OpenCloudOS-Kernel/net/openvswitch/vport.c

581 lines
14 KiB
C
Raw Normal View History

// SPDX-License-Identifier: GPL-2.0-only
/*
* Copyright (c) 2007-2014 Nicira, Inc.
*/
#include <linux/etherdevice.h>
#include <linux/if.h>
#include <linux/if_vlan.h>
#include <linux/jhash.h>
#include <linux/kernel.h>
#include <linux/list.h>
#include <linux/mutex.h>
#include <linux/percpu.h>
#include <linux/rcupdate.h>
#include <linux/rtnetlink.h>
#include <linux/compat.h>
#include <net/net_namespace.h>
#include <linux/module.h>
#include "datapath.h"
#include "vport.h"
#include "vport-internal_dev.h"
static LIST_HEAD(vport_ops_list);
/* Protected by RCU read lock for reading, ovs_mutex for writing. */
static struct hlist_head *dev_table;
#define VPORT_HASH_BUCKETS 1024
/**
* ovs_vport_init - initialize vport subsystem
*
* Called at module load time to initialize the vport subsystem.
*/
int ovs_vport_init(void)
{
treewide: kzalloc() -> kcalloc() The kzalloc() function has a 2-factor argument form, kcalloc(). This patch replaces cases of: kzalloc(a * b, gfp) with: kcalloc(a * b, gfp) as well as handling cases of: kzalloc(a * b * c, gfp) with: kzalloc(array3_size(a, b, c), gfp) as it's slightly less ugly than: kzalloc_array(array_size(a, b), c, gfp) This does, however, attempt to ignore constant size factors like: kzalloc(4 * 1024, gfp) though any constants defined via macros get caught up in the conversion. Any factors with a sizeof() of "unsigned char", "char", and "u8" were dropped, since they're redundant. The Coccinelle script used for this was: // Fix redundant parens around sizeof(). @@ type TYPE; expression THING, E; @@ ( kzalloc( - (sizeof(TYPE)) * E + sizeof(TYPE) * E , ...) | kzalloc( - (sizeof(THING)) * E + sizeof(THING) * E , ...) ) // Drop single-byte sizes and redundant parens. @@ expression COUNT; typedef u8; typedef __u8; @@ ( kzalloc( - sizeof(u8) * (COUNT) + COUNT , ...) | kzalloc( - sizeof(__u8) * (COUNT) + COUNT , ...) | kzalloc( - sizeof(char) * (COUNT) + COUNT , ...) | kzalloc( - sizeof(unsigned char) * (COUNT) + COUNT , ...) | kzalloc( - sizeof(u8) * COUNT + COUNT , ...) | kzalloc( - sizeof(__u8) * COUNT + COUNT , ...) | kzalloc( - sizeof(char) * COUNT + COUNT , ...) | kzalloc( - sizeof(unsigned char) * COUNT + COUNT , ...) ) // 2-factor product with sizeof(type/expression) and identifier or constant. @@ type TYPE; expression THING; identifier COUNT_ID; constant COUNT_CONST; @@ ( - kzalloc + kcalloc ( - sizeof(TYPE) * (COUNT_ID) + COUNT_ID, sizeof(TYPE) , ...) | - kzalloc + kcalloc ( - sizeof(TYPE) * COUNT_ID + COUNT_ID, sizeof(TYPE) , ...) | - kzalloc + kcalloc ( - sizeof(TYPE) * (COUNT_CONST) + COUNT_CONST, sizeof(TYPE) , ...) | - kzalloc + kcalloc ( - sizeof(TYPE) * COUNT_CONST + COUNT_CONST, sizeof(TYPE) , ...) | - kzalloc + kcalloc ( - sizeof(THING) * (COUNT_ID) + COUNT_ID, sizeof(THING) , ...) | - kzalloc + kcalloc ( - sizeof(THING) * COUNT_ID + COUNT_ID, sizeof(THING) , ...) | - kzalloc + kcalloc ( - sizeof(THING) * (COUNT_CONST) + COUNT_CONST, sizeof(THING) , ...) | - kzalloc + kcalloc ( - sizeof(THING) * COUNT_CONST + COUNT_CONST, sizeof(THING) , ...) ) // 2-factor product, only identifiers. @@ identifier SIZE, COUNT; @@ - kzalloc + kcalloc ( - SIZE * COUNT + COUNT, SIZE , ...) // 3-factor product with 1 sizeof(type) or sizeof(expression), with // redundant parens removed. @@ expression THING; identifier STRIDE, COUNT; type TYPE; @@ ( kzalloc( - sizeof(TYPE) * (COUNT) * (STRIDE) + array3_size(COUNT, STRIDE, sizeof(TYPE)) , ...) | kzalloc( - sizeof(TYPE) * (COUNT) * STRIDE + array3_size(COUNT, STRIDE, sizeof(TYPE)) , ...) | kzalloc( - sizeof(TYPE) * COUNT * (STRIDE) + array3_size(COUNT, STRIDE, sizeof(TYPE)) , ...) | kzalloc( - sizeof(TYPE) * COUNT * STRIDE + array3_size(COUNT, STRIDE, sizeof(TYPE)) , ...) | kzalloc( - sizeof(THING) * (COUNT) * (STRIDE) + array3_size(COUNT, STRIDE, sizeof(THING)) , ...) | kzalloc( - sizeof(THING) * (COUNT) * STRIDE + array3_size(COUNT, STRIDE, sizeof(THING)) , ...) | kzalloc( - sizeof(THING) * COUNT * (STRIDE) + array3_size(COUNT, STRIDE, sizeof(THING)) , ...) | kzalloc( - sizeof(THING) * COUNT * STRIDE + array3_size(COUNT, STRIDE, sizeof(THING)) , ...) ) // 3-factor product with 2 sizeof(variable), with redundant parens removed. @@ expression THING1, THING2; identifier COUNT; type TYPE1, TYPE2; @@ ( kzalloc( - sizeof(TYPE1) * sizeof(TYPE2) * COUNT + array3_size(COUNT, sizeof(TYPE1), sizeof(TYPE2)) , ...) | kzalloc( - sizeof(TYPE1) * sizeof(THING2) * (COUNT) + array3_size(COUNT, sizeof(TYPE1), sizeof(TYPE2)) , ...) | kzalloc( - sizeof(THING1) * sizeof(THING2) * COUNT + array3_size(COUNT, sizeof(THING1), sizeof(THING2)) , ...) | kzalloc( - sizeof(THING1) * sizeof(THING2) * (COUNT) + array3_size(COUNT, sizeof(THING1), sizeof(THING2)) , ...) | kzalloc( - sizeof(TYPE1) * sizeof(THING2) * COUNT + array3_size(COUNT, sizeof(TYPE1), sizeof(THING2)) , ...) | kzalloc( - sizeof(TYPE1) * sizeof(THING2) * (COUNT) + array3_size(COUNT, sizeof(TYPE1), sizeof(THING2)) , ...) ) // 3-factor product, only identifiers, with redundant parens removed. @@ identifier STRIDE, SIZE, COUNT; @@ ( kzalloc( - (COUNT) * STRIDE * SIZE + array3_size(COUNT, STRIDE, SIZE) , ...) | kzalloc( - COUNT * (STRIDE) * SIZE + array3_size(COUNT, STRIDE, SIZE) , ...) | kzalloc( - COUNT * STRIDE * (SIZE) + array3_size(COUNT, STRIDE, SIZE) , ...) | kzalloc( - (COUNT) * (STRIDE) * SIZE + array3_size(COUNT, STRIDE, SIZE) , ...) | kzalloc( - COUNT * (STRIDE) * (SIZE) + array3_size(COUNT, STRIDE, SIZE) , ...) | kzalloc( - (COUNT) * STRIDE * (SIZE) + array3_size(COUNT, STRIDE, SIZE) , ...) | kzalloc( - (COUNT) * (STRIDE) * (SIZE) + array3_size(COUNT, STRIDE, SIZE) , ...) | kzalloc( - COUNT * STRIDE * SIZE + array3_size(COUNT, STRIDE, SIZE) , ...) ) // Any remaining multi-factor products, first at least 3-factor products, // when they're not all constants... @@ expression E1, E2, E3; constant C1, C2, C3; @@ ( kzalloc(C1 * C2 * C3, ...) | kzalloc( - (E1) * E2 * E3 + array3_size(E1, E2, E3) , ...) | kzalloc( - (E1) * (E2) * E3 + array3_size(E1, E2, E3) , ...) | kzalloc( - (E1) * (E2) * (E3) + array3_size(E1, E2, E3) , ...) | kzalloc( - E1 * E2 * E3 + array3_size(E1, E2, E3) , ...) ) // And then all remaining 2 factors products when they're not all constants, // keeping sizeof() as the second factor argument. @@ expression THING, E1, E2; type TYPE; constant C1, C2, C3; @@ ( kzalloc(sizeof(THING) * C2, ...) | kzalloc(sizeof(TYPE) * C2, ...) | kzalloc(C1 * C2 * C3, ...) | kzalloc(C1 * C2, ...) | - kzalloc + kcalloc ( - sizeof(TYPE) * (E2) + E2, sizeof(TYPE) , ...) | - kzalloc + kcalloc ( - sizeof(TYPE) * E2 + E2, sizeof(TYPE) , ...) | - kzalloc + kcalloc ( - sizeof(THING) * (E2) + E2, sizeof(THING) , ...) | - kzalloc + kcalloc ( - sizeof(THING) * E2 + E2, sizeof(THING) , ...) | - kzalloc + kcalloc ( - (E1) * E2 + E1, E2 , ...) | - kzalloc + kcalloc ( - (E1) * (E2) + E1, E2 , ...) | - kzalloc + kcalloc ( - E1 * E2 + E1, E2 , ...) ) Signed-off-by: Kees Cook <keescook@chromium.org>
2018-06-13 05:03:40 +08:00
dev_table = kcalloc(VPORT_HASH_BUCKETS, sizeof(struct hlist_head),
GFP_KERNEL);
if (!dev_table)
return -ENOMEM;
return 0;
}
/**
* ovs_vport_exit - shutdown vport subsystem
*
* Called at module exit time to shutdown the vport subsystem.
*/
void ovs_vport_exit(void)
{
kfree(dev_table);
}
static struct hlist_head *hash_bucket(const struct net *net, const char *name)
{
unsigned int hash = jhash(name, strlen(name), (unsigned long) net);
return &dev_table[hash & (VPORT_HASH_BUCKETS - 1)];
}
int __ovs_vport_ops_register(struct vport_ops *ops)
{
int err = -EEXIST;
struct vport_ops *o;
ovs_lock();
list_for_each_entry(o, &vport_ops_list, list)
if (ops->type == o->type)
goto errout;
list_add_tail(&ops->list, &vport_ops_list);
err = 0;
errout:
ovs_unlock();
return err;
}
EXPORT_SYMBOL_GPL(__ovs_vport_ops_register);
void ovs_vport_ops_unregister(struct vport_ops *ops)
{
ovs_lock();
list_del(&ops->list);
ovs_unlock();
}
EXPORT_SYMBOL_GPL(ovs_vport_ops_unregister);
/**
* ovs_vport_locate - find a port that has already been created
*
* @net: network namespace
* @name: name of port to find
*
* Must be called with ovs or RCU read lock.
*/
struct vport *ovs_vport_locate(const struct net *net, const char *name)
{
struct hlist_head *bucket = hash_bucket(net, name);
struct vport *vport;
hlist_for_each_entry_rcu(vport, bucket, hash_node,
lockdep_ovsl_is_held())
if (!strcmp(name, ovs_vport_name(vport)) &&
net_eq(ovs_dp_get_net(vport->dp), net))
return vport;
return NULL;
}
/**
* ovs_vport_alloc - allocate and initialize new vport
*
* @priv_size: Size of private data area to allocate.
* @ops: vport device ops
* @parms: information about new vport.
*
* Allocate and initialize a new vport defined by @ops. The vport will contain
* a private data area of size @priv_size that can be accessed using
* vport_priv(). Some parameters of the vport will be initialized from @parms.
* @vports that are no longer needed should be released with
* vport_free().
*/
struct vport *ovs_vport_alloc(int priv_size, const struct vport_ops *ops,
const struct vport_parms *parms)
{
struct vport *vport;
size_t alloc_size;
net: openvswitch: fix upcall counter access before allocation Currently, the per cpu upcall counters are allocated after the vport is created and inserted into the system. This could lead to the datapath accessing the counters before they are allocated resulting in a kernel Oops. Here is an example: PID: 59693 TASK: ffff0005f4f51500 CPU: 0 COMMAND: "ovs-vswitchd" #0 [ffff80000a39b5b0] __switch_to at ffffb70f0629f2f4 #1 [ffff80000a39b5d0] __schedule at ffffb70f0629f5cc #2 [ffff80000a39b650] preempt_schedule_common at ffffb70f0629fa60 #3 [ffff80000a39b670] dynamic_might_resched at ffffb70f0629fb58 #4 [ffff80000a39b680] mutex_lock_killable at ffffb70f062a1388 #5 [ffff80000a39b6a0] pcpu_alloc at ffffb70f0594460c #6 [ffff80000a39b750] __alloc_percpu_gfp at ffffb70f05944e68 #7 [ffff80000a39b760] ovs_vport_cmd_new at ffffb70ee6961b90 [openvswitch] ... PID: 58682 TASK: ffff0005b2f0bf00 CPU: 0 COMMAND: "kworker/0:3" #0 [ffff80000a5d2f40] machine_kexec at ffffb70f056a0758 #1 [ffff80000a5d2f70] __crash_kexec at ffffb70f057e2994 #2 [ffff80000a5d3100] crash_kexec at ffffb70f057e2ad8 #3 [ffff80000a5d3120] die at ffffb70f0628234c #4 [ffff80000a5d31e0] die_kernel_fault at ffffb70f062828a8 #5 [ffff80000a5d3210] __do_kernel_fault at ffffb70f056a31f4 #6 [ffff80000a5d3240] do_bad_area at ffffb70f056a32a4 #7 [ffff80000a5d3260] do_translation_fault at ffffb70f062a9710 #8 [ffff80000a5d3270] do_mem_abort at ffffb70f056a2f74 #9 [ffff80000a5d32a0] el1_abort at ffffb70f06297dac #10 [ffff80000a5d32d0] el1h_64_sync_handler at ffffb70f06299b24 #11 [ffff80000a5d3410] el1h_64_sync at ffffb70f056812dc #12 [ffff80000a5d3430] ovs_dp_upcall at ffffb70ee6963c84 [openvswitch] #13 [ffff80000a5d3470] ovs_dp_process_packet at ffffb70ee6963fdc [openvswitch] #14 [ffff80000a5d34f0] ovs_vport_receive at ffffb70ee6972c78 [openvswitch] #15 [ffff80000a5d36f0] netdev_port_receive at ffffb70ee6973948 [openvswitch] #16 [ffff80000a5d3720] netdev_frame_hook at ffffb70ee6973a28 [openvswitch] #17 [ffff80000a5d3730] __netif_receive_skb_core.constprop.0 at ffffb70f06079f90 We moved the per cpu upcall counter allocation to the existing vport alloc and free functions to solve this. Fixes: 95637d91fefd ("net: openvswitch: release vport resources on failure") Fixes: 1933ea365aa7 ("net: openvswitch: Add support to count upcall packets") Signed-off-by: Eelco Chaudron <echaudro@redhat.com> Reviewed-by: Simon Horman <simon.horman@corigine.com> Acked-by: Aaron Conole <aconole@redhat.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2023-06-06 19:56:35 +08:00
int err;
alloc_size = sizeof(struct vport);
if (priv_size) {
alloc_size = ALIGN(alloc_size, VPORT_ALIGN);
alloc_size += priv_size;
}
vport = kzalloc(alloc_size, GFP_KERNEL);
if (!vport)
return ERR_PTR(-ENOMEM);
net: openvswitch: fix upcall counter access before allocation Currently, the per cpu upcall counters are allocated after the vport is created and inserted into the system. This could lead to the datapath accessing the counters before they are allocated resulting in a kernel Oops. Here is an example: PID: 59693 TASK: ffff0005f4f51500 CPU: 0 COMMAND: "ovs-vswitchd" #0 [ffff80000a39b5b0] __switch_to at ffffb70f0629f2f4 #1 [ffff80000a39b5d0] __schedule at ffffb70f0629f5cc #2 [ffff80000a39b650] preempt_schedule_common at ffffb70f0629fa60 #3 [ffff80000a39b670] dynamic_might_resched at ffffb70f0629fb58 #4 [ffff80000a39b680] mutex_lock_killable at ffffb70f062a1388 #5 [ffff80000a39b6a0] pcpu_alloc at ffffb70f0594460c #6 [ffff80000a39b750] __alloc_percpu_gfp at ffffb70f05944e68 #7 [ffff80000a39b760] ovs_vport_cmd_new at ffffb70ee6961b90 [openvswitch] ... PID: 58682 TASK: ffff0005b2f0bf00 CPU: 0 COMMAND: "kworker/0:3" #0 [ffff80000a5d2f40] machine_kexec at ffffb70f056a0758 #1 [ffff80000a5d2f70] __crash_kexec at ffffb70f057e2994 #2 [ffff80000a5d3100] crash_kexec at ffffb70f057e2ad8 #3 [ffff80000a5d3120] die at ffffb70f0628234c #4 [ffff80000a5d31e0] die_kernel_fault at ffffb70f062828a8 #5 [ffff80000a5d3210] __do_kernel_fault at ffffb70f056a31f4 #6 [ffff80000a5d3240] do_bad_area at ffffb70f056a32a4 #7 [ffff80000a5d3260] do_translation_fault at ffffb70f062a9710 #8 [ffff80000a5d3270] do_mem_abort at ffffb70f056a2f74 #9 [ffff80000a5d32a0] el1_abort at ffffb70f06297dac #10 [ffff80000a5d32d0] el1h_64_sync_handler at ffffb70f06299b24 #11 [ffff80000a5d3410] el1h_64_sync at ffffb70f056812dc #12 [ffff80000a5d3430] ovs_dp_upcall at ffffb70ee6963c84 [openvswitch] #13 [ffff80000a5d3470] ovs_dp_process_packet at ffffb70ee6963fdc [openvswitch] #14 [ffff80000a5d34f0] ovs_vport_receive at ffffb70ee6972c78 [openvswitch] #15 [ffff80000a5d36f0] netdev_port_receive at ffffb70ee6973948 [openvswitch] #16 [ffff80000a5d3720] netdev_frame_hook at ffffb70ee6973a28 [openvswitch] #17 [ffff80000a5d3730] __netif_receive_skb_core.constprop.0 at ffffb70f06079f90 We moved the per cpu upcall counter allocation to the existing vport alloc and free functions to solve this. Fixes: 95637d91fefd ("net: openvswitch: release vport resources on failure") Fixes: 1933ea365aa7 ("net: openvswitch: Add support to count upcall packets") Signed-off-by: Eelco Chaudron <echaudro@redhat.com> Reviewed-by: Simon Horman <simon.horman@corigine.com> Acked-by: Aaron Conole <aconole@redhat.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2023-06-06 19:56:35 +08:00
vport->upcall_stats = netdev_alloc_pcpu_stats(struct vport_upcall_stats_percpu);
if (!vport->upcall_stats) {
err = -ENOMEM;
goto err_kfree_vport;
}
vport->dp = parms->dp;
vport->port_no = parms->port_no;
vport->ops = ops;
INIT_HLIST_NODE(&vport->dp_hash_node);
if (ovs_vport_set_upcall_portids(vport, parms->upcall_portids)) {
net: openvswitch: fix upcall counter access before allocation Currently, the per cpu upcall counters are allocated after the vport is created and inserted into the system. This could lead to the datapath accessing the counters before they are allocated resulting in a kernel Oops. Here is an example: PID: 59693 TASK: ffff0005f4f51500 CPU: 0 COMMAND: "ovs-vswitchd" #0 [ffff80000a39b5b0] __switch_to at ffffb70f0629f2f4 #1 [ffff80000a39b5d0] __schedule at ffffb70f0629f5cc #2 [ffff80000a39b650] preempt_schedule_common at ffffb70f0629fa60 #3 [ffff80000a39b670] dynamic_might_resched at ffffb70f0629fb58 #4 [ffff80000a39b680] mutex_lock_killable at ffffb70f062a1388 #5 [ffff80000a39b6a0] pcpu_alloc at ffffb70f0594460c #6 [ffff80000a39b750] __alloc_percpu_gfp at ffffb70f05944e68 #7 [ffff80000a39b760] ovs_vport_cmd_new at ffffb70ee6961b90 [openvswitch] ... PID: 58682 TASK: ffff0005b2f0bf00 CPU: 0 COMMAND: "kworker/0:3" #0 [ffff80000a5d2f40] machine_kexec at ffffb70f056a0758 #1 [ffff80000a5d2f70] __crash_kexec at ffffb70f057e2994 #2 [ffff80000a5d3100] crash_kexec at ffffb70f057e2ad8 #3 [ffff80000a5d3120] die at ffffb70f0628234c #4 [ffff80000a5d31e0] die_kernel_fault at ffffb70f062828a8 #5 [ffff80000a5d3210] __do_kernel_fault at ffffb70f056a31f4 #6 [ffff80000a5d3240] do_bad_area at ffffb70f056a32a4 #7 [ffff80000a5d3260] do_translation_fault at ffffb70f062a9710 #8 [ffff80000a5d3270] do_mem_abort at ffffb70f056a2f74 #9 [ffff80000a5d32a0] el1_abort at ffffb70f06297dac #10 [ffff80000a5d32d0] el1h_64_sync_handler at ffffb70f06299b24 #11 [ffff80000a5d3410] el1h_64_sync at ffffb70f056812dc #12 [ffff80000a5d3430] ovs_dp_upcall at ffffb70ee6963c84 [openvswitch] #13 [ffff80000a5d3470] ovs_dp_process_packet at ffffb70ee6963fdc [openvswitch] #14 [ffff80000a5d34f0] ovs_vport_receive at ffffb70ee6972c78 [openvswitch] #15 [ffff80000a5d36f0] netdev_port_receive at ffffb70ee6973948 [openvswitch] #16 [ffff80000a5d3720] netdev_frame_hook at ffffb70ee6973a28 [openvswitch] #17 [ffff80000a5d3730] __netif_receive_skb_core.constprop.0 at ffffb70f06079f90 We moved the per cpu upcall counter allocation to the existing vport alloc and free functions to solve this. Fixes: 95637d91fefd ("net: openvswitch: release vport resources on failure") Fixes: 1933ea365aa7 ("net: openvswitch: Add support to count upcall packets") Signed-off-by: Eelco Chaudron <echaudro@redhat.com> Reviewed-by: Simon Horman <simon.horman@corigine.com> Acked-by: Aaron Conole <aconole@redhat.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2023-06-06 19:56:35 +08:00
err = -EINVAL;
goto err_free_percpu;
}
return vport;
net: openvswitch: fix upcall counter access before allocation Currently, the per cpu upcall counters are allocated after the vport is created and inserted into the system. This could lead to the datapath accessing the counters before they are allocated resulting in a kernel Oops. Here is an example: PID: 59693 TASK: ffff0005f4f51500 CPU: 0 COMMAND: "ovs-vswitchd" #0 [ffff80000a39b5b0] __switch_to at ffffb70f0629f2f4 #1 [ffff80000a39b5d0] __schedule at ffffb70f0629f5cc #2 [ffff80000a39b650] preempt_schedule_common at ffffb70f0629fa60 #3 [ffff80000a39b670] dynamic_might_resched at ffffb70f0629fb58 #4 [ffff80000a39b680] mutex_lock_killable at ffffb70f062a1388 #5 [ffff80000a39b6a0] pcpu_alloc at ffffb70f0594460c #6 [ffff80000a39b750] __alloc_percpu_gfp at ffffb70f05944e68 #7 [ffff80000a39b760] ovs_vport_cmd_new at ffffb70ee6961b90 [openvswitch] ... PID: 58682 TASK: ffff0005b2f0bf00 CPU: 0 COMMAND: "kworker/0:3" #0 [ffff80000a5d2f40] machine_kexec at ffffb70f056a0758 #1 [ffff80000a5d2f70] __crash_kexec at ffffb70f057e2994 #2 [ffff80000a5d3100] crash_kexec at ffffb70f057e2ad8 #3 [ffff80000a5d3120] die at ffffb70f0628234c #4 [ffff80000a5d31e0] die_kernel_fault at ffffb70f062828a8 #5 [ffff80000a5d3210] __do_kernel_fault at ffffb70f056a31f4 #6 [ffff80000a5d3240] do_bad_area at ffffb70f056a32a4 #7 [ffff80000a5d3260] do_translation_fault at ffffb70f062a9710 #8 [ffff80000a5d3270] do_mem_abort at ffffb70f056a2f74 #9 [ffff80000a5d32a0] el1_abort at ffffb70f06297dac #10 [ffff80000a5d32d0] el1h_64_sync_handler at ffffb70f06299b24 #11 [ffff80000a5d3410] el1h_64_sync at ffffb70f056812dc #12 [ffff80000a5d3430] ovs_dp_upcall at ffffb70ee6963c84 [openvswitch] #13 [ffff80000a5d3470] ovs_dp_process_packet at ffffb70ee6963fdc [openvswitch] #14 [ffff80000a5d34f0] ovs_vport_receive at ffffb70ee6972c78 [openvswitch] #15 [ffff80000a5d36f0] netdev_port_receive at ffffb70ee6973948 [openvswitch] #16 [ffff80000a5d3720] netdev_frame_hook at ffffb70ee6973a28 [openvswitch] #17 [ffff80000a5d3730] __netif_receive_skb_core.constprop.0 at ffffb70f06079f90 We moved the per cpu upcall counter allocation to the existing vport alloc and free functions to solve this. Fixes: 95637d91fefd ("net: openvswitch: release vport resources on failure") Fixes: 1933ea365aa7 ("net: openvswitch: Add support to count upcall packets") Signed-off-by: Eelco Chaudron <echaudro@redhat.com> Reviewed-by: Simon Horman <simon.horman@corigine.com> Acked-by: Aaron Conole <aconole@redhat.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2023-06-06 19:56:35 +08:00
err_free_percpu:
free_percpu(vport->upcall_stats);
err_kfree_vport:
kfree(vport);
return ERR_PTR(err);
}
EXPORT_SYMBOL_GPL(ovs_vport_alloc);
/**
* ovs_vport_free - uninitialize and free vport
*
* @vport: vport to free
*
* Frees a vport allocated with vport_alloc() when it is no longer needed.
*
* The caller must ensure that an RCU grace period has passed since the last
* time @vport was in a datapath.
*/
void ovs_vport_free(struct vport *vport)
{
/* vport is freed from RCU callback or error path, Therefore
* it is safe to use raw dereference.
*/
kfree(rcu_dereference_raw(vport->upcall_portids));
net: openvswitch: fix upcall counter access before allocation Currently, the per cpu upcall counters are allocated after the vport is created and inserted into the system. This could lead to the datapath accessing the counters before they are allocated resulting in a kernel Oops. Here is an example: PID: 59693 TASK: ffff0005f4f51500 CPU: 0 COMMAND: "ovs-vswitchd" #0 [ffff80000a39b5b0] __switch_to at ffffb70f0629f2f4 #1 [ffff80000a39b5d0] __schedule at ffffb70f0629f5cc #2 [ffff80000a39b650] preempt_schedule_common at ffffb70f0629fa60 #3 [ffff80000a39b670] dynamic_might_resched at ffffb70f0629fb58 #4 [ffff80000a39b680] mutex_lock_killable at ffffb70f062a1388 #5 [ffff80000a39b6a0] pcpu_alloc at ffffb70f0594460c #6 [ffff80000a39b750] __alloc_percpu_gfp at ffffb70f05944e68 #7 [ffff80000a39b760] ovs_vport_cmd_new at ffffb70ee6961b90 [openvswitch] ... PID: 58682 TASK: ffff0005b2f0bf00 CPU: 0 COMMAND: "kworker/0:3" #0 [ffff80000a5d2f40] machine_kexec at ffffb70f056a0758 #1 [ffff80000a5d2f70] __crash_kexec at ffffb70f057e2994 #2 [ffff80000a5d3100] crash_kexec at ffffb70f057e2ad8 #3 [ffff80000a5d3120] die at ffffb70f0628234c #4 [ffff80000a5d31e0] die_kernel_fault at ffffb70f062828a8 #5 [ffff80000a5d3210] __do_kernel_fault at ffffb70f056a31f4 #6 [ffff80000a5d3240] do_bad_area at ffffb70f056a32a4 #7 [ffff80000a5d3260] do_translation_fault at ffffb70f062a9710 #8 [ffff80000a5d3270] do_mem_abort at ffffb70f056a2f74 #9 [ffff80000a5d32a0] el1_abort at ffffb70f06297dac #10 [ffff80000a5d32d0] el1h_64_sync_handler at ffffb70f06299b24 #11 [ffff80000a5d3410] el1h_64_sync at ffffb70f056812dc #12 [ffff80000a5d3430] ovs_dp_upcall at ffffb70ee6963c84 [openvswitch] #13 [ffff80000a5d3470] ovs_dp_process_packet at ffffb70ee6963fdc [openvswitch] #14 [ffff80000a5d34f0] ovs_vport_receive at ffffb70ee6972c78 [openvswitch] #15 [ffff80000a5d36f0] netdev_port_receive at ffffb70ee6973948 [openvswitch] #16 [ffff80000a5d3720] netdev_frame_hook at ffffb70ee6973a28 [openvswitch] #17 [ffff80000a5d3730] __netif_receive_skb_core.constprop.0 at ffffb70f06079f90 We moved the per cpu upcall counter allocation to the existing vport alloc and free functions to solve this. Fixes: 95637d91fefd ("net: openvswitch: release vport resources on failure") Fixes: 1933ea365aa7 ("net: openvswitch: Add support to count upcall packets") Signed-off-by: Eelco Chaudron <echaudro@redhat.com> Reviewed-by: Simon Horman <simon.horman@corigine.com> Acked-by: Aaron Conole <aconole@redhat.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2023-06-06 19:56:35 +08:00
free_percpu(vport->upcall_stats);
kfree(vport);
}
EXPORT_SYMBOL_GPL(ovs_vport_free);
static struct vport_ops *ovs_vport_lookup(const struct vport_parms *parms)
{
struct vport_ops *ops;
list_for_each_entry(ops, &vport_ops_list, list)
if (ops->type == parms->type)
return ops;
return NULL;
}
/**
* ovs_vport_add - add vport device (for kernel callers)
*
* @parms: Information about new vport.
*
* Creates a new vport with the specified configuration (which is dependent on
* device type). ovs_mutex must be held.
*/
struct vport *ovs_vport_add(const struct vport_parms *parms)
{
struct vport_ops *ops;
struct vport *vport;
ops = ovs_vport_lookup(parms);
if (ops) {
struct hlist_head *bucket;
if (!try_module_get(ops->owner))
return ERR_PTR(-EAFNOSUPPORT);
vport = ops->create(parms);
if (IS_ERR(vport)) {
module_put(ops->owner);
return vport;
}
bucket = hash_bucket(ovs_dp_get_net(vport->dp),
ovs_vport_name(vport));
hlist_add_head_rcu(&vport->hash_node, bucket);
return vport;
}
/* Unlock to attempt module load and return -EAGAIN if load
* was successful as we need to restart the port addition
* workflow.
*/
ovs_unlock();
request_module("vport-type-%d", parms->type);
ovs_lock();
if (!ovs_vport_lookup(parms))
return ERR_PTR(-EAFNOSUPPORT);
else
return ERR_PTR(-EAGAIN);
}
/**
* ovs_vport_set_options - modify existing vport device (for kernel callers)
*
* @vport: vport to modify.
* @options: New configuration.
*
* Modifies an existing device with the specified configuration (which is
* dependent on device type). ovs_mutex must be held.
*/
int ovs_vport_set_options(struct vport *vport, struct nlattr *options)
{
if (!vport->ops->set_options)
return -EOPNOTSUPP;
return vport->ops->set_options(vport, options);
}
/**
* ovs_vport_del - delete existing vport device
*
* @vport: vport to delete.
*
* Detaches @vport from its datapath and destroys it. ovs_mutex must
* be held.
*/
void ovs_vport_del(struct vport *vport)
{
hlist_del_rcu(&vport->hash_node);
module_put(vport->ops->owner);
vport->ops->destroy(vport);
}
/**
* ovs_vport_get_stats - retrieve device stats
*
* @vport: vport from which to retrieve the stats
* @stats: location to store stats
*
* Retrieves transmit, receive, and error stats for the given device.
*
* Must be called with ovs_mutex or rcu_read_lock.
*/
void ovs_vport_get_stats(struct vport *vport, struct ovs_vport_stats *stats)
{
openvswitch: Fix ovs_vport_get_stats() Not every device has dev->tstats set. So when OVS tries to calculate vport stats it causes kernel panic. Following patch fixes it by using standard API to get net-device stats. ---8<--- Unable to handle kernel paging request at virtual address 766b4008 Internal error: Oops: 96000005 [#1] PREEMPT SMP Modules linked in: vport_vxlan vxlan ip6_udp_tunnel udp_tunnel tun bridge stp llc openvswitch ipv6 CPU: 7 PID: 1108 Comm: ovs-vswitchd Not tainted 4.3.0-rc3+ #82 PC is at ovs_vport_get_stats+0x150/0x1f8 [openvswitch] <snip> Call trace: [<ffffffbffc0859f8>] ovs_vport_get_stats+0x150/0x1f8 [openvswitch] [<ffffffbffc07cdb0>] ovs_vport_cmd_fill_info+0x140/0x1e0 [openvswitch] [<ffffffbffc07cf0c>] ovs_vport_cmd_dump+0xbc/0x138 [openvswitch] [<ffffffc00045a5ac>] netlink_dump+0xb8/0x258 [<ffffffc00045ace0>] __netlink_dump_start+0x120/0x178 [<ffffffc00045dd9c>] genl_family_rcv_msg+0x2d4/0x308 [<ffffffc00045de58>] genl_rcv_msg+0x88/0xc4 [<ffffffc00045cf24>] netlink_rcv_skb+0xd4/0x100 [<ffffffc00045dab0>] genl_rcv+0x30/0x48 [<ffffffc00045c830>] netlink_unicast+0x154/0x200 [<ffffffc00045cc9c>] netlink_sendmsg+0x308/0x364 [<ffffffc00041e10c>] sock_sendmsg+0x14/0x2c [<ffffffc000420d58>] SyS_sendto+0xbc/0xf0 Code: aa1603e1 f94037a4 aa1303e2 aa1703e0 (f9400465) Reported-by: Tomasz Sawicki <tomasz.sawicki@objectiveintegration.uk> Fixes: 8c876639c98 ("openvswitch: Remove vport stats.") Signed-off-by: Pravin B Shelar <pshelar@nicira.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2015-10-03 05:56:34 +08:00
const struct rtnl_link_stats64 *dev_stats;
struct rtnl_link_stats64 temp;
dev_stats = dev_get_stats(vport->dev, &temp);
stats->rx_errors = dev_stats->rx_errors;
stats->tx_errors = dev_stats->tx_errors;
stats->tx_dropped = dev_stats->tx_dropped;
stats->rx_dropped = dev_stats->rx_dropped;
stats->rx_bytes = dev_stats->rx_bytes;
stats->rx_packets = dev_stats->rx_packets;
stats->tx_bytes = dev_stats->tx_bytes;
stats->tx_packets = dev_stats->tx_packets;
}
/**
* ovs_vport_get_upcall_stats - retrieve upcall stats
*
* @vport: vport from which to retrieve the stats.
* @skb: sk_buff where upcall stats should be appended.
*
* Retrieves upcall stats for the given device.
*
* Must be called with ovs_mutex or rcu_read_lock.
*/
int ovs_vport_get_upcall_stats(struct vport *vport, struct sk_buff *skb)
{
struct nlattr *nla;
int i;
__u64 tx_success = 0;
__u64 tx_fail = 0;
for_each_possible_cpu(i) {
const struct vport_upcall_stats_percpu *stats;
unsigned int start;
stats = per_cpu_ptr(vport->upcall_stats, i);
do {
start = u64_stats_fetch_begin(&stats->syncp);
tx_success += u64_stats_read(&stats->n_success);
tx_fail += u64_stats_read(&stats->n_fail);
} while (u64_stats_fetch_retry(&stats->syncp, start));
}
nla = nla_nest_start_noflag(skb, OVS_VPORT_ATTR_UPCALL_STATS);
if (!nla)
return -EMSGSIZE;
if (nla_put_u64_64bit(skb, OVS_VPORT_UPCALL_ATTR_SUCCESS, tx_success,
OVS_VPORT_ATTR_PAD)) {
nla_nest_cancel(skb, nla);
return -EMSGSIZE;
}
if (nla_put_u64_64bit(skb, OVS_VPORT_UPCALL_ATTR_FAIL, tx_fail,
OVS_VPORT_ATTR_PAD)) {
nla_nest_cancel(skb, nla);
return -EMSGSIZE;
}
nla_nest_end(skb, nla);
return 0;
}
/**
* ovs_vport_get_options - retrieve device options
*
* @vport: vport from which to retrieve the options.
* @skb: sk_buff where options should be appended.
*
* Retrieves the configuration of the given device, appending an
* %OVS_VPORT_ATTR_OPTIONS attribute that in turn contains nested
* vport-specific attributes to @skb.
*
* Returns 0 if successful, -EMSGSIZE if @skb has insufficient room, or another
* negative error code if a real error occurred. If an error occurs, @skb is
* left unmodified.
*
* Must be called with ovs_mutex or rcu_read_lock.
*/
int ovs_vport_get_options(const struct vport *vport, struct sk_buff *skb)
{
struct nlattr *nla;
int err;
if (!vport->ops->get_options)
return 0;
nla = nla_nest_start_noflag(skb, OVS_VPORT_ATTR_OPTIONS);
if (!nla)
return -EMSGSIZE;
err = vport->ops->get_options(vport, skb);
if (err) {
nla_nest_cancel(skb, nla);
return err;
}
nla_nest_end(skb, nla);
return 0;
}
/**
* ovs_vport_set_upcall_portids - set upcall portids of @vport.
*
* @vport: vport to modify.
* @ids: new configuration, an array of port ids.
*
* Sets the vport's upcall_portids to @ids.
*
* Returns 0 if successful, -EINVAL if @ids is zero length or cannot be parsed
* as an array of U32.
*
* Must be called with ovs_mutex.
*/
int ovs_vport_set_upcall_portids(struct vport *vport, const struct nlattr *ids)
{
struct vport_portids *old, *vport_portids;
if (!nla_len(ids) || nla_len(ids) % sizeof(u32))
return -EINVAL;
old = ovsl_dereference(vport->upcall_portids);
vport_portids = kmalloc(sizeof(*vport_portids) + nla_len(ids),
GFP_KERNEL);
if (!vport_portids)
return -ENOMEM;
vport_portids->n_ids = nla_len(ids) / sizeof(u32);
vport_portids->rn_ids = reciprocal_value(vport_portids->n_ids);
nla_memcpy(vport_portids->ids, ids, nla_len(ids));
rcu_assign_pointer(vport->upcall_portids, vport_portids);
if (old)
kfree_rcu(old, rcu);
return 0;
}
/**
* ovs_vport_get_upcall_portids - get the upcall_portids of @vport.
*
* @vport: vport from which to retrieve the portids.
* @skb: sk_buff where portids should be appended.
*
* Retrieves the configuration of the given vport, appending the
* %OVS_VPORT_ATTR_UPCALL_PID attribute which is the array of upcall
* portids to @skb.
*
* Returns 0 if successful, -EMSGSIZE if @skb has insufficient room.
* If an error occurs, @skb is left unmodified. Must be called with
* ovs_mutex or rcu_read_lock.
*/
int ovs_vport_get_upcall_portids(const struct vport *vport,
struct sk_buff *skb)
{
struct vport_portids *ids;
ids = rcu_dereference_ovsl(vport->upcall_portids);
if (vport->dp->user_features & OVS_DP_F_VPORT_PIDS)
return nla_put(skb, OVS_VPORT_ATTR_UPCALL_PID,
ids->n_ids * sizeof(u32), (void *)ids->ids);
else
return nla_put_u32(skb, OVS_VPORT_ATTR_UPCALL_PID, ids->ids[0]);
}
/**
* ovs_vport_find_upcall_portid - find the upcall portid to send upcall.
*
* @vport: vport from which the missed packet is received.
* @skb: skb that the missed packet was received.
*
* Uses the skb_get_hash() to select the upcall portid to send the
* upcall.
*
* Returns the portid of the target socket. Must be called with rcu_read_lock.
*/
u32 ovs_vport_find_upcall_portid(const struct vport *vport,
struct sk_buff *skb)
{
struct vport_portids *ids;
u32 ids_index;
u32 hash;
ids = rcu_dereference(vport->upcall_portids);
/* If there is only one portid, select it in the fast-path. */
if (ids->n_ids == 1)
return ids->ids[0];
hash = skb_get_hash(skb);
ids_index = hash - ids->n_ids * reciprocal_divide(hash, ids->rn_ids);
return ids->ids[ids_index];
}
/**
* ovs_vport_receive - pass up received packet to the datapath for processing
*
* @vport: vport that received the packet
* @skb: skb that was received
* @tun_info: tunnel (if any) that carried packet
*
* Must be called with rcu_read_lock. The packet cannot be shared and
* skb->data should point to the Ethernet header.
*/
int ovs_vport_receive(struct vport *vport, struct sk_buff *skb,
const struct ip_tunnel_info *tun_info)
{
struct sw_flow_key key;
int error;
OVS_CB(skb)->input_vport = vport;
openvswitch: Add conntrack action Expose the kernel connection tracker via OVS. Userspace components can make use of the CT action to populate the connection state (ct_state) field for a flow. This state can be subsequently matched. Exposed connection states are OVS_CS_F_*: - NEW (0x01) - Beginning of a new connection. - ESTABLISHED (0x02) - Part of an existing connection. - RELATED (0x04) - Related to an established connection. - INVALID (0x20) - Could not track the connection for this packet. - REPLY_DIR (0x40) - This packet is in the reply direction for the flow. - TRACKED (0x80) - This packet has been sent through conntrack. When the CT action is executed by itself, it will send the packet through the connection tracker and populate the ct_state field with one or more of the connection state flags above. The CT action will always set the TRACKED bit. When the COMMIT flag is passed to the conntrack action, this specifies that information about the connection should be stored. This allows subsequent packets for the same (or related) connections to be correlated with this connection. Sending subsequent packets for the connection through conntrack allows the connection tracker to consider the packets as ESTABLISHED, RELATED, and/or REPLY_DIR. The CT action may optionally take a zone to track the flow within. This allows connections with the same 5-tuple to be kept logically separate from connections in other zones. If the zone is specified, then the "ct_zone" match field will be subsequently populated with the zone id. IP fragments are handled by transparently assembling them as part of the CT action. The maximum received unit (MRU) size is tracked so that refragmentation can occur during output. IP frag handling contributed by Andy Zhou. Based on original design by Justin Pettit. Signed-off-by: Joe Stringer <joestringer@nicira.com> Signed-off-by: Justin Pettit <jpettit@nicira.com> Signed-off-by: Andy Zhou <azhou@nicira.com> Acked-by: Thomas Graf <tgraf@suug.ch> Acked-by: Pravin B Shelar <pshelar@nicira.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2015-08-27 02:31:48 +08:00
OVS_CB(skb)->mru = 0;
OVS_CB(skb)->cutlen = 0;
if (unlikely(dev_net(skb->dev) != ovs_dp_get_net(vport->dp))) {
u32 mark;
mark = skb->mark;
skb_scrub_packet(skb, true);
skb->mark = mark;
tun_info = NULL;
}
/* Extract flow from 'skb' into 'key'. */
error = ovs_flow_key_extract(tun_info, skb, &key);
if (unlikely(error)) {
kfree_skb(skb);
return error;
}
ovs_dp_process_packet(skb, &key);
return 0;
}
static int packet_length(const struct sk_buff *skb,
struct net_device *dev)
{
int length = skb->len - dev->hard_header_len;
if (!skb_vlan_tag_present(skb) &&
eth_type_vlan(skb->protocol))
length -= VLAN_HLEN;
/* Don't subtract for multiple VLAN tags. Most (all?) drivers allow
* (ETH_LEN + VLAN_HLEN) in addition to the mtu value, but almost none
* account for 802.1ad. e.g. is_skb_forwardable().
*/
return length > 0 ? length : 0;
}
void ovs_vport_send(struct vport *vport, struct sk_buff *skb, u8 mac_proto)
{
int mtu = vport->dev->mtu;
switch (vport->dev->type) {
case ARPHRD_NONE:
if (mac_proto == MAC_PROTO_ETHERNET) {
skb_reset_network_header(skb);
skb_reset_mac_len(skb);
skb->protocol = htons(ETH_P_TEB);
} else if (mac_proto != MAC_PROTO_NONE) {
WARN_ON_ONCE(1);
goto drop;
}
break;
case ARPHRD_ETHER:
if (mac_proto != MAC_PROTO_ETHERNET)
goto drop;
break;
default:
goto drop;
}
if (unlikely(packet_length(skb, vport->dev) > mtu &&
!skb_is_gso(skb))) {
vport->dev->stats.tx_errors++;
if (vport->dev->flags & IFF_UP)
net_warn_ratelimited("%s: dropped over-mtu packet: "
"%d > %d\n", vport->dev->name,
packet_length(skb, vport->dev),
mtu);
goto drop;
}
skb->dev = vport->dev;
skb_clear_tstamp(skb);
vport->ops->send(skb);
return;
drop:
kfree_skb(skb);
}