { + *offset += sizeof(endmark); + return -1; + } + return 0; +} + +static void mrp_pdu_parse_vecattr_event(struct mrp_applicant *app, + struct sk_buff *skb, + enum mrp_vecattr_event vaevent) +{ + struct mrp_attr *attr; + enum mrp_event event; + + attr = mrp_attr_lookup(app, mrp_cb(skb)->attrvalue, + mrp_cb(skb)->mh->attrlen, + mrp_cb(skb)->mh->attrtype); + if (attr == NULL) + return; + + switch (vaevent) { + case MRP_VECATTR_EVENT_NEW: + event = MRP_EVENT_R_NEW; + break; + case MRP_VECATTR_EVENT_JOIN_IN: + event = MRP_EVENT_R_JOIN_IN; + break; + case MRP_VECATTR_EVENT_IN: + event = MRP_EVENT_R_IN; + break; + case MRP_VECATTR_EVENT_JOIN_MT: + event = MRP_EVENT_R_JOIN_MT; + break; + case MRP_VECATTR_EVENT_MT: + event = MRP_EVENT_R_MT; + break; + case MRP_VECATTR_EVENT_LV: + event = MRP_EVENT_R_LV; + break; + default: + return; + } + + mrp_attr_event(app, attr, event); +} + +static int mrp_pdu_parse_vecattr(struct mrp_applicant *app, + struct sk_buff *skb, int *offset) +{ + struct mrp_vecattr_hdr _vah; + u16 valen; + u8 vaevents, vaevent; + + mrp_cb(skb)->vah = skb_header_pointer(skb, *offset, sizeof(_vah), + &_vah); + if (!mrp_cb(skb)->vah) + return -1; + *offset += sizeof(_vah); + + if (get_unaligned(&mrp_cb(skb)->vah->lenflags) & + MRP_VECATTR_HDR_FLAG_LA) + mrp_mad_event(app, MRP_EVENT_R_LA); + valen = be16_to_cpu(get_unaligned(&mrp_cb(skb)->vah->lenflags) & + MRP_VECATTR_HDR_LEN_MASK); + + /* The VectorAttribute structure in a PDU carries event information + * about one or more attributes having consecutive values. Only the + * value for the first attribute is contained in the structure. So + * we make a copy of that value, and then increment it each time we + * advance to the next event in its Vector. + */ + if (sizeof(struct mrp_skb_cb) + mrp_cb(skb)->mh->attrlen > + FIELD_SIZEOF(struct sk_buff, cb)) + return -1; + if (skb_copy_bits(skb, *offset, mrp_cb(skb)->attrvalue, + mrp_cb(skb)->mh->attrlen) < 0) + return -1; + *offset += mrp_cb(skb)->mh->attrlen; + + /* In a VectorAttribute, the Vector contains events which are packed + * three to a byte. We process one byte of the Vector at a time. + */ + while (valen > 0) { + if (skb_copy_bits(skb, *offset, &vaevents, + sizeof(vaevents)) < 0) + return -1; + *offset += sizeof(vaevents); + + /* Extract and process the first event. */ + vaevent = vaevents / (__MRP_VECATTR_EVENT_MAX * + __MRP_VECATTR_EVENT_MAX); + if (vaevent >= __MRP_VECATTR_EVENT_MAX) { + /* The byte is malformed; stop processing. */ + return -1; + } + mrp_pdu_parse_vecattr_event(app, skb, vaevent); + + /* If present, extract and process the second event. */ + if (!--valen) + break; + mrp_attrvalue_inc(mrp_cb(skb)->attrvalue, + mrp_cb(skb)->mh->attrlen); + vaevents %= (__MRP_VECATTR_EVENT_MAX * + __MRP_VECATTR_EVENT_MAX); + vaevent = vaevents / __MRP_VECATTR_EVENT_MAX; + mrp_pdu_parse_vecattr_event(app, skb, vaevent); + + /* If present, extract and process the third event. */ + if (!--valen) + break; + mrp_attrvalue_inc(mrp_cb(skb)->attrvalue, + mrp_cb(skb)->mh->attrlen); + vaevents %= __MRP_VECATTR_EVENT_MAX; + vaevent = vaevents; + mrp_pdu_parse_vecattr_event(app, skb, vaevent); + } + return 0; +} + +static int mrp_pdu_parse_msg(struct mrp_applicant *app, struct sk_buff *skb, + int *offset) +{ + struct mrp_msg_hdr _mh; + + mrp_cb(skb)->mh = skb_header_pointer(skb, *offset, sizeof(_mh), &_mh); + if (!mrp_cb(skb)->mh) + return -1; + *offset += sizeof(_mh); + + if (mrp_cb(skb)->mh->attrtype == 0 || + mrp_cb(skb)->mh->attrtype > app->app->maxattr || + mrp_cb(skb)->mh->attrlen == 0) + return -1; + + while (skb->len > *offset) { + if (mrp_pdu_parse_end_mark(skb, offset) < 0) + break; + if (mrp_pdu_parse_vecattr(app, skb, offset) < 0) + return -1; + } + return 0; +} + +static int mrp_rcv(struct sk_buff *skb, struct net_device *dev, + struct packet_type *pt, struct net_device *orig_dev) +{ + struct mrp_application *appl = container_of(pt, struct mrp_application, + pkttype); + struct mrp_port *port; + struct mrp_applicant *app; + struct mrp_pdu_hdr _ph; + const struct mrp_pdu_hdr *ph; + int offset = skb_network_offset(skb); + + /* If the interface is in promiscuous mode, drop the packet if + * it was unicast to another host. + */ + if (unlikely(skb->pkt_type == PACKET_OTHERHOST)) + goto out; + skb = skb_share_check(skb, GFP_ATOMIC); + if (unlikely(!skb)) + goto out; + port = rcu_dereference(dev->mrp_port); + if (unlikely(!port)) + goto out; + app = rcu_dereference(port->applicants[appl->type]); + if (unlikely(!app)) + goto out; + + ph = skb_header_pointer(skb, offset, sizeof(_ph), &_ph); + if (!ph) + goto out; + offset += sizeof(_ph); + + if (ph->version != app->app->version) + goto out; + + spin_lock(&app->lock); + while (skb->len > offset) { + if (mrp_pdu_parse_end_mark(skb, &offset) < 0) + break; + if (mrp_pdu_parse_msg(app, skb, &offset) < 0) + break; + } + spin_unlock(&app->lock); +out: + kfree_skb(skb); + return 0; +} + +static int mrp_init_port(struct net_device *dev) +{ + struct mrp_port *port; + + port = kzalloc(sizeof(*port), GFP_KERNEL); + if (!port) + return -ENOMEM; + rcu_assign_pointer(dev->mrp_port, port); + return 0; +} + +static void mrp_release_port(struct net_device *dev) +{ + struct mrp_port *port = rtnl_dereference(dev->mrp_port); + unsigned int i; + + for (i = 0; i <= MRP_APPLICATION_MAX; i++) { + if (rtnl_dereference(port->applicants[i])) + return; + } + RCU_INIT_POINTER(dev->mrp_port, NULL); + kfree_rcu(port, rcu); +} + +int mrp_init_applicant(struct net_device *dev, struct mrp_application *appl) +{ + struct mrp_applicant *app; + int err; + + ASSERT_RTNL(); + + if (!rtnl_dereference(dev->mrp_port)) { + err = mrp_init_port(dev); + if (err < 0) + goto err1; + } + + err = -ENOMEM; + app = kzalloc(sizeof(*app), GFP_KERNEL); + if (!app) + goto err2; + + err = dev_mc_add(dev, appl->group_address); + if (err < 0) + goto err3; + + app->dev = dev; + app->app = appl; + app->mad = RB_ROOT; + spin_lock_init(&app->lock); + skb_queue_head_init(&app->queue); + rcu_assign_pointer(dev->mrp_port->applicants[appl->type], app); + setup_timer(&app->join_timer, mrp_join_timer, (unsigned long)app); + mrp_join_timer_arm(app); + return 0; + +err3: + kfree(app); +err2: + mrp_release_port(dev); +err1: + return err; +} +EXPORT_SYMBOL_GPL(mrp_init_applicant); + +void mrp_uninit_applicant(struct net_device *dev, struct mrp_application *appl) +{ + struct mrp_port *port = rtnl_dereference(dev->mrp_port); + struct mrp_applicant *app = rtnl_dereference( + port->applicants[appl->type]); + + ASSERT_RTNL(); + + RCU_INIT_POINTER(port->applicants[appl->type], NULL); + + /* Delete timer and generate a final TX event to flush out + * all pending messages before the applicant is gone. + */ + del_timer_sync(&app->join_timer); + mrp_mad_event(app, MRP_EVENT_TX); + mrp_pdu_queue(app); + mrp_queue_xmit(app); + + dev_mc_del(dev, appl->group_address); + kfree_rcu(app, rcu); + mrp_release_port(dev); +} +EXPORT_SYMBOL_GPL(mrp_uninit_applicant); + +int mrp_register_application(struct mrp_application *appl) +{ + appl->pkttype.func = mrp_rcv; + dev_add_pack(&appl->pkttype); + return 0; +} +EXPORT_SYMBOL_GPL(mrp_register_application); + +void mrp_unregister_application(struct mrp_application *appl) +{ + dev_remove_pack(&appl->pkttype); +} +EXPORT_SYMBOL_GPL(mrp_unregister_application); diff --git a/net/8021q/Kconfig b/net/8021q/Kconfig index fa073a54963e..8f7517df41a5 100644 --- a/net/8021q/Kconfig +++ b/net/8021q/Kconfig @@ -27,3 +27,14 @@ config VLAN_8021Q_GVRP automatic propagation of registered VLANs to switches. If unsure, say N. + +config VLAN_8021Q_MVRP + bool "MVRP (Multiple VLAN Registration Protocol) support" + depends on VLAN_8021Q + select MRP + help + Select this to enable MVRP end-system support. MVRP is used for + automatic propagation of registered VLANs to switches; it + supersedes GVRP and is not backwards-compatible. + + If unsure, say N. diff --git a/net/8021q/Makefile b/net/8021q/Makefile index 9f4f174ead1c..7bc8db08d7ef 100644 --- a/net/8021q/Makefile +++ b/net/8021q/Makefile @@ -6,5 +6,6 @@ obj-$(CONFIG_VLAN_8021Q) += 8021q.o 8021q-y := vlan.o vlan_dev.o vlan_netlink.o 8021q-$(CONFIG_VLAN_8021Q_GVRP) += vlan_gvrp.o +8021q-$(CONFIG_VLAN_8021Q_MVRP) += vlan_mvrp.o 8021q-$(CONFIG_PROC_FS) += vlanproc.o diff --git a/net/8021q/vlan.c b/net/8021q/vlan.c index a292e8050ef2..a18714469bf7 100644 --- a/net/8021q/vlan.c +++ b/net/8021q/vlan.c @@ -95,6 +95,8 @@ void unregister_vlan_dev(struct net_device *dev, struct list_head *head) grp->nr_vlan_devs--; + if (vlan->flags & VLAN_FLAG_MVRP) + vlan_mvrp_request_leave(dev); if (vlan->flags & VLAN_FLAG_GVRP) vlan_gvrp_request_leave(dev); @@ -105,8 +107,12 @@ void unregister_vlan_dev(struct net_device *dev, struct list_head *head) */ unregister_netdevice_queue(dev, head); - if (grp->nr_vlan_devs == 0) + netdev_upper_dev_unlink(real_dev, dev); + + if (grp->nr_vlan_devs == 0) { + vlan_mvrp_uninit_applicant(real_dev); vlan_gvrp_uninit_applicant(real_dev); + } /* Get rid of the vlan's reference to real_dev */ dev_put(real_dev); @@ -115,19 +121,12 @@ void unregister_vlan_dev(struct net_device *dev, struct list_head *head) int vlan_check_real_dev(struct net_device *real_dev, u16 vlan_id) { const char *name = real_dev->name; - const struct net_device_ops *ops = real_dev->netdev_ops; if (real_dev->features & NETIF_F_VLAN_CHALLENGED) { pr_info("VLANs not supported on %s\n", name); return -EOPNOTSUPP; } - if ((real_dev->features & NETIF_F_HW_VLAN_FILTER) && - (!ops->ndo_vlan_rx_add_vid || !ops->ndo_vlan_rx_kill_vid)) { - pr_info("Device %s has buggy VLAN hw accel\n", name); - return -EOPNOTSUPP; - } - if (vlan_find_dev(real_dev, vlan_id) != NULL) return -EEXIST; @@ -156,15 +155,22 @@ int register_vlan_dev(struct net_device *dev) err = vlan_gvrp_init_applicant(real_dev); if (err < 0) goto out_vid_del; + err = vlan_mvrp_init_applicant(real_dev); + if (err < 0) + goto out_uninit_gvrp; } err = vlan_group_prealloc_vid(grp, vlan_id); if (err < 0) - goto out_uninit_applicant; + goto out_uninit_mvrp; + + err = netdev_upper_dev_link(real_dev, dev); + if (err) + goto out_uninit_mvrp; err = register_netdevice(dev); if (err < 0) - goto out_uninit_applicant; + goto out_upper_dev_unlink; /* Account for reference in struct vlan_dev_priv */ dev_hold(real_dev); @@ -180,7 +186,12 @@ int register_vlan_dev(struct net_device *dev) return 0; -out_uninit_applicant: +out_upper_dev_unlink: + netdev_upper_dev_unlink(real_dev, dev); +out_uninit_mvrp: + if (grp->nr_vlan_devs == 0) + vlan_mvrp_uninit_applicant(real_dev); +out_uninit_gvrp: if (grp->nr_vlan_devs == 0) vlan_gvrp_uninit_applicant(real_dev); out_vid_del: @@ -654,13 +665,19 @@ static int __init vlan_proto_init(void) if (err < 0) goto err3; - err = vlan_netlink_init(); + err = vlan_mvrp_init(); if (err < 0) goto err4; + err = vlan_netlink_init(); + if (err < 0) + goto err5; + vlan_ioctl_set(vlan_ioctl_handler); return 0; +err5: + vlan_mvrp_uninit(); err4: vlan_gvrp_uninit(); err3: @@ -681,6 +698,7 @@ static void __exit vlan_cleanup_module(void) unregister_pernet_subsys(&vlan_net_ops); rcu_barrier(); /* Wait for completion of call_rcu()'s */ + vlan_mvrp_uninit(); vlan_gvrp_uninit(); } diff --git a/net/8021q/vlan.h b/net/8021q/vlan.h index a4886d94c40c..670f1e8cfc0f 100644 --- a/net/8021q/vlan.h +++ b/net/8021q/vlan.h @@ -171,6 +171,22 @@ static inline int vlan_gvrp_init(void) { return 0; } static inline void vlan_gvrp_uninit(void) {} #endif +#ifdef CONFIG_VLAN_8021Q_MVRP +extern int vlan_mvrp_request_join(const struct net_device *dev); +extern void vlan_mvrp_request_leave(const struct net_device *dev); +extern int vlan_mvrp_init_applicant(struct net_device *dev); +extern void vlan_mvrp_uninit_applicant(struct net_device *dev); +extern int vlan_mvrp_init(void); +extern void vlan_mvrp_uninit(void); +#else +static inline int vlan_mvrp_request_join(const struct net_device *dev) { return 0; } +static inline void vlan_mvrp_request_leave(const struct net_device *dev) {} +static inline int vlan_mvrp_init_applicant(struct net_device *dev) { return 0; } +static inline void vlan_mvrp_uninit_applicant(struct net_device *dev) {} +static inline int vlan_mvrp_init(void) { return 0; } +static inline void vlan_mvrp_uninit(void) {} +#endif + extern const char vlan_fullname[]; extern const char vlan_version[]; extern int vlan_netlink_init(void); diff --git a/net/8021q/vlan_core.c b/net/8021q/vlan_core.c index 65e06abe023f..f3b6f515eba6 100644 --- a/net/8021q/vlan_core.c +++ b/net/8021q/vlan_core.c @@ -60,21 +60,25 @@ bool vlan_do_receive(struct sk_buff **skbp) return true; } -/* Must be invoked with rcu_read_lock or with RTNL. */ -struct net_device *__vlan_find_dev_deep(struct net_device *real_dev, +/* Must be invoked with rcu_read_lock. */ +struct net_device *__vlan_find_dev_deep(struct net_device *dev, u16 vlan_id) { - struct vlan_info *vlan_info = rcu_dereference_rtnl(real_dev->vlan_info); + struct vlan_info *vlan_info = rcu_dereference(dev->vlan_info); if (vlan_info) { return vlan_group_get_device(&vlan_info->grp, vlan_id); } else { /* - * Bonding slaves do not have grp assigned to themselves. - * Grp is assigned to bonding master instead. + * Lower devices of master uppers (bonding, team) do not have + * grp assigned to themselves. Grp is assigned to upper device + * instead. */ - if (netif_is_bond_slave(real_dev)) - return __vlan_find_dev_deep(real_dev->master, vlan_id); + struct net_device *upper_dev; + + upper_dev = netdev_master_upper_dev_get_rcu(dev); + if (upper_dev) + return __vlan_find_dev_deep(upper_dev, vlan_id); } return NULL; @@ -140,6 +144,7 @@ err_free: kfree_skb(skb); return NULL; } +EXPORT_SYMBOL(vlan_untag); /* @@ -220,8 +225,7 @@ static int __vlan_vid_add(struct vlan_info *vlan_info, unsigned short vid, if (!vid_info) return -ENOMEM; - if ((dev->features & NETIF_F_HW_VLAN_FILTER) && - ops->ndo_vlan_rx_add_vid) { + if (dev->features & NETIF_F_HW_VLAN_FILTER) { err = ops->ndo_vlan_rx_add_vid(dev, vid); if (err) { kfree(vid_info); @@ -278,8 +282,7 @@ static void __vlan_vid_del(struct vlan_info *vlan_info, unsigned short vid = vid_info->vid; int err; - if ((dev->features & NETIF_F_HW_VLAN_FILTER) && - ops->ndo_vlan_rx_kill_vid) { + if (dev->features & NETIF_F_HW_VLAN_FILTER) { err = ops->ndo_vlan_rx_kill_vid(dev, vid); if (err) { pr_warn("failed to kill vid %d for device %s\n", diff --git a/net/8021q/vlan_dev.c b/net/8021q/vlan_dev.c index 4a6d31a082b9..19cf81bf9f69 100644 --- a/net/8021q/vlan_dev.c +++ b/net/8021q/vlan_dev.c @@ -261,7 +261,7 @@ int vlan_dev_change_flags(const struct net_device *dev, u32 flags, u32 mask) u32 old_flags = vlan->flags; if (mask & ~(VLAN_FLAG_REORDER_HDR | VLAN_FLAG_GVRP | - VLAN_FLAG_LOOSE_BINDING)) + VLAN_FLAG_LOOSE_BINDING | VLAN_FLAG_MVRP)) return -EINVAL; vlan->flags = (old_flags & ~mask) | (flags & mask); @@ -272,6 +272,13 @@ int vlan_dev_change_flags(const struct net_device *dev, u32 flags, u32 mask) else vlan_gvrp_request_leave(dev); } + + if (netif_running(dev) && (vlan->flags ^ old_flags) & VLAN_FLAG_MVRP) { + if (vlan->flags & VLAN_FLAG_MVRP) + vlan_mvrp_request_join(dev); + else + vlan_mvrp_request_leave(dev); + } return 0; } @@ -312,6 +319,9 @@ static int vlan_dev_open(struct net_device *dev) if (vlan->flags & VLAN_FLAG_GVRP) vlan_gvrp_request_join(dev); + if (vlan->flags & VLAN_FLAG_MVRP) + vlan_mvrp_request_join(dev); + if (netif_carrier_ok(real_dev)) netif_carrier_on(dev); return 0; @@ -640,9 +650,9 @@ static int vlan_ethtool_get_settings(struct net_device *dev, static void vlan_ethtool_get_drvinfo(struct net_device *dev, struct ethtool_drvinfo *info) { - strcpy(info->driver, vlan_fullname); - strcpy(info->version, vlan_version); - strcpy(info->fw_version, "N/A"); + strlcpy(info->driver, vlan_fullname, sizeof(info->driver)); + strlcpy(info->version, vlan_version, sizeof(info->version)); + strlcpy(info->fw_version, "N/A", sizeof(info->fw_version)); } static struct rtnl_link_stats64 *vlan_dev_get_stats64(struct net_device *dev, struct rtnl_link_stats64 *stats) @@ -723,7 +733,7 @@ static void vlan_dev_netpoll_cleanup(struct net_device *dev) vlan->netpoll = NULL; - __netpoll_free_rcu(netpoll); + __netpoll_free_async(netpoll); } #endif /* CONFIG_NET_POLL_CONTROLLER */ diff --git a/net/8021q/vlan_mvrp.c b/net/8021q/vlan_mvrp.c new file mode 100644 index 000000000000..d9ec1d5964aa --- /dev/null +++ b/net/8021q/vlan_mvrp.c @@ -0,0 +1,72 @@ +/* + * IEEE 802.1Q Multiple VLAN Registration Protocol (MVRP) + * + * Copyright (c) 2012 Massachusetts Institute of Technology + * + * Adapted from code in net/8021q/vlan_gvrp.c + * Copyright (c) 2008 Patrick McHardy <kaber@trash.net> + * + * 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. + */ +#include <linux/types.h> +#include <linux/if_ether.h> +#include <linux/if_vlan.h> +#include <net/mrp.h> +#include "vlan.h" + +#define MRP_MVRP_ADDRESS { 0x01, 0x80, 0xc2, 0x00, 0x00, 0x21 } + +enum mvrp_attributes { + MVRP_ATTR_INVALID, + MVRP_ATTR_VID, + __MVRP_ATTR_MAX +}; +#define MVRP_ATTR_MAX (__MVRP_ATTR_MAX - 1) + +static struct mrp_application vlan_mrp_app __read_mostly = { + .type = MRP_APPLICATION_MVRP, + .maxattr = MVRP_ATTR_MAX, + .pkttype.type = htons(ETH_P_MVRP), + .group_address = MRP_MVRP_ADDRESS, + .version = 0, +}; + +int vlan_mvrp_request_join(const struct net_device *dev) +{ + const struct vlan_dev_priv *vlan = vlan_dev_priv(dev); + __be16 vlan_id = htons(vlan->vlan_id); + + return mrp_request_join(vlan->real_dev, &vlan_mrp_app, + &vlan_id, sizeof(vlan_id), MVRP_ATTR_VID); +} + +void vlan_mvrp_request_leave(const struct net_device *dev) +{ + const struct vlan_dev_priv *vlan = vlan_dev_priv(dev); + __be16 vlan_id = htons(vlan->vlan_id); + + mrp_request_leave(vlan->real_dev, &vlan_mrp_app, + &vlan_id, sizeof(vlan_id), MVRP_ATTR_VID); +} + +int vlan_mvrp_init_applicant(struct net_device *dev) +{ + return mrp_init_applicant(dev, &vlan_mrp_app); +} + +void vlan_mvrp_uninit_applicant(struct net_device *dev) +{ + mrp_uninit_applicant(dev, &vlan_mrp_app); +} + +int __init vlan_mvrp_init(void) +{ + return mrp_register_application(&vlan_mrp_app); +} + +void vlan_mvrp_uninit(void) +{ + mrp_unregister_application(&vlan_mrp_app); +} diff --git a/net/8021q/vlan_netlink.c b/net/8021q/vlan_netlink.c index 708c80ea1874..1789658b7cd7 100644 --- a/net/8021q/vlan_netlink.c +++ b/net/8021q/vlan_netlink.c @@ -62,7 +62,7 @@ static int vlan_validate(struct nlattr *tb[], struct nlattr *data[]) flags = nla_data(data[IFLA_VLAN_FLAGS]); if ((flags->flags & flags->mask) & ~(VLAN_FLAG_REORDER_HDR | VLAN_FLAG_GVRP | - VLAN_FLAG_LOOSE_BINDING)) + VLAN_FLAG_LOOSE_BINDING | VLAN_FLAG_MVRP)) return -EINVAL; } diff --git a/net/Kconfig b/net/Kconfig index 30b48f523135..5a1888bb036d 100644 --- a/net/Kconfig +++ b/net/Kconfig @@ -209,7 +209,6 @@ source "net/ipx/Kconfig" source "drivers/net/appletalk/Kconfig" source "net/x25/Kconfig" source "net/lapb/Kconfig" -source "net/wanrouter/Kconfig" source "net/phonet/Kconfig" source "net/ieee802154/Kconfig" source "net/mac802154/Kconfig" @@ -218,6 +217,7 @@ source "net/dcb/Kconfig" source "net/dns_resolver/Kconfig" source "net/batman-adv/Kconfig" source "net/openvswitch/Kconfig" +source "net/vmw_vsock/Kconfig" config RPS boolean @@ -232,7 +232,7 @@ config RFS_ACCEL config XPS boolean - depends on SMP && SYSFS && USE_GENERIC_SMP_HELPERS + depends on SMP && USE_GENERIC_SMP_HELPERS default y config NETPRIO_CGROUP diff --git a/net/Makefile b/net/Makefile index 4f4ee083064c..091e7b04f301 100644 --- a/net/Makefile +++ b/net/Makefile @@ -26,7 +26,6 @@ obj-$(CONFIG_BRIDGE) += bridge/ obj-$(CONFIG_NET_DSA) += dsa/ obj-$(CONFIG_IPX) += ipx/ obj-$(CONFIG_ATALK) += appletalk/ -obj-$(CONFIG_WAN_ROUTER) += wanrouter/ obj-$(CONFIG_X25) += x25/ obj-$(CONFIG_LAPB) += lapb/ obj-$(CONFIG_NETROM) += netrom/ @@ -70,3 +69,4 @@ obj-$(CONFIG_CEPH_LIB) += ceph/ obj-$(CONFIG_BATMAN_ADV) += batman-adv/ obj-$(CONFIG_NFC) += nfc/ obj-$(CONFIG_OPENVSWITCH) += openvswitch/ +obj-$(CONFIG_VSOCKETS) += vmw_vsock/ diff --git a/net/batman-adv/bat_algo.h b/net/batman-adv/bat_algo.h index a0ba3bff9b36..a4808c29ea3d 100644 --- a/net/batman-adv/bat_algo.h +++ b/net/batman-adv/bat_algo.h @@ -1,4 +1,4 @@ -/* Copyright (C) 2011-2012 B.A.T.M.A.N. contributors: +/* Copyright (C) 2011-2013 B.A.T.M.A.N. contributors: * * Marek Lindner * diff --git a/net/batman-adv/bat_iv_ogm.c b/net/batman-adv/bat_iv_ogm.c index 9f3925a85aab..72fe1bbf7721 100644 --- a/net/batman-adv/bat_iv_ogm.c +++ b/net/batman-adv/bat_iv_ogm.c @@ -1,4 +1,4 @@ -/* Copyright (C) 2007-2012 B.A.T.M.A.N. contributors: +/* Copyright (C) 2007-2013 B.A.T.M.A.N. contributors: * * Marek Lindner, Simon Wunderlich * @@ -123,7 +123,7 @@ batadv_iv_ogm_emit_send_time(const struct batadv_priv *bat_priv) unsigned int msecs; msecs = atomic_read(&bat_priv->orig_interval) - BATADV_JITTER; - msecs += (random32() % 2 * BATADV_JITTER); + msecs += prandom_u32() % (2 * BATADV_JITTER); return jiffies + msecs_to_jiffies(msecs); } @@ -131,7 +131,7 @@ batadv_iv_ogm_emit_send_time(const struct batadv_priv *bat_priv) /* when do we schedule a ogm packet to be sent */ static unsigned long batadv_iv_ogm_fwd_send_time(void) { - return jiffies + msecs_to_jiffies(random32() % (BATADV_JITTER / 2)); + return jiffies + msecs_to_jiffies(prandom_u32() % (BATADV_JITTER / 2)); } /* apply hop penalty for a normal link */ @@ -183,7 +183,6 @@ static void batadv_iv_ogm_send_to_if(struct batadv_forw_packet *forw_packet, /* adjust all flags and log packets */ while (batadv_iv_ogm_aggr_packet(buff_pos, forw_packet->packet_len, batadv_ogm_packet->tt_num_changes)) { - /* we might have aggregated direct link packets with an * ordinary base packet */ @@ -261,7 +260,6 @@ static void batadv_iv_ogm_emit(struct batadv_forw_packet *forw_packet) */ if ((directlink && (batadv_ogm_packet->header.ttl == 1)) || (forw_packet->own && (forw_packet->if_incoming != primary_if))) { - /* FIXME: what about aggregated packets ? */ batadv_dbg(BATADV_DBG_BATMAN, bat_priv, "%s packet (originator %pM, seqno %u, TTL %d) on interface %s [%pM]\n", @@ -325,7 +323,6 @@ batadv_iv_ogm_can_aggregate(const struct batadv_ogm_packet *new_bat_ogm_packet, if (time_before(send_time, forw_packet->send_time) && time_after_eq(aggregation_end_time, forw_packet->send_time) && (aggregated_bytes <= BATADV_MAX_AGGREGATION_BYTES)) { - /* check aggregation compatibility * -> direct link packets are broadcasted on * their interface only @@ -815,7 +812,6 @@ static int batadv_iv_ogm_calc_tq(struct batadv_orig_node *orig_node, rcu_read_lock(); hlist_for_each_entry_rcu(tmp_neigh_node, node, &orig_neigh_node->neigh_list, list) { - if (!batadv_compare_eth(tmp_neigh_node->addr, orig_neigh_node->orig)) continue; @@ -949,7 +945,6 @@ batadv_iv_ogm_update_seqnos(const struct ethhdr *ethhdr, rcu_read_lock(); hlist_for_each_entry_rcu(tmp_neigh_node, node, &orig_node->neigh_list, list) { - is_duplicate |= batadv_test_bit(tmp_neigh_node->real_bits, orig_node->last_real_seqno, seqno); @@ -1033,7 +1028,7 @@ static void batadv_iv_ogm_process(const struct ethhdr *ethhdr, is_single_hop_neigh = true; batadv_dbg(BATADV_DBG_BATMAN, bat_priv, - "Received BATMAN packet via NB: %pM, IF: %s [%pM] (from OG: %pM, via prev OG: %pM, seqno %u, ttvn %u, crc %u, changes %u, td %d, TTL %d, V %d, IDF %d)\n", + "Received BATMAN packet via NB: %pM, IF: %s [%pM] (from OG: %pM, via prev OG: %pM, seqno %u, ttvn %u, crc %#.4x, changes %u, tq %d, TTL %d, V %d, IDF %d)\n", ethhdr->h_source, if_incoming->net_dev->name, if_incoming->net_dev->dev_addr, batadv_ogm_packet->orig, batadv_ogm_packet->prev_sender, @@ -1223,7 +1218,6 @@ static void batadv_iv_ogm_process(const struct ethhdr *ethhdr, /* is single hop (direct) neighbor */ if (is_single_hop_neigh) { - /* mark direct link on incoming interface */ batadv_iv_ogm_forward(orig_node, ethhdr, batadv_ogm_packet, is_single_hop_neigh, diff --git a/net/batman-adv/bitarray.c b/net/batman-adv/bitarray.c index 5453b17d8df2..973982414d58 100644 --- a/net/batman-adv/bitarray.c +++ b/net/batman-adv/bitarray.c @@ -1,4 +1,4 @@ -/* Copyright (C) 2006-2012 B.A.T.M.A.N. contributors: +/* Copyright (C) 2006-2013 B.A.T.M.A.N. contributors: * * Simon Wunderlich, Marek Lindner * diff --git a/net/batman-adv/bitarray.h b/net/batman-adv/bitarray.h index cebaae7e148b..a81b9322e382 100644 --- a/net/batman-adv/bitarray.h +++ b/net/batman-adv/bitarray.h @@ -1,4 +1,4 @@ -/* Copyright (C) 2006-2012 B.A.T.M.A.N. contributors: +/* Copyright (C) 2006-2013 B.A.T.M.A.N. contributors: * * Simon Wunderlich, Marek Lindner * diff --git a/net/batman-adv/bridge_loop_avoidance.c b/net/batman-adv/bridge_loop_avoidance.c index 5aebe9327d68..30f46526cbbd 100644 --- a/net/batman-adv/bridge_loop_avoidance.c +++ b/net/batman-adv/bridge_loop_avoidance.c @@ -1,4 +1,4 @@ -/* Copyright (C) 2011-2012 B.A.T.M.A.N. contributors: +/* Copyright (C) 2011-2013 B.A.T.M.A.N. contributors: * * Simon Wunderlich * @@ -34,13 +34,14 @@ static const uint8_t batadv_announce_mac[4] = {0x43, 0x05, 0x43, 0x05}; static void batadv_bla_periodic_work(struct work_struct *work); -static void batadv_bla_send_announce(struct batadv_priv *bat_priv, - struct batadv_backbone_gw *backbone_gw); +static void +batadv_bla_send_announce(struct batadv_priv *bat_priv, + struct batadv_bla_backbone_gw *backbone_gw); /* return the index of the claim */ static inline uint32_t batadv_choose_claim(const void *data, uint32_t size) { - struct batadv_claim *claim = (struct batadv_claim *)data; + struct batadv_bla_claim *claim = (struct batadv_bla_claim *)data; uint32_t hash = 0; hash = batadv_hash_bytes(hash, &claim->addr, sizeof(claim->addr)); @@ -57,7 +58,7 @@ static inline uint32_t batadv_choose_claim(const void *data, uint32_t size) static inline uint32_t batadv_choose_backbone_gw(const void *data, uint32_t size) { - struct batadv_claim *claim = (struct batadv_claim *)data; + const struct batadv_bla_claim *claim = (struct batadv_bla_claim *)data; uint32_t hash = 0; hash = batadv_hash_bytes(hash, &claim->addr, sizeof(claim->addr)); @@ -75,9 +76,9 @@ static inline uint32_t batadv_choose_backbone_gw(const void *data, static int batadv_compare_backbone_gw(const struct hlist_node *node, const void *data2) { - const void *data1 = container_of(node, struct batadv_backbone_gw, + const void *data1 = container_of(node, struct batadv_bla_backbone_gw, hash_entry); - const struct batadv_backbone_gw *gw1 = data1, *gw2 = data2; + const struct batadv_bla_backbone_gw *gw1 = data1, *gw2 = data2; if (!batadv_compare_eth(gw1->orig, gw2->orig)) return 0; @@ -92,9 +93,9 @@ static int batadv_compare_backbone_gw(const struct hlist_node *node, static int batadv_compare_claim(const struct hlist_node *node, const void *data2) { - const void *data1 = container_of(node, struct batadv_claim, + const void *data1 = container_of(node, struct batadv_bla_claim, hash_entry); - const struct batadv_claim *cl1 = data1, *cl2 = data2; + const struct batadv_bla_claim *cl1 = data1, *cl2 = data2; if (!batadv_compare_eth(cl1->addr, cl2->addr)) return 0; @@ -106,7 +107,8 @@ static int batadv_compare_claim(const struct hlist_node *node, } /* free a backbone gw */ -static void batadv_backbone_gw_free_ref(struct batadv_backbone_gw *backbone_gw) +static void +batadv_backbone_gw_free_ref(struct batadv_bla_backbone_gw *backbone_gw) { if (atomic_dec_and_test(&backbone_gw->refcount)) kfree_rcu(backbone_gw, rcu); @@ -115,16 +117,16 @@ static void batadv_backbone_gw_free_ref(struct batadv_backbone_gw *backbone_gw) /* finally deinitialize the claim */ static void batadv_claim_free_rcu(struct rcu_head *rcu) { - struct batadv_claim *claim; + struct batadv_bla_claim *claim; - claim = container_of(rcu, struct batadv_claim, rcu); + claim = container_of(rcu, struct batadv_bla_claim, rcu); batadv_backbone_gw_free_ref(claim->backbone_gw); kfree(claim); } /* free a claim, call claim_free_rcu if its the last reference */ -static void batadv_claim_free_ref(struct batadv_claim *claim) +static void batadv_claim_free_ref(struct batadv_bla_claim *claim) { if (atomic_dec_and_test(&claim->refcount)) call_rcu(&claim->rcu, batadv_claim_free_rcu); @@ -136,14 +138,15 @@ static void batadv_claim_free_ref(struct batadv_claim *claim) * looks for a claim in the hash, and returns it if found * or NULL otherwise. */ -static struct batadv_claim *batadv_claim_hash_find(struct batadv_priv *bat_priv, - struct batadv_claim *data) +static struct batadv_bla_claim +*batadv_claim_hash_find(struct batadv_priv *bat_priv, + struct batadv_bla_claim *data) { struct batadv_hashtable *hash = bat_priv->bla.claim_hash; struct hlist_head *head; struct hlist_node *node; - struct batadv_claim *claim; - struct batadv_claim *claim_tmp = NULL; + struct batadv_bla_claim *claim; + struct batadv_bla_claim *claim_tmp = NULL; int index; if (!hash) @@ -176,15 +179,15 @@ static struct batadv_claim *batadv_claim_hash_find(struct batadv_priv *bat_priv, * * Returns claim if found or NULL otherwise. */ -static struct batadv_backbone_gw * +static struct batadv_bla_backbone_gw * batadv_backbone_hash_find(struct batadv_priv *bat_priv, uint8_t *addr, short vid) { struct batadv_hashtable *hash = bat_priv->bla.backbone_hash; struct hlist_head *head; struct hlist_node *node; - struct batadv_backbone_gw search_entry, *backbone_gw; - struct batadv_backbone_gw *backbone_gw_tmp = NULL; + struct batadv_bla_backbone_gw search_entry, *backbone_gw; + struct batadv_bla_backbone_gw *backbone_gw_tmp = NULL; int index; if (!hash) @@ -215,12 +218,12 @@ batadv_backbone_hash_find(struct batadv_priv *bat_priv, /* delete all claims for a backbone */ static void -batadv_bla_del_backbone_claims(struct batadv_backbone_gw *backbone_gw) +batadv_bla_del_backbone_claims(struct batadv_bla_backbone_gw *backbone_gw) { struct batadv_hashtable *hash; struct hlist_node *node, *node_tmp; struct hlist_head *head; - struct batadv_claim *claim; + struct batadv_bla_claim *claim; int i; spinlock_t *list_lock; /* protects write access to the hash lists */ @@ -235,7 +238,6 @@ batadv_bla_del_backbone_claims(struct batadv_backbone_gw *backbone_gw) spin_lock_bh(list_lock); hlist_for_each_entry_safe(claim, node, node_tmp, head, hash_entry) { - if (claim->backbone_gw != backbone_gw) continue; @@ -338,7 +340,6 @@ static void batadv_bla_send_claim(struct batadv_priv *bat_priv, uint8_t *mac, "bla_send_claim(): REQUEST of %pM to %pMon vid %d\n", ethhdr->h_source, ethhdr->h_dest, vid); break; - } if (vid != -1) @@ -366,11 +367,11 @@ out: * searches for the backbone gw or creates a new one if it could not * be found. */ -static struct batadv_backbone_gw * +static struct batadv_bla_backbone_gw * batadv_bla_get_backbone_gw(struct batadv_priv *bat_priv, uint8_t *orig, short vid, bool own_backbone) { - struct batadv_backbone_gw *entry; + struct batadv_bla_backbone_gw *entry; struct batadv_orig_node *orig_node; int hash_added; @@ -437,7 +438,7 @@ batadv_bla_update_own_backbone_gw(struct batadv_priv *bat_priv, struct batadv_hard_iface *primary_if, short vid) { - struct batadv_backbone_gw *backbone_gw; + struct batadv_bla_backbone_gw *backbone_gw; backbone_gw = batadv_bla_get_backbone_gw(bat_priv, primary_if->net_dev->dev_addr, @@ -462,8 +463,8 @@ static void batadv_bla_answer_request(struct batadv_priv *bat_priv, struct hlist_node *node; struct hlist_head *head; struct batadv_hashtable *hash; - struct batadv_claim *claim; - struct batadv_backbone_gw *backbone_gw; + struct batadv_bla_claim *claim; + struct batadv_bla_backbone_gw *backbone_gw; int i; batadv_dbg(BATADV_DBG_BLA, bat_priv, @@ -502,7 +503,7 @@ static void batadv_bla_answer_request(struct batadv_priv *bat_priv, * After the request, it will repeat all of his own claims and finally * send an announcement claim with which we can check again. */ -static void batadv_bla_send_request(struct batadv_backbone_gw *backbone_gw) +static void batadv_bla_send_request(struct batadv_bla_backbone_gw *backbone_gw) { /* first, remove all old entries */ batadv_bla_del_backbone_claims(backbone_gw); @@ -528,7 +529,7 @@ static void batadv_bla_send_request(struct batadv_backbone_gw *backbone_gw) * places. */ static void batadv_bla_send_announce(struct batadv_priv *bat_priv, - struct batadv_backbone_gw *backbone_gw) + struct batadv_bla_backbone_gw *backbone_gw) { uint8_t mac[ETH_ALEN]; __be16 crc; @@ -539,7 +540,6 @@ static void batadv_bla_send_announce(struct batadv_priv *bat_priv, batadv_bla_send_claim(bat_priv, mac, backbone_gw->vid, BATADV_CLAIM_TYPE_ANNOUNCE); - } /** @@ -551,10 +551,10 @@ static void batadv_bla_send_announce(struct batadv_priv *bat_priv, */ static void batadv_bla_add_claim(struct batadv_priv *bat_priv, const uint8_t *mac, const short vid, - struct batadv_backbone_gw *backbone_gw) + struct batadv_bla_backbone_gw *backbone_gw) { - struct batadv_claim *claim; - struct batadv_claim search_claim; + struct batadv_bla_claim *claim; + struct batadv_bla_claim search_claim; int hash_added; memcpy(search_claim.addr, mac, ETH_ALEN); @@ -598,7 +598,6 @@ static void batadv_bla_add_claim(struct batadv_priv *bat_priv, claim->backbone_gw->crc ^= crc16(0, claim->addr, ETH_ALEN); batadv_backbone_gw_free_ref(claim->backbone_gw); - } /* set (new) backbone gw */ atomic_inc(&backbone_gw->refcount); @@ -617,7 +616,7 @@ claim_free_ref: static void batadv_bla_del_claim(struct batadv_priv *bat_priv, const uint8_t *mac, const short vid) { - struct batadv_claim search_claim, *claim; + struct batadv_bla_claim search_claim, *claim; memcpy(search_claim.addr, mac, ETH_ALEN); search_claim.vid = vid; @@ -643,7 +642,7 @@ static int batadv_handle_announce(struct batadv_priv *bat_priv, uint8_t *an_addr, uint8_t *backbone_addr, short vid) { - struct batadv_backbone_gw *backbone_gw; + struct batadv_bla_backbone_gw *backbone_gw; uint16_t crc; if (memcmp(an_addr, batadv_announce_mac, 4) != 0) @@ -661,12 +660,12 @@ static int batadv_handle_announce(struct batadv_priv *bat_priv, crc = ntohs(*((__be16 *)(&an_addr[4]))); batadv_dbg(BATADV_DBG_BLA, bat_priv, - "handle_announce(): ANNOUNCE vid %d (sent by %pM)... CRC = %04x\n", + "handle_announce(): ANNOUNCE vid %d (sent by %pM)... CRC = %#.4x\n", vid, backbone_gw->orig, crc); if (backbone_gw->crc != crc) { batadv_dbg(BATADV_DBG_BLA, backbone_gw->bat_priv, - "handle_announce(): CRC FAILED for %pM/%d (my = %04x, sent = %04x)\n", + "handle_announce(): CRC FAILED for %pM/%d (my = %#.4x, sent = %#.4x)\n", backbone_gw->orig, backbone_gw->vid, backbone_gw->crc, crc); @@ -715,7 +714,7 @@ static int batadv_handle_unclaim(struct batadv_priv *bat_priv, uint8_t *backbone_addr, uint8_t *claim_addr, short vid) { - struct batadv_backbone_gw *backbone_gw; + struct batadv_bla_backbone_gw *backbone_gw; /* unclaim in any case if it is our own */ if (primary_if && batadv_compare_eth(backbone_addr, @@ -744,7 +743,7 @@ static int batadv_handle_claim(struct batadv_priv *bat_priv, uint8_t *backbone_addr, uint8_t *claim_addr, short vid) { - struct batadv_backbone_gw *backbone_gw; + struct batadv_bla_backbone_gw *backbone_gw; /* register the gateway if not yet available, and add the claim. */ @@ -835,7 +834,7 @@ static int batadv_check_claim_group(struct batadv_priv *bat_priv, /* if our mesh friends mac is bigger, use it for ourselves. */ if (ntohs(bla_dst->group) > ntohs(bla_dst_own->group)) { batadv_dbg(BATADV_DBG_BLA, bat_priv, - "taking other backbones claim group: %04x\n", + "taking other backbones claim group: %#.4x\n", ntohs(bla_dst->group)); bla_dst_own->group = bla_dst->group; } @@ -958,7 +957,7 @@ static int batadv_bla_process_claim(struct batadv_priv *bat_priv, */ static void batadv_bla_purge_backbone_gw(struct batadv_priv *bat_priv, int now) { - struct batadv_backbone_gw *backbone_gw; + struct batadv_bla_backbone_gw *backbone_gw; struct hlist_node *node, *node_tmp; struct hlist_head *head; struct batadv_hashtable *hash; @@ -1013,7 +1012,7 @@ static void batadv_bla_purge_claims(struct batadv_priv *bat_priv, struct batadv_hard_iface *primary_if, int now) { - struct batadv_claim *claim; + struct batadv_bla_claim *claim; struct hlist_node *node; struct hlist_head *head; struct batadv_hashtable *hash; @@ -1062,7 +1061,7 @@ void batadv_bla_update_orig_address(struct batadv_priv *bat_priv, struct batadv_hard_iface *primary_if, struct batadv_hard_iface *oldif) { - struct batadv_backbone_gw *backbone_gw; + struct batadv_bla_backbone_gw *backbone_gw; struct hlist_node *node; struct hlist_head *head; struct batadv_hashtable *hash; @@ -1104,16 +1103,6 @@ void batadv_bla_update_orig_address(struct batadv_priv *bat_priv, } } - - -/* (re)start the timer */ -static void batadv_bla_start_timer(struct batadv_priv *bat_priv) -{ - INIT_DELAYED_WORK(&bat_priv->bla.work, batadv_bla_periodic_work); - queue_delayed_work(batadv_event_workqueue, &bat_priv->bla.work, - msecs_to_jiffies(BATADV_BLA_PERIOD_LENGTH)); -} - /* periodic work to do: * * purge structures when they are too old * * send announcements @@ -1125,7 +1114,7 @@ static void batadv_bla_periodic_work(struct work_struct *work) struct batadv_priv_bla *priv_bla; struct hlist_node *node; struct hlist_head *head; - struct batadv_backbone_gw *backbone_gw; + struct batadv_bla_backbone_gw *backbone_gw; struct batadv_hashtable *hash; struct batadv_hard_iface *primary_if; int i; @@ -1184,7 +1173,8 @@ out: if (primary_if) batadv_hardif_free_ref(primary_if); - batadv_bla_start_timer(bat_priv); + queue_delayed_work(batadv_event_workqueue, &bat_priv->bla.work, + msecs_to_jiffies(BATADV_BLA_PERIOD_LENGTH)); } /* The hash for claim and backbone hash receive the same key because they @@ -1242,7 +1232,10 @@ int batadv_bla_init(struct batadv_priv *bat_priv) batadv_dbg(BATADV_DBG_BLA, bat_priv, "bla hashes initialized\n"); - batadv_bla_start_timer(bat_priv); + INIT_DELAYED_WORK(&bat_priv->bla.work, batadv_bla_periodic_work); + + queue_delayed_work(batadv_event_workqueue, &bat_priv->bla.work, + msecs_to_jiffies(BATADV_BLA_PERIOD_LENGTH)); return 0; } @@ -1330,7 +1323,7 @@ int batadv_bla_is_backbone_gw_orig(struct batadv_priv *bat_priv, uint8_t *orig) struct batadv_hashtable *hash = bat_priv->bla.backbone_hash; struct hlist_head *head; struct hlist_node *node; - struct batadv_backbone_gw *backbone_gw; + struct batadv_bla_backbone_gw *backbone_gw; int i; if (!atomic_read(&bat_priv->bridge_loop_avoidance)) @@ -1371,7 +1364,7 @@ int batadv_bla_is_backbone_gw(struct sk_buff *skb, { struct ethhdr *ethhdr; struct vlan_ethhdr *vhdr; - struct batadv_backbone_gw *backbone_gw; + struct batadv_bla_backbone_gw *backbone_gw; short vid = -1; if (!atomic_read(&orig_node->bat_priv->bridge_loop_avoidance)) @@ -1442,7 +1435,7 @@ int batadv_bla_rx(struct batadv_priv *bat_priv, struct sk_buff *skb, short vid, bool is_bcast) { struct ethhdr *ethhdr; - struct batadv_claim search_claim, *claim = NULL; + struct batadv_bla_claim search_claim, *claim = NULL; struct batadv_hard_iface *primary_if; int ret; @@ -1536,7 +1529,7 @@ out: int batadv_bla_tx(struct batadv_priv *bat_priv, struct sk_buff *skb, short vid) { struct ethhdr *ethhdr; - struct batadv_claim search_claim, *claim = NULL; + struct batadv_bla_claim search_claim, *claim = NULL; struct batadv_hard_iface *primary_if; int ret = 0; @@ -1612,7 +1605,7 @@ int batadv_bla_claim_table_seq_print_text(struct seq_file *seq, void *offset) struct net_device *net_dev = (struct net_device *)seq->private; struct batadv_priv *bat_priv = netdev_priv(net_dev); struct batadv_hashtable *hash = bat_priv->bla.claim_hash; - struct batadv_claim *claim; + struct batadv_bla_claim *claim; struct batadv_hard_iface *primary_if; struct hlist_node *node; struct hlist_head *head; @@ -1626,10 +1619,10 @@ int batadv_bla_claim_table_seq_print_text(struct seq_file *seq, void *offset) primary_addr = primary_if->net_dev->dev_addr; seq_printf(seq, - "Claims announced for the mesh %s (orig %pM, group id %04x)\n", + "Claims announced for the mesh %s (orig %pM, group id %#.4x)\n", net_dev->name, primary_addr, ntohs(bat_priv->bla.claim_dest.group)); - seq_printf(seq, " %-17s %-5s %-17s [o] (%-4s)\n", + seq_printf(seq, " %-17s %-5s %-17s [o] (%-6s)\n", "Client", "VID", "Originator", "CRC"); for (i = 0; i < hash->size; i++) { head = &hash->table[i]; @@ -1638,7 +1631,7 @@ int batadv_bla_claim_table_seq_print_text(struct seq_file *seq, void *offset) hlist_for_each_entry_rcu(claim, node, head, hash_entry) { is_own = batadv_compare_eth(claim->backbone_gw->orig, primary_addr); - seq_printf(seq, " * %pM on % 5d by %pM [%c] (%04x)\n", + seq_printf(seq, " * %pM on % 5d by %pM [%c] (%#.4x)\n", claim->addr, claim->vid, claim->backbone_gw->orig, (is_own ? 'x' : ' '), @@ -1657,7 +1650,7 @@ int batadv_bla_backbone_table_seq_print_text(struct seq_file *seq, void *offset) struct net_device *net_dev = (struct net_device *)seq->private; struct batadv_priv *bat_priv = netdev_priv(net_dev); struct batadv_hashtable *hash = bat_priv->bla.backbone_hash; - struct batadv_backbone_gw *backbone_gw; + struct batadv_bla_backbone_gw *backbone_gw; struct batadv_hard_iface *primary_if; struct hlist_node *node; struct hlist_head *head; @@ -1672,10 +1665,10 @@ int batadv_bla_backbone_table_seq_print_text(struct seq_file *seq, void *offset) primary_addr = primary_if->net_dev->dev_addr; seq_printf(seq, - "Backbones announced for the mesh %s (orig %pM, group id %04x)\n", + "Backbones announced for the mesh %s (orig %pM, group id %#.4x)\n", net_dev->name, primary_addr, ntohs(bat_priv->bla.claim_dest.group)); - seq_printf(seq, " %-17s %-5s %-9s (%-4s)\n", + seq_printf(seq, " %-17s %-5s %-9s (%-6s)\n", "Originator", "VID", "last seen", "CRC"); for (i = 0; i < hash->size; i++) { head = &hash->table[i]; @@ -1693,7 +1686,7 @@ int batadv_bla_backbone_table_seq_print_text(struct seq_file *seq, void *offset) continue; seq_printf(seq, - " * %pM on % 5d % 4i.%03is (%04x)\n", + " * %pM on % 5d % 4i.%03is (%#.4x)\n", backbone_gw->orig, backbone_gw->vid, secs, msecs, backbone_gw->crc); } diff --git a/net/batman-adv/bridge_loop_avoidance.h b/net/batman-adv/bridge_loop_avoidance.h index 196d9a0254bc..dea2fbc5d98d 100644 --- a/net/batman-adv/bridge_loop_avoidance.h +++ b/net/batman-adv/bridge_loop_avoidance.h @@ -1,4 +1,4 @@ -/* Copyright (C) 2011-2012 B.A.T.M.A.N. contributors: +/* Copyright (C) 2011-2013 B.A.T.M.A.N. contributors: * * Simon Wunderlich * diff --git a/net/batman-adv/debugfs.c b/net/batman-adv/debugfs.c index 6f58ddd53bff..6ae86516db4d 100644 --- a/net/batman-adv/debugfs.c +++ b/net/batman-adv/debugfs.c @@ -1,4 +1,4 @@ -/* Copyright (C) 2010-2012 B.A.T.M.A.N. contributors: +/* Copyright (C) 2010-2013 B.A.T.M.A.N. contributors: * * Marek Lindner * @@ -40,13 +40,14 @@ static struct dentry *batadv_debugfs; static const int batadv_log_buff_len = BATADV_LOG_BUF_LEN; -static char *batadv_log_char_addr(struct batadv_debug_log *debug_log, +static char *batadv_log_char_addr(struct batadv_priv_debug_log *debug_log, size_t idx) { return &debug_log->log_buff[idx & BATADV_LOG_BUFF_MASK]; } -static void batadv_emit_log_char(struct batadv_debug_log *debug_log, char c) +static void batadv_emit_log_char(struct batadv_priv_debug_log *debug_log, + char c) { char *char_addr; @@ -59,7 +60,7 @@ static void batadv_emit_log_char(struct batadv_debug_log *debug_log, char c) } __printf(2, 3) -static int batadv_fdebug_log(struct batadv_debug_log *debug_log, +static int batadv_fdebug_log(struct batadv_priv_debug_log *debug_log, const char *fmt, ...) { va_list args; @@ -114,7 +115,7 @@ static int batadv_log_release(struct inode *inode, struct file *file) return 0; } -static int batadv_log_empty(struct batadv_debug_log *debug_log) +static int batadv_log_empty(struct batadv_priv_debug_log *debug_log) { return !(debug_log->log_start - debug_log->log_end); } @@ -123,7 +124,7 @@ static ssize_t batadv_log_read(struct file *file, char __user *buf, size_t count, loff_t *ppos) { struct batadv_priv *bat_priv = file->private_data; - struct batadv_debug_log *debug_log = bat_priv->debug_log; + struct batadv_priv_debug_log *debug_log = bat_priv->debug_log; int error, i = 0; char *char_addr; char c; @@ -164,7 +165,6 @@ static ssize_t batadv_log_read(struct file *file, char __user *buf, buf++; i++; - } spin_unlock_bh(&debug_log->lock); @@ -178,7 +178,7 @@ static ssize_t batadv_log_read(struct file *file, char __user *buf, static unsigned int batadv_log_poll(struct file *file, poll_table *wait) { struct batadv_priv *bat_priv = file->private_data; - struct batadv_debug_log *debug_log = bat_priv->debug_log; + struct batadv_priv_debug_log *debug_log = bat_priv->debug_log; poll_wait(file, &debug_log->queue_wait, wait); @@ -230,7 +230,6 @@ static void batadv_debug_log_cleanup(struct batadv_priv *bat_priv) #else /* CONFIG_BATMAN_ADV_DEBUG */ static int batadv_debug_log_setup(struct batadv_priv *bat_priv) { - bat_priv->debug_log = NULL; return 0; } @@ -397,10 +396,8 @@ err: void batadv_debugfs_destroy(void) { - if (batadv_debugfs) { - debugfs_remove_recursive(batadv_debugfs); - batadv_debugfs = NULL; - } + debugfs_remove_recursive(batadv_debugfs); + batadv_debugfs = NULL; } int batadv_debugfs_add_meshif(struct net_device *dev) diff --git a/net/batman-adv/debugfs.h b/net/batman-adv/debugfs.h index 3319e1f21f55..f8c3849edff4 100644 --- a/net/batman-adv/debugfs.h +++ b/net/batman-adv/debugfs.h @@ -1,4 +1,4 @@ -/* Copyright (C) 2010-2012 B.A.T.M.A.N. contributors: +/* Copyright (C) 2010-2013 B.A.T.M.A.N. contributors: * * Marek Lindner * diff --git a/net/batman-adv/distributed-arp-table.c b/net/batman-adv/distributed-arp-table.c index 8e1d89d2b1c1..ea0bd31d41c2 100644 --- a/net/batman-adv/distributed-arp-table.c +++ b/net/batman-adv/distributed-arp-table.c @@ -1,4 +1,4 @@ -/* Copyright (C) 2011-2012 B.A.T.M.A.N. contributors: +/* Copyright (C) 2011-2013 B.A.T.M.A.N. contributors: * * Antonio Quartulli * @@ -738,6 +738,7 @@ static uint16_t batadv_arp_get_type(struct batadv_priv *bat_priv, struct arphdr *arphdr; struct ethhdr *ethhdr; __be32 ip_src, ip_dst; + uint8_t *hw_src, *hw_dst; uint16_t type = 0; /* pull the ethernet header */ @@ -777,9 +778,23 @@ static uint16_t batadv_arp_get_type(struct batadv_priv *bat_priv, ip_src = batadv_arp_ip_src(skb, hdr_size); ip_dst = batadv_arp_ip_dst(skb, hdr_size); if (ipv4_is_loopback(ip_src) || ipv4_is_multicast(ip_src) || - ipv4_is_loopback(ip_dst) || ipv4_is_multicast(ip_dst)) + ipv4_is_loopback(ip_dst) || ipv4_is_multicast(ip_dst) || + ipv4_is_zeronet(ip_src) || ipv4_is_lbcast(ip_src) || + ipv4_is_zeronet(ip_dst) || ipv4_is_lbcast(ip_dst)) goto out; + hw_src = batadv_arp_hw_src(skb, hdr_size); + if (is_zero_ether_addr(hw_src) || is_multicast_ether_addr(hw_src)) + goto out; + + /* we don't care about the destination MAC address in ARP requests */ + if (arphdr->ar_op != htons(ARPOP_REQUEST)) { + hw_dst = batadv_arp_hw_dst(skb, hdr_size); + if (is_zero_ether_addr(hw_dst) || + is_multicast_ether_addr(hw_dst)) + goto out; + } + type = ntohs(arphdr->ar_op); out: return type; @@ -1012,6 +1027,8 @@ bool batadv_dat_snoop_incoming_arp_reply(struct batadv_priv *bat_priv, */ ret = !batadv_is_my_client(bat_priv, hw_dst); out: + if (ret) + kfree_skb(skb); /* if ret == false -> packet has to be delivered to the interface */ return ret; } diff --git a/net/batman-adv/distributed-arp-table.h b/net/batman-adv/distributed-arp-table.h index d060c033e7de..125c8c6fcfad 100644 --- a/net/batman-adv/distributed-arp-table.h +++ b/net/batman-adv/distributed-arp-table.h @@ -1,4 +1,4 @@ -/* Copyright (C) 2011-2012 B.A.T.M.A.N. contributors: +/* Copyright (C) 2011-2013 B.A.T.M.A.N. contributors: * * Antonio Quartulli * diff --git a/net/batman-adv/gateway_client.c b/net/batman-adv/gateway_client.c index dd07c7e3654f..074107f2cfaa 100644 --- a/net/batman-adv/gateway_client.c +++ b/net/batman-adv/gateway_client.c @@ -1,4 +1,4 @@ -/* Copyright (C) 2009-2012 B.A.T.M.A.N. contributors: +/* Copyright (C) 2009-2013 B.A.T.M.A.N. contributors: * * Marek Lindner * diff --git a/net/batman-adv/gateway_client.h b/net/batman-adv/gateway_client.h index f0d129e323c8..039902dca4a6 100644 --- a/net/batman-adv/gateway_client.h +++ b/net/batman-adv/gateway_client.h @@ -1,4 +1,4 @@ -/* Copyright (C) 2009-2012 B.A.T.M.A.N. contributors: +/* Copyright (C) 2009-2013 B.A.T.M.A.N. contributors: * * Marek Lindner * diff --git a/net/batman-adv/gateway_common.c b/net/batman-adv/gateway_common.c index 9001208d1752..84bb2b18d711 100644 --- a/net/batman-adv/gateway_common.c +++ b/net/batman-adv/gateway_common.c @@ -1,4 +1,4 @@ -/* Copyright (C) 2009-2012 B.A.T.M.A.N. contributors: +/* Copyright (C) 2009-2013 B.A.T.M.A.N. contributors: * * Marek Lindner * diff --git a/net/batman-adv/gateway_common.h b/net/batman-adv/gateway_common.h index 13697f6e7113..509b2bf8c2f4 100644 --- a/net/batman-adv/gateway_common.h +++ b/net/batman-adv/gateway_common.h @@ -1,4 +1,4 @@ -/* Copyright (C) 2009-2012 B.A.T.M.A.N. contributors: +/* Copyright (C) 2009-2013 B.A.T.M.A.N. contributors: * * Marek Lindner * diff --git a/net/batman-adv/hard-interface.c b/net/batman-adv/hard-interface.c index f1d37cd81815..368219e026a9 100644 --- a/net/batman-adv/hard-interface.c +++ b/net/batman-adv/hard-interface.c @@ -1,4 +1,4 @@ -/* Copyright (C) 2007-2012 B.A.T.M.A.N. contributors: +/* Copyright (C) 2007-2013 B.A.T.M.A.N. contributors: * * Marek Lindner, Simon Wunderlich * @@ -457,6 +457,24 @@ out: batadv_hardif_free_ref(primary_if); } +/** + * batadv_hardif_remove_interface_finish - cleans up the remains of a hardif + * @work: work queue item + * + * Free the parts of the hard interface which can not be removed under + * rtnl lock (to prevent deadlock situations). + */ +static void batadv_hardif_remove_interface_finish(struct work_struct *work) +{ + struct batadv_hard_iface *hard_iface; + + hard_iface = container_of(work, struct batadv_hard_iface, + cleanup_work); + + batadv_sysfs_del_hardif(&hard_iface->hardif_obj); + batadv_hardif_free_ref(hard_iface); +} + static struct batadv_hard_iface * batadv_hardif_add_interface(struct net_device *net_dev) { @@ -484,6 +502,9 @@ batadv_hardif_add_interface(struct net_device *net_dev) hard_iface->soft_iface = NULL; hard_iface->if_status = BATADV_IF_NOT_IN_USE; INIT_LIST_HEAD(&hard_iface->list); + INIT_WORK(&hard_iface->cleanup_work, + batadv_hardif_remove_interface_finish); + /* extra reference for return */ atomic_set(&hard_iface->refcount, 2); @@ -518,8 +539,7 @@ static void batadv_hardif_remove_interface(struct batadv_hard_iface *hard_iface) return; hard_iface->if_status = BATADV_IF_TO_BE_REMOVED; - batadv_sysfs_del_hardif(&hard_iface->hardif_obj); - batadv_hardif_free_ref(hard_iface); + queue_work(batadv_event_workqueue, &hard_iface->cleanup_work); } void batadv_hardif_remove_interfaces(void) diff --git a/net/batman-adv/hard-interface.h b/net/batman-adv/hard-interface.h index 3732366e7445..308437d52e22 100644 --- a/net/batman-adv/hard-interface.h +++ b/net/batman-adv/hard-interface.h @@ -1,4 +1,4 @@ -/* Copyright (C) 2007-2012 B.A.T.M.A.N. contributors: +/* Copyright (C) 2007-2013 B.A.T.M.A.N. contributors: * * Marek Lindner, Simon Wunderlich * diff --git a/net/batman-adv/hash.c b/net/batman-adv/hash.c index 15a849c2d414..7198dafd3bf3 100644 --- a/net/batman-adv/hash.c +++ b/net/batman-adv/hash.c @@ -1,4 +1,4 @@ -/* Copyright (C) 2006-2012 B.A.T.M.A.N. contributors: +/* Copyright (C) 2006-2013 B.A.T.M.A.N. contributors: * * Simon Wunderlich, Marek Lindner * diff --git a/net/batman-adv/hash.h b/net/batman-adv/hash.h index e05333905afd..1b4da72f2093 100644 --- a/net/batman-adv/hash.h +++ b/net/batman-adv/hash.h @@ -1,4 +1,4 @@ -/* Copyright (C) 2006-2012 B.A.T.M.A.N. contributors: +/* Copyright (C) 2006-2013 B.A.T.M.A.N. contributors: * * Simon Wunderlich, Marek Lindner * @@ -89,7 +89,7 @@ static inline void batadv_hash_delete(struct batadv_hashtable *hash, * * Returns the new hash value. */ -static inline uint32_t batadv_hash_bytes(uint32_t hash, void *data, +static inline uint32_t batadv_hash_bytes(uint32_t hash, const void *data, uint32_t size) { const unsigned char *key = data; diff --git a/net/batman-adv/icmp_socket.c b/net/batman-adv/icmp_socket.c index 87ca8095b011..0ba6c899b2d3 100644 --- a/net/batman-adv/icmp_socket.c +++ b/net/batman-adv/icmp_socket.c @@ -1,4 +1,4 @@ -/* Copyright (C) 2007-2012 B.A.T.M.A.N. contributors: +/* Copyright (C) 2007-2013 B.A.T.M.A.N. contributors: * * Marek Lindner * diff --git a/net/batman-adv/icmp_socket.h b/net/batman-adv/icmp_socket.h index 29443a1dbb5c..1fcca37b6223 100644 --- a/net/batman-adv/icmp_socket.h +++ b/net/batman-adv/icmp_socket.h @@ -1,4 +1,4 @@ -/* Copyright (C) 2007-2012 B.A.T.M.A.N. contributors: +/* Copyright (C) 2007-2013 B.A.T.M.A.N. contributors: * * Marek Lindner * diff --git a/net/batman-adv/main.c b/net/batman-adv/main.c index f65a222b7b83..21fe6987733b 100644 --- a/net/batman-adv/main.c +++ b/net/batman-adv/main.c @@ -1,4 +1,4 @@ -/* Copyright (C) 2007-2012 B.A.T.M.A.N. contributors: +/* Copyright (C) 2007-2013 B.A.T.M.A.N. contributors: * * Marek Lindner, Simon Wunderlich * diff --git a/net/batman-adv/main.h b/net/batman-adv/main.h index 2f85577086a7..ced08b936a96 100644 --- a/net/batman-adv/main.h +++ b/net/batman-adv/main.h @@ -1,4 +1,4 @@ -/* Copyright (C) 2007-2012 B.A.T.M.A.N. contributors: +/* Copyright (C) 2007-2013 B.A.T.M.A.N. contributors: * * Marek Lindner, Simon Wunderlich * @@ -26,7 +26,7 @@ #define BATADV_DRIVER_DEVICE "batman-adv" #ifndef BATADV_SOURCE_VERSION -#define BATADV_SOURCE_VERSION "2012.5.0" +#define BATADV_SOURCE_VERSION "2013.1.0" #endif /* B.A.T.M.A.N. parameters */ @@ -41,9 +41,11 @@ * -> TODO: check influence on BATADV_TQ_LOCAL_WINDOW_SIZE */ #define BATADV_PURGE_TIMEOUT 200000 /* 200 seconds */ -#define BATADV_TT_LOCAL_TIMEOUT 3600000 /* in milliseconds */ +#define BATADV_TT_LOCAL_TIMEOUT 600000 /* in milliseconds */ #define BATADV_TT_CLIENT_ROAM_TIMEOUT 600000 /* in milliseconds */ #define BATADV_TT_CLIENT_TEMP_TIMEOUT 600000 /* in milliseconds */ +#define BATADV_TT_WORK_PERIOD 5000 /* 5 seconds */ +#define BATADV_ORIG_WORK_PERIOD 1000 /* 1 second */ #define BATADV_DAT_ENTRY_TIMEOUT (5*60000) /* 5 mins in milliseconds */ /* sliding packet range of received originator messages in sequence numbers * (should be a multiple of our word size) @@ -276,9 +278,7 @@ static inline bool batadv_has_timed_out(unsigned long timestamp, static inline void batadv_add_counter(struct batadv_priv *bat_priv, size_t idx, size_t count) { - int cpu = get_cpu(); - per_cpu_ptr(bat_priv->bat_counters, cpu)[idx] += count; - put_cpu(); + this_cpu_add(bat_priv->bat_counters[idx], count); } #define batadv_inc_counter(b, i) batadv_add_counter(b, i, 1) diff --git a/net/batman-adv/originator.c b/net/batman-adv/originator.c index 8c32cf1c2dec..457ea445217c 100644 --- a/net/batman-adv/originator.c +++ b/net/batman-adv/originator.c @@ -1,4 +1,4 @@ -/* Copyright (C) 2009-2012 B.A.T.M.A.N. contributors: +/* Copyright (C) 2009-2013 B.A.T.M.A.N. contributors: * * Marek Lindner, Simon Wunderlich * @@ -29,14 +29,10 @@ #include "soft-interface.h" #include "bridge_loop_avoidance.h" -static void batadv_purge_orig(struct work_struct *work); +/* hash class keys */ +static struct lock_class_key batadv_orig_hash_lock_class_key; -static void batadv_start_purge_timer(struct batadv_priv *bat_priv) -{ - INIT_DELAYED_WORK(&bat_priv->orig_work, batadv_purge_orig); - queue_delayed_work(batadv_event_workqueue, - &bat_priv->orig_work, msecs_to_jiffies(1000)); -} +static void batadv_purge_orig(struct work_struct *work); /* returns 1 if they are the same originator */ static int batadv_compare_orig(const struct hlist_node *node, const void *data2) @@ -57,7 +53,14 @@ int batadv_originator_init(struct batadv_priv *bat_priv) if (!bat_priv->orig_hash) goto err; - batadv_start_purge_timer(bat_priv); + batadv_hash_set_lock_class(bat_priv->orig_hash, + &batadv_orig_hash_lock_class_key); + + INIT_DELAYED_WORK(&bat_priv->orig_work, batadv_purge_orig); + queue_delayed_work(batadv_event_workqueue, + &bat_priv->orig_work, + msecs_to_jiffies(BATADV_ORIG_WORK_PERIOD)); + return 0; err: @@ -178,7 +181,6 @@ void batadv_originator_free(struct batadv_priv *bat_priv) spin_lock_bh(list_lock); hlist_for_each_entry_safe(orig_node, node, node_tmp, head, hash_entry) { - hlist_del_rcu(node); batadv_orig_node_free_ref(orig_node); } @@ -285,7 +287,6 @@ batadv_purge_orig_neighbors(struct batadv_priv *bat_priv, /* for all neighbors towards this originator ... */ hlist_for_each_entry_safe(neigh_node, node, node_tmp, &orig_node->neigh_list, list) { - last_seen = neigh_node->last_seen; if_incoming = neigh_node->if_incoming; @@ -293,7 +294,6 @@ batadv_purge_orig_neighbors(struct batadv_priv *bat_priv, (if_incoming->if_status == BATADV_IF_INACTIVE) || (if_incoming->if_status == BATADV_IF_NOT_IN_USE) || (if_incoming->if_status == BATADV_IF_TO_BE_REMOVED)) { - if ((if_incoming->if_status == BATADV_IF_INACTIVE) || (if_incoming->if_status == BATADV_IF_NOT_IN_USE) || (if_incoming->if_status == BATADV_IF_TO_BE_REMOVED)) @@ -393,7 +393,9 @@ static void batadv_purge_orig(struct work_struct *work) delayed_work = container_of(work, struct delayed_work, work); bat_priv = container_of(delayed_work, struct batadv_priv, orig_work); _batadv_purge_orig(bat_priv); - batadv_start_purge_timer(bat_priv); + queue_delayed_work(batadv_event_workqueue, + &bat_priv->orig_work, + msecs_to_jiffies(BATADV_ORIG_WORK_PERIOD)); } void batadv_purge_orig_ref(struct batadv_priv *bat_priv) diff --git a/net/batman-adv/originator.h b/net/batman-adv/originator.h index 9778e656dec7..286bf743e76a 100644 --- a/net/batman-adv/originator.h +++ b/net/batman-adv/originator.h @@ -1,4 +1,4 @@ -/* Copyright (C) 2007-2012 B.A.T.M.A.N. contributors: +/* Copyright (C) 2007-2013 B.A.T.M.A.N. contributors: * * Marek Lindner, Simon Wunderlich * diff --git a/net/batman-adv/packet.h b/net/batman-adv/packet.h index cb6405bf755c..ed0aa89bbf8b 100644 --- a/net/batman-adv/packet.h +++ b/net/batman-adv/packet.h @@ -1,4 +1,4 @@ -/* Copyright (C) 2007-2012 B.A.T.M.A.N. contributors: +/* Copyright (C) 2007-2013 B.A.T.M.A.N. contributors: * * Marek Lindner, Simon Wunderlich * diff --git a/net/batman-adv/ring_buffer.c b/net/batman-adv/ring_buffer.c index c8f61e395b74..ccab0bbdbb59 100644 --- a/net/batman-adv/ring_buffer.c +++ b/net/batman-adv/ring_buffer.c @@ -1,4 +1,4 @@ -/* Copyright (C) 2007-2012 B.A.T.M.A.N. contributors: +/* Copyright (C) 2007-2013 B.A.T.M.A.N. contributors: * * Marek Lindner * diff --git a/net/batman-adv/ring_buffer.h b/net/batman-adv/ring_buffer.h index fda8c17df273..3f92ae248e83 100644 --- a/net/batman-adv/ring_buffer.h +++ b/net/batman-adv/ring_buffer.h @@ -1,4 +1,4 @@ -/* Copyright (C) 2007-2012 B.A.T.M.A.N. contributors: +/* Copyright (C) 2007-2013 B.A.T.M.A.N. contributors: * * Marek Lindner * diff --git a/net/batman-adv/routing.c b/net/batman-adv/routing.c index 1aa1722d0187..60ba03fc8390 100644 --- a/net/batman-adv/routing.c +++ b/net/batman-adv/routing.c @@ -1,4 +1,4 @@ -/* Copyright (C) 2007-2012 B.A.T.M.A.N. contributors: +/* Copyright (C) 2007-2013 B.A.T.M.A.N. contributors: * * Marek Lindner, Simon Wunderlich * @@ -80,7 +80,6 @@ static void _batadv_update_route(struct batadv_priv *bat_priv, /* route added */ } else if ((!curr_router) && (neigh_node)) { - batadv_dbg(BATADV_DBG_ROUTES, bat_priv, "Adding route towards: %pM (via %pM)\n", orig_node->orig, neigh_node->addr); @@ -172,7 +171,6 @@ void batadv_bonding_candidate_add(struct batadv_orig_node *orig_node, */ hlist_for_each_entry_rcu(tmp_neigh_node, node, &orig_node->neigh_list, list) { - if (tmp_neigh_node == neigh_node) continue; @@ -836,7 +834,6 @@ static int batadv_route_unicast_packet(struct sk_buff *skb, if (unicast_packet->header.packet_type == BATADV_UNICAST_FRAG && batadv_frag_can_reassemble(skb, neigh_node->if_incoming->net_dev->mtu)) { - ret = batadv_frag_reassemble_skb(skb, bat_priv, &new_skb); if (ret == NET_RX_DROP) @@ -1103,7 +1100,6 @@ int batadv_recv_ucast_frag_packet(struct sk_buff *skb, /* packet for me */ if (batadv_is_my_mac(unicast_packet->dest)) { - ret = batadv_frag_reassemble_skb(skb, bat_priv, &new_skb); if (ret == NET_RX_DROP) diff --git a/net/batman-adv/routing.h b/net/batman-adv/routing.h index 9262279ea667..99eeafaba407 100644 --- a/net/batman-adv/routing.h +++ b/net/batman-adv/routing.h @@ -1,4 +1,4 @@ -/* Copyright (C) 2007-2012 B.A.T.M.A.N. contributors: +/* Copyright (C) 2007-2013 B.A.T.M.A.N. contributors: * * Marek Lindner, Simon Wunderlich * diff --git a/net/batman-adv/send.c b/net/batman-adv/send.c index 4425af9dad40..80ca65fc89a1 100644 --- a/net/batman-adv/send.c +++ b/net/batman-adv/send.c @@ -1,4 +1,4 @@ -/* Copyright (C) 2007-2012 B.A.T.M.A.N. contributors: +/* Copyright (C) 2007-2013 B.A.T.M.A.N. contributors: * * Marek Lindner, Simon Wunderlich * @@ -155,8 +155,6 @@ _batadv_add_bcast_packet_to_list(struct batadv_priv *bat_priv, spin_unlock_bh(&bat_priv->forw_bcast_list_lock); /* start timer for this packet */ - INIT_DELAYED_WORK(&forw_packet->delayed_work, - batadv_send_outstanding_bcast_packet); queue_delayed_work(batadv_event_workqueue, &forw_packet->delayed_work, send_time); } @@ -210,6 +208,9 @@ int batadv_add_bcast_packet_to_list(struct batadv_priv *bat_priv, /* how often did we send the bcast packet ? */ forw_packet->num_packets = 0; + INIT_DELAYED_WORK(&forw_packet->delayed_work, + batadv_send_outstanding_bcast_packet); + _batadv_add_bcast_packet_to_list(bat_priv, forw_packet, delay); return NETDEV_TX_OK; @@ -330,7 +331,6 @@ batadv_purge_outstanding_packets(struct batadv_priv *bat_priv, spin_lock_bh(&bat_priv->forw_bcast_list_lock); hlist_for_each_entry_safe(forw_packet, tmp_node, safe_tmp_node, &bat_priv->forw_bcast_list, list) { - /* if purge_outstanding_packets() was called with an argument * we delete only packets belonging to the given interface */ @@ -357,7 +357,6 @@ batadv_purge_outstanding_packets(struct batadv_priv *bat_priv, spin_lock_bh(&bat_priv->forw_bat_list_lock); hlist_for_each_entry_safe(forw_packet, tmp_node, safe_tmp_node, &bat_priv->forw_bat_list, list) { - /* if purge_outstanding_packets() was called with an argument * we delete only packets belonging to the given interface */ diff --git a/net/batman-adv/send.h b/net/batman-adv/send.h index 0078dece1abc..38e662f619ac 100644 --- a/net/batman-adv/send.h +++ b/net/batman-adv/send.h @@ -1,4 +1,4 @@ -/* Copyright (C) 2007-2012 B.A.T.M.A.N. contributors: +/* Copyright (C) 2007-2013 B.A.T.M.A.N. contributors: * * Marek Lindner, Simon Wunderlich * diff --git a/net/batman-adv/soft-interface.c b/net/batman-adv/soft-interface.c index 6b548fde8e04..2711e870f557 100644 --- a/net/batman-adv/soft-interface.c +++ b/net/batman-adv/soft-interface.c @@ -1,4 +1,4 @@ -/* Copyright (C) 2007-2012 B.A.T.M.A.N. contributors: +/* Copyright (C) 2007-2013 B.A.T.M.A.N. contributors: * * Marek Lindner, Simon Wunderlich * @@ -124,7 +124,6 @@ static int batadv_interface_set_mac_addr(struct net_device *dev, void *p) batadv_tt_local_add(dev, addr->sa_data, BATADV_NULL_IFINDEX); } - dev->addr_assign_type &= ~NET_ADDR_RANDOM; return 0; } @@ -181,7 +180,8 @@ static int batadv_interface_tx(struct sk_buff *skb, goto dropped; /* Register the client MAC in the transtable */ - batadv_tt_local_add(soft_iface, ethhdr->h_source, skb->skb_iif); + if (!is_multicast_ether_addr(ethhdr->h_source)) + batadv_tt_local_add(soft_iface, ethhdr->h_source, skb->skb_iif); /* don't accept stp packets. STP does not help in meshes. * better use the bridge loop avoidance ... @@ -449,6 +449,30 @@ static void batadv_interface_setup(struct net_device *dev) memset(priv, 0, sizeof(*priv)); } +/** + * batadv_softif_destroy_finish - cleans up the remains of a softif + * @work: work queue item + * + * Free the parts of the soft interface which can not be removed under + * rtnl lock (to prevent deadlock situations). + */ +static void batadv_softif_destroy_finish(struct work_struct *work) +{ + struct batadv_priv *bat_priv; + struct net_device *soft_iface; + + bat_priv = container_of(work, struct batadv_priv, + cleanup_work); + soft_iface = bat_priv->soft_iface; + + batadv_debugfs_del_meshif(soft_iface); + batadv_sysfs_del_meshif(soft_iface); + + rtnl_lock(); + unregister_netdevice(soft_iface); + rtnl_unlock(); +} + struct net_device *batadv_softif_create(const char *name) { struct net_device *soft_iface; @@ -463,6 +487,8 @@ struct net_device *batadv_softif_create(const char *name) goto out; bat_priv = netdev_priv(soft_iface); + bat_priv->soft_iface = soft_iface; + INIT_WORK(&bat_priv->cleanup_work, batadv_softif_destroy_finish); /* batadv_interface_stats() needs to be available as soon as * register_netdevice() has been called @@ -480,7 +506,9 @@ struct net_device *batadv_softif_create(const char *name) atomic_set(&bat_priv->aggregated_ogms, 1); atomic_set(&bat_priv->bonding, 0); +#ifdef CONFIG_BATMAN_ADV_BLA atomic_set(&bat_priv->bridge_loop_avoidance, 0); +#endif #ifdef CONFIG_BATMAN_ADV_DAT atomic_set(&bat_priv->distributed_arp_table, 1); #endif @@ -491,7 +519,9 @@ struct net_device *batadv_softif_create(const char *name) atomic_set(&bat_priv->gw_bandwidth, 41); atomic_set(&bat_priv->orig_interval, 1000); atomic_set(&bat_priv->hop_penalty, 30); +#ifdef CONFIG_BATMAN_ADV_DEBUG atomic_set(&bat_priv->log_level, 0); +#endif atomic_set(&bat_priv->fragmentation, 1); atomic_set(&bat_priv->bcast_queue_left, BATADV_BCAST_QUEUE_LEN); atomic_set(&bat_priv->batman_queue_left, BATADV_BATMAN_QUEUE_LEN); @@ -547,10 +577,10 @@ out: void batadv_softif_destroy(struct net_device *soft_iface) { - batadv_debugfs_del_meshif(soft_iface); - batadv_sysfs_del_meshif(soft_iface); + struct batadv_priv *bat_priv = netdev_priv(soft_iface); + batadv_mesh_free(soft_iface); - unregister_netdevice(soft_iface); + queue_work(batadv_event_workqueue, &bat_priv->cleanup_work); } int batadv_softif_is_valid(const struct net_device *net_dev) @@ -581,10 +611,10 @@ static int batadv_get_settings(struct net_device *dev, struct ethtool_cmd *cmd) static void batadv_get_drvinfo(struct net_device *dev, struct ethtool_drvinfo *info) { - strcpy(info->driver, "B.A.T.M.A.N. advanced"); - strcpy(info->version, BATADV_SOURCE_VERSION); - strcpy(info->fw_version, "N/A"); - strcpy(info->bus_info, "batman"); + strlcpy(info->driver, "B.A.T.M.A.N. advanced", sizeof(info->driver)); + strlcpy(info->version, BATADV_SOURCE_VERSION, sizeof(info->version)); + strlcpy(info->fw_version, "N/A", sizeof(info->fw_version)); + strlcpy(info->bus_info, "batman", sizeof(info->bus_info)); } static u32 batadv_get_msglevel(struct net_device *dev) diff --git a/net/batman-adv/soft-interface.h b/net/batman-adv/soft-interface.h index 07a08fed28b9..43182e5e603a 100644 --- a/net/batman-adv/soft-interface.h +++ b/net/batman-adv/soft-interface.h @@ -1,4 +1,4 @@ -/* Copyright (C) 2007-2012 B.A.T.M.A.N. contributors: +/* Copyright (C) 2007-2013 B.A.T.M.A.N. contributors: * * Marek Lindner * diff --git a/net/batman-adv/sysfs.c b/net/batman-adv/sysfs.c index 84a55cb19b0b..afbba319d73a 100644 --- a/net/batman-adv/sysfs.c +++ b/net/batman-adv/sysfs.c @@ -1,4 +1,4 @@ -/* Copyright (C) 2010-2012 B.A.T.M.A.N. contributors: +/* Copyright (C) 2010-2013 B.A.T.M.A.N. contributors: * * Marek Lindner * diff --git a/net/batman-adv/sysfs.h b/net/batman-adv/sysfs.h index 3fd1412b0620..479acf4c16f4 100644 --- a/net/batman-adv/sysfs.h +++ b/net/batman-adv/sysfs.h @@ -1,4 +1,4 @@ -/* Copyright (C) 2010-2012 B.A.T.M.A.N. contributors: +/* Copyright (C) 2010-2013 B.A.T.M.A.N. contributors: * * Marek Lindner * diff --git a/net/batman-adv/translation-table.c b/net/batman-adv/translation-table.c index 22457a7952ba..d44672f4a349 100644 --- a/net/batman-adv/translation-table.c +++ b/net/batman-adv/translation-table.c @@ -1,4 +1,4 @@ -/* Copyright (C) 2007-2012 B.A.T.M.A.N. contributors: +/* Copyright (C) 2007-2013 B.A.T.M.A.N. contributors: * * Marek Lindner, Simon Wunderlich, Antonio Quartulli * @@ -29,6 +29,10 @@ #include <linux/crc16.h> +/* hash class keys */ +static struct lock_class_key batadv_tt_local_hash_lock_class_key; +static struct lock_class_key batadv_tt_global_hash_lock_class_key; + static void batadv_send_roam_adv(struct batadv_priv *bat_priv, uint8_t *client, struct batadv_orig_node *orig_node); static void batadv_tt_purge(struct work_struct *work); @@ -48,13 +52,6 @@ static int batadv_compare_tt(const struct hlist_node *node, const void *data2) return (memcmp(data1, data2, ETH_ALEN) == 0 ? 1 : 0); } -static void batadv_tt_start_timer(struct batadv_priv *bat_priv) -{ - INIT_DELAYED_WORK(&bat_priv->tt.work, batadv_tt_purge); - queue_delayed_work(batadv_event_workqueue, &bat_priv->tt.work, - msecs_to_jiffies(5000)); -} - static struct batadv_tt_common_entry * batadv_tt_hash_find(struct batadv_hashtable *hash, const void *data) { @@ -112,7 +109,6 @@ batadv_tt_global_hash_find(struct batadv_priv *bat_priv, const void *data) struct batadv_tt_global_entry, common); return tt_global_entry; - } static void @@ -235,6 +231,9 @@ static int batadv_tt_local_init(struct batadv_priv *bat_priv) if (!bat_priv->tt.local_hash) return -ENOMEM; + batadv_hash_set_lock_class(bat_priv->tt.local_hash, + &batadv_tt_local_hash_lock_class_key); + return 0; } @@ -249,7 +248,6 @@ static void batadv_tt_global_free(struct batadv_priv *bat_priv, batadv_hash_remove(bat_priv->tt.global_hash, batadv_compare_tt, batadv_choose_orig, tt_global->common.addr); batadv_tt_global_entry_free_ref(tt_global); - } void batadv_tt_local_add(struct net_device *soft_iface, const uint8_t *addr, @@ -305,7 +303,11 @@ void batadv_tt_local_add(struct net_device *soft_iface, const uint8_t *addr, (uint8_t)atomic_read(&bat_priv->tt.vn)); memcpy(tt_local->common.addr, addr, ETH_ALEN); - tt_local->common.flags = BATADV_NO_FLAGS; + /* The local entry has to be marked as NEW to avoid to send it in + * a full table response going out before the next ttvn increment + * (consistency check) + */ + tt_local->common.flags = BATADV_TT_CLIENT_NEW; if (batadv_is_wifi_iface(ifindex)) tt_local->common.flags |= BATADV_TT_CLIENT_WIFI; atomic_set(&tt_local->common.refcount, 2); @@ -316,12 +318,6 @@ void batadv_tt_local_add(struct net_device *soft_iface, const uint8_t *addr, if (batadv_compare_eth(addr, soft_iface->dev_addr)) tt_local->common.flags |= BATADV_TT_CLIENT_NOPURGE; - /* The local entry has to be marked as NEW to avoid to send it in - * a full table response going out before the next ttvn increment - * (consistency check) - */ - tt_local->common.flags |= BATADV_TT_CLIENT_NEW; - hash_added = batadv_hash_add(bat_priv->tt.local_hash, batadv_compare_tt, batadv_choose_orig, &tt_local->common, &tt_local->common.hash_entry); @@ -472,18 +468,27 @@ int batadv_tt_local_seq_print_text(struct seq_file *seq, void *offset) struct batadv_priv *bat_priv = netdev_priv(net_dev); struct batadv_hashtable *hash = bat_priv->tt.local_hash; struct batadv_tt_common_entry *tt_common_entry; + struct batadv_tt_local_entry *tt_local; struct batadv_hard_iface *primary_if; struct hlist_node *node; struct hlist_head *head; uint32_t i; + int last_seen_secs; + int last_seen_msecs; + unsigned long last_seen_jiffies; + bool no_purge; + uint16_t np_flag = BATADV_TT_CLIENT_NOPURGE; primary_if = batadv_seq_print_text_primary_if_get(seq); if (!primary_if) goto out; seq_printf(seq, - "Locally retrieved addresses (from %s) announced via TT (TTVN: %u):\n", - net_dev->name, (uint8_t)atomic_read(&bat_priv->tt.vn)); + "Locally retrieved addresses (from %s) announced via TT (TTVN: %u CRC: %#.4x):\n", + net_dev->name, (uint8_t)atomic_read(&bat_priv->tt.vn), + bat_priv->tt.local_crc); + seq_printf(seq, " %-13s %-7s %-10s\n", "Client", "Flags", + "Last seen"); for (i = 0; i < hash->size; i++) { head = &hash->table[i]; @@ -491,18 +496,29 @@ int batadv_tt_local_seq_print_text(struct seq_file *seq, void *offset) rcu_read_lock(); hlist_for_each_entry_rcu(tt_common_entry, node, head, hash_entry) { - seq_printf(seq, " * %pM [%c%c%c%c%c]\n", + tt_local = container_of(tt_common_entry, + struct batadv_tt_local_entry, + common); + last_seen_jiffies = jiffies - tt_local->last_seen; + last_seen_msecs = jiffies_to_msecs(last_seen_jiffies); + last_seen_secs = last_seen_msecs / 1000; + last_seen_msecs = last_seen_msecs % 1000; + + no_purge = tt_common_entry->flags & np_flag; + + seq_printf(seq, " * %pM [%c%c%c%c%c] %3u.%03u\n", tt_common_entry->addr, (tt_common_entry->flags & BATADV_TT_CLIENT_ROAM ? 'R' : '.'), - (tt_common_entry->flags & - BATADV_TT_CLIENT_NOPURGE ? 'P' : '.'), + no_purge ? 'P' : '.', (tt_common_entry->flags & BATADV_TT_CLIENT_NEW ? 'N' : '.'), (tt_common_entry->flags & BATADV_TT_CLIENT_PENDING ? 'X' : '.'), (tt_common_entry->flags & - BATADV_TT_CLIENT_WIFI ? 'W' : '.')); + BATADV_TT_CLIENT_WIFI ? 'W' : '.'), + no_purge ? 0 : last_seen_secs, + no_purge ? 0 : last_seen_msecs); } rcu_read_unlock(); } @@ -627,7 +643,6 @@ static void batadv_tt_local_purge(struct batadv_priv *bat_priv) batadv_tt_local_purge_list(bat_priv, head); spin_unlock_bh(list_lock); } - } static void batadv_tt_local_table_free(struct batadv_priv *bat_priv) @@ -676,6 +691,9 @@ static int batadv_tt_global_init(struct batadv_priv *bat_priv) if (!bat_priv->tt.global_hash) return -ENOMEM; + batadv_hash_set_lock_class(bat_priv->tt.global_hash, + &batadv_tt_global_hash_lock_class_key); + return 0; } @@ -967,10 +985,11 @@ batadv_tt_global_print_entry(struct batadv_tt_global_entry *tt_global_entry, best_entry = batadv_transtable_best_orig(tt_global_entry); if (best_entry) { last_ttvn = atomic_read(&best_entry->orig_node->last_ttvn); - seq_printf(seq, " %c %pM (%3u) via %pM (%3u) [%c%c%c]\n", + seq_printf(seq, + " %c %pM (%3u) via %pM (%3u) (%#.4x) [%c%c%c]\n", '*', tt_global_entry->common.addr, best_entry->ttvn, best_entry->orig_node->orig, - last_ttvn, + last_ttvn, best_entry->orig_node->tt_crc, (flags & BATADV_TT_CLIENT_ROAM ? 'R' : '.'), (flags & BATADV_TT_CLIENT_WIFI ? 'W' : '.'), (flags & BATADV_TT_CLIENT_TEMP ? 'T' : '.')); @@ -1012,8 +1031,9 @@ int batadv_tt_global_seq_print_text(struct seq_file *seq, void *offset) seq_printf(seq, "Globally announced TT entries received via the mesh %s\n", net_dev->name); - seq_printf(seq, " %-13s %s %-15s %s %s\n", - "Client", "(TTVN)", "Originator", "(Curr TTVN)", "Flags"); + seq_printf(seq, " %-13s %s %-15s %s (%-6s) %s\n", + "Client", "(TTVN)", "Originator", "(Curr TTVN)", "CRC", + "Flags"); for (i = 0; i < hash->size; i++) { head = &hash->table[i]; @@ -1049,7 +1069,6 @@ batadv_tt_global_del_orig_list(struct batadv_tt_global_entry *tt_global_entry) batadv_tt_orig_list_entry_free_ref(orig_entry); } spin_unlock_bh(&tt_global_entry->list_lock); - } static void @@ -1825,7 +1844,6 @@ out: if (!ret) kfree_skb(skb); return ret; - } static bool @@ -2111,7 +2129,9 @@ int batadv_tt_init(struct batadv_priv *bat_priv) if (ret < 0) return ret; - batadv_tt_start_timer(bat_priv); + INIT_DELAYED_WORK(&bat_priv->tt.work, batadv_tt_purge); + queue_delayed_work(batadv_event_workqueue, &bat_priv->tt.work, + msecs_to_jiffies(BATADV_TT_WORK_PERIOD)); return 1; } @@ -2261,7 +2281,8 @@ static void batadv_tt_purge(struct work_struct *work) batadv_tt_req_purge(bat_priv); batadv_tt_roam_purge(bat_priv); - batadv_tt_start_timer(bat_priv); + queue_delayed_work(batadv_event_workqueue, &bat_priv->tt.work, + msecs_to_jiffies(BATADV_TT_WORK_PERIOD)); } void batadv_tt_free(struct batadv_priv *bat_priv) @@ -2352,7 +2373,6 @@ static void batadv_tt_local_purge_pending_clients(struct batadv_priv *bat_priv) } spin_unlock_bh(list_lock); } - } static int batadv_tt_commit_changes(struct batadv_priv *bat_priv, @@ -2496,7 +2516,7 @@ void batadv_tt_update_orig(struct batadv_priv *bat_priv, orig_node->tt_crc != tt_crc) { request_table: batadv_dbg(BATADV_DBG_TT, bat_priv, - "TT inconsistency for %pM. Need to retrieve the correct information (ttvn: %u last_ttvn: %u crc: %u last_crc: %u num_changes: %u)\n", + "TT inconsistency for %pM. Need to retrieve the correct information (ttvn: %u last_ttvn: %u crc: %#.4x last_crc: %#.4x num_changes: %u)\n", orig_node->orig, ttvn, orig_ttvn, tt_crc, orig_node->tt_crc, tt_num_changes); batadv_send_tt_request(bat_priv, orig_node, ttvn, @@ -2549,7 +2569,6 @@ bool batadv_tt_local_client_is_roaming(struct batadv_priv *bat_priv, batadv_tt_local_entry_free_ref(tt_local_entry); out: return ret; - } bool batadv_tt_add_temporary_global_entry(struct batadv_priv *bat_priv, diff --git a/net/batman-adv/translation-table.h b/net/batman-adv/translation-table.h index 46d4451a59ee..ab8e683b402f 100644 --- a/net/batman-adv/translation-table.h +++ b/net/batman-adv/translation-table.h @@ -1,4 +1,4 @@ -/* Copyright (C) 2007-2012 B.A.T.M.A.N. contributors: +/* Copyright (C) 2007-2013 B.A.T.M.A.N. contributors: * * Marek Lindner, Simon Wunderlich, Antonio Quartulli * diff --git a/net/batman-adv/types.h b/net/batman-adv/types.h index ae9ac9aca8c5..4cd87a0b5b80 100644 --- a/net/batman-adv/types.h +++ b/net/batman-adv/types.h @@ -1,4 +1,4 @@ -/* Copyright (C) 2007-2012 B.A.T.M.A.N. contributors: +/* Copyright (C) 2007-2013 B.A.T.M.A.N. contributors: * * Marek Lindner, Simon Wunderlich * @@ -24,6 +24,9 @@ #include "bitarray.h" #include <linux/kernel.h> +/** + * Maximum overhead for the encapsulation for a payload packet + */ #define BATADV_HEADER_LEN \ (ETH_HLEN + max(sizeof(struct batadv_unicast_packet), \ sizeof(struct batadv_bcast_packet))) @@ -51,6 +54,22 @@ struct batadv_hard_iface_bat_iv { atomic_t ogm_seqno; }; +/** + * struct batadv_hard_iface - network device known to batman-adv + * @list: list node for batadv_hardif_list + * @if_num: identificator of the interface + * @if_status: status of the interface for batman-adv + * @net_dev: pointer to the net_device + * @frag_seqno: last fragment sequence number sent by this interface + * @hardif_obj: kobject of the per interface sysfs "mesh" directory + * @refcount: number of contexts the object is used + * @batman_adv_ptype: packet type describing packets that should be processed by + * batman-adv for this interface + * @soft_iface: the batman-adv interface which uses this network interface + * @rcu: struct used for freeing in an RCU-safe manner + * @bat_iv: BATMAN IV specific per hard interface data + * @cleanup_work: work queue callback item for hard interface deinit + */ struct batadv_hard_iface { struct list_head list; int16_t if_num; @@ -63,22 +82,52 @@ struct batadv_hard_iface { struct net_device *soft_iface; struct rcu_head rcu; struct batadv_hard_iface_bat_iv bat_iv; + struct work_struct cleanup_work; }; /** - * struct batadv_orig_node - structure for orig_list maintaining nodes of mesh - * @primary_addr: hosts primary interface address - * @last_seen: when last packet from this node was received - * @bcast_seqno_reset: time when the broadcast seqno window was reset - * @batman_seqno_reset: time when the batman seqno window was reset - * @gw_flags: flags related to gateway class - * @flags: for now only VIS_SERVER flag - * @last_real_seqno: last and best known sequence number - * @last_ttl: ttl of last received packet - * @last_bcast_seqno: last broadcast sequence number received by this host - * - * @candidates: how many candidates are available - * @selected: next bonding candidate + * struct batadv_orig_node - structure for orig_list maintaining nodes of mesh + * @orig: originator ethernet address + * @primary_addr: hosts primary interface address + * @router: router that should be used to reach this originator + * @batadv_dat_addr_t: address of the orig node in the distributed hash + * @bcast_own: bitfield containing the number of our OGMs this orig_node + * rebroadcasted "back" to us (relative to last_real_seqno) + * @bcast_own_sum: counted result of bcast_own + * @last_seen: time when last packet from this node was received + * @bcast_seqno_reset: time when the broadcast seqno window was reset + * @batman_seqno_reset: time when the batman seqno window was reset + * @gw_flags: flags related to gateway class + * @flags: for now only VIS_SERVER flag + * @last_ttvn: last seen translation table version number + * @tt_crc: CRC of the translation table + * @tt_buff: last tt changeset this node received from the orig node + * @tt_buff_len: length of the last tt changeset this node received from the + * orig node + * @tt_buff_lock: lock that protects tt_buff and tt_buff_len + * @tt_size: number of global TT entries announced by the orig node + * @tt_initialised: bool keeping track of whether or not this node have received + * any translation table information from the orig node yet + * @last_real_seqno: last and best known sequence number + * @last_ttl: ttl of last received packet + * @bcast_bits: bitfield containing the info which payload broadcast originated + * from this orig node this host already has seen (relative to + * last_bcast_seqno) + * @last_bcast_seqno: last broadcast sequence number received by this host + * @neigh_list: list of potential next hop neighbor towards this orig node + * @frag_list: fragmentation buffer list for fragment re-assembly + * @last_frag_packet: time when last fragmented packet from this node was + * received + * @neigh_list_lock: lock protecting neigh_list, router and bonding_list + * @hash_entry: hlist node for batadv_priv::orig_hash + * @bat_priv: pointer to soft_iface this orig node belongs to + * @ogm_cnt_lock: lock protecting bcast_own, bcast_own_sum, + * neigh_node->real_bits & neigh_node->real_packet_count + * @bcast_seqno_lock: lock protecting bcast_bits & last_bcast_seqno + * @bond_candidates: how many candidates are available + * @bond_list: list of bonding candidates + * @refcount: number of contexts the object is used + * @rcu: struct used for freeing in an RCU-safe manner */ struct batadv_orig_node { uint8_t orig[ETH_ALEN]; @@ -94,11 +143,11 @@ struct batadv_orig_node { unsigned long batman_seqno_reset; uint8_t gw_flags; uint8_t flags; - atomic_t last_ttvn; /* last seen translation table version number */ + atomic_t last_ttvn; uint16_t tt_crc; unsigned char *tt_buff; int16_t tt_buff_len; - spinlock_t tt_buff_lock; /* protects tt_buff */ + spinlock_t tt_buff_lock; /* protects tt_buff & tt_buff_len */ atomic_t tt_size; bool tt_initialised; uint32_t last_real_seqno; @@ -107,23 +156,31 @@ struct batadv_orig_node { uint32_t last_bcast_seqno; struct hlist_head neigh_list; struct list_head frag_list; - spinlock_t neigh_list_lock; /* protects neigh_list and router */ - atomic_t refcount; - struct rcu_head rcu; + unsigned long last_frag_packet; + /* neigh_list_lock protects: neigh_list, router & bonding_list */ + spinlock_t neigh_list_lock; struct hlist_node hash_entry; struct batadv_priv *bat_priv; - unsigned long last_frag_packet; /* ogm_cnt_lock protects: bcast_own, bcast_own_sum, - * neigh_node->real_bits, neigh_node->real_packet_count + * neigh_node->real_bits & neigh_node->real_packet_count */ spinlock_t ogm_cnt_lock; - /* bcast_seqno_lock protects bcast_bits, last_bcast_seqno */ + /* bcast_seqno_lock protects: bcast_bits & last_bcast_seqno */ spinlock_t bcast_seqno_lock; - spinlock_t tt_list_lock; /* protects tt_list */ atomic_t bond_candidates; struct list_head bond_list; + atomic_t refcount; + struct rcu_head rcu; }; +/** + * struct batadv_gw_node - structure for orig nodes announcing gw capabilities + * @list: list node for batadv_priv_gw::list + * @orig_node: pointer to corresponding orig node + * @deleted: this struct is scheduled for deletion + * @refcount: number of contexts the object is used + * @rcu: struct used for freeing in an RCU-safe manner + */ struct batadv_gw_node { struct hlist_node list; struct batadv_orig_node *orig_node; @@ -132,13 +189,28 @@ struct batadv_gw_node { struct rcu_head rcu; }; -/* batadv_neigh_node - * @last_seen: when last packet via this neighbor was received +/** + * struct batadv_neigh_node - structure for single hop neighbors + * @list: list node for batadv_orig_node::neigh_list + * @addr: mac address of neigh node + * @tq_recv: ring buffer of received TQ values from this neigh node + * @tq_index: ring buffer index + * @tq_avg: averaged tq of all tq values in the ring buffer (tq_recv) + * @last_ttl: last received ttl from this neigh node + * @bonding_list: list node for batadv_orig_node::bond_list + * @last_seen: when last packet via this neighbor was received + * @real_bits: bitfield containing the number of OGMs received from this neigh + * node (relative to orig_node->last_real_seqno) + * @real_packet_count: counted result of real_bits + * @orig_node: pointer to corresponding orig_node + * @if_incoming: pointer to incoming hard interface + * @lq_update_lock: lock protecting tq_recv & tq_index + * @refcount: number of contexts the object is used + * @rcu: struct used for freeing in an RCU-safe manner */ struct batadv_neigh_node { struct hlist_node list; uint8_t addr[ETH_ALEN]; - uint8_t real_packet_count; uint8_t tq_recv[BATADV_TQ_GLOBAL_WINDOW_SIZE]; uint8_t tq_index; uint8_t tq_avg; @@ -146,13 +218,20 @@ struct batadv_neigh_node { struct list_head bonding_list; unsigned long last_seen; DECLARE_BITMAP(real_bits, BATADV_TQ_LOCAL_WINDOW_SIZE); - atomic_t refcount; - struct rcu_head rcu; + uint8_t real_packet_count; struct batadv_orig_node *orig_node; struct batadv_hard_iface *if_incoming; - spinlock_t lq_update_lock; /* protects: tq_recv, tq_index */ + spinlock_t lq_update_lock; /* protects tq_recv & tq_index */ + atomic_t refcount; + struct rcu_head rcu; }; +/** + * struct batadv_bcast_duplist_entry - structure for LAN broadcast suppression + * @orig[ETH_ALEN]: mac address of orig node orginating the broadcast + * @crc: crc32 checksum of broadcast payload + * @entrytime: time when the broadcast packet was received + */ #ifdef CONFIG_BATMAN_ADV_BLA struct batadv_bcast_duplist_entry { uint8_t orig[ETH_ALEN]; @@ -161,6 +240,33 @@ struct batadv_bcast_duplist_entry { }; #endif +/** + * enum batadv_counters - indices for traffic counters + * @BATADV_CNT_TX: transmitted payload traffic packet counter + * @BATADV_CNT_TX_BYTES: transmitted payload traffic bytes counter + * @BATADV_CNT_TX_DROPPED: dropped transmission payload traffic packet counter + * @BATADV_CNT_RX: received payload traffic packet counter + * @BATADV_CNT_RX_BYTES: received payload traffic bytes counter + * @BATADV_CNT_FORWARD: forwarded payload traffic packet counter + * @BATADV_CNT_FORWARD_BYTES: forwarded payload traffic bytes counter + * @BATADV_CNT_MGMT_TX: transmitted routing protocol traffic packet counter + * @BATADV_CNT_MGMT_TX_BYTES: transmitted routing protocol traffic bytes counter + * @BATADV_CNT_MGMT_RX: received routing protocol traffic packet counter + * @BATADV_CNT_MGMT_RX_BYTES: received routing protocol traffic bytes counter + * @BATADV_CNT_TT_REQUEST_TX: transmitted tt req traffic packet counter + * @BATADV_CNT_TT_REQUEST_RX: received tt req traffic packet counter + * @BATADV_CNT_TT_RESPONSE_TX: transmitted tt resp traffic packet counter + * @BATADV_CNT_TT_RESPONSE_RX: received tt resp traffic packet counter + * @BATADV_CNT_TT_ROAM_ADV_TX: transmitted tt roam traffic packet counter + * @BATADV_CNT_TT_ROAM_ADV_RX: received tt roam traffic packet counter + * @BATADV_CNT_DAT_GET_TX: transmitted dht GET traffic packet counter + * @BATADV_CNT_DAT_GET_RX: received dht GET traffic packet counter + * @BATADV_CNT_DAT_PUT_TX: transmitted dht PUT traffic packet counter + * @BATADV_CNT_DAT_PUT_RX: received dht PUT traffic packet counter + * @BATADV_CNT_DAT_CACHED_REPLY_TX: transmitted dat cache reply traffic packet + * counter + * @BATADV_CNT_NUM: number of traffic counters + */ enum batadv_counters { BATADV_CNT_TX, BATADV_CNT_TX_BYTES, @@ -192,14 +298,23 @@ enum batadv_counters { /** * struct batadv_priv_tt - per mesh interface translation table data * @vn: translation table version number + * @ogm_append_cnt: counter of number of OGMs containing the local tt diff * @local_changes: changes registered in an originator interval - * @poss_change: Detect an ongoing roaming phase. If true, then this node - * received a roaming_adv and has to inspect every packet directed to it to - * check whether it still is the true destination or not. This flag will be - * reset to false as soon as the this node's ttvn is increased * @changes_list: tracks tt local changes within an originator interval - * @req_list: list of pending tt_requests + * @local_hash: local translation table hash table + * @global_hash: global translation table hash table + * @req_list: list of pending & unanswered tt_requests + * @roam_list: list of the last roaming events of each client limiting the + * number of roaming events to avoid route flapping + * @changes_list_lock: lock protecting changes_list + * @req_list_lock: lock protecting req_list + * @roam_list_lock: lock protecting roam_list + * @local_entry_num: number of entries in the local hash table * @local_crc: Checksum of the local table, recomputed before sending a new OGM + * @last_changeset: last tt changeset this host has generated + * @last_changeset_len: length of last tt changeset this host has generated + * @last_changeset_lock: lock protecting last_changeset & last_changeset_len + * @work: work queue callback item for translation table purging */ struct batadv_priv_tt { atomic_t vn; @@ -217,36 +332,83 @@ struct batadv_priv_tt { uint16_t local_crc; unsigned char *last_changeset; int16_t last_changeset_len; - spinlock_t last_changeset_lock; /* protects last_changeset */ + /* protects last_changeset & last_changeset_len */ + spinlock_t last_changeset_lock; struct delayed_work work; }; +/** + * struct batadv_priv_bla - per mesh interface bridge loope avoidance data + * @num_requests; number of bla requests in flight + * @claim_hash: hash table containing mesh nodes this host has claimed + * @backbone_hash: hash table containing all detected backbone gateways + * @bcast_duplist: recently received broadcast packets array (for broadcast + * duplicate suppression) + * @bcast_duplist_curr: index of last broadcast packet added to bcast_duplist + * @bcast_duplist_lock: lock protecting bcast_duplist & bcast_duplist_curr + * @claim_dest: local claim data (e.g. claim group) + * @work: work queue callback item for cleanups & bla announcements + */ #ifdef CONFIG_BATMAN_ADV_BLA struct batadv_priv_bla { - atomic_t num_requests; /* number of bla requests in flight */ + atomic_t num_requests; struct batadv_hashtable *claim_hash; struct batadv_hashtable *backbone_hash; struct batadv_bcast_duplist_entry bcast_duplist[BATADV_DUPLIST_SIZE]; int bcast_duplist_curr; - /* protects bcast_duplist and bcast_duplist_curr */ + /* protects bcast_duplist & bcast_duplist_curr */ spinlock_t bcast_duplist_lock; struct batadv_bla_claim_dst claim_dest; struct delayed_work work; }; #endif +/** + * struct batadv_debug_log - debug logging data + * @log_buff: buffer holding the logs (ring bufer) + * @log_start: index of next character to read + * @log_end: index of next character to write + * @lock: lock protecting log_buff, log_start & log_end + * @queue_wait: log reader's wait queue + */ +#ifdef CONFIG_BATMAN_ADV_DEBUG +struct batadv_priv_debug_log { + char log_buff[BATADV_LOG_BUF_LEN]; + unsigned long log_start; + unsigned long log_end; + spinlock_t lock; /* protects log_buff, log_start and log_end */ + wait_queue_head_t queue_wait; +}; +#endif + +/** + * struct batadv_priv_gw - per mesh interface gateway data + * @list: list of available gateway nodes + * @list_lock: lock protecting gw_list & curr_gw + * @curr_gw: pointer to currently selected gateway node + * @reselect: bool indicating a gateway re-selection is in progress + */ struct batadv_priv_gw { struct hlist_head list; - spinlock_t list_lock; /* protects gw_list and curr_gw */ + spinlock_t list_lock; /* protects gw_list & curr_gw */ struct batadv_gw_node __rcu *curr_gw; /* rcu protected pointer */ atomic_t reselect; }; +/** + * struct batadv_priv_vis - per mesh interface vis data + * @send_list: list of batadv_vis_info packets to sent + * @hash: hash table containing vis data from other nodes in the network + * @hash_lock: lock protecting the hash table + * @list_lock: lock protecting my_info::recv_list + * @work: work queue callback item for vis packet sending + * @my_info: holds this node's vis data sent on a regular basis + */ struct batadv_priv_vis { struct list_head send_list; struct batadv_hashtable *hash; spinlock_t hash_lock; /* protects hash */ - spinlock_t list_lock; /* protects info::recv_list */ + spinlock_t list_lock; /* protects my_info::recv_list */ struct delayed_work work; struct batadv_vis_info *my_info; }; @@ -265,30 +427,78 @@ struct batadv_priv_dat { }; #endif +/** + * struct batadv_priv - per mesh interface data + * @mesh_state: current status of the mesh (inactive/active/deactivating) + * @soft_iface: net device which holds this struct as private data + * @stats: structure holding the data for the ndo_get_stats() call + * @bat_counters: mesh internal traffic statistic counters (see batadv_counters) + * @aggregated_ogms: bool indicating whether OGM aggregation is enabled + * @bonding: bool indicating whether traffic bonding is enabled + * @fragmentation: bool indicating whether traffic fragmentation is enabled + * @ap_isolation: bool indicating whether ap isolation is enabled + * @bridge_loop_avoidance: bool indicating whether bridge loop avoidance is + * enabled + * @distributed_arp_table: bool indicating whether distributed ARP table is + * enabled + * @vis_mode: vis operation: client or server (see batadv_vis_packettype) + * @gw_mode: gateway operation: off, client or server (see batadv_gw_modes) + * @gw_sel_class: gateway selection class (applies if gw_mode client) + * @gw_bandwidth: gateway announced bandwidth (applies if gw_mode server) + * @orig_interval: OGM broadcast interval in milliseconds + * @hop_penalty: penalty which will be applied to an OGM's tq-field on every hop + * @log_level: configured log level (see batadv_dbg_level) + * @bcast_seqno: last sent broadcast packet sequence number + * @bcast_queue_left: number of remaining buffered broadcast packet slots + * @batman_queue_left: number of remaining OGM packet slots + * @num_ifaces: number of interfaces assigned to this mesh interface + * @mesh_obj: kobject for sysfs mesh subdirectory + * @debug_dir: dentry for debugfs batman-adv subdirectory + * @forw_bat_list: list of aggregated OGMs that will be forwarded + * @forw_bcast_list: list of broadcast packets that will be rebroadcasted + * @orig_hash: hash table containing mesh participants (orig nodes) + * @forw_bat_list_lock: lock protecting forw_bat_list + * @forw_bcast_list_lock: lock protecting forw_bcast_list + * @orig_work: work queue callback item for orig node purging + * @cleanup_work: work queue callback item for soft interface deinit + * @primary_if: one of the hard interfaces assigned to this mesh interface + * becomes the primary interface + * @bat_algo_ops: routing algorithm used by this mesh interface + * @bla: bridge loope avoidance data + * @debug_log: holding debug logging relevant data + * @gw: gateway data + * @tt: translation table data + * @vis: vis data + * @dat: distributed arp table data + */ struct batadv_priv { atomic_t mesh_state; + struct net_device *soft_iface; struct net_device_stats stats; uint64_t __percpu *bat_counters; /* Per cpu counters */ - atomic_t aggregated_ogms; /* boolean */ - atomic_t bonding; /* boolean */ - atomic_t fragmentation; /* boolean */ - atomic_t ap_isolation; /* boolean */ - atomic_t bridge_loop_avoidance; /* boolean */ + atomic_t aggregated_ogms; + atomic_t bonding; + atomic_t fragmentation; + atomic_t ap_isolation; +#ifdef CONFIG_BATMAN_ADV_BLA + atomic_t bridge_loop_avoidance; +#endif #ifdef CONFIG_BATMAN_ADV_DAT - atomic_t distributed_arp_table; /* boolean */ + atomic_t distributed_arp_table; +#endif + atomic_t vis_mode; + atomic_t gw_mode; + atomic_t gw_sel_class; + atomic_t gw_bandwidth; + atomic_t orig_interval; + atomic_t hop_penalty; +#ifdef CONFIG_BATMAN_ADV_DEBUG + atomic_t log_level; #endif - atomic_t vis_mode; /* VIS_TYPE_* */ - atomic_t gw_mode; /* GW_MODE_* */ - atomic_t gw_sel_class; /* uint */ - atomic_t gw_bandwidth; /* gw bandwidth */ - atomic_t orig_interval; /* uint */ - atomic_t hop_penalty; /* uint */ - atomic_t log_level; /* uint */ atomic_t bcast_seqno; atomic_t bcast_queue_left; atomic_t batman_queue_left; char num_ifaces; - struct batadv_debug_log *debug_log; struct kobject *mesh_obj; struct dentry *debug_dir; struct hlist_head forw_bat_list; @@ -297,11 +507,15 @@ struct batadv_priv { spinlock_t forw_bat_list_lock; /* protects forw_bat_list */ spinlock_t forw_bcast_list_lock; /* protects forw_bcast_list */ struct delayed_work orig_work; + struct work_struct cleanup_work; struct batadv_hard_iface __rcu *primary_if; /* rcu protected pointer */ struct batadv_algo_ops *bat_algo_ops; #ifdef CONFIG_BATMAN_ADV_BLA struct batadv_priv_bla bla; #endif +#ifdef CONFIG_BATMAN_ADV_DEBUG + struct batadv_priv_debug_log *debug_log; +#endif struct batadv_priv_gw gw; struct batadv_priv_tt tt; struct batadv_priv_vis vis; @@ -310,21 +524,97 @@ struct batadv_priv { #endif }; +/** + * struct batadv_socket_client - layer2 icmp socket client data + * @queue_list: packet queue for packets destined for this socket client + * @queue_len: number of packets in the packet queue (queue_list) + * @index: socket client's index in the batadv_socket_client_hash + * @lock: lock protecting queue_list, queue_len & index + * @queue_wait: socket client's wait queue + * @bat_priv: pointer to soft_iface this client belongs to + */ struct batadv_socket_client { struct list_head queue_list; unsigned int queue_len; unsigned char index; - spinlock_t lock; /* protects queue_list, queue_len, index */ + spinlock_t lock; /* protects queue_list, queue_len & index */ wait_queue_head_t queue_wait; struct batadv_priv *bat_priv; }; +/** + * struct batadv_socket_packet - layer2 icmp packet for socket client + * @list: list node for batadv_socket_client::queue_list + * @icmp_len: size of the layer2 icmp packet + * @icmp_packet: layer2 icmp packet + */ struct batadv_socket_packet { struct list_head list; size_t icmp_len; struct batadv_icmp_packet_rr icmp_packet; }; +/** + * struct batadv_bla_backbone_gw - batman-adv gateway bridged into the LAN + * @orig: originator address of backbone node (mac address of primary iface) + * @vid: vlan id this gateway was detected on + * @hash_entry: hlist node for batadv_priv_bla::backbone_hash + * @bat_priv: pointer to soft_iface this backbone gateway belongs to + * @lasttime: last time we heard of this backbone gw + * @wait_periods: grace time for bridge forward delays and bla group forming at + * bootup phase - no bcast traffic is formwared until it has elapsed + * @request_sent: if this bool is set to true we are out of sync with this + * backbone gateway - no bcast traffic is formwared until the situation was + * resolved + * @crc: crc16 checksum over all claims + * @refcount: number of contexts the object is used + * @rcu: struct used for freeing in an RCU-safe manner + */ +#ifdef CONFIG_BATMAN_ADV_BLA +struct batadv_bla_backbone_gw { + uint8_t orig[ETH_ALEN]; + short vid; + struct hlist_node hash_entry; + struct batadv_priv *bat_priv; + unsigned long lasttime; + atomic_t wait_periods; + atomic_t request_sent; + uint16_t crc; + atomic_t refcount; + struct rcu_head rcu; +}; + +/** + * struct batadv_bla_claim - claimed non-mesh client structure + * @addr: mac address of claimed non-mesh client + * @vid: vlan id this client was detected on + * @batadv_bla_backbone_gw: pointer to backbone gw claiming this client + * @lasttime: last time we heard of claim (locals only) + * @hash_entry: hlist node for batadv_priv_bla::claim_hash + * @refcount: number of contexts the object is used + * @rcu: struct used for freeing in an RCU-safe manner + */ +struct batadv_bla_claim { + uint8_t addr[ETH_ALEN]; + short vid; + struct batadv_bla_backbone_gw *backbone_gw; + unsigned long lasttime; + struct hlist_node hash_entry; + struct rcu_head rcu; + atomic_t refcount; +}; +#endif + +/** + * struct batadv_tt_common_entry - tt local & tt global common data + * @addr: mac address of non-mesh client + * @hash_entry: hlist node for batadv_priv_tt::local_hash or for + * batadv_priv_tt::global_hash + * @flags: various state handling flags (see batadv_tt_client_flags) + * @added_at: timestamp used for purging stale tt common entries + * @refcount: number of contexts the object is used + * @rcu: struct used for freeing in an RCU-safe manner + */ struct batadv_tt_common_entry { uint8_t addr[ETH_ALEN]; struct hlist_node hash_entry; @@ -334,62 +624,76 @@ struct batadv_tt_common_entry { struct rcu_head rcu; }; +/** + * struct batadv_tt_local_entry - translation table local entry data + * @common: general translation table data + * @last_seen: timestamp used for purging stale tt local entries + */ struct batadv_tt_local_entry { struct batadv_tt_common_entry common; unsigned long last_seen; }; +/** + * struct batadv_tt_global_entry - translation table global entry data + * @common: general translation table data + * @orig_list: list of orig nodes announcing this non-mesh client + * @list_lock: lock protecting orig_list + * @roam_at: time at which TT_GLOBAL_ROAM was set + */ struct batadv_tt_global_entry { struct batadv_tt_common_entry common; struct hlist_head orig_list; - spinlock_t list_lock; /* protects the list */ - unsigned long roam_at; /* time at which TT_GLOBAL_ROAM was set */ + spinlock_t list_lock; /* protects orig_list */ + unsigned long roam_at; }; +/** + * struct batadv_tt_orig_list_entry - orig node announcing a non-mesh client + * @orig_node: pointer to orig node announcing this non-mesh client + * @ttvn: translation table version number which added the non-mesh client + * @list: list node for batadv_tt_global_entry::orig_list + * @refcount: number of contexts the object is used + * @rcu: struct used for freeing in an RCU-safe manner + */ struct batadv_tt_orig_list_entry { struct batadv_orig_node *orig_node; uint8_t ttvn; - atomic_t refcount; - struct rcu_head rcu; struct hlist_node list; -}; - -#ifdef CONFIG_BATMAN_ADV_BLA -struct batadv_backbone_gw { - uint8_t orig[ETH_ALEN]; - short vid; /* used VLAN ID */ - struct hlist_node hash_entry; - struct batadv_priv *bat_priv; - unsigned long lasttime; /* last time we heard of this backbone gw */ - atomic_t wait_periods; - atomic_t request_sent; atomic_t refcount; struct rcu_head rcu; - uint16_t crc; /* crc checksum over all claims */ -}; - -struct batadv_claim { - uint8_t addr[ETH_ALEN]; - short vid; - struct batadv_backbone_gw *backbone_gw; - unsigned long lasttime; /* last time we heard of claim (locals only) */ - struct rcu_head rcu; - atomic_t refcount; - struct hlist_node hash_entry; }; -#endif +/** + * struct batadv_tt_change_node - structure for tt changes occured + * @list: list node for batadv_priv_tt::changes_list + * @change: holds the actual translation table diff data + */ struct batadv_tt_change_node { struct list_head list; struct batadv_tt_change change; }; +/** + * struct batadv_tt_req_node - data to keep track of the tt requests in flight + * @addr: mac address address of the originator this request was sent to + * @issued_at: timestamp used for purging stale tt requests + * @list: list node for batadv_priv_tt::req_list + */ struct batadv_tt_req_node { uint8_t addr[ETH_ALEN]; unsigned long issued_at; struct list_head list; }; +/** + * struct batadv_tt_roam_node - roaming client data + * @addr: mac address of the client in the roaming phase + * @counter: number of allowed roaming events per client within a single + * OGM interval (changes are committed with each OGM) + * @first_time: timestamp used for purging stale roaming node entries + * @list: list node for batadv_priv_tt::roam_list + */ struct batadv_tt_roam_node { uint8_t addr[ETH_ALEN]; atomic_t counter; @@ -397,8 +701,19 @@ struct batadv_tt_roam_node { struct list_head list; }; -/* forw_packet - structure for forw_list maintaining packets to be - * send/forwarded +/** + * struct batadv_forw_packet - structure for bcast packets to be sent/forwarded + * @list: list node for batadv_socket_client::queue_list + * @send_time: execution time for delayed_work (packet sending) + * @own: bool for locally generated packets (local OGMs are re-scheduled after + * sending) + * @skb: bcast packet's skb buffer + * @packet_len: size of aggregated OGM packet inside the skb buffer + * @direct_link_flags: direct link flags for aggregated OGM packets + * @num_packets: counter for bcast packet retransmission + * @delayed_work: work queue callback item for packet sending + * @if_incoming: pointer incoming hard-iface or primary iface if locally + * generated packet */ struct batadv_forw_packet { struct hlist_node list; @@ -412,72 +727,98 @@ struct batadv_forw_packet { struct batadv_hard_iface *if_incoming; }; -/* While scanning for vis-entries of a particular vis-originator - * this list collects its interfaces to create a subgraph/cluster - * out of them later +/** + * struct batadv_frag_packet_list_entry - storage for fragment packet + * @list: list node for orig_node::frag_list + * @seqno: sequence number of the fragment + * @skb: fragment's skb buffer */ -struct batadv_if_list_entry { - uint8_t addr[ETH_ALEN]; - bool primary; - struct hlist_node list; -}; - -struct batadv_debug_log { - char log_buff[BATADV_LOG_BUF_LEN]; - unsigned long log_start; - unsigned long log_end; - spinlock_t lock; /* protects log_buff, log_start and log_end */ - wait_queue_head_t queue_wait; -}; - struct batadv_frag_packet_list_entry { struct list_head list; uint16_t seqno; struct sk_buff *skb; }; +/** + * struct batadv_vis_info - local data for vis information + * @first_seen: timestamp used for purging stale vis info entries + * @recv_list: List of server-neighbors we have received this packet from. This + * packet should not be re-forward to them again. List elements are struct + * batadv_vis_recvlist_node + * @send_list: list of packets to be forwarded + * @refcount: number of contexts the object is used + * @hash_entry: hlist node for batadv_priv_vis::hash + * @bat_priv: pointer to soft_iface this orig node belongs to + * @skb_packet: contains the vis packet + */ struct batadv_vis_info { unsigned long first_seen; - /* list of server-neighbors we received a vis-packet - * from. we should not reply to them. - */ struct list_head recv_list; struct list_head send_list; struct kref refcount; struct hlist_node hash_entry; struct batadv_priv *bat_priv; - /* this packet might be part of the vis send queue. */ struct sk_buff *skb_packet; - /* vis_info may follow here */ } __packed; +/** + * struct batadv_vis_info_entry - contains link information for vis + * @src: source MAC of the link, all zero for local TT entry + * @dst: destination MAC of the link, client mac address for local TT entry + * @quality: transmission quality of the link, or 0 for local TT entry + */ struct batadv_vis_info_entry { uint8_t src[ETH_ALEN]; uint8_t dest[ETH_ALEN]; - uint8_t quality; /* quality = 0 client */ + uint8_t quality; } __packed; -struct batadv_recvlist_node { +/** + * struct batadv_vis_recvlist_node - list entry for batadv_vis_info::recv_list + * @list: list node for batadv_vis_info::recv_list + * @mac: MAC address of the originator from where the vis_info was received + */ +struct batadv_vis_recvlist_node { struct list_head list; uint8_t mac[ETH_ALEN]; }; +/** + * struct batadv_vis_if_list_entry - auxiliary data for vis data generation + * @addr: MAC address of the interface + * @primary: true if this interface is the primary interface + * @list: list node the interface list + * + * While scanning for vis-entries of a particular vis-originator + * this list collects its interfaces to create a subgraph/cluster + * out of them later + */ +struct batadv_vis_if_list_entry { + uint8_t addr[ETH_ALEN]; + bool primary; + struct hlist_node list; +}; + +/** + * struct batadv_algo_ops - mesh algorithm callbacks + * @list: list node for the batadv_algo_list + * @name: name of the algorithm + * @bat_iface_enable: init routing info when hard-interface is enabled + * @bat_iface_disable: de-init routing info when hard-interface is disabled + * @bat_iface_update_mac: (re-)init mac addresses of the protocol information + * belonging to this hard-interface + * @bat_primary_iface_set: called when primary interface is selected / changed + * @bat_ogm_schedule: prepare a new outgoing OGM for the send queue + * @bat_ogm_emit: send scheduled OGM + */ struct batadv_algo_ops { struct hlist_node list; char *name; - /* init routing info when hard-interface is enabled */ int (*bat_iface_enable)(struct batadv_hard_iface *hard_iface); - /* de-init routing info when hard-interface is disabled */ void (*bat_iface_disable)(struct batadv_hard_iface *hard_iface); - /* (re-)init mac addresses of the protocol information - * belonging to this hard-interface - */ void (*bat_iface_update_mac)(struct batadv_hard_iface *hard_iface); - /* called when primary interface is selected / changed */ void (*bat_primary_iface_set)(struct batadv_hard_iface *hard_iface); - /* prepare a new outgoing OGM for the send queue */ void (*bat_ogm_schedule)(struct batadv_hard_iface *hard_iface); - /* send scheduled OGM */ void (*bat_ogm_emit)(struct batadv_forw_packet *forw_packet); }; diff --git a/net/batman-adv/unicast.c b/net/batman-adv/unicast.c index 10aff49fcf25..50e079f00be6 100644 --- a/net/batman-adv/unicast.c +++ b/net/batman-adv/unicast.c @@ -1,4 +1,4 @@ -/* Copyright (C) 2010-2012 B.A.T.M.A.N. contributors: +/* Copyright (C) 2010-2013 B.A.T.M.A.N. contributors: * * Andreas Langer * @@ -133,7 +133,6 @@ batadv_frag_search_packet(struct list_head *head, is_head = !!(up->flags & BATADV_UNI_FRAG_HEAD); list_for_each_entry(tfp, head, list) { - if (!tfp->skb) continue; @@ -162,7 +161,6 @@ void batadv_frag_list_free(struct list_head *head) struct batadv_frag_packet_list_entry *pf, *tmp_pf; if (!list_empty(head)) { - list_for_each_entry_safe(pf, tmp_pf, head, list) { kfree_skb(pf->skb); list_del(&pf->list); diff --git a/net/batman-adv/unicast.h b/net/batman-adv/unicast.h index 61abba58bd8f..429cf8a4a31e 100644 --- a/net/batman-adv/unicast.h +++ b/net/batman-adv/unicast.h @@ -1,4 +1,4 @@ -/* Copyright (C) 2010-2012 B.A.T.M.A.N. contributors: +/* Copyright (C) 2010-2013 B.A.T.M.A.N. contributors: * * Andreas Langer * diff --git a/net/batman-adv/vis.c b/net/batman-adv/vis.c index 0f65a9de5f74..22d2785177d1 100644 --- a/net/batman-adv/vis.c +++ b/net/batman-adv/vis.c @@ -1,4 +1,4 @@ -/* Copyright (C) 2008-2012 B.A.T.M.A.N. contributors: +/* Copyright (C) 2008-2013 B.A.T.M.A.N. contributors: * * Simon Wunderlich * @@ -28,14 +28,15 @@ #define BATADV_MAX_VIS_PACKET_SIZE 1000 -static void batadv_start_vis_timer(struct batadv_priv *bat_priv); +/* hash class keys */ +static struct lock_class_key batadv_vis_hash_lock_class_key; /* free the info */ static void batadv_free_info(struct kref *ref) { struct batadv_vis_info *info; struct batadv_priv *bat_priv; - struct batadv_recvlist_node *entry, *tmp; + struct batadv_vis_recvlist_node *entry, *tmp; info = container_of(ref, struct batadv_vis_info, refcount); bat_priv = info->bat_priv; @@ -126,7 +127,7 @@ static void batadv_vis_data_insert_interface(const uint8_t *interface, struct hlist_head *if_list, bool primary) { - struct batadv_if_list_entry *entry; + struct batadv_vis_if_list_entry *entry; struct hlist_node *pos; hlist_for_each_entry(entry, pos, if_list, list) { @@ -146,7 +147,7 @@ static void batadv_vis_data_insert_interface(const uint8_t *interface, static void batadv_vis_data_read_prim_sec(struct seq_file *seq, const struct hlist_head *if_list) { - struct batadv_if_list_entry *entry; + struct batadv_vis_if_list_entry *entry; struct hlist_node *pos; hlist_for_each_entry(entry, pos, if_list, list) { @@ -196,7 +197,7 @@ static void batadv_vis_data_read_entries(struct seq_file *seq, struct batadv_vis_info_entry *entries) { int i; - struct batadv_if_list_entry *entry; + struct batadv_vis_if_list_entry *entry; struct hlist_node *pos; hlist_for_each_entry(entry, pos, list, list) { @@ -222,7 +223,7 @@ static void batadv_vis_seq_print_text_bucket(struct seq_file *seq, struct batadv_vis_packet *packet; uint8_t *entries_pos; struct batadv_vis_info_entry *entries; - struct batadv_if_list_entry *entry; + struct batadv_vis_if_list_entry *entry; struct hlist_node *pos, *n; HLIST_HEAD(vis_if_list); @@ -304,7 +305,7 @@ static void batadv_send_list_del(struct batadv_vis_info *info) static void batadv_recv_list_add(struct batadv_priv *bat_priv, struct list_head *recv_list, const char *mac) { - struct batadv_recvlist_node *entry; + struct batadv_vis_recvlist_node *entry; entry = kmalloc(sizeof(*entry), GFP_ATOMIC); if (!entry) @@ -321,7 +322,7 @@ static int batadv_recv_list_is_in(struct batadv_priv *bat_priv, const struct list_head *recv_list, const char *mac) { - const struct batadv_recvlist_node *entry; + const struct batadv_vis_recvlist_node *entry; spin_lock_bh(&bat_priv->vis.list_lock); list_for_each_entry(entry, recv_list, list) { @@ -827,7 +828,9 @@ static void batadv_send_vis_packets(struct work_struct *work) kref_put(&info->refcount, batadv_free_info); } spin_unlock_bh(&bat_priv->vis.hash_lock); - batadv_start_vis_timer(bat_priv); + + queue_delayed_work(batadv_event_workqueue, &bat_priv->vis.work, + msecs_to_jiffies(BATADV_VIS_INTERVAL)); } /* init the vis server. this may only be called when if_list is already @@ -852,6 +855,9 @@ int batadv_vis_init(struct batadv_priv *bat_priv) goto err; } + batadv_hash_set_lock_class(bat_priv->vis.hash, + &batadv_vis_hash_lock_class_key); + bat_priv->vis.my_info = kmalloc(BATADV_MAX_VIS_PACKET_SIZE, GFP_ATOMIC); if (!bat_priv->vis.my_info) goto err; @@ -894,7 +900,11 @@ int batadv_vis_init(struct batadv_priv *bat_priv) } spin_unlock_bh(&bat_priv->vis.hash_lock); - batadv_start_vis_timer(bat_priv); + + INIT_DELAYED_WORK(&bat_priv->vis.work, batadv_send_vis_packets); + queue_delayed_work(batadv_event_workqueue, &bat_priv->vis.work, + msecs_to_jiffies(BATADV_VIS_INTERVAL)); + return 0; free_info: @@ -931,11 +941,3 @@ void batadv_vis_quit(struct batadv_priv *bat_priv) bat_priv->vis.my_info = NULL; spin_unlock_bh(&bat_priv->vis.hash_lock); } - -/* schedule packets for (re)transmission */ -static void batadv_start_vis_timer(struct batadv_priv *bat_priv) -{ - INIT_DELAYED_WORK(&bat_priv->vis.work, batadv_send_vis_packets); - queue_delayed_work(batadv_event_workqueue, &bat_priv->vis.work, - msecs_to_jiffies(BATADV_VIS_INTERVAL)); -} diff --git a/net/batman-adv/vis.h b/net/batman-adv/vis.h index 873282fa86da..ad92b0e3c230 100644 --- a/net/batman-adv/vis.h +++ b/net/batman-adv/vis.h @@ -1,4 +1,4 @@ -/* Copyright (C) 2008-2012 B.A.T.M.A.N. contributors: +/* Copyright (C) 2008-2013 B.A.T.M.A.N. contributors: * * Simon Wunderlich, Marek Lindner * diff --git a/net/bluetooth/rfcomm/core.c b/net/bluetooth/rfcomm/core.c index 201fdf737209..b23e2713fea8 100644 --- a/net/bluetooth/rfcomm/core.c +++ b/net/bluetooth/rfcomm/core.c @@ -257,7 +257,7 @@ static void rfcomm_session_clear_timer(struct rfcomm_session *s) { BT_DBG("session %p state %ld", s, s->state); - if (timer_pending(&s->timer) && del_timer(&s->timer)) + if (del_timer(&s->timer)) rfcomm_session_put(s); } @@ -285,7 +285,7 @@ static void rfcomm_dlc_clear_timer(struct rfcomm_dlc *d) { BT_DBG("dlc %p state %ld", d, d->state); - if (timer_pending(&d->timer) && del_timer(&d->timer)) + if (del_timer(&d->timer)) rfcomm_dlc_put(d); } diff --git a/net/bridge/Kconfig b/net/bridge/Kconfig index 6dee7bf648a9..aa0d3b2f1bb7 100644 --- a/net/bridge/Kconfig +++ b/net/bridge/Kconfig @@ -46,3 +46,17 @@ config BRIDGE_IGMP_SNOOPING Say N to exclude this support and reduce the binary size. If unsure, say Y. + +config BRIDGE_VLAN_FILTERING + bool "VLAN filtering" + depends on BRIDGE + depends on VLAN_8021Q + default n + ---help--- + If you say Y here, then the Ethernet bridge will be able selectively + receive and forward traffic based on VLAN information in the packet + any VLAN information configured on the bridge port or bridge device. + + Say N to exclude this support and reduce the binary size. + + If unsure, say Y. diff --git a/net/bridge/Makefile b/net/bridge/Makefile index e859098f5ee9..e85498b2f166 100644 --- a/net/bridge/Makefile +++ b/net/bridge/Makefile @@ -14,4 +14,6 @@ bridge-$(CONFIG_BRIDGE_NETFILTER) += br_netfilter.o bridge-$(CONFIG_BRIDGE_IGMP_SNOOPING) += br_multicast.o br_mdb.o +bridge-$(CONFIG_BRIDGE_VLAN_FILTERING) += br_vlan.o + obj-$(CONFIG_BRIDGE_NF_EBTABLES) += netfilter/ diff --git a/net/bridge/br_device.c b/net/bridge/br_device.c index 7c78e2640190..d5f1d3fd4b28 100644 --- a/net/bridge/br_device.c +++ b/net/bridge/br_device.c @@ -30,6 +30,7 @@ netdev_tx_t br_dev_xmit(struct sk_buff *skb, struct net_device *dev) struct net_bridge_fdb_entry *dst; struct net_bridge_mdb_entry *mdst; struct br_cpu_netstats *brstats = this_cpu_ptr(br->stats); + u16 vid = 0; rcu_read_lock(); #ifdef CONFIG_BRIDGE_NETFILTER @@ -45,6 +46,9 @@ netdev_tx_t br_dev_xmit(struct sk_buff *skb, struct net_device *dev) brstats->tx_bytes += skb->len; u64_stats_update_end(&brstats->syncp); + if (!br_allowed_ingress(br, br_get_vlan_info(br), skb, &vid)) + goto out; + BR_INPUT_SKB_CB(skb)->brdev = dev; skb_reset_mac_header(skb); @@ -67,7 +71,7 @@ netdev_tx_t br_dev_xmit(struct sk_buff *skb, struct net_device *dev) br_multicast_deliver(mdst, skb); else br_flood_deliver(br, skb); - } else if ((dst = __br_fdb_get(br, dest)) != NULL) + } else if ((dst = __br_fdb_get(br, dest, vid)) != NULL) br_deliver(dst->dst, skb); else br_flood_deliver(br, skb); @@ -172,12 +176,10 @@ static int br_set_mac_address(struct net_device *dev, void *p) spin_lock_bh(&br->lock); if (!ether_addr_equal(dev->dev_addr, addr->sa_data)) { - dev->addr_assign_type &= ~NET_ADDR_RANDOM; memcpy(dev->dev_addr, addr->sa_data, ETH_ALEN); br_fdb_change_mac_address(br, addr->sa_data); br_stp_change_bridge_id(br, addr->sa_data); } - br->flags |= BR_SET_MAC_ADDR; spin_unlock_bh(&br->lock); return 0; @@ -185,10 +187,10 @@ static int br_set_mac_address(struct net_device *dev, void *p) static void br_getinfo(struct net_device *dev, struct ethtool_drvinfo *info) { - strcpy(info->driver, "bridge"); - strcpy(info->version, BR_VERSION); - strcpy(info->fw_version, "N/A"); - strcpy(info->bus_info, "N/A"); + strlcpy(info->driver, "bridge", sizeof(info->driver)); + strlcpy(info->version, BR_VERSION, sizeof(info->version)); + strlcpy(info->fw_version, "N/A", sizeof(info->fw_version)); + strlcpy(info->bus_info, "N/A", sizeof(info->bus_info)); } static netdev_features_t br_fix_features(struct net_device *dev, @@ -267,7 +269,7 @@ void br_netpoll_disable(struct net_bridge_port *p) p->np = NULL; - __netpoll_free_rcu(np); + __netpoll_free_async(np); } #endif @@ -315,6 +317,7 @@ static const struct net_device_ops br_netdev_ops = { .ndo_fdb_dump = br_fdb_dump, .ndo_bridge_getlink = br_getlink, .ndo_bridge_setlink = br_setlink, + .ndo_bridge_dellink = br_dellink, }; static void br_dev_free(struct net_device *dev) diff --git a/net/bridge/br_fdb.c b/net/bridge/br_fdb.c index d9576e6de2b8..8117900af4de 100644 --- a/net/bridge/br_fdb.c +++ b/net/bridge/br_fdb.c @@ -23,11 +23,12 @@ #include <linux/slab.h> #include <linux/atomic.h> #include <asm/unaligned.h> +#include <linux/if_vlan.h> #include "br_private.h" static struct kmem_cache *br_fdb_cache __read_mostly; static int fdb_insert(struct net_bridge *br, struct net_bridge_port *source, - const unsigned char *addr); + const unsigned char *addr, u16 vid); static void fdb_notify(struct net_bridge *br, const struct net_bridge_fdb_entry *, int); @@ -67,11 +68,11 @@ static inline int has_expired(const struct net_bridge *br, time_before_eq(fdb->updated + hold_time(br), jiffies); } -static inline int br_mac_hash(const unsigned char *mac) +static inline int br_mac_hash(const unsigned char *mac, __u16 vid) { - /* use 1 byte of OUI cnd 3 bytes of NIC */ + /* use 1 byte of OUI and 3 bytes of NIC */ u32 key = get_unaligned((u32 *)(mac + 2)); - return jhash_1word(key, fdb_salt) & (BR_HASH_SIZE - 1); + return jhash_2words(key, vid, fdb_salt) & (BR_HASH_SIZE - 1); } static void fdb_rcu_free(struct rcu_head *head) @@ -91,6 +92,7 @@ static void fdb_delete(struct net_bridge *br, struct net_bridge_fdb_entry *f) void br_fdb_changeaddr(struct net_bridge_port *p, const unsigned char *newaddr) { struct net_bridge *br = p->br; + bool no_vlan = (nbp_get_vlan_info(p) == NULL) ? true : false; int i; spin_lock_bh(&br->hash_lock); @@ -105,10 +107,12 @@ void br_fdb_changeaddr(struct net_bridge_port *p, const unsigned char *newaddr) if (f->dst == p && f->is_local) { /* maybe another port has same hw addr? */ struct net_bridge_port *op; + u16 vid = f->vlan_id; list_for_each_entry(op, &br->port_list, list) { if (op != p && ether_addr_equal(op->dev->dev_addr, - f->addr.addr)) { + f->addr.addr) && + nbp_vlan_find(op, vid)) { f->dst = op; goto insert; } @@ -116,27 +120,55 @@ void br_fdb_changeaddr(struct net_bridge_port *p, const unsigned char *newaddr) /* delete old one */ fdb_delete(br, f); - goto insert; +insert: + /* insert new address, may fail if invalid + * address or dup. + */ + fdb_insert(br, p, newaddr, vid); + + /* if this port has no vlan information + * configured, we can safely be done at + * this point. + */ + if (no_vlan) + goto done; } } } - insert: - /* insert new address, may fail if invalid address or dup. */ - fdb_insert(br, p, newaddr); +done: spin_unlock_bh(&br->hash_lock); } void br_fdb_change_mac_address(struct net_bridge *br, const u8 *newaddr) { struct net_bridge_fdb_entry *f; + struct net_port_vlans *pv; + u16 vid = 0; /* If old entry was unassociated with any port, then delete it. */ - f = __br_fdb_get(br, br->dev->dev_addr); + f = __br_fdb_get(br, br->dev->dev_addr, 0); if (f && f->is_local && !f->dst) fdb_delete(br, f); - fdb_insert(br, NULL, newaddr); + fdb_insert(br, NULL, newaddr, 0); + + /* Now remove and add entries for every VLAN configured on the + * bridge. This function runs under RTNL so the bitmap will not + * change from under us. + */ + pv = br_get_vlan_info(br); + if (!pv) + return; + + for (vid = find_next_bit(pv->vlan_bitmap, BR_VLAN_BITMAP_LEN, vid); + vid < BR_VLAN_BITMAP_LEN; + vid = find_next_bit(pv->vlan_bitmap, BR_VLAN_BITMAP_LEN, vid+1)) { + f = __br_fdb_get(br, br->dev->dev_addr, vid); + if (f && f->is_local && !f->dst) + fdb_delete(br, f); + fdb_insert(br, NULL, newaddr, vid); + } } void br_fdb_cleanup(unsigned long _data) @@ -231,13 +263,16 @@ void br_fdb_delete_by_port(struct net_bridge *br, /* No locking or refcounting, assumes caller has rcu_read_lock */ struct net_bridge_fdb_entry *__br_fdb_get(struct net_bridge *br, - const unsigned char *addr) + const unsigned char *addr, + __u16 vid) { struct hlist_node *h; struct net_bridge_fdb_entry *fdb; - hlist_for_each_entry_rcu(fdb, h, &br->hash[br_mac_hash(addr)], hlist) { - if (ether_addr_equal(fdb->addr.addr, addr)) { + hlist_for_each_entry_rcu(fdb, h, + &br->hash[br_mac_hash(addr, vid)], hlist) { + if (ether_addr_equal(fdb->addr.addr, addr) && + fdb->vlan_id == vid) { if (unlikely(has_expired(br, fdb))) break; return fdb; @@ -261,7 +296,7 @@ int br_fdb_test_addr(struct net_device *dev, unsigned char *addr) if (!port) ret = 0; else { - fdb = __br_fdb_get(port->br, addr); + fdb = __br_fdb_get(port->br, addr, 0); ret = fdb && fdb->dst && fdb->dst->dev != dev && fdb->dst->state == BR_STATE_FORWARDING; } @@ -325,26 +360,30 @@ int br_fdb_fillbuf(struct net_bridge *br, void *buf, } static struct net_bridge_fdb_entry *fdb_find(struct hlist_head *head, - const unsigned char *addr) + const unsigned char *addr, + __u16 vid) { struct hlist_node *h; struct net_bridge_fdb_entry *fdb; hlist_for_each_entry(fdb, h, head, hlist) { - if (ether_addr_equal(fdb->addr.addr, addr)) + if (ether_addr_equal(fdb->addr.addr, addr) && + fdb->vlan_id == vid) return fdb; } return NULL; } static struct net_bridge_fdb_entry *fdb_find_rcu(struct hlist_head *head, - const unsigned char *addr) + const unsigned char *addr, + __u16 vid) { struct hlist_node *h; struct net_bridge_fdb_entry *fdb; hlist_for_each_entry_rcu(fdb, h, head, hlist) { - if (ether_addr_equal(fdb->addr.addr, addr)) + if (ether_addr_equal(fdb->addr.addr, addr) && + fdb->vlan_id == vid) return fdb; } return NULL; @@ -352,7 +391,8 @@ static struct net_bridge_fdb_entry *fdb_find_rcu(struct hlist_head *head, static struct net_bridge_fdb_entry *fdb_create(struct hlist_head *head, struct net_bridge_port *source, - const unsigned char *addr) + const unsigned char *addr, + __u16 vid) { struct net_bridge_fdb_entry *fdb; @@ -360,6 +400,7 @@ static struct net_bridge_fdb_entry *fdb_create(struct hlist_head *head, if (fdb) { memcpy(fdb->addr.addr, addr, ETH_ALEN); fdb->dst = source; + fdb->vlan_id = vid; fdb->is_local = 0; fdb->is_static = 0; fdb->updated = fdb->used = jiffies; @@ -369,15 +410,15 @@ static struct net_bridge_fdb_entry *fdb_create(struct hlist_head *head, } static int fdb_insert(struct net_bridge *br, struct net_bridge_port *source, - const unsigned char *addr) + const unsigned char *addr, u16 vid) { - struct hlist_head *head = &br->hash[br_mac_hash(addr)]; + struct hlist_head *head = &br->hash[br_mac_hash(addr, vid)]; struct net_bridge_fdb_entry *fdb; if (!is_valid_ether_addr(addr)) return -EINVAL; - fdb = fdb_find(head, addr); + fdb = fdb_find(head, addr, vid); if (fdb) { /* it is okay to have multiple ports with same * address, just use the first one. @@ -390,7 +431,7 @@ static int fdb_insert(struct net_bridge *br, struct net_bridge_port *source, fdb_delete(br, fdb); } - fdb = fdb_create(head, source, addr); + fdb = fdb_create(head, source, addr, vid); if (!fdb) return -ENOMEM; @@ -401,20 +442,20 @@ static int fdb_insert(struct net_bridge *br, struct net_bridge_port *source, /* Add entry for local address of interface */ int br_fdb_insert(struct net_bridge *br, struct net_bridge_port *source, - const unsigned char *addr) + const unsigned char *addr, u16 vid) { int ret; spin_lock_bh(&br->hash_lock); - ret = fdb_insert(br, source, addr); + ret = fdb_insert(br, source, addr, vid); spin_unlock_bh(&br->hash_lock); return ret; } void br_fdb_update(struct net_bridge *br, struct net_bridge_port *source, - const unsigned char *addr) + const unsigned char *addr, u16 vid) { - struct hlist_head *head = &br->hash[br_mac_hash(addr)]; + struct hlist_head *head = &br->hash[br_mac_hash(addr, vid)]; struct net_bridge_fdb_entry *fdb; /* some users want to always flood. */ @@ -426,7 +467,7 @@ void br_fdb_update(struct net_bridge *br, struct net_bridge_port *source, source->state == BR_STATE_FORWARDING)) return; - fdb = fdb_find_rcu(head, addr); + fdb = fdb_find_rcu(head, addr, vid); if (likely(fdb)) { /* attempt to update an entry for a local interface */ if (unlikely(fdb->is_local)) { @@ -441,8 +482,8 @@ void br_fdb_update(struct net_bridge *br, struct net_bridge_port *source, } } else { spin_lock(&br->hash_lock); - if (likely(!fdb_find(head, addr))) { - fdb = fdb_create(head, source, addr); + if (likely(!fdb_find(head, addr, vid))) { + fdb = fdb_create(head, source, addr, vid); if (fdb) fdb_notify(br, fdb, RTM_NEWNEIGH); } @@ -495,6 +536,10 @@ static int fdb_fill_info(struct sk_buff *skb, const struct net_bridge *br, ci.ndm_refcnt = 0; if (nla_put(skb, NDA_CACHEINFO, sizeof(ci), &ci)) goto nla_put_failure; + + if (nla_put(skb, NDA_VLAN, sizeof(u16), &fdb->vlan_id)) + goto nla_put_failure; + return nlmsg_end(skb, nlh); nla_put_failure: @@ -506,6 +551,7 @@ static inline size_t fdb_nlmsg_size(void) { return NLMSG_ALIGN(sizeof(struct ndmsg)) + nla_total_size(ETH_ALEN) /* NDA_LLADDR */ + + nla_total_size(sizeof(u16)) /* NDA_VLAN */ + nla_total_size(sizeof(struct nda_cacheinfo)); } @@ -571,18 +617,18 @@ out: /* Update (create or replace) forwarding database entry */ static int fdb_add_entry(struct net_bridge_port *source, const __u8 *addr, - __u16 state, __u16 flags) + __u16 state, __u16 flags, __u16 vid) { struct net_bridge *br = source->br; - struct hlist_head *head = &br->hash[br_mac_hash(addr)]; + struct hlist_head *head = &br->hash[br_mac_hash(addr, vid)]; struct net_bridge_fdb_entry *fdb; - fdb = fdb_find(head, addr); + fdb = fdb_find(head, addr, vid); if (fdb == NULL) { if (!(flags & NLM_F_CREATE)) return -ENOENT; - fdb = fdb_create(head, source, addr); + fdb = fdb_create(head, source, addr, vid); if (!fdb) return -ENOMEM; fdb_notify(br, fdb, RTM_NEWNEIGH); @@ -607,6 +653,25 @@ static int fdb_add_entry(struct net_bridge_port *source, const __u8 *addr, return 0; } +static int __br_fdb_add(struct ndmsg *ndm, struct net_bridge_port *p, + const unsigned char *addr, u16 nlh_flags, u16 vid) +{ + int err = 0; + + if (ndm->ndm_flags & NTF_USE) { + rcu_read_lock(); + br_fdb_update(p->br, p, addr, vid); + rcu_read_unlock(); + } else { + spin_lock_bh(&p->br->hash_lock); + err = fdb_add_entry(p, addr, ndm->ndm_state, + nlh_flags, vid); + spin_unlock_bh(&p->br->hash_lock); + } + + return err; +} + /* Add new permanent fdb entry with RTM_NEWNEIGH */ int br_fdb_add(struct ndmsg *ndm, struct nlattr *tb[], struct net_device *dev, @@ -614,12 +679,29 @@ int br_fdb_add(struct ndmsg *ndm, struct nlattr *tb[], { struct net_bridge_port *p; int err = 0; + struct net_port_vlans *pv; + unsigned short vid = VLAN_N_VID; if (!(ndm->ndm_state & (NUD_PERMANENT|NUD_NOARP|NUD_REACHABLE))) { pr_info("bridge: RTM_NEWNEIGH with invalid state %#x\n", ndm->ndm_state); return -EINVAL; } + if (tb[NDA_VLAN]) { + if (nla_len(tb[NDA_VLAN]) != sizeof(unsigned short)) { + pr_info("bridge: RTM_NEWNEIGH with invalid vlan\n"); + return -EINVAL; + } + + vid = nla_get_u16(tb[NDA_VLAN]); + + if (vid >= VLAN_N_VID) { + pr_info("bridge: RTM_NEWNEIGH with invalid vlan id %d\n", + vid); + return -EINVAL; + } + } + p = br_port_get_rtnl(dev); if (p == NULL) { pr_info("bridge: RTM_NEWNEIGH %s not a bridge port\n", @@ -627,40 +709,90 @@ int br_fdb_add(struct ndmsg *ndm, struct nlattr *tb[], return -EINVAL; } - if (ndm->ndm_flags & NTF_USE) { - rcu_read_lock(); - br_fdb_update(p->br, p, addr); - rcu_read_unlock(); + pv = nbp_get_vlan_info(p); + if (vid != VLAN_N_VID) { + if (!pv || !test_bit(vid, pv->vlan_bitmap)) { + pr_info("bridge: RTM_NEWNEIGH with unconfigured " + "vlan %d on port %s\n", vid, dev->name); + return -EINVAL; + } + + /* VID was specified, so use it. */ + err = __br_fdb_add(ndm, p, addr, nlh_flags, vid); } else { - spin_lock_bh(&p->br->hash_lock); - err = fdb_add_entry(p, addr, ndm->ndm_state, nlh_flags); - spin_unlock_bh(&p->br->hash_lock); + if (!pv || bitmap_empty(pv->vlan_bitmap, BR_VLAN_BITMAP_LEN)) { + err = __br_fdb_add(ndm, p, addr, nlh_flags, 0); + goto out; + } + + /* We have vlans configured on this port and user didn't + * specify a VLAN. To be nice, add/update entry for every + * vlan on this port. + */ + vid = find_first_bit(pv->vlan_bitmap, BR_VLAN_BITMAP_LEN); + while (vid < BR_VLAN_BITMAP_LEN) { + err = __br_fdb_add(ndm, p, addr, nlh_flags, vid); + if (err) + goto out; + vid = find_next_bit(pv->vlan_bitmap, + BR_VLAN_BITMAP_LEN, vid+1); + } } +out: return err; } -static int fdb_delete_by_addr(struct net_bridge_port *p, const u8 *addr) +int fdb_delete_by_addr(struct net_bridge *br, const u8 *addr, + u16 vlan) { - struct net_bridge *br = p->br; - struct hlist_head *head = &br->hash[br_mac_hash(addr)]; + struct hlist_head *head = &br->hash[br_mac_hash(addr, vlan)]; struct net_bridge_fdb_entry *fdb; - fdb = fdb_find(head, addr); + fdb = fdb_find(head, addr, vlan); if (!fdb) return -ENOENT; - fdb_delete(p->br, fdb); + fdb_delete(br, fdb); return 0; } +static int __br_fdb_delete(struct net_bridge_port *p, + const unsigned char *addr, u16 vid) +{ + int err; + + spin_lock_bh(&p->br->hash_lock); + err = fdb_delete_by_addr(p->br, addr, vid); + spin_unlock_bh(&p->br->hash_lock); + + return err; +} + /* Remove neighbor entry with RTM_DELNEIGH */ -int br_fdb_delete(struct ndmsg *ndm, struct net_device *dev, +int br_fdb_delete(struct ndmsg *ndm, struct nlattr *tb[], + struct net_device *dev, const unsigned char *addr) { struct net_bridge_port *p; int err; + struct net_port_vlans *pv; + unsigned short vid = VLAN_N_VID; + + if (tb[NDA_VLAN]) { + if (nla_len(tb[NDA_VLAN]) != sizeof(unsigned short)) { + pr_info("bridge: RTM_NEWNEIGH with invalid vlan\n"); + return -EINVAL; + } + + vid = nla_get_u16(tb[NDA_VLAN]); + if (vid >= VLAN_N_VID) { + pr_info("bridge: RTM_NEWNEIGH with invalid vlan id %d\n", + vid); + return -EINVAL; + } + } p = br_port_get_rtnl(dev); if (p == NULL) { pr_info("bridge: RTM_DELNEIGH %s not a bridge port\n", @@ -668,9 +800,33 @@ int br_fdb_delete(struct ndmsg *ndm, struct net_device *dev, return -EINVAL; } - spin_lock_bh(&p->br->hash_lock); - err = fdb_delete_by_addr(p, addr); - spin_unlock_bh(&p->br->hash_lock); + pv = nbp_get_vlan_info(p); + if (vid != VLAN_N_VID) { + if (!pv || !test_bit(vid, pv->vlan_bitmap)) { + pr_info("bridge: RTM_DELNEIGH with unconfigured " + "vlan %d on port %s\n", vid, dev->name); + return -EINVAL; + } + + err = __br_fdb_delete(p, addr, vid); + } else { + if (!pv || bitmap_empty(pv->vlan_bitmap, BR_VLAN_BITMAP_LEN)) { + err = __br_fdb_delete(p, addr, 0); + goto out; + } + /* We have vlans configured on this port and user didn't + * specify a VLAN. To be nice, add/update entry for every + * vlan on this port. + */ + err = -ENOENT; + vid = find_first_bit(pv->vlan_bitmap, BR_VLAN_BITMAP_LEN); + while (vid < BR_VLAN_BITMAP_LEN) { + err &= __br_fdb_delete(p, addr, vid); + vid = find_next_bit(pv->vlan_bitmap, + BR_VLAN_BITMAP_LEN, vid+1); + } + } +out: return err; } diff --git a/net/bridge/br_forward.c b/net/bridge/br_forward.c index 02015a505d2a..092b20e4ee4c 100644 --- a/net/bridge/br_forward.c +++ b/net/bridge/br_forward.c @@ -31,6 +31,7 @@ static inline int should_deliver(const struct net_bridge_port *p, const struct sk_buff *skb) { return (((p->flags & BR_HAIRPIN_MODE) || skb->dev != p->dev) && + br_allowed_egress(p->br, nbp_get_vlan_info(p), skb) && p->state == BR_STATE_FORWARDING); } @@ -63,6 +64,10 @@ int br_forward_finish(struct sk_buff *skb) static void __br_deliver(const struct net_bridge_port *to, struct sk_buff *skb) { + skb = br_handle_vlan(to->br, nbp_get_vlan_info(to), skb); + if (!skb) + return; + skb->dev = to->dev; if (unlikely(netpoll_tx_running(to->br->dev))) { @@ -88,6 +93,10 @@ static void __br_forward(const struct net_bridge_port *to, struct sk_buff *skb) return; } + skb = br_handle_vlan(to->br, nbp_get_vlan_info(to), skb); + if (!skb) + return; + indev = skb->dev; skb->dev = to->dev; skb_forward_csum(skb); diff --git a/net/bridge/br_if.c b/net/bridge/br_if.c index 1c8fdc3558cd..ef1b91431c6b 100644 --- a/net/bridge/br_if.c +++ b/net/bridge/br_if.c @@ -23,6 +23,7 @@ #include <linux/if_ether.h> #include <linux/slab.h> #include <net/sock.h> +#include <linux/if_vlan.h> #include "br_private.h" @@ -66,14 +67,14 @@ void br_port_carrier_check(struct net_bridge_port *p) struct net_device *dev = p->dev; struct net_bridge *br = p->br; - if (netif_running(dev) && netif_carrier_ok(dev)) + if (netif_running(dev) && netif_oper_up(dev)) p->path_cost = port_cost(dev); if (!netif_running(br->dev)) return; spin_lock_bh(&br->lock); - if (netif_running(dev) && netif_carrier_ok(dev)) { + if (netif_running(dev) && netif_oper_up(dev)) { if (p->state == BR_STATE_DISABLED) br_stp_enable_port(p); } else { @@ -139,6 +140,7 @@ static void del_nbp(struct net_bridge_port *p) br_ifinfo_notify(RTM_DELLINK, p); + nbp_vlan_flush(p); br_fdb_delete_by_port(br, p, 1); list_del_rcu(&p->list); @@ -148,7 +150,7 @@ static void del_nbp(struct net_bridge_port *p) netdev_rx_handler_unregister(dev); synchronize_net(); - netdev_set_master(dev, NULL); + netdev_upper_dev_unlink(dev, br->dev); br_multicast_del_port(p); @@ -364,13 +366,13 @@ int br_add_if(struct net_bridge *br, struct net_device *dev) if (br_netpoll_info(br) && ((err = br_netpoll_enable(p, GFP_KERNEL)))) goto err3; - err = netdev_set_master(dev, br->dev); + err = netdev_master_upper_dev_link(dev, br->dev); if (err) - goto err3; + goto err4; err = netdev_rx_handler_register(dev, br_handle_frame, p); if (err) - goto err4; + goto err5; dev->priv_flags |= IFF_BRIDGE_PORT; @@ -383,7 +385,7 @@ int br_add_if(struct net_bridge *br, struct net_device *dev) spin_lock_bh(&br->lock); changed_addr = br_stp_recalculate_bridge_id(br); - if ((dev->flags & IFF_UP) && netif_carrier_ok(dev) && + if (netif_running(dev) && netif_oper_up(dev) && (br->dev->flags & IFF_UP)) br_stp_enable_port(p); spin_unlock_bh(&br->lock); @@ -395,15 +397,17 @@ int br_add_if(struct net_bridge *br, struct net_device *dev) dev_set_mtu(br->dev, br_min_mtu(br)); - if (br_fdb_insert(br, p, dev->dev_addr)) + if (br_fdb_insert(br, p, dev->dev_addr, 0)) netdev_err(dev, "failed insert local address bridge forwarding table\n"); kobject_uevent(&p->kobj, KOBJ_ADD); return 0; +err5: + netdev_upper_dev_unlink(dev, br->dev); err4: - netdev_set_master(dev, NULL); + br_netpoll_disable(p); err3: sysfs_remove_link(br->ifobj, p->dev->name); err2: diff --git a/net/bridge/br_input.c b/net/bridge/br_input.c index 4b34207419b1..480330151898 100644 --- a/net/bridge/br_input.c +++ b/net/bridge/br_input.c @@ -17,6 +17,7 @@ #include <linux/etherdevice.h> #include <linux/netfilter_bridge.h> #include <linux/export.h> +#include <linux/rculist.h> #include "br_private.h" /* Hook for brouter */ @@ -34,6 +35,20 @@ static int br_pass_frame_up(struct sk_buff *skb) brstats->rx_bytes += skb->len; u64_stats_update_end(&brstats->syncp); + /* Bridge is just like any other port. Make sure the + * packet is allowed except in promisc modue when someone + * may be running packet capture. + */ + if (!(brdev->flags & IFF_PROMISC) && + !br_allowed_egress(br, br_get_vlan_info(br), skb)) { + kfree_skb(skb); + return NET_RX_DROP; + } + + skb = br_handle_vlan(br, br_get_vlan_info(br), skb); + if (!skb) + return NET_RX_DROP; + indev = skb->dev; skb->dev = brdev; @@ -50,13 +65,17 @@ int br_handle_frame_finish(struct sk_buff *skb) struct net_bridge_fdb_entry *dst; struct net_bridge_mdb_entry *mdst; struct sk_buff *skb2; + u16 vid = 0; if (!p || p->state == BR_STATE_DISABLED) goto drop; + if (!br_allowed_ingress(p->br, nbp_get_vlan_info(p), skb, &vid)) + goto drop; + /* insert into forwarding database after filtering to avoid spoofing */ br = p->br; - br_fdb_update(br, p, eth_hdr(skb)->h_source); + br_fdb_update(br, p, eth_hdr(skb)->h_source, vid); if (!is_broadcast_ether_addr(dest) && is_multicast_ether_addr(dest) && br_multicast_rcv(br, p, skb)) @@ -91,7 +110,8 @@ int br_handle_frame_finish(struct sk_buff *skb) skb2 = skb; br->dev->stats.multicast++; - } else if ((dst = __br_fdb_get(br, dest)) && dst->is_local) { + } else if ((dst = __br_fdb_get(br, dest, vid)) && + dst->is_local) { skb2 = skb; /* Do not forward the packet since it's local. */ skb = NULL; @@ -119,8 +139,10 @@ drop: static int br_handle_local_finish(struct sk_buff *skb) { struct net_bridge_port *p = br_port_get_rcu(skb->dev); + u16 vid = 0; - br_fdb_update(p->br, p, eth_hdr(skb)->h_source); + br_vlan_get_tag(skb, &vid); + br_fdb_update(p->br, p, eth_hdr(skb)->h_source, vid); return 0; /* process further */ } diff --git a/net/bridge/br_mdb.c b/net/bridge/br_mdb.c index acc9f4cc18f7..38991e03646d 100644 --- a/net/bridge/br_mdb.c +++ b/net/bridge/br_mdb.c @@ -272,9 +272,6 @@ static int br_mdb_parse(struct sk_buff *skb, struct nlmsghdr *nlh, struct net_device *dev; int err; - if (!capable(CAP_NET_ADMIN)) - return -EPERM; - err = nlmsg_parse(nlh, sizeof(*bpm), tb, MDBA_SET_ENTRY, NULL); if (err < 0) return err; diff --git a/net/bridge/br_multicast.c b/net/bridge/br_multicast.c index 5391ca43336a..7d886b0a8b7b 100644 --- a/net/bridge/br_multicast.c +++ b/net/bridge/br_multicast.c @@ -39,6 +39,8 @@ static inline int br_ip_equal(const struct br_ip *a, const struct br_ip *b) { if (a->proto != b->proto) return 0; + if (a->vid != b->vid) + return 0; switch (a->proto) { case htons(ETH_P_IP): return a->u.ip4 == b->u.ip4; @@ -50,16 +52,19 @@ static inline int br_ip_equal(const struct br_ip *a, const struct br_ip *b) return 0; } -static inline int __br_ip4_hash(struct net_bridge_mdb_htable *mdb, __be32 ip) +static inline int __br_ip4_hash(struct net_bridge_mdb_htable *mdb, __be32 ip, + __u16 vid) { - return jhash_1word(mdb->secret, (__force u32)ip) & (mdb->max - 1); + return jhash_2words((__force u32)ip, vid, mdb->secret) & (mdb->max - 1); } #if IS_ENABLED(CONFIG_IPV6) static inline int __br_ip6_hash(struct net_bridge_mdb_htable *mdb, - const struct in6_addr *ip) + const struct in6_addr *ip, + __u16 vid) { - return jhash2((__force u32 *)ip->s6_addr32, 4, mdb->secret) & (mdb->max - 1); + return jhash_2words(ipv6_addr_hash(ip), vid, + mdb->secret) & (mdb->max - 1); } #endif @@ -68,10 +73,10 @@ static inline int br_ip_hash(struct net_bridge_mdb_htable *mdb, { switch (ip->proto) { case htons(ETH_P_IP): - return __br_ip4_hash(mdb, ip->u.ip4); + return __br_ip4_hash(mdb, ip->u.ip4, ip->vid); #if IS_ENABLED(CONFIG_IPV6) case htons(ETH_P_IPV6): - return __br_ip6_hash(mdb, &ip->u.ip6); + return __br_ip6_hash(mdb, &ip->u.ip6, ip->vid); #endif } return 0; @@ -101,24 +106,27 @@ struct net_bridge_mdb_entry *br_mdb_ip_get(struct net_bridge_mdb_htable *mdb, } static struct net_bridge_mdb_entry *br_mdb_ip4_get( - struct net_bridge_mdb_htable *mdb, __be32 dst) + struct net_bridge_mdb_htable *mdb, __be32 dst, __u16 vid) { struct br_ip br_dst; br_dst.u.ip4 = dst; br_dst.proto = htons(ETH_P_IP); + br_dst.vid = vid; return br_mdb_ip_get(mdb, &br_dst); } #if IS_ENABLED(CONFIG_IPV6) static struct net_bridge_mdb_entry *br_mdb_ip6_get( - struct net_bridge_mdb_htable *mdb, const struct in6_addr *dst) + struct net_bridge_mdb_htable *mdb, const struct in6_addr *dst, + __u16 vid) { struct br_ip br_dst; br_dst.u.ip6 = *dst; br_dst.proto = htons(ETH_P_IPV6); + br_dst.vid = vid; return br_mdb_ip_get(mdb, &br_dst); } @@ -694,7 +702,8 @@ err: static int br_ip4_multicast_add_group(struct net_bridge *br, struct net_bridge_port *port, - __be32 group) + __be32 group, + __u16 vid) { struct br_ip br_group; @@ -703,6 +712,7 @@ static int br_ip4_multicast_add_group(struct net_bridge *br, br_group.u.ip4 = group; br_group.proto = htons(ETH_P_IP); + br_group.vid = vid; return br_multicast_add_group(br, port, &br_group); } @@ -710,7 +720,8 @@ static int br_ip4_multicast_add_group(struct net_bridge *br, #if IS_ENABLED(CONFIG_IPV6) static int br_ip6_multicast_add_group(struct net_bridge *br, struct net_bridge_port *port, - const struct in6_addr *group) + const struct in6_addr *group, + __u16 vid) { struct br_ip br_group; @@ -719,6 +730,7 @@ static int br_ip6_multicast_add_group(struct net_bridge *br, br_group.u.ip6 = *group; br_group.proto = htons(ETH_P_IPV6); + br_group.vid = vid; return br_multicast_add_group(br, port, &br_group); } @@ -895,10 +907,12 @@ static int br_ip4_multicast_igmp3_report(struct net_bridge *br, int type; int err = 0; __be32 group; + u16 vid = 0; if (!pskb_may_pull(skb, sizeof(*ih))) return -EINVAL; + br_vlan_get_tag(skb, &vid); ih = igmpv3_report_hdr(skb); num = ntohs(ih->ngrec); len = sizeof(*ih); @@ -930,7 +944,7 @@ static int br_ip4_multicast_igmp3_report(struct net_bridge *br, continue; } - err = br_ip4_multicast_add_group(br, port, group); + err = br_ip4_multicast_add_group(br, port, group, vid); if (err) break; } @@ -949,10 +963,12 @@ static int br_ip6_multicast_mld2_report(struct net_bridge *br, int len; int num; int err = 0; + u16 vid = 0; if (!pskb_may_pull(skb, sizeof(*icmp6h))) return -EINVAL; + br_vlan_get_tag(skb, &vid); icmp6h = icmp6_hdr(skb); num = ntohs(icmp6h->icmp6_dataun.un_data16[1]); len = sizeof(*icmp6h); @@ -990,7 +1006,8 @@ static int br_ip6_multicast_mld2_report(struct net_bridge *br, continue; } - err = br_ip6_multicast_add_group(br, port, &grec->grec_mca); + err = br_ip6_multicast_add_group(br, port, &grec->grec_mca, + vid); if (!err) break; } @@ -1074,6 +1091,7 @@ static int br_ip4_multicast_query(struct net_bridge *br, unsigned long now = jiffies; __be32 group; int err = 0; + u16 vid = 0; spin_lock(&br->multicast_lock); if (!netif_running(br->dev) || @@ -1108,7 +1126,8 @@ static int br_ip4_multicast_query(struct net_bridge *br, if (!group) goto out; - mp = br_mdb_ip4_get(mlock_dereference(br->mdb, br), group); + br_vlan_get_tag(skb, &vid); + mp = br_mdb_ip4_get(mlock_dereference(br->mdb, br), group, vid); if (!mp) goto out; @@ -1149,6 +1168,7 @@ static int br_ip6_multicast_query(struct net_bridge *br, unsigned long now = jiffies; const struct in6_addr *group = NULL; int err = 0; + u16 vid = 0; spin_lock(&br->multicast_lock); if (!netif_running(br->dev) || @@ -1180,7 +1200,8 @@ static int br_ip6_multicast_query(struct net_bridge *br, if (!group) goto out; - mp = br_mdb_ip6_get(mlock_dereference(br->mdb, br), group); + br_vlan_get_tag(skb, &vid); + mp = br_mdb_ip6_get(mlock_dereference(br->mdb, br), group, vid); if (!mp) goto out; @@ -1286,7 +1307,8 @@ out: static void br_ip4_multicast_leave_group(struct net_bridge *br, struct net_bridge_port *port, - __be32 group) + __be32 group, + __u16 vid) { struct br_ip br_group; @@ -1295,6 +1317,7 @@ static void br_ip4_multicast_leave_group(struct net_bridge *br, br_group.u.ip4 = group; br_group.proto = htons(ETH_P_IP); + br_group.vid = vid; br_multicast_leave_group(br, port, &br_group); } @@ -1302,7 +1325,8 @@ static void br_ip4_multicast_leave_group(struct net_bridge *br, #if IS_ENABLED(CONFIG_IPV6) static void br_ip6_multicast_leave_group(struct net_bridge *br, struct net_bridge_port *port, - const struct in6_addr *group) + const struct in6_addr *group, + __u16 vid) { struct br_ip br_group; @@ -1311,6 +1335,7 @@ static void br_ip6_multicast_leave_group(struct net_bridge *br, br_group.u.ip6 = *group; br_group.proto = htons(ETH_P_IPV6); + br_group.vid = vid; br_multicast_leave_group(br, port, &br_group); } @@ -1326,6 +1351,7 @@ static int br_multicast_ipv4_rcv(struct net_bridge *br, unsigned int len; unsigned int offset; int err; + u16 vid = 0; /* We treat OOM as packet loss for now. */ if (!pskb_may_pull(skb, sizeof(*iph))) @@ -1386,6 +1412,7 @@ static int br_multicast_ipv4_rcv(struct net_bridge *br, err = 0; + br_vlan_get_tag(skb2, &vid); BR_INPUT_SKB_CB(skb)->igmp = 1; ih = igmp_hdr(skb2); @@ -1393,7 +1420,7 @@ static int br_multicast_ipv4_rcv(struct net_bridge *br, case IGMP_HOST_MEMBERSHIP_REPORT: case IGMPV2_HOST_MEMBERSHIP_REPORT: BR_INPUT_SKB_CB(skb)->mrouters_only = 1; - err = br_ip4_multicast_add_group(br, port, ih->group); + err = br_ip4_multicast_add_group(br, port, ih->group, vid); break; case IGMPV3_HOST_MEMBERSHIP_REPORT: err = br_ip4_multicast_igmp3_report(br, port, skb2); @@ -1402,7 +1429,7 @@ static int br_multicast_ipv4_rcv(struct net_bridge *br, err = br_ip4_multicast_query(br, port, skb2); break; case IGMP_HOST_LEAVE_MESSAGE: - br_ip4_multicast_leave_group(br, port, ih->group); + br_ip4_multicast_leave_group(br, port, ih->group, vid); break; } @@ -1427,6 +1454,7 @@ static int br_multicast_ipv6_rcv(struct net_bridge *br, unsigned int len; int offset; int err; + u16 vid = 0; if (!pskb_may_pull(skb, sizeof(*ip6h))) return -EINVAL; @@ -1510,6 +1538,7 @@ static int br_multicast_ipv6_rcv(struct net_bridge *br, err = 0; + br_vlan_get_tag(skb, &vid); BR_INPUT_SKB_CB(skb)->igmp = 1; switch (icmp6_type) { @@ -1522,7 +1551,7 @@ static int br_multicast_ipv6_rcv(struct net_bridge *br, } mld = (struct mld_msg *)skb_transport_header(skb2); BR_INPUT_SKB_CB(skb)->mrouters_only = 1; - err = br_ip6_multicast_add_group(br, port, &mld->mld_mca); + err = br_ip6_multicast_add_group(br, port, &mld->mld_mca, vid); break; } case ICMPV6_MLD2_REPORT: @@ -1539,7 +1568,7 @@ static int br_multicast_ipv6_rcv(struct net_bridge *br, goto out; } mld = (struct mld_msg *)skb_transport_header(skb2); - br_ip6_multicast_leave_group(br, port, &mld->mld_mca); + br_ip6_multicast_leave_group(br, port, &mld->mld_mca, vid); } } @@ -1608,7 +1637,6 @@ void br_multicast_init(struct net_bridge *br) br_multicast_querier_expired, (unsigned long)br); setup_timer(&br->multicast_query_timer, br_multicast_query_expired, (unsigned long)br); - br_mdb_init(); } void br_multicast_open(struct net_bridge *br) @@ -1633,7 +1661,6 @@ void br_multicast_stop(struct net_bridge *br) del_timer_sync(&br->multicast_querier_timer); del_timer_sync(&br->multicast_query_timer); - br_mdb_uninit(); spin_lock_bh(&br->multicast_lock); mdb = mlock_dereference(br->mdb, br); if (!mdb) diff --git a/net/bridge/br_netlink.c b/net/bridge/br_netlink.c index 97ba0189c6f7..27aa3ee517ce 100644 --- a/net/bridge/br_netlink.c +++ b/net/bridge/br_netlink.c @@ -16,6 +16,7 @@ #include <net/rtnetlink.h> #include <net/net_namespace.h> #include <net/sock.h> +#include <uapi/linux/if_bridge.h> #include "br_private.h" #include "br_private_stp.h" @@ -64,15 +65,21 @@ static int br_port_fill_attrs(struct sk_buff *skb, * Create one netlink message for one interface * Contains port and master info as well as carrier and bridge state. */ -static int br_fill_ifinfo(struct sk_buff *skb, const struct net_bridge_port *port, - u32 pid, u32 seq, int event, unsigned int flags) +static int br_fill_ifinfo(struct sk_buff *skb, + const struct net_bridge_port *port, + u32 pid, u32 seq, int event, unsigned int flags, + u32 filter_mask, const struct net_device *dev) { - const struct net_bridge *br = port->br; - const struct net_device *dev = port->dev; + const struct net_bridge *br; struct ifinfomsg *hdr; struct nlmsghdr *nlh; u8 operstate = netif_running(dev) ? dev->operstate : IF_OPER_DOWN; + if (port) + br = port->br; + else + br = netdev_priv(dev); + br_debug(br, "br_fill_info event %d port %s master %s\n", event, dev->name, br->dev->name); @@ -98,7 +105,7 @@ static int br_fill_ifinfo(struct sk_buff *skb, const struct net_bridge_port *por nla_put_u32(skb, IFLA_LINK, dev->iflink))) goto nla_put_failure; - if (event == RTM_NEWLINK) { + if (event == RTM_NEWLINK && port) { struct nlattr *nest = nla_nest_start(skb, IFLA_PROTINFO | NLA_F_NESTED); @@ -107,6 +114,48 @@ static int br_fill_ifinfo(struct sk_buff *skb, const struct net_bridge_port *por nla_nest_end(skb, nest); } + /* Check if the VID information is requested */ + if (filter_mask & RTEXT_FILTER_BRVLAN) { + struct nlattr *af; + const struct net_port_vlans *pv; + struct bridge_vlan_info vinfo; + u16 vid; + u16 pvid; + + if (port) + pv = nbp_get_vlan_info(port); + else + pv = br_get_vlan_info(br); + + if (!pv || bitmap_empty(pv->vlan_bitmap, BR_VLAN_BITMAP_LEN)) + goto done; + + af = nla_nest_start(skb, IFLA_AF_SPEC); + if (!af) + goto nla_put_failure; + + pvid = br_get_pvid(pv); + for (vid = find_first_bit(pv->vlan_bitmap, BR_VLAN_BITMAP_LEN); + vid < BR_VLAN_BITMAP_LEN; + vid = find_next_bit(pv->vlan_bitmap, + BR_VLAN_BITMAP_LEN, vid+1)) { + vinfo.vid = vid; + vinfo.flags = 0; + if (vid == pvid) + vinfo.flags |= BRIDGE_VLAN_INFO_PVID; + + if (test_bit(vid, pv->untagged_bitmap)) + vinfo.flags |= BRIDGE_VLAN_INFO_UNTAGGED; + + if (nla_put(skb, IFLA_BRIDGE_VLAN_INFO, + sizeof(vinfo), &vinfo)) + goto nla_put_failure; + } + + nla_nest_end(skb, af); + } + +done: return nlmsg_end(skb, nlh); nla_put_failure: @@ -119,10 +168,14 @@ nla_put_failure: */ void br_ifinfo_notify(int event, struct net_bridge_port *port) { - struct net *net = dev_net(port->dev); + struct net *net; struct sk_buff *skb; int err = -ENOBUFS; + if (!port) + return; + + net = dev_net(port->dev); br_debug(port->br, "port %u(%s) event %d\n", (unsigned int)port->port_no, port->dev->name, event); @@ -130,7 +183,7 @@ void br_ifinfo_notify(int event, struct net_bridge_port *port) if (skb == NULL) goto errout; - err = br_fill_ifinfo(skb, port, 0, 0, event, 0); + err = br_fill_ifinfo(skb, port, 0, 0, event, 0, 0, port->dev); if (err < 0) { /* -EMSGSIZE implies BUG in br_nlmsg_size() */ WARN_ON(err == -EMSGSIZE); @@ -144,24 +197,85 @@ errout: rtnl_set_sk_err(net, RTNLGRP_LINK, err); } + /* * Dump information about all ports, in response to GETLINK */ int br_getlink(struct sk_buff *skb, u32 pid, u32 seq, - struct net_device *dev) + struct net_device *dev, u32 filter_mask) { int err = 0; struct net_bridge_port *port = br_port_get_rcu(dev); - /* not a bridge port */ - if (!port) + /* not a bridge port and */ + if (!port && !(filter_mask & RTEXT_FILTER_BRVLAN)) goto out; - err = br_fill_ifinfo(skb, port, pid, seq, RTM_NEWLINK, NLM_F_MULTI); + err = br_fill_ifinfo(skb, port, pid, seq, RTM_NEWLINK, NLM_F_MULTI, + filter_mask, dev); out: return err; } +static const struct nla_policy ifla_br_policy[IFLA_MAX+1] = { + [IFLA_BRIDGE_FLAGS] = { .type = NLA_U16 }, + [IFLA_BRIDGE_MODE] = { .type = NLA_U16 }, + [IFLA_BRIDGE_VLAN_INFO] = { .type = NLA_BINARY, + .len = sizeof(struct bridge_vlan_info), }, +}; + +static int br_afspec(struct net_bridge *br, + struct net_bridge_port *p, + struct nlattr *af_spec, + int cmd) +{ + struct nlattr *tb[IFLA_BRIDGE_MAX+1]; + int err = 0; + + err = nla_parse_nested(tb, IFLA_BRIDGE_MAX, af_spec, ifla_br_policy); + if (err) + return err; + + if (tb[IFLA_BRIDGE_VLAN_INFO]) { + struct bridge_vlan_info *vinfo; + + vinfo = nla_data(tb[IFLA_BRIDGE_VLAN_INFO]); + + if (vinfo->vid >= VLAN_N_VID) + return -EINVAL; + + switch (cmd) { + case RTM_SETLINK: + if (p) { + err = nbp_vlan_add(p, vinfo->vid, vinfo->flags); + if (err) + break; + + if (vinfo->flags & BRIDGE_VLAN_INFO_MASTER) + err = br_vlan_add(p->br, vinfo->vid, + vinfo->flags); + } else + err = br_vlan_add(br, vinfo->vid, vinfo->flags); + + if (err) + break; + + break; + + case RTM_DELLINK: + if (p) { + nbp_vlan_delete(p, vinfo->vid); + if (vinfo->flags & BRIDGE_VLAN_INFO_MASTER) + br_vlan_delete(p->br, vinfo->vid); + } else + br_vlan_delete(br, vinfo->vid); + break; + } + } + + return err; +} + static const struct nla_policy ifla_brport_policy[IFLA_BRPORT_MAX + 1] = { [IFLA_BRPORT_STATE] = { .type = NLA_U8 }, [IFLA_BRPORT_COST] = { .type = NLA_U32 }, @@ -181,8 +295,11 @@ static int br_set_port_state(struct net_bridge_port *p, u8 state) if (p->br->stp_enabled == BR_KERNEL_STP) return -EBUSY; + /* if device is not up, change is not allowed + * if link is not present, only allowable state is disabled + */ if (!netif_running(p->dev) || - (!netif_carrier_ok(p->dev) && state != BR_STATE_DISABLED)) + (!netif_oper_up(p->dev) && state != BR_STATE_DISABLED)) return -ENETDOWN; p->state = state; @@ -238,6 +355,7 @@ int br_setlink(struct net_device *dev, struct nlmsghdr *nlh) { struct ifinfomsg *ifm; struct nlattr *protinfo; + struct nlattr *afspec; struct net_bridge_port *p; struct nlattr *tb[IFLA_BRPORT_MAX + 1]; int err; @@ -245,38 +363,76 @@ int br_setlink(struct net_device *dev, struct nlmsghdr *nlh) ifm = nlmsg_data(nlh); protinfo = nlmsg_find_attr(nlh, sizeof(*ifm), IFLA_PROTINFO); - if (!protinfo) + afspec = nlmsg_find_attr(nlh, sizeof(*ifm), IFLA_AF_SPEC); + if (!protinfo && !afspec) return 0; p = br_port_get_rtnl(dev); - if (!p) + /* We want to accept dev as bridge itself if the AF_SPEC + * is set to see if someone is setting vlan info on the brigde + */ + if (!p && ((dev->priv_flags & IFF_EBRIDGE) && !afspec)) return -EINVAL; - if (protinfo->nla_type & NLA_F_NESTED) { - err = nla_parse_nested(tb, IFLA_BRPORT_MAX, - protinfo, ifla_brport_policy); + if (p && protinfo) { + if (protinfo->nla_type & NLA_F_NESTED) { + err = nla_parse_nested(tb, IFLA_BRPORT_MAX, + protinfo, ifla_brport_policy); + if (err) + return err; + + spin_lock_bh(&p->br->lock); + err = br_setport(p, tb); + spin_unlock_bh(&p->br->lock); + } else { + /* Binary compatability with old RSTP */ + if (nla_len(protinfo) < sizeof(u8)) + return -EINVAL; + + spin_lock_bh(&p->br->lock); + err = br_set_port_state(p, nla_get_u8(protinfo)); + spin_unlock_bh(&p->br->lock); + } if (err) - return err; - - spin_lock_bh(&p->br->lock); - err = br_setport(p, tb); - spin_unlock_bh(&p->br->lock); - } else { - /* Binary compatability with old RSTP */ - if (nla_len(protinfo) < sizeof(u8)) - return -EINVAL; + goto out; + } - spin_lock_bh(&p->br->lock); - err = br_set_port_state(p, nla_get_u8(protinfo)); - spin_unlock_bh(&p->br->lock); + if (afspec) { + err = br_afspec((struct net_bridge *)netdev_priv(dev), p, + afspec, RTM_SETLINK); } if (err == 0) br_ifinfo_notify(RTM_NEWLINK, p); +out: return err; } +/* Delete port information */ +int br_dellink(struct net_device *dev, struct nlmsghdr *nlh) +{ + struct ifinfomsg *ifm; + struct nlattr *afspec; + struct net_bridge_port *p; + int err; + + ifm = nlmsg_data(nlh); + + afspec = nlmsg_find_attr(nlh, sizeof(*ifm), IFLA_AF_SPEC); + if (!afspec) + return 0; + + p = br_port_get_rtnl(dev); + /* We want to accept dev as bridge itself as well */ + if (!p && !(dev->priv_flags & IFF_EBRIDGE)) + return -EINVAL; + + err = br_afspec((struct net_bridge *)netdev_priv(dev), p, + afspec, RTM_DELLINK); + + return err; +} static int br_validate(struct nlattr *tb[], struct nlattr *data[]) { if (tb[IFLA_ADDRESS]) { @@ -289,6 +445,29 @@ static int br_validate(struct nlattr *tb[], struct nlattr *data[]) return 0; } +static size_t br_get_link_af_size(const struct net_device *dev) +{ + struct net_port_vlans *pv; + + if (br_port_exists(dev)) + pv = nbp_get_vlan_info(br_port_get_rcu(dev)); + else if (dev->priv_flags & IFF_EBRIDGE) + pv = br_get_vlan_info((struct net_bridge *)netdev_priv(dev)); + else + return 0; + + if (!pv) + return 0; + + /* Each VLAN is returned in bridge_vlan_info along with flags */ + return pv->num_vlans * nla_total_size(sizeof(struct bridge_vlan_info)); +} + +static struct rtnl_af_ops br_af_ops = { + .family = AF_BRIDGE, + .get_link_af_size = br_get_link_af_size, +}; + struct rtnl_link_ops br_link_ops __read_mostly = { .kind = "bridge", .priv_size = sizeof(struct net_bridge), @@ -299,10 +478,29 @@ struct rtnl_link_ops br_link_ops __read_mostly = { int __init br_netlink_init(void) { - return rtnl_link_register(&br_link_ops); + int err; + + br_mdb_init(); + err = rtnl_af_register(&br_af_ops); + if (err) + goto out; + + err = rtnl_link_register(&br_link_ops); + if (err) + goto out_af; + + return 0; + +out_af: + rtnl_af_unregister(&br_af_ops); +out: + br_mdb_uninit(); + return err; } void __exit br_netlink_fini(void) { + br_mdb_uninit(); + rtnl_af_unregister(&br_af_ops); rtnl_link_unregister(&br_link_ops); } diff --git a/net/bridge/br_notify.c b/net/bridge/br_notify.c index a76b62135558..1644b3e1f947 100644 --- a/net/bridge/br_notify.c +++ b/net/bridge/br_notify.c @@ -82,7 +82,7 @@ static int br_device_event(struct notifier_block *unused, unsigned long event, v break; case NETDEV_UP: - if (netif_carrier_ok(dev) && (br->dev->flags & IFF_UP)) { + if (netif_running(br->dev) && netif_oper_up(dev)) { spin_lock_bh(&br->lock); br_stp_enable_port(p); spin_unlock_bh(&br->lock); diff --git a/net/bridge/br_private.h b/net/bridge/br_private.h index 8d83be5ffedc..6d314c4e6bcb 100644 --- a/net/bridge/br_private.h +++ b/net/bridge/br_private.h @@ -18,6 +18,7 @@ #include <linux/netpoll.h> #include <linux/u64_stats_sync.h> #include <net/route.h> +#include <linux/if_vlan.h> #define BR_HASH_BITS 8 #define BR_HASH_SIZE (1 << BR_HASH_BITS) @@ -26,6 +27,7 @@ #define BR_PORT_BITS 10 #define BR_MAX_PORTS (1<<BR_PORT_BITS) +#define BR_VLAN_BITMAP_LEN BITS_TO_LONGS(VLAN_N_VID) #define BR_VERSION "2.3" @@ -61,6 +63,20 @@ struct br_ip #endif } u; __be16 proto; + __u16 vid; +}; + +struct net_port_vlans { + u16 port_idx; + u16 pvid; + union { + struct net_bridge_port *port; + struct net_bridge *br; + } parent; + struct rcu_head rcu; + unsigned long vlan_bitmap[BR_VLAN_BITMAP_LEN]; + unsigned long untagged_bitmap[BR_VLAN_BITMAP_LEN]; + u16 num_vlans; }; struct net_bridge_fdb_entry @@ -74,6 +90,7 @@ struct net_bridge_fdb_entry mac_addr addr; unsigned char is_local; unsigned char is_static; + __u16 vlan_id; }; struct net_bridge_port_group { @@ -156,6 +173,9 @@ struct net_bridge_port #ifdef CONFIG_NET_POLL_CONTROLLER struct netpoll *np; #endif +#ifdef CONFIG_BRIDGE_VLAN_FILTERING + struct net_port_vlans __rcu *vlan_info; +#endif }; #define br_port_exists(dev) (dev->priv_flags & IFF_BRIDGE_PORT) @@ -197,9 +217,6 @@ struct net_bridge bool nf_call_ip6tables; bool nf_call_arptables; #endif - unsigned long flags; -#define BR_SET_MAC_ADDR 0x00000001 - u16 group_fwd_mask; /* STP */ @@ -260,6 +277,10 @@ struct net_bridge struct timer_list topology_change_timer; struct timer_list gc_timer; struct kobject *ifobj; +#ifdef CONFIG_BRIDGE_VLAN_FILTERING + u8 vlan_enabled; + struct net_port_vlans __rcu *vlan_info; +#endif }; struct br_input_skb_cb { @@ -355,18 +376,22 @@ extern void br_fdb_cleanup(unsigned long arg); extern void br_fdb_delete_by_port(struct net_bridge *br, const struct net_bridge_port *p, int do_all); extern struct net_bridge_fdb_entry *__br_fdb_get(struct net_bridge *br, - const unsigned char *addr); + const unsigned char *addr, + __u16 vid); extern int br_fdb_test_addr(struct net_device *dev, unsigned char *addr); extern int br_fdb_fillbuf(struct net_bridge *br, void *buf, unsigned long count, unsigned long off); extern int br_fdb_insert(struct net_bridge *br, struct net_bridge_port *source, - const unsigned char *addr); + const unsigned char *addr, + u16 vid); extern void br_fdb_update(struct net_bridge *br, struct net_bridge_port *source, - const unsigned char *addr); + const unsigned char *addr, + u16 vid); +extern int fdb_delete_by_addr(struct net_bridge *br, const u8 *addr, u16 vid); -extern int br_fdb_delete(struct ndmsg *ndm, +extern int br_fdb_delete(struct ndmsg *ndm, struct nlattr *tb[], struct net_device *dev, const unsigned char *addr); extern int br_fdb_add(struct ndmsg *nlh, struct nlattr *tb[], @@ -526,6 +551,148 @@ static inline bool br_multicast_is_router(struct net_bridge *br) { return 0; } +static inline void br_mdb_init(void) +{ +} +static inline void br_mdb_uninit(void) +{ +} +#endif + +/* br_vlan.c */ +#ifdef CONFIG_BRIDGE_VLAN_FILTERING +extern bool br_allowed_ingress(struct net_bridge *br, struct net_port_vlans *v, + struct sk_buff *skb, u16 *vid); +extern bool br_allowed_egress(struct net_bridge *br, + const struct net_port_vlans *v, + const struct sk_buff *skb); +extern struct sk_buff *br_handle_vlan(struct net_bridge *br, + const struct net_port_vlans *v, + struct sk_buff *skb); +extern int br_vlan_add(struct net_bridge *br, u16 vid, u16 flags); +extern int br_vlan_delete(struct net_bridge *br, u16 vid); +extern void br_vlan_flush(struct net_bridge *br); +extern int br_vlan_filter_toggle(struct net_bridge *br, unsigned long val); +extern int nbp_vlan_add(struct net_bridge_port *port, u16 vid, u16 flags); +extern int nbp_vlan_delete(struct net_bridge_port *port, u16 vid); +extern void nbp_vlan_flush(struct net_bridge_port *port); +extern bool nbp_vlan_find(struct net_bridge_port *port, u16 vid); + +static inline struct net_port_vlans *br_get_vlan_info( + const struct net_bridge *br) +{ + return rcu_dereference_rtnl(br->vlan_info); +} + +static inline struct net_port_vlans *nbp_get_vlan_info( + const struct net_bridge_port *p) +{ + return rcu_dereference_rtnl(p->vlan_info); +} + +/* Since bridge now depends on 8021Q module, but the time bridge sees the + * skb, the vlan tag will always be present if the frame was tagged. + */ +static inline int br_vlan_get_tag(const struct sk_buff *skb, u16 *vid) +{ + int err = 0; + + if (vlan_tx_tag_present(skb)) + *vid = vlan_tx_tag_get(skb) & VLAN_VID_MASK; + else { + *vid = 0; + err = -EINVAL; + } + + return err; +} + +static inline u16 br_get_pvid(const struct net_port_vlans *v) +{ + /* Return just the VID if it is set, or VLAN_N_VID (invalid vid) if + * vid wasn't set + */ + smp_rmb(); + return (v->pvid & VLAN_TAG_PRESENT) ? + (v->pvid & ~VLAN_TAG_PRESENT) : + VLAN_N_VID; +} + +#else +static inline bool br_allowed_ingress(struct net_bridge *br, + struct net_port_vlans *v, + struct sk_buff *skb, + u16 *vid) +{ + return true; +} + +static inline bool br_allowed_egress(struct net_bridge *br, + const struct net_port_vlans *v, + const struct sk_buff *skb) +{ + return true; +} + +static inline struct sk_buff *br_handle_vlan(struct net_bridge *br, + const struct net_port_vlans *v, + struct sk_buff *skb) +{ + return skb; +} + +static inline int br_vlan_add(struct net_bridge *br, u16 vid, u16 flags) +{ + return -EOPNOTSUPP; +} + +static inline int br_vlan_delete(struct net_bridge *br, u16 vid) +{ + return -EOPNOTSUPP; +} + +static inline void br_vlan_flush(struct net_bridge *br) +{ +} + +static inline int nbp_vlan_add(struct net_bridge_port *port, u16 vid, u16 flags) +{ + return -EOPNOTSUPP; +} + +static inline int nbp_vlan_delete(struct net_bridge_port *port, u16 vid) +{ + return -EOPNOTSUPP; +} + +static inline void nbp_vlan_flush(struct net_bridge_port *port) +{ +} + +static inline struct net_port_vlans *br_get_vlan_info( + const struct net_bridge *br) +{ + return NULL; +} +static inline struct net_port_vlans *nbp_get_vlan_info( + const struct net_bridge_port *p) +{ + return NULL; +} + +static inline bool nbp_vlan_find(struct net_bridge_port *port, u16 vid) +{ + return false; +} + +static inline u16 br_vlan_get_tag(const struct sk_buff *skb, u16 *tag) +{ + return 0; +} +static inline u16 br_get_pvid(const struct net_port_vlans *v) +{ + return VLAN_N_VID; /* Returns invalid vid */ +} #endif /* br_netfilter.c */ @@ -588,8 +755,9 @@ extern int br_netlink_init(void); extern void br_netlink_fini(void); extern void br_ifinfo_notify(int event, struct net_bridge_port *port); extern int br_setlink(struct net_device *dev, struct nlmsghdr *nlmsg); +extern int br_dellink(struct net_device *dev, struct nlmsghdr *nlmsg); extern int br_getlink(struct sk_buff *skb, u32 pid, u32 seq, - struct net_device *dev); + struct net_device *dev, u32 filter_mask); #ifdef CONFIG_SYSFS /* br_sysfs_if.c */ diff --git a/net/bridge/br_stp_bpdu.c b/net/bridge/br_stp_bpdu.c index 7f884e3fb955..8660ea3be705 100644 --- a/net/bridge/br_stp_bpdu.c +++ b/net/bridge/br_stp_bpdu.c @@ -16,6 +16,7 @@ #include <linux/etherdevice.h> #include <linux/llc.h> #include <linux/slab.h> +#include <linux/pkt_sched.h> #include <net/net_namespace.h> #include <net/llc.h> #include <net/llc_pdu.h> @@ -40,6 +41,7 @@ static void br_send_bpdu(struct net_bridge_port *p, skb->dev = p->dev; skb->protocol = htons(ETH_P_802_2); + skb->priority = TC_PRIO_CONTROL; skb_reserve(skb, LLC_RESERVE); memcpy(__skb_put(skb, length), data, length); diff --git a/net/bridge/br_stp_if.c b/net/bridge/br_stp_if.c index 9d5a414a3943..0bdb4ebd362b 100644 --- a/net/bridge/br_stp_if.c +++ b/net/bridge/br_stp_if.c @@ -54,7 +54,7 @@ void br_stp_enable_bridge(struct net_bridge *br) br_config_bpdu_generation(br); list_for_each_entry(p, &br->port_list, list) { - if ((p->dev->flags & IFF_UP) && netif_carrier_ok(p->dev)) + if (netif_running(p->dev) && netif_oper_up(p->dev)) br_stp_enable_port(p); } @@ -216,7 +216,7 @@ bool br_stp_recalculate_bridge_id(struct net_bridge *br) struct net_bridge_port *p; /* user has chosen a value so keep it */ - if (br->flags & BR_SET_MAC_ADDR) + if (br->dev->addr_assign_type == NET_ADDR_SET) return false; list_for_each_entry(p, &br->port_list, list) { diff --git a/net/bridge/br_sysfs_br.c b/net/bridge/br_sysfs_br.c index 5913a3a0047b..8baa9c08e1a4 100644 --- a/net/bridge/br_sysfs_br.c +++ b/net/bridge/br_sysfs_br.c @@ -691,6 +691,24 @@ static ssize_t store_nf_call_arptables( static DEVICE_ATTR(nf_call_arptables, S_IRUGO | S_IWUSR, show_nf_call_arptables, store_nf_call_arptables); #endif +#ifdef CONFIG_BRIDGE_VLAN_FILTERING +static ssize_t show_vlan_filtering(struct device *d, + struct device_attribute *attr, + char *buf) +{ + struct net_bridge *br = to_bridge(d); + return sprintf(buf, "%d\n", br->vlan_enabled); +} + +static ssize_t store_vlan_filtering(struct device *d, + struct device_attribute *attr, + const char *buf, size_t len) +{ + return store_bridge_parm(d, buf, len, br_vlan_filter_toggle); +} +static DEVICE_ATTR(vlan_filtering, S_IRUGO | S_IWUSR, + show_vlan_filtering, store_vlan_filtering); +#endif static struct attribute *bridge_attrs[] = { &dev_attr_forward_delay.attr, @@ -732,6 +750,9 @@ static struct attribute *bridge_attrs[] = { &dev_attr_nf_call_ip6tables.attr, &dev_attr_nf_call_arptables.attr, #endif +#ifdef CONFIG_BRIDGE_VLAN_FILTERING + &dev_attr_vlan_filtering.attr, +#endif NULL }; diff --git a/net/bridge/br_vlan.c b/net/bridge/br_vlan.c new file mode 100644 index 000000000000..93dde75923f0 --- /dev/null +++ b/net/bridge/br_vlan.c @@ -0,0 +1,415 @@ +#include <linux/kernel.h> +#include <linux/netdevice.h> +#include <linux/rtnetlink.h> +#include <linux/slab.h> + +#include "br_private.h" + +static void __vlan_add_pvid(struct net_port_vlans *v, u16 vid) +{ + if (v->pvid == vid) + return; + + smp_wmb(); + v->pvid = vid; +} + +static void __vlan_delete_pvid(struct net_port_vlans *v, u16 vid) +{ + if (v->pvid != vid) + return; + + smp_wmb(); + v->pvid = 0; +} + +static void __vlan_add_flags(struct net_port_vlans *v, u16 vid, u16 flags) +{ + if (flags & BRIDGE_VLAN_INFO_PVID) + __vlan_add_pvid(v, vid); + + if (flags & BRIDGE_VLAN_INFO_UNTAGGED) + set_bit(vid, v->untagged_bitmap); +} + +static int __vlan_add(struct net_port_vlans *v, u16 vid, u16 flags) +{ + struct net_bridge_port *p = NULL; + struct net_bridge *br; + struct net_device *dev; + int err; + + if (test_bit(vid, v->vlan_bitmap)) { + __vlan_add_flags(v, vid, flags); + return 0; + } + + if (vid) { + if (v->port_idx) { + p = v->parent.port; + br = p->br; + dev = p->dev; + } else { + br = v->parent.br; + dev = br->dev; + } + + if (p && (dev->features & NETIF_F_HW_VLAN_FILTER)) { + /* Add VLAN to the device filter if it is supported. + * Stricly speaking, this is not necessary now, since + * devices are made promiscuous by the bridge, but if + * that ever changes this code will allow tagged + * traffic to enter the bridge. + */ + err = dev->netdev_ops->ndo_vlan_rx_add_vid(dev, vid); + if (err) + return err; + } + + err = br_fdb_insert(br, p, dev->dev_addr, vid); + if (err) { + br_err(br, "failed insert local address into bridge " + "forwarding table\n"); + goto out_filt; + } + + } + + set_bit(vid, v->vlan_bitmap); + v->num_vlans++; + __vlan_add_flags(v, vid, flags); + + return 0; + +out_filt: + if (p && (dev->features & NETIF_F_HW_VLAN_FILTER)) + dev->netdev_ops->ndo_vlan_rx_kill_vid(dev, vid); + return err; +} + +static int __vlan_del(struct net_port_vlans *v, u16 vid) +{ + if (!test_bit(vid, v->vlan_bitmap)) + return -EINVAL; + + __vlan_delete_pvid(v, vid); + clear_bit(vid, v->untagged_bitmap); + + if (v->port_idx && vid) { + struct net_device *dev = v->parent.port->dev; + + if (dev->features & NETIF_F_HW_VLAN_FILTER) + dev->netdev_ops->ndo_vlan_rx_kill_vid(dev, vid); + } + + clear_bit(vid, v->vlan_bitmap); + v->num_vlans--; + if (bitmap_empty(v->vlan_bitmap, BR_VLAN_BITMAP_LEN)) { + if (v->port_idx) + rcu_assign_pointer(v->parent.port->vlan_info, NULL); + else + rcu_assign_pointer(v->parent.br->vlan_info, NULL); + kfree_rcu(v, rcu); + } + return 0; +} + +static void __vlan_flush(struct net_port_vlans *v) +{ + smp_wmb(); + v->pvid = 0; + bitmap_zero(v->vlan_bitmap, BR_VLAN_BITMAP_LEN); + if (v->port_idx) + rcu_assign_pointer(v->parent.port->vlan_info, NULL); + else + rcu_assign_pointer(v->parent.br->vlan_info, NULL); + kfree_rcu(v, rcu); +} + +/* Strip the tag from the packet. Will return skb with tci set 0. */ +static struct sk_buff *br_vlan_untag(struct sk_buff *skb) +{ + if (skb->protocol != htons(ETH_P_8021Q)) { + skb->vlan_tci = 0; + return skb; + } + + skb->vlan_tci = 0; + skb = vlan_untag(skb); + if (skb) + skb->vlan_tci = 0; + + return skb; +} + +struct sk_buff *br_handle_vlan(struct net_bridge *br, + const struct net_port_vlans *pv, + struct sk_buff *skb) +{ + u16 vid; + + if (!br->vlan_enabled) + goto out; + + /* At this point, we know that the frame was filtered and contains + * a valid vlan id. If the vlan id is set in the untagged bitmap, + * send untagged; otherwise, send taged. + */ + br_vlan_get_tag(skb, &vid); + if (test_bit(vid, pv->untagged_bitmap)) + skb = br_vlan_untag(skb); + else { + /* Egress policy says "send tagged". If output device + * is the bridge, we need to add the VLAN header + * ourselves since we'll be going through the RX path. + * Sending to ports puts the frame on the TX path and + * we let dev_hard_start_xmit() add the header. + */ + if (skb->protocol != htons(ETH_P_8021Q) && + pv->port_idx == 0) { + /* vlan_put_tag expects skb->data to point to + * mac header. + */ + skb_push(skb, ETH_HLEN); + skb = __vlan_put_tag(skb, skb->vlan_tci); + if (!skb) + goto out; + /* put skb->data back to where it was */ + skb_pull(skb, ETH_HLEN); + skb->vlan_tci = 0; + } + } + +out: + return skb; +} + +/* Called under RCU */ +bool br_allowed_ingress(struct net_bridge *br, struct net_port_vlans *v, + struct sk_buff *skb, u16 *vid) +{ + /* If VLAN filtering is disabled on the bridge, all packets are + * permitted. + */ + if (!br->vlan_enabled) + return true; + + /* If there are no vlan in the permitted list, all packets are + * rejected. + */ + if (!v) + return false; + + if (br_vlan_get_tag(skb, vid)) { + u16 pvid = br_get_pvid(v); + + /* Frame did not have a tag. See if pvid is set + * on this port. That tells us which vlan untagged + * traffic belongs to. + */ + if (pvid == VLAN_N_VID) + return false; + + /* PVID is set on this port. Any untagged ingress + * frame is considered to belong to this vlan. + */ + __vlan_hwaccel_put_tag(skb, pvid); + return true; + } + + /* Frame had a valid vlan tag. See if vlan is allowed */ + if (test_bit(*vid, v->vlan_bitmap)) + return true; + + return false; +} + +/* Called under RCU. */ +bool br_allowed_egress(struct net_bridge *br, + const struct net_port_vlans *v, + const struct sk_buff *skb) +{ + u16 vid; + + if (!br->vlan_enabled) + return true; + + if (!v) + return false; + + br_vlan_get_tag(skb, &vid); + if (test_bit(vid, v->vlan_bitmap)) + return true; + + return false; +} + +/* Must be protected by RTNL */ +int br_vlan_add(struct net_bridge *br, u16 vid, u16 flags) +{ + struct net_port_vlans *pv = NULL; + int err; + + ASSERT_RTNL(); + + pv = rtnl_dereference(br->vlan_info); + if (pv) + return __vlan_add(pv, vid, flags); + + /* Create port vlan infomration + */ + pv = kzalloc(sizeof(*pv), GFP_KERNEL); + if (!pv) + return -ENOMEM; + + pv->parent.br = br; + err = __vlan_add(pv, vid, flags); + if (err) + goto out; + + rcu_assign_pointer(br->vlan_info, pv); + return 0; +out: + kfree(pv); + return err; +} + +/* Must be protected by RTNL */ +int br_vlan_delete(struct net_bridge *br, u16 vid) +{ + struct net_port_vlans *pv; + + ASSERT_RTNL(); + + pv = rtnl_dereference(br->vlan_info); + if (!pv) + return -EINVAL; + + if (vid) { + /* If the VID !=0 remove fdb for this vid. VID 0 is special + * in that it's the default and is always there in the fdb. + */ + spin_lock_bh(&br->hash_lock); + fdb_delete_by_addr(br, br->dev->dev_addr, vid); + spin_unlock_bh(&br->hash_lock); + } + + __vlan_del(pv, vid); + return 0; +} + +void br_vlan_flush(struct net_bridge *br) +{ + struct net_port_vlans *pv; + + ASSERT_RTNL(); + pv = rtnl_dereference(br->vlan_info); + if (!pv) + return; + + __vlan_flush(pv); +} + +int br_vlan_filter_toggle(struct net_bridge *br, unsigned long val) +{ + if (!rtnl_trylock()) + return restart_syscall(); + + if (br->vlan_enabled == val) + goto unlock; + + br->vlan_enabled = val; + +unlock: + rtnl_unlock(); + return 0; +} + +/* Must be protected by RTNL */ +int nbp_vlan_add(struct net_bridge_port *port, u16 vid, u16 flags) +{ + struct net_port_vlans *pv = NULL; + int err; + + ASSERT_RTNL(); + + pv = rtnl_dereference(port->vlan_info); + if (pv) + return __vlan_add(pv, vid, flags); + + /* Create port vlan infomration + */ + pv = kzalloc(sizeof(*pv), GFP_KERNEL); + if (!pv) { + err = -ENOMEM; + goto clean_up; + } + + pv->port_idx = port->port_no; + pv->parent.port = port; + err = __vlan_add(pv, vid, flags); + if (err) + goto clean_up; + + rcu_assign_pointer(port->vlan_info, pv); + return 0; + +clean_up: + kfree(pv); + return err; +} + +/* Must be protected by RTNL */ +int nbp_vlan_delete(struct net_bridge_port *port, u16 vid) +{ + struct net_port_vlans *pv; + + ASSERT_RTNL(); + + pv = rtnl_dereference(port->vlan_info); + if (!pv) + return -EINVAL; + + if (vid) { + /* If the VID !=0 remove fdb for this vid. VID 0 is special + * in that it's the default and is always there in the fdb. + */ + spin_lock_bh(&port->br->hash_lock); + fdb_delete_by_addr(port->br, port->dev->dev_addr, vid); + spin_unlock_bh(&port->br->hash_lock); + } + + return __vlan_del(pv, vid); +} + +void nbp_vlan_flush(struct net_bridge_port *port) +{ + struct net_port_vlans *pv; + + ASSERT_RTNL(); + + pv = rtnl_dereference(port->vlan_info); + if (!pv) + return; + + __vlan_flush(pv); +} + +bool nbp_vlan_find(struct net_bridge_port *port, u16 vid) +{ + struct net_port_vlans *pv; + bool found = false; + + rcu_read_lock(); + pv = rcu_dereference(port->vlan_info); + + if (!pv) + goto out; + + if (test_bit(vid, pv->vlan_bitmap)) + found = true; + +out: + rcu_read_unlock(); + return found; +} diff --git a/net/bridge/netfilter/ebt_ulog.c b/net/bridge/netfilter/ebt_ulog.c index 3476ec469740..3bf43f7bb9d4 100644 --- a/net/bridge/netfilter/ebt_ulog.c +++ b/net/bridge/netfilter/ebt_ulog.c @@ -70,8 +70,7 @@ static void ulog_send(unsigned int nlgroup) { ebt_ulog_buff_t *ub = &ulog_buffers[nlgroup]; - if (timer_pending(&ub->timer)) - del_timer(&ub->timer); + del_timer(&ub->timer); if (!ub->skb) return; @@ -319,8 +318,7 @@ static void __exit ebt_ulog_fini(void) xt_unregister_target(&ebt_ulog_tg_reg); for (i = 0; i < EBT_ULOG_MAXNLGROUPS; i++) { ub = &ulog_buffers[i]; - if (timer_pending(&ub->timer)) - del_timer(&ub->timer); + del_timer(&ub->timer); spin_lock_bh(&ub->lock); if (ub->skb) { kfree_skb(ub->skb); diff --git a/net/bridge/netfilter/ebtables.c b/net/bridge/netfilter/ebtables.c index 5fe2ff3b01ef..8d493c91a562 100644 --- a/net/bridge/netfilter/ebtables.c +++ b/net/bridge/netfilter/ebtables.c @@ -1472,16 +1472,17 @@ static int do_ebt_set_ctl(struct sock *sk, int cmd, void __user *user, unsigned int len) { int ret; + struct net *net = sock_net(sk); - if (!capable(CAP_NET_ADMIN)) + if (!ns_capable(net->user_ns, CAP_NET_ADMIN)) return -EPERM; switch(cmd) { case EBT_SO_SET_ENTRIES: - ret = do_replace(sock_net(sk), user, len); + ret = do_replace(net, user, len); break; case EBT_SO_SET_COUNTERS: - ret = update_counters(sock_net(sk), user, len); + ret = update_counters(net, user, len); break; default: ret = -EINVAL; @@ -1494,14 +1495,15 @@ static int do_ebt_get_ctl(struct sock *sk, int cmd, void __user *user, int *len) int ret; struct ebt_replace tmp; struct ebt_table *t; + struct net *net = sock_net(sk); - if (!capable(CAP_NET_ADMIN)) + if (!ns_capable(net->user_ns, CAP_NET_ADMIN)) return -EPERM; if (copy_from_user(&tmp, user, sizeof(tmp))) return -EFAULT; - t = find_table_lock(sock_net(sk), tmp.name, &ret, &ebt_mutex); + t = find_table_lock(net, tmp.name, &ret, &ebt_mutex); if (!t) return ret; @@ -2279,16 +2281,17 @@ static int compat_do_ebt_set_ctl(struct sock *sk, int cmd, void __user *user, unsigned int len) { int ret; + struct net *net = sock_net(sk); - if (!capable(CAP_NET_ADMIN)) + if (!ns_capable(net->user_ns, CAP_NET_ADMIN)) return -EPERM; switch (cmd) { case EBT_SO_SET_ENTRIES: - ret = compat_do_replace(sock_net(sk), user, len); + ret = compat_do_replace(net, user, len); break; case EBT_SO_SET_COUNTERS: - ret = compat_update_counters(sock_net(sk), user, len); + ret = compat_update_counters(net, user, len); break; default: ret = -EINVAL; @@ -2302,8 +2305,9 @@ static int compat_do_ebt_get_ctl(struct sock *sk, int cmd, int ret; struct compat_ebt_replace tmp; struct ebt_table *t; + struct net *net = sock_net(sk); - if (!capable(CAP_NET_ADMIN)) + if (!ns_capable(net->user_ns, CAP_NET_ADMIN)) return -EPERM; /* try real handler in case userland supplied needed padding */ @@ -2314,7 +2318,7 @@ static int compat_do_ebt_get_ctl(struct sock *sk, int cmd, if (copy_from_user(&tmp, user, sizeof(tmp))) return -EFAULT; - t = find_table_lock(sock_net(sk), tmp.name, &ret, &ebt_mutex); + t = find_table_lock(net, tmp.name, &ret, &ebt_mutex); if (!t) return ret; diff --git a/net/can/Kconfig b/net/can/Kconfig index 03200699d274..a15c0e0d1fc7 100644 --- a/net/can/Kconfig +++ b/net/can/Kconfig @@ -16,10 +16,11 @@ menuconfig CAN If you want CAN support you should say Y here and also to the specific driver for your controller(s) below. +if CAN + config CAN_RAW tristate "Raw CAN Protocol (raw access with CAN-ID filtering)" - depends on CAN - default N + default y ---help--- The raw CAN protocol option offers access to the CAN bus via the BSD socket API. You probably want to use the raw socket in @@ -29,8 +30,7 @@ config CAN_RAW config CAN_BCM tristate "Broadcast Manager CAN Protocol (with content filtering)" - depends on CAN - default N + default y ---help--- The Broadcast Manager offers content filtering, timeout monitoring, sending of RTR frames, and cyclic CAN messages without permanent user @@ -42,8 +42,7 @@ config CAN_BCM config CAN_GW tristate "CAN Gateway/Router (with netlink configuration)" - depends on CAN - default N + default y ---help--- The CAN Gateway/Router is used to route (and modify) CAN frames. It is based on the PF_CAN core infrastructure for msg filtering and @@ -53,3 +52,5 @@ config CAN_GW by the netlink configuration interface known e.g. from iptables. source "drivers/net/can/Kconfig" + +endif diff --git a/net/can/bcm.c b/net/can/bcm.c index 969b7cdff59d..28e12d18f0f1 100644 --- a/net/can/bcm.c +++ b/net/can/bcm.c @@ -54,6 +54,7 @@ #include <linux/skbuff.h> #include <linux/can.h> #include <linux/can/core.h> +#include <linux/can/skb.h> #include <linux/can/bcm.h> #include <linux/slab.h> #include <net/sock.h> @@ -256,10 +257,13 @@ static void bcm_can_tx(struct bcm_op *op) return; } - skb = alloc_skb(CFSIZ, gfp_any()); + skb = alloc_skb(CFSIZ + sizeof(struct can_skb_priv), gfp_any()); if (!skb) goto out; + can_skb_reserve(skb); + can_skb_prv(skb)->ifindex = dev->ifindex; + memcpy(skb_put(skb, CFSIZ), cf, CFSIZ); /* send with loopback */ @@ -1199,11 +1203,12 @@ static int bcm_tx_send(struct msghdr *msg, int ifindex, struct sock *sk) if (!ifindex) return -ENODEV; - skb = alloc_skb(CFSIZ, GFP_KERNEL); - + skb = alloc_skb(CFSIZ + sizeof(struct can_skb_priv), GFP_KERNEL); if (!skb) return -ENOMEM; + can_skb_reserve(skb); + err = memcpy_fromiovec(skb_put(skb, CFSIZ), msg->msg_iov, CFSIZ); if (err < 0) { kfree_skb(skb); @@ -1216,6 +1221,7 @@ static int bcm_tx_send(struct msghdr *msg, int ifindex, struct sock *sk) return -ENODEV; } + can_skb_prv(skb)->ifindex = dev->ifindex; skb->dev = dev; skb->sk = sk; err = can_send(skb, 1); /* send with loopback */ diff --git a/net/can/gw.c b/net/can/gw.c index 574dda78eb0f..c185fcd5e828 100644 --- a/net/can/gw.c +++ b/net/can/gw.c @@ -42,6 +42,7 @@ #include <linux/module.h> #include <linux/init.h> #include <linux/types.h> +#include <linux/kernel.h> #include <linux/list.h> #include <linux/spinlock.h> #include <linux/rcupdate.h> @@ -52,19 +53,31 @@ #include <linux/skbuff.h> #include <linux/can.h> #include <linux/can/core.h> +#include <linux/can/skb.h> #include <linux/can/gw.h> #include <net/rtnetlink.h> #include <net/net_namespace.h> #include <net/sock.h> -#define CAN_GW_VERSION "20101209" -static __initconst const char banner[] = - KERN_INFO "can: netlink gateway (rev " CAN_GW_VERSION ")\n"; +#define CAN_GW_VERSION "20130117" +#define CAN_GW_NAME "can-gw" MODULE_DESCRIPTION("PF_CAN netlink gateway"); MODULE_LICENSE("Dual BSD/GPL"); MODULE_AUTHOR("Oliver Hartkopp <oliver.hartkopp@volkswagen.de>"); -MODULE_ALIAS("can-gw"); +MODULE_ALIAS(CAN_GW_NAME); + +#define CGW_MIN_HOPS 1 +#define CGW_MAX_HOPS 6 +#define CGW_DEFAULT_HOPS 1 + +static unsigned int max_hops __read_mostly = CGW_DEFAULT_HOPS; +module_param(max_hops, uint, S_IRUGO); +MODULE_PARM_DESC(max_hops, + "maximum " CAN_GW_NAME " routing hops for CAN frames " + "(valid values: " __stringify(CGW_MIN_HOPS) "-" + __stringify(CGW_MAX_HOPS) " hops, " + "default: " __stringify(CGW_DEFAULT_HOPS) ")"); static HLIST_HEAD(cgw_list); static struct notifier_block notifier; @@ -118,6 +131,7 @@ struct cgw_job { struct rcu_head rcu; u32 handled_frames; u32 dropped_frames; + u32 deleted_frames; struct cf_mod mod; union { /* CAN frame data source */ @@ -338,15 +352,38 @@ static void can_can_gw_rcv(struct sk_buff *skb, void *data) struct sk_buff *nskb; int modidx = 0; - /* do not handle already routed frames - see comment below */ - if (skb_mac_header_was_set(skb)) + /* + * Do not handle CAN frames routed more than 'max_hops' times. + * In general we should never catch this delimiter which is intended + * to cover a misconfiguration protection (e.g. circular CAN routes). + * + * The Controller Area Network controllers only accept CAN frames with + * correct CRCs - which are not visible in the controller registers. + * According to skbuff.h documentation the csum_start element for IP + * checksums is undefined/unsued when ip_summed == CHECKSUM_UNNECESSARY. + * Only CAN skbs can be processed here which already have this property. + */ + +#define cgw_hops(skb) ((skb)->csum_start) + + BUG_ON(skb->ip_summed != CHECKSUM_UNNECESSARY); + + if (cgw_hops(skb) >= max_hops) { + /* indicate deleted frames due to misconfiguration */ + gwj->deleted_frames++; return; + } if (!(gwj->dst.dev->flags & IFF_UP)) { gwj->dropped_frames++; return; } + /* is sending the skb back to the incoming interface not allowed? */ + if (!(gwj->flags & CGW_FLAGS_CAN_IIF_TX_OK) && + can_skb_prv(skb)->ifindex == gwj->dst.dev->ifindex) + return; + /* * clone the given skb, which has not been done in can_rcv() * @@ -363,15 +400,8 @@ static void can_can_gw_rcv(struct sk_buff *skb, void *data) return; } - /* - * Mark routed frames by setting some mac header length which is - * not relevant for the CAN frames located in the skb->data section. - * - * As dev->header_ops is not set in CAN netdevices no one is ever - * accessing the various header offsets in the CAN skbuffs anyway. - * E.g. using the packet socket to read CAN frames is still working. - */ - skb_set_mac_header(nskb, 8); + /* put the incremented hop counter in the cloned skb */ + cgw_hops(nskb) = cgw_hops(skb) + 1; nskb->dev = gwj->dst.dev; /* pointer to modifiable CAN frame */ @@ -472,6 +502,11 @@ static int cgw_put_job(struct sk_buff *skb, struct cgw_job *gwj, int type, goto cancel; } + if (gwj->deleted_frames) { + if (nla_put_u32(skb, CGW_DELETED, gwj->deleted_frames) < 0) + goto cancel; + } + /* check non default settings of attributes */ if (gwj->mod.modtype.and) { @@ -771,6 +806,7 @@ static int cgw_create_job(struct sk_buff *skb, struct nlmsghdr *nlh, gwj->handled_frames = 0; gwj->dropped_frames = 0; + gwj->deleted_frames = 0; gwj->flags = r->flags; gwj->gwtype = r->gwtype; @@ -895,7 +931,11 @@ static int cgw_remove_job(struct sk_buff *skb, struct nlmsghdr *nlh, void *arg) static __init int cgw_module_init(void) { - printk(banner); + /* sanitize given module parameter */ + max_hops = clamp_t(unsigned int, max_hops, CGW_MIN_HOPS, CGW_MAX_HOPS); + + pr_info("can: netlink gateway (rev " CAN_GW_VERSION ") max_hops=%d\n", + max_hops); cgw_cache = kmem_cache_create("can_gw", sizeof(struct cgw_job), 0, 0, NULL); diff --git a/net/can/raw.c b/net/can/raw.c index 5b0e3e330d97..c1764e41ddaf 100644 --- a/net/can/raw.c +++ b/net/can/raw.c @@ -50,6 +50,7 @@ #include <linux/skbuff.h> #include <linux/can.h> #include <linux/can/core.h> +#include <linux/can/skb.h> #include <linux/can/raw.h> #include <net/sock.h> #include <net/net_namespace.h> @@ -699,11 +700,14 @@ static int raw_sendmsg(struct kiocb *iocb, struct socket *sock, if (!dev) return -ENXIO; - skb = sock_alloc_send_skb(sk, size, msg->msg_flags & MSG_DONTWAIT, - &err); + skb = sock_alloc_send_skb(sk, size + sizeof(struct can_skb_priv), + msg->msg_flags & MSG_DONTWAIT, &err); if (!skb) goto put_dev; + can_skb_reserve(skb); + can_skb_prv(skb)->ifindex = dev->ifindex; + err = memcpy_fromiovec(skb_put(skb, size), msg->msg_iov, size); if (err < 0) goto free_skb; diff --git a/net/ceph/messenger.c b/net/ceph/messenger.c index 4d111fd2b492..5ccf87ed8d68 100644 --- a/net/ceph/messenger.c +++ b/net/ceph/messenger.c @@ -506,6 +506,7 @@ static void reset_connection(struct ceph_connection *con) { /* reset connection, out_queue, msg_ and connect_seq */ /* discard existing out_queue and msg_seq */ + dout("reset_connection %p\n", con); ceph_msg_remove_list(&con->out_queue); ceph_msg_remove_list(&con->out_sent); @@ -561,7 +562,7 @@ void ceph_con_open(struct ceph_connection *con, mutex_lock(&con->mutex); dout("con_open %p %s\n", con, ceph_pr_addr(&addr->in_addr)); - BUG_ON(con->state != CON_STATE_CLOSED); + WARN_ON(con->state != CON_STATE_CLOSED); con->state = CON_STATE_PREOPEN; con->peer_name.type = (__u8) entity_type; @@ -1506,13 +1507,6 @@ static int process_banner(struct ceph_connection *con) return 0; } -static void fail_protocol(struct ceph_connection *con) -{ - reset_connection(con); - BUG_ON(con->state != CON_STATE_NEGOTIATING); - con->state = CON_STATE_CLOSED; -} - static int process_connect(struct ceph_connection *con) { u64 sup_feat = con->msgr->supported_features; @@ -1530,7 +1524,7 @@ static int process_connect(struct ceph_connection *con) ceph_pr_addr(&con->peer_addr.in_addr), sup_feat, server_feat, server_feat & ~sup_feat); con->error_msg = "missing required protocol features"; - fail_protocol(con); + reset_connection(con); return -1; case CEPH_MSGR_TAG_BADPROTOVER: @@ -1541,7 +1535,7 @@ static int process_connect(struct ceph_connection *con) le32_to_cpu(con->out_connect.protocol_version), le32_to_cpu(con->in_reply.protocol_version)); con->error_msg = "protocol version mismatch"; - fail_protocol(con); + reset_connection(con); return -1; case CEPH_MSGR_TAG_BADAUTHORIZER: @@ -1631,11 +1625,11 @@ static int process_connect(struct ceph_connection *con) ceph_pr_addr(&con->peer_addr.in_addr), req_feat, server_feat, req_feat & ~server_feat); con->error_msg = "missing required protocol features"; - fail_protocol(con); + reset_connection(con); return -1; } - BUG_ON(con->state != CON_STATE_NEGOTIATING); + WARN_ON(con->state != CON_STATE_NEGOTIATING); con->state = CON_STATE_OPEN; con->peer_global_seq = le32_to_cpu(con->in_reply.global_seq); @@ -2132,7 +2126,6 @@ more: if (ret < 0) goto out; - BUG_ON(con->state != CON_STATE_CONNECTING); con->state = CON_STATE_NEGOTIATING; /* @@ -2160,7 +2153,7 @@ more: goto more; } - BUG_ON(con->state != CON_STATE_OPEN); + WARN_ON(con->state != CON_STATE_OPEN); if (con->in_base_pos < 0) { /* @@ -2382,7 +2375,7 @@ static void ceph_fault(struct ceph_connection *con) dout("fault %p state %lu to peer %s\n", con, con->state, ceph_pr_addr(&con->peer_addr.in_addr)); - BUG_ON(con->state != CON_STATE_CONNECTING && + WARN_ON(con->state != CON_STATE_CONNECTING && con->state != CON_STATE_NEGOTIATING && con->state != CON_STATE_OPEN); diff --git a/net/ceph/osd_client.c b/net/ceph/osd_client.c index 780caf6b0491..eb9a44478764 100644 --- a/net/ceph/osd_client.c +++ b/net/ceph/osd_client.c @@ -1270,7 +1270,7 @@ static void reset_changed_osds(struct ceph_osd_client *osdc) * Requeue requests whose mapping to an OSD has changed. If requests map to * no osd, request a new map. * - * Caller should hold map_sem for read and request_mutex. + * Caller should hold map_sem for read. */ static void kick_requests(struct ceph_osd_client *osdc, int force_resend) { @@ -1284,6 +1284,24 @@ static void kick_requests(struct ceph_osd_client *osdc, int force_resend) for (p = rb_first(&osdc->requests); p; ) { req = rb_entry(p, struct ceph_osd_request, r_node); p = rb_next(p); + + /* + * For linger requests that have not yet been + * registered, move them to the linger list; they'll + * be sent to the osd in the loop below. Unregister + * the request before re-registering it as a linger + * request to ensure the __map_request() below + * will decide it needs to be sent. + */ + if (req->r_linger && list_empty(&req->r_linger_item)) { + dout("%p tid %llu restart on osd%d\n", + req, req->r_tid, + req->r_osd ? req->r_osd->o_osd : -1); + __unregister_request(osdc, req); + __register_linger_request(osdc, req); + continue; + } + err = __map_request(osdc, req, force_resend); if (err < 0) continue; /* error */ @@ -1298,17 +1316,6 @@ static void kick_requests(struct ceph_osd_client *osdc, int force_resend) req->r_flags |= CEPH_OSD_FLAG_RETRY; } } - if (req->r_linger && list_empty(&req->r_linger_item)) { - /* - * register as a linger so that we will - * re-submit below and get a new tid - */ - dout("%p tid %llu restart on osd%d\n", - req, req->r_tid, - req->r_osd ? req->r_osd->o_osd : -1); - __register_linger_request(osdc, req); - __unregister_request(osdc, req); - } } list_for_each_entry_safe(req, nreq, &osdc->req_linger, @@ -1316,6 +1323,7 @@ static void kick_requests(struct ceph_osd_client *osdc, int force_resend) dout("linger req=%p req->r_osd=%p\n", req, req->r_osd); err = __map_request(osdc, req, force_resend); + dout("__map_request returned %d\n", err); if (err == 0) continue; /* no change and no osd was specified */ if (err < 0) @@ -1337,6 +1345,7 @@ static void kick_requests(struct ceph_osd_client *osdc, int force_resend) dout("%d requests for down osds, need new map\n", needmap); ceph_monc_request_next_osdmap(&osdc->client->monc); } + reset_changed_osds(osdc); } @@ -1393,7 +1402,6 @@ void ceph_osdc_handle_map(struct ceph_osd_client *osdc, struct ceph_msg *msg) osdc->osdmap = newmap; } kick_requests(osdc, 0); - reset_changed_osds(osdc); } else { dout("ignoring incremental map %u len %d\n", epoch, maplen); diff --git a/net/core/Makefile b/net/core/Makefile index 674641b13aea..0c5e3618c80b 100644 --- a/net/core/Makefile +++ b/net/core/Makefile @@ -9,7 +9,7 @@ obj-$(CONFIG_SYSCTL) += sysctl_net_core.o obj-y += dev.o ethtool.o dev_addr_lists.o dst.o netevent.o \ neighbour.o rtnetlink.o utils.o link_watch.o filter.o \ - sock_diag.o + sock_diag.o dev_ioctl.o obj-$(CONFIG_XFRM) += flow.o obj-y += net-sysfs.o diff --git a/net/core/datagram.c b/net/core/datagram.c index 0337e2b76862..368f9c3f9dc6 100644 --- a/net/core/datagram.c +++ b/net/core/datagram.c @@ -187,7 +187,7 @@ struct sk_buff *__skb_recv_datagram(struct sock *sk, unsigned int flags, skb_queue_walk(queue, skb) { *peeked = skb->peeked; if (flags & MSG_PEEK) { - if (*off >= skb->len) { + if (*off >= skb->len && skb->len) { *off -= skb->len; continue; } diff --git a/net/core/dev.c b/net/core/dev.c index d0cbc93fcf32..1932d351ed7c 100644 --- a/net/core/dev.c +++ b/net/core/dev.c @@ -106,7 +106,6 @@ #include <net/xfrm.h> #include <linux/highmem.h> #include <linux/init.h> -#include <linux/kmod.h> #include <linux/module.h> #include <linux/netpoll.h> #include <linux/rcupdate.h> @@ -132,9 +131,7 @@ #include <linux/pci.h> #include <linux/inetdevice.h> #include <linux/cpu_rmap.h> -#include <linux/net_tstamp.h> #include <linux/static_key.h> -#include <net/flow_keys.h> #include "net-sysfs.h" @@ -203,7 +200,7 @@ static struct list_head offload_base __read_mostly; DEFINE_RWLOCK(dev_base_lock); EXPORT_SYMBOL(dev_base_lock); -DEFINE_SEQLOCK(devnet_rename_seq); +seqcount_t devnet_rename_seq; static inline void dev_base_seq_inc(struct net *net) { @@ -1093,10 +1090,10 @@ int dev_change_name(struct net_device *dev, const char *newname) if (dev->flags & IFF_UP) return -EBUSY; - write_seqlock(&devnet_rename_seq); + write_seqcount_begin(&devnet_rename_seq); if (strncmp(newname, dev->name, IFNAMSIZ) == 0) { - write_sequnlock(&devnet_rename_seq); + write_seqcount_end(&devnet_rename_seq); return 0; } @@ -1104,7 +1101,7 @@ int dev_change_name(struct net_device *dev, const char *newname) err = dev_get_valid_name(net, dev, newname); if (err < 0) { - write_sequnlock(&devnet_rename_seq); + write_seqcount_end(&devnet_rename_seq); return err; } @@ -1112,11 +1109,11 @@ rollback: ret = device_rename(&dev->dev, dev->name); if (ret) { memcpy(dev->name, oldname, IFNAMSIZ); - write_sequnlock(&devnet_rename_seq); + write_seqcount_end(&devnet_rename_seq); return ret; } - write_sequnlock(&devnet_rename_seq); + write_seqcount_end(&devnet_rename_seq); write_lock_bh(&dev_base_lock); hlist_del_rcu(&dev->name_hlist); @@ -1135,7 +1132,7 @@ rollback: /* err >= 0 after dev_alloc_name() or stores the first errno */ if (err >= 0) { err = ret; - write_seqlock(&devnet_rename_seq); + write_seqcount_begin(&devnet_rename_seq); memcpy(dev->name, oldname, IFNAMSIZ); goto rollback; } else { @@ -1227,36 +1224,6 @@ void netdev_notify_peers(struct net_device *dev) } EXPORT_SYMBOL(netdev_notify_peers); -/** - * dev_load - load a network module - * @net: the applicable net namespace - * @name: name of interface - * - * If a network interface is not present and the process has suitable - * privileges this function loads the module. If module loading is not - * available in this kernel then it becomes a nop. - */ - -void dev_load(struct net *net, const char *name) -{ - struct net_device *dev; - int no_module; - - rcu_read_lock(); - dev = dev_get_by_name_rcu(net, name); - rcu_read_unlock(); - - no_module = !dev; - if (no_module && capable(CAP_NET_ADMIN)) - no_module = request_module("netdev-%s", name); - if (no_module && capable(CAP_SYS_MODULE)) { - if (!request_module("%s", name)) - pr_warn("Loading kernel module for a network device with CAP_SYS_MODULE (deprecated). Use CAP_NET_ADMIN and alias netdev-%s instead.\n", - name); - } -} -EXPORT_SYMBOL(dev_load); - static int __dev_open(struct net_device *dev) { const struct net_device_ops *ops = dev->netdev_ops; @@ -1267,6 +1234,14 @@ static int __dev_open(struct net_device *dev) if (!netif_device_present(dev)) return -ENODEV; + /* Block netpoll from trying to do any rx path servicing. + * If we don't do this there is a chance ndo_poll_controller + * or ndo_poll may be running while we open the device + */ + ret = netpoll_rx_disable(dev); + if (ret) + return ret; + ret = call_netdevice_notifiers(NETDEV_PRE_UP, dev); ret = notifier_to_errno(ret); if (ret) @@ -1280,6 +1255,8 @@ static int __dev_open(struct net_device *dev) if (!ret && ops->ndo_open) ret = ops->ndo_open(dev); + netpoll_rx_enable(dev); + if (ret) clear_bit(__LINK_STATE_START, &dev->state); else { @@ -1371,9 +1348,16 @@ static int __dev_close(struct net_device *dev) int retval; LIST_HEAD(single); + /* Temporarily disable netpoll until the interface is down */ + retval = netpoll_rx_disable(dev); + if (retval) + return retval; + list_add(&dev->unreg_list, &single); retval = __dev_close_many(&single); list_del(&single); + + netpoll_rx_enable(dev); return retval; } @@ -1409,14 +1393,22 @@ static int dev_close_many(struct list_head *head) */ int dev_close(struct net_device *dev) { + int ret = 0; if (dev->flags & IFF_UP) { LIST_HEAD(single); + /* Block netpoll rx while the interface is going down */ + ret = netpoll_rx_disable(dev); + if (ret) + return ret; + list_add(&dev->unreg_list, &single); dev_close_many(&single); list_del(&single); + + netpoll_rx_enable(dev); } - return 0; + return ret; } EXPORT_SYMBOL(dev_close); @@ -1621,57 +1613,6 @@ static inline void net_timestamp_set(struct sk_buff *skb) __net_timestamp(SKB); \ } \ -static int net_hwtstamp_validate(struct ifreq *ifr) -{ - struct hwtstamp_config cfg; - enum hwtstamp_tx_types tx_type; - enum hwtstamp_rx_filters rx_filter; - int tx_type_valid = 0; - int rx_filter_valid = 0; - - if (copy_from_user(&cfg, ifr->ifr_data, sizeof(cfg))) - return -EFAULT; - - if (cfg.flags) /* reserved for future extensions */ - return -EINVAL; - - tx_type = cfg.tx_type; - rx_filter = cfg.rx_filter; - - switch (tx_type) { - case HWTSTAMP_TX_OFF: - case HWTSTAMP_TX_ON: - case HWTSTAMP_TX_ONESTEP_SYNC: - tx_type_valid = 1; - break; - } - - switch (rx_filter) { - case HWTSTAMP_FILTER_NONE: - case HWTSTAMP_FILTER_ALL: - case HWTSTAMP_FILTER_SOME: - case HWTSTAMP_FILTER_PTP_V1_L4_EVENT: - case HWTSTAMP_FILTER_PTP_V1_L4_SYNC: - case HWTSTAMP_FILTER_PTP_V1_L4_DELAY_REQ: - case HWTSTAMP_FILTER_PTP_V2_L4_EVENT: - case HWTSTAMP_FILTER_PTP_V2_L4_SYNC: - case HWTSTAMP_FILTER_PTP_V2_L4_DELAY_REQ: - case HWTSTAMP_FILTER_PTP_V2_L2_EVENT: - case HWTSTAMP_FILTER_PTP_V2_L2_SYNC: - case HWTSTAMP_FILTER_PTP_V2_L2_DELAY_REQ: - case HWTSTAMP_FILTER_PTP_V2_EVENT: - case HWTSTAMP_FILTER_PTP_V2_SYNC: - case HWTSTAMP_FILTER_PTP_V2_DELAY_REQ: - rx_filter_valid = 1; - break; - } - - if (!tx_type_valid || !rx_filter_valid) - return -ERANGE; - - return 0; -} - static inline bool is_skb_forwardable(struct net_device *dev, struct sk_buff *skb) { @@ -1857,6 +1798,228 @@ static void netif_setup_tc(struct net_device *dev, unsigned int txq) } } +#ifdef CONFIG_XPS +static DEFINE_MUTEX(xps_map_mutex); +#define xmap_dereference(P) \ + rcu_dereference_protected((P), lockdep_is_held(&xps_map_mutex)) + +static struct xps_map *remove_xps_queue(struct xps_dev_maps *dev_maps, + int cpu, u16 index) +{ + struct xps_map *map = NULL; + int pos; + + if (dev_maps) + map = xmap_dereference(dev_maps->cpu_map[cpu]); + + for (pos = 0; map && pos < map->len; pos++) { + if (map->queues[pos] == index) { + if (map->len > 1) { + map->queues[pos] = map->queues[--map->len]; + } else { + RCU_INIT_POINTER(dev_maps->cpu_map[cpu], NULL); + kfree_rcu(map, rcu); + map = NULL; + } + break; + } + } + + return map; +} + +static void netif_reset_xps_queues_gt(struct net_device *dev, u16 index) +{ + struct xps_dev_maps *dev_maps; + int cpu, i; + bool active = false; + + mutex_lock(&xps_map_mutex); + dev_maps = xmap_dereference(dev->xps_maps); + + if (!dev_maps) + goto out_no_maps; + + for_each_possible_cpu(cpu) { + for (i = index; i < dev->num_tx_queues; i++) { + if (!remove_xps_queue(dev_maps, cpu, i)) + break; + } + if (i == dev->num_tx_queues) + active = true; + } + + if (!active) { + RCU_INIT_POINTER(dev->xps_maps, NULL); + kfree_rcu(dev_maps, rcu); + } + + for (i = index; i < dev->num_tx_queues; i++) + netdev_queue_numa_node_write(netdev_get_tx_queue(dev, i), + NUMA_NO_NODE); + +out_no_maps: + mutex_unlock(&xps_map_mutex); +} + +static struct xps_map *expand_xps_map(struct xps_map *map, + int cpu, u16 index) +{ + struct xps_map *new_map; + int alloc_len = XPS_MIN_MAP_ALLOC; + int i, pos; + + for (pos = 0; map && pos < map->len; pos++) { + if (map->queues[pos] != index) + continue; + return map; + } + + /* Need to add queue to this CPU's existing map */ + if (map) { + if (pos < map->alloc_len) + return map; + + alloc_len = map->alloc_len * 2; + } + + /* Need to allocate new map to store queue on this CPU's map */ + new_map = kzalloc_node(XPS_MAP_SIZE(alloc_len), GFP_KERNEL, + cpu_to_node(cpu)); + if (!new_map) + return NULL; + + for (i = 0; i < pos; i++) + new_map->queues[i] = map->queues[i]; + new_map->alloc_len = alloc_len; + new_map->len = pos; + + return new_map; +} + +int netif_set_xps_queue(struct net_device *dev, struct cpumask *mask, u16 index) +{ + struct xps_dev_maps *dev_maps, *new_dev_maps = NULL; + struct xps_map *map, *new_map; + int maps_sz = max_t(unsigned int, XPS_DEV_MAPS_SIZE, L1_CACHE_BYTES); + int cpu, numa_node_id = -2; + bool active = false; + + mutex_lock(&xps_map_mutex); + + dev_maps = xmap_dereference(dev->xps_maps); + + /* allocate memory for queue storage */ + for_each_online_cpu(cpu) { + if (!cpumask_test_cpu(cpu, mask)) + continue; + + if (!new_dev_maps) + new_dev_maps = kzalloc(maps_sz, GFP_KERNEL); + if (!new_dev_maps) + return -ENOMEM; + + map = dev_maps ? xmap_dereference(dev_maps->cpu_map[cpu]) : + NULL; + + map = expand_xps_map(map, cpu, index); + if (!map) + goto error; + + RCU_INIT_POINTER(new_dev_maps->cpu_map[cpu], map); + } + + if (!new_dev_maps) + goto out_no_new_maps; + + for_each_possible_cpu(cpu) { + if (cpumask_test_cpu(cpu, mask) && cpu_online(cpu)) { + /* add queue to CPU maps */ + int pos = 0; + + map = xmap_dereference(new_dev_maps->cpu_map[cpu]); + while ((pos < map->len) && (map->queues[pos] != index)) + pos++; + + if (pos == map->len) + map->queues[map->len++] = index; +#ifdef CONFIG_NUMA + if (numa_node_id == -2) + numa_node_id = cpu_to_node(cpu); + else if (numa_node_id != cpu_to_node(cpu)) + numa_node_id = -1; +#endif + } else if (dev_maps) { + /* fill in the new device map from the old device map */ + map = xmap_dereference(dev_maps->cpu_map[cpu]); + RCU_INIT_POINTER(new_dev_maps->cpu_map[cpu], map); + } + + } + + rcu_assign_pointer(dev->xps_maps, new_dev_maps); + + /* Cleanup old maps */ + if (dev_maps) { + for_each_possible_cpu(cpu) { + new_map = xmap_dereference(new_dev_maps->cpu_map[cpu]); + map = xmap_dereference(dev_maps->cpu_map[cpu]); + if (map && map != new_map) + kfree_rcu(map, rcu); + } + + kfree_rcu(dev_maps, rcu); + } + + dev_maps = new_dev_maps; + active = true; + +out_no_new_maps: + /* update Tx queue numa node */ + netdev_queue_numa_node_write(netdev_get_tx_queue(dev, index), + (numa_node_id >= 0) ? numa_node_id : + NUMA_NO_NODE); + + if (!dev_maps) + goto out_no_maps; + + /* removes queue from unused CPUs */ + for_each_possible_cpu(cpu) { + if (cpumask_test_cpu(cpu, mask) && cpu_online(cpu)) + continue; + + if (remove_xps_queue(dev_maps, cpu, index)) + active = true; + } + + /* free map if not active */ + if (!active) { + RCU_INIT_POINTER(dev->xps_maps, NULL); + kfree_rcu(dev_maps, rcu); + } + +out_no_maps: + mutex_unlock(&xps_map_mutex); + + return 0; +error: + /* remove any maps that we added */ + for_each_possible_cpu(cpu) { + new_map = xmap_dereference(new_dev_maps->cpu_map[cpu]); + map = dev_maps ? xmap_dereference(dev_maps->cpu_map[cpu]) : + NULL; + if (new_map && new_map != map) + kfree(new_map); + } + + mutex_unlock(&xps_map_mutex); + + kfree(new_dev_maps); + return -ENOMEM; +} +EXPORT_SYMBOL(netif_set_xps_queue); + +#endif /* * Routine to help set real_num_tx_queues. To avoid skbs mapped to queues * greater then real_num_tx_queues stale skbs on the qdisc must be flushed. @@ -1880,8 +2043,12 @@ int netif_set_real_num_tx_queues(struct net_device *dev, unsigned int txq) if (dev->num_tc) netif_setup_tc(dev, txq); - if (txq < dev->real_num_tx_queues) + if (txq < dev->real_num_tx_queues) { qdisc_reset_all_tx_gt(dev, txq); +#ifdef CONFIG_XPS + netif_reset_xps_queues_gt(dev, txq); +#endif + } } dev->real_num_tx_queues = txq; @@ -2046,6 +2213,15 @@ int skb_checksum_help(struct sk_buff *skb) return -EINVAL; } + /* Before computing a checksum, we should make sure no frag could + * be modified by an external entity : checksum could be wrong. + */ + if (skb_has_shared_frag(skb)) { + ret = __skb_linearize(skb); + if (ret) + goto out; + } + offset = skb_checksum_start_offset(skb); BUG_ON(offset >= skb_headlen(skb)); csum = skb_checksum(skb, offset, skb->len - offset, 0); @@ -2069,25 +2245,19 @@ out: EXPORT_SYMBOL(skb_checksum_help); /** - * skb_gso_segment - Perform segmentation on skb. + * skb_mac_gso_segment - mac layer segmentation handler. * @skb: buffer to segment * @features: features for the output path (see dev->features) - * - * This function segments the given skb and returns a list of segments. - * - * It may return NULL if the skb requires no segmentation. This is - * only possible when GSO is used for verifying header integrity. */ -struct sk_buff *skb_gso_segment(struct sk_buff *skb, - netdev_features_t features) +struct sk_buff *skb_mac_gso_segment(struct sk_buff *skb, + netdev_features_t features) { struct sk_buff *segs = ERR_PTR(-EPROTONOSUPPORT); struct packet_offload *ptype; __be16 type = skb->protocol; - int vlan_depth = ETH_HLEN; - int err; while (type == htons(ETH_P_8021Q)) { + int vlan_depth = ETH_HLEN; struct vlan_hdr *vh; if (unlikely(!pskb_may_pull(skb, vlan_depth + VLAN_HLEN))) @@ -2098,22 +2268,14 @@ struct sk_buff *skb_gso_segment(struct sk_buff *skb, vlan_depth += VLAN_HLEN; } - skb_reset_mac_header(skb); - skb->mac_len = skb->network_header - skb->mac_header; __skb_pull(skb, skb->mac_len); - if (unlikely(skb->ip_summed != CHECKSUM_PARTIAL)) { - skb_warn_bad_offload(skb); - - if (skb_header_cloned(skb) && - (err = pskb_expand_head(skb, 0, 0, GFP_ATOMIC))) - return ERR_PTR(err); - } - rcu_read_lock(); list_for_each_entry_rcu(ptype, &offload_base, list) { if (ptype->type == type && ptype->callbacks.gso_segment) { if (unlikely(skb->ip_summed != CHECKSUM_PARTIAL)) { + int err; + err = ptype->callbacks.gso_send_check(skb); segs = ERR_PTR(err); if (err || skb_gso_ok(skb, features)) @@ -2131,7 +2293,50 @@ struct sk_buff *skb_gso_segment(struct sk_buff *skb, return segs; } -EXPORT_SYMBOL(skb_gso_segment); +EXPORT_SYMBOL(skb_mac_gso_segment); + + +/* openvswitch calls this on rx path, so we need a different check. + */ +static inline bool skb_needs_check(struct sk_buff *skb, bool tx_path) +{ + if (tx_path) + return skb->ip_summed != CHECKSUM_PARTIAL; + else + return skb->ip_summed == CHECKSUM_NONE; +} + +/** + * __skb_gso_segment - Perform segmentation on skb. + * @skb: buffer to segment + * @features: features for the output path (see dev->features) + * @tx_path: whether it is called in TX path + * + * This function segments the given skb and returns a list of segments. + * + * It may return NULL if the skb requires no segmentation. This is + * only possible when GSO is used for verifying header integrity. + */ +struct sk_buff *__skb_gso_segment(struct sk_buff *skb, + netdev_features_t features, bool tx_path) +{ + if (unlikely(skb_needs_check(skb, tx_path))) { + int err; + + skb_warn_bad_offload(skb); + + if (skb_header_cloned(skb) && + (err = pskb_expand_head(skb, 0, 0, GFP_ATOMIC))) + return ERR_PTR(err); + } + + SKB_GSO_CB(skb)->mac_offset = skb_headroom(skb); + skb_reset_mac_header(skb); + skb_reset_mac_len(skb); + + return skb_mac_gso_segment(skb, features); +} +EXPORT_SYMBOL(__skb_gso_segment); /* Take action when hardware reception checksum errors are detected. */ #ifdef CONFIG_BUG @@ -2410,126 +2615,28 @@ out: return rc; } -static u32 hashrnd __read_mostly; - -/* - * Returns a Tx hash based on the given packet descriptor a Tx queues' number - * to be used as a distribution range. - */ -u16 __skb_tx_hash(const struct net_device *dev, const struct sk_buff *skb, - unsigned int num_tx_queues) +static void qdisc_pkt_len_init(struct sk_buff *skb) { - u32 hash; - u16 qoffset = 0; - u16 qcount = num_tx_queues; - - if (skb_rx_queue_recorded(skb)) { - hash = skb_get_rx_queue(skb); - while (unlikely(hash >= num_tx_queues)) - hash -= num_tx_queues; - return hash; - } - - if (dev->num_tc) { - u8 tc = netdev_get_prio_tc_map(dev, skb->priority); - qoffset = dev->tc_to_txq[tc].offset; - qcount = dev->tc_to_txq[tc].count; - } - - if (skb->sk && skb->sk->sk_hash) - hash = skb->sk->sk_hash; - else - hash = (__force u16) skb->protocol; - hash = jhash_1word(hash, hashrnd); + const struct skb_shared_info *shinfo = skb_shinfo(skb); - return (u16) (((u64) hash * qcount) >> 32) + qoffset; -} -EXPORT_SYMBOL(__skb_tx_hash); - -static inline u16 dev_cap_txqueue(struct net_device *dev, u16 queue_index) -{ - if (unlikely(queue_index >= dev->real_num_tx_queues)) { - net_warn_ratelimited("%s selects TX queue %d, but real number of TX queues is %d\n", - dev->name, queue_index, - dev->real_num_tx_queues); - return 0; - } - return queue_index; -} - -static inline int get_xps_queue(struct net_device *dev, struct sk_buff *skb) -{ -#ifdef CONFIG_XPS - struct xps_dev_maps *dev_maps; - struct xps_map *map; - int queue_index = -1; - - rcu_read_lock(); - dev_maps = rcu_dereference(dev->xps_maps); - if (dev_maps) { - map = rcu_dereference( - dev_maps->cpu_map[raw_smp_processor_id()]); - if (map) { - if (map->len == 1) - queue_index = map->queues[0]; - else { - u32 hash; - if (skb->sk && skb->sk->sk_hash) - hash = skb->sk->sk_hash; - else - hash = (__force u16) skb->protocol ^ - skb->rxhash; - hash = jhash_1word(hash, hashrnd); - queue_index = map->queues[ - ((u64)hash * map->len) >> 32]; - } - if (unlikely(queue_index >= dev->real_num_tx_queues)) - queue_index = -1; - } - } - rcu_read_unlock(); - - return queue_index; -#else - return -1; -#endif -} - -struct netdev_queue *netdev_pick_tx(struct net_device *dev, - struct sk_buff *skb) -{ - int queue_index; - const struct net_device_ops *ops = dev->netdev_ops; - - if (dev->real_num_tx_queues == 1) - queue_index = 0; - else if (ops->ndo_select_queue) { - queue_index = ops->ndo_select_queue(dev, skb); - queue_index = dev_cap_txqueue(dev, queue_index); - } else { - struct sock *sk = skb->sk; - queue_index = sk_tx_queue_get(sk); - - if (queue_index < 0 || skb->ooo_okay || - queue_index >= dev->real_num_tx_queues) { - int old_index = queue_index; + qdisc_skb_cb(skb)->pkt_len = skb->len; - queue_index = get_xps_queue(dev, skb); - if (queue_index < 0) - queue_index = skb_tx_hash(dev, skb); + /* To get more precise estimation of bytes sent on wire, + * we add to pkt_len the headers size of all segments + */ + if (shinfo->gso_size) { + unsigned int hdr_len; - if (queue_index != old_index && sk) { - struct dst_entry *dst = - rcu_dereference_check(sk->sk_dst_cache, 1); + /* mac layer + network layer */ + hdr_len = skb_transport_header(skb) - skb_mac_header(skb); - if (dst && skb_dst(skb) == dst) - sk_tx_queue_set(sk, queue_index); - } - } + /* + transport layer */ + if (likely(shinfo->gso_type & (SKB_GSO_TCPV4 | SKB_GSO_TCPV6))) + hdr_len += tcp_hdrlen(skb); + else + hdr_len += sizeof(struct udphdr); + qdisc_skb_cb(skb)->pkt_len += (shinfo->gso_segs - 1) * hdr_len; } - - skb_set_queue_mapping(skb, queue_index); - return netdev_get_tx_queue(dev, queue_index); } static inline int __dev_xmit_skb(struct sk_buff *skb, struct Qdisc *q, @@ -2540,7 +2647,7 @@ static inline int __dev_xmit_skb(struct sk_buff *skb, struct Qdisc *q, bool contended; int rc; - qdisc_skb_cb(skb)->pkt_len = skb->len; + qdisc_pkt_len_init(skb); qdisc_calculate_pkt_len(skb, q); /* * Heuristic to force contended enqueues to serialize on a @@ -2663,6 +2770,8 @@ int dev_queue_xmit(struct sk_buff *skb) struct Qdisc *q; int rc = -ENOMEM; + skb_reset_mac_header(skb); + /* Disable soft irqs for various locks below. Also * stops preemption for RCU. */ @@ -2757,41 +2866,6 @@ static inline void ____napi_schedule(struct softnet_data *sd, __raise_softirq_irqoff(NET_RX_SOFTIRQ); } -/* - * __skb_get_rxhash: calculate a flow hash based on src/dst addresses - * and src/dst port numbers. Sets rxhash in skb to non-zero hash value - * on success, zero indicates no valid hash. Also, sets l4_rxhash in skb - * if hash is a canonical 4-tuple hash over transport ports. - */ -void __skb_get_rxhash(struct sk_buff *skb) -{ - struct flow_keys keys; - u32 hash; - - if (!skb_flow_dissect(skb, &keys)) - return; - - if (keys.ports) - skb->l4_rxhash = 1; - - /* get a consistent hash (same value on both flow directions) */ - if (((__force u32)keys.dst < (__force u32)keys.src) || - (((__force u32)keys.dst == (__force u32)keys.src) && - ((__force u16)keys.port16[1] < (__force u16)keys.port16[0]))) { - swap(keys.dst, keys.src); - swap(keys.port16[0], keys.port16[1]); - } - - hash = jhash_3words((__force u32)keys.dst, - (__force u32)keys.src, - (__force u32)keys.ports, hashrnd); - if (!hash) - hash = 1; - - skb->rxhash = hash; -} -EXPORT_SYMBOL(__skb_get_rxhash); - #ifdef CONFIG_RPS /* One global table that all flow-based protocols share. */ @@ -3318,7 +3392,7 @@ static bool skb_pfmemalloc_protocol(struct sk_buff *skb) } } -static int __netif_receive_skb(struct sk_buff *skb) +static int __netif_receive_skb_core(struct sk_buff *skb, bool pfmemalloc) { struct packet_type *ptype, *pt_prev; rx_handler_func_t *rx_handler; @@ -3327,24 +3401,11 @@ static int __netif_receive_skb(struct sk_buff *skb) bool deliver_exact = false; int ret = NET_RX_DROP; __be16 type; - unsigned long pflags = current->flags; net_timestamp_check(!netdev_tstamp_prequeue, skb); trace_netif_receive_skb(skb); - /* - * PFMEMALLOC skbs are special, they should - * - be delivered to SOCK_MEMALLOC sockets only - * - stay away from userspace - * - have bounded memory usage - * - * Use PF_MEMALLOC as this saves us from propagating the allocation - * context down to all allocation sites. - */ - if (sk_memalloc_socks() && skb_pfmemalloc(skb)) - current->flags |= PF_MEMALLOC; - /* if we've gotten here through NAPI, check netpoll */ if (netpoll_receive_skb(skb)) goto out; @@ -3352,7 +3413,8 @@ static int __netif_receive_skb(struct sk_buff *skb) orig_dev = skb->dev; skb_reset_network_header(skb); - skb_reset_transport_header(skb); + if (!skb_transport_header_was_set(skb)) + skb_reset_transport_header(skb); skb_reset_mac_len(skb); pt_prev = NULL; @@ -3377,7 +3439,7 @@ another_round: } #endif - if (sk_memalloc_socks() && skb_pfmemalloc(skb)) + if (pfmemalloc) goto skip_taps; list_for_each_entry_rcu(ptype, &ptype_all, list) { @@ -3396,8 +3458,7 @@ skip_taps: ncls: #endif - if (sk_memalloc_socks() && skb_pfmemalloc(skb) - && !skb_pfmemalloc_protocol(skb)) + if (pfmemalloc && !skb_pfmemalloc_protocol(skb)) goto drop; if (vlan_tx_tag_present(skb)) { @@ -3467,7 +3528,31 @@ drop: unlock: rcu_read_unlock(); out: - tsk_restore_flags(current, pflags, PF_MEMALLOC); + return ret; +} + +static int __netif_receive_skb(struct sk_buff *skb) +{ + int ret; + + if (sk_memalloc_socks() && skb_pfmemalloc(skb)) { + unsigned long pflags = current->flags; + + /* + * PFMEMALLOC skbs are special, they should + * - be delivered to SOCK_MEMALLOC sockets only + * - stay away from userspace + * - have bounded memory usage + * + * Use PF_MEMALLOC as this saves us from propagating the allocation + * context down to all allocation sites. + */ + current->flags |= PF_MEMALLOC; + ret = __netif_receive_skb_core(skb, true); + tsk_restore_flags(current, pflags, PF_MEMALLOC); + } else + ret = __netif_receive_skb_core(skb, false); + return ret; } @@ -3634,7 +3719,6 @@ static enum gro_result dev_gro_receive(struct napi_struct *napi, struct sk_buff __be16 type = skb->protocol; struct list_head *head = &offload_base; int same_flow; - int mac_len; enum gro_result ret; if (!(skb->dev->features & NETIF_F_GRO) || netpoll_rx_on(skb)) @@ -3651,8 +3735,7 @@ static enum gro_result dev_gro_receive(struct napi_struct *napi, struct sk_buff continue; skb_set_network_header(skb, skb_gro_offset(skb)); - mac_len = skb->network_header - skb->mac_header; - skb->mac_len = mac_len; + skb_reset_mac_len(skb); NAPI_GRO_CB(skb)->same_flow = 0; NAPI_GRO_CB(skb)->flush = 0; NAPI_GRO_CB(skb)->free = 0; @@ -4134,127 +4217,6 @@ softnet_break: goto out; } -static gifconf_func_t *gifconf_list[NPROTO]; - -/** - * register_gifconf - register a SIOCGIF handler - * @family: Address family - * @gifconf: Function handler - * - * Register protocol dependent address dumping routines. The handler - * that is passed must not be freed or reused until it has been replaced - * by another handler. - */ -int register_gifconf(unsigned int family, gifconf_func_t *gifconf) -{ - if (family >= NPROTO) - return -EINVAL; - gifconf_list[family] = gifconf; - return 0; -} -EXPORT_SYMBOL(register_gifconf); - - -/* - * Map an interface index to its name (SIOCGIFNAME) - */ - -/* - * We need this ioctl for efficient implementation of the - * if_indextoname() function required by the IPv6 API. Without - * it, we would have to search all the interfaces to find a - * match. --pb - */ - -static int dev_ifname(struct net *net, struct ifreq __user *arg) -{ - struct net_device *dev; - struct ifreq ifr; - unsigned seq; - - /* - * Fetch the caller's info block. - */ - - if (copy_from_user(&ifr, arg, sizeof(struct ifreq))) - return -EFAULT; - -retry: - seq = read_seqbegin(&devnet_rename_seq); - rcu_read_lock(); - dev = dev_get_by_index_rcu(net, ifr.ifr_ifindex); - if (!dev) { - rcu_read_unlock(); - return -ENODEV; - } - - strcpy(ifr.ifr_name, dev->name); - rcu_read_unlock(); - if (read_seqretry(&devnet_rename_seq, seq)) - goto retry; - - if (copy_to_user(arg, &ifr, sizeof(struct ifreq))) - return -EFAULT; - return 0; -} - -/* - * Perform a SIOCGIFCONF call. This structure will change - * size eventually, and there is nothing I can do about it. - * Thus we will need a 'compatibility mode'. - */ - -static int dev_ifconf(struct net *net, char __user *arg) -{ - struct ifconf ifc; - struct net_device *dev; - char __user *pos; - int len; - int total; - int i; - - /* - * Fetch the caller's info block. - */ - - if (copy_from_user(&ifc, arg, sizeof(struct ifconf))) - return -EFAULT; - - pos = ifc.ifc_buf; - len = ifc.ifc_len; - - /* - * Loop over the interfaces, and write an info block for each. - */ - - total = 0; - for_each_netdev(net, dev) { - for (i = 0; i < NPROTO; i++) { - if (gifconf_list[i]) { - int done; - if (!pos) - done = gifconf_list[i](dev, NULL, 0); - else - done = gifconf_list[i](dev, pos + total, - len - total); - if (done < 0) - return -EFAULT; - total += done; - } - } - } - - /* - * All done. Write the updated control block back to the caller. - */ - ifc.ifc_len = total; - - /* - * Both BSD and Solaris return 0 here, so we do too. - */ - return copy_to_user(arg, &ifc, sizeof(struct ifconf)) ? -EFAULT : 0; -} - #ifdef CONFIG_PROC_FS #define BUCKET_SPACE (32 - NETDEV_HASHBITS - 1) @@ -4600,64 +4562,231 @@ static int __init dev_proc_init(void) #endif /* CONFIG_PROC_FS */ +struct netdev_upper { + struct net_device *dev; + bool master; + struct list_head list; + struct rcu_head rcu; + struct list_head search_list; +}; + +static void __append_search_uppers(struct list_head *search_list, + struct net_device *dev) +{ + struct netdev_upper *upper; + + list_for_each_entry(upper, &dev->upper_dev_list, list) { + /* check if this upper is not already in search list */ + if (list_empty(&upper->search_list)) + list_add_tail(&upper->search_list, search_list); + } +} + +static bool __netdev_search_upper_dev(struct net_device *dev, + struct net_device *upper_dev) +{ + LIST_HEAD(search_list); + struct netdev_upper *upper; + struct netdev_upper *tmp; + bool ret = false; + + __append_search_uppers(&search_list, dev); + list_for_each_entry(upper, &search_list, search_list) { + if (upper->dev == upper_dev) { + ret = true; + break; + } + __append_search_uppers(&search_list, upper->dev); + } + list_for_each_entry_safe(upper, tmp, &search_list, search_list) + INIT_LIST_HEAD(&upper->search_list); + return ret; +} + +static struct netdev_upper *__netdev_find_upper(struct net_device *dev, + struct net_device *upper_dev) +{ + struct netdev_upper *upper; + + list_for_each_entry(upper, &dev->upper_dev_list, list) { + if (upper->dev == upper_dev) + return upper; + } + return NULL; +} + /** - * netdev_set_master - set up master pointer - * @slave: slave device - * @master: new master device + * netdev_has_upper_dev - Check if device is linked to an upper device + * @dev: device + * @upper_dev: upper device to check * - * Changes the master device of the slave. Pass %NULL to break the - * bonding. The caller must hold the RTNL semaphore. On a failure - * a negative errno code is returned. On success the reference counts - * are adjusted and the function returns zero. + * Find out if a device is linked to specified upper device and return true + * in case it is. Note that this checks only immediate upper device, + * not through a complete stack of devices. The caller must hold the RTNL lock. */ -int netdev_set_master(struct net_device *slave, struct net_device *master) +bool netdev_has_upper_dev(struct net_device *dev, + struct net_device *upper_dev) { - struct net_device *old = slave->master; + ASSERT_RTNL(); + return __netdev_find_upper(dev, upper_dev); +} +EXPORT_SYMBOL(netdev_has_upper_dev); + +/** + * netdev_has_any_upper_dev - Check if device is linked to some device + * @dev: device + * + * Find out if a device is linked to an upper device and return true in case + * it is. The caller must hold the RTNL lock. + */ +bool netdev_has_any_upper_dev(struct net_device *dev) +{ ASSERT_RTNL(); - if (master) { - if (old) - return -EBUSY; - dev_hold(master); - } + return !list_empty(&dev->upper_dev_list); +} +EXPORT_SYMBOL(netdev_has_any_upper_dev); - slave->master = master; +/** + * netdev_master_upper_dev_get - Get master upper device + * @dev: device + * + * Find a master upper device and return pointer to it or NULL in case + * it's not there. The caller must hold the RTNL lock. + */ +struct net_device *netdev_master_upper_dev_get(struct net_device *dev) +{ + struct netdev_upper *upper; - if (old) - dev_put(old); - return 0; + ASSERT_RTNL(); + + if (list_empty(&dev->upper_dev_list)) + return NULL; + + upper = list_first_entry(&dev->upper_dev_list, + struct netdev_upper, list); + if (likely(upper->master)) + return upper->dev; + return NULL; } -EXPORT_SYMBOL(netdev_set_master); +EXPORT_SYMBOL(netdev_master_upper_dev_get); /** - * netdev_set_bond_master - set up bonding master/slave pair - * @slave: slave device - * @master: new master device + * netdev_master_upper_dev_get_rcu - Get master upper device + * @dev: device * - * Changes the master device of the slave. Pass %NULL to break the - * bonding. The caller must hold the RTNL semaphore. On a failure - * a negative errno code is returned. On success %RTM_NEWLINK is sent - * to the routing socket and the function returns zero. + * Find a master upper device and return pointer to it or NULL in case + * it's not there. The caller must hold the RCU read lock. */ -int netdev_set_bond_master(struct net_device *slave, struct net_device *master) +struct net_device *netdev_master_upper_dev_get_rcu(struct net_device *dev) { - int err; + struct netdev_upper *upper; + + upper = list_first_or_null_rcu(&dev->upper_dev_list, + struct netdev_upper, list); + if (upper && likely(upper->master)) + return upper->dev; + return NULL; +} +EXPORT_SYMBOL(netdev_master_upper_dev_get_rcu); + +static int __netdev_upper_dev_link(struct net_device *dev, + struct net_device *upper_dev, bool master) +{ + struct netdev_upper *upper; ASSERT_RTNL(); - err = netdev_set_master(slave, master); - if (err) - return err; + if (dev == upper_dev) + return -EBUSY; + + /* To prevent loops, check if dev is not upper device to upper_dev. */ + if (__netdev_search_upper_dev(upper_dev, dev)) + return -EBUSY; + + if (__netdev_find_upper(dev, upper_dev)) + return -EEXIST; + + if (master && netdev_master_upper_dev_get(dev)) + return -EBUSY; + + upper = kmalloc(sizeof(*upper), GFP_KERNEL); + if (!upper) + return -ENOMEM; + + upper->dev = upper_dev; + upper->master = master; + INIT_LIST_HEAD(&upper->search_list); + + /* Ensure that master upper link is always the first item in list. */ if (master) - slave->flags |= IFF_SLAVE; + list_add_rcu(&upper->list, &dev->upper_dev_list); else - slave->flags &= ~IFF_SLAVE; + list_add_tail_rcu(&upper->list, &dev->upper_dev_list); + dev_hold(upper_dev); - rtmsg_ifinfo(RTM_NEWLINK, slave, IFF_SLAVE); return 0; } -EXPORT_SYMBOL(netdev_set_bond_master); + +/** + * netdev_upper_dev_link - Add a link to the upper device + * @dev: device + * @upper_dev: new upper device + * + * Adds a link to device which is upper to this one. The caller must hold + * the RTNL lock. On a failure a negative errno code is returned. + * On success the reference counts are adjusted and the function + * returns zero. + */ +int netdev_upper_dev_link(struct net_device *dev, + struct net_device *upper_dev) +{ + return __netdev_upper_dev_link(dev, upper_dev, false); +} +EXPORT_SYMBOL(netdev_upper_dev_link); + +/** + * netdev_master_upper_dev_link - Add a master link to the upper device + * @dev: device + * @upper_dev: new upper device + * + * Adds a link to device which is upper to this one. In this case, only + * one master upper device can be linked, although other non-master devices + * might be linked as well. The caller must hold the RTNL lock. + * On a failure a negative errno code is returned. On success the reference + * counts are adjusted and the function returns zero. + */ +int netdev_master_upper_dev_link(struct net_device *dev, + struct net_device *upper_dev) +{ + return __netdev_upper_dev_link(dev, upper_dev, true); +} +EXPORT_SYMBOL(netdev_master_upper_dev_link); + +/** + * netdev_upper_dev_unlink - Removes a link to upper device + * @dev: device + * @upper_dev: new upper device + * + * Removes a link to device which is upper to this one. The caller must hold + * the RTNL lock. + */ +void netdev_upper_dev_unlink(struct net_device *dev, + struct net_device *upper_dev) +{ + struct netdev_upper *upper; + + ASSERT_RTNL(); + + upper = __netdev_find_upper(dev, upper_dev); + if (!upper) + return; + list_del_rcu(&upper->list); + dev_put(upper_dev); + kfree_rcu(upper, rcu); +} +EXPORT_SYMBOL(netdev_upper_dev_unlink); static void dev_change_rx_flags(struct net_device *dev, int flags) { @@ -5020,381 +5149,33 @@ int dev_set_mac_address(struct net_device *dev, struct sockaddr *sa) if (!netif_device_present(dev)) return -ENODEV; err = ops->ndo_set_mac_address(dev, sa); - if (!err) - call_netdevice_notifiers(NETDEV_CHANGEADDR, dev); + if (err) + return err; + dev->addr_assign_type = NET_ADDR_SET; + call_netdevice_notifiers(NETDEV_CHANGEADDR, dev); add_device_randomness(dev->dev_addr, dev->addr_len); - return err; + return 0; } EXPORT_SYMBOL(dev_set_mac_address); -/* - * Perform the SIOCxIFxxx calls, inside rcu_read_lock() - */ -static int dev_ifsioc_locked(struct net *net, struct ifreq *ifr, unsigned int cmd) -{ - int err; - struct net_device *dev = dev_get_by_name_rcu(net, ifr->ifr_name); - - if (!dev) - return -ENODEV; - - switch (cmd) { - case SIOCGIFFLAGS: /* Get interface flags */ - ifr->ifr_flags = (short) dev_get_flags(dev); - return 0; - - case SIOCGIFMETRIC: /* Get the metric on the interface - (currently unused) */ - ifr->ifr_metric = 0; - return 0; - - case SIOCGIFMTU: /* Get the MTU of a device */ - ifr->ifr_mtu = dev->mtu; - return 0; - - case SIOCGIFHWADDR: - if (!dev->addr_len) - memset(ifr->ifr_hwaddr.sa_data, 0, sizeof ifr->ifr_hwaddr.sa_data); - else - memcpy(ifr->ifr_hwaddr.sa_data, dev->dev_addr, - min(sizeof ifr->ifr_hwaddr.sa_data, (size_t) dev->addr_len)); - ifr->ifr_hwaddr.sa_family = dev->type; - return 0; - - case SIOCGIFSLAVE: - err = -EINVAL; - break; - - case SIOCGIFMAP: - ifr->ifr_map.mem_start = dev->mem_start; - ifr->ifr_map.mem_end = dev->mem_end; - ifr->ifr_map.base_addr = dev->base_addr; - ifr->ifr_map.irq = dev->irq; - ifr->ifr_map.dma = dev->dma; - ifr->ifr_map.port = dev->if_port; - return 0; - - case SIOCGIFINDEX: - ifr->ifr_ifindex = dev->ifindex; - return 0; - - case SIOCGIFTXQLEN: - ifr->ifr_qlen = dev->tx_queue_len; - return 0; - - default: - /* dev_ioctl() should ensure this case - * is never reached - */ - WARN_ON(1); - err = -ENOTTY; - break; - - } - return err; -} - -/* - * Perform the SIOCxIFxxx calls, inside rtnl_lock() - */ -static int dev_ifsioc(struct net *net, struct ifreq *ifr, unsigned int cmd) -{ - int err; - struct net_device *dev = __dev_get_by_name(net, ifr->ifr_name); - const struct net_device_ops *ops; - - if (!dev) - return -ENODEV; - - ops = dev->netdev_ops; - - switch (cmd) { - case SIOCSIFFLAGS: /* Set interface flags */ - return dev_change_flags(dev, ifr->ifr_flags); - - case SIOCSIFMETRIC: /* Set the metric on the interface - (currently unused) */ - return -EOPNOTSUPP; - - case SIOCSIFMTU: /* Set the MTU of a device */ - return dev_set_mtu(dev, ifr->ifr_mtu); - - case SIOCSIFHWADDR: - return dev_set_mac_address(dev, &ifr->ifr_hwaddr); - - case SIOCSIFHWBROADCAST: - if (ifr->ifr_hwaddr.sa_family != dev->type) - return -EINVAL; - memcpy(dev->broadcast, ifr->ifr_hwaddr.sa_data, - min(sizeof ifr->ifr_hwaddr.sa_data, (size_t) dev->addr_len)); - call_netdevice_notifiers(NETDEV_CHANGEADDR, dev); - return 0; - - case SIOCSIFMAP: - if (ops->ndo_set_config) { - if (!netif_device_present(dev)) - return -ENODEV; - return ops->ndo_set_config(dev, &ifr->ifr_map); - } - return -EOPNOTSUPP; - - case SIOCADDMULTI: - if (!ops->ndo_set_rx_mode || - ifr->ifr_hwaddr.sa_family != AF_UNSPEC) - return -EINVAL; - if (!netif_device_present(dev)) - return -ENODEV; - return dev_mc_add_global(dev, ifr->ifr_hwaddr.sa_data); - - case SIOCDELMULTI: - if (!ops->ndo_set_rx_mode || - ifr->ifr_hwaddr.sa_family != AF_UNSPEC) - return -EINVAL; - if (!netif_device_present(dev)) - return -ENODEV; - return dev_mc_del_global(dev, ifr->ifr_hwaddr.sa_data); - - case SIOCSIFTXQLEN: - if (ifr->ifr_qlen < 0) - return -EINVAL; - dev->tx_queue_len = ifr->ifr_qlen; - return 0; - - case SIOCSIFNAME: - ifr->ifr_newname[IFNAMSIZ-1] = '\0'; - return dev_change_name(dev, ifr->ifr_newname); - - case SIOCSHWTSTAMP: - err = net_hwtstamp_validate(ifr); - if (err) - return err; - /* fall through */ - - /* - * Unknown or private ioctl - */ - default: - if ((cmd >= SIOCDEVPRIVATE && - cmd <= SIOCDEVPRIVATE + 15) || - cmd == SIOCBONDENSLAVE || - cmd == SIOCBONDRELEASE || - cmd == SIOCBONDSETHWADDR || - cmd == SIOCBONDSLAVEINFOQUERY || - cmd == SIOCBONDINFOQUERY || - cmd == SIOCBONDCHANGEACTIVE || - cmd == SIOCGMIIPHY || - cmd == SIOCGMIIREG || - cmd == SIOCSMIIREG || - cmd == SIOCBRADDIF || - cmd == SIOCBRDELIF || - cmd == SIOCSHWTSTAMP || - cmd == SIOCWANDEV) { - err = -EOPNOTSUPP; - if (ops->ndo_do_ioctl) { - if (netif_device_present(dev)) - err = ops->ndo_do_ioctl(dev, ifr, cmd); - else - err = -ENODEV; - } - } else - err = -EINVAL; - - } - return err; -} - -/* - * This function handles all "interface"-type I/O control requests. The actual - * 'doing' part of this is dev_ifsioc above. - */ - /** - * dev_ioctl - network device ioctl - * @net: the applicable net namespace - * @cmd: command to issue - * @arg: pointer to a struct ifreq in user space + * dev_change_carrier - Change device carrier + * @dev: device + * @new_carries: new value * - * Issue ioctl functions to devices. This is normally called by the - * user space syscall interfaces but can sometimes be useful for - * other purposes. The return value is the return from the syscall if - * positive or a negative errno code on error. + * Change device carrier */ - -int dev_ioctl(struct net *net, unsigned int cmd, void __user *arg) +int dev_change_carrier(struct net_device *dev, bool new_carrier) { - struct ifreq ifr; - int ret; - char *colon; - - /* One special case: SIOCGIFCONF takes ifconf argument - and requires shared lock, because it sleeps writing - to user space. - */ - - if (cmd == SIOCGIFCONF) { - rtnl_lock(); - ret = dev_ifconf(net, (char __user *) arg); - rtnl_unlock(); - return ret; - } - if (cmd == SIOCGIFNAME) - return dev_ifname(net, (struct ifreq __user *)arg); - - if (copy_from_user(&ifr, arg, sizeof(struct ifreq))) - return -EFAULT; - - ifr.ifr_name[IFNAMSIZ-1] = 0; - - colon = strchr(ifr.ifr_name, ':'); - if (colon) - *colon = 0; - - /* - * See which interface the caller is talking about. - */ - - switch (cmd) { - /* - * These ioctl calls: - * - can be done by all. - * - atomic and do not require locking. - * - return a value - */ - case SIOCGIFFLAGS: - case SIOCGIFMETRIC: - case SIOCGIFMTU: - case SIOCGIFHWADDR: - case SIOCGIFSLAVE: - case SIOCGIFMAP: - case SIOCGIFINDEX: - case SIOCGIFTXQLEN: - dev_load(net, ifr.ifr_name); - rcu_read_lock(); - ret = dev_ifsioc_locked(net, &ifr, cmd); - rcu_read_unlock(); - if (!ret) { - if (colon) - *colon = ':'; - if (copy_to_user(arg, &ifr, - sizeof(struct ifreq))) - ret = -EFAULT; - } - return ret; - - case SIOCETHTOOL: - dev_load(net, ifr.ifr_name); - rtnl_lock(); - ret = dev_ethtool(net, &ifr); - rtnl_unlock(); - if (!ret) { - if (colon) - *colon = ':'; - if (copy_to_user(arg, &ifr, - sizeof(struct ifreq))) - ret = -EFAULT; - } - return ret; - - /* - * These ioctl calls: - * - require superuser power. - * - require strict serialization. - * - return a value - */ - case SIOCGMIIPHY: - case SIOCGMIIREG: - case SIOCSIFNAME: - if (!ns_capable(net->user_ns, CAP_NET_ADMIN)) - return -EPERM; - dev_load(net, ifr.ifr_name); - rtnl_lock(); - ret = dev_ifsioc(net, &ifr, cmd); - rtnl_unlock(); - if (!ret) { - if (colon) - *colon = ':'; - if (copy_to_user(arg, &ifr, - sizeof(struct ifreq))) - ret = -EFAULT; - } - return ret; - - /* - * These ioctl calls: - * - require superuser power. - * - require strict serialization. - * - do not return a value - */ - case SIOCSIFMAP: - case SIOCSIFTXQLEN: - if (!capable(CAP_NET_ADMIN)) - return -EPERM; - /* fall through */ - /* - * These ioctl calls: - * - require local superuser power. - * - require strict serialization. - * - do not return a value - */ - case SIOCSIFFLAGS: - case SIOCSIFMETRIC: - case SIOCSIFMTU: - case SIOCSIFHWADDR: - case SIOCSIFSLAVE: - case SIOCADDMULTI: - case SIOCDELMULTI: - case SIOCSIFHWBROADCAST: - case SIOCSMIIREG: - case SIOCBONDENSLAVE: - case SIOCBONDRELEASE: - case SIOCBONDSETHWADDR: - case SIOCBONDCHANGEACTIVE: - case SIOCBRADDIF: - case SIOCBRDELIF: - case SIOCSHWTSTAMP: - if (!ns_capable(net->user_ns, CAP_NET_ADMIN)) - return -EPERM; - /* fall through */ - case SIOCBONDSLAVEINFOQUERY: - case SIOCBONDINFOQUERY: - dev_load(net, ifr.ifr_name); - rtnl_lock(); - ret = dev_ifsioc(net, &ifr, cmd); - rtnl_unlock(); - return ret; - - case SIOCGIFMEM: - /* Get the per device memory space. We can add this but - * currently do not support it */ - case SIOCSIFMEM: - /* Set the per device memory buffer space. - * Not applicable in our case */ - case SIOCSIFLINK: - return -ENOTTY; + const struct net_device_ops *ops = dev->netdev_ops; - /* - * Unknown or private ioctl. - */ - default: - if (cmd == SIOCWANDEV || - (cmd >= SIOCDEVPRIVATE && - cmd <= SIOCDEVPRIVATE + 15)) { - dev_load(net, ifr.ifr_name); - rtnl_lock(); - ret = dev_ifsioc(net, &ifr, cmd); - rtnl_unlock(); - if (!ret && copy_to_user(arg, &ifr, - sizeof(struct ifreq))) - ret = -EFAULT; - return ret; - } - /* Take care of Wireless Extensions */ - if (cmd >= SIOCIWFIRST && cmd <= SIOCIWLAST) - return wext_handle_ioctl(net, &ifr, cmd, arg); - return -ENOTTY; - } + if (!ops->ndo_change_carrier) + return -EOPNOTSUPP; + if (!netif_device_present(dev)) + return -ENODEV; + return ops->ndo_change_carrier(dev, new_carrier); } - +EXPORT_SYMBOL(dev_change_carrier); /** * dev_new_index - allocate an ifindex @@ -5482,11 +5263,15 @@ static void rollback_registered_many(struct list_head *head) if (dev->netdev_ops->ndo_uninit) dev->netdev_ops->ndo_uninit(dev); - /* Notifier chain MUST detach us from master device. */ - WARN_ON(dev->master); + /* Notifier chain MUST detach us all upper devices. */ + WARN_ON(netdev_has_any_upper_dev(dev)); /* Remove entries from kobject tree */ netdev_unregister_kobject(dev); +#ifdef CONFIG_XPS + /* Remove XPS queueing entries */ + netif_reset_xps_queues_gt(dev, 0); +#endif } synchronize_net(); @@ -5664,10 +5449,9 @@ static int netif_alloc_rx_queues(struct net_device *dev) BUG_ON(count < 1); rx = kcalloc(count, sizeof(struct netdev_rx_queue), GFP_KERNEL); - if (!rx) { - pr_err("netdev: Unable to allocate %u rx queues\n", count); + if (!rx) return -ENOMEM; - } + dev->_rx = rx; for (i = 0; i < count; i++) @@ -5698,10 +5482,9 @@ static int netif_alloc_netdev_queues(struct net_device *dev) BUG_ON(count < 1); tx = kcalloc(count, sizeof(struct netdev_queue), GFP_KERNEL); - if (!tx) { - pr_err("netdev: Unable to allocate %u tx queues\n", count); + if (!tx) return -ENOMEM; - } + dev->_tx = tx; netdev_for_each_tx_queue(dev, netdev_init_one_queue, NULL); @@ -5760,6 +5543,14 @@ int register_netdevice(struct net_device *dev) } } + if (((dev->hw_features | dev->features) & NETIF_F_HW_VLAN_FILTER) && + (!dev->netdev_ops->ndo_vlan_rx_add_vid || + !dev->netdev_ops->ndo_vlan_rx_kill_vid)) { + netdev_WARN(dev, "Buggy VLAN acceleration in driver!\n"); + ret = -EINVAL; + goto err_uninit; + } + ret = -EBUSY; if (!dev->ifindex) dev->ifindex = dev_new_index(net); @@ -5815,6 +5606,13 @@ int register_netdevice(struct net_device *dev) list_netdevice(dev); add_device_randomness(dev->dev_addr, dev->addr_len); + /* If the device has permanent device address, driver should + * set dev_addr and also addr_assign_type should be set to + * NET_ADDR_PERM (default value). + */ + if (dev->addr_assign_type == NET_ADDR_PERM) + memcpy(dev->perm_addr, dev->dev_addr, dev->addr_len); + /* Notify protocols, that a new device appeared. */ ret = call_netdevice_notifiers(NETDEV_REGISTER, dev); ret = notifier_to_errno(ret); @@ -6121,6 +5919,14 @@ struct netdev_queue *dev_ingress_queue_create(struct net_device *dev) static const struct ethtool_ops default_ethtool_ops; +void netdev_set_default_ethtool_ops(struct net_device *dev, + const struct ethtool_ops *ops) +{ + if (dev->ethtool_ops == &default_ethtool_ops) + dev->ethtool_ops = ops; +} +EXPORT_SYMBOL_GPL(netdev_set_default_ethtool_ops); + /** * alloc_netdev_mqs - allocate network device * @sizeof_priv: size of private data to allocate space for @@ -6165,10 +5971,8 @@ struct net_device *alloc_netdev_mqs(int sizeof_priv, const char *name, alloc_size += NETDEV_ALIGN - 1; p = kzalloc(alloc_size, GFP_KERNEL); - if (!p) { - pr_err("alloc_netdev: Unable to allocate device\n"); + if (!p) return NULL; - } dev = PTR_ALIGN(p, NETDEV_ALIGN); dev->padded = (char *)dev - (char *)p; @@ -6191,6 +5995,7 @@ struct net_device *alloc_netdev_mqs(int sizeof_priv, const char *name, INIT_LIST_HEAD(&dev->napi_list); INIT_LIST_HEAD(&dev->unreg_list); INIT_LIST_HEAD(&dev->link_watch_list); + INIT_LIST_HEAD(&dev->upper_dev_list); dev->priv_flags = IFF_XMIT_DST_RELEASE; setup(dev); @@ -6841,12 +6646,3 @@ out: } subsys_initcall(net_dev_init); - -static int __init initialize_hashrnd(void) -{ - get_random_bytes(&hashrnd, sizeof(hashrnd)); - return 0; -} - -late_initcall_sync(initialize_hashrnd); - diff --git a/net/core/dev_ioctl.c b/net/core/dev_ioctl.c new file mode 100644 index 000000000000..6cc0481faade --- /dev/null +++ b/net/core/dev_ioctl.c @@ -0,0 +1,576 @@ +#include <linux/kmod.h> +#include <linux/netdevice.h> +#include <linux/etherdevice.h> +#include <linux/rtnetlink.h> +#include <linux/net_tstamp.h> +#include <linux/wireless.h> +#include <net/wext.h> + +/* + * Map an interface index to its name (SIOCGIFNAME) + */ + +/* + * We need this ioctl for efficient implementation of the + * if_indextoname() function required by the IPv6 API. Without + * it, we would have to search all the interfaces to find a + * match. --pb + */ + +static int dev_ifname(struct net *net, struct ifreq __user *arg) +{ + struct net_device *dev; + struct ifreq ifr; + unsigned seq; + + /* + * Fetch the caller's info block. + */ + + if (copy_from_user(&ifr, arg, sizeof(struct ifreq))) + return -EFAULT; + +retry: + seq = read_seqcount_begin(&devnet_rename_seq); + rcu_read_lock(); + dev = dev_get_by_index_rcu(net, ifr.ifr_ifindex); + if (!dev) { + rcu_read_unlock(); + return -ENODEV; + } + + strcpy(ifr.ifr_name, dev->name); + rcu_read_unlock(); + if (read_seqcount_retry(&devnet_rename_seq, seq)) + goto retry; + + if (copy_to_user(arg, &ifr, sizeof(struct ifreq))) + return -EFAULT; + return 0; +} + +static gifconf_func_t *gifconf_list[NPROTO]; + +/** + * register_gifconf - register a SIOCGIF handler + * @family: Address family + * @gifconf: Function handler + * + * Register protocol dependent address dumping routines. The handler + * that is passed must not be freed or reused until it has been replaced + * by another handler. + */ +int register_gifconf(unsigned int family, gifconf_func_t *gifconf) +{ + if (family >= NPROTO) + return -EINVAL; + gifconf_list[family] = gifconf; + return 0; +} +EXPORT_SYMBOL(register_gifconf); + +/* + * Perform a SIOCGIFCONF call. This structure will change + * size eventually, and there is nothing I can do about it. + * Thus we will need a 'compatibility mode'. + */ + +static int dev_ifconf(struct net *net, char __user *arg) +{ + struct ifconf ifc; + struct net_device *dev; + char __user *pos; + int len; + int total; + int i; + + /* + * Fetch the caller's info block. + */ + + if (copy_from_user(&ifc, arg, sizeof(struct ifconf))) + return -EFAULT; + + pos = ifc.ifc_buf; + len = ifc.ifc_len; + + /* + * Loop over the interfaces, and write an info block for each. + */ + + total = 0; + for_each_netdev(net, dev) { + for (i = 0; i < NPROTO; i++) { + if (gifconf_list[i]) { + int done; + if (!pos) + done = gifconf_list[i](dev, NULL, 0); + else + done = gifconf_list[i](dev, pos + total, + len - total); + if (done < 0) + return -EFAULT; + total += done; + } + } + } + + /* + * All done. Write the updated control block back to the caller. + */ + ifc.ifc_len = total; + + /* + * Both BSD and Solaris return 0 here, so we do too. + */ + return copy_to_user(arg, &ifc, sizeof(struct ifconf)) ? -EFAULT : 0; +} + +/* + * Perform the SIOCxIFxxx calls, inside rcu_read_lock() + */ +static int dev_ifsioc_locked(struct net *net, struct ifreq *ifr, unsigned int cmd) +{ + int err; + struct net_device *dev = dev_get_by_name_rcu(net, ifr->ifr_name); + + if (!dev) + return -ENODEV; + + switch (cmd) { + case SIOCGIFFLAGS: /* Get interface flags */ + ifr->ifr_flags = (short) dev_get_flags(dev); + return 0; + + case SIOCGIFMETRIC: /* Get the metric on the interface + (currently unused) */ + ifr->ifr_metric = 0; + return 0; + + case SIOCGIFMTU: /* Get the MTU of a device */ + ifr->ifr_mtu = dev->mtu; + return 0; + + case SIOCGIFHWADDR: + if (!dev->addr_len) + memset(ifr->ifr_hwaddr.sa_data, 0, sizeof ifr->ifr_hwaddr.sa_data); + else + memcpy(ifr->ifr_hwaddr.sa_data, dev->dev_addr, + min(sizeof ifr->ifr_hwaddr.sa_data, (size_t) dev->addr_len)); + ifr->ifr_hwaddr.sa_family = dev->type; + return 0; + + case SIOCGIFSLAVE: + err = -EINVAL; + break; + + case SIOCGIFMAP: + ifr->ifr_map.mem_start = dev->mem_start; + ifr->ifr_map.mem_end = dev->mem_end; + ifr->ifr_map.base_addr = dev->base_addr; + ifr->ifr_map.irq = dev->irq; + ifr->ifr_map.dma = dev->dma; + ifr->ifr_map.port = dev->if_port; + return 0; + + case SIOCGIFINDEX: + ifr->ifr_ifindex = dev->ifindex; + return 0; + + case SIOCGIFTXQLEN: + ifr->ifr_qlen = dev->tx_queue_len; + return 0; + + default: + /* dev_ioctl() should ensure this case + * is never reached + */ + WARN_ON(1); + err = -ENOTTY; + break; + + } + return err; +} + +static int net_hwtstamp_validate(struct ifreq *ifr) +{ + struct hwtstamp_config cfg; + enum hwtstamp_tx_types tx_type; + enum hwtstamp_rx_filters rx_filter; + int tx_type_valid = 0; + int rx_filter_valid = 0; + + if (copy_from_user(&cfg, ifr->ifr_data, sizeof(cfg))) + return -EFAULT; + + if (cfg.flags) /* reserved for future extensions */ + return -EINVAL; + + tx_type = cfg.tx_type; + rx_filter = cfg.rx_filter; + + switch (tx_type) { + case HWTSTAMP_TX_OFF: + case HWTSTAMP_TX_ON: + case HWTSTAMP_TX_ONESTEP_SYNC: + tx_type_valid = 1; + break; + } + + switch (rx_filter) { + case HWTSTAMP_FILTER_NONE: + case HWTSTAMP_FILTER_ALL: + case HWTSTAMP_FILTER_SOME: + case HWTSTAMP_FILTER_PTP_V1_L4_EVENT: + case HWTSTAMP_FILTER_PTP_V1_L4_SYNC: + case HWTSTAMP_FILTER_PTP_V1_L4_DELAY_REQ: + case HWTSTAMP_FILTER_PTP_V2_L4_EVENT: + case HWTSTAMP_FILTER_PTP_V2_L4_SYNC: + case HWTSTAMP_FILTER_PTP_V2_L4_DELAY_REQ: + case HWTSTAMP_FILTER_PTP_V2_L2_EVENT: + case HWTSTAMP_FILTER_PTP_V2_L2_SYNC: + case HWTSTAMP_FILTER_PTP_V2_L2_DELAY_REQ: + case HWTSTAMP_FILTER_PTP_V2_EVENT: + case HWTSTAMP_FILTER_PTP_V2_SYNC: + case HWTSTAMP_FILTER_PTP_V2_DELAY_REQ: + rx_filter_valid = 1; + break; + } + + if (!tx_type_valid || !rx_filter_valid) + return -ERANGE; + + return 0; +} + +/* + * Perform the SIOCxIFxxx calls, inside rtnl_lock() + */ +static int dev_ifsioc(struct net *net, struct ifreq *ifr, unsigned int cmd) +{ + int err; + struct net_device *dev = __dev_get_by_name(net, ifr->ifr_name); + const struct net_device_ops *ops; + + if (!dev) + return -ENODEV; + + ops = dev->netdev_ops; + + switch (cmd) { + case SIOCSIFFLAGS: /* Set interface flags */ + return dev_change_flags(dev, ifr->ifr_flags); + + case SIOCSIFMETRIC: /* Set the metric on the interface + (currently unused) */ + return -EOPNOTSUPP; + + case SIOCSIFMTU: /* Set the MTU of a device */ + return dev_set_mtu(dev, ifr->ifr_mtu); + + case SIOCSIFHWADDR: + return dev_set_mac_address(dev, &ifr->ifr_hwaddr); + + case SIOCSIFHWBROADCAST: + if (ifr->ifr_hwaddr.sa_family != dev->type) + return -EINVAL; + memcpy(dev->broadcast, ifr->ifr_hwaddr.sa_data, + min(sizeof ifr->ifr_hwaddr.sa_data, (size_t) dev->addr_len)); + call_netdevice_notifiers(NETDEV_CHANGEADDR, dev); + return 0; + + case SIOCSIFMAP: + if (ops->ndo_set_config) { + if (!netif_device_present(dev)) + return -ENODEV; + return ops->ndo_set_config(dev, &ifr->ifr_map); + } + return -EOPNOTSUPP; + + case SIOCADDMULTI: + if (!ops->ndo_set_rx_mode || + ifr->ifr_hwaddr.sa_family != AF_UNSPEC) + return -EINVAL; + if (!netif_device_present(dev)) + return -ENODEV; + return dev_mc_add_global(dev, ifr->ifr_hwaddr.sa_data); + + case SIOCDELMULTI: + if (!ops->ndo_set_rx_mode || + ifr->ifr_hwaddr.sa_family != AF_UNSPEC) + return -EINVAL; + if (!netif_device_present(dev)) + return -ENODEV; + return dev_mc_del_global(dev, ifr->ifr_hwaddr.sa_data); + + case SIOCSIFTXQLEN: + if (ifr->ifr_qlen < 0) + return -EINVAL; + dev->tx_queue_len = ifr->ifr_qlen; + return 0; + + case SIOCSIFNAME: + ifr->ifr_newname[IFNAMSIZ-1] = '\0'; + return dev_change_name(dev, ifr->ifr_newname); + + case SIOCSHWTSTAMP: + err = net_hwtstamp_validate(ifr); + if (err) + return err; + /* fall through */ + + /* + * Unknown or private ioctl + */ + default: + if ((cmd >= SIOCDEVPRIVATE && + cmd <= SIOCDEVPRIVATE + 15) || + cmd == SIOCBONDENSLAVE || + cmd == SIOCBONDRELEASE || + cmd == SIOCBONDSETHWADDR || + cmd == SIOCBONDSLAVEINFOQUERY || + cmd == SIOCBONDINFOQUERY || + cmd == SIOCBONDCHANGEACTIVE || + cmd == SIOCGMIIPHY || + cmd == SIOCGMIIREG || + cmd == SIOCSMIIREG || + cmd == SIOCBRADDIF || + cmd == SIOCBRDELIF || + cmd == SIOCSHWTSTAMP || + cmd == SIOCWANDEV) { + err = -EOPNOTSUPP; + if (ops->ndo_do_ioctl) { + if (netif_device_present(dev)) + err = ops->ndo_do_ioctl(dev, ifr, cmd); + else + err = -ENODEV; + } + } else + err = -EINVAL; + + } + return err; +} + +/** + * dev_load - load a network module + * @net: the applicable net namespace + * @name: name of interface + * + * If a network interface is not present and the process has suitable + * privileges this function loads the module. If module loading is not + * available in this kernel then it becomes a nop. + */ + +void dev_load(struct net *net, const char *name) +{ + struct net_device *dev; + int no_module; + + rcu_read_lock(); + dev = dev_get_by_name_rcu(net, name); + rcu_read_unlock(); + + no_module = !dev; + if (no_module && capable(CAP_NET_ADMIN)) + no_module = request_module("netdev-%s", name); + if (no_module && capable(CAP_SYS_MODULE)) { + if (!request_module("%s", name)) + pr_warn("Loading kernel module for a network device with CAP_SYS_MODULE (deprecated). Use CAP_NET_ADMIN and alias netdev-%s instead.\n", + name); + } +} +EXPORT_SYMBOL(dev_load); + +/* + * This function handles all "interface"-type I/O control requests. The actual + * 'doing' part of this is dev_ifsioc above. + */ + +/** + * dev_ioctl - network device ioctl + * @net: the applicable net namespace + * @cmd: command to issue + * @arg: pointer to a struct ifreq in user space + * + * Issue ioctl functions to devices. This is normally called by the + * user space syscall interfaces but can sometimes be useful for + * other purposes. The return value is the return from the syscall if + * positive or a negative errno code on error. + */ + +int dev_ioctl(struct net *net, unsigned int cmd, void __user *arg) +{ + struct ifreq ifr; + int ret; + char *colon; + + /* One special case: SIOCGIFCONF takes ifconf argument + and requires shared lock, because it sleeps writing + to user space. + */ + + if (cmd == SIOCGIFCONF) { + rtnl_lock(); + ret = dev_ifconf(net, (char __user *) arg); + rtnl_unlock(); + return ret; + } + if (cmd == SIOCGIFNAME) + return dev_ifname(net, (struct ifreq __user *)arg); + + if (copy_from_user(&ifr, arg, sizeof(struct ifreq))) + return -EFAULT; + + ifr.ifr_name[IFNAMSIZ-1] = 0; + + colon = strchr(ifr.ifr_name, ':'); + if (colon) + *colon = 0; + + /* + * See which interface the caller is talking about. + */ + + switch (cmd) { + /* + * These ioctl calls: + * - can be done by all. + * - atomic and do not require locking. + * - return a value + */ + case SIOCGIFFLAGS: + case SIOCGIFMETRIC: + case SIOCGIFMTU: + case SIOCGIFHWADDR: + case SIOCGIFSLAVE: + case SIOCGIFMAP: + case SIOCGIFINDEX: + case SIOCGIFTXQLEN: + dev_load(net, ifr.ifr_name); + rcu_read_lock(); + ret = dev_ifsioc_locked(net, &ifr, cmd); + rcu_read_unlock(); + if (!ret) { + if (colon) + *colon = ':'; + if (copy_to_user(arg, &ifr, + sizeof(struct ifreq))) + ret = -EFAULT; + } + return ret; + + case SIOCETHTOOL: + dev_load(net, ifr.ifr_name); + rtnl_lock(); + ret = dev_ethtool(net, &ifr); + rtnl_unlock(); + if (!ret) { + if (colon) + *colon = ':'; + if (copy_to_user(arg, &ifr, + sizeof(struct ifreq))) + ret = -EFAULT; + } + return ret; + + /* + * These ioctl calls: + * - require superuser power. + * - require strict serialization. + * - return a value + */ + case SIOCGMIIPHY: + case SIOCGMIIREG: + case SIOCSIFNAME: + if (!ns_capable(net->user_ns, CAP_NET_ADMIN)) + return -EPERM; + dev_load(net, ifr.ifr_name); + rtnl_lock(); + ret = dev_ifsioc(net, &ifr, cmd); + rtnl_unlock(); + if (!ret) { + if (colon) + *colon = ':'; + if (copy_to_user(arg, &ifr, + sizeof(struct ifreq))) + ret = -EFAULT; + } + return ret; + + /* + * These ioctl calls: + * - require superuser power. + * - require strict serialization. + * - do not return a value + */ + case SIOCSIFMAP: + case SIOCSIFTXQLEN: + if (!capable(CAP_NET_ADMIN)) + return -EPERM; + /* fall through */ + /* + * These ioctl calls: + * - require local superuser power. + * - require strict serialization. + * - do not return a value + */ + case SIOCSIFFLAGS: + case SIOCSIFMETRIC: + case SIOCSIFMTU: + case SIOCSIFHWADDR: + case SIOCSIFSLAVE: + case SIOCADDMULTI: + case SIOCDELMULTI: + case SIOCSIFHWBROADCAST: + case SIOCSMIIREG: + case SIOCBONDENSLAVE: + case SIOCBONDRELEASE: + case SIOCBONDSETHWADDR: + case SIOCBONDCHANGEACTIVE: + case SIOCBRADDIF: + case SIOCBRDELIF: + case SIOCSHWTSTAMP: + if (!ns_capable(net->user_ns, CAP_NET_ADMIN)) + return -EPERM; + /* fall through */ + case SIOCBONDSLAVEINFOQUERY: + case SIOCBONDINFOQUERY: + dev_load(net, ifr.ifr_name); + rtnl_lock(); + ret = dev_ifsioc(net, &ifr, cmd); + rtnl_unlock(); + return ret; + + case SIOCGIFMEM: + /* Get the per device memory space. We can add this but + * currently do not support it */ + case SIOCSIFMEM: + /* Set the per device memory buffer space. + * Not applicable in our case */ + case SIOCSIFLINK: + return -ENOTTY; + + /* + * Unknown or private ioctl. + */ + default: + if (cmd == SIOCWANDEV || + (cmd >= SIOCDEVPRIVATE && + cmd <= SIOCDEVPRIVATE + 15)) { + dev_load(net, ifr.ifr_name); + rtnl_lock(); + ret = dev_ifsioc(net, &ifr, cmd); + rtnl_unlock(); + if (!ret && copy_to_user(arg, &ifr, + sizeof(struct ifreq))) + ret = -EFAULT; + return ret; + } + /* Take care of Wireless Extensions */ + if (cmd >= SIOCIWFIRST && cmd <= SIOCIWLAST) + return wext_handle_ioctl(net, &ifr, cmd, arg); + return -ENOTTY; + } +} diff --git a/net/core/ethtool.c b/net/core/ethtool.c index a8705432e4b1..3e9b2c3e30f0 100644 --- a/net/core/ethtool.c +++ b/net/core/ethtool.c @@ -77,6 +77,7 @@ static const char netdev_features_strings[NETDEV_FEATURE_COUNT][ETH_GSTRING_LEN] [NETIF_F_TSO_ECN_BIT] = "tx-tcp-ecn-segmentation", [NETIF_F_TSO6_BIT] = "tx-tcp6-segmentation", [NETIF_F_FSO_BIT] = "tx-fcoe-segmentation", + [NETIF_F_GSO_GRE_BIT] = "tx-gre-segmentation", [NETIF_F_FCOE_CRC_BIT] = "tx-checksum-fcoe-crc", [NETIF_F_SCTP_CSUM_BIT] = "tx-checksum-sctp", @@ -175,7 +176,7 @@ static int __ethtool_get_sset_count(struct net_device *dev, int sset) if (sset == ETH_SS_FEATURES) return ARRAY_SIZE(netdev_features_strings); - if (ops && ops->get_sset_count && ops->get_strings) + if (ops->get_sset_count && ops->get_strings) return ops->get_sset_count(dev, sset); else return -EOPNOTSUPP; @@ -311,7 +312,7 @@ int __ethtool_get_settings(struct net_device *dev, struct ethtool_cmd *cmd) { ASSERT_RTNL(); - if (!dev->ethtool_ops || !dev->ethtool_ops->get_settings) + if (!dev->ethtool_ops->get_settings) return -EOPNOTSUPP; memset(cmd, 0, sizeof(struct ethtool_cmd)); @@ -355,7 +356,7 @@ static noinline_for_stack int ethtool_get_drvinfo(struct net_device *dev, memset(&info, 0, sizeof(info)); info.cmd = ETHTOOL_GDRVINFO; - if (ops && ops->get_drvinfo) { + if (ops->get_drvinfo) { ops->get_drvinfo(dev, &info); } else if (dev->dev.parent && dev->dev.parent->driver) { strlcpy(info.bus_info, dev_name(dev->dev.parent), @@ -370,7 +371,7 @@ static noinline_for_stack int ethtool_get_drvinfo(struct net_device *dev, * this method of obtaining string set info is deprecated; * Use ETHTOOL_GSSET_INFO instead. */ - if (ops && ops->get_sset_count) { + if (ops->get_sset_count) { int rc; rc = ops->get_sset_count(dev, ETH_SS_TEST); @@ -383,9 +384,9 @@ static noinline_for_stack int ethtool_get_drvinfo(struct net_device *dev, if (rc >= 0) info.n_priv_flags = rc; } - if (ops && ops->get_regs_len) + if (ops->get_regs_len) info.regdump_len = ops->get_regs_len(dev); - if (ops && ops->get_eeprom_len) + if (ops->get_eeprom_len) info.eedump_len = ops->get_eeprom_len(dev); if (copy_to_user(useraddr, &info, sizeof(info))) @@ -590,13 +591,14 @@ static noinline_for_stack int ethtool_set_rxfh_indir(struct net_device *dev, struct ethtool_rxnfc rx_rings; u32 user_size, dev_size, i; u32 *indir; + const struct ethtool_ops *ops = dev->ethtool_ops; int ret; - if (!dev->ethtool_ops->get_rxfh_indir_size || - !dev->ethtool_ops->set_rxfh_indir || - !dev->ethtool_ops->get_rxnfc) + if (!ops->get_rxfh_indir_size || !ops->set_rxfh_indir || + !ops->get_rxnfc) return -EOPNOTSUPP; - dev_size = dev->ethtool_ops->get_rxfh_indir_size(dev); + + dev_size = ops->get_rxfh_indir_size(dev); if (dev_size == 0) return -EOPNOTSUPP; @@ -613,7 +615,7 @@ static noinline_for_stack int ethtool_set_rxfh_indir(struct net_device *dev, return -ENOMEM; rx_rings.cmd = ETHTOOL_GRXRINGS; - ret = dev->ethtool_ops->get_rxnfc(dev, &rx_rings, NULL); + ret = ops->get_rxnfc(dev, &rx_rings, NULL); if (ret) goto out; @@ -639,7 +641,7 @@ static noinline_for_stack int ethtool_set_rxfh_indir(struct net_device *dev, } } - ret = dev->ethtool_ops->set_rxfh_indir(dev, indir); + ret = ops->set_rxfh_indir(dev, indir); out: kfree(indir); @@ -1082,9 +1084,10 @@ static int ethtool_phys_id(struct net_device *dev, void __user *useraddr) { struct ethtool_value id; static bool busy; + const struct ethtool_ops *ops = dev->ethtool_ops; int rc; - if (!dev->ethtool_ops->set_phys_id) + if (!ops->set_phys_id) return -EOPNOTSUPP; if (busy) @@ -1093,7 +1096,7 @@ static int ethtool_phys_id(struct net_device *dev, void __user *useraddr) if (copy_from_user(&id, useraddr, sizeof(id))) return -EFAULT; - rc = dev->ethtool_ops->set_phys_id(dev, ETHTOOL_ID_ACTIVE); + rc = ops->set_phys_id(dev, ETHTOOL_ID_ACTIVE); if (rc < 0) return rc; @@ -1118,7 +1121,7 @@ static int ethtool_phys_id(struct net_device *dev, void __user *useraddr) i = n; do { rtnl_lock(); - rc = dev->ethtool_ops->set_phys_id(dev, + rc = ops->set_phys_id(dev, (i & 1) ? ETHTOOL_ID_OFF : ETHTOOL_ID_ON); rtnl_unlock(); if (rc) @@ -1133,7 +1136,7 @@ static int ethtool_phys_id(struct net_device *dev, void __user *useraddr) dev_put(dev); busy = false; - (void)dev->ethtool_ops->set_phys_id(dev, ETHTOOL_ID_INACTIVE); + (void) ops->set_phys_id(dev, ETHTOOL_ID_INACTIVE); return rc; } @@ -1275,7 +1278,7 @@ static int ethtool_get_dump_flag(struct net_device *dev, struct ethtool_dump dump; const struct ethtool_ops *ops = dev->ethtool_ops; - if (!dev->ethtool_ops->get_dump_flag) + if (!ops->get_dump_flag) return -EOPNOTSUPP; if (copy_from_user(&dump, useraddr, sizeof(dump))) @@ -1299,8 +1302,7 @@ static int ethtool_get_dump_data(struct net_device *dev, const struct ethtool_ops *ops = dev->ethtool_ops; void *data = NULL; - if (!dev->ethtool_ops->get_dump_data || - !dev->ethtool_ops->get_dump_flag) + if (!ops->get_dump_data || !ops->get_dump_flag) return -EOPNOTSUPP; if (copy_from_user(&dump, useraddr, sizeof(dump))) @@ -1346,13 +1348,9 @@ static int ethtool_get_ts_info(struct net_device *dev, void __user *useraddr) info.cmd = ETHTOOL_GET_TS_INFO; if (phydev && phydev->drv && phydev->drv->ts_info) { - err = phydev->drv->ts_info(phydev, &info); - - } else if (dev->ethtool_ops && dev->ethtool_ops->get_ts_info) { - + } else if (ops->get_ts_info) { err = ops->get_ts_info(dev, &info); - } else { info.so_timestamping = SOF_TIMESTAMPING_RX_SOFTWARE | diff --git a/net/core/filter.c b/net/core/filter.c index c23543cba132..2e20b55a7830 100644 --- a/net/core/filter.c +++ b/net/core/filter.c @@ -532,6 +532,7 @@ int sk_chk_filter(struct sock_filter *filter, unsigned int flen) [BPF_JMP|BPF_JSET|BPF_X] = BPF_S_JMP_JSET_X, }; int pc; + bool anc_found; if (flen == 0 || flen > BPF_MAXINSNS) return -EINVAL; @@ -592,8 +593,10 @@ int sk_chk_filter(struct sock_filter *filter, unsigned int flen) case BPF_S_LD_W_ABS: case BPF_S_LD_H_ABS: case BPF_S_LD_B_ABS: + anc_found = false; #define ANCILLARY(CODE) case SKF_AD_OFF + SKF_AD_##CODE: \ code = BPF_S_ANC_##CODE; \ + anc_found = true; \ break switch (ftest->k) { ANCILLARY(PROTOCOL); @@ -610,6 +613,10 @@ int sk_chk_filter(struct sock_filter *filter, unsigned int flen) ANCILLARY(VLAN_TAG); ANCILLARY(VLAN_TAG_PRESENT); } + + /* ancillary operation unknown or unsupported */ + if (anc_found == false && ftest->k >= SKF_AD_OFF) + return -EINVAL; } ftest->code = code; } @@ -714,6 +721,9 @@ int sk_attach_filter(struct sock_fprog *fprog, struct sock *sk) unsigned int fsize = sizeof(struct sock_filter) * fprog->len; int err; + if (sock_flag(sk, SOCK_FILTER_LOCKED)) + return -EPERM; + /* Make sure new filter is there and in the right amounts. */ if (fprog->filter == NULL) return -EINVAL; @@ -750,6 +760,9 @@ int sk_detach_filter(struct sock *sk) int ret = -ENOENT; struct sk_filter *filter; + if (sock_flag(sk, SOCK_FILTER_LOCKED)) + return -EPERM; + filter = rcu_dereference_protected(sk->sk_filter, sock_owned_by_user(sk)); if (filter) { diff --git a/net/core/flow.c b/net/core/flow.c index b0901ee5a002..43f7495df27a 100644 --- a/net/core/flow.c +++ b/net/core/flow.c @@ -286,7 +286,7 @@ nocache: else fle->genid--; } else { - if (flo && !IS_ERR(flo)) + if (!IS_ERR_OR_NULL(flo)) flo->ops->delete(flo); } ret_object: diff --git a/net/core/flow_dissector.c b/net/core/flow_dissector.c index 466820b6e344..9d4c7201400d 100644 --- a/net/core/flow_dissector.c +++ b/net/core/flow_dissector.c @@ -143,3 +143,176 @@ ipv6: return true; } EXPORT_SYMBOL(skb_flow_dissect); + +static u32 hashrnd __read_mostly; + +/* + * __skb_get_rxhash: calculate a flow hash based on src/dst addresses + * and src/dst port numbers. Sets rxhash in skb to non-zero hash value + * on success, zero indicates no valid hash. Also, sets l4_rxhash in skb + * if hash is a canonical 4-tuple hash over transport ports. + */ +void __skb_get_rxhash(struct sk_buff *skb) +{ + struct flow_keys keys; + u32 hash; + + if (!skb_flow_dissect(skb, &keys)) + return; + + if (keys.ports) + skb->l4_rxhash = 1; + + /* get a consistent hash (same value on both flow directions) */ + if (((__force u32)keys.dst < (__force u32)keys.src) || + (((__force u32)keys.dst == (__force u32)keys.src) && + ((__force u16)keys.port16[1] < (__force u16)keys.port16[0]))) { + swap(keys.dst, keys.src); + swap(keys.port16[0], keys.port16[1]); + } + + hash = jhash_3words((__force u32)keys.dst, + (__force u32)keys.src, + (__force u32)keys.ports, hashrnd); + if (!hash) + hash = 1; + + skb->rxhash = hash; +} +EXPORT_SYMBOL(__skb_get_rxhash); + +/* + * Returns a Tx hash based on the given packet descriptor a Tx queues' number + * to be used as a distribution range. + */ +u16 __skb_tx_hash(const struct net_device *dev, const struct sk_buff *skb, + unsigned int num_tx_queues) +{ + u32 hash; + u16 qoffset = 0; + u16 qcount = num_tx_queues; + + if (skb_rx_queue_recorded(skb)) { + hash = skb_get_rx_queue(skb); + while (unlikely(hash >= num_tx_queues)) + hash -= num_tx_queues; + return hash; + } + + if (dev->num_tc) { + u8 tc = netdev_get_prio_tc_map(dev, skb->priority); + qoffset = dev->tc_to_txq[tc].offset; + qcount = dev->tc_to_txq[tc].count; + } + + if (skb->sk && skb->sk->sk_hash) + hash = skb->sk->sk_hash; + else + hash = (__force u16) skb->protocol; + hash = jhash_1word(hash, hashrnd); + + return (u16) (((u64) hash * qcount) >> 32) + qoffset; +} +EXPORT_SYMBOL(__skb_tx_hash); + +static inline u16 dev_cap_txqueue(struct net_device *dev, u16 queue_index) +{ + if (unlikely(queue_index >= dev->real_num_tx_queues)) { + net_warn_ratelimited("%s selects TX queue %d, but real number of TX queues is %d\n", + dev->name, queue_index, + dev->real_num_tx_queues); + return 0; + } + return queue_index; +} + +static inline int get_xps_queue(struct net_device *dev, struct sk_buff *skb) +{ +#ifdef CONFIG_XPS + struct xps_dev_maps *dev_maps; + struct xps_map *map; + int queue_index = -1; + + rcu_read_lock(); + dev_maps = rcu_dereference(dev->xps_maps); + if (dev_maps) { + map = rcu_dereference( + dev_maps->cpu_map[raw_smp_processor_id()]); + if (map) { + if (map->len == 1) + queue_index = map->queues[0]; + else { + u32 hash; + if (skb->sk && skb->sk->sk_hash) + hash = skb->sk->sk_hash; + else + hash = (__force u16) skb->protocol ^ + skb->rxhash; + hash = jhash_1word(hash, hashrnd); + queue_index = map->queues[ + ((u64)hash * map->len) >> 32]; + } + if (unlikely(queue_index >= dev->real_num_tx_queues)) + queue_index = -1; + } + } + rcu_read_unlock(); + + return queue_index; +#else + return -1; +#endif +} + +u16 __netdev_pick_tx(struct net_device *dev, struct sk_buff *skb) +{ + struct sock *sk = skb->sk; + int queue_index = sk_tx_queue_get(sk); + + if (queue_index < 0 || skb->ooo_okay || + queue_index >= dev->real_num_tx_queues) { + int new_index = get_xps_queue(dev, skb); + if (new_index < 0) + new_index = skb_tx_hash(dev, skb); + + if (queue_index != new_index && sk) { + struct dst_entry *dst = + rcu_dereference_check(sk->sk_dst_cache, 1); + + if (dst && skb_dst(skb) == dst) + sk_tx_queue_set(sk, queue_index); + + } + + queue_index = new_index; + } + + return queue_index; +} +EXPORT_SYMBOL(__netdev_pick_tx); + +struct netdev_queue *netdev_pick_tx(struct net_device *dev, + struct sk_buff *skb) +{ + int queue_index = 0; + + if (dev->real_num_tx_queues != 1) { + const struct net_device_ops *ops = dev->netdev_ops; + if (ops->ndo_select_queue) + queue_index = ops->ndo_select_queue(dev, skb); + else + queue_index = __netdev_pick_tx(dev, skb); + queue_index = dev_cap_txqueue(dev, queue_index); + } + + skb_set_queue_mapping(skb, queue_index); + return netdev_get_tx_queue(dev, queue_index); +} + +static int __init initialize_hashrnd(void) +{ + get_random_bytes(&hashrnd, sizeof(hashrnd)); + return 0; +} + +late_initcall_sync(initialize_hashrnd); diff --git a/net/core/neighbour.c b/net/core/neighbour.c index c815f285e5ab..3863b8f639c5 100644 --- a/net/core/neighbour.c +++ b/net/core/neighbour.c @@ -290,15 +290,7 @@ static struct neighbour *neigh_alloc(struct neigh_table *tbl, struct net_device goto out_entries; } - if (tbl->entry_size) - n = kzalloc(tbl->entry_size, GFP_ATOMIC); - else { - int sz = sizeof(*n) + tbl->key_len; - - sz = ALIGN(sz, NEIGH_PRIV_ALIGN); - sz += dev->neigh_priv_len; - n = kzalloc(sz, GFP_ATOMIC); - } + n = kzalloc(tbl->entry_size + dev->neigh_priv_len, GFP_ATOMIC); if (!n) goto out_entries; @@ -778,6 +770,9 @@ static void neigh_periodic_work(struct work_struct *work) nht = rcu_dereference_protected(tbl->nht, lockdep_is_held(&tbl->lock)); + if (atomic_read(&tbl->entries) < tbl->gc_thresh1) + goto out; + /* * periodically recompute ReachableTime from random function */ @@ -832,6 +827,7 @@ next_elt: nht = rcu_dereference_protected(tbl->nht, lockdep_is_held(&tbl->lock)); } +out: /* Cycle through all hash buckets every base_reachable_time/2 ticks. * ARP entry timeouts range from 1/2 base_reachable_time to 3/2 * base_reachable_time. @@ -1542,6 +1538,12 @@ static void neigh_table_init_no_netlink(struct neigh_table *tbl) if (!tbl->nht || !tbl->phash_buckets) panic("cannot allocate neighbour cache hashes"); + if (!tbl->entry_size) + tbl->entry_size = ALIGN(offsetof(struct neighbour, primary_key) + + tbl->key_len, NEIGH_PRIV_ALIGN); + else + WARN_ON(tbl->entry_size % NEIGH_PRIV_ALIGN); + rwlock_init(&tbl->lock); INIT_DEFERRABLE_WORK(&tbl->gc_work, neigh_periodic_work); schedule_delayed_work(&tbl->gc_work, tbl->parms.reachable_time); diff --git a/net/core/net-sysfs.c b/net/core/net-sysfs.c index 334efd5d67a9..a5b89a6fec6d 100644 --- a/net/core/net-sysfs.c +++ b/net/core/net-sysfs.c @@ -126,6 +126,19 @@ static ssize_t show_broadcast(struct device *dev, return -EINVAL; } +static int change_carrier(struct net_device *net, unsigned long new_carrier) +{ + if (!netif_running(net)) + return -EINVAL; + return dev_change_carrier(net, (bool) new_carrier); +} + +static ssize_t store_carrier(struct device *dev, struct device_attribute *attr, + const char *buf, size_t len) +{ + return netdev_store(dev, attr, buf, len, change_carrier); +} + static ssize_t show_carrier(struct device *dev, struct device_attribute *attr, char *buf) { @@ -331,7 +344,7 @@ static struct device_attribute net_class_attributes[] = { __ATTR(link_mode, S_IRUGO, show_link_mode, NULL), __ATTR(address, S_IRUGO, show_address, NULL), __ATTR(broadcast, S_IRUGO, show_broadcast, NULL), - __ATTR(carrier, S_IRUGO, show_carrier, NULL), + __ATTR(carrier, S_IRUGO | S_IWUSR, show_carrier, store_carrier), __ATTR(speed, S_IRUGO, show_speed, NULL), __ATTR(duplex, S_IRUGO, show_duplex, NULL), __ATTR(dormant, S_IRUGO, show_dormant, NULL), @@ -989,68 +1002,14 @@ static ssize_t show_xps_map(struct netdev_queue *queue, return len; } -static DEFINE_MUTEX(xps_map_mutex); -#define xmap_dereference(P) \ - rcu_dereference_protected((P), lockdep_is_held(&xps_map_mutex)) - -static void xps_queue_release(struct netdev_queue *queue) -{ - struct net_device *dev = queue->dev; - struct xps_dev_maps *dev_maps; - struct xps_map *map; - unsigned long index; - int i, pos, nonempty = 0; - - index = get_netdev_queue_index(queue); - - mutex_lock(&xps_map_mutex); - dev_maps = xmap_dereference(dev->xps_maps); - - if (dev_maps) { - for_each_possible_cpu(i) { - map = xmap_dereference(dev_maps->cpu_map[i]); - if (!map) - continue; - - for (pos = 0; pos < map->len; pos++) - if (map->queues[pos] == index) - break; - - if (pos < map->len) { - if (map->len > 1) - map->queues[pos] = - map->queues[--map->len]; - else { - RCU_INIT_POINTER(dev_maps->cpu_map[i], - NULL); - kfree_rcu(map, rcu); - map = NULL; - } - } - if (map) - nonempty = 1; - } - - if (!nonempty) { - RCU_INIT_POINTER(dev->xps_maps, NULL); - kfree_rcu(dev_maps, rcu); - } - } - mutex_unlock(&xps_map_mutex); -} - static ssize_t store_xps_map(struct netdev_queue *queue, struct netdev_queue_attribute *attribute, const char *buf, size_t len) { struct net_device *dev = queue->dev; - cpumask_var_t mask; - int err, i, cpu, pos, map_len, alloc_len, need_set; unsigned long index; - struct xps_map *map, *new_map; - struct xps_dev_maps *dev_maps, *new_dev_maps; - int nonempty = 0; - int numa_node_id = -2; + cpumask_var_t mask; + int err; if (!capable(CAP_NET_ADMIN)) return -EPERM; @@ -1066,105 +1025,11 @@ static ssize_t store_xps_map(struct netdev_queue *queue, return err; } - new_dev_maps = kzalloc(max_t(unsigned int, - XPS_DEV_MAPS_SIZE, L1_CACHE_BYTES), GFP_KERNEL); - if (!new_dev_maps) { - free_cpumask_var(mask); - return -ENOMEM; - } - - mutex_lock(&xps_map_mutex); - - dev_maps = xmap_dereference(dev->xps_maps); - - for_each_possible_cpu(cpu) { - map = dev_maps ? - xmap_dereference(dev_maps->cpu_map[cpu]) : NULL; - new_map = map; - if (map) { - for (pos = 0; pos < map->len; pos++) - if (map->queues[pos] == index) - break; - map_len = map->len; - alloc_len = map->alloc_len; - } else - pos = map_len = alloc_len = 0; - - need_set = cpumask_test_cpu(cpu, mask) && cpu_online(cpu); -#ifdef CONFIG_NUMA - if (need_set) { - if (numa_node_id == -2) - numa_node_id = cpu_to_node(cpu); - else if (numa_node_id != cpu_to_node(cpu)) - numa_node_id = -1; - } -#endif - if (need_set && pos >= map_len) { - /* Need to add queue to this CPU's map */ - if (map_len >= alloc_len) { - alloc_len = alloc_len ? - 2 * alloc_len : XPS_MIN_MAP_ALLOC; - new_map = kzalloc_node(XPS_MAP_SIZE(alloc_len), - GFP_KERNEL, - cpu_to_node(cpu)); - if (!new_map) - goto error; - new_map->alloc_len = alloc_len; - for (i = 0; i < map_len; i++) - new_map->queues[i] = map->queues[i]; - new_map->len = map_len; - } - new_map->queues[new_map->len++] = index; - } else if (!need_set && pos < map_len) { - /* Need to remove queue from this CPU's map */ - if (map_len > 1) - new_map->queues[pos] = - new_map->queues[--new_map->len]; - else - new_map = NULL; - } - RCU_INIT_POINTER(new_dev_maps->cpu_map[cpu], new_map); - } - - /* Cleanup old maps */ - for_each_possible_cpu(cpu) { - map = dev_maps ? - xmap_dereference(dev_maps->cpu_map[cpu]) : NULL; - if (map && xmap_dereference(new_dev_maps->cpu_map[cpu]) != map) - kfree_rcu(map, rcu); - if (new_dev_maps->cpu_map[cpu]) - nonempty = 1; - } - - if (nonempty) { - rcu_assign_pointer(dev->xps_maps, new_dev_maps); - } else { - kfree(new_dev_maps); - RCU_INIT_POINTER(dev->xps_maps, NULL); - } - - if (dev_maps) - kfree_rcu(dev_maps, rcu); - - netdev_queue_numa_node_write(queue, (numa_node_id >= 0) ? numa_node_id : - NUMA_NO_NODE); - - mutex_unlock(&xps_map_mutex); + err = netif_set_xps_queue(dev, mask, index); free_cpumask_var(mask); - return len; -error: - mutex_unlock(&xps_map_mutex); - - if (new_dev_maps) - for_each_possible_cpu(i) - kfree(rcu_dereference_protected( - new_dev_maps->cpu_map[i], - 1)); - kfree(new_dev_maps); - free_cpumask_var(mask); - return -ENOMEM; + return err ? : len; } static struct netdev_queue_attribute xps_cpus_attribute = @@ -1183,10 +1048,6 @@ static void netdev_queue_release(struct kobject *kobj) { struct netdev_queue *queue = to_netdev_queue(kobj); -#ifdef CONFIG_XPS - xps_queue_release(queue); -#endif - memset(kobj, 0, sizeof(*kobj)); dev_put(queue->dev); } @@ -1334,7 +1195,6 @@ struct kobj_ns_type_operations net_ns_type_operations = { }; EXPORT_SYMBOL_GPL(net_ns_type_operations); -#ifdef CONFIG_HOTPLUG static int netdev_uevent(struct device *d, struct kobj_uevent_env *env) { struct net_device *dev = to_net_dev(d); @@ -1353,7 +1213,6 @@ static int netdev_uevent(struct device *d, struct kobj_uevent_env *env) exit: return retval; } -#endif /* * netdev_release -- destroy and free a dead device. @@ -1382,9 +1241,7 @@ static struct class net_class = { #ifdef CONFIG_SYSFS .dev_attrs = net_class_attributes, #endif /* CONFIG_SYSFS */ -#ifdef CONFIG_HOTPLUG .dev_uevent = netdev_uevent, -#endif .ns_type = &net_ns_type_operations, .namespace = net_namespace, }; diff --git a/net/core/netpoll.c b/net/core/netpoll.c index 3151acf5ec13..fa32899006a2 100644 --- a/net/core/netpoll.c +++ b/net/core/netpoll.c @@ -29,6 +29,9 @@ #include <linux/if_vlan.h> #include <net/tcp.h> #include <net/udp.h> +#include <net/addrconf.h> +#include <net/ndisc.h> +#include <net/ip6_checksum.h> #include <asm/unaligned.h> #include <trace/events/napi.h> @@ -44,6 +47,8 @@ static struct sk_buff_head skb_pool; static atomic_t trapped; +static struct srcu_struct netpoll_srcu; + #define USEC_PER_POLL 50 #define NETPOLL_RX_ENABLED 1 #define NETPOLL_RX_DROP 2 @@ -55,7 +60,8 @@ static atomic_t trapped; MAX_UDP_CHUNK) static void zap_completion_queue(void); -static void netpoll_arp_reply(struct sk_buff *skb, struct netpoll_info *npinfo); +static void netpoll_neigh_reply(struct sk_buff *skb, struct netpoll_info *npinfo); +static void netpoll_async_cleanup(struct work_struct *work); static unsigned int carrier_timeout = 4; module_param(carrier_timeout, uint, 0644); @@ -181,13 +187,13 @@ static void poll_napi(struct net_device *dev) } } -static void service_arp_queue(struct netpoll_info *npi) +static void service_neigh_queue(struct netpoll_info *npi) { if (npi) { struct sk_buff *skb; - while ((skb = skb_dequeue(&npi->arp_tx))) - netpoll_arp_reply(skb, npi); + while ((skb = skb_dequeue(&npi->neigh_tx))) + netpoll_neigh_reply(skb, npi); } } @@ -196,35 +202,76 @@ static void netpoll_poll_dev(struct net_device *dev) const struct net_device_ops *ops; struct netpoll_info *ni = rcu_dereference_bh(dev->npinfo); - if (!dev || !netif_running(dev)) + /* Don't do any rx activity if the dev_lock mutex is held + * the dev_open/close paths use this to block netpoll activity + * while changing device state + */ + if (!mutex_trylock(&ni->dev_lock)) return; + if (!netif_running(dev)) { + mutex_unlock(&ni->dev_lock); + return; + } + ops = dev->netdev_ops; - if (!ops->ndo_poll_controller) + if (!ops->ndo_poll_controller) { + mutex_unlock(&ni->dev_lock); return; + } /* Process pending work on NIC */ ops->ndo_poll_controller(dev); poll_napi(dev); + mutex_unlock(&ni->dev_lock); + if (dev->flags & IFF_SLAVE) { if (ni) { - struct net_device *bond_dev = dev->master; + struct net_device *bond_dev; struct sk_buff *skb; - struct netpoll_info *bond_ni = rcu_dereference_bh(bond_dev->npinfo); - while ((skb = skb_dequeue(&ni->arp_tx))) { + struct netpoll_info *bond_ni; + + bond_dev = netdev_master_upper_dev_get_rcu(dev); + bond_ni = rcu_dereference_bh(bond_dev->npinfo); + while ((skb = skb_dequeue(&ni->neigh_tx))) { skb->dev = bond_dev; - skb_queue_tail(&bond_ni->arp_tx, skb); + skb_queue_tail(&bond_ni->neigh_tx, skb); } } } - service_arp_queue(ni); + service_neigh_queue(ni); zap_completion_queue(); } +int netpoll_rx_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); + if (ni) + mutex_lock(&ni->dev_lock); + srcu_read_unlock(&netpoll_srcu, idx); + return 0; +} +EXPORT_SYMBOL(netpoll_rx_disable); + +void netpoll_rx_enable(struct net_device *dev) +{ + struct netpoll_info *ni; + rcu_read_lock(); + ni = rcu_dereference(dev->npinfo); + if (ni) + mutex_unlock(&ni->dev_lock); + rcu_read_unlock(); +} +EXPORT_SYMBOL(netpoll_rx_enable); + static void refill_skbs(void) { struct sk_buff *skb; @@ -381,9 +428,14 @@ void netpoll_send_udp(struct netpoll *np, const char *msg, int len) struct iphdr *iph; struct ethhdr *eth; static atomic_t ip_ident; + struct ipv6hdr *ip6h; udp_len = len + sizeof(*udph); - ip_len = udp_len + sizeof(*iph); + if (np->ipv6) + ip_len = udp_len + sizeof(*ip6h); + else + ip_len = udp_len + sizeof(*iph); + total_len = ip_len + LL_RESERVED_SPACE(np->dev); skb = find_skb(np, total_len + np->dev->needed_tailroom, @@ -400,34 +452,66 @@ void netpoll_send_udp(struct netpoll *np, const char *msg, int len) udph->source = htons(np->local_port); udph->dest = htons(np->remote_port); udph->len = htons(udp_len); - udph->check = 0; - udph->check = csum_tcpudp_magic(np->local_ip, - np->remote_ip, - udp_len, IPPROTO_UDP, - csum_partial(udph, udp_len, 0)); - if (udph->check == 0) - udph->check = CSUM_MANGLED_0; - - skb_push(skb, sizeof(*iph)); - skb_reset_network_header(skb); - iph = ip_hdr(skb); - - /* iph->version = 4; iph->ihl = 5; */ - put_unaligned(0x45, (unsigned char *)iph); - iph->tos = 0; - put_unaligned(htons(ip_len), &(iph->tot_len)); - iph->id = htons(atomic_inc_return(&ip_ident)); - iph->frag_off = 0; - iph->ttl = 64; - iph->protocol = IPPROTO_UDP; - iph->check = 0; - put_unaligned(np->local_ip, &(iph->saddr)); - put_unaligned(np->remote_ip, &(iph->daddr)); - iph->check = ip_fast_csum((unsigned char *)iph, iph->ihl); - - eth = (struct ethhdr *) skb_push(skb, ETH_HLEN); - skb_reset_mac_header(skb); - skb->protocol = eth->h_proto = htons(ETH_P_IP); + + if (np->ipv6) { + udph->check = 0; + udph->check = csum_ipv6_magic(&np->local_ip.in6, + &np->remote_ip.in6, + udp_len, IPPROTO_UDP, + csum_partial(udph, udp_len, 0)); + if (udph->check == 0) + udph->check = CSUM_MANGLED_0; + + skb_push(skb, sizeof(*ip6h)); + skb_reset_network_header(skb); + ip6h = ipv6_hdr(skb); + + /* ip6h->version = 6; ip6h->priority = 0; */ + put_unaligned(0x60, (unsigned char *)ip6h); + ip6h->flow_lbl[0] = 0; + ip6h->flow_lbl[1] = 0; + ip6h->flow_lbl[2] = 0; + + ip6h->payload_len = htons(sizeof(struct udphdr) + len); + ip6h->nexthdr = IPPROTO_UDP; + ip6h->hop_limit = 32; + ip6h->saddr = np->local_ip.in6; + ip6h->daddr = np->remote_ip.in6; + + eth = (struct ethhdr *) skb_push(skb, ETH_HLEN); + skb_reset_mac_header(skb); + skb->protocol = eth->h_proto = htons(ETH_P_IPV6); + } else { + udph->check = 0; + udph->check = csum_tcpudp_magic(np->local_ip.ip, + np->remote_ip.ip, + udp_len, IPPROTO_UDP, + csum_partial(udph, udp_len, 0)); + if (udph->check == 0) + udph->check = CSUM_MANGLED_0; + + skb_push(skb, sizeof(*iph)); + skb_reset_network_header(skb); + iph = ip_hdr(skb); + + /* iph->version = 4; iph->ihl = 5; */ + put_unaligned(0x45, (unsigned char *)iph); + iph->tos = 0; + put_unaligned(htons(ip_len), &(iph->tot_len)); + iph->id = htons(atomic_inc_return(&ip_ident)); + iph->frag_off = 0; + iph->ttl = 64; + iph->protocol = IPPROTO_UDP; + iph->check = 0; + put_unaligned(np->local_ip.ip, &(iph->saddr)); + put_unaligned(np->remote_ip.ip, &(iph->daddr)); + iph->check = ip_fast_csum((unsigned char *)iph, iph->ihl); + + eth = (struct ethhdr *) skb_push(skb, ETH_HLEN); + skb_reset_mac_header(skb); + skb->protocol = eth->h_proto = htons(ETH_P_IP); + } + memcpy(eth->h_source, np->dev->dev_addr, ETH_ALEN); memcpy(eth->h_dest, np->remote_mac, ETH_ALEN); @@ -437,18 +521,16 @@ void netpoll_send_udp(struct netpoll *np, const char *msg, int len) } EXPORT_SYMBOL(netpoll_send_udp); -static void netpoll_arp_reply(struct sk_buff *skb, struct netpoll_info *npinfo) +static void netpoll_neigh_reply(struct sk_buff *skb, struct netpoll_info *npinfo) { - struct arphdr *arp; - unsigned char *arp_ptr; - int size, type = ARPOP_REPLY, ptype = ETH_P_ARP; + int size, type = ARPOP_REPLY; __be32 sip, tip; unsigned char *sha; struct sk_buff *send_skb; struct netpoll *np, *tmp; unsigned long flags; int hlen, tlen; - int hits = 0; + int hits = 0, proto; if (list_empty(&npinfo->rx_np)) return; @@ -466,94 +548,214 @@ static void netpoll_arp_reply(struct sk_buff *skb, struct netpoll_info *npinfo) if (!hits) return; - /* No arp on this interface */ - if (skb->dev->flags & IFF_NOARP) - return; - - if (!pskb_may_pull(skb, arp_hdr_len(skb->dev))) - return; + proto = ntohs(eth_hdr(skb)->h_proto); + if (proto == ETH_P_IP) { + struct arphdr *arp; + unsigned char *arp_ptr; + /* No arp on this interface */ + if (skb->dev->flags & IFF_NOARP) + return; - skb_reset_network_header(skb); - skb_reset_transport_header(skb); - arp = arp_hdr(skb); + if (!pskb_may_pull(skb, arp_hdr_len(skb->dev))) + return; - if ((arp->ar_hrd != htons(ARPHRD_ETHER) && - arp->ar_hrd != htons(ARPHRD_IEEE802)) || - arp->ar_pro != htons(ETH_P_IP) || - arp->ar_op != htons(ARPOP_REQUEST)) - return; + skb_reset_network_header(skb); + skb_reset_transport_header(skb); + arp = arp_hdr(skb); - arp_ptr = (unsigned char *)(arp+1); - /* save the location of the src hw addr */ - sha = arp_ptr; - arp_ptr += skb->dev->addr_len; - memcpy(&sip, arp_ptr, 4); - arp_ptr += 4; - /* If we actually cared about dst hw addr, - it would get copied here */ - arp_ptr += skb->dev->addr_len; - memcpy(&tip, arp_ptr, 4); - - /* Should we ignore arp? */ - if (ipv4_is_loopback(tip) || ipv4_is_multicast(tip)) - return; + if ((arp->ar_hrd != htons(ARPHRD_ETHER) && + arp->ar_hrd != htons(ARPHRD_IEEE802)) || + arp->ar_pro != htons(ETH_P_IP) || + arp->ar_op != htons(ARPOP_REQUEST)) + return; - size = arp_hdr_len(skb->dev); + arp_ptr = (unsigned char *)(arp+1); + /* save the location of the src hw addr */ + sha = arp_ptr; + arp_ptr += skb->dev->addr_len; + memcpy(&sip, arp_ptr, 4); + arp_ptr += 4; + /* If we actually cared about dst hw addr, + it would get copied here */ + arp_ptr += skb->dev->addr_len; + memcpy(&tip, arp_ptr, 4); - spin_lock_irqsave(&npinfo->rx_lock, flags); - list_for_each_entry_safe(np, tmp, &npinfo->rx_np, rx) { - if (tip != np->local_ip) - continue; + /* Should we ignore arp? */ + if (ipv4_is_loopback(tip) || ipv4_is_multicast(tip)) + return; - hlen = LL_RESERVED_SPACE(np->dev); - tlen = np->dev->needed_tailroom; - send_skb = find_skb(np, size + hlen + tlen, hlen); - if (!send_skb) - continue; + size = arp_hdr_len(skb->dev); - skb_reset_network_header(send_skb); - arp = (struct arphdr *) skb_put(send_skb, size); - send_skb->dev = skb->dev; - send_skb->protocol = htons(ETH_P_ARP); + spin_lock_irqsave(&npinfo->rx_lock, flags); + list_for_each_entry_safe(np, tmp, &npinfo->rx_np, rx) { + if (tip != np->local_ip.ip) + continue; + + hlen = LL_RESERVED_SPACE(np->dev); + tlen = np->dev->needed_tailroom; + send_skb = find_skb(np, size + hlen + tlen, hlen); + if (!send_skb) + continue; + + skb_reset_network_header(send_skb); + arp = (struct arphdr *) skb_put(send_skb, size); + send_skb->dev = skb->dev; + send_skb->protocol = htons(ETH_P_ARP); + + /* Fill the device header for the ARP frame */ + if (dev_hard_header(send_skb, skb->dev, ETH_P_ARP, + sha, np->dev->dev_addr, + send_skb->len) < 0) { + kfree_skb(send_skb); + continue; + } - /* Fill the device header for the ARP frame */ - if (dev_hard_header(send_skb, skb->dev, ptype, - sha, np->dev->dev_addr, - send_skb->len) < 0) { - kfree_skb(send_skb); - continue; + /* + * Fill out the arp protocol part. + * + * we only support ethernet device type, + * which (according to RFC 1390) should + * always equal 1 (Ethernet). + */ + + arp->ar_hrd = htons(np->dev->type); + arp->ar_pro = htons(ETH_P_IP); + arp->ar_hln = np->dev->addr_len; + arp->ar_pln = 4; + arp->ar_op = htons(type); + + arp_ptr = (unsigned char *)(arp + 1); + memcpy(arp_ptr, np->dev->dev_addr, np->dev->addr_len); + arp_ptr += np->dev->addr_len; + memcpy(arp_ptr, &tip, 4); + arp_ptr += 4; + memcpy(arp_ptr, sha, np->dev->addr_len); + arp_ptr += np->dev->addr_len; + memcpy(arp_ptr, &sip, 4); + + netpoll_send_skb(np, send_skb); + + /* If there are several rx_hooks for the same address, + we're fine by sending a single reply */ + break; } + spin_unlock_irqrestore(&npinfo->rx_lock, flags); + } else if( proto == ETH_P_IPV6) { +#if IS_ENABLED(CONFIG_IPV6) + struct nd_msg *msg; + u8 *lladdr = NULL; + struct ipv6hdr *hdr; + struct icmp6hdr *icmp6h; + const struct in6_addr *saddr; + const struct in6_addr *daddr; + struct inet6_dev *in6_dev = NULL; + struct in6_addr *target; + + in6_dev = in6_dev_get(skb->dev); + if (!in6_dev || !in6_dev->cnf.accept_ra) + return; - /* - * Fill out the arp protocol part. - * - * we only support ethernet device type, - * which (according to RFC 1390) should - * always equal 1 (Ethernet). - */ + if (!pskb_may_pull(skb, skb->len)) + return; - arp->ar_hrd = htons(np->dev->type); - arp->ar_pro = htons(ETH_P_IP); - arp->ar_hln = np->dev->addr_len; - arp->ar_pln = 4; - arp->ar_op = htons(type); + msg = (struct nd_msg *)skb_transport_header(skb); - arp_ptr = (unsigned char *)(arp + 1); - memcpy(arp_ptr, np->dev->dev_addr, np->dev->addr_len); - arp_ptr += np->dev->addr_len; - memcpy(arp_ptr, &tip, 4); - arp_ptr += 4; - memcpy(arp_ptr, sha, np->dev->addr_len); - arp_ptr += np->dev->addr_len; - memcpy(arp_ptr, &sip, 4); + __skb_push(skb, skb->data - skb_transport_header(skb)); - netpoll_send_skb(np, send_skb); + if (ipv6_hdr(skb)->hop_limit != 255) + return; + if (msg->icmph.icmp6_code != 0) + return; + if (msg->icmph.icmp6_type != NDISC_NEIGHBOUR_SOLICITATION) + return; + + saddr = &ipv6_hdr(skb)->saddr; + daddr = &ipv6_hdr(skb)->daddr; - /* If there are several rx_hooks for the same address, - we're fine by sending a single reply */ - break; + size = sizeof(struct icmp6hdr) + sizeof(struct in6_addr); + + spin_lock_irqsave(&npinfo->rx_lock, flags); + list_for_each_entry_safe(np, tmp, &npinfo->rx_np, rx) { + if (!ipv6_addr_equal(daddr, &np->local_ip.in6)) + continue; + + hlen = LL_RESERVED_SPACE(np->dev); + tlen = np->dev->needed_tailroom; + send_skb = find_skb(np, size + hlen + tlen, hlen); + if (!send_skb) + continue; + + send_skb->protocol = htons(ETH_P_IPV6); + send_skb->dev = skb->dev; + + skb_reset_network_header(send_skb); + skb_put(send_skb, sizeof(struct ipv6hdr)); + hdr = ipv6_hdr(send_skb); + + *(__be32*)hdr = htonl(0x60000000); + + hdr->payload_len = htons(size); + hdr->nexthdr = IPPROTO_ICMPV6; + hdr->hop_limit = 255; + hdr->saddr = *saddr; + hdr->daddr = *daddr; + + send_skb->transport_header = send_skb->tail; + skb_put(send_skb, size); + + icmp6h = (struct icmp6hdr *)skb_transport_header(skb); + icmp6h->icmp6_type = NDISC_NEIGHBOUR_ADVERTISEMENT; + icmp6h->icmp6_router = 0; + icmp6h->icmp6_solicited = 1; + target = (struct in6_addr *)(skb_transport_header(send_skb) + sizeof(struct icmp6hdr)); + *target = msg->target; + icmp6h->icmp6_cksum = csum_ipv6_magic(saddr, daddr, size, + IPPROTO_ICMPV6, + csum_partial(icmp6h, + size, 0)); + + if (dev_hard_header(send_skb, skb->dev, ETH_P_IPV6, + lladdr, np->dev->dev_addr, + send_skb->len) < 0) { + kfree_skb(send_skb); + continue; + } + + netpoll_send_skb(np, send_skb); + + /* If there are several rx_hooks for the same address, + we're fine by sending a single reply */ + break; + } + spin_unlock_irqrestore(&npinfo->rx_lock, flags); +#endif } - spin_unlock_irqrestore(&npinfo->rx_lock, flags); +} + +static bool pkt_is_ns(struct sk_buff *skb) +{ + struct nd_msg *msg; + struct ipv6hdr *hdr; + + if (skb->protocol != htons(ETH_P_ARP)) + return false; + if (!pskb_may_pull(skb, sizeof(struct ipv6hdr) + sizeof(struct nd_msg))) + return false; + + msg = (struct nd_msg *)skb_transport_header(skb); + __skb_push(skb, skb->data - skb_transport_header(skb)); + hdr = ipv6_hdr(skb); + + if (hdr->nexthdr != IPPROTO_ICMPV6) + return false; + if (hdr->hop_limit != 255) + return false; + if (msg->icmph.icmp6_code != 0) + return false; + if (msg->icmph.icmp6_type != NDISC_NEIGHBOUR_SOLICITATION) + return false; + + return true; } int __netpoll_rx(struct sk_buff *skb, struct netpoll_info *npinfo) @@ -571,9 +773,11 @@ int __netpoll_rx(struct sk_buff *skb, struct netpoll_info *npinfo) goto out; /* check if netpoll clients need ARP */ - if (skb->protocol == htons(ETH_P_ARP) && - atomic_read(&trapped)) { - skb_queue_tail(&npinfo->arp_tx, skb); + if (skb->protocol == htons(ETH_P_ARP) && atomic_read(&trapped)) { + skb_queue_tail(&npinfo->neigh_tx, skb); + return 1; + } else if (pkt_is_ns(skb) && atomic_read(&trapped)) { + skb_queue_tail(&npinfo->neigh_tx, skb); return 1; } @@ -584,60 +788,100 @@ int __netpoll_rx(struct sk_buff *skb, struct netpoll_info *npinfo) } proto = ntohs(eth_hdr(skb)->h_proto); - if (proto != ETH_P_IP) + if (proto != ETH_P_IP && proto != ETH_P_IPV6) goto out; if (skb->pkt_type == PACKET_OTHERHOST) goto out; if (skb_shared(skb)) goto out; - if (!pskb_may_pull(skb, sizeof(struct iphdr))) - goto out; - iph = (struct iphdr *)skb->data; - if (iph->ihl < 5 || iph->version != 4) - goto out; - if (!pskb_may_pull(skb, iph->ihl*4)) - goto out; - iph = (struct iphdr *)skb->data; - if (ip_fast_csum((u8 *)iph, iph->ihl) != 0) - goto out; - - len = ntohs(iph->tot_len); - if (skb->len < len || len < iph->ihl*4) - goto out; + if (proto == ETH_P_IP) { + if (!pskb_may_pull(skb, sizeof(struct iphdr))) + goto out; + iph = (struct iphdr *)skb->data; + if (iph->ihl < 5 || iph->version != 4) + goto out; + if (!pskb_may_pull(skb, iph->ihl*4)) + goto out; + iph = (struct iphdr *)skb->data; + if (ip_fast_csum((u8 *)iph, iph->ihl) != 0) + goto out; - /* - * Our transport medium may have padded the buffer out. - * Now We trim to the true length of the frame. - */ - if (pskb_trim_rcsum(skb, len)) - goto out; + len = ntohs(iph->tot_len); + if (skb->len < len || len < iph->ihl*4) + goto out; - iph = (struct iphdr *)skb->data; - if (iph->protocol != IPPROTO_UDP) - goto out; + /* + * Our transport medium may have padded the buffer out. + * Now We trim to the true length of the frame. + */ + if (pskb_trim_rcsum(skb, len)) + goto out; - len -= iph->ihl*4; - uh = (struct udphdr *)(((char *)iph) + iph->ihl*4); - ulen = ntohs(uh->len); + iph = (struct iphdr *)skb->data; + if (iph->protocol != IPPROTO_UDP) + goto out; - if (ulen != len) - goto out; - if (checksum_udp(skb, uh, ulen, iph->saddr, iph->daddr)) - goto out; + len -= iph->ihl*4; + uh = (struct udphdr *)(((char *)iph) + iph->ihl*4); + ulen = ntohs(uh->len); - list_for_each_entry_safe(np, tmp, &npinfo->rx_np, rx) { - if (np->local_ip && np->local_ip != iph->daddr) - continue; - if (np->remote_ip && np->remote_ip != iph->saddr) - continue; - if (np->local_port && np->local_port != ntohs(uh->dest)) - continue; + if (ulen != len) + goto out; + if (checksum_udp(skb, uh, ulen, iph->saddr, iph->daddr)) + goto out; + list_for_each_entry_safe(np, tmp, &npinfo->rx_np, rx) { + if (np->local_ip.ip && np->local_ip.ip != iph->daddr) + continue; + if (np->remote_ip.ip && np->remote_ip.ip != iph->saddr) + continue; + if (np->local_port && np->local_port != ntohs(uh->dest)) + continue; + + np->rx_hook(np, ntohs(uh->source), + (char *)(uh+1), + ulen - sizeof(struct udphdr)); + hits++; + } + } else { +#if IS_ENABLED(CONFIG_IPV6) + const struct ipv6hdr *ip6h; - np->rx_hook(np, ntohs(uh->source), - (char *)(uh+1), - ulen - sizeof(struct udphdr)); - hits++; + if (!pskb_may_pull(skb, sizeof(struct ipv6hdr))) + goto out; + ip6h = (struct ipv6hdr *)skb->data; + if (ip6h->version != 6) + goto out; + len = ntohs(ip6h->payload_len); + if (!len) + goto out; + if (len + sizeof(struct ipv6hdr) > skb->len) + goto out; + if (pskb_trim_rcsum(skb, len + sizeof(struct ipv6hdr))) + goto out; + ip6h = ipv6_hdr(skb); + if (!pskb_may_pull(skb, sizeof(struct udphdr))) + goto out; + uh = udp_hdr(skb); + ulen = ntohs(uh->len); + if (ulen != skb->len) + goto out; + if (udp6_csum_init(skb, uh, IPPROTO_UDP)) + goto out; + list_for_each_entry_safe(np, tmp, &npinfo->rx_np, rx) { + if (!ipv6_addr_equal(&np->local_ip.in6, &ip6h->daddr)) + continue; + if (!ipv6_addr_equal(&np->remote_ip.in6, &ip6h->saddr)) + continue; + if (np->local_port && np->local_port != ntohs(uh->dest)) + continue; + + np->rx_hook(np, ntohs(uh->source), + (char *)(uh+1), + ulen - sizeof(struct udphdr)); + hits++; + } +#endif } if (!hits) @@ -658,17 +902,44 @@ out: void netpoll_print_options(struct netpoll *np) { np_info(np, "local port %d\n", np->local_port); - np_info(np, "local IP %pI4\n", &np->local_ip); + if (np->ipv6) + np_info(np, "local IPv6 address %pI6c\n", &np->local_ip.in6); + else + np_info(np, "local IPv4 address %pI4\n", &np->local_ip.ip); np_info(np, "interface '%s'\n", np->dev_name); np_info(np, "remote port %d\n", np->remote_port); - np_info(np, "remote IP %pI4\n", &np->remote_ip); + if (np->ipv6) + np_info(np, "remote IPv6 address %pI6c\n", &np->remote_ip.in6); + else + np_info(np, "remote IPv4 address %pI4\n", &np->remote_ip.ip); np_info(np, "remote ethernet address %pM\n", np->remote_mac); } EXPORT_SYMBOL(netpoll_print_options); +static int netpoll_parse_ip_addr(const char *str, union inet_addr *addr) +{ + const char *end; + + if (!strchr(str, ':') && + in4_pton(str, -1, (void *)addr, -1, &end) > 0) { + if (!*end) + return 0; + } + if (in6_pton(str, -1, addr->in6.s6_addr, -1, &end) > 0) { +#if IS_ENABLED(CONFIG_IPV6) + if (!*end) + return 1; +#else + return -1; +#endif + } + return -1; +} + int netpoll_parse_options(struct netpoll *np, char *opt) { char *cur=opt, *delim; + int ipv6; if (*cur != '@') { if ((delim = strchr(cur, '@')) == NULL) @@ -684,7 +955,11 @@ int netpoll_parse_options(struct netpoll *np, char *opt) if ((delim = strchr(cur, '/')) == NULL) goto parse_failed; *delim = 0; - np->local_ip = in_aton(cur); + ipv6 = netpoll_parse_ip_addr(cur, &np->local_ip); + if (ipv6 < 0) + goto parse_failed; + else + np->ipv6 = (bool)ipv6; cur = delim; } cur++; @@ -716,7 +991,13 @@ int netpoll_parse_options(struct netpoll *np, char *opt) if ((delim = strchr(cur, '/')) == NULL) goto parse_failed; *delim = 0; - np->remote_ip = in_aton(cur); + ipv6 = netpoll_parse_ip_addr(cur, &np->remote_ip); + if (ipv6 < 0) + goto parse_failed; + else if (np->ipv6 != (bool)ipv6) + goto parse_failed; + else + np->ipv6 = (bool)ipv6; cur = delim + 1; if (*cur != 0) { @@ -744,6 +1025,7 @@ int __netpoll_setup(struct netpoll *np, struct net_device *ndev, gfp_t gfp) np->dev = ndev; strlcpy(np->dev_name, ndev->name, IFNAMSIZ); + INIT_WORK(&np->cleanup_work, netpoll_async_cleanup); if ((ndev->priv_flags & IFF_DISABLE_NETPOLL) || !ndev->netdev_ops->ndo_poll_controller) { @@ -764,7 +1046,8 @@ int __netpoll_setup(struct netpoll *np, struct net_device *ndev, gfp_t gfp) INIT_LIST_HEAD(&npinfo->rx_np); spin_lock_init(&npinfo->rx_lock); - skb_queue_head_init(&npinfo->arp_tx); + mutex_init(&npinfo->dev_lock); + skb_queue_head_init(&npinfo->neigh_tx); skb_queue_head_init(&npinfo->txq); INIT_DELAYED_WORK(&npinfo->tx_work, queue_process); @@ -777,7 +1060,7 @@ int __netpoll_setup(struct netpoll *np, struct net_device *ndev, gfp_t gfp) goto free_npinfo; } } else { - npinfo = ndev->npinfo; + npinfo = rtnl_dereference(ndev->npinfo); atomic_inc(&npinfo->refcnt); } @@ -808,14 +1091,19 @@ int netpoll_setup(struct netpoll *np) struct in_device *in_dev; int err; - if (np->dev_name) - ndev = dev_get_by_name(&init_net, np->dev_name); + rtnl_lock(); + if (np->dev_name) { + struct net *net = current->nsproxy->net_ns; + ndev = __dev_get_by_name(net, np->dev_name); + } if (!ndev) { np_err(np, "%s doesn't exist, aborting\n", np->dev_name); - return -ENODEV; + err = -ENODEV; + goto unlock; } + dev_hold(ndev); - if (ndev->master) { + if (netdev_master_upper_dev_get(ndev)) { np_err(np, "%s is a slave device, aborting\n", np->dev_name); err = -EBUSY; goto put; @@ -826,15 +1114,14 @@ int netpoll_setup(struct netpoll *np) np_info(np, "device %s not up yet, forcing it\n", np->dev_name); - rtnl_lock(); err = dev_open(ndev); - rtnl_unlock(); if (err) { np_err(np, "failed to open %s\n", ndev->name); goto put; } + rtnl_unlock(); atleast = jiffies + HZ/10; atmost = jiffies + carrier_timeout * HZ; while (!netif_carrier_ok(ndev)) { @@ -854,39 +1141,70 @@ int netpoll_setup(struct netpoll *np) np_notice(np, "carrier detect appears untrustworthy, waiting 4 seconds\n"); msleep(4000); } + rtnl_lock(); } - if (!np->local_ip) { - rcu_read_lock(); - in_dev = __in_dev_get_rcu(ndev); + if (!np->local_ip.ip) { + if (!np->ipv6) { + in_dev = __in_dev_get_rtnl(ndev); + + if (!in_dev || !in_dev->ifa_list) { + np_err(np, "no IP address for %s, aborting\n", + np->dev_name); + err = -EDESTADDRREQ; + goto put; + } + + np->local_ip.ip = in_dev->ifa_list->ifa_local; + np_info(np, "local IP %pI4\n", &np->local_ip.ip); + } else { +#if IS_ENABLED(CONFIG_IPV6) + struct inet6_dev *idev; - if (!in_dev || !in_dev->ifa_list) { - rcu_read_unlock(); - np_err(np, "no IP address for %s, aborting\n", - np->dev_name); err = -EDESTADDRREQ; + idev = __in6_dev_get(ndev); + if (idev) { + struct inet6_ifaddr *ifp; + + read_lock_bh(&idev->lock); + list_for_each_entry(ifp, &idev->addr_list, if_list) { + if (ipv6_addr_type(&ifp->addr) & IPV6_ADDR_LINKLOCAL) + continue; + np->local_ip.in6 = ifp->addr; + err = 0; + break; + } + read_unlock_bh(&idev->lock); + } + if (err) { + np_err(np, "no IPv6 address for %s, aborting\n", + np->dev_name); + goto put; + } else + np_info(np, "local IPv6 %pI6c\n", &np->local_ip.in6); +#else + np_err(np, "IPv6 is not supported %s, aborting\n", + np->dev_name); + err = -EINVAL; goto put; +#endif } - - np->local_ip = in_dev->ifa_list->ifa_local; - rcu_read_unlock(); - np_info(np, "local IP %pI4\n", &np->local_ip); } /* fill up the skb queue */ refill_skbs(); - rtnl_lock(); err = __netpoll_setup(np, ndev, GFP_KERNEL); - rtnl_unlock(); - if (err) goto put; + rtnl_unlock(); return 0; put: dev_put(ndev); +unlock: + rtnl_unlock(); return err; } EXPORT_SYMBOL(netpoll_setup); @@ -894,6 +1212,7 @@ EXPORT_SYMBOL(netpoll_setup); static int __init netpoll_init(void) { skb_queue_head_init(&skb_pool); + init_srcu_struct(&netpoll_srcu); return 0; } core_initcall(netpoll_init); @@ -903,7 +1222,7 @@ static void rcu_cleanup_netpoll_info(struct rcu_head *rcu_head) struct netpoll_info *npinfo = container_of(rcu_head, struct netpoll_info, rcu); - skb_queue_purge(&npinfo->arp_tx); + skb_queue_purge(&npinfo->neigh_tx); skb_queue_purge(&npinfo->txq); /* we can't call cancel_delayed_work_sync here, as we are in softirq */ @@ -921,7 +1240,11 @@ void __netpoll_cleanup(struct netpoll *np) struct netpoll_info *npinfo; unsigned long flags; - npinfo = np->dev->npinfo; + /* rtnl_dereference would be preferable here but + * rcu_cleanup_netpoll path can put us in here safely without + * holding the rtnl, so plain rcu_dereference it is + */ + npinfo = rtnl_dereference(np->dev->npinfo); if (!npinfo) return; @@ -933,6 +1256,8 @@ void __netpoll_cleanup(struct netpoll *np) spin_unlock_irqrestore(&npinfo->rx_lock, flags); } + synchronize_srcu(&netpoll_srcu); + if (atomic_dec_and_test(&npinfo->refcnt)) { const struct net_device_ops *ops; @@ -940,25 +1265,27 @@ void __netpoll_cleanup(struct netpoll *np) if (ops->ndo_netpoll_cleanup) ops->ndo_netpoll_cleanup(np->dev); - RCU_INIT_POINTER(np->dev->npinfo, NULL); + rcu_assign_pointer(np->dev->npinfo, NULL); call_rcu_bh(&npinfo->rcu, rcu_cleanup_netpoll_info); } } EXPORT_SYMBOL_GPL(__netpoll_cleanup); -static void rcu_cleanup_netpoll(struct rcu_head *rcu_head) +static void netpoll_async_cleanup(struct work_struct *work) { - struct netpoll *np = container_of(rcu_head, struct netpoll, rcu); + struct netpoll *np = container_of(work, struct netpoll, cleanup_work); + rtnl_lock(); __netpoll_cleanup(np); + rtnl_unlock(); kfree(np); } -void __netpoll_free_rcu(struct netpoll *np) +void __netpoll_free_async(struct netpoll *np) { - call_rcu_bh(&np->rcu, rcu_cleanup_netpoll); + schedule_work(&np->cleanup_work); } -EXPORT_SYMBOL_GPL(__netpoll_free_rcu); +EXPORT_SYMBOL_GPL(__netpoll_free_async); void netpoll_cleanup(struct netpoll *np) { diff --git a/net/core/netprio_cgroup.c b/net/core/netprio_cgroup.c index 5e67defe2cb0..0777d0aa18c3 100644 --- a/net/core/netprio_cgroup.c +++ b/net/core/netprio_cgroup.c @@ -69,10 +69,8 @@ static int extend_netdev_table(struct net_device *dev, u32 target_idx) /* allocate & copy */ new = kzalloc(new_sz, GFP_KERNEL); - if (!new) { - pr_warn("Unable to alloc new priomap!\n"); + if (!new) return -ENOMEM; - } if (old) memcpy(new->priomap, old->priomap, diff --git a/net/core/pktgen.c b/net/core/pktgen.c index b29dacf900f9..2201e699ad67 100644 --- a/net/core/pktgen.c +++ b/net/core/pktgen.c @@ -164,6 +164,7 @@ #ifdef CONFIG_XFRM #include <net/xfrm.h> #endif +#include <net/netns/generic.h> #include <asm/byteorder.h> #include <linux/rcupdate.h> #include <linux/bitops.h> @@ -212,7 +213,6 @@ #define PKTGEN_MAGIC 0xbe9be955 #define PG_PROC_DIR "pktgen" #define PGCTRL "pgctrl" -static struct proc_dir_entry *pg_proc_dir; #define MAX_CFLOWS 65536 @@ -397,7 +397,15 @@ struct pktgen_hdr { __be32 tv_usec; }; -static bool pktgen_exiting __read_mostly; + +static int pg_net_id __read_mostly; + +struct pktgen_net { + struct net *net; + struct proc_dir_entry *proc_dir; + struct list_head pktgen_threads; + bool pktgen_exiting; +}; struct pktgen_thread { spinlock_t if_lock; /* for list of devices */ @@ -414,6 +422,7 @@ struct pktgen_thread { wait_queue_head_t queue; struct completion start_done; + struct pktgen_net *net; }; #define REMOVE 1 @@ -428,9 +437,9 @@ static int pktgen_add_device(struct pktgen_thread *t, const char *ifname); static struct pktgen_dev *pktgen_find_dev(struct pktgen_thread *t, const char *ifname, bool exact); static int pktgen_device_event(struct notifier_block *, unsigned long, void *); -static void pktgen_run_all_threads(void); -static void pktgen_reset_all_threads(void); -static void pktgen_stop_all_threads_ifs(void); +static void pktgen_run_all_threads(struct pktgen_net *pn); +static void pktgen_reset_all_threads(struct pktgen_net *pn); +static void pktgen_stop_all_threads_ifs(struct pktgen_net *pn); static void pktgen_stop(struct pktgen_thread *t); static void pktgen_clear_counters(struct pktgen_dev *pkt_dev); @@ -442,7 +451,6 @@ static int pg_clone_skb_d __read_mostly; static int debug __read_mostly; static DEFINE_MUTEX(pktgen_thread_lock); -static LIST_HEAD(pktgen_threads); static struct notifier_block pktgen_notifier_block = { .notifier_call = pktgen_device_event, @@ -464,6 +472,7 @@ static ssize_t pgctrl_write(struct file *file, const char __user *buf, { int err = 0; char data[128]; + struct pktgen_net *pn = net_generic(current->nsproxy->net_ns, pg_net_id); if (!capable(CAP_NET_ADMIN)) { err = -EPERM; @@ -480,13 +489,13 @@ static ssize_t pgctrl_write(struct file *file, const char __user *buf, data[count - 1] = 0; /* Make string */ if (!strcmp(data, "stop")) - pktgen_stop_all_threads_ifs(); + pktgen_stop_all_threads_ifs(pn); else if (!strcmp(data, "start")) - pktgen_run_all_threads(); + pktgen_run_all_threads(pn); else if (!strcmp(data, "reset")) - pktgen_reset_all_threads(); + pktgen_reset_all_threads(pn); else pr_warning("Unknown command: %s\n", data); @@ -1781,10 +1790,13 @@ static ssize_t pktgen_thread_write(struct file *file, return -EFAULT; i += len; mutex_lock(&pktgen_thread_lock); - pktgen_add_device(t, f); + ret = pktgen_add_device(t, f); mutex_unlock(&pktgen_thread_lock); - ret = count; - sprintf(pg_result, "OK: add_device=%s", f); + if (!ret) { + ret = count; + sprintf(pg_result, "OK: add_device=%s", f); + } else + sprintf(pg_result, "ERROR: can not add device %s", f); goto out; } @@ -1824,13 +1836,14 @@ static const struct file_operations pktgen_thread_fops = { }; /* Think find or remove for NN */ -static struct pktgen_dev *__pktgen_NN_threads(const char *ifname, int remove) +static struct pktgen_dev *__pktgen_NN_threads(const struct pktgen_net *pn, + const char *ifname, int remove) { struct pktgen_thread *t; struct pktgen_dev *pkt_dev = NULL; bool exact = (remove == FIND); - list_for_each_entry(t, &pktgen_threads, th_list) { + list_for_each_entry(t, &pn->pktgen_threads, th_list) { pkt_dev = pktgen_find_dev(t, ifname, exact); if (pkt_dev) { if (remove) { @@ -1848,7 +1861,7 @@ static struct pktgen_dev *__pktgen_NN_threads(const char *ifname, int remove) /* * mark a device for removal */ -static void pktgen_mark_device(const char *ifname) +static void pktgen_mark_device(const struct pktgen_net *pn, const char *ifname) { struct pktgen_dev *pkt_dev = NULL; const int max_tries = 10, msec_per_try = 125; @@ -1859,7 +1872,7 @@ static void pktgen_mark_device(const char *ifname) while (1) { - pkt_dev = __pktgen_NN_threads(ifname, REMOVE); + pkt_dev = __pktgen_NN_threads(pn, ifname, REMOVE); if (pkt_dev == NULL) break; /* success */ @@ -1880,21 +1893,21 @@ static void pktgen_mark_device(const char *ifname) mutex_unlock(&pktgen_thread_lock); } -static void pktgen_change_name(struct net_device *dev) +static void pktgen_change_name(const struct pktgen_net *pn, struct net_device *dev) { struct pktgen_thread *t; - list_for_each_entry(t, &pktgen_threads, th_list) { + list_for_each_entry(t, &pn->pktgen_threads, th_list) { struct pktgen_dev *pkt_dev; list_for_each_entry(pkt_dev, &t->if_list, list) { if (pkt_dev->odev != dev) continue; - remove_proc_entry(pkt_dev->entry->name, pg_proc_dir); + remove_proc_entry(pkt_dev->entry->name, pn->proc_dir); pkt_dev->entry = proc_create_data(dev->name, 0600, - pg_proc_dir, + pn->proc_dir, &pktgen_if_fops, pkt_dev); if (!pkt_dev->entry) @@ -1909,8 +1922,9 @@ static int pktgen_device_event(struct notifier_block *unused, unsigned long event, void *ptr) { struct net_device *dev = ptr; + struct pktgen_net *pn = net_generic(dev_net(dev), pg_net_id); - if (!net_eq(dev_net(dev), &init_net) || pktgen_exiting) + if (pn->pktgen_exiting) return NOTIFY_DONE; /* It is OK that we do not hold the group lock right now, @@ -1919,18 +1933,19 @@ static int pktgen_device_event(struct notifier_block *unused, switch (event) { case NETDEV_CHANGENAME: - pktgen_change_name(dev); + pktgen_change_name(pn, dev); break; case NETDEV_UNREGISTER: - pktgen_mark_device(dev->name); + pktgen_mark_device(pn, dev->name); break; } return NOTIFY_DONE; } -static struct net_device *pktgen_dev_get_by_name(struct pktgen_dev *pkt_dev, +static struct net_device *pktgen_dev_get_by_name(const struct pktgen_net *pn, + struct pktgen_dev *pkt_dev, const char *ifname) { char b[IFNAMSIZ+5]; @@ -1944,13 +1959,14 @@ static struct net_device *pktgen_dev_get_by_name(struct pktgen_dev *pkt_dev, } b[i] = 0; - return dev_get_by_name(&init_net, b); + return dev_get_by_name(pn->net, b); } /* Associate pktgen_dev with a device. */ -static int pktgen_setup_dev(struct pktgen_dev *pkt_dev, const char *ifname) +static int pktgen_setup_dev(const struct pktgen_net *pn, + struct pktgen_dev *pkt_dev, const char *ifname) { struct net_device *odev; int err; @@ -1961,7 +1977,7 @@ static int pktgen_setup_dev(struct pktgen_dev *pkt_dev, const char *ifname) pkt_dev->odev = NULL; } - odev = pktgen_dev_get_by_name(pkt_dev, ifname); + odev = pktgen_dev_get_by_name(pn, pkt_dev, ifname); if (!odev) { pr_err("no such netdevice: \"%s\"\n", ifname); return -ENODEV; @@ -2203,9 +2219,10 @@ static inline int f_pick(struct pktgen_dev *pkt_dev) static void get_ipsec_sa(struct pktgen_dev *pkt_dev, int flow) { struct xfrm_state *x = pkt_dev->flows[flow].x; + struct pktgen_net *pn = net_generic(dev_net(pkt_dev->odev), pg_net_id); if (!x) { /*slow path: we dont already have xfrm_state*/ - x = xfrm_stateonly_find(&init_net, DUMMY_MARK, + x = xfrm_stateonly_find(pn->net, DUMMY_MARK, (xfrm_address_t *)&pkt_dev->cur_daddr, (xfrm_address_t *)&pkt_dev->cur_saddr, AF_INET, @@ -2912,7 +2929,7 @@ static void pktgen_run(struct pktgen_thread *t) t->control &= ~(T_STOP); } -static void pktgen_stop_all_threads_ifs(void) +static void pktgen_stop_all_threads_ifs(struct pktgen_net *pn) { struct pktgen_thread *t; @@ -2920,7 +2937,7 @@ static void pktgen_stop_all_threads_ifs(void) mutex_lock(&pktgen_thread_lock); - list_for_each_entry(t, &pktgen_threads, th_list) + list_for_each_entry(t, &pn->pktgen_threads, th_list) t->control |= T_STOP; mutex_unlock(&pktgen_thread_lock); @@ -2956,28 +2973,28 @@ signal: return 0; } -static int pktgen_wait_all_threads_run(void) +static int pktgen_wait_all_threads_run(struct pktgen_net *pn) { struct pktgen_thread *t; int sig = 1; mutex_lock(&pktgen_thread_lock); - list_for_each_entry(t, &pktgen_threads, th_list) { + list_for_each_entry(t, &pn->pktgen_threads, th_list) { sig = pktgen_wait_thread_run(t); if (sig == 0) break; } if (sig == 0) - list_for_each_entry(t, &pktgen_threads, th_list) + list_for_each_entry(t, &pn->pktgen_threads, th_list) t->control |= (T_STOP); mutex_unlock(&pktgen_thread_lock); return sig; } -static void pktgen_run_all_threads(void) +static void pktgen_run_all_threads(struct pktgen_net *pn) { struct pktgen_thread *t; @@ -2985,7 +3002,7 @@ static void pktgen_run_all_threads(void) mutex_lock(&pktgen_thread_lock); - list_for_each_entry(t, &pktgen_threads, th_list) + list_for_each_entry(t, &pn->pktgen_threads, th_list) t->control |= (T_RUN); mutex_unlock(&pktgen_thread_lock); @@ -2993,10 +3010,10 @@ static void pktgen_run_all_threads(void) /* Propagate thread->control */ schedule_timeout_interruptible(msecs_to_jiffies(125)); - pktgen_wait_all_threads_run(); + pktgen_wait_all_threads_run(pn); } -static void pktgen_reset_all_threads(void) +static void pktgen_reset_all_threads(struct pktgen_net *pn) { struct pktgen_thread *t; @@ -3004,7 +3021,7 @@ static void pktgen_reset_all_threads(void) mutex_lock(&pktgen_thread_lock); - list_for_each_entry(t, &pktgen_threads, th_list) + list_for_each_entry(t, &pn->pktgen_threads, th_list) t->control |= (T_REMDEVALL); mutex_unlock(&pktgen_thread_lock); @@ -3012,7 +3029,7 @@ static void pktgen_reset_all_threads(void) /* Propagate thread->control */ schedule_timeout_interruptible(msecs_to_jiffies(125)); - pktgen_wait_all_threads_run(); + pktgen_wait_all_threads_run(pn); } static void show_results(struct pktgen_dev *pkt_dev, int nr_frags) @@ -3154,9 +3171,7 @@ static void pktgen_rem_all_ifs(struct pktgen_thread *t) static void pktgen_rem_thread(struct pktgen_thread *t) { /* Remove from the thread list */ - - remove_proc_entry(t->tsk->comm, pg_proc_dir); - + remove_proc_entry(t->tsk->comm, t->net->proc_dir); } static void pktgen_resched(struct pktgen_dev *pkt_dev) @@ -3302,7 +3317,7 @@ static int pktgen_thread_worker(void *arg) pkt_dev = next_to_run(t); if (unlikely(!pkt_dev && t->control == 0)) { - if (pktgen_exiting) + if (t->net->pktgen_exiting) break; wait_event_interruptible_timeout(t->queue, t->control != 0, @@ -3424,7 +3439,7 @@ static int pktgen_add_device(struct pktgen_thread *t, const char *ifname) /* We don't allow a device to be on several threads */ - pkt_dev = __pktgen_NN_threads(ifname, FIND); + pkt_dev = __pktgen_NN_threads(t->net, ifname, FIND); if (pkt_dev) { pr_err("ERROR: interface already used\n"); return -EBUSY; @@ -3459,13 +3474,13 @@ static int pktgen_add_device(struct pktgen_thread *t, const char *ifname) pkt_dev->svlan_id = 0xffff; pkt_dev->node = -1; - err = pktgen_setup_dev(pkt_dev, ifname); + err = pktgen_setup_dev(t->net, pkt_dev, ifname); if (err) goto out1; if (pkt_dev->odev->priv_flags & IFF_TX_SKB_SHARING) pkt_dev->clone_skb = pg_clone_skb_d; - pkt_dev->entry = proc_create_data(ifname, 0600, pg_proc_dir, + pkt_dev->entry = proc_create_data(ifname, 0600, t->net->proc_dir, &pktgen_if_fops, pkt_dev); if (!pkt_dev->entry) { pr_err("cannot create %s/%s procfs entry\n", @@ -3490,7 +3505,7 @@ out1: return err; } -static int __init pktgen_create_thread(int cpu) +static int __net_init pktgen_create_thread(int cpu, struct pktgen_net *pn) { struct pktgen_thread *t; struct proc_dir_entry *pe; @@ -3508,7 +3523,7 @@ static int __init pktgen_create_thread(int cpu) INIT_LIST_HEAD(&t->if_list); - list_add_tail(&t->th_list, &pktgen_threads); + list_add_tail(&t->th_list, &pn->pktgen_threads); init_completion(&t->start_done); p = kthread_create_on_node(pktgen_thread_worker, @@ -3524,7 +3539,7 @@ static int __init pktgen_create_thread(int cpu) kthread_bind(p, cpu); t->tsk = p; - pe = proc_create_data(t->tsk->comm, 0600, pg_proc_dir, + pe = proc_create_data(t->tsk->comm, 0600, pn->proc_dir, &pktgen_thread_fops, t); if (!pe) { pr_err("cannot create %s/%s procfs entry\n", @@ -3535,6 +3550,7 @@ static int __init pktgen_create_thread(int cpu) return -EINVAL; } + t->net = pn; wake_up_process(p); wait_for_completion(&t->start_done); @@ -3560,6 +3576,7 @@ static void _rem_dev_from_if_list(struct pktgen_thread *t, static int pktgen_remove_device(struct pktgen_thread *t, struct pktgen_dev *pkt_dev) { + struct pktgen_net *pn = t->net; pr_debug("remove_device pkt_dev=%p\n", pkt_dev); @@ -3580,7 +3597,7 @@ static int pktgen_remove_device(struct pktgen_thread *t, _rem_dev_from_if_list(t, pkt_dev); if (pkt_dev->entry) - remove_proc_entry(pkt_dev->entry->name, pg_proc_dir); + remove_proc_entry(pkt_dev->entry->name, pn->proc_dir); #ifdef CONFIG_XFRM free_SAs(pkt_dev); @@ -3592,63 +3609,63 @@ static int pktgen_remove_device(struct pktgen_thread *t, return 0; } -static int __init pg_init(void) +static int __net_init pg_net_init(struct net *net) { - int cpu; + struct pktgen_net *pn = net_generic(net, pg_net_id); struct proc_dir_entry *pe; - int ret = 0; - - pr_info("%s", version); - - pg_proc_dir = proc_mkdir(PG_PROC_DIR, init_net.proc_net); - if (!pg_proc_dir) + int cpu, ret = 0; + + pn->net = net; + INIT_LIST_HEAD(&pn->pktgen_threads); + pn->pktgen_exiting = false; + pn->proc_dir = proc_mkdir(PG_PROC_DIR, pn->net->proc_net); + if (!pn->proc_dir) { + pr_warn("cannot create /proc/net/%s\n", PG_PROC_DIR); return -ENODEV; - - pe = proc_create(PGCTRL, 0600, pg_proc_dir, &pktgen_fops); + } + pe = proc_create(PGCTRL, 0600, pn->proc_dir, &pktgen_fops); if (pe == NULL) { - pr_err("ERROR: cannot create %s procfs entry\n", PGCTRL); + pr_err("cannot create %s procfs entry\n", PGCTRL); ret = -EINVAL; - goto remove_dir; + goto remove; } - register_netdevice_notifier(&pktgen_notifier_block); - for_each_online_cpu(cpu) { int err; - err = pktgen_create_thread(cpu); + err = pktgen_create_thread(cpu, pn); if (err) - pr_warning("WARNING: Cannot create thread for cpu %d (%d)\n", + pr_warn("Cannot create thread for cpu %d (%d)\n", cpu, err); } - if (list_empty(&pktgen_threads)) { - pr_err("ERROR: Initialization failed for all threads\n"); + if (list_empty(&pn->pktgen_threads)) { + pr_err("Initialization failed for all threads\n"); ret = -ENODEV; - goto unregister; + goto remove_entry; } return 0; - unregister: - unregister_netdevice_notifier(&pktgen_notifier_block); - remove_proc_entry(PGCTRL, pg_proc_dir); - remove_dir: - proc_net_remove(&init_net, PG_PROC_DIR); +remove_entry: + remove_proc_entry(PGCTRL, pn->proc_dir); +remove: + proc_net_remove(pn->net, PG_PROC_DIR); return ret; } -static void __exit pg_cleanup(void) +static void __net_exit pg_net_exit(struct net *net) { + struct pktgen_net *pn = net_generic(net, pg_net_id); struct pktgen_thread *t; struct list_head *q, *n; LIST_HEAD(list); /* Stop all interfaces & threads */ - pktgen_exiting = true; + pn->pktgen_exiting = true; mutex_lock(&pktgen_thread_lock); - list_splice_init(&pktgen_threads, &list); + list_splice_init(&pn->pktgen_threads, &list); mutex_unlock(&pktgen_thread_lock); list_for_each_safe(q, n, &list) { @@ -3658,12 +3675,36 @@ static void __exit pg_cleanup(void) kfree(t); } - /* Un-register us from receiving netdevice events */ - unregister_netdevice_notifier(&pktgen_notifier_block); + remove_proc_entry(PGCTRL, pn->proc_dir); + proc_net_remove(pn->net, PG_PROC_DIR); +} + +static struct pernet_operations pg_net_ops = { + .init = pg_net_init, + .exit = pg_net_exit, + .id = &pg_net_id, + .size = sizeof(struct pktgen_net), +}; + +static int __init pg_init(void) +{ + int ret = 0; - /* Clean up proc file system */ - remove_proc_entry(PGCTRL, pg_proc_dir); - proc_net_remove(&init_net, PG_PROC_DIR); + pr_info("%s", version); + ret = register_pernet_subsys(&pg_net_ops); + if (ret) + return ret; + ret = register_netdevice_notifier(&pktgen_notifier_block); + if (ret) + unregister_pernet_subsys(&pg_net_ops); + + return ret; +} + +static void __exit pg_cleanup(void) +{ + unregister_netdevice_notifier(&pktgen_notifier_block); + unregister_pernet_subsys(&pg_net_ops); } module_init(pg_init); diff --git a/net/core/request_sock.c b/net/core/request_sock.c index c31d9e8668c3..4425148d2b51 100644 --- a/net/core/request_sock.c +++ b/net/core/request_sock.c @@ -186,8 +186,6 @@ void reqsk_fastopen_remove(struct sock *sk, struct request_sock *req, struct fastopen_queue *fastopenq = inet_csk(lsk)->icsk_accept_queue.fastopenq; - BUG_ON(!spin_is_locked(&sk->sk_lock.slock) && !sock_owned_by_user(sk)); - tcp_sk(sk)->fastopen_rsk = NULL; spin_lock_bh(&fastopenq->lock); fastopenq->qlen--; diff --git a/net/core/rtnetlink.c b/net/core/rtnetlink.c index 1868625af25e..d8aa20f6a46e 100644 --- a/net/core/rtnetlink.c +++ b/net/core/rtnetlink.c @@ -780,6 +780,7 @@ static noinline size_t if_nlmsg_size(const struct net_device *dev, + nla_total_size(4) /* IFLA_MTU */ + nla_total_size(4) /* IFLA_LINK */ + nla_total_size(4) /* IFLA_MASTER */ + + nla_total_size(1) /* IFLA_CARRIER */ + nla_total_size(4) /* IFLA_PROMISCUITY */ + nla_total_size(4) /* IFLA_NUM_TX_QUEUES */ + nla_total_size(4) /* IFLA_NUM_RX_QUEUES */ @@ -879,6 +880,7 @@ static int rtnl_fill_ifinfo(struct sk_buff *skb, struct net_device *dev, const struct rtnl_link_stats64 *stats; struct nlattr *attr, *af_spec; struct rtnl_af_ops *af_ops; + struct net_device *upper_dev = netdev_master_upper_dev_get(dev); ASSERT_RTNL(); nlh = nlmsg_put(skb, pid, seq, type, sizeof(*ifm), flags); @@ -907,8 +909,9 @@ static int rtnl_fill_ifinfo(struct sk_buff *skb, struct net_device *dev, #endif (dev->ifindex != dev->iflink && nla_put_u32(skb, IFLA_LINK, dev->iflink)) || - (dev->master && - nla_put_u32(skb, IFLA_MASTER, dev->master->ifindex)) || + (upper_dev && + nla_put_u32(skb, IFLA_MASTER, upper_dev->ifindex)) || + nla_put_u8(skb, IFLA_CARRIER, netif_carrier_ok(dev)) || (dev->qdisc && nla_put_string(skb, IFLA_QDISC, dev->qdisc->ops->id)) || (dev->ifalias && @@ -1108,6 +1111,7 @@ const struct nla_policy ifla_policy[IFLA_MAX+1] = { [IFLA_MTU] = { .type = NLA_U32 }, [IFLA_LINK] = { .type = NLA_U32 }, [IFLA_MASTER] = { .type = NLA_U32 }, + [IFLA_CARRIER] = { .type = NLA_U8 }, [IFLA_TXQLEN] = { .type = NLA_U32 }, [IFLA_WEIGHT] = { .type = NLA_U32 }, [IFLA_OPERSTATE] = { .type = NLA_U8 }, @@ -1270,16 +1274,16 @@ static int do_setvfinfo(struct net_device *dev, struct nlattr *attr) static int do_set_master(struct net_device *dev, int ifindex) { - struct net_device *master_dev; + struct net_device *upper_dev = netdev_master_upper_dev_get(dev); const struct net_device_ops *ops; int err; - if (dev->master) { - if (dev->master->ifindex == ifindex) + if (upper_dev) { + if (upper_dev->ifindex == ifindex) return 0; - ops = dev->master->netdev_ops; + ops = upper_dev->netdev_ops; if (ops->ndo_del_slave) { - err = ops->ndo_del_slave(dev->master, dev); + err = ops->ndo_del_slave(upper_dev, dev); if (err) return err; } else { @@ -1288,12 +1292,12 @@ static int do_set_master(struct net_device *dev, int ifindex) } if (ifindex) { - master_dev = __dev_get_by_index(dev_net(dev), ifindex); - if (!master_dev) + upper_dev = __dev_get_by_index(dev_net(dev), ifindex); + if (!upper_dev) return -EINVAL; - ops = master_dev->netdev_ops; + ops = upper_dev->netdev_ops; if (ops->ndo_add_slave) { - err = ops->ndo_add_slave(master_dev, dev); + err = ops->ndo_add_slave(upper_dev, dev); if (err) return err; } else { @@ -1307,7 +1311,6 @@ static int do_setlink(struct net_device *dev, struct ifinfomsg *ifm, struct nlattr **tb, char *ifname, int modified) { const struct net_device_ops *ops = dev->netdev_ops; - int send_addr_notify = 0; int err; if (tb[IFLA_NET_NS_PID] || tb[IFLA_NET_NS_FD]) { @@ -1360,16 +1363,6 @@ static int do_setlink(struct net_device *dev, struct ifinfomsg *ifm, struct sockaddr *sa; int len; - if (!ops->ndo_set_mac_address) { - err = -EOPNOTSUPP; - goto errout; - } - - if (!netif_device_present(dev)) { - err = -ENODEV; - goto errout; - } - len = sizeof(sa_family_t) + dev->addr_len; sa = kmalloc(len, GFP_KERNEL); if (!sa) { @@ -1379,13 +1372,11 @@ static int do_setlink(struct net_device *dev, struct ifinfomsg *ifm, sa->sa_family = dev->type; memcpy(sa->sa_data, nla_data(tb[IFLA_ADDRESS]), dev->addr_len); - err = ops->ndo_set_mac_address(dev, sa); + err = dev_set_mac_address(dev, sa); kfree(sa); if (err) goto errout; - send_addr_notify = 1; modified = 1; - add_device_randomness(dev->dev_addr, dev->addr_len); } if (tb[IFLA_MTU]) { @@ -1422,7 +1413,7 @@ static int do_setlink(struct net_device *dev, struct ifinfomsg *ifm, if (tb[IFLA_BROADCAST]) { nla_memcpy(dev->broadcast, tb[IFLA_BROADCAST], dev->addr_len); - send_addr_notify = 1; + call_netdevice_notifiers(NETDEV_CHANGEADDR, dev); } if (ifm->ifi_flags || ifm->ifi_change) { @@ -1438,6 +1429,13 @@ static int do_setlink(struct net_device *dev, struct ifinfomsg *ifm, modified = 1; } + if (tb[IFLA_CARRIER]) { + err = dev_change_carrier(dev, nla_get_u8(tb[IFLA_CARRIER])); + if (err) + goto errout; + modified = 1; + } + if (tb[IFLA_TXQLEN]) dev->tx_queue_len = nla_get_u32(tb[IFLA_TXQLEN]); @@ -1536,9 +1534,6 @@ errout: net_warn_ratelimited("A link change request failed with some changes committed already. Interface %s may have been left with an inconsistent configuration, please check.\n", dev->name); - if (send_addr_notify) - call_netdevice_notifiers(NETDEV_CHANGEADDR, dev); - return err; } @@ -1672,9 +1667,11 @@ struct net_device *rtnl_create_link(struct net *net, if (tb[IFLA_MTU]) dev->mtu = nla_get_u32(tb[IFLA_MTU]); - if (tb[IFLA_ADDRESS]) + if (tb[IFLA_ADDRESS]) { memcpy(dev->dev_addr, nla_data(tb[IFLA_ADDRESS]), nla_len(tb[IFLA_ADDRESS])); + dev->addr_assign_type = NET_ADDR_SET; + } if (tb[IFLA_BROADCAST]) memcpy(dev->broadcast, nla_data(tb[IFLA_BROADCAST]), nla_len(tb[IFLA_BROADCAST])); @@ -1992,6 +1989,7 @@ errout: if (err < 0) rtnl_set_sk_err(net, RTNLGRP_LINK, err); } +EXPORT_SYMBOL(rtmsg_ifinfo); static int nlmsg_populate_fdb_fill(struct sk_buff *skb, struct net_device *dev, @@ -2054,16 +2052,12 @@ errout: static int rtnl_fdb_add(struct sk_buff *skb, struct nlmsghdr *nlh, void *arg) { struct net *net = sock_net(skb->sk); - struct net_device *master = NULL; struct ndmsg *ndm; struct nlattr *tb[NDA_MAX+1]; struct net_device *dev; u8 *addr; int err; - if (!capable(CAP_NET_ADMIN)) - return -EPERM; - err = nlmsg_parse(nlh, sizeof(*ndm), tb, NDA_MAX, NULL); if (err < 0) return err; @@ -2096,10 +2090,10 @@ static int rtnl_fdb_add(struct sk_buff *skb, struct nlmsghdr *nlh, void *arg) /* Support fdb on master device the net/bridge default case */ if ((!ndm->ndm_flags || ndm->ndm_flags & NTF_MASTER) && (dev->priv_flags & IFF_BRIDGE_PORT)) { - master = dev->master; - err = master->netdev_ops->ndo_fdb_add(ndm, tb, - dev, addr, - nlh->nlmsg_flags); + struct net_device *br_dev = netdev_master_upper_dev_get(dev); + const struct net_device_ops *ops = br_dev->netdev_ops; + + err = ops->ndo_fdb_add(ndm, tb, dev, addr, nlh->nlmsg_flags); if (err) goto out; else @@ -2125,7 +2119,7 @@ static int rtnl_fdb_del(struct sk_buff *skb, struct nlmsghdr *nlh, void *arg) { struct net *net = sock_net(skb->sk); struct ndmsg *ndm; - struct nlattr *llattr; + struct nlattr *tb[NDA_MAX+1]; struct net_device *dev; int err = -EINVAL; __u8 *addr; @@ -2133,8 +2127,9 @@ static int rtnl_fdb_del(struct sk_buff *skb, struct nlmsghdr *nlh, void *arg) if (!capable(CAP_NET_ADMIN)) return -EPERM; - if (nlmsg_len(nlh) < sizeof(*ndm)) - return -EINVAL; + err = nlmsg_parse(nlh, sizeof(*ndm), tb, NDA_MAX, NULL); + if (err < 0) + return err; ndm = nlmsg_data(nlh); if (ndm->ndm_ifindex == 0) { @@ -2148,22 +2143,27 @@ static int rtnl_fdb_del(struct sk_buff *skb, struct nlmsghdr *nlh, void *arg) return -ENODEV; } - llattr = nlmsg_find_attr(nlh, sizeof(*ndm), NDA_LLADDR); - if (llattr == NULL || nla_len(llattr) != ETH_ALEN) { - pr_info("PF_BRIGDE: RTM_DELNEIGH with invalid address\n"); + if (!tb[NDA_LLADDR] || nla_len(tb[NDA_LLADDR]) != ETH_ALEN) { + pr_info("PF_BRIDGE: RTM_DELNEIGH with invalid address\n"); + return -EINVAL; + } + + addr = nla_data(tb[NDA_LLADDR]); + if (!is_valid_ether_addr(addr)) { + pr_info("PF_BRIDGE: RTM_DELNEIGH with invalid ether address\n"); return -EINVAL; } - addr = nla_data(llattr); err = -EOPNOTSUPP; /* Support fdb on master device the net/bridge default case */ if ((!ndm->ndm_flags || ndm->ndm_flags & NTF_MASTER) && (dev->priv_flags & IFF_BRIDGE_PORT)) { - struct net_device *master = dev->master; + struct net_device *br_dev = netdev_master_upper_dev_get(dev); + const struct net_device_ops *ops = br_dev->netdev_ops; - if (master->netdev_ops->ndo_fdb_del) - err = master->netdev_ops->ndo_fdb_del(ndm, dev, addr); + if (ops->ndo_fdb_del) + err = ops->ndo_fdb_del(ndm, tb, dev, addr); if (err) goto out; @@ -2173,7 +2173,7 @@ static int rtnl_fdb_del(struct sk_buff *skb, struct nlmsghdr *nlh, void *arg) /* Embedded bridge, macvlan, and any other device support */ if ((ndm->ndm_flags & NTF_SELF) && dev->netdev_ops->ndo_fdb_del) { - err = dev->netdev_ops->ndo_fdb_del(ndm, dev, addr); + err = dev->netdev_ops->ndo_fdb_del(ndm, tb, dev, addr); if (!err) { rtnl_fdb_notify(dev, addr, RTM_DELNEIGH); @@ -2247,9 +2247,11 @@ static int rtnl_fdb_dump(struct sk_buff *skb, struct netlink_callback *cb) rcu_read_lock(); for_each_netdev_rcu(net, dev) { if (dev->priv_flags & IFF_BRIDGE_PORT) { - struct net_device *master = dev->master; - const struct net_device_ops *ops = master->netdev_ops; + struct net_device *br_dev; + const struct net_device_ops *ops; + br_dev = netdev_master_upper_dev_get(dev); + ops = br_dev->netdev_ops; if (ops->ndo_fdb_dump) idx = ops->ndo_fdb_dump(skb, cb, dev, idx); } @@ -2270,6 +2272,7 @@ int ndo_dflt_bridge_getlink(struct sk_buff *skb, u32 pid, u32 seq, struct ifinfomsg *ifm; struct nlattr *br_afspec; u8 operstate = netif_running(dev) ? dev->operstate : IF_OPER_DOWN; + struct net_device *br_dev = netdev_master_upper_dev_get(dev); nlh = nlmsg_put(skb, pid, seq, RTM_NEWLINK, sizeof(*ifm), NLM_F_MULTI); if (nlh == NULL) @@ -2287,8 +2290,8 @@ int ndo_dflt_bridge_getlink(struct sk_buff *skb, u32 pid, u32 seq, if (nla_put_string(skb, IFLA_IFNAME, dev->name) || nla_put_u32(skb, IFLA_MTU, dev->mtu) || nla_put_u8(skb, IFLA_OPERSTATE, operstate) || - (dev->master && - nla_put_u32(skb, IFLA_MASTER, dev->master->ifindex)) || + (br_dev && + nla_put_u32(skb, IFLA_MASTER, br_dev->ifindex)) || (dev->addr_len && nla_put(skb, IFLA_ADDRESS, dev->addr_len, dev->dev_addr)) || (dev->ifindex != dev->iflink && @@ -2320,23 +2323,31 @@ static int rtnl_bridge_getlink(struct sk_buff *skb, struct netlink_callback *cb) int idx = 0; u32 portid = NETLINK_CB(cb->skb).portid; u32 seq = cb->nlh->nlmsg_seq; + struct nlattr *extfilt; + u32 filter_mask = 0; + + extfilt = nlmsg_find_attr(cb->nlh, sizeof(struct rtgenmsg), + IFLA_EXT_MASK); + if (extfilt) + filter_mask = nla_get_u32(extfilt); rcu_read_lock(); for_each_netdev_rcu(net, dev) { const struct net_device_ops *ops = dev->netdev_ops; - struct net_device *master = dev->master; + struct net_device *br_dev = netdev_master_upper_dev_get(dev); - if (master && master->netdev_ops->ndo_bridge_getlink) { + if (br_dev && br_dev->netdev_ops->ndo_bridge_getlink) { if (idx >= cb->args[0] && - master->netdev_ops->ndo_bridge_getlink( - skb, portid, seq, dev) < 0) + br_dev->netdev_ops->ndo_bridge_getlink( + skb, portid, seq, dev, filter_mask) < 0) break; idx++; } if (ops->ndo_bridge_getlink) { if (idx >= cb->args[0] && - ops->ndo_bridge_getlink(skb, portid, seq, dev) < 0) + ops->ndo_bridge_getlink(skb, portid, seq, dev, + filter_mask) < 0) break; idx++; } @@ -2365,7 +2376,7 @@ static inline size_t bridge_nlmsg_size(void) static int rtnl_bridge_notify(struct net_device *dev, u16 flags) { struct net *net = dev_net(dev); - struct net_device *master = dev->master; + struct net_device *br_dev = netdev_master_upper_dev_get(dev); struct sk_buff *skb; int err = -EOPNOTSUPP; @@ -2376,15 +2387,15 @@ static int rtnl_bridge_notify(struct net_device *dev, u16 flags) } if ((!flags || (flags & BRIDGE_FLAGS_MASTER)) && - master && master->netdev_ops->ndo_bridge_getlink) { - err = master->netdev_ops->ndo_bridge_getlink(skb, 0, 0, dev); + br_dev && br_dev->netdev_ops->ndo_bridge_getlink) { + err = br_dev->netdev_ops->ndo_bridge_getlink(skb, 0, 0, dev, 0); if (err < 0) goto errout; } if ((flags & BRIDGE_FLAGS_SELF) && dev->netdev_ops->ndo_bridge_getlink) { - err = dev->netdev_ops->ndo_bridge_getlink(skb, 0, 0, dev); + err = dev->netdev_ops->ndo_bridge_getlink(skb, 0, 0, dev, 0); if (err < 0) goto errout; } @@ -2436,13 +2447,14 @@ static int rtnl_bridge_setlink(struct sk_buff *skb, struct nlmsghdr *nlh, oflags = flags; if (!flags || (flags & BRIDGE_FLAGS_MASTER)) { - if (!dev->master || - !dev->master->netdev_ops->ndo_bridge_setlink) { + struct net_device *br_dev = netdev_master_upper_dev_get(dev); + + if (!br_dev || !br_dev->netdev_ops->ndo_bridge_setlink) { err = -EOPNOTSUPP; goto out; } - err = dev->master->netdev_ops->ndo_bridge_setlink(dev, nlh); + err = br_dev->netdev_ops->ndo_bridge_setlink(dev, nlh); if (err) goto out; @@ -2468,6 +2480,77 @@ out: return err; } +static int rtnl_bridge_dellink(struct sk_buff *skb, struct nlmsghdr *nlh, + void *arg) +{ + struct net *net = sock_net(skb->sk); + struct ifinfomsg *ifm; + struct net_device *dev; + struct nlattr *br_spec, *attr = NULL; + int rem, err = -EOPNOTSUPP; + u16 oflags, flags = 0; + bool have_flags = false; + + if (nlmsg_len(nlh) < sizeof(*ifm)) + return -EINVAL; + + ifm = nlmsg_data(nlh); + if (ifm->ifi_family != AF_BRIDGE) + return -EPFNOSUPPORT; + + dev = __dev_get_by_index(net, ifm->ifi_index); + if (!dev) { + pr_info("PF_BRIDGE: RTM_SETLINK with unknown ifindex\n"); + return -ENODEV; + } + + br_spec = nlmsg_find_attr(nlh, sizeof(struct ifinfomsg), IFLA_AF_SPEC); + if (br_spec) { + nla_for_each_nested(attr, br_spec, rem) { + if (nla_type(attr) == IFLA_BRIDGE_FLAGS) { + have_flags = true; + flags = nla_get_u16(attr); + break; + } + } + } + + oflags = flags; + + if (!flags || (flags & BRIDGE_FLAGS_MASTER)) { + struct net_device *br_dev = netdev_master_upper_dev_get(dev); + + if (!br_dev || !br_dev->netdev_ops->ndo_bridge_dellink) { + err = -EOPNOTSUPP; + goto out; + } + + err = br_dev->netdev_ops->ndo_bridge_dellink(dev, nlh); + if (err) + goto out; + + flags &= ~BRIDGE_FLAGS_MASTER; + } + + if ((flags & BRIDGE_FLAGS_SELF)) { + if (!dev->netdev_ops->ndo_bridge_dellink) + err = -EOPNOTSUPP; + else + err = dev->netdev_ops->ndo_bridge_dellink(dev, nlh); + + if (!err) + flags &= ~BRIDGE_FLAGS_SELF; + } + + if (have_flags) + memcpy(nla_data(attr), &flags, sizeof(flags)); + /* Generate event to notify upper layer of bridge change */ + if (!err) + err = rtnl_bridge_notify(dev, oflags); +out: + return err; +} + /* Protected by RTNL sempahore. */ static struct rtattr **rta_buf; static int rtattr_max; @@ -2651,6 +2734,7 @@ void __init rtnetlink_init(void) rtnl_register(PF_BRIDGE, RTM_GETNEIGH, NULL, rtnl_fdb_dump, NULL); rtnl_register(PF_BRIDGE, RTM_GETLINK, NULL, rtnl_bridge_getlink, NULL); + rtnl_register(PF_BRIDGE, RTM_DELLINK, rtnl_bridge_dellink, NULL, NULL); rtnl_register(PF_BRIDGE, RTM_SETLINK, rtnl_bridge_setlink, NULL, NULL); } diff --git a/net/core/scm.c b/net/core/scm.c index 57fb1ee6649f..905dcc6ad1e3 100644 --- a/net/core/scm.c +++ b/net/core/scm.c @@ -35,6 +35,7 @@ #include <net/sock.h> #include <net/compat.h> #include <net/scm.h> +#include <net/cls_cgroup.h> /* @@ -302,8 +303,10 @@ void scm_detach_fds(struct msghdr *msg, struct scm_cookie *scm) } /* Bump the usage count and install the file. */ sock = sock_from_file(fp[i], &err); - if (sock) + if (sock) { sock_update_netprioidx(sock->sk, current); + sock_update_classid(sock->sk, current); + } fd_install(new_fd, get_file(fp[i])); } diff --git a/net/core/skbuff.c b/net/core/skbuff.c index 3ab989b0de42..2a3ca33c30aa 100644 --- a/net/core/skbuff.c +++ b/net/core/skbuff.c @@ -104,47 +104,37 @@ static const struct pipe_buf_operations sock_pipe_buf_ops = { .get = sock_pipe_buf_get, }; -/* - * Keep out-of-line to prevent kernel bloat. - * __builtin_return_address is not used because it is not always - * reliable. - */ - /** - * skb_over_panic - private function - * @skb: buffer - * @sz: size - * @here: address - * - * Out of line support code for skb_put(). Not user callable. + * skb_panic - private function for out-of-line support + * @skb: buffer + * @sz: size + * @addr: address + * @msg: skb_over_panic or skb_under_panic + * + * Out-of-line support for skb_put() and skb_push(). + * Called via the wrapper skb_over_panic() or skb_under_panic(). + * Keep out of line to prevent kernel bloat. + * __builtin_return_address is not used because it is not always reliable. */ -static void skb_over_panic(struct sk_buff *skb, int sz, void *here) +static void skb_panic(struct sk_buff *skb, unsigned int sz, void *addr, + const char msg[]) { pr_emerg("%s: text:%p len:%d put:%d head:%p data:%p tail:%#lx end:%#lx dev:%s\n", - __func__, here, skb->len, sz, skb->head, skb->data, + msg, addr, skb->len, sz, skb->head, skb->data, (unsigned long)skb->tail, (unsigned long)skb->end, skb->dev ? skb->dev->name : "<NULL>"); BUG(); } -/** - * skb_under_panic - private function - * @skb: buffer - * @sz: size - * @here: address - * - * Out of line support code for skb_push(). Not user callable. - */ - -static void skb_under_panic(struct sk_buff *skb, int sz, void *here) +static void skb_over_panic(struct sk_buff *skb, unsigned int sz, void *addr) { - pr_emerg("%s: text:%p len:%d put:%d head:%p data:%p tail:%#lx end:%#lx dev:%s\n", - __func__, here, skb->len, sz, skb->head, skb->data, - (unsigned long)skb->tail, (unsigned long)skb->end, - skb->dev ? skb->dev->name : "<NULL>"); - BUG(); + skb_panic(skb, sz, addr, __func__); } +static void skb_under_panic(struct sk_buff *skb, unsigned int sz, void *addr) +{ + skb_panic(skb, sz, addr, __func__); +} /* * kmalloc_reserve is a wrapper around kmalloc_node_track_caller that tells @@ -155,8 +145,9 @@ static void skb_under_panic(struct sk_buff *skb, int sz, void *here) */ #define kmalloc_reserve(size, gfp, node, pfmemalloc) \ __kmalloc_reserve(size, gfp, node, _RET_IP_, pfmemalloc) -void *__kmalloc_reserve(size_t size, gfp_t flags, int node, unsigned long ip, - bool *pfmemalloc) + +static void *__kmalloc_reserve(size_t size, gfp_t flags, int node, + unsigned long ip, bool *pfmemalloc) { void *obj; bool ret_pfmemalloc = false; @@ -259,6 +250,7 @@ struct sk_buff *__alloc_skb(unsigned int size, gfp_t gfp_mask, skb->end = skb->tail + size; #ifdef NET_SKBUFF_DATA_USES_OFFSET skb->mac_header = ~0U; + skb->transport_header = ~0U; #endif /* make sure we initialize shinfo sequentially */ @@ -327,6 +319,7 @@ struct sk_buff *build_skb(void *data, unsigned int frag_size) skb->end = skb->tail + size; #ifdef NET_SKBUFF_DATA_USES_OFFSET skb->mac_header = ~0U; + skb->transport_header = ~0U; #endif /* make sure we initialize shinfo sequentially */ @@ -348,10 +341,6 @@ struct netdev_alloc_cache { }; static DEFINE_PER_CPU(struct netdev_alloc_cache, netdev_alloc_cache); -#define NETDEV_FRAG_PAGE_MAX_ORDER get_order(32768) -#define NETDEV_FRAG_PAGE_MAX_SIZE (PAGE_SIZE << NETDEV_FRAG_PAGE_MAX_ORDER) -#define NETDEV_PAGECNT_MAX_BIAS NETDEV_FRAG_PAGE_MAX_SIZE - static void *__netdev_alloc_frag(unsigned int fragsz, gfp_t gfp_mask) { struct netdev_alloc_cache *nc; @@ -683,7 +672,7 @@ static void __copy_skb_header(struct sk_buff *new, const struct sk_buff *old) new->network_header = old->network_header; new->mac_header = old->mac_header; new->inner_transport_header = old->inner_transport_header; - new->inner_network_header = old->inner_transport_header; + new->inner_network_header = old->inner_network_header; skb_dst_copy(new, old); new->rxhash = old->rxhash; new->ooo_okay = old->ooo_okay; @@ -1649,7 +1638,7 @@ static void sock_spd_release(struct splice_pipe_desc *spd, unsigned int i) static struct page *linear_to_page(struct page *page, unsigned int *len, unsigned int *offset, - struct sk_buff *skb, struct sock *sk) + struct sock *sk) { struct page_frag *pfrag = sk_page_frag(sk); @@ -1682,14 +1671,14 @@ static bool spd_can_coalesce(const struct splice_pipe_desc *spd, static bool spd_fill_page(struct splice_pipe_desc *spd, struct pipe_inode_info *pipe, struct page *page, unsigned int *len, unsigned int offset, - struct sk_buff *skb, bool linear, + bool linear, struct sock *sk) { if (unlikely(spd->nr_pages == MAX_SKB_FRAGS)) return true; if (linear) { - page = linear_to_page(page, len, &offset, skb, sk); + page = linear_to_page(page, len, &offset, sk); if (!page) return true; } @@ -1706,23 +1695,9 @@ static bool spd_fill_page(struct splice_pipe_desc *spd, return false; } -static inline void __segment_seek(struct page **page, unsigned int *poff, - unsigned int *plen, unsigned int off) -{ - unsigned long n; - - *poff += off; - n = *poff / PAGE_SIZE; - if (n) - *page = nth_page(*page, n); - - *poff = *poff % PAGE_SIZE; - *plen -= off; -} - static bool __splice_segment(struct page *page, unsigned int poff, unsigned int plen, unsigned int *off, - unsigned int *len, struct sk_buff *skb, + unsigned int *len, struct splice_pipe_desc *spd, bool linear, struct sock *sk, struct pipe_inode_info *pipe) @@ -1737,23 +1712,19 @@ static bool __splice_segment(struct page *page, unsigned int poff, } /* ignore any bits we already processed */ - if (*off) { - __segment_seek(&page, &poff, &plen, *off); - *off = 0; - } + poff += *off; + plen -= *off; + *off = 0; do { unsigned int flen = min(*len, plen); - /* the linear region may spread across several pages */ - flen = min_t(unsigned int, flen, PAGE_SIZE - poff); - - if (spd_fill_page(spd, pipe, page, &flen, poff, skb, linear, sk)) + if (spd_fill_page(spd, pipe, page, &flen, poff, + linear, sk)) return true; - - __segment_seek(&page, &poff, &plen, flen); + poff += flen; + plen -= flen; *len -= flen; - } while (*len && plen); return false; @@ -1777,7 +1748,7 @@ static bool __skb_splice_bits(struct sk_buff *skb, struct pipe_inode_info *pipe, if (__splice_segment(virt_to_page(skb->data), (unsigned long) skb->data & (PAGE_SIZE - 1), skb_headlen(skb), - offset, len, skb, spd, + offset, len, spd, skb_head_is_locked(skb), sk, pipe)) return true; @@ -1790,7 +1761,7 @@ static bool __skb_splice_bits(struct sk_buff *skb, struct pipe_inode_info *pipe, if (__splice_segment(skb_frag_page(f), f->page_offset, skb_frag_size(f), - offset, len, skb, spd, false, sk, pipe)) + offset, len, spd, false, sk, pipe)) return true; } @@ -2355,6 +2326,7 @@ void skb_split(struct sk_buff *skb, struct sk_buff *skb1, const u32 len) { int pos = skb_headlen(skb); + skb_shinfo(skb)->tx_flags = skb_shinfo(skb1)->tx_flags & SKBTX_SHARED_FRAG; if (len < pos) /* Split line is inside header. */ skb_split_inside_header(skb, skb1, len, pos); else /* Second chunk has no header, nothing to copy. */ @@ -2686,48 +2658,37 @@ int skb_append_datato_frags(struct sock *sk, struct sk_buff *skb, int len, int odd, struct sk_buff *skb), void *from, int length) { - int frg_cnt = 0; - skb_frag_t *frag = NULL; - struct page *page = NULL; - int copy, left; + int frg_cnt = skb_shinfo(skb)->nr_frags; + int copy; int offset = 0; int ret; + struct page_frag *pfrag = ¤t->task_frag; do { /* Return error if we don't have space for new frag */ - frg_cnt = skb_shinfo(skb)->nr_frags; if (frg_cnt >= MAX_SKB_FRAGS) - return -EFAULT; + return -EMSGSIZE; - /* allocate a new page for next frag */ - page = alloc_pages(sk->sk_allocation, 0); - - /* If alloc_page fails just return failure and caller will - * free previous allocated pages by doing kfree_skb() - */ - if (page == NULL) + if (!sk_page_frag_refill(sk, pfrag)) return -ENOMEM; - /* initialize the next frag */ - skb_fill_page_desc(skb, frg_cnt, page, 0, 0); - skb->truesize += PAGE_SIZE; - atomic_add(PAGE_SIZE, &sk->sk_wmem_alloc); - - /* get the new initialized frag */ - frg_cnt = skb_shinfo(skb)->nr_frags; - frag = &skb_shinfo(skb)->frags[frg_cnt - 1]; - /* copy the user data to page */ - left = PAGE_SIZE - frag->page_offset; - copy = (length > left)? left : length; + copy = min_t(int, length, pfrag->size - pfrag->offset); - ret = getfrag(from, skb_frag_address(frag) + skb_frag_size(frag), - offset, copy, 0, skb); + ret = getfrag(from, page_address(pfrag->page) + pfrag->offset, + offset, copy, 0, skb); if (ret < 0) return -EFAULT; /* copy was successful so update the size parameters */ - skb_frag_size_add(frag, copy); + skb_fill_page_desc(skb, frg_cnt, pfrag->page, pfrag->offset, + copy); + frg_cnt++; + pfrag->offset += copy; + get_page(pfrag->page); + + skb->truesize += copy; + atomic_add(copy, &sk->sk_wmem_alloc); skb->len += copy; skb->data_len += copy; offset += copy; @@ -2777,6 +2738,7 @@ struct sk_buff *skb_segment(struct sk_buff *skb, netdev_features_t features) unsigned int mss = skb_shinfo(skb)->gso_size; unsigned int doffset = skb->data - skb_mac_header(skb); unsigned int offset = doffset; + unsigned int tnl_hlen = skb_tnl_header_len(skb); unsigned int headroom; unsigned int len; int sg = !!(features & NETIF_F_SG); @@ -2853,7 +2815,10 @@ struct sk_buff *skb_segment(struct sk_buff *skb, netdev_features_t features) skb_set_network_header(nskb, skb->mac_len); nskb->transport_header = (nskb->network_header + skb_network_header_len(skb)); - skb_copy_from_linear_data(skb, nskb->data, doffset); + + skb_copy_from_linear_data_offset(skb, -tnl_hlen, + nskb->data - tnl_hlen, + doffset + tnl_hlen); if (fskb != skb_shinfo(skb)->frag_list) continue; @@ -2871,6 +2836,8 @@ struct sk_buff *skb_segment(struct sk_buff *skb, netdev_features_t features) skb_copy_from_linear_data_offset(skb, offset, skb_put(nskb, hsize), hsize); + skb_shinfo(nskb)->tx_flags = skb_shinfo(skb)->tx_flags & SKBTX_SHARED_FRAG; + while (pos < offset + len && i < nfrags) { *frag = skb_shinfo(skb)->frags[i]; __skb_frag_ref(frag); diff --git a/net/core/sock.c b/net/core/sock.c index a692ef49c9bb..f1e14e20d181 100644 --- a/net/core/sock.c +++ b/net/core/sock.c @@ -583,7 +583,7 @@ static int sock_getbindtodevice(struct sock *sk, char __user *optval, goto out; retry: - seq = read_seqbegin(&devnet_rename_seq); + seq = read_seqcount_begin(&devnet_rename_seq); rcu_read_lock(); dev = dev_get_by_index_rcu(net, sk->sk_bound_dev_if); ret = -ENODEV; @@ -594,7 +594,7 @@ retry: strcpy(devname, dev->name); rcu_read_unlock(); - if (read_seqretry(&devnet_rename_seq, seq)) + if (read_seqcount_retry(&devnet_rename_seq, seq)) goto retry; len = strlen(devname) + 1; @@ -665,6 +665,9 @@ int sock_setsockopt(struct socket *sock, int level, int optname, case SO_REUSEADDR: sk->sk_reuse = (valbool ? SK_CAN_REUSE : SK_NO_REUSE); break; + case SO_REUSEPORT: + sk->sk_reuseport = valbool; + break; case SO_TYPE: case SO_PROTOCOL: case SO_DOMAIN: @@ -861,6 +864,13 @@ set_rcvbuf: ret = sk_detach_filter(sk); break; + case SO_LOCK_FILTER: + if (sock_flag(sk, SOCK_FILTER_LOCKED) && !valbool) + ret = -EPERM; + else + sock_valbool_flag(sk, SOCK_FILTER_LOCKED, valbool); + break; + case SO_PASSSEC: if (valbool) set_bit(SOCK_PASSSEC, &sock->flags); @@ -965,6 +975,10 @@ int sock_getsockopt(struct socket *sock, int level, int optname, v.val = sk->sk_reuse; break; + case SO_REUSEPORT: + v.val = sk->sk_reuseport; + break; + case SO_KEEPALIVE: v.val = sock_flag(sk, SOCK_KEEPOPEN); break; @@ -1140,6 +1154,10 @@ int sock_getsockopt(struct socket *sock, int level, int optname, goto lenout; + case SO_LOCK_FILTER: + v.val = sock_flag(sk, SOCK_FILTER_LOCKED); + break; + default: return -ENOPROTOOPT; } @@ -2212,7 +2230,7 @@ EXPORT_SYMBOL(sk_reset_timer); void sk_stop_timer(struct sock *sk, struct timer_list* timer) { - if (timer_pending(timer) && del_timer(timer)) + if (del_timer(timer)) __sock_put(sk); } EXPORT_SYMBOL(sk_stop_timer); diff --git a/net/core/sysctl_net_core.c b/net/core/sysctl_net_core.c index d1b08045a9df..cfdb46ab3a7f 100644 --- a/net/core/sysctl_net_core.c +++ b/net/core/sysctl_net_core.c @@ -20,6 +20,8 @@ #include <net/sock.h> #include <net/net_ratelimit.h> +static int one = 1; + #ifdef CONFIG_RPS static int rps_sock_flow_sysctl(ctl_table *table, int write, void __user *buffer, size_t *lenp, loff_t *ppos) @@ -92,28 +94,32 @@ static struct ctl_table net_core_table[] = { .data = &sysctl_wmem_max, .maxlen = sizeof(int), .mode = 0644, - .proc_handler = proc_dointvec + .proc_handler = proc_dointvec_minmax, + .extra1 = &one, }, { .procname = "rmem_max", .data = &sysctl_rmem_max, .maxlen = sizeof(int), .mode = 0644, - .proc_handler = proc_dointvec + .proc_handler = proc_dointvec_minmax, + .extra1 = &one, }, { .procname = "wmem_default", .data = &sysctl_wmem_default, .maxlen = sizeof(int), .mode = 0644, - .proc_handler = proc_dointvec + .proc_handler = proc_dointvec_minmax, + .extra1 = &one, }, { .procname = "rmem_default", .data = &sysctl_rmem_default, .maxlen = sizeof(int), .mode = 0644, - .proc_handler = proc_dointvec + .proc_handler = proc_dointvec_minmax, + .extra1 = &one, }, { .procname = "dev_weight", diff --git a/net/decnet/af_decnet.c b/net/decnet/af_decnet.c index 307c322d53bb..64d9843f9e04 100644 --- a/net/decnet/af_decnet.c +++ b/net/decnet/af_decnet.c @@ -909,6 +909,7 @@ static int __dn_connect(struct sock *sk, struct sockaddr_dn *addr, int addrlen, struct dn_scp *scp = DN_SK(sk); int err = -EISCONN; struct flowidn fld; + struct dst_entry *dst; if (sock->state == SS_CONNECTED) goto out; @@ -955,10 +956,11 @@ static int __dn_connect(struct sock *sk, struct sockaddr_dn *addr, int addrlen, fld.flowidn_proto = DNPROTO_NSP; if (dn_route_output_sock(&sk->sk_dst_cache, &fld, sk, flags) < 0) goto out; - sk->sk_route_caps = sk->sk_dst_cache->dev->features; + dst = __sk_dst_get(sk); + sk->sk_route_caps = dst->dev->features; sock->state = SS_CONNECTING; scp->state = DN_CI; - scp->segsize_loc = dst_metric_advmss(sk->sk_dst_cache); + scp->segsize_loc = dst_metric_advmss(dst); dn_nsp_send_conninit(sk, NSP_CI); err = -EINPROGRESS; diff --git a/net/decnet/dn_neigh.c b/net/decnet/dn_neigh.c index 3aede1b459fd..856636addd76 100644 --- a/net/decnet/dn_neigh.c +++ b/net/decnet/dn_neigh.c @@ -95,7 +95,7 @@ static u32 dn_neigh_hash(const void *pkey, struct neigh_table dn_neigh_table = { .family = PF_DECnet, - .entry_size = sizeof(struct dn_neigh), + .entry_size = NEIGH_ENTRY_SIZE(sizeof(struct dn_neigh)), .key_len = sizeof(__le16), .hash = dn_neigh_hash, .constructor = dn_neigh_construct, diff --git a/net/decnet/dn_nsp_out.c b/net/decnet/dn_nsp_out.c index 8a96047c7c94..1aaa51ebbda6 100644 --- a/net/decnet/dn_nsp_out.c +++ b/net/decnet/dn_nsp_out.c @@ -598,7 +598,7 @@ void dn_nsp_send_disc(struct sock *sk, unsigned char msgflg, if (reason == 0) reason = le16_to_cpu(scp->discdata_out.opt_status); - dn_nsp_do_disc(sk, msgflg, reason, gfp, sk->sk_dst_cache, ddl, + dn_nsp_do_disc(sk, msgflg, reason, gfp, __sk_dst_get(sk), ddl, scp->discdata_out.opt_data, scp->addrrem, scp->addrloc); } diff --git a/net/decnet/dn_route.c b/net/decnet/dn_route.c index b57419cc41a4..1550028fcd8e 100644 --- a/net/decnet/dn_route.c +++ b/net/decnet/dn_route.c @@ -1282,7 +1282,7 @@ static int dn_route_output_key(struct dst_entry **pprt, struct flowidn *flp, int return err; } -int dn_route_output_sock(struct dst_entry **pprt, struct flowidn *fl, struct sock *sk, int flags) +int dn_route_output_sock(struct dst_entry __rcu **pprt, struct flowidn *fl, struct sock *sk, int flags) { int err; diff --git a/net/dsa/dsa.c b/net/dsa/dsa.c index 45295ca09571..2bc62ea857c8 100644 --- a/net/dsa/dsa.c +++ b/net/dsa/dsa.c @@ -80,6 +80,7 @@ dsa_switch_setup(struct dsa_switch_tree *dst, int index, int ret; char *name; int i; + bool valid_name_found = false; /* * Probe for switch model. @@ -131,8 +132,13 @@ dsa_switch_setup(struct dsa_switch_tree *dst, int index, } else { ds->phys_port_mask |= 1 << i; } + valid_name_found = true; } + if (!valid_name_found && i == DSA_MAX_PORTS) { + ret = -EINVAL; + goto out; + } /* * If the CPU connects to this switch, set the switch tree diff --git a/net/dsa/slave.c b/net/dsa/slave.c index e32083d5d8f8..6ebd8fbd9285 100644 --- a/net/dsa/slave.c +++ b/net/dsa/slave.c @@ -41,8 +41,8 @@ void dsa_slave_mii_bus_init(struct dsa_switch *ds) ds->slave_mii_bus->name = "dsa slave smi"; ds->slave_mii_bus->read = dsa_slave_phy_read; ds->slave_mii_bus->write = dsa_slave_phy_write; - snprintf(ds->slave_mii_bus->id, MII_BUS_ID_SIZE, "%s:%.2x", - ds->master_mii_bus->id, ds->pd->sw_addr); + snprintf(ds->slave_mii_bus->id, MII_BUS_ID_SIZE, "dsa-%d:%.2x", + ds->index, ds->pd->sw_addr); ds->slave_mii_bus->parent = &ds->master_mii_bus->dev; } @@ -203,10 +203,10 @@ dsa_slave_set_settings(struct net_device *dev, struct ethtool_cmd *cmd) static void dsa_slave_get_drvinfo(struct net_device *dev, struct ethtool_drvinfo *drvinfo) { - strncpy(drvinfo->driver, "dsa", 32); - strncpy(drvinfo->version, dsa_driver_version, 32); - strncpy(drvinfo->fw_version, "N/A", 32); - strncpy(drvinfo->bus_info, "platform", 32); + strlcpy(drvinfo->driver, "dsa", sizeof(drvinfo->driver)); + strlcpy(drvinfo->version, dsa_driver_version, sizeof(drvinfo->version)); + strlcpy(drvinfo->fw_version, "N/A", sizeof(drvinfo->fw_version)); + strlcpy(drvinfo->bus_info, "platform", sizeof(drvinfo->bus_info)); } static int dsa_slave_nway_reset(struct net_device *dev) @@ -391,7 +391,7 @@ dsa_slave_create(struct dsa_switch *ds, struct device *parent, if (p->phy != NULL) { phy_attach(slave_dev, dev_name(&p->phy->dev), - 0, PHY_INTERFACE_MODE_GMII); + PHY_INTERFACE_MODE_GMII); p->phy->autoneg = AUTONEG_ENABLE; p->phy->speed = 0; diff --git a/net/ethernet/eth.c b/net/ethernet/eth.c index 4efad533e5f6..a36c85eab5b4 100644 --- a/net/ethernet/eth.c +++ b/net/ethernet/eth.c @@ -272,6 +272,36 @@ void eth_header_cache_update(struct hh_cache *hh, EXPORT_SYMBOL(eth_header_cache_update); /** + * eth_prepare_mac_addr_change - prepare for mac change + * @dev: network device + * @p: socket address + */ +int eth_prepare_mac_addr_change(struct net_device *dev, void *p) +{ + struct sockaddr *addr = p; + + if (!(dev->priv_flags & IFF_LIVE_ADDR_CHANGE) && netif_running(dev)) + return -EBUSY; + if (!is_valid_ether_addr(addr->sa_data)) + return -EADDRNOTAVAIL; + return 0; +} +EXPORT_SYMBOL(eth_prepare_mac_addr_change); + +/** + * eth_commit_mac_addr_change - commit mac change + * @dev: network device + * @p: socket address + */ +void eth_commit_mac_addr_change(struct net_device *dev, void *p) +{ + struct sockaddr *addr = p; + + memcpy(dev->dev_addr, addr->sa_data, ETH_ALEN); +} +EXPORT_SYMBOL(eth_commit_mac_addr_change); + +/** * eth_mac_addr - set new Ethernet hardware address * @dev: network device * @p: socket address @@ -283,15 +313,12 @@ EXPORT_SYMBOL(eth_header_cache_update); */ int eth_mac_addr(struct net_device *dev, void *p) { - struct sockaddr *addr = p; + int ret; - if (!(dev->priv_flags & IFF_LIVE_ADDR_CHANGE) && netif_running(dev)) - return -EBUSY; - if (!is_valid_ether_addr(addr->sa_data)) - return -EADDRNOTAVAIL; - memcpy(dev->dev_addr, addr->sa_data, ETH_ALEN); - /* if device marked as NET_ADDR_RANDOM, reset it */ - dev->addr_assign_type &= ~NET_ADDR_RANDOM; + ret = eth_prepare_mac_addr_change(dev, p); + if (ret < 0) + return ret; + eth_commit_mac_addr_change(dev, p); return 0; } EXPORT_SYMBOL(eth_mac_addr); diff --git a/net/ieee802154/6lowpan.c b/net/ieee802154/6lowpan.c index f651da60f161..43b95ca61114 100644 --- a/net/ieee802154/6lowpan.c +++ b/net/ieee802154/6lowpan.c @@ -377,17 +377,14 @@ static int lowpan_header_create(struct sk_buff *skb, struct ipv6hdr *hdr; const u8 *saddr = _saddr; const u8 *daddr = _daddr; - u8 *head; + u8 head[100]; struct ieee802154_addr sa, da; + /* TODO: + * if this package isn't ipv6 one, where should it be routed? + */ if (type != ETH_P_IPV6) return 0; - /* TODO: - * if this package isn't ipv6 one, where should it be routed? - */ - head = kzalloc(100, GFP_KERNEL); - if (head == NULL) - return -ENOMEM; hdr = ipv6_hdr(skb); hc06_ptr = head + 2; @@ -561,8 +558,6 @@ static int lowpan_header_create(struct sk_buff *skb, skb_pull(skb, sizeof(struct ipv6hdr)); memcpy(skb_push(skb, hc06_ptr - head), head, hc06_ptr - head); - kfree(head); - lowpan_raw_dump_table(__func__, "raw skb data dump", skb->data, skb->len); @@ -594,10 +589,32 @@ static int lowpan_header_create(struct sk_buff *skb, } } +static int lowpan_give_skb_to_devices(struct sk_buff *skb) +{ + struct lowpan_dev_record *entry; + struct sk_buff *skb_cp; + int stat = NET_RX_SUCCESS; + + rcu_read_lock(); + list_for_each_entry_rcu(entry, &lowpan_devices, list) + if (lowpan_dev_info(entry->ldev)->real_dev == skb->dev) { + skb_cp = skb_copy(skb, GFP_ATOMIC); + if (!skb_cp) { + stat = -ENOMEM; + break; + } + + skb_cp->dev = entry->ldev; + stat = netif_rx(skb_cp); + } + rcu_read_unlock(); + + return stat; +} + static int lowpan_skb_deliver(struct sk_buff *skb, struct ipv6hdr *hdr) { struct sk_buff *new; - struct lowpan_dev_record *entry; int stat = NET_RX_SUCCESS; new = skb_copy_expand(skb, sizeof(struct ipv6hdr), skb_tailroom(skb), @@ -614,19 +631,7 @@ static int lowpan_skb_deliver(struct sk_buff *skb, struct ipv6hdr *hdr) new->protocol = htons(ETH_P_IPV6); new->pkt_type = PACKET_HOST; - rcu_read_lock(); - list_for_each_entry_rcu(entry, &lowpan_devices, list) - if (lowpan_dev_info(entry->ldev)->real_dev == new->dev) { - skb = skb_copy(new, GFP_ATOMIC); - if (!skb) { - stat = -ENOMEM; - break; - } - - skb->dev = entry->ldev; - stat = netif_rx(skb); - } - rcu_read_unlock(); + stat = lowpan_give_skb_to_devices(new); kfree_skb(new); @@ -1137,19 +1142,42 @@ static int lowpan_rcv(struct sk_buff *skb, struct net_device *dev, goto drop; /* check that it's our buffer */ - switch (skb->data[0] & 0xe0) { - case LOWPAN_DISPATCH_IPHC: /* ipv6 datagram */ - case LOWPAN_DISPATCH_FRAG1: /* first fragment header */ - case LOWPAN_DISPATCH_FRAGN: /* next fragments headers */ - local_skb = skb_clone(skb, GFP_ATOMIC); + if (skb->data[0] == LOWPAN_DISPATCH_IPV6) { + /* Copy the packet so that the IPv6 header is + * properly aligned. + */ + local_skb = skb_copy_expand(skb, NET_SKB_PAD - 1, + skb_tailroom(skb), GFP_ATOMIC); if (!local_skb) goto drop; - lowpan_process_data(local_skb); + local_skb->protocol = htons(ETH_P_IPV6); + local_skb->pkt_type = PACKET_HOST; + + /* Pull off the 1-byte of 6lowpan header. */ + skb_pull(local_skb, 1); + skb_reset_network_header(local_skb); + skb_set_transport_header(local_skb, sizeof(struct ipv6hdr)); + + lowpan_give_skb_to_devices(local_skb); + + kfree_skb(local_skb); kfree_skb(skb); - break; - default: - break; + } else { + switch (skb->data[0] & 0xe0) { + case LOWPAN_DISPATCH_IPHC: /* ipv6 datagram */ + case LOWPAN_DISPATCH_FRAG1: /* first fragment header */ + case LOWPAN_DISPATCH_FRAGN: /* next fragments headers */ + local_skb = skb_clone(skb, GFP_ATOMIC); + if (!local_skb) + goto drop; + lowpan_process_data(local_skb); + + kfree_skb(skb); + break; + default: + break; + } } return NET_RX_SUCCESS; @@ -1234,7 +1262,7 @@ static inline int __init lowpan_netlink_init(void) return rtnl_link_register(&lowpan_link_ops); } -static inline void __init lowpan_netlink_fini(void) +static inline void lowpan_netlink_fini(void) { rtnl_link_unregister(&lowpan_link_ops); } diff --git a/net/ipv4/af_inet.c b/net/ipv4/af_inet.c index 24b384b7903e..e225a4e5b572 100644 --- a/net/ipv4/af_inet.c +++ b/net/ipv4/af_inet.c @@ -263,21 +263,6 @@ void build_ehash_secret(void) } EXPORT_SYMBOL(build_ehash_secret); -static inline int inet_netns_ok(struct net *net, __u8 protocol) -{ - const struct net_protocol *ipprot; - - if (net_eq(net, &init_net)) - return 1; - - ipprot = rcu_dereference(inet_protos[protocol]); - if (ipprot == NULL) { - /* raw IP is OK */ - return 1; - } - return ipprot->netns_ok; -} - /* * Create an inet socket. */ @@ -350,10 +335,6 @@ lookup_protocol: !ns_capable(net->user_ns, CAP_NET_RAW)) goto out_rcu_unlock; - err = -EAFNOSUPPORT; - if (!inet_netns_ok(net, protocol)) - goto out_rcu_unlock; - sock->ops = answer->ops; answer_prot = answer->prot; answer_no_check = answer->no_check; @@ -1306,6 +1287,7 @@ static struct sk_buff *inet_gso_segment(struct sk_buff *skb, SKB_GSO_UDP | SKB_GSO_DODGY | SKB_GSO_TCP_ECN | + SKB_GSO_GRE | 0))) goto out; @@ -1333,7 +1315,7 @@ static struct sk_buff *inet_gso_segment(struct sk_buff *skb, segs = ops->callbacks.gso_segment(skb, features); rcu_read_unlock(); - if (!segs || IS_ERR(segs)) + if (IS_ERR_OR_NULL(segs)) goto out; skb = segs; @@ -1705,12 +1687,11 @@ static struct packet_type ip_packet_type __read_mostly = { static int __init inet_init(void) { - struct sk_buff *dummy_skb; struct inet_protosw *q; struct list_head *r; int rc = -EINVAL; - BUILD_BUG_ON(sizeof(struct inet_skb_parm) > sizeof(dummy_skb->cb)); + BUILD_BUG_ON(sizeof(struct inet_skb_parm) > FIELD_SIZEOF(struct sk_buff, cb)); sysctl_local_reserved_ports = kzalloc(65536 / 8, GFP_KERNEL); if (!sysctl_local_reserved_ports) diff --git a/net/ipv4/ah4.c b/net/ipv4/ah4.c index a0d8392491c3..2e7f1948216f 100644 --- a/net/ipv4/ah4.c +++ b/net/ipv4/ah4.c @@ -269,7 +269,11 @@ static void ah_input_done(struct crypto_async_request *base, int err) skb->network_header += ah_hlen; memcpy(skb_network_header(skb), work_iph, ihl); __skb_pull(skb, ah_hlen + ihl); - skb_set_transport_header(skb, -ihl); + + if (x->props.mode == XFRM_MODE_TUNNEL) + skb_reset_transport_header(skb); + else + skb_set_transport_header(skb, -ihl); out: kfree(AH_SKB_CB(skb)->tmp); xfrm_input_resume(skb, err); @@ -317,8 +321,7 @@ static int ah_input(struct xfrm_state *x, struct sk_buff *skb) /* We are going to _remove_ AH header to keep sockets happy, * so... Later this can change. */ - if (skb_cloned(skb) && - pskb_expand_head(skb, 0, 0, GFP_ATOMIC)) + if (skb_unclone(skb, GFP_ATOMIC)) goto out; skb->ip_summed = CHECKSUM_NONE; @@ -381,7 +384,10 @@ static int ah_input(struct xfrm_state *x, struct sk_buff *skb) skb->network_header += ah_hlen; memcpy(skb_network_header(skb), work_iph, ihl); __skb_pull(skb, ah_hlen + ihl); - skb_set_transport_header(skb, -ihl); + if (x->props.mode == XFRM_MODE_TUNNEL) + skb_reset_transport_header(skb); + else + skb_set_transport_header(skb, -ihl); err = nexthdr; @@ -413,9 +419,12 @@ static void ah4_err(struct sk_buff *skb, u32 info) if (!x) return; - if (icmp_hdr(skb)->type == ICMP_DEST_UNREACH) + if (icmp_hdr(skb)->type == ICMP_DEST_UNREACH) { + atomic_inc(&flow_cache_genid); + rt_genid_bump(net); + ipv4_update_pmtu(skb, net, info, 0, 0, IPPROTO_AH, 0); - else + } else ipv4_redirect(skb, net, 0, 0, IPPROTO_AH, 0); xfrm_state_put(x); } diff --git a/net/ipv4/arp.c b/net/ipv4/arp.c index ce6fbdfd40b8..ded146b217f1 100644 --- a/net/ipv4/arp.c +++ b/net/ipv4/arp.c @@ -321,7 +321,7 @@ static void arp_error_report(struct neighbour *neigh, struct sk_buff *skb) static void arp_solicit(struct neighbour *neigh, struct sk_buff *skb) { __be32 saddr = 0; - u8 *dst_ha = NULL; + u8 dst_ha[MAX_ADDR_LEN], *dst_hw = NULL; struct net_device *dev = neigh->dev; __be32 target = *(__be32 *)neigh->primary_key; int probes = atomic_read(&neigh->probes); @@ -363,8 +363,8 @@ static void arp_solicit(struct neighbour *neigh, struct sk_buff *skb) if (probes < 0) { if (!(neigh->nud_state & NUD_VALID)) pr_debug("trying to ucast probe in NUD_INVALID\n"); - dst_ha = neigh->ha; - read_lock_bh(&neigh->lock); + neigh_ha_snapshot(dst_ha, neigh, dev); + dst_hw = dst_ha; } else { probes -= neigh->parms->app_probes; if (probes < 0) { @@ -376,9 +376,7 @@ static void arp_solicit(struct neighbour *neigh, struct sk_buff *skb) } arp_send(ARPOP_REQUEST, ETH_P_ARP, target, dev, saddr, - dst_ha, dev->dev_addr, NULL); - if (dst_ha) - read_unlock_bh(&neigh->lock); + dst_hw, dev->dev_addr, NULL); } static int arp_ignore(struct in_device *in_dev, __be32 sip, __be32 tip) @@ -930,24 +928,25 @@ static void parp_redo(struct sk_buff *skb) static int arp_rcv(struct sk_buff *skb, struct net_device *dev, struct packet_type *pt, struct net_device *orig_dev) { - struct arphdr *arp; + const struct arphdr *arp; + + if (dev->flags & IFF_NOARP || + skb->pkt_type == PACKET_OTHERHOST || + skb->pkt_type == PACKET_LOOPBACK) + goto freeskb; + + skb = skb_share_check(skb, GFP_ATOMIC); + if (!skb) + goto out_of_mem; /* ARP header, plus 2 device addresses, plus 2 IP addresses. */ if (!pskb_may_pull(skb, arp_hdr_len(dev))) goto freeskb; arp = arp_hdr(skb); - if (arp->ar_hln != dev->addr_len || - dev->flags & IFF_NOARP || - skb->pkt_type == PACKET_OTHERHOST || - skb->pkt_type == PACKET_LOOPBACK || - arp->ar_pln != 4) + if (arp->ar_hln != dev->addr_len || arp->ar_pln != 4) goto freeskb; - skb = skb_share_check(skb, GFP_ATOMIC); - if (skb == NULL) - goto out_of_mem; - memset(NEIGH_CB(skb), 0, sizeof(struct neighbour_cb)); return NF_HOOK(NFPROTO_ARP, NF_ARP_IN, skb, dev, NULL, arp_process); diff --git a/net/ipv4/datagram.c b/net/ipv4/datagram.c index 424fafbc8cb0..b28e863fe0a7 100644 --- a/net/ipv4/datagram.c +++ b/net/ipv4/datagram.c @@ -85,3 +85,28 @@ out: return err; } EXPORT_SYMBOL(ip4_datagram_connect); + +void ip4_datagram_release_cb(struct sock *sk) +{ + const struct inet_sock *inet = inet_sk(sk); + const struct ip_options_rcu *inet_opt; + __be32 daddr = inet->inet_daddr; + struct flowi4 fl4; + struct rtable *rt; + + if (! __sk_dst_get(sk) || __sk_dst_check(sk, 0)) + return; + + rcu_read_lock(); + inet_opt = rcu_dereference(inet->inet_opt); + if (inet_opt && inet_opt->opt.srr) + daddr = inet_opt->opt.faddr; + rt = ip_route_output_ports(sock_net(sk), &fl4, sk, daddr, + inet->inet_saddr, inet->inet_dport, + inet->inet_sport, sk->sk_protocol, + RT_CONN_FLAGS(sk), sk->sk_bound_dev_if); + if (!IS_ERR(rt)) + __sk_dst_set(sk, &rt->dst); + rcu_read_unlock(); +} +EXPORT_SYMBOL_GPL(ip4_datagram_release_cb); diff --git a/net/ipv4/devinet.c b/net/ipv4/devinet.c index cc06a47f1216..5281314886c1 100644 --- a/net/ipv4/devinet.c +++ b/net/ipv4/devinet.c @@ -63,6 +63,7 @@ #include <net/ip_fib.h> #include <net/rtnetlink.h> #include <net/net_namespace.h> +#include <net/addrconf.h> #include "fib_lookup.h" @@ -93,6 +94,7 @@ static const struct nla_policy ifa_ipv4_policy[IFA_MAX+1] = { [IFA_ADDRESS] = { .type = NLA_U32 }, [IFA_BROADCAST] = { .type = NLA_U32 }, [IFA_LABEL] = { .type = NLA_STRING, .len = IFNAMSIZ - 1 }, + [IFA_CACHEINFO] = { .len = sizeof(struct ifa_cacheinfo) }, }; #define IN4_ADDR_HSIZE_SHIFT 8 @@ -417,6 +419,10 @@ static void inet_del_ifa(struct in_device *in_dev, struct in_ifaddr **ifap, __inet_del_ifa(in_dev, ifap, destroy, NULL, 0); } +static void check_lifetime(struct work_struct *work); + +static DECLARE_DELAYED_WORK(check_lifetime_work, check_lifetime); + static int __inet_insert_ifa(struct in_ifaddr *ifa, struct nlmsghdr *nlh, u32 portid) { @@ -462,6 +468,9 @@ static int __inet_insert_ifa(struct in_ifaddr *ifa, struct nlmsghdr *nlh, inet_hash_insert(dev_net(in_dev->dev), ifa); + cancel_delayed_work(&check_lifetime_work); + schedule_delayed_work(&check_lifetime_work, 0); + /* Send message first, then call notifier. Notifier will trigger FIB update, so that listeners of netlink will know about new ifaddr */ @@ -573,7 +582,107 @@ errout: return err; } -static struct in_ifaddr *rtm_to_ifaddr(struct net *net, struct nlmsghdr *nlh) +#define INFINITY_LIFE_TIME 0xFFFFFFFF + +static void check_lifetime(struct work_struct *work) +{ + unsigned long now, next, next_sec, next_sched; + struct in_ifaddr *ifa; + struct hlist_node *node; + int i; + + now = jiffies; + next = round_jiffies_up(now + ADDR_CHECK_FREQUENCY); + + rcu_read_lock(); + for (i = 0; i < IN4_ADDR_HSIZE; i++) { + hlist_for_each_entry_rcu(ifa, node, + &inet_addr_lst[i], hash) { + unsigned long age; + + if (ifa->ifa_flags & IFA_F_PERMANENT) + continue; + + /* We try to batch several events at once. */ + age = (now - ifa->ifa_tstamp + + ADDRCONF_TIMER_FUZZ_MINUS) / HZ; + + if (ifa->ifa_valid_lft != INFINITY_LIFE_TIME && + age >= ifa->ifa_valid_lft) { + struct in_ifaddr **ifap ; + + rtnl_lock(); + for (ifap = &ifa->ifa_dev->ifa_list; + *ifap != NULL; ifap = &ifa->ifa_next) { + if (*ifap == ifa) + inet_del_ifa(ifa->ifa_dev, + ifap, 1); + } + rtnl_unlock(); + } else if (ifa->ifa_preferred_lft == + INFINITY_LIFE_TIME) { + continue; + } else if (age >= ifa->ifa_preferred_lft) { + if (time_before(ifa->ifa_tstamp + + ifa->ifa_valid_lft * HZ, next)) + next = ifa->ifa_tstamp + + ifa->ifa_valid_lft * HZ; + + if (!(ifa->ifa_flags & IFA_F_DEPRECATED)) { + ifa->ifa_flags |= IFA_F_DEPRECATED; + rtmsg_ifa(RTM_NEWADDR, ifa, NULL, 0); + } + } else if (time_before(ifa->ifa_tstamp + + ifa->ifa_preferred_lft * HZ, + next)) { + next = ifa->ifa_tstamp + + ifa->ifa_preferred_lft * HZ; + } + } + } + rcu_read_unlock(); + + next_sec = round_jiffies_up(next); + next_sched = next; + + /* If rounded timeout is accurate enough, accept it. */ + if (time_before(next_sec, next + ADDRCONF_TIMER_FUZZ)) + next_sched = next_sec; + + now = jiffies; + /* And minimum interval is ADDRCONF_TIMER_FUZZ_MAX. */ + if (time_before(next_sched, now + ADDRCONF_TIMER_FUZZ_MAX)) + next_sched = now + ADDRCONF_TIMER_FUZZ_MAX; + + schedule_delayed_work(&check_lifetime_work, next_sched - now); +} + +static void set_ifa_lifetime(struct in_ifaddr *ifa, __u32 valid_lft, + __u32 prefered_lft) +{ + unsigned long timeout; + + ifa->ifa_flags &= ~(IFA_F_PERMANENT | IFA_F_DEPRECATED); + + timeout = addrconf_timeout_fixup(valid_lft, HZ); + if (addrconf_finite_timeout(timeout)) + ifa->ifa_valid_lft = timeout; + else + ifa->ifa_flags |= IFA_F_PERMANENT; + + timeout = addrconf_timeout_fixup(prefered_lft, HZ); + if (addrconf_finite_timeout(timeout)) { + if (timeout == 0) + ifa->ifa_flags |= IFA_F_DEPRECATED; + ifa->ifa_preferred_lft = timeout; + } + ifa->ifa_tstamp = jiffies; + if (!ifa->ifa_cstamp) + ifa->ifa_cstamp = ifa->ifa_tstamp; +} + +static struct in_ifaddr *rtm_to_ifaddr(struct net *net, struct nlmsghdr *nlh, + __u32 *pvalid_lft, __u32 *pprefered_lft) { struct nlattr *tb[IFA_MAX+1]; struct in_ifaddr *ifa; @@ -633,24 +742,73 @@ static struct in_ifaddr *rtm_to_ifaddr(struct net *net, struct nlmsghdr *nlh) else memcpy(ifa->ifa_label, dev->name, IFNAMSIZ); + if (tb[IFA_CACHEINFO]) { + struct ifa_cacheinfo *ci; + + ci = nla_data(tb[IFA_CACHEINFO]); + if (!ci->ifa_valid || ci->ifa_prefered > ci->ifa_valid) { + err = -EINVAL; + goto errout; + } + *pvalid_lft = ci->ifa_valid; + *pprefered_lft = ci->ifa_prefered; + } + return ifa; errout: return ERR_PTR(err); } +static struct in_ifaddr *find_matching_ifa(struct in_ifaddr *ifa) +{ + struct in_device *in_dev = ifa->ifa_dev; + struct in_ifaddr *ifa1, **ifap; + + if (!ifa->ifa_local) + return NULL; + + for (ifap = &in_dev->ifa_list; (ifa1 = *ifap) != NULL; + ifap = &ifa1->ifa_next) { + if (ifa1->ifa_mask == ifa->ifa_mask && + inet_ifa_match(ifa1->ifa_address, ifa) && + ifa1->ifa_local == ifa->ifa_local) + return ifa1; + } + return NULL; +} + static int inet_rtm_newaddr(struct sk_buff *skb, struct nlmsghdr *nlh, void *arg) { struct net *net = sock_net(skb->sk); struct in_ifaddr *ifa; + struct in_ifaddr *ifa_existing; + __u32 valid_lft = INFINITY_LIFE_TIME; + __u32 prefered_lft = INFINITY_LIFE_TIME; ASSERT_RTNL(); - ifa = rtm_to_ifaddr(net, nlh); + ifa = rtm_to_ifaddr(net, nlh, &valid_lft, &prefered_lft); if (IS_ERR(ifa)) return PTR_ERR(ifa); - return __inet_insert_ifa(ifa, nlh, NETLINK_CB(skb).portid); + ifa_existing = find_matching_ifa(ifa); + if (!ifa_existing) { + /* It would be best to check for !NLM_F_CREATE here but + * userspace alreay relies on not having to provide this. + */ + set_ifa_lifetime(ifa, valid_lft, prefered_lft); + return __inet_insert_ifa(ifa, nlh, NETLINK_CB(skb).portid); + } else { + inet_free_ifa(ifa); + + if (nlh->nlmsg_flags & NLM_F_EXCL || + !(nlh->nlmsg_flags & NLM_F_REPLACE)) + return -EEXIST; + + set_ifa_lifetime(ifa_existing, valid_lft, prefered_lft); + } + return 0; } /* @@ -823,9 +981,9 @@ int devinet_ioctl(struct net *net, unsigned int cmd, void __user *arg) if (!ifa) { ret = -ENOBUFS; ifa = inet_alloc_ifa(); - INIT_HLIST_NODE(&ifa->hash); if (!ifa) break; + INIT_HLIST_NODE(&ifa->hash); if (colon) memcpy(ifa->ifa_label, ifr.ifr_name, IFNAMSIZ); else @@ -852,6 +1010,7 @@ int devinet_ioctl(struct net *net, unsigned int cmd, void __user *arg) ifa->ifa_prefixlen = 32; ifa->ifa_mask = inet_make_mask(32); } + set_ifa_lifetime(ifa, INFINITY_LIFE_TIME, INFINITY_LIFE_TIME); ret = inet_set_ifa(dev, ifa); break; @@ -1190,6 +1349,8 @@ static int inetdev_event(struct notifier_block *this, unsigned long event, 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, + INFINITY_LIFE_TIME); inet_insert_ifa(ifa); } } @@ -1246,11 +1407,30 @@ static size_t inet_nlmsg_size(void) + nla_total_size(IFNAMSIZ); /* IFA_LABEL */ } +static inline u32 cstamp_delta(unsigned long cstamp) +{ + return (cstamp - INITIAL_JIFFIES) * 100UL / HZ; +} + +static int put_cacheinfo(struct sk_buff *skb, unsigned long cstamp, + unsigned long tstamp, u32 preferred, u32 valid) +{ + struct ifa_cacheinfo ci; + + ci.cstamp = cstamp_delta(cstamp); + ci.tstamp = cstamp_delta(tstamp); + ci.ifa_prefered = preferred; + ci.ifa_valid = valid; + + return nla_put(skb, IFA_CACHEINFO, sizeof(ci), &ci); +} + static int inet_fill_ifaddr(struct sk_buff *skb, struct in_ifaddr *ifa, u32 portid, u32 seq, int event, unsigned int flags) { struct ifaddrmsg *ifm; struct nlmsghdr *nlh; + u32 preferred, valid; nlh = nlmsg_put(skb, portid, seq, event, sizeof(*ifm), flags); if (nlh == NULL) @@ -1259,10 +1439,31 @@ static int inet_fill_ifaddr(struct sk_buff *skb, struct in_ifaddr *ifa, ifm = nlmsg_data(nlh); ifm->ifa_family = AF_INET; ifm->ifa_prefixlen = ifa->ifa_prefixlen; - ifm->ifa_flags = ifa->ifa_flags|IFA_F_PERMANENT; + ifm->ifa_flags = ifa->ifa_flags; ifm->ifa_scope = ifa->ifa_scope; ifm->ifa_index = ifa->ifa_dev->dev->ifindex; + if (!(ifm->ifa_flags & IFA_F_PERMANENT)) { + preferred = ifa->ifa_preferred_lft; + valid = ifa->ifa_valid_lft; + if (preferred != INFINITY_LIFE_TIME) { + long tval = (jiffies - ifa->ifa_tstamp) / HZ; + + if (preferred > tval) + preferred -= tval; + else + preferred = 0; + if (valid != INFINITY_LIFE_TIME) { + if (valid > tval) + valid -= tval; + else + valid = 0; + } + } + } else { + preferred = INFINITY_LIFE_TIME; + valid = INFINITY_LIFE_TIME; + } if ((ifa->ifa_address && nla_put_be32(skb, IFA_ADDRESS, ifa->ifa_address)) || (ifa->ifa_local && @@ -1270,7 +1471,9 @@ static int inet_fill_ifaddr(struct sk_buff *skb, struct in_ifaddr *ifa, (ifa->ifa_broadcast && nla_put_be32(skb, IFA_BROADCAST, ifa->ifa_broadcast)) || (ifa->ifa_label[0] && - nla_put_string(skb, IFA_LABEL, ifa->ifa_label))) + nla_put_string(skb, IFA_LABEL, ifa->ifa_label)) || + put_cacheinfo(skb, ifa->ifa_cstamp, ifa->ifa_tstamp, + preferred, valid)) goto nla_put_failure; return nlmsg_end(skb, nlh); @@ -1988,6 +2191,8 @@ void __init devinet_init(void) register_gifconf(PF_INET, inet_gifconf); register_netdevice_notifier(&ip_netdev_notifier); + schedule_delayed_work(&check_lifetime_work, 0); + rtnl_af_register(&inet_af_ops); rtnl_register(PF_INET, RTM_NEWADDR, inet_rtm_newaddr, NULL, NULL); diff --git a/net/ipv4/esp4.c b/net/ipv4/esp4.c index b61e9deb7c7e..3b4f0cd2e63e 100644 --- a/net/ipv4/esp4.c +++ b/net/ipv4/esp4.c @@ -346,7 +346,10 @@ static int esp_input_done2(struct sk_buff *skb, int err) pskb_trim(skb, skb->len - alen - padlen - 2); __skb_pull(skb, hlen); - skb_set_transport_header(skb, -ihl); + if (x->props.mode == XFRM_MODE_TUNNEL) + skb_reset_transport_header(skb); + else + skb_set_transport_header(skb, -ihl); err = nexthdr[1]; @@ -499,9 +502,12 @@ static void esp4_err(struct sk_buff *skb, u32 info) if (!x) return; - if (icmp_hdr(skb)->type == ICMP_DEST_UNREACH) + if (icmp_hdr(skb)->type == ICMP_DEST_UNREACH) { + atomic_inc(&flow_cache_genid); + rt_genid_bump(net); + ipv4_update_pmtu(skb, net, info, 0, 0, IPPROTO_ESP, 0); - else + } else ipv4_redirect(skb, net, 0, 0, IPPROTO_ESP, 0); xfrm_state_put(x); } diff --git a/net/ipv4/fib_frontend.c b/net/ipv4/fib_frontend.c index 5cd75e2dab2c..99f00d39d10b 100644 --- a/net/ipv4/fib_frontend.c +++ b/net/ipv4/fib_frontend.c @@ -974,7 +974,7 @@ static void nl_fib_input(struct sk_buff *skb) nl_fib_lookup(frn, tb); - portid = NETLINK_CB(skb).portid; /* pid of sending process */ + portid = NETLINK_CB(skb).portid; /* netlink portid */ NETLINK_CB(skb).portid = 0; /* from kernel */ NETLINK_CB(skb).dst_group = 0; /* unicast */ netlink_unicast(net->ipv4.fibnl, skb, portid, MSG_DONTWAIT); diff --git a/net/ipv4/gre.c b/net/ipv4/gre.c index 42a491055c76..7a4c710c4cdd 100644 --- a/net/ipv4/gre.c +++ b/net/ipv4/gre.c @@ -19,6 +19,7 @@ #include <linux/in.h> #include <linux/ip.h> #include <linux/netdevice.h> +#include <linux/if_tunnel.h> #include <linux/spinlock.h> #include <net/protocol.h> #include <net/gre.h> @@ -26,6 +27,11 @@ static const struct gre_protocol __rcu *gre_proto[GREPROTO_MAX] __read_mostly; static DEFINE_SPINLOCK(gre_proto_lock); +struct gre_base_hdr { + __be16 flags; + __be16 protocol; +}; +#define GRE_HEADER_SECTION 4 int gre_add_protocol(const struct gre_protocol *proto, u8 version) { @@ -112,12 +118,117 @@ static void gre_err(struct sk_buff *skb, u32 info) rcu_read_unlock(); } +static struct sk_buff *gre_gso_segment(struct sk_buff *skb, + netdev_features_t features) +{ + struct sk_buff *segs = ERR_PTR(-EINVAL); + netdev_features_t enc_features; + int ghl = GRE_HEADER_SECTION; + struct gre_base_hdr *greh; + int mac_len = skb->mac_len; + int tnl_hlen; + bool csum; + + if (unlikely(skb_shinfo(skb)->gso_type & + ~(SKB_GSO_TCPV4 | + SKB_GSO_TCPV6 | + SKB_GSO_UDP | + SKB_GSO_DODGY | + SKB_GSO_TCP_ECN | + SKB_GSO_GRE))) + goto out; + + if (unlikely(!pskb_may_pull(skb, sizeof(*greh)))) + goto out; + + greh = (struct gre_base_hdr *)skb_transport_header(skb); + + if (greh->flags & GRE_KEY) + ghl += GRE_HEADER_SECTION; + if (greh->flags & GRE_SEQ) + ghl += GRE_HEADER_SECTION; + if (greh->flags & GRE_CSUM) { + ghl += GRE_HEADER_SECTION; + csum = true; + } else + csum = false; + + /* setup inner skb. */ + if (greh->protocol == htons(ETH_P_TEB)) { + struct ethhdr *eth = eth_hdr(skb); + skb->protocol = eth->h_proto; + } else { + skb->protocol = greh->protocol; + } + + skb->encapsulation = 0; + + if (unlikely(!pskb_may_pull(skb, ghl))) + goto out; + __skb_pull(skb, ghl); + skb_reset_mac_header(skb); + skb_set_network_header(skb, skb_inner_network_offset(skb)); + skb->mac_len = skb_inner_network_offset(skb); + + /* segment inner packet. */ + enc_features = skb->dev->hw_enc_features & netif_skb_features(skb); + segs = skb_mac_gso_segment(skb, enc_features); + if (!segs || IS_ERR(segs)) + goto out; + + skb = segs; + tnl_hlen = skb_tnl_header_len(skb); + do { + __skb_push(skb, ghl); + if (csum) { + __be32 *pcsum; + + if (skb_has_shared_frag(skb)) { + int err; + + err = __skb_linearize(skb); + if (err) { + kfree_skb(segs); + segs = ERR_PTR(err); + goto out; + } + } + + greh = (struct gre_base_hdr *)(skb->data); + pcsum = (__be32 *)(greh + 1); + *pcsum = 0; + *(__sum16 *)pcsum = csum_fold(skb_checksum(skb, 0, skb->len, 0)); + } + __skb_push(skb, tnl_hlen - ghl); + + skb_reset_mac_header(skb); + skb_set_network_header(skb, mac_len); + skb->mac_len = mac_len; + } while ((skb = skb->next)); +out: + return segs; +} + +static int gre_gso_send_check(struct sk_buff *skb) +{ + if (!skb->encapsulation) + return -EINVAL; + return 0; +} + static const struct net_protocol net_gre_protocol = { .handler = gre_rcv, .err_handler = gre_err, .netns_ok = 1, }; +static const struct net_offload gre_offload = { + .callbacks = { + .gso_send_check = gre_gso_send_check, + .gso_segment = gre_gso_segment, + }, +}; + static int __init gre_init(void) { pr_info("GRE over IPv4 demultiplexor driver\n"); @@ -127,11 +238,18 @@ static int __init gre_init(void) return -EAGAIN; } + if (inet_add_offload(&gre_offload, IPPROTO_GRE)) { + pr_err("can't add protocol offload\n"); + inet_del_protocol(&net_gre_protocol, IPPROTO_GRE); + return -EAGAIN; + } + return 0; } static void __exit gre_exit(void) { + inet_del_offload(&gre_offload, IPPROTO_GRE); inet_del_protocol(&net_gre_protocol, IPPROTO_GRE); } diff --git a/net/ipv4/inet_connection_sock.c b/net/ipv4/inet_connection_sock.c index d0670f00d524..11cb4979a465 100644 --- a/net/ipv4/inet_connection_sock.c +++ b/net/ipv4/inet_connection_sock.c @@ -59,6 +59,8 @@ int inet_csk_bind_conflict(const struct sock *sk, struct sock *sk2; struct hlist_node *node; int reuse = sk->sk_reuse; + int reuseport = sk->sk_reuseport; + kuid_t uid = sock_i_uid((struct sock *)sk); /* * Unlike other sk lookup places we do not check @@ -73,8 +75,11 @@ int inet_csk_bind_conflict(const struct sock *sk, (!sk->sk_bound_dev_if || !sk2->sk_bound_dev_if || sk->sk_bound_dev_if == sk2->sk_bound_dev_if)) { - if (!reuse || !sk2->sk_reuse || - sk2->sk_state == TCP_LISTEN) { + if ((!reuse || !sk2->sk_reuse || + sk2->sk_state == TCP_LISTEN) && + (!reuseport || !sk2->sk_reuseport || + (sk2->sk_state != TCP_TIME_WAIT && + !uid_eq(uid, sock_i_uid(sk2))))) { const __be32 sk2_rcv_saddr = sk_rcv_saddr(sk2); if (!sk2_rcv_saddr || !sk_rcv_saddr(sk) || sk2_rcv_saddr == sk_rcv_saddr(sk)) @@ -106,6 +111,7 @@ int inet_csk_get_port(struct sock *sk, unsigned short snum) int ret, attempts = 5; struct net *net = sock_net(sk); int smallest_size = -1, smallest_rover; + kuid_t uid = sock_i_uid(sk); local_bh_disable(); if (!snum) { @@ -125,9 +131,12 @@ again: spin_lock(&head->lock); inet_bind_bucket_for_each(tb, node, &head->chain) if (net_eq(ib_net(tb), net) && tb->port == rover) { - if (tb->fastreuse > 0 && - sk->sk_reuse && - sk->sk_state != TCP_LISTEN && + if (((tb->fastreuse > 0 && + sk->sk_reuse && + sk->sk_state != TCP_LISTEN) || + (tb->fastreuseport > 0 && + sk->sk_reuseport && + uid_eq(tb->fastuid, uid))) && (tb->num_owners < smallest_size || smallest_size == -1)) { smallest_size = tb->num_owners; smallest_rover = rover; @@ -185,14 +194,18 @@ tb_found: if (sk->sk_reuse == SK_FORCE_REUSE) goto success; - if (tb->fastreuse > 0 && - sk->sk_reuse && sk->sk_state != TCP_LISTEN && + if (((tb->fastreuse > 0 && + sk->sk_reuse && sk->sk_state != TCP_LISTEN) || + (tb->fastreuseport > 0 && + sk->sk_reuseport && uid_eq(tb->fastuid, uid))) && smallest_size == -1) { goto success; } else { ret = 1; if (inet_csk(sk)->icsk_af_ops->bind_conflict(sk, tb, true)) { - if (sk->sk_reuse && sk->sk_state != TCP_LISTEN && + if (((sk->sk_reuse && sk->sk_state != TCP_LISTEN) || + (tb->fastreuseport > 0 && + sk->sk_reuseport && uid_eq(tb->fastuid, uid))) && smallest_size != -1 && --attempts >= 0) { spin_unlock(&head->lock); goto again; @@ -212,9 +225,19 @@ tb_not_found: tb->fastreuse = 1; else tb->fastreuse = 0; - } else if (tb->fastreuse && - (!sk->sk_reuse || sk->sk_state == TCP_LISTEN)) - tb->fastreuse = 0; + if (sk->sk_reuseport) { + tb->fastreuseport = 1; + tb->fastuid = uid; + } else + tb->fastreuseport = 0; + } else { + if (tb->fastreuse && + (!sk->sk_reuse || sk->sk_state == TCP_LISTEN)) + tb->fastreuse = 0; + if (tb->fastreuseport && + (!sk->sk_reuseport || !uid_eq(tb->fastuid, uid))) + tb->fastreuseport = 0; + } success: if (!inet_csk(sk)->icsk_bind_hash) inet_bind_hash(sk, tb, snum); diff --git a/net/ipv4/inet_fragment.c b/net/ipv4/inet_fragment.c index 4750d2b74d79..2e453bde6992 100644 --- a/net/ipv4/inet_fragment.c +++ b/net/ipv4/inet_fragment.c @@ -73,8 +73,9 @@ EXPORT_SYMBOL(inet_frags_init); void inet_frags_init_net(struct netns_frags *nf) { nf->nqueues = 0; - atomic_set(&nf->mem, 0); + init_frag_mem_limit(nf); INIT_LIST_HEAD(&nf->lru_list); + spin_lock_init(&nf->lru_lock); } EXPORT_SYMBOL(inet_frags_init_net); @@ -91,6 +92,8 @@ void inet_frags_exit_net(struct netns_frags *nf, struct inet_frags *f) local_bh_disable(); inet_frag_evictor(nf, f, true); local_bh_enable(); + + percpu_counter_destroy(&nf->mem); } EXPORT_SYMBOL(inet_frags_exit_net); @@ -98,9 +101,9 @@ static inline void fq_unlink(struct inet_frag_queue *fq, struct inet_frags *f) { write_lock(&f->lock); hlist_del(&fq->list); - list_del(&fq->lru_list); fq->net->nqueues--; write_unlock(&f->lock); + inet_frag_lru_del(fq); } void inet_frag_kill(struct inet_frag_queue *fq, struct inet_frags *f) @@ -117,12 +120,8 @@ void inet_frag_kill(struct inet_frag_queue *fq, struct inet_frags *f) EXPORT_SYMBOL(inet_frag_kill); static inline void frag_kfree_skb(struct netns_frags *nf, struct inet_frags *f, - struct sk_buff *skb, int *work) + struct sk_buff *skb) { - if (work) - *work -= skb->truesize; - - atomic_sub(skb->truesize, &nf->mem); if (f->skb_free) f->skb_free(skb); kfree_skb(skb); @@ -133,6 +132,7 @@ void inet_frag_destroy(struct inet_frag_queue *q, struct inet_frags *f, { struct sk_buff *fp; struct netns_frags *nf; + unsigned int sum, sum_truesize = 0; WARN_ON(!(q->last_in & INET_FRAG_COMPLETE)); WARN_ON(del_timer(&q->timer) != 0); @@ -143,13 +143,14 @@ void inet_frag_destroy(struct inet_frag_queue *q, struct inet_frags *f, while (fp) { struct sk_buff *xp = fp->next; - frag_kfree_skb(nf, f, fp, work); + sum_truesize += fp->truesize; + frag_kfree_skb(nf, f, fp); fp = xp; } - + sum = sum_truesize + f->qsize; if (work) - *work -= f->qsize; - atomic_sub(f->qsize, &nf->mem); + *work -= sum; + sub_frag_mem_limit(q, sum); if (f->destructor) f->destructor(q); @@ -164,22 +165,23 @@ int inet_frag_evictor(struct netns_frags *nf, struct inet_frags *f, bool force) int work, evicted = 0; if (!force) { - if (atomic_read(&nf->mem) <= nf->high_thresh) + if (frag_mem_limit(nf) <= nf->high_thresh) return 0; } - work = atomic_read(&nf->mem) - nf->low_thresh; + work = frag_mem_limit(nf) - nf->low_thresh; while (work > 0) { - read_lock(&f->lock); + spin_lock(&nf->lru_lock); + if (list_empty(&nf->lru_list)) { - read_unlock(&f->lock); + spin_unlock(&nf->lru_lock); break; } q = list_first_entry(&nf->lru_list, struct inet_frag_queue, lru_list); atomic_inc(&q->refcnt); - read_unlock(&f->lock); + spin_unlock(&nf->lru_lock); spin_lock(&q->lock); if (!(q->last_in & INET_FRAG_COMPLETE)) @@ -233,9 +235,9 @@ static struct inet_frag_queue *inet_frag_intern(struct netns_frags *nf, atomic_inc(&qp->refcnt); hlist_add_head(&qp->list, &f->hash[hash]); - list_add_tail(&qp->lru_list, &nf->lru_list); nf->nqueues++; write_unlock(&f->lock); + inet_frag_lru_add(nf, qp); return qp; } @@ -250,7 +252,8 @@ static struct inet_frag_queue *inet_frag_alloc(struct netns_frags *nf, q->net = nf; f->constructor(q, arg); - atomic_add(f->qsize, &nf->mem); + add_frag_mem_limit(q, f->qsize); + setup_timer(&q->timer, f->frag_expire, (unsigned long)q); spin_lock_init(&q->lock); atomic_set(&q->refcnt, 1); diff --git a/net/ipv4/inet_hashtables.c b/net/ipv4/inet_hashtables.c index fa3ae8148710..0ce0595d9861 100644 --- a/net/ipv4/inet_hashtables.c +++ b/net/ipv4/inet_hashtables.c @@ -39,6 +39,7 @@ struct inet_bind_bucket *inet_bind_bucket_create(struct kmem_cache *cachep, write_pnet(&tb->ib_net, hold_net(net)); tb->port = snum; tb->fastreuse = 0; + tb->fastreuseport = 0; tb->num_owners = 0; INIT_HLIST_HEAD(&tb->owners); hlist_add_head(&tb->node, &head->chain); @@ -151,16 +152,16 @@ static inline int compute_score(struct sock *sk, struct net *net, if (net_eq(sock_net(sk), net) && inet->inet_num == hnum && !ipv6_only_sock(sk)) { __be32 rcv_saddr = inet->inet_rcv_saddr; - score = sk->sk_family == PF_INET ? 1 : 0; + score = sk->sk_family == PF_INET ? 2 : 1; if (rcv_saddr) { if (rcv_saddr != daddr) return -1; - score += 2; + score += 4; } if (sk->sk_bound_dev_if) { if (sk->sk_bound_dev_if != dif) return -1; - score += 2; + score += 4; } } return score; @@ -176,6 +177,7 @@ static inline int compute_score(struct sock *sk, struct net *net, struct sock *__inet_lookup_listener(struct net *net, struct inet_hashinfo *hashinfo, + const __be32 saddr, __be16 sport, const __be32 daddr, const unsigned short hnum, const int dif) { @@ -183,17 +185,29 @@ struct sock *__inet_lookup_listener(struct net *net, struct hlist_nulls_node *node; unsigned int hash = inet_lhashfn(net, hnum); struct inet_listen_hashbucket *ilb = &hashinfo->listening_hash[hash]; - int score, hiscore; + int score, hiscore, matches = 0, reuseport = 0; + u32 phash = 0; rcu_read_lock(); begin: result = NULL; - hiscore = -1; + hiscore = 0; sk_nulls_for_each_rcu(sk, node, &ilb->head) { score = compute_score(sk, net, hnum, daddr, dif); if (score > hiscore) { result = sk; hiscore = score; + reuseport = sk->sk_reuseport; + if (reuseport) { + phash = inet_ehashfn(net, daddr, hnum, + saddr, sport); + matches = 1; + } + } else if (score == hiscore && reuseport) { + matches++; + if (((u64)phash * matches) >> 32 == 0) + result = sk; + phash = next_pseudo_random32(phash); } } /* @@ -501,7 +515,8 @@ int __inet_hash_connect(struct inet_timewait_death_row *death_row, inet_bind_bucket_for_each(tb, node, &head->chain) { if (net_eq(ib_net(tb), net) && tb->port == port) { - if (tb->fastreuse >= 0) + if (tb->fastreuse >= 0 || + tb->fastreuseport >= 0) goto next_port; WARN_ON(hlist_empty(&tb->owners)); if (!check_established(death_row, sk, @@ -518,6 +533,7 @@ int __inet_hash_connect(struct inet_timewait_death_row *death_row, break; } tb->fastreuse = -1; + tb->fastreuseport = -1; goto ok; next_port: diff --git a/net/ipv4/ip_fragment.c b/net/ipv4/ip_fragment.c index eb9d63a570cd..b6d30acb600c 100644 --- a/net/ipv4/ip_fragment.c +++ b/net/ipv4/ip_fragment.c @@ -122,7 +122,7 @@ int ip_frag_nqueues(struct net *net) int ip_frag_mem(struct net *net) { - return atomic_read(&net->ipv4.frags.mem); + return sum_frag_mem_limit(&net->ipv4.frags); } static int ip_frag_reasm(struct ipq *qp, struct sk_buff *prev, @@ -161,13 +161,6 @@ static bool ip4_frag_match(struct inet_frag_queue *q, void *a) qp->user == arg->user; } -/* Memory Tracking Functions. */ -static void frag_kfree_skb(struct netns_frags *nf, struct sk_buff *skb) -{ - atomic_sub(skb->truesize, &nf->mem); - kfree_skb(skb); -} - static void ip4_frag_init(struct inet_frag_queue *q, void *a) { struct ipq *qp = container_of(q, struct ipq, q); @@ -340,6 +333,7 @@ static inline int ip_frag_too_far(struct ipq *qp) static int ip_frag_reinit(struct ipq *qp) { struct sk_buff *fp; + unsigned int sum_truesize = 0; if (!mod_timer(&qp->q.timer, jiffies + qp->q.net->timeout)) { atomic_inc(&qp->q.refcnt); @@ -349,9 +343,12 @@ static int ip_frag_reinit(struct ipq *qp) fp = qp->q.fragments; do { struct sk_buff *xp = fp->next; - frag_kfree_skb(qp->q.net, fp); + + sum_truesize += fp->truesize; + kfree_skb(fp); fp = xp; } while (fp); + sub_frag_mem_limit(&qp->q, sum_truesize); qp->q.last_in = 0; qp->q.len = 0; @@ -496,7 +493,8 @@ found: qp->q.fragments = next; qp->q.meat -= free_it->len; - frag_kfree_skb(qp->q.net, free_it); + sub_frag_mem_limit(&qp->q, free_it->truesize); + kfree_skb(free_it); } } @@ -519,7 +517,7 @@ found: qp->q.stamp = skb->tstamp; qp->q.meat += skb->len; qp->ecn |= ecn; - atomic_add(skb->truesize, &qp->q.net->mem); + add_frag_mem_limit(&qp->q, skb->truesize); if (offset == 0) qp->q.last_in |= INET_FRAG_FIRST_IN; @@ -531,9 +529,7 @@ found: qp->q.meat == qp->q.len) return ip_frag_reasm(qp, prev, dev); - write_lock(&ip4_frags.lock); - list_move_tail(&qp->q.lru_list, &qp->q.net->lru_list); - write_unlock(&ip4_frags.lock); + inet_frag_lru_move(&qp->q); return -EINPROGRESS; err: @@ -594,7 +590,7 @@ static int ip_frag_reasm(struct ipq *qp, struct sk_buff *prev, goto out_oversize; /* Head of list must not be cloned. */ - if (skb_cloned(head) && pskb_expand_head(head, 0, 0, GFP_ATOMIC)) + if (skb_unclone(head, GFP_ATOMIC)) goto out_nomem; /* If the first fragment is fragmented itself, we split @@ -617,7 +613,7 @@ static int ip_frag_reasm(struct ipq *qp, struct sk_buff *prev, head->len -= clone->len; clone->csum = 0; clone->ip_summed = head->ip_summed; - atomic_add(clone->truesize, &qp->q.net->mem); + add_frag_mem_limit(&qp->q, clone->truesize); } skb_push(head, head->data - skb_network_header(head)); @@ -645,7 +641,7 @@ static int ip_frag_reasm(struct ipq *qp, struct sk_buff *prev, } fp = next; } - atomic_sub(sum_truesize, &qp->q.net->mem); + sub_frag_mem_limit(&qp->q, sum_truesize); head->next = NULL; head->dev = dev; @@ -851,14 +847,22 @@ static inline void ip4_frags_ctl_register(void) static int __net_init ipv4_frags_init_net(struct net *net) { - /* - * Fragment cache limits. We will commit 256K at one time. Should we - * cross that limit we will prune down to 192K. This should cope with - * even the most extreme cases without allowing an attacker to - * measurably harm machine performance. + /* Fragment cache limits. + * + * The fragment memory accounting code, (tries to) account for + * the real memory usage, by measuring both the size of frag + * queue struct (inet_frag_queue (ipv4:ipq/ipv6:frag_queue)) + * and the SKB's truesize. + * + * A 64K fragment consumes 129736 bytes (44*2944)+200 + * (1500 truesize == 2944, sizeof(struct ipq) == 200) + * + * We will commit 4MB at one time. Should we cross that limit + * we will prune down to 3MB, making room for approx 8 big 64K + * fragments 8x128k. */ - net->ipv4.frags.high_thresh = 256 * 1024; - net->ipv4.frags.low_thresh = 192 * 1024; + net->ipv4.frags.high_thresh = 4 * 1024 * 1024; + net->ipv4.frags.low_thresh = 3 * 1024 * 1024; /* * Important NOTE! Fragment queue must be destroyed before MSL expires. * RFC791 is wrong proposing to prolongate timer each fragment arrival diff --git a/net/ipv4/ip_gre.c b/net/ipv4/ip_gre.c index a85ae2f7a21c..a56f1182c176 100644 --- a/net/ipv4/ip_gre.c +++ b/net/ipv4/ip_gre.c @@ -735,10 +735,35 @@ drop: return 0; } +static struct sk_buff *handle_offloads(struct sk_buff *skb) +{ + int err; + + if (skb_is_gso(skb)) { + err = skb_unclone(skb, GFP_ATOMIC); + if (unlikely(err)) + goto error; + skb_shinfo(skb)->gso_type |= SKB_GSO_GRE; + return skb; + } else if (skb->ip_summed == CHECKSUM_PARTIAL) { + err = skb_checksum_help(skb); + if (unlikely(err)) + goto error; + } + skb->ip_summed = CHECKSUM_NONE; + + return skb; + +error: + kfree_skb(skb); + return ERR_PTR(err); +} + static netdev_tx_t ipgre_tunnel_xmit(struct sk_buff *skb, struct net_device *dev) { + struct pcpu_tstats *tstats = this_cpu_ptr(dev->tstats); struct ip_tunnel *tunnel = netdev_priv(dev); - const struct iphdr *old_iph = ip_hdr(skb); + const struct iphdr *old_iph; const struct iphdr *tiph; struct flowi4 fl4; u8 tos; @@ -750,17 +775,32 @@ static netdev_tx_t ipgre_tunnel_xmit(struct sk_buff *skb, struct net_device *dev int gre_hlen; __be32 dst; int mtu; + u8 ttl; + int err; + int pkt_len; - if (skb->ip_summed == CHECKSUM_PARTIAL && - skb_checksum_help(skb)) - goto tx_error; + skb = handle_offloads(skb); + if (IS_ERR(skb)) { + dev->stats.tx_dropped++; + return NETDEV_TX_OK; + } + + if (!skb->encapsulation) { + skb_reset_inner_headers(skb); + skb->encapsulation = 1; + } + + old_iph = ip_hdr(skb); if (dev->type == ARPHRD_ETHER) IPCB(skb)->flags = 0; if (dev->header_ops && dev->type == ARPHRD_IPGRE) { gre_hlen = 0; - tiph = (const struct iphdr *)skb->data; + if (skb->protocol == htons(ETH_P_IP)) + tiph = (const struct iphdr *)skb->data; + else + tiph = &tunnel->parms.iph; } else { gre_hlen = tunnel->hlen; tiph = &tunnel->parms.iph; @@ -812,9 +852,10 @@ static netdev_tx_t ipgre_tunnel_xmit(struct sk_buff *skb, struct net_device *dev goto tx_error; } + ttl = tiph->ttl; tos = tiph->tos; - if (tos == 1) { - tos = 0; + if (tos & 0x1) { + tos &= ~0x1; if (skb->protocol == htons(ETH_P_IP)) tos = old_iph->tos; else if (skb->protocol == htons(ETH_P_IPV6)) @@ -848,7 +889,8 @@ static netdev_tx_t ipgre_tunnel_xmit(struct sk_buff *skb, struct net_device *dev if (skb->protocol == htons(ETH_P_IP)) { df |= (old_iph->frag_off&htons(IP_DF)); - if ((old_iph->frag_off&htons(IP_DF)) && + if (!skb_is_gso(skb) && + (old_iph->frag_off&htons(IP_DF)) && mtu < ntohs(old_iph->tot_len)) { icmp_send(skb, ICMP_DEST_UNREACH, ICMP_FRAG_NEEDED, htonl(mtu)); ip_rt_put(rt); @@ -868,7 +910,9 @@ static netdev_tx_t ipgre_tunnel_xmit(struct sk_buff *skb, struct net_device *dev } } - if (mtu >= IPV6_MIN_MTU && mtu < skb->len - tunnel->hlen + gre_hlen) { + if (!skb_is_gso(skb) && + mtu >= IPV6_MIN_MTU && + mtu < skb->len - tunnel->hlen + gre_hlen) { icmpv6_send(skb, ICMPV6_PKT_TOOBIG, 0, mtu); ip_rt_put(rt); goto tx_error; @@ -904,11 +948,12 @@ static netdev_tx_t ipgre_tunnel_xmit(struct sk_buff *skb, struct net_device *dev dev_kfree_skb(skb); skb = new_skb; old_iph = ip_hdr(skb); + /* Warning : tiph value might point to freed memory */ } - skb_reset_transport_header(skb); skb_push(skb, gre_hlen); skb_reset_network_header(skb); + skb_set_transport_header(skb, sizeof(*iph)); memset(&(IPCB(skb)->opt), 0, sizeof(IPCB(skb)->opt)); IPCB(skb)->flags &= ~(IPSKB_XFRM_TUNNEL_SIZE | IPSKB_XFRM_TRANSFORMED | IPSKB_REROUTED); @@ -927,8 +972,10 @@ static netdev_tx_t ipgre_tunnel_xmit(struct sk_buff *skb, struct net_device *dev iph->tos = ipgre_ecn_encapsulate(tos, old_iph, skb); iph->daddr = fl4.daddr; iph->saddr = fl4.saddr; + iph->ttl = ttl; + iph->id = 0; - if ((iph->ttl = tiph->ttl) == 0) { + if (ttl == 0) { if (skb->protocol == htons(ETH_P_IP)) iph->ttl = old_iph->ttl; #if IS_ENABLED(CONFIG_IPV6) @@ -955,13 +1002,39 @@ static netdev_tx_t ipgre_tunnel_xmit(struct sk_buff *skb, struct net_device *dev *ptr = tunnel->parms.o_key; ptr--; } - if (tunnel->parms.o_flags&GRE_CSUM) { + /* Skip GRE checksum if skb is getting offloaded. */ + if (!(skb_shinfo(skb)->gso_type & SKB_GSO_GRE) && + (tunnel->parms.o_flags&GRE_CSUM)) { + int offset = skb_transport_offset(skb); + + if (skb_has_shared_frag(skb)) { + err = __skb_linearize(skb); + if (err) { + ip_rt_put(rt); + goto tx_error; + } + } + *ptr = 0; - *(__sum16 *)ptr = ip_compute_csum((void *)(iph+1), skb->len - sizeof(struct iphdr)); + *(__sum16 *)ptr = csum_fold(skb_checksum(skb, offset, + skb->len - offset, + 0)); } } - iptunnel_xmit(skb, dev); + nf_reset(skb); + + pkt_len = skb->len - skb_transport_offset(skb); + err = ip_local_out(skb); + if (likely(net_xmit_eval(err) == 0)) { + u64_stats_update_begin(&tstats->syncp); + tstats->tx_bytes += pkt_len; + tstats->tx_packets++; + u64_stats_update_end(&tstats->syncp); + } else { + dev->stats.tx_errors++; + dev->stats.tx_aborted_errors++; + } return NETDEV_TX_OK; #if IS_ENABLED(CONFIG_IPV6) @@ -1031,6 +1104,11 @@ static int ipgre_tunnel_bind_dev(struct net_device *dev) mtu = 68; tunnel->hlen = addend; + /* TCP offload with GRE SEQ is not supported. */ + if (!(tunnel->parms.o_flags & GRE_SEQ)) { + dev->features |= NETIF_F_GSO_SOFTWARE; + dev->hw_features |= NETIF_F_GSO_SOFTWARE; + } return mtu; } @@ -1580,6 +1658,9 @@ static void ipgre_tap_setup(struct net_device *dev) dev->iflink = 0; dev->features |= NETIF_F_NETNS_LOCAL; + + dev->features |= GRE_FEATURES; + dev->hw_features |= GRE_FEATURES; } static int ipgre_newlink(struct net *src_net, struct net_device *dev, struct nlattr *tb[], diff --git a/net/ipv4/ip_input.c b/net/ipv4/ip_input.c index f1395a6fb35f..87abd3e2bd32 100644 --- a/net/ipv4/ip_input.c +++ b/net/ipv4/ip_input.c @@ -208,13 +208,6 @@ static int ip_local_deliver_finish(struct sk_buff *skb) if (ipprot != NULL) { int ret; - if (!net_eq(net, &init_net) && !ipprot->netns_ok) { - net_info_ratelimited("%s: proto %d isn't netns-ready\n", - __func__, protocol); - kfree_skb(skb); - goto out; - } - if (!ipprot->no_policy) { if (!xfrm4_policy_check(NULL, XFRM_POLICY_IN, skb)) { kfree_skb(skb); diff --git a/net/ipv4/ip_output.c b/net/ipv4/ip_output.c index 3e98ed2bff55..5e12dca7b3dd 100644 --- a/net/ipv4/ip_output.c +++ b/net/ipv4/ip_output.c @@ -598,6 +598,7 @@ slow_path: /* for offloaded checksums cleanup checksum before fragmentation */ if ((skb->ip_summed == CHECKSUM_PARTIAL) && skb_checksum_help(skb)) goto fail; + iph = ip_hdr(skb); left = skb->len - hlen; /* Space per frame */ ptr = hlen; /* Where to start from */ diff --git a/net/ipv4/ip_sockglue.c b/net/ipv4/ip_sockglue.c index 3c9d20880283..d9c4f113d709 100644 --- a/net/ipv4/ip_sockglue.c +++ b/net/ipv4/ip_sockglue.c @@ -590,7 +590,7 @@ static int do_ip_setsockopt(struct sock *sk, int level, case IP_TTL: if (optlen < 1) goto e_inval; - if (val != -1 && (val < 0 || val > 255)) + if (val != -1 && (val < 1 || val > 255)) goto e_inval; inet->uc_ttl = val; break; diff --git a/net/ipv4/ipcomp.c b/net/ipv4/ipcomp.c index d3ab47e19a89..f01d1b1aff7f 100644 --- a/net/ipv4/ipcomp.c +++ b/net/ipv4/ipcomp.c @@ -47,9 +47,12 @@ static void ipcomp4_err(struct sk_buff *skb, u32 info) if (!x) return; - if (icmp_hdr(skb)->type == ICMP_DEST_UNREACH) + if (icmp_hdr(skb)->type == ICMP_DEST_UNREACH) { + atomic_inc(&flow_cache_genid); + rt_genid_bump(net); + ipv4_update_pmtu(skb, net, info, 0, 0, IPPROTO_COMP, 0); - else + } else ipv4_redirect(skb, net, 0, 0, IPPROTO_COMP, 0); xfrm_state_put(x); } @@ -160,6 +163,7 @@ static const struct net_protocol ipcomp4_protocol = { .handler = xfrm4_rcv, .err_handler = ipcomp4_err, .no_policy = 1, + .netns_ok = 1, }; static int __init ipcomp4_init(void) diff --git a/net/ipv4/ipconfig.c b/net/ipv4/ipconfig.c index d763701cff1b..a2e50ae80b53 100644 --- a/net/ipv4/ipconfig.c +++ b/net/ipv4/ipconfig.c @@ -136,6 +136,8 @@ __be32 ic_myaddr = NONE; /* My IP address */ static __be32 ic_netmask = NONE; /* Netmask for local subnet */ __be32 ic_gateway = NONE; /* Gateway IP address */ +__be32 ic_addrservaddr = NONE; /* IP Address of the IP addresses'server */ + __be32 ic_servaddr = NONE; /* Boot server IP address */ __be32 root_server_addr = NONE; /* Address of NFS server */ @@ -558,6 +560,7 @@ ic_rarp_recv(struct sk_buff *skb, struct net_device *dev, struct packet_type *pt if (ic_myaddr == NONE) ic_myaddr = tip; ic_servaddr = sip; + ic_addrservaddr = sip; ic_got_reply = IC_RARP; drop_unlock: @@ -1068,7 +1071,7 @@ static int __init ic_bootp_recv(struct sk_buff *skb, struct net_device *dev, str ic_servaddr = server_id; #ifdef IPCONFIG_DEBUG printk("DHCP: Offered address %pI4 by server %pI4\n", - &ic_myaddr, &ic_servaddr); + &ic_myaddr, &b->iph.saddr); #endif /* The DHCP indicated server address takes * precedence over the bootp header one if @@ -1113,6 +1116,7 @@ static int __init ic_bootp_recv(struct sk_buff *skb, struct net_device *dev, str ic_dev = dev; ic_myaddr = b->your_ip; ic_servaddr = b->server_ip; + ic_addrservaddr = b->iph.saddr; if (ic_gateway == NONE && b->relay_ip) ic_gateway = b->relay_ip; if (ic_nameservers[0] == NONE) @@ -1268,7 +1272,7 @@ static int __init ic_dynamic(void) printk("IP-Config: Got %s answer from %pI4, ", ((ic_got_reply & IC_RARP) ? "RARP" : (ic_proto_enabled & IC_USE_DHCP) ? "DHCP" : "BOOTP"), - &ic_servaddr); + &ic_addrservaddr); pr_cont("my address is %pI4\n", &ic_myaddr); return 0; diff --git a/net/ipv4/ipip.c b/net/ipv4/ipip.c index 191fc24a745a..8f024d41eefa 100644 --- a/net/ipv4/ipip.c +++ b/net/ipv4/ipip.c @@ -472,7 +472,7 @@ static netdev_tx_t ipip_tunnel_xmit(struct sk_buff *skb, struct net_device *dev) __be16 df = tiph->frag_off; struct rtable *rt; /* Route to the other host */ struct net_device *tdev; /* Device to other host */ - const struct iphdr *old_iph = ip_hdr(skb); + const struct iphdr *old_iph; struct iphdr *iph; /* Our new IP header */ unsigned int max_headroom; /* The extra header space needed */ __be32 dst = tiph->daddr; @@ -486,6 +486,8 @@ static netdev_tx_t ipip_tunnel_xmit(struct sk_buff *skb, struct net_device *dev) skb_checksum_help(skb)) goto tx_error; + old_iph = ip_hdr(skb); + if (tos & 1) tos = old_iph->tos; diff --git a/net/ipv4/ipmr.c b/net/ipv4/ipmr.c index a9454cbd953c..7085b9b51e7f 100644 --- a/net/ipv4/ipmr.c +++ b/net/ipv4/ipmr.c @@ -828,6 +828,49 @@ static struct mfc_cache *ipmr_cache_find(struct mr_table *mrt, return NULL; } +/* Look for a (*,*,oif) entry */ +static struct mfc_cache *ipmr_cache_find_any_parent(struct mr_table *mrt, + int vifi) +{ + int line = MFC_HASH(htonl(INADDR_ANY), htonl(INADDR_ANY)); + struct mfc_cache *c; + + list_for_each_entry_rcu(c, &mrt->mfc_cache_array[line], list) + if (c->mfc_origin == htonl(INADDR_ANY) && + c->mfc_mcastgrp == htonl(INADDR_ANY) && + c->mfc_un.res.ttls[vifi] < 255) + return c; + + return NULL; +} + +/* Look for a (*,G) entry */ +static struct mfc_cache *ipmr_cache_find_any(struct mr_table *mrt, + __be32 mcastgrp, int vifi) +{ + int line = MFC_HASH(mcastgrp, htonl(INADDR_ANY)); + struct mfc_cache *c, *proxy; + + if (mcastgrp == htonl(INADDR_ANY)) + goto skip; + + list_for_each_entry_rcu(c, &mrt->mfc_cache_array[line], list) + if (c->mfc_origin == htonl(INADDR_ANY) && + c->mfc_mcastgrp == mcastgrp) { + if (c->mfc_un.res.ttls[vifi] < 255) + return c; + + /* It's ok if the vifi is part of the static tree */ + proxy = ipmr_cache_find_any_parent(mrt, + c->mfc_parent); + if (proxy && proxy->mfc_un.res.ttls[vifi] < 255) + return c; + } + +skip: + return ipmr_cache_find_any_parent(mrt, vifi); +} + /* * Allocate a multicast cache entry */ @@ -1053,7 +1096,7 @@ ipmr_cache_unresolved(struct mr_table *mrt, vifi_t vifi, struct sk_buff *skb) * MFC cache manipulation by user space mroute daemon */ -static int ipmr_mfc_delete(struct mr_table *mrt, struct mfcctl *mfc) +static int ipmr_mfc_delete(struct mr_table *mrt, struct mfcctl *mfc, int parent) { int line; struct mfc_cache *c, *next; @@ -1062,7 +1105,8 @@ static int ipmr_mfc_delete(struct mr_table *mrt, struct mfcctl *mfc) list_for_each_entry_safe(c, next, &mrt->mfc_cache_array[line], list) { if (c->mfc_origin == mfc->mfcc_origin.s_addr && - c->mfc_mcastgrp == mfc->mfcc_mcastgrp.s_addr) { + c->mfc_mcastgrp == mfc->mfcc_mcastgrp.s_addr && + (parent == -1 || parent == c->mfc_parent)) { list_del_rcu(&c->list); mroute_netlink_event(mrt, c, RTM_DELROUTE); ipmr_cache_free(c); @@ -1073,7 +1117,7 @@ static int ipmr_mfc_delete(struct mr_table *mrt, struct mfcctl *mfc) } static int ipmr_mfc_add(struct net *net, struct mr_table *mrt, - struct mfcctl *mfc, int mrtsock) + struct mfcctl *mfc, int mrtsock, int parent) { bool found = false; int line; @@ -1086,7 +1130,8 @@ static int ipmr_mfc_add(struct net *net, struct mr_table *mrt, list_for_each_entry(c, &mrt->mfc_cache_array[line], list) { if (c->mfc_origin == mfc->mfcc_origin.s_addr && - c->mfc_mcastgrp == mfc->mfcc_mcastgrp.s_addr) { + c->mfc_mcastgrp == mfc->mfcc_mcastgrp.s_addr && + (parent == -1 || parent == c->mfc_parent)) { found = true; break; } @@ -1103,7 +1148,8 @@ static int ipmr_mfc_add(struct net *net, struct mr_table *mrt, return 0; } - if (!ipv4_is_multicast(mfc->mfcc_mcastgrp.s_addr)) + if (mfc->mfcc_mcastgrp.s_addr != htonl(INADDR_ANY) && + !ipv4_is_multicast(mfc->mfcc_mcastgrp.s_addr)) return -EINVAL; c = ipmr_cache_alloc(); @@ -1218,7 +1264,7 @@ static void mrtsock_destruct(struct sock *sk) int ip_mroute_setsockopt(struct sock *sk, int optname, char __user *optval, unsigned int optlen) { - int ret; + int ret, parent = 0; struct vifctl vif; struct mfcctl mfc; struct net *net = sock_net(sk); @@ -1287,16 +1333,22 @@ int ip_mroute_setsockopt(struct sock *sk, int optname, char __user *optval, unsi */ case MRT_ADD_MFC: case MRT_DEL_MFC: + parent = -1; + case MRT_ADD_MFC_PROXY: + case MRT_DEL_MFC_PROXY: if (optlen != sizeof(mfc)) return -EINVAL; if (copy_from_user(&mfc, optval, sizeof(mfc))) return -EFAULT; + if (parent == 0) + parent = mfc.mfcc_parent; rtnl_lock(); - if (optname == MRT_DEL_MFC) - ret = ipmr_mfc_delete(mrt, &mfc); + if (optname == MRT_DEL_MFC || optname == MRT_DEL_MFC_PROXY) + ret = ipmr_mfc_delete(mrt, &mfc, parent); else ret = ipmr_mfc_add(net, mrt, &mfc, - sk == rtnl_dereference(mrt->mroute_sk)); + sk == rtnl_dereference(mrt->mroute_sk), + parent); rtnl_unlock(); return ret; /* @@ -1749,17 +1801,28 @@ static int ip_mr_forward(struct net *net, struct mr_table *mrt, { int psend = -1; int vif, ct; + int true_vifi = ipmr_find_vif(mrt, skb->dev); vif = cache->mfc_parent; cache->mfc_un.res.pkt++; cache->mfc_un.res.bytes += skb->len; + if (cache->mfc_origin == htonl(INADDR_ANY) && true_vifi >= 0) { + struct mfc_cache *cache_proxy; + + /* For an (*,G) entry, we only check that the incomming + * interface is part of the static tree. + */ + cache_proxy = ipmr_cache_find_any_parent(mrt, vif); + if (cache_proxy && + cache_proxy->mfc_un.res.ttls[true_vifi] < 255) + goto forward; + } + /* * Wrong interface: drop packet and (maybe) send PIM assert. */ if (mrt->vif_table[vif].dev != skb->dev) { - int true_vifi; - if (rt_is_output_route(skb_rtable(skb))) { /* It is our own packet, looped back. * Very complicated situation... @@ -1776,7 +1839,6 @@ static int ip_mr_forward(struct net *net, struct mr_table *mrt, } cache->mfc_un.res.wrong_if++; - true_vifi = ipmr_find_vif(mrt, skb->dev); if (true_vifi >= 0 && mrt->mroute_do_assert && /* pimsm uses asserts, when switching from RPT to SPT, @@ -1794,15 +1856,34 @@ static int ip_mr_forward(struct net *net, struct mr_table *mrt, goto dont_forward; } +forward: mrt->vif_table[vif].pkt_in++; mrt->vif_table[vif].bytes_in += skb->len; /* * Forward the frame */ + if (cache->mfc_origin == htonl(INADDR_ANY) && + cache->mfc_mcastgrp == htonl(INADDR_ANY)) { + if (true_vifi >= 0 && + true_vifi != cache->mfc_parent && + ip_hdr(skb)->ttl > + cache->mfc_un.res.ttls[cache->mfc_parent]) { + /* It's an (*,*) entry and the packet is not coming from + * the upstream: forward the packet to the upstream + * only. + */ + psend = cache->mfc_parent; + goto last_forward; + } + goto dont_forward; + } for (ct = cache->mfc_un.res.maxvif - 1; ct >= cache->mfc_un.res.minvif; ct--) { - if (ip_hdr(skb)->ttl > cache->mfc_un.res.ttls[ct]) { + /* For (*,G) entry, don't forward to the incoming interface */ + if ((cache->mfc_origin != htonl(INADDR_ANY) || + ct != true_vifi) && + ip_hdr(skb)->ttl > cache->mfc_un.res.ttls[ct]) { if (psend != -1) { struct sk_buff *skb2 = skb_clone(skb, GFP_ATOMIC); @@ -1813,6 +1894,7 @@ static int ip_mr_forward(struct net *net, struct mr_table *mrt, psend = ct; } } +last_forward: if (psend != -1) { if (local) { struct sk_buff *skb2 = skb_clone(skb, GFP_ATOMIC); @@ -1902,6 +1984,13 @@ int ip_mr_input(struct sk_buff *skb) /* already under rcu_read_lock() */ cache = ipmr_cache_find(mrt, ip_hdr(skb)->saddr, ip_hdr(skb)->daddr); + if (cache == NULL) { + int vif = ipmr_find_vif(mrt, skb->dev); + + if (vif >= 0) + cache = ipmr_cache_find_any(mrt, ip_hdr(skb)->daddr, + vif); + } /* * No usable cache entry @@ -2107,7 +2196,12 @@ int ipmr_get_route(struct net *net, struct sk_buff *skb, rcu_read_lock(); cache = ipmr_cache_find(mrt, saddr, daddr); + if (cache == NULL && skb->dev) { + int vif = ipmr_find_vif(mrt, skb->dev); + if (vif >= 0) + cache = ipmr_cache_find_any(mrt, daddr, vif); + } if (cache == NULL) { struct sk_buff *skb2; struct iphdr *iph; diff --git a/net/ipv4/netfilter/arp_tables.c b/net/ipv4/netfilter/arp_tables.c index 3ea4127404d6..7dc6a9743592 100644 --- a/net/ipv4/netfilter/arp_tables.c +++ b/net/ipv4/netfilter/arp_tables.c @@ -901,7 +901,7 @@ static int get_info(struct net *net, void __user *user, #endif t = try_then_request_module(xt_find_table_lock(net, NFPROTO_ARP, name), "arptable_%s", name); - if (t && !IS_ERR(t)) { + if (!IS_ERR_OR_NULL(t)) { struct arpt_getinfo info; const struct xt_table_info *private = t->private; #ifdef CONFIG_COMPAT @@ -958,7 +958,7 @@ static int get_entries(struct net *net, struct arpt_get_entries __user *uptr, } t = xt_find_table_lock(net, NFPROTO_ARP, get.name); - if (t && !IS_ERR(t)) { + if (!IS_ERR_OR_NULL(t)) { const struct xt_table_info *private = t->private; duprintf("t->private->number = %u\n", @@ -1001,7 +1001,7 @@ static int __do_replace(struct net *net, const char *name, t = try_then_request_module(xt_find_table_lock(net, NFPROTO_ARP, name), "arptable_%s", name); - if (!t || IS_ERR(t)) { + if (IS_ERR_OR_NULL(t)) { ret = t ? PTR_ERR(t) : -ENOENT; goto free_newinfo_counters_untrans; } @@ -1158,7 +1158,7 @@ static int do_add_counters(struct net *net, const void __user *user, } t = xt_find_table_lock(net, NFPROTO_ARP, name); - if (!t || IS_ERR(t)) { + if (IS_ERR_OR_NULL(t)) { ret = t ? PTR_ERR(t) : -ENOENT; goto free; } @@ -1646,7 +1646,7 @@ static int compat_get_entries(struct net *net, xt_compat_lock(NFPROTO_ARP); t = xt_find_table_lock(net, NFPROTO_ARP, get.name); - if (t && !IS_ERR(t)) { + if (!IS_ERR_OR_NULL(t)) { const struct xt_table_info *private = t->private; struct xt_table_info info; diff --git a/net/ipv4/netfilter/ip_tables.c b/net/ipv4/netfilter/ip_tables.c index 17c5e06da662..3efcf87400c3 100644 --- a/net/ipv4/netfilter/ip_tables.c +++ b/net/ipv4/netfilter/ip_tables.c @@ -1090,7 +1090,7 @@ static int get_info(struct net *net, void __user *user, #endif t = try_then_request_module(xt_find_table_lock(net, AF_INET, name), "iptable_%s", name); - if (t && !IS_ERR(t)) { + if (!IS_ERR_OR_NULL(t)) { struct ipt_getinfo info; const struct xt_table_info *private = t->private; #ifdef CONFIG_COMPAT @@ -1149,7 +1149,7 @@ get_entries(struct net *net, struct ipt_get_entries __user *uptr, } t = xt_find_table_lock(net, AF_INET, get.name); - if (t && !IS_ERR(t)) { + if (!IS_ERR_OR_NULL(t)) { const struct xt_table_info *private = t->private; duprintf("t->private->number = %u\n", private->number); if (get.size == private->size) @@ -1189,7 +1189,7 @@ __do_replace(struct net *net, const char *name, unsigned int valid_hooks, t = try_then_request_module(xt_find_table_lock(net, AF_INET, name), "iptable_%s", name); - if (!t || IS_ERR(t)) { + if (IS_ERR_OR_NULL(t)) { ret = t ? PTR_ERR(t) : -ENOENT; goto free_newinfo_counters_untrans; } @@ -1347,7 +1347,7 @@ do_add_counters(struct net *net, const void __user *user, } t = xt_find_table_lock(net, AF_INET, name); - if (!t || IS_ERR(t)) { + if (IS_ERR_OR_NULL(t)) { ret = t ? PTR_ERR(t) : -ENOENT; goto free; } @@ -1931,7 +1931,7 @@ compat_get_entries(struct net *net, struct compat_ipt_get_entries __user *uptr, xt_compat_lock(AF_INET); t = xt_find_table_lock(net, AF_INET, get.name); - if (t && !IS_ERR(t)) { + if (!IS_ERR_OR_NULL(t)) { const struct xt_table_info *private = t->private; struct xt_table_info info; duprintf("t->private->number = %u\n", private->number); diff --git a/net/ipv4/netfilter/ipt_REJECT.c b/net/ipv4/netfilter/ipt_REJECT.c index 51f13f8ec724..04b18c1ac345 100644 --- a/net/ipv4/netfilter/ipt_REJECT.c +++ b/net/ipv4/netfilter/ipt_REJECT.c @@ -81,6 +81,7 @@ static void send_reset(struct sk_buff *oldskb, int hook) niph->saddr = oiph->daddr; niph->daddr = oiph->saddr; + skb_reset_transport_header(nskb); tcph = (struct tcphdr *)skb_put(nskb, sizeof(struct tcphdr)); memset(tcph, 0, sizeof(*tcph)); tcph->source = oth->dest; diff --git a/net/ipv4/netfilter/ipt_ULOG.c b/net/ipv4/netfilter/ipt_ULOG.c index b5ef3cba2250..7d168dcbd135 100644 --- a/net/ipv4/netfilter/ipt_ULOG.c +++ b/net/ipv4/netfilter/ipt_ULOG.c @@ -88,10 +88,8 @@ static void ulog_send(unsigned int nlgroupnum) { ulog_buff_t *ub = &ulog_buffers[nlgroupnum]; - if (timer_pending(&ub->timer)) { - pr_debug("ulog_send: timer was pending, deleting\n"); - del_timer(&ub->timer); - } + pr_debug("ulog_send: timer is deleting\n"); + del_timer(&ub->timer); if (!ub->skb) { pr_debug("ulog_send: nothing to send\n"); @@ -426,10 +424,8 @@ static void __exit ulog_tg_exit(void) /* remove pending timers and free allocated skb's */ for (i = 0; i < ULOG_MAXNLGROUPS; i++) { ub = &ulog_buffers[i]; - if (timer_pending(&ub->timer)) { - pr_debug("timer was pending, deleting\n"); - del_timer(&ub->timer); - } + pr_debug("timer is deleting\n"); + del_timer(&ub->timer); if (ub->skb) { kfree_skb(ub->skb); diff --git a/net/ipv4/netfilter/iptable_nat.c b/net/ipv4/netfilter/iptable_nat.c index da2c8a368f68..eeaff7e4acb5 100644 --- a/net/ipv4/netfilter/iptable_nat.c +++ b/net/ipv4/netfilter/iptable_nat.c @@ -124,23 +124,28 @@ nf_nat_ipv4_fn(unsigned int hooknum, ret = nf_nat_rule_find(skb, hooknum, in, out, ct); if (ret != NF_ACCEPT) return ret; - } else + } else { pr_debug("Already setup manip %s for ct %p\n", maniptype == NF_NAT_MANIP_SRC ? "SRC" : "DST", ct); + if (nf_nat_oif_changed(hooknum, ctinfo, nat, out)) + goto oif_changed; + } break; default: /* ESTABLISHED */ NF_CT_ASSERT(ctinfo == IP_CT_ESTABLISHED || ctinfo == IP_CT_ESTABLISHED_REPLY); - if (nf_nat_oif_changed(hooknum, ctinfo, nat, out)) { - nf_ct_kill_acct(ct, ctinfo, skb); - return NF_DROP; - } + if (nf_nat_oif_changed(hooknum, ctinfo, nat, out)) + goto oif_changed; } return nf_nat_packet(ct, ctinfo, hooknum, skb); + +oif_changed: + nf_ct_kill_acct(ct, ctinfo, skb); + return NF_DROP; } static unsigned int diff --git a/net/ipv4/netfilter/nf_conntrack_l3proto_ipv4.c b/net/ipv4/netfilter/nf_conntrack_l3proto_ipv4.c index fcdd0c2406e6..48990ada0e1e 100644 --- a/net/ipv4/netfilter/nf_conntrack_l3proto_ipv4.c +++ b/net/ipv4/netfilter/nf_conntrack_l3proto_ipv4.c @@ -420,54 +420,43 @@ static int ipv4_net_init(struct net *net) { int ret = 0; - ret = nf_conntrack_l4proto_register(net, - &nf_conntrack_l4proto_tcp4); + ret = nf_ct_l4proto_pernet_register(net, &nf_conntrack_l4proto_tcp4); if (ret < 0) { - pr_err("nf_conntrack_l4proto_tcp4 :protocol register failed\n"); + pr_err("nf_conntrack_tcp4: pernet registration failed\n"); goto out_tcp; } - ret = nf_conntrack_l4proto_register(net, - &nf_conntrack_l4proto_udp4); + ret = nf_ct_l4proto_pernet_register(net, &nf_conntrack_l4proto_udp4); if (ret < 0) { - pr_err("nf_conntrack_l4proto_udp4 :protocol register failed\n"); + pr_err("nf_conntrack_udp4: pernet registration failed\n"); goto out_udp; } - ret = nf_conntrack_l4proto_register(net, - &nf_conntrack_l4proto_icmp); + ret = nf_ct_l4proto_pernet_register(net, &nf_conntrack_l4proto_icmp); if (ret < 0) { - pr_err("nf_conntrack_l4proto_icmp4 :protocol register failed\n"); + pr_err("nf_conntrack_icmp4: pernet registration failed\n"); goto out_icmp; } - ret = nf_conntrack_l3proto_register(net, - &nf_conntrack_l3proto_ipv4); + ret = nf_ct_l3proto_pernet_register(net, &nf_conntrack_l3proto_ipv4); if (ret < 0) { - pr_err("nf_conntrack_l3proto_ipv4 :protocol register failed\n"); + pr_err("nf_conntrack_ipv4: pernet registration failed\n"); goto out_ipv4; } return 0; out_ipv4: - nf_conntrack_l4proto_unregister(net, - &nf_conntrack_l4proto_icmp); + nf_ct_l4proto_pernet_unregister(net, &nf_conntrack_l4proto_icmp); out_icmp: - nf_conntrack_l4proto_unregister(net, - &nf_conntrack_l4proto_udp4); + nf_ct_l4proto_pernet_unregister(net, &nf_conntrack_l4proto_udp4); out_udp: - nf_conntrack_l4proto_unregister(net, - &nf_conntrack_l4proto_tcp4); + nf_ct_l4proto_pernet_unregister(net, &nf_conntrack_l4proto_tcp4); out_tcp: return ret; } static void ipv4_net_exit(struct net *net) { - nf_conntrack_l3proto_unregister(net, - &nf_conntrack_l3proto_ipv4); - nf_conntrack_l4proto_unregister(net, - &nf_conntrack_l4proto_icmp); - nf_conntrack_l4proto_unregister(net, - &nf_conntrack_l4proto_udp4); - nf_conntrack_l4proto_unregister(net, - &nf_conntrack_l4proto_tcp4); + nf_ct_l3proto_pernet_unregister(net, &nf_conntrack_l3proto_ipv4); + nf_ct_l4proto_pernet_unregister(net, &nf_conntrack_l4proto_icmp); + nf_ct_l4proto_pernet_unregister(net, &nf_conntrack_l4proto_udp4); + nf_ct_l4proto_pernet_unregister(net, &nf_conntrack_l4proto_tcp4); } static struct pernet_operations ipv4_net_ops = { @@ -500,16 +489,49 @@ static int __init nf_conntrack_l3proto_ipv4_init(void) pr_err("nf_conntrack_ipv4: can't register hooks.\n"); goto cleanup_pernet; } + + ret = nf_ct_l4proto_register(&nf_conntrack_l4proto_tcp4); + if (ret < 0) { + pr_err("nf_conntrack_ipv4: can't register tcp4 proto.\n"); + goto cleanup_hooks; + } + + ret = nf_ct_l4proto_register(&nf_conntrack_l4proto_udp4); + if (ret < 0) { + pr_err("nf_conntrack_ipv4: can't register udp4 proto.\n"); + goto cleanup_tcp4; + } + + ret = nf_ct_l4proto_register(&nf_conntrack_l4proto_icmp); + if (ret < 0) { + pr_err("nf_conntrack_ipv4: can't register icmpv4 proto.\n"); + goto cleanup_udp4; + } + + ret = nf_ct_l3proto_register(&nf_conntrack_l3proto_ipv4); + if (ret < 0) { + pr_err("nf_conntrack_ipv4: can't register ipv4 proto.\n"); + goto cleanup_icmpv4; + } + #if defined(CONFIG_PROC_FS) && defined(CONFIG_NF_CONNTRACK_PROC_COMPAT) ret = nf_conntrack_ipv4_compat_init(); if (ret < 0) - goto cleanup_hooks; + goto cleanup_proto; #endif return ret; #if defined(CONFIG_PROC_FS) && defined(CONFIG_NF_CONNTRACK_PROC_COMPAT) + cleanup_proto: + nf_ct_l3proto_unregister(&nf_conntrack_l3proto_ipv4); +#endif + cleanup_icmpv4: + nf_ct_l4proto_unregister(&nf_conntrack_l4proto_icmp); + cleanup_udp4: + nf_ct_l4proto_unregister(&nf_conntrack_l4proto_udp4); + cleanup_tcp4: + nf_ct_l4proto_unregister(&nf_conntrack_l4proto_tcp4); cleanup_hooks: nf_unregister_hooks(ipv4_conntrack_ops, ARRAY_SIZE(ipv4_conntrack_ops)); -#endif cleanup_pernet: unregister_pernet_subsys(&ipv4_net_ops); cleanup_sockopt: @@ -523,6 +545,10 @@ static void __exit nf_conntrack_l3proto_ipv4_fini(void) #if defined(CONFIG_PROC_FS) && defined(CONFIG_NF_CONNTRACK_PROC_COMPAT) nf_conntrack_ipv4_compat_fini(); #endif + nf_ct_l3proto_unregister(&nf_conntrack_l3proto_ipv4); + nf_ct_l4proto_unregister(&nf_conntrack_l4proto_icmp); + nf_ct_l4proto_unregister(&nf_conntrack_l4proto_udp4); + nf_ct_l4proto_unregister(&nf_conntrack_l4proto_tcp4); nf_unregister_hooks(ipv4_conntrack_ops, ARRAY_SIZE(ipv4_conntrack_ops)); unregister_pernet_subsys(&ipv4_net_ops); nf_unregister_sockopt(&so_getorigdst); diff --git a/net/ipv4/ping.c b/net/ipv4/ping.c index 8f3d05424a3e..6f9c07268cf6 100644 --- a/net/ipv4/ping.c +++ b/net/ipv4/ping.c @@ -738,6 +738,7 @@ struct proto ping_prot = { .recvmsg = ping_recvmsg, .bind = ping_bind, .backlog_rcv = ping_queue_rcv_skb, + .release_cb = ip4_datagram_release_cb, .hash = ping_v4_hash, .unhash = ping_v4_unhash, .get_port = ping_v4_get_port, diff --git a/net/ipv4/protocol.c b/net/ipv4/protocol.c index 0f9d09f54bd9..ce848461acbb 100644 --- a/net/ipv4/protocol.c +++ b/net/ipv4/protocol.c @@ -37,6 +37,12 @@ const struct net_offload __rcu *inet_offloads[MAX_INET_PROTOS] __read_mostly; int inet_add_protocol(const struct net_protocol *prot, unsigned char protocol) { + if (!prot->netns_ok) { + pr_err("Protocol %u is not namespace aware, cannot register.\n", + protocol); + return -EINVAL; + } + return !cmpxchg((const struct net_protocol **)&inet_protos[protocol], NULL, prot) ? 0 : -1; } diff --git a/net/ipv4/raw.c b/net/ipv4/raw.c index 73d1e4df4bf6..6f08991409c3 100644 --- a/net/ipv4/raw.c +++ b/net/ipv4/raw.c @@ -894,6 +894,7 @@ struct proto raw_prot = { .recvmsg = raw_recvmsg, .bind = raw_bind, .backlog_rcv = raw_rcv_skb, + .release_cb = ip4_datagram_release_cb, .hash = raw_hash_sk, .unhash = raw_unhash_sk, .obj_size = sizeof(struct raw_sock), diff --git a/net/ipv4/route.c b/net/ipv4/route.c index 844a9ef60dbd..a0fcc47fee73 100644 --- a/net/ipv4/route.c +++ b/net/ipv4/route.c @@ -912,6 +912,9 @@ static void __ip_rt_update_pmtu(struct rtable *rt, struct flowi4 *fl4, u32 mtu) struct dst_entry *dst = &rt->dst; struct fib_result res; + if (dst_metric_locked(dst, RTAX_MTU)) + return; + if (dst->dev->mtu < mtu) return; @@ -962,7 +965,7 @@ void ipv4_update_pmtu(struct sk_buff *skb, struct net *net, u32 mtu, } EXPORT_SYMBOL_GPL(ipv4_update_pmtu); -void ipv4_sk_update_pmtu(struct sk_buff *skb, struct sock *sk, u32 mtu) +static void __ipv4_sk_update_pmtu(struct sk_buff *skb, struct sock *sk, u32 mtu) { const struct iphdr *iph = (const struct iphdr *) skb->data; struct flowi4 fl4; @@ -975,6 +978,53 @@ void ipv4_sk_update_pmtu(struct sk_buff *skb, struct sock *sk, u32 mtu) ip_rt_put(rt); } } + +void ipv4_sk_update_pmtu(struct sk_buff *skb, struct sock *sk, u32 mtu) +{ + const struct iphdr *iph = (const struct iphdr *) skb->data; + struct flowi4 fl4; + struct rtable *rt; + struct dst_entry *dst; + bool new = false; + + bh_lock_sock(sk); + rt = (struct rtable *) __sk_dst_get(sk); + + if (sock_owned_by_user(sk) || !rt) { + __ipv4_sk_update_pmtu(skb, sk, mtu); + goto out; + } + + __build_flow_key(&fl4, sk, iph, 0, 0, 0, 0, 0); + + if (!__sk_dst_check(sk, 0)) { + rt = ip_route_output_flow(sock_net(sk), &fl4, sk); + if (IS_ERR(rt)) + goto out; + + new = true; + } + + __ip_rt_update_pmtu((struct rtable *) rt->dst.path, &fl4, mtu); + + dst = dst_check(&rt->dst, 0); + if (!dst) { + if (new) + dst_release(&rt->dst); + + rt = ip_route_output_flow(sock_net(sk), &fl4, sk); + if (IS_ERR(rt)) + goto out; + + new = true; + } + + if (new) + __sk_dst_set(sk, &rt->dst); + +out: + bh_unlock_sock(sk); +} EXPORT_SYMBOL_GPL(ipv4_sk_update_pmtu); void ipv4_redirect(struct sk_buff *skb, struct net *net, @@ -1120,7 +1170,7 @@ static unsigned int ipv4_mtu(const struct dst_entry *dst) if (!mtu || time_after_eq(jiffies, rt->dst.expires)) mtu = dst_metric_raw(dst, RTAX_MTU); - if (mtu && rt_is_output_route(rt)) + if (mtu) return mtu; mtu = dst->dev->mtu; diff --git a/net/ipv4/syncookies.c b/net/ipv4/syncookies.c index b236ef04914f..ef54377fb11c 100644 --- a/net/ipv4/syncookies.c +++ b/net/ipv4/syncookies.c @@ -232,7 +232,8 @@ static inline struct sock *get_cookie_sock(struct sock *sk, struct sk_buff *skb, * * return false if we decode an option that should not be. */ -bool cookie_check_timestamp(struct tcp_options_received *tcp_opt, bool *ecn_ok) +bool cookie_check_timestamp(struct tcp_options_received *tcp_opt, + struct net *net, bool *ecn_ok) { /* echoed timestamp, lowest bits contain options */ u32 options = tcp_opt->rcv_tsecr & TSMASK; @@ -247,7 +248,7 @@ bool cookie_check_timestamp(struct tcp_options_received *tcp_opt, bool *ecn_ok) tcp_opt->sack_ok = (options & (1 << 4)) ? TCP_SACK_SEEN : 0; *ecn_ok = (options >> 5) & 1; - if (*ecn_ok && !sysctl_tcp_ecn) + if (*ecn_ok && !net->ipv4.sysctl_tcp_ecn) return false; if (tcp_opt->sack_ok && !sysctl_tcp_sack) @@ -295,7 +296,7 @@ struct sock *cookie_v4_check(struct sock *sk, struct sk_buff *skb, memset(&tcp_opt, 0, sizeof(tcp_opt)); tcp_parse_options(skb, &tcp_opt, &hash_location, 0, NULL); - if (!cookie_check_timestamp(&tcp_opt, &ecn_ok)) + if (!cookie_check_timestamp(&tcp_opt, sock_net(sk), &ecn_ok)) goto out; ret = NULL; diff --git a/net/ipv4/sysctl_net_ipv4.c b/net/ipv4/sysctl_net_ipv4.c index d84400b65049..960fd29d9b8e 100644 --- a/net/ipv4/sysctl_net_ipv4.c +++ b/net/ipv4/sysctl_net_ipv4.c @@ -27,6 +27,7 @@ #include <net/tcp_memcontrol.h> static int zero; +static int one = 1; static int two = 2; static int tcp_retr1_max = 255; static int ip_local_port_range_min[] = { 1, 1 }; @@ -232,8 +233,8 @@ static int ipv4_tcp_mem(ctl_table *ctl, int write, return 0; } -int proc_tcp_fastopen_key(ctl_table *ctl, int write, void __user *buffer, - size_t *lenp, loff_t *ppos) +static int proc_tcp_fastopen_key(ctl_table *ctl, int write, void __user *buffer, + size_t *lenp, loff_t *ppos) { ctl_table tbl = { .maxlen = (TCP_FASTOPEN_KEY_LENGTH * 2 + 10) }; struct tcp_fastopen_context *ctxt; @@ -538,13 +539,6 @@ static struct ctl_table ipv4_table[] = { .proc_handler = proc_dointvec }, { - .procname = "tcp_ecn", - .data = &sysctl_tcp_ecn, - .maxlen = sizeof(int), - .mode = 0644, - .proc_handler = proc_dointvec - }, - { .procname = "tcp_dsack", .data = &sysctl_tcp_dsack, .maxlen = sizeof(int), @@ -556,14 +550,16 @@ static struct ctl_table ipv4_table[] = { .data = &sysctl_tcp_wmem, .maxlen = sizeof(sysctl_tcp_wmem), .mode = 0644, - .proc_handler = proc_dointvec + .proc_handler = proc_dointvec_minmax, + .extra1 = &one, }, { .procname = "tcp_rmem", .data = &sysctl_tcp_rmem, .maxlen = sizeof(sysctl_tcp_rmem), .mode = 0644, - .proc_handler = proc_dointvec + .proc_handler = proc_dointvec_minmax, + .extra1 = &one, }, { .procname = "tcp_app_win", @@ -637,13 +633,6 @@ static struct ctl_table ipv4_table[] = { .proc_handler = proc_tcp_congestion_control, }, { - .procname = "tcp_abc", - .data = &sysctl_tcp_abc, - .maxlen = sizeof(int), - .mode = 0644, - .proc_handler = proc_dointvec, - }, - { .procname = "tcp_mtu_probing", .data = &sysctl_tcp_mtu_probing, .maxlen = sizeof(int), @@ -786,7 +775,7 @@ static struct ctl_table ipv4_table[] = { .maxlen = sizeof(sysctl_udp_rmem_min), .mode = 0644, .proc_handler = proc_dointvec_minmax, - .extra1 = &zero + .extra1 = &one }, { .procname = "udp_wmem_min", @@ -794,7 +783,7 @@ static struct ctl_table ipv4_table[] = { .maxlen = sizeof(sysctl_udp_wmem_min), .mode = 0644, .proc_handler = proc_dointvec_minmax, - .extra1 = &zero + .extra1 = &one }, { } }; @@ -850,6 +839,13 @@ static struct ctl_table ipv4_net_table[] = { .proc_handler = ipv4_ping_group_range, }, { + .procname = "tcp_ecn", + .data = &init_net.ipv4.sysctl_tcp_ecn, + .maxlen = sizeof(int), + .mode = 0644, + .proc_handler = proc_dointvec + }, + { .procname = "tcp_mem", .maxlen = sizeof(init_net.ipv4.sysctl_tcp_mem), .mode = 0644, @@ -882,6 +878,8 @@ static __net_init int ipv4_sysctl_init_net(struct net *net) &net->ipv4.sysctl_icmp_ratemask; table[6].data = &net->ipv4.sysctl_ping_group_range; + table[7].data = + &net->ipv4.sysctl_tcp_ecn; /* Don't export sysctls to unprivileged users */ if (net->user_ns != &init_user_ns) diff --git a/net/ipv4/tcp.c b/net/ipv4/tcp.c index 1ca253635f7a..7a5ba48c2cc9 100644 --- a/net/ipv4/tcp.c +++ b/net/ipv4/tcp.c @@ -400,6 +400,8 @@ void tcp_init_sock(struct sock *sk) tcp_enable_early_retrans(tp); icsk->icsk_ca_ops = &tcp_init_congestion_ops; + tp->tsoffset = 0; + sk->sk_state = TCP_CLOSE; sk->sk_write_space = sk_stream_write_space; @@ -895,6 +897,7 @@ new_segment: get_page(page); skb_fill_page_desc(skb, i, page, offset, copy); } + skb_shinfo(skb)->tx_flags |= SKBTX_SHARED_FRAG; skb->len += copy; skb->data_len += copy; @@ -1428,12 +1431,12 @@ static void tcp_service_net_dma(struct sock *sk, bool wait) } #endif -static inline struct sk_buff *tcp_recv_skb(struct sock *sk, u32 seq, u32 *off) +static struct sk_buff *tcp_recv_skb(struct sock *sk, u32 seq, u32 *off) { struct sk_buff *skb; u32 offset; - skb_queue_walk(&sk->sk_receive_queue, skb) { + while ((skb = skb_peek(&sk->sk_receive_queue)) != NULL) { offset = seq - TCP_SKB_CB(skb)->seq; if (tcp_hdr(skb)->syn) offset--; @@ -1441,6 +1444,11 @@ static inline struct sk_buff *tcp_recv_skb(struct sock *sk, u32 seq, u32 *off) *off = offset; return skb; } + /* This looks weird, but this can happen if TCP collapsing + * splitted a fat GRO packet, while we released socket lock + * in skb_splice_bits() + */ + sk_eat_skb(sk, skb, false); } return NULL; } @@ -1482,7 +1490,7 @@ int tcp_read_sock(struct sock *sk, read_descriptor_t *desc, break; } used = recv_actor(desc, skb, offset, len); - if (used < 0) { + if (used <= 0) { if (!copied) copied = used; break; @@ -1520,8 +1528,10 @@ int tcp_read_sock(struct sock *sk, read_descriptor_t *desc, tcp_rcv_space_adjust(sk); /* Clean up data we have read: This will do ACK frames. */ - if (copied > 0) + if (copied > 0) { + tcp_recv_skb(sk, seq, &offset); tcp_cleanup_rbuf(sk, copied); + } return copied; } EXPORT_SYMBOL(tcp_read_sock); @@ -2280,7 +2290,6 @@ int tcp_disconnect(struct sock *sk, int flags) tp->packets_out = 0; tp->snd_ssthresh = TCP_INFINITE_SSTHRESH; tp->snd_cwnd_cnt = 0; - tp->bytes_acked = 0; tp->window_clamp = 0; tcp_set_ca_state(sk, TCP_CA_Open); tcp_clear_retrans(tp); @@ -2704,6 +2713,12 @@ static int do_tcp_setsockopt(struct sock *sk, int level, else err = -EINVAL; break; + case TCP_TIMESTAMP: + if (!tp->repair) + err = -EPERM; + else + tp->tsoffset = val - tcp_time_stamp; + break; default: err = -ENOPROTOOPT; break; @@ -2952,6 +2967,9 @@ static int do_tcp_getsockopt(struct sock *sk, int level, case TCP_USER_TIMEOUT: val = jiffies_to_msecs(icsk->icsk_user_timeout); break; + case TCP_TIMESTAMP: + val = tcp_time_stamp + tp->tsoffset; + break; default: return -ENOPROTOOPT; } @@ -3025,6 +3043,7 @@ struct sk_buff *tcp_tso_segment(struct sk_buff *skb, SKB_GSO_DODGY | SKB_GSO_TCP_ECN | SKB_GSO_TCPV6 | + SKB_GSO_GRE | 0) || !(type & (SKB_GSO_TCPV4 | SKB_GSO_TCPV6)))) goto out; @@ -3236,7 +3255,7 @@ __tcp_alloc_md5sig_pool(struct sock *sk) struct crypto_hash *hash; hash = crypto_alloc_hash("md5", 0, CRYPTO_ALG_ASYNC); - if (!hash || IS_ERR(hash)) + if (IS_ERR_OR_NULL(hash)) goto out_free; per_cpu_ptr(pool, cpu)->md5_desc.tfm = hash; diff --git a/net/ipv4/tcp_cong.c b/net/ipv4/tcp_cong.c index 291f2ed7cc31..019c2389a341 100644 --- a/net/ipv4/tcp_cong.c +++ b/net/ipv4/tcp_cong.c @@ -310,35 +310,24 @@ void tcp_slow_start(struct tcp_sock *tp) { int cnt; /* increase in packets */ unsigned int delta = 0; + u32 snd_cwnd = tp->snd_cwnd; - /* RFC3465: ABC Slow start - * Increase only after a full MSS of bytes is acked - * - * TCP sender SHOULD increase cwnd by the number of - * previously unacknowledged bytes ACKed by each incoming - * acknowledgment, provided the increase is not more than L - */ - if (sysctl_tcp_abc && tp->bytes_acked < tp->mss_cache) - return; + if (unlikely(!snd_cwnd)) { + pr_err_once("snd_cwnd is nul, please report this bug.\n"); + snd_cwnd = 1U; + } if (sysctl_tcp_max_ssthresh > 0 && tp->snd_cwnd > sysctl_tcp_max_ssthresh) cnt = sysctl_tcp_max_ssthresh >> 1; /* limited slow start */ else - cnt = tp->snd_cwnd; /* exponential increase */ - - /* RFC3465: ABC - * We MAY increase by 2 if discovered delayed ack - */ - if (sysctl_tcp_abc > 1 && tp->bytes_acked >= 2*tp->mss_cache) - cnt <<= 1; - tp->bytes_acked = 0; + cnt = snd_cwnd; /* exponential increase */ tp->snd_cwnd_cnt += cnt; - while (tp->snd_cwnd_cnt >= tp->snd_cwnd) { - tp->snd_cwnd_cnt -= tp->snd_cwnd; + while (tp->snd_cwnd_cnt >= snd_cwnd) { + tp->snd_cwnd_cnt -= snd_cwnd; delta++; } - tp->snd_cwnd = min(tp->snd_cwnd + delta, tp->snd_cwnd_clamp); + tp->snd_cwnd = min(snd_cwnd + delta, tp->snd_cwnd_clamp); } EXPORT_SYMBOL_GPL(tcp_slow_start); @@ -372,20 +361,9 @@ void tcp_reno_cong_avoid(struct sock *sk, u32 ack, u32 in_flight) /* In "safe" area, increase. */ if (tp->snd_cwnd <= tp->snd_ssthresh) tcp_slow_start(tp); - /* In dangerous area, increase slowly. */ - else if (sysctl_tcp_abc) { - /* RFC3465: Appropriate Byte Count - * increase once for each full cwnd acked - */ - if (tp->bytes_acked >= tp->snd_cwnd*tp->mss_cache) { - tp->bytes_acked -= tp->snd_cwnd*tp->mss_cache; - if (tp->snd_cwnd < tp->snd_cwnd_clamp) - tp->snd_cwnd++; - } - } else { + else tcp_cong_avoid_ai(tp, tp->snd_cwnd); - } } EXPORT_SYMBOL_GPL(tcp_reno_cong_avoid); diff --git a/net/ipv4/tcp_input.c b/net/ipv4/tcp_input.c index a13692560e63..a759e19496d2 100644 --- a/net/ipv4/tcp_input.c +++ b/net/ipv4/tcp_input.c @@ -81,8 +81,6 @@ int sysctl_tcp_sack __read_mostly = 1; int sysctl_tcp_fack __read_mostly = 1; int sysctl_tcp_reordering __read_mostly = TCP_FASTRETRANS_THRESH; EXPORT_SYMBOL(sysctl_tcp_reordering); -int sysctl_tcp_ecn __read_mostly = 2; -EXPORT_SYMBOL(sysctl_tcp_ecn); int sysctl_tcp_dsack __read_mostly = 1; int sysctl_tcp_app_win __read_mostly = 31; int sysctl_tcp_adv_win_scale __read_mostly = 1; @@ -100,7 +98,6 @@ int sysctl_tcp_frto_response __read_mostly; int sysctl_tcp_thin_dupack __read_mostly; int sysctl_tcp_moderate_rcvbuf __read_mostly = 1; -int sysctl_tcp_abc __read_mostly; int sysctl_tcp_early_retrans __read_mostly = 2; #define FLAG_DATA 0x01 /* Incoming frame contained data. */ @@ -2009,7 +2006,6 @@ static void tcp_enter_frto_loss(struct sock *sk, int allowed_segments, int flag) tp->snd_cwnd_cnt = 0; tp->snd_cwnd_stamp = tcp_time_stamp; tp->frto_counter = 0; - tp->bytes_acked = 0; tp->reordering = min_t(unsigned int, tp->reordering, sysctl_tcp_reordering); @@ -2058,7 +2054,6 @@ void tcp_enter_loss(struct sock *sk, int how) tp->snd_cwnd_cnt = 0; tp->snd_cwnd_stamp = tcp_time_stamp; - tp->bytes_acked = 0; tcp_clear_retrans_partial(tp); if (tcp_is_reno(tp)) @@ -2686,7 +2681,6 @@ static void tcp_init_cwnd_reduction(struct sock *sk, const bool set_ssthresh) struct tcp_sock *tp = tcp_sk(sk); tp->high_seq = tp->snd_nxt; - tp->bytes_acked = 0; tp->snd_cwnd_cnt = 0; tp->prior_cwnd = tp->snd_cwnd; tp->prr_delivered = 0; @@ -2737,7 +2731,6 @@ void tcp_enter_cwr(struct sock *sk, const int set_ssthresh) struct tcp_sock *tp = tcp_sk(sk); tp->prior_ssthresh = 0; - tp->bytes_acked = 0; if (inet_csk(sk)->icsk_ca_state < TCP_CA_CWR) { tp->undo_marker = 0; tcp_init_cwnd_reduction(sk, set_ssthresh); @@ -3419,7 +3412,6 @@ static void tcp_conservative_spur_to_response(struct tcp_sock *tp) { tp->snd_cwnd = min(tp->snd_cwnd, tp->snd_ssthresh); tp->snd_cwnd_cnt = 0; - tp->bytes_acked = 0; TCP_ECN_queue_cwr(tp); tcp_moderate_cwnd(tp); } @@ -3504,6 +3496,11 @@ static bool tcp_process_frto(struct sock *sk, int flag) } } else { if (!(flag & FLAG_DATA_ACKED) && (tp->frto_counter == 1)) { + if (!tcp_packets_in_flight(tp)) { + tcp_enter_frto_loss(sk, 2, flag); + return true; + } + /* Prevent sending of new data. */ tp->snd_cwnd = min(tp->snd_cwnd, tcp_packets_in_flight(tp)); @@ -3610,15 +3607,6 @@ static int tcp_ack(struct sock *sk, const struct sk_buff *skb, int flag) if (after(ack, prior_snd_una)) flag |= FLAG_SND_UNA_ADVANCED; - if (sysctl_tcp_abc) { - if (icsk->icsk_ca_state < TCP_CA_CWR) - tp->bytes_acked += ack - prior_snd_una; - else if (icsk->icsk_ca_state == TCP_CA_Loss) - /* we assume just one segment left network */ - tp->bytes_acked += min(ack - prior_snd_una, - tp->mss_cache); - } - prior_fackets = tp->fackets_out; prior_in_flight = tcp_packets_in_flight(tp); @@ -3872,7 +3860,7 @@ static bool tcp_parse_aligned_timestamp(struct tcp_sock *tp, const struct tcphdr ++ptr; tp->rx_opt.rcv_tsval = ntohl(*ptr); ++ptr; - tp->rx_opt.rcv_tsecr = ntohl(*ptr); + tp->rx_opt.rcv_tsecr = ntohl(*ptr) - tp->tsoffset; return true; } return false; @@ -3896,7 +3884,11 @@ static bool tcp_fast_parse_options(const struct sk_buff *skb, if (tcp_parse_aligned_timestamp(tp, th)) return true; } + tcp_parse_options(skb, &tp->rx_opt, hvpp, 1, NULL); + if (tp->rx_opt.saw_tstamp) + tp->rx_opt.rcv_tsecr -= tp->tsoffset; + return true; } @@ -5543,6 +5535,9 @@ slow_path: if (len < (th->doff << 2) || tcp_checksum_complete_user(sk, skb)) goto csum_error; + if (!th->ack && !th->rst) + goto discard; + /* * Standard slow path. */ @@ -5551,7 +5546,7 @@ slow_path: return 0; step5: - if (th->ack && tcp_ack(sk, skb, FLAG_SLOWPATH) < 0) + if (tcp_ack(sk, skb, FLAG_SLOWPATH) < 0) goto discard; /* ts_recent update must be made after we are sure that the packet @@ -5646,8 +5641,7 @@ static bool tcp_rcv_fastopen_synack(struct sock *sk, struct sk_buff *synack, * the remote receives only the retransmitted (regular) SYNs: either * the original SYN-data or the corresponding SYN-ACK is lost. */ - syn_drop = (cookie->len <= 0 && data && - inet_csk(sk)->icsk_retransmits); + syn_drop = (cookie->len <= 0 && data && tp->total_retrans); tcp_fastopen_cache_set(sk, mss, cookie, syn_drop); @@ -5675,6 +5669,8 @@ static int tcp_rcv_synsent_state_process(struct sock *sk, struct sk_buff *skb, int saved_clamp = tp->rx_opt.mss_clamp; tcp_parse_options(skb, &tp->rx_opt, &hash_location, 0, &foc); + if (tp->rx_opt.saw_tstamp) + tp->rx_opt.rcv_tsecr -= tp->tsoffset; if (th->ack) { /* rfc793: @@ -5984,11 +5980,15 @@ int tcp_rcv_state_process(struct sock *sk, struct sk_buff *skb, if (tcp_check_req(sk, skb, req, NULL, true) == NULL) goto discard; } + + if (!th->ack && !th->rst) + goto discard; + if (!tcp_validate_incoming(sk, skb, th, 0)) return 0; /* step 5: check the ACK field */ - if (th->ack) { + if (true) { int acceptable = tcp_ack(sk, skb, FLAG_SLOWPATH) > 0; switch (sk->sk_state) { @@ -6138,8 +6138,7 @@ int tcp_rcv_state_process(struct sock *sk, struct sk_buff *skb, } break; } - } else - goto discard; + } /* ts_recent update must be made after we are sure that the packet * is in window. diff --git a/net/ipv4/tcp_ipv4.c b/net/ipv4/tcp_ipv4.c index 54139fa514e6..77f5050efc8d 100644 --- a/net/ipv4/tcp_ipv4.c +++ b/net/ipv4/tcp_ipv4.c @@ -369,11 +369,10 @@ void tcp_v4_err(struct sk_buff *icmp_skb, u32 info) * We do take care of PMTU discovery (RFC1191) special case : * we can receive locally generated ICMP messages while socket is held. */ - if (sock_owned_by_user(sk) && - type != ICMP_DEST_UNREACH && - code != ICMP_FRAG_NEEDED) - NET_INC_STATS_BH(net, LINUX_MIB_LOCKDROPPEDICMPS); - + if (sock_owned_by_user(sk)) { + if (!(type == ICMP_DEST_UNREACH && code == ICMP_FRAG_NEEDED)) + NET_INC_STATS_BH(net, LINUX_MIB_LOCKDROPPEDICMPS); + } if (sk->sk_state == TCP_CLOSE) goto out; @@ -497,6 +496,7 @@ void tcp_v4_err(struct sk_buff *icmp_skb, u32 info) * errors returned from accept(). */ inet_csk_reqsk_queue_drop(sk, req, prev); + NET_INC_STATS_BH(sock_net(sk), LINUX_MIB_LISTENDROPS); goto out; case TCP_SYN_SENT: @@ -657,7 +657,8 @@ static void tcp_v4_send_reset(struct sock *sk, struct sk_buff *skb) * no RST generated if md5 hash doesn't match. */ sk1 = __inet_lookup_listener(dev_net(skb_dst(skb)->dev), - &tcp_hashinfo, ip_hdr(skb)->daddr, + &tcp_hashinfo, ip_hdr(skb)->saddr, + th->source, ip_hdr(skb)->daddr, ntohs(th->source), inet_iif(skb)); /* don't send rst if it can't find key */ if (!sk1) @@ -725,7 +726,7 @@ release_sk1: */ static void tcp_v4_send_ack(struct sk_buff *skb, u32 seq, u32 ack, - u32 win, u32 ts, int oif, + u32 win, u32 tsval, u32 tsecr, int oif, struct tcp_md5sig_key *key, int reply_flags, u8 tos) { @@ -746,12 +747,12 @@ static void tcp_v4_send_ack(struct sk_buff *skb, u32 seq, u32 ack, arg.iov[0].iov_base = (unsigned char *)&rep; arg.iov[0].iov_len = sizeof(rep.th); - if (ts) { + if (tsecr) { rep.opt[0] = htonl((TCPOPT_NOP << 24) | (TCPOPT_NOP << 16) | (TCPOPT_TIMESTAMP << 8) | TCPOLEN_TIMESTAMP); - rep.opt[1] = htonl(tcp_time_stamp); - rep.opt[2] = htonl(ts); + rep.opt[1] = htonl(tsval); + rep.opt[2] = htonl(tsecr); arg.iov[0].iov_len += TCPOLEN_TSTAMP_ALIGNED; } @@ -766,7 +767,7 @@ static void tcp_v4_send_ack(struct sk_buff *skb, u32 seq, u32 ack, #ifdef CONFIG_TCP_MD5SIG if (key) { - int offset = (ts) ? 3 : 0; + int offset = (tsecr) ? 3 : 0; rep.opt[offset++] = htonl((TCPOPT_NOP << 24) | (TCPOPT_NOP << 16) | @@ -801,6 +802,7 @@ static void tcp_v4_timewait_ack(struct sock *sk, struct sk_buff *skb) tcp_v4_send_ack(skb, tcptw->tw_snd_nxt, tcptw->tw_rcv_nxt, tcptw->tw_rcv_wnd >> tw->tw_rcv_wscale, + tcp_time_stamp + tcptw->tw_ts_offset, tcptw->tw_ts_recent, tw->tw_bound_dev_if, tcp_twsk_md5_key(tcptw), @@ -820,6 +822,7 @@ static void tcp_v4_reqsk_send_ack(struct sock *sk, struct sk_buff *skb, tcp_v4_send_ack(skb, (sk->sk_state == TCP_LISTEN) ? tcp_rsk(req)->snt_isn + 1 : tcp_sk(sk)->snd_nxt, tcp_rsk(req)->rcv_nxt, req->rcv_wnd, + tcp_time_stamp, req->ts_recent, 0, tcp_md5_do_lookup(sk, (union tcp_md5_addr *)&ip_hdr(skb)->daddr, @@ -1501,8 +1504,10 @@ int tcp_v4_conn_request(struct sock *sk, struct sk_buff *skb) * clogging syn queue with openreqs with exponentially increasing * timeout. */ - if (sk_acceptq_is_full(sk) && inet_csk_reqsk_queue_young(sk) > 1) + if (sk_acceptq_is_full(sk) && inet_csk_reqsk_queue_young(sk) > 1) { + NET_INC_STATS_BH(sock_net(sk), LINUX_MIB_LISTENOVERFLOWS); goto drop; + } req = inet_reqsk_alloc(&tcp_request_sock_ops); if (!req) @@ -1568,7 +1573,7 @@ int tcp_v4_conn_request(struct sock *sk, struct sk_buff *skb) goto drop_and_free; if (!want_cookie || tmp_opt.tstamp_ok) - TCP_ECN_create_request(req, skb); + TCP_ECN_create_request(req, skb, sock_net(sk)); if (want_cookie) { isn = cookie_v4_init_sequence(sk, skb, &req->mss); @@ -1667,6 +1672,7 @@ drop_and_release: drop_and_free: reqsk_free(req); drop: + NET_INC_STATS_BH(sock_net(sk), LINUX_MIB_LISTENDROPS); return 0; } EXPORT_SYMBOL(tcp_v4_conn_request); @@ -2074,6 +2080,7 @@ do_time_wait: case TCP_TW_SYN: { struct sock *sk2 = inet_lookup_listener(dev_net(skb->dev), &tcp_hashinfo, + iph->saddr, th->source, iph->daddr, th->dest, inet_iif(skb)); if (sk2) { @@ -2888,6 +2895,7 @@ EXPORT_SYMBOL(tcp_prot); static int __net_init tcp_sk_init(struct net *net) { + net->ipv4.sysctl_tcp_ecn = 2; return 0; } diff --git a/net/ipv4/tcp_minisocks.c b/net/ipv4/tcp_minisocks.c index f35f2dfb6401..b83a49cc3816 100644 --- a/net/ipv4/tcp_minisocks.c +++ b/net/ipv4/tcp_minisocks.c @@ -102,6 +102,7 @@ tcp_timewait_state_process(struct inet_timewait_sock *tw, struct sk_buff *skb, tcp_parse_options(skb, &tmp_opt, &hash_location, 0, NULL); if (tmp_opt.saw_tstamp) { + 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; paws_reject = tcp_paws_reject(&tmp_opt, th->rst); @@ -288,6 +289,7 @@ void tcp_time_wait(struct sock *sk, int state, int timeo) tcptw->tw_rcv_wnd = tcp_receive_window(tp); tcptw->tw_ts_recent = tp->rx_opt.ts_recent; tcptw->tw_ts_recent_stamp = tp->rx_opt.ts_recent_stamp; + tcptw->tw_ts_offset = tp->tsoffset; #if IS_ENABLED(CONFIG_IPV6) if (tw->tw_family == PF_INET6) { @@ -446,7 +448,6 @@ struct sock *tcp_create_openreq_child(struct sock *sk, struct request_sock *req, */ newtp->snd_cwnd = TCP_INIT_CWND; newtp->snd_cwnd_cnt = 0; - newtp->bytes_acked = 0; newtp->frto_counter = 0; newtp->frto_highmark = 0; @@ -500,6 +501,7 @@ struct sock *tcp_create_openreq_child(struct sock *sk, struct request_sock *req, newtp->rx_opt.ts_recent_stamp = 0; newtp->tcp_header_len = sizeof(struct tcphdr); } + newtp->tsoffset = 0; #ifdef CONFIG_TCP_MD5SIG newtp->md5sig_info = NULL; /*XXX*/ if (newtp->af_specific->md5_lookup(sk, newsk)) diff --git a/net/ipv4/tcp_output.c b/net/ipv4/tcp_output.c index 5d451593ef16..fd0cea114b5d 100644 --- a/net/ipv4/tcp_output.c +++ b/net/ipv4/tcp_output.c @@ -314,7 +314,7 @@ static inline void TCP_ECN_send_syn(struct sock *sk, struct sk_buff *skb) struct tcp_sock *tp = tcp_sk(sk); tp->ecn_flags = 0; - if (sysctl_tcp_ecn == 1) { + if (sock_net(sk)->ipv4.sysctl_tcp_ecn == 1) { TCP_SKB_CB(skb)->tcp_flags |= TCPHDR_ECE | TCPHDR_CWR; tp->ecn_flags = TCP_ECN_OK; } @@ -622,7 +622,7 @@ static unsigned int tcp_syn_options(struct sock *sk, struct sk_buff *skb, if (likely(sysctl_tcp_timestamps && *md5 == NULL)) { opts->options |= OPTION_TS; - opts->tsval = TCP_SKB_CB(skb)->when; + opts->tsval = TCP_SKB_CB(skb)->when + tp->tsoffset; opts->tsecr = tp->rx_opt.ts_recent; remaining -= TCPOLEN_TSTAMP_ALIGNED; } @@ -806,7 +806,7 @@ static unsigned int tcp_established_options(struct sock *sk, struct sk_buff *skb if (likely(tp->rx_opt.tstamp_ok)) { opts->options |= OPTION_TS; - opts->tsval = tcb ? tcb->when : 0; + opts->tsval = tcb ? tcb->when + tp->tsoffset : 0; opts->tsecr = tp->rx_opt.ts_recent; size += TCPOLEN_TSTAMP_ALIGNED; } @@ -1331,7 +1331,7 @@ static void __pskb_trim_head(struct sk_buff *skb, int len) /* Remove acked data from a packet in the transmit queue. */ int tcp_trim_head(struct sock *sk, struct sk_buff *skb, u32 len) { - if (skb_cloned(skb) && pskb_expand_head(skb, 0, 0, GFP_ATOMIC)) + if (skb_unclone(skb, GFP_ATOMIC)) return -ENOMEM; __pskb_trim_head(skb, len); diff --git a/net/ipv4/udp.c b/net/ipv4/udp.c index 79c8dbe59b54..39a5e7a9a77f 100644 --- a/net/ipv4/udp.c +++ b/net/ipv4/udp.c @@ -139,6 +139,7 @@ static int udp_lib_lport_inuse(struct net *net, __u16 num, { struct sock *sk2; struct hlist_nulls_node *node; + kuid_t uid = sock_i_uid(sk); sk_nulls_for_each(sk2, node, &hslot->head) if (net_eq(sock_net(sk2), net) && @@ -147,6 +148,8 @@ static int udp_lib_lport_inuse(struct net *net, __u16 num, (!sk2->sk_reuse || !sk->sk_reuse) && (!sk2->sk_bound_dev_if || !sk->sk_bound_dev_if || sk2->sk_bound_dev_if == sk->sk_bound_dev_if) && + (!sk2->sk_reuseport || !sk->sk_reuseport || + !uid_eq(uid, sock_i_uid(sk2))) && (*saddr_comp)(sk, sk2)) { if (bitmap) __set_bit(udp_sk(sk2)->udp_port_hash >> log, @@ -169,6 +172,7 @@ static int udp_lib_lport_inuse2(struct net *net, __u16 num, { struct sock *sk2; struct hlist_nulls_node *node; + kuid_t uid = sock_i_uid(sk); int res = 0; spin_lock(&hslot2->lock); @@ -179,6 +183,8 @@ static int udp_lib_lport_inuse2(struct net *net, __u16 num, (!sk2->sk_reuse || !sk->sk_reuse) && (!sk2->sk_bound_dev_if || !sk->sk_bound_dev_if || sk2->sk_bound_dev_if == sk->sk_bound_dev_if) && + (!sk2->sk_reuseport || !sk->sk_reuseport || + !uid_eq(uid, sock_i_uid(sk2))) && (*saddr_comp)(sk, sk2)) { res = 1; break; @@ -337,26 +343,26 @@ static inline int compute_score(struct sock *sk, struct net *net, __be32 saddr, !ipv6_only_sock(sk)) { struct inet_sock *inet = inet_sk(sk); - score = (sk->sk_family == PF_INET ? 1 : 0); + score = (sk->sk_family == PF_INET ? 2 : 1); if (inet->inet_rcv_saddr) { if (inet->inet_rcv_saddr != daddr) return -1; - score += 2; + score += 4; } if (inet->inet_daddr) { if (inet->inet_daddr != saddr) return -1; - score += 2; + score += 4; } if (inet->inet_dport) { if (inet->inet_dport != sport) return -1; - score += 2; + score += 4; } if (sk->sk_bound_dev_if) { if (sk->sk_bound_dev_if != dif) return -1; - score += 2; + score += 4; } } return score; @@ -365,7 +371,6 @@ static inline int compute_score(struct sock *sk, struct net *net, __be32 saddr, /* * In this second variant, we check (daddr, dport) matches (inet_rcv_sadd, inet_num) */ -#define SCORE2_MAX (1 + 2 + 2 + 2) static inline int compute_score2(struct sock *sk, struct net *net, __be32 saddr, __be16 sport, __be32 daddr, unsigned int hnum, int dif) @@ -380,21 +385,21 @@ static inline int compute_score2(struct sock *sk, struct net *net, if (inet->inet_num != hnum) return -1; - score = (sk->sk_family == PF_INET ? 1 : 0); + score = (sk->sk_family == PF_INET ? 2 : 1); if (inet->inet_daddr) { if (inet->inet_daddr != saddr) return -1; - score += 2; + score += 4; } if (inet->inet_dport) { if (inet->inet_dport != sport) return -1; - score += 2; + score += 4; } if (sk->sk_bound_dev_if) { if (sk->sk_bound_dev_if != dif) return -1; - score += 2; + score += 4; } } return score; @@ -409,19 +414,29 @@ static struct sock *udp4_lib_lookup2(struct net *net, { struct sock *sk, *result; struct hlist_nulls_node *node; - int score, badness; + int score, badness, matches = 0, reuseport = 0; + u32 hash = 0; begin: result = NULL; - badness = -1; + badness = 0; udp_portaddr_for_each_entry_rcu(sk, node, &hslot2->head) { score = compute_score2(sk, net, saddr, sport, daddr, hnum, dif); if (score > badness) { result = sk; badness = score; - if (score == SCORE2_MAX) - goto exact_match; + reuseport = sk->sk_reuseport; + if (reuseport) { + hash = inet_ehashfn(net, daddr, hnum, + saddr, htons(sport)); + matches = 1; + } + } else if (score == badness && reuseport) { + matches++; + if (((u64)hash * matches) >> 32 == 0) + result = sk; + hash = next_pseudo_random32(hash); } } /* @@ -431,9 +446,7 @@ begin: */ if (get_nulls_value(node) != slot2) goto begin; - if (result) { -exact_match: if (unlikely(!atomic_inc_not_zero_hint(&result->sk_refcnt, 2))) result = NULL; else if (unlikely(compute_score2(result, net, saddr, sport, @@ -457,7 +470,8 @@ struct sock *__udp4_lib_lookup(struct net *net, __be32 saddr, unsigned short hnum = ntohs(dport); unsigned int hash2, slot2, slot = udp_hashfn(net, hnum, udptable->mask); struct udp_hslot *hslot2, *hslot = &udptable->hash[slot]; - int score, badness; + int score, badness, matches = 0, reuseport = 0; + u32 hash = 0; rcu_read_lock(); if (hslot->count > 10) { @@ -486,13 +500,24 @@ struct sock *__udp4_lib_lookup(struct net *net, __be32 saddr, } begin: result = NULL; - badness = -1; + badness = 0; sk_nulls_for_each_rcu(sk, node, &hslot->head) { score = compute_score(sk, net, saddr, hnum, sport, daddr, dport, dif); if (score > badness) { result = sk; badness = score; + reuseport = sk->sk_reuseport; + if (reuseport) { + hash = inet_ehashfn(net, daddr, hnum, + saddr, htons(sport)); + matches = 1; + } + } else if (score == badness && reuseport) { + matches++; + if (((u64)hash * matches) >> 32 == 0) + result = sk; + hash = next_pseudo_random32(hash); } } /* @@ -971,7 +996,7 @@ back_from_confirm: sizeof(struct udphdr), &ipc, &rt, msg->msg_flags); err = PTR_ERR(skb); - if (skb && !IS_ERR(skb)) + if (!IS_ERR_OR_NULL(skb)) err = udp_send_skb(skb, fl4); goto out; } @@ -1952,6 +1977,7 @@ struct proto udp_prot = { .recvmsg = udp_recvmsg, .sendpage = udp_sendpage, .backlog_rcv = __udp_queue_rcv_skb, + .release_cb = ip4_datagram_release_cb, .hash = udp_lib_hash, .unhash = udp_lib_unhash, .rehash = udp_v4_rehash, @@ -2279,7 +2305,8 @@ struct sk_buff *udp4_ufo_fragment(struct sk_buff *skb, /* Packet is from an untrusted source, reset gso_segs. */ int type = skb_shinfo(skb)->gso_type; - if (unlikely(type & ~(SKB_GSO_UDP | SKB_GSO_DODGY) || + if (unlikely(type & ~(SKB_GSO_UDP | SKB_GSO_DODGY | + SKB_GSO_GRE) || !(type & (SKB_GSO_UDP)))) goto out; diff --git a/net/ipv4/xfrm4_input.c b/net/ipv4/xfrm4_input.c index 06814b6216dc..1f12c8b45864 100644 --- a/net/ipv4/xfrm4_input.c +++ b/net/ipv4/xfrm4_input.c @@ -132,7 +132,7 @@ int xfrm4_udp_encap_rcv(struct sock *sk, struct sk_buff *skb) * header and optional ESP marker bytes) and then modify the * protocol to ESP, and then call into the transform receiver. */ - if (skb_cloned(skb) && pskb_expand_head(skb, 0, 0, GFP_ATOMIC)) + if (skb_unclone(skb, GFP_ATOMIC)) goto drop; /* Now we can update and verify the packet length... */ diff --git a/net/ipv4/xfrm4_mode_tunnel.c b/net/ipv4/xfrm4_mode_tunnel.c index ddee0a099a2c..fe5189e2e114 100644 --- a/net/ipv4/xfrm4_mode_tunnel.c +++ b/net/ipv4/xfrm4_mode_tunnel.c @@ -142,8 +142,8 @@ static int xfrm4_mode_tunnel_input(struct xfrm_state *x, struct sk_buff *skb) for_each_input_rcu(rcv_notify_handlers, handler) handler->handler(skb); - if (skb_cloned(skb) && - (err = pskb_expand_head(skb, 0, 0, GFP_ATOMIC))) + err = skb_unclone(skb, GFP_ATOMIC); + if (err) goto out; if (x->props.flags & XFRM_STATE_DECAP_DSCP) diff --git a/net/ipv4/xfrm4_policy.c b/net/ipv4/xfrm4_policy.c index 3be0ac2c1920..9a459be24af7 100644 --- a/net/ipv4/xfrm4_policy.c +++ b/net/ipv4/xfrm4_policy.c @@ -262,21 +262,56 @@ static struct ctl_table xfrm4_policy_table[] = { { } }; -static struct ctl_table_header *sysctl_hdr; -#endif - -static void __init xfrm4_policy_init(void) +static int __net_init xfrm4_net_init(struct net *net) { - xfrm_policy_register_afinfo(&xfrm4_policy_afinfo); + struct ctl_table *table; + struct ctl_table_header *hdr; + + table = xfrm4_policy_table; + if (!net_eq(net, &init_net)) { + table = kmemdup(table, sizeof(xfrm4_policy_table), GFP_KERNEL); + if (!table) + goto err_alloc; + + table[0].data = &net->xfrm.xfrm4_dst_ops.gc_thresh; + } + + hdr = register_net_sysctl(net, "net/ipv4", table); + if (!hdr) + goto err_reg; + + net->ipv4.xfrm4_hdr = hdr; + return 0; + +err_reg: + if (!net_eq(net, &init_net)) + kfree(table); +err_alloc: + return -ENOMEM; } -static void __exit xfrm4_policy_fini(void) +static void __net_exit xfrm4_net_exit(struct net *net) { -#ifdef CONFIG_SYSCTL - if (sysctl_hdr) - unregister_net_sysctl_table(sysctl_hdr); + struct ctl_table *table; + + if (net->ipv4.xfrm4_hdr == NULL) + return; + + table = net->ipv4.xfrm4_hdr->ctl_table_arg; + unregister_net_sysctl_table(net->ipv4.xfrm4_hdr); + if (!net_eq(net, &init_net)) + kfree(table); +} + +static struct pernet_operations __net_initdata xfrm4_net_ops = { + .init = xfrm4_net_init, + .exit = xfrm4_net_exit, +}; #endif - xfrm_policy_unregister_afinfo(&xfrm4_policy_afinfo); + +static void __init xfrm4_policy_init(void) +{ + xfrm_policy_register_afinfo(&xfrm4_policy_afinfo); } void __init xfrm4_init(void) @@ -286,8 +321,7 @@ void __init xfrm4_init(void) xfrm4_state_init(); xfrm4_policy_init(); #ifdef CONFIG_SYSCTL - sysctl_hdr = register_net_sysctl(&init_net, "net/ipv4", - xfrm4_policy_table); + register_pernet_subsys(&xfrm4_net_ops); #endif } diff --git a/net/ipv6/Makefile b/net/ipv6/Makefile index 4ea244891b58..309af19a0a0a 100644 --- a/net/ipv6/Makefile +++ b/net/ipv6/Makefile @@ -40,7 +40,7 @@ obj-$(CONFIG_IPV6_SIT) += sit.o obj-$(CONFIG_IPV6_TUNNEL) += ip6_tunnel.o obj-$(CONFIG_IPV6_GRE) += ip6_gre.o -obj-y += addrconf_core.o exthdrs_core.o +obj-y += addrconf_core.o exthdrs_core.o ip6_checksum.o obj-$(CONFIG_INET) += output_core.o protocol.o $(ipv6-offload) obj-$(subst m,y,$(CONFIG_IPV6)) += inet6_hashtables.o diff --git a/net/ipv6/addrconf.c b/net/ipv6/addrconf.c index 408cac4ae00a..86c235d05aba 100644 --- a/net/ipv6/addrconf.c +++ b/net/ipv6/addrconf.c @@ -110,10 +110,6 @@ static inline u32 cstamp_delta(unsigned long cstamp) return (cstamp - INITIAL_JIFFIES) * 100UL / HZ; } -#define ADDRCONF_TIMER_FUZZ_MINUS (HZ > 50 ? HZ/50 : 1) -#define ADDRCONF_TIMER_FUZZ (HZ / 4) -#define ADDRCONF_TIMER_FUZZ_MAX (HZ) - #ifdef CONFIG_SYSCTL static void addrconf_sysctl_register(struct inet6_dev *idev); static void addrconf_sysctl_unregister(struct inet6_dev *idev); @@ -154,6 +150,11 @@ static void addrconf_type_change(struct net_device *dev, unsigned long event); static int addrconf_ifdown(struct net_device *dev, int how); +static struct rt6_info *addrconf_get_prefix_route(const struct in6_addr *pfx, + int plen, + const struct net_device *dev, + u32 flags, u32 noflags); + static void addrconf_dad_start(struct inet6_ifaddr *ifp); static void addrconf_dad_timer(unsigned long data); static void addrconf_dad_completed(struct inet6_ifaddr *ifp); @@ -243,6 +244,9 @@ const struct in6_addr in6addr_any = IN6ADDR_ANY_INIT; const struct in6_addr in6addr_loopback = IN6ADDR_LOOPBACK_INIT; const struct in6_addr in6addr_linklocal_allnodes = IN6ADDR_LINKLOCAL_ALLNODES_INIT; const struct in6_addr in6addr_linklocal_allrouters = IN6ADDR_LINKLOCAL_ALLROUTERS_INIT; +const struct in6_addr in6addr_interfacelocal_allnodes = IN6ADDR_INTERFACELOCAL_ALLNODES_INIT; +const struct in6_addr in6addr_interfacelocal_allrouters = IN6ADDR_INTERFACELOCAL_ALLROUTERS_INIT; +const struct in6_addr in6addr_sitelocal_allrouters = IN6ADDR_SITELOCAL_ALLROUTERS_INIT; /* Check if a valid qdisc is available */ static inline bool addrconf_qdisc_ok(const struct net_device *dev) @@ -250,12 +254,6 @@ static inline bool addrconf_qdisc_ok(const struct net_device *dev) return !qdisc_tx_is_noop(dev); } -/* Check if a route is valid prefix route */ -static inline int addrconf_is_prefix_route(const struct rt6_info *rt) -{ - return (rt->rt6i_flags & (RTF_GATEWAY | RTF_DEFAULT)) == 0; -} - static void addrconf_del_timer(struct inet6_ifaddr *ifp) { if (del_timer(&ifp->timer)) @@ -433,6 +431,9 @@ static struct inet6_dev *ipv6_add_dev(struct net_device *dev) /* protected by rtnl_lock */ rcu_assign_pointer(dev->ip6_ptr, ndev); + /* Join interface-local all-node multicast group */ + ipv6_dev_mc_inc(dev, &in6addr_interfacelocal_allnodes); + /* Join all-node multicast group */ ipv6_dev_mc_inc(dev, &in6addr_linklocal_allnodes); @@ -616,10 +617,15 @@ static void dev_forward_change(struct inet6_dev *idev) if (idev->cnf.forwarding) dev_disable_lro(dev); if (dev->flags & IFF_MULTICAST) { - if (idev->cnf.forwarding) + if (idev->cnf.forwarding) { ipv6_dev_mc_inc(dev, &in6addr_linklocal_allrouters); - else + ipv6_dev_mc_inc(dev, &in6addr_interfacelocal_allrouters); + ipv6_dev_mc_inc(dev, &in6addr_sitelocal_allrouters); + } else { ipv6_dev_mc_dec(dev, &in6addr_linklocal_allrouters); + ipv6_dev_mc_dec(dev, &in6addr_interfacelocal_allrouters); + ipv6_dev_mc_dec(dev, &in6addr_sitelocal_allrouters); + } } list_for_each_entry(ifa, &idev->addr_list, if_list) { @@ -941,17 +947,15 @@ static void ipv6_del_addr(struct inet6_ifaddr *ifp) if ((ifp->flags & IFA_F_PERMANENT) && onlink < 1) { struct in6_addr prefix; struct rt6_info *rt; - struct net *net = dev_net(ifp->idev->dev); - struct flowi6 fl6 = {}; ipv6_addr_prefix(&prefix, &ifp->addr, ifp->prefix_len); - fl6.flowi6_oif = ifp->idev->dev->ifindex; - fl6.daddr = prefix; - rt = (struct rt6_info *)ip6_route_lookup(net, &fl6, - RT6_LOOKUP_F_IFACE); - if (rt != net->ipv6.ip6_null_entry && - addrconf_is_prefix_route(rt)) { + rt = addrconf_get_prefix_route(&prefix, + ifp->prefix_len, + ifp->idev->dev, + 0, RTF_GATEWAY | RTF_DEFAULT); + + if (rt) { if (onlink == 0) { ip6_del_rt(rt); rt = NULL; @@ -1054,7 +1058,7 @@ retry: ipv6_add_addr(idev, &addr, tmp_plen, ipv6_addr_type(&addr)&IPV6_ADDR_SCOPE_MASK, addr_flags) : NULL; - if (!ift || IS_ERR(ift)) { + if (IS_ERR_OR_NULL(ift)) { in6_ifa_put(ifp); in6_dev_put(idev); pr_info("%s: retry temporary address regeneration\n", __func__); @@ -1663,6 +1667,7 @@ static int addrconf_ifid_eui64(u8 *eui, struct net_device *dev) if (dev->addr_len != IEEE802154_ADDR_LEN) return -1; memcpy(eui, dev->dev_addr, 8); + eui[0] ^= 2; return 0; } @@ -1877,7 +1882,7 @@ static struct rt6_info *addrconf_get_prefix_route(const struct in6_addr *pfx, continue; if ((rt->rt6i_flags & flags) != flags) continue; - if ((noflags != 0) && ((rt->rt6i_flags & flags) != 0)) + if ((rt->rt6i_flags & noflags) != 0) continue; dst_hold(&rt->dst); break; @@ -2082,7 +2087,7 @@ ok: addr_type&IPV6_ADDR_SCOPE_MASK, addr_flags); - if (!ifp || IS_ERR(ifp)) { + if (IS_ERR_OR_NULL(ifp)) { in6_dev_put(in6_dev); return; } diff --git a/net/ipv6/af_inet6.c b/net/ipv6/af_inet6.c index b043c60429bd..6b793bfc0e10 100644 --- a/net/ipv6/af_inet6.c +++ b/net/ipv6/af_inet6.c @@ -811,11 +811,10 @@ static struct pernet_operations inet6_net_ops = { static int __init inet6_init(void) { - struct sk_buff *dummy_skb; struct list_head *r; int err = 0; - BUILD_BUG_ON(sizeof(struct inet6_skb_parm) > sizeof(dummy_skb->cb)); + BUILD_BUG_ON(sizeof(struct inet6_skb_parm) > FIELD_SIZEOF(struct sk_buff, cb)); /* Register the socket-side information for inet6_create. */ for (r = &inetsw6[0]; r < &inetsw6[SOCK_MAX]; ++r) diff --git a/net/ipv6/ah6.c b/net/ipv6/ah6.c index ecc35b93314b..bb02e176cb70 100644 --- a/net/ipv6/ah6.c +++ b/net/ipv6/ah6.c @@ -472,7 +472,10 @@ static void ah6_input_done(struct crypto_async_request *base, int err) skb->network_header += ah_hlen; memcpy(skb_network_header(skb), work_iph, hdr_len); __skb_pull(skb, ah_hlen + hdr_len); - skb_set_transport_header(skb, -hdr_len); + if (x->props.mode == XFRM_MODE_TUNNEL) + skb_reset_transport_header(skb); + else + skb_set_transport_header(skb, -hdr_len); out: kfree(AH_SKB_CB(skb)->tmp); xfrm_input_resume(skb, err); @@ -518,8 +521,7 @@ static int ah6_input(struct xfrm_state *x, struct sk_buff *skb) /* We are going to _remove_ AH header to keep sockets happy, * so... Later this can change. */ - if (skb_cloned(skb) && - pskb_expand_head(skb, 0, 0, GFP_ATOMIC)) + if (skb_unclone(skb, GFP_ATOMIC)) goto out; skb->ip_summed = CHECKSUM_NONE; @@ -593,9 +595,13 @@ static int ah6_input(struct xfrm_state *x, struct sk_buff *skb) skb->network_header += ah_hlen; memcpy(skb_network_header(skb), work_iph, hdr_len); - skb->transport_header = skb->network_header; __skb_pull(skb, ah_hlen + hdr_len); + if (x->props.mode == XFRM_MODE_TUNNEL) + skb_reset_transport_header(skb); + else + skb_set_transport_header(skb, -hdr_len); + err = nexthdr; out_free: diff --git a/net/ipv6/anycast.c b/net/ipv6/anycast.c index 757a810d8f15..921b8b398a8c 100644 --- a/net/ipv6/anycast.c +++ b/net/ipv6/anycast.c @@ -47,7 +47,7 @@ static int ipv6_dev_ac_dec(struct net_device *dev, const struct in6_addr *addr); /* Big ac list lock for all the sockets */ -static DEFINE_RWLOCK(ipv6_sk_ac_lock); +static DEFINE_SPINLOCK(ipv6_sk_ac_lock); /* @@ -128,10 +128,10 @@ int ipv6_sock_ac_join(struct sock *sk, int ifindex, const struct in6_addr *addr) err = ipv6_dev_ac_inc(dev, addr); if (!err) { - write_lock_bh(&ipv6_sk_ac_lock); + spin_lock_bh(&ipv6_sk_ac_lock); pac->acl_next = np->ipv6_ac_list; np->ipv6_ac_list = pac; - write_unlock_bh(&ipv6_sk_ac_lock); + spin_unlock_bh(&ipv6_sk_ac_lock); pac = NULL; } @@ -152,7 +152,7 @@ int ipv6_sock_ac_drop(struct sock *sk, int ifindex, const struct in6_addr *addr) struct ipv6_ac_socklist *pac, *prev_pac; struct net *net = sock_net(sk); - write_lock_bh(&ipv6_sk_ac_lock); + spin_lock_bh(&ipv6_sk_ac_lock); prev_pac = NULL; for (pac = np->ipv6_ac_list; pac; pac = pac->acl_next) { if ((ifindex == 0 || pac->acl_ifindex == ifindex) && @@ -161,7 +161,7 @@ int ipv6_sock_ac_drop(struct sock *sk, int ifindex, const struct in6_addr *addr) prev_pac = pac; } if (!pac) { - write_unlock_bh(&ipv6_sk_ac_lock); + spin_unlock_bh(&ipv6_sk_ac_lock); return -ENOENT; } if (prev_pac) @@ -169,7 +169,7 @@ int ipv6_sock_ac_drop(struct sock *sk, int ifindex, const struct in6_addr *addr) else np->ipv6_ac_list = pac->acl_next; - write_unlock_bh(&ipv6_sk_ac_lock); + spin_unlock_bh(&ipv6_sk_ac_lock); rcu_read_lock(); dev = dev_get_by_index_rcu(net, pac->acl_ifindex); @@ -192,10 +192,10 @@ void ipv6_sock_ac_close(struct sock *sk) if (!np->ipv6_ac_list) return; - write_lock_bh(&ipv6_sk_ac_lock); + spin_lock_bh(&ipv6_sk_ac_lock); pac = np->ipv6_ac_list; np->ipv6_ac_list = NULL; - write_unlock_bh(&ipv6_sk_ac_lock); + spin_unlock_bh(&ipv6_sk_ac_lock); prev_index = 0; rcu_read_lock(); diff --git a/net/ipv6/datagram.c b/net/ipv6/datagram.c index 8edf2601065a..f5a54782a340 100644 --- a/net/ipv6/datagram.c +++ b/net/ipv6/datagram.c @@ -30,6 +30,7 @@ #include <net/transp_v6.h> #include <net/ip6_route.h> #include <net/tcp_states.h> +#include <net/dsfield.h> #include <linux/errqueue.h> #include <asm/uaccess.h> @@ -356,12 +357,11 @@ int ipv6_recv_error(struct sock *sk, struct msghdr *msg, int len) sin->sin6_port = serr->port; sin->sin6_scope_id = 0; if (skb->protocol == htons(ETH_P_IPV6)) { - sin->sin6_addr = - *(struct in6_addr *)(nh + serr->addr_offset); + const struct ipv6hdr *ip6h = container_of((struct in6_addr *)(nh + serr->addr_offset), + struct ipv6hdr, daddr); + sin->sin6_addr = ip6h->daddr; if (np->sndflow) - sin->sin6_flowinfo = - (*(__be32 *)(nh + serr->addr_offset - 24) & - IPV6_FLOWINFO_MASK); + sin->sin6_flowinfo = ip6_flowinfo(ip6h); if (ipv6_addr_type(&sin->sin6_addr) & IPV6_ADDR_LINKLOCAL) sin->sin6_scope_id = IP6CB(skb)->iif; } else { @@ -380,7 +380,7 @@ int ipv6_recv_error(struct sock *sk, struct msghdr *msg, int len) if (skb->protocol == htons(ETH_P_IPV6)) { sin->sin6_addr = ipv6_hdr(skb)->saddr; if (np->rxopt.all) - datagram_recv_ctl(sk, msg, skb); + ip6_datagram_recv_ctl(sk, msg, skb); if (ipv6_addr_type(&sin->sin6_addr) & IPV6_ADDR_LINKLOCAL) sin->sin6_scope_id = IP6CB(skb)->iif; } else { @@ -468,7 +468,8 @@ out: } -int datagram_recv_ctl(struct sock *sk, struct msghdr *msg, struct sk_buff *skb) +int ip6_datagram_recv_ctl(struct sock *sk, struct msghdr *msg, + struct sk_buff *skb) { struct ipv6_pinfo *np = inet6_sk(sk); struct inet6_skb_parm *opt = IP6CB(skb); @@ -488,13 +489,14 @@ int datagram_recv_ctl(struct sock *sk, struct msghdr *msg, struct sk_buff *skb) } if (np->rxopt.bits.rxtclass) { - int tclass = ipv6_tclass(ipv6_hdr(skb)); + int tclass = ipv6_get_dsfield(ipv6_hdr(skb)); put_cmsg(msg, SOL_IPV6, IPV6_TCLASS, sizeof(tclass), &tclass); } - if (np->rxopt.bits.rxflow && (*(__be32 *)nh & IPV6_FLOWINFO_MASK)) { - __be32 flowinfo = *(__be32 *)nh & IPV6_FLOWINFO_MASK; - put_cmsg(msg, SOL_IPV6, IPV6_FLOWINFO, sizeof(flowinfo), &flowinfo); + if (np->rxopt.bits.rxflow) { + __be32 flowinfo = ip6_flowinfo((struct ipv6hdr *)nh); + if (flowinfo) + put_cmsg(msg, SOL_IPV6, IPV6_FLOWINFO, sizeof(flowinfo), &flowinfo); } /* HbH is allowed only once */ @@ -597,11 +599,12 @@ int datagram_recv_ctl(struct sock *sk, struct msghdr *msg, struct sk_buff *skb) } return 0; } +EXPORT_SYMBOL_GPL(ip6_datagram_recv_ctl); -int datagram_send_ctl(struct net *net, struct sock *sk, - struct msghdr *msg, struct flowi6 *fl6, - struct ipv6_txoptions *opt, - int *hlimit, int *tclass, int *dontfrag) +int ip6_datagram_send_ctl(struct net *net, struct sock *sk, + struct msghdr *msg, struct flowi6 *fl6, + struct ipv6_txoptions *opt, + int *hlimit, int *tclass, int *dontfrag) { struct in6_pktinfo *src_info; struct cmsghdr *cmsg; @@ -871,4 +874,4 @@ int datagram_send_ctl(struct net *net, struct sock *sk, exit_f: return err; } -EXPORT_SYMBOL_GPL(datagram_send_ctl); +EXPORT_SYMBOL_GPL(ip6_datagram_send_ctl); diff --git a/net/ipv6/esp6.c b/net/ipv6/esp6.c index 282f3723ee19..40ffd72243a4 100644 --- a/net/ipv6/esp6.c +++ b/net/ipv6/esp6.c @@ -300,7 +300,10 @@ static int esp_input_done2(struct sk_buff *skb, int err) pskb_trim(skb, skb->len - alen - padlen - 2); __skb_pull(skb, hlen); - skb_set_transport_header(skb, -hdr_len); + if (x->props.mode == XFRM_MODE_TUNNEL) + skb_reset_transport_header(skb); + else + skb_set_transport_header(skb, -hdr_len); err = nexthdr[1]; diff --git a/net/ipv6/exthdrs.c b/net/ipv6/exthdrs.c index 473f628f9f20..07a7d65a7cb6 100644 --- a/net/ipv6/exthdrs.c +++ b/net/ipv6/exthdrs.c @@ -553,7 +553,8 @@ static bool ipv6_hop_ra(struct sk_buff *skb, int optoff) const unsigned char *nh = skb_network_header(skb); if (nh[optoff + 1] == 2) { - IP6CB(skb)->ra = optoff; + IP6CB(skb)->flags |= IP6SKB_ROUTERALERT; + memcpy(&IP6CB(skb)->ra, nh + optoff + 2, sizeof(IP6CB(skb)->ra)); return true; } LIMIT_NETDEBUG(KERN_DEBUG "ipv6_hop_ra: wrong RA length %d\n", diff --git a/net/ipv6/icmp.c b/net/ipv6/icmp.c index b4a9fd51dae7..fff5bdd8b680 100644 --- a/net/ipv6/icmp.c +++ b/net/ipv6/icmp.c @@ -81,10 +81,22 @@ static inline struct sock *icmpv6_sk(struct net *net) return net->ipv6.icmp_sk[smp_processor_id()]; } +static void icmpv6_err(struct sk_buff *skb, struct inet6_skb_parm *opt, + u8 type, u8 code, int offset, __be32 info) +{ + struct net *net = dev_net(skb->dev); + + if (type == ICMPV6_PKT_TOOBIG) + ip6_update_pmtu(skb, net, info, 0, 0); + else if (type == NDISC_REDIRECT) + ip6_redirect(skb, net, 0, 0); +} + static int icmpv6_rcv(struct sk_buff *skb); static const struct inet6_protocol icmpv6_protocol = { .handler = icmpv6_rcv, + .err_handler = icmpv6_err, .flags = INET6_PROTO_NOPOLICY|INET6_PROTO_FINAL, }; diff --git a/net/ipv6/inet6_connection_sock.c b/net/ipv6/inet6_connection_sock.c index 30647857a375..b386a2ce4c6f 100644 --- a/net/ipv6/inet6_connection_sock.c +++ b/net/ipv6/inet6_connection_sock.c @@ -32,6 +32,9 @@ int inet6_csk_bind_conflict(const struct sock *sk, { const struct sock *sk2; const struct hlist_node *node; + int reuse = sk->sk_reuse; + int reuseport = sk->sk_reuseport; + kuid_t uid = sock_i_uid((struct sock *)sk); /* We must walk the whole port owner list in this case. -DaveM */ /* @@ -42,11 +45,17 @@ int inet6_csk_bind_conflict(const struct sock *sk, if (sk != sk2 && (!sk->sk_bound_dev_if || !sk2->sk_bound_dev_if || - sk->sk_bound_dev_if == sk2->sk_bound_dev_if) && - (!sk->sk_reuse || !sk2->sk_reuse || - sk2->sk_state == TCP_LISTEN) && - ipv6_rcv_saddr_equal(sk, sk2)) - break; + sk->sk_bound_dev_if == sk2->sk_bound_dev_if)) { + if ((!reuse || !sk2->sk_reuse || + sk2->sk_state == TCP_LISTEN) && + (!reuseport || !sk2->sk_reuseport || + (sk2->sk_state != TCP_TIME_WAIT && + !uid_eq(uid, + sock_i_uid((struct sock *)sk2))))) { + if (ipv6_rcv_saddr_equal(sk, sk2)) + break; + } + } } return node != NULL; diff --git a/net/ipv6/inet6_hashtables.c b/net/ipv6/inet6_hashtables.c index dea17fd28e50..32b4a1675d82 100644 --- a/net/ipv6/inet6_hashtables.c +++ b/net/ipv6/inet6_hashtables.c @@ -158,25 +158,38 @@ static inline int compute_score(struct sock *sk, struct net *net, } struct sock *inet6_lookup_listener(struct net *net, - struct inet_hashinfo *hashinfo, const struct in6_addr *daddr, + struct inet_hashinfo *hashinfo, const struct in6_addr *saddr, + const __be16 sport, const struct in6_addr *daddr, const unsigned short hnum, const int dif) { struct sock *sk; const struct hlist_nulls_node *node; struct sock *result; - int score, hiscore; + int score, hiscore, matches = 0, reuseport = 0; + u32 phash = 0; unsigned int hash = inet_lhashfn(net, hnum); struct inet_listen_hashbucket *ilb = &hashinfo->listening_hash[hash]; rcu_read_lock(); begin: result = NULL; - hiscore = -1; + hiscore = 0; sk_nulls_for_each(sk, node, &ilb->head) { score = compute_score(sk, net, hnum, daddr, dif); if (score > hiscore) { hiscore = score; result = sk; + reuseport = sk->sk_reuseport; + if (reuseport) { + phash = inet6_ehashfn(net, daddr, hnum, + saddr, sport); + matches = 1; + } + } else if (score == hiscore && reuseport) { + matches++; + if (((u64)phash * matches) >> 32 == 0) + result = sk; + phash = next_pseudo_random32(phash); } } /* diff --git a/net/ipv6/ip6_checksum.c b/net/ipv6/ip6_checksum.c new file mode 100644 index 000000000000..72d198b8e4d2 --- /dev/null +++ b/net/ipv6/ip6_checksum.c @@ -0,0 +1,97 @@ +#include <net/ip.h> +#include <net/udp.h> +#include <net/udplite.h> +#include <asm/checksum.h> + +#ifndef _HAVE_ARCH_IPV6_CSUM +__sum16 csum_ipv6_magic(const struct in6_addr *saddr, + const struct in6_addr *daddr, + __u32 len, unsigned short proto, + __wsum csum) +{ + + int carry; + __u32 ulen; + __u32 uproto; + __u32 sum = (__force u32)csum; + + sum += (__force u32)saddr->s6_addr32[0]; + carry = (sum < (__force u32)saddr->s6_addr32[0]); + sum += carry; + + sum += (__force u32)saddr->s6_addr32[1]; + carry = (sum < (__force u32)saddr->s6_addr32[1]); + sum += carry; + + sum += (__force u32)saddr->s6_addr32[2]; + carry = (sum < (__force u32)saddr->s6_addr32[2]); + sum += carry; + + sum += (__force u32)saddr->s6_addr32[3]; + carry = (sum < (__force u32)saddr->s6_addr32[3]); + sum += carry; + + sum += (__force u32)daddr->s6_addr32[0]; + carry = (sum < (__force u32)daddr->s6_addr32[0]); + sum += carry; + + sum += (__force u32)daddr->s6_addr32[1]; + carry = (sum < (__force u32)daddr->s6_addr32[1]); + sum += carry; + + sum += (__force u32)daddr->s6_addr32[2]; + carry = (sum < (__force u32)daddr->s6_addr32[2]); + sum += carry; + + sum += (__force u32)daddr->s6_addr32[3]; + carry = (sum < (__force u32)daddr->s6_addr32[3]); + sum += carry; + + ulen = (__force u32)htonl((__u32) len); + sum += ulen; + carry = (sum < ulen); + sum += carry; + + uproto = (__force u32)htonl(proto); + sum += uproto; + carry = (sum < uproto); + sum += carry; + + return csum_fold((__force __wsum)sum); +} +EXPORT_SYMBOL(csum_ipv6_magic); +#endif + +int udp6_csum_init(struct sk_buff *skb, struct udphdr *uh, int proto) +{ + int err; + + UDP_SKB_CB(skb)->partial_cov = 0; + UDP_SKB_CB(skb)->cscov = skb->len; + + if (proto == IPPROTO_UDPLITE) { + err = udplite_checksum_init(skb, uh); + if (err) + return err; + } + + if (uh->check == 0) { + /* RFC 2460 section 8.1 says that we SHOULD log + this error. Well, it is reasonable. + */ + LIMIT_NETDEBUG(KERN_INFO "IPv6: udp checksum is 0\n"); + return 1; + } + if (skb->ip_summed == CHECKSUM_COMPLETE && + !csum_ipv6_magic(&ipv6_hdr(skb)->saddr, &ipv6_hdr(skb)->daddr, + skb->len, proto, skb->csum)) + skb->ip_summed = CHECKSUM_UNNECESSARY; + + if (!skb_csum_unnecessary(skb)) + skb->csum = ~csum_unfold(csum_ipv6_magic(&ipv6_hdr(skb)->saddr, + &ipv6_hdr(skb)->daddr, + skb->len, proto, 0)); + + return 0; +} +EXPORT_SYMBOL(udp6_csum_init); diff --git a/net/ipv6/ip6_flowlabel.c b/net/ipv6/ip6_flowlabel.c index 29124b7a04c8..a7da2f472479 100644 --- a/net/ipv6/ip6_flowlabel.c +++ b/net/ipv6/ip6_flowlabel.c @@ -51,25 +51,38 @@ #define FL_HASH(l) (ntohl(l)&FL_HASH_MASK) static atomic_t fl_size = ATOMIC_INIT(0); -static struct ip6_flowlabel *fl_ht[FL_HASH_MASK+1]; +static struct ip6_flowlabel __rcu *fl_ht[FL_HASH_MASK+1]; static void ip6_fl_gc(unsigned long dummy); static DEFINE_TIMER(ip6_fl_gc_timer, ip6_fl_gc, 0, 0); /* FL hash table lock: it protects only of GC */ -static DEFINE_RWLOCK(ip6_fl_lock); +static DEFINE_SPINLOCK(ip6_fl_lock); /* Big socket sock */ -static DEFINE_RWLOCK(ip6_sk_fl_lock); +static DEFINE_SPINLOCK(ip6_sk_fl_lock); +#define for_each_fl_rcu(hash, fl) \ + for (fl = rcu_dereference_bh(fl_ht[(hash)]); \ + fl != NULL; \ + fl = rcu_dereference_bh(fl->next)) +#define for_each_fl_continue_rcu(fl) \ + for (fl = rcu_dereference_bh(fl->next); \ + fl != NULL; \ + fl = rcu_dereference_bh(fl->next)) + +#define for_each_sk_fl_rcu(np, sfl) \ + for (sfl = rcu_dereference_bh(np->ipv6_fl_list); \ + sfl != NULL; \ + sfl = rcu_dereference_bh(sfl->next)) static inline struct ip6_flowlabel *__fl_lookup(struct net *net, __be32 label) { struct ip6_flowlabel *fl; - for (fl=fl_ht[FL_HASH(label)]; fl; fl = fl->next) { + for_each_fl_rcu(FL_HASH(label), fl) { if (fl->label == label && net_eq(fl->fl_net, net)) return fl; } @@ -80,11 +93,11 @@ static struct ip6_flowlabel *fl_lookup(struct net *net, __be32 label) { struct ip6_flowlabel *fl; - read_lock_bh(&ip6_fl_lock); + rcu_read_lock_bh(); fl = __fl_lookup(net, label); - if (fl) - atomic_inc(&fl->users); - read_unlock_bh(&ip6_fl_lock); + if (fl && !atomic_inc_not_zero(&fl->users)) + fl = NULL; + rcu_read_unlock_bh(); return fl; } @@ -96,13 +109,13 @@ static void fl_free(struct ip6_flowlabel *fl) put_pid(fl->owner.pid); release_net(fl->fl_net); kfree(fl->opt); + kfree_rcu(fl, rcu); } - kfree(fl); } static void fl_release(struct ip6_flowlabel *fl) { - write_lock_bh(&ip6_fl_lock); + spin_lock_bh(&ip6_fl_lock); fl->lastuse = jiffies; if (atomic_dec_and_test(&fl->users)) { @@ -119,7 +132,7 @@ static void fl_release(struct ip6_flowlabel *fl) time_after(ip6_fl_gc_timer.expires, ttd)) mod_timer(&ip6_fl_gc_timer, ttd); } - write_unlock_bh(&ip6_fl_lock); + spin_unlock_bh(&ip6_fl_lock); } static void ip6_fl_gc(unsigned long dummy) @@ -128,12 +141,13 @@ static void ip6_fl_gc(unsigned long dummy) unsigned long now = jiffies; unsigned long sched = 0; - write_lock(&ip6_fl_lock); + spin_lock(&ip6_fl_lock); for (i=0; i<=FL_HASH_MASK; i++) { struct ip6_flowlabel *fl, **flp; flp = &fl_ht[i]; - while ((fl=*flp) != NULL) { + while ((fl = rcu_dereference_protected(*flp, + lockdep_is_held(&ip6_fl_lock))) != NULL) { if (atomic_read(&fl->users) == 0) { unsigned long ttd = fl->lastuse + fl->linger; if (time_after(ttd, fl->expires)) @@ -156,18 +170,19 @@ static void ip6_fl_gc(unsigned long dummy) if (sched) { mod_timer(&ip6_fl_gc_timer, sched); } - write_unlock(&ip6_fl_lock); + spin_unlock(&ip6_fl_lock); } static void __net_exit ip6_fl_purge(struct net *net) { int i; - write_lock(&ip6_fl_lock); + spin_lock(&ip6_fl_lock); for (i = 0; i <= FL_HASH_MASK; i++) { struct ip6_flowlabel *fl, **flp; flp = &fl_ht[i]; - while ((fl = *flp) != NULL) { + while ((fl = rcu_dereference_protected(*flp, + lockdep_is_held(&ip6_fl_lock))) != NULL) { if (net_eq(fl->fl_net, net) && atomic_read(&fl->users) == 0) { *flp = fl->next; @@ -178,7 +193,7 @@ static void __net_exit ip6_fl_purge(struct net *net) flp = &fl->next; } } - write_unlock(&ip6_fl_lock); + spin_unlock(&ip6_fl_lock); } static struct ip6_flowlabel *fl_intern(struct net *net, @@ -188,7 +203,7 @@ static struct ip6_flowlabel *fl_intern(struct net *net, fl->label = label & IPV6_FLOWLABEL_MASK; - write_lock_bh(&ip6_fl_lock); + spin_lock_bh(&ip6_fl_lock); if (label == 0) { for (;;) { fl->label = htonl(net_random())&IPV6_FLOWLABEL_MASK; @@ -210,16 +225,16 @@ static struct ip6_flowlabel *fl_intern(struct net *net, lfl = __fl_lookup(net, fl->label); if (lfl != NULL) { atomic_inc(&lfl->users); - write_unlock_bh(&ip6_fl_lock); + spin_unlock_bh(&ip6_fl_lock); return lfl; } } fl->lastuse = jiffies; fl->next = fl_ht[FL_HASH(fl->label)]; - fl_ht[FL_HASH(fl->label)] = fl; + rcu_assign_pointer(fl_ht[FL_HASH(fl->label)], fl); atomic_inc(&fl_size); - write_unlock_bh(&ip6_fl_lock); + spin_unlock_bh(&ip6_fl_lock); return NULL; } @@ -234,17 +249,17 @@ struct ip6_flowlabel * fl6_sock_lookup(struct sock *sk, __be32 label) label &= IPV6_FLOWLABEL_MASK; - read_lock_bh(&ip6_sk_fl_lock); - for (sfl=np->ipv6_fl_list; sfl; sfl = sfl->next) { + rcu_read_lock_bh(); + for_each_sk_fl_rcu(np, sfl) { struct ip6_flowlabel *fl = sfl->fl; if (fl->label == label) { fl->lastuse = jiffies; atomic_inc(&fl->users); - read_unlock_bh(&ip6_sk_fl_lock); + rcu_read_unlock_bh(); return fl; } } - read_unlock_bh(&ip6_sk_fl_lock); + rcu_read_unlock_bh(); return NULL; } @@ -255,11 +270,21 @@ void fl6_free_socklist(struct sock *sk) struct ipv6_pinfo *np = inet6_sk(sk); struct ipv6_fl_socklist *sfl; - while ((sfl = np->ipv6_fl_list) != NULL) { + if (!rcu_access_pointer(np->ipv6_fl_list)) + return; + + spin_lock_bh(&ip6_sk_fl_lock); + while ((sfl = rcu_dereference_protected(np->ipv6_fl_list, + lockdep_is_held(&ip6_sk_fl_lock))) != NULL) { np->ipv6_fl_list = sfl->next; + spin_unlock_bh(&ip6_sk_fl_lock); + fl_release(sfl->fl); - kfree(sfl); + kfree_rcu(sfl, rcu); + + spin_lock_bh(&ip6_sk_fl_lock); } + spin_unlock_bh(&ip6_sk_fl_lock); } /* Service routines */ @@ -365,8 +390,8 @@ fl_create(struct net *net, struct sock *sk, struct in6_flowlabel_req *freq, msg.msg_control = (void*)(fl->opt+1); memset(&flowi6, 0, sizeof(flowi6)); - err = datagram_send_ctl(net, sk, &msg, &flowi6, fl->opt, &junk, - &junk, &junk); + err = ip6_datagram_send_ctl(net, sk, &msg, &flowi6, fl->opt, + &junk, &junk, &junk); if (err) goto done; err = -EINVAL; @@ -424,7 +449,7 @@ static int mem_check(struct sock *sk) if (room > FL_MAX_SIZE - FL_MAX_PER_SOCK) return 0; - for (sfl = np->ipv6_fl_list; sfl; sfl = sfl->next) + for_each_sk_fl_rcu(np, sfl) count++; if (room <= 0 || @@ -467,11 +492,11 @@ static bool ipv6_opt_cmp(struct ipv6_txoptions *o1, struct ipv6_txoptions *o2) static inline void fl_link(struct ipv6_pinfo *np, struct ipv6_fl_socklist *sfl, struct ip6_flowlabel *fl) { - write_lock_bh(&ip6_sk_fl_lock); + spin_lock_bh(&ip6_sk_fl_lock); sfl->fl = fl; sfl->next = np->ipv6_fl_list; - np->ipv6_fl_list = sfl; - write_unlock_bh(&ip6_sk_fl_lock); + rcu_assign_pointer(np->ipv6_fl_list, sfl); + spin_unlock_bh(&ip6_sk_fl_lock); } int ipv6_flowlabel_opt(struct sock *sk, char __user *optval, int optlen) @@ -493,31 +518,33 @@ int ipv6_flowlabel_opt(struct sock *sk, char __user *optval, int optlen) switch (freq.flr_action) { case IPV6_FL_A_PUT: - write_lock_bh(&ip6_sk_fl_lock); - for (sflp = &np->ipv6_fl_list; (sfl=*sflp)!=NULL; sflp = &sfl->next) { + spin_lock_bh(&ip6_sk_fl_lock); + for (sflp = &np->ipv6_fl_list; + (sfl = rcu_dereference(*sflp))!=NULL; + sflp = &sfl->next) { if (sfl->fl->label == freq.flr_label) { if (freq.flr_label == (np->flow_label&IPV6_FLOWLABEL_MASK)) np->flow_label &= ~IPV6_FLOWLABEL_MASK; - *sflp = sfl->next; - write_unlock_bh(&ip6_sk_fl_lock); + *sflp = rcu_dereference(sfl->next); + spin_unlock_bh(&ip6_sk_fl_lock); fl_release(sfl->fl); - kfree(sfl); + kfree_rcu(sfl, rcu); return 0; } } - write_unlock_bh(&ip6_sk_fl_lock); + spin_unlock_bh(&ip6_sk_fl_lock); return -ESRCH; case IPV6_FL_A_RENEW: - read_lock_bh(&ip6_sk_fl_lock); - for (sfl = np->ipv6_fl_list; sfl; sfl = sfl->next) { + rcu_read_lock_bh(); + for_each_sk_fl_rcu(np, sfl) { if (sfl->fl->label == freq.flr_label) { err = fl6_renew(sfl->fl, freq.flr_linger, freq.flr_expires); - read_unlock_bh(&ip6_sk_fl_lock); + rcu_read_unlock_bh(); return err; } } - read_unlock_bh(&ip6_sk_fl_lock); + rcu_read_unlock_bh(); if (freq.flr_share == IPV6_FL_S_NONE && ns_capable(net->user_ns, CAP_NET_ADMIN)) { @@ -541,11 +568,11 @@ int ipv6_flowlabel_opt(struct sock *sk, char __user *optval, int optlen) if (freq.flr_label) { err = -EEXIST; - read_lock_bh(&ip6_sk_fl_lock); - for (sfl = np->ipv6_fl_list; sfl; sfl = sfl->next) { + rcu_read_lock_bh(); + for_each_sk_fl_rcu(np, sfl) { if (sfl->fl->label == freq.flr_label) { if (freq.flr_flags&IPV6_FL_F_EXCL) { - read_unlock_bh(&ip6_sk_fl_lock); + rcu_read_unlock_bh(); goto done; } fl1 = sfl->fl; @@ -553,7 +580,7 @@ int ipv6_flowlabel_opt(struct sock *sk, char __user *optval, int optlen) break; } } - read_unlock_bh(&ip6_sk_fl_lock); + rcu_read_unlock_bh(); if (fl1 == NULL) fl1 = fl_lookup(net, freq.flr_label); @@ -641,13 +668,13 @@ static struct ip6_flowlabel *ip6fl_get_first(struct seq_file *seq) struct net *net = seq_file_net(seq); for (state->bucket = 0; state->bucket <= FL_HASH_MASK; ++state->bucket) { - fl = fl_ht[state->bucket]; - - while (fl && !net_eq(fl->fl_net, net)) - fl = fl->next; - if (fl) - break; + for_each_fl_rcu(state->bucket, fl) { + if (net_eq(fl->fl_net, net)) + goto out; + } } + fl = NULL; +out: return fl; } @@ -656,18 +683,22 @@ static struct ip6_flowlabel *ip6fl_get_next(struct seq_file *seq, struct ip6_flo struct ip6fl_iter_state *state = ip6fl_seq_private(seq); struct net *net = seq_file_net(seq); - fl = fl->next; + for_each_fl_continue_rcu(fl) { + if (net_eq(fl->fl_net, net)) + goto out; + } + try_again: - while (fl && !net_eq(fl->fl_net, net)) - fl = fl->next; - - while (!fl) { - if (++state->bucket <= FL_HASH_MASK) { - fl = fl_ht[state->bucket]; - goto try_again; - } else - break; + if (++state->bucket <= FL_HASH_MASK) { + for_each_fl_rcu(state->bucket, fl) { + if (net_eq(fl->fl_net, net)) + goto out; + } + goto try_again; } + fl = NULL; + +out: return fl; } @@ -681,9 +712,9 @@ static struct ip6_flowlabel *ip6fl_get_idx(struct seq_file *seq, loff_t pos) } static void *ip6fl_seq_start(struct seq_file *seq, loff_t *pos) - __acquires(ip6_fl_lock) + __acquires(RCU) { - read_lock_bh(&ip6_fl_lock); + rcu_read_lock_bh(); return *pos ? ip6fl_get_idx(seq, *pos - 1) : SEQ_START_TOKEN; } @@ -700,9 +731,9 @@ static void *ip6fl_seq_next(struct seq_file *seq, void *v, loff_t *pos) } static void ip6fl_seq_stop(struct seq_file *seq, void *v) - __releases(ip6_fl_lock) + __releases(RCU) { - read_unlock_bh(&ip6_fl_lock); + rcu_read_unlock_bh(); } static int ip6fl_seq_show(struct seq_file *seq, void *v) diff --git a/net/ipv6/ip6_gre.c b/net/ipv6/ip6_gre.c index 867466c96aac..e4efffe2522e 100644 --- a/net/ipv6/ip6_gre.c +++ b/net/ipv6/ip6_gre.c @@ -758,8 +758,6 @@ static netdev_tx_t ip6gre_xmit2(struct sk_buff *skb, skb_dst_set_noref(skb, dst); } - skb->transport_header = skb->network_header; - proto = NEXTHDR_GRE; if (encap_limit >= 0) { init_tel_txopt(&opt, encap_limit); @@ -768,14 +766,13 @@ static netdev_tx_t ip6gre_xmit2(struct sk_buff *skb, skb_push(skb, gre_hlen); skb_reset_network_header(skb); + skb_set_transport_header(skb, sizeof(*ipv6h)); /* * Push down and install the IP header. */ ipv6h = ipv6_hdr(skb); - *(__be32 *)ipv6h = fl6->flowlabel | htonl(0x60000000); - dsfield = INET_ECN_encapsulate(0, dsfield); - ipv6_change_dsfield(ipv6h, ~INET_ECN_MASK, dsfield); + ip6_flow_hdr(ipv6h, INET_ECN_encapsulate(0, dsfield), fl6->flowlabel); ipv6h->hop_limit = tunnel->parms.hop_limit; ipv6h->nexthdr = proto; ipv6h->saddr = fl6->saddr; @@ -961,7 +958,7 @@ static netdev_tx_t ip6gre_tunnel_xmit(struct sk_buff *skb, int ret; if (!ip6_tnl_xmit_ctl(t)) - return -1; + goto tx_err; switch (skb->protocol) { case htons(ETH_P_IP): @@ -1241,7 +1238,7 @@ static int ip6gre_header(struct sk_buff *skb, struct net_device *dev, struct ipv6hdr *ipv6h = (struct ipv6hdr *)skb_push(skb, t->hlen); __be16 *p = (__be16 *)(ipv6h+1); - *(__be32 *)ipv6h = t->fl.u.ip6.flowlabel | htonl(0x60000000); + ip6_flow_hdr(ipv6h, 0, t->fl.u.ip6.flowlabel); ipv6h->hop_limit = t->parms.hop_limit; ipv6h->nexthdr = NEXTHDR_GRE; ipv6h->saddr = t->parms.laddr; diff --git a/net/ipv6/ip6_input.c b/net/ipv6/ip6_input.c index a52d864d562b..5b10414e619e 100644 --- a/net/ipv6/ip6_input.c +++ b/net/ipv6/ip6_input.c @@ -118,6 +118,15 @@ int ipv6_rcv(struct sk_buff *skb, struct net_device *dev, struct packet_type *pt ipv6_addr_loopback(&hdr->daddr)) goto err; + /* RFC4291 2.7 + * Nodes must not originate a packet to a multicast address whose scope + * field contains the reserved value 0; if such a packet is received, it + * must be silently dropped. + */ + if (ipv6_addr_is_multicast(&hdr->daddr) && + IPV6_ADDR_MC_SCOPE(&hdr->daddr) == 0) + goto err; + /* * RFC4291 2.7 * Multicast addresses must not be used as source addresses in IPv6 @@ -212,7 +221,7 @@ resubmit: if (ipv6_addr_is_multicast(&hdr->daddr) && !ipv6_chk_mcast_addr(skb->dev, &hdr->daddr, &hdr->saddr) && - !ipv6_is_mld(skb, nexthdr)) + !ipv6_is_mld(skb, nexthdr, skb_network_header_len(skb))) goto discard; } if (!(ipprot->flags & INET6_PROTO_NOPOLICY) && @@ -280,10 +289,8 @@ int ip6_mc_input(struct sk_buff *skb) struct inet6_skb_parm *opt = IP6CB(skb); /* Check for MLD */ - if (unlikely(opt->ra)) { + if (unlikely(opt->flags & IP6SKB_ROUTERALERT)) { /* Check if this is a mld message */ - u8 *ptr = skb_network_header(skb) + opt->ra; - struct icmp6hdr *icmp6; u8 nexthdr = hdr->nexthdr; __be16 frag_off; int offset; @@ -291,7 +298,7 @@ int ip6_mc_input(struct sk_buff *skb) /* Check if the value of Router Alert * is for MLD (0x0000). */ - if ((ptr[2] | ptr[3]) == 0) { + if (opt->ra == htons(IPV6_OPT_ROUTERALERT_MLD)) { deliver = false; if (!ipv6_ext_hdr(nexthdr)) { @@ -303,24 +310,10 @@ int ip6_mc_input(struct sk_buff *skb) if (offset < 0) goto out; - if (nexthdr != IPPROTO_ICMPV6) + if (!ipv6_is_mld(skb, nexthdr, offset)) goto out; - if (!pskb_may_pull(skb, (skb_network_header(skb) + - offset + 1 - skb->data))) - goto out; - - icmp6 = (struct icmp6hdr *)(skb_network_header(skb) + offset); - - switch (icmp6->icmp6_type) { - case ICMPV6_MGM_QUERY: - case ICMPV6_MGM_REPORT: - case ICMPV6_MGM_REDUCTION: - case ICMPV6_MLD2_REPORT: - deliver = true; - break; - } - goto out; + deliver = true; } /* unknown RA - process it normally */ } diff --git a/net/ipv6/ip6_offload.c b/net/ipv6/ip6_offload.c index f26f0da7f095..8234c1dcdf72 100644 --- a/net/ipv6/ip6_offload.c +++ b/net/ipv6/ip6_offload.c @@ -99,6 +99,7 @@ static struct sk_buff *ipv6_gso_segment(struct sk_buff *skb, ~(SKB_GSO_UDP | SKB_GSO_DODGY | SKB_GSO_TCP_ECN | + SKB_GSO_GRE | SKB_GSO_TCPV6 | 0))) goto out; diff --git a/net/ipv6/ip6_output.c b/net/ipv6/ip6_output.c index 5552d13ae92f..155eccfa7760 100644 --- a/net/ipv6/ip6_output.c +++ b/net/ipv6/ip6_output.c @@ -56,8 +56,6 @@ #include <net/checksum.h> #include <linux/mroute6.h> -int ip6_fragment(struct sk_buff *skb, int (*output)(struct sk_buff *)); - int __ip6_local_out(struct sk_buff *skb) { int len; @@ -88,7 +86,8 @@ static int ip6_finish_output2(struct sk_buff *skb) struct dst_entry *dst = skb_dst(skb); struct net_device *dev = dst->dev; struct neighbour *neigh; - struct rt6_info *rt; + struct in6_addr *nexthop; + int ret; skb->protocol = htons(ETH_P_IPV6); skb->dev = dev; @@ -121,12 +120,26 @@ static int ip6_finish_output2(struct sk_buff *skb) IP6_UPD_PO_STATS(dev_net(dev), idev, IPSTATS_MIB_OUTMCAST, skb->len); + + if (IPV6_ADDR_MC_SCOPE(&ipv6_hdr(skb)->daddr) <= + IPV6_ADDR_SCOPE_NODELOCAL && + !(dev->flags & IFF_LOOPBACK)) { + kfree_skb(skb); + return 0; + } } - rt = (struct rt6_info *) dst; - neigh = rt->n; - if (neigh) - return dst_neigh_output(dst, neigh, skb); + rcu_read_lock_bh(); + nexthop = rt6_nexthop((struct rt6_info *)dst, &ipv6_hdr(skb)->daddr); + neigh = __ipv6_neigh_lookup_noref(dst->dev, nexthop); + if (unlikely(!neigh)) + neigh = __neigh_create(&nd_tbl, nexthop, dst->dev, false); + if (!IS_ERR(neigh)) { + ret = dst_neigh_output(dst, neigh, skb); + rcu_read_unlock_bh(); + return ret; + } + rcu_read_unlock_bh(); IP6_INC_STATS_BH(dev_net(dst->dev), ip6_dst_idev(dst), IPSTATS_MIB_OUTNOROUTES); @@ -216,7 +229,7 @@ int ip6_xmit(struct sock *sk, struct sk_buff *skb, struct flowi6 *fl6, if (hlimit < 0) hlimit = ip6_dst_hoplimit(dst); - *(__be32 *)hdr = htonl(0x60000000 | (tclass << 20)) | fl6->flowlabel; + ip6_flow_hdr(hdr, tclass, fl6->flowlabel); hdr->payload_len = htons(seg_len); hdr->nexthdr = proto; @@ -236,9 +249,8 @@ int ip6_xmit(struct sock *sk, struct sk_buff *skb, struct flowi6 *fl6, dst->dev, dst_output); } - net_dbg_ratelimited("IPv6: sending pkt_too_big to self\n"); skb->dev = dst->dev; - icmpv6_send(skb, ICMPV6_PKT_TOOBIG, 0, mtu); + ipv6_local_error(sk, EMSGSIZE, fl6, mtu); IP6_INC_STATS(net, ip6_dst_idev(skb_dst(skb)), IPSTATS_MIB_FRAGFAILS); kfree_skb(skb); return -EMSGSIZE; @@ -246,39 +258,6 @@ int ip6_xmit(struct sock *sk, struct sk_buff *skb, struct flowi6 *fl6, EXPORT_SYMBOL(ip6_xmit); -/* - * To avoid extra problems ND packets are send through this - * routine. It's code duplication but I really want to avoid - * extra checks since ipv6_build_header is used by TCP (which - * is for us performance critical) - */ - -int ip6_nd_hdr(struct sock *sk, struct sk_buff *skb, struct net_device *dev, - const struct in6_addr *saddr, const struct in6_addr *daddr, - int proto, int len) -{ - struct ipv6_pinfo *np = inet6_sk(sk); - struct ipv6hdr *hdr; - - skb->protocol = htons(ETH_P_IPV6); - skb->dev = dev; - - skb_reset_network_header(skb); - skb_put(skb, sizeof(struct ipv6hdr)); - hdr = ipv6_hdr(skb); - - *(__be32*)hdr = htonl(0x60000000); - - hdr->payload_len = htons(len); - hdr->nexthdr = proto; - hdr->hop_limit = np->hop_limit; - - hdr->saddr = *saddr; - hdr->daddr = *daddr; - - return 0; -} - static int ip6_call_ra_chain(struct sk_buff *skb, int sel) { struct ip6_ra_chain *ra; @@ -913,8 +892,12 @@ static int ip6_dst_lookup_tail(struct sock *sk, * dst entry of the nexthop router */ rt = (struct rt6_info *) *dst; - n = rt->n; - if (n && !(n->nud_state & NUD_VALID)) { + rcu_read_lock_bh(); + n = __ipv6_neigh_lookup_noref(rt->dst.dev, rt6_nexthop(rt, &fl6->daddr)); + err = n && !(n->nud_state & NUD_VALID) ? -EINVAL : 0; + rcu_read_unlock_bh(); + + if (err) { struct inet6_ifaddr *ifp; struct flowi6 fl_gw6; int redirect; @@ -1213,10 +1196,10 @@ int ip6_append_data(struct sock *sk, int getfrag(void *from, char *to, if (dst_allfrag(rt->dst.path)) cork->flags |= IPCORK_ALLFRAG; cork->length = 0; - exthdrlen = (opt ? opt->opt_flen : 0) - rt->rt6i_nfheader_len; + exthdrlen = (opt ? opt->opt_flen : 0); length += exthdrlen; transhdrlen += exthdrlen; - dst_exthdrlen = rt->dst.header_len; + dst_exthdrlen = rt->dst.header_len - rt->rt6i_nfheader_len; } else { rt = (struct rt6_info *)cork->dst; fl6 = &inet->cork.fl.u.ip6; @@ -1548,9 +1531,7 @@ int ip6_push_pending_frames(struct sock *sk) skb_reset_network_header(skb); hdr = ipv6_hdr(skb); - *(__be32*)hdr = fl6->flowlabel | - htonl(0x60000000 | ((int)np->cork.tclass << 20)); - + ip6_flow_hdr(hdr, np->cork.tclass, fl6->flowlabel); hdr->hop_limit = np->cork.hop_limit; hdr->nexthdr = proto; hdr->saddr = fl6->saddr; diff --git a/net/ipv6/ip6_tunnel.c b/net/ipv6/ip6_tunnel.c index a14f28b280f5..fff83cbc197f 100644 --- a/net/ipv6/ip6_tunnel.c +++ b/net/ipv6/ip6_tunnel.c @@ -1030,9 +1030,7 @@ static int ip6_tnl_xmit2(struct sk_buff *skb, skb_push(skb, sizeof(struct ipv6hdr)); skb_reset_network_header(skb); ipv6h = ipv6_hdr(skb); - *(__be32*)ipv6h = fl6->flowlabel | htonl(0x60000000); - dsfield = INET_ECN_encapsulate(0, dsfield); - ipv6_change_dsfield(ipv6h, ~INET_ECN_MASK, dsfield); + ip6_flow_hdr(ipv6h, INET_ECN_encapsulate(0, dsfield), fl6->flowlabel); ipv6h->hop_limit = t->parms.hop_limit; ipv6h->nexthdr = proto; ipv6h->saddr = fl6->saddr; diff --git a/net/ipv6/ip6mr.c b/net/ipv6/ip6mr.c index 26dcdec9e3a5..351ce98e90d9 100644 --- a/net/ipv6/ip6mr.c +++ b/net/ipv6/ip6mr.c @@ -1017,6 +1017,50 @@ static struct mfc6_cache *ip6mr_cache_find(struct mr6_table *mrt, return NULL; } +/* Look for a (*,*,oif) entry */ +static struct mfc6_cache *ip6mr_cache_find_any_parent(struct mr6_table *mrt, + mifi_t mifi) +{ + int line = MFC6_HASH(&in6addr_any, &in6addr_any); + struct mfc6_cache *c; + + list_for_each_entry(c, &mrt->mfc6_cache_array[line], list) + if (ipv6_addr_any(&c->mf6c_origin) && + ipv6_addr_any(&c->mf6c_mcastgrp) && + (c->mfc_un.res.ttls[mifi] < 255)) + return c; + + return NULL; +} + +/* Look for a (*,G) entry */ +static struct mfc6_cache *ip6mr_cache_find_any(struct mr6_table *mrt, + struct in6_addr *mcastgrp, + mifi_t mifi) +{ + int line = MFC6_HASH(mcastgrp, &in6addr_any); + struct mfc6_cache *c, *proxy; + + if (ipv6_addr_any(mcastgrp)) + goto skip; + + list_for_each_entry(c, &mrt->mfc6_cache_array[line], list) + if (ipv6_addr_any(&c->mf6c_origin) && + ipv6_addr_equal(&c->mf6c_mcastgrp, mcastgrp)) { + if (c->mfc_un.res.ttls[mifi] < 255) + return c; + + /* It's ok if the mifi is part of the static tree */ + proxy = ip6mr_cache_find_any_parent(mrt, + c->mf6c_parent); + if (proxy && proxy->mfc_un.res.ttls[mifi] < 255) + return c; + } + +skip: + return ip6mr_cache_find_any_parent(mrt, mifi); +} + /* * Allocate a multicast cache entry */ @@ -1247,7 +1291,8 @@ ip6mr_cache_unresolved(struct mr6_table *mrt, mifi_t mifi, struct sk_buff *skb) * MFC6 cache manipulation by user space */ -static int ip6mr_mfc_delete(struct mr6_table *mrt, struct mf6cctl *mfc) +static int ip6mr_mfc_delete(struct mr6_table *mrt, struct mf6cctl *mfc, + int parent) { int line; struct mfc6_cache *c, *next; @@ -1256,7 +1301,9 @@ static int ip6mr_mfc_delete(struct mr6_table *mrt, struct mf6cctl *mfc) list_for_each_entry_safe(c, next, &mrt->mfc6_cache_array[line], list) { if (ipv6_addr_equal(&c->mf6c_origin, &mfc->mf6cc_origin.sin6_addr) && - ipv6_addr_equal(&c->mf6c_mcastgrp, &mfc->mf6cc_mcastgrp.sin6_addr)) { + ipv6_addr_equal(&c->mf6c_mcastgrp, + &mfc->mf6cc_mcastgrp.sin6_addr) && + (parent == -1 || parent == c->mf6c_parent)) { write_lock_bh(&mrt_lock); list_del(&c->list); write_unlock_bh(&mrt_lock); @@ -1391,7 +1438,7 @@ void ip6_mr_cleanup(void) } static int ip6mr_mfc_add(struct net *net, struct mr6_table *mrt, - struct mf6cctl *mfc, int mrtsock) + struct mf6cctl *mfc, int mrtsock, int parent) { bool found = false; int line; @@ -1413,7 +1460,9 @@ static int ip6mr_mfc_add(struct net *net, struct mr6_table *mrt, list_for_each_entry(c, &mrt->mfc6_cache_array[line], list) { if (ipv6_addr_equal(&c->mf6c_origin, &mfc->mf6cc_origin.sin6_addr) && - ipv6_addr_equal(&c->mf6c_mcastgrp, &mfc->mf6cc_mcastgrp.sin6_addr)) { + ipv6_addr_equal(&c->mf6c_mcastgrp, + &mfc->mf6cc_mcastgrp.sin6_addr) && + (parent == -1 || parent == mfc->mf6cc_parent)) { found = true; break; } @@ -1430,7 +1479,8 @@ static int ip6mr_mfc_add(struct net *net, struct mr6_table *mrt, return 0; } - if (!ipv6_addr_is_multicast(&mfc->mf6cc_mcastgrp.sin6_addr)) + if (!ipv6_addr_any(&mfc->mf6cc_mcastgrp.sin6_addr) && + !ipv6_addr_is_multicast(&mfc->mf6cc_mcastgrp.sin6_addr)) return -EINVAL; c = ip6mr_cache_alloc(); @@ -1596,7 +1646,7 @@ struct sock *mroute6_socket(struct net *net, struct sk_buff *skb) int ip6_mroute_setsockopt(struct sock *sk, int optname, char __user *optval, unsigned int optlen) { - int ret; + int ret, parent = 0; struct mif6ctl vif; struct mf6cctl mfc; mifi_t mifi; @@ -1653,15 +1703,21 @@ int ip6_mroute_setsockopt(struct sock *sk, int optname, char __user *optval, uns */ case MRT6_ADD_MFC: case MRT6_DEL_MFC: + parent = -1; + case MRT6_ADD_MFC_PROXY: + case MRT6_DEL_MFC_PROXY: if (optlen < sizeof(mfc)) return -EINVAL; if (copy_from_user(&mfc, optval, sizeof(mfc))) return -EFAULT; + if (parent == 0) + parent = mfc.mf6cc_parent; rtnl_lock(); - if (optname == MRT6_DEL_MFC) - ret = ip6mr_mfc_delete(mrt, &mfc); + if (optname == MRT6_DEL_MFC || optname == MRT6_DEL_MFC_PROXY) + ret = ip6mr_mfc_delete(mrt, &mfc, parent); else - ret = ip6mr_mfc_add(net, mrt, &mfc, sk == mrt->mroute6_sk); + ret = ip6mr_mfc_add(net, mrt, &mfc, + sk == mrt->mroute6_sk, parent); rtnl_unlock(); return ret; @@ -1710,6 +1766,9 @@ int ip6_mroute_setsockopt(struct sock *sk, int optname, char __user *optval, uns return -EINVAL; if (get_user(v, (u32 __user *)optval)) return -EFAULT; + /* "pim6reg%u" should not exceed 16 bytes (IFNAMSIZ) */ + if (v != RT_TABLE_DEFAULT && v >= 100000000) + return -EINVAL; if (sk == mrt->mroute6_sk) return -EBUSY; @@ -2015,19 +2074,29 @@ static int ip6_mr_forward(struct net *net, struct mr6_table *mrt, { int psend = -1; int vif, ct; + int true_vifi = ip6mr_find_vif(mrt, skb->dev); vif = cache->mf6c_parent; cache->mfc_un.res.pkt++; cache->mfc_un.res.bytes += skb->len; + if (ipv6_addr_any(&cache->mf6c_origin) && true_vifi >= 0) { + struct mfc6_cache *cache_proxy; + + /* For an (*,G) entry, we only check that the incomming + * interface is part of the static tree. + */ + cache_proxy = ip6mr_cache_find_any_parent(mrt, vif); + if (cache_proxy && + cache_proxy->mfc_un.res.ttls[true_vifi] < 255) + goto forward; + } + /* * Wrong interface: drop packet and (maybe) send PIM assert. */ if (mrt->vif6_table[vif].dev != skb->dev) { - int true_vifi; - cache->mfc_un.res.wrong_if++; - true_vifi = ip6mr_find_vif(mrt, skb->dev); if (true_vifi >= 0 && mrt->mroute_do_assert && /* pimsm uses asserts, when switching from RPT to SPT, @@ -2045,14 +2114,32 @@ static int ip6_mr_forward(struct net *net, struct mr6_table *mrt, goto dont_forward; } +forward: mrt->vif6_table[vif].pkt_in++; mrt->vif6_table[vif].bytes_in += skb->len; /* * Forward the frame */ + if (ipv6_addr_any(&cache->mf6c_origin) && + ipv6_addr_any(&cache->mf6c_mcastgrp)) { + if (true_vifi >= 0 && + true_vifi != cache->mf6c_parent && + ipv6_hdr(skb)->hop_limit > + cache->mfc_un.res.ttls[cache->mf6c_parent]) { + /* It's an (*,*) entry and the packet is not coming from + * the upstream: forward the packet to the upstream + * only. + */ + psend = cache->mf6c_parent; + goto last_forward; + } + goto dont_forward; + } for (ct = cache->mfc_un.res.maxvif - 1; ct >= cache->mfc_un.res.minvif; ct--) { - if (ipv6_hdr(skb)->hop_limit > cache->mfc_un.res.ttls[ct]) { + /* For (*,G) entry, don't forward to the incoming interface */ + if ((!ipv6_addr_any(&cache->mf6c_origin) || ct != true_vifi) && + ipv6_hdr(skb)->hop_limit > cache->mfc_un.res.ttls[ct]) { if (psend != -1) { struct sk_buff *skb2 = skb_clone(skb, GFP_ATOMIC); if (skb2) @@ -2061,6 +2148,7 @@ static int ip6_mr_forward(struct net *net, struct mr6_table *mrt, psend = ct; } } +last_forward: if (psend != -1) { ip6mr_forward2(net, mrt, skb, cache, psend); return 0; @@ -2096,6 +2184,14 @@ int ip6_mr_input(struct sk_buff *skb) read_lock(&mrt_lock); cache = ip6mr_cache_find(mrt, &ipv6_hdr(skb)->saddr, &ipv6_hdr(skb)->daddr); + if (cache == NULL) { + int vif = ip6mr_find_vif(mrt, skb->dev); + + if (vif >= 0) + cache = ip6mr_cache_find_any(mrt, + &ipv6_hdr(skb)->daddr, + vif); + } /* * No usable cache entry @@ -2183,6 +2279,13 @@ int ip6mr_get_route(struct net *net, read_lock(&mrt_lock); cache = ip6mr_cache_find(mrt, &rt->rt6i_src.addr, &rt->rt6i_dst.addr); + if (!cache && skb->dev) { + int vif = ip6mr_find_vif(mrt, skb->dev); + + if (vif >= 0) + cache = ip6mr_cache_find_any(mrt, &rt->rt6i_dst.addr, + vif); + } if (!cache) { struct sk_buff *skb2; diff --git a/net/ipv6/ipv6_sockglue.c b/net/ipv6/ipv6_sockglue.c index ee94d31c9d4d..d1e2e8ef29c5 100644 --- a/net/ipv6/ipv6_sockglue.c +++ b/net/ipv6/ipv6_sockglue.c @@ -476,8 +476,8 @@ sticky_done: msg.msg_controllen = optlen; msg.msg_control = (void*)(opt+1); - retv = datagram_send_ctl(net, sk, &msg, &fl6, opt, &junk, &junk, - &junk); + retv = ip6_datagram_send_ctl(net, sk, &msg, &fl6, opt, &junk, + &junk, &junk); if (retv) goto done; update: @@ -1002,7 +1002,7 @@ static int do_ipv6_getsockopt(struct sock *sk, int level, int optname, release_sock(sk); if (skb) { - int err = datagram_recv_ctl(sk, &msg, skb); + int err = ip6_datagram_recv_ctl(sk, &msg, skb); kfree_skb(skb); if (err) return err; diff --git a/net/ipv6/mcast.c b/net/ipv6/mcast.c index 28dfa5f3801f..3a2849f660ca 100644 --- a/net/ipv6/mcast.c +++ b/net/ipv6/mcast.c @@ -376,8 +376,7 @@ int ip6_mc_source(int add, int omode, struct sock *sk, goto done; /* err = -EADDRNOTAVAIL */ rv = !0; for (i=0; i<psl->sl_count; i++) { - rv = memcmp(&psl->sl_addr[i], source, - sizeof(struct in6_addr)); + rv = !ipv6_addr_equal(&psl->sl_addr[i], source); if (rv == 0) break; } @@ -427,12 +426,10 @@ int ip6_mc_source(int add, int omode, struct sock *sk, } rv = 1; /* > 0 for insert logic below if sl_count is 0 */ for (i=0; i<psl->sl_count; i++) { - rv = memcmp(&psl->sl_addr[i], source, sizeof(struct in6_addr)); - if (rv == 0) - break; + rv = !ipv6_addr_equal(&psl->sl_addr[i], source); + if (rv == 0) /* There is an error in the address. */ + goto done; } - if (rv == 0) /* address already there is an error */ - goto done; for (j=psl->sl_count-1; j>=i; j--) psl->sl_addr[j+1] = psl->sl_addr[j]; psl->sl_addr[i] = *source; @@ -664,6 +661,10 @@ static void igmp6_group_added(struct ifmcaddr6 *mc) struct net_device *dev = mc->idev->dev; char buf[MAX_ADDR_LEN]; + if (IPV6_ADDR_MC_SCOPE(&mc->mca_addr) < + IPV6_ADDR_SCOPE_LINKLOCAL) + return; + spin_lock_bh(&mc->mca_lock); if (!(mc->mca_flags&MAF_LOADED)) { mc->mca_flags |= MAF_LOADED; @@ -690,6 +691,10 @@ static void igmp6_group_dropped(struct ifmcaddr6 *mc) struct net_device *dev = mc->idev->dev; char buf[MAX_ADDR_LEN]; + if (IPV6_ADDR_MC_SCOPE(&mc->mca_addr) < + IPV6_ADDR_SCOPE_LINKLOCAL) + return; + spin_lock_bh(&mc->mca_lock); if (mc->mca_flags&MAF_LOADED) { mc->mca_flags &= ~MAF_LOADED; @@ -935,33 +940,6 @@ int ipv6_dev_mc_dec(struct net_device *dev, const struct in6_addr *addr) } /* - * identify MLD packets for MLD filter exceptions - */ -bool ipv6_is_mld(struct sk_buff *skb, int nexthdr) -{ - struct icmp6hdr *pic; - - if (nexthdr != IPPROTO_ICMPV6) - return false; - - if (!pskb_may_pull(skb, sizeof(struct icmp6hdr))) - return false; - - pic = icmp6_hdr(skb); - - switch (pic->icmp6_type) { - case ICMPV6_MGM_QUERY: - case ICMPV6_MGM_REPORT: - case ICMPV6_MGM_REDUCTION: - case ICMPV6_MLD2_REPORT: - return true; - default: - break; - } - return false; -} - -/* * check if the interface/address pair is valid */ bool ipv6_chk_mcast_addr(struct net_device *dev, const struct in6_addr *group, @@ -1340,6 +1318,31 @@ mld_scount(struct ifmcaddr6 *pmc, int type, int gdeleted, int sdeleted) return scount; } +static void ip6_mc_hdr(struct sock *sk, struct sk_buff *skb, + struct net_device *dev, + const struct in6_addr *saddr, + const struct in6_addr *daddr, + int proto, int len) +{ + struct ipv6hdr *hdr; + + skb->protocol = htons(ETH_P_IPV6); + skb->dev = dev; + + skb_reset_network_header(skb); + skb_put(skb, sizeof(struct ipv6hdr)); + hdr = ipv6_hdr(skb); + + ip6_flow_hdr(hdr, 0, 0); + + hdr->payload_len = htons(len); + hdr->nexthdr = proto; + hdr->hop_limit = inet6_sk(sk)->hop_limit; + + hdr->saddr = *saddr; + hdr->daddr = *daddr; +} + static struct sk_buff *mld_newpack(struct net_device *dev, int size) { struct net *net = dev_net(dev); @@ -1375,7 +1378,7 @@ static struct sk_buff *mld_newpack(struct net_device *dev, int size) } else saddr = &addr_buf; - ip6_nd_hdr(sk, skb, dev, saddr, &mld2_all_mcr, NEXTHDR_HOP, 0); + ip6_mc_hdr(sk, skb, dev, saddr, &mld2_all_mcr, NEXTHDR_HOP, 0); memcpy(skb_put(skb, sizeof(ra)), ra, sizeof(ra)); @@ -1418,7 +1421,7 @@ static void mld_sendpack(struct sk_buff *skb) icmpv6_flow_init(net->ipv6.igmp_sk, &fl6, ICMPV6_MLD2_REPORT, &ipv6_hdr(skb)->saddr, &ipv6_hdr(skb)->daddr, skb->dev->ifindex); - dst = icmp6_dst_alloc(skb->dev, NULL, &fl6); + dst = icmp6_dst_alloc(skb->dev, &fl6); err = 0; if (IS_ERR(dst)) { @@ -1767,7 +1770,7 @@ static void igmp6_send(struct in6_addr *addr, struct net_device *dev, int type) } else saddr = &addr_buf; - ip6_nd_hdr(sk, skb, dev, saddr, snd_addr, NEXTHDR_HOP, payload_len); + ip6_mc_hdr(sk, skb, dev, saddr, snd_addr, NEXTHDR_HOP, payload_len); memcpy(skb_put(skb, sizeof(ra)), ra, sizeof(ra)); @@ -1786,7 +1789,7 @@ static void igmp6_send(struct in6_addr *addr, struct net_device *dev, int type) icmpv6_flow_init(sk, &fl6, type, &ipv6_hdr(skb)->saddr, &ipv6_hdr(skb)->daddr, skb->dev->ifindex); - dst = icmp6_dst_alloc(skb->dev, NULL, &fl6); + dst = icmp6_dst_alloc(skb->dev, &fl6); if (IS_ERR(dst)) { err = PTR_ERR(dst); goto err_out; diff --git a/net/ipv6/ndisc.c b/net/ipv6/ndisc.c index 6574175795df..76ef4353d518 100644 --- a/net/ipv6/ndisc.c +++ b/net/ipv6/ndisc.c @@ -143,16 +143,12 @@ struct neigh_table nd_tbl = { .gc_thresh3 = 1024, }; -static inline int ndisc_opt_addr_space(struct net_device *dev) +static void ndisc_fill_addr_option(struct sk_buff *skb, int type, void *data) { - return NDISC_OPT_SPACE(dev->addr_len + ndisc_addr_option_pad(dev->type)); -} - -static u8 *ndisc_fill_addr_option(u8 *opt, int type, void *data, int data_len, - unsigned short addr_type) -{ - int pad = ndisc_addr_option_pad(addr_type); - int space = NDISC_OPT_SPACE(data_len + pad); + int pad = ndisc_addr_option_pad(skb->dev->type); + int data_len = skb->dev->addr_len; + int space = ndisc_opt_addr_space(skb->dev); + u8 *opt = skb_put(skb, space); opt[0] = type; opt[1] = space>>3; @@ -166,7 +162,6 @@ static u8 *ndisc_fill_addr_option(u8 *opt, int type, void *data, int data_len, opt += data_len; if ((space -= data_len) > 0) memset(opt, 0, space); - return opt + space; } static struct nd_opt_hdr *ndisc_next_option(struct nd_opt_hdr *cur, @@ -370,91 +365,88 @@ static void pndisc_destructor(struct pneigh_entry *n) ipv6_dev_mc_dec(dev, &maddr); } -static struct sk_buff *ndisc_build_skb(struct net_device *dev, - const struct in6_addr *daddr, - const struct in6_addr *saddr, - struct icmp6hdr *icmp6h, - const struct in6_addr *target, - int llinfo) +static struct sk_buff *ndisc_alloc_skb(struct net_device *dev, + int len) { - struct net *net = dev_net(dev); - struct sock *sk = net->ipv6.ndisc_sk; - struct sk_buff *skb; - struct icmp6hdr *hdr; int hlen = LL_RESERVED_SPACE(dev); int tlen = dev->needed_tailroom; - int len; + struct sock *sk = dev_net(dev)->ipv6.ndisc_sk; + struct sk_buff *skb; int err; - u8 *opt; - - if (!dev->addr_len) - llinfo = 0; - - len = sizeof(struct icmp6hdr) + (target ? sizeof(*target) : 0); - if (llinfo) - len += ndisc_opt_addr_space(dev); skb = sock_alloc_send_skb(sk, - (MAX_HEADER + sizeof(struct ipv6hdr) + - len + hlen + tlen), + hlen + sizeof(struct ipv6hdr) + len + tlen, 1, &err); if (!skb) { - ND_PRINTK(0, err, "ND: %s failed to allocate an skb, err=%d\n", + ND_PRINTK(0, err, "ndisc: %s failed to allocate an skb, err=%d\n", __func__, err); return NULL; } - skb_reserve(skb, hlen); - ip6_nd_hdr(sk, skb, dev, saddr, daddr, IPPROTO_ICMPV6, len); + skb->protocol = htons(ETH_P_IPV6); + skb->dev = dev; - skb->transport_header = skb->tail; - skb_put(skb, len); + skb_reserve(skb, hlen + sizeof(struct ipv6hdr)); + skb_reset_transport_header(skb); - hdr = (struct icmp6hdr *)skb_transport_header(skb); - memcpy(hdr, icmp6h, sizeof(*hdr)); + return skb; +} - opt = skb_transport_header(skb) + sizeof(struct icmp6hdr); - if (target) { - *(struct in6_addr *)opt = *target; - opt += sizeof(*target); - } +static void ip6_nd_hdr(struct sk_buff *skb, + const struct in6_addr *saddr, + const struct in6_addr *daddr, + int hop_limit, int len) +{ + struct ipv6hdr *hdr; - if (llinfo) - ndisc_fill_addr_option(opt, llinfo, dev->dev_addr, - dev->addr_len, dev->type); + skb_push(skb, sizeof(*hdr)); + skb_reset_network_header(skb); + hdr = ipv6_hdr(skb); - hdr->icmp6_cksum = csum_ipv6_magic(saddr, daddr, len, - IPPROTO_ICMPV6, - csum_partial(hdr, - len, 0)); + ip6_flow_hdr(hdr, 0, 0); - return skb; + hdr->payload_len = htons(len); + hdr->nexthdr = IPPROTO_ICMPV6; + hdr->hop_limit = hop_limit; + + hdr->saddr = *saddr; + hdr->daddr = *daddr; } -static void ndisc_send_skb(struct sk_buff *skb, struct net_device *dev, - struct neighbour *neigh, +static void ndisc_send_skb(struct sk_buff *skb, const struct in6_addr *daddr, - const struct in6_addr *saddr, - struct icmp6hdr *icmp6h) + const struct in6_addr *saddr) { - struct flowi6 fl6; - struct dst_entry *dst; - struct net *net = dev_net(dev); + struct dst_entry *dst = skb_dst(skb); + struct net *net = dev_net(skb->dev); struct sock *sk = net->ipv6.ndisc_sk; struct inet6_dev *idev; int err; + struct icmp6hdr *icmp6h = icmp6_hdr(skb); u8 type; type = icmp6h->icmp6_type; - icmpv6_flow_init(sk, &fl6, type, saddr, daddr, dev->ifindex); - dst = icmp6_dst_alloc(dev, neigh, &fl6); - if (IS_ERR(dst)) { - kfree_skb(skb); - return; + if (!dst) { + struct sock *sk = net->ipv6.ndisc_sk; + struct flowi6 fl6; + + icmpv6_flow_init(sk, &fl6, type, saddr, daddr, skb->dev->ifindex); + dst = icmp6_dst_alloc(skb->dev, &fl6); + if (IS_ERR(dst)) { + kfree_skb(skb); + return; + } + + skb_dst_set(skb, dst); } - skb_dst_set(skb, dst); + icmp6h->icmp6_cksum = csum_ipv6_magic(saddr, daddr, skb->len, + IPPROTO_ICMPV6, + csum_partial(icmp6h, + skb->len, 0)); + + ip6_nd_hdr(skb, saddr, daddr, inet6_sk(sk)->hop_limit, skb->len); rcu_read_lock(); idev = __in6_dev_get(dst->dev); @@ -470,36 +462,17 @@ static void ndisc_send_skb(struct sk_buff *skb, struct net_device *dev, rcu_read_unlock(); } -/* - * Send a Neighbour Discover packet - */ -static void __ndisc_send(struct net_device *dev, - struct neighbour *neigh, - const struct in6_addr *daddr, - const struct in6_addr *saddr, - struct icmp6hdr *icmp6h, const struct in6_addr *target, - int llinfo) -{ - struct sk_buff *skb; - - skb = ndisc_build_skb(dev, daddr, saddr, icmp6h, target, llinfo); - if (!skb) - return; - - ndisc_send_skb(skb, dev, neigh, daddr, saddr, icmp6h); -} - static void ndisc_send_na(struct net_device *dev, struct neighbour *neigh, const struct in6_addr *daddr, const struct in6_addr *solicited_addr, - int router, int solicited, int override, int inc_opt) + bool router, bool solicited, bool override, bool inc_opt) { + struct sk_buff *skb; struct in6_addr tmpaddr; struct inet6_ifaddr *ifp; const struct in6_addr *src_addr; - struct icmp6hdr icmp6h = { - .icmp6_type = NDISC_NEIGHBOUR_ADVERTISEMENT, - }; + struct nd_msg *msg; + int optlen = 0; /* for anycast or proxy, solicited_addr != src_addr */ ifp = ipv6_get_ifaddr(dev_net(dev), solicited_addr, dev, 1); @@ -517,13 +490,32 @@ static void ndisc_send_na(struct net_device *dev, struct neighbour *neigh, src_addr = &tmpaddr; } - icmp6h.icmp6_router = router; - icmp6h.icmp6_solicited = solicited; - icmp6h.icmp6_override = override; + if (!dev->addr_len) + inc_opt = 0; + if (inc_opt) + optlen += ndisc_opt_addr_space(dev); + + skb = ndisc_alloc_skb(dev, sizeof(*msg) + optlen); + if (!skb) + return; - __ndisc_send(dev, neigh, daddr, src_addr, - &icmp6h, solicited_addr, - inc_opt ? ND_OPT_TARGET_LL_ADDR : 0); + msg = (struct nd_msg *)skb_put(skb, sizeof(*msg)); + *msg = (struct nd_msg) { + .icmph = { + .icmp6_type = NDISC_NEIGHBOUR_ADVERTISEMENT, + .icmp6_router = router, + .icmp6_solicited = solicited, + .icmp6_override = override, + }, + .target = *solicited_addr, + }; + + if (inc_opt) + ndisc_fill_addr_option(skb, ND_OPT_TARGET_LL_ADDR, + dev->dev_addr); + + + ndisc_send_skb(skb, daddr, src_addr); } static void ndisc_send_unsol_na(struct net_device *dev) @@ -551,10 +543,11 @@ void ndisc_send_ns(struct net_device *dev, struct neighbour *neigh, const struct in6_addr *solicit, const struct in6_addr *daddr, const struct in6_addr *saddr) { + struct sk_buff *skb; struct in6_addr addr_buf; - struct icmp6hdr icmp6h = { - .icmp6_type = NDISC_NEIGHBOUR_SOLICITATION, - }; + int inc_opt = dev->addr_len; + int optlen = 0; + struct nd_msg *msg; if (saddr == NULL) { if (ipv6_get_lladdr(dev, &addr_buf, @@ -563,18 +556,37 @@ void ndisc_send_ns(struct net_device *dev, struct neighbour *neigh, saddr = &addr_buf; } - __ndisc_send(dev, neigh, daddr, saddr, - &icmp6h, solicit, - !ipv6_addr_any(saddr) ? ND_OPT_SOURCE_LL_ADDR : 0); + if (ipv6_addr_any(saddr)) + inc_opt = 0; + if (inc_opt) + optlen += ndisc_opt_addr_space(dev); + + skb = ndisc_alloc_skb(dev, sizeof(*msg) + optlen); + if (!skb) + return; + + msg = (struct nd_msg *)skb_put(skb, sizeof(*msg)); + *msg = (struct nd_msg) { + .icmph = { + .icmp6_type = NDISC_NEIGHBOUR_SOLICITATION, + }, + .target = *solicit, + }; + + if (inc_opt) + ndisc_fill_addr_option(skb, ND_OPT_SOURCE_LL_ADDR, + dev->dev_addr); + + ndisc_send_skb(skb, daddr, saddr); } void ndisc_send_rs(struct net_device *dev, const struct in6_addr *saddr, const struct in6_addr *daddr) { - struct icmp6hdr icmp6h = { - .icmp6_type = NDISC_ROUTER_SOLICITATION, - }; + struct sk_buff *skb; + struct rs_msg *msg; int send_sllao = dev->addr_len; + int optlen = 0; #ifdef CONFIG_IPV6_OPTIMISTIC_DAD /* @@ -598,9 +610,27 @@ void ndisc_send_rs(struct net_device *dev, const struct in6_addr *saddr, } } #endif - __ndisc_send(dev, NULL, daddr, saddr, - &icmp6h, NULL, - send_sllao ? ND_OPT_SOURCE_LL_ADDR : 0); + if (!dev->addr_len) + send_sllao = 0; + if (send_sllao) + optlen += ndisc_opt_addr_space(dev); + + skb = ndisc_alloc_skb(dev, sizeof(*msg) + optlen); + if (!skb) + return; + + msg = (struct rs_msg *)skb_put(skb, sizeof(*msg)); + *msg = (struct rs_msg) { + .icmph = { + .icmp6_type = NDISC_ROUTER_SOLICITATION, + }, + }; + + if (send_sllao) + ndisc_fill_addr_option(skb, ND_OPT_SOURCE_LL_ADDR, + dev->dev_addr); + + ndisc_send_skb(skb, daddr, saddr); } @@ -676,6 +706,11 @@ static void ndisc_recv_ns(struct sk_buff *skb) bool inc; int is_router = -1; + if (skb->len < sizeof(struct nd_msg)) { + ND_PRINTK(2, warn, "NS: packet too short\n"); + return; + } + if (ipv6_addr_is_multicast(&msg->target)) { ND_PRINTK(2, warn, "NS: multicast target address\n"); return; @@ -685,11 +720,7 @@ static void ndisc_recv_ns(struct sk_buff *skb) * RFC2461 7.1.1: * DAD has to be destined for solicited node multicast address. */ - if (dad && - !(daddr->s6_addr32[0] == htonl(0xff020000) && - daddr->s6_addr32[1] == htonl(0x00000000) && - daddr->s6_addr32[2] == htonl(0x00000001) && - daddr->s6_addr [12] == 0xff )) { + if (dad && !ipv6_addr_is_solict_mult(daddr)) { ND_PRINTK(2, warn, "NS: bad DAD packet (wrong destination)\n"); return; } @@ -780,11 +811,11 @@ static void ndisc_recv_ns(struct sk_buff *skb) } if (is_router < 0) - is_router = !!idev->cnf.forwarding; + is_router = idev->cnf.forwarding; if (dad) { ndisc_send_na(dev, NULL, &in6addr_linklocal_allnodes, &msg->target, - is_router, 0, (ifp != NULL), 1); + !!is_router, false, (ifp != NULL), true); goto out; } @@ -805,8 +836,8 @@ static void ndisc_recv_ns(struct sk_buff *skb) NEIGH_UPDATE_F_OVERRIDE); if (neigh || !dev->header_ops) { ndisc_send_na(dev, neigh, saddr, &msg->target, - is_router, - 1, (ifp != NULL && inc), inc); + !!is_router, + true, (ifp != NULL && inc), inc); if (neigh) neigh_release(neigh); } @@ -1350,25 +1381,34 @@ static void ndisc_redirect_rcv(struct sk_buff *skb) icmpv6_notify(skb, NDISC_REDIRECT, 0, 0); } +static void ndisc_fill_redirect_hdr_option(struct sk_buff *skb, + struct sk_buff *orig_skb, + int rd_len) +{ + u8 *opt = skb_put(skb, rd_len); + + memset(opt, 0, 8); + *(opt++) = ND_OPT_REDIRECT_HDR; + *(opt++) = (rd_len >> 3); + opt += 6; + + memcpy(opt, ipv6_hdr(orig_skb), rd_len - 8); +} + void ndisc_send_redirect(struct sk_buff *skb, const struct in6_addr *target) { struct net_device *dev = skb->dev; struct net *net = dev_net(dev); struct sock *sk = net->ipv6.ndisc_sk; - int len = sizeof(struct icmp6hdr) + 2 * sizeof(struct in6_addr); + int optlen = 0; struct inet_peer *peer; struct sk_buff *buff; - struct icmp6hdr *icmph; + struct rd_msg *msg; struct in6_addr saddr_buf; - struct in6_addr *addrp; struct rt6_info *rt; struct dst_entry *dst; - struct inet6_dev *idev; struct flowi6 fl6; - u8 *opt; - int hlen, tlen; int rd_len; - int err; u8 ha_buf[MAX_ADDR_LEN], *ha = NULL; bool ret; @@ -1424,7 +1464,7 @@ void ndisc_send_redirect(struct sk_buff *skb, const struct in6_addr *target) memcpy(ha_buf, neigh->ha, dev->addr_len); read_unlock_bh(&neigh->lock); ha = ha_buf; - len += ndisc_opt_addr_space(dev); + optlen += ndisc_opt_addr_space(dev); } else read_unlock_bh(&neigh->lock); @@ -1432,80 +1472,40 @@ void ndisc_send_redirect(struct sk_buff *skb, const struct in6_addr *target) } rd_len = min_t(unsigned int, - IPV6_MIN_MTU-sizeof(struct ipv6hdr)-len, skb->len + 8); + IPV6_MIN_MTU - sizeof(struct ipv6hdr) - sizeof(*msg) - optlen, + skb->len + 8); rd_len &= ~0x7; - len += rd_len; - - hlen = LL_RESERVED_SPACE(dev); - tlen = dev->needed_tailroom; - buff = sock_alloc_send_skb(sk, - (MAX_HEADER + sizeof(struct ipv6hdr) + - len + hlen + tlen), - 1, &err); - if (buff == NULL) { - ND_PRINTK(0, err, - "Redirect: %s failed to allocate an skb, err=%d\n", - __func__, err); - goto release; - } - - skb_reserve(buff, hlen); - ip6_nd_hdr(sk, buff, dev, &saddr_buf, &ipv6_hdr(skb)->saddr, - IPPROTO_ICMPV6, len); - - skb_set_transport_header(buff, skb_tail_pointer(buff) - buff->data); - skb_put(buff, len); - icmph = icmp6_hdr(buff); - - memset(icmph, 0, sizeof(struct icmp6hdr)); - icmph->icmp6_type = NDISC_REDIRECT; + optlen += rd_len; - /* - * copy target and destination addresses - */ - - addrp = (struct in6_addr *)(icmph + 1); - *addrp = *target; - addrp++; - *addrp = ipv6_hdr(skb)->daddr; + buff = ndisc_alloc_skb(dev, sizeof(*msg) + optlen); + if (!buff) + goto release; - opt = (u8*) (addrp + 1); + msg = (struct rd_msg *)skb_put(buff, sizeof(*msg)); + *msg = (struct rd_msg) { + .icmph = { + .icmp6_type = NDISC_REDIRECT, + }, + .target = *target, + .dest = ipv6_hdr(skb)->daddr, + }; /* * include target_address option */ if (ha) - opt = ndisc_fill_addr_option(opt, ND_OPT_TARGET_LL_ADDR, ha, - dev->addr_len, dev->type); + ndisc_fill_addr_option(skb, ND_OPT_TARGET_LL_ADDR, ha); /* * build redirect option and copy skb over to the new packet. */ - memset(opt, 0, 8); - *(opt++) = ND_OPT_REDIRECT_HDR; - *(opt++) = (rd_len >> 3); - opt += 6; - - memcpy(opt, ipv6_hdr(skb), rd_len - 8); - - icmph->icmp6_cksum = csum_ipv6_magic(&saddr_buf, &ipv6_hdr(skb)->saddr, - len, IPPROTO_ICMPV6, - csum_partial(icmph, len, 0)); + if (rd_len) + ndisc_fill_redirect_hdr_option(buff, skb, rd_len); skb_dst_set(buff, dst); - rcu_read_lock(); - idev = __in6_dev_get(dst->dev); - IP6_UPD_PO_STATS(net, idev, IPSTATS_MIB_OUT, skb->len); - err = NF_HOOK(NFPROTO_IPV6, NF_INET_LOCAL_OUT, buff, NULL, dst->dev, - dst_output); - if (!err) { - ICMP6MSGOUT_INC_STATS(net, idev, NDISC_REDIRECT); - ICMP6_INC_STATS(net, idev, ICMP6_MIB_OUTMSGS); - } - - rcu_read_unlock(); + ndisc_send_skb(buff, &ipv6_hdr(skb)->saddr, &saddr_buf); return; release: @@ -1522,7 +1522,7 @@ int ndisc_rcv(struct sk_buff *skb) { struct nd_msg *msg; - if (!pskb_may_pull(skb, skb->len)) + if (skb_linearize(skb)) return 0; msg = (struct nd_msg *)skb_transport_header(skb); diff --git a/net/ipv6/netfilter/ip6_tables.c b/net/ipv6/netfilter/ip6_tables.c index 125a90d6a795..341b54ade72c 100644 --- a/net/ipv6/netfilter/ip6_tables.c +++ b/net/ipv6/netfilter/ip6_tables.c @@ -1098,7 +1098,7 @@ static int get_info(struct net *net, void __user *user, #endif t = try_then_request_module(xt_find_table_lock(net, AF_INET6, name), "ip6table_%s", name); - if (t && !IS_ERR(t)) { + if (!IS_ERR_OR_NULL(t)) { struct ip6t_getinfo info; const struct xt_table_info *private = t->private; #ifdef CONFIG_COMPAT @@ -1157,7 +1157,7 @@ get_entries(struct net *net, struct ip6t_get_entries __user *uptr, } t = xt_find_table_lock(net, AF_INET6, get.name); - if (t && !IS_ERR(t)) { + if (!IS_ERR_OR_NULL(t)) { struct xt_table_info *private = t->private; duprintf("t->private->number = %u\n", private->number); if (get.size == private->size) @@ -1197,7 +1197,7 @@ __do_replace(struct net *net, const char *name, unsigned int valid_hooks, t = try_then_request_module(xt_find_table_lock(net, AF_INET6, name), "ip6table_%s", name); - if (!t || IS_ERR(t)) { + if (IS_ERR_OR_NULL(t)) { ret = t ? PTR_ERR(t) : -ENOENT; goto free_newinfo_counters_untrans; } @@ -1355,7 +1355,7 @@ do_add_counters(struct net *net, const void __user *user, unsigned int len, } t = xt_find_table_lock(net, AF_INET6, name); - if (!t || IS_ERR(t)) { + if (IS_ERR_OR_NULL(t)) { ret = t ? PTR_ERR(t) : -ENOENT; goto free; } @@ -1939,7 +1939,7 @@ compat_get_entries(struct net *net, struct compat_ip6t_get_entries __user *uptr, xt_compat_lock(AF_INET6); t = xt_find_table_lock(net, AF_INET6, get.name); - if (t && !IS_ERR(t)) { + if (!IS_ERR_OR_NULL(t)) { const struct xt_table_info *private = t->private; struct xt_table_info info; duprintf("t->private->number = %u\n", private->number); diff --git a/net/ipv6/netfilter/ip6t_NPT.c b/net/ipv6/netfilter/ip6t_NPT.c index e9486915eff6..83acc1405a18 100644 --- a/net/ipv6/netfilter/ip6t_NPT.c +++ b/net/ipv6/netfilter/ip6t_NPT.c @@ -9,47 +9,38 @@ #include <linux/module.h> #include <linux/skbuff.h> #include <linux/ipv6.h> +#include <net/ipv6.h> #include <linux/netfilter.h> #include <linux/netfilter_ipv6.h> #include <linux/netfilter_ipv6/ip6t_NPT.h> #include <linux/netfilter/x_tables.h> -static __sum16 csum16_complement(__sum16 a) -{ - return (__force __sum16)(0xffff - (__force u16)a); -} - -static __sum16 csum16_add(__sum16 a, __sum16 b) -{ - u16 sum; - - sum = (__force u16)a + (__force u16)b; - sum += (__force u16)a < (__force u16)b; - return (__force __sum16)sum; -} - -static __sum16 csum16_sub(__sum16 a, __sum16 b) -{ - return csum16_add(a, csum16_complement(b)); -} - static int ip6t_npt_checkentry(const struct xt_tgchk_param *par) { struct ip6t_npt_tginfo *npt = par->targinfo; - __sum16 src_sum = 0, dst_sum = 0; + __wsum src_sum = 0, dst_sum = 0; + struct in6_addr pfx; unsigned int i; if (npt->src_pfx_len > 64 || npt->dst_pfx_len > 64) return -EINVAL; + /* Ensure that LSB of prefix is zero */ + ipv6_addr_prefix(&pfx, &npt->src_pfx.in6, npt->src_pfx_len); + if (!ipv6_addr_equal(&pfx, &npt->src_pfx.in6)) + return -EINVAL; + ipv6_addr_prefix(&pfx, &npt->dst_pfx.in6, npt->dst_pfx_len); + if (!ipv6_addr_equal(&pfx, &npt->dst_pfx.in6)) + return -EINVAL; + for (i = 0; i < ARRAY_SIZE(npt->src_pfx.in6.s6_addr16); i++) { - src_sum = csum16_add(src_sum, - (__force __sum16)npt->src_pfx.in6.s6_addr16[i]); - dst_sum = csum16_add(dst_sum, - (__force __sum16)npt->dst_pfx.in6.s6_addr16[i]); + src_sum = csum_add(src_sum, + (__force __wsum)npt->src_pfx.in6.s6_addr16[i]); + dst_sum = csum_add(dst_sum, + (__force __wsum)npt->dst_pfx.in6.s6_addr16[i]); } - npt->adjustment = csum16_sub(src_sum, dst_sum); + npt->adjustment = ~csum_fold(csum_sub(src_sum, dst_sum)); return 0; } @@ -70,7 +61,7 @@ static bool ip6t_npt_map_pfx(const struct ip6t_npt_tginfo *npt, idx = i / 32; addr->s6_addr32[idx] &= mask; - addr->s6_addr32[idx] |= npt->dst_pfx.in6.s6_addr32[idx]; + addr->s6_addr32[idx] |= ~mask & npt->dst_pfx.in6.s6_addr32[idx]; } if (pfx_len <= 48) @@ -85,8 +76,8 @@ static bool ip6t_npt_map_pfx(const struct ip6t_npt_tginfo *npt, return false; } - sum = csum16_add((__force __sum16)addr->s6_addr16[idx], - npt->adjustment); + sum = ~csum_fold(csum_add(csum_unfold((__force __sum16)addr->s6_addr16[idx]), + csum_unfold(npt->adjustment))); if (sum == CSUM_MANGLED_0) sum = 0; *(__force __sum16 *)&addr->s6_addr16[idx] = sum; diff --git a/net/ipv6/netfilter/ip6t_REJECT.c b/net/ipv6/netfilter/ip6t_REJECT.c index fd4fb34c51c7..ed3b427b2841 100644 --- a/net/ipv6/netfilter/ip6t_REJECT.c +++ b/net/ipv6/netfilter/ip6t_REJECT.c @@ -126,12 +126,13 @@ static void send_reset(struct net *net, struct sk_buff *oldskb) skb_put(nskb, sizeof(struct ipv6hdr)); skb_reset_network_header(nskb); ip6h = ipv6_hdr(nskb); - *(__be32 *)ip6h = htonl(0x60000000 | (tclass << 20)); + ip6_flow_hdr(ip6h, tclass, 0); ip6h->hop_limit = ip6_dst_hoplimit(dst); ip6h->nexthdr = IPPROTO_TCP; ip6h->saddr = oip6h->daddr; ip6h->daddr = oip6h->saddr; + skb_reset_transport_header(nskb); tcph = (struct tcphdr *)skb_put(nskb, sizeof(struct tcphdr)); /* Truncate to length (no data) */ tcph->doff = sizeof(struct tcphdr)/4; diff --git a/net/ipv6/netfilter/ip6table_mangle.c b/net/ipv6/netfilter/ip6table_mangle.c index 7431121b87de..6134a1ebfb1b 100644 --- a/net/ipv6/netfilter/ip6table_mangle.c +++ b/net/ipv6/netfilter/ip6table_mangle.c @@ -11,6 +11,7 @@ #include <linux/module.h> #include <linux/netfilter_ipv6/ip6_tables.h> #include <linux/slab.h> +#include <net/ipv6.h> MODULE_LICENSE("GPL"); MODULE_AUTHOR("Netfilter Core Team <coreteam@netfilter.org>"); @@ -60,8 +61,8 @@ ip6t_mangle_out(struct sk_buff *skb, const struct net_device *out) dev_net(out)->ipv6.ip6table_mangle); if (ret != NF_DROP && ret != NF_STOLEN && - (memcmp(&ipv6_hdr(skb)->saddr, &saddr, sizeof(saddr)) || - memcmp(&ipv6_hdr(skb)->daddr, &daddr, sizeof(daddr)) || + (!ipv6_addr_equal(&ipv6_hdr(skb)->saddr, &saddr) || + !ipv6_addr_equal(&ipv6_hdr(skb)->daddr, &daddr) || skb->mark != mark || ipv6_hdr(skb)->hop_limit != hop_limit || flowlabel != *((u_int32_t *)ipv6_hdr(skb)))) diff --git a/net/ipv6/netfilter/ip6table_nat.c b/net/ipv6/netfilter/ip6table_nat.c index 6c8ae24b85eb..e0e788d25b14 100644 --- a/net/ipv6/netfilter/ip6table_nat.c +++ b/net/ipv6/netfilter/ip6table_nat.c @@ -127,23 +127,28 @@ nf_nat_ipv6_fn(unsigned int hooknum, ret = nf_nat_rule_find(skb, hooknum, in, out, ct); if (ret != NF_ACCEPT) return ret; - } else + } else { pr_debug("Already setup manip %s for ct %p\n", maniptype == NF_NAT_MANIP_SRC ? "SRC" : "DST", ct); + if (nf_nat_oif_changed(hooknum, ctinfo, nat, out)) + goto oif_changed; + } break; default: /* ESTABLISHED */ NF_CT_ASSERT(ctinfo == IP_CT_ESTABLISHED || ctinfo == IP_CT_ESTABLISHED_REPLY); - if (nf_nat_oif_changed(hooknum, ctinfo, nat, out)) { - nf_ct_kill_acct(ct, ctinfo, skb); - return NF_DROP; - } + if (nf_nat_oif_changed(hooknum, ctinfo, nat, out)) + goto oif_changed; } return nf_nat_packet(ct, ctinfo, hooknum, skb); + +oif_changed: + nf_ct_kill_acct(ct, ctinfo, skb); + return NF_DROP; } static unsigned int diff --git a/net/ipv6/netfilter/nf_conntrack_l3proto_ipv6.c b/net/ipv6/netfilter/nf_conntrack_l3proto_ipv6.c index 00ee17c3e893..8a45bb20bedb 100644 --- a/net/ipv6/netfilter/nf_conntrack_l3proto_ipv6.c +++ b/net/ipv6/netfilter/nf_conntrack_l3proto_ipv6.c @@ -81,8 +81,8 @@ static int ipv6_get_l4proto(const struct sk_buff *skb, unsigned int nhoff, } protoff = ipv6_skip_exthdr(skb, extoff, &nexthdr, &frag_off); /* - * (protoff == skb->len) mean that the packet doesn't have no data - * except of IPv6 & ext headers. but it's tracked anyway. - YK + * (protoff == skb->len) means the packet has not data, just + * IPv6 and possibly extensions headers, but it is tracked anyway */ if (protoff < 0 || (frag_off & htons(~0x7)) != 0) { pr_debug("ip6_conntrack_core: can't find proto in pkt\n"); @@ -421,54 +421,43 @@ static int ipv6_net_init(struct net *net) { int ret = 0; - ret = nf_conntrack_l4proto_register(net, - &nf_conntrack_l4proto_tcp6); + ret = nf_ct_l4proto_pernet_register(net, &nf_conntrack_l4proto_tcp6); if (ret < 0) { - printk(KERN_ERR "nf_conntrack_l4proto_tcp6: protocol register failed\n"); + pr_err("nf_conntrack_tcp6: pernet registration failed\n"); goto out; } - ret = nf_conntrack_l4proto_register(net, - &nf_conntrack_l4proto_udp6); + ret = nf_ct_l4proto_pernet_register(net, &nf_conntrack_l4proto_udp6); if (ret < 0) { - printk(KERN_ERR "nf_conntrack_l4proto_udp6: protocol register failed\n"); + pr_err("nf_conntrack_udp6: pernet registration failed\n"); goto cleanup_tcp6; } - ret = nf_conntrack_l4proto_register(net, - &nf_conntrack_l4proto_icmpv6); + ret = nf_ct_l4proto_pernet_register(net, &nf_conntrack_l4proto_icmpv6); if (ret < 0) { - printk(KERN_ERR "nf_conntrack_l4proto_icmp6: protocol register failed\n"); + pr_err("nf_conntrack_icmp6: pernet registration failed\n"); goto cleanup_udp6; } - ret = nf_conntrack_l3proto_register(net, - &nf_conntrack_l3proto_ipv6); + ret = nf_ct_l3proto_pernet_register(net, &nf_conntrack_l3proto_ipv6); if (ret < 0) { - printk(KERN_ERR "nf_conntrack_l3proto_ipv6: protocol register failed\n"); + pr_err("nf_conntrack_ipv6: pernet registration failed.\n"); goto cleanup_icmpv6; } return 0; cleanup_icmpv6: - nf_conntrack_l4proto_unregister(net, - &nf_conntrack_l4proto_icmpv6); + nf_ct_l4proto_pernet_unregister(net, &nf_conntrack_l4proto_icmpv6); cleanup_udp6: - nf_conntrack_l4proto_unregister(net, - &nf_conntrack_l4proto_udp6); + nf_ct_l4proto_pernet_unregister(net, &nf_conntrack_l4proto_udp6); cleanup_tcp6: - nf_conntrack_l4proto_unregister(net, - &nf_conntrack_l4proto_tcp6); + nf_ct_l4proto_pernet_unregister(net, &nf_conntrack_l4proto_tcp6); out: return ret; } static void ipv6_net_exit(struct net *net) { - nf_conntrack_l3proto_unregister(net, - &nf_conntrack_l3proto_ipv6); - nf_conntrack_l4proto_unregister(net, - &nf_conntrack_l4proto_icmpv6); - nf_conntrack_l4proto_unregister(net, - &nf_conntrack_l4proto_udp6); - nf_conntrack_l4proto_unregister(net, - &nf_conntrack_l4proto_tcp6); + nf_ct_l3proto_pernet_unregister(net, &nf_conntrack_l3proto_ipv6); + nf_ct_l4proto_pernet_unregister(net, &nf_conntrack_l4proto_icmpv6); + nf_ct_l4proto_pernet_unregister(net, &nf_conntrack_l4proto_udp6); + nf_ct_l4proto_pernet_unregister(net, &nf_conntrack_l4proto_tcp6); } static struct pernet_operations ipv6_net_ops = { @@ -491,19 +480,52 @@ static int __init nf_conntrack_l3proto_ipv6_init(void) ret = register_pernet_subsys(&ipv6_net_ops); if (ret < 0) - goto cleanup_pernet; + goto cleanup_sockopt; + ret = nf_register_hooks(ipv6_conntrack_ops, ARRAY_SIZE(ipv6_conntrack_ops)); if (ret < 0) { pr_err("nf_conntrack_ipv6: can't register pre-routing defrag " "hook.\n"); - goto cleanup_ipv6; + goto cleanup_pernet; + } + + ret = nf_ct_l4proto_register(&nf_conntrack_l4proto_tcp6); + if (ret < 0) { + pr_err("nf_conntrack_ipv6: can't register tcp6 proto.\n"); + goto cleanup_hooks; + } + + ret = nf_ct_l4proto_register(&nf_conntrack_l4proto_udp6); + if (ret < 0) { + pr_err("nf_conntrack_ipv6: can't register udp6 proto.\n"); + goto cleanup_tcp6; + } + + ret = nf_ct_l4proto_register(&nf_conntrack_l4proto_icmpv6); + if (ret < 0) { + pr_err("nf_conntrack_ipv6: can't register icmpv6 proto.\n"); + goto cleanup_udp6; + } + + ret = nf_ct_l3proto_register(&nf_conntrack_l3proto_ipv6); + if (ret < 0) { + pr_err("nf_conntrack_ipv6: can't register ipv6 proto.\n"); + goto cleanup_icmpv6; } return ret; - cleanup_ipv6: - unregister_pernet_subsys(&ipv6_net_ops); + cleanup_icmpv6: + nf_ct_l4proto_unregister(&nf_conntrack_l4proto_icmpv6); + cleanup_udp6: + nf_ct_l4proto_unregister(&nf_conntrack_l4proto_udp6); + cleanup_tcp6: + nf_ct_l4proto_unregister(&nf_conntrack_l4proto_tcp6); + cleanup_hooks: + nf_unregister_hooks(ipv6_conntrack_ops, ARRAY_SIZE(ipv6_conntrack_ops)); cleanup_pernet: + unregister_pernet_subsys(&ipv6_net_ops); + cleanup_sockopt: nf_unregister_sockopt(&so_getorigdst6); return ret; } @@ -511,6 +533,10 @@ static int __init nf_conntrack_l3proto_ipv6_init(void) static void __exit nf_conntrack_l3proto_ipv6_fini(void) { synchronize_net(); + nf_ct_l3proto_unregister(&nf_conntrack_l3proto_ipv6); + nf_ct_l4proto_unregister(&nf_conntrack_l4proto_tcp6); + nf_ct_l4proto_unregister(&nf_conntrack_l4proto_udp6); + nf_ct_l4proto_unregister(&nf_conntrack_l4proto_icmpv6); nf_unregister_hooks(ipv6_conntrack_ops, ARRAY_SIZE(ipv6_conntrack_ops)); unregister_pernet_subsys(&ipv6_net_ops); nf_unregister_sockopt(&so_getorigdst6); diff --git a/net/ipv6/netfilter/nf_conntrack_reasm.c b/net/ipv6/netfilter/nf_conntrack_reasm.c index 22c8ea951185..b89a8c3186cd 100644 --- a/net/ipv6/netfilter/nf_conntrack_reasm.c +++ b/net/ipv6/netfilter/nf_conntrack_reasm.c @@ -311,12 +311,15 @@ found: else fq->q.fragments = skb; - skb->dev = NULL; + if (skb->dev) { + fq->iif = skb->dev->ifindex; + skb->dev = NULL; + } fq->q.stamp = skb->tstamp; fq->q.meat += skb->len; if (payload_len > fq->q.max_size) fq->q.max_size = payload_len; - atomic_add(skb->truesize, &fq->q.net->mem); + add_frag_mem_limit(&fq->q, skb->truesize); /* The first fragment. * nhoffset is obtained from the first fragment, of course. @@ -325,9 +328,8 @@ found: fq->nhoffset = nhoff; fq->q.last_in |= INET_FRAG_FIRST_IN; } - write_lock(&nf_frags.lock); - list_move_tail(&fq->q.lru_list, &fq->q.net->lru_list); - write_unlock(&nf_frags.lock); + + inet_frag_lru_move(&fq->q); return 0; discard_fq: @@ -366,7 +368,7 @@ nf_ct_frag6_reasm(struct frag_queue *fq, struct net_device *dev) } /* Head of list must not be cloned. */ - if (skb_cloned(head) && pskb_expand_head(head, 0, 0, GFP_ATOMIC)) { + if (skb_unclone(head, GFP_ATOMIC)) { pr_debug("skb is cloned but can't expand head"); goto out_oom; } @@ -395,7 +397,7 @@ nf_ct_frag6_reasm(struct frag_queue *fq, struct net_device *dev) clone->ip_summed = head->ip_summed; NFCT_FRAG6_CB(clone)->orig = NULL; - atomic_add(clone->truesize, &fq->q.net->mem); + add_frag_mem_limit(&fq->q, clone->truesize); } /* We have to remove fragment header from datagram and to relocate @@ -419,7 +421,7 @@ nf_ct_frag6_reasm(struct frag_queue *fq, struct net_device *dev) head->csum = csum_add(head->csum, fp->csum); head->truesize += fp->truesize; } - atomic_sub(head->truesize, &fq->q.net->mem); + sub_frag_mem_limit(&fq->q, head->truesize); head->local_df = 1; head->next = NULL; diff --git a/net/ipv6/raw.c b/net/ipv6/raw.c index 6cd29b1e8b92..70fa81449997 100644 --- a/net/ipv6/raw.c +++ b/net/ipv6/raw.c @@ -507,7 +507,7 @@ static int rawv6_recvmsg(struct kiocb *iocb, struct sock *sk, sock_recv_ts_and_drops(msg, sk, skb); if (np->rxopt.all) - datagram_recv_ctl(sk, msg, skb); + ip6_datagram_recv_ctl(sk, msg, skb); err = copied; if (flags & MSG_TRUNC) @@ -822,8 +822,8 @@ static int rawv6_sendmsg(struct kiocb *iocb, struct sock *sk, memset(opt, 0, sizeof(struct ipv6_txoptions)); opt->tot_len = sizeof(struct ipv6_txoptions); - err = datagram_send_ctl(sock_net(sk), sk, msg, &fl6, opt, - &hlimit, &tclass, &dontfrag); + err = ip6_datagram_send_ctl(sock_net(sk), sk, msg, &fl6, opt, + &hlimit, &tclass, &dontfrag); if (err < 0) { fl6_sock_release(flowlabel); return err; diff --git a/net/ipv6/reassembly.c b/net/ipv6/reassembly.c index e5253ec9e0fc..9a6428aaa2d8 100644 --- a/net/ipv6/reassembly.c +++ b/net/ipv6/reassembly.c @@ -79,20 +79,7 @@ unsigned int inet6_hash_frag(__be32 id, const struct in6_addr *saddr, { u32 c; - c = jhash_3words((__force u32)saddr->s6_addr32[0], - (__force u32)saddr->s6_addr32[1], - (__force u32)saddr->s6_addr32[2], - rnd); - - c = jhash_3words((__force u32)saddr->s6_addr32[3], - (__force u32)daddr->s6_addr32[0], - (__force u32)daddr->s6_addr32[1], - c); - - c = jhash_3words((__force u32)daddr->s6_addr32[2], - (__force u32)daddr->s6_addr32[3], - (__force u32)id, - c); + c = jhash_3words(ipv6_addr_hash(saddr), ipv6_addr_hash(daddr), id, rnd); return c & (INETFRAGS_HASHSZ - 1); } @@ -327,7 +314,7 @@ found: } fq->q.stamp = skb->tstamp; fq->q.meat += skb->len; - atomic_add(skb->truesize, &fq->q.net->mem); + add_frag_mem_limit(&fq->q, skb->truesize); /* The first fragment. * nhoffset is obtained from the first fragment, of course. @@ -341,9 +328,7 @@ found: fq->q.meat == fq->q.len) return ip6_frag_reasm(fq, prev, dev); - write_lock(&ip6_frags.lock); - list_move_tail(&fq->q.lru_list, &fq->q.net->lru_list); - write_unlock(&ip6_frags.lock); + inet_frag_lru_move(&fq->q); return -1; discard_fq: @@ -406,7 +391,7 @@ static int ip6_frag_reasm(struct frag_queue *fq, struct sk_buff *prev, goto out_oversize; /* Head of list must not be cloned. */ - if (skb_cloned(head) && pskb_expand_head(head, 0, 0, GFP_ATOMIC)) + if (skb_unclone(head, GFP_ATOMIC)) goto out_oom; /* If the first fragment is fragmented itself, we split @@ -429,7 +414,7 @@ static int ip6_frag_reasm(struct frag_queue *fq, struct sk_buff *prev, head->len -= clone->len; clone->csum = 0; clone->ip_summed = head->ip_summed; - atomic_add(clone->truesize, &fq->q.net->mem); + add_frag_mem_limit(&fq->q, clone->truesize); } /* We have to remove fragment header from datagram and to relocate @@ -467,7 +452,7 @@ static int ip6_frag_reasm(struct frag_queue *fq, struct sk_buff *prev, } fp = next; } - atomic_sub(sum_truesize, &fq->q.net->mem); + sub_frag_mem_limit(&fq->q, sum_truesize); head->next = NULL; head->dev = dev; diff --git a/net/ipv6/route.c b/net/ipv6/route.c index e229a3bc345d..f3328bc1174f 100644 --- a/net/ipv6/route.c +++ b/net/ipv6/route.c @@ -145,25 +145,12 @@ static struct neighbour *ip6_neigh_lookup(const struct dst_entry *dst, struct neighbour *n; daddr = choose_neigh_daddr(rt, skb, daddr); - n = __ipv6_neigh_lookup(&nd_tbl, dst->dev, daddr); + n = __ipv6_neigh_lookup(dst->dev, daddr); if (n) return n; return neigh_create(&nd_tbl, daddr, dst->dev); } -static int rt6_bind_neighbour(struct rt6_info *rt, struct net_device *dev) -{ - struct neighbour *n = __ipv6_neigh_lookup(&nd_tbl, dev, &rt->rt6i_gateway); - if (!n) { - n = neigh_create(&nd_tbl, &rt->rt6i_gateway, dev); - if (IS_ERR(n)) - return PTR_ERR(n); - } - rt->n = n; - - return 0; -} - static struct dst_ops ip6_dst_ops_template = { .family = AF_INET6, .protocol = cpu_to_be16(ETH_P_IPV6), @@ -301,9 +288,6 @@ static void ip6_dst_destroy(struct dst_entry *dst) struct rt6_info *rt = (struct rt6_info *)dst; struct inet6_dev *idev = rt->rt6i_idev; - if (rt->n) - neigh_release(rt->n); - if (!(rt->dst.flags & DST_HOST)) dst_destroy_metrics_generic(dst); @@ -354,11 +338,6 @@ static void ip6_dst_ifdown(struct dst_entry *dst, struct net_device *dev, in6_dev_put(idev); } } - if (rt->n && rt->n->dev == dev) { - rt->n->dev = loopback_dev; - dev_hold(loopback_dev); - dev_put(dev); - } } } @@ -388,15 +367,8 @@ static int rt6_info_hash_nhsfn(unsigned int candidate_count, { unsigned int val = fl6->flowi6_proto; - val ^= (__force u32)fl6->daddr.s6_addr32[0]; - val ^= (__force u32)fl6->daddr.s6_addr32[1]; - val ^= (__force u32)fl6->daddr.s6_addr32[2]; - val ^= (__force u32)fl6->daddr.s6_addr32[3]; - - val ^= (__force u32)fl6->saddr.s6_addr32[0]; - val ^= (__force u32)fl6->saddr.s6_addr32[1]; - val ^= (__force u32)fl6->saddr.s6_addr32[2]; - val ^= (__force u32)fl6->saddr.s6_addr32[3]; + val ^= ipv6_addr_hash(&fl6->daddr); + val ^= ipv6_addr_hash(&fl6->saddr); /* Work only if this not encapsulated */ switch (fl6->flowi6_proto) { @@ -505,24 +477,34 @@ static void rt6_probe(struct rt6_info *rt) * Router Reachability Probe MUST be rate-limited * to no more than one per minute. */ - neigh = rt ? rt->n : NULL; - if (!neigh || (neigh->nud_state & NUD_VALID)) + if (!rt || !(rt->rt6i_flags & RTF_GATEWAY)) return; - read_lock_bh(&neigh->lock); - if (!(neigh->nud_state & NUD_VALID) && + rcu_read_lock_bh(); + neigh = __ipv6_neigh_lookup_noref(rt->dst.dev, &rt->rt6i_gateway); + if (neigh) { + write_lock(&neigh->lock); + if (neigh->nud_state & NUD_VALID) + goto out; + } + + if (!neigh || time_after(jiffies, neigh->updated + rt->rt6i_idev->cnf.rtr_probe_interval)) { struct in6_addr mcaddr; struct in6_addr *target; - neigh->updated = jiffies; - read_unlock_bh(&neigh->lock); + if (neigh) { + neigh->updated = jiffies; + write_unlock(&neigh->lock); + } - target = (struct in6_addr *)&neigh->primary_key; + target = (struct in6_addr *)&rt->rt6i_gateway; addrconf_addr_solict_mult(target, &mcaddr); ndisc_send_ns(rt->dst.dev, NULL, target, &mcaddr, NULL); } else { - read_unlock_bh(&neigh->lock); +out: + write_unlock(&neigh->lock); } + rcu_read_unlock_bh(); } #else static inline void rt6_probe(struct rt6_info *rt) @@ -549,20 +531,24 @@ static inline bool rt6_check_neigh(struct rt6_info *rt) struct neighbour *neigh; bool ret = false; - neigh = rt->n; if (rt->rt6i_flags & RTF_NONEXTHOP || !(rt->rt6i_flags & RTF_GATEWAY)) - ret = true; - else if (neigh) { - read_lock_bh(&neigh->lock); + return true; + + rcu_read_lock_bh(); + neigh = __ipv6_neigh_lookup_noref(rt->dst.dev, &rt->rt6i_gateway); + if (neigh) { + read_lock(&neigh->lock); if (neigh->nud_state & NUD_VALID) ret = true; #ifdef CONFIG_IPV6_ROUTER_PREF else if (!(neigh->nud_state & NUD_FAILED)) ret = true; #endif - read_unlock_bh(&neigh->lock); + read_unlock(&neigh->lock); } + rcu_read_unlock_bh(); + return ret; } @@ -838,8 +824,6 @@ static struct rt6_info *rt6_alloc_cow(struct rt6_info *ort, rt = ip6_rt_copy(ort, daddr); if (rt) { - int attempts = !in_softirq(); - if (!(rt->rt6i_flags & RTF_GATEWAY)) { if (ort->rt6i_dst.plen != 128 && ipv6_addr_equal(&ort->rt6i_dst.addr, daddr)) @@ -855,32 +839,6 @@ static struct rt6_info *rt6_alloc_cow(struct rt6_info *ort, rt->rt6i_src.plen = 128; } #endif - - retry: - if (rt6_bind_neighbour(rt, rt->dst.dev)) { - struct net *net = dev_net(rt->dst.dev); - int saved_rt_min_interval = - net->ipv6.sysctl.ip6_rt_gc_min_interval; - int saved_rt_elasticity = - net->ipv6.sysctl.ip6_rt_gc_elasticity; - - if (attempts-- > 0) { - net->ipv6.sysctl.ip6_rt_gc_elasticity = 1; - net->ipv6.sysctl.ip6_rt_gc_min_interval = 0; - - ip6_dst_gc(&net->ipv6.ip6_dst_ops); - - net->ipv6.sysctl.ip6_rt_gc_elasticity = - saved_rt_elasticity; - net->ipv6.sysctl.ip6_rt_gc_min_interval = - saved_rt_min_interval; - goto retry; - } - - net_warn_ratelimited("Neighbour table overflow\n"); - dst_free(&rt->dst); - return NULL; - } } return rt; @@ -891,10 +849,8 @@ static struct rt6_info *rt6_alloc_clone(struct rt6_info *ort, { struct rt6_info *rt = ip6_rt_copy(ort, daddr); - if (rt) { + if (rt) rt->rt6i_flags |= RTF_CACHE; - rt->n = neigh_clone(ort->n); - } return rt; } @@ -928,7 +884,7 @@ restart: dst_hold(&rt->dst); read_unlock_bh(&table->tb6_lock); - if (!rt->n && !(rt->rt6i_flags & RTF_NONEXTHOP)) + if (!(rt->rt6i_flags & (RTF_NONEXTHOP | RTF_GATEWAY))) nrt = rt6_alloc_cow(rt, &fl6->daddr, &fl6->saddr); else if (!(rt->dst.flags & DST_HOST)) nrt = rt6_alloc_clone(rt, &fl6->daddr); @@ -994,7 +950,7 @@ void ip6_route_input(struct sk_buff *skb) .flowi6_iif = skb->dev->ifindex, .daddr = iph->daddr, .saddr = iph->saddr, - .flowlabel = (* (__be32 *) iph) & IPV6_FLOWINFO_MASK, + .flowlabel = ip6_flowinfo(iph), .flowi6_mark = skb->mark, .flowi6_proto = iph->nexthdr, }; @@ -1159,7 +1115,7 @@ void ip6_update_pmtu(struct sk_buff *skb, struct net *net, __be32 mtu, fl6.flowi6_flags = 0; fl6.daddr = iph->daddr; fl6.saddr = iph->saddr; - fl6.flowlabel = (*(__be32 *) iph) & IPV6_FLOWINFO_MASK; + fl6.flowlabel = ip6_flowinfo(iph); dst = ip6_route_output(net, NULL, &fl6); if (!dst->error) @@ -1187,7 +1143,7 @@ void ip6_redirect(struct sk_buff *skb, struct net *net, int oif, u32 mark) fl6.flowi6_flags = 0; fl6.daddr = iph->daddr; fl6.saddr = iph->saddr; - fl6.flowlabel = (*(__be32 *) iph) & IPV6_FLOWINFO_MASK; + fl6.flowlabel = ip6_flowinfo(iph); dst = ip6_route_output(net, NULL, &fl6); if (!dst->error) @@ -1247,7 +1203,6 @@ static struct dst_entry *icmp6_dst_gc_list; static DEFINE_SPINLOCK(icmp6_dst_lock); struct dst_entry *icmp6_dst_alloc(struct net_device *dev, - struct neighbour *neigh, struct flowi6 *fl6) { struct dst_entry *dst; @@ -1265,20 +1220,8 @@ struct dst_entry *icmp6_dst_alloc(struct net_device *dev, goto out; } - if (neigh) - neigh_hold(neigh); - else { - neigh = ip6_neigh_lookup(&rt->dst, NULL, &fl6->daddr); - if (IS_ERR(neigh)) { - in6_dev_put(idev); - dst_free(&rt->dst); - return ERR_CAST(neigh); - } - } - rt->dst.flags |= DST_HOST; rt->dst.output = ip6_output; - rt->n = neigh; atomic_set(&rt->dst.__refcnt, 1); rt->rt6i_dst.addr = fl6->daddr; rt->rt6i_dst.plen = 128; @@ -1587,12 +1530,6 @@ int ip6_route_add(struct fib6_config *cfg) } else rt->rt6i_prefsrc.plen = 0; - if (cfg->fc_flags & (RTF_GATEWAY | RTF_NONEXTHOP)) { - err = rt6_bind_neighbour(rt, dev); - if (err) - goto out; - } - rt->rt6i_flags = cfg->fc_flags; install_route: @@ -1705,37 +1642,32 @@ static void rt6_do_redirect(struct dst_entry *dst, struct sock *sk, struct sk_bu struct net *net = dev_net(skb->dev); struct netevent_redirect netevent; struct rt6_info *rt, *nrt = NULL; - const struct in6_addr *target; struct ndisc_options ndopts; - const struct in6_addr *dest; - struct neighbour *old_neigh; struct inet6_dev *in6_dev; struct neighbour *neigh; - struct icmp6hdr *icmph; + struct rd_msg *msg; int optlen, on_link; u8 *lladdr; optlen = skb->tail - skb->transport_header; - optlen -= sizeof(struct icmp6hdr) + 2 * sizeof(struct in6_addr); + optlen -= sizeof(*msg); if (optlen < 0) { net_dbg_ratelimited("rt6_do_redirect: packet too short\n"); return; } - icmph = icmp6_hdr(skb); - target = (const struct in6_addr *) (icmph + 1); - dest = target + 1; + msg = (struct rd_msg *)icmp6_hdr(skb); - if (ipv6_addr_is_multicast(dest)) { + if (ipv6_addr_is_multicast(&msg->dest)) { net_dbg_ratelimited("rt6_do_redirect: destination address is multicast\n"); return; } on_link = 0; - if (ipv6_addr_equal(dest, target)) { + if (ipv6_addr_equal(&msg->dest, &msg->target)) { on_link = 1; - } else if (ipv6_addr_type(target) != + } else if (ipv6_addr_type(&msg->target) != (IPV6_ADDR_UNICAST|IPV6_ADDR_LINKLOCAL)) { net_dbg_ratelimited("rt6_do_redirect: target address is not link-local unicast\n"); return; @@ -1752,7 +1684,7 @@ static void rt6_do_redirect(struct dst_entry *dst, struct sock *sk, struct sk_bu * first-hop router for the specified ICMP Destination Address. */ - if (!ndisc_parse_options((u8*)(dest + 1), optlen, &ndopts)) { + if (!ndisc_parse_options(msg->opt, optlen, &ndopts)) { net_dbg_ratelimited("rt6_redirect: invalid ND options\n"); return; } @@ -1779,15 +1711,10 @@ static void rt6_do_redirect(struct dst_entry *dst, struct sock *sk, struct sk_bu */ dst_confirm(&rt->dst); - neigh = __neigh_lookup(&nd_tbl, target, skb->dev, 1); + neigh = __neigh_lookup(&nd_tbl, &msg->target, skb->dev, 1); if (!neigh) return; - /* Duplicate redirect: silently ignore. */ - old_neigh = rt->n; - if (neigh == old_neigh) - goto out; - /* * We have finally decided to accept it. */ @@ -1799,7 +1726,7 @@ static void rt6_do_redirect(struct dst_entry *dst, struct sock *sk, struct sk_bu NEIGH_UPDATE_F_ISROUTER)) ); - nrt = ip6_rt_copy(rt, dest); + nrt = ip6_rt_copy(rt, &msg->dest); if (!nrt) goto out; @@ -1808,16 +1735,14 @@ static void rt6_do_redirect(struct dst_entry *dst, struct sock *sk, struct sk_bu nrt->rt6i_flags &= ~RTF_GATEWAY; nrt->rt6i_gateway = *(struct in6_addr *)neigh->primary_key; - nrt->n = neigh_clone(neigh); if (ip6_ins_rt(nrt)) goto out; netevent.old = &rt->dst; - netevent.old_neigh = old_neigh; netevent.new = &nrt->dst; - netevent.new_neigh = neigh; - netevent.daddr = dest; + netevent.daddr = &msg->dest; + netevent.neigh = neigh; call_netevent_notifiers(NETEVENT_REDIRECT, &netevent); if (rt->rt6i_flags & RTF_CACHE) { @@ -2123,7 +2048,6 @@ struct rt6_info *addrconf_dst_alloc(struct inet6_dev *idev, { struct net *net = dev_net(idev->dev); struct rt6_info *rt = ip6_dst_alloc(net, net->loopback_dev, 0, NULL); - int err; if (!rt) { net_warn_ratelimited("Maximum number of routes reached, consider increasing route/max_size\n"); @@ -2142,11 +2066,6 @@ struct rt6_info *addrconf_dst_alloc(struct inet6_dev *idev, rt->rt6i_flags |= RTF_ANYCAST; else rt->rt6i_flags |= RTF_LOCAL; - err = rt6_bind_neighbour(rt, rt->dst.dev); - if (err) { - dst_free(&rt->dst); - return ERR_PTR(err); - } rt->rt6i_dst.addr = *addr; rt->rt6i_dst.plen = 128; @@ -2492,7 +2411,6 @@ static int rt6_fill_node(struct net *net, struct nlmsghdr *nlh; long expires; u32 table; - struct neighbour *n; if (prefix) { /* user wants prefix routes only */ if (!(rt->rt6i_flags & RTF_PREFIX_RT)) { @@ -2605,9 +2523,8 @@ static int rt6_fill_node(struct net *net, if (rtnetlink_put_metrics(skb, dst_metrics_ptr(&rt->dst)) < 0) goto nla_put_failure; - n = rt->n; - if (n) { - if (nla_put(skb, RTA_GATEWAY, 16, &n->primary_key) < 0) + if (rt->rt6i_flags & RTF_GATEWAY) { + if (nla_put(skb, RTA_GATEWAY, 16, &rt->rt6i_gateway) < 0) goto nla_put_failure; } @@ -2802,7 +2719,6 @@ struct rt6_proc_arg static int rt6_info_route(struct rt6_info *rt, void *p_arg) { struct seq_file *m = p_arg; - struct neighbour *n; seq_printf(m, "%pi6 %02x ", &rt->rt6i_dst.addr, rt->rt6i_dst.plen); @@ -2811,9 +2727,8 @@ static int rt6_info_route(struct rt6_info *rt, void *p_arg) #else seq_puts(m, "00000000000000000000000000000000 00 "); #endif - n = rt->n; - if (n) { - seq_printf(m, "%pi6", n->primary_key); + if (rt->rt6i_flags & RTF_GATEWAY) { + seq_printf(m, "%pi6", &rt->rt6i_gateway); } else { seq_puts(m, "00000000000000000000000000000000"); } diff --git a/net/ipv6/sit.c b/net/ipv6/sit.c index cfba99b2c2a4..02f96dcbcf02 100644 --- a/net/ipv6/sit.c +++ b/net/ipv6/sit.c @@ -72,6 +72,8 @@ MODULE_PARM_DESC(log_ecn_error, "Log packets received with corrupted ECN"); static int ipip6_tunnel_init(struct net_device *dev); static void ipip6_tunnel_setup(struct net_device *dev); static void ipip6_dev_free(struct net_device *dev); +static bool check_6rd(struct ip_tunnel *tunnel, const struct in6_addr *v6dst, + __be32 *v4dst); static struct rtnl_link_ops sit_link_ops __read_mostly; static int sit_net_id __read_mostly; @@ -590,17 +592,21 @@ out: return err; } +static inline bool is_spoofed_6rd(struct ip_tunnel *tunnel, const __be32 v4addr, + const struct in6_addr *v6addr) +{ + __be32 v4embed = 0; + if (check_6rd(tunnel, v6addr, &v4embed) && v4addr != v4embed) + return true; + return false; +} + static int ipip6_rcv(struct sk_buff *skb) { - const struct iphdr *iph; + const struct iphdr *iph = ip_hdr(skb); struct ip_tunnel *tunnel; int err; - if (!pskb_may_pull(skb, sizeof(struct ipv6hdr))) - goto out; - - iph = ip_hdr(skb); - tunnel = ipip6_tunnel_lookup(dev_net(skb->dev), skb->dev, iph->saddr, iph->daddr); if (tunnel != NULL) { @@ -613,10 +619,19 @@ static int ipip6_rcv(struct sk_buff *skb) skb->protocol = htons(ETH_P_IPV6); skb->pkt_type = PACKET_HOST; - if ((tunnel->dev->priv_flags & IFF_ISATAP) && - !isatap_chksrc(skb, iph, tunnel)) { - tunnel->dev->stats.rx_errors++; - goto out; + if (tunnel->dev->priv_flags & IFF_ISATAP) { + if (!isatap_chksrc(skb, iph, tunnel)) { + tunnel->dev->stats.rx_errors++; + goto out; + } + } else { + if (is_spoofed_6rd(tunnel, iph->saddr, + &ipv6_hdr(skb)->saddr) || + is_spoofed_6rd(tunnel, iph->daddr, + &ipv6_hdr(skb)->daddr)) { + tunnel->dev->stats.rx_errors++; + goto out; + } } __skb_tunnel_rx(skb, tunnel->dev); @@ -650,14 +665,12 @@ out: } /* - * Returns the embedded IPv4 address if the IPv6 address - * comes from 6rd / 6to4 (RFC 3056) addr space. + * If the IPv6 address comes from 6rd / 6to4 (RFC 3056) addr space this function + * stores the embedded IPv4 address in v4dst and returns true. */ -static inline -__be32 try_6rd(const struct in6_addr *v6dst, struct ip_tunnel *tunnel) +static bool check_6rd(struct ip_tunnel *tunnel, const struct in6_addr *v6dst, + __be32 *v4dst) { - __be32 dst = 0; - #ifdef CONFIG_IPV6_SIT_6RD if (ipv6_prefix_equal(v6dst, &tunnel->ip6rd.prefix, tunnel->ip6rd.prefixlen)) { @@ -676,14 +689,24 @@ __be32 try_6rd(const struct in6_addr *v6dst, struct ip_tunnel *tunnel) d |= ntohl(v6dst->s6_addr32[pbw0 + 1]) >> (32 - pbi1); - dst = tunnel->ip6rd.relay_prefix | htonl(d); + *v4dst = tunnel->ip6rd.relay_prefix | htonl(d); + return true; } #else if (v6dst->s6_addr16[0] == htons(0x2002)) { /* 6to4 v6 addr has 16 bits prefix, 32 v4addr, 16 SLA, ... */ - memcpy(&dst, &v6dst->s6_addr16[1], 4); + memcpy(v4dst, &v6dst->s6_addr16[1], 4); + return true; } #endif + return false; +} + +static inline __be32 try_6rd(struct ip_tunnel *tunnel, + const struct in6_addr *v6dst) +{ + __be32 dst = 0; + check_6rd(tunnel, v6dst, &dst); return dst; } @@ -744,7 +767,7 @@ static netdev_tx_t ipip6_tunnel_xmit(struct sk_buff *skb, } if (!dst) - dst = try_6rd(&iph6->daddr, tunnel); + dst = try_6rd(tunnel, &iph6->daddr); if (!dst) { struct neighbour *neigh = NULL; diff --git a/net/ipv6/syncookies.c b/net/ipv6/syncookies.c index 40161977f7cf..8a0848b60b35 100644 --- a/net/ipv6/syncookies.c +++ b/net/ipv6/syncookies.c @@ -179,7 +179,7 @@ struct sock *cookie_v6_check(struct sock *sk, struct sk_buff *skb) memset(&tcp_opt, 0, sizeof(tcp_opt)); tcp_parse_options(skb, &tcp_opt, &hash_location, 0, NULL); - if (!cookie_check_timestamp(&tcp_opt, &ecn_ok)) + if (!cookie_check_timestamp(&tcp_opt, sock_net(sk), &ecn_ok)) goto out; ret = NULL; diff --git a/net/ipv6/tcp_ipv6.c b/net/ipv6/tcp_ipv6.c index 93825dd3a7c0..9b6460055df5 100644 --- a/net/ipv6/tcp_ipv6.c +++ b/net/ipv6/tcp_ipv6.c @@ -423,6 +423,7 @@ static void tcp_v6_err(struct sk_buff *skb, struct inet6_skb_parm *opt, } inet_csk_reqsk_queue_drop(sk, req, prev); + NET_INC_STATS_BH(sock_net(sk), LINUX_MIB_LISTENDROPS); goto out; case TCP_SYN_SENT: @@ -712,7 +713,8 @@ static const struct tcp_request_sock_ops tcp_request_sock_ipv6_ops = { #endif static void tcp_v6_send_response(struct sk_buff *skb, u32 seq, u32 ack, u32 win, - u32 ts, struct tcp_md5sig_key *key, int rst, u8 tclass) + u32 tsval, u32 tsecr, + struct tcp_md5sig_key *key, int rst, u8 tclass) { const struct tcphdr *th = tcp_hdr(skb); struct tcphdr *t1; @@ -724,7 +726,7 @@ static void tcp_v6_send_response(struct sk_buff *skb, u32 seq, u32 ack, u32 win, struct dst_entry *dst; __be32 *topt; - if (ts) + if (tsecr) tot_len += TCPOLEN_TSTAMP_ALIGNED; #ifdef CONFIG_TCP_MD5SIG if (key) @@ -754,11 +756,11 @@ static void tcp_v6_send_response(struct sk_buff *skb, u32 seq, u32 ack, u32 win, topt = (__be32 *)(t1 + 1); - if (ts) { + if (tsecr) { *topt++ = htonl((TCPOPT_NOP << 24) | (TCPOPT_NOP << 16) | (TCPOPT_TIMESTAMP << 8) | TCPOLEN_TIMESTAMP); - *topt++ = htonl(tcp_time_stamp); - *topt++ = htonl(ts); + *topt++ = htonl(tsval); + *topt++ = htonl(tsecr); } #ifdef CONFIG_TCP_MD5SIG @@ -834,7 +836,8 @@ static void tcp_v6_send_reset(struct sock *sk, struct sk_buff *skb) * no RST generated if md5 hash doesn't match. */ sk1 = inet6_lookup_listener(dev_net(skb_dst(skb)->dev), - &tcp_hashinfo, &ipv6h->daddr, + &tcp_hashinfo, &ipv6h->saddr, + th->source, &ipv6h->daddr, ntohs(th->source), inet6_iif(skb)); if (!sk1) return; @@ -858,7 +861,7 @@ static void tcp_v6_send_reset(struct sock *sk, struct sk_buff *skb) ack_seq = ntohl(th->seq) + th->syn + th->fin + skb->len - (th->doff << 2); - tcp_v6_send_response(skb, seq, ack_seq, 0, 0, key, 1, 0); + tcp_v6_send_response(skb, seq, ack_seq, 0, 0, 0, key, 1, 0); #ifdef CONFIG_TCP_MD5SIG release_sk1: @@ -869,10 +872,11 @@ release_sk1: #endif } -static void tcp_v6_send_ack(struct sk_buff *skb, u32 seq, u32 ack, u32 win, u32 ts, +static void tcp_v6_send_ack(struct sk_buff *skb, u32 seq, u32 ack, + u32 win, u32 tsval, u32 tsecr, struct tcp_md5sig_key *key, u8 tclass) { - tcp_v6_send_response(skb, seq, ack, win, ts, key, 0, tclass); + tcp_v6_send_response(skb, seq, ack, win, tsval, tsecr, key, 0, tclass); } static void tcp_v6_timewait_ack(struct sock *sk, struct sk_buff *skb) @@ -882,6 +886,7 @@ static void tcp_v6_timewait_ack(struct sock *sk, struct sk_buff *skb) tcp_v6_send_ack(skb, tcptw->tw_snd_nxt, tcptw->tw_rcv_nxt, tcptw->tw_rcv_wnd >> tw->tw_rcv_wscale, + tcp_time_stamp + tcptw->tw_ts_offset, tcptw->tw_ts_recent, tcp_twsk_md5_key(tcptw), tw->tw_tclass); @@ -891,7 +896,8 @@ static void tcp_v6_timewait_ack(struct sock *sk, struct sk_buff *skb) static void tcp_v6_reqsk_send_ack(struct sock *sk, struct sk_buff *skb, struct request_sock *req) { - tcp_v6_send_ack(skb, tcp_rsk(req)->snt_isn + 1, tcp_rsk(req)->rcv_isn + 1, req->rcv_wnd, req->ts_recent, + tcp_v6_send_ack(skb, tcp_rsk(req)->snt_isn + 1, tcp_rsk(req)->rcv_isn + 1, + req->rcv_wnd, tcp_time_stamp, req->ts_recent, tcp_v6_md5_do_lookup(sk, &ipv6_hdr(skb)->daddr), 0); } @@ -958,8 +964,10 @@ static int tcp_v6_conn_request(struct sock *sk, struct sk_buff *skb) goto drop; } - if (sk_acceptq_is_full(sk) && inet_csk_reqsk_queue_young(sk) > 1) + if (sk_acceptq_is_full(sk) && inet_csk_reqsk_queue_young(sk) > 1) { + NET_INC_STATS_BH(sock_net(sk), LINUX_MIB_LISTENOVERFLOWS); goto drop; + } req = inet6_reqsk_alloc(&tcp6_request_sock_ops); if (req == NULL) @@ -1027,7 +1035,7 @@ static int tcp_v6_conn_request(struct sock *sk, struct sk_buff *skb) treq->rmt_addr = ipv6_hdr(skb)->saddr; treq->loc_addr = ipv6_hdr(skb)->daddr; if (!want_cookie || tmp_opt.tstamp_ok) - TCP_ECN_create_request(req, skb); + TCP_ECN_create_request(req, skb, sock_net(sk)); treq->iif = sk->sk_bound_dev_if; @@ -1108,6 +1116,7 @@ drop_and_release: drop_and_free: reqsk_free(req); drop: + NET_INC_STATS_BH(sock_net(sk), LINUX_MIB_LISTENDROPS); return 0; /* don't send reset */ } @@ -1163,7 +1172,7 @@ static struct sock * tcp_v6_syn_recv_sock(struct sock *sk, struct sk_buff *skb, newnp->opt = NULL; newnp->mcast_oif = inet6_iif(skb); newnp->mcast_hops = ipv6_hdr(skb)->hop_limit; - newnp->rcv_tclass = ipv6_tclass(ipv6_hdr(skb)); + newnp->rcv_tclass = ipv6_get_dsfield(ipv6_hdr(skb)); /* * No need to charge this sock to the relevant IPv6 refcnt debug socks count @@ -1243,7 +1252,7 @@ static struct sock * tcp_v6_syn_recv_sock(struct sock *sk, struct sk_buff *skb, newnp->opt = NULL; newnp->mcast_oif = inet6_iif(skb); newnp->mcast_hops = ipv6_hdr(skb)->hop_limit; - newnp->rcv_tclass = ipv6_tclass(ipv6_hdr(skb)); + newnp->rcv_tclass = ipv6_get_dsfield(ipv6_hdr(skb)); /* Clone native IPv6 options from listening socket (if any) @@ -1456,7 +1465,7 @@ ipv6_pktoptions: if (np->rxopt.bits.rxhlim || np->rxopt.bits.rxohlim) np->mcast_hops = ipv6_hdr(opt_skb)->hop_limit; if (np->rxopt.bits.rxtclass) - np->rcv_tclass = ipv6_tclass(ipv6_hdr(skb)); + np->rcv_tclass = ipv6_get_dsfield(ipv6_hdr(skb)); if (ipv6_opt_accepted(sk, opt_skb)) { skb_set_owner_r(opt_skb, sk); opt_skb = xchg(&np->pktoptions, opt_skb); @@ -1598,6 +1607,7 @@ do_time_wait: struct sock *sk2; sk2 = inet6_lookup_listener(dev_net(skb->dev), &tcp_hashinfo, + &ipv6_hdr(skb)->saddr, th->source, &ipv6_hdr(skb)->daddr, ntohs(th->dest), inet6_iif(skb)); if (sk2 != NULL) { diff --git a/net/ipv6/udp.c b/net/ipv6/udp.c index dfaa29b8b293..599e1ba6d1ce 100644 --- a/net/ipv6/udp.c +++ b/net/ipv6/udp.c @@ -45,6 +45,7 @@ #include <net/tcp_states.h> #include <net/ip6_checksum.h> #include <net/xfrm.h> +#include <net/inet6_hashtables.h> #include <linux/proc_fs.h> #include <linux/seq_file.h> @@ -203,7 +204,8 @@ static struct sock *udp6_lib_lookup2(struct net *net, { struct sock *sk, *result; struct hlist_nulls_node *node; - int score, badness; + int score, badness, matches = 0, reuseport = 0; + u32 hash = 0; begin: result = NULL; @@ -214,8 +216,18 @@ begin: if (score > badness) { result = sk; badness = score; - if (score == SCORE2_MAX) + reuseport = sk->sk_reuseport; + if (reuseport) { + hash = inet6_ehashfn(net, daddr, hnum, + saddr, sport); + matches = 1; + } else if (score == SCORE2_MAX) goto exact_match; + } else if (score == badness && reuseport) { + matches++; + if (((u64)hash * matches) >> 32 == 0) + result = sk; + hash = next_pseudo_random32(hash); } } /* @@ -249,7 +261,8 @@ struct sock *__udp6_lib_lookup(struct net *net, unsigned short hnum = ntohs(dport); unsigned int hash2, slot2, slot = udp_hashfn(net, hnum, udptable->mask); struct udp_hslot *hslot2, *hslot = &udptable->hash[slot]; - int score, badness; + int score, badness, matches = 0, reuseport = 0; + u32 hash = 0; rcu_read_lock(); if (hslot->count > 10) { @@ -284,6 +297,17 @@ begin: if (score > badness) { result = sk; badness = score; + reuseport = sk->sk_reuseport; + if (reuseport) { + hash = inet6_ehashfn(net, daddr, hnum, + saddr, sport); + matches = 1; + } + } else if (score == badness && reuseport) { + matches++; + if (((u64)hash * matches) >> 32 == 0) + result = sk; + hash = next_pseudo_random32(hash); } } /* @@ -443,7 +467,7 @@ try_again: ip_cmsg_recv(msg, skb); } else { if (np->rxopt.all) - datagram_recv_ctl(sk, msg, skb); + ip6_datagram_recv_ctl(sk, msg, skb); } err = copied; @@ -752,40 +776,6 @@ static int __udp6_lib_mcast_deliver(struct net *net, struct sk_buff *skb, return 0; } -static inline int udp6_csum_init(struct sk_buff *skb, struct udphdr *uh, - int proto) -{ - int err; - - UDP_SKB_CB(skb)->partial_cov = 0; - UDP_SKB_CB(skb)->cscov = skb->len; - - if (proto == IPPROTO_UDPLITE) { - err = udplite_checksum_init(skb, uh); - if (err) - return err; - } - - if (uh->check == 0) { - /* RFC 2460 section 8.1 says that we SHOULD log - this error. Well, it is reasonable. - */ - LIMIT_NETDEBUG(KERN_INFO "IPv6: udp checksum is 0\n"); - return 1; - } - if (skb->ip_summed == CHECKSUM_COMPLETE && - !csum_ipv6_magic(&ipv6_hdr(skb)->saddr, &ipv6_hdr(skb)->daddr, - skb->len, proto, skb->csum)) - skb->ip_summed = CHECKSUM_UNNECESSARY; - - if (!skb_csum_unnecessary(skb)) - skb->csum = ~csum_unfold(csum_ipv6_magic(&ipv6_hdr(skb)->saddr, - &ipv6_hdr(skb)->daddr, - skb->len, proto, 0)); - - return 0; -} - int __udp6_lib_rcv(struct sk_buff *skb, struct udp_table *udptable, int proto) { @@ -1153,8 +1143,8 @@ do_udp_sendmsg: memset(opt, 0, sizeof(struct ipv6_txoptions)); opt->tot_len = sizeof(*opt); - err = datagram_send_ctl(sock_net(sk), sk, msg, &fl6, opt, - &hlimit, &tclass, &dontfrag); + err = ip6_datagram_send_ctl(sock_net(sk), sk, msg, &fl6, opt, + &hlimit, &tclass, &dontfrag); if (err < 0) { fl6_sock_release(flowlabel); return err; diff --git a/net/ipv6/udp_offload.c b/net/ipv6/udp_offload.c index 0c8934a317c2..cf05cf073c51 100644 --- a/net/ipv6/udp_offload.c +++ b/net/ipv6/udp_offload.c @@ -56,7 +56,8 @@ static struct sk_buff *udp6_ufo_fragment(struct sk_buff *skb, /* Packet is from an untrusted source, reset gso_segs. */ int type = skb_shinfo(skb)->gso_type; - if (unlikely(type & ~(SKB_GSO_UDP | SKB_GSO_DODGY) || + if (unlikely(type & ~(SKB_GSO_UDP | SKB_GSO_DODGY | + SKB_GSO_GRE) || !(type & (SKB_GSO_UDP)))) goto out; diff --git a/net/ipv6/xfrm6_mode_tunnel.c b/net/ipv6/xfrm6_mode_tunnel.c index 9f2095b19ad0..9bf6a74a71d2 100644 --- a/net/ipv6/xfrm6_mode_tunnel.c +++ b/net/ipv6/xfrm6_mode_tunnel.c @@ -69,8 +69,8 @@ static int xfrm6_mode_tunnel_input(struct xfrm_state *x, struct sk_buff *skb) if (!pskb_may_pull(skb, sizeof(struct ipv6hdr))) goto out; - if (skb_cloned(skb) && - (err = pskb_expand_head(skb, 0, 0, GFP_ATOMIC))) + err = skb_unclone(skb, GFP_ATOMIC); + if (err) goto out; if (x->props.flags & XFRM_STATE_DECAP_DSCP) diff --git a/net/ipv6/xfrm6_policy.c b/net/ipv6/xfrm6_policy.c index c9844135c9ca..4ef7bdb65440 100644 --- a/net/ipv6/xfrm6_policy.c +++ b/net/ipv6/xfrm6_policy.c @@ -110,7 +110,6 @@ static int xfrm6_fill_dst(struct xfrm_dst *xdst, struct net_device *dev, /* Sheit... I remember I did this right. Apparently, * it was magically lost, so this code needs audit */ - xdst->u.rt6.n = neigh_clone(rt->n); xdst->u.rt6.rt6i_flags = rt->rt6i_flags & (RTF_ANYCAST | RTF_LOCAL); xdst->u.rt6.rt6i_metric = rt->rt6i_metric; @@ -321,7 +320,51 @@ static struct ctl_table xfrm6_policy_table[] = { { } }; -static struct ctl_table_header *sysctl_hdr; +static int __net_init xfrm6_net_init(struct net *net) +{ + struct ctl_table *table; + struct ctl_table_header *hdr; + + table = xfrm6_policy_table; + if (!net_eq(net, &init_net)) { + table = kmemdup(table, sizeof(xfrm6_policy_table), GFP_KERNEL); + if (!table) + goto err_alloc; + + table[0].data = &net->xfrm.xfrm6_dst_ops.gc_thresh; + } + + hdr = register_net_sysctl(net, "net/ipv6", table); + if (!hdr) + goto err_reg; + + net->ipv6.sysctl.xfrm6_hdr = hdr; + return 0; + +err_reg: + if (!net_eq(net, &init_net)) + kfree(table); +err_alloc: + return -ENOMEM; +} + +static void __net_exit xfrm6_net_exit(struct net *net) +{ + struct ctl_table *table; + + if (net->ipv6.sysctl.xfrm6_hdr == NULL) + return; + + table = net->ipv6.sysctl.xfrm6_hdr->ctl_table_arg; + unregister_net_sysctl_table(net->ipv6.sysctl.xfrm6_hdr); + if (!net_eq(net, &init_net)) + kfree(table); +} + +static struct pernet_operations xfrm6_net_ops = { + .init = xfrm6_net_init, + .exit = xfrm6_net_exit, +}; #endif int __init xfrm6_init(void) @@ -340,8 +383,7 @@ int __init xfrm6_init(void) goto out_policy; #ifdef CONFIG_SYSCTL - sysctl_hdr = register_net_sysctl(&init_net, "net/ipv6", - xfrm6_policy_table); + register_pernet_subsys(&xfrm6_net_ops); #endif out: return ret; @@ -353,8 +395,7 @@ out_policy: void xfrm6_fini(void) { #ifdef CONFIG_SYSCTL - if (sysctl_hdr) - unregister_net_sysctl_table(sysctl_hdr); + unregister_pernet_subsys(&xfrm6_net_ops); #endif xfrm6_policy_fini(); xfrm6_state_fini(); diff --git a/net/ipv6/xfrm6_tunnel.c b/net/ipv6/xfrm6_tunnel.c index ee5a7065aacc..6cc48012b730 100644 --- a/net/ipv6/xfrm6_tunnel.c +++ b/net/ipv6/xfrm6_tunnel.c @@ -72,7 +72,7 @@ static inline unsigned int xfrm6_tunnel_spi_hash_byaddr(const xfrm_address_t *ad { unsigned int h; - h = (__force u32)(addr->a6[0] ^ addr->a6[1] ^ addr->a6[2] ^ addr->a6[3]); + h = ipv6_addr_hash((const struct in6_addr *)addr); h ^= h >> 16; h ^= h >> 8; h &= XFRM6_TUNNEL_SPI_BYADDR_HSIZE - 1; @@ -94,7 +94,7 @@ static struct xfrm6_tunnel_spi *__xfrm6_tunnel_spi_lookup(struct net *net, const hlist_for_each_entry_rcu(x6spi, pos, &xfrm6_tn->spi_byaddr[xfrm6_tunnel_spi_hash_byaddr(saddr)], list_byaddr) { - if (memcmp(&x6spi->addr, saddr, sizeof(x6spi->addr)) == 0) + if (xfrm6_addr_equal(&x6spi->addr, saddr)) return x6spi; } @@ -211,7 +211,7 @@ static void xfrm6_tunnel_free_spi(struct net *net, xfrm_address_t *saddr) &xfrm6_tn->spi_byaddr[xfrm6_tunnel_spi_hash_byaddr(saddr)], list_byaddr) { - if (memcmp(&x6spi->addr, saddr, sizeof(x6spi->addr)) == 0) { + if (xfrm6_addr_equal(&x6spi->addr, saddr)) { if (atomic_dec_and_test(&x6spi->refcnt)) { hlist_del_rcu(&x6spi->list_byaddr); hlist_del_rcu(&x6spi->list_byspi); diff --git a/net/irda/af_irda.c b/net/irda/af_irda.c index b833677d83d6..d07e3a626446 100644 --- a/net/irda/af_irda.c +++ b/net/irda/af_irda.c @@ -2567,8 +2567,7 @@ bed: err); /* If watchdog is still activated, kill it! */ - if(timer_pending(&(self->watchdog))) - del_timer(&(self->watchdog)); + del_timer(&(self->watchdog)); IRDA_DEBUG(1, "%s(), ...waking up !\n", __func__); diff --git a/net/irda/irnet/irnet_ppp.c b/net/irda/irnet/irnet_ppp.c index 2bb2beb6a373..3c83a1e5ab03 100644 --- a/net/irda/irnet/irnet_ppp.c +++ b/net/irda/irnet/irnet_ppp.c @@ -214,8 +214,7 @@ irnet_get_discovery_log(irnet_socket * ap) * After reading : discoveries = NULL ; disco_index = Y ; disco_number = -1 */ static inline int -irnet_read_discovery_log(irnet_socket * ap, - char * event) +irnet_read_discovery_log(irnet_socket *ap, char *event, int buf_size) { int done_event = 0; @@ -237,12 +236,13 @@ irnet_read_discovery_log(irnet_socket * ap, if(ap->disco_index < ap->disco_number) { /* Write an event */ - sprintf(event, "Found %08x (%s) behind %08x {hints %02X-%02X}\n", - ap->discoveries[ap->disco_index].daddr, - ap->discoveries[ap->disco_index].info, - ap->discoveries[ap->disco_index].saddr, - ap->discoveries[ap->disco_index].hints[0], - ap->discoveries[ap->disco_index].hints[1]); + snprintf(event, buf_size, + "Found %08x (%s) behind %08x {hints %02X-%02X}\n", + ap->discoveries[ap->disco_index].daddr, + ap->discoveries[ap->disco_index].info, + ap->discoveries[ap->disco_index].saddr, + ap->discoveries[ap->disco_index].hints[0], + ap->discoveries[ap->disco_index].hints[1]); DEBUG(CTRL_INFO, "Writing discovery %d : %s\n", ap->disco_index, ap->discoveries[ap->disco_index].info); @@ -282,27 +282,24 @@ irnet_ctrl_read(irnet_socket * ap, size_t count) { DECLARE_WAITQUEUE(wait, current); - char event[64]; /* Max event is 61 char */ + char event[75]; ssize_t ret = 0; DENTER(CTRL_TRACE, "(ap=0x%p, count=%Zd)\n", ap, count); - /* Check if we can write an event out in one go */ - DABORT(count < sizeof(event), -EOVERFLOW, CTRL_ERROR, "Buffer to small.\n"); - #ifdef INITIAL_DISCOVERY /* Check if we have read the log */ - if(irnet_read_discovery_log(ap, event)) + if (irnet_read_discovery_log(ap, event, sizeof(event))) { - /* We have an event !!! Copy it to the user */ - if(copy_to_user(buf, event, strlen(event))) + count = min(strlen(event), count); + if (copy_to_user(buf, event, count)) { DERROR(CTRL_ERROR, "Invalid user space pointer.\n"); return -EFAULT; } DEXIT(CTRL_TRACE, "\n"); - return strlen(event); + return count; } #endif /* INITIAL_DISCOVERY */ @@ -339,79 +336,81 @@ irnet_ctrl_read(irnet_socket * ap, switch(irnet_events.log[ap->event_index].event) { case IRNET_DISCOVER: - sprintf(event, "Discovered %08x (%s) behind %08x {hints %02X-%02X}\n", - irnet_events.log[ap->event_index].daddr, - irnet_events.log[ap->event_index].name, - irnet_events.log[ap->event_index].saddr, - irnet_events.log[ap->event_index].hints.byte[0], - irnet_events.log[ap->event_index].hints.byte[1]); + snprintf(event, sizeof(event), + "Discovered %08x (%s) behind %08x {hints %02X-%02X}\n", + irnet_events.log[ap->event_index].daddr, + irnet_events.log[ap->event_index].name, + irnet_events.log[ap->event_index].saddr, + irnet_events.log[ap->event_index].hints.byte[0], + irnet_events.log[ap->event_index].hints.byte[1]); break; case IRNET_EXPIRE: - sprintf(event, "Expired %08x (%s) behind %08x {hints %02X-%02X}\n", - irnet_events.log[ap->event_index].daddr, - irnet_events.log[ap->event_index].name, - irnet_events.log[ap->event_index].saddr, - irnet_events.log[ap->event_index].hints.byte[0], - irnet_events.log[ap->event_index].hints.byte[1]); + snprintf(event, sizeof(event), + "Expired %08x (%s) behind %08x {hints %02X-%02X}\n", + irnet_events.log[ap->event_index].daddr, + irnet_events.log[ap->event_index].name, + irnet_events.log[ap->event_index].saddr, + irnet_events.log[ap->event_index].hints.byte[0], + irnet_events.log[ap->event_index].hints.byte[1]); break; case IRNET_CONNECT_TO: - sprintf(event, "Connected to %08x (%s) on ppp%d\n", - irnet_events.log[ap->event_index].daddr, - irnet_events.log[ap->event_index].name, - irnet_events.log[ap->event_index].unit); + snprintf(event, sizeof(event), "Connected to %08x (%s) on ppp%d\n", + irnet_events.log[ap->event_index].daddr, + irnet_events.log[ap->event_index].name, + irnet_events.log[ap->event_index].unit); break; case IRNET_CONNECT_FROM: - sprintf(event, "Connection from %08x (%s) on ppp%d\n", - irnet_events.log[ap->event_index].daddr, - irnet_events.log[ap->event_index].name, - irnet_events.log[ap->event_index].unit); + snprintf(event, sizeof(event), "Connection from %08x (%s) on ppp%d\n", + irnet_events.log[ap->event_index].daddr, + irnet_events.log[ap->event_index].name, + irnet_events.log[ap->event_index].unit); break; case IRNET_REQUEST_FROM: - sprintf(event, "Request from %08x (%s) behind %08x\n", - irnet_events.log[ap->event_index].daddr, - irnet_events.log[ap->event_index].name, - irnet_events.log[ap->event_index].saddr); + snprintf(event, sizeof(event), "Request from %08x (%s) behind %08x\n", + irnet_events.log[ap->event_index].daddr, + irnet_events.log[ap->event_index].name, + irnet_events.log[ap->event_index].saddr); break; case IRNET_NOANSWER_FROM: - sprintf(event, "No-answer from %08x (%s) on ppp%d\n", - irnet_events.log[ap->event_index].daddr, - irnet_events.log[ap->event_index].name, - irnet_events.log[ap->event_index].unit); + snprintf(event, sizeof(event), "No-answer from %08x (%s) on ppp%d\n", + irnet_events.log[ap->event_index].daddr, + irnet_events.log[ap->event_index].name, + irnet_events.log[ap->event_index].unit); break; case IRNET_BLOCKED_LINK: - sprintf(event, "Blocked link with %08x (%s) on ppp%d\n", - irnet_events.log[ap->event_index].daddr, - irnet_events.log[ap->event_index].name, - irnet_events.log[ap->event_index].unit); + snprintf(event, sizeof(event), "Blocked link with %08x (%s) on ppp%d\n", + irnet_events.log[ap->event_index].daddr, + irnet_events.log[ap->event_index].name, + irnet_events.log[ap->event_index].unit); break; case IRNET_DISCONNECT_FROM: - sprintf(event, "Disconnection from %08x (%s) on ppp%d\n", - irnet_events.log[ap->event_index].daddr, - irnet_events.log[ap->event_index].name, - irnet_events.log[ap->event_index].unit); + snprintf(event, sizeof(event), "Disconnection from %08x (%s) on ppp%d\n", + irnet_events.log[ap->event_index].daddr, + irnet_events.log[ap->event_index].name, + irnet_events.log[ap->event_index].unit); break; case IRNET_DISCONNECT_TO: - sprintf(event, "Disconnected to %08x (%s)\n", - irnet_events.log[ap->event_index].daddr, - irnet_events.log[ap->event_index].name); + snprintf(event, sizeof(event), "Disconnected to %08x (%s)\n", + irnet_events.log[ap->event_index].daddr, + irnet_events.log[ap->event_index].name); break; default: - sprintf(event, "Bug\n"); + snprintf(event, sizeof(event), "Bug\n"); } /* Increment our event index */ ap->event_index = (ap->event_index + 1) % IRNET_MAX_EVENTS; DEBUG(CTRL_INFO, "Event is :%s", event); - /* Copy it to the user */ - if(copy_to_user(buf, event, strlen(event))) + count = min(strlen(event), count); + if (copy_to_user(buf, event, count)) { DERROR(CTRL_ERROR, "Invalid user space pointer.\n"); return -EFAULT; } DEXIT(CTRL_TRACE, "\n"); - return strlen(event); + return count; } /*------------------------------------------------------------------*/ diff --git a/net/iucv/iucv.c b/net/iucv/iucv.c index 3ad1f9db5f8b..df082508362d 100644 --- a/net/iucv/iucv.c +++ b/net/iucv/iucv.c @@ -1806,7 +1806,7 @@ static void iucv_external_interrupt(struct ext_code ext_code, struct iucv_irq_data *p; struct iucv_irq_list *work; - kstat_cpu(smp_processor_id()).irqs[EXTINT_IUC]++; + inc_irq_stat(IRQEXT_IUC); p = iucv_irq_data[smp_processor_id()]; if (p->ippathid >= iucv_max_pathid) { WARN_ON(p->ippathid >= iucv_max_pathid); diff --git a/net/key/af_key.c b/net/key/af_key.c index 5b426a646544..7b3ba32ca678 100644 --- a/net/key/af_key.c +++ b/net/key/af_key.c @@ -203,7 +203,6 @@ static int pfkey_broadcast_one(struct sk_buff *skb, struct sk_buff **skb2, } if (*skb2 != NULL) { if (atomic_read(&sk->sk_rmem_alloc) <= sk->sk_rcvbuf) { - skb_orphan(*skb2); skb_set_owner_r(*skb2, sk); skb_queue_tail(&sk->sk_receive_queue, *skb2); sk->sk_data_ready(sk, (*skb2)->len); @@ -762,7 +761,7 @@ static struct sk_buff *__pfkey_xfrm_state2msg(const struct xfrm_state *x, } /* identity & sensitivity */ - if (xfrm_addr_cmp(&x->sel.saddr, &x->props.saddr, x->props.family)) + if (!xfrm_addr_equal(&x->sel.saddr, &x->props.saddr, x->props.family)) size += sizeof(struct sadb_address) + sockaddr_size; if (add_keys) { @@ -816,18 +815,21 @@ static struct sk_buff *__pfkey_xfrm_state2msg(const struct xfrm_state *x, sa->sadb_sa_auth = 0; if (x->aalg) { struct xfrm_algo_desc *a = xfrm_aalg_get_byname(x->aalg->alg_name, 0); - sa->sadb_sa_auth = a ? a->desc.sadb_alg_id : 0; + sa->sadb_sa_auth = (a && a->pfkey_supported) ? + a->desc.sadb_alg_id : 0; } sa->sadb_sa_encrypt = 0; BUG_ON(x->ealg && x->calg); if (x->ealg) { struct xfrm_algo_desc *a = xfrm_ealg_get_byname(x->ealg->alg_name, 0); - sa->sadb_sa_encrypt = a ? a->desc.sadb_alg_id : 0; + sa->sadb_sa_encrypt = (a && a->pfkey_supported) ? + a->desc.sadb_alg_id : 0; } /* KAME compatible: sadb_sa_encrypt is overloaded with calg id */ if (x->calg) { struct xfrm_algo_desc *a = xfrm_calg_get_byname(x->calg->alg_name, 0); - sa->sadb_sa_encrypt = a ? a->desc.sadb_alg_id : 0; + sa->sadb_sa_encrypt = (a && a->pfkey_supported) ? + a->desc.sadb_alg_id : 0; } sa->sadb_sa_flags = 0; @@ -909,8 +911,8 @@ static struct sk_buff *__pfkey_xfrm_state2msg(const struct xfrm_state *x, if (!addr->sadb_address_prefixlen) BUG(); - if (xfrm_addr_cmp(&x->sel.saddr, &x->props.saddr, - x->props.family)) { + if (!xfrm_addr_equal(&x->sel.saddr, &x->props.saddr, + x->props.family)) { addr = (struct sadb_address*) skb_put(skb, sizeof(struct sadb_address)+sockaddr_size); addr->sadb_address_len = @@ -1138,7 +1140,7 @@ static struct xfrm_state * pfkey_msg2xfrm_state(struct net *net, if (sa->sadb_sa_auth) { int keysize = 0; struct xfrm_algo_desc *a = xfrm_aalg_get_byid(sa->sadb_sa_auth); - if (!a) { + if (!a || !a->pfkey_supported) { err = -ENOSYS; goto out; } @@ -1160,7 +1162,7 @@ static struct xfrm_state * pfkey_msg2xfrm_state(struct net *net, if (sa->sadb_sa_encrypt) { if (hdr->sadb_msg_satype == SADB_X_SATYPE_IPCOMP) { struct xfrm_algo_desc *a = xfrm_calg_get_byid(sa->sadb_sa_encrypt); - if (!a) { + if (!a || !a->pfkey_supported) { err = -ENOSYS; goto out; } @@ -1172,7 +1174,7 @@ static struct xfrm_state * pfkey_msg2xfrm_state(struct net *net, } else { int keysize = 0; struct xfrm_algo_desc *a = xfrm_ealg_get_byid(sa->sadb_sa_encrypt); - if (!a) { + if (!a || !a->pfkey_supported) { err = -ENOSYS; goto out; } @@ -1321,7 +1323,7 @@ static int pfkey_getspi(struct sock *sk, struct sk_buff *skb, const struct sadb_ if (hdr->sadb_msg_seq) { x = xfrm_find_acq_byseq(net, DUMMY_MARK, hdr->sadb_msg_seq); - if (x && xfrm_addr_cmp(&x->id.daddr, xdaddr, family)) { + if (x && !xfrm_addr_equal(&x->id.daddr, xdaddr, family)) { xfrm_state_put(x); x = NULL; } @@ -1578,13 +1580,13 @@ static struct sk_buff *compose_sadb_supported(const struct sadb_msg *orig, struct sadb_msg *hdr; int len, auth_len, enc_len, i; - auth_len = xfrm_count_auth_supported(); + auth_len = xfrm_count_pfkey_auth_supported(); if (auth_len) { auth_len *= sizeof(struct sadb_alg); auth_len += sizeof(struct sadb_supported); } - enc_len = xfrm_count_enc_supported(); + enc_len = xfrm_count_pfkey_enc_supported(); if (enc_len) { enc_len *= sizeof(struct sadb_alg); enc_len += sizeof(struct sadb_supported); @@ -1615,6 +1617,8 @@ static struct sk_buff *compose_sadb_supported(const struct sadb_msg *orig, struct xfrm_algo_desc *aalg = xfrm_aalg_get_byidx(i); if (!aalg) break; + if (!aalg->pfkey_supported) + continue; if (aalg->available) *ap++ = aalg->desc; } @@ -1634,6 +1638,8 @@ static struct sk_buff *compose_sadb_supported(const struct sadb_msg *orig, struct xfrm_algo_desc *ealg = xfrm_ealg_get_byidx(i); if (!ealg) break; + if (!ealg->pfkey_supported) + continue; if (ealg->available) *ap++ = ealg->desc; } @@ -2825,6 +2831,8 @@ static int count_ah_combs(const struct xfrm_tmpl *t) const struct xfrm_algo_desc *aalg = xfrm_aalg_get_byidx(i); if (!aalg) break; + if (!aalg->pfkey_supported) + continue; if (aalg_tmpl_set(t, aalg) && aalg->available) sz += sizeof(struct sadb_comb); } @@ -2840,6 +2848,9 @@ static int count_esp_combs(const struct xfrm_tmpl *t) if (!ealg) break; + if (!ealg->pfkey_supported) + continue; + if (!(ealg_tmpl_set(t, ealg) && ealg->available)) continue; @@ -2848,6 +2859,9 @@ static int count_esp_combs(const struct xfrm_tmpl *t) if (!aalg) break; + if (!aalg->pfkey_supported) + continue; + if (aalg_tmpl_set(t, aalg) && aalg->available) sz += sizeof(struct sadb_comb); } @@ -2871,6 +2885,9 @@ static void dump_ah_combs(struct sk_buff *skb, const struct xfrm_tmpl *t) if (!aalg) break; + if (!aalg->pfkey_supported) + continue; + if (aalg_tmpl_set(t, aalg) && aalg->available) { struct sadb_comb *c; c = (struct sadb_comb*)skb_put(skb, sizeof(struct sadb_comb)); @@ -2903,6 +2920,9 @@ static void dump_esp_combs(struct sk_buff *skb, const struct xfrm_tmpl *t) if (!ealg) break; + if (!ealg->pfkey_supported) + continue; + if (!(ealg_tmpl_set(t, ealg) && ealg->available)) continue; @@ -2911,6 +2931,8 @@ static void dump_esp_combs(struct sk_buff *skb, const struct xfrm_tmpl *t) const struct xfrm_algo_desc *aalg = xfrm_aalg_get_byidx(k); if (!aalg) break; + if (!aalg->pfkey_supported) + continue; if (!(aalg_tmpl_set(t, aalg) && aalg->available)) continue; c = (struct sadb_comb*)skb_put(skb, sizeof(struct sadb_comb)); diff --git a/net/l2tp/l2tp_core.c b/net/l2tp/l2tp_core.c index 1a9f3723c13c..dcfd64e83ab7 100644 --- a/net/l2tp/l2tp_core.c +++ b/net/l2tp/l2tp_core.c @@ -101,6 +101,7 @@ struct l2tp_skb_cb { static atomic_t l2tp_tunnel_count; static atomic_t l2tp_session_count; +static struct workqueue_struct *l2tp_wq; /* per-net private data for this module */ static unsigned int l2tp_net_id; @@ -122,7 +123,6 @@ static inline struct l2tp_net *l2tp_pernet(struct net *net) return net_generic(net, l2tp_net_id); } - /* Tunnel reference counts. Incremented per session that is added to * the tunnel. */ @@ -168,6 +168,51 @@ l2tp_session_id_hash_2(struct l2tp_net *pn, u32 session_id) } +/* Lookup the tunnel socket, possibly involving the fs code if the socket is + * owned by userspace. A struct sock returned from this function must be + * released using l2tp_tunnel_sock_put once you're done with it. + */ +struct sock *l2tp_tunnel_sock_lookup(struct l2tp_tunnel *tunnel) +{ + int err = 0; + struct socket *sock = NULL; + struct sock *sk = NULL; + + if (!tunnel) + goto out; + + if (tunnel->fd >= 0) { + /* Socket is owned by userspace, who might be in the process + * of closing it. Look the socket up using the fd to ensure + * consistency. + */ + sock = sockfd_lookup(tunnel->fd, &err); + if (sock) + sk = sock->sk; + } else { + /* Socket is owned by kernelspace */ + sk = tunnel->sock; + } + +out: + return sk; +} +EXPORT_SYMBOL_GPL(l2tp_tunnel_sock_lookup); + +/* Drop a reference to a tunnel socket obtained via. l2tp_tunnel_sock_put */ +void l2tp_tunnel_sock_put(struct sock *sk) +{ + struct l2tp_tunnel *tunnel = l2tp_sock_to_tunnel(sk); + if (tunnel) { + if (tunnel->fd >= 0) { + /* Socket is owned by userspace */ + sockfd_put(sk->sk_socket); + } + sock_put(sk); + } +} +EXPORT_SYMBOL_GPL(l2tp_tunnel_sock_put); + /* Lookup a session by id in the global session list */ static struct l2tp_session *l2tp_session_find_2(struct net *net, u32 session_id) @@ -1123,8 +1168,6 @@ int l2tp_xmit_skb(struct l2tp_session *session, struct sk_buff *skb, int hdr_len struct udphdr *uh; struct inet_sock *inet; __wsum csum; - int old_headroom; - int new_headroom; int headroom; int uhlen = (tunnel->encap == L2TP_ENCAPTYPE_UDP) ? sizeof(struct udphdr) : 0; int udp_len; @@ -1136,16 +1179,12 @@ int l2tp_xmit_skb(struct l2tp_session *session, struct sk_buff *skb, int hdr_len */ headroom = NET_SKB_PAD + sizeof(struct iphdr) + uhlen + hdr_len; - old_headroom = skb_headroom(skb); if (skb_cow_head(skb, headroom)) { kfree_skb(skb); return NET_XMIT_DROP; } - new_headroom = skb_headroom(skb); skb_orphan(skb); - skb->truesize += new_headroom - old_headroom; - /* Setup L2TP header */ session->build_header(session, __skb_push(skb, hdr_len)); @@ -1232,6 +1271,7 @@ EXPORT_SYMBOL_GPL(l2tp_xmit_skb); static void l2tp_tunnel_destruct(struct sock *sk) { struct l2tp_tunnel *tunnel; + struct l2tp_net *pn; tunnel = sk->sk_user_data; if (tunnel == NULL) @@ -1239,9 +1279,8 @@ static void l2tp_tunnel_destruct(struct sock *sk) l2tp_info(tunnel, L2TP_MSG_CONTROL, "%s: closing...\n", tunnel->name); - /* Close all sessions */ - l2tp_tunnel_closeall(tunnel); + /* Disable udp encapsulation */ switch (tunnel->encap) { case L2TP_ENCAPTYPE_UDP: /* No longer an encapsulation socket. See net/ipv4/udp.c */ @@ -1253,17 +1292,23 @@ static void l2tp_tunnel_destruct(struct sock *sk) } /* Remove hooks into tunnel socket */ - tunnel->sock = NULL; sk->sk_destruct = tunnel->old_sk_destruct; sk->sk_user_data = NULL; + tunnel->sock = NULL; - /* Call the original destructor */ - if (sk->sk_destruct) - (*sk->sk_destruct)(sk); + /* Remove the tunnel struct from the tunnel list */ + pn = l2tp_pernet(tunnel->l2tp_net); + spin_lock_bh(&pn->l2tp_tunnel_list_lock); + list_del_rcu(&tunnel->list); + spin_unlock_bh(&pn->l2tp_tunnel_list_lock); + atomic_dec(&l2tp_tunnel_count); - /* We're finished with the socket */ + l2tp_tunnel_closeall(tunnel); l2tp_tunnel_dec_refcount(tunnel); + /* Call the original destructor */ + if (sk->sk_destruct) + (*sk->sk_destruct)(sk); end: return; } @@ -1337,48 +1382,77 @@ again: */ static void l2tp_tunnel_free(struct l2tp_tunnel *tunnel) { - struct l2tp_net *pn = l2tp_pernet(tunnel->l2tp_net); - BUG_ON(atomic_read(&tunnel->ref_count) != 0); BUG_ON(tunnel->sock != NULL); - l2tp_info(tunnel, L2TP_MSG_CONTROL, "%s: free...\n", tunnel->name); - - /* Remove from tunnel list */ - spin_lock_bh(&pn->l2tp_tunnel_list_lock); - list_del_rcu(&tunnel->list); kfree_rcu(tunnel, rcu); - spin_unlock_bh(&pn->l2tp_tunnel_list_lock); +} - atomic_dec(&l2tp_tunnel_count); +/* Workqueue tunnel deletion function */ +static void l2tp_tunnel_del_work(struct work_struct *work) +{ + struct l2tp_tunnel *tunnel = NULL; + struct socket *sock = NULL; + struct sock *sk = NULL; + + tunnel = container_of(work, struct l2tp_tunnel, del_work); + sk = l2tp_tunnel_sock_lookup(tunnel); + if (!sk) + return; + + sock = sk->sk_socket; + BUG_ON(!sock); + + /* If the tunnel socket was created directly by the kernel, use the + * sk_* API to release the socket now. Otherwise go through the + * inet_* layer to shut the socket down, and let userspace close it. + * In either case the tunnel resources are freed in the socket + * destructor when the tunnel socket goes away. + */ + if (sock->file == NULL) { + kernel_sock_shutdown(sock, SHUT_RDWR); + sk_release_kernel(sk); + } else { + inet_shutdown(sock, 2); + } + + l2tp_tunnel_sock_put(sk); } /* Create a socket for the tunnel, if one isn't set up by * userspace. This is used for static tunnels where there is no * managing L2TP daemon. + * + * Since we don't want these sockets to keep a namespace alive by + * themselves, we drop the socket's namespace refcount after creation. + * These sockets are freed when the namespace exits using the pernet + * exit hook. */ -static int l2tp_tunnel_sock_create(u32 tunnel_id, u32 peer_tunnel_id, struct l2tp_tunnel_cfg *cfg, struct socket **sockp) +static int l2tp_tunnel_sock_create(struct net *net, + u32 tunnel_id, + u32 peer_tunnel_id, + struct l2tp_tunnel_cfg *cfg, + struct socket **sockp) { int err = -EINVAL; - struct sockaddr_in udp_addr; + struct socket *sock = NULL; + struct sockaddr_in udp_addr = {0}; + struct sockaddr_l2tpip ip_addr = {0}; #if IS_ENABLED(CONFIG_IPV6) - struct sockaddr_in6 udp6_addr; - struct sockaddr_l2tpip6 ip6_addr; + struct sockaddr_in6 udp6_addr = {0}; + struct sockaddr_l2tpip6 ip6_addr = {0}; #endif - struct sockaddr_l2tpip ip_addr; - struct socket *sock = NULL; switch (cfg->encap) { case L2TP_ENCAPTYPE_UDP: #if IS_ENABLED(CONFIG_IPV6) if (cfg->local_ip6 && cfg->peer_ip6) { - err = sock_create(AF_INET6, SOCK_DGRAM, 0, sockp); + err = sock_create_kern(AF_INET6, SOCK_DGRAM, 0, &sock); if (err < 0) goto out; - sock = *sockp; + sk_change_net(sock->sk, net); - memset(&udp6_addr, 0, sizeof(udp6_addr)); udp6_addr.sin6_family = AF_INET6; memcpy(&udp6_addr.sin6_addr, cfg->local_ip6, sizeof(udp6_addr.sin6_addr)); @@ -1400,13 +1474,12 @@ static int l2tp_tunnel_sock_create(u32 tunnel_id, u32 peer_tunnel_id, struct l2t } else #endif { - err = sock_create(AF_INET, SOCK_DGRAM, 0, sockp); + err = sock_create_kern(AF_INET, SOCK_DGRAM, 0, &sock); if (err < 0) goto out; - sock = *sockp; + sk_change_net(sock->sk, net); - memset(&udp_addr, 0, sizeof(udp_addr)); udp_addr.sin_family = AF_INET; udp_addr.sin_addr = cfg->local_ip; udp_addr.sin_port = htons(cfg->local_udp_port); @@ -1433,14 +1506,13 @@ static int l2tp_tunnel_sock_create(u32 tunnel_id, u32 peer_tunnel_id, struct l2t case L2TP_ENCAPTYPE_IP: #if IS_ENABLED(CONFIG_IPV6) if (cfg->local_ip6 && cfg->peer_ip6) { - err = sock_create(AF_INET6, SOCK_DGRAM, IPPROTO_L2TP, - sockp); + err = sock_create_kern(AF_INET6, SOCK_DGRAM, + IPPROTO_L2TP, &sock); if (err < 0) goto out; - sock = *sockp; + sk_change_net(sock->sk, net); - memset(&ip6_addr, 0, sizeof(ip6_addr)); ip6_addr.l2tp_family = AF_INET6; memcpy(&ip6_addr.l2tp_addr, cfg->local_ip6, sizeof(ip6_addr.l2tp_addr)); @@ -1462,14 +1534,13 @@ static int l2tp_tunnel_sock_create(u32 tunnel_id, u32 peer_tunnel_id, struct l2t } else #endif { - err = sock_create(AF_INET, SOCK_DGRAM, IPPROTO_L2TP, - sockp); + err = sock_create_kern(AF_INET, SOCK_DGRAM, + IPPROTO_L2TP, &sock); if (err < 0) goto out; - sock = *sockp; + sk_change_net(sock->sk, net); - memset(&ip_addr, 0, sizeof(ip_addr)); ip_addr.l2tp_family = AF_INET; ip_addr.l2tp_addr = cfg->local_ip; ip_addr.l2tp_conn_id = tunnel_id; @@ -1493,8 +1564,10 @@ static int l2tp_tunnel_sock_create(u32 tunnel_id, u32 peer_tunnel_id, struct l2t } out: + *sockp = sock; if ((err < 0) && sock) { - sock_release(sock); + kernel_sock_shutdown(sock, SHUT_RDWR); + sk_release_kernel(sock->sk); *sockp = NULL; } @@ -1517,15 +1590,23 @@ int l2tp_tunnel_create(struct net *net, int fd, int version, u32 tunnel_id, u32 * kernel socket. */ if (fd < 0) { - err = l2tp_tunnel_sock_create(tunnel_id, peer_tunnel_id, cfg, &sock); + err = l2tp_tunnel_sock_create(net, tunnel_id, peer_tunnel_id, + cfg, &sock); if (err < 0) goto err; } else { - err = -EBADF; sock = sockfd_lookup(fd, &err); if (!sock) { - pr_err("tunl %hu: sockfd_lookup(fd=%d) returned %d\n", + pr_err("tunl %u: sockfd_lookup(fd=%d) returned %d\n", tunnel_id, fd, err); + err = -EBADF; + goto err; + } + + /* Reject namespace mismatches */ + if (!net_eq(sock_net(sock->sk), net)) { + pr_err("tunl %u: netns mismatch\n", tunnel_id); + err = -EINVAL; goto err; } } @@ -1607,10 +1688,14 @@ int l2tp_tunnel_create(struct net *net, int fd, int version, u32 tunnel_id, u32 tunnel->old_sk_destruct = sk->sk_destruct; sk->sk_destruct = &l2tp_tunnel_destruct; tunnel->sock = sk; + tunnel->fd = fd; lockdep_set_class_and_name(&sk->sk_lock.slock, &l2tp_socket_class, "l2tp_sock"); sk->sk_allocation = GFP_ATOMIC; + /* Init delete workqueue struct */ + INIT_WORK(&tunnel->del_work, l2tp_tunnel_del_work); + /* Add tunnel to our list */ INIT_LIST_HEAD(&tunnel->list); atomic_inc(&l2tp_tunnel_count); @@ -1642,25 +1727,7 @@ EXPORT_SYMBOL_GPL(l2tp_tunnel_create); */ int l2tp_tunnel_delete(struct l2tp_tunnel *tunnel) { - int err = 0; - struct socket *sock = tunnel->sock ? tunnel->sock->sk_socket : NULL; - - /* Force the tunnel socket to close. This will eventually - * cause the tunnel to be deleted via the normal socket close - * mechanisms when userspace closes the tunnel socket. - */ - if (sock != NULL) { - err = inet_shutdown(sock, 2); - - /* If the tunnel's socket was created by the kernel, - * close the socket here since the socket was not - * created by userspace. - */ - if (sock->file == NULL) - err = inet_release(sock); - } - - return err; + return (false == queue_work(l2tp_wq, &tunnel->del_work)); } EXPORT_SYMBOL_GPL(l2tp_tunnel_delete); @@ -1844,8 +1911,21 @@ static __net_init int l2tp_init_net(struct net *net) return 0; } +static __net_exit void l2tp_exit_net(struct net *net) +{ + struct l2tp_net *pn = l2tp_pernet(net); + struct l2tp_tunnel *tunnel = NULL; + + rcu_read_lock_bh(); + list_for_each_entry_rcu(tunnel, &pn->l2tp_tunnel_list, list) { + (void)l2tp_tunnel_delete(tunnel); + } + rcu_read_unlock_bh(); +} + static struct pernet_operations l2tp_net_ops = { .init = l2tp_init_net, + .exit = l2tp_exit_net, .id = &l2tp_net_id, .size = sizeof(struct l2tp_net), }; @@ -1858,6 +1938,13 @@ static int __init l2tp_init(void) if (rc) goto out; + l2tp_wq = alloc_workqueue("l2tp", WQ_NON_REENTRANT | WQ_UNBOUND, 0); + if (!l2tp_wq) { + pr_err("alloc_workqueue failed\n"); + rc = -ENOMEM; + goto out; + } + pr_info("L2TP core driver, %s\n", L2TP_DRV_VERSION); out: @@ -1867,6 +1954,10 @@ out: static void __exit l2tp_exit(void) { unregister_pernet_device(&l2tp_net_ops); + if (l2tp_wq) { + destroy_workqueue(l2tp_wq); + l2tp_wq = NULL; + } } module_init(l2tp_init); diff --git a/net/l2tp/l2tp_core.h b/net/l2tp/l2tp_core.h index 56d583e083a7..8eb8f1d47f3a 100644 --- a/net/l2tp/l2tp_core.h +++ b/net/l2tp/l2tp_core.h @@ -188,7 +188,10 @@ struct l2tp_tunnel { int (*recv_payload_hook)(struct sk_buff *skb); void (*old_sk_destruct)(struct sock *); struct sock *sock; /* Parent socket */ - int fd; + int fd; /* Parent fd, if tunnel socket + * was created by userspace */ + + struct work_struct del_work; uint8_t priv[0]; /* private data */ }; @@ -228,6 +231,8 @@ out: return tunnel; } +extern struct sock *l2tp_tunnel_sock_lookup(struct l2tp_tunnel *tunnel); +extern void l2tp_tunnel_sock_put(struct sock *sk); extern struct l2tp_session *l2tp_session_find(struct net *net, struct l2tp_tunnel *tunnel, u32 session_id); extern struct l2tp_session *l2tp_session_find_nth(struct l2tp_tunnel *tunnel, int nth); extern struct l2tp_session *l2tp_session_find_by_ifname(struct net *net, char *ifname); diff --git a/net/l2tp/l2tp_ip.c b/net/l2tp/l2tp_ip.c index 61d8b75d2686..f7ac8f42fee2 100644 --- a/net/l2tp/l2tp_ip.c +++ b/net/l2tp/l2tp_ip.c @@ -115,6 +115,7 @@ static inline struct sock *l2tp_ip_bind_lookup(struct net *net, __be32 laddr, in */ static int l2tp_ip_recv(struct sk_buff *skb) { + struct net *net = dev_net(skb->dev); struct sock *sk; u32 session_id; u32 tunnel_id; @@ -142,7 +143,7 @@ static int l2tp_ip_recv(struct sk_buff *skb) } /* Ok, this is a data packet. Lookup the session. */ - session = l2tp_session_find(&init_net, NULL, session_id); + session = l2tp_session_find(net, NULL, session_id); if (session == NULL) goto discard; @@ -173,14 +174,14 @@ pass_up: goto discard; tunnel_id = ntohl(*(__be32 *) &skb->data[4]); - tunnel = l2tp_tunnel_find(&init_net, tunnel_id); + tunnel = l2tp_tunnel_find(net, tunnel_id); if (tunnel != NULL) sk = tunnel->sock; else { struct iphdr *iph = (struct iphdr *) skb_network_header(skb); read_lock_bh(&l2tp_ip_lock); - sk = __l2tp_ip_bind_lookup(&init_net, iph->daddr, 0, tunnel_id); + sk = __l2tp_ip_bind_lookup(net, iph->daddr, 0, tunnel_id); read_unlock_bh(&l2tp_ip_lock); } @@ -239,6 +240,7 @@ 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); int ret; int chk_addr_ret; @@ -251,7 +253,8 @@ static int l2tp_ip_bind(struct sock *sk, struct sockaddr *uaddr, int addr_len) ret = -EADDRINUSE; read_lock_bh(&l2tp_ip_lock); - if (__l2tp_ip_bind_lookup(&init_net, addr->l2tp_addr.s_addr, sk->sk_bound_dev_if, addr->l2tp_conn_id)) + if (__l2tp_ip_bind_lookup(net, addr->l2tp_addr.s_addr, + sk->sk_bound_dev_if, addr->l2tp_conn_id)) goto out_in_use; read_unlock_bh(&l2tp_ip_lock); @@ -260,7 +263,7 @@ static int l2tp_ip_bind(struct sock *sk, struct sockaddr *uaddr, int addr_len) if (sk->sk_state != TCP_CLOSE || addr_len < sizeof(struct sockaddr_l2tpip)) goto out; - chk_addr_ret = inet_addr_type(&init_net, addr->l2tp_addr.s_addr); + chk_addr_ret = inet_addr_type(net, addr->l2tp_addr.s_addr); ret = -EADDRNOTAVAIL; if (addr->l2tp_addr.s_addr && chk_addr_ret != RTN_LOCAL && chk_addr_ret != RTN_MULTICAST && chk_addr_ret != RTN_BROADCAST) @@ -369,7 +372,7 @@ static int l2tp_ip_backlog_recv(struct sock *sk, struct sk_buff *skb) return 0; drop: - IP_INC_STATS(&init_net, IPSTATS_MIB_INDISCARDS); + IP_INC_STATS(sock_net(sk), IPSTATS_MIB_INDISCARDS); kfree_skb(skb); return -1; } @@ -605,6 +608,7 @@ static struct inet_protosw l2tp_ip_protosw = { static struct net_protocol l2tp_ip_protocol __read_mostly = { .handler = l2tp_ip_recv, + .netns_ok = 1, }; static int __init l2tp_ip_init(void) diff --git a/net/l2tp/l2tp_ip6.c b/net/l2tp/l2tp_ip6.c index 927547171bc7..8ee4a86ae996 100644 --- a/net/l2tp/l2tp_ip6.c +++ b/net/l2tp/l2tp_ip6.c @@ -554,8 +554,8 @@ static int l2tp_ip6_sendmsg(struct kiocb *iocb, struct sock *sk, memset(opt, 0, sizeof(struct ipv6_txoptions)); opt->tot_len = sizeof(struct ipv6_txoptions); - err = datagram_send_ctl(sock_net(sk), sk, msg, &fl6, opt, - &hlimit, &tclass, &dontfrag); + err = ip6_datagram_send_ctl(sock_net(sk), sk, msg, &fl6, opt, + &hlimit, &tclass, &dontfrag); if (err < 0) { fl6_sock_release(flowlabel); return err; @@ -646,7 +646,7 @@ static int l2tp_ip6_recvmsg(struct kiocb *iocb, struct sock *sk, struct msghdr *msg, size_t len, int noblock, int flags, int *addr_len) { - struct inet_sock *inet = inet_sk(sk); + struct ipv6_pinfo *np = inet6_sk(sk); struct sockaddr_l2tpip6 *lsa = (struct sockaddr_l2tpip6 *)msg->msg_name; size_t copied = 0; int err = -EOPNOTSUPP; @@ -688,8 +688,8 @@ static int l2tp_ip6_recvmsg(struct kiocb *iocb, struct sock *sk, lsa->l2tp_scope_id = IP6CB(skb)->iif; } - if (inet->cmsg_flags) - ip_cmsg_recv(msg, skb); + if (np->rxopt.all) + ip6_datagram_recv_ctl(sk, msg, skb); if (flags & MSG_TRUNC) copied = skb->len; diff --git a/net/l2tp/l2tp_netlink.c b/net/l2tp/l2tp_netlink.c index bbba3a19e944..c1bab22db85e 100644 --- a/net/l2tp/l2tp_netlink.c +++ b/net/l2tp/l2tp_netlink.c @@ -37,6 +37,7 @@ static struct genl_family l2tp_nl_family = { .version = L2TP_GENL_VERSION, .hdrsize = 0, .maxattr = L2TP_ATTR_MAX, + .netnsok = true, }; /* Accessed under genl lock */ diff --git a/net/l2tp/l2tp_ppp.c b/net/l2tp/l2tp_ppp.c index 286366ef8930..716605c241f4 100644 --- a/net/l2tp/l2tp_ppp.c +++ b/net/l2tp/l2tp_ppp.c @@ -388,8 +388,6 @@ static int pppol2tp_xmit(struct ppp_channel *chan, struct sk_buff *skb) struct l2tp_session *session; struct l2tp_tunnel *tunnel; struct pppol2tp_session *ps; - int old_headroom; - int new_headroom; int uhlen, headroom; if (sock_flag(sk, SOCK_DEAD) || !(sk->sk_state & PPPOX_CONNECTED)) @@ -408,7 +406,6 @@ static int pppol2tp_xmit(struct ppp_channel *chan, struct sk_buff *skb) if (tunnel == NULL) goto abort_put_sess; - old_headroom = skb_headroom(skb); uhlen = (tunnel->encap == L2TP_ENCAPTYPE_UDP) ? sizeof(struct udphdr) : 0; headroom = NET_SKB_PAD + sizeof(struct iphdr) + /* IP header */ @@ -418,9 +415,6 @@ static int pppol2tp_xmit(struct ppp_channel *chan, struct sk_buff *skb) if (skb_cow_head(skb, headroom)) goto abort_put_sess_tun; - new_headroom = skb_headroom(skb); - skb->truesize += new_headroom - old_headroom; - /* Setup PPP header */ __skb_push(skb, sizeof(ppph)); skb->data[0] = ppph[0]; diff --git a/net/mac802154/wpan.c b/net/mac802154/wpan.c index 1191039c2b1b..d20c6d3c247d 100644 --- a/net/mac802154/wpan.c +++ b/net/mac802154/wpan.c @@ -41,7 +41,7 @@ static inline int mac802154_fetch_skb_u8(struct sk_buff *skb, u8 *val) return -EINVAL; *val = skb->data[0]; - skb_pull(skb, 1); + skb_pull(skb, 1); return 0; } @@ -137,16 +137,12 @@ static int mac802154_header_create(struct sk_buff *skb, struct ieee802154_addr dev_addr; struct mac802154_sub_if_data *priv = netdev_priv(dev); int pos = 2; - u8 *head; + u8 head[MAC802154_FRAME_HARD_HEADER_LEN]; u16 fc; if (!daddr) return -EINVAL; - head = kzalloc(MAC802154_FRAME_HARD_HEADER_LEN, GFP_KERNEL); - if (head == NULL) - return -ENOMEM; - head[pos++] = mac_cb(skb)->seq; /* DSN/BSN */ fc = mac_cb_type(skb); @@ -210,7 +206,6 @@ static int mac802154_header_create(struct sk_buff *skb, head[1] = fc >> 8; memcpy(skb_push(skb, pos), head, pos); - kfree(head); return pos; } @@ -389,7 +384,7 @@ void mac802154_wpan_setup(struct net_device *dev) static int mac802154_process_data(struct net_device *dev, struct sk_buff *skb) { - return netif_rx(skb); + return netif_rx_ni(skb); } static int diff --git a/net/netfilter/Kconfig b/net/netfilter/Kconfig index fefa514b9917..eb2c8ebf6d99 100644 --- a/net/netfilter/Kconfig +++ b/net/netfilter/Kconfig @@ -124,6 +124,12 @@ config NF_CONNTRACK_TIMESTAMP If unsure, say `N'. +config NF_CONNTRACK_LABELS + bool + help + This option enables support for assigning user-defined flag bits + to connection tracking entries. It selected by the connlabel match. + config NF_CT_PROTO_DCCP tristate 'DCCP protocol connection tracking support (EXPERIMENTAL)' depends on EXPERIMENTAL @@ -680,6 +686,13 @@ config NETFILTER_XT_TARGET_NFQUEUE To compile it as a module, choose M here. If unsure, say N. +config NETFILTER_XT_TARGET_NOTRACK + tristate '"NOTRACK" target support (DEPRECATED)' + depends on NF_CONNTRACK + depends on IP_NF_RAW || IP6_NF_RAW + depends on NETFILTER_ADVANCED + select NETFILTER_XT_TARGET_CT + config NETFILTER_XT_TARGET_RATEEST tristate '"RATEEST" target support' depends on NETFILTER_ADVANCED @@ -798,6 +811,15 @@ config NETFILTER_XT_MATCH_ADDRTYPE If you want to compile it as a module, say M here and read <file:Documentation/kbuild/modules.txt>. If unsure, say `N'. +config NETFILTER_XT_MATCH_BPF + tristate '"bpf" match support' + depends on NETFILTER_ADVANCED + help + BPF matching applies a linux socket filter to each packet and + accepts those for which the filter returns non-zero. + + To compile it as a module, choose M here. If unsure, say N. + config NETFILTER_XT_MATCH_CLUSTER tristate '"cluster" match support' depends on NF_CONNTRACK @@ -835,6 +857,18 @@ config NETFILTER_XT_MATCH_CONNBYTES If you want to compile it as a module, say M here and read <file:Documentation/kbuild/modules.txt>. If unsure, say `N'. +config NETFILTER_XT_MATCH_CONNLABEL + tristate '"connlabel" match support' + select NF_CONNTRACK_LABELS + depends on NETFILTER_ADVANCED + ---help--- + This match allows you to test and assign userspace-defined labels names + to a connection. The kernel only stores bit values - mapping + names to bits is done by userspace. + + Unlike connmark, more than 32 flag bits may be assigned to a + connection simultaneously. + config NETFILTER_XT_MATCH_CONNLIMIT tristate '"connlimit" match support"' depends on NF_CONNTRACK diff --git a/net/netfilter/Makefile b/net/netfilter/Makefile index 32596978df1d..a1abf87d43bf 100644 --- a/net/netfilter/Makefile +++ b/net/netfilter/Makefile @@ -4,6 +4,7 @@ nf_conntrack-y := nf_conntrack_core.o nf_conntrack_standalone.o nf_conntrack_exp nf_conntrack-$(CONFIG_NF_CONNTRACK_TIMEOUT) += nf_conntrack_timeout.o nf_conntrack-$(CONFIG_NF_CONNTRACK_TIMESTAMP) += nf_conntrack_timestamp.o nf_conntrack-$(CONFIG_NF_CONNTRACK_EVENTS) += nf_conntrack_ecache.o +nf_conntrack-$(CONFIG_NF_CONNTRACK_LABELS) += nf_conntrack_labels.o obj-$(CONFIG_NETFILTER) = netfilter.o @@ -98,9 +99,11 @@ obj-$(CONFIG_NETFILTER_XT_TARGET_IDLETIMER) += xt_IDLETIMER.o # matches obj-$(CONFIG_NETFILTER_XT_MATCH_ADDRTYPE) += xt_addrtype.o +obj-$(CONFIG_NETFILTER_XT_MATCH_BPF) += xt_bpf.o obj-$(CONFIG_NETFILTER_XT_MATCH_CLUSTER) += xt_cluster.o obj-$(CONFIG_NETFILTER_XT_MATCH_COMMENT) += xt_comment.o obj-$(CONFIG_NETFILTER_XT_MATCH_CONNBYTES) += xt_connbytes.o +obj-$(CONFIG_NETFILTER_XT_MATCH_CONNLABEL) += xt_connlabel.o obj-$(CONFIG_NETFILTER_XT_MATCH_CONNLIMIT) += xt_connlimit.o obj-$(CONFIG_NETFILTER_XT_MATCH_CONNTRACK) += xt_conntrack.o obj-$(CONFIG_NETFILTER_XT_MATCH_CPU) += xt_cpu.o diff --git a/net/netfilter/ipset/ip_set_hash_ip.c b/net/netfilter/ipset/ip_set_hash_ip.c index 5c0b78528e55..b7d4cb475ae6 100644 --- a/net/netfilter/ipset/ip_set_hash_ip.c +++ b/net/netfilter/ipset/ip_set_hash_ip.c @@ -234,7 +234,7 @@ hash_ip6_data_equal(const struct hash_ip6_elem *ip1, const struct hash_ip6_elem *ip2, u32 *multi) { - return ipv6_addr_cmp(&ip1->ip.in6, &ip2->ip.in6) == 0; + return ipv6_addr_equal(&ip1->ip.in6, &ip2->ip.in6); } static inline bool diff --git a/net/netfilter/ipset/ip_set_hash_ipport.c b/net/netfilter/ipset/ip_set_hash_ipport.c index 6283351f4eeb..d8f77bacae86 100644 --- a/net/netfilter/ipset/ip_set_hash_ipport.c +++ b/net/netfilter/ipset/ip_set_hash_ipport.c @@ -284,7 +284,7 @@ hash_ipport6_data_equal(const struct hash_ipport6_elem *ip1, const struct hash_ipport6_elem *ip2, u32 *multi) { - return ipv6_addr_cmp(&ip1->ip.in6, &ip2->ip.in6) == 0 && + return ipv6_addr_equal(&ip1->ip.in6, &ip2->ip.in6) && ip1->port == ip2->port && ip1->proto == ip2->proto; } diff --git a/net/netfilter/ipset/ip_set_hash_ipportip.c b/net/netfilter/ipset/ip_set_hash_ipportip.c index 6a21271c8d5a..1da1e955f38b 100644 --- a/net/netfilter/ipset/ip_set_hash_ipportip.c +++ b/net/netfilter/ipset/ip_set_hash_ipportip.c @@ -294,8 +294,8 @@ hash_ipportip6_data_equal(const struct hash_ipportip6_elem *ip1, const struct hash_ipportip6_elem *ip2, u32 *multi) { - return ipv6_addr_cmp(&ip1->ip.in6, &ip2->ip.in6) == 0 && - ipv6_addr_cmp(&ip1->ip2.in6, &ip2->ip2.in6) == 0 && + return ipv6_addr_equal(&ip1->ip.in6, &ip2->ip.in6) && + ipv6_addr_equal(&ip1->ip2.in6, &ip2->ip2.in6) && ip1->port == ip2->port && ip1->proto == ip2->proto; } diff --git a/net/netfilter/ipset/ip_set_hash_ipportnet.c b/net/netfilter/ipset/ip_set_hash_ipportnet.c index 2d5cd4ee30eb..f2627226a087 100644 --- a/net/netfilter/ipset/ip_set_hash_ipportnet.c +++ b/net/netfilter/ipset/ip_set_hash_ipportnet.c @@ -388,8 +388,8 @@ hash_ipportnet6_data_equal(const struct hash_ipportnet6_elem *ip1, const struct hash_ipportnet6_elem *ip2, u32 *multi) { - return ipv6_addr_cmp(&ip1->ip.in6, &ip2->ip.in6) == 0 && - ipv6_addr_cmp(&ip1->ip2.in6, &ip2->ip2.in6) == 0 && + return ipv6_addr_equal(&ip1->ip.in6, &ip2->ip.in6) && + ipv6_addr_equal(&ip1->ip2.in6, &ip2->ip2.in6) && ip1->cidr == ip2->cidr && ip1->port == ip2->port && ip1->proto == ip2->proto; diff --git a/net/netfilter/ipset/ip_set_hash_net.c b/net/netfilter/ipset/ip_set_hash_net.c index 29e94b981f3f..4b677cf6bf7d 100644 --- a/net/netfilter/ipset/ip_set_hash_net.c +++ b/net/netfilter/ipset/ip_set_hash_net.c @@ -286,7 +286,7 @@ hash_net6_data_equal(const struct hash_net6_elem *ip1, const struct hash_net6_elem *ip2, u32 *multi) { - return ipv6_addr_cmp(&ip1->ip.in6, &ip2->ip.in6) == 0 && + return ipv6_addr_equal(&ip1->ip.in6, &ip2->ip.in6) && ip1->cidr == ip2->cidr; } diff --git a/net/netfilter/ipset/ip_set_hash_netiface.c b/net/netfilter/ipset/ip_set_hash_netiface.c index 45a101439bc5..6ba985f1c96f 100644 --- a/net/netfilter/ipset/ip_set_hash_netiface.c +++ b/net/netfilter/ipset/ip_set_hash_netiface.c @@ -471,7 +471,7 @@ hash_netiface6_data_equal(const struct hash_netiface6_elem *ip1, const struct hash_netiface6_elem *ip2, u32 *multi) { - return ipv6_addr_cmp(&ip1->ip.in6, &ip2->ip.in6) == 0 && + return ipv6_addr_equal(&ip1->ip.in6, &ip2->ip.in6) && ip1->cidr == ip2->cidr && (++*multi) && ip1->physdev == ip2->physdev && diff --git a/net/netfilter/ipset/ip_set_hash_netport.c b/net/netfilter/ipset/ip_set_hash_netport.c index 7ef700de596c..af20c0c5ced2 100644 --- a/net/netfilter/ipset/ip_set_hash_netport.c +++ b/net/netfilter/ipset/ip_set_hash_netport.c @@ -350,7 +350,7 @@ hash_netport6_data_equal(const struct hash_netport6_elem *ip1, const struct hash_netport6_elem *ip2, u32 *multi) { - return ipv6_addr_cmp(&ip1->ip.in6, &ip2->ip.in6) == 0 && + return ipv6_addr_equal(&ip1->ip.in6, &ip2->ip.in6) && ip1->port == ip2->port && ip1->proto == ip2->proto && ip1->cidr == ip2->cidr; diff --git a/net/netfilter/ipvs/ip_vs_conn.c b/net/netfilter/ipvs/ip_vs_conn.c index 30e764ad021f..68e368a4beed 100644 --- a/net/netfilter/ipvs/ip_vs_conn.c +++ b/net/netfilter/ipvs/ip_vs_conn.c @@ -796,8 +796,7 @@ static void ip_vs_conn_expire(unsigned long data) */ if (likely(atomic_read(&cp->refcnt) == 1)) { /* delete the timer if it is activated by other users */ - if (timer_pending(&cp->timer)) - del_timer(&cp->timer); + del_timer(&cp->timer); /* does anybody control me? */ if (cp->control) diff --git a/net/netfilter/ipvs/ip_vs_proto_sctp.c b/net/netfilter/ipvs/ip_vs_proto_sctp.c index 746048b13ef3..ae8ec6f27688 100644 --- a/net/netfilter/ipvs/ip_vs_proto_sctp.c +++ b/net/netfilter/ipvs/ip_vs_proto_sctp.c @@ -61,14 +61,27 @@ sctp_conn_schedule(int af, struct sk_buff *skb, struct ip_vs_proto_data *pd, return 1; } +static void sctp_nat_csum(struct sk_buff *skb, sctp_sctphdr_t *sctph, + unsigned int sctphoff) +{ + __u32 crc32; + struct sk_buff *iter; + + crc32 = sctp_start_cksum((__u8 *)sctph, skb_headlen(skb) - sctphoff); + skb_walk_frags(skb, iter) + crc32 = sctp_update_cksum((u8 *) iter->data, + skb_headlen(iter), crc32); + sctph->checksum = sctp_end_cksum(crc32); + + skb->ip_summed = CHECKSUM_UNNECESSARY; +} + static int sctp_snat_handler(struct sk_buff *skb, struct ip_vs_protocol *pp, struct ip_vs_conn *cp, struct ip_vs_iphdr *iph) { sctp_sctphdr_t *sctph; unsigned int sctphoff = iph->len; - struct sk_buff *iter; - __be32 crc32; #ifdef CONFIG_IP_VS_IPV6 if (cp->af == AF_INET6 && iph->fragoffs) @@ -92,13 +105,7 @@ sctp_snat_handler(struct sk_buff *skb, struct ip_vs_protocol *pp, sctph = (void *) skb_network_header(skb) + sctphoff; sctph->source = cp->vport; - /* Calculate the checksum */ - crc32 = sctp_start_cksum((u8 *) sctph, skb_headlen(skb) - sctphoff); - skb_walk_frags(skb, iter) - crc32 = sctp_update_cksum((u8 *) iter->data, skb_headlen(iter), - crc32); - crc32 = sctp_end_cksum(crc32); - sctph->checksum = crc32; + sctp_nat_csum(skb, sctph, sctphoff); return 1; } @@ -109,8 +116,6 @@ sctp_dnat_handler(struct sk_buff *skb, struct ip_vs_protocol *pp, { sctp_sctphdr_t *sctph; unsigned int sctphoff = iph->len; - struct sk_buff *iter; - __be32 crc32; #ifdef CONFIG_IP_VS_IPV6 if (cp->af == AF_INET6 && iph->fragoffs) @@ -134,13 +139,7 @@ sctp_dnat_handler(struct sk_buff *skb, struct ip_vs_protocol *pp, sctph = (void *) skb_network_header(skb) + sctphoff; sctph->dest = cp->dport; - /* Calculate the checksum */ - crc32 = sctp_start_cksum((u8 *) sctph, skb_headlen(skb) - sctphoff); - skb_walk_frags(skb, iter) - crc32 = sctp_update_cksum((u8 *) iter->data, skb_headlen(iter), - crc32); - crc32 = sctp_end_cksum(crc32); - sctph->checksum = crc32; + sctp_nat_csum(skb, sctph, sctphoff); return 1; } diff --git a/net/netfilter/ipvs/ip_vs_sync.c b/net/netfilter/ipvs/ip_vs_sync.c index effa10c9e4e3..44fd10c539ac 100644 --- a/net/netfilter/ipvs/ip_vs_sync.c +++ b/net/netfilter/ipvs/ip_vs_sync.c @@ -1795,6 +1795,8 @@ int start_sync_thread(struct net *net, int state, char *mcast_ifn, __u8 syncid) GFP_KERNEL); if (!tinfo->buf) goto outtinfo; + } else { + tinfo->buf = NULL; } tinfo->id = id; diff --git a/net/netfilter/nf_conntrack_acct.c b/net/netfilter/nf_conntrack_acct.c index 7df424e2d10c..2d3030ab5b61 100644 --- a/net/netfilter/nf_conntrack_acct.c +++ b/net/netfilter/nf_conntrack_acct.c @@ -106,36 +106,26 @@ static void nf_conntrack_acct_fini_sysctl(struct net *net) } #endif -int nf_conntrack_acct_init(struct net *net) +int nf_conntrack_acct_pernet_init(struct net *net) { - int ret; - net->ct.sysctl_acct = nf_ct_acct; + return nf_conntrack_acct_init_sysctl(net); +} - if (net_eq(net, &init_net)) { - ret = nf_ct_extend_register(&acct_extend); - if (ret < 0) { - printk(KERN_ERR "nf_conntrack_acct: Unable to register extension\n"); - goto out_extend_register; - } - } +void nf_conntrack_acct_pernet_fini(struct net *net) +{ + nf_conntrack_acct_fini_sysctl(net); +} - ret = nf_conntrack_acct_init_sysctl(net); +int nf_conntrack_acct_init(void) +{ + int ret = nf_ct_extend_register(&acct_extend); if (ret < 0) - goto out_sysctl; - - return 0; - -out_sysctl: - if (net_eq(net, &init_net)) - nf_ct_extend_unregister(&acct_extend); -out_extend_register: + pr_err("nf_conntrack_acct: Unable to register extension\n"); return ret; } -void nf_conntrack_acct_fini(struct net *net) +void nf_conntrack_acct_fini(void) { - nf_conntrack_acct_fini_sysctl(net); - if (net_eq(net, &init_net)) - nf_ct_extend_unregister(&acct_extend); + nf_ct_extend_unregister(&acct_extend); } diff --git a/net/netfilter/nf_conntrack_core.c b/net/netfilter/nf_conntrack_core.c index 08cdc71d8e87..c8e001a9c45b 100644 --- a/net/netfilter/nf_conntrack_core.c +++ b/net/netfilter/nf_conntrack_core.c @@ -45,6 +45,7 @@ #include <net/netfilter/nf_conntrack_zones.h> #include <net/netfilter/nf_conntrack_timestamp.h> #include <net/netfilter/nf_conntrack_timeout.h> +#include <net/netfilter/nf_conntrack_labels.h> #include <net/netfilter/nf_nat.h> #include <net/netfilter/nf_nat_core.h> @@ -763,6 +764,7 @@ void nf_conntrack_free(struct nf_conn *ct) } EXPORT_SYMBOL_GPL(nf_conntrack_free); + /* Allocate a new conntrack: we return -ENOMEM if classification failed due to stress. Otherwise it really is unclassifiable. */ static struct nf_conntrack_tuple_hash * @@ -809,6 +811,7 @@ init_conntrack(struct net *net, struct nf_conn *tmpl, nf_ct_acct_ext_add(ct, GFP_ATOMIC); nf_ct_tstamp_ext_add(ct, GFP_ATOMIC); + nf_ct_labels_ext_add(ct); ecache = tmpl ? nf_ct_ecache_find(tmpl) : NULL; nf_ct_ecache_ext_add(ct, ecache ? ecache->ctmask : 0, @@ -1331,18 +1334,42 @@ static int untrack_refs(void) return cnt; } -static void nf_conntrack_cleanup_init_net(void) +void nf_conntrack_cleanup_start(void) { + RCU_INIT_POINTER(ip_ct_attach, NULL); +} + +void nf_conntrack_cleanup_end(void) +{ + RCU_INIT_POINTER(nf_ct_destroy, NULL); while (untrack_refs() > 0) schedule(); #ifdef CONFIG_NF_CONNTRACK_ZONES nf_ct_extend_unregister(&nf_ct_zone_extend); #endif + nf_conntrack_proto_fini(); + nf_conntrack_labels_fini(); + nf_conntrack_helper_fini(); + nf_conntrack_timeout_fini(); + nf_conntrack_ecache_fini(); + nf_conntrack_tstamp_fini(); + nf_conntrack_acct_fini(); + nf_conntrack_expect_fini(); } -static void nf_conntrack_cleanup_net(struct net *net) +/* + * Mishearing the voices in his head, our hero wonders how he's + * supposed to kill the mall. + */ +void nf_conntrack_cleanup_net(struct net *net) { + /* + * This makes sure all current packets have passed through + * netfilter framework. Roll on, two-stage module + * delete... + */ + synchronize_net(); i_see_dead_people: nf_ct_iterate_cleanup(net, kill_all, NULL); nf_ct_release_dying_list(net); @@ -1352,37 +1379,17 @@ static void nf_conntrack_cleanup_net(struct net *net) } nf_ct_free_hashtable(net->ct.hash, net->ct.htable_size); - nf_conntrack_helper_fini(net); - nf_conntrack_timeout_fini(net); - nf_conntrack_ecache_fini(net); - nf_conntrack_tstamp_fini(net); - nf_conntrack_acct_fini(net); - nf_conntrack_expect_fini(net); + nf_conntrack_proto_pernet_fini(net); + nf_conntrack_helper_pernet_fini(net); + nf_conntrack_ecache_pernet_fini(net); + nf_conntrack_tstamp_pernet_fini(net); + nf_conntrack_acct_pernet_fini(net); + nf_conntrack_expect_pernet_fini(net); kmem_cache_destroy(net->ct.nf_conntrack_cachep); kfree(net->ct.slabname); free_percpu(net->ct.stat); } -/* Mishearing the voices in his head, our hero wonders how he's - supposed to kill the mall. */ -void nf_conntrack_cleanup(struct net *net) -{ - if (net_eq(net, &init_net)) - RCU_INIT_POINTER(ip_ct_attach, NULL); - - /* This makes sure all current packets have passed through - netfilter framework. Roll on, two-stage module - delete... */ - synchronize_net(); - nf_conntrack_proto_fini(net); - nf_conntrack_cleanup_net(net); - - if (net_eq(net, &init_net)) { - RCU_INIT_POINTER(nf_ct_destroy, NULL); - nf_conntrack_cleanup_init_net(); - } -} - void *nf_ct_alloc_hashtable(unsigned int *sizep, int nulls) { struct hlist_nulls_head *hash; @@ -1473,7 +1480,7 @@ void nf_ct_untracked_status_or(unsigned long bits) } EXPORT_SYMBOL_GPL(nf_ct_untracked_status_or); -static int nf_conntrack_init_init_net(void) +int nf_conntrack_init_start(void) { int max_factor = 8; int ret, cpu; @@ -1500,11 +1507,44 @@ static int nf_conntrack_init_init_net(void) printk(KERN_INFO "nf_conntrack version %s (%u buckets, %d max)\n", NF_CONNTRACK_VERSION, nf_conntrack_htable_size, nf_conntrack_max); + + ret = nf_conntrack_expect_init(); + if (ret < 0) + goto err_expect; + + ret = nf_conntrack_acct_init(); + if (ret < 0) + goto err_acct; + + ret = nf_conntrack_tstamp_init(); + if (ret < 0) + goto err_tstamp; + + ret = nf_conntrack_ecache_init(); + if (ret < 0) + goto err_ecache; + + ret = nf_conntrack_timeout_init(); + if (ret < 0) + goto err_timeout; + + ret = nf_conntrack_helper_init(); + if (ret < 0) + goto err_helper; + + ret = nf_conntrack_labels_init(); + if (ret < 0) + goto err_labels; + #ifdef CONFIG_NF_CONNTRACK_ZONES ret = nf_ct_extend_register(&nf_ct_zone_extend); if (ret < 0) goto err_extend; #endif + ret = nf_conntrack_proto_init(); + if (ret < 0) + goto err_proto; + /* Set up fake conntrack: to never be deleted, not in any hashes */ for_each_possible_cpu(cpu) { struct nf_conn *ct = &per_cpu(nf_conntrack_untracked, cpu); @@ -1515,25 +1555,53 @@ static int nf_conntrack_init_init_net(void) nf_ct_untracked_status_or(IPS_CONFIRMED | IPS_UNTRACKED); return 0; +err_proto: #ifdef CONFIG_NF_CONNTRACK_ZONES + nf_ct_extend_unregister(&nf_ct_zone_extend); err_extend: #endif + nf_conntrack_labels_fini(); +err_labels: + nf_conntrack_helper_fini(); +err_helper: + nf_conntrack_timeout_fini(); +err_timeout: + nf_conntrack_ecache_fini(); +err_ecache: + nf_conntrack_tstamp_fini(); +err_tstamp: + nf_conntrack_acct_fini(); +err_acct: + nf_conntrack_expect_fini(); +err_expect: return ret; } +void nf_conntrack_init_end(void) +{ + /* For use by REJECT target */ + RCU_INIT_POINTER(ip_ct_attach, nf_conntrack_attach); + RCU_INIT_POINTER(nf_ct_destroy, destroy_conntrack); + + /* Howto get NAT offsets */ + RCU_INIT_POINTER(nf_ct_nat_offset, NULL); +} + /* * We need to use special "null" values, not used in hash table */ #define UNCONFIRMED_NULLS_VAL ((1<<30)+0) #define DYING_NULLS_VAL ((1<<30)+1) +#define TEMPLATE_NULLS_VAL ((1<<30)+2) -static int nf_conntrack_init_net(struct net *net) +int nf_conntrack_init_net(struct net *net) { int ret; atomic_set(&net->ct.count, 0); INIT_HLIST_NULLS_HEAD(&net->ct.unconfirmed, UNCONFIRMED_NULLS_VAL); INIT_HLIST_NULLS_HEAD(&net->ct.dying, DYING_NULLS_VAL); + INIT_HLIST_NULLS_HEAD(&net->ct.tmpl, TEMPLATE_NULLS_VAL); net->ct.stat = alloc_percpu(struct ip_conntrack_stat); if (!net->ct.stat) { ret = -ENOMEM; @@ -1562,35 +1630,36 @@ static int nf_conntrack_init_net(struct net *net) printk(KERN_ERR "Unable to create nf_conntrack_hash\n"); goto err_hash; } - ret = nf_conntrack_expect_init(net); + ret = nf_conntrack_expect_pernet_init(net); if (ret < 0) goto err_expect; - ret = nf_conntrack_acct_init(net); + ret = nf_conntrack_acct_pernet_init(net); if (ret < 0) goto err_acct; - ret = nf_conntrack_tstamp_init(net); + ret = nf_conntrack_tstamp_pernet_init(net); if (ret < 0) goto err_tstamp; - ret = nf_conntrack_ecache_init(net); + ret = nf_conntrack_ecache_pernet_init(net); if (ret < 0) goto err_ecache; - ret = nf_conntrack_timeout_init(net); - if (ret < 0) - goto err_timeout; - ret = nf_conntrack_helper_init(net); + ret = nf_conntrack_helper_pernet_init(net); if (ret < 0) goto err_helper; + ret = nf_conntrack_proto_pernet_init(net); + if (ret < 0) + goto err_proto; return 0; + +err_proto: + nf_conntrack_helper_pernet_fini(net); err_helper: - nf_conntrack_timeout_fini(net); -err_timeout: - nf_conntrack_ecache_fini(net); + nf_conntrack_ecache_pernet_fini(net); err_ecache: - nf_conntrack_tstamp_fini(net); + nf_conntrack_tstamp_pernet_fini(net); err_tstamp: - nf_conntrack_acct_fini(net); + nf_conntrack_acct_pernet_fini(net); err_acct: - nf_conntrack_expect_fini(net); + nf_conntrack_expect_pernet_fini(net); err_expect: nf_ct_free_hashtable(net->ct.hash, net->ct.htable_size); err_hash: @@ -1607,38 +1676,3 @@ s16 (*nf_ct_nat_offset)(const struct nf_conn *ct, enum ip_conntrack_dir dir, u32 seq); EXPORT_SYMBOL_GPL(nf_ct_nat_offset); - -int nf_conntrack_init(struct net *net) -{ - int ret; - - if (net_eq(net, &init_net)) { - ret = nf_conntrack_init_init_net(); - if (ret < 0) - goto out_init_net; - } - ret = nf_conntrack_proto_init(net); - if (ret < 0) - goto out_proto; - ret = nf_conntrack_init_net(net); - if (ret < 0) - goto out_net; - - if (net_eq(net, &init_net)) { - /* For use by REJECT target */ - RCU_INIT_POINTER(ip_ct_attach, nf_conntrack_attach); - RCU_INIT_POINTER(nf_ct_destroy, destroy_conntrack); - - /* Howto get NAT offsets */ - RCU_INIT_POINTER(nf_ct_nat_offset, NULL); - } - return 0; - -out_net: - nf_conntrack_proto_fini(net); -out_proto: - if (net_eq(net, &init_net)) - nf_conntrack_cleanup_init_net(); -out_init_net: - return ret; -} diff --git a/net/netfilter/nf_conntrack_ecache.c b/net/netfilter/nf_conntrack_ecache.c index faa978f1714b..b5d2eb8bf0d5 100644 --- a/net/netfilter/nf_conntrack_ecache.c +++ b/net/netfilter/nf_conntrack_ecache.c @@ -233,38 +233,27 @@ static void nf_conntrack_event_fini_sysctl(struct net *net) } #endif /* CONFIG_SYSCTL */ -int nf_conntrack_ecache_init(struct net *net) +int nf_conntrack_ecache_pernet_init(struct net *net) { - int ret; - net->ct.sysctl_events = nf_ct_events; net->ct.sysctl_events_retry_timeout = nf_ct_events_retry_timeout; + return nf_conntrack_event_init_sysctl(net); +} - if (net_eq(net, &init_net)) { - ret = nf_ct_extend_register(&event_extend); - if (ret < 0) { - printk(KERN_ERR "nf_ct_event: Unable to register " - "event extension.\n"); - goto out_extend_register; - } - } +void nf_conntrack_ecache_pernet_fini(struct net *net) +{ + nf_conntrack_event_fini_sysctl(net); +} - ret = nf_conntrack_event_init_sysctl(net); +int nf_conntrack_ecache_init(void) +{ + int ret = nf_ct_extend_register(&event_extend); if (ret < 0) - goto out_sysctl; - - return 0; - -out_sysctl: - if (net_eq(net, &init_net)) - nf_ct_extend_unregister(&event_extend); -out_extend_register: + pr_err("nf_ct_event: Unable to register event extension.\n"); return ret; } -void nf_conntrack_ecache_fini(struct net *net) +void nf_conntrack_ecache_fini(void) { - nf_conntrack_event_fini_sysctl(net); - if (net_eq(net, &init_net)) - nf_ct_extend_unregister(&event_extend); + nf_ct_extend_unregister(&event_extend); } diff --git a/net/netfilter/nf_conntrack_expect.c b/net/netfilter/nf_conntrack_expect.c index 527651a53a45..bdd341899ed3 100644 --- a/net/netfilter/nf_conntrack_expect.c +++ b/net/netfilter/nf_conntrack_expect.c @@ -587,53 +587,50 @@ static void exp_proc_remove(struct net *net) module_param_named(expect_hashsize, nf_ct_expect_hsize, uint, 0400); -int nf_conntrack_expect_init(struct net *net) +int nf_conntrack_expect_pernet_init(struct net *net) { int err = -ENOMEM; - if (net_eq(net, &init_net)) { - if (!nf_ct_expect_hsize) { - nf_ct_expect_hsize = net->ct.htable_size / 256; - if (!nf_ct_expect_hsize) - nf_ct_expect_hsize = 1; - } - nf_ct_expect_max = nf_ct_expect_hsize * 4; - } - net->ct.expect_count = 0; net->ct.expect_hash = nf_ct_alloc_hashtable(&nf_ct_expect_hsize, 0); if (net->ct.expect_hash == NULL) goto err1; - if (net_eq(net, &init_net)) { - nf_ct_expect_cachep = kmem_cache_create("nf_conntrack_expect", - sizeof(struct nf_conntrack_expect), - 0, 0, NULL); - if (!nf_ct_expect_cachep) - goto err2; - } - err = exp_proc_init(net); if (err < 0) - goto err3; + goto err2; return 0; - -err3: - if (net_eq(net, &init_net)) - kmem_cache_destroy(nf_ct_expect_cachep); err2: nf_ct_free_hashtable(net->ct.expect_hash, nf_ct_expect_hsize); err1: return err; } -void nf_conntrack_expect_fini(struct net *net) +void nf_conntrack_expect_pernet_fini(struct net *net) { exp_proc_remove(net); - if (net_eq(net, &init_net)) { - rcu_barrier(); /* Wait for call_rcu() before destroy */ - kmem_cache_destroy(nf_ct_expect_cachep); - } nf_ct_free_hashtable(net->ct.expect_hash, nf_ct_expect_hsize); } + +int nf_conntrack_expect_init(void) +{ + if (!nf_ct_expect_hsize) { + nf_ct_expect_hsize = nf_conntrack_htable_size / 256; + if (!nf_ct_expect_hsize) + nf_ct_expect_hsize = 1; + } + nf_ct_expect_max = nf_ct_expect_hsize * 4; + nf_ct_expect_cachep = kmem_cache_create("nf_conntrack_expect", + sizeof(struct nf_conntrack_expect), + 0, 0, NULL); + if (!nf_ct_expect_cachep) + return -ENOMEM; + return 0; +} + +void nf_conntrack_expect_fini(void) +{ + rcu_barrier(); /* Wait for call_rcu() before destroy */ + kmem_cache_destroy(nf_ct_expect_cachep); +} diff --git a/net/netfilter/nf_conntrack_helper.c b/net/netfilter/nf_conntrack_helper.c index 884f2b39319a..2f380f73c4c0 100644 --- a/net/netfilter/nf_conntrack_helper.c +++ b/net/netfilter/nf_conntrack_helper.c @@ -423,44 +423,41 @@ static struct nf_ct_ext_type helper_extend __read_mostly = { .id = NF_CT_EXT_HELPER, }; -int nf_conntrack_helper_init(struct net *net) +int nf_conntrack_helper_pernet_init(struct net *net) { - int err; - net->ct.auto_assign_helper_warned = false; net->ct.sysctl_auto_assign_helper = nf_ct_auto_assign_helper; + return nf_conntrack_helper_init_sysctl(net); +} - if (net_eq(net, &init_net)) { - nf_ct_helper_hsize = 1; /* gets rounded up to use one page */ - nf_ct_helper_hash = - nf_ct_alloc_hashtable(&nf_ct_helper_hsize, 0); - if (!nf_ct_helper_hash) - return -ENOMEM; +void nf_conntrack_helper_pernet_fini(struct net *net) +{ + nf_conntrack_helper_fini_sysctl(net); +} - err = nf_ct_extend_register(&helper_extend); - if (err < 0) - goto err1; +int nf_conntrack_helper_init(void) +{ + int ret; + nf_ct_helper_hsize = 1; /* gets rounded up to use one page */ + nf_ct_helper_hash = + nf_ct_alloc_hashtable(&nf_ct_helper_hsize, 0); + if (!nf_ct_helper_hash) + return -ENOMEM; + + ret = nf_ct_extend_register(&helper_extend); + if (ret < 0) { + pr_err("nf_ct_helper: Unable to register helper extension.\n"); + goto out_extend; } - err = nf_conntrack_helper_init_sysctl(net); - if (err < 0) - goto out_sysctl; - return 0; - -out_sysctl: - if (net_eq(net, &init_net)) - nf_ct_extend_unregister(&helper_extend); -err1: +out_extend: nf_ct_free_hashtable(nf_ct_helper_hash, nf_ct_helper_hsize); - return err; + return ret; } -void nf_conntrack_helper_fini(struct net *net) +void nf_conntrack_helper_fini(void) { - nf_conntrack_helper_fini_sysctl(net); - if (net_eq(net, &init_net)) { - nf_ct_extend_unregister(&helper_extend); - nf_ct_free_hashtable(nf_ct_helper_hash, nf_ct_helper_hsize); - } + nf_ct_extend_unregister(&helper_extend); + nf_ct_free_hashtable(nf_ct_helper_hash, nf_ct_helper_hsize); } diff --git a/net/netfilter/nf_conntrack_labels.c b/net/netfilter/nf_conntrack_labels.c new file mode 100644 index 000000000000..8fe2e99428b7 --- /dev/null +++ b/net/netfilter/nf_conntrack_labels.c @@ -0,0 +1,112 @@ +/* + * test/set flag bits stored in conntrack extension area. + * + * (C) 2013 Astaro GmbH & Co KG + * + * 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. + */ + +#include <linux/ctype.h> +#include <linux/export.h> +#include <linux/jhash.h> +#include <linux/spinlock.h> +#include <linux/types.h> +#include <linux/slab.h> + +#include <net/netfilter/nf_conntrack_ecache.h> +#include <net/netfilter/nf_conntrack_labels.h> + +static unsigned int label_bits(const struct nf_conn_labels *l) +{ + unsigned int longs = l->words; + return longs * BITS_PER_LONG; +} + +bool nf_connlabel_match(const struct nf_conn *ct, u16 bit) +{ + struct nf_conn_labels *labels = nf_ct_labels_find(ct); + + if (!labels) + return false; + + return bit < label_bits(labels) && test_bit(bit, labels->bits); +} +EXPORT_SYMBOL_GPL(nf_connlabel_match); + +int nf_connlabel_set(struct nf_conn *ct, u16 bit) +{ + struct nf_conn_labels *labels = nf_ct_labels_find(ct); + + if (!labels || bit >= label_bits(labels)) + return -ENOSPC; + + if (test_bit(bit, labels->bits)) + return 0; + + if (test_and_set_bit(bit, labels->bits)) + nf_conntrack_event_cache(IPCT_LABEL, ct); + + return 0; +} +EXPORT_SYMBOL_GPL(nf_connlabel_set); + +#if IS_ENABLED(CONFIG_NF_CT_NETLINK) +static void replace_u32(u32 *address, u32 mask, u32 new) +{ + u32 old, tmp; + + do { + old = *address; + tmp = (old & mask) ^ new; + } while (cmpxchg(address, old, tmp) != old); +} + +int nf_connlabels_replace(struct nf_conn *ct, + const u32 *data, + const u32 *mask, unsigned int words32) +{ + struct nf_conn_labels *labels; + unsigned int size, i; + u32 *dst; + + labels = nf_ct_labels_find(ct); + if (!labels) + return -ENOSPC; + + size = labels->words * sizeof(long); + if (size < (words32 * sizeof(u32))) + words32 = size / sizeof(u32); + + dst = (u32 *) labels->bits; + if (words32) { + for (i = 0; i < words32; i++) + replace_u32(&dst[i], mask ? ~mask[i] : 0, data[i]); + } + + size /= sizeof(u32); + for (i = words32; i < size; i++) /* pad */ + replace_u32(&dst[i], 0, 0); + + nf_conntrack_event_cache(IPCT_LABEL, ct); + return 0; +} +EXPORT_SYMBOL_GPL(nf_connlabels_replace); +#endif + +static struct nf_ct_ext_type labels_extend __read_mostly = { + .len = sizeof(struct nf_conn_labels), + .align = __alignof__(struct nf_conn_labels), + .id = NF_CT_EXT_LABELS, +}; + +int nf_conntrack_labels_init(void) +{ + return nf_ct_extend_register(&labels_extend); +} + +void nf_conntrack_labels_fini(void) +{ + nf_ct_extend_unregister(&labels_extend); +} diff --git a/net/netfilter/nf_conntrack_netlink.c b/net/netfilter/nf_conntrack_netlink.c index 4e078cd84d83..2334cc5d2b16 100644 --- a/net/netfilter/nf_conntrack_netlink.c +++ b/net/netfilter/nf_conntrack_netlink.c @@ -43,6 +43,7 @@ #include <net/netfilter/nf_conntrack_acct.h> #include <net/netfilter/nf_conntrack_zones.h> #include <net/netfilter/nf_conntrack_timestamp.h> +#include <net/netfilter/nf_conntrack_labels.h> #ifdef CONFIG_NF_NAT_NEEDED #include <net/netfilter/nf_nat_core.h> #include <net/netfilter/nf_nat_l4proto.h> @@ -323,6 +324,40 @@ nla_put_failure: #define ctnetlink_dump_secctx(a, b) (0) #endif +#ifdef CONFIG_NF_CONNTRACK_LABELS +static int ctnetlink_label_size(const struct nf_conn *ct) +{ + struct nf_conn_labels *labels = nf_ct_labels_find(ct); + + if (!labels) + return 0; + return nla_total_size(labels->words * sizeof(long)); +} + +static int +ctnetlink_dump_labels(struct sk_buff *skb, const struct nf_conn *ct) +{ + struct nf_conn_labels *labels = nf_ct_labels_find(ct); + unsigned int len, i; + + if (!labels) + return 0; + + len = labels->words * sizeof(long); + i = 0; + do { + if (labels->bits[i] != 0) + return nla_put(skb, CTA_LABELS, len, labels->bits); + i++; + } while (i < labels->words); + + 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) static inline int @@ -463,6 +498,7 @@ ctnetlink_fill_info(struct sk_buff *skb, u32 portid, u32 seq, u32 type, ctnetlink_dump_helpinfo(skb, ct) < 0 || ctnetlink_dump_mark(skb, ct) < 0 || ctnetlink_dump_secctx(skb, ct) < 0 || + ctnetlink_dump_labels(skb, ct) < 0 || ctnetlink_dump_id(skb, ct) < 0 || ctnetlink_dump_use(skb, ct) < 0 || ctnetlink_dump_master(skb, ct) < 0 || @@ -561,6 +597,7 @@ ctnetlink_nlmsg_size(const struct nf_conn *ct) + nla_total_size(sizeof(u_int32_t)) /* CTA_MARK */ #endif + ctnetlink_proto_size(ct) + + ctnetlink_label_size(ct) ; } @@ -662,6 +699,9 @@ ctnetlink_conntrack_event(unsigned int events, struct nf_ct_event *item) && ctnetlink_dump_secctx(skb, ct) < 0) goto nla_put_failure; #endif + if (events & (1 << IPCT_LABEL) && + ctnetlink_dump_labels(skb, ct) < 0) + goto nla_put_failure; if (events & (1 << IPCT_RELATED) && ctnetlink_dump_master(skb, ct) < 0) @@ -921,6 +961,7 @@ ctnetlink_parse_help(const struct nlattr *attr, char **helper_name, return 0; } +#define __CTA_LABELS_MAX_LENGTH ((XT_CONNLABEL_MAXBIT + 1) / BITS_PER_BYTE) static const struct nla_policy ct_nla_policy[CTA_MAX+1] = { [CTA_TUPLE_ORIG] = { .type = NLA_NESTED }, [CTA_TUPLE_REPLY] = { .type = NLA_NESTED }, @@ -937,6 +978,10 @@ static const struct nla_policy ct_nla_policy[CTA_MAX+1] = { [CTA_NAT_SEQ_ADJ_REPLY] = { .type = NLA_NESTED }, [CTA_ZONE] = { .type = NLA_U16 }, [CTA_MARK_MASK] = { .type = NLA_U32 }, + [CTA_LABELS] = { .type = NLA_BINARY, + .len = __CTA_LABELS_MAX_LENGTH }, + [CTA_LABELS_MASK] = { .type = NLA_BINARY, + .len = __CTA_LABELS_MAX_LENGTH }, }; static int @@ -1465,6 +1510,31 @@ ctnetlink_change_nat_seq_adj(struct nf_conn *ct, #endif static int +ctnetlink_attach_labels(struct nf_conn *ct, const struct nlattr * const cda[]) +{ +#ifdef CONFIG_NF_CONNTRACK_LABELS + size_t len = nla_len(cda[CTA_LABELS]); + const void *mask = cda[CTA_LABELS_MASK]; + + if (len & (sizeof(u32)-1)) /* must be multiple of u32 */ + return -EINVAL; + + if (mask) { + if (nla_len(cda[CTA_LABELS_MASK]) == 0 || + nla_len(cda[CTA_LABELS_MASK]) != len) + return -EINVAL; + mask = nla_data(cda[CTA_LABELS_MASK]); + } + + len /= sizeof(u32); + + return nf_connlabels_replace(ct, nla_data(cda[CTA_LABELS]), mask, len); +#else + return -EOPNOTSUPP; +#endif +} + +static int ctnetlink_change_conntrack(struct nf_conn *ct, const struct nlattr * const cda[]) { @@ -1510,6 +1580,11 @@ ctnetlink_change_conntrack(struct nf_conn *ct, return err; } #endif + if (cda[CTA_LABELS]) { + err = ctnetlink_attach_labels(ct, cda); + if (err < 0) + return err; + } return 0; } @@ -1598,6 +1673,8 @@ ctnetlink_create_conntrack(struct net *net, u16 zone, nf_ct_acct_ext_add(ct, GFP_ATOMIC); nf_ct_tstamp_ext_add(ct, GFP_ATOMIC); nf_ct_ecache_ext_add(ct, 0, 0, GFP_ATOMIC); + nf_ct_labels_ext_add(ct); + /* we must add conntrack extensions before confirmation. */ ct->status |= IPS_CONFIRMED; @@ -1716,6 +1793,10 @@ ctnetlink_new_conntrack(struct sock *ctnl, struct sk_buff *skb, else events = IPCT_NEW; + if (cda[CTA_LABELS] && + ctnetlink_attach_labels(ct, cda) == 0) + events |= (1 << IPCT_LABEL); + nf_conntrack_eventmask_report((1 << IPCT_REPLY) | (1 << IPCT_ASSURED) | (1 << IPCT_HELPER) | @@ -1983,6 +2064,8 @@ ctnetlink_nfqueue_build(struct sk_buff *skb, struct nf_conn *ct) if (ct->mark && ctnetlink_dump_mark(skb, ct) < 0) goto nla_put_failure; #endif + if (ctnetlink_dump_labels(skb, ct) < 0) + goto nla_put_failure; rcu_read_unlock(); return 0; @@ -2011,6 +2094,11 @@ ctnetlink_nfqueue_parse_ct(const struct nlattr *cda[], struct nf_conn *ct) if (err < 0) return err; } + if (cda[CTA_LABELS]) { + err = ctnetlink_attach_labels(ct, cda); + if (err < 0) + return err; + } #if defined(CONFIG_NF_CONNTRACK_MARK) if (cda[CTA_MARK]) ct->mark = ntohl(nla_get_be32(cda[CTA_MARK])); @@ -2624,7 +2712,7 @@ ctnetlink_create_expect(struct net *net, u16 zone, if (!help) { if (!cda[CTA_EXPECT_TIMEOUT]) { err = -EINVAL; - goto out; + goto err_out; } exp->timeout.expires = jiffies + ntohl(nla_get_be32(cda[CTA_EXPECT_TIMEOUT])) * HZ; diff --git a/net/netfilter/nf_conntrack_proto.c b/net/netfilter/nf_conntrack_proto.c index 51e928db48c8..58ab4050830c 100644 --- a/net/netfilter/nf_conntrack_proto.c +++ b/net/netfilter/nf_conntrack_proto.c @@ -212,8 +212,7 @@ static void nf_ct_l3proto_unregister_sysctl(struct net *net, #endif } -static int -nf_conntrack_l3proto_register_net(struct nf_conntrack_l3proto *proto) +int nf_ct_l3proto_register(struct nf_conntrack_l3proto *proto) { int ret = 0; struct nf_conntrack_l3proto *old; @@ -242,8 +241,9 @@ out_unlock: return ret; } +EXPORT_SYMBOL_GPL(nf_ct_l3proto_register); -int nf_conntrack_l3proto_register(struct net *net, +int nf_ct_l3proto_pernet_register(struct net *net, struct nf_conntrack_l3proto *proto) { int ret = 0; @@ -254,22 +254,11 @@ int nf_conntrack_l3proto_register(struct net *net, return ret; } - ret = nf_ct_l3proto_register_sysctl(net, proto); - if (ret < 0) - return ret; - - if (net == &init_net) { - ret = nf_conntrack_l3proto_register_net(proto); - if (ret < 0) - nf_ct_l3proto_unregister_sysctl(net, proto); - } - - return ret; + return nf_ct_l3proto_register_sysctl(net, proto); } -EXPORT_SYMBOL_GPL(nf_conntrack_l3proto_register); +EXPORT_SYMBOL_GPL(nf_ct_l3proto_pernet_register); -static void -nf_conntrack_l3proto_unregister_net(struct nf_conntrack_l3proto *proto) +void nf_ct_l3proto_unregister(struct nf_conntrack_l3proto *proto) { BUG_ON(proto->l3proto >= AF_MAX); @@ -283,19 +272,17 @@ nf_conntrack_l3proto_unregister_net(struct nf_conntrack_l3proto *proto) synchronize_rcu(); } +EXPORT_SYMBOL_GPL(nf_ct_l3proto_unregister); -void nf_conntrack_l3proto_unregister(struct net *net, +void nf_ct_l3proto_pernet_unregister(struct net *net, struct nf_conntrack_l3proto *proto) { - if (net == &init_net) - nf_conntrack_l3proto_unregister_net(proto); - nf_ct_l3proto_unregister_sysctl(net, proto); /* Remove all contrack entries for this protocol */ nf_ct_iterate_cleanup(net, kill_l3proto, proto); } -EXPORT_SYMBOL_GPL(nf_conntrack_l3proto_unregister); +EXPORT_SYMBOL_GPL(nf_ct_l3proto_pernet_unregister); static struct nf_proto_net *nf_ct_l4proto_net(struct net *net, struct nf_conntrack_l4proto *l4proto) @@ -376,8 +363,7 @@ void nf_ct_l4proto_unregister_sysctl(struct net *net, /* FIXME: Allow NULL functions and sub in pointers to generic for them. --RR */ -static int -nf_conntrack_l4proto_register_net(struct nf_conntrack_l4proto *l4proto) +int nf_ct_l4proto_register(struct nf_conntrack_l4proto *l4proto) { int ret = 0; @@ -431,8 +417,9 @@ out_unlock: mutex_unlock(&nf_ct_proto_mutex); return ret; } +EXPORT_SYMBOL_GPL(nf_ct_l4proto_register); -int nf_conntrack_l4proto_register(struct net *net, +int nf_ct_l4proto_pernet_register(struct net *net, struct nf_conntrack_l4proto *l4proto) { int ret = 0; @@ -452,22 +439,13 @@ int nf_conntrack_l4proto_register(struct net *net, if (ret < 0) goto out; - if (net == &init_net) { - ret = nf_conntrack_l4proto_register_net(l4proto); - if (ret < 0) { - nf_ct_l4proto_unregister_sysctl(net, pn, l4proto); - goto out; - } - } - pn->users++; out: return ret; } -EXPORT_SYMBOL_GPL(nf_conntrack_l4proto_register); +EXPORT_SYMBOL_GPL(nf_ct_l4proto_pernet_register); -static void -nf_conntrack_l4proto_unregister_net(struct nf_conntrack_l4proto *l4proto) +void nf_ct_l4proto_unregister(struct nf_conntrack_l4proto *l4proto) { BUG_ON(l4proto->l3proto >= PF_MAX); @@ -482,15 +460,13 @@ nf_conntrack_l4proto_unregister_net(struct nf_conntrack_l4proto *l4proto) synchronize_rcu(); } +EXPORT_SYMBOL_GPL(nf_ct_l4proto_unregister); -void nf_conntrack_l4proto_unregister(struct net *net, +void nf_ct_l4proto_pernet_unregister(struct net *net, struct nf_conntrack_l4proto *l4proto) { struct nf_proto_net *pn = NULL; - if (net == &init_net) - nf_conntrack_l4proto_unregister_net(l4proto); - pn = nf_ct_l4proto_net(net, l4proto); if (pn == NULL) return; @@ -501,11 +477,10 @@ void nf_conntrack_l4proto_unregister(struct net *net, /* Remove all contrack entries for this protocol */ nf_ct_iterate_cleanup(net, kill_l4proto, l4proto); } -EXPORT_SYMBOL_GPL(nf_conntrack_l4proto_unregister); +EXPORT_SYMBOL_GPL(nf_ct_l4proto_pernet_unregister); -int nf_conntrack_proto_init(struct net *net) +int nf_conntrack_proto_pernet_init(struct net *net) { - unsigned int i; int err; struct nf_proto_net *pn = nf_ct_l4proto_net(net, &nf_conntrack_l4proto_generic); @@ -520,19 +495,12 @@ int nf_conntrack_proto_init(struct net *net) if (err < 0) return err; - if (net == &init_net) { - for (i = 0; i < AF_MAX; i++) - rcu_assign_pointer(nf_ct_l3protos[i], - &nf_conntrack_l3proto_generic); - } - pn->users++; return 0; } -void nf_conntrack_proto_fini(struct net *net) +void nf_conntrack_proto_pernet_fini(struct net *net) { - unsigned int i; struct nf_proto_net *pn = nf_ct_l4proto_net(net, &nf_conntrack_l4proto_generic); @@ -540,9 +508,21 @@ void nf_conntrack_proto_fini(struct net *net) nf_ct_l4proto_unregister_sysctl(net, pn, &nf_conntrack_l4proto_generic); - if (net == &init_net) { - /* free l3proto protocol tables */ - for (i = 0; i < PF_MAX; i++) - kfree(nf_ct_protos[i]); - } +} + +int nf_conntrack_proto_init(void) +{ + unsigned int i; + for (i = 0; i < AF_MAX; i++) + rcu_assign_pointer(nf_ct_l3protos[i], + &nf_conntrack_l3proto_generic); + return 0; +} + +void nf_conntrack_proto_fini(void) +{ + unsigned int i; + /* free l3proto protocol tables */ + for (i = 0; i < PF_MAX; i++) + kfree(nf_ct_protos[i]); } diff --git a/net/netfilter/nf_conntrack_proto_dccp.c b/net/netfilter/nf_conntrack_proto_dccp.c index a8ae287bc7af..432f95780003 100644 --- a/net/netfilter/nf_conntrack_proto_dccp.c +++ b/net/netfilter/nf_conntrack_proto_dccp.c @@ -935,32 +935,27 @@ static struct nf_conntrack_l4proto dccp_proto6 __read_mostly = { static __net_init int dccp_net_init(struct net *net) { int ret = 0; - ret = nf_conntrack_l4proto_register(net, - &dccp_proto4); + ret = nf_ct_l4proto_pernet_register(net, &dccp_proto4); if (ret < 0) { - pr_err("nf_conntrack_l4proto_dccp4 :protocol register failed.\n"); + pr_err("nf_conntrack_dccp4: pernet registration failed.\n"); goto out; } - ret = nf_conntrack_l4proto_register(net, - &dccp_proto6); + ret = nf_ct_l4proto_pernet_register(net, &dccp_proto6); if (ret < 0) { - pr_err("nf_conntrack_l4proto_dccp6 :protocol register failed.\n"); + pr_err("nf_conntrack_dccp6: pernet registration failed.\n"); goto cleanup_dccp4; } return 0; cleanup_dccp4: - nf_conntrack_l4proto_unregister(net, - &dccp_proto4); + nf_ct_l4proto_pernet_unregister(net, &dccp_proto4); out: return ret; } static __net_exit void dccp_net_exit(struct net *net) { - nf_conntrack_l4proto_unregister(net, - &dccp_proto6); - nf_conntrack_l4proto_unregister(net, - &dccp_proto4); + nf_ct_l4proto_pernet_unregister(net, &dccp_proto6); + nf_ct_l4proto_pernet_unregister(net, &dccp_proto4); } static struct pernet_operations dccp_net_ops = { @@ -972,11 +967,33 @@ static struct pernet_operations dccp_net_ops = { static int __init nf_conntrack_proto_dccp_init(void) { - return register_pernet_subsys(&dccp_net_ops); + int ret; + + ret = nf_ct_l4proto_register(&dccp_proto4); + if (ret < 0) + goto out_dccp4; + + ret = nf_ct_l4proto_register(&dccp_proto6); + if (ret < 0) + goto out_dccp6; + + ret = register_pernet_subsys(&dccp_net_ops); + if (ret < 0) + goto out_pernet; + + return 0; +out_pernet: + nf_ct_l4proto_unregister(&dccp_proto6); +out_dccp6: + nf_ct_l4proto_unregister(&dccp_proto4); +out_dccp4: + return ret; } static void __exit nf_conntrack_proto_dccp_fini(void) { + nf_ct_l4proto_unregister(&dccp_proto6); + nf_ct_l4proto_unregister(&dccp_proto4); unregister_pernet_subsys(&dccp_net_ops); } diff --git a/net/netfilter/nf_conntrack_proto_gre.c b/net/netfilter/nf_conntrack_proto_gre.c index b09b7af7f6f8..bd7d01d9c7e7 100644 --- a/net/netfilter/nf_conntrack_proto_gre.c +++ b/net/netfilter/nf_conntrack_proto_gre.c @@ -397,15 +397,15 @@ static struct nf_conntrack_l4proto nf_conntrack_l4proto_gre4 __read_mostly = { static int proto_gre_net_init(struct net *net) { int ret = 0; - ret = nf_conntrack_l4proto_register(net, &nf_conntrack_l4proto_gre4); + ret = nf_ct_l4proto_pernet_register(net, &nf_conntrack_l4proto_gre4); if (ret < 0) - pr_err("nf_conntrack_l4proto_gre4 :protocol register failed.\n"); + pr_err("nf_conntrack_gre4: pernet registration failed.\n"); return ret; } static void proto_gre_net_exit(struct net *net) { - nf_conntrack_l4proto_unregister(net, &nf_conntrack_l4proto_gre4); + nf_ct_l4proto_pernet_unregister(net, &nf_conntrack_l4proto_gre4); nf_ct_gre_keymap_flush(net); } @@ -418,11 +418,26 @@ static struct pernet_operations proto_gre_net_ops = { static int __init nf_ct_proto_gre_init(void) { - return register_pernet_subsys(&proto_gre_net_ops); + int ret; + + ret = nf_ct_l4proto_register(&nf_conntrack_l4proto_gre4); + if (ret < 0) + goto out_gre4; + + ret = register_pernet_subsys(&proto_gre_net_ops); + if (ret < 0) + goto out_pernet; + + return 0; +out_pernet: + nf_ct_l4proto_unregister(&nf_conntrack_l4proto_gre4); +out_gre4: + return ret; } static void __exit nf_ct_proto_gre_fini(void) { + nf_ct_l4proto_unregister(&nf_conntrack_l4proto_gre4); unregister_pernet_subsys(&proto_gre_net_ops); } diff --git a/net/netfilter/nf_conntrack_proto_sctp.c b/net/netfilter/nf_conntrack_proto_sctp.c index c746d61f83ed..480f616d5936 100644 --- a/net/netfilter/nf_conntrack_proto_sctp.c +++ b/net/netfilter/nf_conntrack_proto_sctp.c @@ -853,33 +853,28 @@ static int sctp_net_init(struct net *net) { int ret = 0; - ret = nf_conntrack_l4proto_register(net, - &nf_conntrack_l4proto_sctp4); + ret = nf_ct_l4proto_pernet_register(net, &nf_conntrack_l4proto_sctp4); if (ret < 0) { - pr_err("nf_conntrack_l4proto_sctp4 :protocol register failed.\n"); + pr_err("nf_conntrack_sctp4: pernet registration failed.\n"); goto out; } - ret = nf_conntrack_l4proto_register(net, - &nf_conntrack_l4proto_sctp6); + ret = nf_ct_l4proto_pernet_register(net, &nf_conntrack_l4proto_sctp6); if (ret < 0) { - pr_err("nf_conntrack_l4proto_sctp6 :protocol register failed.\n"); + pr_err("nf_conntrack_sctp6: pernet registration failed.\n"); goto cleanup_sctp4; } return 0; cleanup_sctp4: - nf_conntrack_l4proto_unregister(net, - &nf_conntrack_l4proto_sctp4); + nf_ct_l4proto_pernet_unregister(net, &nf_conntrack_l4proto_sctp4); out: return ret; } static void sctp_net_exit(struct net *net) { - nf_conntrack_l4proto_unregister(net, - &nf_conntrack_l4proto_sctp6); - nf_conntrack_l4proto_unregister(net, - &nf_conntrack_l4proto_sctp4); + nf_ct_l4proto_pernet_unregister(net, &nf_conntrack_l4proto_sctp6); + nf_ct_l4proto_pernet_unregister(net, &nf_conntrack_l4proto_sctp4); } static struct pernet_operations sctp_net_ops = { @@ -891,11 +886,33 @@ static struct pernet_operations sctp_net_ops = { static int __init nf_conntrack_proto_sctp_init(void) { - return register_pernet_subsys(&sctp_net_ops); + int ret; + + ret = nf_ct_l4proto_register(&nf_conntrack_l4proto_sctp4); + if (ret < 0) + goto out_sctp4; + + ret = nf_ct_l4proto_register(&nf_conntrack_l4proto_sctp6); + if (ret < 0) + goto out_sctp6; + + ret = register_pernet_subsys(&sctp_net_ops); + if (ret < 0) + goto out_pernet; + + return 0; +out_pernet: + nf_ct_l4proto_unregister(&nf_conntrack_l4proto_sctp6); +out_sctp6: + nf_ct_l4proto_unregister(&nf_conntrack_l4proto_sctp4); +out_sctp4: + return ret; } static void __exit nf_conntrack_proto_sctp_fini(void) { + nf_ct_l4proto_unregister(&nf_conntrack_l4proto_sctp6); + nf_ct_l4proto_unregister(&nf_conntrack_l4proto_sctp4); unregister_pernet_subsys(&sctp_net_ops); } diff --git a/net/netfilter/nf_conntrack_proto_udplite.c b/net/netfilter/nf_conntrack_proto_udplite.c index 4b66df209286..157489581c31 100644 --- a/net/netfilter/nf_conntrack_proto_udplite.c +++ b/net/netfilter/nf_conntrack_proto_udplite.c @@ -336,30 +336,28 @@ static int udplite_net_init(struct net *net) { int ret = 0; - ret = nf_conntrack_l4proto_register(net, - &nf_conntrack_l4proto_udplite4); + ret = nf_ct_l4proto_pernet_register(net, &nf_conntrack_l4proto_udplite4); if (ret < 0) { - pr_err("nf_conntrack_l4proto_udplite4 :protocol register failed.\n"); + pr_err("nf_conntrack_udplite4: pernet registration failed.\n"); goto out; } - ret = nf_conntrack_l4proto_register(net, - &nf_conntrack_l4proto_udplite6); + ret = nf_ct_l4proto_pernet_register(net, &nf_conntrack_l4proto_udplite6); if (ret < 0) { - pr_err("nf_conntrack_l4proto_udplite4 :protocol register failed.\n"); + pr_err("nf_conntrack_udplite6: pernet registration failed.\n"); goto cleanup_udplite4; } return 0; cleanup_udplite4: - nf_conntrack_l4proto_unregister(net, &nf_conntrack_l4proto_udplite4); + nf_ct_l4proto_pernet_unregister(net, &nf_conntrack_l4proto_udplite4); out: return ret; } static void udplite_net_exit(struct net *net) { - nf_conntrack_l4proto_unregister(net, &nf_conntrack_l4proto_udplite6); - nf_conntrack_l4proto_unregister(net, &nf_conntrack_l4proto_udplite4); + nf_ct_l4proto_pernet_unregister(net, &nf_conntrack_l4proto_udplite6); + nf_ct_l4proto_pernet_unregister(net, &nf_conntrack_l4proto_udplite4); } static struct pernet_operations udplite_net_ops = { @@ -371,11 +369,33 @@ static struct pernet_operations udplite_net_ops = { static int __init nf_conntrack_proto_udplite_init(void) { - return register_pernet_subsys(&udplite_net_ops); + int ret; + + ret = nf_ct_l4proto_register(&nf_conntrack_l4proto_udplite4); + if (ret < 0) + goto out_udplite4; + + ret = nf_ct_l4proto_register(&nf_conntrack_l4proto_udplite6); + if (ret < 0) + goto out_udplite6; + + ret = register_pernet_subsys(&udplite_net_ops); + if (ret < 0) + goto out_pernet; + + return 0; +out_pernet: + nf_ct_l4proto_unregister(&nf_conntrack_l4proto_udplite6); +out_udplite6: + nf_ct_l4proto_unregister(&nf_conntrack_l4proto_udplite4); +out_udplite4: + return ret; } static void __exit nf_conntrack_proto_udplite_exit(void) { + nf_ct_l4proto_unregister(&nf_conntrack_l4proto_udplite6); + nf_ct_l4proto_unregister(&nf_conntrack_l4proto_udplite4); unregister_pernet_subsys(&udplite_net_ops); } diff --git a/net/netfilter/nf_conntrack_sip.c b/net/netfilter/nf_conntrack_sip.c index df8f4f284481..72a67bbe3518 100644 --- a/net/netfilter/nf_conntrack_sip.c +++ b/net/netfilter/nf_conntrack_sip.c @@ -1440,8 +1440,25 @@ static int process_sip_request(struct sk_buff *skb, unsigned int protoff, { enum ip_conntrack_info ctinfo; struct nf_conn *ct = nf_ct_get(skb, &ctinfo); + struct nf_ct_sip_master *ct_sip_info = nfct_help_data(ct); + enum ip_conntrack_dir dir = CTINFO2DIR(ctinfo); unsigned int matchoff, matchlen; unsigned int cseq, i; + union nf_inet_addr addr; + __be16 port; + + /* Many Cisco IP phones use a high source port for SIP requests, but + * listen for the response on port 5060. If we are the local + * router for one of these phones, save the port number from the + * Via: header so that nf_nat_sip can redirect the responses to + * the correct port. + */ + if (ct_sip_parse_header_uri(ct, *dptr, NULL, *datalen, + SIP_HDR_VIA_UDP, NULL, &matchoff, + &matchlen, &addr, &port) > 0 && + port != ct->tuplehash[dir].tuple.src.u.udp.port && + nf_inet_addr_cmp(&addr, &ct->tuplehash[dir].tuple.src.u3)) + ct_sip_info->forced_dport = port; for (i = 0; i < ARRAY_SIZE(sip_handlers); i++) { const struct sip_handler *handler; diff --git a/net/netfilter/nf_conntrack_snmp.c b/net/netfilter/nf_conntrack_snmp.c index 6e545e26289e..87b95a2c270c 100644 --- a/net/netfilter/nf_conntrack_snmp.c +++ b/net/netfilter/nf_conntrack_snmp.c @@ -16,6 +16,7 @@ #include <net/netfilter/nf_conntrack.h> #include <net/netfilter/nf_conntrack_helper.h> #include <net/netfilter/nf_conntrack_expect.h> +#include <linux/netfilter/nf_conntrack_snmp.h> #define SNMP_PORT 161 diff --git a/net/netfilter/nf_conntrack_standalone.c b/net/netfilter/nf_conntrack_standalone.c index 363285d544a1..7936bf7f90ba 100644 --- a/net/netfilter/nf_conntrack_standalone.c +++ b/net/netfilter/nf_conntrack_standalone.c @@ -472,13 +472,6 @@ static int nf_conntrack_standalone_init_sysctl(struct net *net) { struct ctl_table *table; - if (net_eq(net, &init_net)) { - nf_ct_netfilter_header = - register_net_sysctl(&init_net, "net", nf_ct_netfilter_table); - if (!nf_ct_netfilter_header) - goto out; - } - table = kmemdup(nf_ct_sysctl_table, sizeof(nf_ct_sysctl_table), GFP_KERNEL); if (!table) @@ -502,10 +495,6 @@ static int nf_conntrack_standalone_init_sysctl(struct net *net) out_unregister_netfilter: kfree(table); out_kmemdup: - if (net_eq(net, &init_net)) - unregister_net_sysctl_table(nf_ct_netfilter_header); -out: - printk(KERN_ERR "nf_conntrack: can't register to sysctl.\n"); return -ENOMEM; } @@ -513,8 +502,6 @@ static void nf_conntrack_standalone_fini_sysctl(struct net *net) { struct ctl_table *table; - if (net_eq(net, &init_net)) - unregister_net_sysctl_table(nf_ct_netfilter_header); table = net->ct.sysctl_header->ctl_table_arg; unregister_net_sysctl_table(net->ct.sysctl_header); kfree(table); @@ -530,51 +517,86 @@ static void nf_conntrack_standalone_fini_sysctl(struct net *net) } #endif /* CONFIG_SYSCTL */ -static int nf_conntrack_net_init(struct net *net) +static int nf_conntrack_pernet_init(struct net *net) { int ret; - ret = nf_conntrack_init(net); + ret = nf_conntrack_init_net(net); if (ret < 0) goto out_init; + ret = nf_conntrack_standalone_init_proc(net); if (ret < 0) goto out_proc; + net->ct.sysctl_checksum = 1; net->ct.sysctl_log_invalid = 0; ret = nf_conntrack_standalone_init_sysctl(net); if (ret < 0) goto out_sysctl; + return 0; out_sysctl: nf_conntrack_standalone_fini_proc(net); out_proc: - nf_conntrack_cleanup(net); + nf_conntrack_cleanup_net(net); out_init: return ret; } -static void nf_conntrack_net_exit(struct net *net) +static void nf_conntrack_pernet_exit(struct net *net) { nf_conntrack_standalone_fini_sysctl(net); nf_conntrack_standalone_fini_proc(net); - nf_conntrack_cleanup(net); + nf_conntrack_cleanup_net(net); } static struct pernet_operations nf_conntrack_net_ops = { - .init = nf_conntrack_net_init, - .exit = nf_conntrack_net_exit, + .init = nf_conntrack_pernet_init, + .exit = nf_conntrack_pernet_exit, }; static int __init nf_conntrack_standalone_init(void) { - return register_pernet_subsys(&nf_conntrack_net_ops); + int ret = nf_conntrack_init_start(); + if (ret < 0) + goto out_start; + +#ifdef CONFIG_SYSCTL + nf_ct_netfilter_header = + register_net_sysctl(&init_net, "net", nf_ct_netfilter_table); + if (!nf_ct_netfilter_header) { + pr_err("nf_conntrack: can't register to sysctl.\n"); + goto out_sysctl; + } +#endif + + ret = register_pernet_subsys(&nf_conntrack_net_ops); + if (ret < 0) + goto out_pernet; + + nf_conntrack_init_end(); + return 0; + +out_pernet: +#ifdef CONFIG_SYSCTL + unregister_net_sysctl_table(nf_ct_netfilter_header); +out_sysctl: +#endif + nf_conntrack_cleanup_end(); +out_start: + return ret; } static void __exit nf_conntrack_standalone_fini(void) { + nf_conntrack_cleanup_start(); unregister_pernet_subsys(&nf_conntrack_net_ops); +#ifdef CONFIG_SYSCTL + unregister_net_sysctl_table(nf_ct_netfilter_header); +#endif + nf_conntrack_cleanup_end(); } module_init(nf_conntrack_standalone_init); diff --git a/net/netfilter/nf_conntrack_timeout.c b/net/netfilter/nf_conntrack_timeout.c index a878ce5b252c..93da609d9d29 100644 --- a/net/netfilter/nf_conntrack_timeout.c +++ b/net/netfilter/nf_conntrack_timeout.c @@ -37,24 +37,15 @@ static struct nf_ct_ext_type timeout_extend __read_mostly = { .id = NF_CT_EXT_TIMEOUT, }; -int nf_conntrack_timeout_init(struct net *net) +int nf_conntrack_timeout_init(void) { - int ret = 0; - - if (net_eq(net, &init_net)) { - ret = nf_ct_extend_register(&timeout_extend); - if (ret < 0) { - printk(KERN_ERR "nf_ct_timeout: Unable to register " - "timeout extension.\n"); - return ret; - } - } - - return 0; + int ret = nf_ct_extend_register(&timeout_extend); + if (ret < 0) + pr_err("nf_ct_timeout: Unable to register timeout extension.\n"); + return ret; } -void nf_conntrack_timeout_fini(struct net *net) +void nf_conntrack_timeout_fini(void) { - if (net_eq(net, &init_net)) - nf_ct_extend_unregister(&timeout_extend); + nf_ct_extend_unregister(&timeout_extend); } diff --git a/net/netfilter/nf_conntrack_timestamp.c b/net/netfilter/nf_conntrack_timestamp.c index 7ea8026f07c9..902fb0a6b38a 100644 --- a/net/netfilter/nf_conntrack_timestamp.c +++ b/net/netfilter/nf_conntrack_timestamp.c @@ -88,37 +88,28 @@ static void nf_conntrack_tstamp_fini_sysctl(struct net *net) } #endif -int nf_conntrack_tstamp_init(struct net *net) +int nf_conntrack_tstamp_pernet_init(struct net *net) { - int ret; - net->ct.sysctl_tstamp = nf_ct_tstamp; + return nf_conntrack_tstamp_init_sysctl(net); +} - if (net_eq(net, &init_net)) { - ret = nf_ct_extend_register(&tstamp_extend); - if (ret < 0) { - printk(KERN_ERR "nf_ct_tstamp: Unable to register " - "extension\n"); - goto out_extend_register; - } - } +void nf_conntrack_tstamp_pernet_fini(struct net *net) +{ + nf_conntrack_tstamp_fini_sysctl(net); + nf_ct_extend_unregister(&tstamp_extend); +} - ret = nf_conntrack_tstamp_init_sysctl(net); +int nf_conntrack_tstamp_init(void) +{ + int ret; + ret = nf_ct_extend_register(&tstamp_extend); if (ret < 0) - goto out_sysctl; - - return 0; - -out_sysctl: - if (net_eq(net, &init_net)) - nf_ct_extend_unregister(&tstamp_extend); -out_extend_register: + pr_err("nf_ct_tstamp: Unable to register extension\n"); return ret; } -void nf_conntrack_tstamp_fini(struct net *net) +void nf_conntrack_tstamp_fini(void) { - nf_conntrack_tstamp_fini_sysctl(net); - if (net_eq(net, &init_net)) - nf_ct_extend_unregister(&tstamp_extend); + nf_ct_extend_unregister(&tstamp_extend); } diff --git a/net/netfilter/nf_nat_sip.c b/net/netfilter/nf_nat_sip.c index 16303c752213..5951146e7688 100644 --- a/net/netfilter/nf_nat_sip.c +++ b/net/netfilter/nf_nat_sip.c @@ -95,6 +95,7 @@ static int map_addr(struct sk_buff *skb, unsigned int protoff, enum ip_conntrack_info ctinfo; struct nf_conn *ct = nf_ct_get(skb, &ctinfo); enum ip_conntrack_dir dir = CTINFO2DIR(ctinfo); + struct nf_ct_sip_master *ct_sip_info = nfct_help_data(ct); char buffer[INET6_ADDRSTRLEN + sizeof("[]:nnnnn")]; unsigned int buflen; union nf_inet_addr newaddr; @@ -107,7 +108,8 @@ static int map_addr(struct sk_buff *skb, unsigned int protoff, } else if (nf_inet_addr_cmp(&ct->tuplehash[dir].tuple.dst.u3, addr) && ct->tuplehash[dir].tuple.dst.u.udp.port == port) { newaddr = ct->tuplehash[!dir].tuple.src.u3; - newport = ct->tuplehash[!dir].tuple.src.u.udp.port; + newport = ct_sip_info->forced_dport ? : + ct->tuplehash[!dir].tuple.src.u.udp.port; } else return 1; @@ -144,6 +146,7 @@ static unsigned int nf_nat_sip(struct sk_buff *skb, unsigned int protoff, enum ip_conntrack_info ctinfo; struct nf_conn *ct = nf_ct_get(skb, &ctinfo); enum ip_conntrack_dir dir = CTINFO2DIR(ctinfo); + struct nf_ct_sip_master *ct_sip_info = nfct_help_data(ct); unsigned int coff, matchoff, matchlen; enum sip_header_types hdr; union nf_inet_addr addr; @@ -258,6 +261,21 @@ next: !map_sip_addr(skb, protoff, dataoff, dptr, datalen, SIP_HDR_TO)) return NF_DROP; + /* Mangle destination port for Cisco phones, then fix up checksums */ + if (dir == IP_CT_DIR_REPLY && ct_sip_info->forced_dport) { + struct udphdr *uh; + + if (!skb_make_writable(skb, skb->len)) + return NF_DROP; + + uh = (void *)skb->data + protoff; + uh->dest = ct_sip_info->forced_dport; + + if (!nf_nat_mangle_udp_packet(skb, ct, ctinfo, protoff, + 0, 0, NULL, 0)) + return NF_DROP; + } + return NF_ACCEPT; } @@ -311,8 +329,10 @@ static unsigned int nf_nat_sip_expect(struct sk_buff *skb, unsigned int protoff, enum ip_conntrack_info ctinfo; struct nf_conn *ct = nf_ct_get(skb, &ctinfo); enum ip_conntrack_dir dir = CTINFO2DIR(ctinfo); + struct nf_ct_sip_master *ct_sip_info = nfct_help_data(ct); union nf_inet_addr newaddr; u_int16_t port; + __be16 srcport; char buffer[INET6_ADDRSTRLEN + sizeof("[]:nnnnn")]; unsigned int buflen; @@ -326,8 +346,9 @@ static unsigned int nf_nat_sip_expect(struct sk_buff *skb, unsigned int protoff, /* If the signalling port matches the connection's source port in the * original direction, try to use the destination port in the opposite * direction. */ - if (exp->tuple.dst.u.udp.port == - ct->tuplehash[dir].tuple.src.u.udp.port) + srcport = ct_sip_info->forced_dport ? : + ct->tuplehash[dir].tuple.src.u.udp.port; + if (exp->tuple.dst.u.udp.port == srcport) port = ntohs(ct->tuplehash[!dir].tuple.dst.u.udp.port); else port = ntohs(exp->tuple.dst.u.udp.port); diff --git a/net/netfilter/nfnetlink_log.c b/net/netfilter/nfnetlink_log.c index 9f199f2e31fa..92fd8eca0d31 100644 --- a/net/netfilter/nfnetlink_log.c +++ b/net/netfilter/nfnetlink_log.c @@ -13,6 +13,7 @@ */ #include <linux/module.h> #include <linux/skbuff.h> +#include <linux/if_arp.h> #include <linux/init.h> #include <linux/ip.h> #include <linux/ipv6.h> @@ -384,6 +385,7 @@ __build_packet_message(struct nfulnl_instance *inst, struct nfgenmsg *nfmsg; sk_buff_data_t old_tail = inst->skb->tail; struct sock *sk; + const unsigned char *hwhdrp; nlh = nlmsg_put(inst->skb, 0, 0, NFNL_SUBSYS_ULOG << 8 | NFULNL_MSG_PACKET, @@ -485,9 +487,17 @@ __build_packet_message(struct nfulnl_instance *inst, if (indev && skb_mac_header_was_set(skb)) { if (nla_put_be16(inst->skb, NFULA_HWTYPE, htons(skb->dev->type)) || nla_put_be16(inst->skb, NFULA_HWLEN, - htons(skb->dev->hard_header_len)) || - nla_put(inst->skb, NFULA_HWHEADER, skb->dev->hard_header_len, - skb_mac_header(skb))) + htons(skb->dev->hard_header_len))) + goto nla_put_failure; + + hwhdrp = skb_mac_header(skb); + + if (skb->dev->type == ARPHRD_SIT) + hwhdrp -= ETH_HLEN; + + if (hwhdrp >= skb->head && + nla_put(inst->skb, NFULA_HWHEADER, + skb->dev->hard_header_len, hwhdrp)) goto nla_put_failure; } diff --git a/net/netfilter/x_tables.c b/net/netfilter/x_tables.c index 8d987c3573fd..7b3a9e5999c0 100644 --- a/net/netfilter/x_tables.c +++ b/net/netfilter/x_tables.c @@ -345,19 +345,27 @@ int xt_find_revision(u8 af, const char *name, u8 revision, int target, } EXPORT_SYMBOL_GPL(xt_find_revision); -static char *textify_hooks(char *buf, size_t size, unsigned int mask) +static char * +textify_hooks(char *buf, size_t size, unsigned int mask, uint8_t nfproto) { - static const char *const names[] = { + static const char *const inetbr_names[] = { "PREROUTING", "INPUT", "FORWARD", "OUTPUT", "POSTROUTING", "BROUTING", }; - unsigned int i; + static const char *const arp_names[] = { + "INPUT", "FORWARD", "OUTPUT", + }; + const char *const *names; + unsigned int i, max; char *p = buf; bool np = false; int res; + names = (nfproto == NFPROTO_ARP) ? arp_names : inetbr_names; + max = (nfproto == NFPROTO_ARP) ? ARRAY_SIZE(arp_names) : + ARRAY_SIZE(inetbr_names); *p = '\0'; - for (i = 0; i < ARRAY_SIZE(names); ++i) { + for (i = 0; i < max; ++i) { if (!(mask & (1 << i))) continue; res = snprintf(p, size, "%s%s", np ? "/" : "", names[i]); @@ -402,8 +410,10 @@ int xt_check_match(struct xt_mtchk_param *par, pr_err("%s_tables: %s match: used from hooks %s, but only " "valid from %s\n", xt_prefix[par->family], par->match->name, - textify_hooks(used, sizeof(used), par->hook_mask), - textify_hooks(allow, sizeof(allow), par->match->hooks)); + textify_hooks(used, sizeof(used), par->hook_mask, + par->family), + textify_hooks(allow, sizeof(allow), par->match->hooks, + par->family)); return -EINVAL; } if (par->match->proto && (par->match->proto != proto || inv_proto)) { @@ -575,8 +585,10 @@ int xt_check_target(struct xt_tgchk_param *par, pr_err("%s_tables: %s target: used from hooks %s, but only " "usable from %s\n", xt_prefix[par->family], par->target->name, - textify_hooks(used, sizeof(used), par->hook_mask), - textify_hooks(allow, sizeof(allow), par->target->hooks)); + textify_hooks(used, sizeof(used), par->hook_mask, + par->family), + textify_hooks(allow, sizeof(allow), par->target->hooks, + par->family)); return -EINVAL; } if (par->target->proto && (par->target->proto != proto || inv_proto)) { diff --git a/net/netfilter/xt_CT.c b/net/netfilter/xt_CT.c index ae7f5daeee43..bde009ed8d3b 100644 --- a/net/netfilter/xt_CT.c +++ b/net/netfilter/xt_CT.c @@ -109,7 +109,7 @@ static int xt_ct_tg_check_v0(const struct xt_tgchk_param *par) struct xt_ct_target_info *info = par->targinfo; struct nf_conntrack_tuple t; struct nf_conn *ct; - int ret; + int ret = -EOPNOTSUPP; if (info->flags & ~XT_CT_NOTRACK) return -EINVAL; @@ -149,6 +149,10 @@ static int xt_ct_tg_check_v0(const struct xt_tgchk_param *par) __set_bit(IPS_TEMPLATE_BIT, &ct->status); __set_bit(IPS_CONFIRMED_BIT, &ct->status); + + /* Overload tuple linked list to put us in template list. */ + hlist_nulls_add_head_rcu(&ct->tuplehash[IP_CT_DIR_ORIGINAL].hnnode, + &par->net->ct.tmpl); out: info->ct = ct; return 0; @@ -243,7 +247,7 @@ static int xt_ct_tg_check_v1(const struct xt_tgchk_param *par) struct xt_ct_target_info_v1 *info = par->targinfo; struct nf_conntrack_tuple t; struct nf_conn *ct; - int ret; + int ret = -EOPNOTSUPP; if (info->flags & ~XT_CT_NOTRACK) return -EINVAL; @@ -289,6 +293,10 @@ static int xt_ct_tg_check_v1(const struct xt_tgchk_param *par) __set_bit(IPS_TEMPLATE_BIT, &ct->status); __set_bit(IPS_CONFIRMED_BIT, &ct->status); + + /* Overload tuple linked list to put us in template list. */ + hlist_nulls_add_head_rcu(&ct->tuplehash[IP_CT_DIR_ORIGINAL].hnnode, + &par->net->ct.tmpl); out: info->ct = ct; return 0; @@ -377,14 +385,60 @@ static struct xt_target xt_ct_tg_reg[] __read_mostly = { }, }; +static unsigned int +notrack_tg(struct sk_buff *skb, const struct xt_action_param *par) +{ + /* Previously seen (loopback)? Ignore. */ + if (skb->nfct != NULL) + return XT_CONTINUE; + + skb->nfct = &nf_ct_untracked_get()->ct_general; + skb->nfctinfo = IP_CT_NEW; + nf_conntrack_get(skb->nfct); + + return XT_CONTINUE; +} + +static int notrack_chk(const struct xt_tgchk_param *par) +{ + if (!par->net->xt.notrack_deprecated_warning) { + pr_info("netfilter: NOTRACK target is deprecated, " + "use CT instead or upgrade iptables\n"); + par->net->xt.notrack_deprecated_warning = true; + } + return 0; +} + +static struct xt_target notrack_tg_reg __read_mostly = { + .name = "NOTRACK", + .revision = 0, + .family = NFPROTO_UNSPEC, + .checkentry = notrack_chk, + .target = notrack_tg, + .table = "raw", + .me = THIS_MODULE, +}; + static int __init xt_ct_tg_init(void) { - return xt_register_targets(xt_ct_tg_reg, ARRAY_SIZE(xt_ct_tg_reg)); + int ret; + + ret = xt_register_target(¬rack_tg_reg); + if (ret < 0) + return ret; + + ret = xt_register_targets(xt_ct_tg_reg, ARRAY_SIZE(xt_ct_tg_reg)); + if (ret < 0) { + xt_unregister_target(¬rack_tg_reg); + return ret; + } + return 0; } static void __exit xt_ct_tg_exit(void) { xt_unregister_targets(xt_ct_tg_reg, ARRAY_SIZE(xt_ct_tg_reg)); + xt_unregister_target(¬rack_tg_reg); } module_init(xt_ct_tg_init); @@ -394,3 +448,5 @@ MODULE_LICENSE("GPL"); MODULE_DESCRIPTION("Xtables: connection tracking target"); MODULE_ALIAS("ipt_CT"); MODULE_ALIAS("ip6t_CT"); +MODULE_ALIAS("ipt_NOTRACK"); +MODULE_ALIAS("ip6t_NOTRACK"); diff --git a/net/netfilter/xt_bpf.c b/net/netfilter/xt_bpf.c new file mode 100644 index 000000000000..12d4da8e6c77 --- /dev/null +++ b/net/netfilter/xt_bpf.c @@ -0,0 +1,73 @@ +/* Xtables module to match packets using a BPF filter. + * Copyright 2013 Google Inc. + * Written by Willem de Bruijn <willemb@google.com> + * + * 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. + */ + +#include <linux/module.h> +#include <linux/skbuff.h> +#include <linux/filter.h> + +#include <linux/netfilter/xt_bpf.h> +#include <linux/netfilter/x_tables.h> + +MODULE_AUTHOR("Willem de Bruijn <willemb@google.com>"); +MODULE_DESCRIPTION("Xtables: BPF filter match"); +MODULE_LICENSE("GPL"); +MODULE_ALIAS("ipt_bpf"); +MODULE_ALIAS("ip6t_bpf"); + +static int bpf_mt_check(const struct xt_mtchk_param *par) +{ + struct xt_bpf_info *info = par->matchinfo; + struct sock_fprog program; + + program.len = info->bpf_program_num_elem; + program.filter = (struct sock_filter __user *) info->bpf_program; + if (sk_unattached_filter_create(&info->filter, &program)) { + pr_info("bpf: check failed: parse error\n"); + return -EINVAL; + } + + return 0; +} + +static bool bpf_mt(const struct sk_buff *skb, struct xt_action_param *par) +{ + const struct xt_bpf_info *info = par->matchinfo; + + return SK_RUN_FILTER(info->filter, skb); +} + +static void bpf_mt_destroy(const struct xt_mtdtor_param *par) +{ + const struct xt_bpf_info *info = par->matchinfo; + sk_unattached_filter_destroy(info->filter); +} + +static struct xt_match bpf_mt_reg __read_mostly = { + .name = "bpf", + .revision = 0, + .family = NFPROTO_UNSPEC, + .checkentry = bpf_mt_check, + .match = bpf_mt, + .destroy = bpf_mt_destroy, + .matchsize = sizeof(struct xt_bpf_info), + .me = THIS_MODULE, +}; + +static int __init bpf_mt_init(void) +{ + return xt_register_match(&bpf_mt_reg); +} + +static void __exit bpf_mt_exit(void) +{ + xt_unregister_match(&bpf_mt_reg); +} + +module_init(bpf_mt_init); +module_exit(bpf_mt_exit); diff --git a/net/netfilter/xt_connlabel.c b/net/netfilter/xt_connlabel.c new file mode 100644 index 000000000000..9f8719df2001 --- /dev/null +++ b/net/netfilter/xt_connlabel.c @@ -0,0 +1,99 @@ +/* + * (C) 2013 Astaro GmbH & Co KG + * + * 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. + */ + +#include <linux/module.h> +#include <linux/skbuff.h> +#include <net/netfilter/nf_conntrack.h> +#include <net/netfilter/nf_conntrack_labels.h> +#include <linux/netfilter/x_tables.h> + +MODULE_LICENSE("GPL"); +MODULE_AUTHOR("Florian Westphal <fw@strlen.de>"); +MODULE_DESCRIPTION("Xtables: add/match connection trackling labels"); +MODULE_ALIAS("ipt_connlabel"); +MODULE_ALIAS("ip6t_connlabel"); + +static bool +connlabel_mt(const struct sk_buff *skb, struct xt_action_param *par) +{ + const struct xt_connlabel_mtinfo *info = par->matchinfo; + enum ip_conntrack_info ctinfo; + struct nf_conn *ct; + bool invert = info->options & XT_CONNLABEL_OP_INVERT; + + ct = nf_ct_get(skb, &ctinfo); + if (ct == NULL || nf_ct_is_untracked(ct)) + return invert; + + if (info->options & XT_CONNLABEL_OP_SET) + return (nf_connlabel_set(ct, info->bit) == 0) ^ invert; + + return nf_connlabel_match(ct, info->bit) ^ invert; +} + +static int connlabel_mt_check(const struct xt_mtchk_param *par) +{ + const int options = XT_CONNLABEL_OP_INVERT | + XT_CONNLABEL_OP_SET; + struct xt_connlabel_mtinfo *info = par->matchinfo; + int ret; + size_t words; + + if (info->bit > XT_CONNLABEL_MAXBIT) + return -ERANGE; + + if (info->options & ~options) { + pr_err("Unknown options in mask %x\n", info->options); + return -EINVAL; + } + + ret = nf_ct_l3proto_try_module_get(par->family); + if (ret < 0) { + pr_info("cannot load conntrack support for proto=%u\n", + par->family); + return ret; + } + + par->net->ct.labels_used++; + words = BITS_TO_LONGS(info->bit+1); + if (words > par->net->ct.label_words) + par->net->ct.label_words = words; + + return ret; +} + +static void connlabel_mt_destroy(const struct xt_mtdtor_param *par) +{ + par->net->ct.labels_used--; + if (par->net->ct.labels_used == 0) + par->net->ct.label_words = 0; + nf_ct_l3proto_module_put(par->family); +} + +static struct xt_match connlabels_mt_reg __read_mostly = { + .name = "connlabel", + .family = NFPROTO_UNSPEC, + .checkentry = connlabel_mt_check, + .match = connlabel_mt, + .matchsize = sizeof(struct xt_connlabel_mtinfo), + .destroy = connlabel_mt_destroy, + .me = THIS_MODULE, +}; + +static int __init connlabel_mt_init(void) +{ + return xt_register_match(&connlabels_mt_reg); +} + +static void __exit connlabel_mt_exit(void) +{ + xt_unregister_match(&connlabels_mt_reg); +} + +module_init(connlabel_mt_init); +module_exit(connlabel_mt_exit); diff --git a/net/netfilter/xt_hashlimit.c b/net/netfilter/xt_hashlimit.c index 26a668a84aa2..a9d7af953ceb 100644 --- a/net/netfilter/xt_hashlimit.c +++ b/net/netfilter/xt_hashlimit.c @@ -157,11 +157,22 @@ dsthash_find(const struct xt_hashlimit_htable *ht, /* allocate dsthash_ent, initialize dst, put in htable and lock it */ static struct dsthash_ent * dsthash_alloc_init(struct xt_hashlimit_htable *ht, - const struct dsthash_dst *dst) + const struct dsthash_dst *dst, bool *race) { struct dsthash_ent *ent; spin_lock(&ht->lock); + + /* Two or more packets may race to create the same entry in the + * hashtable, double check if this packet lost race. + */ + ent = dsthash_find(ht, dst); + if (ent != NULL) { + spin_unlock(&ht->lock); + *race = true; + return ent; + } + /* initialize hash with random val at the time we allocate * the first hashtable entry */ if (unlikely(!ht->rnd_initialized)) { @@ -318,7 +329,10 @@ static void htable_destroy(struct xt_hashlimit_htable *hinfo) parent = hashlimit_net->ipt_hashlimit; else parent = hashlimit_net->ip6t_hashlimit; - remove_proc_entry(hinfo->pde->name, parent); + + if(parent != NULL) + remove_proc_entry(hinfo->pde->name, parent); + htable_selective_cleanup(hinfo, select_all); vfree(hinfo); } @@ -585,6 +599,7 @@ hashlimit_mt(const struct sk_buff *skb, struct xt_action_param *par) unsigned long now = jiffies; struct dsthash_ent *dh; struct dsthash_dst dst; + bool race = false; u32 cost; if (hashlimit_init_dst(hinfo, &dst, skb, par->thoff) < 0) @@ -593,13 +608,18 @@ hashlimit_mt(const struct sk_buff *skb, struct xt_action_param *par) rcu_read_lock_bh(); dh = dsthash_find(hinfo, &dst); if (dh == NULL) { - dh = dsthash_alloc_init(hinfo, &dst); + dh = dsthash_alloc_init(hinfo, &dst, &race); if (dh == NULL) { rcu_read_unlock_bh(); goto hotdrop; + } else if (race) { + /* Already got an entry, update expiration timeout */ + dh->expires = now + msecs_to_jiffies(hinfo->cfg.expire); + rateinfo_recalc(dh, now, hinfo->cfg.mode); + } else { + dh->expires = jiffies + msecs_to_jiffies(hinfo->cfg.expire); + rateinfo_init(dh, hinfo); } - dh->expires = jiffies + msecs_to_jiffies(hinfo->cfg.expire); - rateinfo_init(dh, hinfo); } else { /* update expiration timeout */ dh->expires = now + msecs_to_jiffies(hinfo->cfg.expire); @@ -856,6 +876,27 @@ static int __net_init hashlimit_proc_net_init(struct net *net) static void __net_exit hashlimit_proc_net_exit(struct net *net) { + struct xt_hashlimit_htable *hinfo; + struct hlist_node *pos; + struct proc_dir_entry *pde; + struct hashlimit_net *hashlimit_net = hashlimit_pernet(net); + + /* recent_net_exit() is called before recent_mt_destroy(). Make sure + * that the parent xt_recent proc entry is is empty before trying to + * remove it. + */ + mutex_lock(&hashlimit_mutex); + pde = hashlimit_net->ipt_hashlimit; + if (pde == NULL) + pde = hashlimit_net->ip6t_hashlimit; + + hlist_for_each_entry(hinfo, pos, &hashlimit_net->htables, node) + remove_proc_entry(hinfo->pde->name, pde); + + hashlimit_net->ipt_hashlimit = NULL; + hashlimit_net->ip6t_hashlimit = NULL; + mutex_unlock(&hashlimit_mutex); + proc_net_remove(net, "ipt_hashlimit"); #if IS_ENABLED(CONFIG_IP6_NF_IPTABLES) proc_net_remove(net, "ip6t_hashlimit"); @@ -872,9 +913,6 @@ static int __net_init hashlimit_net_init(struct net *net) static void __net_exit hashlimit_net_exit(struct net *net) { - struct hashlimit_net *hashlimit_net = hashlimit_pernet(net); - - BUG_ON(!hlist_empty(&hashlimit_net->htables)); hashlimit_proc_net_exit(net); } diff --git a/net/netfilter/xt_recent.c b/net/netfilter/xt_recent.c index 4635c9b00459..978efc9b555a 100644 --- a/net/netfilter/xt_recent.c +++ b/net/netfilter/xt_recent.c @@ -29,6 +29,7 @@ #include <linux/skbuff.h> #include <linux/inet.h> #include <linux/slab.h> +#include <linux/vmalloc.h> #include <net/net_namespace.h> #include <net/netns/generic.h> @@ -310,6 +311,14 @@ out: return ret; } +static void recent_table_free(void *addr) +{ + if (is_vmalloc_addr(addr)) + vfree(addr); + else + kfree(addr); +} + static int recent_mt_check(const struct xt_mtchk_param *par, const struct xt_recent_mtinfo_v1 *info) { @@ -322,6 +331,7 @@ static int recent_mt_check(const struct xt_mtchk_param *par, #endif unsigned int i; int ret = -EINVAL; + size_t sz; if (unlikely(!hash_rnd_inited)) { get_random_bytes(&hash_rnd, sizeof(hash_rnd)); @@ -360,8 +370,11 @@ static int recent_mt_check(const struct xt_mtchk_param *par, goto out; } - t = kzalloc(sizeof(*t) + sizeof(t->iphash[0]) * ip_list_hash_size, - GFP_KERNEL); + sz = sizeof(*t) + sizeof(t->iphash[0]) * ip_list_hash_size; + if (sz <= PAGE_SIZE) + t = kzalloc(sz, GFP_KERNEL); + else + t = vzalloc(sz); if (t == NULL) { ret = -ENOMEM; goto out; @@ -377,14 +390,14 @@ static int recent_mt_check(const struct xt_mtchk_param *par, uid = make_kuid(&init_user_ns, ip_list_uid); gid = make_kgid(&init_user_ns, ip_list_gid); if (!uid_valid(uid) || !gid_valid(gid)) { - kfree(t); + recent_table_free(t); ret = -EINVAL; goto out; } pde = proc_create_data(t->name, ip_list_perms, recent_net->xt_recent, &recent_mt_fops, t); if (pde == NULL) { - kfree(t); + recent_table_free(t); ret = -ENOMEM; goto out; } @@ -431,10 +444,11 @@ static void recent_mt_destroy(const struct xt_mtdtor_param *par) list_del(&t->list); spin_unlock_bh(&recent_lock); #ifdef CONFIG_PROC_FS - remove_proc_entry(t->name, recent_net->xt_recent); + if (recent_net->xt_recent != NULL) + remove_proc_entry(t->name, recent_net->xt_recent); #endif recent_table_flush(t); - kfree(t); + recent_table_free(t); } mutex_unlock(&recent_mutex); } @@ -615,6 +629,20 @@ static int __net_init recent_proc_net_init(struct net *net) static void __net_exit recent_proc_net_exit(struct net *net) { + struct recent_net *recent_net = recent_pernet(net); + struct recent_table *t; + + /* recent_net_exit() is called before recent_mt_destroy(). Make sure + * that the parent xt_recent proc entry is is empty before trying to + * remove it. + */ + spin_lock_bh(&recent_lock); + list_for_each_entry(t, &recent_net->tables, list) + remove_proc_entry(t->name, recent_net->xt_recent); + + recent_net->xt_recent = NULL; + spin_unlock_bh(&recent_lock); + proc_net_remove(net, "xt_recent"); } #else @@ -638,9 +666,6 @@ static int __net_init recent_net_init(struct net *net) static void __net_exit recent_net_exit(struct net *net) { - struct recent_net *recent_net = recent_pernet(net); - - BUG_ON(!list_empty(&recent_net->tables)); recent_proc_net_exit(net); } diff --git a/net/netlink/af_netlink.c b/net/netlink/af_netlink.c index c0353d55d56f..74827e3b26a1 100644 --- a/net/netlink/af_netlink.c +++ b/net/netlink/af_netlink.c @@ -2185,7 +2185,6 @@ static struct pernet_operations __net_initdata netlink_net_ops = { static int __init netlink_proto_init(void) { - struct sk_buff *dummy_skb; int i; unsigned long limit; unsigned int order; @@ -2194,7 +2193,7 @@ static int __init netlink_proto_init(void) if (err != 0) goto out; - BUILD_BUG_ON(sizeof(struct netlink_skb_parms) > sizeof(dummy_skb->cb)); + BUILD_BUG_ON(sizeof(struct netlink_skb_parms) > FIELD_SIZEOF(struct sk_buff, cb)); nl_table = kcalloc(MAX_LINKS, sizeof(*nl_table), GFP_KERNEL); if (!nl_table) diff --git a/net/openvswitch/datapath.c b/net/openvswitch/datapath.c index f996db343247..9dc537df46c4 100644 --- a/net/openvswitch/datapath.c +++ b/net/openvswitch/datapath.c @@ -301,7 +301,7 @@ static int queue_gso_packets(struct net *net, int dp_ifindex, struct sk_buff *segs, *nskb; int err; - segs = skb_gso_segment(skb, NETIF_F_SG | NETIF_F_HW_CSUM); + segs = __skb_gso_segment(skb, NETIF_F_SG | NETIF_F_HW_CSUM, false); if (IS_ERR(segs)) return PTR_ERR(segs); @@ -1989,10 +1989,9 @@ static struct pernet_operations ovs_net_ops = { static int __init dp_init(void) { - struct sk_buff *dummy_skb; int err; - BUILD_BUG_ON(sizeof(struct ovs_skb_cb) > sizeof(dummy_skb->cb)); + BUILD_BUG_ON(sizeof(struct ovs_skb_cb) > FIELD_SIZEOF(struct sk_buff, cb)); pr_info("Open vSwitch switching datapath\n"); diff --git a/net/openvswitch/vport-internal_dev.c b/net/openvswitch/vport-internal_dev.c index 5d460c37df07..0531de6c7a4a 100644 --- a/net/openvswitch/vport-internal_dev.c +++ b/net/openvswitch/vport-internal_dev.c @@ -69,7 +69,6 @@ static int internal_dev_mac_addr(struct net_device *dev, void *p) if (!is_valid_ether_addr(addr->sa_data)) return -EADDRNOTAVAIL; - dev->addr_assign_type &= ~NET_ADDR_RANDOM; memcpy(dev->dev_addr, addr->sa_data, dev->addr_len); return 0; } @@ -98,7 +97,7 @@ static int internal_dev_stop(struct net_device *netdev) static void internal_dev_getinfo(struct net_device *netdev, struct ethtool_drvinfo *info) { - strcpy(info->driver, "openvswitch"); + strlcpy(info->driver, "openvswitch", sizeof(info->driver)); } static const struct ethtool_ops internal_dev_ethtool_ops = { diff --git a/net/openvswitch/vport-netdev.c b/net/openvswitch/vport-netdev.c index a9327e2e48ce..670cbc3518de 100644 --- a/net/openvswitch/vport-netdev.c +++ b/net/openvswitch/vport-netdev.c @@ -35,10 +35,11 @@ /* Must be called with rcu_read_lock. */ static void netdev_port_receive(struct vport *vport, struct sk_buff *skb) { - if (unlikely(!vport)) { - kfree_skb(skb); - return; - } + if (unlikely(!vport)) + goto error; + + if (unlikely(skb_warn_if_lro(skb))) + goto error; /* Make our own copy of the packet. Otherwise we will mangle the * packet for anyone who came before us (e.g. tcpdump via AF_PACKET). @@ -50,6 +51,10 @@ static void netdev_port_receive(struct vport *vport, struct sk_buff *skb) skb_push(skb, ETH_HLEN); ovs_vport_receive(vport, skb); + return; + +error: + kfree_skb(skb); } /* Called with rcu_read_lock and bottom-halves disabled. */ @@ -169,9 +174,6 @@ static int netdev_send(struct vport *vport, struct sk_buff *skb) goto error; } - if (unlikely(skb_warn_if_lro(skb))) - goto error; - skb->dev = netdev_vport->dev; len = skb->len; dev_queue_xmit(skb); diff --git a/net/packet/af_packet.c b/net/packet/af_packet.c index e639645e8fec..c111bd0e083a 100644 --- a/net/packet/af_packet.c +++ b/net/packet/af_packet.c @@ -2361,13 +2361,15 @@ static int packet_release(struct socket *sock) packet_flush_mclist(sk); - memset(&req_u, 0, sizeof(req_u)); - - if (po->rx_ring.pg_vec) + if (po->rx_ring.pg_vec) { + memset(&req_u, 0, sizeof(req_u)); packet_set_ring(sk, &req_u, 1, 0); + } - if (po->tx_ring.pg_vec) + if (po->tx_ring.pg_vec) { + memset(&req_u, 0, sizeof(req_u)); packet_set_ring(sk, &req_u, 1, 1); + } fanout_release(sk); diff --git a/net/rds/ib_cm.c b/net/rds/ib_cm.c index a1e116277477..31b74f5e61ad 100644 --- a/net/rds/ib_cm.c +++ b/net/rds/ib_cm.c @@ -434,12 +434,11 @@ static u32 rds_ib_protocol_compatible(struct rdma_cm_event *event) version = RDS_PROTOCOL_3_0; while ((common >>= 1) != 0) version++; - } - printk_ratelimited(KERN_NOTICE "RDS: Connection from %pI4 using " - "incompatible protocol version %u.%u\n", - &dp->dp_saddr, - dp->dp_protocol_major, - dp->dp_protocol_minor); + } else + printk_ratelimited(KERN_NOTICE "RDS: Connection from %pI4 using incompatible protocol version %u.%u\n", + &dp->dp_saddr, + dp->dp_protocol_major, + dp->dp_protocol_minor); return version; } diff --git a/net/rds/ib_recv.c b/net/rds/ib_recv.c index 8c5bc857f04d..8eb9501e3d60 100644 --- a/net/rds/ib_recv.c +++ b/net/rds/ib_recv.c @@ -339,8 +339,8 @@ static int rds_ib_recv_refill_one(struct rds_connection *conn, sge->length = sizeof(struct rds_header); sge = &recv->r_sge[1]; - sge->addr = sg_dma_address(&recv->r_frag->f_sg); - sge->length = sg_dma_len(&recv->r_frag->f_sg); + sge->addr = ib_sg_dma_address(ic->i_cm_id->device, &recv->r_frag->f_sg); + sge->length = ib_sg_dma_len(ic->i_cm_id->device, &recv->r_frag->f_sg); ret = 0; out: @@ -381,7 +381,10 @@ void rds_ib_recv_refill(struct rds_connection *conn, int prefill) ret = ib_post_recv(ic->i_cm_id->qp, &recv->r_wr, &failed_wr); rdsdebug("recv %p ibinc %p page %p addr %lu ret %d\n", recv, recv->r_ibinc, sg_page(&recv->r_frag->f_sg), - (long) sg_dma_address(&recv->r_frag->f_sg), ret); + (long) ib_sg_dma_address( + ic->i_cm_id->device, + &recv->r_frag->f_sg), + ret); if (ret) { rds_ib_conn_error(conn, "recv post on " "%pI4 returned %d, disconnecting and " diff --git a/net/rxrpc/af_rxrpc.c b/net/rxrpc/af_rxrpc.c index 05996d0dd828..5b0fd291babb 100644 --- a/net/rxrpc/af_rxrpc.c +++ b/net/rxrpc/af_rxrpc.c @@ -10,6 +10,7 @@ */ #include <linux/module.h> +#include <linux/kernel.h> #include <linux/net.h> #include <linux/slab.h> #include <linux/skbuff.h> @@ -792,10 +793,9 @@ static const struct net_proto_family rxrpc_family_ops = { */ static int __init af_rxrpc_init(void) { - struct sk_buff *dummy_skb; int ret = -1; - BUILD_BUG_ON(sizeof(struct rxrpc_skb_priv) > sizeof(dummy_skb->cb)); + BUILD_BUG_ON(sizeof(struct rxrpc_skb_priv) > FIELD_SIZEOF(struct sk_buff, cb)); rxrpc_epoch = htonl(get_seconds()); diff --git a/net/sched/act_api.c b/net/sched/act_api.c index 65d240cbf74b..8579c4bb20c9 100644 --- a/net/sched/act_api.c +++ b/net/sched/act_api.c @@ -485,8 +485,9 @@ errout: return err; } -struct tc_action *tcf_action_init_1(struct nlattr *nla, struct nlattr *est, - char *name, int ovr, int bind) +struct tc_action *tcf_action_init_1(struct net *net, struct nlattr *nla, + struct nlattr *est, char *name, int ovr, + int bind) { struct tc_action *a; struct tc_action_ops *a_o; @@ -542,9 +543,9 @@ struct tc_action *tcf_action_init_1(struct nlattr *nla, struct nlattr *est, /* backward compatibility for policer */ if (name == NULL) - err = a_o->init(tb[TCA_ACT_OPTIONS], est, a, ovr, bind); + err = a_o->init(net, tb[TCA_ACT_OPTIONS], est, a, ovr, bind); else - err = a_o->init(nla, est, a, ovr, bind); + err = a_o->init(net, nla, est, a, ovr, bind); if (err < 0) goto err_free; @@ -566,8 +567,9 @@ err_out: return ERR_PTR(err); } -struct tc_action *tcf_action_init(struct nlattr *nla, struct nlattr *est, - char *name, int ovr, int bind) +struct tc_action *tcf_action_init(struct net *net, struct nlattr *nla, + struct nlattr *est, char *name, int ovr, + int bind) { struct nlattr *tb[TCA_ACT_MAX_PRIO + 1]; struct tc_action *head = NULL, *act, *act_prev = NULL; @@ -579,7 +581,7 @@ struct tc_action *tcf_action_init(struct nlattr *nla, struct nlattr *est, return ERR_PTR(err); for (i = 1; i <= TCA_ACT_MAX_PRIO && tb[i]; i++) { - act = tcf_action_init_1(tb[i], est, name, ovr, bind); + act = tcf_action_init_1(net, tb[i], est, name, ovr, bind); if (IS_ERR(act)) goto err; act->order = i; @@ -960,7 +962,7 @@ tcf_action_add(struct net *net, struct nlattr *nla, struct nlmsghdr *n, struct tc_action *a; u32 seq = n->nlmsg_seq; - act = tcf_action_init(nla, NULL, NULL, ovr, 0); + act = tcf_action_init(net, nla, NULL, NULL, ovr, 0); if (act == NULL) goto done; if (IS_ERR(act)) { diff --git a/net/sched/act_csum.c b/net/sched/act_csum.c index 2c8ad7c86e43..08fa1e8a4ca4 100644 --- a/net/sched/act_csum.c +++ b/net/sched/act_csum.c @@ -51,7 +51,7 @@ static const struct nla_policy csum_policy[TCA_CSUM_MAX + 1] = { [TCA_CSUM_PARMS] = { .len = sizeof(struct tc_csum), }, }; -static int tcf_csum_init(struct nlattr *nla, struct nlattr *est, +static int tcf_csum_init(struct net *n, struct nlattr *nla, struct nlattr *est, struct tc_action *a, int ovr, int bind) { struct nlattr *tb[TCA_CSUM_MAX + 1]; diff --git a/net/sched/act_gact.c b/net/sched/act_gact.c index 05d60859d8e3..fd2b3cff5fa2 100644 --- a/net/sched/act_gact.c +++ b/net/sched/act_gact.c @@ -58,8 +58,9 @@ static const struct nla_policy gact_policy[TCA_GACT_MAX + 1] = { [TCA_GACT_PROB] = { .len = sizeof(struct tc_gact_p) }, }; -static int tcf_gact_init(struct nlattr *nla, struct nlattr *est, - struct tc_action *a, int ovr, int bind) +static int tcf_gact_init(struct net *net, struct nlattr *nla, + struct nlattr *est, struct tc_action *a, + int ovr, int bind) { struct nlattr *tb[TCA_GACT_MAX + 1]; struct tc_gact *parm; diff --git a/net/sched/act_ipt.c b/net/sched/act_ipt.c index 58fb3c7aab9e..e0f6de64afec 100644 --- a/net/sched/act_ipt.c +++ b/net/sched/act_ipt.c @@ -102,7 +102,7 @@ static const struct nla_policy ipt_policy[TCA_IPT_MAX + 1] = { [TCA_IPT_TARG] = { .len = sizeof(struct xt_entry_target) }, }; -static int tcf_ipt_init(struct nlattr *nla, struct nlattr *est, +static int tcf_ipt_init(struct net *net, struct nlattr *nla, struct nlattr *est, struct tc_action *a, int ovr, int bind) { struct nlattr *tb[TCA_IPT_MAX + 1]; @@ -207,10 +207,8 @@ static int tcf_ipt(struct sk_buff *skb, const struct tc_action *a, struct tcf_ipt *ipt = a->priv; struct xt_action_param par; - if (skb_cloned(skb)) { - if (pskb_expand_head(skb, 0, 0, GFP_ATOMIC)) - return TC_ACT_UNSPEC; - } + if (skb_unclone(skb, GFP_ATOMIC)) + return TC_ACT_UNSPEC; spin_lock(&ipt->tcf_lock); diff --git a/net/sched/act_mirred.c b/net/sched/act_mirred.c index 9c0fd0c78814..5d676edc22a6 100644 --- a/net/sched/act_mirred.c +++ b/net/sched/act_mirred.c @@ -62,8 +62,9 @@ static const struct nla_policy mirred_policy[TCA_MIRRED_MAX + 1] = { [TCA_MIRRED_PARMS] = { .len = sizeof(struct tc_mirred) }, }; -static int tcf_mirred_init(struct nlattr *nla, struct nlattr *est, - struct tc_action *a, int ovr, int bind) +static int tcf_mirred_init(struct net *net, struct nlattr *nla, + struct nlattr *est, struct tc_action *a, int ovr, + int bind) { struct nlattr *tb[TCA_MIRRED_MAX + 1]; struct tc_mirred *parm; @@ -88,7 +89,7 @@ static int tcf_mirred_init(struct nlattr *nla, struct nlattr *est, return -EINVAL; } if (parm->ifindex) { - dev = __dev_get_by_index(&init_net, parm->ifindex); + dev = __dev_get_by_index(net, parm->ifindex); if (dev == NULL) return -ENODEV; switch (dev->type) { diff --git a/net/sched/act_nat.c b/net/sched/act_nat.c index b5d029eb44f2..876f0ef29694 100644 --- a/net/sched/act_nat.c +++ b/net/sched/act_nat.c @@ -44,7 +44,7 @@ static const struct nla_policy nat_policy[TCA_NAT_MAX + 1] = { [TCA_NAT_PARMS] = { .len = sizeof(struct tc_nat) }, }; -static int tcf_nat_init(struct nlattr *nla, struct nlattr *est, +static int tcf_nat_init(struct net *net, struct nlattr *nla, struct nlattr *est, struct tc_action *a, int ovr, int bind) { struct nlattr *tb[TCA_NAT_MAX + 1]; diff --git a/net/sched/act_pedit.c b/net/sched/act_pedit.c index 45c53ab067a6..7ed78c9e505c 100644 --- a/net/sched/act_pedit.c +++ b/net/sched/act_pedit.c @@ -38,8 +38,9 @@ static const struct nla_policy pedit_policy[TCA_PEDIT_MAX + 1] = { [TCA_PEDIT_PARMS] = { .len = sizeof(struct tc_pedit) }, }; -static int tcf_pedit_init(struct nlattr *nla, struct nlattr *est, - struct tc_action *a, int ovr, int bind) +static int tcf_pedit_init(struct net *net, struct nlattr *nla, + struct nlattr *est, struct tc_action *a, + int ovr, int bind) { struct nlattr *tb[TCA_PEDIT_MAX + 1]; struct tc_pedit *parm; @@ -130,8 +131,7 @@ static int tcf_pedit(struct sk_buff *skb, const struct tc_action *a, int i, munged = 0; unsigned int off; - if (skb_cloned(skb) && - pskb_expand_head(skb, 0, 0, GFP_ATOMIC)) + if (skb_unclone(skb, GFP_ATOMIC)) return p->tcf_action; off = skb_network_offset(skb); diff --git a/net/sched/act_police.c b/net/sched/act_police.c index a9de23297d47..823463adbd21 100644 --- a/net/sched/act_police.c +++ b/net/sched/act_police.c @@ -22,8 +22,23 @@ #include <net/act_api.h> #include <net/netlink.h> -#define L2T(p, L) qdisc_l2t((p)->tcfp_R_tab, L) -#define L2T_P(p, L) qdisc_l2t((p)->tcfp_P_tab, L) +struct tcf_police { + struct tcf_common common; + int tcfp_result; + u32 tcfp_ewma_rate; + s64 tcfp_burst; + u32 tcfp_mtu; + s64 tcfp_toks; + s64 tcfp_ptoks; + s64 tcfp_mtu_ptoks; + s64 tcfp_t_c; + struct psched_ratecfg rate; + bool rate_present; + struct psched_ratecfg peak; + bool peak_present; +}; +#define to_police(pc) \ + container_of(pc, struct tcf_police, common) #define POL_TAB_MASK 15 static struct tcf_common *tcf_police_ht[POL_TAB_MASK + 1]; @@ -108,10 +123,6 @@ static void tcf_police_destroy(struct tcf_police *p) write_unlock_bh(&police_lock); gen_kill_estimator(&p->tcf_bstats, &p->tcf_rate_est); - if (p->tcfp_R_tab) - qdisc_put_rtab(p->tcfp_R_tab); - if (p->tcfp_P_tab) - qdisc_put_rtab(p->tcfp_P_tab); /* * gen_estimator est_timer() might access p->tcf_lock * or bstats, wait a RCU grace period before freeing p @@ -130,8 +141,9 @@ static const struct nla_policy police_policy[TCA_POLICE_MAX + 1] = { [TCA_POLICE_RESULT] = { .type = NLA_U32 }, }; -static int tcf_act_police_locate(struct nlattr *nla, struct nlattr *est, - struct tc_action *a, int ovr, int bind) +static int tcf_act_police_locate(struct net *net, struct nlattr *nla, + struct nlattr *est, struct tc_action *a, + int ovr, int bind) { unsigned int h; int ret = 0, err; @@ -211,26 +223,36 @@ override: } /* No failure allowed after this point */ - if (R_tab != NULL) { - qdisc_put_rtab(police->tcfp_R_tab); - police->tcfp_R_tab = R_tab; + police->tcfp_mtu = parm->mtu; + if (police->tcfp_mtu == 0) { + police->tcfp_mtu = ~0; + if (R_tab) + police->tcfp_mtu = 255 << R_tab->rate.cell_log; + } + if (R_tab) { + police->rate_present = true; + psched_ratecfg_precompute(&police->rate, R_tab->rate.rate); + qdisc_put_rtab(R_tab); + } else { + police->rate_present = false; } - if (P_tab != NULL) { - qdisc_put_rtab(police->tcfp_P_tab); - police->tcfp_P_tab = P_tab; + if (P_tab) { + police->peak_present = true; + psched_ratecfg_precompute(&police->peak, P_tab->rate.rate); + qdisc_put_rtab(P_tab); + } else { + police->peak_present = false; } if (tb[TCA_POLICE_RESULT]) police->tcfp_result = nla_get_u32(tb[TCA_POLICE_RESULT]); - police->tcfp_toks = police->tcfp_burst = parm->burst; - police->tcfp_mtu = parm->mtu; - if (police->tcfp_mtu == 0) { - police->tcfp_mtu = ~0; - if (police->tcfp_R_tab) - police->tcfp_mtu = 255<<police->tcfp_R_tab->rate.cell_log; + police->tcfp_burst = PSCHED_TICKS2NS(parm->burst); + police->tcfp_toks = police->tcfp_burst; + if (police->peak_present) { + police->tcfp_mtu_ptoks = (s64) psched_l2t_ns(&police->peak, + police->tcfp_mtu); + police->tcfp_ptoks = police->tcfp_mtu_ptoks; } - if (police->tcfp_P_tab) - police->tcfp_ptoks = L2T_P(police, police->tcfp_mtu); police->tcf_action = parm->action; if (tb[TCA_POLICE_AVRATE]) @@ -240,7 +262,7 @@ override: if (ret != ACT_P_CREATED) return ret; - police->tcfp_t_c = psched_get_time(); + police->tcfp_t_c = ktime_to_ns(ktime_get()); police->tcf_index = parm->index ? parm->index : tcf_hash_new_index(&police_idx_gen, &police_hash_info); h = tcf_hash(police->tcf_index, POL_TAB_MASK); @@ -286,9 +308,9 @@ static int tcf_act_police(struct sk_buff *skb, const struct tc_action *a, struct tcf_result *res) { struct tcf_police *police = a->priv; - psched_time_t now; - long toks; - long ptoks = 0; + s64 now; + s64 toks; + s64 ptoks = 0; spin_lock(&police->tcf_lock); @@ -304,24 +326,25 @@ static int tcf_act_police(struct sk_buff *skb, const struct tc_action *a, } if (qdisc_pkt_len(skb) <= police->tcfp_mtu) { - if (police->tcfp_R_tab == NULL) { + if (!police->rate_present) { spin_unlock(&police->tcf_lock); return police->tcfp_result; } - now = psched_get_time(); - toks = psched_tdiff_bounded(now, police->tcfp_t_c, - police->tcfp_burst); - if (police->tcfp_P_tab) { + now = ktime_to_ns(ktime_get()); + toks = min_t(s64, now - police->tcfp_t_c, + police->tcfp_burst); + if (police->peak_present) { ptoks = toks + police->tcfp_ptoks; - if (ptoks > (long)L2T_P(police, police->tcfp_mtu)) - ptoks = (long)L2T_P(police, police->tcfp_mtu); - ptoks -= L2T_P(police, qdisc_pkt_len(skb)); + if (ptoks > police->tcfp_mtu_ptoks) + ptoks = police->tcfp_mtu_ptoks; + ptoks -= (s64) psched_l2t_ns(&police->peak, + qdisc_pkt_len(skb)); } toks += police->tcfp_toks; - if (toks > (long)police->tcfp_burst) + if (toks > police->tcfp_burst) toks = police->tcfp_burst; - toks -= L2T(police, qdisc_pkt_len(skb)); + toks -= (s64) psched_l2t_ns(&police->rate, qdisc_pkt_len(skb)); if ((toks|ptoks) >= 0) { police->tcfp_t_c = now; police->tcfp_toks = toks; @@ -347,15 +370,15 @@ tcf_act_police_dump(struct sk_buff *skb, struct tc_action *a, int bind, int ref) .index = police->tcf_index, .action = police->tcf_action, .mtu = police->tcfp_mtu, - .burst = police->tcfp_burst, + .burst = PSCHED_NS2TICKS(police->tcfp_burst), .refcnt = police->tcf_refcnt - ref, .bindcnt = police->tcf_bindcnt - bind, }; - if (police->tcfp_R_tab) - opt.rate = police->tcfp_R_tab->rate; - if (police->tcfp_P_tab) - opt.peakrate = police->tcfp_P_tab->rate; + if (police->rate_present) + opt.rate.rate = psched_ratecfg_getrate(&police->rate); + if (police->peak_present) + opt.peakrate.rate = psched_ratecfg_getrate(&police->peak); if (nla_put(skb, TCA_POLICE_TBF, sizeof(opt), &opt)) goto nla_put_failure; if (police->tcfp_result && diff --git a/net/sched/act_simple.c b/net/sched/act_simple.c index 3714f60f0b3c..7725eb4ab756 100644 --- a/net/sched/act_simple.c +++ b/net/sched/act_simple.c @@ -95,8 +95,9 @@ static const struct nla_policy simple_policy[TCA_DEF_MAX + 1] = { [TCA_DEF_DATA] = { .type = NLA_STRING, .len = SIMP_MAX_DATA }, }; -static int tcf_simp_init(struct nlattr *nla, struct nlattr *est, - struct tc_action *a, int ovr, int bind) +static int tcf_simp_init(struct net *net, struct nlattr *nla, + struct nlattr *est, struct tc_action *a, + int ovr, int bind) { struct nlattr *tb[TCA_DEF_MAX + 1]; struct tc_defact *parm; diff --git a/net/sched/act_skbedit.c b/net/sched/act_skbedit.c index 476e0fac6712..cb4221171f93 100644 --- a/net/sched/act_skbedit.c +++ b/net/sched/act_skbedit.c @@ -67,8 +67,9 @@ static const struct nla_policy skbedit_policy[TCA_SKBEDIT_MAX + 1] = { [TCA_SKBEDIT_MARK] = { .len = sizeof(u32) }, }; -static int tcf_skbedit_init(struct nlattr *nla, struct nlattr *est, - struct tc_action *a, int ovr, int bind) +static int tcf_skbedit_init(struct net *net, struct nlattr *nla, + struct nlattr *est, struct tc_action *a, + int ovr, int bind) { struct nlattr *tb[TCA_SKBEDIT_MAX + 1]; struct tc_skbedit *parm; diff --git a/net/sched/cls_api.c b/net/sched/cls_api.c index ff55ed6c49b2..964f5e4f4b8a 100644 --- a/net/sched/cls_api.c +++ b/net/sched/cls_api.c @@ -321,7 +321,7 @@ replay: } } - err = tp->ops->change(skb, tp, cl, t->tcm_handle, tca, &fh); + err = tp->ops->change(net, skb, tp, cl, t->tcm_handle, tca, &fh); if (err == 0) { if (tp_created) { spin_lock_bh(root_lock); @@ -508,7 +508,7 @@ void tcf_exts_destroy(struct tcf_proto *tp, struct tcf_exts *exts) } EXPORT_SYMBOL(tcf_exts_destroy); -int tcf_exts_validate(struct tcf_proto *tp, struct nlattr **tb, +int tcf_exts_validate(struct net *net, struct tcf_proto *tp, struct nlattr **tb, struct nlattr *rate_tlv, struct tcf_exts *exts, const struct tcf_ext_map *map) { @@ -519,7 +519,7 @@ int tcf_exts_validate(struct tcf_proto *tp, struct nlattr **tb, struct tc_action *act; if (map->police && tb[map->police]) { - act = tcf_action_init_1(tb[map->police], rate_tlv, + act = tcf_action_init_1(net, tb[map->police], rate_tlv, "police", TCA_ACT_NOREPLACE, TCA_ACT_BIND); if (IS_ERR(act)) @@ -528,8 +528,9 @@ int tcf_exts_validate(struct tcf_proto *tp, struct nlattr **tb, act->type = TCA_OLD_COMPAT; exts->action = act; } else if (map->action && tb[map->action]) { - act = tcf_action_init(tb[map->action], rate_tlv, NULL, - TCA_ACT_NOREPLACE, TCA_ACT_BIND); + act = tcf_action_init(net, tb[map->action], rate_tlv, + NULL, TCA_ACT_NOREPLACE, + TCA_ACT_BIND); if (IS_ERR(act)) return PTR_ERR(act); diff --git a/net/sched/cls_basic.c b/net/sched/cls_basic.c index 344a11b342e5..d76a35d0dc85 100644 --- a/net/sched/cls_basic.c +++ b/net/sched/cls_basic.c @@ -132,15 +132,16 @@ static const struct nla_policy basic_policy[TCA_BASIC_MAX + 1] = { [TCA_BASIC_EMATCHES] = { .type = NLA_NESTED }, }; -static int basic_set_parms(struct tcf_proto *tp, struct basic_filter *f, - unsigned long base, struct nlattr **tb, +static int basic_set_parms(struct net *net, struct tcf_proto *tp, + struct basic_filter *f, unsigned long base, + struct nlattr **tb, struct nlattr *est) { int err = -EINVAL; struct tcf_exts e; struct tcf_ematch_tree t; - err = tcf_exts_validate(tp, tb, est, &e, &basic_ext_map); + err = tcf_exts_validate(net, tp, tb, est, &e, &basic_ext_map); if (err < 0) return err; @@ -162,7 +163,7 @@ errout: return err; } -static int basic_change(struct sk_buff *in_skb, +static int basic_change(struct net *net, struct sk_buff *in_skb, struct tcf_proto *tp, unsigned long base, u32 handle, struct nlattr **tca, unsigned long *arg) { @@ -182,7 +183,7 @@ static int basic_change(struct sk_buff *in_skb, if (f != NULL) { if (handle && f->handle != handle) return -EINVAL; - return basic_set_parms(tp, f, base, tb, tca[TCA_RATE]); + return basic_set_parms(net, tp, f, base, tb, tca[TCA_RATE]); } err = -ENOBUFS; @@ -208,7 +209,7 @@ static int basic_change(struct sk_buff *in_skb, f->handle = head->hgenerator; } - err = basic_set_parms(tp, f, base, tb, tca[TCA_RATE]); + err = basic_set_parms(net, tp, f, base, tb, tca[TCA_RATE]); if (err < 0) goto errout; diff --git a/net/sched/cls_cgroup.c b/net/sched/cls_cgroup.c index 6db7855b9029..3a294eb98d61 100644 --- a/net/sched/cls_cgroup.c +++ b/net/sched/cls_cgroup.c @@ -178,7 +178,7 @@ static const struct nla_policy cgroup_policy[TCA_CGROUP_MAX + 1] = { [TCA_CGROUP_EMATCHES] = { .type = NLA_NESTED }, }; -static int cls_cgroup_change(struct sk_buff *in_skb, +static int cls_cgroup_change(struct net *net, struct sk_buff *in_skb, struct tcf_proto *tp, unsigned long base, u32 handle, struct nlattr **tca, unsigned long *arg) @@ -215,7 +215,8 @@ static int cls_cgroup_change(struct sk_buff *in_skb, if (err < 0) return err; - err = tcf_exts_validate(tp, tb, tca[TCA_RATE], &e, &cgroup_ext_map); + err = tcf_exts_validate(net, tp, tb, tca[TCA_RATE], &e, + &cgroup_ext_map); if (err < 0) return err; diff --git a/net/sched/cls_flow.c b/net/sched/cls_flow.c index ce82d0cb1b47..aa36a8c8b33b 100644 --- a/net/sched/cls_flow.c +++ b/net/sched/cls_flow.c @@ -351,7 +351,7 @@ static const struct nla_policy flow_policy[TCA_FLOW_MAX + 1] = { [TCA_FLOW_PERTURB] = { .type = NLA_U32 }, }; -static int flow_change(struct sk_buff *in_skb, +static int flow_change(struct net *net, struct sk_buff *in_skb, struct tcf_proto *tp, unsigned long base, u32 handle, struct nlattr **tca, unsigned long *arg) @@ -397,7 +397,7 @@ static int flow_change(struct sk_buff *in_skb, return -EOPNOTSUPP; } - err = tcf_exts_validate(tp, tb, tca[TCA_RATE], &e, &flow_ext_map); + err = tcf_exts_validate(net, tp, tb, tca[TCA_RATE], &e, &flow_ext_map); if (err < 0) return err; diff --git a/net/sched/cls_fw.c b/net/sched/cls_fw.c index 4075a0aef2aa..1135d8227f9b 100644 --- a/net/sched/cls_fw.c +++ b/net/sched/cls_fw.c @@ -192,7 +192,7 @@ static const struct nla_policy fw_policy[TCA_FW_MAX + 1] = { }; static int -fw_change_attrs(struct tcf_proto *tp, struct fw_filter *f, +fw_change_attrs(struct net *net, struct tcf_proto *tp, struct fw_filter *f, struct nlattr **tb, struct nlattr **tca, unsigned long base) { struct fw_head *head = (struct fw_head *)tp->root; @@ -200,7 +200,7 @@ fw_change_attrs(struct tcf_proto *tp, struct fw_filter *f, u32 mask; int err; - err = tcf_exts_validate(tp, tb, tca[TCA_RATE], &e, &fw_ext_map); + err = tcf_exts_validate(net, tp, tb, tca[TCA_RATE], &e, &fw_ext_map); if (err < 0) return err; @@ -233,7 +233,7 @@ errout: return err; } -static int fw_change(struct sk_buff *in_skb, +static int fw_change(struct net *net, struct sk_buff *in_skb, struct tcf_proto *tp, unsigned long base, u32 handle, struct nlattr **tca, @@ -255,7 +255,7 @@ static int fw_change(struct sk_buff *in_skb, if (f != NULL) { if (f->id != handle && handle) return -EINVAL; - return fw_change_attrs(tp, f, tb, tca, base); + return fw_change_attrs(net, tp, f, tb, tca, base); } if (!handle) @@ -282,7 +282,7 @@ static int fw_change(struct sk_buff *in_skb, f->id = handle; - err = fw_change_attrs(tp, f, tb, tca, base); + err = fw_change_attrs(net, tp, f, tb, tca, base); if (err < 0) goto errout; diff --git a/net/sched/cls_route.c b/net/sched/cls_route.c index c10d57bf98f2..37da567d833e 100644 --- a/net/sched/cls_route.c +++ b/net/sched/cls_route.c @@ -335,9 +335,10 @@ static const struct nla_policy route4_policy[TCA_ROUTE4_MAX + 1] = { [TCA_ROUTE4_IIF] = { .type = NLA_U32 }, }; -static int route4_set_parms(struct tcf_proto *tp, unsigned long base, - struct route4_filter *f, u32 handle, struct route4_head *head, - struct nlattr **tb, struct nlattr *est, int new) +static int route4_set_parms(struct net *net, struct tcf_proto *tp, + unsigned long base, struct route4_filter *f, + u32 handle, struct route4_head *head, + struct nlattr **tb, struct nlattr *est, int new) { int err; u32 id = 0, to = 0, nhandle = 0x8000; @@ -346,7 +347,7 @@ static int route4_set_parms(struct tcf_proto *tp, unsigned long base, struct route4_bucket *b; struct tcf_exts e; - err = tcf_exts_validate(tp, tb, est, &e, &route_ext_map); + err = tcf_exts_validate(net, tp, tb, est, &e, &route_ext_map); if (err < 0) return err; @@ -427,7 +428,7 @@ errout: return err; } -static int route4_change(struct sk_buff *in_skb, +static int route4_change(struct net *net, struct sk_buff *in_skb, struct tcf_proto *tp, unsigned long base, u32 handle, struct nlattr **tca, @@ -457,7 +458,7 @@ static int route4_change(struct sk_buff *in_skb, if (f->bkt) old_handle = f->handle; - err = route4_set_parms(tp, base, f, handle, head, tb, + err = route4_set_parms(net, tp, base, f, handle, head, tb, tca[TCA_RATE], 0); if (err < 0) return err; @@ -480,7 +481,7 @@ static int route4_change(struct sk_buff *in_skb, if (f == NULL) goto errout; - err = route4_set_parms(tp, base, f, handle, head, tb, + err = route4_set_parms(net, tp, base, f, handle, head, tb, tca[TCA_RATE], 1); if (err < 0) goto errout; diff --git a/net/sched/cls_rsvp.h b/net/sched/cls_rsvp.h index 494bbb90924a..252d8b05872e 100644 --- a/net/sched/cls_rsvp.h +++ b/net/sched/cls_rsvp.h @@ -416,7 +416,7 @@ static const struct nla_policy rsvp_policy[TCA_RSVP_MAX + 1] = { [TCA_RSVP_PINFO] = { .len = sizeof(struct tc_rsvp_pinfo) }, }; -static int rsvp_change(struct sk_buff *in_skb, +static int rsvp_change(struct net *net, struct sk_buff *in_skb, struct tcf_proto *tp, unsigned long base, u32 handle, struct nlattr **tca, @@ -440,7 +440,7 @@ static int rsvp_change(struct sk_buff *in_skb, if (err < 0) return err; - err = tcf_exts_validate(tp, tb, tca[TCA_RATE], &e, &rsvp_ext_map); + err = tcf_exts_validate(net, tp, tb, tca[TCA_RATE], &e, &rsvp_ext_map); if (err < 0) return err; diff --git a/net/sched/cls_tcindex.c b/net/sched/cls_tcindex.c index a1293b4ab7a1..b86535a40169 100644 --- a/net/sched/cls_tcindex.c +++ b/net/sched/cls_tcindex.c @@ -197,9 +197,10 @@ static const struct nla_policy tcindex_policy[TCA_TCINDEX_MAX + 1] = { }; static int -tcindex_set_parms(struct tcf_proto *tp, unsigned long base, u32 handle, - struct tcindex_data *p, struct tcindex_filter_result *r, - struct nlattr **tb, struct nlattr *est) +tcindex_set_parms(struct net *net, struct tcf_proto *tp, unsigned long base, + u32 handle, struct tcindex_data *p, + struct tcindex_filter_result *r, struct nlattr **tb, + struct nlattr *est) { int err, balloc = 0; struct tcindex_filter_result new_filter_result, *old_r = r; @@ -208,7 +209,7 @@ tcindex_set_parms(struct tcf_proto *tp, unsigned long base, u32 handle, struct tcindex_filter *f = NULL; /* make gcc behave */ struct tcf_exts e; - err = tcf_exts_validate(tp, tb, est, &e, &tcindex_ext_map); + err = tcf_exts_validate(net, tp, tb, est, &e, &tcindex_ext_map); if (err < 0) return err; @@ -332,7 +333,7 @@ errout: } static int -tcindex_change(struct sk_buff *in_skb, +tcindex_change(struct net *net, struct sk_buff *in_skb, struct tcf_proto *tp, unsigned long base, u32 handle, struct nlattr **tca, unsigned long *arg) { @@ -353,7 +354,8 @@ tcindex_change(struct sk_buff *in_skb, if (err < 0) return err; - return tcindex_set_parms(tp, base, handle, p, r, tb, tca[TCA_RATE]); + return tcindex_set_parms(net, tp, base, handle, p, r, tb, + tca[TCA_RATE]); } diff --git a/net/sched/cls_u32.c b/net/sched/cls_u32.c index c7c27bc91b5a..eb07a1e536e6 100644 --- a/net/sched/cls_u32.c +++ b/net/sched/cls_u32.c @@ -488,15 +488,15 @@ static const struct nla_policy u32_policy[TCA_U32_MAX + 1] = { [TCA_U32_MARK] = { .len = sizeof(struct tc_u32_mark) }, }; -static int u32_set_parms(struct tcf_proto *tp, unsigned long base, - struct tc_u_hnode *ht, +static int u32_set_parms(struct net *net, struct tcf_proto *tp, + unsigned long base, struct tc_u_hnode *ht, struct tc_u_knode *n, struct nlattr **tb, struct nlattr *est) { int err; struct tcf_exts e; - err = tcf_exts_validate(tp, tb, est, &e, &u32_ext_map); + err = tcf_exts_validate(net, tp, tb, est, &e, &u32_ext_map); if (err < 0) return err; @@ -544,7 +544,7 @@ errout: return err; } -static int u32_change(struct sk_buff *in_skb, +static int u32_change(struct net *net, struct sk_buff *in_skb, struct tcf_proto *tp, unsigned long base, u32 handle, struct nlattr **tca, unsigned long *arg) @@ -570,7 +570,8 @@ static int u32_change(struct sk_buff *in_skb, if (TC_U32_KEY(n->handle) == 0) return -EINVAL; - return u32_set_parms(tp, base, n->ht_up, n, tb, tca[TCA_RATE]); + return u32_set_parms(net, tp, base, n->ht_up, n, tb, + tca[TCA_RATE]); } if (tb[TCA_U32_DIVISOR]) { @@ -656,7 +657,7 @@ static int u32_change(struct sk_buff *in_skb, } #endif - err = u32_set_parms(tp, base, ht, n, tb, tca[TCA_RATE]); + err = u32_set_parms(net, tp, base, ht, n, tb, tca[TCA_RATE]); if (err == 0) { struct tc_u_knode **ins; for (ins = &ht->ht[TC_U32_HASH(handle)]; *ins; ins = &(*ins)->next) diff --git a/net/sched/sch_api.c b/net/sched/sch_api.c index d84f7e734cd7..fe1ba54b93f7 100644 --- a/net/sched/sch_api.c +++ b/net/sched/sch_api.c @@ -493,7 +493,7 @@ void qdisc_watchdog_init(struct qdisc_watchdog *wd, struct Qdisc *qdisc) } EXPORT_SYMBOL(qdisc_watchdog_init); -void qdisc_watchdog_schedule(struct qdisc_watchdog *wd, psched_time_t expires) +void qdisc_watchdog_schedule_ns(struct qdisc_watchdog *wd, u64 expires) { if (test_bit(__QDISC_STATE_DEACTIVATED, &qdisc_root_sleeping(wd->qdisc)->state)) @@ -502,10 +502,10 @@ void qdisc_watchdog_schedule(struct qdisc_watchdog *wd, psched_time_t expires) qdisc_throttled(wd->qdisc); hrtimer_start(&wd->timer, - ns_to_ktime(PSCHED_TICKS2NS(expires)), + ns_to_ktime(expires), HRTIMER_MODE_ABS); } -EXPORT_SYMBOL(qdisc_watchdog_schedule); +EXPORT_SYMBOL(qdisc_watchdog_schedule_ns); void qdisc_watchdog_cancel(struct qdisc_watchdog *wd) { diff --git a/net/sched/sch_generic.c b/net/sched/sch_generic.c index 5d81a4478514..ffad48109a22 100644 --- a/net/sched/sch_generic.c +++ b/net/sched/sch_generic.c @@ -25,6 +25,7 @@ #include <linux/rcupdate.h> #include <linux/list.h> #include <linux/slab.h> +#include <net/sch_generic.h> #include <net/pkt_sched.h> #include <net/dst.h> @@ -896,3 +897,39 @@ void dev_shutdown(struct net_device *dev) WARN_ON(timer_pending(&dev->watchdog_timer)); } + +void psched_ratecfg_precompute(struct psched_ratecfg *r, u32 rate) +{ + u64 factor; + u64 mult; + int shift; + + r->rate_bps = rate << 3; + r->shift = 0; + r->mult = 1; + /* + * Calibrate mult, shift so that token counting is accurate + * for smallest packet size (64 bytes). Token (time in ns) is + * computed as (bytes * 8) * NSEC_PER_SEC / rate_bps. It will + * work as long as the smallest packet transfer time can be + * accurately represented in nanosec. + */ + if (r->rate_bps > 0) { + /* + * Higher shift gives better accuracy. Find the largest + * shift such that mult fits in 32 bits. + */ + for (shift = 0; shift < 16; shift++) { + r->shift = shift; + factor = 8LLU * NSEC_PER_SEC * (1 << r->shift); + mult = div64_u64(factor, r->rate_bps); + if (mult > UINT_MAX) + break; + } + + r->shift = shift - 1; + factor = 8LLU * NSEC_PER_SEC * (1 << r->shift); + r->mult = div64_u64(factor, r->rate_bps); + } +} +EXPORT_SYMBOL(psched_ratecfg_precompute); diff --git a/net/sched/sch_htb.c b/net/sched/sch_htb.c index d2922c0ef57a..03c2692ca01e 100644 --- a/net/sched/sch_htb.c +++ b/net/sched/sch_htb.c @@ -38,6 +38,7 @@ #include <linux/workqueue.h> #include <linux/slab.h> #include <net/netlink.h> +#include <net/sch_generic.h> #include <net/pkt_sched.h> /* HTB algorithm. @@ -71,12 +72,6 @@ enum htb_cmode { HTB_CAN_SEND /* class can send */ }; -struct htb_rate_cfg { - u64 rate_bps; - u32 mult; - u32 shift; -}; - /* interior & leaf nodes; props specific to leaves are marked L: */ struct htb_class { struct Qdisc_class_common common; @@ -124,8 +119,8 @@ struct htb_class { int filter_cnt; /* token bucket parameters */ - struct htb_rate_cfg rate; - struct htb_rate_cfg ceil; + struct psched_ratecfg rate; + struct psched_ratecfg ceil; s64 buffer, cbuffer; /* token bucket depth/rate */ psched_tdiff_t mbuffer; /* max wait time */ s64 tokens, ctokens; /* current number of tokens */ @@ -168,45 +163,6 @@ struct htb_sched { struct work_struct work; }; -static u64 l2t_ns(struct htb_rate_cfg *r, unsigned int len) -{ - return ((u64)len * r->mult) >> r->shift; -} - -static void htb_precompute_ratedata(struct htb_rate_cfg *r) -{ - u64 factor; - u64 mult; - int shift; - - r->shift = 0; - r->mult = 1; - /* - * Calibrate mult, shift so that token counting is accurate - * for smallest packet size (64 bytes). Token (time in ns) is - * computed as (bytes * 8) * NSEC_PER_SEC / rate_bps. It will - * work as long as the smallest packet transfer time can be - * accurately represented in nanosec. - */ - if (r->rate_bps > 0) { - /* - * Higher shift gives better accuracy. Find the largest - * shift such that mult fits in 32 bits. - */ - for (shift = 0; shift < 16; shift++) { - r->shift = shift; - factor = 8LLU * NSEC_PER_SEC * (1 << r->shift); - mult = div64_u64(factor, r->rate_bps); - if (mult > UINT_MAX) - break; - } - - r->shift = shift - 1; - factor = 8LLU * NSEC_PER_SEC * (1 << r->shift); - r->mult = div64_u64(factor, r->rate_bps); - } -} - /* find class in global hash table using given handle */ static inline struct htb_class *htb_find(u32 handle, struct Qdisc *sch) { @@ -632,7 +588,7 @@ static inline void htb_accnt_tokens(struct htb_class *cl, int bytes, s64 diff) if (toks > cl->buffer) toks = cl->buffer; - toks -= (s64) l2t_ns(&cl->rate, bytes); + toks -= (s64) psched_l2t_ns(&cl->rate, bytes); if (toks <= -cl->mbuffer) toks = 1 - cl->mbuffer; @@ -645,7 +601,7 @@ static inline void htb_accnt_ctokens(struct htb_class *cl, int bytes, s64 diff) if (toks > cl->cbuffer) toks = cl->cbuffer; - toks -= (s64) l2t_ns(&cl->ceil, bytes); + toks -= (s64) psched_l2t_ns(&cl->ceil, bytes); if (toks <= -cl->mbuffer) toks = 1 - cl->mbuffer; @@ -919,7 +875,7 @@ ok: q->now = ktime_to_ns(ktime_get()); start_at = jiffies; - next_event = q->now + 5 * NSEC_PER_SEC; + next_event = q->now + 5LLU * NSEC_PER_SEC; for (level = 0; level < TC_HTB_MAXDEPTH; level++) { /* common case optimization - skip event handler quickly */ @@ -1134,10 +1090,10 @@ static int htb_dump_class(struct Qdisc *sch, unsigned long arg, memset(&opt, 0, sizeof(opt)); - opt.rate.rate = cl->rate.rate_bps >> 3; - opt.buffer = cl->buffer; - opt.ceil.rate = cl->ceil.rate_bps >> 3; - opt.cbuffer = cl->cbuffer; + opt.rate.rate = psched_ratecfg_getrate(&cl->rate); + opt.buffer = PSCHED_NS2TICKS(cl->buffer); + opt.ceil.rate = psched_ratecfg_getrate(&cl->ceil); + opt.cbuffer = PSCHED_NS2TICKS(cl->cbuffer); opt.quantum = cl->quantum; opt.prio = cl->prio; opt.level = cl->level; @@ -1459,8 +1415,8 @@ static int htb_change_class(struct Qdisc *sch, u32 classid, cl->parent = parent; /* set class to be in HTB_CAN_SEND state */ - cl->tokens = hopt->buffer; - cl->ctokens = hopt->cbuffer; + cl->tokens = PSCHED_TICKS2NS(hopt->buffer); + cl->ctokens = PSCHED_TICKS2NS(hopt->cbuffer); cl->mbuffer = 60 * PSCHED_TICKS_PER_SEC; /* 1min */ cl->t_c = psched_get_time(); cl->cmode = HTB_CAN_SEND; @@ -1503,17 +1459,11 @@ static int htb_change_class(struct Qdisc *sch, u32 classid, cl->prio = TC_HTB_NUMPRIO - 1; } - cl->buffer = hopt->buffer; - cl->cbuffer = hopt->cbuffer; - - cl->rate.rate_bps = (u64)hopt->rate.rate << 3; - cl->ceil.rate_bps = (u64)hopt->ceil.rate << 3; - - htb_precompute_ratedata(&cl->rate); - htb_precompute_ratedata(&cl->ceil); + psched_ratecfg_precompute(&cl->rate, hopt->rate.rate); + psched_ratecfg_precompute(&cl->ceil, hopt->ceil.rate); - cl->buffer = hopt->buffer << PSCHED_SHIFT; - cl->cbuffer = hopt->buffer << PSCHED_SHIFT; + cl->buffer = PSCHED_TICKS2NS(hopt->buffer); + cl->cbuffer = PSCHED_TICKS2NS(hopt->buffer); sch_tree_unlock(sch); diff --git a/net/sched/sch_netem.c b/net/sched/sch_netem.c index 298c0ddfb57e..3d2acc7a9c80 100644 --- a/net/sched/sch_netem.c +++ b/net/sched/sch_netem.c @@ -438,18 +438,18 @@ static int netem_enqueue(struct sk_buff *skb, struct Qdisc *sch) if (q->rate) { struct sk_buff_head *list = &sch->q; - delay += packet_len_2_sched_time(skb->len, q); - if (!skb_queue_empty(list)) { /* - * Last packet in queue is reference point (now). - * First packet in queue is already in flight, - * calculate this time bonus and substract + * Last packet in queue is reference point (now), + * calculate this time bonus and subtract * from delay. */ - delay -= now - netem_skb_cb(skb_peek(list))->time_to_send; + delay -= netem_skb_cb(skb_peek_tail(list))->time_to_send - now; + delay = max_t(psched_tdiff_t, 0, delay); now = netem_skb_cb(skb_peek_tail(list))->time_to_send; } + + delay += packet_len_2_sched_time(skb->len, q); } cb->time_to_send = now + delay; diff --git a/net/sched/sch_tbf.c b/net/sched/sch_tbf.c index 4b056c15e90c..c8388f3c3426 100644 --- a/net/sched/sch_tbf.c +++ b/net/sched/sch_tbf.c @@ -19,6 +19,7 @@ #include <linux/errno.h> #include <linux/skbuff.h> #include <net/netlink.h> +#include <net/sch_generic.h> #include <net/pkt_sched.h> @@ -100,23 +101,21 @@ struct tbf_sched_data { /* Parameters */ u32 limit; /* Maximal length of backlog: bytes */ - u32 buffer; /* Token bucket depth/rate: MUST BE >= MTU/B */ - u32 mtu; + s64 buffer; /* Token bucket depth/rate: MUST BE >= MTU/B */ + s64 mtu; u32 max_size; - struct qdisc_rate_table *R_tab; - struct qdisc_rate_table *P_tab; + struct psched_ratecfg rate; + struct psched_ratecfg peak; + bool peak_present; /* Variables */ - long tokens; /* Current number of B tokens */ - long ptokens; /* Current number of P tokens */ - psched_time_t t_c; /* Time check-point */ + s64 tokens; /* Current number of B tokens */ + s64 ptokens; /* Current number of P tokens */ + s64 t_c; /* Time check-point */ struct Qdisc *qdisc; /* Inner qdisc, default - bfifo queue */ struct qdisc_watchdog watchdog; /* Watchdog timer */ }; -#define L2T(q, L) qdisc_l2t((q)->R_tab, L) -#define L2T_P(q, L) qdisc_l2t((q)->P_tab, L) - static int tbf_enqueue(struct sk_buff *skb, struct Qdisc *sch) { struct tbf_sched_data *q = qdisc_priv(sch); @@ -156,24 +155,24 @@ static struct sk_buff *tbf_dequeue(struct Qdisc *sch) skb = q->qdisc->ops->peek(q->qdisc); if (skb) { - psched_time_t now; - long toks; - long ptoks = 0; + s64 now; + s64 toks; + s64 ptoks = 0; unsigned int len = qdisc_pkt_len(skb); - now = psched_get_time(); - toks = psched_tdiff_bounded(now, q->t_c, q->buffer); + now = ktime_to_ns(ktime_get()); + toks = min_t(s64, now - q->t_c, q->buffer); - if (q->P_tab) { + if (q->peak_present) { ptoks = toks + q->ptokens; - if (ptoks > (long)q->mtu) + if (ptoks > q->mtu) ptoks = q->mtu; - ptoks -= L2T_P(q, len); + ptoks -= (s64) psched_l2t_ns(&q->peak, len); } toks += q->tokens; - if (toks > (long)q->buffer) + if (toks > q->buffer) toks = q->buffer; - toks -= L2T(q, len); + toks -= (s64) psched_l2t_ns(&q->rate, len); if ((toks|ptoks) >= 0) { skb = qdisc_dequeue_peeked(q->qdisc); @@ -189,8 +188,8 @@ static struct sk_buff *tbf_dequeue(struct Qdisc *sch) return skb; } - qdisc_watchdog_schedule(&q->watchdog, - now + max_t(long, -toks, -ptoks)); + qdisc_watchdog_schedule_ns(&q->watchdog, + now + max_t(long, -toks, -ptoks)); /* Maybe we have a shorter packet in the queue, which can be sent now. It sounds cool, @@ -214,7 +213,7 @@ static void tbf_reset(struct Qdisc *sch) qdisc_reset(q->qdisc); sch->q.qlen = 0; - q->t_c = psched_get_time(); + q->t_c = ktime_to_ns(ktime_get()); q->tokens = q->buffer; q->ptokens = q->mtu; qdisc_watchdog_cancel(&q->watchdog); @@ -293,14 +292,19 @@ static int tbf_change(struct Qdisc *sch, struct nlattr *opt) q->qdisc = child; } q->limit = qopt->limit; - q->mtu = qopt->mtu; + q->mtu = PSCHED_TICKS2NS(qopt->mtu); q->max_size = max_size; - q->buffer = qopt->buffer; + q->buffer = PSCHED_TICKS2NS(qopt->buffer); q->tokens = q->buffer; q->ptokens = q->mtu; - swap(q->R_tab, rtab); - swap(q->P_tab, ptab); + psched_ratecfg_precompute(&q->rate, rtab->rate.rate); + if (ptab) { + psched_ratecfg_precompute(&q->peak, ptab->rate.rate); + q->peak_present = true; + } else { + q->peak_present = false; + } sch_tree_unlock(sch); err = 0; @@ -319,7 +323,7 @@ static int tbf_init(struct Qdisc *sch, struct nlattr *opt) if (opt == NULL) return -EINVAL; - q->t_c = psched_get_time(); + q->t_c = ktime_to_ns(ktime_get()); qdisc_watchdog_init(&q->watchdog, sch); q->qdisc = &noop_qdisc; @@ -331,12 +335,6 @@ static void tbf_destroy(struct Qdisc *sch) struct tbf_sched_data *q = qdisc_priv(sch); qdisc_watchdog_cancel(&q->watchdog); - - if (q->P_tab) - qdisc_put_rtab(q->P_tab); - if (q->R_tab) - qdisc_put_rtab(q->R_tab); - qdisc_destroy(q->qdisc); } @@ -352,13 +350,13 @@ static int tbf_dump(struct Qdisc *sch, struct sk_buff *skb) goto nla_put_failure; opt.limit = q->limit; - opt.rate = q->R_tab->rate; - if (q->P_tab) - opt.peakrate = q->P_tab->rate; + opt.rate.rate = psched_ratecfg_getrate(&q->rate); + if (q->peak_present) + opt.peakrate.rate = psched_ratecfg_getrate(&q->peak); else memset(&opt.peakrate, 0, sizeof(opt.peakrate)); - opt.mtu = q->mtu; - opt.buffer = q->buffer; + opt.mtu = PSCHED_NS2TICKS(q->mtu); + opt.buffer = PSCHED_NS2TICKS(q->buffer); if (nla_put(skb, TCA_TBF_PARMS, sizeof(opt), &opt)) goto nla_put_failure; diff --git a/net/sctp/Kconfig b/net/sctp/Kconfig index c26210618e14..7521d944c0fb 100644 --- a/net/sctp/Kconfig +++ b/net/sctp/Kconfig @@ -68,7 +68,7 @@ config SCTP_DBG_OBJCNT If unsure, say N choice prompt "Default SCTP cookie HMAC encoding" - default SCTP_COOKIE_HMAC_MD5 + default SCTP_DEFAULT_COOKIE_HMAC_MD5 help This option sets the default sctp cookie hmac algorithm when in doubt select 'md5' diff --git a/net/sctp/associola.c b/net/sctp/associola.c index b45ed1f96921..2f95f5a5145d 100644 --- a/net/sctp/associola.c +++ b/net/sctp/associola.c @@ -434,8 +434,7 @@ void sctp_association_free(struct sctp_association *asoc) * on our state. */ for (i = SCTP_EVENT_TIMEOUT_NONE; i < SCTP_NUM_TIMEOUT_TYPES; ++i) { - if (timer_pending(&asoc->timers[i]) && - del_timer(&asoc->timers[i])) + if (del_timer(&asoc->timers[i])) sctp_association_put(asoc); } @@ -1497,7 +1496,7 @@ void sctp_assoc_rwnd_increase(struct sctp_association *asoc, unsigned int len) /* Stop the SACK timer. */ timer = &asoc->timers[SCTP_EVENT_TIMEOUT_SACK]; - if (timer_pending(timer) && del_timer(timer)) + if (del_timer(timer)) sctp_association_put(asoc); } } diff --git a/net/sctp/auth.c b/net/sctp/auth.c index 159b9bc5d633..ba1dfc3f8def 100644 --- a/net/sctp/auth.c +++ b/net/sctp/auth.c @@ -71,7 +71,7 @@ void sctp_auth_key_put(struct sctp_auth_bytes *key) return; if (atomic_dec_and_test(&key->refcnt)) { - kfree(key); + kzfree(key); SCTP_DBG_OBJCNT_DEC(keys); } } @@ -200,27 +200,28 @@ static struct sctp_auth_bytes *sctp_auth_make_key_vector( struct sctp_auth_bytes *new; __u32 len; __u32 offset = 0; + __u16 random_len, hmacs_len, chunks_len = 0; - len = ntohs(random->param_hdr.length) + ntohs(hmacs->param_hdr.length); - if (chunks) - len += ntohs(chunks->param_hdr.length); + random_len = ntohs(random->param_hdr.length); + hmacs_len = ntohs(hmacs->param_hdr.length); + if (chunks) + chunks_len = ntohs(chunks->param_hdr.length); - new = kmalloc(sizeof(struct sctp_auth_bytes) + len, gfp); + len = random_len + hmacs_len + chunks_len; + + new = sctp_auth_create_key(len, gfp); if (!new) return NULL; - new->len = len; - - memcpy(new->data, random, ntohs(random->param_hdr.length)); - offset += ntohs(random->param_hdr.length); + memcpy(new->data, random, random_len); + offset += random_len; if (chunks) { - memcpy(new->data + offset, chunks, - ntohs(chunks->param_hdr.length)); - offset += ntohs(chunks->param_hdr.length); + memcpy(new->data + offset, chunks, chunks_len); + offset += chunks_len; } - memcpy(new->data + offset, hmacs, ntohs(hmacs->param_hdr.length)); + memcpy(new->data + offset, hmacs, hmacs_len); return new; } @@ -350,8 +351,8 @@ static struct sctp_auth_bytes *sctp_auth_asoc_create_secret( secret = sctp_auth_asoc_set_secret(ep_key, first_vector, last_vector, gfp); out: - kfree(local_key_vector); - kfree(peer_key_vector); + sctp_auth_key_put(local_key_vector); + sctp_auth_key_put(peer_key_vector); return secret; } diff --git a/net/sctp/endpointola.c b/net/sctp/endpointola.c index 17a001bac2cc..73aad3d16a45 100644 --- a/net/sctp/endpointola.c +++ b/net/sctp/endpointola.c @@ -151,9 +151,7 @@ static struct sctp_endpoint *sctp_endpoint_init(struct sctp_endpoint *ep, ep->rcvbuf_policy = net->sctp.rcvbuf_policy; /* Initialize the secret key used with cookie. */ - get_random_bytes(&ep->secret_key[0], SCTP_SECRET_SIZE); - ep->last_key = ep->current_key = 0; - ep->key_changed_at = jiffies; + get_random_bytes(ep->secret_key, sizeof(ep->secret_key)); /* SCTP-AUTH extensions*/ INIT_LIST_HEAD(&ep->endpoint_shared_keys); @@ -271,6 +269,8 @@ static void sctp_endpoint_destroy(struct sctp_endpoint *ep) sctp_inq_free(&ep->base.inqueue); sctp_bind_addr_free(&ep->base.bind_addr); + memset(ep->secret_key, 0, sizeof(ep->secret_key)); + /* Remove and free the port */ if (sctp_sk(ep->base.sk)->bind_hash) sctp_put_port(ep->base.sk); diff --git a/net/sctp/input.c b/net/sctp/input.c index 8bd3c279427e..965bbbbe48d4 100644 --- a/net/sctp/input.c +++ b/net/sctp/input.c @@ -468,8 +468,7 @@ void sctp_icmp_proto_unreachable(struct sock *sk, } else { struct net *net = sock_net(sk); - if (timer_pending(&t->proto_unreach_timer) && - del_timer(&t->proto_unreach_timer)) + if (del_timer(&t->proto_unreach_timer)) sctp_association_put(asoc); sctp_do_sm(net, SCTP_EVENT_T_OTHER, diff --git a/net/sctp/outqueue.c b/net/sctp/outqueue.c index 379c81dee9d1..01dca753db16 100644 --- a/net/sctp/outqueue.c +++ b/net/sctp/outqueue.c @@ -224,7 +224,7 @@ void sctp_outq_init(struct sctp_association *asoc, struct sctp_outq *q) /* Free the outqueue structure and any related pending chunks. */ -void sctp_outq_teardown(struct sctp_outq *q) +static void __sctp_outq_teardown(struct sctp_outq *q) { struct sctp_transport *transport; struct list_head *lchunk, *temp; @@ -277,8 +277,6 @@ void sctp_outq_teardown(struct sctp_outq *q) sctp_chunk_free(chunk); } - q->error = 0; - /* Throw away any leftover control chunks. */ list_for_each_entry_safe(chunk, tmp, &q->control_chunk_list, list) { list_del_init(&chunk->list); @@ -286,11 +284,17 @@ void sctp_outq_teardown(struct sctp_outq *q) } } +void sctp_outq_teardown(struct sctp_outq *q) +{ + __sctp_outq_teardown(q); + sctp_outq_init(q->asoc, q); +} + /* Free the outqueue structure and any related pending chunks. */ void sctp_outq_free(struct sctp_outq *q) { /* Throw away leftover chunks. */ - sctp_outq_teardown(q); + __sctp_outq_teardown(q); /* If we were kmalloc()'d, free the memory. */ if (q->malloced) @@ -1696,10 +1700,8 @@ static void sctp_check_transmitted(struct sctp_outq *q, * address. */ if (!transport->flight_size) { - if (timer_pending(&transport->T3_rtx_timer) && - del_timer(&transport->T3_rtx_timer)) { + if (del_timer(&transport->T3_rtx_timer)) sctp_transport_put(transport); - } } else if (restart_timer) { if (!mod_timer(&transport->T3_rtx_timer, jiffies + transport->rto)) diff --git a/net/sctp/probe.c b/net/sctp/probe.c index 5f7518de2fd1..261b7b9858a4 100644 --- a/net/sctp/probe.c +++ b/net/sctp/probe.c @@ -122,12 +122,12 @@ static const struct file_operations sctpprobe_fops = { .llseek = noop_llseek, }; -sctp_disposition_t jsctp_sf_eat_sack(struct net *net, - const struct sctp_endpoint *ep, - const struct sctp_association *asoc, - const sctp_subtype_t type, - void *arg, - sctp_cmd_seq_t *commands) +static sctp_disposition_t jsctp_sf_eat_sack(struct net *net, + const struct sctp_endpoint *ep, + const struct sctp_association *asoc, + const sctp_subtype_t type, + void *arg, + sctp_cmd_seq_t *commands) { struct sctp_transport *sp; static __u32 lcwnd = 0; @@ -183,6 +183,13 @@ static __init int sctpprobe_init(void) { int ret = -ENOMEM; + /* Warning: if the function signature of sctp_sf_eat_sack_6_2, + * has been changed, you also have to change the signature of + * jsctp_sf_eat_sack, otherwise you end up right here! + */ + BUILD_BUG_ON(__same_type(sctp_sf_eat_sack_6_2, + jsctp_sf_eat_sack) == 0); + init_waitqueue_head(&sctpw.wait); spin_lock_init(&sctpw.lock); if (kfifo_alloc(&sctpw.fifo, bufsize, GFP_KERNEL)) diff --git a/net/sctp/protocol.c b/net/sctp/protocol.c index f898b1c58bd2..1c2e46cb9191 100644 --- a/net/sctp/protocol.c +++ b/net/sctp/protocol.c @@ -595,7 +595,7 @@ static void sctp_v4_ecn_capable(struct sock *sk) INET_ECN_xmit(sk); } -void sctp_addr_wq_timeout_handler(unsigned long arg) +static void sctp_addr_wq_timeout_handler(unsigned long arg) { struct net *net = (struct net *)arg; struct sctp_sockaddr_entry *addrw, *temp; diff --git a/net/sctp/sm_make_chunk.c b/net/sctp/sm_make_chunk.c index e1c5fc2be6b8..a193f3bc8144 100644 --- a/net/sctp/sm_make_chunk.c +++ b/net/sctp/sm_make_chunk.c @@ -1589,8 +1589,6 @@ static sctp_cookie_param_t *sctp_pack_cookie(const struct sctp_endpoint *ep, struct sctp_signed_cookie *cookie; struct scatterlist sg; int headersize, bodysize; - unsigned int keylen; - char *key; /* Header size is static data prior to the actual cookie, including * any padding. @@ -1650,12 +1648,11 @@ static sctp_cookie_param_t *sctp_pack_cookie(const struct sctp_endpoint *ep, /* Sign the message. */ sg_init_one(&sg, &cookie->c, bodysize); - keylen = SCTP_SECRET_SIZE; - key = (char *)ep->secret_key[ep->current_key]; desc.tfm = sctp_sk(ep->base.sk)->hmac; desc.flags = 0; - if (crypto_hash_setkey(desc.tfm, key, keylen) || + if (crypto_hash_setkey(desc.tfm, ep->secret_key, + sizeof(ep->secret_key)) || crypto_hash_digest(&desc, &sg, bodysize, cookie->signature)) goto free_cookie; } @@ -1682,8 +1679,7 @@ struct sctp_association *sctp_unpack_cookie( int headersize, bodysize, fixed_size; __u8 *digest = ep->digest; struct scatterlist sg; - unsigned int keylen, len; - char *key; + unsigned int len; sctp_scope_t scope; struct sk_buff *skb = chunk->skb; struct timeval tv; @@ -1718,34 +1714,21 @@ struct sctp_association *sctp_unpack_cookie( goto no_hmac; /* Check the signature. */ - keylen = SCTP_SECRET_SIZE; sg_init_one(&sg, bear_cookie, bodysize); - key = (char *)ep->secret_key[ep->current_key]; desc.tfm = sctp_sk(ep->base.sk)->hmac; desc.flags = 0; memset(digest, 0x00, SCTP_SIGNATURE_SIZE); - if (crypto_hash_setkey(desc.tfm, key, keylen) || + if (crypto_hash_setkey(desc.tfm, ep->secret_key, + sizeof(ep->secret_key)) || crypto_hash_digest(&desc, &sg, bodysize, digest)) { *error = -SCTP_IERROR_NOMEM; goto fail; } if (memcmp(digest, cookie->signature, SCTP_SIGNATURE_SIZE)) { - /* Try the previous key. */ - key = (char *)ep->secret_key[ep->last_key]; - memset(digest, 0x00, SCTP_SIGNATURE_SIZE); - if (crypto_hash_setkey(desc.tfm, key, keylen) || - crypto_hash_digest(&desc, &sg, bodysize, digest)) { - *error = -SCTP_IERROR_NOMEM; - goto fail; - } - - if (memcmp(digest, cookie->signature, SCTP_SIGNATURE_SIZE)) { - /* Yikes! Still bad signature! */ - *error = -SCTP_IERROR_BAD_SIG; - goto fail; - } + *error = -SCTP_IERROR_BAD_SIG; + goto fail; } no_hmac: diff --git a/net/sctp/sm_sideeffect.c b/net/sctp/sm_sideeffect.c index c9577754a708..8aab894aeabe 100644 --- a/net/sctp/sm_sideeffect.c +++ b/net/sctp/sm_sideeffect.c @@ -674,10 +674,8 @@ static void sctp_cmd_t3_rtx_timers_stop(sctp_cmd_seq_t *cmds, list_for_each_entry(t, &asoc->peer.transport_addr_list, transports) { - if (timer_pending(&t->T3_rtx_timer) && - del_timer(&t->T3_rtx_timer)) { + if (del_timer(&t->T3_rtx_timer)) sctp_transport_put(t); - } } } @@ -1517,7 +1515,7 @@ static int sctp_cmd_interpreter(sctp_event_t event_type, case SCTP_CMD_TIMER_STOP: timer = &asoc->timers[cmd->obj.to]; - if (timer_pending(timer) && del_timer(timer)) + if (del_timer(timer)) sctp_association_put(asoc); break; diff --git a/net/sctp/sm_statefuns.c b/net/sctp/sm_statefuns.c index 618ec7e216ca..5131fcfedb03 100644 --- a/net/sctp/sm_statefuns.c +++ b/net/sctp/sm_statefuns.c @@ -1779,8 +1779,10 @@ static sctp_disposition_t sctp_sf_do_dupcook_a(struct net *net, /* Update the content of current association. */ sctp_add_cmd_sf(commands, SCTP_CMD_UPDATE_ASSOC, SCTP_ASOC(new_asoc)); - sctp_add_cmd_sf(commands, SCTP_CMD_REPLY, SCTP_CHUNK(repl)); sctp_add_cmd_sf(commands, SCTP_CMD_EVENT_ULP, SCTP_ULPEVENT(ev)); + sctp_add_cmd_sf(commands, SCTP_CMD_NEW_STATE, + SCTP_STATE(SCTP_STATE_ESTABLISHED)); + sctp_add_cmd_sf(commands, SCTP_CMD_REPLY, SCTP_CHUNK(repl)); return SCTP_DISPOSITION_CONSUME; nomem_ev: diff --git a/net/sctp/socket.c b/net/sctp/socket.c index 9e65758cb038..cedd9bf67b8c 100644 --- a/net/sctp/socket.c +++ b/net/sctp/socket.c @@ -3390,7 +3390,7 @@ static int sctp_setsockopt_auth_key(struct sock *sk, ret = sctp_auth_set_key(sctp_sk(sk)->ep, asoc, authkey); out: - kfree(authkey); + kzfree(authkey); return ret; } diff --git a/net/sctp/sysctl.c b/net/sctp/sysctl.c index 043889ac86c0..bf3c6e8fc401 100644 --- a/net/sctp/sysctl.c +++ b/net/sctp/sysctl.c @@ -366,7 +366,11 @@ int sctp_sysctl_net_register(struct net *net) void sctp_sysctl_net_unregister(struct net *net) { + struct ctl_table *table; + + table = net->sctp.sysctl_header->ctl_table_arg; unregister_net_sysctl_table(net->sctp.sysctl_header); + kfree(table); } static struct ctl_table_header * sctp_sysctl_header; diff --git a/net/sctp/transport.c b/net/sctp/transport.c index 4e45bb68aef0..fafd2a461ba0 100644 --- a/net/sctp/transport.c +++ b/net/sctp/transport.c @@ -151,13 +151,11 @@ void sctp_transport_free(struct sctp_transport *transport) * structure hang around in memory since we know * the tranport is going away. */ - if (timer_pending(&transport->T3_rtx_timer) && - del_timer(&transport->T3_rtx_timer)) + if (del_timer(&transport->T3_rtx_timer)) sctp_transport_put(transport); /* Delete the ICMP proto unreachable timer if it's active. */ - if (timer_pending(&transport->proto_unreach_timer) && - del_timer(&transport->proto_unreach_timer)) + if (del_timer(&transport->proto_unreach_timer)) sctp_association_put(transport->asoc); sctp_transport_put(transport); @@ -168,10 +166,6 @@ static void sctp_transport_destroy_rcu(struct rcu_head *head) struct sctp_transport *transport; transport = container_of(head, struct sctp_transport, rcu); - if (transport->asoc) - sctp_association_put(transport->asoc); - - sctp_packet_free(&transport->packet); dst_release(transport->dst); kfree(transport); @@ -186,6 +180,11 @@ static void sctp_transport_destroy(struct sctp_transport *transport) SCTP_ASSERT(transport->dead, "Transport is not dead", return); call_rcu(&transport->rcu, sctp_transport_destroy_rcu); + + sctp_packet_free(&transport->packet); + + if (transport->asoc) + sctp_association_put(transport->asoc); } /* Start T3_rtx timer if it is not already running and update the heartbeat @@ -654,10 +653,9 @@ void sctp_transport_reset(struct sctp_transport *t) void sctp_transport_immediate_rtx(struct sctp_transport *t) { /* Stop pending T3_rtx_timer */ - if (timer_pending(&t->T3_rtx_timer)) { - (void)del_timer(&t->T3_rtx_timer); + if (del_timer(&t->T3_rtx_timer)) sctp_transport_put(t); - } + sctp_retransmit(&t->asoc->outqueue, t, SCTP_RTXR_T3_RTX); if (!timer_pending(&t->T3_rtx_timer)) { if (!mod_timer(&t->T3_rtx_timer, jiffies + t->rto)) diff --git a/net/socket.c b/net/socket.c index 2ca51c719ef9..ee0d029e5130 100644 --- a/net/socket.c +++ b/net/socket.c @@ -69,7 +69,6 @@ #include <linux/proc_fs.h> #include <linux/seq_file.h> #include <linux/mutex.h> -#include <linux/wanrouter.h> #include <linux/if_bridge.h> #include <linux/if_frad.h> #include <linux/if_vlan.h> @@ -2838,7 +2837,7 @@ static int ethtool_ioctl(struct net *net, struct compat_ifreq __user *ifr32) } ifr = compat_alloc_user_space(buf_size); - rxnfc = (void *)ifr + ALIGN(sizeof(struct ifreq), 8); + rxnfc = (void __user *)ifr + ALIGN(sizeof(struct ifreq), 8); if (copy_in_user(&ifr->ifr_name, &ifr32->ifr_name, IFNAMSIZ)) return -EFAULT; @@ -2862,12 +2861,12 @@ static int ethtool_ioctl(struct net *net, struct compat_ifreq __user *ifr32) offsetof(struct ethtool_rxnfc, fs.ring_cookie)); if (copy_in_user(rxnfc, compat_rxnfc, - (void *)(&rxnfc->fs.m_ext + 1) - - (void *)rxnfc) || + (void __user *)(&rxnfc->fs.m_ext + 1) - + (void __user *)rxnfc) || copy_in_user(&rxnfc->fs.ring_cookie, &compat_rxnfc->fs.ring_cookie, - (void *)(&rxnfc->fs.location + 1) - - (void *)&rxnfc->fs.ring_cookie) || + (void __user *)(&rxnfc->fs.location + 1) - + (void __user *)&rxnfc->fs.ring_cookie) || copy_in_user(&rxnfc->rule_cnt, &compat_rxnfc->rule_cnt, sizeof(rxnfc->rule_cnt))) return -EFAULT; @@ -2879,12 +2878,12 @@ static int ethtool_ioctl(struct net *net, struct compat_ifreq __user *ifr32) if (convert_out) { if (copy_in_user(compat_rxnfc, rxnfc, - (const void *)(&rxnfc->fs.m_ext + 1) - - (const void *)rxnfc) || + (const void __user *)(&rxnfc->fs.m_ext + 1) - + (const void __user *)rxnfc) || copy_in_user(&compat_rxnfc->fs.ring_cookie, &rxnfc->fs.ring_cookie, - (const void *)(&rxnfc->fs.location + 1) - - (const void *)&rxnfc->fs.ring_cookie) || + (const void __user *)(&rxnfc->fs.location + 1) - + (const void __user *)&rxnfc->fs.ring_cookie) || copy_in_user(&compat_rxnfc->rule_cnt, &rxnfc->rule_cnt, sizeof(rxnfc->rule_cnt))) return -EFAULT; diff --git a/net/sunrpc/clnt.c b/net/sunrpc/clnt.c index 822f020fa7f4..507b5e84fbdb 100644 --- a/net/sunrpc/clnt.c +++ b/net/sunrpc/clnt.c @@ -555,7 +555,7 @@ EXPORT_SYMBOL_GPL(rpc_clone_client); * rpc_clone_client_set_auth - Clone an RPC client structure and set its auth * * @clnt: RPC client whose parameters are copied - * @auth: security flavor for new client + * @flavor: security flavor for new client * * Returns a fresh RPC client or an ERR_PTR. */ @@ -610,11 +610,6 @@ EXPORT_SYMBOL_GPL(rpc_killall_tasks); */ void rpc_shutdown_client(struct rpc_clnt *clnt) { - /* - * To avoid deadlock, never call rpc_shutdown_client from a - * workqueue context! - */ - WARN_ON_ONCE(current->flags & PF_WQ_WORKER); might_sleep(); dprintk_rcu("RPC: shutting down %s client for %s\n", diff --git a/net/sunrpc/sched.c b/net/sunrpc/sched.c index d17a704aaf5f..fb20f25ddec9 100644 --- a/net/sunrpc/sched.c +++ b/net/sunrpc/sched.c @@ -98,9 +98,25 @@ __rpc_add_timer(struct rpc_wait_queue *queue, struct rpc_task *task) list_add(&task->u.tk_wait.timer_list, &queue->timer_list.list); } +static void rpc_rotate_queue_owner(struct rpc_wait_queue *queue) +{ + struct list_head *q = &queue->tasks[queue->priority]; + struct rpc_task *task; + + if (!list_empty(q)) { + task = list_first_entry(q, struct rpc_task, u.tk_wait.list); + if (task->tk_owner == queue->owner) + list_move_tail(&task->u.tk_wait.list, q); + } +} + static void rpc_set_waitqueue_priority(struct rpc_wait_queue *queue, int priority) { - queue->priority = priority; + if (queue->priority != priority) { + /* Fairness: rotate the list when changing priority */ + rpc_rotate_queue_owner(queue); + queue->priority = priority; + } } static void rpc_set_waitqueue_owner(struct rpc_wait_queue *queue, pid_t pid) @@ -934,16 +950,35 @@ struct rpc_task *rpc_new_task(const struct rpc_task_setup *setup_data) return task; } +/* + * rpc_free_task - release rpc task and perform cleanups + * + * Note that we free up the rpc_task _after_ rpc_release_calldata() + * in order to work around a workqueue dependency issue. + * + * Tejun Heo states: + * "Workqueue currently considers two work items to be the same if they're + * on the same address and won't execute them concurrently - ie. it + * makes a work item which is queued again while being executed wait + * for the previous execution to complete. + * + * If a work function frees the work item, and then waits for an event + * which should be performed by another work item and *that* work item + * recycles the freed work item, it can create a false dependency loop. + * There really is no reliable way to detect this short of verifying + * every memory free." + * + */ static void rpc_free_task(struct rpc_task *task) { - const struct rpc_call_ops *tk_ops = task->tk_ops; - void *calldata = task->tk_calldata; + unsigned short tk_flags = task->tk_flags; + + rpc_release_calldata(task->tk_ops, task->tk_calldata); - if (task->tk_flags & RPC_TASK_DYNAMIC) { + if (tk_flags & RPC_TASK_DYNAMIC) { dprintk("RPC: %5u freeing task\n", task->tk_pid); mempool_free(task, rpc_task_mempool); } - rpc_release_calldata(tk_ops, calldata); } static void rpc_async_release(struct work_struct *work) @@ -953,8 +988,7 @@ static void rpc_async_release(struct work_struct *work) static void rpc_release_resources_task(struct rpc_task *task) { - if (task->tk_rqstp) - xprt_release(task); + xprt_release(task); if (task->tk_msg.rpc_cred) { put_rpccred(task->tk_msg.rpc_cred); task->tk_msg.rpc_cred = NULL; diff --git a/net/sunrpc/svcsock.c b/net/sunrpc/svcsock.c index 0a148c9d2a5c..0f679df7d072 100644 --- a/net/sunrpc/svcsock.c +++ b/net/sunrpc/svcsock.c @@ -465,7 +465,7 @@ static int svc_udp_get_dest_address4(struct svc_rqst *rqstp, } /* - * See net/ipv6/datagram.c : datagram_recv_ctl + * See net/ipv6/datagram.c : ip6_datagram_recv_ctl */ static int svc_udp_get_dest_address6(struct svc_rqst *rqstp, struct cmsghdr *cmh) diff --git a/net/sunrpc/xprt.c b/net/sunrpc/xprt.c index bd462a532acf..33811db8788a 100644 --- a/net/sunrpc/xprt.c +++ b/net/sunrpc/xprt.c @@ -1136,10 +1136,18 @@ static void xprt_request_init(struct rpc_task *task, struct rpc_xprt *xprt) void xprt_release(struct rpc_task *task) { struct rpc_xprt *xprt; - struct rpc_rqst *req; + struct rpc_rqst *req = task->tk_rqstp; - if (!(req = task->tk_rqstp)) + if (req == NULL) { + if (task->tk_client) { + rcu_read_lock(); + xprt = rcu_dereference(task->tk_client->cl_xprt); + if (xprt->snd_task == task) + xprt_release_write(xprt, task); + rcu_read_unlock(); + } return; + } xprt = req->rq_xprt; if (task->tk_ops->rpc_count_stats != NULL) diff --git a/net/tipc/socket.c b/net/tipc/socket.c index 9b4e4833a484..a9622b6cd916 100644 --- a/net/tipc/socket.c +++ b/net/tipc/socket.c @@ -43,7 +43,8 @@ #define SS_LISTENING -1 /* socket is listening */ #define SS_READY -2 /* socket is connectionless */ -#define OVERLOAD_LIMIT_BASE 10000 +#define CONN_OVERLOAD_LIMIT ((TIPC_FLOW_CONTROL_WIN * 2 + 1) * \ + SKB_TRUESIZE(TIPC_MAX_USER_MSG_SIZE)) #define CONN_TIMEOUT_DEFAULT 8000 /* default connect timeout = 8s */ struct tipc_sock { @@ -129,19 +130,6 @@ static void advance_rx_queue(struct sock *sk) } /** - * discard_rx_queue - discard all buffers in socket receive queue - * - * Caller must hold socket lock - */ -static void discard_rx_queue(struct sock *sk) -{ - struct sk_buff *buf; - - while ((buf = __skb_dequeue(&sk->sk_receive_queue))) - kfree_skb(buf); -} - -/** * reject_rx_queue - reject all buffers in socket receive queue * * Caller must hold socket lock @@ -215,7 +203,6 @@ static int tipc_create(struct net *net, struct socket *sock, int protocol, sock_init_data(sock, sk); sk->sk_backlog_rcv = backlog_rcv; - sk->sk_rcvbuf = TIPC_FLOW_CONTROL_WIN * 2 * TIPC_MAX_USER_MSG_SIZE * 2; sk->sk_data_ready = tipc_data_ready; sk->sk_write_space = tipc_write_space; tipc_sk(sk)->p = tp_ptr; @@ -292,7 +279,7 @@ static int release(struct socket *sock) res = tipc_deleteport(tport->ref); /* Discard any remaining (connection-based) messages in receive queue */ - discard_rx_queue(sk); + __skb_queue_purge(&sk->sk_receive_queue); /* Reject any messages that accumulated in backlog queue */ sock->state = SS_DISCONNECTING; @@ -516,8 +503,7 @@ static int send_msg(struct kiocb *iocb, struct socket *sock, if (unlikely((m->msg_namelen < sizeof(*dest)) || (dest->family != AF_TIPC))) return -EINVAL; - if ((total_len > TIPC_MAX_USER_MSG_SIZE) || - (m->msg_iovlen > (unsigned int)INT_MAX)) + if (total_len > TIPC_MAX_USER_MSG_SIZE) return -EMSGSIZE; if (iocb) @@ -625,8 +611,7 @@ static int send_packet(struct kiocb *iocb, struct socket *sock, if (unlikely(dest)) return send_msg(iocb, sock, m, total_len); - if ((total_len > TIPC_MAX_USER_MSG_SIZE) || - (m->msg_iovlen > (unsigned int)INT_MAX)) + if (total_len > TIPC_MAX_USER_MSG_SIZE) return -EMSGSIZE; if (iocb) @@ -711,8 +696,7 @@ static int send_stream(struct kiocb *iocb, struct socket *sock, goto exit; } - if ((total_len > (unsigned int)INT_MAX) || - (m->msg_iovlen > (unsigned int)INT_MAX)) { + if (total_len > (unsigned int)INT_MAX) { res = -EMSGSIZE; goto exit; } @@ -1155,34 +1139,6 @@ static void tipc_data_ready(struct sock *sk, int len) } /** - * rx_queue_full - determine if receive queue can accept another message - * @msg: message to be added to queue - * @queue_size: current size of queue - * @base: nominal maximum size of queue - * - * Returns 1 if queue is unable to accept message, 0 otherwise - */ -static int rx_queue_full(struct tipc_msg *msg, u32 queue_size, u32 base) -{ - u32 threshold; - u32 imp = msg_importance(msg); - - if (imp == TIPC_LOW_IMPORTANCE) - threshold = base; - else if (imp == TIPC_MEDIUM_IMPORTANCE) - threshold = base * 2; - else if (imp == TIPC_HIGH_IMPORTANCE) - threshold = base * 100; - else - return 0; - - if (msg_connected(msg)) - threshold *= 4; - - return queue_size >= threshold; -} - -/** * filter_connect - Handle all incoming messages for a connection-based socket * @tsock: TIPC socket * @msg: message @@ -1260,6 +1216,36 @@ static u32 filter_connect(struct tipc_sock *tsock, struct sk_buff **buf) } /** + * rcvbuf_limit - get proper overload limit of socket receive queue + * @sk: socket + * @buf: message + * + * For all connection oriented messages, irrespective of importance, + * the default overload value (i.e. 67MB) is set as limit. + * + * For all connectionless messages, by default new queue limits are + * as belows: + * + * TIPC_LOW_IMPORTANCE (5MB) + * TIPC_MEDIUM_IMPORTANCE (10MB) + * TIPC_HIGH_IMPORTANCE (20MB) + * TIPC_CRITICAL_IMPORTANCE (40MB) + * + * Returns overload limit according to corresponding message importance + */ +static unsigned int rcvbuf_limit(struct sock *sk, struct sk_buff *buf) +{ + struct tipc_msg *msg = buf_msg(buf); + unsigned int limit; + + if (msg_connected(msg)) + limit = CONN_OVERLOAD_LIMIT; + else + limit = sk->sk_rcvbuf << (msg_importance(msg) + 5); + return limit; +} + +/** * filter_rcv - validate incoming message * @sk: socket * @buf: message @@ -1275,7 +1261,7 @@ static u32 filter_rcv(struct sock *sk, struct sk_buff *buf) { struct socket *sock = sk->sk_socket; struct tipc_msg *msg = buf_msg(buf); - u32 recv_q_len; + unsigned int limit = rcvbuf_limit(sk, buf); u32 res = TIPC_OK; /* Reject message if it is wrong sort of message for socket */ @@ -1292,15 +1278,13 @@ static u32 filter_rcv(struct sock *sk, struct sk_buff *buf) } /* Reject message if there isn't room to queue it */ - recv_q_len = skb_queue_len(&sk->sk_receive_queue); - if (unlikely(recv_q_len >= (OVERLOAD_LIMIT_BASE / 2))) { - if (rx_queue_full(msg, recv_q_len, OVERLOAD_LIMIT_BASE / 2)) - return TIPC_ERR_OVERLOAD; - } + if (sk_rmem_alloc_get(sk) + buf->truesize >= limit) + return TIPC_ERR_OVERLOAD; - /* Enqueue message (finally!) */ + /* Enqueue message */ TIPC_SKB_CB(buf)->handle = 0; __skb_queue_tail(&sk->sk_receive_queue, buf); + skb_set_owner_r(buf, sk); sk->sk_data_ready(sk, 0); return TIPC_OK; @@ -1349,7 +1333,7 @@ static u32 dispatch(struct tipc_port *tport, struct sk_buff *buf) if (!sock_owned_by_user(sk)) { res = filter_rcv(sk, buf); } else { - if (sk_add_backlog(sk, buf, sk->sk_rcvbuf)) + if (sk_add_backlog(sk, buf, rcvbuf_limit(sk, buf))) res = TIPC_ERR_OVERLOAD; else res = TIPC_OK; @@ -1583,6 +1567,7 @@ static int accept(struct socket *sock, struct socket *new_sock, int flags) } else { __skb_dequeue(&sk->sk_receive_queue); __skb_queue_head(&new_sk->sk_receive_queue, buf); + skb_set_owner_r(buf, new_sk); } release_sock(new_sk); @@ -1637,7 +1622,7 @@ restart: case SS_DISCONNECTING: /* Discard any unreceived messages */ - discard_rx_queue(sk); + __skb_queue_purge(&sk->sk_receive_queue); /* Wake up anyone sleeping in poll */ sk->sk_state_change(sk); diff --git a/net/unix/af_unix.c b/net/unix/af_unix.c index 5b5c876c80e9..0c612361c153 100644 --- a/net/unix/af_unix.c +++ b/net/unix/af_unix.c @@ -2426,9 +2426,8 @@ static struct pernet_operations unix_net_ops = { static int __init af_unix_init(void) { int rc = -1; - struct sk_buff *dummy_skb; - BUILD_BUG_ON(sizeof(struct unix_skb_parms) > sizeof(dummy_skb->cb)); + BUILD_BUG_ON(sizeof(struct unix_skb_parms) > FIELD_SIZEOF(struct sk_buff, cb)); rc = proto_register(&unix_proto, 1); if (rc != 0) { diff --git a/net/vmw_vsock/Kconfig b/net/vmw_vsock/Kconfig new file mode 100644 index 000000000000..b5fa7e40cdcb --- /dev/null +++ b/net/vmw_vsock/Kconfig @@ -0,0 +1,28 @@ +# +# Vsock protocol +# + +config VSOCKETS + tristate "Virtual Socket protocol" + help + Virtual Socket Protocol is a socket protocol similar to TCP/IP + allowing comunication between Virtual Machines and hypervisor + or host. + + You should also select one or more hypervisor-specific transports + below. + + To compile this driver as a module, choose M here: the module + will be called vsock. If unsure, say N. + +config VMWARE_VMCI_VSOCKETS + tristate "VMware VMCI transport for Virtual Sockets" + depends on VSOCKETS && VMWARE_VMCI + help + This module implements a VMCI transport for Virtual Sockets. + + Enable this transport if your Virtual Machine runs on a VMware + hypervisor. + + To compile this driver as a module, choose M here: the module + will be called vmw_vsock_vmci_transport. If unsure, say N. diff --git a/net/vmw_vsock/Makefile b/net/vmw_vsock/Makefile new file mode 100644 index 000000000000..2ce52d70f224 --- /dev/null +++ b/net/vmw_vsock/Makefile @@ -0,0 +1,7 @@ +obj-$(CONFIG_VSOCKETS) += vsock.o +obj-$(CONFIG_VMWARE_VMCI_VSOCKETS) += vmw_vsock_vmci_transport.o + +vsock-y += af_vsock.o vsock_addr.o + +vmw_vsock_vmci_transport-y += vmci_transport.o vmci_transport_notify.o \ + vmci_transport_notify_qstate.o diff --git a/net/vmw_vsock/af_vsock.c b/net/vmw_vsock/af_vsock.c new file mode 100644 index 000000000000..54bb7bdf92d3 --- /dev/null +++ b/net/vmw_vsock/af_vsock.c @@ -0,0 +1,2015 @@ +/* + * VMware vSockets Driver + * + * Copyright (C) 2007-2013 VMware, Inc. All rights reserved. + * + * This program is free software; you can redistribute it and/or modify it + * under the terms of the GNU General Public License as published by the Free + * Software Foundation version 2 and no later version. + * + * This program is distributed in the hope that it will be useful, but WITHOUT + * ANY WARRANTY; without even the implied warranty of MERCHANTABILITY or + * FITNESS FOR A PARTICULAR PURPOSE. See the GNU General Public License for + * more details. + */ + +/* Implementation notes: + * + * - There are two kinds of sockets: those created by user action (such as + * calling socket(2)) and those created by incoming connection request packets. + * + * - There are two "global" tables, one for bound sockets (sockets that have + * specified an address that they are responsible for) and one for connected + * sockets (sockets that have established a connection with another socket). + * These tables are "global" in that all sockets on the system are placed + * within them. - Note, though, that the bound table contains an extra entry + * for a list of unbound sockets and SOCK_DGRAM sockets will always remain in + * that list. The bound table is used solely for lookup of sockets when packets + * are received and that's not necessary for SOCK_DGRAM sockets since we create + * a datagram handle for each and need not perform a lookup. Keeping SOCK_DGRAM + * sockets out of the bound hash buckets will reduce the chance of collisions + * when looking for SOCK_STREAM sockets and prevents us from having to check the + * socket type in the hash table lookups. + * + * - Sockets created by user action will either be "client" sockets that + * initiate a connection or "server" sockets that listen for connections; we do + * not support simultaneous connects (two "client" sockets connecting). + * + * - "Server" sockets are referred to as listener sockets throughout this + * implementation because they are in the SS_LISTEN state. When a connection + * request is received (the second kind of socket mentioned above), we create a + * new socket and refer to it as a pending socket. These pending sockets are + * placed on the pending connection list of the listener socket. When future + * packets are received for the address the listener socket is bound to, we + * check if the source of the packet is from one that has an existing pending + * connection. If it does, we process the packet for the pending socket. When + * that socket reaches the connected state, it is removed from the listener + * socket's pending list and enqueued in the listener socket's accept queue. + * Callers of accept(2) will accept connected sockets from the listener socket's + * accept queue. If the socket cannot be accepted for some reason then it is + * marked rejected. Once the connection is accepted, it is owned by the user + * process and the responsibility for cleanup falls with that user process. + * + * - It is possible that these pending sockets will never reach the connected + * state; in fact, we may never receive another packet after the connection + * request. Because of this, we must schedule a cleanup function to run in the + * future, after some amount of time passes where a connection should have been + * established. This function ensures that the socket is off all lists so it + * cannot be retrieved, then drops all references to the socket so it is cleaned + * up (sock_put() -> sk_free() -> our sk_destruct implementation). Note this + * function will also cleanup rejected sockets, those that reach the connected + * state but leave it before they have been accepted. + * + * - Sockets created by user action will be cleaned up when the user process + * calls close(2), causing our release implementation to be called. Our release + * implementation will perform some cleanup then drop the last reference so our + * sk_destruct implementation is invoked. Our sk_destruct implementation will + * perform additional cleanup that's common for both types of sockets. + * + * - A socket's reference count is what ensures that the structure won't be + * freed. Each entry in a list (such as the "global" bound and connected tables + * and the listener socket's pending list and connected queue) ensures a + * reference. When we defer work until process context and pass a socket as our + * argument, we must ensure the reference count is increased to ensure the + * socket isn't freed before the function is run; the deferred function will + * then drop the reference. + */ + +#include <linux/types.h> + +#define EXPORT_SYMTAB +#include <linux/bitops.h> +#include <linux/cred.h> +#include <linux/init.h> +#include <linux/io.h> +#include <linux/kernel.h> +#include <linux/kmod.h> +#include <linux/list.h> +#include <linux/miscdevice.h> +#include <linux/module.h> +#include <linux/mutex.h> +#include <linux/net.h> +#include <linux/poll.h> +#include <linux/skbuff.h> +#include <linux/smp.h> +#include <linux/socket.h> +#include <linux/stddef.h> +#include <linux/unistd.h> +#include <linux/wait.h> +#include <linux/workqueue.h> +#include <net/sock.h> + +#include "af_vsock.h" +#include "vsock_version.h" + +static int __vsock_bind(struct sock *sk, struct sockaddr_vm *addr); +static void vsock_sk_destruct(struct sock *sk); +static int vsock_queue_rcv_skb(struct sock *sk, struct sk_buff *skb); + +/* Protocol family. */ +static struct proto vsock_proto = { + .name = "AF_VSOCK", + .owner = THIS_MODULE, + .obj_size = sizeof(struct vsock_sock), +}; + +/* The default peer timeout indicates how long we will wait for a peer response + * to a control message. + */ +#define VSOCK_DEFAULT_CONNECT_TIMEOUT (2 * HZ) + +#define SS_LISTEN 255 + +static const struct vsock_transport *transport; +static DEFINE_MUTEX(vsock_register_mutex); + +/**** EXPORTS ****/ + +/* Get the ID of the local context. This is transport dependent. */ + +int vm_sockets_get_local_cid(void) +{ + return transport->get_local_cid(); +} +EXPORT_SYMBOL_GPL(vm_sockets_get_local_cid); + +/**** UTILS ****/ + +/* Each bound VSocket is stored in the bind hash table and each connected + * VSocket is stored in the connected hash table. + * + * Unbound sockets are all put on the same list attached to the end of the hash + * table (vsock_unbound_sockets). Bound sockets are added to the hash table in + * the bucket that their local address hashes to (vsock_bound_sockets(addr) + * represents the list that addr hashes to). + * + * Specifically, we initialize the vsock_bind_table array to a size of + * VSOCK_HASH_SIZE + 1 so that vsock_bind_table[0] through + * vsock_bind_table[VSOCK_HASH_SIZE - 1] are for bound sockets and + * vsock_bind_table[VSOCK_HASH_SIZE] is for unbound sockets. The hash function + * mods with VSOCK_HASH_SIZE - 1 to ensure this. + */ +#define VSOCK_HASH_SIZE 251 +#define MAX_PORT_RETRIES 24 + +#define VSOCK_HASH(addr) ((addr)->svm_port % (VSOCK_HASH_SIZE - 1)) +#define vsock_bound_sockets(addr) (&vsock_bind_table[VSOCK_HASH(addr)]) +#define vsock_unbound_sockets (&vsock_bind_table[VSOCK_HASH_SIZE]) + +/* XXX This can probably be implemented in a better way. */ +#define VSOCK_CONN_HASH(src, dst) \ + (((src)->svm_cid ^ (dst)->svm_port) % (VSOCK_HASH_SIZE - 1)) +#define vsock_connected_sockets(src, dst) \ + (&vsock_connected_table[VSOCK_CONN_HASH(src, dst)]) +#define vsock_connected_sockets_vsk(vsk) \ + vsock_connected_sockets(&(vsk)->remote_addr, &(vsk)->local_addr) + +static struct list_head vsock_bind_table[VSOCK_HASH_SIZE + 1]; +static struct list_head vsock_connected_table[VSOCK_HASH_SIZE]; +static DEFINE_SPINLOCK(vsock_table_lock); + +static __init void vsock_init_tables(void) +{ + int i; + + for (i = 0; i < ARRAY_SIZE(vsock_bind_table); i++) + INIT_LIST_HEAD(&vsock_bind_table[i]); + + for (i = 0; i < ARRAY_SIZE(vsock_connected_table); i++) + INIT_LIST_HEAD(&vsock_connected_table[i]); +} + +static void __vsock_insert_bound(struct list_head *list, + struct vsock_sock *vsk) +{ + sock_hold(&vsk->sk); + list_add(&vsk->bound_table, list); +} + +static void __vsock_insert_connected(struct list_head *list, + struct vsock_sock *vsk) +{ + sock_hold(&vsk->sk); + list_add(&vsk->connected_table, list); +} + +static void __vsock_remove_bound(struct vsock_sock *vsk) +{ + list_del_init(&vsk->bound_table); + sock_put(&vsk->sk); +} + +static void __vsock_remove_connected(struct vsock_sock *vsk) +{ + list_del_init(&vsk->connected_table); + sock_put(&vsk->sk); +} + +static struct sock *__vsock_find_bound_socket(struct sockaddr_vm *addr) +{ + struct vsock_sock *vsk; + + list_for_each_entry(vsk, vsock_bound_sockets(addr), bound_table) + if (vsock_addr_equals_addr_any(addr, &vsk->local_addr)) + return sk_vsock(vsk); + + return NULL; +} + +static struct sock *__vsock_find_connected_socket(struct sockaddr_vm *src, + struct sockaddr_vm *dst) +{ + struct vsock_sock *vsk; + + list_for_each_entry(vsk, vsock_connected_sockets(src, dst), + connected_table) { + if (vsock_addr_equals_addr(src, &vsk->remote_addr) + && vsock_addr_equals_addr(dst, &vsk->local_addr)) { + return sk_vsock(vsk); + } + } + + return NULL; +} + +static bool __vsock_in_bound_table(struct vsock_sock *vsk) +{ + return !list_empty(&vsk->bound_table); +} + +static bool __vsock_in_connected_table(struct vsock_sock *vsk) +{ + return !list_empty(&vsk->connected_table); +} + +static void vsock_insert_unbound(struct vsock_sock *vsk) +{ + spin_lock_bh(&vsock_table_lock); + __vsock_insert_bound(vsock_unbound_sockets, vsk); + spin_unlock_bh(&vsock_table_lock); +} + +void vsock_insert_connected(struct vsock_sock *vsk) +{ + struct list_head *list = vsock_connected_sockets( + &vsk->remote_addr, &vsk->local_addr); + + spin_lock_bh(&vsock_table_lock); + __vsock_insert_connected(list, vsk); + spin_unlock_bh(&vsock_table_lock); +} +EXPORT_SYMBOL_GPL(vsock_insert_connected); + +void vsock_remove_bound(struct vsock_sock *vsk) +{ + spin_lock_bh(&vsock_table_lock); + __vsock_remove_bound(vsk); + spin_unlock_bh(&vsock_table_lock); +} +EXPORT_SYMBOL_GPL(vsock_remove_bound); + +void vsock_remove_connected(struct vsock_sock *vsk) +{ + spin_lock_bh(&vsock_table_lock); + __vsock_remove_connected(vsk); + spin_unlock_bh(&vsock_table_lock); +} +EXPORT_SYMBOL_GPL(vsock_remove_connected); + +struct sock *vsock_find_bound_socket(struct sockaddr_vm *addr) +{ + struct sock *sk; + + spin_lock_bh(&vsock_table_lock); + sk = __vsock_find_bound_socket(addr); + if (sk) + sock_hold(sk); + + spin_unlock_bh(&vsock_table_lock); + + return sk; +} +EXPORT_SYMBOL_GPL(vsock_find_bound_socket); + +struct sock *vsock_find_connected_socket(struct sockaddr_vm *src, + struct sockaddr_vm *dst) +{ + struct sock *sk; + + spin_lock_bh(&vsock_table_lock); + sk = __vsock_find_connected_socket(src, dst); + if (sk) + sock_hold(sk); + + spin_unlock_bh(&vsock_table_lock); + + return sk; +} +EXPORT_SYMBOL_GPL(vsock_find_connected_socket); + +static bool vsock_in_bound_table(struct vsock_sock *vsk) +{ + bool ret; + + spin_lock_bh(&vsock_table_lock); + ret = __vsock_in_bound_table(vsk); + spin_unlock_bh(&vsock_table_lock); + + return ret; +} + +static bool vsock_in_connected_table(struct vsock_sock *vsk) +{ + bool ret; + + spin_lock_bh(&vsock_table_lock); + ret = __vsock_in_connected_table(vsk); + spin_unlock_bh(&vsock_table_lock); + + return ret; +} + +void vsock_for_each_connected_socket(void (*fn)(struct sock *sk)) +{ + int i; + + spin_lock_bh(&vsock_table_lock); + + for (i = 0; i < ARRAY_SIZE(vsock_connected_table); i++) { + struct vsock_sock *vsk; + list_for_each_entry(vsk, &vsock_connected_table[i], + connected_table); + fn(sk_vsock(vsk)); + } + + spin_unlock_bh(&vsock_table_lock); +} +EXPORT_SYMBOL_GPL(vsock_for_each_connected_socket); + +void vsock_add_pending(struct sock *listener, struct sock *pending) +{ + struct vsock_sock *vlistener; + struct vsock_sock *vpending; + + vlistener = vsock_sk(listener); + vpending = vsock_sk(pending); + + sock_hold(pending); + sock_hold(listener); + list_add_tail(&vpending->pending_links, &vlistener->pending_links); +} +EXPORT_SYMBOL_GPL(vsock_add_pending); + +void vsock_remove_pending(struct sock *listener, struct sock *pending) +{ + struct vsock_sock *vpending = vsock_sk(pending); + + list_del_init(&vpending->pending_links); + sock_put(listener); + sock_put(pending); +} +EXPORT_SYMBOL_GPL(vsock_remove_pending); + +void vsock_enqueue_accept(struct sock *listener, struct sock *connected) +{ + struct vsock_sock *vlistener; + struct vsock_sock *vconnected; + + vlistener = vsock_sk(listener); + vconnected = vsock_sk(connected); + + sock_hold(connected); + sock_hold(listener); + list_add_tail(&vconnected->accept_queue, &vlistener->accept_queue); +} +EXPORT_SYMBOL_GPL(vsock_enqueue_accept); + +static struct sock *vsock_dequeue_accept(struct sock *listener) +{ + struct vsock_sock *vlistener; + struct vsock_sock *vconnected; + + vlistener = vsock_sk(listener); + + if (list_empty(&vlistener->accept_queue)) + return NULL; + + vconnected = list_entry(vlistener->accept_queue.next, + struct vsock_sock, accept_queue); + + list_del_init(&vconnected->accept_queue); + sock_put(listener); + /* The caller will need a reference on the connected socket so we let + * it call sock_put(). + */ + + return sk_vsock(vconnected); +} + +static bool vsock_is_accept_queue_empty(struct sock *sk) +{ + struct vsock_sock *vsk = vsock_sk(sk); + return list_empty(&vsk->accept_queue); +} + +static bool vsock_is_pending(struct sock *sk) +{ + struct vsock_sock *vsk = vsock_sk(sk); + return !list_empty(&vsk->pending_links); +} + +static int vsock_send_shutdown(struct sock *sk, int mode) +{ + return transport->shutdown(vsock_sk(sk), mode); +} + +void vsock_pending_work(struct work_struct *work) +{ + struct sock *sk; + struct sock *listener; + struct vsock_sock *vsk; + bool cleanup; + + vsk = container_of(work, struct vsock_sock, dwork.work); + sk = sk_vsock(vsk); + listener = vsk->listener; + cleanup = true; + + lock_sock(listener); + lock_sock(sk); + + if (vsock_is_pending(sk)) { + vsock_remove_pending(listener, sk); + } else if (!vsk->rejected) { + /* We are not on the pending list and accept() did not reject + * us, so we must have been accepted by our user process. We + * just need to drop our references to the sockets and be on + * our way. + */ + cleanup = false; + goto out; + } + + listener->sk_ack_backlog--; + + /* We need to remove ourself from the global connected sockets list so + * incoming packets can't find this socket, and to reduce the reference + * count. + */ + if (vsock_in_connected_table(vsk)) + vsock_remove_connected(vsk); + + sk->sk_state = SS_FREE; + +out: + release_sock(sk); + release_sock(listener); + if (cleanup) + sock_put(sk); + + sock_put(sk); + sock_put(listener); +} +EXPORT_SYMBOL_GPL(vsock_pending_work); + +/**** SOCKET OPERATIONS ****/ + +static int __vsock_bind_stream(struct vsock_sock *vsk, + struct sockaddr_vm *addr) +{ + static u32 port = LAST_RESERVED_PORT + 1; + struct sockaddr_vm new_addr; + + vsock_addr_init(&new_addr, addr->svm_cid, addr->svm_port); + + if (addr->svm_port == VMADDR_PORT_ANY) { + bool found = false; + unsigned int i; + + for (i = 0; i < MAX_PORT_RETRIES; i++) { + if (port <= LAST_RESERVED_PORT) + port = LAST_RESERVED_PORT + 1; + + new_addr.svm_port = port++; + + if (!__vsock_find_bound_socket(&new_addr)) { + found = true; + break; + } + } + + if (!found) + return -EADDRNOTAVAIL; + } else { + /* If port is in reserved range, ensure caller + * has necessary privileges. + */ + if (addr->svm_port <= LAST_RESERVED_PORT && + !capable(CAP_NET_BIND_SERVICE)) { + return -EACCES; + } + + if (__vsock_find_bound_socket(&new_addr)) + return -EADDRINUSE; + } + + vsock_addr_init(&vsk->local_addr, new_addr.svm_cid, new_addr.svm_port); + + /* Remove stream sockets from the unbound list and add them to the hash + * table for easy lookup by its address. The unbound list is simply an + * extra entry at the end of the hash table, a trick used by AF_UNIX. + */ + __vsock_remove_bound(vsk); + __vsock_insert_bound(vsock_bound_sockets(&vsk->local_addr), vsk); + + return 0; +} + +static int __vsock_bind_dgram(struct vsock_sock *vsk, + struct sockaddr_vm *addr) +{ + return transport->dgram_bind(vsk, addr); +} + +static int __vsock_bind(struct sock *sk, struct sockaddr_vm *addr) +{ + struct vsock_sock *vsk = vsock_sk(sk); + u32 cid; + int retval; + + /* First ensure this socket isn't already bound. */ + if (vsock_addr_bound(&vsk->local_addr)) + return -EINVAL; + + /* Now bind to the provided address or select appropriate values if + * none are provided (VMADDR_CID_ANY and VMADDR_PORT_ANY). Note that + * like AF_INET prevents binding to a non-local IP address (in most + * cases), we only allow binding to the local CID. + */ + cid = transport->get_local_cid(); + if (addr->svm_cid != cid && addr->svm_cid != VMADDR_CID_ANY) + return -EADDRNOTAVAIL; + + switch (sk->sk_socket->type) { + case SOCK_STREAM: + spin_lock_bh(&vsock_table_lock); + retval = __vsock_bind_stream(vsk, addr); + spin_unlock_bh(&vsock_table_lock); + break; + + case SOCK_DGRAM: + retval = __vsock_bind_dgram(vsk, addr); + break; + + default: + retval = -EINVAL; + break; + } + + return retval; +} + +struct sock *__vsock_create(struct net *net, + struct socket *sock, + struct sock *parent, + gfp_t priority, + unsigned short type) +{ + struct sock *sk; + struct vsock_sock *psk; + struct vsock_sock *vsk; + + sk = sk_alloc(net, AF_VSOCK, priority, &vsock_proto); + if (!sk) + return NULL; + + sock_init_data(sock, sk); + + /* sk->sk_type is normally set in sock_init_data, but only if sock is + * non-NULL. We make sure that our sockets always have a type by + * setting it here if needed. + */ + if (!sock) + sk->sk_type = type; + + vsk = vsock_sk(sk); + vsock_addr_init(&vsk->local_addr, VMADDR_CID_ANY, VMADDR_PORT_ANY); + vsock_addr_init(&vsk->remote_addr, VMADDR_CID_ANY, VMADDR_PORT_ANY); + + sk->sk_destruct = vsock_sk_destruct; + sk->sk_backlog_rcv = vsock_queue_rcv_skb; + sk->sk_state = 0; + sock_reset_flag(sk, SOCK_DONE); + + INIT_LIST_HEAD(&vsk->bound_table); + INIT_LIST_HEAD(&vsk->connected_table); + vsk->listener = NULL; + INIT_LIST_HEAD(&vsk->pending_links); + INIT_LIST_HEAD(&vsk->accept_queue); + vsk->rejected = false; + vsk->sent_request = false; + vsk->ignore_connecting_rst = false; + vsk->peer_shutdown = 0; + + psk = parent ? vsock_sk(parent) : NULL; + if (parent) { + vsk->trusted = psk->trusted; + vsk->owner = get_cred(psk->owner); + vsk->connect_timeout = psk->connect_timeout; + } else { + vsk->trusted = capable(CAP_NET_ADMIN); + vsk->owner = get_current_cred(); + vsk->connect_timeout = VSOCK_DEFAULT_CONNECT_TIMEOUT; + } + + if (transport->init(vsk, psk) < 0) { + sk_free(sk); + return NULL; + } + + if (sock) + vsock_insert_unbound(vsk); + + return sk; +} +EXPORT_SYMBOL_GPL(__vsock_create); + +static void __vsock_release(struct sock *sk) +{ + if (sk) { + struct sk_buff *skb; + struct sock *pending; + struct vsock_sock *vsk; + + vsk = vsock_sk(sk); + pending = NULL; /* Compiler warning. */ + + if (vsock_in_bound_table(vsk)) + vsock_remove_bound(vsk); + + if (vsock_in_connected_table(vsk)) + vsock_remove_connected(vsk); + + transport->release(vsk); + + lock_sock(sk); + sock_orphan(sk); + sk->sk_shutdown = SHUTDOWN_MASK; + + while ((skb = skb_dequeue(&sk->sk_receive_queue))) + kfree_skb(skb); + + /* Clean up any sockets that never were accepted. */ + while ((pending = vsock_dequeue_accept(sk)) != NULL) { + __vsock_release(pending); + sock_put(pending); + } + + release_sock(sk); + sock_put(sk); + } +} + +static void vsock_sk_destruct(struct sock *sk) +{ + struct vsock_sock *vsk = vsock_sk(sk); + + transport->destruct(vsk); + + /* When clearing these addresses, there's no need to set the family and + * possibly register the address family with the kernel. + */ + vsock_addr_init(&vsk->local_addr, VMADDR_CID_ANY, VMADDR_PORT_ANY); + vsock_addr_init(&vsk->remote_addr, VMADDR_CID_ANY, VMADDR_PORT_ANY); + + put_cred(vsk->owner); +} + +static int vsock_queue_rcv_skb(struct sock *sk, struct sk_buff *skb) +{ + int err; + + err = sock_queue_rcv_skb(sk, skb); + if (err) + kfree_skb(skb); + + return err; +} + +s64 vsock_stream_has_data(struct vsock_sock *vsk) +{ + return transport->stream_has_data(vsk); +} +EXPORT_SYMBOL_GPL(vsock_stream_has_data); + +s64 vsock_stream_has_space(struct vsock_sock *vsk) +{ + return transport->stream_has_space(vsk); +} +EXPORT_SYMBOL_GPL(vsock_stream_has_space); + +static int vsock_release(struct socket *sock) +{ + __vsock_release(sock->sk); + sock->sk = NULL; + sock->state = SS_FREE; + + return 0; +} + +static int +vsock_bind(struct socket *sock, struct sockaddr *addr, int addr_len) +{ + int err; + struct sock *sk; + struct sockaddr_vm *vm_addr; + + sk = sock->sk; + + if (vsock_addr_cast(addr, addr_len, &vm_addr) != 0) + return -EINVAL; + + lock_sock(sk); + err = __vsock_bind(sk, vm_addr); + release_sock(sk); + + return err; +} + +static int vsock_getname(struct socket *sock, + struct sockaddr *addr, int *addr_len, int peer) +{ + int err; + struct sock *sk; + struct vsock_sock *vsk; + struct sockaddr_vm *vm_addr; + + sk = sock->sk; + vsk = vsock_sk(sk); + err = 0; + + lock_sock(sk); + + if (peer) { + if (sock->state != SS_CONNECTED) { + err = -ENOTCONN; + goto out; + } + vm_addr = &vsk->remote_addr; + } else { + vm_addr = &vsk->local_addr; + } + + if (!vm_addr) { + err = -EINVAL; + goto out; + } + + /* sys_getsockname() and sys_getpeername() pass us a + * MAX_SOCK_ADDR-sized buffer and don't set addr_len. Unfortunately + * that macro is defined in socket.c instead of .h, so we hardcode its + * value here. + */ + BUILD_BUG_ON(sizeof(*vm_addr) > 128); + memcpy(addr, vm_addr, sizeof(*vm_addr)); + *addr_len = sizeof(*vm_addr); + +out: + release_sock(sk); + return err; +} + +static int vsock_shutdown(struct socket *sock, int mode) +{ + int err; + struct sock *sk; + + /* User level uses SHUT_RD (0) and SHUT_WR (1), but the kernel uses + * RCV_SHUTDOWN (1) and SEND_SHUTDOWN (2), so we must increment mode + * here like the other address families do. Note also that the + * increment makes SHUT_RDWR (2) into RCV_SHUTDOWN | SEND_SHUTDOWN (3), + * which is what we want. + */ + mode++; + + if ((mode & ~SHUTDOWN_MASK) || !mode) + return -EINVAL; + + /* If this is a STREAM socket and it is not connected then bail out + * immediately. If it is a DGRAM socket then we must first kick the + * socket so that it wakes up from any sleeping calls, for example + * recv(), and then afterwards return the error. + */ + + sk = sock->sk; + if (sock->state == SS_UNCONNECTED) { + err = -ENOTCONN; + if (sk->sk_type == SOCK_STREAM) + return err; + } else { + sock->state = SS_DISCONNECTING; + err = 0; + } + + /* Receive and send shutdowns are treated alike. */ + mode = mode & (RCV_SHUTDOWN | SEND_SHUTDOWN); + if (mode) { + lock_sock(sk); + sk->sk_shutdown |= mode; + sk->sk_state_change(sk); + release_sock(sk); + + if (sk->sk_type == SOCK_STREAM) { + sock_reset_flag(sk, SOCK_DONE); + vsock_send_shutdown(sk, mode); + } + } + + return err; +} + +static unsigned int vsock_poll(struct file *file, struct socket *sock, + poll_table *wait) +{ + struct sock *sk; + unsigned int mask; + struct vsock_sock *vsk; + + sk = sock->sk; + vsk = vsock_sk(sk); + + poll_wait(file, sk_sleep(sk), wait); + mask = 0; + + if (sk->sk_err) + /* Signify that there has been an error on this socket. */ + mask |= POLLERR; + + /* INET sockets treat local write shutdown and peer write shutdown as a + * case of POLLHUP set. + */ + if ((sk->sk_shutdown == SHUTDOWN_MASK) || + ((sk->sk_shutdown & SEND_SHUTDOWN) && + (vsk->peer_shutdown & SEND_SHUTDOWN))) { + mask |= POLLHUP; + } + + if (sk->sk_shutdown & RCV_SHUTDOWN || + vsk->peer_shutdown & SEND_SHUTDOWN) { + mask |= POLLRDHUP; + } + + if (sock->type == SOCK_DGRAM) { + /* For datagram sockets we can read if there is something in + * the queue and write as long as the socket isn't shutdown for + * sending. + */ + if (!skb_queue_empty(&sk->sk_receive_queue) || + (sk->sk_shutdown & RCV_SHUTDOWN)) { + mask |= POLLIN | POLLRDNORM; + } + + if (!(sk->sk_shutdown & SEND_SHUTDOWN)) + mask |= POLLOUT | POLLWRNORM | POLLWRBAND; + + } else if (sock->type == SOCK_STREAM) { + lock_sock(sk); + + /* Listening sockets that have connections in their accept + * queue can be read. + */ + if (sk->sk_state == SS_LISTEN + && !vsock_is_accept_queue_empty(sk)) + mask |= POLLIN | POLLRDNORM; + + /* If there is something in the queue then we can read. */ + if (transport->stream_is_active(vsk) && + !(sk->sk_shutdown & RCV_SHUTDOWN)) { + bool data_ready_now = false; + int ret = transport->notify_poll_in( + vsk, 1, &data_ready_now); + if (ret < 0) { + mask |= POLLERR; + } else { + if (data_ready_now) + mask |= POLLIN | POLLRDNORM; + + } + } + + /* Sockets whose connections have been closed, reset, or + * terminated should also be considered read, and we check the + * shutdown flag for that. + */ + if (sk->sk_shutdown & RCV_SHUTDOWN || + vsk->peer_shutdown & SEND_SHUTDOWN) { + mask |= POLLIN | POLLRDNORM; + } + + /* Connected sockets that can produce data can be written. */ + if (sk->sk_state == SS_CONNECTED) { + if (!(sk->sk_shutdown & SEND_SHUTDOWN)) { + bool space_avail_now = false; + int ret = transport->notify_poll_out( + vsk, 1, &space_avail_now); + if (ret < 0) { + mask |= POLLERR; + } else { + if (space_avail_now) + /* Remove POLLWRBAND since INET + * sockets are not setting it. + */ + mask |= POLLOUT | POLLWRNORM; + + } + } + } + + /* Simulate INET socket poll behaviors, which sets + * POLLOUT|POLLWRNORM when peer is closed and nothing to read, + * but local send is not shutdown. + */ + if (sk->sk_state == SS_UNCONNECTED) { + if (!(sk->sk_shutdown & SEND_SHUTDOWN)) + mask |= POLLOUT | POLLWRNORM; + + } + + release_sock(sk); + } + + return mask; +} + +static int vsock_dgram_sendmsg(struct kiocb *kiocb, struct socket *sock, + struct msghdr *msg, size_t len) +{ + int err; + struct sock *sk; + struct vsock_sock *vsk; + struct sockaddr_vm *remote_addr; + + if (msg->msg_flags & MSG_OOB) + return -EOPNOTSUPP; + + /* For now, MSG_DONTWAIT is always assumed... */ + err = 0; + sk = sock->sk; + vsk = vsock_sk(sk); + + lock_sock(sk); + + if (!vsock_addr_bound(&vsk->local_addr)) { + struct sockaddr_vm local_addr; + + vsock_addr_init(&local_addr, VMADDR_CID_ANY, VMADDR_PORT_ANY); + err = __vsock_bind(sk, &local_addr); + if (err != 0) + goto out; + + } + + /* If the provided message contains an address, use that. Otherwise + * fall back on the socket's remote handle (if it has been connected). + */ + if (msg->msg_name && + vsock_addr_cast(msg->msg_name, msg->msg_namelen, + &remote_addr) == 0) { + /* Ensure this address is of the right type and is a valid + * destination. + */ + + if (remote_addr->svm_cid == VMADDR_CID_ANY) + remote_addr->svm_cid = transport->get_local_cid(); + + if (!vsock_addr_bound(remote_addr)) { + err = -EINVAL; + goto out; + } + } else if (sock->state == SS_CONNECTED) { + remote_addr = &vsk->remote_addr; + + if (remote_addr->svm_cid == VMADDR_CID_ANY) + remote_addr->svm_cid = transport->get_local_cid(); + + /* XXX Should connect() or this function ensure remote_addr is + * bound? + */ + if (!vsock_addr_bound(&vsk->remote_addr)) { + err = -EINVAL; + goto out; + } + } else { + err = -EINVAL; + goto out; + } + + if (!transport->dgram_allow(remote_addr->svm_cid, + remote_addr->svm_port)) { + err = -EINVAL; + goto out; + } + + err = transport->dgram_enqueue(vsk, remote_addr, msg->msg_iov, len); + +out: + release_sock(sk); + return err; +} + +static int vsock_dgram_connect(struct socket *sock, + struct sockaddr *addr, int addr_len, int flags) +{ + int err; + struct sock *sk; + struct vsock_sock *vsk; + struct sockaddr_vm *remote_addr; + + sk = sock->sk; + vsk = vsock_sk(sk); + + err = vsock_addr_cast(addr, addr_len, &remote_addr); + if (err == -EAFNOSUPPORT && remote_addr->svm_family == AF_UNSPEC) { + lock_sock(sk); + vsock_addr_init(&vsk->remote_addr, VMADDR_CID_ANY, + VMADDR_PORT_ANY); + sock->state = SS_UNCONNECTED; + release_sock(sk); + return 0; + } else if (err != 0) + return -EINVAL; + + lock_sock(sk); + + if (!vsock_addr_bound(&vsk->local_addr)) { + struct sockaddr_vm local_addr; + + vsock_addr_init(&local_addr, VMADDR_CID_ANY, VMADDR_PORT_ANY); + err = __vsock_bind(sk, &local_addr); + if (err != 0) + goto out; + + } + + if (!transport->dgram_allow(remote_addr->svm_cid, + remote_addr->svm_port)) { + err = -EINVAL; + goto out; + } + + memcpy(&vsk->remote_addr, remote_addr, sizeof(vsk->remote_addr)); + sock->state = SS_CONNECTED; + +out: + release_sock(sk); + return err; +} + +static int vsock_dgram_recvmsg(struct kiocb *kiocb, struct socket *sock, + struct msghdr *msg, size_t len, int flags) +{ + return transport->dgram_dequeue(kiocb, vsock_sk(sock->sk), msg, len, + flags); +} + +static const struct proto_ops vsock_dgram_ops = { + .family = PF_VSOCK, + .owner = THIS_MODULE, + .release = vsock_release, + .bind = vsock_bind, + .connect = vsock_dgram_connect, + .socketpair = sock_no_socketpair, + .accept = sock_no_accept, + .getname = vsock_getname, + .poll = vsock_poll, + .ioctl = sock_no_ioctl, + .listen = sock_no_listen, + .shutdown = vsock_shutdown, + .setsockopt = sock_no_setsockopt, + .getsockopt = sock_no_getsockopt, + .sendmsg = vsock_dgram_sendmsg, + .recvmsg = vsock_dgram_recvmsg, + .mmap = sock_no_mmap, + .sendpage = sock_no_sendpage, +}; + +static void vsock_connect_timeout(struct work_struct *work) +{ + struct sock *sk; + struct vsock_sock *vsk; + + vsk = container_of(work, struct vsock_sock, dwork.work); + sk = sk_vsock(vsk); + + lock_sock(sk); + if (sk->sk_state == SS_CONNECTING && + (sk->sk_shutdown != SHUTDOWN_MASK)) { + sk->sk_state = SS_UNCONNECTED; + sk->sk_err = ETIMEDOUT; + sk->sk_error_report(sk); + } + release_sock(sk); + + sock_put(sk); +} + +static int vsock_stream_connect(struct socket *sock, struct sockaddr *addr, + int addr_len, int flags) +{ + int err; + struct sock *sk; + struct vsock_sock *vsk; + struct sockaddr_vm *remote_addr; + long timeout; + DEFINE_WAIT(wait); + + err = 0; + sk = sock->sk; + vsk = vsock_sk(sk); + + lock_sock(sk); + + /* XXX AF_UNSPEC should make us disconnect like AF_INET. */ + switch (sock->state) { + case SS_CONNECTED: + err = -EISCONN; + goto out; + case SS_DISCONNECTING: + err = -EINVAL; + goto out; + case SS_CONNECTING: + /* This continues on so we can move sock into the SS_CONNECTED + * state once the connection has completed (at which point err + * will be set to zero also). Otherwise, we will either wait + * for the connection or return -EALREADY should this be a + * non-blocking call. + */ + err = -EALREADY; + break; + default: + if ((sk->sk_state == SS_LISTEN) || + vsock_addr_cast(addr, addr_len, &remote_addr) != 0) { + err = -EINVAL; + goto out; + } + + /* The hypervisor and well-known contexts do not have socket + * endpoints. + */ + if (!transport->stream_allow(remote_addr->svm_cid, + remote_addr->svm_port)) { + err = -ENETUNREACH; + goto out; + } + + /* Set the remote address that we are connecting to. */ + memcpy(&vsk->remote_addr, remote_addr, + sizeof(vsk->remote_addr)); + + /* Autobind this socket to the local address if necessary. */ + if (!vsock_addr_bound(&vsk->local_addr)) { + struct sockaddr_vm local_addr; + + vsock_addr_init(&local_addr, VMADDR_CID_ANY, + VMADDR_PORT_ANY); + err = __vsock_bind(sk, &local_addr); + if (err != 0) + goto out; + + } + + sk->sk_state = SS_CONNECTING; + + err = transport->connect(vsk); + if (err < 0) + goto out; + + /* Mark sock as connecting and set the error code to in + * progress in case this is a non-blocking connect. + */ + sock->state = SS_CONNECTING; + err = -EINPROGRESS; + } + + /* The receive path will handle all communication until we are able to + * enter the connected state. Here we wait for the connection to be + * completed or a notification of an error. + */ + timeout = vsk->connect_timeout; + prepare_to_wait(sk_sleep(sk), &wait, TASK_INTERRUPTIBLE); + + while (sk->sk_state != SS_CONNECTED && sk->sk_err == 0) { + if (flags & O_NONBLOCK) { + /* If we're not going to block, we schedule a timeout + * function to generate a timeout on the connection + * attempt, in case the peer doesn't respond in a + * timely manner. We hold on to the socket until the + * timeout fires. + */ + sock_hold(sk); + INIT_DELAYED_WORK(&vsk->dwork, + vsock_connect_timeout); + schedule_delayed_work(&vsk->dwork, timeout); + + /* Skip ahead to preserve error code set above. */ + goto out_wait; + } + + release_sock(sk); + timeout = schedule_timeout(timeout); + lock_sock(sk); + + if (signal_pending(current)) { + err = sock_intr_errno(timeout); + goto out_wait_error; + } else if (timeout == 0) { + err = -ETIMEDOUT; + goto out_wait_error; + } + + prepare_to_wait(sk_sleep(sk), &wait, TASK_INTERRUPTIBLE); + } + + if (sk->sk_err) { + err = -sk->sk_err; + goto out_wait_error; + } else + err = 0; + +out_wait: + finish_wait(sk_sleep(sk), &wait); +out: + release_sock(sk); + return err; + +out_wait_error: + sk->sk_state = SS_UNCONNECTED; + sock->state = SS_UNCONNECTED; + goto out_wait; +} + +static int vsock_accept(struct socket *sock, struct socket *newsock, int flags) +{ + struct sock *listener; + int err; + struct sock *connected; + struct vsock_sock *vconnected; + long timeout; + DEFINE_WAIT(wait); + + err = 0; + listener = sock->sk; + + lock_sock(listener); + + if (sock->type != SOCK_STREAM) { + err = -EOPNOTSUPP; + goto out; + } + + if (listener->sk_state != SS_LISTEN) { + err = -EINVAL; + goto out; + } + + /* Wait for children sockets to appear; these are the new sockets + * created upon connection establishment. + */ + timeout = sock_sndtimeo(listener, flags & O_NONBLOCK); + prepare_to_wait(sk_sleep(listener), &wait, TASK_INTERRUPTIBLE); + + while ((connected = vsock_dequeue_accept(listener)) == NULL && + listener->sk_err == 0) { + release_sock(listener); + timeout = schedule_timeout(timeout); + lock_sock(listener); + + if (signal_pending(current)) { + err = sock_intr_errno(timeout); + goto out_wait; + } else if (timeout == 0) { + err = -EAGAIN; + goto out_wait; + } + + prepare_to_wait(sk_sleep(listener), &wait, TASK_INTERRUPTIBLE); + } + + if (listener->sk_err) + err = -listener->sk_err; + + if (connected) { + listener->sk_ack_backlog--; + + lock_sock(connected); + vconnected = vsock_sk(connected); + + /* If the listener socket has received an error, then we should + * reject this socket and return. Note that we simply mark the + * socket rejected, drop our reference, and let the cleanup + * function handle the cleanup; the fact that we found it in + * the listener's accept queue guarantees that the cleanup + * function hasn't run yet. + */ + if (err) { + vconnected->rejected = true; + release_sock(connected); + sock_put(connected); + goto out_wait; + } + + newsock->state = SS_CONNECTED; + sock_graft(connected, newsock); + release_sock(connected); + sock_put(connected); + } + +out_wait: + finish_wait(sk_sleep(listener), &wait); +out: + release_sock(listener); + return err; +} + +static int vsock_listen(struct socket *sock, int backlog) +{ + int err; + struct sock *sk; + struct vsock_sock *vsk; + + sk = sock->sk; + + lock_sock(sk); + + if (sock->type != SOCK_STREAM) { + err = -EOPNOTSUPP; + goto out; + } + + if (sock->state != SS_UNCONNECTED) { + err = -EINVAL; + goto out; + } + + vsk = vsock_sk(sk); + + if (!vsock_addr_bound(&vsk->local_addr)) { + err = -EINVAL; + goto out; + } + + sk->sk_max_ack_backlog = backlog; + sk->sk_state = SS_LISTEN; + + err = 0; + +out: + release_sock(sk); + return err; +} + +static int vsock_stream_setsockopt(struct socket *sock, + int level, + int optname, + char __user *optval, + unsigned int optlen) +{ + int err; + struct sock *sk; + struct vsock_sock *vsk; + u64 val; + + if (level != AF_VSOCK) + return -ENOPROTOOPT; + +#define COPY_IN(_v) \ + do { \ + if (optlen < sizeof(_v)) { \ + err = -EINVAL; \ + goto exit; \ + } \ + if (copy_from_user(&_v, optval, sizeof(_v)) != 0) { \ + err = -EFAULT; \ + goto exit; \ + } \ + } while (0) + + err = 0; + sk = sock->sk; + vsk = vsock_sk(sk); + + lock_sock(sk); + + switch (optname) { + case SO_VM_SOCKETS_BUFFER_SIZE: + COPY_IN(val); + transport->set_buffer_size(vsk, val); + break; + + case SO_VM_SOCKETS_BUFFER_MAX_SIZE: + COPY_IN(val); + transport->set_max_buffer_size(vsk, val); + break; + + case SO_VM_SOCKETS_BUFFER_MIN_SIZE: + COPY_IN(val); + transport->set_min_buffer_size(vsk, val); + break; + + case SO_VM_SOCKETS_CONNECT_TIMEOUT: { + struct timeval tv; + COPY_IN(tv); + if (tv.tv_sec >= 0 && tv.tv_usec < USEC_PER_SEC && + tv.tv_sec < (MAX_SCHEDULE_TIMEOUT / HZ - 1)) { + vsk->connect_timeout = tv.tv_sec * HZ + + DIV_ROUND_UP(tv.tv_usec, (1000000 / HZ)); + if (vsk->connect_timeout == 0) + vsk->connect_timeout = + VSOCK_DEFAULT_CONNECT_TIMEOUT; + + } else { + err = -ERANGE; + } + break; + } + + default: + err = -ENOPROTOOPT; + break; + } + +#undef COPY_IN + +exit: + release_sock(sk); + return err; +} + +static int vsock_stream_getsockopt(struct socket *sock, + int level, int optname, + char __user *optval, + int __user *optlen) +{ + int err; + int len; + struct sock *sk; + struct vsock_sock *vsk; + u64 val; + + if (level != AF_VSOCK) + return -ENOPROTOOPT; + + err = get_user(len, optlen); + if (err != 0) + return err; + +#define COPY_OUT(_v) \ + do { \ + if (len < sizeof(_v)) \ + return -EINVAL; \ + \ + len = sizeof(_v); \ + if (copy_to_user(optval, &_v, len) != 0) \ + return -EFAULT; \ + \ + } while (0) + + err = 0; + sk = sock->sk; + vsk = vsock_sk(sk); + + switch (optname) { + case SO_VM_SOCKETS_BUFFER_SIZE: + val = transport->get_buffer_size(vsk); + COPY_OUT(val); + break; + + case SO_VM_SOCKETS_BUFFER_MAX_SIZE: + val = transport->get_max_buffer_size(vsk); + COPY_OUT(val); + break; + + case SO_VM_SOCKETS_BUFFER_MIN_SIZE: + val = transport->get_min_buffer_size(vsk); + COPY_OUT(val); + break; + + case SO_VM_SOCKETS_CONNECT_TIMEOUT: { + struct timeval tv; + tv.tv_sec = vsk->connect_timeout / HZ; + tv.tv_usec = + (vsk->connect_timeout - + tv.tv_sec * HZ) * (1000000 / HZ); + COPY_OUT(tv); + break; + } + default: + return -ENOPROTOOPT; + } + + err = put_user(len, optlen); + if (err != 0) + return -EFAULT; + +#undef COPY_OUT + + return 0; +} + +static int vsock_stream_sendmsg(struct kiocb *kiocb, struct socket *sock, + struct msghdr *msg, size_t len) +{ + struct sock *sk; + struct vsock_sock *vsk; + ssize_t total_written; + long timeout; + int err; + struct vsock_transport_send_notify_data send_data; + + DEFINE_WAIT(wait); + + sk = sock->sk; + vsk = vsock_sk(sk); + total_written = 0; + err = 0; + + if (msg->msg_flags & MSG_OOB) + return -EOPNOTSUPP; + + lock_sock(sk); + + /* Callers should not provide a destination with stream sockets. */ + if (msg->msg_namelen) { + err = sk->sk_state == SS_CONNECTED ? -EISCONN : -EOPNOTSUPP; + goto out; + } + + /* Send data only if both sides are not shutdown in the direction. */ + if (sk->sk_shutdown & SEND_SHUTDOWN || + vsk->peer_shutdown & RCV_SHUTDOWN) { + err = -EPIPE; + goto out; + } + + if (sk->sk_state != SS_CONNECTED || + !vsock_addr_bound(&vsk->local_addr)) { + err = -ENOTCONN; + goto out; + } + + if (!vsock_addr_bound(&vsk->remote_addr)) { + err = -EDESTADDRREQ; + goto out; + } + + /* Wait for room in the produce queue to enqueue our user's data. */ + timeout = sock_sndtimeo(sk, msg->msg_flags & MSG_DONTWAIT); + + err = transport->notify_send_init(vsk, &send_data); + if (err < 0) + goto out; + + prepare_to_wait(sk_sleep(sk), &wait, TASK_INTERRUPTIBLE); + + while (total_written < len) { + ssize_t written; + + while (vsock_stream_has_space(vsk) == 0 && + sk->sk_err == 0 && + !(sk->sk_shutdown & SEND_SHUTDOWN) && + !(vsk->peer_shutdown & RCV_SHUTDOWN)) { + + /* Don't wait for non-blocking sockets. */ + if (timeout == 0) { + err = -EAGAIN; + goto out_wait; + } + + err = transport->notify_send_pre_block(vsk, &send_data); + if (err < 0) + goto out_wait; + + release_sock(sk); + timeout = schedule_timeout(timeout); + lock_sock(sk); + if (signal_pending(current)) { + err = sock_intr_errno(timeout); + goto out_wait; + } else if (timeout == 0) { + err = -EAGAIN; + goto out_wait; + } + + prepare_to_wait(sk_sleep(sk), &wait, + TASK_INTERRUPTIBLE); + } + + /* These checks occur both as part of and after the loop + * conditional since we need to check before and after + * sleeping. + */ + if (sk->sk_err) { + err = -sk->sk_err; + goto out_wait; + } else if ((sk->sk_shutdown & SEND_SHUTDOWN) || + (vsk->peer_shutdown & RCV_SHUTDOWN)) { + err = -EPIPE; + goto out_wait; + } + + err = transport->notify_send_pre_enqueue(vsk, &send_data); + if (err < 0) + goto out_wait; + + /* Note that enqueue will only write as many bytes as are free + * in the produce queue, so we don't need to ensure len is + * smaller than the queue size. It is the caller's + * responsibility to check how many bytes we were able to send. + */ + + written = transport->stream_enqueue( + vsk, msg->msg_iov, + len - total_written); + if (written < 0) { + err = -ENOMEM; + goto out_wait; + } + + total_written += written; + + err = transport->notify_send_post_enqueue( + vsk, written, &send_data); + if (err < 0) + goto out_wait; + + } + +out_wait: + if (total_written > 0) + err = total_written; + finish_wait(sk_sleep(sk), &wait); +out: + release_sock(sk); + return err; +} + + +static int +vsock_stream_recvmsg(struct kiocb *kiocb, + struct socket *sock, + struct msghdr *msg, size_t len, int flags) +{ + struct sock *sk; + struct vsock_sock *vsk; + int err; + size_t target; + ssize_t copied; + long timeout; + struct vsock_transport_recv_notify_data recv_data; + + DEFINE_WAIT(wait); + + sk = sock->sk; + vsk = vsock_sk(sk); + err = 0; + + lock_sock(sk); + + if (sk->sk_state != SS_CONNECTED) { + /* Recvmsg is supposed to return 0 if a peer performs an + * orderly shutdown. Differentiate between that case and when a + * peer has not connected or a local shutdown occured with the + * SOCK_DONE flag. + */ + if (sock_flag(sk, SOCK_DONE)) + err = 0; + else + err = -ENOTCONN; + + goto out; + } + + if (flags & MSG_OOB) { + err = -EOPNOTSUPP; + goto out; + } + + /* We don't check peer_shutdown flag here since peer may actually shut + * down, but there can be data in the queue that a local socket can + * receive. + */ + if (sk->sk_shutdown & RCV_SHUTDOWN) { + err = 0; + goto out; + } + + /* It is valid on Linux to pass in a zero-length receive buffer. This + * is not an error. We may as well bail out now. + */ + if (!len) { + err = 0; + goto out; + } + + /* We must not copy less than target bytes into the user's buffer + * before returning successfully, so we wait for the consume queue to + * have that much data to consume before dequeueing. Note that this + * makes it impossible to handle cases where target is greater than the + * queue size. + */ + target = sock_rcvlowat(sk, flags & MSG_WAITALL, len); + if (target >= transport->stream_rcvhiwat(vsk)) { + err = -ENOMEM; + goto out; + } + timeout = sock_rcvtimeo(sk, flags & MSG_DONTWAIT); + copied = 0; + + err = transport->notify_recv_init(vsk, target, &recv_data); + if (err < 0) + goto out; + + prepare_to_wait(sk_sleep(sk), &wait, TASK_INTERRUPTIBLE); + + while (1) { + s64 ready = vsock_stream_has_data(vsk); + + if (ready < 0) { + /* Invalid queue pair content. XXX This should be + * changed to a connection reset in a later change. + */ + + err = -ENOMEM; + goto out_wait; + } else if (ready > 0) { + ssize_t read; + + err = transport->notify_recv_pre_dequeue( + vsk, target, &recv_data); + if (err < 0) + break; + + read = transport->stream_dequeue( + vsk, msg->msg_iov, + len - copied, flags); + if (read < 0) { + err = -ENOMEM; + break; + } + + copied += read; + + err = transport->notify_recv_post_dequeue( + vsk, target, read, + !(flags & MSG_PEEK), &recv_data); + if (err < 0) + goto out_wait; + + if (read >= target || flags & MSG_PEEK) + break; + + target -= read; + } else { + if (sk->sk_err != 0 || (sk->sk_shutdown & RCV_SHUTDOWN) + || (vsk->peer_shutdown & SEND_SHUTDOWN)) { + break; + } + /* Don't wait for non-blocking sockets. */ + if (timeout == 0) { + err = -EAGAIN; + break; + } + + err = transport->notify_recv_pre_block( + vsk, target, &recv_data); + if (err < 0) + break; + + release_sock(sk); + timeout = schedule_timeout(timeout); + lock_sock(sk); + + if (signal_pending(current)) { + err = sock_intr_errno(timeout); + break; + } else if (timeout == 0) { + err = -EAGAIN; + break; + } + + prepare_to_wait(sk_sleep(sk), &wait, + TASK_INTERRUPTIBLE); + } + } + + if (sk->sk_err) + err = -sk->sk_err; + else if (sk->sk_shutdown & RCV_SHUTDOWN) + err = 0; + + if (copied > 0) { + /* We only do these additional bookkeeping/notification steps + * if we actually copied something out of the queue pair + * instead of just peeking ahead. + */ + + if (!(flags & MSG_PEEK)) { + /* If the other side has shutdown for sending and there + * is nothing more to read, then modify the socket + * state. + */ + if (vsk->peer_shutdown & SEND_SHUTDOWN) { + if (vsock_stream_has_data(vsk) <= 0) { + sk->sk_state = SS_UNCONNECTED; + sock_set_flag(sk, SOCK_DONE); + sk->sk_state_change(sk); + } + } + } + err = copied; + } + +out_wait: + finish_wait(sk_sleep(sk), &wait); +out: + release_sock(sk); + return err; +} + +static const struct proto_ops vsock_stream_ops = { + .family = PF_VSOCK, + .owner = THIS_MODULE, + .release = vsock_release, + .bind = vsock_bind, + .connect = vsock_stream_connect, + .socketpair = sock_no_socketpair, + .accept = vsock_accept, + .getname = vsock_getname, + .poll = vsock_poll, + .ioctl = sock_no_ioctl, + .listen = vsock_listen, + .shutdown = vsock_shutdown, + .setsockopt = vsock_stream_setsockopt, + .getsockopt = vsock_stream_getsockopt, + .sendmsg = vsock_stream_sendmsg, + .recvmsg = vsock_stream_recvmsg, + .mmap = sock_no_mmap, + .sendpage = sock_no_sendpage, +}; + +static int vsock_create(struct net *net, struct socket *sock, + int protocol, int kern) +{ + if (!sock) + return -EINVAL; + + if (protocol) + return -EPROTONOSUPPORT; + + switch (sock->type) { + case SOCK_DGRAM: + sock->ops = &vsock_dgram_ops; + break; + case SOCK_STREAM: + sock->ops = &vsock_stream_ops; + break; + default: + return -ESOCKTNOSUPPORT; + } + + sock->state = SS_UNCONNECTED; + + return __vsock_create(net, sock, NULL, GFP_KERNEL, 0) ? 0 : -ENOMEM; +} + +static const struct net_proto_family vsock_family_ops = { + .family = AF_VSOCK, + .create = vsock_create, + .owner = THIS_MODULE, +}; + +static long vsock_dev_do_ioctl(struct file *filp, + unsigned int cmd, void __user *ptr) +{ + u32 __user *p = ptr; + int retval = 0; + + switch (cmd) { + case IOCTL_VM_SOCKETS_GET_LOCAL_CID: + if (put_user(transport->get_local_cid(), p) != 0) + retval = -EFAULT; + break; + + default: + pr_err("Unknown ioctl %d\n", cmd); + retval = -EINVAL; + } + + return retval; +} + +static long vsock_dev_ioctl(struct file *filp, + unsigned int cmd, unsigned long arg) +{ + return vsock_dev_do_ioctl(filp, cmd, (void __user *)arg); +} + +#ifdef CONFIG_COMPAT +static long vsock_dev_compat_ioctl(struct file *filp, + unsigned int cmd, unsigned long arg) +{ + return vsock_dev_do_ioctl(filp, cmd, compat_ptr(arg)); +} +#endif + +static const struct file_operations vsock_device_ops = { + .owner = THIS_MODULE, + .unlocked_ioctl = vsock_dev_ioctl, +#ifdef CONFIG_COMPAT + .compat_ioctl = vsock_dev_compat_ioctl, +#endif + .open = nonseekable_open, +}; + +static struct miscdevice vsock_device = { + .name = "vsock", + .minor = MISC_DYNAMIC_MINOR, + .fops = &vsock_device_ops, +}; + +static int __vsock_core_init(void) +{ + int err; + + vsock_init_tables(); + + err = misc_register(&vsock_device); + if (err) { + pr_err("Failed to register misc device\n"); + return -ENOENT; + } + + err = proto_register(&vsock_proto, 1); /* we want our slab */ + if (err) { + pr_err("Cannot register vsock protocol\n"); + goto err_misc_deregister; + } + + err = sock_register(&vsock_family_ops); + if (err) { + pr_err("could not register af_vsock (%d) address family: %d\n", + AF_VSOCK, err); + goto err_unregister_proto; + } + + return 0; + +err_unregister_proto: + proto_unregister(&vsock_proto); +err_misc_deregister: + misc_deregister(&vsock_device); + return err; +} + +int vsock_core_init(const struct vsock_transport *t) +{ + int retval = mutex_lock_interruptible(&vsock_register_mutex); + if (retval) + return retval; + + if (transport) { + retval = -EBUSY; + goto out; + } + + transport = t; + retval = __vsock_core_init(); + if (retval) + transport = NULL; + +out: + mutex_unlock(&vsock_register_mutex); + return retval; +} +EXPORT_SYMBOL_GPL(vsock_core_init); + +void vsock_core_exit(void) +{ + mutex_lock(&vsock_register_mutex); + + misc_deregister(&vsock_device); + sock_unregister(AF_VSOCK); + proto_unregister(&vsock_proto); + + /* We do not want the assignment below re-ordered. */ + mb(); + transport = NULL; + + mutex_unlock(&vsock_register_mutex); +} +EXPORT_SYMBOL_GPL(vsock_core_exit); + +MODULE_AUTHOR("VMware, Inc."); +MODULE_DESCRIPTION("VMware Virtual Socket Family"); +MODULE_VERSION(VSOCK_DRIVER_VERSION_STRING); +MODULE_LICENSE("GPL v2"); diff --git a/net/vmw_vsock/af_vsock.h b/net/vmw_vsock/af_vsock.h new file mode 100644 index 000000000000..7d64d3609ec9 --- /dev/null +++ b/net/vmw_vsock/af_vsock.h @@ -0,0 +1,175 @@ +/* + * VMware vSockets Driver + * + * Copyright (C) 2007-2013 VMware, Inc. All rights reserved. + * + * This program is free software; you can redistribute it and/or modify it + * under the terms of the GNU General Public License as published by the Free + * Software Foundation version 2 and no later version. + * + * This program is distributed in the hope that it will be useful, but WITHOUT + * ANY WARRANTY; without even the implied warranty of MERCHANTABILITY or + * FITNESS FOR A PARTICULAR PURPOSE. See the GNU General Public License for + * more details. + */ + +#ifndef __AF_VSOCK_H__ +#define __AF_VSOCK_H__ + +#include <linux/kernel.h> +#include <linux/workqueue.h> +#include <linux/vm_sockets.h> + +#include "vsock_addr.h" + +#define LAST_RESERVED_PORT 1023 + +#define vsock_sk(__sk) ((struct vsock_sock *)__sk) +#define sk_vsock(__vsk) (&(__vsk)->sk) + +struct vsock_sock { + /* sk must be the first member. */ + struct sock sk; + struct sockaddr_vm local_addr; + struct sockaddr_vm remote_addr; + /* Links for the global tables of bound and connected sockets. */ + struct list_head bound_table; + struct list_head connected_table; + /* Accessed without the socket lock held. This means it can never be + * modified outsided of socket create or destruct. + */ + bool trusted; + bool cached_peer_allow_dgram; /* Dgram communication allowed to + * cached peer? + */ + u32 cached_peer; /* Context ID of last dgram destination check. */ + const struct cred *owner; + /* Rest are SOCK_STREAM only. */ + long connect_timeout; + /* Listening socket that this came from. */ + struct sock *listener; + /* Used for pending list and accept queue during connection handshake. + * The listening socket is the head for both lists. Sockets created + * for connection requests are placed in the pending list until they + * are connected, at which point they are put in the accept queue list + * so they can be accepted in accept(). If accept() cannot accept the + * connection, it is marked as rejected so the cleanup function knows + * to clean up the socket. + */ + struct list_head pending_links; + struct list_head accept_queue; + bool rejected; + struct delayed_work dwork; + u32 peer_shutdown; + bool sent_request; + bool ignore_connecting_rst; + + /* Private to transport. */ + void *trans; +}; + +s64 vsock_stream_has_data(struct vsock_sock *vsk); +s64 vsock_stream_has_space(struct vsock_sock *vsk); +void vsock_pending_work(struct work_struct *work); +struct sock *__vsock_create(struct net *net, + struct socket *sock, + struct sock *parent, + gfp_t priority, unsigned short type); + +/**** TRANSPORT ****/ + +struct vsock_transport_recv_notify_data { + u64 data1; /* Transport-defined. */ + u64 data2; /* Transport-defined. */ + bool notify_on_block; +}; + +struct vsock_transport_send_notify_data { + u64 data1; /* Transport-defined. */ + u64 data2; /* Transport-defined. */ +}; + +struct vsock_transport { + /* Initialize/tear-down socket. */ + int (*init)(struct vsock_sock *, struct vsock_sock *); + void (*destruct)(struct vsock_sock *); + void (*release)(struct vsock_sock *); + + /* Connections. */ + int (*connect)(struct vsock_sock *); + + /* DGRAM. */ + int (*dgram_bind)(struct vsock_sock *, struct sockaddr_vm *); + int (*dgram_dequeue)(struct kiocb *kiocb, struct vsock_sock *vsk, + struct msghdr *msg, size_t len, int flags); + int (*dgram_enqueue)(struct vsock_sock *, struct sockaddr_vm *, + struct iovec *, size_t len); + bool (*dgram_allow)(u32 cid, u32 port); + + /* STREAM. */ + /* TODO: stream_bind() */ + ssize_t (*stream_dequeue)(struct vsock_sock *, struct iovec *, + size_t len, int flags); + ssize_t (*stream_enqueue)(struct vsock_sock *, struct iovec *, + size_t len); + s64 (*stream_has_data)(struct vsock_sock *); + s64 (*stream_has_space)(struct vsock_sock *); + u64 (*stream_rcvhiwat)(struct vsock_sock *); + bool (*stream_is_active)(struct vsock_sock *); + bool (*stream_allow)(u32 cid, u32 port); + + /* Notification. */ + int (*notify_poll_in)(struct vsock_sock *, size_t, bool *); + int (*notify_poll_out)(struct vsock_sock *, size_t, bool *); + int (*notify_recv_init)(struct vsock_sock *, size_t, + struct vsock_transport_recv_notify_data *); + int (*notify_recv_pre_block)(struct vsock_sock *, size_t, + struct vsock_transport_recv_notify_data *); + int (*notify_recv_pre_dequeue)(struct vsock_sock *, size_t, + struct vsock_transport_recv_notify_data *); + int (*notify_recv_post_dequeue)(struct vsock_sock *, size_t, + ssize_t, bool, struct vsock_transport_recv_notify_data *); + int (*notify_send_init)(struct vsock_sock *, + struct vsock_transport_send_notify_data *); + int (*notify_send_pre_block)(struct vsock_sock *, + struct vsock_transport_send_notify_data *); + int (*notify_send_pre_enqueue)(struct vsock_sock *, + struct vsock_transport_send_notify_data *); + int (*notify_send_post_enqueue)(struct vsock_sock *, ssize_t, + struct vsock_transport_send_notify_data *); + + /* Shutdown. */ + int (*shutdown)(struct vsock_sock *, int); + + /* Buffer sizes. */ + void (*set_buffer_size)(struct vsock_sock *, u64); + void (*set_min_buffer_size)(struct vsock_sock *, u64); + void (*set_max_buffer_size)(struct vsock_sock *, u64); + u64 (*get_buffer_size)(struct vsock_sock *); + u64 (*get_min_buffer_size)(struct vsock_sock *); + u64 (*get_max_buffer_size)(struct vsock_sock *); + + /* Addressing. */ + u32 (*get_local_cid)(void); +}; + +/**** CORE ****/ + +int vsock_core_init(const struct vsock_transport *t); +void vsock_core_exit(void); + +/**** UTILS ****/ + +void vsock_release_pending(struct sock *pending); +void vsock_add_pending(struct sock *listener, struct sock *pending); +void vsock_remove_pending(struct sock *listener, struct sock *pending); +void vsock_enqueue_accept(struct sock *listener, struct sock *connected); +void vsock_insert_connected(struct vsock_sock *vsk); +void vsock_remove_bound(struct vsock_sock *vsk); +void vsock_remove_connected(struct vsock_sock *vsk); +struct sock *vsock_find_bound_socket(struct sockaddr_vm *addr); +struct sock *vsock_find_connected_socket(struct sockaddr_vm *src, + struct sockaddr_vm *dst); +void vsock_for_each_connected_socket(void (*fn)(struct sock *sk)); + +#endif /* __AF_VSOCK_H__ */ diff --git a/net/vmw_vsock/vmci_transport.c b/net/vmw_vsock/vmci_transport.c new file mode 100644 index 000000000000..e8a87cf37072 --- /dev/null +++ b/net/vmw_vsock/vmci_transport.c @@ -0,0 +1,2157 @@ +/* + * VMware vSockets Driver + * + * Copyright (C) 2007-2013 VMware, Inc. All rights reserved. + * + * This program is free software; you can redistribute it and/or modify it + * under the terms of the GNU General Public License as published by the Free + * Software Foundation version 2 and no later version. + * + * This program is distributed in the hope that it will be useful, but WITHOUT + * ANY WARRANTY; without even the implied warranty of MERCHANTABILITY or + * FITNESS FOR A PARTICULAR PURPOSE. See the GNU General Public License for + * more details. + */ + +#include <linux/types.h> + +#define EXPORT_SYMTAB +#include <linux/bitops.h> +#include <linux/cred.h> +#include <linux/init.h> +#include <linux/io.h> +#include <linux/kernel.h> +#include <linux/kmod.h> +#include <linux/list.h> +#include <linux/miscdevice.h> +#include <linux/module.h> +#include <linux/mutex.h> +#include <linux/net.h> +#include <linux/poll.h> +#include <linux/skbuff.h> +#include <linux/smp.h> +#include <linux/socket.h> +#include <linux/stddef.h> +#include <linux/unistd.h> +#include <linux/wait.h> +#include <linux/workqueue.h> +#include <net/sock.h> + +#include "af_vsock.h" +#include "vmci_transport_notify.h" + +static int vmci_transport_recv_dgram_cb(void *data, struct vmci_datagram *dg); +static int vmci_transport_recv_stream_cb(void *data, struct vmci_datagram *dg); +static void vmci_transport_peer_attach_cb(u32 sub_id, + const struct vmci_event_data *ed, + void *client_data); +static void vmci_transport_peer_detach_cb(u32 sub_id, + const struct vmci_event_data *ed, + void *client_data); +static void vmci_transport_recv_pkt_work(struct work_struct *work); +static int vmci_transport_recv_listen(struct sock *sk, + struct vmci_transport_packet *pkt); +static int vmci_transport_recv_connecting_server( + struct sock *sk, + struct sock *pending, + struct vmci_transport_packet *pkt); +static int vmci_transport_recv_connecting_client( + struct sock *sk, + struct vmci_transport_packet *pkt); +static int vmci_transport_recv_connecting_client_negotiate( + struct sock *sk, + struct vmci_transport_packet *pkt); +static int vmci_transport_recv_connecting_client_invalid( + struct sock *sk, + struct vmci_transport_packet *pkt); +static int vmci_transport_recv_connected(struct sock *sk, + struct vmci_transport_packet *pkt); +static bool vmci_transport_old_proto_override(bool *old_pkt_proto); +static u16 vmci_transport_new_proto_supported_versions(void); +static bool vmci_transport_proto_to_notify_struct(struct sock *sk, u16 *proto, + bool old_pkt_proto); + +struct vmci_transport_recv_pkt_info { + struct work_struct work; + struct sock *sk; + struct vmci_transport_packet pkt; +}; + +static struct vmci_handle vmci_transport_stream_handle = { VMCI_INVALID_ID, + VMCI_INVALID_ID }; +static u32 vmci_transport_qp_resumed_sub_id = VMCI_INVALID_ID; + +static int PROTOCOL_OVERRIDE = -1; + +#define VMCI_TRANSPORT_DEFAULT_QP_SIZE_MIN 128 +#define VMCI_TRANSPORT_DEFAULT_QP_SIZE 262144 +#define VMCI_TRANSPORT_DEFAULT_QP_SIZE_MAX 262144 + +/* The default peer timeout indicates how long we will wait for a peer response + * to a control message. + */ +#define VSOCK_DEFAULT_CONNECT_TIMEOUT (2 * HZ) + +#define SS_LISTEN 255 + +/* Helper function to convert from a VMCI error code to a VSock error code. */ + +static s32 vmci_transport_error_to_vsock_error(s32 vmci_error) +{ + int err; + + switch (vmci_error) { + case VMCI_ERROR_NO_MEM: + err = ENOMEM; + break; + case VMCI_ERROR_DUPLICATE_ENTRY: + case VMCI_ERROR_ALREADY_EXISTS: + err = EADDRINUSE; + break; + case VMCI_ERROR_NO_ACCESS: + err = EPERM; + break; + case VMCI_ERROR_NO_RESOURCES: + err = ENOBUFS; + break; + case VMCI_ERROR_INVALID_RESOURCE: + err = EHOSTUNREACH; + break; + case VMCI_ERROR_INVALID_ARGS: + default: + err = EINVAL; + } + + return err > 0 ? -err : err; +} + +static inline void +vmci_transport_packet_init(struct vmci_transport_packet *pkt, + struct sockaddr_vm *src, + struct sockaddr_vm *dst, + u8 type, + u64 size, + u64 mode, + struct vmci_transport_waiting_info *wait, + u16 proto, + struct vmci_handle handle) +{ + /* We register the stream control handler as an any cid handle so we + * must always send from a source address of VMADDR_CID_ANY + */ + pkt->dg.src = vmci_make_handle(VMADDR_CID_ANY, + VMCI_TRANSPORT_PACKET_RID); + pkt->dg.dst = vmci_make_handle(dst->svm_cid, + VMCI_TRANSPORT_PACKET_RID); + pkt->dg.payload_size = sizeof(*pkt) - sizeof(pkt->dg); + pkt->version = VMCI_TRANSPORT_PACKET_VERSION; + pkt->type = type; + pkt->src_port = src->svm_port; + pkt->dst_port = dst->svm_port; + memset(&pkt->proto, 0, sizeof(pkt->proto)); + memset(&pkt->_reserved2, 0, sizeof(pkt->_reserved2)); + + switch (pkt->type) { + case VMCI_TRANSPORT_PACKET_TYPE_INVALID: + pkt->u.size = 0; + break; + + case VMCI_TRANSPORT_PACKET_TYPE_REQUEST: + case VMCI_TRANSPORT_PACKET_TYPE_NEGOTIATE: + pkt->u.size = size; + break; + + case VMCI_TRANSPORT_PACKET_TYPE_OFFER: + case VMCI_TRANSPORT_PACKET_TYPE_ATTACH: + pkt->u.handle = handle; + break; + + case VMCI_TRANSPORT_PACKET_TYPE_WROTE: + case VMCI_TRANSPORT_PACKET_TYPE_READ: + case VMCI_TRANSPORT_PACKET_TYPE_RST: + pkt->u.size = 0; + break; + + case VMCI_TRANSPORT_PACKET_TYPE_SHUTDOWN: + pkt->u.mode = mode; + break; + + case VMCI_TRANSPORT_PACKET_TYPE_WAITING_READ: + case VMCI_TRANSPORT_PACKET_TYPE_WAITING_WRITE: + memcpy(&pkt->u.wait, wait, sizeof(pkt->u.wait)); + break; + + case VMCI_TRANSPORT_PACKET_TYPE_REQUEST2: + case VMCI_TRANSPORT_PACKET_TYPE_NEGOTIATE2: + pkt->u.size = size; + pkt->proto = proto; + break; + } +} + +static inline void +vmci_transport_packet_get_addresses(struct vmci_transport_packet *pkt, + struct sockaddr_vm *local, + struct sockaddr_vm *remote) +{ + vsock_addr_init(local, pkt->dg.dst.context, pkt->dst_port); + vsock_addr_init(remote, pkt->dg.src.context, pkt->src_port); +} + +static int +__vmci_transport_send_control_pkt(struct vmci_transport_packet *pkt, + struct sockaddr_vm *src, + struct sockaddr_vm *dst, + enum vmci_transport_packet_type type, + u64 size, + u64 mode, + struct vmci_transport_waiting_info *wait, + u16 proto, + struct vmci_handle handle, + bool convert_error) +{ + int err; + + vmci_transport_packet_init(pkt, src, dst, type, size, mode, wait, + proto, handle); + err = vmci_datagram_send(&pkt->dg); + if (convert_error && (err < 0)) + return vmci_transport_error_to_vsock_error(err); + + return err; +} + +static int +vmci_transport_reply_control_pkt_fast(struct vmci_transport_packet *pkt, + enum vmci_transport_packet_type type, + u64 size, + u64 mode, + struct vmci_transport_waiting_info *wait, + struct vmci_handle handle) +{ + struct vmci_transport_packet reply; + struct sockaddr_vm src, dst; + + if (pkt->type == VMCI_TRANSPORT_PACKET_TYPE_RST) { + return 0; + } else { + vmci_transport_packet_get_addresses(pkt, &src, &dst); + return __vmci_transport_send_control_pkt(&reply, &src, &dst, + type, + size, mode, wait, + VSOCK_PROTO_INVALID, + handle, true); + } +} + +static int +vmci_transport_send_control_pkt_bh(struct sockaddr_vm *src, + struct sockaddr_vm *dst, + enum vmci_transport_packet_type type, + u64 size, + u64 mode, + struct vmci_transport_waiting_info *wait, + struct vmci_handle handle) +{ + /* Note that it is safe to use a single packet across all CPUs since + * two tasklets of the same type are guaranteed to not ever run + * simultaneously. If that ever changes, or VMCI stops using tasklets, + * we can use per-cpu packets. + */ + static struct vmci_transport_packet pkt; + + return __vmci_transport_send_control_pkt(&pkt, src, dst, type, + size, mode, wait, + VSOCK_PROTO_INVALID, handle, + false); +} + +static int +vmci_transport_send_control_pkt(struct sock *sk, + enum vmci_transport_packet_type type, + u64 size, + u64 mode, + struct vmci_transport_waiting_info *wait, + u16 proto, + struct vmci_handle handle) +{ + struct vmci_transport_packet *pkt; + struct vsock_sock *vsk; + int err; + + vsk = vsock_sk(sk); + + if (!vsock_addr_bound(&vsk->local_addr)) + return -EINVAL; + + if (!vsock_addr_bound(&vsk->remote_addr)) + return -EINVAL; + + pkt = kmalloc(sizeof(*pkt), GFP_KERNEL); + if (!pkt) + return -ENOMEM; + + err = __vmci_transport_send_control_pkt(pkt, &vsk->local_addr, + &vsk->remote_addr, type, size, + mode, wait, proto, handle, + true); + kfree(pkt); + + return err; +} + +static int vmci_transport_send_reset_bh(struct sockaddr_vm *dst, + struct sockaddr_vm *src, + struct vmci_transport_packet *pkt) +{ + if (pkt->type == VMCI_TRANSPORT_PACKET_TYPE_RST) + return 0; + return vmci_transport_send_control_pkt_bh( + dst, src, + VMCI_TRANSPORT_PACKET_TYPE_RST, 0, + 0, NULL, VMCI_INVALID_HANDLE); +} + +static int vmci_transport_send_reset(struct sock *sk, + struct vmci_transport_packet *pkt) +{ + if (pkt->type == VMCI_TRANSPORT_PACKET_TYPE_RST) + return 0; + return vmci_transport_send_control_pkt(sk, + VMCI_TRANSPORT_PACKET_TYPE_RST, + 0, 0, NULL, VSOCK_PROTO_INVALID, + VMCI_INVALID_HANDLE); +} + +static int vmci_transport_send_negotiate(struct sock *sk, size_t size) +{ + return vmci_transport_send_control_pkt( + sk, + VMCI_TRANSPORT_PACKET_TYPE_NEGOTIATE, + size, 0, NULL, + VSOCK_PROTO_INVALID, + VMCI_INVALID_HANDLE); +} + +static int vmci_transport_send_negotiate2(struct sock *sk, size_t size, + u16 version) +{ + return vmci_transport_send_control_pkt( + sk, + VMCI_TRANSPORT_PACKET_TYPE_NEGOTIATE2, + size, 0, NULL, version, + VMCI_INVALID_HANDLE); +} + +static int vmci_transport_send_qp_offer(struct sock *sk, + struct vmci_handle handle) +{ + return vmci_transport_send_control_pkt( + sk, VMCI_TRANSPORT_PACKET_TYPE_OFFER, 0, + 0, NULL, + VSOCK_PROTO_INVALID, handle); +} + +static int vmci_transport_send_attach(struct sock *sk, + struct vmci_handle handle) +{ + return vmci_transport_send_control_pkt( + sk, VMCI_TRANSPORT_PACKET_TYPE_ATTACH, + 0, 0, NULL, VSOCK_PROTO_INVALID, + handle); +} + +static int vmci_transport_reply_reset(struct vmci_transport_packet *pkt) +{ + return vmci_transport_reply_control_pkt_fast( + pkt, + VMCI_TRANSPORT_PACKET_TYPE_RST, + 0, 0, NULL, + VMCI_INVALID_HANDLE); +} + +static int vmci_transport_send_invalid_bh(struct sockaddr_vm *dst, + struct sockaddr_vm *src) +{ + return vmci_transport_send_control_pkt_bh( + dst, src, + VMCI_TRANSPORT_PACKET_TYPE_INVALID, + 0, 0, NULL, VMCI_INVALID_HANDLE); +} + +int vmci_transport_send_wrote_bh(struct sockaddr_vm *dst, + struct sockaddr_vm *src) +{ + return vmci_transport_send_control_pkt_bh( + dst, src, + VMCI_TRANSPORT_PACKET_TYPE_WROTE, 0, + 0, NULL, VMCI_INVALID_HANDLE); +} + +int vmci_transport_send_read_bh(struct sockaddr_vm *dst, + struct sockaddr_vm *src) +{ + return vmci_transport_send_control_pkt_bh( + dst, src, + VMCI_TRANSPORT_PACKET_TYPE_READ, 0, + 0, NULL, VMCI_INVALID_HANDLE); +} + +int vmci_transport_send_wrote(struct sock *sk) +{ + return vmci_transport_send_control_pkt( + sk, VMCI_TRANSPORT_PACKET_TYPE_WROTE, 0, + 0, NULL, VSOCK_PROTO_INVALID, + VMCI_INVALID_HANDLE); +} + +int vmci_transport_send_read(struct sock *sk) +{ + return vmci_transport_send_control_pkt( + sk, VMCI_TRANSPORT_PACKET_TYPE_READ, 0, + 0, NULL, VSOCK_PROTO_INVALID, + VMCI_INVALID_HANDLE); +} + +int vmci_transport_send_waiting_write(struct sock *sk, + struct vmci_transport_waiting_info *wait) +{ + return vmci_transport_send_control_pkt( + sk, VMCI_TRANSPORT_PACKET_TYPE_WAITING_WRITE, + 0, 0, wait, VSOCK_PROTO_INVALID, + VMCI_INVALID_HANDLE); +} + +int vmci_transport_send_waiting_read(struct sock *sk, + struct vmci_transport_waiting_info *wait) +{ + return vmci_transport_send_control_pkt( + sk, VMCI_TRANSPORT_PACKET_TYPE_WAITING_READ, + 0, 0, wait, VSOCK_PROTO_INVALID, + VMCI_INVALID_HANDLE); +} + +static int vmci_transport_shutdown(struct vsock_sock *vsk, int mode) +{ + return vmci_transport_send_control_pkt( + &vsk->sk, + VMCI_TRANSPORT_PACKET_TYPE_SHUTDOWN, + 0, mode, NULL, + VSOCK_PROTO_INVALID, + VMCI_INVALID_HANDLE); +} + +static int vmci_transport_send_conn_request(struct sock *sk, size_t size) +{ + return vmci_transport_send_control_pkt(sk, + VMCI_TRANSPORT_PACKET_TYPE_REQUEST, + size, 0, NULL, + VSOCK_PROTO_INVALID, + VMCI_INVALID_HANDLE); +} + +static int vmci_transport_send_conn_request2(struct sock *sk, size_t size, + u16 version) +{ + return vmci_transport_send_control_pkt( + sk, VMCI_TRANSPORT_PACKET_TYPE_REQUEST2, + size, 0, NULL, version, + VMCI_INVALID_HANDLE); +} + +static struct sock *vmci_transport_get_pending( + struct sock *listener, + struct vmci_transport_packet *pkt) +{ + struct vsock_sock *vlistener; + struct vsock_sock *vpending; + struct sock *pending; + + vlistener = vsock_sk(listener); + + list_for_each_entry(vpending, &vlistener->pending_links, + pending_links) { + struct sockaddr_vm src; + struct sockaddr_vm dst; + + vsock_addr_init(&src, pkt->dg.src.context, pkt->src_port); + vsock_addr_init(&dst, pkt->dg.dst.context, pkt->dst_port); + + if (vsock_addr_equals_addr(&src, &vpending->remote_addr) && + vsock_addr_equals_addr(&dst, &vpending->local_addr)) { + pending = sk_vsock(vpending); + sock_hold(pending); + goto found; + } + } + + pending = NULL; +found: + return pending; + +} + +static void vmci_transport_release_pending(struct sock *pending) +{ + sock_put(pending); +} + +/* We allow two kinds of sockets to communicate with a restricted VM: 1) + * trusted sockets 2) sockets from applications running as the same user as the + * VM (this is only true for the host side and only when using hosted products) + */ + +static bool vmci_transport_is_trusted(struct vsock_sock *vsock, u32 peer_cid) +{ + return vsock->trusted || + vmci_is_context_owner(peer_cid, vsock->owner->uid); +} + +/* We allow sending datagrams to and receiving datagrams from a restricted VM + * only if it is trusted as described in vmci_transport_is_trusted. + */ + +static bool vmci_transport_allow_dgram(struct vsock_sock *vsock, u32 peer_cid) +{ + if (vsock->cached_peer != peer_cid) { + vsock->cached_peer = peer_cid; + if (!vmci_transport_is_trusted(vsock, peer_cid) && + (vmci_context_get_priv_flags(peer_cid) & + VMCI_PRIVILEGE_FLAG_RESTRICTED)) { + vsock->cached_peer_allow_dgram = false; + } else { + vsock->cached_peer_allow_dgram = true; + } + } + + return vsock->cached_peer_allow_dgram; +} + +static int +vmci_transport_queue_pair_alloc(struct vmci_qp **qpair, + struct vmci_handle *handle, + u64 produce_size, + u64 consume_size, + u32 peer, u32 flags, bool trusted) +{ + int err = 0; + + if (trusted) { + /* Try to allocate our queue pair as trusted. This will only + * work if vsock is running in the host. + */ + + err = vmci_qpair_alloc(qpair, handle, produce_size, + consume_size, + peer, flags, + VMCI_PRIVILEGE_FLAG_TRUSTED); + if (err != VMCI_ERROR_NO_ACCESS) + goto out; + + } + + err = vmci_qpair_alloc(qpair, handle, produce_size, consume_size, + peer, flags, VMCI_NO_PRIVILEGE_FLAGS); +out: + if (err < 0) { + pr_err("Could not attach to queue pair with %d\n", + err); + err = vmci_transport_error_to_vsock_error(err); + } + + return err; +} + +static int +vmci_transport_datagram_create_hnd(u32 resource_id, + u32 flags, + vmci_datagram_recv_cb recv_cb, + void *client_data, + struct vmci_handle *out_handle) +{ + int err = 0; + + /* Try to allocate our datagram handler as trusted. This will only work + * if vsock is running in the host. + */ + + err = vmci_datagram_create_handle_priv(resource_id, flags, + VMCI_PRIVILEGE_FLAG_TRUSTED, + recv_cb, + client_data, out_handle); + + if (err == VMCI_ERROR_NO_ACCESS) + err = vmci_datagram_create_handle(resource_id, flags, + recv_cb, client_data, + out_handle); + + return err; +} + +/* This is invoked as part of a tasklet that's scheduled when the VMCI + * interrupt fires. This is run in bottom-half context and if it ever needs to + * sleep it should defer that work to a work queue. + */ + +static int vmci_transport_recv_dgram_cb(void *data, struct vmci_datagram *dg) +{ + struct sock *sk; + size_t size; + struct sk_buff *skb; + struct vsock_sock *vsk; + + sk = (struct sock *)data; + + /* This handler is privileged when this module is running on the host. + * We will get datagrams from all endpoints (even VMs that are in a + * restricted context). If we get one from a restricted context then + * the destination socket must be trusted. + * + * NOTE: We access the socket struct without holding the lock here. + * This is ok because the field we are interested is never modified + * outside of the create and destruct socket functions. + */ + vsk = vsock_sk(sk); + if (!vmci_transport_allow_dgram(vsk, dg->src.context)) + return VMCI_ERROR_NO_ACCESS; + + size = VMCI_DG_SIZE(dg); + + /* Attach the packet to the socket's receive queue as an sk_buff. */ + skb = alloc_skb(size, GFP_ATOMIC); + if (skb) { + /* sk_receive_skb() will do a sock_put(), so hold here. */ + sock_hold(sk); + skb_put(skb, size); + memcpy(skb->data, dg, size); + sk_receive_skb(sk, skb, 0); + } + + return VMCI_SUCCESS; +} + +static bool vmci_transport_stream_allow(u32 cid, u32 port) +{ + static const u32 non_socket_contexts[] = { + VMADDR_CID_HYPERVISOR, + VMADDR_CID_RESERVED, + }; + int i; + + BUILD_BUG_ON(sizeof(cid) != sizeof(*non_socket_contexts)); + + for (i = 0; i < ARRAY_SIZE(non_socket_contexts); i++) { + if (cid == non_socket_contexts[i]) + return false; + } + + return true; +} + +/* This is invoked as part of a tasklet that's scheduled when the VMCI + * interrupt fires. This is run in bottom-half context but it defers most of + * its work to the packet handling work queue. + */ + +static int vmci_transport_recv_stream_cb(void *data, struct vmci_datagram *dg) +{ + struct sock *sk; + struct sockaddr_vm dst; + struct sockaddr_vm src; + struct vmci_transport_packet *pkt; + struct vsock_sock *vsk; + bool bh_process_pkt; + int err; + + sk = NULL; + err = VMCI_SUCCESS; + bh_process_pkt = false; + + /* Ignore incoming packets from contexts without sockets, or resources + * that aren't vsock implementations. + */ + + if (!vmci_transport_stream_allow(dg->src.context, -1) + || VMCI_TRANSPORT_PACKET_RID != dg->src.resource) + return VMCI_ERROR_NO_ACCESS; + + if (VMCI_DG_SIZE(dg) < sizeof(*pkt)) + /* Drop datagrams that do not contain full VSock packets. */ + return VMCI_ERROR_INVALID_ARGS; + + pkt = (struct vmci_transport_packet *)dg; + + /* Find the socket that should handle this packet. First we look for a + * connected socket and if there is none we look for a socket bound to + * the destintation address. + */ + vsock_addr_init(&src, pkt->dg.src.context, pkt->src_port); + vsock_addr_init(&dst, pkt->dg.dst.context, pkt->dst_port); + + sk = vsock_find_connected_socket(&src, &dst); + if (!sk) { + sk = vsock_find_bound_socket(&dst); + if (!sk) { + /* We could not find a socket for this specified + * address. If this packet is a RST, we just drop it. + * If it is another packet, we send a RST. Note that + * we do not send a RST reply to RSTs so that we do not + * continually send RSTs between two endpoints. + * + * Note that since this is a reply, dst is src and src + * is dst. + */ + if (vmci_transport_send_reset_bh(&dst, &src, pkt) < 0) + pr_err("unable to send reset\n"); + + err = VMCI_ERROR_NOT_FOUND; + goto out; + } + } + + /* If the received packet type is beyond all types known to this + * implementation, reply with an invalid message. Hopefully this will + * help when implementing backwards compatibility in the future. + */ + if (pkt->type >= VMCI_TRANSPORT_PACKET_TYPE_MAX) { + vmci_transport_send_invalid_bh(&dst, &src); + err = VMCI_ERROR_INVALID_ARGS; + goto out; + } + + /* This handler is privileged when this module is running on the host. + * We will get datagram connect requests from all endpoints (even VMs + * that are in a restricted context). If we get one from a restricted + * context then the destination socket must be trusted. + * + * NOTE: We access the socket struct without holding the lock here. + * This is ok because the field we are interested is never modified + * outside of the create and destruct socket functions. + */ + vsk = vsock_sk(sk); + if (!vmci_transport_allow_dgram(vsk, pkt->dg.src.context)) { + err = VMCI_ERROR_NO_ACCESS; + goto out; + } + + /* We do most everything in a work queue, but let's fast path the + * notification of reads and writes to help data transfer performance. + * We can only do this if there is no process context code executing + * for this socket since that may change the state. + */ + bh_lock_sock(sk); + + if (!sock_owned_by_user(sk) && sk->sk_state == SS_CONNECTED) + vmci_trans(vsk)->notify_ops->handle_notify_pkt( + sk, pkt, true, &dst, &src, + &bh_process_pkt); + + bh_unlock_sock(sk); + + if (!bh_process_pkt) { + struct vmci_transport_recv_pkt_info *recv_pkt_info; + + recv_pkt_info = kmalloc(sizeof(*recv_pkt_info), GFP_ATOMIC); + if (!recv_pkt_info) { + if (vmci_transport_send_reset_bh(&dst, &src, pkt) < 0) + pr_err("unable to send reset\n"); + + err = VMCI_ERROR_NO_MEM; + goto out; + } + + recv_pkt_info->sk = sk; + memcpy(&recv_pkt_info->pkt, pkt, sizeof(recv_pkt_info->pkt)); + INIT_WORK(&recv_pkt_info->work, vmci_transport_recv_pkt_work); + + schedule_work(&recv_pkt_info->work); + /* Clear sk so that the reference count incremented by one of + * the Find functions above is not decremented below. We need + * that reference count for the packet handler we've scheduled + * to run. + */ + sk = NULL; + } + +out: + if (sk) + sock_put(sk); + + return err; +} + +static void vmci_transport_peer_attach_cb(u32 sub_id, + const struct vmci_event_data *e_data, + void *client_data) +{ + struct sock *sk = client_data; + const struct vmci_event_payload_qp *e_payload; + struct vsock_sock *vsk; + + e_payload = vmci_event_data_const_payload(e_data); + + vsk = vsock_sk(sk); + + /* We don't ask for delayed CBs when we subscribe to this event (we + * pass 0 as flags to vmci_event_subscribe()). VMCI makes no + * guarantees in that case about what context we might be running in, + * so it could be BH or process, blockable or non-blockable. So we + * need to account for all possible contexts here. + */ + local_bh_disable(); + bh_lock_sock(sk); + + /* XXX This is lame, we should provide a way to lookup sockets by + * qp_handle. + */ + if (vmci_handle_is_equal(vmci_trans(vsk)->qp_handle, + e_payload->handle)) { + /* XXX This doesn't do anything, but in the future we may want + * to set a flag here to verify the attach really did occur and + * we weren't just sent a datagram claiming it was. + */ + goto out; + } + +out: + bh_unlock_sock(sk); + local_bh_enable(); +} + +static void vmci_transport_handle_detach(struct sock *sk) +{ + struct vsock_sock *vsk; + + vsk = vsock_sk(sk); + if (!vmci_handle_is_invalid(vmci_trans(vsk)->qp_handle)) { + sock_set_flag(sk, SOCK_DONE); + + /* On a detach the peer will not be sending or receiving + * anymore. + */ + vsk->peer_shutdown = SHUTDOWN_MASK; + + /* We should not be sending anymore since the peer won't be + * there to receive, but we can still receive if there is data + * left in our consume queue. + */ + if (vsock_stream_has_data(vsk) <= 0) { + if (sk->sk_state == SS_CONNECTING) { + /* The peer may detach from a queue pair while + * we are still in the connecting state, i.e., + * if the peer VM is killed after attaching to + * a queue pair, but before we complete the + * handshake. In that case, we treat the detach + * event like a reset. + */ + + sk->sk_state = SS_UNCONNECTED; + sk->sk_err = ECONNRESET; + sk->sk_error_report(sk); + return; + } + sk->sk_state = SS_UNCONNECTED; + } + sk->sk_state_change(sk); + } +} + +static void vmci_transport_peer_detach_cb(u32 sub_id, + const struct vmci_event_data *e_data, + void *client_data) +{ + struct sock *sk = client_data; + const struct vmci_event_payload_qp *e_payload; + struct vsock_sock *vsk; + + e_payload = vmci_event_data_const_payload(e_data); + vsk = vsock_sk(sk); + if (vmci_handle_is_invalid(e_payload->handle)) + return; + + /* Same rules for locking as for peer_attach_cb(). */ + local_bh_disable(); + bh_lock_sock(sk); + + /* XXX This is lame, we should provide a way to lookup sockets by + * qp_handle. + */ + if (vmci_handle_is_equal(vmci_trans(vsk)->qp_handle, + e_payload->handle)) + vmci_transport_handle_detach(sk); + + bh_unlock_sock(sk); + local_bh_enable(); +} + +static void vmci_transport_qp_resumed_cb(u32 sub_id, + const struct vmci_event_data *e_data, + void *client_data) +{ + vsock_for_each_connected_socket(vmci_transport_handle_detach); +} + +static void vmci_transport_recv_pkt_work(struct work_struct *work) +{ + struct vmci_transport_recv_pkt_info *recv_pkt_info; + struct vmci_transport_packet *pkt; + struct sock *sk; + + recv_pkt_info = + container_of(work, struct vmci_transport_recv_pkt_info, work); + sk = recv_pkt_info->sk; + pkt = &recv_pkt_info->pkt; + + lock_sock(sk); + + switch (sk->sk_state) { + case SS_LISTEN: + vmci_transport_recv_listen(sk, pkt); + break; + case SS_CONNECTING: + /* Processing of pending connections for servers goes through + * the listening socket, so see vmci_transport_recv_listen() + * for that path. + */ + vmci_transport_recv_connecting_client(sk, pkt); + break; + case SS_CONNECTED: + vmci_transport_recv_connected(sk, pkt); + break; + default: + /* Because this function does not run in the same context as + * vmci_transport_recv_stream_cb it is possible that the + * socket has closed. We need to let the other side know or it + * could be sitting in a connect and hang forever. Send a + * reset to prevent that. + */ + vmci_transport_send_reset(sk, pkt); + goto out; + } + +out: + release_sock(sk); + kfree(recv_pkt_info); + /* Release reference obtained in the stream callback when we fetched + * this socket out of the bound or connected list. + */ + sock_put(sk); +} + +static int vmci_transport_recv_listen(struct sock *sk, + struct vmci_transport_packet *pkt) +{ + struct sock *pending; + struct vsock_sock *vpending; + int err; + u64 qp_size; + bool old_request = false; + bool old_pkt_proto = false; + + err = 0; + + /* Because we are in the listen state, we could be receiving a packet + * for ourself or any previous connection requests that we received. + * If it's the latter, we try to find a socket in our list of pending + * connections and, if we do, call the appropriate handler for the + * state that that socket is in. Otherwise we try to service the + * connection request. + */ + pending = vmci_transport_get_pending(sk, pkt); + if (pending) { + lock_sock(pending); + switch (pending->sk_state) { + case SS_CONNECTING: + err = vmci_transport_recv_connecting_server(sk, + pending, + pkt); + break; + default: + vmci_transport_send_reset(pending, pkt); + err = -EINVAL; + } + + if (err < 0) + vsock_remove_pending(sk, pending); + + release_sock(pending); + vmci_transport_release_pending(pending); + + return err; + } + + /* The listen state only accepts connection requests. Reply with a + * reset unless we received a reset. + */ + + if (!(pkt->type == VMCI_TRANSPORT_PACKET_TYPE_REQUEST || + pkt->type == VMCI_TRANSPORT_PACKET_TYPE_REQUEST2)) { + vmci_transport_reply_reset(pkt); + return -EINVAL; + } + + if (pkt->u.size == 0) { + vmci_transport_reply_reset(pkt); + return -EINVAL; + } + + /* If this socket can't accommodate this connection request, we send a + * reset. Otherwise we create and initialize a child socket and reply + * with a connection negotiation. + */ + if (sk->sk_ack_backlog >= sk->sk_max_ack_backlog) { + vmci_transport_reply_reset(pkt); + return -ECONNREFUSED; + } + + pending = __vsock_create(sock_net(sk), NULL, sk, GFP_KERNEL, + sk->sk_type); + if (!pending) { + vmci_transport_send_reset(sk, pkt); + return -ENOMEM; + } + + vpending = vsock_sk(pending); + + vsock_addr_init(&vpending->local_addr, pkt->dg.dst.context, + pkt->dst_port); + vsock_addr_init(&vpending->remote_addr, pkt->dg.src.context, + pkt->src_port); + + /* If the proposed size fits within our min/max, accept it. Otherwise + * propose our own size. + */ + if (pkt->u.size >= vmci_trans(vpending)->queue_pair_min_size && + pkt->u.size <= vmci_trans(vpending)->queue_pair_max_size) { + qp_size = pkt->u.size; + } else { + qp_size = vmci_trans(vpending)->queue_pair_size; + } + + /* Figure out if we are using old or new requests based on the + * overrides pkt types sent by our peer. + */ + if (vmci_transport_old_proto_override(&old_pkt_proto)) { + old_request = old_pkt_proto; + } else { + if (pkt->type == VMCI_TRANSPORT_PACKET_TYPE_REQUEST) + old_request = true; + else if (pkt->type == VMCI_TRANSPORT_PACKET_TYPE_REQUEST2) + old_request = false; + + } + + if (old_request) { + /* Handle a REQUEST (or override) */ + u16 version = VSOCK_PROTO_INVALID; + if (vmci_transport_proto_to_notify_struct( + pending, &version, true)) + err = vmci_transport_send_negotiate(pending, qp_size); + else + err = -EINVAL; + + } else { + /* Handle a REQUEST2 (or override) */ + int proto_int = pkt->proto; + int pos; + u16 active_proto_version = 0; + + /* The list of possible protocols is the intersection of all + * protocols the client supports ... plus all the protocols we + * support. + */ + proto_int &= vmci_transport_new_proto_supported_versions(); + + /* We choose the highest possible protocol version and use that + * one. + */ + pos = fls(proto_int); + if (pos) { + active_proto_version = (1 << (pos - 1)); + if (vmci_transport_proto_to_notify_struct( + pending, &active_proto_version, false)) + err = vmci_transport_send_negotiate2(pending, + qp_size, + active_proto_version); + else + err = -EINVAL; + + } else { + err = -EINVAL; + } + } + + if (err < 0) { + vmci_transport_send_reset(sk, pkt); + sock_put(pending); + err = vmci_transport_error_to_vsock_error(err); + goto out; + } + + vsock_add_pending(sk, pending); + sk->sk_ack_backlog++; + + pending->sk_state = SS_CONNECTING; + vmci_trans(vpending)->produce_size = + vmci_trans(vpending)->consume_size = qp_size; + vmci_trans(vpending)->queue_pair_size = qp_size; + + vmci_trans(vpending)->notify_ops->process_request(pending); + + /* We might never receive another message for this socket and it's not + * connected to any process, so we have to ensure it gets cleaned up + * ourself. Our delayed work function will take care of that. Note + * that we do not ever cancel this function since we have few + * guarantees about its state when calling cancel_delayed_work(). + * Instead we hold a reference on the socket for that function and make + * it capable of handling cases where it needs to do nothing but + * release that reference. + */ + vpending->listener = sk; + sock_hold(sk); + sock_hold(pending); + INIT_DELAYED_WORK(&vpending->dwork, vsock_pending_work); + schedule_delayed_work(&vpending->dwork, HZ); + +out: + return err; +} + +static int +vmci_transport_recv_connecting_server(struct sock *listener, + struct sock *pending, + struct vmci_transport_packet *pkt) +{ + struct vsock_sock *vpending; + struct vmci_handle handle; + struct vmci_qp *qpair; + bool is_local; + u32 flags; + u32 detach_sub_id; + int err; + int skerr; + + vpending = vsock_sk(pending); + detach_sub_id = VMCI_INVALID_ID; + + switch (pkt->type) { + case VMCI_TRANSPORT_PACKET_TYPE_OFFER: + if (vmci_handle_is_invalid(pkt->u.handle)) { + vmci_transport_send_reset(pending, pkt); + skerr = EPROTO; + err = -EINVAL; + goto destroy; + } + break; + default: + /* Close and cleanup the connection. */ + vmci_transport_send_reset(pending, pkt); + skerr = EPROTO; + err = pkt->type == VMCI_TRANSPORT_PACKET_TYPE_RST ? 0 : -EINVAL; + goto destroy; + } + + /* In order to complete the connection we need to attach to the offered + * queue pair and send an attach notification. We also subscribe to the + * detach event so we know when our peer goes away, and we do that + * before attaching so we don't miss an event. If all this succeeds, + * we update our state and wakeup anything waiting in accept() for a + * connection. + */ + + /* We don't care about attach since we ensure the other side has + * attached by specifying the ATTACH_ONLY flag below. + */ + err = vmci_event_subscribe(VMCI_EVENT_QP_PEER_DETACH, + vmci_transport_peer_detach_cb, + pending, &detach_sub_id); + if (err < VMCI_SUCCESS) { + vmci_transport_send_reset(pending, pkt); + err = vmci_transport_error_to_vsock_error(err); + skerr = -err; + goto destroy; + } + + vmci_trans(vpending)->detach_sub_id = detach_sub_id; + + /* Now attach to the queue pair the client created. */ + handle = pkt->u.handle; + + /* vpending->local_addr always has a context id so we do not need to + * worry about VMADDR_CID_ANY in this case. + */ + is_local = + vpending->remote_addr.svm_cid == vpending->local_addr.svm_cid; + flags = VMCI_QPFLAG_ATTACH_ONLY; + flags |= is_local ? VMCI_QPFLAG_LOCAL : 0; + + err = vmci_transport_queue_pair_alloc( + &qpair, + &handle, + vmci_trans(vpending)->produce_size, + vmci_trans(vpending)->consume_size, + pkt->dg.src.context, + flags, + vmci_transport_is_trusted( + vpending, + vpending->remote_addr.svm_cid)); + if (err < 0) { + vmci_transport_send_reset(pending, pkt); + skerr = -err; + goto destroy; + } + + vmci_trans(vpending)->qp_handle = handle; + vmci_trans(vpending)->qpair = qpair; + + /* When we send the attach message, we must be ready to handle incoming + * control messages on the newly connected socket. So we move the + * pending socket to the connected state before sending the attach + * message. Otherwise, an incoming packet triggered by the attach being + * received by the peer may be processed concurrently with what happens + * below after sending the attach message, and that incoming packet + * will find the listening socket instead of the (currently) pending + * socket. Note that enqueueing the socket increments the reference + * count, so even if a reset comes before the connection is accepted, + * the socket will be valid until it is removed from the queue. + * + * If we fail sending the attach below, we remove the socket from the + * connected list and move the socket to SS_UNCONNECTED before + * releasing the lock, so a pending slow path processing of an incoming + * packet will not see the socket in the connected state in that case. + */ + pending->sk_state = SS_CONNECTED; + + vsock_insert_connected(vpending); + + /* Notify our peer of our attach. */ + err = vmci_transport_send_attach(pending, handle); + if (err < 0) { + vsock_remove_connected(vpending); + pr_err("Could not send attach\n"); + vmci_transport_send_reset(pending, pkt); + err = vmci_transport_error_to_vsock_error(err); + skerr = -err; + goto destroy; + } + + /* We have a connection. Move the now connected socket from the + * listener's pending list to the accept queue so callers of accept() + * can find it. + */ + vsock_remove_pending(listener, pending); + vsock_enqueue_accept(listener, pending); + + /* Callers of accept() will be be waiting on the listening socket, not + * the pending socket. + */ + listener->sk_state_change(listener); + + return 0; + +destroy: + pending->sk_err = skerr; + pending->sk_state = SS_UNCONNECTED; + /* As long as we drop our reference, all necessary cleanup will handle + * when the cleanup function drops its reference and our destruct + * implementation is called. Note that since the listen handler will + * remove pending from the pending list upon our failure, the cleanup + * function won't drop the additional reference, which is why we do it + * here. + */ + sock_put(pending); + + return err; +} + +static int +vmci_transport_recv_connecting_client(struct sock *sk, + struct vmci_transport_packet *pkt) +{ + struct vsock_sock *vsk; + int err; + int skerr; + + vsk = vsock_sk(sk); + + switch (pkt->type) { + case VMCI_TRANSPORT_PACKET_TYPE_ATTACH: + if (vmci_handle_is_invalid(pkt->u.handle) || + !vmci_handle_is_equal(pkt->u.handle, + vmci_trans(vsk)->qp_handle)) { + skerr = EPROTO; + err = -EINVAL; + goto destroy; + } + + /* Signify the socket is connected and wakeup the waiter in + * connect(). Also place the socket in the connected table for + * accounting (it can already be found since it's in the bound + * table). + */ + sk->sk_state = SS_CONNECTED; + sk->sk_socket->state = SS_CONNECTED; + vsock_insert_connected(vsk); + sk->sk_state_change(sk); + + break; + case VMCI_TRANSPORT_PACKET_TYPE_NEGOTIATE: + case VMCI_TRANSPORT_PACKET_TYPE_NEGOTIATE2: + if (pkt->u.size == 0 + || pkt->dg.src.context != vsk->remote_addr.svm_cid + || pkt->src_port != vsk->remote_addr.svm_port + || !vmci_handle_is_invalid(vmci_trans(vsk)->qp_handle) + || vmci_trans(vsk)->qpair + || vmci_trans(vsk)->produce_size != 0 + || vmci_trans(vsk)->consume_size != 0 + || vmci_trans(vsk)->attach_sub_id != VMCI_INVALID_ID + || vmci_trans(vsk)->detach_sub_id != VMCI_INVALID_ID) { + skerr = EPROTO; + err = -EINVAL; + + goto destroy; + } + + err = vmci_transport_recv_connecting_client_negotiate(sk, pkt); + if (err) { + skerr = -err; + goto destroy; + } + + break; + case VMCI_TRANSPORT_PACKET_TYPE_INVALID: + err = vmci_transport_recv_connecting_client_invalid(sk, pkt); + if (err) { + skerr = -err; + goto destroy; + } + + break; + case VMCI_TRANSPORT_PACKET_TYPE_RST: + /* Older versions of the linux code (WS 6.5 / ESX 4.0) used to + * continue processing here after they sent an INVALID packet. + * This meant that we got a RST after the INVALID. We ignore a + * RST after an INVALID. The common code doesn't send the RST + * ... so we can hang if an old version of the common code + * fails between getting a REQUEST and sending an OFFER back. + * Not much we can do about it... except hope that it doesn't + * happen. + */ + if (vsk->ignore_connecting_rst) { + vsk->ignore_connecting_rst = false; + } else { + skerr = ECONNRESET; + err = 0; + goto destroy; + } + + break; + default: + /* Close and cleanup the connection. */ + skerr = EPROTO; + err = -EINVAL; + goto destroy; + } + + return 0; + +destroy: + vmci_transport_send_reset(sk, pkt); + + sk->sk_state = SS_UNCONNECTED; + sk->sk_err = skerr; + sk->sk_error_report(sk); + return err; +} + +static int vmci_transport_recv_connecting_client_negotiate( + struct sock *sk, + struct vmci_transport_packet *pkt) +{ + int err; + struct vsock_sock *vsk; + struct vmci_handle handle; + struct vmci_qp *qpair; + u32 attach_sub_id; + u32 detach_sub_id; + bool is_local; + u32 flags; + bool old_proto = true; + bool old_pkt_proto; + u16 version; + + vsk = vsock_sk(sk); + handle = VMCI_INVALID_HANDLE; + attach_sub_id = VMCI_INVALID_ID; + detach_sub_id = VMCI_INVALID_ID; + + /* If we have gotten here then we should be past the point where old + * linux vsock could have sent the bogus rst. + */ + vsk->sent_request = false; + vsk->ignore_connecting_rst = false; + + /* Verify that we're OK with the proposed queue pair size */ + if (pkt->u.size < vmci_trans(vsk)->queue_pair_min_size || + pkt->u.size > vmci_trans(vsk)->queue_pair_max_size) { + err = -EINVAL; + goto destroy; + } + + /* At this point we know the CID the peer is using to talk to us. */ + + if (vsk->local_addr.svm_cid == VMADDR_CID_ANY) + vsk->local_addr.svm_cid = pkt->dg.dst.context; + + /* Setup the notify ops to be the highest supported version that both + * the server and the client support. + */ + + if (vmci_transport_old_proto_override(&old_pkt_proto)) { + old_proto = old_pkt_proto; + } else { + if (pkt->type == VMCI_TRANSPORT_PACKET_TYPE_NEGOTIATE) + old_proto = true; + else if (pkt->type == VMCI_TRANSPORT_PACKET_TYPE_NEGOTIATE2) + old_proto = false; + + } + + if (old_proto) + version = VSOCK_PROTO_INVALID; + else + version = pkt->proto; + + if (!vmci_transport_proto_to_notify_struct(sk, &version, old_proto)) { + err = -EINVAL; + goto destroy; + } + + /* Subscribe to attach and detach events first. + * + * XXX We attach once for each queue pair created for now so it is easy + * to find the socket (it's provided), but later we should only + * subscribe once and add a way to lookup sockets by queue pair handle. + */ + err = vmci_event_subscribe(VMCI_EVENT_QP_PEER_ATTACH, + vmci_transport_peer_attach_cb, + sk, &attach_sub_id); + if (err < VMCI_SUCCESS) { + err = vmci_transport_error_to_vsock_error(err); + goto destroy; + } + + err = vmci_event_subscribe(VMCI_EVENT_QP_PEER_DETACH, + vmci_transport_peer_detach_cb, + sk, &detach_sub_id); + if (err < VMCI_SUCCESS) { + err = vmci_transport_error_to_vsock_error(err); + goto destroy; + } + + /* Make VMCI select the handle for us. */ + handle = VMCI_INVALID_HANDLE; + is_local = vsk->remote_addr.svm_cid == vsk->local_addr.svm_cid; + flags = is_local ? VMCI_QPFLAG_LOCAL : 0; + + err = vmci_transport_queue_pair_alloc(&qpair, + &handle, + pkt->u.size, + pkt->u.size, + vsk->remote_addr.svm_cid, + flags, + vmci_transport_is_trusted( + vsk, + vsk-> + remote_addr.svm_cid)); + if (err < 0) + goto destroy; + + err = vmci_transport_send_qp_offer(sk, handle); + if (err < 0) { + err = vmci_transport_error_to_vsock_error(err); + goto destroy; + } + + vmci_trans(vsk)->qp_handle = handle; + vmci_trans(vsk)->qpair = qpair; + + vmci_trans(vsk)->produce_size = vmci_trans(vsk)->consume_size = + pkt->u.size; + + vmci_trans(vsk)->attach_sub_id = attach_sub_id; + vmci_trans(vsk)->detach_sub_id = detach_sub_id; + + vmci_trans(vsk)->notify_ops->process_negotiate(sk); + + return 0; + +destroy: + if (attach_sub_id != VMCI_INVALID_ID) + vmci_event_unsubscribe(attach_sub_id); + + if (detach_sub_id != VMCI_INVALID_ID) + vmci_event_unsubscribe(detach_sub_id); + + if (!vmci_handle_is_invalid(handle)) + vmci_qpair_detach(&qpair); + + return err; +} + +static int +vmci_transport_recv_connecting_client_invalid(struct sock *sk, + struct vmci_transport_packet *pkt) +{ + int err = 0; + struct vsock_sock *vsk = vsock_sk(sk); + + if (vsk->sent_request) { + vsk->sent_request = false; + vsk->ignore_connecting_rst = true; + + err = vmci_transport_send_conn_request( + sk, vmci_trans(vsk)->queue_pair_size); + if (err < 0) + err = vmci_transport_error_to_vsock_error(err); + else + err = 0; + + } + + return err; +} + +static int vmci_transport_recv_connected(struct sock *sk, + struct vmci_transport_packet *pkt) +{ + struct vsock_sock *vsk; + bool pkt_processed = false; + + /* In cases where we are closing the connection, it's sufficient to + * mark the state change (and maybe error) and wake up any waiting + * threads. Since this is a connected socket, it's owned by a user + * process and will be cleaned up when the failure is passed back on + * the current or next system call. Our system call implementations + * must therefore check for error and state changes on entry and when + * being awoken. + */ + switch (pkt->type) { + case VMCI_TRANSPORT_PACKET_TYPE_SHUTDOWN: + if (pkt->u.mode) { + vsk = vsock_sk(sk); + + vsk->peer_shutdown |= pkt->u.mode; + sk->sk_state_change(sk); + } + break; + + case VMCI_TRANSPORT_PACKET_TYPE_RST: + vsk = vsock_sk(sk); + /* It is possible that we sent our peer a message (e.g a + * WAITING_READ) right before we got notified that the peer had + * detached. If that happens then we can get a RST pkt back + * from our peer even though there is data available for us to + * read. In that case, don't shutdown the socket completely but + * instead allow the local client to finish reading data off + * the queuepair. Always treat a RST pkt in connected mode like + * a clean shutdown. + */ + sock_set_flag(sk, SOCK_DONE); + vsk->peer_shutdown = SHUTDOWN_MASK; + if (vsock_stream_has_data(vsk) <= 0) + sk->sk_state = SS_DISCONNECTING; + + sk->sk_state_change(sk); + break; + + default: + vsk = vsock_sk(sk); + vmci_trans(vsk)->notify_ops->handle_notify_pkt( + sk, pkt, false, NULL, NULL, + &pkt_processed); + if (!pkt_processed) + return -EINVAL; + + break; + } + + return 0; +} + +static int vmci_transport_socket_init(struct vsock_sock *vsk, + struct vsock_sock *psk) +{ + vsk->trans = kmalloc(sizeof(struct vmci_transport), GFP_KERNEL); + if (!vsk->trans) + return -ENOMEM; + + vmci_trans(vsk)->dg_handle = VMCI_INVALID_HANDLE; + vmci_trans(vsk)->qp_handle = VMCI_INVALID_HANDLE; + vmci_trans(vsk)->qpair = NULL; + vmci_trans(vsk)->produce_size = vmci_trans(vsk)->consume_size = 0; + vmci_trans(vsk)->attach_sub_id = vmci_trans(vsk)->detach_sub_id = + VMCI_INVALID_ID; + vmci_trans(vsk)->notify_ops = NULL; + if (psk) { + vmci_trans(vsk)->queue_pair_size = + vmci_trans(psk)->queue_pair_size; + vmci_trans(vsk)->queue_pair_min_size = + vmci_trans(psk)->queue_pair_min_size; + vmci_trans(vsk)->queue_pair_max_size = + vmci_trans(psk)->queue_pair_max_size; + } else { + vmci_trans(vsk)->queue_pair_size = + VMCI_TRANSPORT_DEFAULT_QP_SIZE; + vmci_trans(vsk)->queue_pair_min_size = + VMCI_TRANSPORT_DEFAULT_QP_SIZE_MIN; + vmci_trans(vsk)->queue_pair_max_size = + VMCI_TRANSPORT_DEFAULT_QP_SIZE_MAX; + } + + return 0; +} + +static void vmci_transport_destruct(struct vsock_sock *vsk) +{ + if (vmci_trans(vsk)->attach_sub_id != VMCI_INVALID_ID) { + vmci_event_unsubscribe(vmci_trans(vsk)->attach_sub_id); + vmci_trans(vsk)->attach_sub_id = VMCI_INVALID_ID; + } + + if (vmci_trans(vsk)->detach_sub_id != VMCI_INVALID_ID) { + vmci_event_unsubscribe(vmci_trans(vsk)->detach_sub_id); + vmci_trans(vsk)->detach_sub_id = VMCI_INVALID_ID; + } + + if (!vmci_handle_is_invalid(vmci_trans(vsk)->qp_handle)) { + vmci_qpair_detach(&vmci_trans(vsk)->qpair); + vmci_trans(vsk)->qp_handle = VMCI_INVALID_HANDLE; + vmci_trans(vsk)->produce_size = 0; + vmci_trans(vsk)->consume_size = 0; + } + + if (vmci_trans(vsk)->notify_ops) + vmci_trans(vsk)->notify_ops->socket_destruct(vsk); + + kfree(vsk->trans); + vsk->trans = NULL; +} + +static void vmci_transport_release(struct vsock_sock *vsk) +{ + if (!vmci_handle_is_invalid(vmci_trans(vsk)->dg_handle)) { + vmci_datagram_destroy_handle(vmci_trans(vsk)->dg_handle); + vmci_trans(vsk)->dg_handle = VMCI_INVALID_HANDLE; + } +} + +static int vmci_transport_dgram_bind(struct vsock_sock *vsk, + struct sockaddr_vm *addr) +{ + u32 port; + u32 flags; + int err; + + /* VMCI will select a resource ID for us if we provide + * VMCI_INVALID_ID. + */ + port = addr->svm_port == VMADDR_PORT_ANY ? + VMCI_INVALID_ID : addr->svm_port; + + if (port <= LAST_RESERVED_PORT && !capable(CAP_NET_BIND_SERVICE)) + return -EACCES; + + flags = addr->svm_cid == VMADDR_CID_ANY ? + VMCI_FLAG_ANYCID_DG_HND : 0; + + err = vmci_transport_datagram_create_hnd(port, flags, + vmci_transport_recv_dgram_cb, + &vsk->sk, + &vmci_trans(vsk)->dg_handle); + if (err < VMCI_SUCCESS) + return vmci_transport_error_to_vsock_error(err); + vsock_addr_init(&vsk->local_addr, addr->svm_cid, + vmci_trans(vsk)->dg_handle.resource); + + return 0; +} + +static int vmci_transport_dgram_enqueue( + struct vsock_sock *vsk, + struct sockaddr_vm *remote_addr, + struct iovec *iov, + size_t len) +{ + int err; + struct vmci_datagram *dg; + + if (len > VMCI_MAX_DG_PAYLOAD_SIZE) + return -EMSGSIZE; + + if (!vmci_transport_allow_dgram(vsk, remote_addr->svm_cid)) + return -EPERM; + + /* Allocate a buffer for the user's message and our packet header. */ + dg = kmalloc(len + sizeof(*dg), GFP_KERNEL); + if (!dg) + return -ENOMEM; + + memcpy_fromiovec(VMCI_DG_PAYLOAD(dg), iov, len); + + dg->dst = vmci_make_handle(remote_addr->svm_cid, + remote_addr->svm_port); + dg->src = vmci_make_handle(vsk->local_addr.svm_cid, + vsk->local_addr.svm_port); + dg->payload_size = len; + + err = vmci_datagram_send(dg); + kfree(dg); + if (err < 0) + return vmci_transport_error_to_vsock_error(err); + + return err - sizeof(*dg); +} + +static int vmci_transport_dgram_dequeue(struct kiocb *kiocb, + struct vsock_sock *vsk, + struct msghdr *msg, size_t len, + int flags) +{ + int err; + int noblock; + struct vmci_datagram *dg; + size_t payload_len; + struct sk_buff *skb; + + noblock = flags & MSG_DONTWAIT; + + if (flags & MSG_OOB || flags & MSG_ERRQUEUE) + return -EOPNOTSUPP; + + /* Retrieve the head sk_buff from the socket's receive queue. */ + err = 0; + skb = skb_recv_datagram(&vsk->sk, flags, noblock, &err); + if (err) + return err; + + if (!skb) + return -EAGAIN; + + dg = (struct vmci_datagram *)skb->data; + if (!dg) + /* err is 0, meaning we read zero bytes. */ + goto out; + + payload_len = dg->payload_size; + /* Ensure the sk_buff matches the payload size claimed in the packet. */ + if (payload_len != skb->len - sizeof(*dg)) { + err = -EINVAL; + goto out; + } + + if (payload_len > len) { + payload_len = len; + msg->msg_flags |= MSG_TRUNC; + } + + /* Place the datagram payload in the user's iovec. */ + err = skb_copy_datagram_iovec(skb, sizeof(*dg), msg->msg_iov, + payload_len); + if (err) + goto out; + + msg->msg_namelen = 0; + if (msg->msg_name) { + struct sockaddr_vm *vm_addr; + + /* Provide the address of the sender. */ + vm_addr = (struct sockaddr_vm *)msg->msg_name; + vsock_addr_init(vm_addr, dg->src.context, dg->src.resource); + msg->msg_namelen = sizeof(*vm_addr); + } + err = payload_len; + +out: + skb_free_datagram(&vsk->sk, skb); + return err; +} + +static bool vmci_transport_dgram_allow(u32 cid, u32 port) +{ + if (cid == VMADDR_CID_HYPERVISOR) { + /* Registrations of PBRPC Servers do not modify VMX/Hypervisor + * state and are allowed. + */ + return port == VMCI_UNITY_PBRPC_REGISTER; + } + + return true; +} + +static int vmci_transport_connect(struct vsock_sock *vsk) +{ + int err; + bool old_pkt_proto = false; + struct sock *sk = &vsk->sk; + + if (vmci_transport_old_proto_override(&old_pkt_proto) && + old_pkt_proto) { + err = vmci_transport_send_conn_request( + sk, vmci_trans(vsk)->queue_pair_size); + if (err < 0) { + sk->sk_state = SS_UNCONNECTED; + return err; + } + } else { + int supported_proto_versions = + vmci_transport_new_proto_supported_versions(); + err = vmci_transport_send_conn_request2( + sk, vmci_trans(vsk)->queue_pair_size, + supported_proto_versions); + if (err < 0) { + sk->sk_state = SS_UNCONNECTED; + return err; + } + + vsk->sent_request = true; + } + + return err; +} + +static ssize_t vmci_transport_stream_dequeue( + struct vsock_sock *vsk, + struct iovec *iov, + size_t len, + int flags) +{ + if (flags & MSG_PEEK) + return vmci_qpair_peekv(vmci_trans(vsk)->qpair, iov, len, 0); + else + return vmci_qpair_dequev(vmci_trans(vsk)->qpair, iov, len, 0); +} + +static ssize_t vmci_transport_stream_enqueue( + struct vsock_sock *vsk, + struct iovec *iov, + size_t len) +{ + return vmci_qpair_enquev(vmci_trans(vsk)->qpair, iov, len, 0); +} + +static s64 vmci_transport_stream_has_data(struct vsock_sock *vsk) +{ + return vmci_qpair_consume_buf_ready(vmci_trans(vsk)->qpair); +} + +static s64 vmci_transport_stream_has_space(struct vsock_sock *vsk) +{ + return vmci_qpair_produce_free_space(vmci_trans(vsk)->qpair); +} + +static u64 vmci_transport_stream_rcvhiwat(struct vsock_sock *vsk) +{ + return vmci_trans(vsk)->consume_size; +} + +static bool vmci_transport_stream_is_active(struct vsock_sock *vsk) +{ + return !vmci_handle_is_invalid(vmci_trans(vsk)->qp_handle); +} + +static u64 vmci_transport_get_buffer_size(struct vsock_sock *vsk) +{ + return vmci_trans(vsk)->queue_pair_size; +} + +static u64 vmci_transport_get_min_buffer_size(struct vsock_sock *vsk) +{ + return vmci_trans(vsk)->queue_pair_min_size; +} + +static u64 vmci_transport_get_max_buffer_size(struct vsock_sock *vsk) +{ + return vmci_trans(vsk)->queue_pair_max_size; +} + +static void vmci_transport_set_buffer_size(struct vsock_sock *vsk, u64 val) +{ + if (val < vmci_trans(vsk)->queue_pair_min_size) + vmci_trans(vsk)->queue_pair_min_size = val; + if (val > vmci_trans(vsk)->queue_pair_max_size) + vmci_trans(vsk)->queue_pair_max_size = val; + vmci_trans(vsk)->queue_pair_size = val; +} + +static void vmci_transport_set_min_buffer_size(struct vsock_sock *vsk, + u64 val) +{ + if (val > vmci_trans(vsk)->queue_pair_size) + vmci_trans(vsk)->queue_pair_size = val; + vmci_trans(vsk)->queue_pair_min_size = val; +} + +static void vmci_transport_set_max_buffer_size(struct vsock_sock *vsk, + u64 val) +{ + if (val < vmci_trans(vsk)->queue_pair_size) + vmci_trans(vsk)->queue_pair_size = val; + vmci_trans(vsk)->queue_pair_max_size = val; +} + +static int vmci_transport_notify_poll_in( + struct vsock_sock *vsk, + size_t target, + bool *data_ready_now) +{ + return vmci_trans(vsk)->notify_ops->poll_in( + &vsk->sk, target, data_ready_now); +} + +static int vmci_transport_notify_poll_out( + struct vsock_sock *vsk, + size_t target, + bool *space_available_now) +{ + return vmci_trans(vsk)->notify_ops->poll_out( + &vsk->sk, target, space_available_now); +} + +static int vmci_transport_notify_recv_init( + struct vsock_sock *vsk, + size_t target, + struct vsock_transport_recv_notify_data *data) +{ + return vmci_trans(vsk)->notify_ops->recv_init( + &vsk->sk, target, + (struct vmci_transport_recv_notify_data *)data); +} + +static int vmci_transport_notify_recv_pre_block( + struct vsock_sock *vsk, + size_t target, + struct vsock_transport_recv_notify_data *data) +{ + return vmci_trans(vsk)->notify_ops->recv_pre_block( + &vsk->sk, target, + (struct vmci_transport_recv_notify_data *)data); +} + +static int vmci_transport_notify_recv_pre_dequeue( + struct vsock_sock *vsk, + size_t target, + struct vsock_transport_recv_notify_data *data) +{ + return vmci_trans(vsk)->notify_ops->recv_pre_dequeue( + &vsk->sk, target, + (struct vmci_transport_recv_notify_data *)data); +} + +static int vmci_transport_notify_recv_post_dequeue( + struct vsock_sock *vsk, + size_t target, + ssize_t copied, + bool data_read, + struct vsock_transport_recv_notify_data *data) +{ + return vmci_trans(vsk)->notify_ops->recv_post_dequeue( + &vsk->sk, target, copied, data_read, + (struct vmci_transport_recv_notify_data *)data); +} + +static int vmci_transport_notify_send_init( + struct vsock_sock *vsk, + struct vsock_transport_send_notify_data *data) +{ + return vmci_trans(vsk)->notify_ops->send_init( + &vsk->sk, + (struct vmci_transport_send_notify_data *)data); +} + +static int vmci_transport_notify_send_pre_block( + struct vsock_sock *vsk, + struct vsock_transport_send_notify_data *data) +{ + return vmci_trans(vsk)->notify_ops->send_pre_block( + &vsk->sk, + (struct vmci_transport_send_notify_data *)data); +} + +static int vmci_transport_notify_send_pre_enqueue( + struct vsock_sock *vsk, + struct vsock_transport_send_notify_data *data) +{ + return vmci_trans(vsk)->notify_ops->send_pre_enqueue( + &vsk->sk, + (struct vmci_transport_send_notify_data *)data); +} + +static int vmci_transport_notify_send_post_enqueue( + struct vsock_sock *vsk, + ssize_t written, + struct vsock_transport_send_notify_data *data) +{ + return vmci_trans(vsk)->notify_ops->send_post_enqueue( + &vsk->sk, written, + (struct vmci_transport_send_notify_data *)data); +} + +static bool vmci_transport_old_proto_override(bool *old_pkt_proto) +{ + if (PROTOCOL_OVERRIDE != -1) { + if (PROTOCOL_OVERRIDE == 0) + *old_pkt_proto = true; + else + *old_pkt_proto = false; + + pr_info("Proto override in use\n"); + return true; + } + + return false; +} + +static bool vmci_transport_proto_to_notify_struct(struct sock *sk, + u16 *proto, + bool old_pkt_proto) +{ + struct vsock_sock *vsk = vsock_sk(sk); + + if (old_pkt_proto) { + if (*proto != VSOCK_PROTO_INVALID) { + pr_err("Can't set both an old and new protocol\n"); + return false; + } + vmci_trans(vsk)->notify_ops = &vmci_transport_notify_pkt_ops; + goto exit; + } + + switch (*proto) { + case VSOCK_PROTO_PKT_ON_NOTIFY: + vmci_trans(vsk)->notify_ops = + &vmci_transport_notify_pkt_q_state_ops; + break; + default: + pr_err("Unknown notify protocol version\n"); + return false; + } + +exit: + vmci_trans(vsk)->notify_ops->socket_init(sk); + return true; +} + +static u16 vmci_transport_new_proto_supported_versions(void) +{ + if (PROTOCOL_OVERRIDE != -1) + return PROTOCOL_OVERRIDE; + + return VSOCK_PROTO_ALL_SUPPORTED; +} + +static u32 vmci_transport_get_local_cid(void) +{ + return vmci_get_context_id(); +} + +static struct vsock_transport vmci_transport = { + .init = vmci_transport_socket_init, + .destruct = vmci_transport_destruct, + .release = vmci_transport_release, + .connect = vmci_transport_connect, + .dgram_bind = vmci_transport_dgram_bind, + .dgram_dequeue = vmci_transport_dgram_dequeue, + .dgram_enqueue = vmci_transport_dgram_enqueue, + .dgram_allow = vmci_transport_dgram_allow, + .stream_dequeue = vmci_transport_stream_dequeue, + .stream_enqueue = vmci_transport_stream_enqueue, + .stream_has_data = vmci_transport_stream_has_data, + .stream_has_space = vmci_transport_stream_has_space, + .stream_rcvhiwat = vmci_transport_stream_rcvhiwat, + .stream_is_active = vmci_transport_stream_is_active, + .stream_allow = vmci_transport_stream_allow, + .notify_poll_in = vmci_transport_notify_poll_in, + .notify_poll_out = vmci_transport_notify_poll_out, + .notify_recv_init = vmci_transport_notify_recv_init, + .notify_recv_pre_block = vmci_transport_notify_recv_pre_block, + .notify_recv_pre_dequeue = vmci_transport_notify_recv_pre_dequeue, + .notify_recv_post_dequeue = vmci_transport_notify_recv_post_dequeue, + .notify_send_init = vmci_transport_notify_send_init, + .notify_send_pre_block = vmci_transport_notify_send_pre_block, + .notify_send_pre_enqueue = vmci_transport_notify_send_pre_enqueue, + .notify_send_post_enqueue = vmci_transport_notify_send_post_enqueue, + .shutdown = vmci_transport_shutdown, + .set_buffer_size = vmci_transport_set_buffer_size, + .set_min_buffer_size = vmci_transport_set_min_buffer_size, + .set_max_buffer_size = vmci_transport_set_max_buffer_size, + .get_buffer_size = vmci_transport_get_buffer_size, + .get_min_buffer_size = vmci_transport_get_min_buffer_size, + .get_max_buffer_size = vmci_transport_get_max_buffer_size, + .get_local_cid = vmci_transport_get_local_cid, +}; + +static int __init vmci_transport_init(void) +{ + int err; + + /* Create the datagram handle that we will use to send and receive all + * VSocket control messages for this context. + */ + err = vmci_transport_datagram_create_hnd(VMCI_TRANSPORT_PACKET_RID, + VMCI_FLAG_ANYCID_DG_HND, + vmci_transport_recv_stream_cb, + NULL, + &vmci_transport_stream_handle); + if (err < VMCI_SUCCESS) { + pr_err("Unable to create datagram handle. (%d)\n", err); + return vmci_transport_error_to_vsock_error(err); + } + + err = vmci_event_subscribe(VMCI_EVENT_QP_RESUMED, + vmci_transport_qp_resumed_cb, + NULL, &vmci_transport_qp_resumed_sub_id); + if (err < VMCI_SUCCESS) { + pr_err("Unable to subscribe to resumed event. (%d)\n", err); + err = vmci_transport_error_to_vsock_error(err); + vmci_transport_qp_resumed_sub_id = VMCI_INVALID_ID; + goto err_destroy_stream_handle; + } + + err = vsock_core_init(&vmci_transport); + if (err < 0) + goto err_unsubscribe; + + return 0; + +err_unsubscribe: + vmci_event_unsubscribe(vmci_transport_qp_resumed_sub_id); +err_destroy_stream_handle: + vmci_datagram_destroy_handle(vmci_transport_stream_handle); + return err; +} +module_init(vmci_transport_init); + +static void __exit vmci_transport_exit(void) +{ + if (!vmci_handle_is_invalid(vmci_transport_stream_handle)) { + if (vmci_datagram_destroy_handle( + vmci_transport_stream_handle) != VMCI_SUCCESS) + pr_err("Couldn't destroy datagram handle\n"); + vmci_transport_stream_handle = VMCI_INVALID_HANDLE; + } + + if (vmci_transport_qp_resumed_sub_id != VMCI_INVALID_ID) { + vmci_event_unsubscribe(vmci_transport_qp_resumed_sub_id); + vmci_transport_qp_resumed_sub_id = VMCI_INVALID_ID; + } + + vsock_core_exit(); +} +module_exit(vmci_transport_exit); + +MODULE_AUTHOR("VMware, Inc."); +MODULE_DESCRIPTION("VMCI transport for Virtual Sockets"); +MODULE_LICENSE("GPL v2"); +MODULE_ALIAS("vmware_vsock"); +MODULE_ALIAS_NETPROTO(PF_VSOCK); diff --git a/net/vmw_vsock/vmci_transport.h b/net/vmw_vsock/vmci_transport.h new file mode 100644 index 000000000000..1bf991803ec0 --- /dev/null +++ b/net/vmw_vsock/vmci_transport.h @@ -0,0 +1,139 @@ +/* + * VMware vSockets Driver + * + * Copyright (C) 2013 VMware, Inc. All rights reserved. + * + * This program is free software; you can redistribute it and/or modify it + * under the terms of the GNU General Public License as published by the Free + * Software Foundation version 2 and no later version. + * + * This program is distributed in the hope that it will be useful, but WITHOUT + * ANY WARRANTY; without even the implied warranty of MERCHANTABILITY or + * FITNESS FOR A PARTICULAR PURPOSE. See the GNU General Public License for + * more details. + */ + +#ifndef _VMCI_TRANSPORT_H_ +#define _VMCI_TRANSPORT_H_ + +#include <linux/vmw_vmci_defs.h> +#include <linux/vmw_vmci_api.h> + +#include "vsock_addr.h" +#include "af_vsock.h" + +/* If the packet format changes in a release then this should change too. */ +#define VMCI_TRANSPORT_PACKET_VERSION 1 + +/* The resource ID on which control packets are sent. */ +#define VMCI_TRANSPORT_PACKET_RID 1 + +#define VSOCK_PROTO_INVALID 0 +#define VSOCK_PROTO_PKT_ON_NOTIFY (1 << 0) +#define VSOCK_PROTO_ALL_SUPPORTED (VSOCK_PROTO_PKT_ON_NOTIFY) + +#define vmci_trans(_vsk) ((struct vmci_transport *)((_vsk)->trans)) + +enum vmci_transport_packet_type { + VMCI_TRANSPORT_PACKET_TYPE_INVALID = 0, + VMCI_TRANSPORT_PACKET_TYPE_REQUEST, + VMCI_TRANSPORT_PACKET_TYPE_NEGOTIATE, + VMCI_TRANSPORT_PACKET_TYPE_OFFER, + VMCI_TRANSPORT_PACKET_TYPE_ATTACH, + VMCI_TRANSPORT_PACKET_TYPE_WROTE, + VMCI_TRANSPORT_PACKET_TYPE_READ, + VMCI_TRANSPORT_PACKET_TYPE_RST, + VMCI_TRANSPORT_PACKET_TYPE_SHUTDOWN, + VMCI_TRANSPORT_PACKET_TYPE_WAITING_WRITE, + VMCI_TRANSPORT_PACKET_TYPE_WAITING_READ, + VMCI_TRANSPORT_PACKET_TYPE_REQUEST2, + VMCI_TRANSPORT_PACKET_TYPE_NEGOTIATE2, + VMCI_TRANSPORT_PACKET_TYPE_MAX +}; + +struct vmci_transport_waiting_info { + u64 generation; + u64 offset; +}; + +/* Control packet type for STREAM sockets. DGRAMs have no control packets nor + * special packet header for data packets, they are just raw VMCI DGRAM + * messages. For STREAMs, control packets are sent over the control channel + * while data is written and read directly from queue pairs with no packet + * format. + */ +struct vmci_transport_packet { + struct vmci_datagram dg; + u8 version; + u8 type; + u16 proto; + u32 src_port; + u32 dst_port; + u32 _reserved2; + union { + u64 size; + u64 mode; + struct vmci_handle handle; + struct vmci_transport_waiting_info wait; + } u; +}; + +struct vmci_transport_notify_pkt { + u64 write_notify_window; + u64 write_notify_min_window; + bool peer_waiting_read; + bool peer_waiting_write; + bool peer_waiting_write_detected; + bool sent_waiting_read; + bool sent_waiting_write; + struct vmci_transport_waiting_info peer_waiting_read_info; + struct vmci_transport_waiting_info peer_waiting_write_info; + u64 produce_q_generation; + u64 consume_q_generation; +}; + +struct vmci_transport_notify_pkt_q_state { + u64 write_notify_window; + u64 write_notify_min_window; + bool peer_waiting_write; + bool peer_waiting_write_detected; +}; + +union vmci_transport_notify { + struct vmci_transport_notify_pkt pkt; + struct vmci_transport_notify_pkt_q_state pkt_q_state; +}; + +/* Our transport-specific data. */ +struct vmci_transport { + /* For DGRAMs. */ + struct vmci_handle dg_handle; + /* For STREAMs. */ + struct vmci_handle qp_handle; + struct vmci_qp *qpair; + u64 produce_size; + u64 consume_size; + u64 queue_pair_size; + u64 queue_pair_min_size; + u64 queue_pair_max_size; + u32 attach_sub_id; + u32 detach_sub_id; + union vmci_transport_notify notify; + struct vmci_transport_notify_ops *notify_ops; +}; + +int vmci_transport_register(void); +void vmci_transport_unregister(void); + +int vmci_transport_send_wrote_bh(struct sockaddr_vm *dst, + struct sockaddr_vm *src); +int vmci_transport_send_read_bh(struct sockaddr_vm *dst, + struct sockaddr_vm *src); +int vmci_transport_send_wrote(struct sock *sk); +int vmci_transport_send_read(struct sock *sk); +int vmci_transport_send_waiting_write(struct sock *sk, + struct vmci_transport_waiting_info *wait); +int vmci_transport_send_waiting_read(struct sock *sk, + struct vmci_transport_waiting_info *wait); + +#endif diff --git a/net/vmw_vsock/vmci_transport_notify.c b/net/vmw_vsock/vmci_transport_notify.c new file mode 100644 index 000000000000..9a730744e7bc --- /dev/null +++ b/net/vmw_vsock/vmci_transport_notify.c @@ -0,0 +1,680 @@ +/* + * VMware vSockets Driver + * + * Copyright (C) 2009-2013 VMware, Inc. All rights reserved. + * + * This program is free software; you can redistribute it and/or modify it + * under the terms of the GNU General Public License as published by the Free + * Software Foundation version 2 and no later version. + * + * This program is distributed in the hope that it will be useful, but WITHOUT + * ANY WARRANTY; without even the implied warranty of MERCHANTABILITY or + * FITNESS FOR A PARTICULAR PURPOSE. See the GNU General Public License for + * more details. + */ + +#include <linux/types.h> +#include <linux/socket.h> +#include <linux/stddef.h> +#include <net/sock.h> + +#include "vmci_transport_notify.h" + +#define PKT_FIELD(vsk, field_name) (vmci_trans(vsk)->notify.pkt.field_name) + +static bool vmci_transport_notify_waiting_write(struct vsock_sock *vsk) +{ +#if defined(VSOCK_OPTIMIZATION_WAITING_NOTIFY) + bool retval; + u64 notify_limit; + + if (!PKT_FIELD(vsk, peer_waiting_write)) + return false; + +#ifdef VSOCK_OPTIMIZATION_FLOW_CONTROL + /* When the sender blocks, we take that as a sign that the sender is + * faster than the receiver. To reduce the transmit rate of the sender, + * we delay the sending of the read notification by decreasing the + * write_notify_window. The notification is delayed until the number of + * bytes used in the queue drops below the write_notify_window. + */ + + if (!PKT_FIELD(vsk, peer_waiting_write_detected)) { + PKT_FIELD(vsk, peer_waiting_write_detected) = true; + if (PKT_FIELD(vsk, write_notify_window) < PAGE_SIZE) { + PKT_FIELD(vsk, write_notify_window) = + PKT_FIELD(vsk, write_notify_min_window); + } else { + PKT_FIELD(vsk, write_notify_window) -= PAGE_SIZE; + if (PKT_FIELD(vsk, write_notify_window) < + PKT_FIELD(vsk, write_notify_min_window)) + PKT_FIELD(vsk, write_notify_window) = + PKT_FIELD(vsk, write_notify_min_window); + + } + } + notify_limit = vmci_trans(vsk)->consume_size - + PKT_FIELD(vsk, write_notify_window); +#else + notify_limit = 0; +#endif + + /* For now we ignore the wait information and just see if the free + * space exceeds the notify limit. Note that improving this function + * to be more intelligent will not require a protocol change and will + * retain compatibility between endpoints with mixed versions of this + * function. + * + * The notify_limit is used to delay notifications in the case where + * flow control is enabled. Below the test is expressed in terms of + * free space in the queue: if free_space > ConsumeSize - + * write_notify_window then notify An alternate way of expressing this + * is to rewrite the expression to use the data ready in the receive + * queue: if write_notify_window > bufferReady then notify as + * free_space == ConsumeSize - bufferReady. + */ + retval = vmci_qpair_consume_free_space(vmci_trans(vsk)->qpair) > + notify_limit; +#ifdef VSOCK_OPTIMIZATION_FLOW_CONTROL + if (retval) { + /* + * Once we notify the peer, we reset the detected flag so the + * next wait will again cause a decrease in the window size. + */ + + PKT_FIELD(vsk, peer_waiting_write_detected) = false; + } +#endif + return retval; +#else + return true; +#endif +} + +static bool vmci_transport_notify_waiting_read(struct vsock_sock *vsk) +{ +#if defined(VSOCK_OPTIMIZATION_WAITING_NOTIFY) + if (!PKT_FIELD(vsk, peer_waiting_read)) + return false; + + /* For now we ignore the wait information and just see if there is any + * data for our peer to read. Note that improving this function to be + * more intelligent will not require a protocol change and will retain + * compatibility between endpoints with mixed versions of this + * function. + */ + return vmci_qpair_produce_buf_ready(vmci_trans(vsk)->qpair) > 0; +#else + return true; +#endif +} + +static void +vmci_transport_handle_waiting_read(struct sock *sk, + struct vmci_transport_packet *pkt, + bool bottom_half, + struct sockaddr_vm *dst, + struct sockaddr_vm *src) +{ +#if defined(VSOCK_OPTIMIZATION_WAITING_NOTIFY) + struct vsock_sock *vsk; + + vsk = vsock_sk(sk); + + PKT_FIELD(vsk, peer_waiting_read) = true; + memcpy(&PKT_FIELD(vsk, peer_waiting_read_info), &pkt->u.wait, + sizeof(PKT_FIELD(vsk, peer_waiting_read_info))); + + if (vmci_transport_notify_waiting_read(vsk)) { + bool sent; + + if (bottom_half) + sent = vmci_transport_send_wrote_bh(dst, src) > 0; + else + sent = vmci_transport_send_wrote(sk) > 0; + + if (sent) + PKT_FIELD(vsk, peer_waiting_read) = false; + } +#endif +} + +static void +vmci_transport_handle_waiting_write(struct sock *sk, + struct vmci_transport_packet *pkt, + bool bottom_half, + struct sockaddr_vm *dst, + struct sockaddr_vm *src) +{ +#if defined(VSOCK_OPTIMIZATION_WAITING_NOTIFY) + struct vsock_sock *vsk; + + vsk = vsock_sk(sk); + + PKT_FIELD(vsk, peer_waiting_write) = true; + memcpy(&PKT_FIELD(vsk, peer_waiting_write_info), &pkt->u.wait, + sizeof(PKT_FIELD(vsk, peer_waiting_write_info))); + + if (vmci_transport_notify_waiting_write(vsk)) { + bool sent; + + if (bottom_half) + sent = vmci_transport_send_read_bh(dst, src) > 0; + else + sent = vmci_transport_send_read(sk) > 0; + + if (sent) + PKT_FIELD(vsk, peer_waiting_write) = false; + } +#endif +} + +static void +vmci_transport_handle_read(struct sock *sk, + struct vmci_transport_packet *pkt, + bool bottom_half, + struct sockaddr_vm *dst, struct sockaddr_vm *src) +{ +#if defined(VSOCK_OPTIMIZATION_WAITING_NOTIFY) + struct vsock_sock *vsk; + + vsk = vsock_sk(sk); + PKT_FIELD(vsk, sent_waiting_write) = false; +#endif + + sk->sk_write_space(sk); +} + +static bool send_waiting_read(struct sock *sk, u64 room_needed) +{ +#if defined(VSOCK_OPTIMIZATION_WAITING_NOTIFY) + struct vsock_sock *vsk; + struct vmci_transport_waiting_info waiting_info; + u64 tail; + u64 head; + u64 room_left; + bool ret; + + vsk = vsock_sk(sk); + + if (PKT_FIELD(vsk, sent_waiting_read)) + return true; + + if (PKT_FIELD(vsk, write_notify_window) < + vmci_trans(vsk)->consume_size) + PKT_FIELD(vsk, write_notify_window) = + min(PKT_FIELD(vsk, write_notify_window) + PAGE_SIZE, + vmci_trans(vsk)->consume_size); + + vmci_qpair_get_consume_indexes(vmci_trans(vsk)->qpair, &tail, &head); + room_left = vmci_trans(vsk)->consume_size - head; + if (room_needed >= room_left) { + waiting_info.offset = room_needed - room_left; + waiting_info.generation = + PKT_FIELD(vsk, consume_q_generation) + 1; + } else { + waiting_info.offset = head + room_needed; + waiting_info.generation = PKT_FIELD(vsk, consume_q_generation); + } + + ret = vmci_transport_send_waiting_read(sk, &waiting_info) > 0; + if (ret) + PKT_FIELD(vsk, sent_waiting_read) = true; + + return ret; +#else + return true; +#endif +} + +static bool send_waiting_write(struct sock *sk, u64 room_needed) +{ +#if defined(VSOCK_OPTIMIZATION_WAITING_NOTIFY) + struct vsock_sock *vsk; + struct vmci_transport_waiting_info waiting_info; + u64 tail; + u64 head; + u64 room_left; + bool ret; + + vsk = vsock_sk(sk); + + if (PKT_FIELD(vsk, sent_waiting_write)) + return true; + + vmci_qpair_get_produce_indexes(vmci_trans(vsk)->qpair, &tail, &head); + room_left = vmci_trans(vsk)->produce_size - tail; + if (room_needed + 1 >= room_left) { + /* Wraps around to current generation. */ + waiting_info.offset = room_needed + 1 - room_left; + waiting_info.generation = PKT_FIELD(vsk, produce_q_generation); + } else { + waiting_info.offset = tail + room_needed + 1; + waiting_info.generation = + PKT_FIELD(vsk, produce_q_generation) - 1; + } + + ret = vmci_transport_send_waiting_write(sk, &waiting_info) > 0; + if (ret) + PKT_FIELD(vsk, sent_waiting_write) = true; + + return ret; +#else + return true; +#endif +} + +static int vmci_transport_send_read_notification(struct sock *sk) +{ + struct vsock_sock *vsk; + bool sent_read; + unsigned int retries; + int err; + + vsk = vsock_sk(sk); + sent_read = false; + retries = 0; + err = 0; + + if (vmci_transport_notify_waiting_write(vsk)) { + /* Notify the peer that we have read, retrying the send on + * failure up to our maximum value. XXX For now we just log + * the failure, but later we should schedule a work item to + * handle the resend until it succeeds. That would require + * keeping track of work items in the vsk and cleaning them up + * upon socket close. + */ + while (!(vsk->peer_shutdown & RCV_SHUTDOWN) && + !sent_read && + retries < VMCI_TRANSPORT_MAX_DGRAM_RESENDS) { + err = vmci_transport_send_read(sk); + if (err >= 0) + sent_read = true; + + retries++; + } + + if (retries >= VMCI_TRANSPORT_MAX_DGRAM_RESENDS) + pr_err("%p unable to send read notify to peer\n", sk); + else +#if defined(VSOCK_OPTIMIZATION_WAITING_NOTIFY) + PKT_FIELD(vsk, peer_waiting_write) = false; +#endif + + } + return err; +} + +static void +vmci_transport_handle_wrote(struct sock *sk, + struct vmci_transport_packet *pkt, + bool bottom_half, + struct sockaddr_vm *dst, struct sockaddr_vm *src) +{ +#if defined(VSOCK_OPTIMIZATION_WAITING_NOTIFY) + struct vsock_sock *vsk = vsock_sk(sk); + PKT_FIELD(vsk, sent_waiting_read) = false; +#endif + sk->sk_data_ready(sk, 0); +} + +static void vmci_transport_notify_pkt_socket_init(struct sock *sk) +{ + struct vsock_sock *vsk = vsock_sk(sk); + + PKT_FIELD(vsk, write_notify_window) = PAGE_SIZE; + PKT_FIELD(vsk, write_notify_min_window) = PAGE_SIZE; + PKT_FIELD(vsk, peer_waiting_read) = false; + PKT_FIELD(vsk, peer_waiting_write) = false; + PKT_FIELD(vsk, peer_waiting_write_detected) = false; + PKT_FIELD(vsk, sent_waiting_read) = false; + PKT_FIELD(vsk, sent_waiting_write) = false; + PKT_FIELD(vsk, produce_q_generation) = 0; + PKT_FIELD(vsk, consume_q_generation) = 0; + + memset(&PKT_FIELD(vsk, peer_waiting_read_info), 0, + sizeof(PKT_FIELD(vsk, peer_waiting_read_info))); + memset(&PKT_FIELD(vsk, peer_waiting_write_info), 0, + sizeof(PKT_FIELD(vsk, peer_waiting_write_info))); +} + +static void vmci_transport_notify_pkt_socket_destruct(struct vsock_sock *vsk) +{ +} + +static int +vmci_transport_notify_pkt_poll_in(struct sock *sk, + size_t target, bool *data_ready_now) +{ + struct vsock_sock *vsk = vsock_sk(sk); + + if (vsock_stream_has_data(vsk)) { + *data_ready_now = true; + } else { + /* We can't read right now because there is nothing in the + * queue. Ask for notifications when there is something to + * read. + */ + if (sk->sk_state == SS_CONNECTED) { + if (!send_waiting_read(sk, 1)) + return -1; + + } + *data_ready_now = false; + } + + return 0; +} + +static int +vmci_transport_notify_pkt_poll_out(struct sock *sk, + size_t target, bool *space_avail_now) +{ + s64 produce_q_free_space; + struct vsock_sock *vsk = vsock_sk(sk); + + produce_q_free_space = vsock_stream_has_space(vsk); + if (produce_q_free_space > 0) { + *space_avail_now = true; + return 0; + } else if (produce_q_free_space == 0) { + /* This is a connected socket but we can't currently send data. + * Notify the peer that we are waiting if the queue is full. We + * only send a waiting write if the queue is full because + * otherwise we end up in an infinite WAITING_WRITE, READ, + * WAITING_WRITE, READ, etc. loop. Treat failing to send the + * notification as a socket error, passing that back through + * the mask. + */ + if (!send_waiting_write(sk, 1)) + return -1; + + *space_avail_now = false; + } + + return 0; +} + +static int +vmci_transport_notify_pkt_recv_init( + struct sock *sk, + size_t target, + struct vmci_transport_recv_notify_data *data) +{ + struct vsock_sock *vsk = vsock_sk(sk); + +#ifdef VSOCK_OPTIMIZATION_WAITING_NOTIFY + data->consume_head = 0; + data->produce_tail = 0; +#ifdef VSOCK_OPTIMIZATION_FLOW_CONTROL + data->notify_on_block = false; + + if (PKT_FIELD(vsk, write_notify_min_window) < target + 1) { + PKT_FIELD(vsk, write_notify_min_window) = target + 1; + if (PKT_FIELD(vsk, write_notify_window) < + PKT_FIELD(vsk, write_notify_min_window)) { + /* If the current window is smaller than the new + * minimal window size, we need to reevaluate whether + * we need to notify the sender. If the number of ready + * bytes are smaller than the new window, we need to + * send a notification to the sender before we block. + */ + + PKT_FIELD(vsk, write_notify_window) = + PKT_FIELD(vsk, write_notify_min_window); + data->notify_on_block = true; + } + } +#endif +#endif + + return 0; +} + +static int +vmci_transport_notify_pkt_recv_pre_block( + struct sock *sk, + size_t target, + struct vmci_transport_recv_notify_data *data) +{ + int err = 0; + + /* Notify our peer that we are waiting for data to read. */ + if (!send_waiting_read(sk, target)) { + err = -EHOSTUNREACH; + return err; + } +#ifdef VSOCK_OPTIMIZATION_FLOW_CONTROL + if (data->notify_on_block) { + err = vmci_transport_send_read_notification(sk); + if (err < 0) + return err; + + data->notify_on_block = false; + } +#endif + + return err; +} + +static int +vmci_transport_notify_pkt_recv_pre_dequeue( + struct sock *sk, + size_t target, + struct vmci_transport_recv_notify_data *data) +{ + struct vsock_sock *vsk = vsock_sk(sk); + + /* Now consume up to len bytes from the queue. Note that since we have + * the socket locked we should copy at least ready bytes. + */ +#if defined(VSOCK_OPTIMIZATION_WAITING_NOTIFY) + vmci_qpair_get_consume_indexes(vmci_trans(vsk)->qpair, + &data->produce_tail, + &data->consume_head); +#endif + + return 0; +} + +static int +vmci_transport_notify_pkt_recv_post_dequeue( + struct sock *sk, + size_t target, + ssize_t copied, + bool data_read, + struct vmci_transport_recv_notify_data *data) +{ + struct vsock_sock *vsk; + int err; + + vsk = vsock_sk(sk); + err = 0; + + if (data_read) { +#if defined(VSOCK_OPTIMIZATION_WAITING_NOTIFY) + /* Detect a wrap-around to maintain queue generation. Note + * that this is safe since we hold the socket lock across the + * two queue pair operations. + */ + if (copied >= + vmci_trans(vsk)->consume_size - data->consume_head) + PKT_FIELD(vsk, consume_q_generation)++; +#endif + + err = vmci_transport_send_read_notification(sk); + if (err < 0) + return err; + + } + return err; +} + +static int +vmci_transport_notify_pkt_send_init( + struct sock *sk, + struct vmci_transport_send_notify_data *data) +{ +#ifdef VSOCK_OPTIMIZATION_WAITING_NOTIFY + data->consume_head = 0; + data->produce_tail = 0; +#endif + + return 0; +} + +static int +vmci_transport_notify_pkt_send_pre_block( + struct sock *sk, + struct vmci_transport_send_notify_data *data) +{ + /* Notify our peer that we are waiting for room to write. */ + if (!send_waiting_write(sk, 1)) + return -EHOSTUNREACH; + + return 0; +} + +static int +vmci_transport_notify_pkt_send_pre_enqueue( + struct sock *sk, + struct vmci_transport_send_notify_data *data) +{ + struct vsock_sock *vsk = vsock_sk(sk); + +#if defined(VSOCK_OPTIMIZATION_WAITING_NOTIFY) + vmci_qpair_get_produce_indexes(vmci_trans(vsk)->qpair, + &data->produce_tail, + &data->consume_head); +#endif + + return 0; +} + +static int +vmci_transport_notify_pkt_send_post_enqueue( + struct sock *sk, + ssize_t written, + struct vmci_transport_send_notify_data *data) +{ + int err = 0; + struct vsock_sock *vsk; + bool sent_wrote = false; + int retries = 0; + + vsk = vsock_sk(sk); + +#if defined(VSOCK_OPTIMIZATION_WAITING_NOTIFY) + /* Detect a wrap-around to maintain queue generation. Note that this + * is safe since we hold the socket lock across the two queue pair + * operations. + */ + if (written >= vmci_trans(vsk)->produce_size - data->produce_tail) + PKT_FIELD(vsk, produce_q_generation)++; + +#endif + + if (vmci_transport_notify_waiting_read(vsk)) { + /* Notify the peer that we have written, retrying the send on + * failure up to our maximum value. See the XXX comment for the + * corresponding piece of code in StreamRecvmsg() for potential + * improvements. + */ + while (!(vsk->peer_shutdown & RCV_SHUTDOWN) && + !sent_wrote && + retries < VMCI_TRANSPORT_MAX_DGRAM_RESENDS) { + err = vmci_transport_send_wrote(sk); + if (err >= 0) + sent_wrote = true; + + retries++; + } + + if (retries >= VMCI_TRANSPORT_MAX_DGRAM_RESENDS) { + pr_err("%p unable to send wrote notify to peer\n", sk); + return err; + } else { +#if defined(VSOCK_OPTIMIZATION_WAITING_NOTIFY) + PKT_FIELD(vsk, peer_waiting_read) = false; +#endif + } + } + return err; +} + +static void +vmci_transport_notify_pkt_handle_pkt( + struct sock *sk, + struct vmci_transport_packet *pkt, + bool bottom_half, + struct sockaddr_vm *dst, + struct sockaddr_vm *src, bool *pkt_processed) +{ + bool processed = false; + + switch (pkt->type) { + case VMCI_TRANSPORT_PACKET_TYPE_WROTE: + vmci_transport_handle_wrote(sk, pkt, bottom_half, dst, src); + processed = true; + break; + case VMCI_TRANSPORT_PACKET_TYPE_READ: + vmci_transport_handle_read(sk, pkt, bottom_half, dst, src); + processed = true; + break; + case VMCI_TRANSPORT_PACKET_TYPE_WAITING_WRITE: + vmci_transport_handle_waiting_write(sk, pkt, bottom_half, + dst, src); + processed = true; + break; + + case VMCI_TRANSPORT_PACKET_TYPE_WAITING_READ: + vmci_transport_handle_waiting_read(sk, pkt, bottom_half, + dst, src); + processed = true; + break; + } + + if (pkt_processed) + *pkt_processed = processed; +} + +static void vmci_transport_notify_pkt_process_request(struct sock *sk) +{ + struct vsock_sock *vsk = vsock_sk(sk); + + PKT_FIELD(vsk, write_notify_window) = vmci_trans(vsk)->consume_size; + if (vmci_trans(vsk)->consume_size < + PKT_FIELD(vsk, write_notify_min_window)) + PKT_FIELD(vsk, write_notify_min_window) = + vmci_trans(vsk)->consume_size; +} + +static void vmci_transport_notify_pkt_process_negotiate(struct sock *sk) +{ + struct vsock_sock *vsk = vsock_sk(sk); + + PKT_FIELD(vsk, write_notify_window) = vmci_trans(vsk)->consume_size; + if (vmci_trans(vsk)->consume_size < + PKT_FIELD(vsk, write_notify_min_window)) + PKT_FIELD(vsk, write_notify_min_window) = + vmci_trans(vsk)->consume_size; +} + +/* Socket control packet based operations. */ +struct vmci_transport_notify_ops vmci_transport_notify_pkt_ops = { + vmci_transport_notify_pkt_socket_init, + vmci_transport_notify_pkt_socket_destruct, + vmci_transport_notify_pkt_poll_in, + vmci_transport_notify_pkt_poll_out, + vmci_transport_notify_pkt_handle_pkt, + vmci_transport_notify_pkt_recv_init, + vmci_transport_notify_pkt_recv_pre_block, + vmci_transport_notify_pkt_recv_pre_dequeue, + vmci_transport_notify_pkt_recv_post_dequeue, + vmci_transport_notify_pkt_send_init, + vmci_transport_notify_pkt_send_pre_block, + vmci_transport_notify_pkt_send_pre_enqueue, + vmci_transport_notify_pkt_send_post_enqueue, + vmci_transport_notify_pkt_process_request, + vmci_transport_notify_pkt_process_negotiate, +}; diff --git a/net/vmw_vsock/vmci_transport_notify.h b/net/vmw_vsock/vmci_transport_notify.h new file mode 100644 index 000000000000..7df793249b6c --- /dev/null +++ b/net/vmw_vsock/vmci_transport_notify.h @@ -0,0 +1,83 @@ +/* + * VMware vSockets Driver + * + * Copyright (C) 2009-2013 VMware, Inc. All rights reserved. + * + * This program is free software; you can redistribute it and/or modify it + * under the terms of the GNU General Public License as published by the Free + * Software Foundation version 2 and no later version. + * + * This program is distributed in the hope that it will be useful, but WITHOUT + * ANY WARRANTY; without even the implied warranty of MERCHANTABILITY or + * FITNESS FOR A PARTICULAR PURPOSE. See the GNU General Public License for + * more details. + */ + +#ifndef __VMCI_TRANSPORT_NOTIFY_H__ +#define __VMCI_TRANSPORT_NOTIFY_H__ + +#include <linux/types.h> +#include <linux/vmw_vmci_defs.h> +#include <linux/vmw_vmci_api.h> +#include <linux/vm_sockets.h> + +#include "vmci_transport.h" + +/* Comment this out to compare with old protocol. */ +#define VSOCK_OPTIMIZATION_WAITING_NOTIFY 1 +#if defined(VSOCK_OPTIMIZATION_WAITING_NOTIFY) +/* Comment this out to remove flow control for "new" protocol */ +#define VSOCK_OPTIMIZATION_FLOW_CONTROL 1 +#endif + +#define VMCI_TRANSPORT_MAX_DGRAM_RESENDS 10 + +struct vmci_transport_recv_notify_data { + u64 consume_head; + u64 produce_tail; + bool notify_on_block; +}; + +struct vmci_transport_send_notify_data { + u64 consume_head; + u64 produce_tail; +}; + +/* Socket notification callbacks. */ +struct vmci_transport_notify_ops { + void (*socket_init) (struct sock *sk); + void (*socket_destruct) (struct vsock_sock *vsk); + int (*poll_in) (struct sock *sk, size_t target, + bool *data_ready_now); + int (*poll_out) (struct sock *sk, size_t target, + bool *space_avail_now); + void (*handle_notify_pkt) (struct sock *sk, + struct vmci_transport_packet *pkt, + bool bottom_half, struct sockaddr_vm *dst, + struct sockaddr_vm *src, + bool *pkt_processed); + int (*recv_init) (struct sock *sk, size_t target, + struct vmci_transport_recv_notify_data *data); + int (*recv_pre_block) (struct sock *sk, size_t target, + struct vmci_transport_recv_notify_data *data); + int (*recv_pre_dequeue) (struct sock *sk, size_t target, + struct vmci_transport_recv_notify_data *data); + int (*recv_post_dequeue) (struct sock *sk, size_t target, + ssize_t copied, bool data_read, + struct vmci_transport_recv_notify_data *data); + int (*send_init) (struct sock *sk, + struct vmci_transport_send_notify_data *data); + int (*send_pre_block) (struct sock *sk, + struct vmci_transport_send_notify_data *data); + int (*send_pre_enqueue) (struct sock *sk, + struct vmci_transport_send_notify_data *data); + int (*send_post_enqueue) (struct sock *sk, ssize_t written, + struct vmci_transport_send_notify_data *data); + void (*process_request) (struct sock *sk); + void (*process_negotiate) (struct sock *sk); +}; + +extern struct vmci_transport_notify_ops vmci_transport_notify_pkt_ops; +extern struct vmci_transport_notify_ops vmci_transport_notify_pkt_q_state_ops; + +#endif /* __VMCI_TRANSPORT_NOTIFY_H__ */ diff --git a/net/vmw_vsock/vmci_transport_notify_qstate.c b/net/vmw_vsock/vmci_transport_notify_qstate.c new file mode 100644 index 000000000000..622bd7aa1016 --- /dev/null +++ b/net/vmw_vsock/vmci_transport_notify_qstate.c @@ -0,0 +1,438 @@ +/* + * VMware vSockets Driver + * + * Copyright (C) 2009-2013 VMware, Inc. All rights reserved. + * + * This program is free software; you can redistribute it and/or modify it + * under the terms of the GNU General Public License as published by the Free + * Software Foundation version 2 and no later version. + * + * This program is distributed in the hope that it will be useful, but WITHOUT + * ANY WARRANTY; without even the implied warranty of MERCHANTABILITY or + * FITNESS FOR A PARTICULAR PURPOSE. See the GNU General Public License for + * more details. + */ + +#include <linux/types.h> +#include <linux/socket.h> +#include <linux/stddef.h> +#include <net/sock.h> + +#include "vmci_transport_notify.h" + +#define PKT_FIELD(vsk, field_name) \ + (vmci_trans(vsk)->notify.pkt_q_state.field_name) + +static bool vmci_transport_notify_waiting_write(struct vsock_sock *vsk) +{ + bool retval; + u64 notify_limit; + + if (!PKT_FIELD(vsk, peer_waiting_write)) + return false; + + /* When the sender blocks, we take that as a sign that the sender is + * faster than the receiver. To reduce the transmit rate of the sender, + * we delay the sending of the read notification by decreasing the + * write_notify_window. The notification is delayed until the number of + * bytes used in the queue drops below the write_notify_window. + */ + + if (!PKT_FIELD(vsk, peer_waiting_write_detected)) { + PKT_FIELD(vsk, peer_waiting_write_detected) = true; + if (PKT_FIELD(vsk, write_notify_window) < PAGE_SIZE) { + PKT_FIELD(vsk, write_notify_window) = + PKT_FIELD(vsk, write_notify_min_window); + } else { + PKT_FIELD(vsk, write_notify_window) -= PAGE_SIZE; + if (PKT_FIELD(vsk, write_notify_window) < + PKT_FIELD(vsk, write_notify_min_window)) + PKT_FIELD(vsk, write_notify_window) = + PKT_FIELD(vsk, write_notify_min_window); + + } + } + notify_limit = vmci_trans(vsk)->consume_size - + PKT_FIELD(vsk, write_notify_window); + + /* The notify_limit is used to delay notifications in the case where + * flow control is enabled. Below the test is expressed in terms of + * free space in the queue: if free_space > ConsumeSize - + * write_notify_window then notify An alternate way of expressing this + * is to rewrite the expression to use the data ready in the receive + * queue: if write_notify_window > bufferReady then notify as + * free_space == ConsumeSize - bufferReady. + */ + + retval = vmci_qpair_consume_free_space(vmci_trans(vsk)->qpair) > + notify_limit; + + if (retval) { + /* Once we notify the peer, we reset the detected flag so the + * next wait will again cause a decrease in the window size. + */ + + PKT_FIELD(vsk, peer_waiting_write_detected) = false; + } + return retval; +} + +static void +vmci_transport_handle_read(struct sock *sk, + struct vmci_transport_packet *pkt, + bool bottom_half, + struct sockaddr_vm *dst, struct sockaddr_vm *src) +{ + sk->sk_write_space(sk); +} + +static void +vmci_transport_handle_wrote(struct sock *sk, + struct vmci_transport_packet *pkt, + bool bottom_half, + struct sockaddr_vm *dst, struct sockaddr_vm *src) +{ + sk->sk_data_ready(sk, 0); +} + +static void vsock_block_update_write_window(struct sock *sk) +{ + struct vsock_sock *vsk = vsock_sk(sk); + + if (PKT_FIELD(vsk, write_notify_window) < vmci_trans(vsk)->consume_size) + PKT_FIELD(vsk, write_notify_window) = + min(PKT_FIELD(vsk, write_notify_window) + PAGE_SIZE, + vmci_trans(vsk)->consume_size); +} + +static int vmci_transport_send_read_notification(struct sock *sk) +{ + struct vsock_sock *vsk; + bool sent_read; + unsigned int retries; + int err; + + vsk = vsock_sk(sk); + sent_read = false; + retries = 0; + err = 0; + + if (vmci_transport_notify_waiting_write(vsk)) { + /* Notify the peer that we have read, retrying the send on + * failure up to our maximum value. XXX For now we just log + * the failure, but later we should schedule a work item to + * handle the resend until it succeeds. That would require + * keeping track of work items in the vsk and cleaning them up + * upon socket close. + */ + while (!(vsk->peer_shutdown & RCV_SHUTDOWN) && + !sent_read && + retries < VMCI_TRANSPORT_MAX_DGRAM_RESENDS) { + err = vmci_transport_send_read(sk); + if (err >= 0) + sent_read = true; + + retries++; + } + + if (retries >= VMCI_TRANSPORT_MAX_DGRAM_RESENDS && !sent_read) + pr_err("%p unable to send read notification to peer\n", + sk); + else + PKT_FIELD(vsk, peer_waiting_write) = false; + + } + return err; +} + +static void vmci_transport_notify_pkt_socket_init(struct sock *sk) +{ + struct vsock_sock *vsk = vsock_sk(sk); + + PKT_FIELD(vsk, write_notify_window) = PAGE_SIZE; + PKT_FIELD(vsk, write_notify_min_window) = PAGE_SIZE; + PKT_FIELD(vsk, peer_waiting_write) = false; + PKT_FIELD(vsk, peer_waiting_write_detected) = false; +} + +static void vmci_transport_notify_pkt_socket_destruct(struct vsock_sock *vsk) +{ + PKT_FIELD(vsk, write_notify_window) = PAGE_SIZE; + PKT_FIELD(vsk, write_notify_min_window) = PAGE_SIZE; + PKT_FIELD(vsk, peer_waiting_write) = false; + PKT_FIELD(vsk, peer_waiting_write_detected) = false; +} + +static int +vmci_transport_notify_pkt_poll_in(struct sock *sk, + size_t target, bool *data_ready_now) +{ + struct vsock_sock *vsk = vsock_sk(sk); + + if (vsock_stream_has_data(vsk)) { + *data_ready_now = true; + } else { + /* We can't read right now because there is nothing in the + * queue. Ask for notifications when there is something to + * read. + */ + if (sk->sk_state == SS_CONNECTED) + vsock_block_update_write_window(sk); + *data_ready_now = false; + } + + return 0; +} + +static int +vmci_transport_notify_pkt_poll_out(struct sock *sk, + size_t target, bool *space_avail_now) +{ + s64 produce_q_free_space; + struct vsock_sock *vsk = vsock_sk(sk); + + produce_q_free_space = vsock_stream_has_space(vsk); + if (produce_q_free_space > 0) { + *space_avail_now = true; + return 0; + } else if (produce_q_free_space == 0) { + /* This is a connected socket but we can't currently send data. + * Nothing else to do. + */ + *space_avail_now = false; + } + + return 0; +} + +static int +vmci_transport_notify_pkt_recv_init( + struct sock *sk, + size_t target, + struct vmci_transport_recv_notify_data *data) +{ + struct vsock_sock *vsk = vsock_sk(sk); + + data->consume_head = 0; + data->produce_tail = 0; + data->notify_on_block = false; + + if (PKT_FIELD(vsk, write_notify_min_window) < target + 1) { + PKT_FIELD(vsk, write_notify_min_window) = target + 1; + if (PKT_FIELD(vsk, write_notify_window) < + PKT_FIELD(vsk, write_notify_min_window)) { + /* If the current window is smaller than the new + * minimal window size, we need to reevaluate whether + * we need to notify the sender. If the number of ready + * bytes are smaller than the new window, we need to + * send a notification to the sender before we block. + */ + + PKT_FIELD(vsk, write_notify_window) = + PKT_FIELD(vsk, write_notify_min_window); + data->notify_on_block = true; + } + } + + return 0; +} + +static int +vmci_transport_notify_pkt_recv_pre_block( + struct sock *sk, + size_t target, + struct vmci_transport_recv_notify_data *data) +{ + int err = 0; + + vsock_block_update_write_window(sk); + + if (data->notify_on_block) { + err = vmci_transport_send_read_notification(sk); + if (err < 0) + return err; + data->notify_on_block = false; + } + + return err; +} + +static int +vmci_transport_notify_pkt_recv_post_dequeue( + struct sock *sk, + size_t target, + ssize_t copied, + bool data_read, + struct vmci_transport_recv_notify_data *data) +{ + struct vsock_sock *vsk; + int err; + bool was_full = false; + u64 free_space; + + vsk = vsock_sk(sk); + err = 0; + + if (data_read) { + smp_mb(); + + free_space = + vmci_qpair_consume_free_space(vmci_trans(vsk)->qpair); + was_full = free_space == copied; + + if (was_full) + PKT_FIELD(vsk, peer_waiting_write) = true; + + err = vmci_transport_send_read_notification(sk); + if (err < 0) + return err; + + /* See the comment in + * vmci_transport_notify_pkt_send_post_enqueue(). + */ + sk->sk_data_ready(sk, 0); + } + + return err; +} + +static int +vmci_transport_notify_pkt_send_init( + struct sock *sk, + struct vmci_transport_send_notify_data *data) +{ + data->consume_head = 0; + data->produce_tail = 0; + + return 0; +} + +static int +vmci_transport_notify_pkt_send_post_enqueue( + struct sock *sk, + ssize_t written, + struct vmci_transport_send_notify_data *data) +{ + int err = 0; + struct vsock_sock *vsk; + bool sent_wrote = false; + bool was_empty; + int retries = 0; + + vsk = vsock_sk(sk); + + smp_mb(); + + was_empty = + vmci_qpair_produce_buf_ready(vmci_trans(vsk)->qpair) == written; + if (was_empty) { + while (!(vsk->peer_shutdown & RCV_SHUTDOWN) && + !sent_wrote && + retries < VMCI_TRANSPORT_MAX_DGRAM_RESENDS) { + err = vmci_transport_send_wrote(sk); + if (err >= 0) + sent_wrote = true; + + retries++; + } + } + + if (retries >= VMCI_TRANSPORT_MAX_DGRAM_RESENDS && !sent_wrote) { + pr_err("%p unable to send wrote notification to peer\n", + sk); + return err; + } + + return err; +} + +static void +vmci_transport_notify_pkt_handle_pkt( + struct sock *sk, + struct vmci_transport_packet *pkt, + bool bottom_half, + struct sockaddr_vm *dst, + struct sockaddr_vm *src, bool *pkt_processed) +{ + bool processed = false; + + switch (pkt->type) { + case VMCI_TRANSPORT_PACKET_TYPE_WROTE: + vmci_transport_handle_wrote(sk, pkt, bottom_half, dst, src); + processed = true; + break; + case VMCI_TRANSPORT_PACKET_TYPE_READ: + vmci_transport_handle_read(sk, pkt, bottom_half, dst, src); + processed = true; + break; + } + + if (pkt_processed) + *pkt_processed = processed; +} + +static void vmci_transport_notify_pkt_process_request(struct sock *sk) +{ + struct vsock_sock *vsk = vsock_sk(sk); + + PKT_FIELD(vsk, write_notify_window) = vmci_trans(vsk)->consume_size; + if (vmci_trans(vsk)->consume_size < + PKT_FIELD(vsk, write_notify_min_window)) + PKT_FIELD(vsk, write_notify_min_window) = + vmci_trans(vsk)->consume_size; +} + +static void vmci_transport_notify_pkt_process_negotiate(struct sock *sk) +{ + struct vsock_sock *vsk = vsock_sk(sk); + + PKT_FIELD(vsk, write_notify_window) = vmci_trans(vsk)->consume_size; + if (vmci_trans(vsk)->consume_size < + PKT_FIELD(vsk, write_notify_min_window)) + PKT_FIELD(vsk, write_notify_min_window) = + vmci_trans(vsk)->consume_size; +} + +static int +vmci_transport_notify_pkt_recv_pre_dequeue( + struct sock *sk, + size_t target, + struct vmci_transport_recv_notify_data *data) +{ + return 0; /* NOP for QState. */ +} + +static int +vmci_transport_notify_pkt_send_pre_block( + struct sock *sk, + struct vmci_transport_send_notify_data *data) +{ + return 0; /* NOP for QState. */ +} + +static int +vmci_transport_notify_pkt_send_pre_enqueue( + struct sock *sk, + struct vmci_transport_send_notify_data *data) +{ + return 0; /* NOP for QState. */ +} + +/* Socket always on control packet based operations. */ +struct vmci_transport_notify_ops vmci_transport_notify_pkt_q_state_ops = { + vmci_transport_notify_pkt_socket_init, + vmci_transport_notify_pkt_socket_destruct, + vmci_transport_notify_pkt_poll_in, + vmci_transport_notify_pkt_poll_out, + vmci_transport_notify_pkt_handle_pkt, + vmci_transport_notify_pkt_recv_init, + vmci_transport_notify_pkt_recv_pre_block, + vmci_transport_notify_pkt_recv_pre_dequeue, + vmci_transport_notify_pkt_recv_post_dequeue, + vmci_transport_notify_pkt_send_init, + vmci_transport_notify_pkt_send_pre_block, + vmci_transport_notify_pkt_send_pre_enqueue, + vmci_transport_notify_pkt_send_post_enqueue, + vmci_transport_notify_pkt_process_request, + vmci_transport_notify_pkt_process_negotiate, +}; diff --git a/net/vmw_vsock/vsock_addr.c b/net/vmw_vsock/vsock_addr.c new file mode 100644 index 000000000000..b7df1aea7c59 --- /dev/null +++ b/net/vmw_vsock/vsock_addr.c @@ -0,0 +1,86 @@ +/* + * VMware vSockets Driver + * + * Copyright (C) 2007-2012 VMware, Inc. All rights reserved. + * + * This program is free software; you can redistribute it and/or modify it + * under the terms of the GNU General Public License as published by the Free + * Software Foundation version 2 and no later version. + * + * This program is distributed in the hope that it will be useful, but WITHOUT + * ANY WARRANTY; without even the implied warranty of MERCHANTABILITY or + * FITNESS FOR A PARTICULAR PURPOSE. See the GNU General Public License for + * more details. + */ + +#include <linux/types.h> +#include <linux/socket.h> +#include <linux/stddef.h> +#include <net/sock.h> + +#include "vsock_addr.h" + +void vsock_addr_init(struct sockaddr_vm *addr, u32 cid, u32 port) +{ + memset(addr, 0, sizeof(*addr)); + addr->svm_family = AF_VSOCK; + addr->svm_cid = cid; + addr->svm_port = port; +} +EXPORT_SYMBOL_GPL(vsock_addr_init); + +int vsock_addr_validate(const struct sockaddr_vm *addr) +{ + if (!addr) + return -EFAULT; + + if (addr->svm_family != AF_VSOCK) + return -EAFNOSUPPORT; + + if (addr->svm_zero[0] != 0) + return -EINVAL; + + return 0; +} +EXPORT_SYMBOL_GPL(vsock_addr_validate); + +bool vsock_addr_bound(const struct sockaddr_vm *addr) +{ + return addr->svm_port != VMADDR_PORT_ANY; +} +EXPORT_SYMBOL_GPL(vsock_addr_bound); + +void vsock_addr_unbind(struct sockaddr_vm *addr) +{ + vsock_addr_init(addr, VMADDR_CID_ANY, VMADDR_PORT_ANY); +} +EXPORT_SYMBOL_GPL(vsock_addr_unbind); + +bool vsock_addr_equals_addr(const struct sockaddr_vm *addr, + const struct sockaddr_vm *other) +{ + return addr->svm_cid == other->svm_cid && + addr->svm_port == other->svm_port; +} +EXPORT_SYMBOL_GPL(vsock_addr_equals_addr); + +bool vsock_addr_equals_addr_any(const struct sockaddr_vm *addr, + const struct sockaddr_vm *other) +{ + return (addr->svm_cid == VMADDR_CID_ANY || + other->svm_cid == VMADDR_CID_ANY || + addr->svm_cid == other->svm_cid) && + addr->svm_port == other->svm_port; +} +EXPORT_SYMBOL_GPL(vsock_addr_equals_addr_any); + +int vsock_addr_cast(const struct sockaddr *addr, + size_t len, struct sockaddr_vm **out_addr) +{ + if (len < sizeof(**out_addr)) + return -EFAULT; + + *out_addr = (struct sockaddr_vm *)addr; + return vsock_addr_validate(*out_addr); +} +EXPORT_SYMBOL_GPL(vsock_addr_cast); diff --git a/net/vmw_vsock/vsock_addr.h b/net/vmw_vsock/vsock_addr.h new file mode 100644 index 000000000000..cdfbcefdf843 --- /dev/null +++ b/net/vmw_vsock/vsock_addr.h @@ -0,0 +1,32 @@ +/* + * VMware vSockets Driver + * + * Copyright (C) 2007-2013 VMware, Inc. All rights reserved. + * + * This program is free software; you can redistribute it and/or modify it + * under the terms of the GNU General Public License as published by the Free + * Software Foundation version 2 and no later version. + * + * This program is distributed in the hope that it will be useful, but WITHOUT + * ANY WARRANTY; without even the implied warranty of MERCHANTABILITY or + * FITNESS FOR A PARTICULAR PURPOSE. See the GNU General Public License for + * more details. + */ + +#ifndef _VSOCK_ADDR_H_ +#define _VSOCK_ADDR_H_ + +#include <linux/vm_sockets.h> + +void vsock_addr_init(struct sockaddr_vm *addr, u32 cid, u32 port); +int vsock_addr_validate(const struct sockaddr_vm *addr); +bool vsock_addr_bound(const struct sockaddr_vm *addr); +void vsock_addr_unbind(struct sockaddr_vm *addr); +bool vsock_addr_equals_addr(const struct sockaddr_vm *addr, + const struct sockaddr_vm *other); +bool vsock_addr_equals_addr_any(const struct sockaddr_vm *addr, + const struct sockaddr_vm *other); +int vsock_addr_cast(const struct sockaddr *addr, size_t len, + struct sockaddr_vm **out_addr); + +#endif diff --git a/net/vmw_vsock/vsock_version.h b/net/vmw_vsock/vsock_version.h new file mode 100644 index 000000000000..4df7f5e2151c --- /dev/null +++ b/net/vmw_vsock/vsock_version.h @@ -0,0 +1,22 @@ +/* + * VMware vSockets Driver + * + * Copyright (C) 2011-2012 VMware, Inc. All rights reserved. + * + * This program is free software; you can redistribute it and/or modify it + * under the terms of the GNU General Public License as published by the Free + * Software Foundation version 2 and no later version. + * + * This program is distributed in the hope that it will be useful, but WITHOUT + * ANY WARRANTY; without even the implied warranty of MERCHANTABILITY or + * FITNESS FOR A PARTICULAR PURPOSE. See the GNU General Public License for + * more details. + */ + +#ifndef _VSOCK_VERSION_H_ +#define _VSOCK_VERSION_H_ + +#define VSOCK_DRIVER_VERSION_PARTS { 1, 0, 0, 0 } +#define VSOCK_DRIVER_VERSION_STRING "1.0.0.0-k" + +#endif /* _VSOCK_VERSION_H_ */ diff --git a/net/wanrouter/Kconfig b/net/wanrouter/Kconfig deleted file mode 100644 index a157a2e64e18..000000000000 --- a/net/wanrouter/Kconfig +++ /dev/null @@ -1,27 +0,0 @@ -# -# Configuration for WAN router -# - -config WAN_ROUTER - tristate "WAN router (DEPRECATED)" - depends on EXPERIMENTAL - ---help--- - Wide Area Networks (WANs), such as X.25, frame relay and leased - lines, are used to interconnect Local Area Networks (LANs) over vast - distances with data transfer rates significantly higher than those - achievable with commonly used asynchronous modem connections. - Usually, a quite expensive external device called a `WAN router' is - needed to connect to a WAN. - - As an alternative, WAN routing can be built into the Linux kernel. - With relatively inexpensive WAN interface cards available on the - market, a perfectly usable router can be built for less than half - the price of an external router. If you have one of those cards and - wish to use your Linux box as a WAN router, say Y here and also to - the WAN driver for your card, below. You will then need the - wan-tools package which is available from <ftp://ftp.sangoma.com/>. - - To compile WAN routing support as a module, choose M here: the - module will be called wanrouter. - - If unsure, say N. diff --git a/net/wanrouter/Makefile b/net/wanrouter/Makefile deleted file mode 100644 index 4da14bc48078..000000000000 --- a/net/wanrouter/Makefile +++ /dev/null @@ -1,7 +0,0 @@ -# -# Makefile for the Linux WAN router layer. -# - -obj-$(CONFIG_WAN_ROUTER) += wanrouter.o - -wanrouter-y := wanproc.o wanmain.o diff --git a/net/wanrouter/patchlevel b/net/wanrouter/patchlevel deleted file mode 100644 index c043eea7767e..000000000000 --- a/net/wanrouter/patchlevel +++ /dev/null @@ -1 +0,0 @@ -2.2.1 diff --git a/net/wanrouter/wanmain.c b/net/wanrouter/wanmain.c deleted file mode 100644 index 2ab785064b7e..000000000000 --- a/net/wanrouter/wanmain.c +++ /dev/null @@ -1,782 +0,0 @@ -/***************************************************************************** -* wanmain.c WAN Multiprotocol Router Module. Main code. -* -* This module is completely hardware-independent and provides -* the following common services for the WAN Link Drivers: -* o WAN device management (registering, unregistering) -* o Network interface management -* o Physical connection management (dial-up, incoming calls) -* o Logical connection management (switched virtual circuits) -* o Protocol encapsulation/decapsulation -* -* Author: Gideon Hack -* -* Copyright: (c) 1995-1999 Sangoma Technologies Inc. -* -* This program is free software; you can redistribute it and/or -* modify it under the terms of the GNU General Public License -* as published by the Free Software Foundation; either version -* 2 of the License, or (at your option) any later version. -* ============================================================================ -* Nov 24, 2000 Nenad Corbic Updated for 2.4.X kernels -* Nov 07, 2000 Nenad Corbic Fixed the Mulit-Port PPP for kernels 2.2.16 and -* greater. -* Aug 2, 2000 Nenad Corbic Block the Multi-Port PPP from running on -* kernels 2.2.16 or greater. The SyncPPP -* has changed. -* Jul 13, 2000 Nenad Corbic Added SyncPPP support -* Added extra debugging in device_setup(). -* Oct 01, 1999 Gideon Hack Update for s514 PCI card -* Dec 27, 1996 Gene Kozin Initial version (based on Sangoma's WANPIPE) -* Jan 16, 1997 Gene Kozin router_devlist made public -* Jan 31, 1997 Alan Cox Hacked it about a bit for 2.1 -* Jun 27, 1997 Alan Cox realigned with vendor code -* Oct 15, 1997 Farhan Thawar changed wan_encapsulate to add a pad byte of 0 -* Apr 20, 1998 Alan Cox Fixed 2.1 symbols -* May 17, 1998 K. Baranowski Fixed SNAP encapsulation in wan_encapsulate -* Dec 15, 1998 Arnaldo Melo support for firmwares of up to 128000 bytes -* check wandev->setup return value -* Dec 22, 1998 Arnaldo Melo vmalloc/vfree used in device_setup to allocate -* kernel memory and copy configuration data to -* kernel space (for big firmwares) -* Jun 02, 1999 Gideon Hack Updates for Linux 2.0.X and 2.2.X kernels. -*****************************************************************************/ - -#include <linux/stddef.h> /* offsetof(), etc. */ -#include <linux/capability.h> -#include <linux/errno.h> /* return codes */ -#include <linux/kernel.h> -#include <linux/module.h> /* support for loadable modules */ -#include <linux/slab.h> /* kmalloc(), kfree() */ -#include <linux/mutex.h> -#include <linux/mm.h> -#include <linux/string.h> /* inline mem*, str* functions */ - -#include <asm/byteorder.h> /* htons(), etc. */ -#include <linux/wanrouter.h> /* WAN router API definitions */ - -#include <linux/vmalloc.h> /* vmalloc, vfree */ -#include <asm/uaccess.h> /* copy_to/from_user */ -#include <linux/init.h> /* __initfunc et al. */ - -#define DEV_TO_SLAVE(dev) (*((struct net_device **)netdev_priv(dev))) - -/* - * Function Prototypes - */ - -/* - * WAN device IOCTL handlers - */ - -static DEFINE_MUTEX(wanrouter_mutex); -static int wanrouter_device_setup(struct wan_device *wandev, - wandev_conf_t __user *u_conf); -static int wanrouter_device_stat(struct wan_device *wandev, - wandev_stat_t __user *u_stat); -static int wanrouter_device_shutdown(struct wan_device *wandev); -static int wanrouter_device_new_if(struct wan_device *wandev, - wanif_conf_t __user *u_conf); -static int wanrouter_device_del_if(struct wan_device *wandev, - char __user *u_name); - -/* - * Miscellaneous - */ - -static struct wan_device *wanrouter_find_device(char *name); -static int wanrouter_delete_interface(struct wan_device *wandev, char *name); -static void lock_adapter_irq(spinlock_t *lock, unsigned long *smp_flags) - __acquires(lock); -static void unlock_adapter_irq(spinlock_t *lock, unsigned long *smp_flags) - __releases(lock); - - - -/* - * Global Data - */ - -static char wanrouter_fullname[] = "Sangoma WANPIPE Router"; -static char wanrouter_copyright[] = "(c) 1995-2000 Sangoma Technologies Inc."; -static char wanrouter_modname[] = ROUTER_NAME; /* short module name */ -struct wan_device* wanrouter_router_devlist; /* list of registered devices */ - -/* - * Organize Unique Identifiers for encapsulation/decapsulation - */ - -#if 0 -static unsigned char wanrouter_oui_ether[] = { 0x00, 0x00, 0x00 }; -static unsigned char wanrouter_oui_802_2[] = { 0x00, 0x80, 0xC2 }; -#endif - -static int __init wanrouter_init(void) -{ - int err; - - printk(KERN_INFO "%s v%u.%u %s\n", - wanrouter_fullname, ROUTER_VERSION, ROUTER_RELEASE, - wanrouter_copyright); - - err = wanrouter_proc_init(); - if (err) - printk(KERN_INFO "%s: can't create entry in proc filesystem!\n", - wanrouter_modname); - - return err; -} - -static void __exit wanrouter_cleanup (void) -{ - wanrouter_proc_cleanup(); -} - -/* - * This is just plain dumb. We should move the bugger to drivers/net/wan, - * slap it first in directory and make it module_init(). The only reason - * for subsys_initcall() here is that net goes after drivers (why, BTW?) - */ -subsys_initcall(wanrouter_init); -module_exit(wanrouter_cleanup); - -/* - * Kernel APIs - */ - -/* - * Register WAN device. - * o verify device credentials - * o create an entry for the device in the /proc/net/router directory - * o initialize internally maintained fields of the wan_device structure - * o link device data space to a singly-linked list - * o if it's the first device, then start kernel 'thread' - * o increment module use count - * - * Return: - * 0 Ok - * < 0 error. - * - * Context: process - */ - - -int register_wan_device(struct wan_device *wandev) -{ - int err, namelen; - - if ((wandev == NULL) || (wandev->magic != ROUTER_MAGIC) || - (wandev->name == NULL)) - return -EINVAL; - - namelen = strlen(wandev->name); - if (!namelen || (namelen > WAN_DRVNAME_SZ)) - return -EINVAL; - - if (wanrouter_find_device(wandev->name)) - return -EEXIST; - -#ifdef WANDEBUG - printk(KERN_INFO "%s: registering WAN device %s\n", - wanrouter_modname, wandev->name); -#endif - - /* - * Register /proc directory entry - */ - err = wanrouter_proc_add(wandev); - if (err) { - printk(KERN_INFO - "%s: can't create /proc/net/router/%s entry!\n", - wanrouter_modname, wandev->name); - return err; - } - - /* - * Initialize fields of the wan_device structure maintained by the - * router and update local data. - */ - - wandev->ndev = 0; - wandev->dev = NULL; - wandev->next = wanrouter_router_devlist; - wanrouter_router_devlist = wandev; - return 0; -} - -/* - * Unregister WAN device. - * o shut down device - * o unlink device data space from the linked list - * o delete device entry in the /proc/net/router directory - * o decrement module use count - * - * Return: 0 Ok - * <0 error. - * Context: process - */ - - -int unregister_wan_device(char *name) -{ - struct wan_device *wandev, *prev; - - if (name == NULL) - return -EINVAL; - - for (wandev = wanrouter_router_devlist, prev = NULL; - wandev && strcmp(wandev->name, name); - prev = wandev, wandev = wandev->next) - ; - if (wandev == NULL) - return -ENODEV; - -#ifdef WANDEBUG - printk(KERN_INFO "%s: unregistering WAN device %s\n", - wanrouter_modname, name); -#endif - - if (wandev->state != WAN_UNCONFIGURED) - wanrouter_device_shutdown(wandev); - - if (prev) - prev->next = wandev->next; - else - wanrouter_router_devlist = wandev->next; - - wanrouter_proc_delete(wandev); - return 0; -} - -#if 0 - -/* - * Encapsulate packet. - * - * Return: encapsulation header size - * < 0 - unsupported Ethertype - * - * Notes: - * 1. This function may be called on interrupt context. - */ - - -int wanrouter_encapsulate(struct sk_buff *skb, struct net_device *dev, - unsigned short type) -{ - int hdr_len = 0; - - switch (type) { - case ETH_P_IP: /* IP datagram encapsulation */ - hdr_len += 1; - skb_push(skb, 1); - skb->data[0] = NLPID_IP; - break; - - case ETH_P_IPX: /* SNAP encapsulation */ - case ETH_P_ARP: - hdr_len += 7; - skb_push(skb, 7); - skb->data[0] = 0; - skb->data[1] = NLPID_SNAP; - skb_copy_to_linear_data_offset(skb, 2, wanrouter_oui_ether, - sizeof(wanrouter_oui_ether)); - *((unsigned short*)&skb->data[5]) = htons(type); - break; - - default: /* Unknown packet type */ - printk(KERN_INFO - "%s: unsupported Ethertype 0x%04X on interface %s!\n", - wanrouter_modname, type, dev->name); - hdr_len = -EINVAL; - } - return hdr_len; -} - - -/* - * Decapsulate packet. - * - * Return: Ethertype (in network order) - * 0 unknown encapsulation - * - * Notes: - * 1. This function may be called on interrupt context. - */ - - -__be16 wanrouter_type_trans(struct sk_buff *skb, struct net_device *dev) -{ - int cnt = skb->data[0] ? 0 : 1; /* there may be a pad present */ - __be16 ethertype; - - switch (skb->data[cnt]) { - case NLPID_IP: /* IP datagramm */ - ethertype = htons(ETH_P_IP); - cnt += 1; - break; - - case NLPID_SNAP: /* SNAP encapsulation */ - if (memcmp(&skb->data[cnt + 1], wanrouter_oui_ether, - sizeof(wanrouter_oui_ether))){ - printk(KERN_INFO - "%s: unsupported SNAP OUI %02X-%02X-%02X " - "on interface %s!\n", wanrouter_modname, - skb->data[cnt+1], skb->data[cnt+2], - skb->data[cnt+3], dev->name); - return 0; - } - ethertype = *((__be16*)&skb->data[cnt+4]); - cnt += 6; - break; - - /* add other protocols, e.g. CLNP, ESIS, ISIS, if needed */ - - default: - printk(KERN_INFO - "%s: unsupported NLPID 0x%02X on interface %s!\n", - wanrouter_modname, skb->data[cnt], dev->name); - return 0; - } - skb->protocol = ethertype; - skb->pkt_type = PACKET_HOST; /* Physically point to point */ - skb_pull(skb, cnt); - skb_reset_mac_header(skb); - return ethertype; -} - -#endif /* 0 */ - -/* - * WAN device IOCTL. - * o find WAN device associated with this node - * o execute requested action or pass command to the device driver - */ - -long wanrouter_ioctl(struct file *file, unsigned int cmd, unsigned long arg) -{ - struct inode *inode = file->f_path.dentry->d_inode; - int err = 0; - struct proc_dir_entry *dent; - struct wan_device *wandev; - void __user *data = (void __user *)arg; - - if (!capable(CAP_NET_ADMIN)) - return -EPERM; - - if ((cmd >> 8) != ROUTER_IOCTL) - return -EINVAL; - - dent = PDE(inode); - if ((dent == NULL) || (dent->data == NULL)) - return -EINVAL; - - wandev = dent->data; - if (wandev->magic != ROUTER_MAGIC) - return -EINVAL; - - mutex_lock(&wanrouter_mutex); - switch (cmd) { - case ROUTER_SETUP: - err = wanrouter_device_setup(wandev, data); - break; - - case ROUTER_DOWN: - err = wanrouter_device_shutdown(wandev); - break; - - case ROUTER_STAT: - err = wanrouter_device_stat(wandev, data); - break; - - case ROUTER_IFNEW: - err = wanrouter_device_new_if(wandev, data); - break; - - case ROUTER_IFDEL: - err = wanrouter_device_del_if(wandev, data); - break; - - case ROUTER_IFSTAT: - break; - - default: - if ((cmd >= ROUTER_USER) && - (cmd <= ROUTER_USER_MAX) && - wandev->ioctl) - err = wandev->ioctl(wandev, cmd, arg); - else err = -EINVAL; - } - mutex_unlock(&wanrouter_mutex); - return err; -} - -/* - * WAN Driver IOCTL Handlers - */ - -/* - * Setup WAN link device. - * o verify user address space - * o allocate kernel memory and copy configuration data to kernel space - * o if configuration data includes extension, copy it to kernel space too - * o call driver's setup() entry point - */ - -static int wanrouter_device_setup(struct wan_device *wandev, - wandev_conf_t __user *u_conf) -{ - void *data = NULL; - wandev_conf_t *conf; - int err = -EINVAL; - - if (wandev->setup == NULL) { /* Nothing to do ? */ - printk(KERN_INFO "%s: ERROR, No setup script: wandev->setup()\n", - wandev->name); - return 0; - } - - conf = kmalloc(sizeof(wandev_conf_t), GFP_KERNEL); - if (conf == NULL){ - printk(KERN_INFO "%s: ERROR, Failed to allocate kernel memory !\n", - wandev->name); - return -ENOBUFS; - } - - if (copy_from_user(conf, u_conf, sizeof(wandev_conf_t))) { - printk(KERN_INFO "%s: Failed to copy user config data to kernel space!\n", - wandev->name); - kfree(conf); - return -EFAULT; - } - - if (conf->magic != ROUTER_MAGIC) { - kfree(conf); - printk(KERN_INFO "%s: ERROR, Invalid MAGIC Number\n", - wandev->name); - return -EINVAL; - } - - if (conf->data_size && conf->data) { - if (conf->data_size > 128000) { - printk(KERN_INFO - "%s: ERROR, Invalid firmware data size %i !\n", - wandev->name, conf->data_size); - kfree(conf); - return -EINVAL; - } - - data = vmalloc(conf->data_size); - if (!data) { - printk(KERN_INFO - "%s: ERROR, Failed allocate kernel memory !\n", - wandev->name); - kfree(conf); - return -ENOBUFS; - } - if (!copy_from_user(data, conf->data, conf->data_size)) { - conf->data = data; - err = wandev->setup(wandev, conf); - } else { - printk(KERN_INFO - "%s: ERROR, Failed to copy from user data !\n", - wandev->name); - err = -EFAULT; - } - vfree(data); - } else { - printk(KERN_INFO - "%s: ERROR, No firmware found ! Firmware size = %i !\n", - wandev->name, conf->data_size); - } - - kfree(conf); - return err; -} - -/* - * Shutdown WAN device. - * o delete all not opened logical channels for this device - * o call driver's shutdown() entry point - */ - -static int wanrouter_device_shutdown(struct wan_device *wandev) -{ - struct net_device *dev; - int err=0; - - if (wandev->state == WAN_UNCONFIGURED) - return 0; - - printk(KERN_INFO "\n%s: Shutting Down!\n",wandev->name); - - for (dev = wandev->dev; dev;) { - err = wanrouter_delete_interface(wandev, dev->name); - if (err) - return err; - /* The above function deallocates the current dev - * structure. Therefore, we cannot use netdev_priv(dev) - * as the next element: wandev->dev points to the - * next element */ - dev = wandev->dev; - } - - if (wandev->ndev) - return -EBUSY; /* there are opened interfaces */ - - if (wandev->shutdown) - err=wandev->shutdown(wandev); - - return err; -} - -/* - * Get WAN device status & statistics. - */ - -static int wanrouter_device_stat(struct wan_device *wandev, - wandev_stat_t __user *u_stat) -{ - wandev_stat_t stat; - - memset(&stat, 0, sizeof(stat)); - - /* Ask device driver to update device statistics */ - if ((wandev->state != WAN_UNCONFIGURED) && wandev->update) - wandev->update(wandev); - - /* Fill out structure */ - stat.ndev = wandev->ndev; - stat.state = wandev->state; - - if (copy_to_user(u_stat, &stat, sizeof(stat))) - return -EFAULT; - - return 0; -} - -/* - * Create new WAN interface. - * o verify user address space - * o copy configuration data to kernel address space - * o allocate network interface data space - * o call driver's new_if() entry point - * o make sure there is no interface name conflict - * o register network interface - */ - -static int wanrouter_device_new_if(struct wan_device *wandev, - wanif_conf_t __user *u_conf) -{ - wanif_conf_t *cnf; - struct net_device *dev = NULL; - int err; - - if ((wandev->state == WAN_UNCONFIGURED) || (wandev->new_if == NULL)) - return -ENODEV; - - cnf = kmalloc(sizeof(wanif_conf_t), GFP_KERNEL); - if (!cnf) - return -ENOBUFS; - - err = -EFAULT; - if (copy_from_user(cnf, u_conf, sizeof(wanif_conf_t))) - goto out; - - err = -EINVAL; - if (cnf->magic != ROUTER_MAGIC) - goto out; - - if (cnf->config_id == WANCONFIG_MPPP) { - printk(KERN_INFO "%s: Wanpipe Mulit-Port PPP support has not been compiled in!\n", - wandev->name); - err = -EPROTONOSUPPORT; - goto out; - } else { - err = wandev->new_if(wandev, dev, cnf); - } - - if (!err) { - /* Register network interface. This will invoke init() - * function supplied by the driver. If device registered - * successfully, add it to the interface list. - */ - -#ifdef WANDEBUG - printk(KERN_INFO "%s: registering interface %s...\n", - wanrouter_modname, dev->name); -#endif - - err = register_netdev(dev); - if (!err) { - struct net_device *slave = NULL; - unsigned long smp_flags=0; - - lock_adapter_irq(&wandev->lock, &smp_flags); - - if (wandev->dev == NULL) { - wandev->dev = dev; - } else { - for (slave=wandev->dev; - DEV_TO_SLAVE(slave); - slave = DEV_TO_SLAVE(slave)) - DEV_TO_SLAVE(slave) = dev; - } - ++wandev->ndev; - - unlock_adapter_irq(&wandev->lock, &smp_flags); - err = 0; /* done !!! */ - goto out; - } - if (wandev->del_if) - wandev->del_if(wandev, dev); - free_netdev(dev); - } - -out: - kfree(cnf); - return err; -} - - -/* - * Delete WAN logical channel. - * o verify user address space - * o copy configuration data to kernel address space - */ - -static int wanrouter_device_del_if(struct wan_device *wandev, char __user *u_name) -{ - char name[WAN_IFNAME_SZ + 1]; - int err = 0; - - if (wandev->state == WAN_UNCONFIGURED) - return -ENODEV; - - memset(name, 0, sizeof(name)); - - if (copy_from_user(name, u_name, WAN_IFNAME_SZ)) - return -EFAULT; - - err = wanrouter_delete_interface(wandev, name); - if (err) - return err; - - /* If last interface being deleted, shutdown card - * This helps with administration at leaf nodes - * (You can tell if the person at the other end of the phone - * has an interface configured) and avoids DoS vulnerabilities - * in binary driver files - this fixes a problem with the current - * Sangoma driver going into strange states when all the network - * interfaces are deleted and the link irrecoverably disconnected. - */ - - if (!wandev->ndev && wandev->shutdown) - err = wandev->shutdown(wandev); - - return err; -} - -/* - * Miscellaneous Functions - */ - -/* - * Find WAN device by name. - * Return pointer to the WAN device data space or NULL if device not found. - */ - -static struct wan_device *wanrouter_find_device(char *name) -{ - struct wan_device *wandev; - - for (wandev = wanrouter_router_devlist; - wandev && strcmp(wandev->name, name); - wandev = wandev->next); - return wandev; -} - -/* - * Delete WAN logical channel identified by its name. - * o find logical channel by its name - * o call driver's del_if() entry point - * o unregister network interface - * o unlink channel data space from linked list of channels - * o release channel data space - * - * Return: 0 success - * -ENODEV channel not found. - * -EBUSY interface is open - * - * Note: If (force != 0), then device will be destroyed even if interface - * associated with it is open. It's caller's responsibility to make - * sure that opened interfaces are not removed! - */ - -static int wanrouter_delete_interface(struct wan_device *wandev, char *name) -{ - struct net_device *dev = NULL, *prev = NULL; - unsigned long smp_flags=0; - - lock_adapter_irq(&wandev->lock, &smp_flags); - dev = wandev->dev; - prev = NULL; - while (dev && strcmp(name, dev->name)) { - struct net_device **slave = netdev_priv(dev); - prev = dev; - dev = *slave; - } - unlock_adapter_irq(&wandev->lock, &smp_flags); - - if (dev == NULL) - return -ENODEV; /* interface not found */ - - if (netif_running(dev)) - return -EBUSY; /* interface in use */ - - if (wandev->del_if) - wandev->del_if(wandev, dev); - - lock_adapter_irq(&wandev->lock, &smp_flags); - if (prev) { - struct net_device **prev_slave = netdev_priv(prev); - struct net_device **slave = netdev_priv(dev); - - *prev_slave = *slave; - } else { - struct net_device **slave = netdev_priv(dev); - wandev->dev = *slave; - } - --wandev->ndev; - unlock_adapter_irq(&wandev->lock, &smp_flags); - - printk(KERN_INFO "%s: unregistering '%s'\n", wandev->name, dev->name); - - unregister_netdev(dev); - - free_netdev(dev); - - return 0; -} - -static void lock_adapter_irq(spinlock_t *lock, unsigned long *smp_flags) - __acquires(lock) -{ - spin_lock_irqsave(lock, *smp_flags); -} - - -static void unlock_adapter_irq(spinlock_t *lock, unsigned long *smp_flags) - __releases(lock) -{ - spin_unlock_irqrestore(lock, *smp_flags); -} - -EXPORT_SYMBOL(register_wan_device); -EXPORT_SYMBOL(unregister_wan_device); - -MODULE_LICENSE("GPL"); - -/* - * End - */ diff --git a/net/wanrouter/wanproc.c b/net/wanrouter/wanproc.c deleted file mode 100644 index c43612ee96bb..000000000000 --- a/net/wanrouter/wanproc.c +++ /dev/null @@ -1,380 +0,0 @@ -/***************************************************************************** -* wanproc.c WAN Router Module. /proc filesystem interface. -* -* This module is completely hardware-independent and provides -* access to the router using Linux /proc filesystem. -* -* Author: Gideon Hack -* -* Copyright: (c) 1995-1999 Sangoma Technologies Inc. -* -* This program is free software; you can redistribute it and/or -* modify it under the terms of the GNU General Public License -* as published by the Free Software Foundation; either version -* 2 of the License, or (at your option) any later version. -* ============================================================================ -* Jun 02, 1999 Gideon Hack Updates for Linux 2.2.X kernels. -* Jun 29, 1997 Alan Cox Merged with 1.0.3 vendor code -* Jan 29, 1997 Gene Kozin v1.0.1. Implemented /proc read routines -* Jan 30, 1997 Alan Cox Hacked around for 2.1 -* Dec 13, 1996 Gene Kozin Initial version (based on Sangoma's WANPIPE) -*****************************************************************************/ - -#include <linux/init.h> /* __initfunc et al. */ -#include <linux/stddef.h> /* offsetof(), etc. */ -#include <linux/errno.h> /* return codes */ -#include <linux/kernel.h> -#include <linux/module.h> -#include <linux/wanrouter.h> /* WAN router API definitions */ -#include <linux/seq_file.h> -#include <linux/mutex.h> - -#include <net/net_namespace.h> -#include <asm/io.h> - -#define PROC_STATS_FORMAT "%30s: %12lu\n" - -/****** Defines and Macros **************************************************/ - -#define PROT_DECODE(prot) ((prot == WANCONFIG_FR) ? " FR" :\ - (prot == WANCONFIG_X25) ? " X25" : \ - (prot == WANCONFIG_PPP) ? " PPP" : \ - (prot == WANCONFIG_CHDLC) ? " CHDLC": \ - (prot == WANCONFIG_MPPP) ? " MPPP" : \ - " Unknown" ) - -/****** Function Prototypes *************************************************/ - -#ifdef CONFIG_PROC_FS - -/* Miscellaneous */ - -/* - * Structures for interfacing with the /proc filesystem. - * Router creates its own directory /proc/net/router with the following - * entries: - * config device configuration - * status global device statistics - * <device> entry for each WAN device - */ - -/* - * Generic /proc/net/router/<file> file and inode operations - */ - -/* - * /proc/net/router - */ - -static DEFINE_MUTEX(config_mutex); -static struct proc_dir_entry *proc_router; - -/* Strings */ - -/* - * Interface functions - */ - -/****** Proc filesystem entry points ****************************************/ - -/* - * Iterator - */ -static void *r_start(struct seq_file *m, loff_t *pos) -{ - struct wan_device *wandev; - loff_t l = *pos; - - mutex_lock(&config_mutex); - if (!l--) - return SEQ_START_TOKEN; - for (wandev = wanrouter_router_devlist; l-- && wandev; - wandev = wandev->next) - ; - return wandev; -} - -static void *r_next(struct seq_file *m, void *v, loff_t *pos) -{ - struct wan_device *wandev = v; - (*pos)++; - return (v == SEQ_START_TOKEN) ? wanrouter_router_devlist : wandev->next; -} - -static void r_stop(struct seq_file *m, void *v) -{ - mutex_unlock(&config_mutex); -} - -static int config_show(struct seq_file *m, void *v) -{ - struct wan_device *p = v; - if (v == SEQ_START_TOKEN) { - seq_puts(m, "Device name | port |IRQ|DMA| mem.addr |" - "mem.size|option1|option2|option3|option4\n"); - return 0; - } - if (!p->state) - return 0; - seq_printf(m, "%-15s|0x%-4X|%3u|%3u| 0x%-8lX |0x%-6X|%7u|%7u|%7u|%7u\n", - p->name, p->ioport, p->irq, p->dma, p->maddr, p->msize, - p->hw_opt[0], p->hw_opt[1], p->hw_opt[2], p->hw_opt[3]); - return 0; -} - -static int status_show(struct seq_file *m, void *v) -{ - struct wan_device *p = v; - if (v == SEQ_START_TOKEN) { - seq_puts(m, "Device name |protocol|station|interface|" - "clocking|baud rate| MTU |ndev|link state\n"); - return 0; - } - if (!p->state) - return 0; - seq_printf(m, "%-15s|%-8s| %-7s| %-9s|%-8s|%9u|%5u|%3u |", - p->name, - PROT_DECODE(p->config_id), - p->config_id == WANCONFIG_FR ? - (p->station ? "Node" : "CPE") : - (p->config_id == WANCONFIG_X25 ? - (p->station ? "DCE" : "DTE") : - ("N/A")), - p->interface ? "V.35" : "RS-232", - p->clocking ? "internal" : "external", - p->bps, - p->mtu, - p->ndev); - - switch (p->state) { - case WAN_UNCONFIGURED: - seq_printf(m, "%-12s\n", "unconfigured"); - break; - case WAN_DISCONNECTED: - seq_printf(m, "%-12s\n", "disconnected"); - break; - case WAN_CONNECTING: - seq_printf(m, "%-12s\n", "connecting"); - break; - case WAN_CONNECTED: - seq_printf(m, "%-12s\n", "connected"); - break; - default: - seq_printf(m, "%-12s\n", "invalid"); - break; - } - return 0; -} - -static const struct seq_operations config_op = { - .start = r_start, - .next = r_next, - .stop = r_stop, - .show = config_show, -}; - -static const struct seq_operations status_op = { - .start = r_start, - .next = r_next, - .stop = r_stop, - .show = status_show, -}; - -static int config_open(struct inode *inode, struct file *file) -{ - return seq_open(file, &config_op); -} - -static int status_open(struct inode *inode, struct file *file) -{ - return seq_open(file, &status_op); -} - -static const struct file_operations config_fops = { - .owner = THIS_MODULE, - .open = config_open, - .read = seq_read, - .llseek = seq_lseek, - .release = seq_release, -}; - -static const struct file_operations status_fops = { - .owner = THIS_MODULE, - .open = status_open, - .read = seq_read, - .llseek = seq_lseek, - .release = seq_release, -}; - -static int wandev_show(struct seq_file *m, void *v) -{ - struct wan_device *wandev = m->private; - - if (wandev->magic != ROUTER_MAGIC) - return 0; - - if (!wandev->state) { - seq_puts(m, "device is not configured!\n"); - return 0; - } - - /* Update device statistics */ - if (wandev->update) { - int err = wandev->update(wandev); - if (err == -EAGAIN) { - seq_puts(m, "Device is busy!\n"); - return 0; - } - if (err) { - seq_puts(m, "Device is not configured!\n"); - return 0; - } - } - - seq_printf(m, PROC_STATS_FORMAT, - "total packets received", wandev->stats.rx_packets); - seq_printf(m, PROC_STATS_FORMAT, - "total packets transmitted", wandev->stats.tx_packets); - seq_printf(m, PROC_STATS_FORMAT, - "total bytes received", wandev->stats.rx_bytes); - seq_printf(m, PROC_STATS_FORMAT, - "total bytes transmitted", wandev->stats.tx_bytes); - seq_printf(m, PROC_STATS_FORMAT, - "bad packets received", wandev->stats.rx_errors); - seq_printf(m, PROC_STATS_FORMAT, - "packet transmit problems", wandev->stats.tx_errors); - seq_printf(m, PROC_STATS_FORMAT, - "received frames dropped", wandev->stats.rx_dropped); - seq_printf(m, PROC_STATS_FORMAT, - "transmit frames dropped", wandev->stats.tx_dropped); - seq_printf(m, PROC_STATS_FORMAT, - "multicast packets received", wandev->stats.multicast); - seq_printf(m, PROC_STATS_FORMAT, - "transmit collisions", wandev->stats.collisions); - seq_printf(m, PROC_STATS_FORMAT, - "receive length errors", wandev->stats.rx_length_errors); - seq_printf(m, PROC_STATS_FORMAT, - "receiver overrun errors", wandev->stats.rx_over_errors); - seq_printf(m, PROC_STATS_FORMAT, - "CRC errors", wandev->stats.rx_crc_errors); - seq_printf(m, PROC_STATS_FORMAT, - "frame format errors (aborts)", wandev->stats.rx_frame_errors); - seq_printf(m, PROC_STATS_FORMAT, - "receiver fifo overrun", wandev->stats.rx_fifo_errors); - seq_printf(m, PROC_STATS_FORMAT, - "receiver missed packet", wandev->stats.rx_missed_errors); - seq_printf(m, PROC_STATS_FORMAT, - "aborted frames transmitted", wandev->stats.tx_aborted_errors); - return 0; -} - -static int wandev_open(struct inode *inode, struct file *file) -{ - return single_open(file, wandev_show, PDE(inode)->data); -} - -static const struct file_operations wandev_fops = { - .owner = THIS_MODULE, - .open = wandev_open, - .read = seq_read, - .llseek = seq_lseek, - .release = single_release, - .unlocked_ioctl = wanrouter_ioctl, -}; - -/* - * Initialize router proc interface. - */ - -int __init wanrouter_proc_init(void) -{ - struct proc_dir_entry *p; - proc_router = proc_mkdir(ROUTER_NAME, init_net.proc_net); - if (!proc_router) - goto fail; - - p = proc_create("config", S_IRUGO, proc_router, &config_fops); - if (!p) - goto fail_config; - p = proc_create("status", S_IRUGO, proc_router, &status_fops); - if (!p) - goto fail_stat; - return 0; -fail_stat: - remove_proc_entry("config", proc_router); -fail_config: - remove_proc_entry(ROUTER_NAME, init_net.proc_net); -fail: - return -ENOMEM; -} - -/* - * Clean up router proc interface. - */ - -void wanrouter_proc_cleanup(void) -{ - remove_proc_entry("config", proc_router); - remove_proc_entry("status", proc_router); - remove_proc_entry(ROUTER_NAME, init_net.proc_net); -} - -/* - * Add directory entry for WAN device. - */ - -int wanrouter_proc_add(struct wan_device* wandev) -{ - if (wandev->magic != ROUTER_MAGIC) - return -EINVAL; - - wandev->dent = proc_create(wandev->name, S_IRUGO, - proc_router, &wandev_fops); - if (!wandev->dent) - return -ENOMEM; - wandev->dent->data = wandev; - return 0; -} - -/* - * Delete directory entry for WAN device. - */ -int wanrouter_proc_delete(struct wan_device* wandev) -{ - if (wandev->magic != ROUTER_MAGIC) - return -EINVAL; - remove_proc_entry(wandev->name, proc_router); - return 0; -} - -#else - -/* - * No /proc - output stubs - */ - -int __init wanrouter_proc_init(void) -{ - return 0; -} - -void wanrouter_proc_cleanup(void) -{ -} - -int wanrouter_proc_add(struct wan_device *wandev) -{ - return 0; -} - -int wanrouter_proc_delete(struct wan_device *wandev) -{ - return 0; -} - -#endif - -/* - * End - */ - diff --git a/net/wireless/core.c b/net/wireless/core.c index 33b75b9b8efa..5ffff039b017 100644 --- a/net/wireless/core.c +++ b/net/wireless/core.c @@ -875,8 +875,7 @@ static int cfg80211_netdev_notifier_call(struct notifier_block *nb, /* allow mac80211 to determine the timeout */ wdev->ps_timeout = -1; - if (!dev->ethtool_ops) - dev->ethtool_ops = &cfg80211_ethtool_ops; + netdev_set_default_ethtool_ops(dev, &cfg80211_ethtool_ops); if ((wdev->iftype == NL80211_IFTYPE_STATION || wdev->iftype == NL80211_IFTYPE_P2P_CLIENT || diff --git a/net/wireless/ethtool.c b/net/wireless/ethtool.c index 48c48ffafa1d..e37862f1b127 100644 --- a/net/wireless/ethtool.c +++ b/net/wireless/ethtool.c @@ -15,10 +15,10 @@ static void cfg80211_get_drvinfo(struct net_device *dev, strlcpy(info->version, init_utsname()->release, sizeof(info->version)); if (wdev->wiphy->fw_version[0]) - strncpy(info->fw_version, wdev->wiphy->fw_version, + strlcpy(info->fw_version, wdev->wiphy->fw_version, sizeof(info->fw_version)); else - strncpy(info->fw_version, "N/A", sizeof(info->fw_version)); + strlcpy(info->fw_version, "N/A", sizeof(info->fw_version)); strlcpy(info->bus_info, dev_name(wiphy_dev(wdev->wiphy)), sizeof(info->bus_info)); diff --git a/net/wireless/reg.c b/net/wireless/reg.c index 93ab840957a0..98532c00242d 100644 --- a/net/wireless/reg.c +++ b/net/wireless/reg.c @@ -2265,7 +2265,6 @@ int set_regdom(const struct ieee80211_regdomain *rd) return r; } -#ifdef CONFIG_HOTPLUG int reg_device_uevent(struct device *dev, struct kobj_uevent_env *env) { struct regulatory_request *lr; @@ -2285,12 +2284,6 @@ int reg_device_uevent(struct device *dev, struct kobj_uevent_env *env) alpha2[0], alpha2[1]); return 0; } -#else -int reg_device_uevent(struct device *dev, struct kobj_uevent_env *env) -{ - return -ENODEV; -} -#endif /* CONFIG_HOTPLUG */ void wiphy_regulatory_register(struct wiphy *wiphy) { diff --git a/net/wireless/sysfs.c b/net/wireless/sysfs.c index 73bf39f11314..238ee49b3868 100644 --- a/net/wireless/sysfs.c +++ b/net/wireless/sysfs.c @@ -77,13 +77,11 @@ static void wiphy_dev_release(struct device *dev) cfg80211_dev_free(rdev); } -#ifdef CONFIG_HOTPLUG static int wiphy_uevent(struct device *dev, struct kobj_uevent_env *env) { /* TODO, we probably need stuff here */ return 0; } -#endif static int wiphy_suspend(struct device *dev, pm_message_t state) { @@ -132,9 +130,7 @@ struct class ieee80211_class = { .owner = THIS_MODULE, .dev_release = wiphy_dev_release, .dev_attrs = ieee80211_dev_attrs, -#ifdef CONFIG_HOTPLUG .dev_uevent = wiphy_uevent, -#endif .suspend = wiphy_suspend, .resume = wiphy_resume, .ns_type = &net_ns_type_operations, diff --git a/net/xfrm/xfrm_algo.c b/net/xfrm/xfrm_algo.c index 4ce2d93162c1..6fb9d00a75dc 100644 --- a/net/xfrm/xfrm_algo.c +++ b/net/xfrm/xfrm_algo.c @@ -35,6 +35,8 @@ static struct xfrm_algo_desc aead_list[] = { } }, + .pfkey_supported = 1, + .desc = { .sadb_alg_id = SADB_X_EALG_AES_GCM_ICV8, .sadb_alg_ivlen = 8, @@ -51,6 +53,8 @@ static struct xfrm_algo_desc aead_list[] = { } }, + .pfkey_supported = 1, + .desc = { .sadb_alg_id = SADB_X_EALG_AES_GCM_ICV12, .sadb_alg_ivlen = 8, @@ -67,6 +71,8 @@ static struct xfrm_algo_desc aead_list[] = { } }, + .pfkey_supported = 1, + .desc = { .sadb_alg_id = SADB_X_EALG_AES_GCM_ICV16, .sadb_alg_ivlen = 8, @@ -83,6 +89,8 @@ static struct xfrm_algo_desc aead_list[] = { } }, + .pfkey_supported = 1, + .desc = { .sadb_alg_id = SADB_X_EALG_AES_CCM_ICV8, .sadb_alg_ivlen = 8, @@ -99,6 +107,8 @@ static struct xfrm_algo_desc aead_list[] = { } }, + .pfkey_supported = 1, + .desc = { .sadb_alg_id = SADB_X_EALG_AES_CCM_ICV12, .sadb_alg_ivlen = 8, @@ -115,6 +125,8 @@ static struct xfrm_algo_desc aead_list[] = { } }, + .pfkey_supported = 1, + .desc = { .sadb_alg_id = SADB_X_EALG_AES_CCM_ICV16, .sadb_alg_ivlen = 8, @@ -131,6 +143,8 @@ static struct xfrm_algo_desc aead_list[] = { } }, + .pfkey_supported = 1, + .desc = { .sadb_alg_id = SADB_X_EALG_NULL_AES_GMAC, .sadb_alg_ivlen = 8, @@ -151,6 +165,8 @@ static struct xfrm_algo_desc aalg_list[] = { } }, + .pfkey_supported = 1, + .desc = { .sadb_alg_id = SADB_X_AALG_NULL, .sadb_alg_ivlen = 0, @@ -169,6 +185,8 @@ static struct xfrm_algo_desc aalg_list[] = { } }, + .pfkey_supported = 1, + .desc = { .sadb_alg_id = SADB_AALG_MD5HMAC, .sadb_alg_ivlen = 0, @@ -187,6 +205,8 @@ static struct xfrm_algo_desc aalg_list[] = { } }, + .pfkey_supported = 1, + .desc = { .sadb_alg_id = SADB_AALG_SHA1HMAC, .sadb_alg_ivlen = 0, @@ -205,6 +225,8 @@ static struct xfrm_algo_desc aalg_list[] = { } }, + .pfkey_supported = 1, + .desc = { .sadb_alg_id = SADB_X_AALG_SHA2_256HMAC, .sadb_alg_ivlen = 0, @@ -222,6 +244,8 @@ static struct xfrm_algo_desc aalg_list[] = { } }, + .pfkey_supported = 1, + .desc = { .sadb_alg_id = SADB_X_AALG_SHA2_384HMAC, .sadb_alg_ivlen = 0, @@ -239,6 +263,8 @@ static struct xfrm_algo_desc aalg_list[] = { } }, + .pfkey_supported = 1, + .desc = { .sadb_alg_id = SADB_X_AALG_SHA2_512HMAC, .sadb_alg_ivlen = 0, @@ -257,6 +283,8 @@ static struct xfrm_algo_desc aalg_list[] = { } }, + .pfkey_supported = 1, + .desc = { .sadb_alg_id = SADB_X_AALG_RIPEMD160HMAC, .sadb_alg_ivlen = 0, @@ -274,6 +302,8 @@ static struct xfrm_algo_desc aalg_list[] = { } }, + .pfkey_supported = 1, + .desc = { .sadb_alg_id = SADB_X_AALG_AES_XCBC_MAC, .sadb_alg_ivlen = 0, @@ -295,6 +325,8 @@ static struct xfrm_algo_desc ealg_list[] = { } }, + .pfkey_supported = 1, + .desc = { .sadb_alg_id = SADB_EALG_NULL, .sadb_alg_ivlen = 0, @@ -313,6 +345,8 @@ static struct xfrm_algo_desc ealg_list[] = { } }, + .pfkey_supported = 1, + .desc = { .sadb_alg_id = SADB_EALG_DESCBC, .sadb_alg_ivlen = 8, @@ -331,6 +365,8 @@ static struct xfrm_algo_desc ealg_list[] = { } }, + .pfkey_supported = 1, + .desc = { .sadb_alg_id = SADB_EALG_3DESCBC, .sadb_alg_ivlen = 8, @@ -349,6 +385,8 @@ static struct xfrm_algo_desc ealg_list[] = { } }, + .pfkey_supported = 1, + .desc = { .sadb_alg_id = SADB_X_EALG_CASTCBC, .sadb_alg_ivlen = 8, @@ -367,6 +405,8 @@ static struct xfrm_algo_desc ealg_list[] = { } }, + .pfkey_supported = 1, + .desc = { .sadb_alg_id = SADB_X_EALG_BLOWFISHCBC, .sadb_alg_ivlen = 8, @@ -385,6 +425,8 @@ static struct xfrm_algo_desc ealg_list[] = { } }, + .pfkey_supported = 1, + .desc = { .sadb_alg_id = SADB_X_EALG_AESCBC, .sadb_alg_ivlen = 8, @@ -403,6 +445,8 @@ static struct xfrm_algo_desc ealg_list[] = { } }, + .pfkey_supported = 1, + .desc = { .sadb_alg_id = SADB_X_EALG_SERPENTCBC, .sadb_alg_ivlen = 8, @@ -421,6 +465,8 @@ static struct xfrm_algo_desc ealg_list[] = { } }, + .pfkey_supported = 1, + .desc = { .sadb_alg_id = SADB_X_EALG_CAMELLIACBC, .sadb_alg_ivlen = 8, @@ -439,6 +485,8 @@ static struct xfrm_algo_desc ealg_list[] = { } }, + .pfkey_supported = 1, + .desc = { .sadb_alg_id = SADB_X_EALG_TWOFISHCBC, .sadb_alg_ivlen = 8, @@ -456,6 +504,8 @@ static struct xfrm_algo_desc ealg_list[] = { } }, + .pfkey_supported = 1, + .desc = { .sadb_alg_id = SADB_X_EALG_AESCTR, .sadb_alg_ivlen = 8, @@ -473,6 +523,7 @@ static struct xfrm_algo_desc calg_list[] = { .threshold = 90, } }, + .pfkey_supported = 1, .desc = { .sadb_alg_id = SADB_X_CALG_DEFLATE } }, { @@ -482,6 +533,7 @@ static struct xfrm_algo_desc calg_list[] = { .threshold = 90, } }, + .pfkey_supported = 1, .desc = { .sadb_alg_id = SADB_X_CALG_LZS } }, { @@ -491,6 +543,7 @@ static struct xfrm_algo_desc calg_list[] = { .threshold = 50, } }, + .pfkey_supported = 1, .desc = { .sadb_alg_id = SADB_X_CALG_LZJH } }, }; @@ -700,8 +753,7 @@ void xfrm_probe_algs(void) } for (i = 0; i < ealg_entries(); i++) { - status = crypto_has_blkcipher(ealg_list[i].name, 0, - CRYPTO_ALG_ASYNC); + status = crypto_has_ablkcipher(ealg_list[i].name, 0, 0); if (ealg_list[i].available != status) ealg_list[i].available = status; } @@ -715,27 +767,27 @@ void xfrm_probe_algs(void) } EXPORT_SYMBOL_GPL(xfrm_probe_algs); -int xfrm_count_auth_supported(void) +int xfrm_count_pfkey_auth_supported(void) { int i, n; for (i = 0, n = 0; i < aalg_entries(); i++) - if (aalg_list[i].available) + if (aalg_list[i].available && aalg_list[i].pfkey_supported) n++; return n; } -EXPORT_SYMBOL_GPL(xfrm_count_auth_supported); +EXPORT_SYMBOL_GPL(xfrm_count_pfkey_auth_supported); -int xfrm_count_enc_supported(void) +int xfrm_count_pfkey_enc_supported(void) { int i, n; for (i = 0, n = 0; i < ealg_entries(); i++) - if (ealg_list[i].available) + if (ealg_list[i].available && ealg_list[i].pfkey_supported) n++; return n; } -EXPORT_SYMBOL_GPL(xfrm_count_enc_supported); +EXPORT_SYMBOL_GPL(xfrm_count_pfkey_enc_supported); #if defined(CONFIG_INET_ESP) || defined(CONFIG_INET_ESP_MODULE) || defined(CONFIG_INET6_ESP) || defined(CONFIG_INET6_ESP_MODULE) diff --git a/net/xfrm/xfrm_output.c b/net/xfrm/xfrm_output.c index 95a338c89f99..bcfda8921b5b 100644 --- a/net/xfrm/xfrm_output.c +++ b/net/xfrm/xfrm_output.c @@ -61,6 +61,12 @@ static int xfrm_output_one(struct sk_buff *skb, int err) } spin_lock_bh(&x->lock); + + if (unlikely(x->km.state != XFRM_STATE_VALID)) { + XFRM_INC_STATS(net, LINUX_MIB_XFRMOUTSTATEINVALID); + goto error; + } + err = xfrm_state_check_expire(x); if (err) { XFRM_INC_STATS(net, LINUX_MIB_XFRMOUTSTATEEXPIRED); diff --git a/net/xfrm/xfrm_policy.c b/net/xfrm/xfrm_policy.c index 41eabc46f110..5b47180986f8 100644 --- a/net/xfrm/xfrm_policy.c +++ b/net/xfrm/xfrm_policy.c @@ -35,6 +35,10 @@ #include "xfrm_hash.h" +#define XFRM_QUEUE_TMO_MIN ((unsigned)(HZ/10)) +#define XFRM_QUEUE_TMO_MAX ((unsigned)(60*HZ)) +#define XFRM_MAX_QUEUE_LEN 100 + DEFINE_MUTEX(xfrm_cfg_mutex); EXPORT_SYMBOL(xfrm_cfg_mutex); @@ -51,7 +55,7 @@ static struct kmem_cache *xfrm_dst_cache __read_mostly; static void xfrm_init_pmtu(struct dst_entry *dst); static int stale_bundle(struct dst_entry *dst); static int xfrm_bundle_ok(struct xfrm_dst *xdst); - +static void xfrm_policy_queue_process(unsigned long arg); static struct xfrm_policy *__xfrm_policy_unlink(struct xfrm_policy *pol, int dir); @@ -287,8 +291,11 @@ struct xfrm_policy *xfrm_policy_alloc(struct net *net, gfp_t gfp) INIT_HLIST_NODE(&policy->byidx); rwlock_init(&policy->lock); atomic_set(&policy->refcnt, 1); + skb_queue_head_init(&policy->polq.hold_queue); setup_timer(&policy->timer, xfrm_policy_timer, (unsigned long)policy); + setup_timer(&policy->polq.hold_timer, xfrm_policy_queue_process, + (unsigned long)policy); policy->flo.ops = &xfrm_policy_fc_ops; } return policy; @@ -309,6 +316,16 @@ void xfrm_policy_destroy(struct xfrm_policy *policy) } EXPORT_SYMBOL(xfrm_policy_destroy); +static void xfrm_queue_purge(struct sk_buff_head *list) +{ + struct sk_buff *skb; + + while ((skb = skb_dequeue(list)) != NULL) { + dev_put(skb->dev); + kfree_skb(skb); + } +} + /* Rule must be locked. Release descentant resources, announce * entry dead. The rule must be unlinked from lists to the moment. */ @@ -319,6 +336,9 @@ static void xfrm_policy_kill(struct xfrm_policy *policy) atomic_inc(&policy->genid); + del_timer(&policy->polq.hold_timer); + xfrm_queue_purge(&policy->polq.hold_queue); + if (del_timer(&policy->timer)) xfrm_pol_put(policy); @@ -562,6 +582,46 @@ static inline int selector_cmp(struct xfrm_selector *s1, struct xfrm_selector *s return 0; } +static void xfrm_policy_requeue(struct xfrm_policy *old, + struct xfrm_policy *new) +{ + struct xfrm_policy_queue *pq = &old->polq; + struct sk_buff_head list; + + __skb_queue_head_init(&list); + + spin_lock_bh(&pq->hold_queue.lock); + skb_queue_splice_init(&pq->hold_queue, &list); + del_timer(&pq->hold_timer); + spin_unlock_bh(&pq->hold_queue.lock); + + if (skb_queue_empty(&list)) + return; + + pq = &new->polq; + + spin_lock_bh(&pq->hold_queue.lock); + skb_queue_splice(&list, &pq->hold_queue); + pq->timeout = XFRM_QUEUE_TMO_MIN; + mod_timer(&pq->hold_timer, jiffies); + spin_unlock_bh(&pq->hold_queue.lock); +} + +static bool xfrm_policy_mark_match(struct xfrm_policy *policy, + struct xfrm_policy *pol) +{ + u32 mark = policy->mark.v & policy->mark.m; + + if (policy->mark.v == pol->mark.v && policy->mark.m == pol->mark.m) + return true; + + if ((mark & pol->mark.m) == pol->mark.v && + policy->priority == pol->priority) + return true; + + return false; +} + int xfrm_policy_insert(int dir, struct xfrm_policy *policy, int excl) { struct net *net = xp_net(policy); @@ -569,7 +629,6 @@ int xfrm_policy_insert(int dir, struct xfrm_policy *policy, int excl) struct xfrm_policy *delpol; struct hlist_head *chain; struct hlist_node *entry, *newpos; - u32 mark = policy->mark.v & policy->mark.m; write_lock_bh(&xfrm_policy_lock); chain = policy_hash_bysel(net, &policy->selector, policy->family, dir); @@ -578,7 +637,7 @@ int xfrm_policy_insert(int dir, struct xfrm_policy *policy, int excl) hlist_for_each_entry(pol, entry, chain, bydst) { if (pol->type == policy->type && !selector_cmp(&pol->selector, &policy->selector) && - (mark & pol->mark.m) == pol->mark.v && + xfrm_policy_mark_match(policy, pol) && xfrm_sec_ctx_match(pol->security, policy->security) && !WARN_ON(delpol)) { if (excl) { @@ -603,8 +662,10 @@ int xfrm_policy_insert(int dir, struct xfrm_policy *policy, int excl) net->xfrm.policy_count[dir]++; atomic_inc(&flow_cache_genid); rt_genid_bump(net); - if (delpol) + if (delpol) { + xfrm_policy_requeue(delpol, policy); __xfrm_policy_unlink(delpol, dir); + } policy->index = delpol ? delpol->index : xfrm_gen_index(net, dir); hlist_add_head(&policy->byidx, net->xfrm.policy_byidx+idx_hash(net, policy->index)); policy->curlft.add_time = get_seconds(); @@ -1115,11 +1176,15 @@ int xfrm_sk_policy_insert(struct sock *sk, int dir, struct xfrm_policy *pol) pol->index = xfrm_gen_index(net, XFRM_POLICY_MAX+dir); __xfrm_policy_link(pol, XFRM_POLICY_MAX+dir); } - if (old_pol) + if (old_pol) { + if (pol) + xfrm_policy_requeue(old_pol, pol); + /* Unlinking succeeds always. This is the only function * allowed to delete or replace socket policy. */ __xfrm_policy_unlink(old_pol, XFRM_POLICY_MAX+dir); + } write_unlock_bh(&xfrm_policy_lock); if (old_pol) { @@ -1310,6 +1375,8 @@ static struct flow_cache_object *xfrm_bundle_flo_get(struct flow_cache_object *f * It means we need to try again resolving. */ if (xdst->num_xfrms > 0) return NULL; + } else if (dst->flags & DST_XFRM_QUEUE) { + return NULL; } else { /* Real bundle */ if (stale_bundle(dst)) @@ -1673,6 +1740,171 @@ xfrm_resolve_and_create_bundle(struct xfrm_policy **pols, int num_pols, return xdst; } +static void xfrm_policy_queue_process(unsigned long arg) +{ + int err = 0; + struct sk_buff *skb; + struct sock *sk; + struct dst_entry *dst; + struct net_device *dev; + struct xfrm_policy *pol = (struct xfrm_policy *)arg; + struct xfrm_policy_queue *pq = &pol->polq; + struct flowi fl; + struct sk_buff_head list; + + spin_lock(&pq->hold_queue.lock); + skb = skb_peek(&pq->hold_queue); + dst = skb_dst(skb); + sk = skb->sk; + xfrm_decode_session(skb, &fl, dst->ops->family); + spin_unlock(&pq->hold_queue.lock); + + dst_hold(dst->path); + dst = xfrm_lookup(xp_net(pol), dst->path, &fl, + sk, 0); + if (IS_ERR(dst)) + goto purge_queue; + + if (dst->flags & DST_XFRM_QUEUE) { + dst_release(dst); + + if (pq->timeout >= XFRM_QUEUE_TMO_MAX) + goto purge_queue; + + pq->timeout = pq->timeout << 1; + mod_timer(&pq->hold_timer, jiffies + pq->timeout); + return; + } + + dst_release(dst); + + __skb_queue_head_init(&list); + + spin_lock(&pq->hold_queue.lock); + pq->timeout = 0; + skb_queue_splice_init(&pq->hold_queue, &list); + spin_unlock(&pq->hold_queue.lock); + + while (!skb_queue_empty(&list)) { + skb = __skb_dequeue(&list); + + xfrm_decode_session(skb, &fl, skb_dst(skb)->ops->family); + dst_hold(skb_dst(skb)->path); + dst = xfrm_lookup(xp_net(pol), skb_dst(skb)->path, + &fl, skb->sk, 0); + if (IS_ERR(dst)) { + dev_put(skb->dev); + kfree_skb(skb); + continue; + } + + nf_reset(skb); + skb_dst_drop(skb); + skb_dst_set(skb, dst); + + dev = skb->dev; + err = dst_output(skb); + dev_put(dev); + } + + return; + +purge_queue: + pq->timeout = 0; + xfrm_queue_purge(&pq->hold_queue); +} + +static int xdst_queue_output(struct sk_buff *skb) +{ + unsigned long sched_next; + struct dst_entry *dst = skb_dst(skb); + struct xfrm_dst *xdst = (struct xfrm_dst *) dst; + struct xfrm_policy_queue *pq = &xdst->pols[0]->polq; + + if (pq->hold_queue.qlen > XFRM_MAX_QUEUE_LEN) { + kfree_skb(skb); + return -EAGAIN; + } + + skb_dst_force(skb); + dev_hold(skb->dev); + + spin_lock_bh(&pq->hold_queue.lock); + + if (!pq->timeout) + pq->timeout = XFRM_QUEUE_TMO_MIN; + + sched_next = jiffies + pq->timeout; + + if (del_timer(&pq->hold_timer)) { + if (time_before(pq->hold_timer.expires, sched_next)) + sched_next = pq->hold_timer.expires; + } + + __skb_queue_tail(&pq->hold_queue, skb); + mod_timer(&pq->hold_timer, sched_next); + + spin_unlock_bh(&pq->hold_queue.lock); + + return 0; +} + +static struct xfrm_dst *xfrm_create_dummy_bundle(struct net *net, + struct dst_entry *dst, + const struct flowi *fl, + int num_xfrms, + u16 family) +{ + int err; + struct net_device *dev; + struct dst_entry *dst1; + struct xfrm_dst *xdst; + + xdst = xfrm_alloc_dst(net, family); + if (IS_ERR(xdst)) + return xdst; + + if (net->xfrm.sysctl_larval_drop || num_xfrms <= 0 || + (fl->flowi_flags & FLOWI_FLAG_CAN_SLEEP)) + return xdst; + + dst1 = &xdst->u.dst; + dst_hold(dst); + xdst->route = dst; + + dst_copy_metrics(dst1, dst); + + dst1->obsolete = DST_OBSOLETE_FORCE_CHK; + dst1->flags |= DST_HOST | DST_XFRM_QUEUE; + dst1->lastuse = jiffies; + + dst1->input = dst_discard; + dst1->output = xdst_queue_output; + + dst_hold(dst); + dst1->child = dst; + dst1->path = dst; + + xfrm_init_path((struct xfrm_dst *)dst1, dst, 0); + + err = -ENODEV; + dev = dst->dev; + if (!dev) + goto free_dst; + + err = xfrm_fill_dst(xdst, dev, fl); + if (err) + goto free_dst; + +out: + return xdst; + +free_dst: + dst_release(dst1); + xdst = ERR_PTR(err); + goto out; +} + static struct flow_cache_object * xfrm_bundle_lookup(struct net *net, const struct flowi *fl, u16 family, u8 dir, struct flow_cache_object *oldflo, void *ctx) @@ -1751,7 +1983,7 @@ make_dummy_bundle: /* We found policies, but there's no bundles to instantiate: * either because the policy blocks, has no transformations or * we could not build template (no xfrm_states).*/ - xdst = xfrm_alloc_dst(net, family); + xdst = xfrm_create_dummy_bundle(net, dst_orig, fl, num_xfrms, family); if (IS_ERR(xdst)) { xfrm_pols_put(pols, num_pols); return ERR_CAST(xdst); @@ -2359,6 +2591,9 @@ static int xfrm_bundle_ok(struct xfrm_dst *first) (dst->dev && !netif_running(dst->dev))) return 0; + if (dst->flags & DST_XFRM_QUEUE) + return 1; + last = NULL; do { @@ -2656,7 +2891,7 @@ static void xfrm_policy_fini(struct net *net) WARN_ON(!hlist_empty(&net->xfrm.policy_inexact[dir])); htab = &net->xfrm.policy_bydst[dir]; - sz = (htab->hmask + 1); + sz = (htab->hmask + 1) * sizeof(struct hlist_head); WARN_ON(!hlist_empty(htab->table)); xfrm_hash_free(htab->table, sz); } @@ -2786,10 +3021,10 @@ static bool xfrm_migrate_selector_match(const struct xfrm_selector *sel_cmp, { if (sel_cmp->proto == IPSEC_ULPROTO_ANY) { if (sel_tgt->family == sel_cmp->family && - xfrm_addr_cmp(&sel_tgt->daddr, &sel_cmp->daddr, - sel_cmp->family) == 0 && - xfrm_addr_cmp(&sel_tgt->saddr, &sel_cmp->saddr, - sel_cmp->family) == 0 && + 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; @@ -2847,10 +3082,10 @@ static int migrate_tmpl_match(const struct xfrm_migrate *m, const struct xfrm_tm switch (t->mode) { case XFRM_MODE_TUNNEL: case XFRM_MODE_BEET: - if (xfrm_addr_cmp(&t->id.daddr, &m->old_daddr, - m->old_family) == 0 && - xfrm_addr_cmp(&t->saddr, &m->old_saddr, - m->old_family) == 0) { + if (xfrm_addr_equal(&t->id.daddr, &m->old_daddr, + m->old_family) && + xfrm_addr_equal(&t->saddr, &m->old_saddr, + m->old_family)) { match = 1; } break; @@ -2916,10 +3151,10 @@ static int xfrm_migrate_check(const struct xfrm_migrate *m, int num_migrate) return -EINVAL; for (i = 0; i < num_migrate; i++) { - if ((xfrm_addr_cmp(&m[i].old_daddr, &m[i].new_daddr, - m[i].old_family) == 0) && - (xfrm_addr_cmp(&m[i].old_saddr, &m[i].new_saddr, - m[i].old_family) == 0)) + if (xfrm_addr_equal(&m[i].old_daddr, &m[i].new_daddr, + m[i].old_family) && + xfrm_addr_equal(&m[i].old_saddr, &m[i].new_saddr, + m[i].old_family)) return -EINVAL; if (xfrm_addr_any(&m[i].new_daddr, m[i].new_family) || xfrm_addr_any(&m[i].new_saddr, m[i].new_family)) diff --git a/net/xfrm/xfrm_proc.c b/net/xfrm/xfrm_proc.c index d0a1af8ed584..603903853e89 100644 --- a/net/xfrm/xfrm_proc.c +++ b/net/xfrm/xfrm_proc.c @@ -43,6 +43,7 @@ static const struct snmp_mib xfrm_mib_list[] = { SNMP_MIB_ITEM("XfrmOutPolDead", LINUX_MIB_XFRMOUTPOLDEAD), SNMP_MIB_ITEM("XfrmOutPolError", LINUX_MIB_XFRMOUTPOLERROR), SNMP_MIB_ITEM("XfrmFwdHdrError", LINUX_MIB_XFRMFWDHDRERROR), + SNMP_MIB_ITEM("XfrmOutStateInvalid", LINUX_MIB_XFRMOUTSTATEINVALID), SNMP_MIB_SENTINEL }; diff --git a/net/xfrm/xfrm_replay.c b/net/xfrm/xfrm_replay.c index 765f6fe951eb..35754cc8a9e5 100644 --- a/net/xfrm/xfrm_replay.c +++ b/net/xfrm/xfrm_replay.c @@ -242,11 +242,13 @@ static void xfrm_replay_advance_bmp(struct xfrm_state *x, __be32 net_seq) u32 diff; struct xfrm_replay_state_esn *replay_esn = x->replay_esn; u32 seq = ntohl(net_seq); - u32 pos = (replay_esn->seq - 1) % replay_esn->replay_window; + u32 pos; if (!replay_esn->replay_window) return; + pos = (replay_esn->seq - 1) % replay_esn->replay_window; + if (seq > replay_esn->seq) { diff = seq - replay_esn->seq; diff --git a/net/xfrm/xfrm_state.c b/net/xfrm/xfrm_state.c index 3459692092ec..ae01bdbcb294 100644 --- a/net/xfrm/xfrm_state.c +++ b/net/xfrm/xfrm_state.c @@ -158,8 +158,8 @@ out_unlock: mutex_unlock(&hash_resize_mutex); } -static DEFINE_RWLOCK(xfrm_state_afinfo_lock); -static struct xfrm_state_afinfo *xfrm_state_afinfo[NPROTO]; +static DEFINE_SPINLOCK(xfrm_state_afinfo_lock); +static struct xfrm_state_afinfo __rcu *xfrm_state_afinfo[NPROTO]; static DEFINE_SPINLOCK(xfrm_state_gc_lock); @@ -168,58 +168,45 @@ int __xfrm_state_delete(struct xfrm_state *x); int km_query(struct xfrm_state *x, struct xfrm_tmpl *t, struct xfrm_policy *pol); void km_state_expired(struct xfrm_state *x, int hard, u32 portid); -static struct xfrm_state_afinfo *xfrm_state_lock_afinfo(unsigned int family) -{ - struct xfrm_state_afinfo *afinfo; - if (unlikely(family >= NPROTO)) - return NULL; - write_lock_bh(&xfrm_state_afinfo_lock); - afinfo = xfrm_state_afinfo[family]; - if (unlikely(!afinfo)) - write_unlock_bh(&xfrm_state_afinfo_lock); - return afinfo; -} - -static void xfrm_state_unlock_afinfo(struct xfrm_state_afinfo *afinfo) - __releases(xfrm_state_afinfo_lock) -{ - write_unlock_bh(&xfrm_state_afinfo_lock); -} - +static DEFINE_SPINLOCK(xfrm_type_lock); int xfrm_register_type(const struct xfrm_type *type, unsigned short family) { - struct xfrm_state_afinfo *afinfo = xfrm_state_lock_afinfo(family); + struct xfrm_state_afinfo *afinfo = xfrm_state_get_afinfo(family); const struct xfrm_type **typemap; int err = 0; if (unlikely(afinfo == NULL)) return -EAFNOSUPPORT; typemap = afinfo->type_map; + spin_lock_bh(&xfrm_type_lock); if (likely(typemap[type->proto] == NULL)) typemap[type->proto] = type; else err = -EEXIST; - xfrm_state_unlock_afinfo(afinfo); + spin_unlock_bh(&xfrm_type_lock); + xfrm_state_put_afinfo(afinfo); return err; } EXPORT_SYMBOL(xfrm_register_type); int xfrm_unregister_type(const struct xfrm_type *type, unsigned short family) { - struct xfrm_state_afinfo *afinfo = xfrm_state_lock_afinfo(family); + struct xfrm_state_afinfo *afinfo = xfrm_state_get_afinfo(family); const struct xfrm_type **typemap; int err = 0; if (unlikely(afinfo == NULL)) return -EAFNOSUPPORT; typemap = afinfo->type_map; + spin_lock_bh(&xfrm_type_lock); if (unlikely(typemap[type->proto] != type)) err = -ENOENT; else typemap[type->proto] = NULL; - xfrm_state_unlock_afinfo(afinfo); + spin_unlock_bh(&xfrm_type_lock); + xfrm_state_put_afinfo(afinfo); return err; } EXPORT_SYMBOL(xfrm_unregister_type); @@ -256,6 +243,7 @@ static void xfrm_put_type(const struct xfrm_type *type) module_put(type->owner); } +static DEFINE_SPINLOCK(xfrm_mode_lock); int xfrm_register_mode(struct xfrm_mode *mode, int family) { struct xfrm_state_afinfo *afinfo; @@ -265,12 +253,13 @@ int xfrm_register_mode(struct xfrm_mode *mode, int family) if (unlikely(mode->encap >= XFRM_MODE_MAX)) return -EINVAL; - afinfo = xfrm_state_lock_afinfo(family); + afinfo = xfrm_state_get_afinfo(family); if (unlikely(afinfo == NULL)) return -EAFNOSUPPORT; err = -EEXIST; modemap = afinfo->mode_map; + spin_lock_bh(&xfrm_mode_lock); if (modemap[mode->encap]) goto out; @@ -283,7 +272,8 @@ int xfrm_register_mode(struct xfrm_mode *mode, int family) err = 0; out: - xfrm_state_unlock_afinfo(afinfo); + spin_unlock_bh(&xfrm_mode_lock); + xfrm_state_put_afinfo(afinfo); return err; } EXPORT_SYMBOL(xfrm_register_mode); @@ -297,19 +287,21 @@ int xfrm_unregister_mode(struct xfrm_mode *mode, int family) if (unlikely(mode->encap >= XFRM_MODE_MAX)) return -EINVAL; - afinfo = xfrm_state_lock_afinfo(family); + afinfo = xfrm_state_get_afinfo(family); if (unlikely(afinfo == NULL)) return -EAFNOSUPPORT; err = -ENOENT; modemap = afinfo->mode_map; + spin_lock_bh(&xfrm_mode_lock); if (likely(modemap[mode->encap] == mode)) { modemap[mode->encap] = NULL; module_put(mode->afinfo->owner); err = 0; } - xfrm_state_unlock_afinfo(afinfo); + spin_unlock_bh(&xfrm_mode_lock); + xfrm_state_put_afinfo(afinfo); return err; } EXPORT_SYMBOL(xfrm_unregister_mode); @@ -699,7 +691,7 @@ static struct xfrm_state *__xfrm_state_lookup(struct net *net, u32 mark, if (x->props.family != family || x->id.spi != spi || x->id.proto != proto || - xfrm_addr_cmp(&x->id.daddr, daddr, family)) + !xfrm_addr_equal(&x->id.daddr, daddr, family)) continue; if ((mark & x->mark.m) != x->mark.v) @@ -723,8 +715,8 @@ static struct xfrm_state *__xfrm_state_lookup_byaddr(struct net *net, u32 mark, hlist_for_each_entry(x, entry, net->xfrm.state_bysrc+h, bysrc) { if (x->props.family != family || x->id.proto != proto || - xfrm_addr_cmp(&x->id.daddr, daddr, family) || - xfrm_addr_cmp(&x->props.saddr, saddr, family)) + !xfrm_addr_equal(&x->id.daddr, daddr, family) || + !xfrm_addr_equal(&x->props.saddr, saddr, family)) continue; if ((mark & x->mark.m) != x->mark.v) @@ -989,8 +981,8 @@ static void __xfrm_state_bump_genids(struct xfrm_state *xnew) if (x->props.family == family && x->props.reqid == reqid && (mark & x->mark.m) == x->mark.v && - !xfrm_addr_cmp(&x->id.daddr, &xnew->id.daddr, family) && - !xfrm_addr_cmp(&x->props.saddr, &xnew->props.saddr, family)) + xfrm_addr_equal(&x->id.daddr, &xnew->id.daddr, family) && + xfrm_addr_equal(&x->props.saddr, &xnew->props.saddr, family)) x->genid++; } } @@ -1024,8 +1016,8 @@ static struct xfrm_state *__find_acq_core(struct net *net, struct xfrm_mark *m, x->id.spi != 0 || x->id.proto != proto || (mark & x->mark.m) != x->mark.v || - xfrm_addr_cmp(&x->id.daddr, daddr, family) || - xfrm_addr_cmp(&x->props.saddr, saddr, family)) + !xfrm_addr_equal(&x->id.daddr, daddr, family) || + !xfrm_addr_equal(&x->props.saddr, saddr, family)) continue; xfrm_state_hold(x); @@ -1108,7 +1100,7 @@ int xfrm_state_add(struct xfrm_state *x) if (use_spi && x->km.seq) { x1 = __xfrm_find_acq_byseq(net, mark, x->km.seq); if (x1 && ((x1->id.proto != x->id.proto) || - xfrm_addr_cmp(&x1->id.daddr, &x->id.daddr, family))) { + !xfrm_addr_equal(&x1->id.daddr, &x->id.daddr, family))) { to_put = x1; x1 = NULL; } @@ -1234,10 +1226,10 @@ struct xfrm_state * xfrm_migrate_state_find(struct xfrm_migrate *m) continue; if (m->reqid && x->props.reqid != m->reqid) continue; - if (xfrm_addr_cmp(&x->id.daddr, &m->old_daddr, - m->old_family) || - xfrm_addr_cmp(&x->props.saddr, &m->old_saddr, - m->old_family)) + if (!xfrm_addr_equal(&x->id.daddr, &m->old_daddr, + m->old_family) || + !xfrm_addr_equal(&x->props.saddr, &m->old_saddr, + m->old_family)) continue; xfrm_state_hold(x); return x; @@ -1249,10 +1241,10 @@ struct xfrm_state * xfrm_migrate_state_find(struct xfrm_migrate *m) if (x->props.mode != m->mode || x->id.proto != m->proto) continue; - if (xfrm_addr_cmp(&x->id.daddr, &m->old_daddr, - m->old_family) || - xfrm_addr_cmp(&x->props.saddr, &m->old_saddr, - m->old_family)) + if (!xfrm_addr_equal(&x->id.daddr, &m->old_daddr, + m->old_family) || + !xfrm_addr_equal(&x->props.saddr, &m->old_saddr, + m->old_family)) continue; xfrm_state_hold(x); return x; @@ -1277,7 +1269,7 @@ struct xfrm_state * xfrm_state_migrate(struct xfrm_state *x, memcpy(&xc->props.saddr, &m->new_saddr, sizeof(xc->props.saddr)); /* add state */ - if (!xfrm_addr_cmp(&x->id.daddr, &m->new_daddr, m->new_family)) { + if (xfrm_addr_equal(&x->id.daddr, &m->new_daddr, m->new_family)) { /* a care is needed when the destination address of the state is to be updated as it is a part of triplet */ xfrm_state_insert(xc); @@ -1370,9 +1362,6 @@ int xfrm_state_check_expire(struct xfrm_state *x) if (!x->curlft.use_time) x->curlft.use_time = get_seconds(); - if (x->km.state != XFRM_STATE_VALID) - return -EINVAL; - if (x->curlft.bytes >= x->lft.hard_byte_limit || x->curlft.packets >= x->lft.hard_packet_limit) { x->km.state = XFRM_STATE_EXPIRED; @@ -1648,27 +1637,26 @@ static void xfrm_replay_timer_handler(unsigned long data) } static LIST_HEAD(xfrm_km_list); -static DEFINE_RWLOCK(xfrm_km_lock); void km_policy_notify(struct xfrm_policy *xp, int dir, const struct km_event *c) { struct xfrm_mgr *km; - read_lock(&xfrm_km_lock); - list_for_each_entry(km, &xfrm_km_list, list) + rcu_read_lock(); + list_for_each_entry_rcu(km, &xfrm_km_list, list) if (km->notify_policy) km->notify_policy(xp, dir, c); - read_unlock(&xfrm_km_lock); + rcu_read_unlock(); } void km_state_notify(struct xfrm_state *x, const struct km_event *c) { struct xfrm_mgr *km; - read_lock(&xfrm_km_lock); - list_for_each_entry(km, &xfrm_km_list, list) + rcu_read_lock(); + list_for_each_entry_rcu(km, &xfrm_km_list, list) if (km->notify) km->notify(x, c); - read_unlock(&xfrm_km_lock); + rcu_read_unlock(); } EXPORT_SYMBOL(km_policy_notify); @@ -1698,13 +1686,13 @@ int km_query(struct xfrm_state *x, struct xfrm_tmpl *t, struct xfrm_policy *pol) int err = -EINVAL, acqret; struct xfrm_mgr *km; - read_lock(&xfrm_km_lock); - list_for_each_entry(km, &xfrm_km_list, list) { + rcu_read_lock(); + list_for_each_entry_rcu(km, &xfrm_km_list, list) { acqret = km->acquire(x, t, pol); if (!acqret) err = acqret; } - read_unlock(&xfrm_km_lock); + rcu_read_unlock(); return err; } EXPORT_SYMBOL(km_query); @@ -1714,14 +1702,14 @@ int km_new_mapping(struct xfrm_state *x, xfrm_address_t *ipaddr, __be16 sport) int err = -EINVAL; struct xfrm_mgr *km; - read_lock(&xfrm_km_lock); - list_for_each_entry(km, &xfrm_km_list, list) { + rcu_read_lock(); + list_for_each_entry_rcu(km, &xfrm_km_list, list) { if (km->new_mapping) err = km->new_mapping(x, ipaddr, sport); if (!err) break; } - read_unlock(&xfrm_km_lock); + rcu_read_unlock(); return err; } EXPORT_SYMBOL(km_new_mapping); @@ -1750,15 +1738,15 @@ int km_migrate(const struct xfrm_selector *sel, u8 dir, u8 type, int ret; struct xfrm_mgr *km; - read_lock(&xfrm_km_lock); - list_for_each_entry(km, &xfrm_km_list, list) { + rcu_read_lock(); + list_for_each_entry_rcu(km, &xfrm_km_list, list) { if (km->migrate) { ret = km->migrate(sel, dir, type, m, num_migrate, k); if (!ret) err = ret; } } - read_unlock(&xfrm_km_lock); + rcu_read_unlock(); return err; } EXPORT_SYMBOL(km_migrate); @@ -1770,15 +1758,15 @@ int km_report(struct net *net, u8 proto, struct xfrm_selector *sel, xfrm_address int ret; struct xfrm_mgr *km; - read_lock(&xfrm_km_lock); - list_for_each_entry(km, &xfrm_km_list, list) { + rcu_read_lock(); + list_for_each_entry_rcu(km, &xfrm_km_list, list) { if (km->report) { ret = km->report(net, proto, sel, addr); if (!ret) err = ret; } } - read_unlock(&xfrm_km_lock); + rcu_read_unlock(); return err; } EXPORT_SYMBOL(km_report); @@ -1802,14 +1790,14 @@ int xfrm_user_policy(struct sock *sk, int optname, u8 __user *optval, int optlen goto out; err = -EINVAL; - read_lock(&xfrm_km_lock); - list_for_each_entry(km, &xfrm_km_list, list) { + rcu_read_lock(); + list_for_each_entry_rcu(km, &xfrm_km_list, list) { pol = km->compile_policy(sk, optname, data, optlen, &err); if (err >= 0) break; } - read_unlock(&xfrm_km_lock); + rcu_read_unlock(); if (err >= 0) { xfrm_sk_policy_insert(sk, err, pol); @@ -1823,20 +1811,23 @@ out: } EXPORT_SYMBOL(xfrm_user_policy); +static DEFINE_SPINLOCK(xfrm_km_lock); + int xfrm_register_km(struct xfrm_mgr *km) { - write_lock_bh(&xfrm_km_lock); - list_add_tail(&km->list, &xfrm_km_list); - write_unlock_bh(&xfrm_km_lock); + spin_lock_bh(&xfrm_km_lock); + list_add_tail_rcu(&km->list, &xfrm_km_list); + spin_unlock_bh(&xfrm_km_lock); return 0; } EXPORT_SYMBOL(xfrm_register_km); int xfrm_unregister_km(struct xfrm_mgr *km) { - write_lock_bh(&xfrm_km_lock); - list_del(&km->list); - write_unlock_bh(&xfrm_km_lock); + spin_lock_bh(&xfrm_km_lock); + list_del_rcu(&km->list); + spin_unlock_bh(&xfrm_km_lock); + synchronize_rcu(); return 0; } EXPORT_SYMBOL(xfrm_unregister_km); @@ -1848,12 +1839,12 @@ int xfrm_state_register_afinfo(struct xfrm_state_afinfo *afinfo) return -EINVAL; if (unlikely(afinfo->family >= NPROTO)) return -EAFNOSUPPORT; - write_lock_bh(&xfrm_state_afinfo_lock); + spin_lock_bh(&xfrm_state_afinfo_lock); if (unlikely(xfrm_state_afinfo[afinfo->family] != NULL)) err = -ENOBUFS; else - xfrm_state_afinfo[afinfo->family] = afinfo; - write_unlock_bh(&xfrm_state_afinfo_lock); + rcu_assign_pointer(xfrm_state_afinfo[afinfo->family], afinfo); + spin_unlock_bh(&xfrm_state_afinfo_lock); return err; } EXPORT_SYMBOL(xfrm_state_register_afinfo); @@ -1865,14 +1856,15 @@ int xfrm_state_unregister_afinfo(struct xfrm_state_afinfo *afinfo) return -EINVAL; if (unlikely(afinfo->family >= NPROTO)) return -EAFNOSUPPORT; - write_lock_bh(&xfrm_state_afinfo_lock); + spin_lock_bh(&xfrm_state_afinfo_lock); if (likely(xfrm_state_afinfo[afinfo->family] != NULL)) { if (unlikely(xfrm_state_afinfo[afinfo->family] != afinfo)) err = -EINVAL; else - xfrm_state_afinfo[afinfo->family] = NULL; + RCU_INIT_POINTER(xfrm_state_afinfo[afinfo->family], NULL); } - write_unlock_bh(&xfrm_state_afinfo_lock); + spin_unlock_bh(&xfrm_state_afinfo_lock); + synchronize_rcu(); return err; } EXPORT_SYMBOL(xfrm_state_unregister_afinfo); @@ -1882,17 +1874,16 @@ static struct xfrm_state_afinfo *xfrm_state_get_afinfo(unsigned int family) struct xfrm_state_afinfo *afinfo; if (unlikely(family >= NPROTO)) return NULL; - read_lock(&xfrm_state_afinfo_lock); - afinfo = xfrm_state_afinfo[family]; + rcu_read_lock(); + afinfo = rcu_dereference(xfrm_state_afinfo[family]); if (unlikely(!afinfo)) - read_unlock(&xfrm_state_afinfo_lock); + rcu_read_unlock(); return afinfo; } static void xfrm_state_put_afinfo(struct xfrm_state_afinfo *afinfo) - __releases(xfrm_state_afinfo_lock) { - read_unlock(&xfrm_state_afinfo_lock); + rcu_read_unlock(); } /* Temporarily located here until net/xfrm/xfrm_tunnel.c is created */ diff --git a/net/xfrm/xfrm_user.c b/net/xfrm/xfrm_user.c index eb872b2e366e..fbd9e6cd0fd7 100644 --- a/net/xfrm/xfrm_user.c +++ b/net/xfrm/xfrm_user.c @@ -1112,7 +1112,7 @@ static int xfrm_alloc_userspi(struct sk_buff *skb, struct nlmsghdr *nlh, mark = xfrm_mark_get(attrs, &m); if (p->info.seq) { x = xfrm_find_acq_byseq(net, mark, p->info.seq); - if (x && xfrm_addr_cmp(&x->id.daddr, daddr, family)) { + if (x && !xfrm_addr_equal(&x->id.daddr, daddr, family)) { xfrm_state_put(x); x = NULL; } |