* [PATCH net-next 4/5] be2net: Fix EEH error reset before a flash dump completes
From: Somnath Kotur @ 2012-04-30 6:05 UTC (permalink / raw)
To: netdev; +Cc: Somnath Kotur, Sathya Perla
An EEH error can cause the FW to trigger a flash debug dump.
Resetting the card while flash dump is in progress can cause it not to recover.
Wait for it to finish before letting EEH flow to reset the card.
Signed-off-by: Sathya Perla <Sathya.Perla@emulex.com>
Signed-off-by: Somnath Kotur <somnath.kotur@emulex.com>
---
drivers/net/ethernet/emulex/benet/be_main.c | 5 +++++
1 files changed, 5 insertions(+), 0 deletions(-)
diff --git a/drivers/net/ethernet/emulex/benet/be_main.c b/drivers/net/ethernet/emulex/benet/be_main.c
index b7bc905..6d5d30b 100644
--- a/drivers/net/ethernet/emulex/benet/be_main.c
+++ b/drivers/net/ethernet/emulex/benet/be_main.c
@@ -3821,6 +3821,11 @@ static pci_ers_result_t be_eeh_err_detected(struct pci_dev *pdev,
pci_disable_device(pdev);
+ /* The error could cause the FW to trigger a flash debug dump.
+ * Resetting the card while flash dump is in progress
+ * can cause it not to recover; wait for it to finish
+ */
+ ssleep(30);
return PCI_ERS_RESULT_NEED_RESET;
}
--
1.5.6.1
^ permalink raw reply related
* [PATCH net-next 5/5] be2net: Fix to allow set/get of debug levels in the Firmware.
From: Somnath Kotur @ 2012-04-30 6:05 UTC (permalink / raw)
To: netdev; +Cc: Somnath Kotur, Suresh Reddy
Suggested-by: Ben Hutchings <bhutchings@solarflare.com>
Signed-off-by: Suresh Reddy <Suresh.Reddy@emulex.com>
Signed-off-by: Somnath Kotur <somnath.kotur@emulex.com>
---
drivers/net/ethernet/emulex/benet/be_cmds.c | 60 +++++++++++++
drivers/net/ethernet/emulex/benet/be_cmds.h | 70 +++++++++++++++
drivers/net/ethernet/emulex/benet/be_ethtool.c | 108 ++++++++++++++++++++++++
3 files changed, 238 insertions(+), 0 deletions(-)
diff --git a/drivers/net/ethernet/emulex/benet/be_cmds.c b/drivers/net/ethernet/emulex/benet/be_cmds.c
index 43167e8..29bc5d5 100644
--- a/drivers/net/ethernet/emulex/benet/be_cmds.c
+++ b/drivers/net/ethernet/emulex/benet/be_cmds.c
@@ -2590,3 +2590,63 @@ err:
pci_free_consistent(adapter->pdev, cmd.size, cmd.va, cmd.dma);
return status;
}
+
+int be_cmd_get_ext_fat_capabilites(struct be_adapter *adapter,
+ struct be_dma_mem *cmd)
+{
+ struct be_mcc_wrb *wrb;
+ struct be_cmd_req_get_ext_fat_caps *req;
+ int status;
+
+
+ spin_lock_bh(&adapter->mcc_lock);
+
+ wrb = wrb_from_mccq(adapter);
+ if (!wrb) {
+ status = -EBUSY;
+ goto err;
+ }
+
+ req = cmd->va;
+ be_wrb_cmd_hdr_prepare(&req->hdr, CMD_SUBSYSTEM_COMMON,
+ OPCODE_COMMON_GET_EXT_FAT_CAPABILITES,
+ cmd->size, wrb, cmd);
+ /*
+ * Retrieve currently set parameters
+ */
+ req->parameter_type = cpu_to_le32(1);
+
+ status = be_mcc_notify_wait(adapter);
+err:
+ spin_unlock_bh(&adapter->mcc_lock);
+ return status;
+}
+
+int be_cmd_set_ext_fat_capabilites(struct be_adapter *adapter,
+ struct be_dma_mem *cmd,
+ struct be_fat_conf_params *configs)
+{
+ struct be_mcc_wrb *wrb;
+ struct be_cmd_req_set_ext_fat_caps *req;
+ int status;
+
+ spin_lock_bh(&adapter->mcc_lock);
+
+ wrb = wrb_from_mccq(adapter);
+ if (!wrb) {
+ status = -EBUSY;
+ goto err;
+ }
+
+ req = cmd->va;
+ memcpy(&req->set_params, configs, sizeof(struct be_fat_conf_params));
+ be_wrb_cmd_hdr_prepare(&req->hdr, CMD_SUBSYSTEM_COMMON,
+ OPCODE_COMMON_SET_EXT_FAT_CAPABILITES,
+ cmd->size, wrb, cmd);
+
+ status = be_mcc_notify_wait(adapter);
+err:
+ spin_unlock_bh(&adapter->mcc_lock);
+ return status;
+}
+
diff --git a/drivers/net/ethernet/emulex/benet/be_cmds.h b/drivers/net/ethernet/emulex/benet/be_cmds.h
index 944f031..b244e22 100644
--- a/drivers/net/ethernet/emulex/benet/be_cmds.h
+++ b/drivers/net/ethernet/emulex/benet/be_cmds.h
@@ -189,6 +189,8 @@ struct be_mcc_mailbox {
#define OPCODE_COMMON_GET_PHY_DETAILS 102
#define OPCODE_COMMON_SET_DRIVER_FUNCTION_CAP 103
#define OPCODE_COMMON_GET_CNTL_ADDITIONAL_ATTRIBUTES 121
+#define OPCODE_COMMON_GET_EXT_FAT_CAPABILITES 125
+#define OPCODE_COMMON_SET_EXT_FAT_CAPABILITES 126
#define OPCODE_COMMON_GET_MAC_LIST 147
#define OPCODE_COMMON_SET_MAC_LIST 148
#define OPCODE_COMMON_GET_HSW_CONFIG 152
@@ -1602,6 +1604,69 @@ static inline void *be_erx_stats_from_cmd(struct be_adapter *adapter)
}
}
+
+/************** get fat capabilites *******************/
+#define MAX_MODULES 27
+#define MAX_MODES 4
+#define MODE_UART 0
+
+/* Trace level Valid values */
+enum {
+ TRACE_LEVEL_ALL = 0x0,
+ TRACE_LEVEL_ENTER_FUNCTION = 0x1,
+ TRACE_LEVEL_VERBOSE = 0x4,
+ TRACE_LEVEL_INFO = 0x5,
+ TRACE_LEVEL_TEST = 0x8,
+ TRACE_LEVEL_SHOW = 0x10,
+ TRACE_LEVEL_WARNING = 0x20,
+ TRACE_LEVEL_ERROR = 0x30,
+ TRACE_LEVEL_FATAL = 0x40,
+ TRACE_LEVEL_ALWAYS = 0x80,
+ TRACE_LEVEL_DISABLED = 0xff
+};
+
+struct ext_fat_mode {
+ u8 mode;
+ u8 rsvd0;
+ u16 port_mask;
+ u32 dbg_lvl;
+ u64 fun_mask;
+} __packed;
+
+struct ext_fat_modules {
+ u8 modules_str[32];
+ u32 modules_id;
+ u32 num_modes;
+ struct ext_fat_mode trace_lvl[MAX_MODES];
+} __packed;
+
+struct be_fat_conf_params {
+ u32 max_log_entries;
+ u32 log_entry_size;
+ u8 log_type;
+ u8 max_log_funs;
+ u8 max_log_ports;
+ u8 rsvd0;
+ u32 supp_modes;
+ u32 num_modules;
+ struct ext_fat_modules module[MAX_MODULES];
+} __packed;
+
+struct be_cmd_req_get_ext_fat_caps {
+ struct be_cmd_req_hdr hdr;
+ u32 parameter_type;
+};
+
+struct be_cmd_resp_get_ext_fat_caps {
+ struct be_cmd_resp_hdr hdr;
+ struct be_fat_conf_params get_params;
+};
+
+struct be_cmd_req_set_ext_fat_caps {
+ struct be_cmd_req_hdr hdr;
+ struct be_fat_conf_params set_params;
+};
+
extern int be_pci_fnum_get(struct be_adapter *adapter);
extern int be_cmd_POST(struct be_adapter *adapter);
extern int be_cmd_mac_addr_query(struct be_adapter *adapter, u8 *mac_addr,
@@ -1707,4 +1772,9 @@ extern int be_cmd_set_hsw_config(struct be_adapter *adapter, u16 pvid,
extern int be_cmd_get_hsw_config(struct be_adapter *adapter, u16 *pvid,
u32 domain, u16 intf_id);
extern int be_cmd_get_acpi_wol_cap(struct be_adapter *adapter);
+extern int be_cmd_get_ext_fat_capabilites(struct be_adapter *adapter,
+ struct be_dma_mem *cmd);
+extern int be_cmd_set_ext_fat_capabilites(struct be_adapter *adapter,
+ struct be_dma_mem *cmd,
+ struct be_fat_conf_params *cfgs);
diff --git a/drivers/net/ethernet/emulex/benet/be_ethtool.c b/drivers/net/ethernet/emulex/benet/be_ethtool.c
index 747f68f..10ef946 100644
--- a/drivers/net/ethernet/emulex/benet/be_ethtool.c
+++ b/drivers/net/ethernet/emulex/benet/be_ethtool.c
@@ -878,6 +878,112 @@ be_read_eeprom(struct net_device *netdev, struct ethtool_eeprom *eeprom,
return status;
}
+static u32 be_get_msglevel(struct net_device *netdev)
+{
+ struct be_adapter *adapter = netdev_priv(netdev);
+ struct be_dma_mem extfat_cmd;
+ struct be_fat_conf_params *cfgs;
+ u32 data = TRACE_LEVEL_ERROR;
+ int status, j;
+
+ if (lancer_chip(adapter)) {
+ dev_err(&adapter->pdev->dev, "Operation not supported\n");
+ return -EOPNOTSUPP;
+ }
+
+ memset(&extfat_cmd, 0, sizeof(struct be_dma_mem));
+ extfat_cmd.size = sizeof(struct be_cmd_resp_get_ext_fat_caps);
+ extfat_cmd.va = pci_alloc_consistent(adapter->pdev, extfat_cmd.size,
+ &extfat_cmd.dma);
+ if (!extfat_cmd.va) {
+ dev_err(&adapter->pdev->dev, "%s: Memory allocation failure\n",
+ __func__);
+ goto err;
+ }
+
+ status = be_cmd_get_ext_fat_capabilites(adapter, &extfat_cmd);
+ if (!status) {
+ cfgs = (struct be_fat_conf_params *)(extfat_cmd.va +
+ sizeof(struct be_cmd_resp_hdr));
+ for (j = 0; j < cfgs->module[0].num_modes; j++) {
+ if (cfgs->module[0].trace_lvl[j].mode ==
+ MODE_UART)
+ data = cfgs->module[0].trace_lvl[j].dbg_lvl;
+ }
+ }
+ pci_free_consistent(adapter->pdev, extfat_cmd.size, extfat_cmd.va,
+ extfat_cmd.dma);
+err:
+ return data;
+}
+
+static void be_set_msglevel(struct net_device *netdev, u32 data)
+{
+ struct be_adapter *adapter = netdev_priv(netdev);
+ struct be_dma_mem extfat_cmd;
+ struct be_fat_conf_params *cfgs;
+ int status;
+ int i, j;
+
+ if (lancer_chip(adapter)) {
+ dev_err(&adapter->pdev->dev, "Operation not supported\n");
+ return;
+ }
+
+ switch (data) {
+ case TRACE_LEVEL_ALL:
+ case TRACE_LEVEL_ENTER_FUNCTION:
+ case TRACE_LEVEL_VERBOSE:
+ case TRACE_LEVEL_INFO:
+ case TRACE_LEVEL_TEST:
+ case TRACE_LEVEL_SHOW:
+ case TRACE_LEVEL_WARNING:
+ case TRACE_LEVEL_ERROR:
+ case TRACE_LEVEL_FATAL:
+ case TRACE_LEVEL_ALWAYS:
+ case TRACE_LEVEL_DISABLED:
+ break;
+ default:
+ dev_err(&adapter->pdev->dev, "Invalid message level value\n");
+ return;
+ }
+
+ memset(&extfat_cmd, 0, sizeof(struct be_dma_mem));
+ extfat_cmd.size = sizeof(struct be_cmd_resp_get_ext_fat_caps);
+ extfat_cmd.va = pci_alloc_consistent(adapter->pdev, extfat_cmd.size,
+ &extfat_cmd.dma);
+ if (!extfat_cmd.va) {
+ dev_err(&adapter->pdev->dev, "%s: Memory allocation failure\n",
+ __func__);
+ goto err;
+ }
+ status = be_cmd_get_ext_fat_capabilites(adapter, &extfat_cmd);
+ if (!status) {
+ cfgs = (struct be_fat_conf_params *)(extfat_cmd.va +
+ sizeof(struct be_cmd_resp_hdr));
+ for (i = 0; i < cfgs->num_modules; i++) {
+ for (j = 0; j < cfgs->module[i].num_modes; j++) {
+ if (cfgs->module[i].trace_lvl[j].mode ==
+ MODE_UART)
+ cfgs->module[i].trace_lvl[j].dbg_lvl =
+ cpu_to_le32(data);
+ }
+ }
+ status = be_cmd_set_ext_fat_capabilites(adapter, &extfat_cmd,
+ cfgs);
+ if (status)
+ dev_err(&adapter->pdev->dev,
+ "Message level set failed\n");
+ } else {
+ dev_err(&adapter->pdev->dev, "Message level get failed\n");
+ }
+
+ pci_free_consistent(adapter->pdev, extfat_cmd.size, extfat_cmd.va,
+ extfat_cmd.dma);
+err:
+ return;
+}
+
const struct ethtool_ops be_ethtool_ops = {
.get_settings = be_get_settings,
.get_drvinfo = be_get_drvinfo,
@@ -893,6 +999,8 @@ const struct ethtool_ops be_ethtool_ops = {
.set_pauseparam = be_set_pauseparam,
.get_strings = be_get_stat_strings,
.set_phys_id = be_set_phys_id,
+ .get_msglevel = be_get_msglevel,
+ .set_msglevel = be_set_msglevel,
.get_sset_count = be_get_sset_count,
.get_ethtool_stats = be_get_ethtool_stats,
.get_regs_len = be_get_reg_len,
--
1.5.6.1
^ permalink raw reply related
* [PATCH 1/1] export sysctl symbols needed by ip_vs_sync
From: Hans Schillstrom @ 2012-04-30 6:13 UTC (permalink / raw)
To: horms, ja, wensong, lvs-devel, netdev, netfilter-devel
Cc: hans, Hans Schillstrom
To build ip_vs as a module sysctl_rmem_max and sysctl_wmem_max
needs to be exported.
The dependency was added by "ipvs: wakeup master thread" patch
Signed-off-by: Hans Schillstrom <hans.schillstrom@ericsson.com>
---
net/core/sock.c | 2 ++
1 files changed, 2 insertions(+), 0 deletions(-)
diff --git a/net/core/sock.c b/net/core/sock.c
index 679c5bb..be8fe5d 100644
--- a/net/core/sock.c
+++ b/net/core/sock.c
@@ -258,7 +258,9 @@ static struct lock_class_key af_callback_keys[AF_MAX];
/* Run time adjustable parameters. */
__u32 sysctl_wmem_max __read_mostly = SK_WMEM_MAX;
+EXPORT_SYMBOL(sysctl_wmem_max);
__u32 sysctl_rmem_max __read_mostly = SK_RMEM_MAX;
+EXPORT_SYMBOL(sysctl_rmem_max);
__u32 sysctl_wmem_default __read_mostly = SK_WMEM_MAX;
__u32 sysctl_rmem_default __read_mostly = SK_RMEM_MAX;
--
1.7.2.3
^ permalink raw reply related
* Re: [PATCH 3/5] ipvs: null check of net->ipvs in lblc(r) shedulers
From: Simon Horman @ 2012-04-30 6:35 UTC (permalink / raw)
To: Pablo Neira Ayuso
Cc: lvs-devel, netdev, netfilter-devel, Wensong Zhang,
Julian Anastasov, Hans Schillstrom, Jesper Dangaard Brouer
In-Reply-To: <20120429234301.GA4790@1984>
On Mon, Apr 30, 2012 at 01:43:01AM +0200, Pablo Neira Ayuso wrote:
> On Fri, Apr 27, 2012 at 09:53:57AM +0900, Simon Horman wrote:
> > From: Hans Schillstrom <hans.schillstrom@ericsson.com>
> >
> > Avoid crash when registering shedulers after
> > the IPVS core initialization for netns fails. Do this by
> > checking for present core (net->ipvs).
> >
> > Signed-off-by: Hans Schillstrom <hans.schillstrom@ericsson.com>
> > Julian Anastasov <ja@ssi.bg>
>
> This incomplete tag has slipped through, right?
>
> Looking at the archive, I don't see any comment from Julian on this,
> so I'll just remove it from the patch description.
>
> I'll fix this minor nitppick myself. No need to resend. But you'll
> have to rebase your tree, sorry.
Sorry about that, I thought I had weeded out that problem.
^ permalink raw reply
* Re: [PATCH] net: skb_set_dev do not unconditionally drop ref to dst
From: Frank Blaschka @ 2012-04-30 6:53 UTC (permalink / raw)
To: Eric Dumazet; +Cc: arnd, davem, netdev, linux-s390
In-Reply-To: <1335765093.2296.4.camel@edumazet-glaptop>
On Mon, Apr 30, 2012 at 07:51:33AM +0200, Eric Dumazet wrote:
> On Mon, 2012-04-30 at 07:38 +0200, Frank Blaschka wrote:
> > From: Frank Blaschka <frank.blaschka@de.ibm.com>
> >
> > commit 8a83a00b0735190384a348156837918271034144 unconditionally
> > drops dst reference when skb->dev is set. This causes a regression
> > with VLAN and the qeth_l3 network driver. qeth_l3 can not get gw
> > information from the skb coming from the vlan driver. It is only
> > valid to drop the dst in case of different name spaces.
> >
> > Signed-off-by: Frank Blaschka <frank.blaschka@de.ibm.com>
> > ---
> > net/core/dev.c | 2 +-
> > 1 file changed, 1 insertion(+), 1 deletion(-)
> >
> > --- a/net/core/dev.c
> > +++ b/net/core/dev.c
> > @@ -1881,8 +1881,8 @@ EXPORT_SYMBOL(netif_device_attach);
> > #ifdef CONFIG_NET_NS
> > void skb_set_dev(struct sk_buff *skb, struct net_device *dev)
> > {
> > - skb_dst_drop(skb);
> > if (skb->dev && !net_eq(dev_net(skb->dev), dev_net(dev))) {
> > + skb_dst_drop(skb);
> > secpath_reset(skb);
> > nf_reset(skb);
> > skb_init_secmark(skb);
> >
>
> You forgot CC Arnd Bergmann <arnd@arndb.de> ?
>
> But we do want to do the skb_dst_drop() in dev_forward_skb()
>
> Your patch breaks dev_forward_skb() then.
>
> But apparently this forward path was alredy broken in Arnd patch...
>
Hi Eric,
do you have and suggestions how to fix this regression?
The qeth_l3 driver needs the gw information to address the frame.
The way to look at dst works well for the non vlan case and was
also working for vlan prior Arnds changes.
>
> --
> To unsubscribe from this list: send the line "unsubscribe netdev" in
> the body of a message to majordomo@vger.kernel.org
> More majordomo info at http://vger.kernel.org/majordomo-info.html
>
^ permalink raw reply
* [PATCH] net/nfc: Fix the compilation warning
From: joseph daniel @ 2012-04-30 7:43 UTC (permalink / raw)
To: Lauro Ramos Venancio, Aloisio Almeida Jr, Samuel Ortiz,
David S. Miller, linux-wireless, netdev, linux-kernel
Cc: joseph daniel
the nfc_llcp_general_bytes is defined in nfc/core.c as
static inline u8 *nfc_llcp_general_bytes(struct nfc_dev *dev, size_t *gb_len).
as in nfc/nfc.h:
static inline u8 *nfc_llcp_general_bytes(struct nfc_dev *dev, u8 *gb_len), as
CONFIG_NFC_LLCP is not defined.
so we got some warnings,
net/nfc/core.c:207:2: warning: passing argument 2 of ‘nfc_llcp_general_bytes’ from incompatible pointer type [enabled by default]
net/nfc/nfc.h:87:19: note: expected ‘u8 *’ but argument is of type ‘size_t *’
Signed-off-by: joseph daniel <josephdanielwalter@gmail.com>
---
net/nfc/nfc.h | 2 +-
1 file changed, 1 insertion(+), 1 deletion(-)
diff --git a/net/nfc/nfc.h b/net/nfc/nfc.h
index ec8794c..549382c 100644
--- a/net/nfc/nfc.h
+++ b/net/nfc/nfc.h
@@ -84,7 +84,7 @@ static inline int nfc_llcp_set_remote_gb(struct nfc_dev *dev,
return 0;
}
-static inline u8 *nfc_llcp_general_bytes(struct nfc_dev *dev, u8 *gb_len)
+static inline u8 *nfc_llcp_general_bytes(struct nfc_dev *dev, size_t *gb_len)
{
*gb_len = 0;
return NULL;
--
1.7.9.5
^ permalink raw reply related
* Re: [PATCH 1/1] export sysctl symbols needed by ip_vs_sync
From: Julian Anastasov @ 2012-04-30 7:47 UTC (permalink / raw)
To: Hans Schillstrom
Cc: Horms, Wensong Zhang, lvs-devel, netdev, netfilter-devel, hans
In-Reply-To: <1335766430-30528-1-git-send-email-hans.schillstrom@ericsson.com>
Hello,
On Mon, 30 Apr 2012, Hans Schillstrom wrote:
> To build ip_vs as a module sysctl_rmem_max and sysctl_wmem_max
> needs to be exported.
> The dependency was added by "ipvs: wakeup master thread" patch
>
> Signed-off-by: Hans Schillstrom <hans.schillstrom@ericsson.com>
> ---
> net/core/sock.c | 2 ++
> 1 files changed, 2 insertions(+), 0 deletions(-)
>
> diff --git a/net/core/sock.c b/net/core/sock.c
> index 679c5bb..be8fe5d 100644
> --- a/net/core/sock.c
> +++ b/net/core/sock.c
> @@ -258,7 +258,9 @@ static struct lock_class_key af_callback_keys[AF_MAX];
>
> /* Run time adjustable parameters. */
> __u32 sysctl_wmem_max __read_mostly = SK_WMEM_MAX;
> +EXPORT_SYMBOL(sysctl_wmem_max);
> __u32 sysctl_rmem_max __read_mostly = SK_RMEM_MAX;
> +EXPORT_SYMBOL(sysctl_rmem_max);
> __u32 sysctl_wmem_default __read_mostly = SK_WMEM_MAX;
> __u32 sysctl_rmem_default __read_mostly = SK_RMEM_MAX;
>
> --
> 1.7.2.3
I see why I missed this error. There is some
inefficiency in the build process. Once, I tested the
netns init problems with CONFIG_IP_VS=y, later switched back
to CONFIG_IP_VS=m without 'make clean' but the ip_vs.ko
is not considered, I still get ip_vs as builtin, not as
module:
# cat net/netfilter/ipvs/modules.builtin
kernel/net/netfilter/ipvs/ip_vs.ko
Is only 'make clean' a solution for such
y->m change?
Regards
--
Julian Anastasov <ja@ssi.bg>
^ permalink raw reply
* [PATCH 00/10 net-next] l2tp: misc fixes and add L2TPv3 IP encap over IPv6
From: James Chapman @ 2012-04-30 7:48 UTC (permalink / raw)
To: netdev
This patch series includes several L2TP fixes / cleanups and adds
L2TPv3 IP encapsulation support for IPv6, building on the L2TP UDP
IPv6 support recently added by Ben LaHaise.
1. l2tp: fix locking of 64-bit counters for smp
2. l2tp: Use ip4_datagram_connect() in l2tp_ip_connect()
3. l2tp: remove unused stats from l2tp_ip socket
4. pppox: Replace __attribute__((packed)) in if_pppox.h
5. l2tp: pppol2tp_connect() handles ipv6 sockaddr variants
6. l2tp: show IPv6 addresses in l2tp debugfs file
7. l2tp: netlink api for l2tpv3 ipv6 unmanaged tunnels
8. ipv6: export ipv6 functions for use by other protocols
9. l2tp: introduce L2TPv3 IP encapsulation support for IPv6
10. l2tp: let iproute2 create L2TPv3 IP tunnels using IPv6
Patches 1-4 are fixes / cleanups.
Patches 5-6 improve on the L2TP UDP IPv6 changes recently added.
Patches 7-10 add functionality.
A patch for iproute2 to add support for unmanaged L2TPv3 ethernet
tunnels over IPv6 will be submitted separately.
Chris Elston (4):
l2tp: show IPv6 addresses in l2tp debugfs file
l2tp: netlink api for l2tpv3 ipv6 unmanaged tunnels
ipv6: Export ipv6 functions for use by other protocols
l2tp: introduce L2TPv3 IP encapsulation support for IPv6
James Chapman (6):
l2tp: fix locking of 64-bit counters for smp
l2tp: Use ip4_datagram_connect() in l2tp_ip_connect()
l2tp: remove unused stats from l2tp_ip socket
pppox: Replace __attribute__((packed)) in if_pppox.h
l2tp: pppol2tp_connect() handles ipv6 sockaddr variants
l2tp: let iproute2 create L2TPv3 IP tunnels using IPv6
include/linux/if_pppox.h | 12 +-
include/linux/l2tp.h | 19 ++
net/ipv6/datagram.c | 4 +
net/ipv6/exthdrs.c | 1 +
net/ipv6/ip6_flowlabel.c | 1 +
net/ipv6/ip6_output.c | 3 +
net/l2tp/Makefile | 3 +
net/l2tp/l2tp_core.c | 215 ++++++++++---
net/l2tp/l2tp_core.h | 5 +
net/l2tp/l2tp_debugfs.c | 8 +
net/l2tp/l2tp_ip.c | 86 +-----
net/l2tp/l2tp_ip6.c | 792 ++++++++++++++++++++++++++++++++++++++++++++++
net/l2tp/l2tp_netlink.c | 110 ++++++--
net/l2tp/l2tp_ppp.c | 36 ++-
14 files changed, 1133 insertions(+), 162 deletions(-)
create mode 100644 net/l2tp/l2tp_ip6.c
^ permalink raw reply
* [PATCH 02/10 net-next] l2tp: Use ip4_datagram_connect() in l2tp_ip_connect()
From: James Chapman @ 2012-04-30 7:48 UTC (permalink / raw)
To: netdev
In-Reply-To: <1335772135-27910-1-git-send-email-jchapman@katalix.com>
Cleanup the l2tp_ip code to make use of an existing ipv4 support function.
Signed-off-by: James Chapman <jchapman@katalix.com>
---
net/l2tp/l2tp_ip.c | 54 ++++++---------------------------------------------
1 files changed, 7 insertions(+), 47 deletions(-)
diff --git a/net/l2tp/l2tp_ip.c b/net/l2tp/l2tp_ip.c
index 585d93e..5162592 100644
--- a/net/l2tp/l2tp_ip.c
+++ b/net/l2tp/l2tp_ip.c
@@ -299,67 +299,27 @@ static int l2tp_ip_connect(struct sock *sk, struct sockaddr *uaddr, int addr_len
{
struct sockaddr_l2tpip *lsa = (struct sockaddr_l2tpip *) uaddr;
struct inet_sock *inet = inet_sk(sk);
- struct flowi4 *fl4;
- struct rtable *rt;
- __be32 saddr;
- int oif, rc;
+ int rc;
- rc = -EINVAL;
if (addr_len < sizeof(*lsa))
- goto out;
+ return -EINVAL;
- rc = -EAFNOSUPPORT;
- if (lsa->l2tp_family != AF_INET)
- goto out;
-
- lock_sock(sk);
-
- sk_dst_reset(sk);
-
- oif = sk->sk_bound_dev_if;
- saddr = inet->inet_saddr;
-
- rc = -EINVAL;
if (ipv4_is_multicast(lsa->l2tp_addr.s_addr))
- goto out;
+ return -EINVAL;
- fl4 = &inet->cork.fl.u.ip4;
- rt = ip_route_connect(fl4, lsa->l2tp_addr.s_addr, saddr,
- RT_CONN_FLAGS(sk), oif,
- IPPROTO_L2TP,
- 0, 0, sk, true);
- if (IS_ERR(rt)) {
- rc = PTR_ERR(rt);
- if (rc == -ENETUNREACH)
- IP_INC_STATS_BH(&init_net, IPSTATS_MIB_OUTNOROUTES);
- goto out;
- }
+ rc = ip4_datagram_connect(sk, uaddr, addr_len);
+ if (rc < 0)
+ return rc;
- rc = -ENETUNREACH;
- if (rt->rt_flags & (RTCF_MULTICAST | RTCF_BROADCAST)) {
- ip_rt_put(rt);
- goto out;
- }
+ lock_sock(sk);
l2tp_ip_sk(sk)->peer_conn_id = lsa->l2tp_conn_id;
- if (!inet->inet_saddr)
- inet->inet_saddr = fl4->saddr;
- if (!inet->inet_rcv_saddr)
- inet->inet_rcv_saddr = fl4->saddr;
- inet->inet_daddr = fl4->daddr;
- sk->sk_state = TCP_ESTABLISHED;
- inet->inet_id = jiffies;
-
- sk_dst_set(sk, &rt->dst);
-
write_lock_bh(&l2tp_ip_lock);
hlist_del_init(&sk->sk_bind_node);
sk_add_bind_node(sk, &l2tp_ip_bind_table);
write_unlock_bh(&l2tp_ip_lock);
- rc = 0;
-out:
release_sock(sk);
return rc;
}
--
1.7.0.4
^ permalink raw reply related
* [PATCH 03/10 net-next] l2tp: remove unused stats from l2tp_ip socket
From: James Chapman @ 2012-04-30 7:48 UTC (permalink / raw)
To: netdev
In-Reply-To: <1335772135-27910-1-git-send-email-jchapman@katalix.com>
The l2tp_ip socket currently maintains packet/byte stats in its
private socket structure. But these counters aren't exposed to
userspace and so serve no purpose. The counters were also
smp-unsafe. So this patch just gets rid of the stats.
While here, change a couple of internal __u32 variables to u32.
Signed-off-by: James Chapman <jchapman@katalix.com>
---
net/l2tp/l2tp_ip.c | 32 ++++----------------------------
1 files changed, 4 insertions(+), 28 deletions(-)
diff --git a/net/l2tp/l2tp_ip.c b/net/l2tp/l2tp_ip.c
index 5162592..adefe52 100644
--- a/net/l2tp/l2tp_ip.c
+++ b/net/l2tp/l2tp_ip.c
@@ -32,15 +32,8 @@ struct l2tp_ip_sock {
/* inet_sock has to be the first member of l2tp_ip_sock */
struct inet_sock inet;
- __u32 conn_id;
- __u32 peer_conn_id;
-
- __u64 tx_packets;
- __u64 tx_bytes;
- __u64 tx_errors;
- __u64 rx_packets;
- __u64 rx_bytes;
- __u64 rx_errors;
+ u32 conn_id;
+ u32 peer_conn_id;
};
static DEFINE_RWLOCK(l2tp_ip_lock);
@@ -298,7 +291,6 @@ out_in_use:
static int l2tp_ip_connect(struct sock *sk, struct sockaddr *uaddr, int addr_len)
{
struct sockaddr_l2tpip *lsa = (struct sockaddr_l2tpip *) uaddr;
- struct inet_sock *inet = inet_sk(sk);
int rc;
if (addr_len < sizeof(*lsa))
@@ -374,7 +366,6 @@ static int l2tp_ip_sendmsg(struct kiocb *iocb, struct sock *sk, struct msghdr *m
{
struct sk_buff *skb;
int rc;
- struct l2tp_ip_sock *lsa = l2tp_ip_sk(sk);
struct inet_sock *inet = inet_sk(sk);
struct rtable *rt = NULL;
struct flowi4 *fl4;
@@ -473,14 +464,8 @@ static int l2tp_ip_sendmsg(struct kiocb *iocb, struct sock *sk, struct msghdr *m
rcu_read_unlock();
error:
- /* Update stats */
- if (rc >= 0) {
- lsa->tx_packets++;
- lsa->tx_bytes += len;
+ if (rc >= 0)
rc = len;
- } else {
- lsa->tx_errors++;
- }
out:
release_sock(sk);
@@ -498,7 +483,6 @@ static int l2tp_ip_recvmsg(struct kiocb *iocb, struct sock *sk, struct msghdr *m
size_t len, int noblock, int flags, int *addr_len)
{
struct inet_sock *inet = inet_sk(sk);
- struct l2tp_ip_sock *lsk = l2tp_ip_sk(sk);
size_t copied = 0;
int err = -EOPNOTSUPP;
struct sockaddr_in *sin = (struct sockaddr_in *)msg->msg_name;
@@ -540,15 +524,7 @@ static int l2tp_ip_recvmsg(struct kiocb *iocb, struct sock *sk, struct msghdr *m
done:
skb_free_datagram(sk, skb);
out:
- if (err) {
- lsk->rx_errors++;
- return err;
- }
-
- lsk->rx_packets++;
- lsk->rx_bytes += copied;
-
- return copied;
+ return err ? err : copied;
}
static struct proto l2tp_ip_prot = {
--
1.7.0.4
^ permalink raw reply related
* [PATCH 04/10 net-next] pppox: Replace __attribute__((packed)) in if_pppox.h
From: James Chapman @ 2012-04-30 7:48 UTC (permalink / raw)
To: netdev
In-Reply-To: <1335772135-27910-1-git-send-email-jchapman@katalix.com>
Checkpatch warns about the use of __attribute__((packed)). So use the
recommended __packed syntax instead.
Signed-off-by: James Chapman <jchapman@katalix.com>
---
include/linux/if_pppox.h | 12 ++++++------
1 files changed, 6 insertions(+), 6 deletions(-)
diff --git a/include/linux/if_pppox.h b/include/linux/if_pppox.h
index 6720d57..09c474c 100644
--- a/include/linux/if_pppox.h
+++ b/include/linux/if_pppox.h
@@ -70,7 +70,7 @@ struct sockaddr_pppox {
struct pppoe_addr pppoe;
struct pptp_addr pptp;
} sa_addr;
-} __attribute__((packed));
+} __packed;
/* The use of the above union isn't viable because the size of this
* struct must stay fixed over time -- applications use sizeof(struct
@@ -81,13 +81,13 @@ struct sockaddr_pppol2tp {
__kernel_sa_family_t sa_family; /* address family, AF_PPPOX */
unsigned int sa_protocol; /* protocol identifier */
struct pppol2tp_addr pppol2tp;
-} __attribute__((packed));
+} __packed;
struct sockaddr_pppol2tpin6 {
__kernel_sa_family_t sa_family; /* address family, AF_PPPOX */
unsigned int sa_protocol; /* protocol identifier */
struct pppol2tpin6_addr pppol2tp;
-} __attribute__((packed));
+} __packed;
/* The L2TPv3 protocol changes tunnel and session ids from 16 to 32
* bits. So we need a different sockaddr structure.
@@ -96,13 +96,13 @@ struct sockaddr_pppol2tpv3 {
__kernel_sa_family_t sa_family; /* address family, AF_PPPOX */
unsigned int sa_protocol; /* protocol identifier */
struct pppol2tpv3_addr pppol2tp;
-} __attribute__((packed));
+} __packed;
struct sockaddr_pppol2tpv3in6 {
__kernel_sa_family_t sa_family; /* address family, AF_PPPOX */
unsigned int sa_protocol; /* protocol identifier */
struct pppol2tpv3in6_addr pppol2tp;
-} __attribute__((packed));
+} __packed;
/*********************************************************************
*
@@ -152,7 +152,7 @@ struct pppoe_hdr {
__be16 sid;
__be16 length;
struct pppoe_tag tag[0];
-} __attribute__((packed));
+} __packed;
/* Length of entire PPPoE + PPP header */
#define PPPOE_SES_HLEN 8
--
1.7.0.4
^ permalink raw reply related
* [PATCH 01/10 net-next] l2tp: fix locking of 64-bit counters for smp
From: James Chapman @ 2012-04-30 7:48 UTC (permalink / raw)
To: netdev
In-Reply-To: <1335772135-27910-1-git-send-email-jchapman@katalix.com>
L2TP uses 64-bit counters but since these are not updated atomically,
we need to make them safe for smp. This patch addresses that.
Signed-off-by: James Chapman <jchapman@katalix.com>
---
net/l2tp/l2tp_core.c | 75 +++++++++++++++++++++++++++++++++++------------
net/l2tp/l2tp_core.h | 1 +
net/l2tp/l2tp_netlink.c | 62 ++++++++++++++++++++++++++++----------
3 files changed, 103 insertions(+), 35 deletions(-)
diff --git a/net/l2tp/l2tp_core.c b/net/l2tp/l2tp_core.c
index 8cd5f4b..5e27c05 100644
--- a/net/l2tp/l2tp_core.c
+++ b/net/l2tp/l2tp_core.c
@@ -329,8 +329,10 @@ static void l2tp_recv_queue_skb(struct l2tp_session *session, struct sk_buff *sk
struct sk_buff *skbp;
struct sk_buff *tmp;
u32 ns = L2TP_SKB_CB(skb)->ns;
+ struct l2tp_stats *sstats;
spin_lock_bh(&session->reorder_q.lock);
+ sstats = &session->stats;
skb_queue_walk_safe(&session->reorder_q, skbp, tmp) {
if (L2TP_SKB_CB(skbp)->ns > ns) {
__skb_queue_before(&session->reorder_q, skbp, skb);
@@ -338,7 +340,9 @@ static void l2tp_recv_queue_skb(struct l2tp_session *session, struct sk_buff *sk
"%s: pkt %hu, inserted before %hu, reorder_q len=%d\n",
session->name, ns, L2TP_SKB_CB(skbp)->ns,
skb_queue_len(&session->reorder_q));
- session->stats.rx_oos_packets++;
+ u64_stats_update_begin(&sstats->syncp);
+ sstats->rx_oos_packets++;
+ u64_stats_update_end(&sstats->syncp);
goto out;
}
}
@@ -355,16 +359,23 @@ static void l2tp_recv_dequeue_skb(struct l2tp_session *session, struct sk_buff *
{
struct l2tp_tunnel *tunnel = session->tunnel;
int length = L2TP_SKB_CB(skb)->length;
+ struct l2tp_stats *tstats, *sstats;
/* We're about to requeue the skb, so return resources
* to its current owner (a socket receive buffer).
*/
skb_orphan(skb);
- tunnel->stats.rx_packets++;
- tunnel->stats.rx_bytes += length;
- session->stats.rx_packets++;
- session->stats.rx_bytes += length;
+ tstats = &tunnel->stats;
+ u64_stats_update_begin(&tstats->syncp);
+ sstats = &session->stats;
+ u64_stats_update_begin(&sstats->syncp);
+ tstats->rx_packets++;
+ tstats->rx_bytes += length;
+ sstats->rx_packets++;
+ sstats->rx_bytes += length;
+ u64_stats_update_end(&tstats->syncp);
+ u64_stats_update_end(&sstats->syncp);
if (L2TP_SKB_CB(skb)->has_seq) {
/* Bump our Nr */
@@ -395,6 +406,7 @@ static void l2tp_recv_dequeue(struct l2tp_session *session)
{
struct sk_buff *skb;
struct sk_buff *tmp;
+ struct l2tp_stats *sstats;
/* If the pkt at the head of the queue has the nr that we
* expect to send up next, dequeue it and any other
@@ -402,10 +414,13 @@ static void l2tp_recv_dequeue(struct l2tp_session *session)
*/
start:
spin_lock_bh(&session->reorder_q.lock);
+ sstats = &session->stats;
skb_queue_walk_safe(&session->reorder_q, skb, tmp) {
if (time_after(jiffies, L2TP_SKB_CB(skb)->expires)) {
- session->stats.rx_seq_discards++;
- session->stats.rx_errors++;
+ u64_stats_update_begin(&sstats->syncp);
+ sstats->rx_seq_discards++;
+ sstats->rx_errors++;
+ u64_stats_update_end(&sstats->syncp);
PRINTK(session->debug, L2TP_MSG_SEQ, KERN_DEBUG,
"%s: oos pkt %u len %d discarded (too old), "
"waiting for %u, reorder_q_len=%d\n",
@@ -557,6 +572,7 @@ void l2tp_recv_common(struct l2tp_session *session, struct sk_buff *skb,
struct l2tp_tunnel *tunnel = session->tunnel;
int offset;
u32 ns, nr;
+ struct l2tp_stats *sstats = &session->stats;
/* The ref count is increased since we now hold a pointer to
* the session. Take care to decrement the refcnt when exiting
@@ -572,7 +588,9 @@ void l2tp_recv_common(struct l2tp_session *session, struct sk_buff *skb,
PRINTK(tunnel->debug, L2TP_MSG_DATA, KERN_INFO,
"%s: cookie mismatch (%u/%u). Discarding.\n",
tunnel->name, tunnel->tunnel_id, session->session_id);
- session->stats.rx_cookie_discards++;
+ u64_stats_update_begin(&sstats->syncp);
+ sstats->rx_cookie_discards++;
+ u64_stats_update_end(&sstats->syncp);
goto discard;
}
ptr += session->peer_cookie_len;
@@ -641,7 +659,9 @@ void l2tp_recv_common(struct l2tp_session *session, struct sk_buff *skb,
PRINTK(session->debug, L2TP_MSG_SEQ, KERN_WARNING,
"%s: recv data has no seq numbers when required. "
"Discarding\n", session->name);
- session->stats.rx_seq_discards++;
+ u64_stats_update_begin(&sstats->syncp);
+ sstats->rx_seq_discards++;
+ u64_stats_update_end(&sstats->syncp);
goto discard;
}
@@ -660,7 +680,9 @@ void l2tp_recv_common(struct l2tp_session *session, struct sk_buff *skb,
PRINTK(session->debug, L2TP_MSG_SEQ, KERN_WARNING,
"%s: recv data has no seq numbers when required. "
"Discarding\n", session->name);
- session->stats.rx_seq_discards++;
+ u64_stats_update_begin(&sstats->syncp);
+ sstats->rx_seq_discards++;
+ u64_stats_update_end(&sstats->syncp);
goto discard;
}
}
@@ -714,7 +736,9 @@ void l2tp_recv_common(struct l2tp_session *session, struct sk_buff *skb,
* packets
*/
if (L2TP_SKB_CB(skb)->ns != session->nr) {
- session->stats.rx_seq_discards++;
+ u64_stats_update_begin(&sstats->syncp);
+ sstats->rx_seq_discards++;
+ u64_stats_update_end(&sstats->syncp);
PRINTK(session->debug, L2TP_MSG_SEQ, KERN_DEBUG,
"%s: oos pkt %u len %d discarded, "
"waiting for %u, reorder_q_len=%d\n",
@@ -741,7 +765,9 @@ void l2tp_recv_common(struct l2tp_session *session, struct sk_buff *skb,
return;
discard:
- session->stats.rx_errors++;
+ u64_stats_update_begin(&sstats->syncp);
+ sstats->rx_errors++;
+ u64_stats_update_end(&sstats->syncp);
kfree_skb(skb);
if (session->deref)
@@ -767,6 +793,7 @@ static int l2tp_udp_recv_core(struct l2tp_tunnel *tunnel, struct sk_buff *skb,
int offset;
u16 version;
int length;
+ struct l2tp_stats *tstats;
if (tunnel->sock && l2tp_verify_udp_checksum(tunnel->sock, skb))
goto discard_bad_csum;
@@ -859,7 +886,10 @@ static int l2tp_udp_recv_core(struct l2tp_tunnel *tunnel, struct sk_buff *skb,
discard_bad_csum:
LIMIT_NETDEBUG("%s: UDP: bad checksum\n", tunnel->name);
UDP_INC_STATS_USER(tunnel->l2tp_net, UDP_MIB_INERRORS, 0);
- tunnel->stats.rx_errors++;
+ tstats = &tunnel->stats;
+ u64_stats_update_begin(&tstats->syncp);
+ tstats->rx_errors++;
+ u64_stats_update_end(&tstats->syncp);
kfree_skb(skb);
return 0;
@@ -985,6 +1015,7 @@ static int l2tp_xmit_core(struct l2tp_session *session, struct sk_buff *skb,
struct l2tp_tunnel *tunnel = session->tunnel;
unsigned int len = skb->len;
int error;
+ struct l2tp_stats *tstats, *sstats;
/* Debug */
if (session->send_seq)
@@ -1021,15 +1052,21 @@ static int l2tp_xmit_core(struct l2tp_session *session, struct sk_buff *skb,
error = ip_queue_xmit(skb, fl);
/* Update stats */
+ tstats = &tunnel->stats;
+ u64_stats_update_begin(&tstats->syncp);
+ sstats = &session->stats;
+ u64_stats_update_begin(&sstats->syncp);
if (error >= 0) {
- tunnel->stats.tx_packets++;
- tunnel->stats.tx_bytes += len;
- session->stats.tx_packets++;
- session->stats.tx_bytes += len;
+ tstats->tx_packets++;
+ tstats->tx_bytes += len;
+ sstats->tx_packets++;
+ sstats->tx_bytes += len;
} else {
- tunnel->stats.tx_errors++;
- session->stats.tx_errors++;
+ tstats->tx_errors++;
+ sstats->tx_errors++;
}
+ u64_stats_update_end(&tstats->syncp);
+ u64_stats_update_end(&sstats->syncp);
return 0;
}
diff --git a/net/l2tp/l2tp_core.h b/net/l2tp/l2tp_core.h
index 09e4a38..a8c943b 100644
--- a/net/l2tp/l2tp_core.h
+++ b/net/l2tp/l2tp_core.h
@@ -45,6 +45,7 @@ struct l2tp_stats {
u64 rx_oos_packets;
u64 rx_errors;
u64 rx_cookie_discards;
+ struct u64_stats_sync syncp;
};
struct l2tp_tunnel;
diff --git a/net/l2tp/l2tp_netlink.c b/net/l2tp/l2tp_netlink.c
index bc8c334..1dbb977 100644
--- a/net/l2tp/l2tp_netlink.c
+++ b/net/l2tp/l2tp_netlink.c
@@ -225,6 +225,8 @@ static int l2tp_nl_tunnel_send(struct sk_buff *skb, u32 pid, u32 seq, int flags,
struct nlattr *nest;
struct sock *sk = NULL;
struct inet_sock *inet;
+ struct l2tp_stats stats;
+ unsigned int start;
hdr = genlmsg_put(skb, pid, seq, &l2tp_nl_family, flags,
L2TP_CMD_TUNNEL_GET);
@@ -242,16 +244,28 @@ static int l2tp_nl_tunnel_send(struct sk_buff *skb, u32 pid, u32 seq, int flags,
if (nest == NULL)
goto nla_put_failure;
- if (nla_put_u64(skb, L2TP_ATTR_TX_PACKETS, tunnel->stats.tx_packets) ||
- nla_put_u64(skb, L2TP_ATTR_TX_BYTES, tunnel->stats.tx_bytes) ||
- nla_put_u64(skb, L2TP_ATTR_TX_ERRORS, tunnel->stats.tx_errors) ||
- nla_put_u64(skb, L2TP_ATTR_RX_PACKETS, tunnel->stats.rx_packets) ||
- nla_put_u64(skb, L2TP_ATTR_RX_BYTES, tunnel->stats.rx_bytes) ||
+ do {
+ start = u64_stats_fetch_begin(&tunnel->stats.syncp);
+ stats.tx_packets = tunnel->stats.tx_packets;
+ stats.tx_bytes = tunnel->stats.tx_bytes;
+ stats.tx_errors = tunnel->stats.tx_errors;
+ stats.rx_packets = tunnel->stats.rx_packets;
+ stats.rx_bytes = tunnel->stats.rx_bytes;
+ stats.rx_errors = tunnel->stats.rx_errors;
+ stats.rx_seq_discards = tunnel->stats.rx_seq_discards;
+ stats.rx_oos_packets = tunnel->stats.rx_oos_packets;
+ } while (u64_stats_fetch_retry(&tunnel->stats.syncp, start));
+
+ if (nla_put_u64(skb, L2TP_ATTR_TX_PACKETS, stats.tx_packets) ||
+ nla_put_u64(skb, L2TP_ATTR_TX_BYTES, stats.tx_bytes) ||
+ nla_put_u64(skb, L2TP_ATTR_TX_ERRORS, stats.tx_errors) ||
+ nla_put_u64(skb, L2TP_ATTR_RX_PACKETS, stats.rx_packets) ||
+ nla_put_u64(skb, L2TP_ATTR_RX_BYTES, stats.rx_bytes) ||
nla_put_u64(skb, L2TP_ATTR_RX_SEQ_DISCARDS,
- tunnel->stats.rx_seq_discards) ||
+ stats.rx_seq_discards) ||
nla_put_u64(skb, L2TP_ATTR_RX_OOS_PACKETS,
- tunnel->stats.rx_oos_packets) ||
- nla_put_u64(skb, L2TP_ATTR_RX_ERRORS, tunnel->stats.rx_errors))
+ stats.rx_oos_packets) ||
+ nla_put_u64(skb, L2TP_ATTR_RX_ERRORS, stats.rx_errors))
goto nla_put_failure;
nla_nest_end(skb, nest);
@@ -563,6 +577,8 @@ static int l2tp_nl_session_send(struct sk_buff *skb, u32 pid, u32 seq, int flags
struct nlattr *nest;
struct l2tp_tunnel *tunnel = session->tunnel;
struct sock *sk = NULL;
+ struct l2tp_stats stats;
+ unsigned int start;
sk = tunnel->sock;
@@ -600,19 +616,33 @@ static int l2tp_nl_session_send(struct sk_buff *skb, u32 pid, u32 seq, int flags
(session->reorder_timeout &&
nla_put_msecs(skb, L2TP_ATTR_RECV_TIMEOUT, session->reorder_timeout)))
goto nla_put_failure;
+
nest = nla_nest_start(skb, L2TP_ATTR_STATS);
if (nest == NULL)
goto nla_put_failure;
- if (nla_put_u64(skb, L2TP_ATTR_TX_PACKETS, session->stats.tx_packets) ||
- nla_put_u64(skb, L2TP_ATTR_TX_BYTES, session->stats.tx_bytes) ||
- nla_put_u64(skb, L2TP_ATTR_TX_ERRORS, session->stats.tx_errors) ||
- nla_put_u64(skb, L2TP_ATTR_RX_PACKETS, session->stats.rx_packets) ||
- nla_put_u64(skb, L2TP_ATTR_RX_BYTES, session->stats.rx_bytes) ||
+
+ do {
+ start = u64_stats_fetch_begin(&session->stats.syncp);
+ stats.tx_packets = session->stats.tx_packets;
+ stats.tx_bytes = session->stats.tx_bytes;
+ stats.tx_errors = session->stats.tx_errors;
+ stats.rx_packets = session->stats.rx_packets;
+ stats.rx_bytes = session->stats.rx_bytes;
+ stats.rx_errors = session->stats.rx_errors;
+ stats.rx_seq_discards = session->stats.rx_seq_discards;
+ stats.rx_oos_packets = session->stats.rx_oos_packets;
+ } while (u64_stats_fetch_retry(&session->stats.syncp, start));
+
+ if (nla_put_u64(skb, L2TP_ATTR_TX_PACKETS, stats.tx_packets) ||
+ nla_put_u64(skb, L2TP_ATTR_TX_BYTES, stats.tx_bytes) ||
+ nla_put_u64(skb, L2TP_ATTR_TX_ERRORS, stats.tx_errors) ||
+ nla_put_u64(skb, L2TP_ATTR_RX_PACKETS, stats.rx_packets) ||
+ nla_put_u64(skb, L2TP_ATTR_RX_BYTES, stats.rx_bytes) ||
nla_put_u64(skb, L2TP_ATTR_RX_SEQ_DISCARDS,
- session->stats.rx_seq_discards) ||
+ stats.rx_seq_discards) ||
nla_put_u64(skb, L2TP_ATTR_RX_OOS_PACKETS,
- session->stats.rx_oos_packets) ||
- nla_put_u64(skb, L2TP_ATTR_RX_ERRORS, session->stats.rx_errors))
+ stats.rx_oos_packets) ||
+ nla_put_u64(skb, L2TP_ATTR_RX_ERRORS, stats.rx_errors))
goto nla_put_failure;
nla_nest_end(skb, nest);
--
1.7.0.4
^ permalink raw reply related
* [PATCH 05/10 net-next] l2tp: pppol2tp_connect() handles ipv6 sockaddr variants
From: James Chapman @ 2012-04-30 7:48 UTC (permalink / raw)
To: netdev
In-Reply-To: <1335772135-27910-1-git-send-email-jchapman@katalix.com>
Userspace uses connect() to associate a pppol2tp socket with a tunnel
socket. This needs to allow the caller to supply the new IPv6
sockaddr_pppol2tp structures if IPv6 is used.
Signed-off-by: James Chapman <jchapman@katalix.com>
---
net/l2tp/l2tp_ppp.c | 36 ++++++++++++++++++++++++++++--------
1 files changed, 28 insertions(+), 8 deletions(-)
diff --git a/net/l2tp/l2tp_ppp.c b/net/l2tp/l2tp_ppp.c
index 27b9dec..9f2c421 100644
--- a/net/l2tp/l2tp_ppp.c
+++ b/net/l2tp/l2tp_ppp.c
@@ -628,7 +628,6 @@ static int pppol2tp_connect(struct socket *sock, struct sockaddr *uservaddr,
{
struct sock *sk = sock->sk;
struct sockaddr_pppol2tp *sp = (struct sockaddr_pppol2tp *) uservaddr;
- struct sockaddr_pppol2tpv3 *sp3 = (struct sockaddr_pppol2tpv3 *) uservaddr;
struct pppox_sock *po = pppox_sk(sk);
struct l2tp_session *session = NULL;
struct l2tp_tunnel *tunnel;
@@ -657,7 +656,13 @@ static int pppol2tp_connect(struct socket *sock, struct sockaddr *uservaddr,
if (sk->sk_user_data)
goto end; /* socket is already attached */
- /* Get params from socket address. Handle L2TPv2 and L2TPv3 */
+ /* Get params from socket address. Handle L2TPv2 and L2TPv3.
+ * This is nasty because there are different sockaddr_pppol2tp
+ * structs for L2TPv2, L2TPv3, over IPv4 and IPv6. We use
+ * the sockaddr size to determine which structure the caller
+ * is using.
+ */
+ peer_tunnel_id = 0;
if (sockaddr_len == sizeof(struct sockaddr_pppol2tp)) {
fd = sp->pppol2tp.fd;
tunnel_id = sp->pppol2tp.s_tunnel;
@@ -665,12 +670,31 @@ static int pppol2tp_connect(struct socket *sock, struct sockaddr *uservaddr,
session_id = sp->pppol2tp.s_session;
peer_session_id = sp->pppol2tp.d_session;
} else if (sockaddr_len == sizeof(struct sockaddr_pppol2tpv3)) {
+ struct sockaddr_pppol2tpv3 *sp3 =
+ (struct sockaddr_pppol2tpv3 *) sp;
ver = 3;
fd = sp3->pppol2tp.fd;
tunnel_id = sp3->pppol2tp.s_tunnel;
peer_tunnel_id = sp3->pppol2tp.d_tunnel;
session_id = sp3->pppol2tp.s_session;
peer_session_id = sp3->pppol2tp.d_session;
+ } else if (sockaddr_len == sizeof(struct sockaddr_pppol2tpin6)) {
+ struct sockaddr_pppol2tpin6 *sp6 =
+ (struct sockaddr_pppol2tpin6 *) sp;
+ fd = sp6->pppol2tp.fd;
+ tunnel_id = sp6->pppol2tp.s_tunnel;
+ peer_tunnel_id = sp6->pppol2tp.d_tunnel;
+ session_id = sp6->pppol2tp.s_session;
+ peer_session_id = sp6->pppol2tp.d_session;
+ } else if (sockaddr_len == sizeof(struct sockaddr_pppol2tpv3in6)) {
+ struct sockaddr_pppol2tpv3in6 *sp6 =
+ (struct sockaddr_pppol2tpv3in6 *) sp;
+ ver = 3;
+ fd = sp6->pppol2tp.fd;
+ tunnel_id = sp6->pppol2tp.s_tunnel;
+ peer_tunnel_id = sp6->pppol2tp.d_tunnel;
+ session_id = sp6->pppol2tp.s_session;
+ peer_session_id = sp6->pppol2tp.d_session;
} else {
error = -EINVAL;
goto end; /* bad socket address */
@@ -711,12 +735,8 @@ static int pppol2tp_connect(struct socket *sock, struct sockaddr *uservaddr,
if (tunnel->recv_payload_hook == NULL)
tunnel->recv_payload_hook = pppol2tp_recv_payload_hook;
- if (tunnel->peer_tunnel_id == 0) {
- if (ver == 2)
- tunnel->peer_tunnel_id = sp->pppol2tp.d_tunnel;
- else
- tunnel->peer_tunnel_id = sp3->pppol2tp.d_tunnel;
- }
+ if (tunnel->peer_tunnel_id == 0)
+ tunnel->peer_tunnel_id = peer_tunnel_id;
/* Create session if it doesn't already exist. We handle the
* case where a session was previously created by the netlink
--
1.7.0.4
^ permalink raw reply related
* [PATCH 06/10 net-next] l2tp: show IPv6 addresses in l2tp debugfs file
From: James Chapman @ 2012-04-30 7:48 UTC (permalink / raw)
To: netdev; +Cc: Chris Elston
In-Reply-To: <1335772135-27910-1-git-send-email-jchapman@katalix.com>
From: Chris Elston <celston@katalix.com>
If an L2TP tunnel uses IPv6, make sure the l2tp debugfs file shows the
IPv6 address correctly.
Signed-off-by: Chris Elston <celston@katalix.com>
Signed-off-by: James Chapman <jchapman@katalix.com>
---
net/l2tp/l2tp_debugfs.c | 8 ++++++++
1 files changed, 8 insertions(+), 0 deletions(-)
diff --git a/net/l2tp/l2tp_debugfs.c b/net/l2tp/l2tp_debugfs.c
index 7613013..c0d57ba 100644
--- a/net/l2tp/l2tp_debugfs.c
+++ b/net/l2tp/l2tp_debugfs.c
@@ -122,6 +122,14 @@ static void l2tp_dfs_seq_tunnel_show(struct seq_file *m, void *v)
seq_printf(m, "\nTUNNEL %u peer %u", tunnel->tunnel_id, tunnel->peer_tunnel_id);
if (tunnel->sock) {
struct inet_sock *inet = inet_sk(tunnel->sock);
+
+#if IS_ENABLED(CONFIG_IPV6)
+ if (tunnel->sock->sk_family == AF_INET6) {
+ struct ipv6_pinfo *np = inet6_sk(tunnel->sock);
+ seq_printf(m, " from %pI6c to %pI6c\n",
+ &np->saddr, &np->daddr);
+ } else
+#endif
seq_printf(m, " from %pI4 to %pI4\n",
&inet->inet_saddr, &inet->inet_daddr);
if (tunnel->encap == L2TP_ENCAPTYPE_UDP)
--
1.7.0.4
^ permalink raw reply related
* [PATCH 07/10 net-next] l2tp: netlink api for l2tpv3 ipv6 unmanaged tunnels
From: James Chapman @ 2012-04-30 7:48 UTC (permalink / raw)
To: netdev; +Cc: Chris Elston
In-Reply-To: <1335772135-27910-1-git-send-email-jchapman@katalix.com>
From: Chris Elston <celston@katalix.com>
This patch adds support for unmanaged L2TPv3 tunnels over IPv6 using
the netlink API. We already support unmanaged L2TPv3 tunnels over
IPv4. A patch to iproute2 to make use of this feature will be
submitted separately.
Signed-off-by: Chris Elston <celston@katalix.com>
Signed-off-by: James Chapman <jchapman@katalix.com>
---
include/linux/l2tp.h | 2 +
net/l2tp/l2tp_core.c | 78 ++++++++++++++++++++++++++++++++++++----------
net/l2tp/l2tp_core.h | 4 ++
net/l2tp/l2tp_netlink.c | 48 ++++++++++++++++++++++++++--
4 files changed, 111 insertions(+), 21 deletions(-)
diff --git a/include/linux/l2tp.h b/include/linux/l2tp.h
index e77d7f9..16b8347 100644
--- a/include/linux/l2tp.h
+++ b/include/linux/l2tp.h
@@ -108,6 +108,8 @@ enum {
L2TP_ATTR_MTU, /* u16 */
L2TP_ATTR_MRU, /* u16 */
L2TP_ATTR_STATS, /* nested */
+ L2TP_ATTR_IP6_SADDR, /* struct in6_addr */
+ L2TP_ATTR_IP6_DADDR, /* struct in6_addr */
__L2TP_ATTR_MAX,
};
diff --git a/net/l2tp/l2tp_core.c b/net/l2tp/l2tp_core.c
index 5e27c05..5a7d908 100644
--- a/net/l2tp/l2tp_core.c
+++ b/net/l2tp/l2tp_core.c
@@ -1365,31 +1365,68 @@ static int l2tp_tunnel_sock_create(u32 tunnel_id, u32 peer_tunnel_id, struct l2t
{
int err = -EINVAL;
struct sockaddr_in udp_addr;
+#if IS_ENABLED(CONFIG_IPV6)
+ struct sockaddr_in6 udp6_addr;
+#endif
struct sockaddr_l2tpip ip_addr;
struct socket *sock = NULL;
switch (cfg->encap) {
case L2TP_ENCAPTYPE_UDP:
- err = sock_create(AF_INET, SOCK_DGRAM, 0, sockp);
- if (err < 0)
- goto out;
+#if IS_ENABLED(CONFIG_IPV6)
+ if (cfg->local_ip6 && cfg->peer_ip6) {
+ err = sock_create(AF_INET6, SOCK_DGRAM, 0, sockp);
+ if (err < 0)
+ goto out;
- sock = *sockp;
+ sock = *sockp;
- 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);
- err = kernel_bind(sock, (struct sockaddr *) &udp_addr, sizeof(udp_addr));
- if (err < 0)
- goto out;
+ 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));
+ udp6_addr.sin6_port = htons(cfg->local_udp_port);
+ err = kernel_bind(sock, (struct sockaddr *) &udp6_addr,
+ sizeof(udp6_addr));
+ if (err < 0)
+ goto out;
- udp_addr.sin_family = AF_INET;
- udp_addr.sin_addr = cfg->peer_ip;
- udp_addr.sin_port = htons(cfg->peer_udp_port);
- err = kernel_connect(sock, (struct sockaddr *) &udp_addr, sizeof(udp_addr), 0);
- if (err < 0)
- goto out;
+ udp6_addr.sin6_family = AF_INET6;
+ memcpy(&udp6_addr.sin6_addr, cfg->peer_ip6,
+ sizeof(udp6_addr.sin6_addr));
+ udp6_addr.sin6_port = htons(cfg->peer_udp_port);
+ err = kernel_connect(sock,
+ (struct sockaddr *) &udp6_addr,
+ sizeof(udp6_addr), 0);
+ if (err < 0)
+ goto out;
+ } else
+#endif
+ {
+ err = sock_create(AF_INET, SOCK_DGRAM, 0, sockp);
+ if (err < 0)
+ goto out;
+
+ sock = *sockp;
+
+ 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);
+ err = kernel_bind(sock, (struct sockaddr *) &udp_addr,
+ sizeof(udp_addr));
+ if (err < 0)
+ goto out;
+
+ udp_addr.sin_family = AF_INET;
+ udp_addr.sin_addr = cfg->peer_ip;
+ udp_addr.sin_port = htons(cfg->peer_udp_port);
+ err = kernel_connect(sock,
+ (struct sockaddr *) &udp_addr,
+ sizeof(udp_addr), 0);
+ if (err < 0)
+ goto out;
+ }
if (!cfg->use_udp_checksums)
sock->sk->sk_no_check = UDP_CSUM_NOXMIT;
@@ -1397,6 +1434,13 @@ static int l2tp_tunnel_sock_create(u32 tunnel_id, u32 peer_tunnel_id, struct l2t
break;
case L2TP_ENCAPTYPE_IP:
+#if IS_ENABLED(CONFIG_IPV6)
+ if (cfg->local_ip6 && cfg->peer_ip6) {
+ /* IP encap over IPv6 not yet supported */
+ err = -EPROTONOSUPPORT;
+ goto out;
+ }
+#endif
err = sock_create(AF_INET, SOCK_DGRAM, IPPROTO_L2TP, sockp);
if (err < 0)
goto out;
diff --git a/net/l2tp/l2tp_core.h b/net/l2tp/l2tp_core.h
index a8c943b..0bf60fc 100644
--- a/net/l2tp/l2tp_core.h
+++ b/net/l2tp/l2tp_core.h
@@ -151,6 +151,10 @@ struct l2tp_tunnel_cfg {
/* Used only for kernel-created sockets */
struct in_addr local_ip;
struct in_addr peer_ip;
+#if IS_ENABLED(CONFIG_IPV6)
+ struct in6_addr *local_ip6;
+ struct in6_addr *peer_ip6;
+#endif
u16 local_udp_port;
u16 peer_udp_port;
unsigned int use_udp_checksums:1;
diff --git a/net/l2tp/l2tp_netlink.c b/net/l2tp/l2tp_netlink.c
index 1dbb977..24edad0 100644
--- a/net/l2tp/l2tp_netlink.c
+++ b/net/l2tp/l2tp_netlink.c
@@ -133,10 +133,25 @@ static int l2tp_nl_cmd_tunnel_create(struct sk_buff *skb, struct genl_info *info
if (info->attrs[L2TP_ATTR_FD]) {
fd = nla_get_u32(info->attrs[L2TP_ATTR_FD]);
} else {
- if (info->attrs[L2TP_ATTR_IP_SADDR])
- cfg.local_ip.s_addr = nla_get_be32(info->attrs[L2TP_ATTR_IP_SADDR]);
- if (info->attrs[L2TP_ATTR_IP_DADDR])
- cfg.peer_ip.s_addr = nla_get_be32(info->attrs[L2TP_ATTR_IP_DADDR]);
+#if IS_ENABLED(CONFIG_IPV6)
+ if (info->attrs[L2TP_ATTR_IP6_SADDR] &&
+ info->attrs[L2TP_ATTR_IP6_DADDR]) {
+ cfg.local_ip6 = nla_data(
+ info->attrs[L2TP_ATTR_IP6_SADDR]);
+ cfg.peer_ip6 = nla_data(
+ info->attrs[L2TP_ATTR_IP6_DADDR]);
+ } else
+#endif
+ if (info->attrs[L2TP_ATTR_IP_SADDR] &&
+ info->attrs[L2TP_ATTR_IP_DADDR]) {
+ cfg.local_ip.s_addr = nla_get_be32(
+ info->attrs[L2TP_ATTR_IP_SADDR]);
+ cfg.peer_ip.s_addr = nla_get_be32(
+ info->attrs[L2TP_ATTR_IP_DADDR]);
+ } else {
+ ret = -EINVAL;
+ goto out;
+ }
if (info->attrs[L2TP_ATTR_UDP_SPORT])
cfg.local_udp_port = nla_get_u16(info->attrs[L2TP_ATTR_UDP_SPORT]);
if (info->attrs[L2TP_ATTR_UDP_DPORT])
@@ -225,6 +240,9 @@ static int l2tp_nl_tunnel_send(struct sk_buff *skb, u32 pid, u32 seq, int flags,
struct nlattr *nest;
struct sock *sk = NULL;
struct inet_sock *inet;
+#if IS_ENABLED(CONFIG_IPV6)
+ struct ipv6_pinfo *np = NULL;
+#endif
struct l2tp_stats stats;
unsigned int start;
@@ -273,6 +291,11 @@ static int l2tp_nl_tunnel_send(struct sk_buff *skb, u32 pid, u32 seq, int flags,
if (!sk)
goto out;
+#if IS_ENABLED(CONFIG_IPV6)
+ if (sk->sk_family == AF_INET6)
+ np = inet6_sk(sk);
+#endif
+
inet = inet_sk(sk);
switch (tunnel->encap) {
@@ -284,6 +307,15 @@ static int l2tp_nl_tunnel_send(struct sk_buff *skb, u32 pid, u32 seq, int flags,
goto nla_put_failure;
/* NOBREAK */
case L2TP_ENCAPTYPE_IP:
+#if IS_ENABLED(CONFIG_IPV6)
+ if (np) {
+ if (nla_put(skb, L2TP_ATTR_IP6_SADDR, sizeof(np->saddr),
+ &np->saddr) ||
+ nla_put(skb, L2TP_ATTR_IP6_DADDR, sizeof(np->daddr),
+ &np->daddr))
+ goto nla_put_failure;
+ } else
+#endif
if (nla_put_be32(skb, L2TP_ATTR_IP_SADDR, inet->inet_saddr) ||
nla_put_be32(skb, L2TP_ATTR_IP_DADDR, inet->inet_daddr))
goto nla_put_failure;
@@ -752,6 +784,14 @@ static struct nla_policy l2tp_nl_policy[L2TP_ATTR_MAX + 1] = {
[L2TP_ATTR_MTU] = { .type = NLA_U16, },
[L2TP_ATTR_MRU] = { .type = NLA_U16, },
[L2TP_ATTR_STATS] = { .type = NLA_NESTED, },
+ [L2TP_ATTR_IP6_SADDR] = {
+ .type = NLA_BINARY,
+ .len = sizeof(struct in6_addr),
+ },
+ [L2TP_ATTR_IP6_DADDR] = {
+ .type = NLA_BINARY,
+ .len = sizeof(struct in6_addr),
+ },
[L2TP_ATTR_IFNAME] = {
.type = NLA_NUL_STRING,
.len = IFNAMSIZ - 1,
--
1.7.0.4
^ permalink raw reply related
* [PATCH 08/10 net-next] ipv6: Export ipv6 functions for use by other protocols
From: James Chapman @ 2012-04-30 7:48 UTC (permalink / raw)
To: netdev; +Cc: Chris Elston
In-Reply-To: <1335772135-27910-1-git-send-email-jchapman@katalix.com>
From: Chris Elston <celston@katalix.com>
For implementing other protocols on top of IPv6, such as L2TPv3's IP
encapsulation over ipv6, we'd like to call some IPv6 functions which
are not currently exported. This patch exports them.
Signed-off-by: Chris Elston <celston@katalix.com>
Signed-off-by: James Chapman <jchapman@katalix.com>
---
net/ipv6/datagram.c | 4 ++++
net/ipv6/exthdrs.c | 1 +
net/ipv6/ip6_flowlabel.c | 1 +
net/ipv6/ip6_output.c | 3 +++
4 files changed, 9 insertions(+), 0 deletions(-)
diff --git a/net/ipv6/datagram.c b/net/ipv6/datagram.c
index 7fba35a..b8b61ac 100644
--- a/net/ipv6/datagram.c
+++ b/net/ipv6/datagram.c
@@ -22,6 +22,7 @@
#include <linux/ipv6.h>
#include <linux/route.h>
#include <linux/slab.h>
+#include <linux/export.h>
#include <net/ipv6.h>
#include <net/ndisc.h>
@@ -202,6 +203,7 @@ out:
fl6_sock_release(flowlabel);
return err;
}
+EXPORT_SYMBOL_GPL(ip6_datagram_connect);
void ipv6_icmp_error(struct sock *sk, struct sk_buff *skb, int err,
__be16 port, u32 info, u8 *payload)
@@ -414,6 +416,7 @@ out_free_skb:
out:
return err;
}
+EXPORT_SYMBOL_GPL(ipv6_recv_error);
/*
* Handle IPV6_RECVPATHMTU
@@ -868,3 +871,4 @@ int datagram_send_ctl(struct net *net, struct sock *sk,
exit_f:
return err;
}
+EXPORT_SYMBOL_GPL(datagram_send_ctl);
diff --git a/net/ipv6/exthdrs.c b/net/ipv6/exthdrs.c
index aa0a51e..a93bd23 100644
--- a/net/ipv6/exthdrs.c
+++ b/net/ipv6/exthdrs.c
@@ -883,6 +883,7 @@ struct ipv6_txoptions *ipv6_fixup_options(struct ipv6_txoptions *opt_space,
return opt;
}
+EXPORT_SYMBOL_GPL(ipv6_fixup_options);
/**
* fl6_update_dst - update flowi destination address with info given
diff --git a/net/ipv6/ip6_flowlabel.c b/net/ipv6/ip6_flowlabel.c
index 1dd6329..cb43df6 100644
--- a/net/ipv6/ip6_flowlabel.c
+++ b/net/ipv6/ip6_flowlabel.c
@@ -294,6 +294,7 @@ struct ipv6_txoptions *fl6_merge_options(struct ipv6_txoptions * opt_space,
opt_space->opt_flen = fopt->opt_flen;
return opt_space;
}
+EXPORT_SYMBOL_GPL(fl6_merge_options);
static unsigned long check_linger(unsigned long ttl)
{
diff --git a/net/ipv6/ip6_output.c b/net/ipv6/ip6_output.c
index b7ca461..2a16aa9 100644
--- a/net/ipv6/ip6_output.c
+++ b/net/ipv6/ip6_output.c
@@ -1535,6 +1535,7 @@ error:
IP6_INC_STATS(sock_net(sk), rt->rt6i_idev, IPSTATS_MIB_OUTDISCARDS);
return err;
}
+EXPORT_SYMBOL_GPL(ip6_append_data);
static void ip6_cork_release(struct inet_sock *inet, struct ipv6_pinfo *np)
{
@@ -1638,6 +1639,7 @@ error:
IP6_INC_STATS(net, rt->rt6i_idev, IPSTATS_MIB_OUTDISCARDS);
goto out;
}
+EXPORT_SYMBOL_GPL(ip6_push_pending_frames);
void ip6_flush_pending_frames(struct sock *sk)
{
@@ -1652,3 +1654,4 @@ void ip6_flush_pending_frames(struct sock *sk)
ip6_cork_release(inet_sk(sk), inet6_sk(sk));
}
+EXPORT_SYMBOL_GPL(ip6_flush_pending_frames);
--
1.7.0.4
^ permalink raw reply related
* [PATCH 09/10 net-next] l2tp: introduce L2TPv3 IP encapsulation support for IPv6
From: James Chapman @ 2012-04-30 7:48 UTC (permalink / raw)
To: netdev; +Cc: Chris Elston
In-Reply-To: <1335772135-27910-1-git-send-email-jchapman@katalix.com>
From: Chris Elston <celston@katalix.com>
L2TPv3 defines an IP encapsulation packet format where data is carried
directly over IP (no UDP). The kernel already has support for L2TP IP
encapsulation over IPv4 (l2tp_ip). This patch introduces support for
L2TP IP encapsulation over IPv6.
The implementation is derived from ipv6/raw and ipv4/l2tp_ip.
Signed-off-by: Chris Elston <celston@katalix.com>
Signed-off-by: James Chapman <jchapman@katalix.com>
---
include/linux/l2tp.h | 17 +
net/l2tp/Makefile | 3 +
net/l2tp/l2tp_ip6.c | 792 ++++++++++++++++++++++++++++++++++++++++++++++++++
3 files changed, 812 insertions(+), 0 deletions(-)
create mode 100644 net/l2tp/l2tp_ip6.c
diff --git a/include/linux/l2tp.h b/include/linux/l2tp.h
index 16b8347..7eab668 100644
--- a/include/linux/l2tp.h
+++ b/include/linux/l2tp.h
@@ -11,6 +11,7 @@
#include <linux/socket.h>
#ifdef __KERNEL__
#include <linux/in.h>
+#include <linux/in6.h>
#else
#include <netinet/in.h>
#endif
@@ -39,6 +40,22 @@ struct sockaddr_l2tpip {
sizeof(__u32)];
};
+/**
+ * struct sockaddr_l2tpip6 - the sockaddr structure for L2TP-over-IPv6 sockets
+ * @l2tp_family: address family number AF_L2TPIP.
+ * @l2tp_addr: protocol specific address information
+ * @l2tp_conn_id: connection id of tunnel
+ */
+struct sockaddr_l2tpip6 {
+ /* The first fields must match struct sockaddr_in6 */
+ __kernel_sa_family_t l2tp_family; /* AF_INET6 */
+ __be16 l2tp_unused; /* INET port number (unused) */
+ __be32 l2tp_flowinfo; /* IPv6 flow information */
+ struct in6_addr l2tp_addr; /* IPv6 address */
+ __u32 l2tp_scope_id; /* scope id (new in RFC2553) */
+ __u32 l2tp_conn_id; /* Connection ID of tunnel */
+};
+
/*****************************************************************************
* NETLINK_GENERIC netlink family.
*****************************************************************************/
diff --git a/net/l2tp/Makefile b/net/l2tp/Makefile
index 110e7bc..2870f41 100644
--- a/net/l2tp/Makefile
+++ b/net/l2tp/Makefile
@@ -10,3 +10,6 @@ obj-$(subst y,$(CONFIG_L2TP),$(CONFIG_L2TP_IP)) += l2tp_ip.o
obj-$(subst y,$(CONFIG_L2TP),$(CONFIG_L2TP_V3)) += l2tp_netlink.o
obj-$(subst y,$(CONFIG_L2TP),$(CONFIG_L2TP_ETH)) += l2tp_eth.o
obj-$(subst y,$(CONFIG_L2TP),$(CONFIG_L2TP_DEBUGFS)) += l2tp_debugfs.o
+ifneq ($(CONFIG_IPV6),)
+obj-$(subst y,$(CONFIG_L2TP),$(CONFIG_L2TP_IP)) += l2tp_ip6.o
+endif
diff --git a/net/l2tp/l2tp_ip6.c b/net/l2tp/l2tp_ip6.c
new file mode 100644
index 0000000..88f0abe
--- /dev/null
+++ b/net/l2tp/l2tp_ip6.c
@@ -0,0 +1,792 @@
+/*
+ * L2TPv3 IP encapsulation support for IPv6
+ *
+ * Copyright (c) 2012 Katalix Systems Ltd
+ *
+ * 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.
+ */
+
+#include <linux/icmp.h>
+#include <linux/module.h>
+#include <linux/skbuff.h>
+#include <linux/random.h>
+#include <linux/socket.h>
+#include <linux/l2tp.h>
+#include <linux/in.h>
+#include <linux/in6.h>
+#include <net/sock.h>
+#include <net/ip.h>
+#include <net/icmp.h>
+#include <net/udp.h>
+#include <net/inet_common.h>
+#include <net/inet_hashtables.h>
+#include <net/tcp_states.h>
+#include <net/protocol.h>
+#include <net/xfrm.h>
+
+#include <net/transp_v6.h>
+#include <net/addrconf.h>
+#include <net/ip6_route.h>
+
+#include "l2tp_core.h"
+
+struct l2tp_ip6_sock {
+ /* inet_sock has to be the first member of l2tp_ip6_sock */
+ struct inet_sock inet;
+
+ u32 conn_id;
+ u32 peer_conn_id;
+
+ /* ipv6_pinfo has to be the last member of l2tp_ip6_sock, see
+ inet6_sk_generic */
+ struct ipv6_pinfo inet6;
+};
+
+static DEFINE_RWLOCK(l2tp_ip6_lock);
+static struct hlist_head l2tp_ip6_table;
+static struct hlist_head l2tp_ip6_bind_table;
+
+static inline struct l2tp_ip6_sock *l2tp_ip6_sk(const struct sock *sk)
+{
+ return (struct l2tp_ip6_sock *)sk;
+}
+
+static struct sock *__l2tp_ip6_bind_lookup(struct net *net,
+ struct in6_addr *laddr,
+ int dif, u32 tunnel_id)
+{
+ struct hlist_node *node;
+ struct sock *sk;
+
+ sk_for_each_bound(sk, node, &l2tp_ip6_bind_table) {
+ struct in6_addr *addr = inet6_rcv_saddr(sk);
+ struct l2tp_ip6_sock *l2tp = l2tp_ip6_sk(sk);
+
+ if (l2tp == NULL)
+ continue;
+
+ if ((l2tp->conn_id == tunnel_id) &&
+ net_eq(sock_net(sk), net) &&
+ !(addr && ipv6_addr_equal(addr, laddr)) &&
+ !(sk->sk_bound_dev_if && sk->sk_bound_dev_if != dif))
+ goto found;
+ }
+
+ sk = NULL;
+found:
+ return sk;
+}
+
+static inline struct sock *l2tp_ip6_bind_lookup(struct net *net,
+ struct in6_addr *laddr,
+ int dif, u32 tunnel_id)
+{
+ struct sock *sk = __l2tp_ip6_bind_lookup(net, laddr, dif, tunnel_id);
+ if (sk)
+ sock_hold(sk);
+
+ return sk;
+}
+
+/* When processing receive frames, there are two cases to
+ * consider. Data frames consist of a non-zero session-id and an
+ * optional cookie. Control frames consist of a regular L2TP header
+ * preceded by 32-bits of zeros.
+ *
+ * L2TPv3 Session Header Over IP
+ *
+ * 0 1 2 3
+ * 0 1 2 3 4 5 6 7 8 9 0 1 2 3 4 5 6 7 8 9 0 1 2 3 4 5 6 7 8 9 0 1
+ * +-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+
+ * | Session ID |
+ * +-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+
+ * | Cookie (optional, maximum 64 bits)...
+ * +-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+
+ * |
+ * +-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+
+ *
+ * L2TPv3 Control Message Header Over IP
+ *
+ * 0 1 2 3
+ * 0 1 2 3 4 5 6 7 8 9 0 1 2 3 4 5 6 7 8 9 0 1 2 3 4 5 6 7 8 9 0 1
+ * +-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+
+ * | (32 bits of zeros) |
+ * +-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+
+ * |T|L|x|x|S|x|x|x|x|x|x|x| Ver | Length |
+ * +-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+
+ * | Control Connection ID |
+ * +-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+
+ * | Ns | Nr |
+ * +-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+
+ *
+ * All control frames are passed to userspace.
+ */
+static int l2tp_ip6_recv(struct sk_buff *skb)
+{
+ struct sock *sk;
+ u32 session_id;
+ u32 tunnel_id;
+ unsigned char *ptr, *optr;
+ struct l2tp_session *session;
+ struct l2tp_tunnel *tunnel = NULL;
+ int length;
+ int offset;
+
+ /* Point to L2TP header */
+ optr = ptr = skb->data;
+
+ if (!pskb_may_pull(skb, 4))
+ goto discard;
+
+ session_id = ntohl(*((__be32 *) ptr));
+ ptr += 4;
+
+ /* RFC3931: L2TP/IP packets have the first 4 bytes containing
+ * the session_id. If it is 0, the packet is a L2TP control
+ * frame and the session_id value can be discarded.
+ */
+ if (session_id == 0) {
+ __skb_pull(skb, 4);
+ goto pass_up;
+ }
+
+ /* Ok, this is a data packet. Lookup the session. */
+ session = l2tp_session_find(&init_net, NULL, session_id);
+ if (session == NULL)
+ goto discard;
+
+ tunnel = session->tunnel;
+ if (tunnel == NULL)
+ goto discard;
+
+ /* Trace packet contents, if enabled */
+ if (tunnel->debug & L2TP_MSG_DATA) {
+ length = min(32u, skb->len);
+ if (!pskb_may_pull(skb, length))
+ goto discard;
+
+ printk(KERN_DEBUG "%s: ip recv: ", tunnel->name);
+
+ offset = 0;
+ do {
+ printk(" %02X", ptr[offset]);
+ } while (++offset < length);
+
+ printk("\n");
+ }
+
+ l2tp_recv_common(session, skb, ptr, optr, 0, skb->len,
+ tunnel->recv_payload_hook);
+ return 0;
+
+pass_up:
+ /* Get the tunnel_id from the L2TP header */
+ if (!pskb_may_pull(skb, 12))
+ goto discard;
+
+ if ((skb->data[0] & 0xc0) != 0xc0)
+ goto discard;
+
+ tunnel_id = ntohl(*(__be32 *) &skb->data[4]);
+ tunnel = l2tp_tunnel_find(&init_net, tunnel_id);
+ if (tunnel != NULL)
+ sk = tunnel->sock;
+ else {
+ struct ipv6hdr *iph = ipv6_hdr(skb);
+
+ read_lock_bh(&l2tp_ip6_lock);
+ sk = __l2tp_ip6_bind_lookup(&init_net, &iph->daddr,
+ 0, tunnel_id);
+ read_unlock_bh(&l2tp_ip6_lock);
+ }
+
+ if (sk == NULL)
+ goto discard;
+
+ sock_hold(sk);
+
+ if (!xfrm6_policy_check(sk, XFRM_POLICY_IN, skb))
+ goto discard_put;
+
+ nf_reset(skb);
+
+ return sk_receive_skb(sk, skb, 1);
+
+discard_put:
+ sock_put(sk);
+
+discard:
+ kfree_skb(skb);
+ return 0;
+}
+
+static int l2tp_ip6_open(struct sock *sk)
+{
+ /* Prevent autobind. We don't have ports. */
+ inet_sk(sk)->inet_num = IPPROTO_L2TP;
+
+ write_lock_bh(&l2tp_ip6_lock);
+ sk_add_node(sk, &l2tp_ip6_table);
+ write_unlock_bh(&l2tp_ip6_lock);
+
+ return 0;
+}
+
+static void l2tp_ip6_close(struct sock *sk, long timeout)
+{
+ write_lock_bh(&l2tp_ip6_lock);
+ hlist_del_init(&sk->sk_bind_node);
+ sk_del_node_init(sk);
+ write_unlock_bh(&l2tp_ip6_lock);
+
+ sk_common_release(sk);
+}
+
+static void l2tp_ip6_destroy_sock(struct sock *sk)
+{
+ lock_sock(sk);
+ ip6_flush_pending_frames(sk);
+ release_sock(sk);
+
+ inet6_destroy_sock(sk);
+}
+
+static int l2tp_ip6_bind(struct sock *sk, struct sockaddr *uaddr, int addr_len)
+{
+ struct inet_sock *inet = inet_sk(sk);
+ struct ipv6_pinfo *np = inet6_sk(sk);
+ struct sockaddr_l2tpip6 *addr = (struct sockaddr_l2tpip6 *) uaddr;
+ __be32 v4addr = 0;
+ int addr_type;
+ int err;
+
+ if (addr_len < sizeof(*addr))
+ return -EINVAL;
+
+ addr_type = ipv6_addr_type(&addr->l2tp_addr);
+
+ /* l2tp_ip6 sockets are IPv6 only */
+ if (addr_type == IPV6_ADDR_MAPPED)
+ return -EADDRNOTAVAIL;
+
+ /* L2TP is point-point, not multicast */
+ if (addr_type & IPV6_ADDR_MULTICAST)
+ return -EADDRNOTAVAIL;
+
+ err = -EADDRINUSE;
+ read_lock_bh(&l2tp_ip6_lock);
+ if (__l2tp_ip6_bind_lookup(&init_net, &addr->l2tp_addr,
+ sk->sk_bound_dev_if, addr->l2tp_conn_id))
+ goto out_in_use;
+ read_unlock_bh(&l2tp_ip6_lock);
+
+ lock_sock(sk);
+
+ err = -EINVAL;
+ if (sk->sk_state != TCP_CLOSE)
+ goto out_unlock;
+
+ /* Check if the address belongs to the host. */
+ rcu_read_lock();
+ if (addr_type != IPV6_ADDR_ANY) {
+ struct net_device *dev = NULL;
+
+ if (addr_type & IPV6_ADDR_LINKLOCAL) {
+ if (addr_len >= sizeof(struct sockaddr_in6) &&
+ addr->l2tp_scope_id) {
+ /* Override any existing binding, if another
+ * one is supplied by user.
+ */
+ sk->sk_bound_dev_if = addr->l2tp_scope_id;
+ }
+
+ /* Binding to link-local address requires an
+ interface */
+ if (!sk->sk_bound_dev_if)
+ goto out_unlock_rcu;
+
+ err = -ENODEV;
+ dev = dev_get_by_index_rcu(sock_net(sk),
+ sk->sk_bound_dev_if);
+ if (!dev)
+ goto out_unlock_rcu;
+ }
+
+ /* ipv4 addr of the socket is invalid. Only the
+ * unspecified and mapped address have a v4 equivalent.
+ */
+ v4addr = LOOPBACK4_IPV6;
+ err = -EADDRNOTAVAIL;
+ if (!ipv6_chk_addr(sock_net(sk), &addr->l2tp_addr, dev, 0))
+ goto out_unlock_rcu;
+ }
+ rcu_read_unlock();
+
+ inet->inet_rcv_saddr = inet->inet_saddr = v4addr;
+ np->rcv_saddr = addr->l2tp_addr;
+ np->saddr = addr->l2tp_addr;
+
+ l2tp_ip6_sk(sk)->conn_id = addr->l2tp_conn_id;
+
+ write_lock_bh(&l2tp_ip6_lock);
+ sk_add_bind_node(sk, &l2tp_ip6_bind_table);
+ sk_del_node_init(sk);
+ write_unlock_bh(&l2tp_ip6_lock);
+
+ release_sock(sk);
+ return 0;
+
+out_unlock_rcu:
+ rcu_read_unlock();
+out_unlock:
+ release_sock(sk);
+ return err;
+
+out_in_use:
+ read_unlock_bh(&l2tp_ip6_lock);
+ return err;
+}
+
+static int l2tp_ip6_connect(struct sock *sk, struct sockaddr *uaddr,
+ int addr_len)
+{
+ struct sockaddr_l2tpip6 *lsa = (struct sockaddr_l2tpip6 *) uaddr;
+ struct sockaddr_in6 *usin = (struct sockaddr_in6 *) uaddr;
+ struct in6_addr *daddr;
+ int addr_type;
+ int rc;
+
+ if (addr_len < sizeof(*lsa))
+ return -EINVAL;
+
+ addr_type = ipv6_addr_type(&usin->sin6_addr);
+ if (addr_type & IPV6_ADDR_MULTICAST)
+ return -EINVAL;
+
+ if (addr_type & IPV6_ADDR_MAPPED) {
+ daddr = &usin->sin6_addr;
+ if (ipv4_is_multicast(daddr->s6_addr32[3]))
+ return -EINVAL;
+ }
+
+ rc = ip6_datagram_connect(sk, uaddr, addr_len);
+
+ lock_sock(sk);
+
+ l2tp_ip6_sk(sk)->peer_conn_id = lsa->l2tp_conn_id;
+
+ write_lock_bh(&l2tp_ip6_lock);
+ hlist_del_init(&sk->sk_bind_node);
+ sk_add_bind_node(sk, &l2tp_ip6_bind_table);
+ write_unlock_bh(&l2tp_ip6_lock);
+
+ release_sock(sk);
+
+ return rc;
+}
+
+static int l2tp_ip6_getname(struct socket *sock, struct sockaddr *uaddr,
+ int *uaddr_len, int peer)
+{
+ struct sockaddr_l2tpip6 *lsa = (struct sockaddr_l2tpip6 *)uaddr;
+ struct sock *sk = sock->sk;
+ struct ipv6_pinfo *np = inet6_sk(sk);
+ struct l2tp_ip6_sock *lsk = l2tp_ip6_sk(sk);
+
+ lsa->l2tp_family = AF_INET6;
+ lsa->l2tp_flowinfo = 0;
+ lsa->l2tp_scope_id = 0;
+ if (peer) {
+ if (!lsk->peer_conn_id)
+ return -ENOTCONN;
+ lsa->l2tp_conn_id = lsk->peer_conn_id;
+ lsa->l2tp_addr = np->daddr;
+ if (np->sndflow)
+ lsa->l2tp_flowinfo = np->flow_label;
+ } else {
+ if (ipv6_addr_any(&np->rcv_saddr))
+ lsa->l2tp_addr = np->saddr;
+ else
+ lsa->l2tp_addr = np->rcv_saddr;
+
+ lsa->l2tp_conn_id = lsk->conn_id;
+ }
+ if (ipv6_addr_type(&lsa->l2tp_addr) & IPV6_ADDR_LINKLOCAL)
+ lsa->l2tp_scope_id = sk->sk_bound_dev_if;
+ *uaddr_len = sizeof(*lsa);
+ return 0;
+}
+
+static int l2tp_ip6_backlog_recv(struct sock *sk, struct sk_buff *skb)
+{
+ int rc;
+
+ /* Charge it to the socket, dropping if the queue is full. */
+ rc = sock_queue_rcv_skb(sk, skb);
+ if (rc < 0)
+ goto drop;
+
+ return 0;
+
+drop:
+ IP_INC_STATS(&init_net, IPSTATS_MIB_INDISCARDS);
+ kfree_skb(skb);
+ return -1;
+}
+
+static int l2tp_ip6_push_pending_frames(struct sock *sk)
+{
+ struct sk_buff *skb;
+ __be32 *transhdr = NULL;
+ int err = 0;
+
+ skb = skb_peek(&sk->sk_write_queue);
+ if (skb == NULL)
+ goto out;
+
+ transhdr = (__be32 *)skb_transport_header(skb);
+ *transhdr = 0;
+
+ err = ip6_push_pending_frames(sk);
+
+out:
+ return err;
+}
+
+/* Userspace will call sendmsg() on the tunnel socket to send L2TP
+ * control frames.
+ */
+static int l2tp_ip6_sendmsg(struct kiocb *iocb, struct sock *sk,
+ struct msghdr *msg, size_t len)
+{
+ struct ipv6_txoptions opt_space;
+ struct sockaddr_l2tpip6 *lsa =
+ (struct sockaddr_l2tpip6 *) msg->msg_name;
+ struct in6_addr *daddr, *final_p, final;
+ struct ipv6_pinfo *np = inet6_sk(sk);
+ struct ipv6_txoptions *opt = NULL;
+ struct ip6_flowlabel *flowlabel = NULL;
+ struct dst_entry *dst = NULL;
+ struct flowi6 fl6;
+ int addr_len = msg->msg_namelen;
+ int hlimit = -1;
+ int tclass = -1;
+ int dontfrag = -1;
+ int transhdrlen = 4; /* zero session-id */
+ int ulen = len + transhdrlen;
+ int err;
+
+ /* Rough check on arithmetic overflow,
+ better check is made in ip6_append_data().
+ */
+ if (len > INT_MAX)
+ return -EMSGSIZE;
+
+ /* Mirror BSD error message compatibility */
+ if (msg->msg_flags & MSG_OOB)
+ return -EOPNOTSUPP;
+
+ /*
+ * Get and verify the address.
+ */
+ memset(&fl6, 0, sizeof(fl6));
+
+ fl6.flowi6_mark = sk->sk_mark;
+
+ if (lsa) {
+ if (addr_len < SIN6_LEN_RFC2133)
+ return -EINVAL;
+
+ if (lsa->l2tp_family && lsa->l2tp_family != AF_INET6)
+ return -EAFNOSUPPORT;
+
+ daddr = &lsa->l2tp_addr;
+ if (np->sndflow) {
+ fl6.flowlabel = lsa->l2tp_flowinfo & IPV6_FLOWINFO_MASK;
+ if (fl6.flowlabel&IPV6_FLOWLABEL_MASK) {
+ flowlabel = fl6_sock_lookup(sk, fl6.flowlabel);
+ if (flowlabel == NULL)
+ return -EINVAL;
+ daddr = &flowlabel->dst;
+ }
+ }
+
+ /*
+ * Otherwise it will be difficult to maintain
+ * sk->sk_dst_cache.
+ */
+ if (sk->sk_state == TCP_ESTABLISHED &&
+ ipv6_addr_equal(daddr, &np->daddr))
+ daddr = &np->daddr;
+
+ if (addr_len >= sizeof(struct sockaddr_in6) &&
+ lsa->l2tp_scope_id &&
+ ipv6_addr_type(daddr) & IPV6_ADDR_LINKLOCAL)
+ fl6.flowi6_oif = lsa->l2tp_scope_id;
+ } else {
+ if (sk->sk_state != TCP_ESTABLISHED)
+ return -EDESTADDRREQ;
+
+ daddr = &np->daddr;
+ fl6.flowlabel = np->flow_label;
+ }
+
+ if (fl6.flowi6_oif == 0)
+ fl6.flowi6_oif = sk->sk_bound_dev_if;
+
+ if (msg->msg_controllen) {
+ opt = &opt_space;
+ 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);
+ if (err < 0) {
+ fl6_sock_release(flowlabel);
+ return err;
+ }
+ if ((fl6.flowlabel & IPV6_FLOWLABEL_MASK) && !flowlabel) {
+ flowlabel = fl6_sock_lookup(sk, fl6.flowlabel);
+ if (flowlabel == NULL)
+ return -EINVAL;
+ }
+ if (!(opt->opt_nflen|opt->opt_flen))
+ opt = NULL;
+ }
+
+ if (opt == NULL)
+ opt = np->opt;
+ if (flowlabel)
+ opt = fl6_merge_options(&opt_space, flowlabel, opt);
+ opt = ipv6_fixup_options(&opt_space, opt);
+
+ fl6.flowi6_proto = sk->sk_protocol;
+ if (!ipv6_addr_any(daddr))
+ fl6.daddr = *daddr;
+ else
+ fl6.daddr.s6_addr[15] = 0x1; /* :: means loopback (BSD'ism) */
+ if (ipv6_addr_any(&fl6.saddr) && !ipv6_addr_any(&np->saddr))
+ fl6.saddr = np->saddr;
+
+ final_p = fl6_update_dst(&fl6, opt, &final);
+
+ if (!fl6.flowi6_oif && ipv6_addr_is_multicast(&fl6.daddr))
+ fl6.flowi6_oif = np->mcast_oif;
+ else if (!fl6.flowi6_oif)
+ fl6.flowi6_oif = np->ucast_oif;
+
+ security_sk_classify_flow(sk, flowi6_to_flowi(&fl6));
+
+ dst = ip6_dst_lookup_flow(sk, &fl6, final_p, true);
+ if (IS_ERR(dst)) {
+ err = PTR_ERR(dst);
+ goto out;
+ }
+
+ if (hlimit < 0) {
+ if (ipv6_addr_is_multicast(&fl6.daddr))
+ hlimit = np->mcast_hops;
+ else
+ hlimit = np->hop_limit;
+ if (hlimit < 0)
+ hlimit = ip6_dst_hoplimit(dst);
+ }
+
+ if (tclass < 0)
+ tclass = np->tclass;
+
+ if (dontfrag < 0)
+ dontfrag = np->dontfrag;
+
+ if (msg->msg_flags & MSG_CONFIRM)
+ goto do_confirm;
+
+back_from_confirm:
+ lock_sock(sk);
+ err = ip6_append_data(sk, ip_generic_getfrag, msg->msg_iov,
+ ulen, transhdrlen, hlimit, tclass, opt,
+ &fl6, (struct rt6_info *)dst,
+ msg->msg_flags, dontfrag);
+ if (err)
+ ip6_flush_pending_frames(sk);
+ else if (!(msg->msg_flags & MSG_MORE))
+ err = l2tp_ip6_push_pending_frames(sk);
+ release_sock(sk);
+done:
+ dst_release(dst);
+out:
+ fl6_sock_release(flowlabel);
+
+ return err < 0 ? err : len;
+
+do_confirm:
+ dst_confirm(dst);
+ if (!(msg->msg_flags & MSG_PROBE) || len)
+ goto back_from_confirm;
+ err = 0;
+ goto done;
+}
+
+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 sockaddr_l2tpip6 *lsa = (struct sockaddr_l2tpip6 *)msg->msg_name;
+ size_t copied = 0;
+ int err = -EOPNOTSUPP;
+ struct sk_buff *skb;
+
+ if (flags & MSG_OOB)
+ goto out;
+
+ if (addr_len)
+ *addr_len = sizeof(*lsa);
+
+ if (flags & MSG_ERRQUEUE)
+ return ipv6_recv_error(sk, msg, len);
+
+ skb = skb_recv_datagram(sk, flags, noblock, &err);
+ if (!skb)
+ goto out;
+
+ copied = skb->len;
+ if (len < copied) {
+ msg->msg_flags |= MSG_TRUNC;
+ copied = len;
+ }
+
+ err = skb_copy_datagram_iovec(skb, 0, msg->msg_iov, copied);
+ if (err)
+ goto done;
+
+ sock_recv_timestamp(msg, sk, skb);
+
+ /* Copy the address. */
+ if (lsa) {
+ lsa->l2tp_family = AF_INET6;
+ lsa->l2tp_unused = 0;
+ lsa->l2tp_addr = ipv6_hdr(skb)->saddr;
+ lsa->l2tp_flowinfo = 0;
+ lsa->l2tp_scope_id = 0;
+ if (ipv6_addr_type(&lsa->l2tp_addr) & IPV6_ADDR_LINKLOCAL)
+ lsa->l2tp_scope_id = IP6CB(skb)->iif;
+ }
+
+ if (inet->cmsg_flags)
+ ip_cmsg_recv(msg, skb);
+
+ if (flags & MSG_TRUNC)
+ copied = skb->len;
+done:
+ skb_free_datagram(sk, skb);
+out:
+ return err ? err : copied;
+}
+
+static struct proto l2tp_ip6_prot = {
+ .name = "L2TP/IPv6",
+ .owner = THIS_MODULE,
+ .init = l2tp_ip6_open,
+ .close = l2tp_ip6_close,
+ .bind = l2tp_ip6_bind,
+ .connect = l2tp_ip6_connect,
+ .disconnect = udp_disconnect,
+ .ioctl = udp_ioctl,
+ .destroy = l2tp_ip6_destroy_sock,
+ .setsockopt = ipv6_setsockopt,
+ .getsockopt = ipv6_getsockopt,
+ .sendmsg = l2tp_ip6_sendmsg,
+ .recvmsg = l2tp_ip6_recvmsg,
+ .backlog_rcv = l2tp_ip6_backlog_recv,
+ .hash = inet_hash,
+ .unhash = inet_unhash,
+ .obj_size = sizeof(struct l2tp_ip6_sock),
+#ifdef CONFIG_COMPAT
+ .compat_setsockopt = compat_ipv6_setsockopt,
+ .compat_getsockopt = compat_ipv6_getsockopt,
+#endif
+};
+
+static const struct proto_ops l2tp_ip6_ops = {
+ .family = PF_INET6,
+ .owner = THIS_MODULE,
+ .release = inet6_release,
+ .bind = inet6_bind,
+ .connect = inet_dgram_connect,
+ .socketpair = sock_no_socketpair,
+ .accept = sock_no_accept,
+ .getname = l2tp_ip6_getname,
+ .poll = datagram_poll,
+ .ioctl = inet6_ioctl,
+ .listen = sock_no_listen,
+ .shutdown = inet_shutdown,
+ .setsockopt = sock_common_setsockopt,
+ .getsockopt = sock_common_getsockopt,
+ .sendmsg = inet_sendmsg,
+ .recvmsg = sock_common_recvmsg,
+ .mmap = sock_no_mmap,
+ .sendpage = sock_no_sendpage,
+#ifdef CONFIG_COMPAT
+ .compat_setsockopt = compat_sock_common_setsockopt,
+ .compat_getsockopt = compat_sock_common_getsockopt,
+#endif
+};
+
+static struct inet_protosw l2tp_ip6_protosw = {
+ .type = SOCK_DGRAM,
+ .protocol = IPPROTO_L2TP,
+ .prot = &l2tp_ip6_prot,
+ .ops = &l2tp_ip6_ops,
+ .no_check = 0,
+};
+
+static struct inet6_protocol l2tp_ip6_protocol __read_mostly = {
+ .handler = l2tp_ip6_recv,
+};
+
+static int __init l2tp_ip6_init(void)
+{
+ int err;
+
+ printk(KERN_INFO "L2TP IP encapsulation support for IPv6 (L2TPv3)\n");
+
+ err = proto_register(&l2tp_ip6_prot, 1);
+ if (err != 0)
+ goto out;
+
+ err = inet6_add_protocol(&l2tp_ip6_protocol, IPPROTO_L2TP);
+ if (err)
+ goto out1;
+
+ inet6_register_protosw(&l2tp_ip6_protosw);
+ return 0;
+
+out1:
+ proto_unregister(&l2tp_ip6_prot);
+out:
+ return err;
+}
+
+static void __exit l2tp_ip6_exit(void)
+{
+ inet6_unregister_protosw(&l2tp_ip6_protosw);
+ inet6_del_protocol(&l2tp_ip6_protocol, IPPROTO_L2TP);
+ proto_unregister(&l2tp_ip6_prot);
+}
+
+module_init(l2tp_ip6_init);
+module_exit(l2tp_ip6_exit);
+
+MODULE_LICENSE("GPL");
+MODULE_AUTHOR("Chris Elston <celston@katalix.com>");
+MODULE_DESCRIPTION("L2TP IP encapsulation for IPv6");
+MODULE_VERSION("1.0");
+
+/* Use the value of SOCK_DGRAM (2) directory, because __stringify doesn't like
+ * enums
+ */
+MODULE_ALIAS_NET_PF_PROTO_TYPE(PF_INET6, 2, IPPROTO_L2TP);
--
1.7.0.4
^ permalink raw reply related
* [PATCH 10/10 net-next] l2tp: let iproute2 create L2TPv3 IP tunnels using IPv6
From: James Chapman @ 2012-04-30 7:48 UTC (permalink / raw)
To: netdev
In-Reply-To: <1335772135-27910-1-git-send-email-jchapman@katalix.com>
The netlink API lets users create unmanaged L2TPv3 tunnels using
iproute2. Until now, a request to create an unmanaged L2TPv3 IP
encapsulation tunnel over IPv6 would be rejected with
EPROTONOSUPPORT. Now that l2tp_ip6 implements sockets for L2TP IP
encapsulation over IPv6, we can add support for that tunnel type.
Signed-off-by: James Chapman <jchapman@katalix.com>
---
net/l2tp/l2tp_core.c | 72 ++++++++++++++++++++++++++++++++++---------------
1 files changed, 50 insertions(+), 22 deletions(-)
diff --git a/net/l2tp/l2tp_core.c b/net/l2tp/l2tp_core.c
index 5a7d908..7415620 100644
--- a/net/l2tp/l2tp_core.c
+++ b/net/l2tp/l2tp_core.c
@@ -1367,6 +1367,7 @@ static int l2tp_tunnel_sock_create(u32 tunnel_id, u32 peer_tunnel_id, struct l2t
struct sockaddr_in udp_addr;
#if IS_ENABLED(CONFIG_IPV6)
struct sockaddr_in6 udp6_addr;
+ struct sockaddr_l2tpip6 ip6_addr;
#endif
struct sockaddr_l2tpip ip_addr;
struct socket *sock = NULL;
@@ -1436,32 +1437,59 @@ 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) {
- /* IP encap over IPv6 not yet supported */
- err = -EPROTONOSUPPORT;
- goto out;
- }
-#endif
- err = sock_create(AF_INET, SOCK_DGRAM, IPPROTO_L2TP, sockp);
- if (err < 0)
- goto out;
+ err = sock_create(AF_INET6, SOCK_DGRAM, IPPROTO_L2TP,
+ sockp);
+ if (err < 0)
+ goto out;
- sock = *sockp;
+ sock = *sockp;
- 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;
- err = kernel_bind(sock, (struct sockaddr *) &ip_addr, sizeof(ip_addr));
- if (err < 0)
- goto out;
+ 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));
+ ip6_addr.l2tp_conn_id = tunnel_id;
+ err = kernel_bind(sock, (struct sockaddr *) &ip6_addr,
+ sizeof(ip6_addr));
+ if (err < 0)
+ goto out;
- ip_addr.l2tp_family = AF_INET;
- ip_addr.l2tp_addr = cfg->peer_ip;
- ip_addr.l2tp_conn_id = peer_tunnel_id;
- err = kernel_connect(sock, (struct sockaddr *) &ip_addr, sizeof(ip_addr), 0);
- if (err < 0)
- goto out;
+ ip6_addr.l2tp_family = AF_INET6;
+ memcpy(&ip6_addr.l2tp_addr, cfg->peer_ip6,
+ sizeof(ip6_addr.l2tp_addr));
+ ip6_addr.l2tp_conn_id = peer_tunnel_id;
+ err = kernel_connect(sock,
+ (struct sockaddr *) &ip6_addr,
+ sizeof(ip6_addr), 0);
+ if (err < 0)
+ goto out;
+ } else
+#endif
+ {
+ err = sock_create(AF_INET, SOCK_DGRAM, IPPROTO_L2TP,
+ sockp);
+ if (err < 0)
+ goto out;
+ sock = *sockp;
+
+ 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;
+ err = kernel_bind(sock, (struct sockaddr *) &ip_addr,
+ sizeof(ip_addr));
+ if (err < 0)
+ goto out;
+
+ ip_addr.l2tp_family = AF_INET;
+ ip_addr.l2tp_addr = cfg->peer_ip;
+ ip_addr.l2tp_conn_id = peer_tunnel_id;
+ err = kernel_connect(sock, (struct sockaddr *) &ip_addr,
+ sizeof(ip_addr), 0);
+ if (err < 0)
+ goto out;
+ }
break;
default:
--
1.7.0.4
^ permalink raw reply related
* Re: [PATCH] usbnet: fix skb traversing races during unlink
From: Ming Lei @ 2012-04-30 8:13 UTC (permalink / raw)
To: David Miller
Cc: gregkh-hQyY1W1yCW8ekmWlsbkhG0B+6BGkLq7r,
netdev-u79uwXL29TY76Z2rM5mHXA, linux-usb-u79uwXL29TY76Z2rM5mHXA,
huajun.li.lee-Re5JQEeQqe8AvxtiuMwx3w, oneukum-l3A5Bk7waGM,
stable-DgEjT+Ai2ygdnm+yROfE0A
In-Reply-To: <20120428.221832.360259077795872366.davem-fT/PcQaiUtIeIZ0/mPfg9Q@public.gmane.org>
On Sun, Apr 29, 2012 at 10:18 AM, David Miller <davem-fT/PcQaiUtIeIZ0/mPfg9Q@public.gmane.org> wrote:
> From: Ming Lei <tom.leiming-Re5JQEeQqe8AvxtiuMwx3w@public.gmane.org>
> Date: Fri, 27 Apr 2012 18:21:35 +0800
>
>> +/*The caller must hold list->lock*/
>
> Please put spaces in your comments, like this:
>
> /* The caller must hold list->lock */
>
>> +
>> + /*speedup unlink by blocking resubmit*/
>
> Same here.
OK, will do it.
>>
>> - entry = (struct skb_data *) skb->cb;
>> + skb_queue_walk(q, skb) {
>> + entry = (struct skb_data *) skb->cb;
>> + if (entry->state != unlink_start)
>> + break;
>> + }
>> + if (skb == (struct sk_buff *)q)
>> + break;
>
> Please do not expose the internal details of SKB lists
> with a test like this. Eventually this will all be
> converted to struct list_head and this kind of test
> will cause unnecessary pain for such a conversion.
>
> Instead, code it like this, as you would for a loop
> using list_for_each*() or similar:
>
> skb_queue_walk(q, skb) {
> if (condition)
> goto found;
> }
> /* No matching entry. */
> break;
> found:
Good suggestion, will do it.
Thanks,
--
Ming Lei
--
To unsubscribe from this list: send the line "unsubscribe linux-usb" in
the body of a message to majordomo-u79uwXL29TY76Z2rM5mHXA@public.gmane.org
More majordomo info at http://vger.kernel.org/majordomo-info.html
^ permalink raw reply
* [PATCH 1/2] net: ucc_geth, increase no. of HW RX descriptors
From: Joakim Tjernlund @ 2012-04-30 8:36 UTC (permalink / raw)
To: netdev@vger.kernel.org; +Cc: Joakim Tjernlund
In a busy network we see ucc_geth is dropping RX pkgs every now
and then. Increase the RX queues HW descriptors from
16 to 32 to deal with this.
Signed-off-by: Joakim Tjernlund <Joakim.Tjernlund@transmode.se>
---
drivers/net/ethernet/freescale/ucc_geth.h | 2 +-
1 files changed, 1 insertions(+), 1 deletions(-)
diff --git a/drivers/net/ethernet/freescale/ucc_geth.h b/drivers/net/ethernet/freescale/ucc_geth.h
index 2e395a2..f71b3e7 100644
--- a/drivers/net/ethernet/freescale/ucc_geth.h
+++ b/drivers/net/ethernet/freescale/ucc_geth.h
@@ -877,7 +877,7 @@ struct ucc_geth_hardware_statistics {
/* Driver definitions */
#define TX_BD_RING_LEN 0x10
-#define RX_BD_RING_LEN 0x10
+#define RX_BD_RING_LEN 0x20
#define TX_RING_MOD_MASK(size) (size-1)
#define RX_RING_MOD_MASK(size) (size-1)
--
1.7.3.4
^ permalink raw reply related
* [PATCH 2/2] ucc_geth: Add 16 bytes to max TX frame for VLANs
From: Joakim Tjernlund @ 2012-04-30 8:36 UTC (permalink / raw)
To: netdev@vger.kernel.org; +Cc: Joakim Tjernlund
In-Reply-To: <1335775015-14718-1-git-send-email-Joakim.Tjernlund@transmode.se>
Creating a VLAN interface on top of ucc_geth adds 4 bytes
to the frame and the HW controller is not prepared to
TX a frame bigger than 1518 bytes which is 4 bytes too
small for a full VLAN frame. Add 16 bytes which will handle
the a simple VLAN and leaves 12 bytes for future expansion.
Signed-off-by: Joakim Tjernlund <Joakim.Tjernlund@transmode.se>
---
drivers/net/ethernet/freescale/ucc_geth.c | 6 +++---
1 files changed, 3 insertions(+), 3 deletions(-)
diff --git a/drivers/net/ethernet/freescale/ucc_geth.c b/drivers/net/ethernet/freescale/ucc_geth.c
index ba2dc08..638c8cb 100644
--- a/drivers/net/ethernet/freescale/ucc_geth.c
+++ b/drivers/net/ethernet/freescale/ucc_geth.c
@@ -116,10 +116,10 @@ static struct ucc_geth_info ugeth_primary_info = {
.maxGroupAddrInHash = 4,
.maxIndAddrInHash = 4,
.prel = 7,
- .maxFrameLength = 1518,
+ .maxFrameLength = 1518+16, /* Add extra bytes for VLANs etc. */
.minFrameLength = 64,
- .maxD1Length = 1520,
- .maxD2Length = 1520,
+ .maxD1Length = 1520+16, /* Add extra bytes for VLANs etc. */
+ .maxD2Length = 1520+16, /* Add extra bytes for VLANs etc. */
.vlantype = 0x8100,
.ecamptr = ((uint32_t) NULL),
.eventRegMask = UCCE_OTHER,
--
1.7.3.4
^ permalink raw reply related
* [PATCH] bridge: make brctl showstp display port id
From: Joakim Tjernlund @ 2012-04-30 8:39 UTC (permalink / raw)
To: netdev@vger.kernel.org; +Cc: Joakim Tjernlund
My brctl showstp br0 always shows a 0 port id:
eth2 (1)
port id 0 state disabled
designated root 8000.00069c00b2fb path cost 100
because port id is printed as a hex number in sys fs. Change the
two hex occurrences(port no and port id) to decimal, just like all
the other numbers in this area.
Signed-off-by: Joakim Tjernlund <Joakim.Tjernlund@transmode.se>
---
net/bridge/br_sysfs_if.c | 4 ++--
1 files changed, 2 insertions(+), 2 deletions(-)
diff --git a/net/bridge/br_sysfs_if.c b/net/bridge/br_sysfs_if.c
index fd5799c..9c4c2eb 100644
--- a/net/bridge/br_sysfs_if.c
+++ b/net/bridge/br_sysfs_if.c
@@ -86,13 +86,13 @@ static BRPORT_ATTR(designated_cost, S_IRUGO, show_designated_cost, NULL);
static ssize_t show_port_id(struct net_bridge_port *p, char *buf)
{
- return sprintf(buf, "0x%x\n", p->port_id);
+ return sprintf(buf, "%d\n", p->port_id);
}
static BRPORT_ATTR(port_id, S_IRUGO, show_port_id, NULL);
static ssize_t show_port_no(struct net_bridge_port *p, char *buf)
{
- return sprintf(buf, "0x%x\n", p->port_no);
+ return sprintf(buf, "%d\n", p->port_no);
}
static BRPORT_ATTR(port_no, S_IRUGO, show_port_no, NULL);
--
1.7.3.4
^ permalink raw reply related
* [PATCH 1/3] usbnet: fix leak of transfer buffer of dev->interrupt
From: Ming Lei @ 2012-04-30 8:51 UTC (permalink / raw)
To: David S. Miller, Greg Kroah-Hartman
Cc: netdev-u79uwXL29TY76Z2rM5mHXA, linux-usb-u79uwXL29TY76Z2rM5mHXA,
Ming Lei
In-Reply-To: <1335775864-4873-1-git-send-email-tom.leiming-Re5JQEeQqe8AvxtiuMwx3w@public.gmane.org>
The transfer buffer of dev->interrupt is allocated in .probe path,
but not freed in .disconnet path, so mark the interrupt URB as
URB_FREE_BUFFER to free the buffer when the URB is destroyed.
Signed-off-by: Ming Lei <tom.leiming-Re5JQEeQqe8AvxtiuMwx3w@public.gmane.org>
---
drivers/net/usb/usbnet.c | 1 +
1 file changed, 1 insertion(+)
diff --git a/drivers/net/usb/usbnet.c b/drivers/net/usb/usbnet.c
index db99536..5b38a3a 100644
--- a/drivers/net/usb/usbnet.c
+++ b/drivers/net/usb/usbnet.c
@@ -210,6 +210,7 @@ static int init_status (struct usbnet *dev, struct usb_interface *intf)
} else {
usb_fill_int_urb(dev->interrupt, dev->udev, pipe,
buf, maxp, intr_complete, dev, period);
+ dev->interrupt->transfer_flags |= URB_FREE_BUFFER;
dev_dbg(&intf->dev,
"status ep%din, %d bytes period %d\n",
usb_pipeendpoint(pipe), maxp, period);
--
1.7.9.5
--
To unsubscribe from this list: send the line "unsubscribe linux-usb" in
the body of a message to majordomo-u79uwXL29TY76Z2rM5mHXA@public.gmane.org
More majordomo info at http://vger.kernel.org/majordomo-info.html
^ permalink raw reply related
* [PATCH 2/3] usbnet: fix failure handling in usbnet_probe
From: Ming Lei @ 2012-04-30 8:51 UTC (permalink / raw)
To: David S. Miller, Greg Kroah-Hartman
Cc: netdev-u79uwXL29TY76Z2rM5mHXA, linux-usb-u79uwXL29TY76Z2rM5mHXA,
Ming Lei
In-Reply-To: <1335775864-4873-1-git-send-email-tom.leiming-Re5JQEeQqe8AvxtiuMwx3w@public.gmane.org>
If register_netdev returns failure, the dev->interrupt and
its transfer buffer should be released, so just fix it.
Signed-off-by: Ming Lei <tom.leiming-Re5JQEeQqe8AvxtiuMwx3w@public.gmane.org>
---
drivers/net/usb/usbnet.c | 4 +++-
1 file changed, 3 insertions(+), 1 deletion(-)
diff --git a/drivers/net/usb/usbnet.c b/drivers/net/usb/usbnet.c
index 5b38a3a..80b837c 100644
--- a/drivers/net/usb/usbnet.c
+++ b/drivers/net/usb/usbnet.c
@@ -1445,7 +1445,7 @@ usbnet_probe (struct usb_interface *udev, const struct usb_device_id *prod)
status = register_netdev (net);
if (status)
- goto out3;
+ goto out4;
netif_info(dev, probe, dev->net,
"register '%s' at usb-%s-%s, %s, %pM\n",
udev->dev.driver->name,
@@ -1463,6 +1463,8 @@ usbnet_probe (struct usb_interface *udev, const struct usb_device_id *prod)
return 0;
+out4:
+ usb_free_urb(dev->interrupt);
out3:
if (info->unbind)
info->unbind (dev, udev);
--
1.7.9.5
--
To unsubscribe from this list: send the line "unsubscribe linux-usb" in
the body of a message to majordomo-u79uwXL29TY76Z2rM5mHXA@public.gmane.org
More majordomo info at http://vger.kernel.org/majordomo-info.html
^ permalink raw reply related
* [PATCH 3/3] usbnet: fix skb traversing races during unlink(v1)
From: Ming Lei @ 2012-04-30 8:51 UTC (permalink / raw)
To: David S. Miller, Greg Kroah-Hartman
Cc: netdev-u79uwXL29TY76Z2rM5mHXA, linux-usb-u79uwXL29TY76Z2rM5mHXA,
Ming Lei, Huajun Li, Oliver Neukum, stable-DgEjT+Ai2ygdnm+yROfE0A
In-Reply-To: <1335775864-4873-1-git-send-email-tom.leiming-Re5JQEeQqe8AvxtiuMwx3w@public.gmane.org>
Commit 4231d47e6fe69f061f96c98c30eaf9fb4c14b96d(net/usbnet: avoid
recursive locking in usbnet_stop()) fixes the recursive locking
problem by releasing the skb queue lock before unlink, but may
cause skb traversing races:
- after URB is unlinked and the queue lock is released,
the refered skb and skb->next may be moved to done queue,
even be released
- in skb_queue_walk_safe, the next skb is still obtained
by next pointer of the last skb
- so maybe trigger oops or other problems
This patch extends the usage of entry->state to describe 'start_unlink'
state, so always holding the queue(rx/tx) lock to change the state if
the referd skb is in rx or tx queue because we need to know if the
refered urb has been started unlinking in unlink_urbs.
Also the patch uses usb_block_urb introduced by Oliver to block
URB resubmit in complete handler if the URB will be unlinked.
The other part of this patch is based on Huajun's patch:
always traverse from head of the tx/rx queue to get skb which is
to be unlinked but not been started unlinking.
Signed-off-by: Huajun Li <huajun.li.lee-Re5JQEeQqe8AvxtiuMwx3w@public.gmane.org>
Signed-off-by: Ming Lei <tom.leiming-Re5JQEeQqe8AvxtiuMwx3w@public.gmane.org>
Cc: Oliver Neukum <oneukum-l3A5Bk7waGM@public.gmane.org>
Cc: stable-DgEjT+Ai2ygdnm+yROfE0A@public.gmane.org
---
v1:
- fix comment style and avoiding to expose the internal
details of SKB lists, as suggested by David Miller
This patch depends on the usb_block_urb/usb_unblock_urb patch from
Oliver.
drivers/net/usb/usbnet.c | 53 +++++++++++++++++++++++++++++++-------------
include/linux/usb/usbnet.h | 3 ++-
2 files changed, 40 insertions(+), 16 deletions(-)
diff --git a/drivers/net/usb/usbnet.c b/drivers/net/usb/usbnet.c
index 80b837c..2013001 100644
--- a/drivers/net/usb/usbnet.c
+++ b/drivers/net/usb/usbnet.c
@@ -282,17 +282,30 @@ int usbnet_change_mtu (struct net_device *net, int new_mtu)
}
EXPORT_SYMBOL_GPL(usbnet_change_mtu);
+/* The caller must hold list->lock */
+static void __usbnet_queue_skb(struct sk_buff_head *list,
+ struct sk_buff *newsk, enum skb_state state)
+{
+ struct skb_data *entry = (struct skb_data *) newsk->cb;
+
+ __skb_queue_tail(list, newsk);
+ entry->state = state;
+}
+
/*-------------------------------------------------------------------------*/
/* some LK 2.4 HCDs oopsed if we freed or resubmitted urbs from
* completion callbacks. 2.5 should have fixed those bugs...
*/
-static void defer_bh(struct usbnet *dev, struct sk_buff *skb, struct sk_buff_head *list)
+static void defer_bh(struct usbnet *dev, struct sk_buff *skb,
+ struct sk_buff_head *list, enum skb_state state)
{
unsigned long flags;
+ struct skb_data *entry = (struct skb_data *) skb->cb;
spin_lock_irqsave(&list->lock, flags);
+ entry->state = state;
__skb_unlink(skb, list);
spin_unlock(&list->lock);
spin_lock(&dev->done.lock);
@@ -340,7 +353,6 @@ static int rx_submit (struct usbnet *dev, struct urb *urb, gfp_t flags)
entry = (struct skb_data *) skb->cb;
entry->urb = urb;
entry->dev = dev;
- entry->state = rx_start;
entry->length = 0;
usb_fill_bulk_urb (urb, dev->udev, dev->in,
@@ -372,7 +384,7 @@ static int rx_submit (struct usbnet *dev, struct urb *urb, gfp_t flags)
tasklet_schedule (&dev->bh);
break;
case 0:
- __skb_queue_tail (&dev->rxq, skb);
+ __usbnet_queue_skb(&dev->rxq, skb, rx_start);
}
} else {
netif_dbg(dev, ifdown, dev->net, "rx: stopped\n");
@@ -423,16 +435,17 @@ static void rx_complete (struct urb *urb)
struct skb_data *entry = (struct skb_data *) skb->cb;
struct usbnet *dev = entry->dev;
int urb_status = urb->status;
+ enum skb_state state;
skb_put (skb, urb->actual_length);
- entry->state = rx_done;
+ state = rx_done;
entry->urb = NULL;
switch (urb_status) {
/* success */
case 0:
if (skb->len < dev->net->hard_header_len) {
- entry->state = rx_cleanup;
+ state = rx_cleanup;
dev->net->stats.rx_errors++;
dev->net->stats.rx_length_errors++;
netif_dbg(dev, rx_err, dev->net,
@@ -471,7 +484,7 @@ static void rx_complete (struct urb *urb)
"rx throttle %d\n", urb_status);
}
block:
- entry->state = rx_cleanup;
+ state = rx_cleanup;
entry->urb = urb;
urb = NULL;
break;
@@ -482,13 +495,13 @@ block:
// FALLTHROUGH
default:
- entry->state = rx_cleanup;
+ state = rx_cleanup;
dev->net->stats.rx_errors++;
netif_dbg(dev, rx_err, dev->net, "rx status %d\n", urb_status);
break;
}
- defer_bh(dev, skb, &dev->rxq);
+ defer_bh(dev, skb, &dev->rxq, state);
if (urb) {
if (netif_running (dev->net) &&
@@ -579,16 +592,23 @@ EXPORT_SYMBOL_GPL(usbnet_purge_paused_rxq);
static int unlink_urbs (struct usbnet *dev, struct sk_buff_head *q)
{
unsigned long flags;
- struct sk_buff *skb, *skbnext;
+ struct sk_buff *skb;
int count = 0;
spin_lock_irqsave (&q->lock, flags);
- skb_queue_walk_safe(q, skb, skbnext) {
+ while (!skb_queue_empty(q)) {
struct skb_data *entry;
struct urb *urb;
int retval;
- entry = (struct skb_data *) skb->cb;
+ skb_queue_walk(q, skb) {
+ entry = (struct skb_data *) skb->cb;
+ if (entry->state != unlink_start)
+ goto found;
+ }
+ break;
+found:
+ entry->state = unlink_start;
urb = entry->urb;
/*
@@ -599,6 +619,10 @@ static int unlink_urbs (struct usbnet *dev, struct sk_buff_head *q)
* handler(include defer_bh).
*/
usb_get_urb(urb);
+
+ /* speedup unlink by blocking resubmit */
+ usb_block_urb(urb);
+
spin_unlock_irqrestore(&q->lock, flags);
// during some PM-driven resume scenarios,
// these (async) unlinks complete immediately
@@ -607,6 +631,7 @@ static int unlink_urbs (struct usbnet *dev, struct sk_buff_head *q)
netdev_dbg(dev->net, "unlink urb err, %d\n", retval);
else
count++;
+ usb_unblock_urb(urb);
usb_put_urb(urb);
spin_lock_irqsave(&q->lock, flags);
}
@@ -1040,8 +1065,7 @@ static void tx_complete (struct urb *urb)
}
usb_autopm_put_interface_async(dev->intf);
- entry->state = tx_done;
- defer_bh(dev, skb, &dev->txq);
+ defer_bh(dev, skb, &dev->txq, tx_done);
}
/*-------------------------------------------------------------------------*/
@@ -1097,7 +1121,6 @@ netdev_tx_t usbnet_start_xmit (struct sk_buff *skb,
entry = (struct skb_data *) skb->cb;
entry->urb = urb;
entry->dev = dev;
- entry->state = tx_start;
entry->length = length;
usb_fill_bulk_urb (urb, dev->udev, dev->out,
@@ -1156,7 +1179,7 @@ netdev_tx_t usbnet_start_xmit (struct sk_buff *skb,
break;
case 0:
net->trans_start = jiffies;
- __skb_queue_tail (&dev->txq, skb);
+ __usbnet_queue_skb(&dev->txq, skb, tx_start);
if (dev->txq.qlen >= TX_QLEN (dev))
netif_stop_queue (net);
}
diff --git a/include/linux/usb/usbnet.h b/include/linux/usb/usbnet.h
index 605b0aa..76f4396 100644
--- a/include/linux/usb/usbnet.h
+++ b/include/linux/usb/usbnet.h
@@ -191,7 +191,8 @@ extern void usbnet_cdc_status(struct usbnet *, struct urb *);
enum skb_state {
illegal = 0,
tx_start, tx_done,
- rx_start, rx_done, rx_cleanup
+ rx_start, rx_done, rx_cleanup,
+ unlink_start
};
struct skb_data { /* skb->cb is one of these */
--
1.7.9.5
--
To unsubscribe from this list: send the line "unsubscribe linux-usb" in
the body of a message to majordomo-u79uwXL29TY76Z2rM5mHXA@public.gmane.org
More majordomo info at http://vger.kernel.org/majordomo-info.html
^ permalink raw reply related
page: next (older) | prev (newer) | latest
- recent:[subjects (threaded)|topics (new)|topics (active)]
This is a public inbox, see mirroring instructions
for how to clone and mirror all data and code used for this inbox