* Re: [PATCHv2 net-next] vxlan: add ttl inherit support
From: Hangbin Liu @ 2018-04-18 2:15 UTC (permalink / raw)
To: David Miller; +Cc: netdev, jbenc, lucien.xin, sbrivio
In-Reply-To: <20180417.151627.1849186462841531455.davem@davemloft.net>
On Tue, Apr 17, 2018 at 03:16:27PM -0400, David Miller wrote:
> From: Hangbin Liu <liuhangbin@gmail.com>
> Date: Tue, 17 Apr 2018 20:52:54 +0800
>
> > Like tos inherit, ttl inherit should also means inherit the inner protocol's
> > ttl values, which actually not implemented in vxlan yet.
> >
> > But we could not treat ttl == 0 as "use the inner TTL", because that would be
> > used also when the "ttl" option is not specified and that would be a behavior
> > change, and breaking real use cases.
> >
> > So add a different attribute IFLA_VXLAN_TTL_INHERIT when "ttl inherit" is
> > specified.
> >
> > ---
> > v2: As suggested by Stefano, clean up function ip_tunnel_get_ttl().
> >
> > Suggested-by: Jiri Benc <jbenc@redhat.com>
> > Signed-off-by: Hangbin Liu <liuhangbin@gmail.com>
>
> I already applied V1 of your patch.
>
> Furthermore, this commit message would cause your signoffs and other tags
> to be removed due to the "---" deliminator.
>
> I generally encourage people to leave the change history text _in_ the
> commit message anyways. It is useful information for the future.
Thanks for the reminding. I will keep this in mind.
Cheers
Hangbin
^ permalink raw reply
* [PATCH] ethtool: Support ETHTOOL_GSTATS2 API.
From: greearb @ 2018-04-18 1:50 UTC (permalink / raw)
To: netdev; +Cc: Ben Greear
From: Ben Greear <greearb@candelatech.com>
This allows users to specify flags to the get-stats
API, potentially saving expensive stats queries when
they are not desired.
Signed-off-by: Ben Greear <greearb@candelatech.com>
---
ethtool-copy.h | 9 +++++++++
ethtool.c | 25 ++++++++++++++++++++-----
2 files changed, 29 insertions(+), 5 deletions(-)
diff --git a/ethtool-copy.h b/ethtool-copy.h
index 8cc61e9..11ce456 100644
--- a/ethtool-copy.h
+++ b/ethtool-copy.h
@@ -1390,11 +1390,20 @@ enum ethtool_fec_config_bits {
#define ETHTOOL_PHY_STUNABLE 0x0000004f /* Set PHY tunable configuration */
#define ETHTOOL_GFECPARAM 0x00000050 /* Get FEC settings */
#define ETHTOOL_SFECPARAM 0x00000051 /* Set FEC settings */
+#define ETHTOOL_GSTATS2 0x00000052 /* get NIC-specific statistics
+ * with ability to specify flags.
+ * See ETHTOOL_GS2* below.
+ */
/* compatibility with older code */
#define SPARC_ETH_GSET ETHTOOL_GSET
#define SPARC_ETH_SSET ETHTOOL_SSET
+/* GSTATS2 flags */
+#define ETHTOOL_GS2_SKIP_NONE (0) /* default is to update all stats */
+#define ETHTOOL_GS2_SKIP_FW (1<<0) /* Skip reading stats that probe firmware,
+ * and thus are slow/expensive.
+ */
/* Link mode bit indices */
enum ethtool_link_mode_bit_indices {
ETHTOOL_LINK_MODE_10baseT_Half_BIT = 0,
diff --git a/ethtool.c b/ethtool.c
index 3289e0f..6a11077 100644
--- a/ethtool.c
+++ b/ethtool.c
@@ -3440,14 +3440,14 @@ static int do_phys_id(struct cmd_context *ctx)
}
static int do_gstats(struct cmd_context *ctx, int cmd, int stringset,
- const char *name)
+ const char *name, u32 flags)
{
struct ethtool_gstrings *strings;
struct ethtool_stats *stats;
unsigned int n_stats, sz_stats, i;
int err;
- if (ctx->argc != 0)
+ if ((ctx->argc != 0) && (flags == ETHTOOL_GS2_SKIP_NONE))
exit_bad_args();
strings = get_stringset(ctx, stringset,
@@ -3475,7 +3475,10 @@ static int do_gstats(struct cmd_context *ctx, int cmd, int stringset,
}
stats->cmd = cmd;
- stats->n_stats = n_stats;
+ if (cmd == ETHTOOL_GSTATS2)
+ stats->n_stats = flags;
+ else
+ stats->n_stats = n_stats;
err = send_ioctl(ctx, stats);
if (err < 0) {
perror("Cannot get stats information");
@@ -3500,12 +3503,22 @@ static int do_gstats(struct cmd_context *ctx, int cmd, int stringset,
static int do_gnicstats(struct cmd_context *ctx)
{
- return do_gstats(ctx, ETHTOOL_GSTATS, ETH_SS_STATS, "NIC");
+ return do_gstats(ctx, ETHTOOL_GSTATS, ETH_SS_STATS, "NIC", ETHTOOL_GS2_SKIP_NONE);
+}
+
+static int do_gnicstats2(struct cmd_context *ctx)
+{
+ u32 flags = ETHTOOL_GS2_SKIP_NONE;
+ if (ctx->argc >= 1)
+ if (strcmp(ctx->argp[0], "nofw") == 0)
+ flags |= ETHTOOL_GS2_SKIP_FW;
+ return do_gstats(ctx, ETHTOOL_GSTATS2, ETH_SS_STATS, "NIC", flags);
}
static int do_gphystats(struct cmd_context *ctx)
{
- return do_gstats(ctx, ETHTOOL_GPHYSTATS, ETH_SS_PHY_STATS, "PHY");
+ return do_gstats(ctx, ETHTOOL_GPHYSTATS, ETH_SS_PHY_STATS, "PHY",
+ ETHTOOL_GS2_SKIP_NONE);
}
static int do_srxntuple(struct cmd_context *ctx,
@@ -5118,6 +5131,8 @@ static const struct option {
{ "-t|--test", 1, do_test, "Execute adapter self test",
" [ online | offline | external_lb ]\n" },
{ "-S|--statistics", 1, do_gnicstats, "Show adapter statistics" },
+ { "-2|--S2", 1, do_gnicstats2, "Show adapter statistics with flags",
+ " [ nofw ]\n" },
{ "--phy-statistics", 1, do_gphystats,
"Show phy statistics" },
{ "-n|-u|--show-nfc|--show-ntuple", 1, do_grxclass,
--
2.4.11
^ permalink raw reply related
* [PATCH 3/3] ath10k: Support ethtool gstats2 API.
From: greearb @ 2018-04-18 1:49 UTC (permalink / raw)
To: netdev; +Cc: linux-wireless, ath10k, Ben Greear
In-Reply-To: <1524016176-3881-1-git-send-email-greearb@candelatech.com>
From: Ben Greear <greearb@candelatech.com>
Skip a firmware stats update when calling
code indicates the stats refresh is not needed.
Signed-off-by: Ben Greear <greearb@candelatech.com>
---
drivers/net/wireless/ath/ath10k/debug.c | 18 +++++++++++++++---
drivers/net/wireless/ath/ath10k/debug.h | 4 ++++
drivers/net/wireless/ath/ath10k/mac.c | 1 +
3 files changed, 20 insertions(+), 3 deletions(-)
diff --git a/drivers/net/wireless/ath/ath10k/debug.c b/drivers/net/wireless/ath/ath10k/debug.c
index bac832c..d559a3f 100644
--- a/drivers/net/wireless/ath/ath10k/debug.c
+++ b/drivers/net/wireless/ath/ath10k/debug.c
@@ -1159,9 +1159,10 @@ int ath10k_debug_get_et_sset_count(struct ieee80211_hw *hw,
return 0;
}
-void ath10k_debug_get_et_stats(struct ieee80211_hw *hw,
- struct ieee80211_vif *vif,
- struct ethtool_stats *stats, u64 *data)
+void ath10k_debug_get_et_stats2(struct ieee80211_hw *hw,
+ struct ieee80211_vif *vif,
+ struct ethtool_stats *stats, u64 *data,
+ u32 flags)
{
struct ath10k *ar = hw->priv;
static const struct ath10k_fw_stats_pdev zero_stats = {};
@@ -1170,6 +1171,9 @@ void ath10k_debug_get_et_stats(struct ieee80211_hw *hw,
mutex_lock(&ar->conf_mutex);
+ if (flags & ETHTOOL_GS2_SKIP_FW)
+ goto skip_query_fw_stats;
+
if (ar->state == ATH10K_STATE_ON) {
ret = ath10k_debug_fw_stats_request(ar);
if (ret) {
@@ -1180,6 +1184,7 @@ void ath10k_debug_get_et_stats(struct ieee80211_hw *hw,
}
}
+skip_query_fw_stats:
pdev_stats = list_first_entry_or_null(&ar->debug.fw_stats.pdevs,
struct ath10k_fw_stats_pdev,
list);
@@ -1244,6 +1249,13 @@ void ath10k_debug_get_et_stats(struct ieee80211_hw *hw,
WARN_ON(i != ATH10K_SSTATS_LEN);
}
+void ath10k_debug_get_et_stats(struct ieee80211_hw *hw,
+ struct ieee80211_vif *vif,
+ struct ethtool_stats *stats, u64 *data)
+{
+ ath10k_debug_get_et_stats2(hw, vif, stats, data, 0);
+}
+
static const struct file_operations fops_fw_dbglog = {
.read = ath10k_read_fw_dbglog,
.write = ath10k_write_fw_dbglog,
diff --git a/drivers/net/wireless/ath/ath10k/debug.h b/drivers/net/wireless/ath/ath10k/debug.h
index 0afca5c..595d964 100644
--- a/drivers/net/wireless/ath/ath10k/debug.h
+++ b/drivers/net/wireless/ath/ath10k/debug.h
@@ -117,6 +117,10 @@ int ath10k_debug_get_et_sset_count(struct ieee80211_hw *hw,
void ath10k_debug_get_et_stats(struct ieee80211_hw *hw,
struct ieee80211_vif *vif,
struct ethtool_stats *stats, u64 *data);
+void ath10k_debug_get_et_stats2(struct ieee80211_hw *hw,
+ struct ieee80211_vif *vif,
+ struct ethtool_stats *stats, u64 *data,
+ u32 level);
static inline u64 ath10k_debug_get_fw_dbglog_mask(struct ath10k *ar)
{
diff --git a/drivers/net/wireless/ath/ath10k/mac.c b/drivers/net/wireless/ath/ath10k/mac.c
index bf05a36..27b793c 100644
--- a/drivers/net/wireless/ath/ath10k/mac.c
+++ b/drivers/net/wireless/ath/ath10k/mac.c
@@ -7734,6 +7734,7 @@ static const struct ieee80211_ops ath10k_ops = {
.ampdu_action = ath10k_ampdu_action,
.get_et_sset_count = ath10k_debug_get_et_sset_count,
.get_et_stats = ath10k_debug_get_et_stats,
+ .get_et_stats2 = ath10k_debug_get_et_stats2,
.get_et_strings = ath10k_debug_get_et_strings,
.add_chanctx = ath10k_mac_op_add_chanctx,
.remove_chanctx = ath10k_mac_op_remove_chanctx,
--
2.4.11
^ permalink raw reply related
* [PATCH 2/3] mac80211: Add support for ethtool gstats2 API.
From: greearb @ 2018-04-18 1:49 UTC (permalink / raw)
To: netdev; +Cc: linux-wireless, ath10k, Ben Greear
In-Reply-To: <1524016176-3881-1-git-send-email-greearb@candelatech.com>
From: Ben Greear <greearb@candelatech.com>
This enables users to request fewer stats to be refreshed
in cases where firmware does not need to be probed.
Signed-off-by: Ben Greear <greearb@candelatech.com>
---
include/net/mac80211.h | 6 ++++++
net/mac80211/driver-ops.h | 9 +++++++--
net/mac80211/ethtool.c | 18 +++++++++++++-----
3 files changed, 26 insertions(+), 7 deletions(-)
diff --git a/include/net/mac80211.h b/include/net/mac80211.h
index d2279b2..4854f33 100644
--- a/include/net/mac80211.h
+++ b/include/net/mac80211.h
@@ -3361,6 +3361,8 @@ enum ieee80211_reconfig_type {
*
* @get_et_stats: Ethtool API to get a set of u64 stats.
*
+ * @get_et_stats2: Ethtool API to get a set of u64 stats, with flags.
+ *
* @get_et_strings: Ethtool API to get a set of strings to describe stats
* and perhaps other supported types of ethtool data-sets.
*
@@ -3692,6 +3694,10 @@ struct ieee80211_ops {
void (*get_et_stats)(struct ieee80211_hw *hw,
struct ieee80211_vif *vif,
struct ethtool_stats *stats, u64 *data);
+ void (*get_et_stats2)(struct ieee80211_hw *hw,
+ struct ieee80211_vif *vif,
+ struct ethtool_stats *stats, u64 *data,
+ u32 flags);
void (*get_et_strings)(struct ieee80211_hw *hw,
struct ieee80211_vif *vif,
u32 sset, u8 *data);
diff --git a/net/mac80211/driver-ops.h b/net/mac80211/driver-ops.h
index 4d82fe7..519d2db 100644
--- a/net/mac80211/driver-ops.h
+++ b/net/mac80211/driver-ops.h
@@ -58,10 +58,15 @@ static inline void drv_get_et_strings(struct ieee80211_sub_if_data *sdata,
static inline void drv_get_et_stats(struct ieee80211_sub_if_data *sdata,
struct ethtool_stats *stats,
- u64 *data)
+ u64 *data, u32 flags)
{
struct ieee80211_local *local = sdata->local;
- if (local->ops->get_et_stats) {
+ if (local->ops->get_et_stats2) {
+ trace_drv_get_et_stats(local);
+ local->ops->get_et_stats2(&local->hw, &sdata->vif, stats, data,
+ flags);
+ trace_drv_return_void(local);
+ } else if (local->ops->get_et_stats) {
trace_drv_get_et_stats(local);
local->ops->get_et_stats(&local->hw, &sdata->vif, stats, data);
trace_drv_return_void(local);
diff --git a/net/mac80211/ethtool.c b/net/mac80211/ethtool.c
index 9cc986d..b67520e 100644
--- a/net/mac80211/ethtool.c
+++ b/net/mac80211/ethtool.c
@@ -61,9 +61,9 @@ static int ieee80211_get_sset_count(struct net_device *dev, int sset)
return rv;
}
-static void ieee80211_get_stats(struct net_device *dev,
- struct ethtool_stats *stats,
- u64 *data)
+static void ieee80211_get_stats2(struct net_device *dev,
+ struct ethtool_stats *stats,
+ u64 *data, u32 flags)
{
struct ieee80211_sub_if_data *sdata = IEEE80211_DEV_TO_SUB_IF(dev);
struct ieee80211_chanctx_conf *chanctx_conf;
@@ -199,7 +199,14 @@ static void ieee80211_get_stats(struct net_device *dev,
if (WARN_ON(i != STA_STATS_LEN))
return;
- drv_get_et_stats(sdata, stats, &(data[STA_STATS_LEN]));
+ drv_get_et_stats(sdata, stats, &data[STA_STATS_LEN], flags);
+}
+
+static void ieee80211_get_stats(struct net_device *dev,
+ struct ethtool_stats *stats,
+ u64 *data)
+{
+ ieee80211_get_stats2(dev, stats, data, 0);
}
static void ieee80211_get_strings(struct net_device *dev, u32 sset, u8 *data)
@@ -211,7 +218,7 @@ static void ieee80211_get_strings(struct net_device *dev, u32 sset, u8 *data)
sz_sta_stats = sizeof(ieee80211_gstrings_sta_stats);
memcpy(data, ieee80211_gstrings_sta_stats, sz_sta_stats);
}
- drv_get_et_strings(sdata, sset, &(data[sz_sta_stats]));
+ drv_get_et_strings(sdata, sset, &data[sz_sta_stats]);
}
static int ieee80211_get_regs_len(struct net_device *dev)
@@ -238,5 +245,6 @@ const struct ethtool_ops ieee80211_ethtool_ops = {
.set_ringparam = ieee80211_set_ringparam,
.get_strings = ieee80211_get_strings,
.get_ethtool_stats = ieee80211_get_stats,
+ .get_ethtool_stats2 = ieee80211_get_stats2,
.get_sset_count = ieee80211_get_sset_count,
};
--
2.4.11
^ permalink raw reply related
* [PATCH 1/3] ethtool: Support ETHTOOL_GSTATS2 command.
From: greearb-my8/4N5VtI7c+919tysfdA @ 2018-04-18 1:49 UTC (permalink / raw)
To: netdev-u79uwXL29TY76Z2rM5mHXA
Cc: linux-wireless-u79uwXL29TY76Z2rM5mHXA,
ath10k-IAPFreCvJWM7uuMidbF8XUB+6BGkLq7r, Ben Greear
From: Ben Greear <greearb-my8/4N5VtI7c+919tysfdA@public.gmane.org>
This is similar to ETHTOOL_GSTATS, but it allows you to specify
flags. These flags can be used by the driver to decrease the
amount of stats refreshed. In particular, this helps with ath10k
since getting the firmware stats can be slow.
Signed-off-by: Ben Greear <greearb-my8/4N5VtI7c+919tysfdA@public.gmane.org>
---
include/linux/ethtool.h | 12 ++++++++++++
include/uapi/linux/ethtool.h | 10 ++++++++++
net/core/ethtool.c | 40 +++++++++++++++++++++++++++++++++++-----
3 files changed, 57 insertions(+), 5 deletions(-)
diff --git a/include/linux/ethtool.h b/include/linux/ethtool.h
index ebe4181..a4aa11f 100644
--- a/include/linux/ethtool.h
+++ b/include/linux/ethtool.h
@@ -243,6 +243,15 @@ bool ethtool_convert_link_mode_to_legacy_u32(u32 *legacy_u32,
* @get_ethtool_stats: Return extended statistics about the device.
* This is only useful if the device maintains statistics not
* included in &struct rtnl_link_stats64.
+ * @get_ethtool_stats2: Return extended statistics about the device.
+ * This is only useful if the device maintains statistics not
+ * included in &struct rtnl_link_stats64.
+ * Takes a flags argument: 0 means all (same as get_ethtool_stats),
+ * 0x1 (ETHTOOL_GS2_SKIP_FW) means skip firmware stats.
+ * Other flags are reserved for now.
+ * Same number of stats will be returned, but some of them might
+ * not be as accurate/refreshed. This is to allow not querying
+ * firmware or other expensive-to-read stats, for instance.
* @begin: Function to be called before any other operation. Returns a
* negative error code or zero.
* @complete: Function to be called after any other operation except
@@ -355,6 +364,9 @@ struct ethtool_ops {
int (*set_phys_id)(struct net_device *, enum ethtool_phys_id_state);
void (*get_ethtool_stats)(struct net_device *,
struct ethtool_stats *, u64 *);
+ void (*get_ethtool_stats2)(struct net_device *dev,
+ struct ethtool_stats *gstats, u64 *data,
+ u32 flags);
int (*begin)(struct net_device *);
void (*complete)(struct net_device *);
u32 (*get_priv_flags)(struct net_device *);
diff --git a/include/uapi/linux/ethtool.h b/include/uapi/linux/ethtool.h
index 4ca65b5..1c74f3e 100644
--- a/include/uapi/linux/ethtool.h
+++ b/include/uapi/linux/ethtool.h
@@ -1396,11 +1396,21 @@ enum ethtool_fec_config_bits {
#define ETHTOOL_PHY_STUNABLE 0x0000004f /* Set PHY tunable configuration */
#define ETHTOOL_GFECPARAM 0x00000050 /* Get FEC settings */
#define ETHTOOL_SFECPARAM 0x00000051 /* Set FEC settings */
+#define ETHTOOL_GSTATS2 0x00000052 /* get NIC-specific statistics
+ * with ability to specify flags.
+ * See ETHTOOL_GS2* below.
+ */
/* compatibility with older code */
#define SPARC_ETH_GSET ETHTOOL_GSET
#define SPARC_ETH_SSET ETHTOOL_SSET
+/* GSTATS2 flags */
+#define ETHTOOL_GS2_SKIP_NONE (0) /* default is to update all stats */
+#define ETHTOOL_GS2_SKIP_FW (1<<0) /* Skip reading stats that probe firmware,
+ * and thus are slow/expensive.
+ */
+
/* Link mode bit indices */
enum ethtool_link_mode_bit_indices {
ETHTOOL_LINK_MODE_10baseT_Half_BIT = 0,
diff --git a/net/core/ethtool.c b/net/core/ethtool.c
index 03416e6..6ec3413 100644
--- a/net/core/ethtool.c
+++ b/net/core/ethtool.c
@@ -1952,16 +1952,14 @@ static int ethtool_phys_id(struct net_device *dev, void __user *useraddr)
return rc;
}
-static int ethtool_get_stats(struct net_device *dev, void __user *useraddr)
+static int _ethtool_get_stats(struct net_device *dev, void __user *useraddr,
+ u32 flags)
{
struct ethtool_stats stats;
const struct ethtool_ops *ops = dev->ethtool_ops;
u64 *data;
int ret, n_stats;
- if (!ops->get_ethtool_stats || !ops->get_sset_count)
- return -EOPNOTSUPP;
-
n_stats = ops->get_sset_count(dev, ETH_SS_STATS);
if (n_stats < 0)
return n_stats;
@@ -1976,7 +1974,10 @@ static int ethtool_get_stats(struct net_device *dev, void __user *useraddr)
if (n_stats && !data)
return -ENOMEM;
- ops->get_ethtool_stats(dev, &stats, data);
+ if (flags != ETHTOOL_GS2_SKIP_NONE)
+ ops->get_ethtool_stats2(dev, &stats, data, flags);
+ else
+ ops->get_ethtool_stats(dev, &stats, data);
ret = -EFAULT;
if (copy_to_user(useraddr, &stats, sizeof(stats)))
@@ -1991,6 +1992,31 @@ static int ethtool_get_stats(struct net_device *dev, void __user *useraddr)
return ret;
}
+static int ethtool_get_stats(struct net_device *dev, void __user *useraddr)
+{
+ const struct ethtool_ops *ops = dev->ethtool_ops;
+
+ if (!ops->get_ethtool_stats || !ops->get_sset_count)
+ return -EOPNOTSUPP;
+ return _ethtool_get_stats(dev, useraddr, ETHTOOL_GS2_SKIP_NONE);
+}
+
+static int ethtool_get_stats2(struct net_device *dev, void __user *useraddr)
+{
+ struct ethtool_stats stats;
+ const struct ethtool_ops *ops = dev->ethtool_ops;
+ u32 flags = 0;
+
+ if (!ops->get_ethtool_stats2 || !ops->get_sset_count)
+ return -EOPNOTSUPP;
+
+ if (copy_from_user(&stats, useraddr, sizeof(stats)))
+ return -EFAULT;
+
+ flags = stats.n_stats;
+ return _ethtool_get_stats(dev, useraddr, flags);
+}
+
static int ethtool_get_phy_stats(struct net_device *dev, void __user *useraddr)
{
struct ethtool_stats stats;
@@ -2632,6 +2658,7 @@ int dev_ethtool(struct net *net, struct ifreq *ifr)
case ETHTOOL_GSSET_INFO:
case ETHTOOL_GSTRINGS:
case ETHTOOL_GSTATS:
+ case ETHTOOL_GSTATS2:
case ETHTOOL_GPHYSTATS:
case ETHTOOL_GTSO:
case ETHTOOL_GPERMADDR:
@@ -2742,6 +2769,9 @@ int dev_ethtool(struct net *net, struct ifreq *ifr)
case ETHTOOL_GSTATS:
rc = ethtool_get_stats(dev, useraddr);
break;
+ case ETHTOOL_GSTATS2:
+ rc = ethtool_get_stats2(dev, useraddr);
+ break;
case ETHTOOL_GPERMADDR:
rc = ethtool_get_perm_addr(dev, useraddr);
break;
--
2.4.11
^ permalink raw reply related
* Re: [PATCH v3 net,stable] tun: fix vlan packet truncation
From: Jason Wang @ 2018-04-18 1:43 UTC (permalink / raw)
To: Bjørn Mork, netdev
In-Reply-To: <20180417204638.11800-1-bjorn@mork.no>
On 2018年04月18日 04:46, Bjørn Mork wrote:
> Bogus trimming in tun_net_xmit() causes truncated vlan packets.
>
> skb->len is correct whether or not skb_vlan_tag_present() is true. There
> is no more reason to adjust the skb length on xmit in this driver than
> any other driver. tun_put_user() adds 4 bytes to the total for tagged
> packets because it transmits the tag inline to userspace. This is
> similar to a nic transmitting the tag inline on the wire.
>
> Reproducing the bug by sending any tagged packet through back-to-back
> connected tap interfaces:
>
> socat TUN,tun-type=tap,iff-up,tun-name=in TUN,tun-type=tap,iff-up,tun-name=out &
> ip link add link in name in.20 type vlan id 20
> ip addr add 10.9.9.9/24 dev in.20
> ip link set in.20 up
> tshark -nxxi in -f arp -c1 2>/dev/null &
> tshark -nxxi out -f arp -c1 2>/dev/null &
> ping -c 1 10.9.9.5 >/dev/null 2>&1
>
> The output from the 'in' and 'out' interfaces are different when the
> bug is present:
>
> Capturing on 'in'
> 0000 ff ff ff ff ff ff 76 cf 76 37 d5 0a 81 00 00 14 ......v.v7......
> 0010 08 06 00 01 08 00 06 04 00 01 76 cf 76 37 d5 0a ..........v.v7..
> 0020 0a 09 09 09 00 00 00 00 00 00 0a 09 09 05 ..............
>
> Capturing on 'out'
> 0000 ff ff ff ff ff ff 76 cf 76 37 d5 0a 81 00 00 14 ......v.v7......
> 0010 08 06 00 01 08 00 06 04 00 01 76 cf 76 37 d5 0a ..........v.v7..
> 0020 0a 09 09 09 00 00 00 00 00 00 ..........
>
> Fixes: aff3d70a07ff ("tun: allow to attach ebpf socket filter")
> Cc: Jason Wang <jasowang@redhat.com>
> Signed-off-by: Bjørn Mork <bjorn@mork.no>
> ---
> v2:
> - Must still call pskb_trim() after running the filter, as pointed out by
> Jason and David. But no need to check if len < 0 anymore, since
> run_ebpf_filter() returns insigned ints.
>
> v3:
> - actually change the len <= 0 test as mentioned above
>
>
> drivers/net/tun.c | 7 +------
> 1 file changed, 1 insertion(+), 6 deletions(-)
>
> diff --git a/drivers/net/tun.c b/drivers/net/tun.c
> index 28583aa0c17d..ef33950a45d9 100644
> --- a/drivers/net/tun.c
> +++ b/drivers/net/tun.c
> @@ -1102,12 +1102,7 @@ static netdev_tx_t tun_net_xmit(struct sk_buff *skb, struct net_device *dev)
> goto drop;
>
> len = run_ebpf_filter(tun, skb, len);
> -
> - /* Trim extra bytes since we may insert vlan proto & TCI
> - * in tun_put_user().
> - */
> - len -= skb_vlan_tag_present(skb) ? sizeof(struct veth) : 0;
> - if (len <= 0 || pskb_trim(skb, len))
> + if (len == 0 || pskb_trim(skb, len))
> goto drop;
>
> if (unlikely(skb_orphan_frags_rx(skb, GFP_ATOMIC)))
Acked-by: Jason Wang <jasowang@redhat.com>
Thanks
^ permalink raw reply
* Re: [PATCH net-next 0/5] virtio-net: Add SCTP checksum offload support
From: Marcelo Ricardo Leitner @ 2018-04-18 1:33 UTC (permalink / raw)
To: Vlad Yasevich
Cc: Vladislav Yasevich, netdev, linux-sctp, virtualization, mst,
jasowang, nhorman, Xin Long
In-Reply-To: <6bc762f6-d6fb-5471-2893-a888cce199f9@redhat.com>
On Tue, Apr 17, 2018 at 04:35:18PM -0400, Vlad Yasevich wrote:
> On 04/02/2018 10:47 AM, Marcelo Ricardo Leitner wrote:
> > On Mon, Apr 02, 2018 at 09:40:01AM -0400, Vladislav Yasevich wrote:
> >> Now that we have SCTP offload capabilities in the kernel, we can add
> >> them to virtio as well. First step is SCTP checksum.
> >
> > Thanks.
> >
> >> As for GSO, the way sctp GSO is currently implemented buys us nothing
> >> in added support to virtio. To add true GSO, would require a lot of
> >> re-work inside of SCTP and would require extensions to the virtio
> >> net header to carry extra sctp data.
> >
> > Can you please elaborate more on this? Is this because SCTP GSO relies
> > on the gso skb format for knowing how to segment it instead of having
> > a list of sizes?
> >
>
> it's mainly because all the true segmentation, placing data into chunks,
> has already happened. All that GSO does is allow for higher bundling
> rate between VMs. If that is all SCTP GSO ever going to do, that fine,
> but the goal is to do real GSO eventually and potentially reduce the
> amount of memory copying we are doing.
> If we do that, any current attempt at GSO in virtio would have to be
> depricated and we'd need GSO2 or something like that.
>
> This is why, after doing the GSO support, I decided not to include it.
Gotcha. I don't think it will ever go further than what we have now.
Placing data into chunks later is not really feasible/wanted,
especially now with stream schedulers and idata chunks. Doesn't seem
worth the hassle... we would have to support things like, "segment
half of this message plus a third of this other one from that other
stream." (in case it's round robin).
Marcelo
^ permalink raw reply
* [Regression] net/phy/micrel.c v4.9.94
From: Chris Ruehl @ 2018-04-18 1:34 UTC (permalink / raw)
To: f.fainelli, netdev
Hello,
I like to get your heads up at a regression introduced in 4.9.94
commitment lead to a kernel ops and make the network unusable on my MX6DL
customized board.
Race condition resume is called on startup and the phy not yet initialized.
[ 7.313366] Unable to handle kernel NULL pointer dereference at virtual
address 00000008
[ 7.321602] pgd = ecfc0000
[ 7.324950] [00000008] *pgd=8e901831
[ 7.328652] Internal error: Oops: 17 [#1] PREEMPT SMP ARM
[ 7.334061] Modules linked in:
[ 7.337146] CPU: 0 PID: 269 Comm: ip Not tainted 4.9.94 #11
[ 7.342725] Hardware name: Freescale i.MX6 Quad/DualLite (Device Tree)
[ 7.349259] task: ece59900 task.stack: ec9ea000
[ 7.353809] PC is at kszphy_config_reset+0x14/0x148
[ 7.358703] LR is at kszphy_resume+0x1c/0x6c
[ 7.362983] pc : [<c056a24c>] lr : [<c056a4fc>] psr: 60030013
[ 7.362983] sp : ec9eb918 ip : ec9eb938 fp : ec9eb934
[ 7.374467] r10: 00000007 r9 : 00000000 r8 : ee693c00
[ 7.379700] r7 : 00000000 r6 : 00000000 r5 : 00000000 r4 : ee6fc000
[ 7.386234] r3 : 00000001 r2 : 00000000 r1 : 00000110 r0 : ee6fc000
[ 7.392768] Flags: nZCv IRQs on FIQs on Mode SVC_32 ISA ARM Segment none
[ 7.399911] Control: 10c5387d Table: 3cfc004a DAC: 00000051
[ 7.405663] Process ip (pid: 269, stack limit = 0xec9ea210)
[ 7.411244] Stack: (0xec9eb918 to 0xec9ec000)
[ 7.415611] b900:
ee6fc000 00000000
[ 7.423800] b920: ee031000 00000000 ec9eb94c ec9eb938 c056a4fc c056a244
ee6fc000 00000000
[ 7.431988] b940: ec9eb97c ec9eb950 c05681e4 c056a4ec 00000007 ee6fc000
ee6fc000 c056ce7c
[ 7.440174] b960: c056ce7c ee031000 ee55c818 00000000 ec9eb99c ec9eb980
c05683cc c0568134
[ 7.448364] b980: 00000007 ec9eba10 ee6fc000 00000007 ec9eb9c4 ec9eb9a0
c0568450 c05683bc
[ 7.456550] b9a0: 00000007 00000005 ee031000 ec9eb9d3 00000200 c1508da4
ec9eba6c ec9eb9c8
[ 7.464736] b9c0: c056ce24 c0568410 00000005 ee03162c 32000001 30383831
652e3030 72656874
[ 7.472921] b9e0: 2d74656e 00000031 000003e8 000000c8 c01732ec c0172adc
000003e8 000000c8
[ 7.481109] ba00: 024000c0 ee55c000 c150e454 024000c0 38383132 2e303030
65687465 74656e72
[ 7.489296] ba20: 303a312d ee000035 ec9eba6c ec9eba38 c0224b50 c0175eb8
ec9eba6c c056eb44
[ 7.497482] ba40: c056bbe0 f0c16000 ee031000 ee55c000 00000200 f0c16000
ee031000 ee55c000
[ 7.505667] ba60: ec9ebaa4 ec9eba70 c056eba4 c056cd1c 00000001 ee03162c
ec9ebaa4 ee031000
[ 7.513855] ba80: 00000000 c09566ec ee031030 00000000 ec9ccd10 ecb39900
ec9ebacc ec9ebaa8
[ 7.522043] baa0: c06ad6e0 c056e92c ec9ebacc ee031000 ee031000 00000001
00001003 00001002
[ 7.530229] bac0: ec9ebaf4 ec9ebad0 c06ad99c c06ad63c 00001002 ee031000
ee031148 00001002
[ 7.538414] bae0: 00000000 00000000 ec9ebb1c ec9ebaf8 c06ada6c c06ad90c
00001002 00000000
[ 7.546601] bb00: ee031000 ec9ebc28 00000000 c09566ec ec9ebb94 ec9ebb20
c06c1034 c06ada58
[ 7.554787] bb20: c0c50df8 2e184000 ec9ebb44 ec9ebb38 c0173528 c0173320
ec9ebbd4 c0e82b6c
[ 7.562972] bb40: 00000000 ece59dc8 ebb4e9d0 c9eae3f3 ece59900 00000003
ece59900 0000005e
[ 7.571157] bb60: c14e30ec c0d1e51c ece59900 00000000 ee031000 ec9ccd00
00000000 00000000
[ 7.579346] bb80: ec9ebb98 00000000 ec9ebd04 ec9ebb98 c06c30cc c06c0d68
ec9ebbc4 00000000
[ 7.587531] bba0: c01758bc ecb39900 c09eb3a0 ec9ccd20 00000000 ec9ccd10
00000001 ece59900
[ 7.595715] bbc0: c01e0e64 00000000 00000000 00000001 ec9ebbfc 00000000
00000000 00000000
[ 7.603900] bbe0: 00000000 00000000 00000000 ffffff00 ec9ebc0c ec9ebc00
c0173528 c0173320
[ 7.612084] bc00: ec9ebc9c ec9ebc10 c01e0e64 c0173520 00000000 0000000e
ece59900 00000096
[ 7.620269] bc20: c14e30ec c0d1e51c 00000000 00000000 00000000 00000000
00000000 00000000
[ 7.628452] bc40: 00000000 00000000 00000000 00000000 00000000 00000000
00000000 00000000
[ 7.636636] bc60: 00000000 00000000 00000000 00000000 00000000 00000000
00000000 00000000
[ 7.644819] bc80: 00000000 00000000 00000000 00000000 00000000 00000000
00000000 00000000
[ 7.653003] bca0: 00000000 00000000 00000000 00000000 00000000 00000000
00000000 00000000
[ 7.661186] bcc0: 00000000 00000000 00000000 00000000 00000000 00000000
c06d3870 00000000
[ 7.669372] bce0: ec9ccd00 ecb39900 c15226e4 00000000 00000000 ecb39900
ec9ebd44 ec9ebd08
[ 7.677556] bd00: c06c343c c06c2bdc c0869c2c c0173520 00000001 00000000
c06c06e4 00000000
[ 7.685741] bd20: 00000000 ec9ccd00 c06c32b8 ecb39900 ecb39900 00000000
ec9ebd64 ec9ebd48
[ 7.693926] bd40: c06d86cc c06c32c4 00000000 ecb39900 00000020 ec970400
ec9ebd7c ec9ebd68
[ 7.702110] bd60: c06c06f4 c06d8630 c06c06c4 ee15f400 ec9ebdac ec9ebd80
c06d802c c06c06d0
[ 7.710294] bd80: ec9ebf50 7fffffff ec970400 ec9ebf48 ec970400 00000000
00000020 00000000
[ 7.718477] bda0: ec9ebe0c ec9ebdb0 c06d84e8 c06d7ec8 0000000c ec9ebe48
0000000c 00000000
[ 7.726661] bdc0: beee97bc 00000008 00000000 ee0cbd80 00000000 0000010d
00000000 00000000
[ 7.734845] bde0: ec9ebe24 ec9ebf48 00000000 eda478c0 00000128 00000000
00000000 ec9ebe28
[ 7.743029] be00: ec9ebe1c ec9ebe10 c068b124 c06d8180 ec9ebf34 ec9ebe20
c068bcac c068b114
[ 7.751213] be20: ec9ebe8c 00000000 c01759cc c01704b0 ec9ebea4 ec9ebe40
c0209960 c01187ac
[ 7.759396] be40: 00000000 00000000 beeed828 00000020 00000000 00000000
600f0113 ec98ce70
[ 7.767580] be60: beee9000 ed7ac714 ece59900 ed7ac6c0 00000817 beee977c
ed7ac714 00000055
[ 7.775764] be80: ec9ebea4 ec9ebe90 00000010 00000000 00000000 ec9ebfb0
ec9ebefc ec9ebea8
[ 7.783948] bea0: c0115b74 c016ec18 00000000 c0d55a61 c025e178 ffffffea
ee022f10 00000000
[ 7.792131] bec0: 00000000 00000000 00000800 00000000 c025ddc0 c0d0a44c
00000817 c0115990
[ 7.800315] bee0: beee977c ec9ebfb0 00054694 beeedec0 ec9ebfac ec9ebf00
c0101368 c011599c
[ 7.808500] bf00: ec9ebf1c ec9ebf10 c025a578 eda478c0 00000000 beee97a4
00000128 c0107ee4
[ 7.816685] bf20: ec9ea000 00000000 ec9ebf94 ec9ebf38 c068ca54 c068bad4
00000000 00000000
[ 7.824868] bf40: 00000000 fffffff7 ec9ebe88 0000000c 00000001 00000000
00000000 ec9ebe50
[ 7.833052] bf60: 00000000 00000001 00000000 00000000 00000000 00000000
ec9ebf94 0000000c
[ 7.841235] bf80: 00000010 beee9790 ec9ebfa4 ec9ebf98 c068ca94 c068ca18
00000000 ec9ebfa8
[ 7.849419] bfa0: c0107d20 c068ca90 0000000c 00000010 00000003 beee97a4
00000000 00000005
[ 7.857604] bfc0: 0000000c 00000010 beee9790 00000128 00000000 00054694
beee97a4 beee97c0
[ 7.865789] bfe0: 00000000 beee9774 00034d1d b6eaaf16 400f0030 00000003
3fffd861 3fffdc61
[ 7.873968] Backtrace:
[ 7.876450] [<c056a238>] (kszphy_config_reset) from [<c056a4fc>]
(kszphy_resume+0x1c/0x6c)
[ 7.884723] r7:00000000 r6:ee031000 r5:00000000 r4:ee6fc000
[ 7.890392] [<c056a4e0>] (kszphy_resume) from [<c05681e4>]
(phy_attach_direct+0xbc/0x1bc)
[ 7.898575] r5:00000000 r4:ee6fc000
[ 7.902158] [<c0568128>] (phy_attach_direct) from [<c05683cc>]
(phy_connect_direct+0x1c/0x54)
[ 7.910691] r10:00000000 r9:ee55c818 r8:ee031000 r7:c056ce7c r6:c056ce7c
r5:ee6fc000
[ 7.918525] r4:ee6fc000 r3:00000007
[ 7.922108] [<c05683b0>] (phy_connect_direct) from [<c0568450>]
(phy_connect+0x4c/0x80)
[ 7.930117] r6:00000007 r5:ee6fc000 r4:ec9eba10 r3:00000007
[ 7.935785] [<c0568404>] (phy_connect) from [<c056ce24>]
(fec_enet_mii_probe+0x114/0x16c)
[ 7.943969] r8:c1508da4 r7:00000200 r6:ec9eb9d3 r5:ee031000 r4:00000005
r3:00000007
[ 7.951720] [<c056cd10>] (fec_enet_mii_probe) from [<c056eba4>]
(fec_enet_open+0x284/0x320)
[ 7.960076] r6:ee55c000 r5:ee031000 r4:f0c16000
[ 7.964704] [<c056e920>] (fec_enet_open) from [<c06ad6e0>]
(__dev_open+0xb0/0x114)
[ 7.972281] r10:ecb39900 r9:ec9ccd10 r8:00000000 r7:ee031030 r6:c09566ec
r5:00000000
[ 7.980113] r4:ee031000
[ 7.982655] [<c06ad630>] (__dev_open) from [<c06ad99c>]
(__dev_change_flags+0x9c/0x14c)
[ 7.990665] r7:00001002 r6:00001003 r5:00000001 r4:ee031000
[ 7.996333] [<c06ad900>] (__dev_change_flags) from [<c06ada6c>]
(dev_change_flags+0x20/0x50)
[ 8.004777] r8:00000000 r7:00000000 r6:00001002 r5:ee031148 r4:ee031000
r3:00001002
[ 8.012533] [<c06ada4c>] (dev_change_flags) from [<c06c1034>]
(do_setlink+0x2d8/0x838)
[ 8.020456] r8:c09566ec r7:00000000 r6:ec9ebc28 r5:ee031000 r4:00000000
r3:00001002
[ 8.028207] [<c06c0d5c>] (do_setlink) from [<c06c30cc>]
(rtnl_newlink+0x4fc/0x6e8)
[ 8.035784] r10:00000000 r9:ec9ebb98 r8:00000000 r7:00000000 r6:ec9ccd00
r5:ee031000
[ 8.043616] r4:00000000
[ 8.046159] [<c06c2bd0>] (rtnl_newlink) from [<c06c343c>]
(rtnetlink_rcv_msg+0x184/0x234)
[ 8.054343] r10:ecb39900 r9:00000000 r8:00000000 r7:c15226e4 r6:ecb39900
r5:ec9ccd00
[ 8.062175] r4:00000000
[ 8.064720] [<c06c32b8>] (rtnetlink_rcv_msg) from [<c06d86cc>]
(netlink_rcv_skb+0xa8/0xc4)
[ 8.072990] r8:00000000 r7:ecb39900 r6:ecb39900 r5:c06c32b8 r4:ec9ccd00
[ 8.079701] [<c06d8624>] (netlink_rcv_skb) from [<c06c06f4>]
(rtnetlink_rcv+0x30/0x38)
[ 8.087622] r6:ec970400 r5:00000020 r4:ecb39900 r3:00000000
[ 8.093291] [<c06c06c4>] (rtnetlink_rcv) from [<c06d802c>]
(netlink_unicast+0x170/0x1f8)
[ 8.101384] r4:ee15f400 r3:c06c06c4
[ 8.104968] [<c06d7ebc>] (netlink_unicast) from [<c06d84e8>]
(netlink_sendmsg+0x374/0x388)
[ 8.113238] r8:00000000 r7:00000020 r6:00000000 r5:ec970400 r4:ec9ebf48
[ 8.119952] [<c06d8174>] (netlink_sendmsg) from [<c068b124>]
(sock_sendmsg+0x1c/0x2c)
[ 8.127789] r10:ec9ebe28 r9:00000000 r8:00000000 r7:00000128 r6:eda478c0
r5:00000000
[ 8.135621] r4:ec9ebf48
[ 8.138167] [<c068b108>] (sock_sendmsg) from [<c068bcac>]
(___sys_sendmsg+0x1e4/0x20c)
[ 8.146095] [<c068bac8>] (___sys_sendmsg) from [<c068ca54>]
(__sys_sendmsg+0x48/0x78)
[ 8.153932] r10:00000000 r9:ec9ea000 r8:c0107ee4 r7:00000128 r6:beee97a4
r5:00000000
[ 8.161764] r4:eda478c0
[ 8.164304] [<c068ca0c>] (__sys_sendmsg) from [<c068ca94>]
(SyS_sendmsg+0x10/0x14)
[ 8.171880] r6:beee9790 r5:00000010 r4:0000000c
[ 8.176510] [<c068ca84>] (SyS_sendmsg) from [<c0107d20>]
(ret_fast_syscall+0x0/0x1c)
[ 8.184261] Code: e92dd8f0 e24cb004 e590628c e1a04000 (e5d63008)
[ 8.192713] ---[ end trace 07c02ee14784bc48 ]---
Kind regards
Chris
--
GTSYS Limited RFID Technology
9/F, Unit E, R07, Kwai Shing Industrial Building Phase 2,
42-46 Tai Lin Pai Road, Kwai Chung, N.T., Hong Kong
Tel (852) 9079 9521
Disclaimer: https://www.gtsys.com.hk/email/classified.html
^ permalink raw reply
* Re:Re: [PATCH net] net: Fix one possible memleak in ip_setup_cork
From: Gao Feng @ 2018-04-18 1:33 UTC (permalink / raw)
To: Eric Dumazet
Cc: davem@davemloft.net, kuznet@ms2.inr.ac.ru, netdev@vger.kernel.org
In-Reply-To: <e6c20036-4b68-560a-636f-f949e483d07a@gmail.com>
At 2018-04-17 05:18:25, "Eric Dumazet" <eric.dumazet@gmail.com> wrote:
>
>
>On 04/16/2018 09:58 AM, David Miller wrote:
>> From: gfree.wind@vip.163.com
>> Date: Mon, 16 Apr 2018 10:16:45 +0800
>>
>>> From: Gao Feng <gfree.wind@vip.163.com>
>>>
>>> It would allocate memory in this function when the cork->opt is NULL. But
>>> the memory isn't freed if failed in the latter rt check, and return error
>>> directly. It causes the memleak if its caller is ip_make_skb which also
>>> doesn't free the cork->opt when meet a error.
>>>
>>> Now move the rt check ahead to avoid the memleak.
>>>
>>> Signed-off-by: Gao Feng <gfree.wind@vip.163.com>
>>
>> Looks good, applied and queued up for -stable.
>>
>> I guess in the other code paths, ip_flush_pending_frames() or similar
>> would clean up the in-sock cork information.
>>
>
>I am not sure ip_make_skb() can be called with a NULL rt.
>
>Patch makes no harm, but does not seem to fix a bug.
>
Thanks Eric.
I just look up current all callers of ip_make_skb and ip_append_data, they check
if the rt is valid ahead. So current codes won't pass one NULL rt to ip_setup_cork indeed.
Then this patch is just as an enhancement, not a fix.
As the programming rule, the function should free the mem which is allocated by itself when
it failed.
Best Regards
Feng
^ permalink raw reply
* Re: [PATCH 04/10] net: ax88796: Add block_input/output hooks to ax_plat_data
From: Finn Thain @ 2018-04-18 1:23 UTC (permalink / raw)
To: Michael Schmitz
Cc: kbuild test robot, kbuild-all, netdev, Linux/m68k,
Michael Karcher, Michael Karcher
In-Reply-To: <CAOmrzkKSmp5phhLYvs14N13tPCuAYCOi-2eBrRqnOgB6+Q6Nyw@mail.gmail.com>
On Wed, 18 Apr 2018, Michael Schmitz wrote:
> I think this is a false positive - we're encouraged to provide the
> full parameter list for functions, so the sreuct sk_buff* can't be
> avoided.
>
I don't think it's a false positive. I think ax88796.h would need to
#include <linux/skbuff.h>.
You may be able to get away with a forward declaration, as in,
struct skbuff;
but I'm not sure about that. I would have to build mach-anubis.c to check.
But why do you need to pass an skbuff pointer here? xs100_block_input()
only accesses skb->data.
BTW, this patch has an unrelated whitespace change.
--
> Cheers,
>
> Michael
>
>
> On Wed, Apr 18, 2018 at 6:46 AM, kbuild test robot <lkp@intel.com> wrote:
> > Hi Michael,
> >
> > I love your patch! Perhaps something to improve:
> >
> > [auto build test WARNING on v4.16]
> > [cannot apply to net-next/master net/master v4.17-rc1 next-20180417]
> > [if your patch is applied to the wrong git tree, please drop us a note to help improve the system]
> >
> > url: https://github.com/0day-ci/linux/commits/Michael-Schmitz/New-network-driver-for-Amiga-X-Surf-100-m68k/20180417-141150
> > config: arm-samsung (attached as .config)
> > compiler: arm-linux-gnueabi-gcc (Debian 7.2.0-11) 7.2.0
> > reproduce:
> > wget https://raw.githubusercontent.com/intel/lkp-tests/master/sbin/make.cross -O ~/bin/make.cross
> > chmod +x ~/bin/make.cross
> > # save the attached .config to linux build tree
> > make.cross ARCH=arm
> >
> > All warnings (new ones prefixed by >>):
> >
> > In file included from arch/arm/mach-s3c24xx/mach-anubis.c:42:0:
> >>> include/net/ax88796.h:35:11: warning: 'struct sk_buff' declared inside parameter list will not be visible outside of this definition or declaration
> > struct sk_buff *skb, int ring_offset);
> > ^~~~~~~
> >
> > vim +35 include/net/ax88796.h
> >
> > 20
> > 21 struct ax_plat_data {
> > 22 unsigned int flags;
> > 23 unsigned char wordlength; /* 1 or 2 */
> > 24 unsigned char dcr_val; /* default value for DCR */
> > 25 unsigned char rcr_val; /* default value for RCR */
> > 26 unsigned char gpoc_val; /* default value for GPOC */
> > 27 u32 *reg_offsets; /* register offsets */
> > 28 u8 *mac_addr; /* MAC addr (only used when
> > 29 AXFLG_MAC_FROMPLATFORM is used */
> > 30
> > 31 /* uses default ax88796 buffer if set to NULL */
> > 32 void (*block_output)(struct net_device *dev, int count,
> > 33 const unsigned char *buf, int star_page);
> > 34 void (*block_input)(struct net_device *dev, int count,
> > > 35 struct sk_buff *skb, int ring_offset);
> > 36 };
> > 37
> >
> > ---
> > 0-DAY kernel test infrastructure Open Source Technology Center
> > https://lists.01.org/pipermail/kbuild-all Intel Corporation
> --
> To unsubscribe from this list: send the line "unsubscribe linux-m68k" 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 v3] net: change the comment of dev_mc_init
From: sunlianwen @ 2018-04-18 1:22 UTC (permalink / raw)
To: netdev
The comment of dev_mc_init() is wrong. which use dev_mc_flush
instead of dev_mc_init.
Signed-off-by: Lianwen Sun <sunlw.fnst@cn.fujitsu.com
---
net/core/dev_addr_lists.c | 2 +-
1 file changed, 1 insertion(+), 1 deletion(-)
diff --git a/net/core/dev_addr_lists.c b/net/core/dev_addr_lists.c
index e3e6a3e2ca22..d884d8f5f0e5 100644
--- a/net/core/dev_addr_lists.c
+++ b/net/core/dev_addr_lists.c
@@ -839,7 +839,7 @@ void dev_mc_flush(struct net_device *dev)
EXPORT_SYMBOL(dev_mc_flush);
/**
- * dev_mc_flush - Init multicast address list
+ * dev_mc_init - Init multicast address list
* @dev: device
*
* Init multicast address list.
--
2.17.0
^ permalink raw reply related
* Re: [PATCH 04/10] net: ax88796: Add block_input/output hooks to ax_plat_data
From: Andrew Lunn @ 2018-04-18 1:19 UTC (permalink / raw)
To: Michael Schmitz
Cc: kbuild test robot, kbuild-all, netdev, Linux/m68k,
Michael Karcher, Michael Karcher
In-Reply-To: <CAOmrzkKSmp5phhLYvs14N13tPCuAYCOi-2eBrRqnOgB6+Q6Nyw@mail.gmail.com>
On Wed, Apr 18, 2018 at 12:53:21PM +1200, Michael Schmitz wrote:
> I think this is a false positive - we're encouraged to provide the
> full parameter list for functions, so the sreuct sk_buff* can't be
> avoided.
Hi Michael
How is <linux/skbuff.h> being included?
You probably want to build using the .config file and see.
Andrew
^ permalink raw reply
* Re: [RFC v2] virtio: support packed ring
From: Tiwei Bie @ 2018-04-18 1:17 UTC (permalink / raw)
To: Michael S. Tsirkin; +Cc: netdev, linux-kernel, virtualization, wexu
In-Reply-To: <20180417184810-mutt-send-email-mst@kernel.org>
On Tue, Apr 17, 2018 at 06:54:51PM +0300, Michael S. Tsirkin wrote:
> On Tue, Apr 17, 2018 at 10:56:26PM +0800, Tiwei Bie wrote:
> > On Tue, Apr 17, 2018 at 05:04:59PM +0300, Michael S. Tsirkin wrote:
> > > On Tue, Apr 17, 2018 at 08:47:16PM +0800, Tiwei Bie wrote:
> > > > On Tue, Apr 17, 2018 at 03:17:41PM +0300, Michael S. Tsirkin wrote:
> > > > > On Tue, Apr 17, 2018 at 10:51:33AM +0800, Tiwei Bie wrote:
> > > > > > On Tue, Apr 17, 2018 at 10:11:58AM +0800, Jason Wang wrote:
> > > > > > > On 2018年04月13日 15:15, Tiwei Bie wrote:
> > > > > > > > On Fri, Apr 13, 2018 at 12:30:24PM +0800, Jason Wang wrote:
> > > > > > > > > On 2018年04月01日 22:12, Tiwei Bie wrote:
> > > > > > [...]
> > > > > > > > > > +static int detach_buf_packed(struct vring_virtqueue *vq, unsigned int head,
> > > > > > > > > > + void **ctx)
> > > > > > > > > > +{
> > > > > > > > > > + struct vring_packed_desc *desc;
> > > > > > > > > > + unsigned int i, j;
> > > > > > > > > > +
> > > > > > > > > > + /* Clear data ptr. */
> > > > > > > > > > + vq->desc_state[head].data = NULL;
> > > > > > > > > > +
> > > > > > > > > > + i = head;
> > > > > > > > > > +
> > > > > > > > > > + for (j = 0; j < vq->desc_state[head].num; j++) {
> > > > > > > > > > + desc = &vq->vring_packed.desc[i];
> > > > > > > > > > + vring_unmap_one_packed(vq, desc);
> > > > > > > > > > + desc->flags = 0x0;
> > > > > > > > > Looks like this is unnecessary.
> > > > > > > > It's safer to zero it. If we don't zero it, after we
> > > > > > > > call virtqueue_detach_unused_buf_packed() which calls
> > > > > > > > this function, the desc is still available to the
> > > > > > > > device.
> > > > > > >
> > > > > > > Well detach_unused_buf_packed() should be called after device is stopped,
> > > > > > > otherwise even if you try to clear, there will still be a window that device
> > > > > > > may use it.
> > > > > >
> > > > > > This is not about whether the device has been stopped or
> > > > > > not. We don't have other places to re-initialize the ring
> > > > > > descriptors and wrap_counter. So they need to be set to
> > > > > > the correct values when doing detach_unused_buf.
> > > > > >
> > > > > > Best regards,
> > > > > > Tiwei Bie
> > > > >
> > > > > find vqs is the time to do it.
> > > >
> > > > The .find_vqs() will call .setup_vq() which will eventually
> > > > call vring_create_virtqueue(). It's a different case. Here
> > > > we're talking about re-initializing the descs and updating
> > > > the wrap counter when detaching the unused descs (In this
> > > > case, split ring just needs to decrease vring.avail->idx).
> > > >
> > > > Best regards,
> > > > Tiwei Bie
> > >
> > > There's no requirement that virtqueue_detach_unused_buf re-initializes
> > > the descs. It happens on cleanup path just before drivers delete the
> > > vqs.
> >
> > Cool, I wasn't aware of it. I saw split ring decrease
> > vring.avail->idx after detaching an unused desc, so I
> > thought detaching unused desc also needs to make sure
> > that the ring state will be updated correspondingly.
>
>
> Hmm. You are right. Seems to be out console driver being out of spec.
> Will have to look at how to fix that :(
>
> It was done here:
>
> Commit b3258ff1d6086bd2b9eeb556844a868ad7d49bc8
> Author: Amit Shah <amit.shah@redhat.com>
> Date: Wed Mar 16 19:12:10 2011 +0530
>
> virtio: Decrement avail idx on buffer detach
>
> When detaching a buffer from a vq, the avail.idx value should be
> decremented as well.
>
> This was noticed by hot-unplugging a virtio console port and then
> plugging in a new one on the same number (re-using the vqs which were
> just 'disowned'). qemu reported
>
> 'Guest moved used index from 0 to 256'
>
> when any IO was attempted on the new port.
>
> CC: stable@kernel.org
> Reported-by: juzhang <juzhang@redhat.com>
> Signed-off-by: Amit Shah <amit.shah@redhat.com>
> Signed-off-by: Rusty Russell <rusty@rustcorp.com.au>
>
> The spec is quite explicit though:
> A driver MUST NOT decrement the available idx on a live virtqueue (ie. there is no way to “unexpose”
> buffers).
>
Hmm.. Got it. Thanks!
Best regards,
Tiwei Bie
>
>
>
>
> > If there is no such requirement, do you think it's OK
> > to remove below two lines:
> >
> > vq->avail_idx_shadow--;
> > vq->vring.avail->idx = cpu_to_virtio16(_vq->vdev, vq->avail_idx_shadow);
> >
> > from virtqueue_detach_unused_buf(), and we could have
> > one generic function to handle both rings:
> >
> > void *virtqueue_detach_unused_buf(struct virtqueue *_vq)
> > {
> > struct vring_virtqueue *vq = to_vvq(_vq);
> > unsigned int num, i;
> > void *buf;
> >
> > START_USE(vq);
> >
> > num = vq->packed ? vq->vring_packed.num : vq->vring.num;
> >
> > for (i = 0; i < num; i++) {
> > if (!vq->desc_state[i].data)
> > continue;
> > /* detach_buf clears data, so grab it now. */
> > buf = vq->desc_state[i].data;
> > detach_buf(vq, i, NULL);
> > END_USE(vq);
> > return buf;
> > }
> > /* That should have freed everything. */
> > BUG_ON(vq->vq.num_free != num);
> >
> > END_USE(vq);
> > return NULL;
> > }
> >
> > Best regards,
> > Tiwei Bie
_______________________________________________
Virtualization mailing list
Virtualization@lists.linux-foundation.org
https://lists.linuxfoundation.org/mailman/listinfo/virtualization
^ permalink raw reply
* [PATCH net-next] ipv6: frags: fix a lockdep false positive
From: Eric Dumazet @ 2018-04-18 1:11 UTC (permalink / raw)
To: David S . Miller; +Cc: netdev, Eric Dumazet, Eric Dumazet
lockdep does not know that the locks used by IPv4 defrag
and IPv6 reassembly units are of different classes.
It complains because of following chains :
1) sch_direct_xmit() (lock txq->_xmit_lock)
dev_hard_start_xmit()
xmit_one()
dev_queue_xmit_nit()
packet_rcv_fanout()
ip_check_defrag()
ip_defrag()
spin_lock() (lock frag queue spinlock)
2) ip6_input_finish()
ipv6_frag_rcv() (lock frag queue spinlock)
ip6_frag_queue()
icmpv6_param_prob() (lock txq->_xmit_lock at some point)
We could add lockdep annotations, but we also can make sure IPv6
calls icmpv6_param_prob() only after the release of the frag queue spinlock,
since this naturally makes frag queue spinlock a leaf in lock hierarchy.
Signed-off-by: Eric Dumazet <edumazet@google.com>
---
Note do David: I chose net-next because of recent changes in net-next,
and because it is a false positive, but can respin for net tree
if you prefer. Thanks !
net/ipv6/reassembly.c | 23 ++++++++++++-----------
1 file changed, 12 insertions(+), 11 deletions(-)
diff --git a/net/ipv6/reassembly.c b/net/ipv6/reassembly.c
index 2cdf3dcf8c2c1f7629154f71a7bd199b2bf05fd1..b939b94e7e91ddae1552f0b6f6a54c42ab180615 100644
--- a/net/ipv6/reassembly.c
+++ b/net/ipv6/reassembly.c
@@ -163,7 +163,8 @@ fq_find(struct net *net, __be32 id, const struct ipv6hdr *hdr, int iif)
}
static int ip6_frag_queue(struct frag_queue *fq, struct sk_buff *skb,
- struct frag_hdr *fhdr, int nhoff)
+ struct frag_hdr *fhdr, int nhoff,
+ u32 *prob_offset)
{
struct sk_buff *prev, *next;
struct net_device *dev;
@@ -179,11 +180,7 @@ static int ip6_frag_queue(struct frag_queue *fq, struct sk_buff *skb,
((u8 *)(fhdr + 1) - (u8 *)(ipv6_hdr(skb) + 1)));
if ((unsigned int)end > IPV6_MAXPLEN) {
- __IP6_INC_STATS(net, __in6_dev_get_safely(skb->dev),
- IPSTATS_MIB_INHDRERRORS);
- icmpv6_param_prob(skb, ICMPV6_HDR_FIELD,
- ((u8 *)&fhdr->frag_off -
- skb_network_header(skb)));
+ *prob_offset = (u8 *)&fhdr->frag_off - skb_network_header(skb);
return -1;
}
@@ -214,10 +211,7 @@ static int ip6_frag_queue(struct frag_queue *fq, struct sk_buff *skb,
/* RFC2460 says always send parameter problem in
* this case. -DaveM
*/
- __IP6_INC_STATS(net, __in6_dev_get_safely(skb->dev),
- IPSTATS_MIB_INHDRERRORS);
- icmpv6_param_prob(skb, ICMPV6_HDR_FIELD,
- offsetof(struct ipv6hdr, payload_len));
+ *prob_offset = offsetof(struct ipv6hdr, payload_len);
return -1;
}
if (end > fq->q.len) {
@@ -519,15 +513,22 @@ static int ipv6_frag_rcv(struct sk_buff *skb)
iif = skb->dev ? skb->dev->ifindex : 0;
fq = fq_find(net, fhdr->identification, hdr, iif);
if (fq) {
+ u32 prob_offset = 0;
int ret;
spin_lock(&fq->q.lock);
fq->iif = iif;
- ret = ip6_frag_queue(fq, skb, fhdr, IP6CB(skb)->nhoff);
+ ret = ip6_frag_queue(fq, skb, fhdr, IP6CB(skb)->nhoff,
+ &prob_offset);
spin_unlock(&fq->q.lock);
inet_frag_put(&fq->q);
+ if (prob_offset) {
+ __IP6_INC_STATS(net, __in6_dev_get_safely(skb->dev),
+ IPSTATS_MIB_INHDRERRORS);
+ icmpv6_param_prob(skb, ICMPV6_HDR_FIELD, prob_offset);
+ }
return ret;
}
--
2.17.0.484.g0c8726318c-goog
^ permalink raw reply related
* Re: [PATCH bpf-next v3 2/8] bpf: add documentation for eBPF helpers (01-11)
From: Alexei Starovoitov @ 2018-04-18 1:04 UTC (permalink / raw)
To: Quentin Monnet; +Cc: daniel, ast, netdev, oss-drivers, linux-doc, linux-man
In-Reply-To: <20180417143438.7018-3-quentin.monnet@netronome.com>
On Tue, Apr 17, 2018 at 03:34:32PM +0100, Quentin Monnet wrote:
> Add documentation for eBPF helper functions to bpf.h user header file.
> This documentation can be parsed with the Python script provided in
> another commit of the patch series, in order to provide a RST document
> that can later be converted into a man page.
>
> The objective is to make the documentation easily understandable and
> accessible to all eBPF developers, including beginners.
>
> This patch contains descriptions for the following helper functions, all
> written by Alexei:
>
> - bpf_map_lookup_elem()
> - bpf_map_update_elem()
> - bpf_map_delete_elem()
> - bpf_probe_read()
> - bpf_ktime_get_ns()
> - bpf_trace_printk()
> - bpf_skb_store_bytes()
> - bpf_l3_csum_replace()
> - bpf_l4_csum_replace()
> - bpf_tail_call()
> - bpf_clone_redirect()
>
> v3:
> - bpf_map_lookup_elem(): Fix description of restrictions for flags
> related to the existence of the entry.
> - bpf_trace_printk(): State that trace_pipe can be configured. Fix
> return value in case an unknown format specifier is met. Add a note on
> kernel log notice when the helper is used. Edit example.
> - bpf_tail_call(): Improve comment on stack inheritance.
> - bpf_clone_redirect(): Improve description of BPF_F_INGRESS flag.
>
> Cc: Alexei Starovoitov <ast@kernel.org>
> Signed-off-by: Quentin Monnet <quentin.monnet@netronome.com>
Acked-by: Alexei Starovoitov <ast@kernel.org>
^ permalink raw reply
* Re: [PATCH v2 bpf-next 0/3] Add missing types to bpftool, libbpf
From: Alexei Starovoitov @ 2018-04-18 0:58 UTC (permalink / raw)
To: Andrey Ignatov; +Cc: ast, daniel, kubakici, quentin.monnet, netdev, kernel-team
In-Reply-To: <cover.1523985784.git.rdna@fb.com>
On Tue, Apr 17, 2018 at 10:28:43AM -0700, Andrey Ignatov wrote:
> v1->v2:
> - add new types to bpftool-cgroup man page;
> - add new types to bash completion for bpftool;
> - don't add types that should not be in bpftool cgroup.
>
> Add support for various BPF prog types and attach types that have been
> added to kernel recently but not to bpftool or libbpf yet.
lgtm. for the set:
Acked-by: Alexei Starovoitov <ast@kernel.org>
^ permalink raw reply
* Re: [PATCH 04/10] net: ax88796: Add block_input/output hooks to ax_plat_data
From: Michael Schmitz @ 2018-04-18 0:53 UTC (permalink / raw)
To: kbuild test robot
Cc: kbuild-all, netdev, Linux/m68k, Michael Karcher, Michael Karcher
In-Reply-To: <201804180104.AHpJjbYg%fengguang.wu@intel.com>
I think this is a false positive - we're encouraged to provide the
full parameter list for functions, so the sreuct sk_buff* can't be
avoided.
Cheers,
Michael
On Wed, Apr 18, 2018 at 6:46 AM, kbuild test robot <lkp@intel.com> wrote:
> Hi Michael,
>
> I love your patch! Perhaps something to improve:
>
> [auto build test WARNING on v4.16]
> [cannot apply to net-next/master net/master v4.17-rc1 next-20180417]
> [if your patch is applied to the wrong git tree, please drop us a note to help improve the system]
>
> url: https://github.com/0day-ci/linux/commits/Michael-Schmitz/New-network-driver-for-Amiga-X-Surf-100-m68k/20180417-141150
> config: arm-samsung (attached as .config)
> compiler: arm-linux-gnueabi-gcc (Debian 7.2.0-11) 7.2.0
> reproduce:
> wget https://raw.githubusercontent.com/intel/lkp-tests/master/sbin/make.cross -O ~/bin/make.cross
> chmod +x ~/bin/make.cross
> # save the attached .config to linux build tree
> make.cross ARCH=arm
>
> All warnings (new ones prefixed by >>):
>
> In file included from arch/arm/mach-s3c24xx/mach-anubis.c:42:0:
>>> include/net/ax88796.h:35:11: warning: 'struct sk_buff' declared inside parameter list will not be visible outside of this definition or declaration
> struct sk_buff *skb, int ring_offset);
> ^~~~~~~
>
> vim +35 include/net/ax88796.h
>
> 20
> 21 struct ax_plat_data {
> 22 unsigned int flags;
> 23 unsigned char wordlength; /* 1 or 2 */
> 24 unsigned char dcr_val; /* default value for DCR */
> 25 unsigned char rcr_val; /* default value for RCR */
> 26 unsigned char gpoc_val; /* default value for GPOC */
> 27 u32 *reg_offsets; /* register offsets */
> 28 u8 *mac_addr; /* MAC addr (only used when
> 29 AXFLG_MAC_FROMPLATFORM is used */
> 30
> 31 /* uses default ax88796 buffer if set to NULL */
> 32 void (*block_output)(struct net_device *dev, int count,
> 33 const unsigned char *buf, int star_page);
> 34 void (*block_input)(struct net_device *dev, int count,
> > 35 struct sk_buff *skb, int ring_offset);
> 36 };
> 37
>
> ---
> 0-DAY kernel test infrastructure Open Source Technology Center
> https://lists.01.org/pipermail/kbuild-all Intel Corporation
^ permalink raw reply
* Re: [PATCH RFC net-next 06/11] udp: add gso support to virtual devices
From: Dimitris Michailidis @ 2018-04-18 0:43 UTC (permalink / raw)
To: Willem de Bruijn; +Cc: netdev, Willem de Bruijn
In-Reply-To: <20180417200059.30154-7-willemdebruijn.kernel@gmail.com>
On Tue, Apr 17, 2018 at 1:00 PM, Willem de Bruijn
<willemdebruijn.kernel@gmail.com> wrote:
> From: Willem de Bruijn <willemb@google.com>
>
> Virtual devices such as tunnels and bonding can handle large packets.
> Only segment packets when reaching a physical or loopback device.
>
> Signed-off-by: Willem de Bruijn <willemb@google.com>
> ---
> include/linux/netdev_features.h | 3 +++
> 1 file changed, 3 insertions(+)
>
> diff --git a/include/linux/netdev_features.h b/include/linux/netdev_features.h
> index 35b79f47a13d..1e4883bb02a7 100644
> --- a/include/linux/netdev_features.h
> +++ b/include/linux/netdev_features.h
> @@ -80,6 +80,7 @@ enum {
>
> NETIF_F_GRO_HW_BIT, /* Hardware Generic receive offload */
> NETIF_F_HW_TLS_RECORD_BIT, /* Offload TLS record */
> + NETIF_F_GSO_UDP_L4_BIT, /* UDP payload GSO (not UFO) */
Please add an entry for the new flag to
net/core/ethtool.c:netdev_features_strings
and a description to Documentation/networking/netdev-features.txt.
>
> /*
> * Add your fresh new feature above and remember to update
> @@ -147,6 +148,7 @@ enum {
> #define NETIF_F_HW_ESP_TX_CSUM __NETIF_F(HW_ESP_TX_CSUM)
> #define NETIF_F_RX_UDP_TUNNEL_PORT __NETIF_F(RX_UDP_TUNNEL_PORT)
> #define NETIF_F_HW_TLS_RECORD __NETIF_F(HW_TLS_RECORD)
> +#define NETIF_F_GSO_UDP_L4 __NETIF_F(GSO_UDP_L4)
>
> #define for_each_netdev_feature(mask_addr, bit) \
> for_each_set_bit(bit, (unsigned long *)mask_addr, NETDEV_FEATURE_COUNT)
> @@ -216,6 +218,7 @@ enum {
> NETIF_F_GSO_GRE_CSUM | \
> NETIF_F_GSO_IPXIP4 | \
> NETIF_F_GSO_IPXIP6 | \
> + NETIF_F_GSO_UDP_L4 | \
> NETIF_F_GSO_UDP_TUNNEL | \
> NETIF_F_GSO_UDP_TUNNEL_CSUM)
>
> --
> 2.17.0.484.g0c8726318c-goog
>
^ permalink raw reply
* Re: [PATCH bpf-next 08/10] [bpf]: make netronome nfp compatible w/ bpf_xdp_adjust_tail
From: Jakub Kicinski @ 2018-04-18 0:40 UTC (permalink / raw)
To: Alexei Starovoitov
Cc: Nikita V. Shirokov, Alexei Starovoitov, Daniel Borkmann, netdev
In-Reply-To: <20180417230828.p745neslgxoy5fus@ast-mbp>
On Tue, 17 Apr 2018 16:08:29 -0700, Alexei Starovoitov wrote:
> On Mon, Apr 16, 2018 at 11:51:29PM -0700, Nikita V. Shirokov wrote:
> > w/ bpf_xdp_adjust_tail helper xdp's data_end pointer could be changed as
> > well (only "decrease" of pointer's location is going to be supported).
> > changing of this pointer will change packet's size.
> > for nfp driver we will just calculate packet's length unconditionally
> >
> > Signed-off-by: Nikita V. Shirokov <tehnerd@tehnerd.com>
> > ---
> > drivers/net/ethernet/netronome/nfp/nfp_net_common.c | 2 +-
> > 1 file changed, 1 insertion(+), 1 deletion(-)
> >
> > diff --git a/drivers/net/ethernet/netronome/nfp/nfp_net_common.c b/drivers/net/ethernet/netronome/nfp/nfp_net_common.c
> > index 1eb6549f2a54..d9111c077699 100644
> > --- a/drivers/net/ethernet/netronome/nfp/nfp_net_common.c
> > +++ b/drivers/net/ethernet/netronome/nfp/nfp_net_common.c
> > @@ -1722,7 +1722,7 @@ static int nfp_net_rx(struct nfp_net_rx_ring *rx_ring, int budget)
> >
> > act = bpf_prog_run_xdp(xdp_prog, &xdp);
> >
> > - pkt_len -= xdp.data - orig_data;
> > + pkt_len = xdp.data_end - xdp.data;
>
> Looks correct, but Jakub please review.
Indeed:
Acked-by: Jakub Kicinski <jakub.kicinski@netronome.com>
Thanks!
^ permalink raw reply
* Re: Repeatable inet6_dump_fib crash in stock 4.12.0-rc4+
From: David Ahern @ 2018-04-18 0:38 UTC (permalink / raw)
To: Ben Greear, Michal Kubecek; +Cc: Cong Wang, Eric Dumazet, netdev
In-Reply-To: <0b938b4e-bfe7-c320-4f61-031ae5870159@candelatech.com>
On 4/17/18 5:29 PM, Ben Greear wrote:
>
> FYI, problem still happens in 4.16. I'm going to re-enable my hack below
> for this kernel as well...I had hopes it might be fixed...
Interesting. I was hoping the same.
>
> BUG: unable to handle kernel NULL pointer dereference at 8
> IP: fib6_walk_continue+0x5b/0x140 [ipv6]
> PGD 80000007dfc0c067 P4D 80000007dfc0c067 PUD 7e66ff067 PMD 0
> Oops: 0000 [#1] PREEMPT SMP PTI
> Modules linked in: nf_conntrack_netlink nf_conntrack nfnetlink
> nf_defrag_ipv4 libcrc32c vrf]
> CPU: 3 PID: 15117 Comm: ip Tainted: G O 4.16.0+ #5
> Hardware name: Iron_Systems,Inc CS-CAD-2U-A02/X10SRL-F, BIOS 2.0b
> 05/02/2017
> RIP: 0010:fib6_walk_continue+0x5b/0x140 [ipv6]
> RSP: 0018:ffffc90008c3bc10 EFLAGS: 00010287
> RAX: ffff88085ac45050 RBX: ffff8807e03008a0 RCX: 0000000000000000
> RDX: 0000000000000000 RSI: ffffc90008c3bc48 RDI: ffffffff8232b240
> RBP: ffff880819167600 R08: 0000000000000008 R09: ffff8807dff10071
> R10: ffffc90008c3bbd0 R11: 0000000000000000 R12: ffff8807e03008a0
> R13: 0000000000000002 R14: ffff8807e05744c8 R15: ffff8807e08ef000
> FS: 00007f2f04342700(0000) GS:ffff88087fcc0000(0000)
> knlGS:0000000000000000
> CS: 0010 DS: 0000 ES: 0000 CR0: 0000000080050033
> CR2: 0000000000000008 CR3: 00000007e0556002 CR4: 00000000003606e0
> DR0: 0000000000000000 DR1: 0000000000000000 DR2: 0000000000000000
> DR3: 0000000000000000 DR6: 00000000fffe0ff0 DR7: 0000000000000400
> Call Trace:
> inet6_dump_fib+0x14b/0x2c0 [ipv6]
> netlink_dump+0x216/0x2a0
> netlink_recvmsg+0x254/0x400
> ? copy_msghdr_from_user+0xb5/0x110
> ___sys_recvmsg+0xe9/0x230
> ? find_held_lock+0x3b/0xb0
> ? __handle_mm_fault+0x617/0x1180
> ? __audit_syscall_entry+0xb3/0x110
> ? __sys_recvmsg+0x39/0x70
> __sys_recvmsg+0x39/0x70
> do_syscall_64+0x63/0x120
> entry_SYSCALL_64_after_hwframe+0x3d/0xa2
> RIP: 0033:0x7f2f03a72030
> RSP: 002b:00007fffab3de508 EFLAGS: 00000246 ORIG_RAX: 000000000000002f
> RAX: ffffffffffffffda RBX: 00007fffab3e641c RCX: 00007f2f03a72030
> RDX: 0000000000000000 RSI: 00007fffab3de570 RDI: 0000000000000004
> RBP: 0000000000000000 R08: 0000000000007e6c R09: 00007fffab3e63a8
> R10: 00007fffab3de5b0 R11: 0000000000000246 R12: 00007fffab3e6608
> R13: 000000000066b460 R14: 0000000000007e6c R15: 0000000000000000
> Code: 85 d2 74 17 f6 40 2a 04 74 11 8b 53 2c 85 d2 0f 84 d7 00 00 00 83
> ea 01 89 53 2c c7 4
> RIP: fib6_walk_continue+0x5b/0x140 [ipv6] RSP: ffffc90008c3bc10
> CR2: 0000000000000008
> ---[ end trace bd03458864eb266c ]---
> Kernel panic - not syncing: Fatal exception in interrupt
> Kernel Offset: disabled
> Rebooting in 10 seconds..
> ACPI MEMORY or I/O RESET_REG.
>
Since you can reproduce, would you mind trying
https://github.com/dsahern/linux.git ipv6/fib6-change-v2
Hopefully these will be committed upstream soon. It changes the game a
bit with the FIB walker. Would be interesting to know if this problem
goes away.
^ permalink raw reply
* [PATCH net-next v2 21/21] net/ipv6: Remove unused code and variables for rt6_info
From: David Ahern @ 2018-04-18 0:33 UTC (permalink / raw)
To: netdev
Cc: davem, idosch, roopa, eric.dumazet, weiwan, kafai, yoshfuji,
David Ahern
In-Reply-To: <20180418003327.19992-1-dsahern@gmail.com>
Drop unneeded elements from rt6_info struct and rearrange layout to
something more relevant for the data path.
Signed-off-by: David Ahern <dsahern@gmail.com>
---
include/net/ip6_fib.h | 60 +++----------------------------------------------
net/ipv6/ip6_fib.c | 22 ------------------
net/ipv6/route.c | 27 ++--------------------
net/ipv6/xfrm6_policy.c | 2 --
4 files changed, 5 insertions(+), 106 deletions(-)
diff --git a/include/net/ip6_fib.h b/include/net/ip6_fib.h
index d41b7bd69fb3..a36116b92100 100644
--- a/include/net/ip6_fib.h
+++ b/include/net/ip6_fib.h
@@ -175,58 +175,20 @@ struct fib6_info {
struct rt6_info {
struct dst_entry dst;
- struct rt6_info __rcu *rt6_next;
struct fib6_info *from;
- /*
- * Tail elements of dst_entry (__refcnt etc.)
- * and these elements (rarely used in hot path) are in
- * the same cache line.
- */
- struct fib6_table *rt6i_table;
- struct fib6_node __rcu *rt6i_node;
-
+ struct rt6key rt6i_dst;
+ struct rt6key rt6i_src;
struct in6_addr rt6i_gateway;
-
- /* Multipath routes:
- * siblings is a list of rt6_info that have the the same metric/weight,
- * destination, but not the same gateway. nsiblings is just a cache
- * to speed up lookup.
- */
- struct list_head rt6i_siblings;
- unsigned int rt6i_nsiblings;
-
- atomic_t rt6i_ref;
-
- /* These are in a separate cache line. */
- struct rt6key rt6i_dst ____cacheline_aligned_in_smp;
+ struct inet6_dev *rt6i_idev;
u32 rt6i_flags;
- struct rt6key rt6i_src;
struct rt6key rt6i_prefsrc;
struct list_head rt6i_uncached;
struct uncached_list *rt6i_uncached_list;
- struct inet6_dev *rt6i_idev;
- struct rt6_info * __percpu *rt6i_pcpu;
- struct rt6_exception_bucket __rcu *rt6i_exception_bucket;
-
- u32 rt6i_metric;
/* more non-fragment space at head required */
unsigned short rt6i_nfheader_len;
- u8 rt6i_protocol;
- u8 fib6_type;
- u8 exception_bucket_flushed:1,
- should_flush:1,
- dst_nocount:1,
- dst_nopolicy:1,
- dst_host:1,
- unused:3;
-
- unsigned long expires;
- struct dst_metrics *fib6_metrics;
-#define fib6_pmtu fib6_metrics->metrics[RTAX_MTU-1]
- struct fib6_nh fib6_nh;
};
#define for_each_fib6_node_rt_rcu(fn) \
@@ -328,8 +290,6 @@ static inline void ip6_rt_put(struct rt6_info *rt)
dst_release(&rt->dst);
}
-void rt6_free_pcpu(struct rt6_info *non_pcpu_rt);
-
struct fib6_info *fib6_info_alloc(gfp_t gfp_flags);
void fib6_info_destroy(struct fib6_info *f6i);
@@ -344,20 +304,6 @@ static inline void fib6_info_release(struct fib6_info *f6i)
fib6_info_destroy(f6i);
}
-static inline void rt6_hold(struct rt6_info *rt)
-{
- atomic_inc(&rt->rt6i_ref);
-}
-
-static inline void rt6_release(struct rt6_info *rt)
-{
- if (atomic_dec_and_test(&rt->rt6i_ref)) {
- rt6_free_pcpu(rt);
- dst_dev_put(&rt->dst);
- dst_release(&rt->dst);
- }
-}
-
enum fib6_walk_state {
#ifdef CONFIG_IPV6_SUBTREES
FWS_S,
diff --git a/net/ipv6/ip6_fib.c b/net/ipv6/ip6_fib.c
index 77cf43b2d858..2ab49b7cac22 100644
--- a/net/ipv6/ip6_fib.c
+++ b/net/ipv6/ip6_fib.c
@@ -240,28 +240,6 @@ static void node_free(struct net *net, struct fib6_node *fn)
net->ipv6.rt6_stats->fib_nodes--;
}
-void rt6_free_pcpu(struct rt6_info *non_pcpu_rt)
-{
- int cpu;
-
- if (!non_pcpu_rt->rt6i_pcpu)
- return;
-
- for_each_possible_cpu(cpu) {
- struct rt6_info **ppcpu_rt;
- struct rt6_info *pcpu_rt;
-
- ppcpu_rt = per_cpu_ptr(non_pcpu_rt->rt6i_pcpu, cpu);
- pcpu_rt = *ppcpu_rt;
- if (pcpu_rt) {
- dst_dev_put(&pcpu_rt->dst);
- dst_release(&pcpu_rt->dst);
- *ppcpu_rt = NULL;
- }
- }
-}
-EXPORT_SYMBOL_GPL(rt6_free_pcpu);
-
static void fib6_free_table(struct fib6_table *table)
{
inetpeer_invalidate_tree(&table->tb6_peers);
diff --git a/net/ipv6/route.c b/net/ipv6/route.c
index 2ccf939e1a20..f9c363327d62 100644
--- a/net/ipv6/route.c
+++ b/net/ipv6/route.c
@@ -302,10 +302,6 @@ static const struct rt6_info ip6_null_entry_template = {
.output = ip6_pkt_discard_out,
},
.rt6i_flags = (RTF_REJECT | RTF_NONEXTHOP),
- .rt6i_protocol = RTPROT_KERNEL,
- .rt6i_metric = ~(u32) 0,
- .rt6i_ref = ATOMIC_INIT(1),
- .fib6_type = RTN_UNREACHABLE,
};
#ifdef CONFIG_IPV6_MULTIPLE_TABLES
@@ -320,10 +316,6 @@ static const struct rt6_info ip6_prohibit_entry_template = {
.output = ip6_pkt_prohibit_out,
},
.rt6i_flags = (RTF_REJECT | RTF_NONEXTHOP),
- .rt6i_protocol = RTPROT_KERNEL,
- .rt6i_metric = ~(u32) 0,
- .rt6i_ref = ATOMIC_INIT(1),
- .fib6_type = RTN_PROHIBIT,
};
static const struct rt6_info ip6_blk_hole_entry_template = {
@@ -336,10 +328,6 @@ static const struct rt6_info ip6_blk_hole_entry_template = {
.output = dst_discard_out,
},
.rt6i_flags = (RTF_REJECT | RTF_NONEXTHOP),
- .rt6i_protocol = RTPROT_KERNEL,
- .rt6i_metric = ~(u32) 0,
- .rt6i_ref = ATOMIC_INIT(1),
- .fib6_type = RTN_BLACKHOLE,
};
#endif
@@ -349,7 +337,6 @@ static void rt6_info_init(struct rt6_info *rt)
struct dst_entry *dst = &rt->dst;
memset(dst + 1, 0, sizeof(*rt) - sizeof(*dst));
- INIT_LIST_HEAD(&rt->rt6i_siblings);
INIT_LIST_HEAD(&rt->rt6i_uncached);
}
@@ -999,12 +986,10 @@ static void ip6_rt_copy_init(struct rt6_info *rt, struct fib6_info *ort)
rt->rt6i_gateway = ort->fib6_nh.nh_gw;
rt->rt6i_flags = ort->rt6i_flags;
rt6_set_from(rt, ort);
- rt->rt6i_metric = ort->rt6i_metric;
#ifdef CONFIG_IPV6_SUBTREES
rt->rt6i_src = ort->rt6i_src;
#endif
rt->rt6i_prefsrc = ort->rt6i_prefsrc;
- rt->rt6i_table = ort->rt6i_table;
rt->dst.lwtstate = lwtstate_get(ort->fib6_nh.nh_lwtstate);
}
@@ -1192,7 +1177,6 @@ static struct rt6_info *ip6_rt_cache_alloc(struct fib6_info *ort,
ip6_rt_copy_init(rt, ort);
rt->rt6i_flags |= RTF_CACHE;
- rt->rt6i_metric = 0;
rt->dst.flags |= DST_HOST;
rt->rt6i_dst.addr = *daddr;
rt->rt6i_dst.plen = 128;
@@ -1225,7 +1209,6 @@ static struct rt6_info *ip6_rt_pcpu_alloc(struct fib6_info *rt)
if (!pcpu_rt)
return NULL;
ip6_rt_copy_init(pcpu_rt, rt);
- pcpu_rt->rt6i_protocol = rt->rt6i_protocol;
pcpu_rt->rt6i_flags |= RTF_PCPU;
return pcpu_rt;
}
@@ -1279,9 +1262,8 @@ static void rt6_remove_exception(struct rt6_exception_bucket *bucket,
return;
net = dev_net(rt6_ex->rt6i->dst.dev);
- rt6_ex->rt6i->rt6i_node = NULL;
hlist_del_rcu(&rt6_ex->hlist);
- ip6_rt_put(rt6_ex->rt6i);
+ dst_release(&rt6_ex->rt6i->dst);
kfree_rcu(rt6_ex, rcu);
WARN_ON_ONCE(!bucket->depth);
bucket->depth--;
@@ -1463,8 +1445,6 @@ static int rt6_insert_exception(struct rt6_info *nrt,
}
rt6_ex->rt6i = nrt;
rt6_ex->stamp = jiffies;
- atomic_inc(&nrt->rt6i_ref);
- nrt->rt6i_node = ort->rt6i_node;
hlist_add_head_rcu(&rt6_ex->hlist, &bucket->chain);
bucket->depth++;
net->ipv6.rt6_stats->fib_rt_cache++;
@@ -2122,7 +2102,6 @@ struct dst_entry *ip6_blackhole_route(struct net *net, struct dst_entry *dst_ori
rt->rt6i_idev = in6_dev_get(loopback_dev);
rt->rt6i_gateway = ort->rt6i_gateway;
rt->rt6i_flags = ort->rt6i_flags & ~RTF_PCPU;
- rt->rt6i_metric = 0;
memcpy(&rt->rt6i_dst, &ort->rt6i_dst, sizeof(struct rt6key));
#ifdef CONFIG_IPV6_SUBTREES
@@ -2247,8 +2226,7 @@ static void rt6_do_update_pmtu(struct rt6_info *rt, u32 mtu)
static bool rt6_cache_allowed_for_pmtu(const struct rt6_info *rt)
{
return !(rt->rt6i_flags & RTF_CACHE) &&
- (rt->rt6i_flags & RTF_PCPU ||
- rcu_access_pointer(rt->rt6i_node));
+ (rt->rt6i_flags & RTF_PCPU || rt->from);
}
static void __ip6_rt_update_pmtu(struct dst_entry *dst, const struct sock *sk,
@@ -3313,7 +3291,6 @@ static void rt6_do_redirect(struct dst_entry *dst, struct sock *sk, struct sk_bu
if (on_link)
nrt->rt6i_flags &= ~RTF_GATEWAY;
- nrt->rt6i_protocol = RTPROT_REDIRECT;
nrt->rt6i_gateway = *(struct in6_addr *)neigh->primary_key;
/* No need to remove rt from the exception table if rt is
diff --git a/net/ipv6/xfrm6_policy.c b/net/ipv6/xfrm6_policy.c
index 416fe67271a9..2cff209d0fc1 100644
--- a/net/ipv6/xfrm6_policy.c
+++ b/net/ipv6/xfrm6_policy.c
@@ -107,8 +107,6 @@ static int xfrm6_fill_dst(struct xfrm_dst *xdst, struct net_device *dev,
* it was magically lost, so this code needs audit */
xdst->u.rt6.rt6i_flags = rt->rt6i_flags & (RTF_ANYCAST |
RTF_LOCAL);
- xdst->u.rt6.rt6i_metric = rt->rt6i_metric;
- xdst->u.rt6.rt6i_node = rt->rt6i_node;
xdst->route_cookie = rt6_get_cookie(rt);
xdst->u.rt6.rt6i_gateway = rt->rt6i_gateway;
xdst->u.rt6.rt6i_dst = rt->rt6i_dst;
--
2.11.0
^ permalink raw reply related
* [PATCH net-next v2 20/21] net/ipv6: Flip FIB entries to fib6_info
From: David Ahern @ 2018-04-18 0:33 UTC (permalink / raw)
To: netdev
Cc: davem, idosch, roopa, eric.dumazet, weiwan, kafai, yoshfuji,
David Ahern
In-Reply-To: <20180418003327.19992-1-dsahern@gmail.com>
Convert all code paths referencing a FIB entry from
rt6_info to fib6_info.
Signed-off-by: David Ahern <dsahern@gmail.com>
---
.../net/ethernet/mellanox/mlxsw/spectrum_router.c | 64 ++---
include/net/if_inet6.h | 4 +-
include/net/ip6_fib.h | 42 ++--
include/net/ip6_route.h | 28 +--
include/net/netns/ipv6.h | 2 +-
net/ipv6/addrconf.c | 20 +-
net/ipv6/anycast.c | 4 +-
net/ipv6/ip6_fib.c | 116 ++++-----
net/ipv6/ndisc.c | 2 +-
net/ipv6/route.c | 259 +++++++++++----------
10 files changed, 271 insertions(+), 270 deletions(-)
diff --git a/drivers/net/ethernet/mellanox/mlxsw/spectrum_router.c b/drivers/net/ethernet/mellanox/mlxsw/spectrum_router.c
index d995a0b52d7c..b85b15851841 100644
--- a/drivers/net/ethernet/mellanox/mlxsw/spectrum_router.c
+++ b/drivers/net/ethernet/mellanox/mlxsw/spectrum_router.c
@@ -442,7 +442,7 @@ struct mlxsw_sp_fib6_entry {
struct mlxsw_sp_rt6 {
struct list_head list;
- struct rt6_info *rt;
+ struct fib6_info *rt;
};
struct mlxsw_sp_lpm_tree {
@@ -3834,7 +3834,7 @@ mlxsw_sp_rt6_nexthop(struct mlxsw_sp_nexthop_group *nh_grp,
for (i = 0; i < nh_grp->count; i++) {
struct mlxsw_sp_nexthop *nh = &nh_grp->nexthops[i];
- struct rt6_info *rt = mlxsw_sp_rt6->rt;
+ struct fib6_info *rt = mlxsw_sp_rt6->rt;
if (nh->rif && nh->rif->dev == rt->fib6_nh.nh_dev &&
ipv6_addr_equal((const struct in6_addr *) &nh->gw_addr,
@@ -3920,7 +3920,7 @@ mlxsw_sp_fib6_entry_offload_unset(struct mlxsw_sp_fib_entry *fib_entry)
fib6_entry = container_of(fib_entry, struct mlxsw_sp_fib6_entry,
common);
list_for_each_entry(mlxsw_sp_rt6, &fib6_entry->rt6_list, list) {
- struct rt6_info *rt = mlxsw_sp_rt6->rt;
+ struct fib6_info *rt = mlxsw_sp_rt6->rt;
rt->fib6_nh.nh_flags &= ~RTNH_F_OFFLOAD;
}
@@ -4699,7 +4699,7 @@ static void mlxsw_sp_router_fib4_del(struct mlxsw_sp *mlxsw_sp,
mlxsw_sp_fib_node_put(mlxsw_sp, fib_node);
}
-static bool mlxsw_sp_fib6_rt_should_ignore(const struct rt6_info *rt)
+static bool mlxsw_sp_fib6_rt_should_ignore(const struct fib6_info *rt)
{
/* Packets with link-local destination IP arriving to the router
* are trapped to the CPU, so no need to program specific routes
@@ -4721,7 +4721,7 @@ static bool mlxsw_sp_fib6_rt_should_ignore(const struct rt6_info *rt)
return false;
}
-static struct mlxsw_sp_rt6 *mlxsw_sp_rt6_create(struct rt6_info *rt)
+static struct mlxsw_sp_rt6 *mlxsw_sp_rt6_create(struct fib6_info *rt)
{
struct mlxsw_sp_rt6 *mlxsw_sp_rt6;
@@ -4734,18 +4734,18 @@ static struct mlxsw_sp_rt6 *mlxsw_sp_rt6_create(struct rt6_info *rt)
* memory.
*/
mlxsw_sp_rt6->rt = rt;
- rt6_hold(rt);
+ fib6_info_hold(rt);
return mlxsw_sp_rt6;
}
#if IS_ENABLED(CONFIG_IPV6)
-static void mlxsw_sp_rt6_release(struct rt6_info *rt)
+static void mlxsw_sp_rt6_release(struct fib6_info *rt)
{
- rt6_release(rt);
+ fib6_info_release(rt);
}
#else
-static void mlxsw_sp_rt6_release(struct rt6_info *rt)
+static void mlxsw_sp_rt6_release(struct fib6_info *rt)
{
}
#endif
@@ -4756,13 +4756,13 @@ static void mlxsw_sp_rt6_destroy(struct mlxsw_sp_rt6 *mlxsw_sp_rt6)
kfree(mlxsw_sp_rt6);
}
-static bool mlxsw_sp_fib6_rt_can_mp(const struct rt6_info *rt)
+static bool mlxsw_sp_fib6_rt_can_mp(const struct fib6_info *rt)
{
/* RTF_CACHE routes are ignored */
return (rt->rt6i_flags & (RTF_GATEWAY | RTF_ADDRCONF)) == RTF_GATEWAY;
}
-static struct rt6_info *
+static struct fib6_info *
mlxsw_sp_fib6_entry_rt(const struct mlxsw_sp_fib6_entry *fib6_entry)
{
return list_first_entry(&fib6_entry->rt6_list, struct mlxsw_sp_rt6,
@@ -4771,7 +4771,7 @@ mlxsw_sp_fib6_entry_rt(const struct mlxsw_sp_fib6_entry *fib6_entry)
static struct mlxsw_sp_fib6_entry *
mlxsw_sp_fib6_node_mp_entry_find(const struct mlxsw_sp_fib_node *fib_node,
- const struct rt6_info *nrt, bool replace)
+ const struct fib6_info *nrt, bool replace)
{
struct mlxsw_sp_fib6_entry *fib6_entry;
@@ -4779,7 +4779,7 @@ mlxsw_sp_fib6_node_mp_entry_find(const struct mlxsw_sp_fib_node *fib_node,
return NULL;
list_for_each_entry(fib6_entry, &fib_node->entry_list, common.list) {
- struct rt6_info *rt = mlxsw_sp_fib6_entry_rt(fib6_entry);
+ struct fib6_info *rt = mlxsw_sp_fib6_entry_rt(fib6_entry);
/* RT6_TABLE_LOCAL and RT6_TABLE_MAIN share the same
* virtual router.
@@ -4802,7 +4802,7 @@ mlxsw_sp_fib6_node_mp_entry_find(const struct mlxsw_sp_fib_node *fib_node,
static struct mlxsw_sp_rt6 *
mlxsw_sp_fib6_entry_rt_find(const struct mlxsw_sp_fib6_entry *fib6_entry,
- const struct rt6_info *rt)
+ const struct fib6_info *rt)
{
struct mlxsw_sp_rt6 *mlxsw_sp_rt6;
@@ -4815,7 +4815,7 @@ mlxsw_sp_fib6_entry_rt_find(const struct mlxsw_sp_fib6_entry *fib6_entry,
}
static bool mlxsw_sp_nexthop6_ipip_type(const struct mlxsw_sp *mlxsw_sp,
- const struct rt6_info *rt,
+ const struct fib6_info *rt,
enum mlxsw_sp_ipip_type *ret)
{
return rt->fib6_nh.nh_dev &&
@@ -4825,7 +4825,7 @@ static bool mlxsw_sp_nexthop6_ipip_type(const struct mlxsw_sp *mlxsw_sp,
static int mlxsw_sp_nexthop6_type_init(struct mlxsw_sp *mlxsw_sp,
struct mlxsw_sp_nexthop_group *nh_grp,
struct mlxsw_sp_nexthop *nh,
- const struct rt6_info *rt)
+ const struct fib6_info *rt)
{
const struct mlxsw_sp_ipip_ops *ipip_ops;
struct mlxsw_sp_ipip_entry *ipip_entry;
@@ -4870,7 +4870,7 @@ static void mlxsw_sp_nexthop6_type_fini(struct mlxsw_sp *mlxsw_sp,
static int mlxsw_sp_nexthop6_init(struct mlxsw_sp *mlxsw_sp,
struct mlxsw_sp_nexthop_group *nh_grp,
struct mlxsw_sp_nexthop *nh,
- const struct rt6_info *rt)
+ const struct fib6_info *rt)
{
struct net_device *dev = rt->fib6_nh.nh_dev;
@@ -4897,7 +4897,7 @@ static void mlxsw_sp_nexthop6_fini(struct mlxsw_sp *mlxsw_sp,
}
static bool mlxsw_sp_rt6_is_gateway(const struct mlxsw_sp *mlxsw_sp,
- const struct rt6_info *rt)
+ const struct fib6_info *rt)
{
return rt->rt6i_flags & RTF_GATEWAY ||
mlxsw_sp_nexthop6_ipip_type(mlxsw_sp, rt, NULL);
@@ -4928,7 +4928,7 @@ mlxsw_sp_nexthop6_group_create(struct mlxsw_sp *mlxsw_sp,
nh_grp->gateway = mlxsw_sp_rt6_is_gateway(mlxsw_sp, mlxsw_sp_rt6->rt);
nh_grp->count = fib6_entry->nrt6;
for (i = 0; i < nh_grp->count; i++) {
- struct rt6_info *rt = mlxsw_sp_rt6->rt;
+ struct fib6_info *rt = mlxsw_sp_rt6->rt;
nh = &nh_grp->nexthops[i];
err = mlxsw_sp_nexthop6_init(mlxsw_sp, nh_grp, nh, rt);
@@ -5040,7 +5040,7 @@ mlxsw_sp_nexthop6_group_update(struct mlxsw_sp *mlxsw_sp,
static int
mlxsw_sp_fib6_entry_nexthop_add(struct mlxsw_sp *mlxsw_sp,
struct mlxsw_sp_fib6_entry *fib6_entry,
- struct rt6_info *rt)
+ struct fib6_info *rt)
{
struct mlxsw_sp_rt6 *mlxsw_sp_rt6;
int err;
@@ -5068,7 +5068,7 @@ mlxsw_sp_fib6_entry_nexthop_add(struct mlxsw_sp *mlxsw_sp,
static void
mlxsw_sp_fib6_entry_nexthop_del(struct mlxsw_sp *mlxsw_sp,
struct mlxsw_sp_fib6_entry *fib6_entry,
- struct rt6_info *rt)
+ struct fib6_info *rt)
{
struct mlxsw_sp_rt6 *mlxsw_sp_rt6;
@@ -5084,7 +5084,7 @@ mlxsw_sp_fib6_entry_nexthop_del(struct mlxsw_sp *mlxsw_sp,
static void mlxsw_sp_fib6_entry_type_set(struct mlxsw_sp *mlxsw_sp,
struct mlxsw_sp_fib_entry *fib_entry,
- const struct rt6_info *rt)
+ const struct fib6_info *rt)
{
/* Packets hitting RTF_REJECT routes need to be discarded by the
* stack. We can rely on their destination device not having a
@@ -5118,7 +5118,7 @@ mlxsw_sp_fib6_entry_rt_destroy_all(struct mlxsw_sp_fib6_entry *fib6_entry)
static struct mlxsw_sp_fib6_entry *
mlxsw_sp_fib6_entry_create(struct mlxsw_sp *mlxsw_sp,
struct mlxsw_sp_fib_node *fib_node,
- struct rt6_info *rt)
+ struct fib6_info *rt)
{
struct mlxsw_sp_fib6_entry *fib6_entry;
struct mlxsw_sp_fib_entry *fib_entry;
@@ -5168,12 +5168,12 @@ static void mlxsw_sp_fib6_entry_destroy(struct mlxsw_sp *mlxsw_sp,
static struct mlxsw_sp_fib6_entry *
mlxsw_sp_fib6_node_entry_find(const struct mlxsw_sp_fib_node *fib_node,
- const struct rt6_info *nrt, bool replace)
+ const struct fib6_info *nrt, bool replace)
{
struct mlxsw_sp_fib6_entry *fib6_entry, *fallback = NULL;
list_for_each_entry(fib6_entry, &fib_node->entry_list, common.list) {
- struct rt6_info *rt = mlxsw_sp_fib6_entry_rt(fib6_entry);
+ struct fib6_info *rt = mlxsw_sp_fib6_entry_rt(fib6_entry);
if (rt->rt6i_table->tb6_id > nrt->rt6i_table->tb6_id)
continue;
@@ -5198,7 +5198,7 @@ mlxsw_sp_fib6_node_list_insert(struct mlxsw_sp_fib6_entry *new6_entry,
bool replace)
{
struct mlxsw_sp_fib_node *fib_node = new6_entry->common.fib_node;
- struct rt6_info *nrt = mlxsw_sp_fib6_entry_rt(new6_entry);
+ struct fib6_info *nrt = mlxsw_sp_fib6_entry_rt(new6_entry);
struct mlxsw_sp_fib6_entry *fib6_entry;
fib6_entry = mlxsw_sp_fib6_node_entry_find(fib_node, nrt, replace);
@@ -5213,7 +5213,7 @@ mlxsw_sp_fib6_node_list_insert(struct mlxsw_sp_fib6_entry *new6_entry,
struct mlxsw_sp_fib6_entry *last;
list_for_each_entry(last, &fib_node->entry_list, common.list) {
- struct rt6_info *rt = mlxsw_sp_fib6_entry_rt(last);
+ struct fib6_info *rt = mlxsw_sp_fib6_entry_rt(last);
if (nrt->rt6i_table->tb6_id > rt->rt6i_table->tb6_id)
break;
@@ -5268,7 +5268,7 @@ mlxsw_sp_fib6_node_entry_unlink(struct mlxsw_sp *mlxsw_sp,
static struct mlxsw_sp_fib6_entry *
mlxsw_sp_fib6_entry_lookup(struct mlxsw_sp *mlxsw_sp,
- const struct rt6_info *rt)
+ const struct fib6_info *rt)
{
struct mlxsw_sp_fib6_entry *fib6_entry;
struct mlxsw_sp_fib_node *fib_node;
@@ -5287,7 +5287,7 @@ mlxsw_sp_fib6_entry_lookup(struct mlxsw_sp *mlxsw_sp,
return NULL;
list_for_each_entry(fib6_entry, &fib_node->entry_list, common.list) {
- struct rt6_info *iter_rt = mlxsw_sp_fib6_entry_rt(fib6_entry);
+ struct fib6_info *iter_rt = mlxsw_sp_fib6_entry_rt(fib6_entry);
if (rt->rt6i_table->tb6_id == iter_rt->rt6i_table->tb6_id &&
rt->rt6i_metric == iter_rt->rt6i_metric &&
@@ -5316,7 +5316,7 @@ static void mlxsw_sp_fib6_entry_replace(struct mlxsw_sp *mlxsw_sp,
}
static int mlxsw_sp_router_fib6_add(struct mlxsw_sp *mlxsw_sp,
- struct rt6_info *rt, bool replace)
+ struct fib6_info *rt, bool replace)
{
struct mlxsw_sp_fib6_entry *fib6_entry;
struct mlxsw_sp_fib_node *fib_node;
@@ -5373,7 +5373,7 @@ static int mlxsw_sp_router_fib6_add(struct mlxsw_sp *mlxsw_sp,
}
static void mlxsw_sp_router_fib6_del(struct mlxsw_sp *mlxsw_sp,
- struct rt6_info *rt)
+ struct fib6_info *rt)
{
struct mlxsw_sp_fib6_entry *fib6_entry;
struct mlxsw_sp_fib_node *fib_node;
@@ -5836,7 +5836,7 @@ static void mlxsw_sp_router_fib6_event(struct mlxsw_sp_fib_event_work *fib_work,
fen6_info = container_of(info, struct fib6_entry_notifier_info,
info);
fib_work->fen6_info = *fen6_info;
- rt6_hold(fib_work->fen6_info.rt);
+ fib6_info_hold(fib_work->fen6_info.rt);
break;
}
}
diff --git a/include/net/if_inet6.h b/include/net/if_inet6.h
index d4088d1a688d..d6089b2e64fe 100644
--- a/include/net/if_inet6.h
+++ b/include/net/if_inet6.h
@@ -64,7 +64,7 @@ struct inet6_ifaddr {
struct delayed_work dad_work;
struct inet6_dev *idev;
- struct rt6_info *rt;
+ struct fib6_info *rt;
struct hlist_node addr_lst;
struct list_head if_list;
@@ -144,7 +144,7 @@ struct ipv6_ac_socklist {
struct ifacaddr6 {
struct in6_addr aca_addr;
struct inet6_dev *aca_idev;
- struct rt6_info *aca_rt;
+ struct fib6_info *aca_rt;
struct ifacaddr6 *aca_next;
int aca_users;
refcount_t aca_refcnt;
diff --git a/include/net/ip6_fib.h b/include/net/ip6_fib.h
index 6c3d92bb3459..d41b7bd69fb3 100644
--- a/include/net/ip6_fib.h
+++ b/include/net/ip6_fib.h
@@ -75,12 +75,12 @@ struct fib6_node {
#ifdef CONFIG_IPV6_SUBTREES
struct fib6_node __rcu *subtree;
#endif
- struct rt6_info __rcu *leaf;
+ struct fib6_info __rcu *leaf;
__u16 fn_bit; /* bit key */
__u16 fn_flags;
int fn_sernum;
- struct rt6_info __rcu *rr_ptr;
+ struct fib6_info __rcu *rr_ptr;
struct rcu_head rcu;
};
@@ -176,7 +176,7 @@ struct fib6_info {
struct rt6_info {
struct dst_entry dst;
struct rt6_info __rcu *rt6_next;
- struct rt6_info *from;
+ struct fib6_info *from;
/*
* Tail elements of dst_entry (__refcnt etc.)
@@ -242,20 +242,20 @@ static inline struct inet6_dev *ip6_dst_idev(struct dst_entry *dst)
return ((struct rt6_info *)dst)->rt6i_idev;
}
-static inline void fib6_clean_expires(struct rt6_info *f6i)
+static inline void fib6_clean_expires(struct fib6_info *f6i)
{
f6i->rt6i_flags &= ~RTF_EXPIRES;
f6i->expires = 0;
}
-static inline void fib6_set_expires(struct rt6_info *f6i,
+static inline void fib6_set_expires(struct fib6_info *f6i,
unsigned long expires)
{
f6i->expires = expires;
f6i->rt6i_flags |= RTF_EXPIRES;
}
-static inline bool fib6_check_expired(const struct rt6_info *f6i)
+static inline bool fib6_check_expired(const struct fib6_info *f6i)
{
if (f6i->rt6i_flags & RTF_EXPIRES)
return time_after(jiffies, f6i->expires);
@@ -288,7 +288,7 @@ static inline void rt6_update_expires(struct rt6_info *rt0, int timeout)
* Return true if we can get cookie safely
* Return false if not
*/
-static inline bool rt6_get_cookie_safe(const struct rt6_info *rt,
+static inline bool rt6_get_cookie_safe(const struct fib6_info *rt,
u32 *cookie)
{
struct fib6_node *fn;
@@ -330,15 +330,15 @@ static inline void ip6_rt_put(struct rt6_info *rt)
void rt6_free_pcpu(struct rt6_info *non_pcpu_rt);
-struct rt6_info *fib6_info_alloc(gfp_t gfp_flags);
-void fib6_info_destroy(struct rt6_info *f6i);
+struct fib6_info *fib6_info_alloc(gfp_t gfp_flags);
+void fib6_info_destroy(struct fib6_info *f6i);
-static inline void fib6_info_hold(struct rt6_info *f6i)
+static inline void fib6_info_hold(struct fib6_info *f6i)
{
atomic_inc(&f6i->rt6i_ref);
}
-static inline void fib6_info_release(struct rt6_info *f6i)
+static inline void fib6_info_release(struct fib6_info *f6i)
{
if (f6i && atomic_dec_and_test(&f6i->rt6i_ref))
fib6_info_destroy(f6i);
@@ -371,7 +371,7 @@ enum fib6_walk_state {
struct fib6_walker {
struct list_head lh;
struct fib6_node *root, *node;
- struct rt6_info *leaf;
+ struct fib6_info *leaf;
enum fib6_walk_state state;
unsigned int skip;
unsigned int count;
@@ -435,7 +435,7 @@ typedef struct rt6_info *(*pol_lookup_t)(struct net *,
struct fib6_entry_notifier_info {
struct fib_notifier_info info; /* must be first */
- struct rt6_info *rt;
+ struct fib6_info *rt;
};
/*
@@ -457,14 +457,14 @@ struct fib6_node *fib6_locate(struct fib6_node *root,
const struct in6_addr *saddr, int src_len,
bool exact_match);
-void fib6_clean_all(struct net *net, int (*func)(struct rt6_info *, void *arg),
+void fib6_clean_all(struct net *net, int (*func)(struct fib6_info *, void *arg),
void *arg);
-int fib6_add(struct fib6_node *root, struct rt6_info *rt,
+int fib6_add(struct fib6_node *root, struct fib6_info *rt,
struct nl_info *info, struct netlink_ext_ack *extack);
-int fib6_del(struct rt6_info *rt, struct nl_info *info);
+int fib6_del(struct fib6_info *rt, struct nl_info *info);
-void inet6_rt_notify(int event, struct rt6_info *rt, struct nl_info *info,
+void inet6_rt_notify(int event, struct fib6_info *rt, struct nl_info *info,
unsigned int flags);
void fib6_run_gc(unsigned long expires, struct net *net, bool force);
@@ -487,11 +487,11 @@ void __net_exit fib6_notifier_exit(struct net *net);
unsigned int fib6_tables_seq_read(struct net *net);
int fib6_tables_dump(struct net *net, struct notifier_block *nb);
-void fib6_update_sernum(struct net *net, struct rt6_info *rt);
-void fib6_update_sernum_upto_root(struct net *net, struct rt6_info *rt);
+void fib6_update_sernum(struct net *net, struct fib6_info *rt);
+void fib6_update_sernum_upto_root(struct net *net, struct fib6_info *rt);
-void fib6_metric_set(struct rt6_info *f6i, int metric, u32 val);
-static inline bool fib6_metric_locked(struct rt6_info *f6i, int metric)
+void fib6_metric_set(struct fib6_info *f6i, int metric, u32 val);
+static inline bool fib6_metric_locked(struct fib6_info *f6i, int metric)
{
return !!(f6i->fib6_metrics->metrics[RTAX_LOCK - 1] & (1 << metric));
}
diff --git a/include/net/ip6_route.h b/include/net/ip6_route.h
index 57d0d45667f1..d5fb1e4ae7ac 100644
--- a/include/net/ip6_route.h
+++ b/include/net/ip6_route.h
@@ -66,7 +66,7 @@ static inline bool rt6_need_strict(const struct in6_addr *daddr)
(IPV6_ADDR_MULTICAST | IPV6_ADDR_LINKLOCAL | IPV6_ADDR_LOOPBACK);
}
-static inline bool rt6_qualify_for_ecmp(const struct rt6_info *rt)
+static inline bool rt6_qualify_for_ecmp(const struct fib6_info *rt)
{
return (rt->rt6i_flags & (RTF_GATEWAY|RTF_ADDRCONF|RTF_DYNAMIC)) ==
RTF_GATEWAY;
@@ -102,14 +102,14 @@ int ipv6_route_ioctl(struct net *net, unsigned int cmd, void __user *arg);
int ip6_route_add(struct fib6_config *cfg, gfp_t gfp_flags,
struct netlink_ext_ack *extack);
-int ip6_ins_rt(struct net *net, struct rt6_info *rt);
-int ip6_del_rt(struct net *net, struct rt6_info *rt);
+int ip6_ins_rt(struct net *net, struct fib6_info *rt);
+int ip6_del_rt(struct net *net, struct fib6_info *rt);
-void rt6_flush_exceptions(struct rt6_info *rt);
-void rt6_age_exceptions(struct rt6_info *rt, struct fib6_gc_args *gc_args,
+void rt6_flush_exceptions(struct fib6_info *rt);
+void rt6_age_exceptions(struct fib6_info *rt, struct fib6_gc_args *gc_args,
unsigned long now);
-static inline int ip6_route_get_saddr(struct net *net, struct rt6_info *rt,
+static inline int ip6_route_get_saddr(struct net *net, struct fib6_info *rt,
const struct in6_addr *daddr,
unsigned int prefs,
struct in6_addr *saddr)
@@ -136,9 +136,9 @@ struct dst_entry *icmp6_dst_alloc(struct net_device *dev, struct flowi6 *fl6);
void fib6_force_start_gc(struct net *net);
-struct rt6_info *addrconf_dst_alloc(struct net *net, struct inet6_dev *idev,
- const struct in6_addr *addr, bool anycast,
- gfp_t gfp_flags);
+struct fib6_info *addrconf_dst_alloc(struct net *net, struct inet6_dev *idev,
+ const struct in6_addr *addr, bool anycast,
+ gfp_t gfp_flags);
struct rt6_info *ip6_dst_alloc(struct net *net, struct net_device *dev,
int flags);
@@ -147,10 +147,10 @@ struct rt6_info *ip6_dst_alloc(struct net *net, struct net_device *dev,
* support functions for ND
*
*/
-struct rt6_info *rt6_get_dflt_router(struct net *net,
+struct fib6_info *rt6_get_dflt_router(struct net *net,
const struct in6_addr *addr,
struct net_device *dev);
-struct rt6_info *rt6_add_dflt_router(struct net *net,
+struct fib6_info *rt6_add_dflt_router(struct net *net,
const struct in6_addr *gwaddr,
struct net_device *dev, unsigned int pref);
@@ -176,14 +176,14 @@ struct rt6_rtnl_dump_arg {
struct net *net;
};
-int rt6_dump_route(struct rt6_info *rt, void *p_arg);
+int rt6_dump_route(struct fib6_info *rt, void *p_arg);
void rt6_mtu_change(struct net_device *dev, unsigned int mtu);
void rt6_remove_prefsrc(struct inet6_ifaddr *ifp);
void rt6_clean_tohost(struct net *net, struct in6_addr *gateway);
void rt6_sync_up(struct net_device *dev, unsigned int nh_flags);
void rt6_disable_ip(struct net_device *dev, unsigned long event);
void rt6_sync_down_dev(struct net_device *dev, unsigned long event);
-void rt6_multipath_rebalance(struct rt6_info *rt);
+void rt6_multipath_rebalance(struct fib6_info *rt);
void rt6_uncached_list_add(struct rt6_info *rt);
void rt6_uncached_list_del(struct rt6_info *rt);
@@ -271,7 +271,7 @@ static inline struct in6_addr *rt6_nexthop(struct rt6_info *rt,
return daddr;
}
-static inline bool rt6_duplicate_nexthop(struct rt6_info *a, struct rt6_info *b)
+static inline bool rt6_duplicate_nexthop(struct fib6_info *a, struct fib6_info *b)
{
return a->fib6_nh.nh_dev == b->fib6_nh.nh_dev &&
a->rt6i_idev == b->rt6i_idev &&
diff --git a/include/net/netns/ipv6.h b/include/net/netns/ipv6.h
index 74e4e1e449d5..97b3a54579c8 100644
--- a/include/net/netns/ipv6.h
+++ b/include/net/netns/ipv6.h
@@ -60,7 +60,7 @@ struct netns_ipv6 {
#endif
struct xt_table *ip6table_nat;
#endif
- struct rt6_info *fib6_null_entry;
+ struct fib6_info *fib6_null_entry;
struct rt6_info *ip6_null_entry;
struct rt6_statistics *rt6_stats;
struct timer_list ip6_fib_timer;
diff --git a/net/ipv6/addrconf.c b/net/ipv6/addrconf.c
index e533a447f68c..a294e86a9b25 100644
--- a/net/ipv6/addrconf.c
+++ b/net/ipv6/addrconf.c
@@ -170,7 +170,7 @@ static void addrconf_type_change(struct net_device *dev,
unsigned long event);
static int addrconf_ifdown(struct net_device *dev, int how);
-static struct rt6_info *addrconf_get_prefix_route(const struct in6_addr *pfx,
+static struct fib6_info *addrconf_get_prefix_route(const struct in6_addr *pfx,
int plen,
const struct net_device *dev,
u32 flags, u32 noflags);
@@ -994,7 +994,7 @@ ipv6_add_addr(struct inet6_dev *idev, const struct in6_addr *addr,
gfp_t gfp_flags = can_block ? GFP_KERNEL : GFP_ATOMIC;
struct net *net = dev_net(idev->dev);
struct inet6_ifaddr *ifa = NULL;
- struct rt6_info *rt = NULL;
+ struct fib6_info *rt = NULL;
int err = 0;
int addr_type = ipv6_addr_type(addr);
@@ -1178,7 +1178,7 @@ check_cleanup_prefix_route(struct inet6_ifaddr *ifp, unsigned long *expires)
static void
cleanup_prefix_route(struct inet6_ifaddr *ifp, unsigned long expires, bool del_rt)
{
- struct rt6_info *rt;
+ struct fib6_info *rt;
rt = addrconf_get_prefix_route(&ifp->addr,
ifp->prefix_len,
@@ -2348,13 +2348,13 @@ addrconf_prefix_route(struct in6_addr *pfx, int plen, struct net_device *dev,
}
-static struct rt6_info *addrconf_get_prefix_route(const struct in6_addr *pfx,
+static struct fib6_info *addrconf_get_prefix_route(const struct in6_addr *pfx,
int plen,
const struct net_device *dev,
u32 flags, u32 noflags)
{
struct fib6_node *fn;
- struct rt6_info *rt = NULL;
+ struct fib6_info *rt = NULL;
struct fib6_table *table;
u32 tb_id = l3mdev_fib_table(dev) ? : RT6_TABLE_PREFIX;
@@ -2641,7 +2641,7 @@ void addrconf_prefix_rcv(struct net_device *dev, u8 *opt, int len, bool sllao)
*/
if (pinfo->onlink) {
- struct rt6_info *rt;
+ struct fib6_info *rt;
unsigned long rt_expires;
/* Avoid arithmetic overflow. Really, we could
@@ -3346,7 +3346,7 @@ static int fixup_permanent_addr(struct net *net,
* case regenerate the host route.
*/
if (!ifp->rt || !ifp->rt->rt6i_node) {
- struct rt6_info *rt, *prev;
+ struct fib6_info *rt, *prev;
rt = addrconf_dst_alloc(net, idev, &ifp->addr, false,
GFP_ATOMIC);
@@ -3713,7 +3713,7 @@ static int addrconf_ifdown(struct net_device *dev, int how)
keep_addr = (!how && _keep_addr > 0 && !idev->cnf.disable_ipv6);
list_for_each_entry_safe(ifa, tmp, &idev->addr_list, if_list) {
- struct rt6_info *rt = NULL;
+ struct fib6_info *rt = NULL;
bool keep;
addrconf_del_dad_work(ifa);
@@ -5626,7 +5626,7 @@ static void __ipv6_ifa_notify(int event, struct inet6_ifaddr *ifp)
addrconf_leave_anycast(ifp);
addrconf_leave_solict(ifp->idev, &ifp->addr);
if (!ipv6_addr_any(&ifp->peer_addr)) {
- struct rt6_info *rt;
+ struct fib6_info *rt;
rt = addrconf_get_prefix_route(&ifp->peer_addr, 128,
ifp->idev->dev, 0, 0);
@@ -5982,7 +5982,7 @@ void addrconf_disable_policy_idev(struct inet6_dev *idev, int val)
list_for_each_entry(ifa, &idev->addr_list, if_list) {
spin_lock(&ifa->lock);
if (ifa->rt) {
- struct rt6_info *rt = ifa->rt;
+ struct fib6_info *rt = ifa->rt;
int cpu;
rcu_read_lock();
diff --git a/net/ipv6/anycast.c b/net/ipv6/anycast.c
index 3db8fe10322b..0e35657501a7 100644
--- a/net/ipv6/anycast.c
+++ b/net/ipv6/anycast.c
@@ -218,7 +218,7 @@ static void aca_put(struct ifacaddr6 *ac)
}
}
-static struct ifacaddr6 *aca_alloc(struct rt6_info *rt,
+static struct ifacaddr6 *aca_alloc(struct fib6_info *rt,
const struct in6_addr *addr)
{
struct inet6_dev *idev = rt->rt6i_idev;
@@ -247,7 +247,7 @@ static struct ifacaddr6 *aca_alloc(struct rt6_info *rt,
int __ipv6_dev_ac_inc(struct inet6_dev *idev, const struct in6_addr *addr)
{
struct ifacaddr6 *aca;
- struct rt6_info *rt;
+ struct fib6_info *rt;
struct net *net;
int err;
diff --git a/net/ipv6/ip6_fib.c b/net/ipv6/ip6_fib.c
index 4d6bd033dccd..77cf43b2d858 100644
--- a/net/ipv6/ip6_fib.c
+++ b/net/ipv6/ip6_fib.c
@@ -43,7 +43,7 @@ static struct kmem_cache *fib6_node_kmem __read_mostly;
struct fib6_cleaner {
struct fib6_walker w;
struct net *net;
- int (*func)(struct rt6_info *, void *arg);
+ int (*func)(struct fib6_info *, void *arg);
int sernum;
void *arg;
};
@@ -54,7 +54,7 @@ struct fib6_cleaner {
#define FWS_INIT FWS_L
#endif
-static struct rt6_info *fib6_find_prefix(struct net *net,
+static struct fib6_info *fib6_find_prefix(struct net *net,
struct fib6_table *table,
struct fib6_node *fn);
static struct fib6_node *fib6_repair_tree(struct net *net,
@@ -105,7 +105,7 @@ enum {
FIB6_NO_SERNUM_CHANGE = 0,
};
-void fib6_update_sernum(struct net *net, struct rt6_info *rt)
+void fib6_update_sernum(struct net *net, struct fib6_info *rt)
{
struct fib6_node *fn;
@@ -145,9 +145,9 @@ static __be32 addr_bit_set(const void *token, int fn_bit)
addr[fn_bit >> 5];
}
-struct rt6_info *fib6_info_alloc(gfp_t gfp_flags)
+struct fib6_info *fib6_info_alloc(gfp_t gfp_flags)
{
- struct rt6_info *f6i;
+ struct fib6_info *f6i;
f6i = kzalloc(sizeof(*f6i), gfp_flags);
if (!f6i)
@@ -167,7 +167,7 @@ struct rt6_info *fib6_info_alloc(gfp_t gfp_flags)
return f6i;
}
-void fib6_info_destroy(struct rt6_info *f6i)
+void fib6_info_destroy(struct fib6_info *f6i)
{
struct rt6_exception_bucket *bucket;
struct dst_metrics *m;
@@ -404,7 +404,7 @@ unsigned int fib6_tables_seq_read(struct net *net)
static int call_fib6_entry_notifier(struct notifier_block *nb, struct net *net,
enum fib_event_type event_type,
- struct rt6_info *rt)
+ struct fib6_info *rt)
{
struct fib6_entry_notifier_info info = {
.rt = rt,
@@ -415,7 +415,7 @@ static int call_fib6_entry_notifier(struct notifier_block *nb, struct net *net,
static int call_fib6_entry_notifiers(struct net *net,
enum fib_event_type event_type,
- struct rt6_info *rt,
+ struct fib6_info *rt,
struct netlink_ext_ack *extack)
{
struct fib6_entry_notifier_info info = {
@@ -432,7 +432,7 @@ struct fib6_dump_arg {
struct notifier_block *nb;
};
-static void fib6_rt_dump(struct rt6_info *rt, struct fib6_dump_arg *arg)
+static void fib6_rt_dump(struct fib6_info *rt, struct fib6_dump_arg *arg)
{
if (rt == arg->net->ipv6.fib6_null_entry)
return;
@@ -441,7 +441,7 @@ static void fib6_rt_dump(struct rt6_info *rt, struct fib6_dump_arg *arg)
static int fib6_node_dump(struct fib6_walker *w)
{
- struct rt6_info *rt;
+ struct fib6_info *rt;
for_each_fib6_walker_rt(w)
fib6_rt_dump(rt, w->args);
@@ -490,7 +490,7 @@ int fib6_tables_dump(struct net *net, struct notifier_block *nb)
static int fib6_dump_node(struct fib6_walker *w)
{
int res;
- struct rt6_info *rt;
+ struct fib6_info *rt;
for_each_fib6_walker_rt(w) {
res = rt6_dump_route(rt, w->args);
@@ -507,7 +507,7 @@ static int fib6_dump_node(struct fib6_walker *w)
*/
if (rt->rt6i_nsiblings)
rt = list_last_entry(&rt->rt6i_siblings,
- struct rt6_info,
+ struct fib6_info,
rt6i_siblings);
}
w->leaf = NULL;
@@ -643,7 +643,7 @@ static int inet6_dump_fib(struct sk_buff *skb, struct netlink_callback *cb)
return res;
}
-void fib6_metric_set(struct rt6_info *f6i, int metric, u32 val)
+void fib6_metric_set(struct fib6_info *f6i, int metric, u32 val)
{
if (!f6i)
return;
@@ -690,7 +690,7 @@ static struct fib6_node *fib6_add_1(struct net *net,
fn = root;
do {
- struct rt6_info *leaf = rcu_dereference_protected(fn->leaf,
+ struct fib6_info *leaf = rcu_dereference_protected(fn->leaf,
lockdep_is_held(&table->tb6_lock));
key = (struct rt6key *)((u8 *)leaf + offset);
@@ -884,7 +884,7 @@ static struct fib6_node *fib6_add_1(struct net *net,
return ln;
}
-static void fib6_purge_rt(struct rt6_info *rt, struct fib6_node *fn,
+static void fib6_purge_rt(struct fib6_info *rt, struct fib6_node *fn,
struct net *net)
{
struct fib6_table *table = rt->rt6i_table;
@@ -897,9 +897,9 @@ static void fib6_purge_rt(struct rt6_info *rt, struct fib6_node *fn,
* to still alive ones.
*/
while (fn) {
- struct rt6_info *leaf = rcu_dereference_protected(fn->leaf,
+ struct fib6_info *leaf = rcu_dereference_protected(fn->leaf,
lockdep_is_held(&table->tb6_lock));
- struct rt6_info *new_leaf;
+ struct fib6_info *new_leaf;
if (!(fn->fn_flags & RTN_RTINFO) && leaf == rt) {
new_leaf = fib6_find_prefix(net, table, fn);
atomic_inc(&new_leaf->rt6i_ref);
@@ -936,15 +936,15 @@ static void fib6_purge_rt(struct rt6_info *rt, struct fib6_node *fn,
* Insert routing information in a node.
*/
-static int fib6_add_rt2node(struct fib6_node *fn, struct rt6_info *rt,
+static int fib6_add_rt2node(struct fib6_node *fn, struct fib6_info *rt,
struct nl_info *info,
struct netlink_ext_ack *extack)
{
- struct rt6_info *leaf = rcu_dereference_protected(fn->leaf,
+ struct fib6_info *leaf = rcu_dereference_protected(fn->leaf,
lockdep_is_held(&rt->rt6i_table->tb6_lock));
- struct rt6_info *iter = NULL;
- struct rt6_info __rcu **ins;
- struct rt6_info __rcu **fallback_ins = NULL;
+ struct fib6_info *iter = NULL;
+ struct fib6_info __rcu **ins;
+ struct fib6_info __rcu **fallback_ins = NULL;
int replace = (info->nlh &&
(info->nlh->nlmsg_flags & NLM_F_REPLACE));
int add = (!info->nlh ||
@@ -1035,7 +1035,7 @@ static int fib6_add_rt2node(struct fib6_node *fn, struct rt6_info *rt,
/* Link this route to others same route. */
if (rt->rt6i_nsiblings) {
unsigned int rt6i_nsiblings;
- struct rt6_info *sibling, *temp_sibling;
+ struct fib6_info *sibling, *temp_sibling;
/* Find the first route that have the same metric */
sibling = leaf;
@@ -1156,7 +1156,7 @@ static int fib6_add_rt2node(struct fib6_node *fn, struct rt6_info *rt,
return 0;
}
-static void fib6_start_gc(struct net *net, struct rt6_info *rt)
+static void fib6_start_gc(struct net *net, struct fib6_info *rt)
{
if (!timer_pending(&net->ipv6.ip6_fib_timer) &&
(rt->rt6i_flags & RTF_EXPIRES))
@@ -1171,7 +1171,7 @@ void fib6_force_start_gc(struct net *net)
jiffies + net->ipv6.sysctl.ip6_rt_gc_interval);
}
-static void __fib6_update_sernum_upto_root(struct rt6_info *rt,
+static void __fib6_update_sernum_upto_root(struct fib6_info *rt,
int sernum)
{
struct fib6_node *fn = rcu_dereference_protected(rt->rt6i_node,
@@ -1186,7 +1186,7 @@ static void __fib6_update_sernum_upto_root(struct rt6_info *rt,
}
}
-void fib6_update_sernum_upto_root(struct net *net, struct rt6_info *rt)
+void fib6_update_sernum_upto_root(struct net *net, struct fib6_info *rt)
{
__fib6_update_sernum_upto_root(rt, fib6_new_sernum(net));
}
@@ -1198,7 +1198,7 @@ void fib6_update_sernum_upto_root(struct net *net, struct rt6_info *rt)
* Need to own table->tb6_lock
*/
-int fib6_add(struct fib6_node *root, struct rt6_info *rt,
+int fib6_add(struct fib6_node *root, struct fib6_info *rt,
struct nl_info *info, struct netlink_ext_ack *extack)
{
struct fib6_table *table = rt->rt6i_table;
@@ -1219,7 +1219,7 @@ int fib6_add(struct fib6_node *root, struct rt6_info *rt,
fn = fib6_add_1(info->nl_net, table, root,
&rt->rt6i_dst.addr, rt->rt6i_dst.plen,
- offsetof(struct rt6_info, rt6i_dst), allow_create,
+ offsetof(struct fib6_info, rt6i_dst), allow_create,
replace_required, extack);
if (IS_ERR(fn)) {
err = PTR_ERR(fn);
@@ -1260,7 +1260,7 @@ int fib6_add(struct fib6_node *root, struct rt6_info *rt,
sn = fib6_add_1(info->nl_net, table, sfn,
&rt->rt6i_src.addr, rt->rt6i_src.plen,
- offsetof(struct rt6_info, rt6i_src),
+ offsetof(struct fib6_info, rt6i_src),
allow_create, replace_required, extack);
if (IS_ERR(sn)) {
@@ -1279,7 +1279,7 @@ int fib6_add(struct fib6_node *root, struct rt6_info *rt,
} else {
sn = fib6_add_1(info->nl_net, table, FIB6_SUBTREE(fn),
&rt->rt6i_src.addr, rt->rt6i_src.plen,
- offsetof(struct rt6_info, rt6i_src),
+ offsetof(struct fib6_info, rt6i_src),
allow_create, replace_required, extack);
if (IS_ERR(sn)) {
@@ -1316,7 +1316,7 @@ int fib6_add(struct fib6_node *root, struct rt6_info *rt,
* super-tree leaf node we have to find a new one for it.
*/
if (pn != fn) {
- struct rt6_info *pn_leaf =
+ struct fib6_info *pn_leaf =
rcu_dereference_protected(pn->leaf,
lockdep_is_held(&table->tb6_lock));
if (pn_leaf == rt) {
@@ -1365,7 +1365,7 @@ int fib6_add(struct fib6_node *root, struct rt6_info *rt,
*/
struct lookup_args {
- int offset; /* key offset on rt6_info */
+ int offset; /* key offset on fib6_info */
const struct in6_addr *addr; /* search key */
};
@@ -1403,7 +1403,7 @@ static struct fib6_node *fib6_lookup_1(struct fib6_node *root,
struct fib6_node *subtree = FIB6_SUBTREE(fn);
if (subtree || fn->fn_flags & RTN_RTINFO) {
- struct rt6_info *leaf = rcu_dereference(fn->leaf);
+ struct fib6_info *leaf = rcu_dereference(fn->leaf);
struct rt6key *key;
if (!leaf)
@@ -1443,12 +1443,12 @@ struct fib6_node *fib6_lookup(struct fib6_node *root, const struct in6_addr *dad
struct fib6_node *fn;
struct lookup_args args[] = {
{
- .offset = offsetof(struct rt6_info, rt6i_dst),
+ .offset = offsetof(struct fib6_info, rt6i_dst),
.addr = daddr,
},
#ifdef CONFIG_IPV6_SUBTREES
{
- .offset = offsetof(struct rt6_info, rt6i_src),
+ .offset = offsetof(struct fib6_info, rt6i_src),
.addr = saddr,
},
#endif
@@ -1484,7 +1484,7 @@ static struct fib6_node *fib6_locate_1(struct fib6_node *root,
struct fib6_node *fn, *prev = NULL;
for (fn = root; fn ; ) {
- struct rt6_info *leaf = rcu_dereference(fn->leaf);
+ struct fib6_info *leaf = rcu_dereference(fn->leaf);
struct rt6key *key;
/* This node is being deleted */
@@ -1533,7 +1533,7 @@ struct fib6_node *fib6_locate(struct fib6_node *root,
struct fib6_node *fn;
fn = fib6_locate_1(root, daddr, dst_len,
- offsetof(struct rt6_info, rt6i_dst),
+ offsetof(struct fib6_info, rt6i_dst),
exact_match);
#ifdef CONFIG_IPV6_SUBTREES
@@ -1544,7 +1544,7 @@ struct fib6_node *fib6_locate(struct fib6_node *root,
if (subtree) {
fn = fib6_locate_1(subtree, saddr, src_len,
- offsetof(struct rt6_info, rt6i_src),
+ offsetof(struct fib6_info, rt6i_src),
exact_match);
}
}
@@ -1563,7 +1563,7 @@ struct fib6_node *fib6_locate(struct fib6_node *root,
*
*/
-static struct rt6_info *fib6_find_prefix(struct net *net,
+static struct fib6_info *fib6_find_prefix(struct net *net,
struct fib6_table *table,
struct fib6_node *fn)
{
@@ -1622,11 +1622,11 @@ static struct fib6_node *fib6_repair_tree(struct net *net,
lockdep_is_held(&table->tb6_lock));
struct fib6_node *pn_l = rcu_dereference_protected(pn->left,
lockdep_is_held(&table->tb6_lock));
- struct rt6_info *fn_leaf = rcu_dereference_protected(fn->leaf,
+ struct fib6_info *fn_leaf = rcu_dereference_protected(fn->leaf,
lockdep_is_held(&table->tb6_lock));
- struct rt6_info *pn_leaf = rcu_dereference_protected(pn->leaf,
+ struct fib6_info *pn_leaf = rcu_dereference_protected(pn->leaf,
lockdep_is_held(&table->tb6_lock));
- struct rt6_info *new_fn_leaf;
+ struct fib6_info *new_fn_leaf;
RT6_TRACE("fixing tree: plen=%d iter=%d\n", fn->fn_bit, iter);
iter++;
@@ -1717,10 +1717,10 @@ static struct fib6_node *fib6_repair_tree(struct net *net,
}
static void fib6_del_route(struct fib6_table *table, struct fib6_node *fn,
- struct rt6_info __rcu **rtp, struct nl_info *info)
+ struct fib6_info __rcu **rtp, struct nl_info *info)
{
struct fib6_walker *w;
- struct rt6_info *rt = rcu_dereference_protected(*rtp,
+ struct fib6_info *rt = rcu_dereference_protected(*rtp,
lockdep_is_held(&table->tb6_lock));
struct net *net = info->nl_net;
@@ -1741,7 +1741,7 @@ static void fib6_del_route(struct fib6_table *table, struct fib6_node *fn,
/* Remove this entry from other siblings */
if (rt->rt6i_nsiblings) {
- struct rt6_info *sibling, *next_sibling;
+ struct fib6_info *sibling, *next_sibling;
list_for_each_entry_safe(sibling, next_sibling,
&rt->rt6i_siblings, rt6i_siblings)
@@ -1785,14 +1785,14 @@ static void fib6_del_route(struct fib6_table *table, struct fib6_node *fn,
}
/* Need to own table->tb6_lock */
-int fib6_del(struct rt6_info *rt, struct nl_info *info)
+int fib6_del(struct fib6_info *rt, struct nl_info *info)
{
struct fib6_node *fn = rcu_dereference_protected(rt->rt6i_node,
lockdep_is_held(&rt->rt6i_table->tb6_lock));
struct fib6_table *table = rt->rt6i_table;
struct net *net = info->nl_net;
- struct rt6_info __rcu **rtp;
- struct rt6_info __rcu **rtp_next;
+ struct fib6_info __rcu **rtp;
+ struct fib6_info __rcu **rtp_next;
if (!fn || rt == net->ipv6.fib6_null_entry)
return -ENOENT;
@@ -1804,7 +1804,7 @@ int fib6_del(struct rt6_info *rt, struct nl_info *info)
*/
for (rtp = &fn->leaf; *rtp; rtp = rtp_next) {
- struct rt6_info *cur = rcu_dereference_protected(*rtp,
+ struct fib6_info *cur = rcu_dereference_protected(*rtp,
lockdep_is_held(&table->tb6_lock));
if (rt == cur) {
fib6_del_route(table, fn, rtp, info);
@@ -1948,7 +1948,7 @@ static int fib6_walk(struct net *net, struct fib6_walker *w)
static int fib6_clean_node(struct fib6_walker *w)
{
int res;
- struct rt6_info *rt;
+ struct fib6_info *rt;
struct fib6_cleaner *c = container_of(w, struct fib6_cleaner, w);
struct nl_info info = {
.nl_net = c->net,
@@ -1983,7 +1983,7 @@ static int fib6_clean_node(struct fib6_walker *w)
if (WARN_ON(!rt->rt6i_nsiblings))
continue;
rt = list_last_entry(&rt->rt6i_siblings,
- struct rt6_info, rt6i_siblings);
+ struct fib6_info, rt6i_siblings);
continue;
}
WARN_ON(res != 0);
@@ -2002,7 +2002,7 @@ static int fib6_clean_node(struct fib6_walker *w)
*/
static void fib6_clean_tree(struct net *net, struct fib6_node *root,
- int (*func)(struct rt6_info *, void *arg),
+ int (*func)(struct fib6_info *, void *arg),
int sernum, void *arg)
{
struct fib6_cleaner c;
@@ -2020,7 +2020,7 @@ static void fib6_clean_tree(struct net *net, struct fib6_node *root,
}
static void __fib6_clean_all(struct net *net,
- int (*func)(struct rt6_info *, void *),
+ int (*func)(struct fib6_info *, void *),
int sernum, void *arg)
{
struct fib6_table *table;
@@ -2040,7 +2040,7 @@ static void __fib6_clean_all(struct net *net,
rcu_read_unlock();
}
-void fib6_clean_all(struct net *net, int (*func)(struct rt6_info *, void *),
+void fib6_clean_all(struct net *net, int (*func)(struct fib6_info *, void *),
void *arg)
{
__fib6_clean_all(net, func, FIB6_NO_SERNUM_CHANGE, arg);
@@ -2057,7 +2057,7 @@ static void fib6_flush_trees(struct net *net)
* Garbage collection
*/
-static int fib6_age(struct rt6_info *rt, void *arg)
+static int fib6_age(struct fib6_info *rt, void *arg)
{
struct fib6_gc_args *gc_args = arg;
unsigned long now = jiffies;
@@ -2261,7 +2261,7 @@ struct ipv6_route_iter {
static int ipv6_route_seq_show(struct seq_file *seq, void *v)
{
- struct rt6_info *rt = v;
+ struct fib6_info *rt = v;
struct ipv6_route_iter *iter = seq->private;
const struct net_device *dev;
@@ -2353,14 +2353,14 @@ static void ipv6_route_check_sernum(struct ipv6_route_iter *iter)
static void *ipv6_route_seq_next(struct seq_file *seq, void *v, loff_t *pos)
{
int r;
- struct rt6_info *n;
+ struct fib6_info *n;
struct net *net = seq_file_net(seq);
struct ipv6_route_iter *iter = seq->private;
if (!v)
goto iter_table;
- n = rcu_dereference_bh(((struct rt6_info *)v)->rt6_next);
+ n = rcu_dereference_bh(((struct fib6_info *)v)->rt6_next);
if (n) {
++*pos;
return n;
diff --git a/net/ipv6/ndisc.c b/net/ipv6/ndisc.c
index a28857088bff..102645298692 100644
--- a/net/ipv6/ndisc.c
+++ b/net/ipv6/ndisc.c
@@ -1155,7 +1155,7 @@ static void ndisc_router_discovery(struct sk_buff *skb)
struct ra_msg *ra_msg = (struct ra_msg *)skb_transport_header(skb);
struct neighbour *neigh = NULL;
struct inet6_dev *in6_dev;
- struct rt6_info *rt = NULL;
+ struct fib6_info *rt = NULL;
struct net *net;
int lifetime;
struct ndisc_options ndopts;
diff --git a/net/ipv6/route.c b/net/ipv6/route.c
index 0d861bd07673..2ccf939e1a20 100644
--- a/net/ipv6/route.c
+++ b/net/ipv6/route.c
@@ -96,24 +96,24 @@ static void ip6_rt_update_pmtu(struct dst_entry *dst, struct sock *sk,
struct sk_buff *skb, u32 mtu);
static void rt6_do_redirect(struct dst_entry *dst, struct sock *sk,
struct sk_buff *skb);
-static int rt6_score_route(struct rt6_info *rt, int oif, int strict);
-static size_t rt6_nlmsg_size(struct rt6_info *rt);
+static int rt6_score_route(struct fib6_info *rt, int oif, int strict);
+static size_t rt6_nlmsg_size(struct fib6_info *rt);
static int rt6_fill_node(struct net *net, struct sk_buff *skb,
- struct rt6_info *rt, struct dst_entry *dst,
+ struct fib6_info *rt, struct dst_entry *dst,
struct in6_addr *dest, struct in6_addr *src,
int iif, int type, u32 portid, u32 seq,
unsigned int flags);
-static struct rt6_info *rt6_find_cached_rt(struct rt6_info *rt,
+static struct rt6_info *rt6_find_cached_rt(struct fib6_info *rt,
struct in6_addr *daddr,
struct in6_addr *saddr);
#ifdef CONFIG_IPV6_ROUTE_INFO
-static struct rt6_info *rt6_add_route_info(struct net *net,
+static struct fib6_info *rt6_add_route_info(struct net *net,
const struct in6_addr *prefix, int prefixlen,
const struct in6_addr *gwaddr,
struct net_device *dev,
unsigned int pref);
-static struct rt6_info *rt6_get_route_info(struct net *net,
+static struct fib6_info *rt6_get_route_info(struct net *net,
const struct in6_addr *prefix, int prefixlen,
const struct in6_addr *gwaddr,
struct net_device *dev);
@@ -283,7 +283,7 @@ static const u32 ip6_template_metrics[RTAX_MAX] = {
[RTAX_HOPLIMIT - 1] = 0,
};
-static const struct rt6_info fib6_null_entry_template = {
+static const struct fib6_info fib6_null_entry_template = {
.rt6i_flags = (RTF_REJECT | RTF_NONEXTHOP),
.rt6i_protocol = RTPROT_KERNEL,
.rt6i_metric = ~(u32)0,
@@ -372,7 +372,7 @@ EXPORT_SYMBOL(ip6_dst_alloc);
static void ip6_dst_destroy(struct dst_entry *dst)
{
struct rt6_info *rt = (struct rt6_info *)dst;
- struct rt6_info *from = rt->from;
+ struct fib6_info *from = rt->from;
struct inet6_dev *idev;
dst_destroy_metrics_generic(dst);
@@ -425,13 +425,13 @@ static bool rt6_check_expired(const struct rt6_info *rt)
return false;
}
-static struct rt6_info *rt6_multipath_select(const struct net *net,
- struct rt6_info *match,
+static struct fib6_info *rt6_multipath_select(const struct net *net,
+ struct fib6_info *match,
struct flowi6 *fl6, int oif,
const struct sk_buff *skb,
int strict)
{
- struct rt6_info *sibling, *next_sibling;
+ struct fib6_info *sibling, *next_sibling;
/* We might have already computed the hash for ICMPv6 errors. In such
* case it will always be non-zero. Otherwise now is the time to do it.
@@ -462,14 +462,14 @@ static struct rt6_info *rt6_multipath_select(const struct net *net,
* Route lookup. rcu_read_lock() should be held.
*/
-static inline struct rt6_info *rt6_device_match(struct net *net,
- struct rt6_info *rt,
+static inline struct fib6_info *rt6_device_match(struct net *net,
+ struct fib6_info *rt,
const struct in6_addr *saddr,
int oif,
int flags)
{
- struct rt6_info *local = NULL;
- struct rt6_info *sprt;
+ struct fib6_info *local = NULL;
+ struct fib6_info *sprt;
if (!oif && ipv6_addr_any(saddr) &&
!(rt->fib6_nh.nh_flags & RTNH_F_DEAD))
@@ -532,7 +532,7 @@ static void rt6_probe_deferred(struct work_struct *w)
kfree(work);
}
-static void rt6_probe(struct rt6_info *rt)
+static void rt6_probe(struct fib6_info *rt)
{
struct __rt6_probe_work *work;
const struct in6_addr *nh_gw;
@@ -585,7 +585,7 @@ static void rt6_probe(struct rt6_info *rt)
rcu_read_unlock_bh();
}
#else
-static inline void rt6_probe(struct rt6_info *rt)
+static inline void rt6_probe(struct fib6_info *rt)
{
}
#endif
@@ -593,7 +593,7 @@ static inline void rt6_probe(struct rt6_info *rt)
/*
* Default Router Selection (RFC 2461 6.3.6)
*/
-static inline int rt6_check_dev(struct rt6_info *rt, int oif)
+static inline int rt6_check_dev(struct fib6_info *rt, int oif)
{
const struct net_device *dev = rt->fib6_nh.nh_dev;
@@ -605,7 +605,7 @@ static inline int rt6_check_dev(struct rt6_info *rt, int oif)
return 0;
}
-static inline enum rt6_nud_state rt6_check_neigh(struct rt6_info *rt)
+static inline enum rt6_nud_state rt6_check_neigh(struct fib6_info *rt)
{
enum rt6_nud_state ret = RT6_NUD_FAIL_HARD;
struct neighbour *neigh;
@@ -637,8 +637,7 @@ static inline enum rt6_nud_state rt6_check_neigh(struct rt6_info *rt)
return ret;
}
-static int rt6_score_route(struct rt6_info *rt, int oif,
- int strict)
+static int rt6_score_route(struct fib6_info *rt, int oif, int strict)
{
int m;
@@ -656,8 +655,8 @@ static int rt6_score_route(struct rt6_info *rt, int oif,
return m;
}
-static struct rt6_info *find_match(struct rt6_info *rt, int oif, int strict,
- int *mpri, struct rt6_info *match,
+static struct fib6_info *find_match(struct fib6_info *rt, int oif, int strict,
+ int *mpri, struct fib6_info *match,
bool *do_rr)
{
int m;
@@ -696,13 +695,13 @@ static struct rt6_info *find_match(struct rt6_info *rt, int oif, int strict,
return match;
}
-static struct rt6_info *find_rr_leaf(struct fib6_node *fn,
- struct rt6_info *leaf,
- struct rt6_info *rr_head,
+static struct fib6_info *find_rr_leaf(struct fib6_node *fn,
+ struct fib6_info *leaf,
+ struct fib6_info *rr_head,
u32 metric, int oif, int strict,
bool *do_rr)
{
- struct rt6_info *rt, *match, *cont;
+ struct fib6_info *rt, *match, *cont;
int mpri = -1;
match = NULL;
@@ -735,11 +734,11 @@ static struct rt6_info *find_rr_leaf(struct fib6_node *fn,
return match;
}
-static struct rt6_info *rt6_select(struct net *net, struct fib6_node *fn,
+static struct fib6_info *rt6_select(struct net *net, struct fib6_node *fn,
int oif, int strict)
{
- struct rt6_info *leaf = rcu_dereference(fn->leaf);
- struct rt6_info *match, *rt0;
+ struct fib6_info *leaf = rcu_dereference(fn->leaf);
+ struct fib6_info *match, *rt0;
bool do_rr = false;
int key_plen;
@@ -767,7 +766,7 @@ static struct rt6_info *rt6_select(struct net *net, struct fib6_node *fn,
&do_rr);
if (do_rr) {
- struct rt6_info *next = rcu_dereference(rt0->rt6_next);
+ struct fib6_info *next = rcu_dereference(rt0->rt6_next);
/* no entries matched; do round-robin */
if (!next || next->rt6i_metric != rt0->rt6i_metric)
@@ -785,7 +784,7 @@ static struct rt6_info *rt6_select(struct net *net, struct fib6_node *fn,
return match ? match : net->ipv6.fib6_null_entry;
}
-static bool rt6_is_gw_or_nonexthop(const struct rt6_info *rt)
+static bool rt6_is_gw_or_nonexthop(const struct fib6_info *rt)
{
return (rt->rt6i_flags & (RTF_NONEXTHOP | RTF_GATEWAY));
}
@@ -799,7 +798,7 @@ int rt6_route_rcv(struct net_device *dev, u8 *opt, int len,
struct in6_addr prefix_buf, *prefix;
unsigned int pref;
unsigned long lifetime;
- struct rt6_info *rt;
+ struct fib6_info *rt;
if (len < sizeof(struct route_info)) {
return -EINVAL;
@@ -871,7 +870,7 @@ int rt6_route_rcv(struct net_device *dev, u8 *opt, int len,
*/
/* called with rcu_lock held */
-static struct net_device *ip6_rt_get_dev_rcu(struct rt6_info *rt)
+static struct net_device *ip6_rt_get_dev_rcu(struct fib6_info *rt)
{
struct net_device *dev = rt->fib6_nh.nh_dev;
@@ -913,7 +912,7 @@ static int ip6_rt_type_to_error(u8 fib6_type)
return fib6_prop[fib6_type];
}
-static unsigned short fib6_info_dst_flags(struct rt6_info *rt)
+static unsigned short fib6_info_dst_flags(struct fib6_info *rt)
{
unsigned short flags = 0;
@@ -927,7 +926,7 @@ static unsigned short fib6_info_dst_flags(struct rt6_info *rt)
return flags;
}
-static void ip6_rt_init_dst_reject(struct rt6_info *rt, struct rt6_info *ort)
+static void ip6_rt_init_dst_reject(struct rt6_info *rt, struct fib6_info *ort)
{
rt->dst.error = ip6_rt_type_to_error(ort->fib6_type);
@@ -949,7 +948,7 @@ static void ip6_rt_init_dst_reject(struct rt6_info *rt, struct rt6_info *ort)
}
}
-static void ip6_rt_init_dst(struct rt6_info *rt, struct rt6_info *ort)
+static void ip6_rt_init_dst(struct rt6_info *rt, struct fib6_info *ort)
{
rt->dst.flags |= fib6_info_dst_flags(ort);
@@ -977,7 +976,7 @@ static void ip6_rt_init_dst(struct rt6_info *rt, struct rt6_info *ort)
rt->dst.lastuse = jiffies;
}
-static void rt6_set_from(struct rt6_info *rt, struct rt6_info *from)
+static void rt6_set_from(struct rt6_info *rt, struct fib6_info *from)
{
rt->rt6i_flags &= ~RTF_EXPIRES;
fib6_info_hold(from);
@@ -989,7 +988,7 @@ static void rt6_set_from(struct rt6_info *rt, struct rt6_info *from)
}
}
-static void ip6_rt_copy_init(struct rt6_info *rt, struct rt6_info *ort)
+static void ip6_rt_copy_init(struct rt6_info *rt, struct fib6_info *ort)
{
ip6_rt_init_dst(rt, ort);
@@ -1045,7 +1044,7 @@ static bool ip6_hold_safe(struct net *net, struct rt6_info **prt,
}
/* called with rcu_lock held */
-static struct rt6_info *ip6_create_rt_rcu(struct rt6_info *rt)
+static struct rt6_info *ip6_create_rt_rcu(struct fib6_info *rt)
{
unsigned short flags = fib6_info_dst_flags(rt);
struct net_device *dev = rt->fib6_nh.nh_dev;
@@ -1064,7 +1063,7 @@ static struct rt6_info *ip6_pol_route_lookup(struct net *net,
const struct sk_buff *skb,
int flags)
{
- struct rt6_info *f6i;
+ struct fib6_info *f6i;
struct fib6_node *fn;
struct rt6_info *rt;
@@ -1152,7 +1151,7 @@ EXPORT_SYMBOL(rt6_lookup);
* Caller must hold dst before calling it.
*/
-static int __ip6_ins_rt(struct rt6_info *rt, struct nl_info *info,
+static int __ip6_ins_rt(struct fib6_info *rt, struct nl_info *info,
struct netlink_ext_ack *extack)
{
int err;
@@ -1166,14 +1165,14 @@ static int __ip6_ins_rt(struct rt6_info *rt, struct nl_info *info,
return err;
}
-int ip6_ins_rt(struct net *net, struct rt6_info *rt)
+int ip6_ins_rt(struct net *net, struct fib6_info *rt)
{
struct nl_info info = { .nl_net = net, };
return __ip6_ins_rt(rt, &info, NULL);
}
-static struct rt6_info *ip6_rt_cache_alloc(struct rt6_info *ort,
+static struct rt6_info *ip6_rt_cache_alloc(struct fib6_info *ort,
const struct in6_addr *daddr,
const struct in6_addr *saddr)
{
@@ -1213,7 +1212,7 @@ static struct rt6_info *ip6_rt_cache_alloc(struct rt6_info *ort,
return rt;
}
-static struct rt6_info *ip6_rt_pcpu_alloc(struct rt6_info *rt)
+static struct rt6_info *ip6_rt_pcpu_alloc(struct fib6_info *rt)
{
unsigned short flags = fib6_info_dst_flags(rt);
struct net_device *dev;
@@ -1232,7 +1231,7 @@ static struct rt6_info *ip6_rt_pcpu_alloc(struct rt6_info *rt)
}
/* It should be called with rcu_read_lock() acquired */
-static struct rt6_info *rt6_get_pcpu_route(struct rt6_info *rt)
+static struct rt6_info *rt6_get_pcpu_route(struct fib6_info *rt)
{
struct rt6_info *pcpu_rt, **p;
@@ -1246,7 +1245,7 @@ static struct rt6_info *rt6_get_pcpu_route(struct rt6_info *rt)
}
static struct rt6_info *rt6_make_pcpu_route(struct net *net,
- struct rt6_info *rt)
+ struct fib6_info *rt)
{
struct rt6_info *pcpu_rt, *prev, **p;
@@ -1390,7 +1389,7 @@ __rt6_find_exception_rcu(struct rt6_exception_bucket **bucket,
return NULL;
}
-static unsigned int fib6_mtu(const struct rt6_info *rt)
+static unsigned int fib6_mtu(const struct fib6_info *rt)
{
unsigned int mtu;
@@ -1401,7 +1400,7 @@ static unsigned int fib6_mtu(const struct rt6_info *rt)
}
static int rt6_insert_exception(struct rt6_info *nrt,
- struct rt6_info *ort)
+ struct fib6_info *ort)
{
struct net *net = dev_net(nrt->dst.dev);
struct rt6_exception_bucket *bucket;
@@ -1487,7 +1486,7 @@ static int rt6_insert_exception(struct rt6_info *nrt,
return err;
}
-void rt6_flush_exceptions(struct rt6_info *rt)
+void rt6_flush_exceptions(struct fib6_info *rt)
{
struct rt6_exception_bucket *bucket;
struct rt6_exception *rt6_ex;
@@ -1517,7 +1516,7 @@ void rt6_flush_exceptions(struct rt6_info *rt)
/* Find cached rt in the hash table inside passed in rt
* Caller has to hold rcu_read_lock()
*/
-static struct rt6_info *rt6_find_cached_rt(struct rt6_info *rt,
+static struct rt6_info *rt6_find_cached_rt(struct fib6_info *rt,
struct in6_addr *daddr,
struct in6_addr *saddr)
{
@@ -1550,7 +1549,7 @@ static struct rt6_info *rt6_find_cached_rt(struct rt6_info *rt,
static int rt6_remove_exception_rt(struct rt6_info *rt)
{
struct rt6_exception_bucket *bucket;
- struct rt6_info *from = rt->from;
+ struct fib6_info *from = rt->from;
struct in6_addr *src_key = NULL;
struct rt6_exception *rt6_ex;
int err;
@@ -1595,7 +1594,7 @@ static int rt6_remove_exception_rt(struct rt6_info *rt)
static void rt6_update_exception_stamp_rt(struct rt6_info *rt)
{
struct rt6_exception_bucket *bucket;
- struct rt6_info *from = rt->from;
+ struct fib6_info *from = rt->from;
struct in6_addr *src_key = NULL;
struct rt6_exception *rt6_ex;
@@ -1625,7 +1624,7 @@ static void rt6_update_exception_stamp_rt(struct rt6_info *rt)
rcu_read_unlock();
}
-static void rt6_exceptions_remove_prefsrc(struct rt6_info *rt)
+static void rt6_exceptions_remove_prefsrc(struct fib6_info *rt)
{
struct rt6_exception_bucket *bucket;
struct rt6_exception *rt6_ex;
@@ -1667,7 +1666,7 @@ static bool rt6_mtu_change_route_allowed(struct inet6_dev *idev,
}
static void rt6_exceptions_update_pmtu(struct inet6_dev *idev,
- struct rt6_info *rt, int mtu)
+ struct fib6_info *rt, int mtu)
{
struct rt6_exception_bucket *bucket;
struct rt6_exception *rt6_ex;
@@ -1697,7 +1696,7 @@ static void rt6_exceptions_update_pmtu(struct inet6_dev *idev,
#define RTF_CACHE_GATEWAY (RTF_GATEWAY | RTF_CACHE)
-static void rt6_exceptions_clean_tohost(struct rt6_info *rt,
+static void rt6_exceptions_clean_tohost(struct fib6_info *rt,
struct in6_addr *gateway)
{
struct rt6_exception_bucket *bucket;
@@ -1776,7 +1775,7 @@ static void rt6_age_examine_exception(struct rt6_exception_bucket *bucket,
gc_args->more++;
}
-void rt6_age_exceptions(struct rt6_info *rt,
+void rt6_age_exceptions(struct fib6_info *rt,
struct fib6_gc_args *gc_args,
unsigned long now)
{
@@ -1812,7 +1811,7 @@ struct rt6_info *ip6_pol_route(struct net *net, struct fib6_table *table,
const struct sk_buff *skb, int flags)
{
struct fib6_node *fn, *saved_fn;
- struct rt6_info *f6i;
+ struct fib6_info *f6i;
struct rt6_info *rt;
int strict = 0;
@@ -2139,7 +2138,7 @@ struct dst_entry *ip6_blackhole_route(struct net *net, struct dst_entry *dst_ori
* Destination cache support functions
*/
-static bool fib6_check(struct rt6_info *f6i, u32 cookie)
+static bool fib6_check(struct fib6_info *f6i, u32 cookie)
{
u32 rt_cookie = 0;
@@ -2374,7 +2373,7 @@ static struct rt6_info *__ip6_route_redirect(struct net *net,
{
struct ip6rd_flowi *rdfl = (struct ip6rd_flowi *)fl6;
struct rt6_info *ret = NULL, *rt_cache;
- struct rt6_info *rt;
+ struct fib6_info *rt;
struct fib6_node *fn;
/* Get the "current" route for this destination and
@@ -2620,7 +2619,7 @@ static int ip6_dst_gc(struct dst_ops *ops)
return entries > rt_max_size;
}
-static int ip6_convert_metrics(struct net *net, struct rt6_info *rt,
+static int ip6_convert_metrics(struct net *net, struct fib6_info *rt,
struct fib6_config *cfg)
{
int err = 0;
@@ -2823,12 +2822,12 @@ static int ip6_validate_gw(struct net *net, struct fib6_config *cfg,
return err;
}
-static struct rt6_info *ip6_route_info_create(struct fib6_config *cfg,
+static struct fib6_info *ip6_route_info_create(struct fib6_config *cfg,
gfp_t gfp_flags,
struct netlink_ext_ack *extack)
{
struct net *net = cfg->fc_nlinfo.nl_net;
- struct rt6_info *rt = NULL;
+ struct fib6_info *rt = NULL;
struct net_device *dev = NULL;
struct inet6_dev *idev = NULL;
struct fib6_table *table;
@@ -3047,7 +3046,7 @@ static struct rt6_info *ip6_route_info_create(struct fib6_config *cfg,
int ip6_route_add(struct fib6_config *cfg, gfp_t gfp_flags,
struct netlink_ext_ack *extack)
{
- struct rt6_info *rt;
+ struct fib6_info *rt;
int err;
rt = ip6_route_info_create(cfg, gfp_flags, extack);
@@ -3060,7 +3059,7 @@ int ip6_route_add(struct fib6_config *cfg, gfp_t gfp_flags,
return err;
}
-static int __ip6_del_rt(struct rt6_info *rt, struct nl_info *info)
+static int __ip6_del_rt(struct fib6_info *rt, struct nl_info *info)
{
struct net *net = info->nl_net;
struct fib6_table *table;
@@ -3081,14 +3080,14 @@ static int __ip6_del_rt(struct rt6_info *rt, struct nl_info *info)
return err;
}
-int ip6_del_rt(struct net *net, struct rt6_info *rt)
+int ip6_del_rt(struct net *net, struct fib6_info *rt)
{
struct nl_info info = { .nl_net = net };
return __ip6_del_rt(rt, &info);
}
-static int __ip6_del_rt_siblings(struct rt6_info *rt, struct fib6_config *cfg)
+static int __ip6_del_rt_siblings(struct fib6_info *rt, struct fib6_config *cfg)
{
struct nl_info *info = &cfg->fc_nlinfo;
struct net *net = info->nl_net;
@@ -3102,7 +3101,7 @@ static int __ip6_del_rt_siblings(struct rt6_info *rt, struct fib6_config *cfg)
spin_lock_bh(&table->tb6_lock);
if (rt->rt6i_nsiblings && cfg->fc_delete_all_nh) {
- struct rt6_info *sibling, *next_sibling;
+ struct fib6_info *sibling, *next_sibling;
/* prefer to send a single notification with all hops */
skb = nlmsg_new(rt6_nlmsg_size(rt), gfp_any());
@@ -3159,8 +3158,9 @@ static int ip6_del_cached_rt(struct rt6_info *rt, struct fib6_config *cfg)
static int ip6_route_del(struct fib6_config *cfg,
struct netlink_ext_ack *extack)
{
- struct rt6_info *rt, *rt_cache;
+ struct rt6_info *rt_cache;
struct fib6_table *table;
+ struct fib6_info *rt;
struct fib6_node *fn;
int err = -ESRCH;
@@ -3336,7 +3336,7 @@ static void rt6_do_redirect(struct dst_entry *dst, struct sock *sk, struct sk_bu
}
#ifdef CONFIG_IPV6_ROUTE_INFO
-static struct rt6_info *rt6_get_route_info(struct net *net,
+static struct fib6_info *rt6_get_route_info(struct net *net,
const struct in6_addr *prefix, int prefixlen,
const struct in6_addr *gwaddr,
struct net_device *dev)
@@ -3344,7 +3344,7 @@ static struct rt6_info *rt6_get_route_info(struct net *net,
u32 tb_id = l3mdev_fib_table(dev) ? : RT6_TABLE_INFO;
int ifindex = dev->ifindex;
struct fib6_node *fn;
- struct rt6_info *rt = NULL;
+ struct fib6_info *rt = NULL;
struct fib6_table *table;
table = fib6_get_table(net, tb_id);
@@ -3363,7 +3363,7 @@ static struct rt6_info *rt6_get_route_info(struct net *net,
continue;
if (!ipv6_addr_equal(&rt->fib6_nh.nh_gw, gwaddr))
continue;
- ip6_hold_safe(NULL, &rt, false);
+ fib6_info_hold(rt);
break;
}
out:
@@ -3371,7 +3371,7 @@ static struct rt6_info *rt6_get_route_info(struct net *net,
return rt;
}
-static struct rt6_info *rt6_add_route_info(struct net *net,
+static struct fib6_info *rt6_add_route_info(struct net *net,
const struct in6_addr *prefix, int prefixlen,
const struct in6_addr *gwaddr,
struct net_device *dev,
@@ -3404,12 +3404,12 @@ static struct rt6_info *rt6_add_route_info(struct net *net,
}
#endif
-struct rt6_info *rt6_get_dflt_router(struct net *net,
+struct fib6_info *rt6_get_dflt_router(struct net *net,
const struct in6_addr *addr,
struct net_device *dev)
{
u32 tb_id = l3mdev_fib_table(dev) ? : RT6_TABLE_DFLT;
- struct rt6_info *rt;
+ struct fib6_info *rt;
struct fib6_table *table;
table = fib6_get_table(net, tb_id);
@@ -3424,12 +3424,12 @@ struct rt6_info *rt6_get_dflt_router(struct net *net,
break;
}
if (rt)
- ip6_hold_safe(NULL, &rt, false);
+ fib6_info_hold(rt);
rcu_read_unlock();
return rt;
}
-struct rt6_info *rt6_add_dflt_router(struct net *net,
+struct fib6_info *rt6_add_dflt_router(struct net *net,
const struct in6_addr *gwaddr,
struct net_device *dev,
unsigned int pref)
@@ -3463,7 +3463,7 @@ struct rt6_info *rt6_add_dflt_router(struct net *net,
static void __rt6_purge_dflt_routers(struct net *net,
struct fib6_table *table)
{
- struct rt6_info *rt;
+ struct fib6_info *rt;
restart:
rcu_read_lock();
@@ -3614,14 +3614,14 @@ static int ip6_pkt_prohibit_out(struct net *net, struct sock *sk, struct sk_buff
* Allocate a dst for local (unicast / anycast) address.
*/
-struct rt6_info *addrconf_dst_alloc(struct net *net,
+struct fib6_info *addrconf_dst_alloc(struct net *net,
struct inet6_dev *idev,
const struct in6_addr *addr,
bool anycast, gfp_t gfp_flags)
{
u32 tb_id;
struct net_device *dev = idev->dev;
- struct rt6_info *rt;
+ struct fib6_info *rt;
rt = fib6_info_alloc(gfp_flags);
if (!rt)
@@ -3661,7 +3661,7 @@ struct arg_dev_net_ip {
struct in6_addr *addr;
};
-static int fib6_remove_prefsrc(struct rt6_info *rt, void *arg)
+static int fib6_remove_prefsrc(struct fib6_info *rt, void *arg)
{
struct net_device *dev = ((struct arg_dev_net_ip *)arg)->dev;
struct net *net = ((struct arg_dev_net_ip *)arg)->net;
@@ -3694,7 +3694,7 @@ void rt6_remove_prefsrc(struct inet6_ifaddr *ifp)
#define RTF_RA_ROUTER (RTF_ADDRCONF | RTF_DEFAULT | RTF_GATEWAY)
/* Remove routers and update dst entries when gateway turn into host. */
-static int fib6_clean_tohost(struct rt6_info *rt, void *arg)
+static int fib6_clean_tohost(struct fib6_info *rt, void *arg)
{
struct in6_addr *gateway = (struct in6_addr *)arg;
@@ -3725,9 +3725,9 @@ struct arg_netdev_event {
};
};
-static struct rt6_info *rt6_multipath_first_sibling(const struct rt6_info *rt)
+static struct fib6_info *rt6_multipath_first_sibling(const struct fib6_info *rt)
{
- struct rt6_info *iter;
+ struct fib6_info *iter;
struct fib6_node *fn;
fn = rcu_dereference_protected(rt->rt6i_node,
@@ -3745,7 +3745,7 @@ static struct rt6_info *rt6_multipath_first_sibling(const struct rt6_info *rt)
return NULL;
}
-static bool rt6_is_dead(const struct rt6_info *rt)
+static bool rt6_is_dead(const struct fib6_info *rt)
{
if (rt->fib6_nh.nh_flags & RTNH_F_DEAD ||
(rt->fib6_nh.nh_flags & RTNH_F_LINKDOWN &&
@@ -3755,9 +3755,9 @@ static bool rt6_is_dead(const struct rt6_info *rt)
return false;
}
-static int rt6_multipath_total_weight(const struct rt6_info *rt)
+static int rt6_multipath_total_weight(const struct fib6_info *rt)
{
- struct rt6_info *iter;
+ struct fib6_info *iter;
int total = 0;
if (!rt6_is_dead(rt))
@@ -3771,7 +3771,7 @@ static int rt6_multipath_total_weight(const struct rt6_info *rt)
return total;
}
-static void rt6_upper_bound_set(struct rt6_info *rt, int *weight, int total)
+static void rt6_upper_bound_set(struct fib6_info *rt, int *weight, int total)
{
int upper_bound = -1;
@@ -3783,9 +3783,9 @@ static void rt6_upper_bound_set(struct rt6_info *rt, int *weight, int total)
atomic_set(&rt->fib6_nh.nh_upper_bound, upper_bound);
}
-static void rt6_multipath_upper_bound_set(struct rt6_info *rt, int total)
+static void rt6_multipath_upper_bound_set(struct fib6_info *rt, int total)
{
- struct rt6_info *iter;
+ struct fib6_info *iter;
int weight = 0;
rt6_upper_bound_set(rt, &weight, total);
@@ -3794,9 +3794,9 @@ static void rt6_multipath_upper_bound_set(struct rt6_info *rt, int total)
rt6_upper_bound_set(iter, &weight, total);
}
-void rt6_multipath_rebalance(struct rt6_info *rt)
+void rt6_multipath_rebalance(struct fib6_info *rt)
{
- struct rt6_info *first;
+ struct fib6_info *first;
int total;
/* In case the entire multipath route was marked for flushing,
@@ -3818,7 +3818,7 @@ void rt6_multipath_rebalance(struct rt6_info *rt)
rt6_multipath_upper_bound_set(first, total);
}
-static int fib6_ifup(struct rt6_info *rt, void *p_arg)
+static int fib6_ifup(struct fib6_info *rt, void *p_arg)
{
const struct arg_netdev_event *arg = p_arg;
struct net *net = dev_net(arg->dev);
@@ -3847,10 +3847,10 @@ void rt6_sync_up(struct net_device *dev, unsigned int nh_flags)
fib6_clean_all(dev_net(dev), fib6_ifup, &arg);
}
-static bool rt6_multipath_uses_dev(const struct rt6_info *rt,
+static bool rt6_multipath_uses_dev(const struct fib6_info *rt,
const struct net_device *dev)
{
- struct rt6_info *iter;
+ struct fib6_info *iter;
if (rt->fib6_nh.nh_dev == dev)
return true;
@@ -3861,19 +3861,19 @@ static bool rt6_multipath_uses_dev(const struct rt6_info *rt,
return false;
}
-static void rt6_multipath_flush(struct rt6_info *rt)
+static void rt6_multipath_flush(struct fib6_info *rt)
{
- struct rt6_info *iter;
+ struct fib6_info *iter;
rt->should_flush = 1;
list_for_each_entry(iter, &rt->rt6i_siblings, rt6i_siblings)
iter->should_flush = 1;
}
-static unsigned int rt6_multipath_dead_count(const struct rt6_info *rt,
+static unsigned int rt6_multipath_dead_count(const struct fib6_info *rt,
const struct net_device *down_dev)
{
- struct rt6_info *iter;
+ struct fib6_info *iter;
unsigned int dead = 0;
if (rt->fib6_nh.nh_dev == down_dev ||
@@ -3887,11 +3887,11 @@ static unsigned int rt6_multipath_dead_count(const struct rt6_info *rt,
return dead;
}
-static void rt6_multipath_nh_flags_set(struct rt6_info *rt,
+static void rt6_multipath_nh_flags_set(struct fib6_info *rt,
const struct net_device *dev,
unsigned int nh_flags)
{
- struct rt6_info *iter;
+ struct fib6_info *iter;
if (rt->fib6_nh.nh_dev == dev)
rt->fib6_nh.nh_flags |= nh_flags;
@@ -3901,7 +3901,7 @@ static void rt6_multipath_nh_flags_set(struct rt6_info *rt,
}
/* called with write lock held for table with rt */
-static int fib6_ifdown(struct rt6_info *rt, void *p_arg)
+static int fib6_ifdown(struct fib6_info *rt, void *p_arg)
{
const struct arg_netdev_event *arg = p_arg;
const struct net_device *dev = arg->dev;
@@ -3968,7 +3968,7 @@ struct rt6_mtu_change_arg {
unsigned int mtu;
};
-static int rt6_mtu_change_route(struct rt6_info *rt, void *p_arg)
+static int rt6_mtu_change_route(struct fib6_info *rt, void *p_arg)
{
struct rt6_mtu_change_arg *arg = (struct rt6_mtu_change_arg *) p_arg;
struct inet6_dev *idev;
@@ -4155,7 +4155,7 @@ static int rtm_to_fib6_config(struct sk_buff *skb, struct nlmsghdr *nlh,
}
struct rt6_nh {
- struct rt6_info *rt6_info;
+ struct fib6_info *fib6_info;
struct fib6_config r_cfg;
struct list_head next;
};
@@ -4173,21 +4173,22 @@ static void ip6_print_replace_route_err(struct list_head *rt6_nh_list)
static int ip6_route_info_append(struct net *net,
struct list_head *rt6_nh_list,
- struct rt6_info *rt, struct fib6_config *r_cfg)
+ struct fib6_info *rt,
+ struct fib6_config *r_cfg)
{
struct rt6_nh *nh;
int err = -EEXIST;
list_for_each_entry(nh, rt6_nh_list, next) {
- /* check if rt6_info already exists */
- if (rt6_duplicate_nexthop(nh->rt6_info, rt))
+ /* check if fib6_info already exists */
+ if (rt6_duplicate_nexthop(nh->fib6_info, rt))
return err;
}
nh = kzalloc(sizeof(*nh), GFP_KERNEL);
if (!nh)
return -ENOMEM;
- nh->rt6_info = rt;
+ nh->fib6_info = rt;
err = ip6_convert_metrics(net, rt, r_cfg);
if (err) {
kfree(nh);
@@ -4199,8 +4200,8 @@ static int ip6_route_info_append(struct net *net,
return 0;
}
-static void ip6_route_mpath_notify(struct rt6_info *rt,
- struct rt6_info *rt_last,
+static void ip6_route_mpath_notify(struct fib6_info *rt,
+ struct fib6_info *rt_last,
struct nl_info *info,
__u16 nlflags)
{
@@ -4212,7 +4213,7 @@ static void ip6_route_mpath_notify(struct rt6_info *rt,
*/
if ((nlflags & NLM_F_APPEND) && rt_last && rt_last->rt6i_nsiblings) {
rt = list_first_entry(&rt_last->rt6i_siblings,
- struct rt6_info,
+ struct fib6_info,
rt6i_siblings);
}
@@ -4223,11 +4224,11 @@ static void ip6_route_mpath_notify(struct rt6_info *rt,
static int ip6_route_multipath_add(struct fib6_config *cfg,
struct netlink_ext_ack *extack)
{
- struct rt6_info *rt_notif = NULL, *rt_last = NULL;
+ struct fib6_info *rt_notif = NULL, *rt_last = NULL;
struct nl_info *info = &cfg->fc_nlinfo;
struct fib6_config r_cfg;
struct rtnexthop *rtnh;
- struct rt6_info *rt;
+ struct fib6_info *rt;
struct rt6_nh *err_nh;
struct rt6_nh *nh, *nh_safe;
__u16 nlflags;
@@ -4247,7 +4248,7 @@ static int ip6_route_multipath_add(struct fib6_config *cfg,
rtnh = (struct rtnexthop *)cfg->fc_mp;
/* Parse a Multipath Entry and build a list (rt6_nh_list) of
- * rt6_info structs per nexthop
+ * fib6_info structs per nexthop
*/
while (rtnh_ok(rtnh, remaining)) {
memcpy(&r_cfg, cfg, sizeof(*cfg));
@@ -4297,16 +4298,16 @@ static int ip6_route_multipath_add(struct fib6_config *cfg,
err_nh = NULL;
list_for_each_entry(nh, &rt6_nh_list, next) {
- rt_last = nh->rt6_info;
- err = __ip6_ins_rt(nh->rt6_info, info, extack);
- fib6_info_release(nh->rt6_info);
+ rt_last = nh->fib6_info;
+ err = __ip6_ins_rt(nh->fib6_info, info, extack);
+ fib6_info_release(nh->fib6_info);
/* save reference to first route for notification */
if (!rt_notif && !err)
- rt_notif = nh->rt6_info;
+ rt_notif = nh->fib6_info;
- /* nh->rt6_info is used or freed at this point, reset to NULL*/
- nh->rt6_info = NULL;
+ /* nh->fib6_info is used or freed at this point, reset to NULL*/
+ nh->fib6_info = NULL;
if (err) {
if (replace && nhn)
ip6_print_replace_route_err(&rt6_nh_list);
@@ -4347,8 +4348,8 @@ static int ip6_route_multipath_add(struct fib6_config *cfg,
cleanup:
list_for_each_entry_safe(nh, nh_safe, &rt6_nh_list, next) {
- if (nh->rt6_info)
- fib6_info_release(nh->rt6_info);
+ if (nh->fib6_info)
+ fib6_info_release(nh->fib6_info);
list_del(&nh->next);
kfree(nh);
}
@@ -4428,7 +4429,7 @@ static int inet6_rtm_newroute(struct sk_buff *skb, struct nlmsghdr *nlh,
return ip6_route_add(&cfg, GFP_KERNEL, extack);
}
-static size_t rt6_nlmsg_size(struct rt6_info *rt)
+static size_t rt6_nlmsg_size(struct fib6_info *rt)
{
int nexthop_len = 0;
@@ -4458,7 +4459,7 @@ static size_t rt6_nlmsg_size(struct rt6_info *rt)
+ nexthop_len;
}
-static int rt6_nexthop_info(struct sk_buff *skb, struct rt6_info *rt,
+static int rt6_nexthop_info(struct sk_buff *skb, struct fib6_info *rt,
unsigned int *flags, bool skip_oif)
{
if (rt->fib6_nh.nh_flags & RTNH_F_DEAD)
@@ -4495,7 +4496,7 @@ static int rt6_nexthop_info(struct sk_buff *skb, struct rt6_info *rt,
}
/* add multipath next hop */
-static int rt6_add_nexthop(struct sk_buff *skb, struct rt6_info *rt)
+static int rt6_add_nexthop(struct sk_buff *skb, struct fib6_info *rt)
{
const struct net_device *dev = rt->fib6_nh.nh_dev;
struct rtnexthop *rtnh;
@@ -4523,7 +4524,7 @@ static int rt6_add_nexthop(struct sk_buff *skb, struct rt6_info *rt)
}
static int rt6_fill_node(struct net *net, struct sk_buff *skb,
- struct rt6_info *rt, struct dst_entry *dst,
+ struct fib6_info *rt, struct dst_entry *dst,
struct in6_addr *dest, struct in6_addr *src,
int iif, int type, u32 portid, u32 seq,
unsigned int flags)
@@ -4613,7 +4614,7 @@ static int rt6_fill_node(struct net *net, struct sk_buff *skb,
* each as a nexthop within RTA_MULTIPATH.
*/
if (rt->rt6i_nsiblings) {
- struct rt6_info *sibling, *next_sibling;
+ struct fib6_info *sibling, *next_sibling;
struct nlattr *mp;
mp = nla_nest_start(skb, RTA_MULTIPATH);
@@ -4655,7 +4656,7 @@ static int rt6_fill_node(struct net *net, struct sk_buff *skb,
return -EMSGSIZE;
}
-int rt6_dump_route(struct rt6_info *rt, void *p_arg)
+int rt6_dump_route(struct fib6_info *rt, void *p_arg)
{
struct rt6_rtnl_dump_arg *arg = (struct rt6_rtnl_dump_arg *) p_arg;
struct net *net = arg->net;
@@ -4800,7 +4801,7 @@ static int inet6_rtm_getroute(struct sk_buff *in_skb, struct nlmsghdr *nlh,
return err;
}
-void inet6_rt_notify(int event, struct rt6_info *rt, struct nl_info *info,
+void inet6_rt_notify(int event, struct fib6_info *rt, struct nl_info *info,
unsigned int nlm_flags)
{
struct sk_buff *skb;
--
2.11.0
^ permalink raw reply related
* [PATCH net-next v2 19/21] net/ipv6: separate handling of FIB entries from dst based routes
From: David Ahern @ 2018-04-18 0:33 UTC (permalink / raw)
To: netdev
Cc: davem, idosch, roopa, eric.dumazet, weiwan, kafai, yoshfuji,
David Ahern
In-Reply-To: <20180418003327.19992-1-dsahern@gmail.com>
Last step before flipping the data type for FIB entries:
- use fib6_info_alloc to create FIB entries in ip6_route_info_create
and addrconf_dst_alloc
- use fib6_info_release in place of dst_release, ip6_rt_put and
rt6_release
- remove the dst_hold before calling __ip6_ins_rt or ip6_del_rt
- when purging routes, drop per-cpu routes
- replace inc and dec of rt6i_ref with fib6_info_hold and fib6_info_release
- use rt->from since it points to the FIB entry
- drop references to exception bucket, fib6_metrics and per-cpu from
dst entries (those are relevant for fib entries only)
Signed-off-by: David Ahern <dsahern@gmail.com>
---
include/net/ip6_fib.h | 4 +-
include/net/ip6_route.h | 3 +-
net/ipv6/addrconf.c | 18 +++--
net/ipv6/anycast.c | 7 +-
net/ipv6/ip6_fib.c | 55 ++++++++++------
net/ipv6/ip6_output.c | 3 +-
net/ipv6/ndisc.c | 6 +-
net/ipv6/route.c | 171 +++++++++++++++++-------------------------------
8 files changed, 115 insertions(+), 152 deletions(-)
diff --git a/include/net/ip6_fib.h b/include/net/ip6_fib.h
index 630392ae12d8..6c3d92bb3459 100644
--- a/include/net/ip6_fib.h
+++ b/include/net/ip6_fib.h
@@ -314,9 +314,7 @@ static inline u32 rt6_get_cookie(const struct rt6_info *rt)
if (rt->rt6i_flags & RTF_PCPU ||
(unlikely(!list_empty(&rt->rt6i_uncached)) && rt->from))
- rt = rt->from;
-
- rt6_get_cookie_safe(rt, &cookie);
+ rt6_get_cookie_safe(rt->from, &cookie);
return cookie;
}
diff --git a/include/net/ip6_route.h b/include/net/ip6_route.h
index 686cdc7f356a..57d0d45667f1 100644
--- a/include/net/ip6_route.h
+++ b/include/net/ip6_route.h
@@ -114,8 +114,7 @@ static inline int ip6_route_get_saddr(struct net *net, struct rt6_info *rt,
unsigned int prefs,
struct in6_addr *saddr)
{
- struct inet6_dev *idev =
- rt ? ip6_dst_idev((struct dst_entry *)rt) : NULL;
+ struct inet6_dev *idev = rt ? rt->rt6i_idev : NULL;
int err = 0;
if (rt && rt->rt6i_prefsrc.plen)
diff --git a/net/ipv6/addrconf.c b/net/ipv6/addrconf.c
index 915cd0734b27..e533a447f68c 100644
--- a/net/ipv6/addrconf.c
+++ b/net/ipv6/addrconf.c
@@ -916,7 +916,6 @@ void inet6_ifa_finish_destroy(struct inet6_ifaddr *ifp)
pr_warn("Freeing alive inet6 address %p\n", ifp);
return;
}
- ip6_rt_put(ifp->rt);
kfree_rcu(ifp, rcu);
}
@@ -1102,8 +1101,8 @@ ipv6_add_addr(struct inet6_dev *idev, const struct in6_addr *addr,
inet6addr_notifier_call_chain(NETDEV_UP, ifa);
out:
if (unlikely(err < 0)) {
- if (rt)
- ip6_rt_put(rt);
+ fib6_info_release(rt);
+
if (ifa) {
if (ifa->idev)
in6_dev_put(ifa->idev);
@@ -1191,7 +1190,7 @@ cleanup_prefix_route(struct inet6_ifaddr *ifp, unsigned long expires, bool del_r
else {
if (!(rt->rt6i_flags & RTF_EXPIRES))
fib6_set_expires(rt, expires);
- ip6_rt_put(rt);
+ fib6_info_release(rt);
}
}
}
@@ -2375,8 +2374,7 @@ static struct rt6_info *addrconf_get_prefix_route(const struct in6_addr *pfx,
continue;
if ((rt->rt6i_flags & noflags) != 0)
continue;
- if (!dst_hold_safe(&rt->dst))
- rt = NULL;
+ fib6_info_hold(rt);
break;
}
out:
@@ -2687,7 +2685,7 @@ void addrconf_prefix_rcv(struct net_device *dev, u8 *opt, int len, bool sllao)
addrconf_prefix_route(&pinfo->prefix, pinfo->prefix_len,
dev, expires, flags, GFP_ATOMIC);
}
- ip6_rt_put(rt);
+ fib6_info_release(rt);
}
/* Try to figure out our local address for this prefix */
@@ -3361,7 +3359,7 @@ static int fixup_permanent_addr(struct net *net,
ifp->rt = rt;
spin_unlock(&ifp->lock);
- ip6_rt_put(prev);
+ fib6_info_release(prev);
}
if (!(ifp->flags & IFA_F_NOPREFIXROUTE)) {
@@ -5636,8 +5634,8 @@ static void __ipv6_ifa_notify(int event, struct inet6_ifaddr *ifp)
ip6_del_rt(net, rt);
}
if (ifp->rt) {
- if (dst_hold_safe(&ifp->rt->dst))
- ip6_del_rt(net, ifp->rt);
+ ip6_del_rt(net, ifp->rt);
+ ifp->rt = NULL;
}
rt_genid_bump_ipv6(net);
break;
diff --git a/net/ipv6/anycast.c b/net/ipv6/anycast.c
index e456386fe4d5..3db8fe10322b 100644
--- a/net/ipv6/anycast.c
+++ b/net/ipv6/anycast.c
@@ -213,7 +213,7 @@ static void aca_put(struct ifacaddr6 *ac)
{
if (refcount_dec_and_test(&ac->aca_refcnt)) {
in6_dev_put(ac->aca_idev);
- dst_release(&ac->aca_rt->dst);
+ fib6_info_release(ac->aca_rt);
kfree(ac);
}
}
@@ -231,6 +231,7 @@ static struct ifacaddr6 *aca_alloc(struct rt6_info *rt,
aca->aca_addr = *addr;
in6_dev_hold(idev);
aca->aca_idev = idev;
+ fib6_info_hold(rt);
aca->aca_rt = rt;
aca->aca_users = 1;
/* aca_tstamp should be updated upon changes */
@@ -274,7 +275,7 @@ int __ipv6_dev_ac_inc(struct inet6_dev *idev, const struct in6_addr *addr)
}
aca = aca_alloc(rt, addr);
if (!aca) {
- ip6_rt_put(rt);
+ fib6_info_release(rt);
err = -ENOMEM;
goto out;
}
@@ -330,7 +331,6 @@ int __ipv6_dev_ac_dec(struct inet6_dev *idev, const struct in6_addr *addr)
write_unlock_bh(&idev->lock);
addrconf_leave_solict(idev, &aca->aca_addr);
- dst_hold(&aca->aca_rt->dst);
ip6_del_rt(dev_net(idev->dev), aca->aca_rt);
aca_put(aca);
@@ -358,7 +358,6 @@ void ipv6_ac_destroy_dev(struct inet6_dev *idev)
addrconf_leave_solict(idev, &aca->aca_addr);
- dst_hold(&aca->aca_rt->dst);
ip6_del_rt(dev_net(idev->dev), aca->aca_rt);
aca_put(aca);
diff --git a/net/ipv6/ip6_fib.c b/net/ipv6/ip6_fib.c
index d07578d84db0..4d6bd033dccd 100644
--- a/net/ipv6/ip6_fib.c
+++ b/net/ipv6/ip6_fib.c
@@ -170,6 +170,7 @@ struct rt6_info *fib6_info_alloc(gfp_t gfp_flags)
void fib6_info_destroy(struct rt6_info *f6i)
{
struct rt6_exception_bucket *bucket;
+ struct dst_metrics *m;
WARN_ON(f6i->rt6i_node);
@@ -201,6 +202,10 @@ void fib6_info_destroy(struct rt6_info *f6i)
if (f6i->fib6_nh.nh_dev)
dev_put(f6i->fib6_nh.nh_dev);
+ m = f6i->fib6_metrics;
+ if (m != &dst_default_metrics && refcount_dec_and_test(&m->refcnt))
+ kfree(m);
+
kfree(f6i);
}
EXPORT_SYMBOL_GPL(fib6_info_destroy);
@@ -714,7 +719,7 @@ static struct fib6_node *fib6_add_1(struct net *net,
/* clean up an intermediate node */
if (!(fn->fn_flags & RTN_RTINFO)) {
RCU_INIT_POINTER(fn->leaf, NULL);
- rt6_release(leaf);
+ fib6_info_release(leaf);
/* remove null_entry in the root node */
} else if (fn->fn_flags & RTN_TL_ROOT &&
rcu_access_pointer(fn->leaf) ==
@@ -898,12 +903,32 @@ static void fib6_purge_rt(struct rt6_info *rt, struct fib6_node *fn,
if (!(fn->fn_flags & RTN_RTINFO) && leaf == rt) {
new_leaf = fib6_find_prefix(net, table, fn);
atomic_inc(&new_leaf->rt6i_ref);
+
rcu_assign_pointer(fn->leaf, new_leaf);
- rt6_release(rt);
+ fib6_info_release(rt);
}
fn = rcu_dereference_protected(fn->parent,
lockdep_is_held(&table->tb6_lock));
}
+
+ if (rt->rt6i_pcpu) {
+ int cpu;
+
+ /* release the reference to this fib entry from
+ * all of its cached pcpu routes
+ */
+ for_each_possible_cpu(cpu) {
+ struct rt6_info **ppcpu_rt;
+ struct rt6_info *pcpu_rt;
+
+ ppcpu_rt = per_cpu_ptr(rt->rt6i_pcpu, cpu);
+ pcpu_rt = *ppcpu_rt;
+ if (pcpu_rt) {
+ fib6_info_release(pcpu_rt->from);
+ pcpu_rt->from = NULL;
+ }
+ }
+ }
}
}
@@ -1099,7 +1124,7 @@ static int fib6_add_rt2node(struct fib6_node *fn, struct rt6_info *rt,
fib6_purge_rt(iter, fn, info->nl_net);
if (rcu_access_pointer(fn->rr_ptr) == iter)
fn->rr_ptr = NULL;
- rt6_release(iter);
+ fib6_info_release(iter);
if (nsiblings) {
/* Replacing an ECMP route, remove all siblings */
@@ -1115,7 +1140,7 @@ static int fib6_add_rt2node(struct fib6_node *fn, struct rt6_info *rt,
fib6_purge_rt(iter, fn, info->nl_net);
if (rcu_access_pointer(fn->rr_ptr) == iter)
fn->rr_ptr = NULL;
- rt6_release(iter);
+ fib6_info_release(iter);
nsiblings--;
info->nl_net->ipv6.rt6_stats->fib_rt_entries--;
} else {
@@ -1183,9 +1208,6 @@ int fib6_add(struct fib6_node *root, struct rt6_info *rt,
int replace_required = 0;
int sernum = fib6_new_sernum(info->nl_net);
- if (WARN_ON_ONCE(!atomic_read(&rt->dst.__refcnt)))
- return -EINVAL;
-
if (info->nlh) {
if (!(info->nlh->nlmsg_flags & NLM_F_CREATE))
allow_create = 0;
@@ -1300,7 +1322,7 @@ int fib6_add(struct fib6_node *root, struct rt6_info *rt,
if (pn_leaf == rt) {
pn_leaf = NULL;
RCU_INIT_POINTER(pn->leaf, NULL);
- atomic_dec(&rt->rt6i_ref);
+ fib6_info_release(rt);
}
if (!pn_leaf && !(pn->fn_flags & RTN_RTINFO)) {
pn_leaf = fib6_find_prefix(info->nl_net, table,
@@ -1312,7 +1334,7 @@ int fib6_add(struct fib6_node *root, struct rt6_info *rt,
info->nl_net->ipv6.fib6_null_entry;
}
#endif
- atomic_inc(&pn_leaf->rt6i_ref);
+ fib6_info_hold(pn_leaf);
rcu_assign_pointer(pn->leaf, pn_leaf);
}
}
@@ -1334,10 +1356,6 @@ int fib6_add(struct fib6_node *root, struct rt6_info *rt,
(fn->fn_flags & RTN_TL_ROOT &&
!rcu_access_pointer(fn->leaf))))
fib6_repair_tree(info->nl_net, table, fn);
- /* Always release dst as dst->__refcnt is guaranteed
- * to be taken before entering this function
- */
- dst_release_immediate(&rt->dst);
return err;
}
@@ -1637,7 +1655,7 @@ static struct fib6_node *fib6_repair_tree(struct net *net,
new_fn_leaf = net->ipv6.fib6_null_entry;
}
#endif
- atomic_inc(&new_fn_leaf->rt6i_ref);
+ fib6_info_hold(new_fn_leaf);
rcu_assign_pointer(fn->leaf, new_fn_leaf);
return pn;
}
@@ -1693,7 +1711,7 @@ static struct fib6_node *fib6_repair_tree(struct net *net,
return pn;
RCU_INIT_POINTER(pn->leaf, NULL);
- rt6_release(pn_leaf);
+ fib6_info_release(pn_leaf);
fn = pn;
}
}
@@ -1763,7 +1781,7 @@ static void fib6_del_route(struct fib6_table *table, struct fib6_node *fn,
call_fib6_entry_notifiers(net, FIB_EVENT_ENTRY_DEL, rt, NULL);
if (!info->skip_notify)
inet6_rt_notify(RTM_DELROUTE, rt, info, 0);
- rt6_release(rt);
+ fib6_info_release(rt);
}
/* Need to own table->tb6_lock */
@@ -2261,9 +2279,8 @@ static int ipv6_route_seq_show(struct seq_file *seq, void *v)
dev = rt->fib6_nh.nh_dev;
seq_printf(seq, " %08x %08x %08x %08x %8s\n",
- rt->rt6i_metric, atomic_read(&rt->dst.__refcnt),
- rt->dst.__use, rt->rt6i_flags,
- dev ? dev->name : "");
+ rt->rt6i_metric, atomic_read(&rt->rt6i_ref), 0,
+ rt->rt6i_flags, dev ? dev->name : "");
iter->w.leaf = NULL;
return 0;
}
diff --git a/net/ipv6/ip6_output.c b/net/ipv6/ip6_output.c
index a39b04f9fa6e..3db47986ef38 100644
--- a/net/ipv6/ip6_output.c
+++ b/net/ipv6/ip6_output.c
@@ -968,7 +968,8 @@ static int ip6_dst_lookup_tail(struct net *net, const struct sock *sk,
if (!had_dst)
*dst = ip6_route_output(net, sk, fl6);
rt = (*dst)->error ? NULL : (struct rt6_info *)*dst;
- err = ip6_route_get_saddr(net, rt, &fl6->daddr,
+ err = ip6_route_get_saddr(net, rt ? rt->from : NULL,
+ &fl6->daddr,
sk ? inet6_sk(sk)->srcprefs : 0,
&fl6->saddr);
if (err)
diff --git a/net/ipv6/ndisc.c b/net/ipv6/ndisc.c
index 556717154fa3..a28857088bff 100644
--- a/net/ipv6/ndisc.c
+++ b/net/ipv6/ndisc.c
@@ -1283,7 +1283,7 @@ static void ndisc_router_discovery(struct sk_buff *skb)
ND_PRINTK(0, err,
"RA: %s got default router without neighbour\n",
__func__);
- ip6_rt_put(rt);
+ fib6_info_release(rt);
return;
}
}
@@ -1313,7 +1313,7 @@ static void ndisc_router_discovery(struct sk_buff *skb)
ND_PRINTK(0, err,
"RA: %s got default router without neighbour\n",
__func__);
- ip6_rt_put(rt);
+ fib6_info_release(rt);
return;
}
neigh->flags |= NTF_ROUTER;
@@ -1499,7 +1499,7 @@ static void ndisc_router_discovery(struct sk_buff *skb)
ND_PRINTK(2, warn, "RA: invalid RA options\n");
}
out:
- ip6_rt_put(rt);
+ fib6_info_release(rt);
if (neigh)
neigh_release(neigh);
}
diff --git a/net/ipv6/route.c b/net/ipv6/route.c
index ad9eaecf539c..0d861bd07673 100644
--- a/net/ipv6/route.c
+++ b/net/ipv6/route.c
@@ -351,13 +351,11 @@ static void rt6_info_init(struct rt6_info *rt)
memset(dst + 1, 0, sizeof(*rt) - sizeof(*dst));
INIT_LIST_HEAD(&rt->rt6i_siblings);
INIT_LIST_HEAD(&rt->rt6i_uncached);
- rt->fib6_metrics = (struct dst_metrics *)&dst_default_metrics;
}
/* allocate dst with ip6_dst_ops */
-static struct rt6_info *__ip6_dst_alloc(struct net *net,
- struct net_device *dev,
- int flags)
+struct rt6_info *ip6_dst_alloc(struct net *net, struct net_device *dev,
+ int flags)
{
struct rt6_info *rt = dst_alloc(&net->ipv6.ip6_dst_ops, dev,
1, DST_OBSOLETE_FORCE_CHK, flags);
@@ -369,35 +367,15 @@ static struct rt6_info *__ip6_dst_alloc(struct net *net,
return rt;
}
-
-struct rt6_info *ip6_dst_alloc(struct net *net,
- struct net_device *dev,
- int flags)
-{
- struct rt6_info *rt = __ip6_dst_alloc(net, dev, flags);
-
- if (rt) {
- rt->rt6i_pcpu = alloc_percpu_gfp(struct rt6_info *, GFP_ATOMIC);
- if (!rt->rt6i_pcpu) {
- dst_release_immediate(&rt->dst);
- return NULL;
- }
- }
-
- return rt;
-}
EXPORT_SYMBOL(ip6_dst_alloc);
static void ip6_dst_destroy(struct dst_entry *dst)
{
struct rt6_info *rt = (struct rt6_info *)dst;
- struct rt6_exception_bucket *bucket;
struct rt6_info *from = rt->from;
struct inet6_dev *idev;
- struct dst_metrics *m;
dst_destroy_metrics_generic(dst);
- free_percpu(rt->rt6i_pcpu);
rt6_uncached_list_del(rt);
idev = rt->rt6i_idev;
@@ -405,18 +383,9 @@ static void ip6_dst_destroy(struct dst_entry *dst)
rt->rt6i_idev = NULL;
in6_dev_put(idev);
}
- bucket = rcu_dereference_protected(rt->rt6i_exception_bucket, 1);
- if (bucket) {
- rt->rt6i_exception_bucket = NULL;
- kfree(bucket);
- }
-
- m = rt->fib6_metrics;
- if (m != &dst_default_metrics && refcount_dec_and_test(&m->refcnt))
- kfree(m);
rt->from = NULL;
- dst_release(&from->dst);
+ fib6_info_release(from);
}
static void ip6_dst_ifdown(struct dst_entry *dst, struct net_device *dev,
@@ -891,7 +860,7 @@ int rt6_route_rcv(struct net_device *dev, u8 *opt, int len,
else
fib6_set_expires(rt, jiffies + HZ * lifetime);
- ip6_rt_put(rt);
+ fib6_info_release(rt);
}
return 0;
}
@@ -1010,11 +979,9 @@ static void ip6_rt_init_dst(struct rt6_info *rt, struct rt6_info *ort)
static void rt6_set_from(struct rt6_info *rt, struct rt6_info *from)
{
- BUG_ON(from->from);
-
rt->rt6i_flags &= ~RTF_EXPIRES;
- if (dst_hold_safe(&from->dst))
- rt->from = from;
+ fib6_info_hold(from);
+ rt->from = from;
dst_init_metrics(&rt->dst, from->fib6_metrics->metrics, true);
if (from->fib6_metrics != &dst_default_metrics) {
rt->dst._metrics |= DST_METRICS_REFCOUNTED;
@@ -1084,7 +1051,7 @@ static struct rt6_info *ip6_create_rt_rcu(struct rt6_info *rt)
struct net_device *dev = rt->fib6_nh.nh_dev;
struct rt6_info *nrt;
- nrt = __ip6_dst_alloc(dev_net(dev), dev, flags);
+ nrt = ip6_dst_alloc(dev_net(dev), dev, flags);
if (nrt)
ip6_rt_copy_init(nrt, rt);
@@ -1203,8 +1170,6 @@ int ip6_ins_rt(struct net *net, struct rt6_info *rt)
{
struct nl_info info = { .nl_net = net, };
- /* Hold dst to account for the reference from the fib6 tree */
- dst_hold(&rt->dst);
return __ip6_ins_rt(rt, &info, NULL);
}
@@ -1221,7 +1186,7 @@ static struct rt6_info *ip6_rt_cache_alloc(struct rt6_info *ort,
rcu_read_lock();
dev = ip6_rt_get_dev_rcu(ort);
- rt = __ip6_dst_alloc(dev_net(dev), dev, 0);
+ rt = ip6_dst_alloc(dev_net(dev), dev, 0);
rcu_read_unlock();
if (!rt)
return NULL;
@@ -1256,7 +1221,7 @@ static struct rt6_info *ip6_rt_pcpu_alloc(struct rt6_info *rt)
rcu_read_lock();
dev = ip6_rt_get_dev_rcu(rt);
- pcpu_rt = __ip6_dst_alloc(dev_net(dev), dev, flags);
+ pcpu_rt = ip6_dst_alloc(dev_net(dev), dev, flags);
rcu_read_unlock();
if (!pcpu_rt)
return NULL;
@@ -1317,7 +1282,7 @@ static void rt6_remove_exception(struct rt6_exception_bucket *bucket,
net = dev_net(rt6_ex->rt6i->dst.dev);
rt6_ex->rt6i->rt6i_node = NULL;
hlist_del_rcu(&rt6_ex->hlist);
- rt6_release(rt6_ex->rt6i);
+ ip6_rt_put(rt6_ex->rt6i);
kfree_rcu(rt6_ex, rcu);
WARN_ON_ONCE(!bucket->depth);
bucket->depth--;
@@ -1907,17 +1872,11 @@ struct rt6_info *ip6_pol_route(struct net *net, struct fib6_table *table,
struct rt6_info *uncached_rt;
- if (ip6_hold_safe(net, &f6i, true)) {
- dst_use_noref(&f6i->dst, jiffies);
- } else {
- rcu_read_unlock();
- uncached_rt = f6i;
- goto uncached_rt_out;
- }
+ fib6_info_hold(f6i);
rcu_read_unlock();
uncached_rt = ip6_rt_cache_alloc(f6i, &fl6->daddr, NULL);
- dst_release(&rt->dst);
+ fib6_info_release(f6i);
if (uncached_rt) {
/* Uncached_rt's refcnt is taken during ip6_rt_cache_alloc()
@@ -1930,7 +1889,6 @@ struct rt6_info *ip6_pol_route(struct net *net, struct fib6_table *table,
dst_hold(&uncached_rt->dst);
}
-uncached_rt_out:
trace_fib6_table_lookup(net, uncached_rt, table, fl6);
return uncached_rt;
@@ -1939,24 +1897,12 @@ struct rt6_info *ip6_pol_route(struct net *net, struct fib6_table *table,
struct rt6_info *pcpu_rt;
- dst_use_noref(&f6i->dst, jiffies);
local_bh_disable();
pcpu_rt = rt6_get_pcpu_route(f6i);
- if (!pcpu_rt) {
- /* atomic_inc_not_zero() is needed when using rcu */
- if (atomic_inc_not_zero(&f6i->rt6i_ref)) {
- /* No dst_hold() on rt is needed because grabbing
- * rt->rt6i_ref makes sure rt can't be released.
- */
- pcpu_rt = rt6_make_pcpu_route(net, f6i);
- rt6_release(f6i);
- } else {
- /* rt is already removed from tree */
- pcpu_rt = net->ipv6.ip6_null_entry;
- dst_hold(&pcpu_rt->dst);
- }
- }
+ if (!pcpu_rt)
+ pcpu_rt = rt6_make_pcpu_route(net, f6i);
+
local_bh_enable();
rcu_read_unlock();
trace_fib6_table_lookup(net, pcpu_rt, table, fl6);
@@ -2193,11 +2139,26 @@ struct dst_entry *ip6_blackhole_route(struct net *net, struct dst_entry *dst_ori
* Destination cache support functions
*/
+static bool fib6_check(struct rt6_info *f6i, u32 cookie)
+{
+ u32 rt_cookie = 0;
+
+ if ((f6i && !rt6_get_cookie_safe(f6i, &rt_cookie)) ||
+ rt_cookie != cookie)
+ return false;
+
+ if (fib6_check_expired(f6i))
+ return false;
+
+ return true;
+}
+
static struct dst_entry *rt6_check(struct rt6_info *rt, u32 cookie)
{
u32 rt_cookie = 0;
- if (!rt6_get_cookie_safe(rt, &rt_cookie) || rt_cookie != cookie)
+ if ((rt->from && !rt6_get_cookie_safe(rt->from, &rt_cookie)) ||
+ rt_cookie != cookie)
return NULL;
if (rt6_check_expired(rt))
@@ -2210,7 +2171,7 @@ static struct dst_entry *rt6_dst_from_check(struct rt6_info *rt, u32 cookie)
{
if (!__rt6_check_expired(rt) &&
rt->dst.obsolete == DST_OBSOLETE_FORCE_CHK &&
- rt6_check(rt->from, cookie))
+ fib6_check(rt->from, cookie))
return &rt->dst;
else
return NULL;
@@ -2241,7 +2202,7 @@ static struct dst_entry *ip6_negative_advice(struct dst_entry *dst)
if (rt) {
if (rt->rt6i_flags & RTF_CACHE) {
if (rt6_check_expired(rt)) {
- ip6_del_rt(dev_net(dst->dev), rt);
+ rt6_remove_exception_rt(rt);
dst = NULL;
}
} else {
@@ -2262,12 +2223,12 @@ static void ip6_link_failure(struct sk_buff *skb)
if (rt) {
if (rt->rt6i_flags & RTF_CACHE) {
if (dst_hold_safe(&rt->dst))
- ip6_del_rt(dev_net(rt->dst.dev), rt);
- } else {
+ rt6_remove_exception_rt(rt);
+ } else if (rt->from) {
struct fib6_node *fn;
rcu_read_lock();
- fn = rcu_dereference(rt->rt6i_node);
+ fn = rcu_dereference(rt->from->rt6i_node);
if (fn && (rt->rt6i_flags & RTF_DEFAULT))
fn->fn_sernum = -1;
rcu_read_unlock();
@@ -2949,13 +2910,13 @@ static struct rt6_info *ip6_route_info_create(struct fib6_config *cfg,
if (!table)
goto out;
- rt = ip6_dst_alloc(net, NULL,
- (cfg->fc_flags & RTF_ADDRCONF) ? 0 : DST_NOCOUNT);
-
- if (!rt) {
- err = -ENOMEM;
+ err = -ENOMEM;
+ rt = fib6_info_alloc(gfp_flags);
+ if (!rt)
goto out;
- }
+
+ if (cfg->fc_flags & RTF_ADDRCONF)
+ rt->dst_nocount = true;
err = ip6_convert_metrics(net, rt, cfg);
if (err < 0)
@@ -3029,7 +2990,7 @@ static struct rt6_info *ip6_route_info_create(struct fib6_config *cfg,
if (err)
goto out;
- rt->fib6_nh.nh_gw = rt->rt6i_gateway = cfg->fc_gateway;
+ rt->fib6_nh.nh_gw = cfg->fc_gateway;
}
err = -ENODEV;
@@ -3066,7 +3027,7 @@ static struct rt6_info *ip6_route_info_create(struct fib6_config *cfg,
!netif_carrier_ok(dev))
rt->fib6_nh.nh_flags |= RTNH_F_LINKDOWN;
rt->fib6_nh.nh_flags |= (cfg->fc_flags & RTNH_F_ONLINK);
- rt->fib6_nh.nh_dev = rt->dst.dev = dev;
+ rt->fib6_nh.nh_dev = dev;
rt->rt6i_idev = idev;
rt->rt6i_table = table;
@@ -3078,9 +3039,8 @@ static struct rt6_info *ip6_route_info_create(struct fib6_config *cfg,
dev_put(dev);
if (idev)
in6_dev_put(idev);
- if (rt)
- dst_release_immediate(&rt->dst);
+ fib6_info_release(rt);
return ERR_PTR(err);
}
@@ -3095,6 +3055,7 @@ int ip6_route_add(struct fib6_config *cfg, gfp_t gfp_flags,
return PTR_ERR(rt);
err = __ip6_ins_rt(rt, &cfg->fc_nlinfo, extack);
+ fib6_info_release(rt);
return err;
}
@@ -3116,7 +3077,7 @@ static int __ip6_del_rt(struct rt6_info *rt, struct nl_info *info)
spin_unlock_bh(&table->tb6_lock);
out:
- ip6_rt_put(rt);
+ fib6_info_release(rt);
return err;
}
@@ -3170,7 +3131,7 @@ static int __ip6_del_rt_siblings(struct rt6_info *rt, struct fib6_config *cfg)
out_unlock:
spin_unlock_bh(&table->tb6_lock);
out_put:
- ip6_rt_put(rt);
+ fib6_info_release(rt);
if (skb) {
rtnl_notify(skb, net, info->portid, RTNLGRP_IPV6_ROUTE,
@@ -3241,8 +3202,7 @@ static int ip6_route_del(struct fib6_config *cfg,
continue;
if (cfg->fc_protocol && cfg->fc_protocol != rt->rt6i_protocol)
continue;
- if (!dst_hold_safe(&rt->dst))
- break;
+ fib6_info_hold(rt);
rcu_read_unlock();
/* if gateway was specified only delete the one hop */
@@ -3510,12 +3470,9 @@ static void __rt6_purge_dflt_routers(struct net *net,
for_each_fib6_node_rt_rcu(&table->tb6_root) {
if (rt->rt6i_flags & (RTF_DEFAULT | RTF_ADDRCONF) &&
(!rt->rt6i_idev || rt->rt6i_idev->cnf.accept_ra != 2)) {
- if (dst_hold_safe(&rt->dst)) {
- rcu_read_unlock();
- ip6_del_rt(net, rt);
- } else {
- rcu_read_unlock();
- }
+ fib6_info_hold(rt);
+ rcu_read_unlock();
+ ip6_del_rt(net, rt);
goto restart;
}
}
@@ -3666,7 +3623,7 @@ struct rt6_info *addrconf_dst_alloc(struct net *net,
struct net_device *dev = idev->dev;
struct rt6_info *rt;
- rt = ip6_dst_alloc(net, dev, DST_NOCOUNT);
+ rt = fib6_info_alloc(gfp_flags);
if (!rt)
return ERR_PTR(-ENOMEM);
@@ -3687,8 +3644,8 @@ struct rt6_info *addrconf_dst_alloc(struct net *net,
}
rt->fib6_nh.nh_gw = *addr;
+ dev_hold(dev);
rt->fib6_nh.nh_dev = dev;
- rt->rt6i_gateway = *addr;
rt->rt6i_dst.addr = *addr;
rt->rt6i_dst.plen = 128;
tb_id = l3mdev_fib_table(idev->dev) ? : RT6_TABLE_LOCAL;
@@ -4325,7 +4282,7 @@ static int ip6_route_multipath_add(struct fib6_config *cfg,
err = ip6_route_info_append(info->nl_net, &rt6_nh_list,
rt, &r_cfg);
if (err) {
- dst_release_immediate(&rt->dst);
+ fib6_info_release(rt);
goto cleanup;
}
@@ -4342,6 +4299,8 @@ static int ip6_route_multipath_add(struct fib6_config *cfg,
list_for_each_entry(nh, &rt6_nh_list, next) {
rt_last = nh->rt6_info;
err = __ip6_ins_rt(nh->rt6_info, info, extack);
+ fib6_info_release(nh->rt6_info);
+
/* save reference to first route for notification */
if (!rt_notif && !err)
rt_notif = nh->rt6_info;
@@ -4389,7 +4348,7 @@ static int ip6_route_multipath_add(struct fib6_config *cfg,
cleanup:
list_for_each_entry_safe(nh, nh_safe, &rt6_nh_list, next) {
if (nh->rt6_info)
- dst_release_immediate(&nh->rt6_info->dst);
+ fib6_info_release(nh->rt6_info);
list_del(&nh->next);
kfree(nh);
}
@@ -4814,14 +4773,6 @@ static int inet6_rtm_getroute(struct sk_buff *in_skb, struct nlmsghdr *nlh,
goto errout;
}
- if (fibmatch && rt->from) {
- struct rt6_info *ort = rt->from;
-
- dst_hold(&ort->dst);
- ip6_rt_put(rt);
- rt = ort;
- }
-
skb = alloc_skb(NLMSG_GOODSIZE, GFP_KERNEL);
if (!skb) {
ip6_rt_put(rt);
@@ -4831,12 +4782,12 @@ static int inet6_rtm_getroute(struct sk_buff *in_skb, struct nlmsghdr *nlh,
skb_dst_set(skb, &rt->dst);
if (fibmatch)
- err = rt6_fill_node(net, skb, rt, NULL, NULL, NULL, iif,
+ err = rt6_fill_node(net, skb, rt->from, NULL, NULL, NULL, iif,
RTM_NEWROUTE, NETLINK_CB(in_skb).portid,
nlh->nlmsg_seq, 0);
else
- err = rt6_fill_node(net, skb, rt, dst, &fl6.daddr, &fl6.saddr,
- iif, RTM_NEWROUTE,
+ err = rt6_fill_node(net, skb, rt->from, dst,
+ &fl6.daddr, &fl6.saddr, iif, RTM_NEWROUTE,
NETLINK_CB(in_skb).portid, nlh->nlmsg_seq,
0);
if (err < 0) {
--
2.11.0
^ permalink raw reply related
* [PATCH net-next v2 18/21] net/ipv6: introduce fib6_info struct and helpers
From: David Ahern @ 2018-04-18 0:33 UTC (permalink / raw)
To: netdev
Cc: davem, idosch, roopa, eric.dumazet, weiwan, kafai, yoshfuji,
David Ahern
In-Reply-To: <20180418003327.19992-1-dsahern@gmail.com>
Add fib6_info struct and alloc, destroy, hold and release helpers.
Signed-off-by: David Ahern <dsahern@gmail.com>
---
include/net/ip6_fib.h | 55 ++++++++++++++++++++++++++++++++++++++++++++++
net/ipv6/ip6_fib.c | 60 +++++++++++++++++++++++++++++++++++++++++++++++++++
2 files changed, 115 insertions(+)
diff --git a/include/net/ip6_fib.h b/include/net/ip6_fib.h
index 159f651dee55..630392ae12d8 100644
--- a/include/net/ip6_fib.h
+++ b/include/net/ip6_fib.h
@@ -38,6 +38,7 @@
#endif
struct rt6_info;
+struct fib6_info;
struct fib6_config {
u32 fc_table;
@@ -132,6 +133,46 @@ struct fib6_nh {
int nh_weight;
};
+struct fib6_info {
+ struct fib6_table *rt6i_table;
+ struct fib6_info __rcu *rt6_next;
+ struct fib6_node __rcu *rt6i_node;
+
+ /* Multipath routes:
+ * siblings is a list of fib6_info that have the the same metric/weight,
+ * destination, but not the same gateway. nsiblings is just a cache
+ * to speed up lookup.
+ */
+ struct list_head rt6i_siblings;
+ unsigned int rt6i_nsiblings;
+
+ atomic_t rt6i_ref;
+ struct inet6_dev *rt6i_idev;
+ unsigned long expires;
+ struct dst_metrics *fib6_metrics;
+#define fib6_pmtu fib6_metrics->metrics[RTAX_MTU-1]
+
+ struct rt6key rt6i_dst;
+ u32 rt6i_flags;
+ struct rt6key rt6i_src;
+ struct rt6key rt6i_prefsrc;
+
+ struct rt6_info * __percpu *rt6i_pcpu;
+ struct rt6_exception_bucket __rcu *rt6i_exception_bucket;
+
+ u32 rt6i_metric;
+ u8 rt6i_protocol;
+ u8 fib6_type;
+ u8 exception_bucket_flushed:1,
+ should_flush:1,
+ dst_nocount:1,
+ dst_nopolicy:1,
+ dst_host:1,
+ unused:3;
+
+ struct fib6_nh fib6_nh;
+};
+
struct rt6_info {
struct dst_entry dst;
struct rt6_info __rcu *rt6_next;
@@ -291,6 +332,20 @@ static inline void ip6_rt_put(struct rt6_info *rt)
void rt6_free_pcpu(struct rt6_info *non_pcpu_rt);
+struct rt6_info *fib6_info_alloc(gfp_t gfp_flags);
+void fib6_info_destroy(struct rt6_info *f6i);
+
+static inline void fib6_info_hold(struct rt6_info *f6i)
+{
+ atomic_inc(&f6i->rt6i_ref);
+}
+
+static inline void fib6_info_release(struct rt6_info *f6i)
+{
+ if (f6i && atomic_dec_and_test(&f6i->rt6i_ref))
+ fib6_info_destroy(f6i);
+}
+
static inline void rt6_hold(struct rt6_info *rt)
{
atomic_inc(&rt->rt6i_ref);
diff --git a/net/ipv6/ip6_fib.c b/net/ipv6/ip6_fib.c
index 53df4a98a7f7..d07578d84db0 100644
--- a/net/ipv6/ip6_fib.c
+++ b/net/ipv6/ip6_fib.c
@@ -145,6 +145,66 @@ static __be32 addr_bit_set(const void *token, int fn_bit)
addr[fn_bit >> 5];
}
+struct rt6_info *fib6_info_alloc(gfp_t gfp_flags)
+{
+ struct rt6_info *f6i;
+
+ f6i = kzalloc(sizeof(*f6i), gfp_flags);
+ if (!f6i)
+ return NULL;
+
+ f6i->rt6i_pcpu = alloc_percpu_gfp(struct rt6_info *, gfp_flags);
+ if (!f6i->rt6i_pcpu) {
+ kfree(f6i);
+ return NULL;
+ }
+
+ INIT_LIST_HEAD(&f6i->rt6i_siblings);
+ f6i->fib6_metrics = (struct dst_metrics *)&dst_default_metrics;
+
+ atomic_inc(&f6i->rt6i_ref);
+
+ return f6i;
+}
+
+void fib6_info_destroy(struct rt6_info *f6i)
+{
+ struct rt6_exception_bucket *bucket;
+
+ WARN_ON(f6i->rt6i_node);
+
+ bucket = rcu_dereference_protected(f6i->rt6i_exception_bucket, 1);
+ if (bucket) {
+ f6i->rt6i_exception_bucket = NULL;
+ kfree(bucket);
+ }
+
+ if (f6i->rt6i_pcpu) {
+ int cpu;
+
+ for_each_possible_cpu(cpu) {
+ struct rt6_info **ppcpu_rt;
+ struct rt6_info *pcpu_rt;
+
+ ppcpu_rt = per_cpu_ptr(f6i->rt6i_pcpu, cpu);
+ pcpu_rt = *ppcpu_rt;
+ if (pcpu_rt) {
+ dst_dev_put(&pcpu_rt->dst);
+ dst_release(&pcpu_rt->dst);
+ *ppcpu_rt = NULL;
+ }
+ }
+ }
+
+ if (f6i->rt6i_idev)
+ in6_dev_put(f6i->rt6i_idev);
+ if (f6i->fib6_nh.nh_dev)
+ dev_put(f6i->fib6_nh.nh_dev);
+
+ kfree(f6i);
+}
+EXPORT_SYMBOL_GPL(fib6_info_destroy);
+
static struct fib6_node *node_alloc(struct net *net)
{
struct fib6_node *fn;
--
2.11.0
^ permalink raw reply related
* [PATCH net-next v2 17/21] net/ipv6: Cleanup exception and cache route handling
From: David Ahern @ 2018-04-18 0:33 UTC (permalink / raw)
To: netdev
Cc: davem, idosch, roopa, eric.dumazet, weiwan, kafai, yoshfuji,
David Ahern
In-Reply-To: <20180418003327.19992-1-dsahern@gmail.com>
IPv6 FIB will only contain FIB entries with exception routes added to
the FIB entry. Once this transformation is complete, FIB lookups will
return a fib6_info with the lookup functions still returning a dst
based rt6_info. The current code uses rt6_info for both paths and
overloads the rt6_info variable usually called 'rt'.
This patch introduces a new 'f6i' variable name for the result of the FIB
lookup and keeps 'rt' as the dst based return variable. 'f6i' becomes a
fib6_info in a later patch which is why it is introduced as f6i now;
avoids the additional churn in the later patch.
In addition, remove RTF_CACHE and dst checks from fib6 add and delete
since they can not happen now and will never happen after the data
type flip.
Signed-off-by: David Ahern <dsahern@gmail.com>
---
include/net/ip6_route.h | 1 -
net/ipv6/ip6_fib.c | 16 +-----
net/ipv6/route.c | 142 +++++++++++++++++++++++++++---------------------
3 files changed, 81 insertions(+), 78 deletions(-)
diff --git a/include/net/ip6_route.h b/include/net/ip6_route.h
index ff70266e30d7..686cdc7f356a 100644
--- a/include/net/ip6_route.h
+++ b/include/net/ip6_route.h
@@ -106,7 +106,6 @@ int ip6_ins_rt(struct net *net, struct rt6_info *rt);
int ip6_del_rt(struct net *net, struct rt6_info *rt);
void rt6_flush_exceptions(struct rt6_info *rt);
-int rt6_remove_exception_rt(struct rt6_info *rt);
void rt6_age_exceptions(struct rt6_info *rt, struct fib6_gc_args *gc_args,
unsigned long now);
diff --git a/net/ipv6/ip6_fib.c b/net/ipv6/ip6_fib.c
index 280b69497ad0..53df4a98a7f7 100644
--- a/net/ipv6/ip6_fib.c
+++ b/net/ipv6/ip6_fib.c
@@ -1074,7 +1074,7 @@ static int fib6_add_rt2node(struct fib6_node *fn, struct rt6_info *rt,
static void fib6_start_gc(struct net *net, struct rt6_info *rt)
{
if (!timer_pending(&net->ipv6.ip6_fib_timer) &&
- (rt->rt6i_flags & (RTF_EXPIRES | RTF_CACHE)))
+ (rt->rt6i_flags & RTF_EXPIRES))
mod_timer(&net->ipv6.ip6_fib_timer,
jiffies + net->ipv6.sysctl.ip6_rt_gc_interval);
}
@@ -1125,8 +1125,6 @@ int fib6_add(struct fib6_node *root, struct rt6_info *rt,
if (WARN_ON_ONCE(!atomic_read(&rt->dst.__refcnt)))
return -EINVAL;
- if (WARN_ON_ONCE(rt->rt6i_flags & RTF_CACHE))
- return -EINVAL;
if (info->nlh) {
if (!(info->nlh->nlmsg_flags & NLM_F_CREATE))
@@ -1650,8 +1648,6 @@ static void fib6_del_route(struct fib6_table *table, struct fib6_node *fn,
RT6_TRACE("fib6_del_route\n");
- WARN_ON_ONCE(rt->rt6i_flags & RTF_CACHE);
-
/* Unlink it */
*rtp = rt->rt6_next;
rt->rt6i_node = NULL;
@@ -1720,21 +1716,11 @@ int fib6_del(struct rt6_info *rt, struct nl_info *info)
struct rt6_info __rcu **rtp;
struct rt6_info __rcu **rtp_next;
-#if RT6_DEBUG >= 2
- if (rt->dst.obsolete > 0) {
- WARN_ON(fn);
- return -ENOENT;
- }
-#endif
if (!fn || rt == net->ipv6.fib6_null_entry)
return -ENOENT;
WARN_ON(!(fn->fn_flags & RTN_RTINFO));
- /* remove cached dst from exception table */
- if (rt->rt6i_flags & RTF_CACHE)
- return rt6_remove_exception_rt(rt);
-
/*
* Walk the leaf entries looking for ourself
*/
diff --git a/net/ipv6/route.c b/net/ipv6/route.c
index 56a854b426a6..ad9eaecf539c 100644
--- a/net/ipv6/route.c
+++ b/net/ipv6/route.c
@@ -1013,8 +1013,8 @@ static void rt6_set_from(struct rt6_info *rt, struct rt6_info *from)
BUG_ON(from->from);
rt->rt6i_flags &= ~RTF_EXPIRES;
- dst_hold(&from->dst);
- rt->from = from;
+ if (dst_hold_safe(&from->dst))
+ rt->from = from;
dst_init_metrics(&rt->dst, from->fib6_metrics->metrics, true);
if (from->fib6_metrics != &dst_default_metrics) {
rt->dst._metrics |= DST_METRICS_REFCOUNTED;
@@ -1097,8 +1097,9 @@ static struct rt6_info *ip6_pol_route_lookup(struct net *net,
const struct sk_buff *skb,
int flags)
{
- struct rt6_info *rt, *rt_cache;
+ struct rt6_info *f6i;
struct fib6_node *fn;
+ struct rt6_info *rt;
if (fl6->flowi6_flags & FLOWI_FLAG_SKIP_NH_OIF)
flags &= ~RT6_LOOKUP_F_IFACE;
@@ -1106,36 +1107,36 @@ static struct rt6_info *ip6_pol_route_lookup(struct net *net,
rcu_read_lock();
fn = fib6_lookup(&table->tb6_root, &fl6->daddr, &fl6->saddr);
restart:
- rt = rcu_dereference(fn->leaf);
- if (!rt) {
- rt = net->ipv6.fib6_null_entry;
+ f6i = rcu_dereference(fn->leaf);
+ if (!f6i) {
+ f6i = net->ipv6.fib6_null_entry;
} else {
- rt = rt6_device_match(net, rt, &fl6->saddr,
+ f6i = rt6_device_match(net, f6i, &fl6->saddr,
fl6->flowi6_oif, flags);
- if (rt->rt6i_nsiblings && fl6->flowi6_oif == 0)
- rt = rt6_multipath_select(net, rt, fl6, fl6->flowi6_oif,
- skb, flags);
+ if (f6i->rt6i_nsiblings && fl6->flowi6_oif == 0)
+ f6i = rt6_multipath_select(net, f6i, fl6,
+ fl6->flowi6_oif, skb, flags);
}
- if (rt == net->ipv6.fib6_null_entry) {
+ if (f6i == net->ipv6.fib6_null_entry) {
fn = fib6_backtrack(fn, &fl6->saddr);
if (fn)
goto restart;
}
+
/* Search through exception table */
- rt_cache = rt6_find_cached_rt(rt, &fl6->daddr, &fl6->saddr);
- if (rt_cache) {
- rt = rt_cache;
+ rt = rt6_find_cached_rt(f6i, &fl6->daddr, &fl6->saddr);
+ if (rt) {
if (ip6_hold_safe(net, &rt, true))
dst_use_noref(&rt->dst, jiffies);
- } else if (dst_hold_safe(&rt->dst)) {
- struct rt6_info *nrt;
-
- nrt = ip6_create_rt_rcu(rt);
- dst_release(&rt->dst);
- rt = nrt;
- } else {
+ } else if (f6i == net->ipv6.fib6_null_entry) {
rt = net->ipv6.ip6_null_entry;
dst_hold(&rt->dst);
+ } else {
+ rt = ip6_create_rt_rcu(f6i);
+ if (!rt) {
+ rt = net->ipv6.ip6_null_entry;
+ dst_hold(&rt->dst);
+ }
}
rcu_read_unlock();
@@ -1218,9 +1219,6 @@ static struct rt6_info *ip6_rt_cache_alloc(struct rt6_info *ort,
* Clone the route.
*/
- if (ort->rt6i_flags & (RTF_CACHE | RTF_PCPU))
- ort = ort->from;
-
rcu_read_lock();
dev = ip6_rt_get_dev_rcu(ort);
rt = __ip6_dst_alloc(dev_net(dev), dev, 0);
@@ -1446,11 +1444,6 @@ static int rt6_insert_exception(struct rt6_info *nrt,
struct rt6_exception *rt6_ex;
int err = 0;
- /* ort can't be a cache or pcpu route */
- if (ort->rt6i_flags & (RTF_CACHE | RTF_PCPU))
- ort = ort->from;
- WARN_ON_ONCE(ort->rt6i_flags & (RTF_CACHE | RTF_PCPU));
-
spin_lock_bh(&rt6_exception_lock);
if (ort->exception_bucket_flushed) {
@@ -1589,7 +1582,7 @@ static struct rt6_info *rt6_find_cached_rt(struct rt6_info *rt,
}
/* Remove the passed in cached rt from the hash table that contains it */
-int rt6_remove_exception_rt(struct rt6_info *rt)
+static int rt6_remove_exception_rt(struct rt6_info *rt)
{
struct rt6_exception_bucket *bucket;
struct rt6_info *from = rt->from;
@@ -1854,7 +1847,8 @@ struct rt6_info *ip6_pol_route(struct net *net, struct fib6_table *table,
const struct sk_buff *skb, int flags)
{
struct fib6_node *fn, *saved_fn;
- struct rt6_info *rt, *rt_cache;
+ struct rt6_info *f6i;
+ struct rt6_info *rt;
int strict = 0;
strict |= flags & RT6_LOOKUP_F_IFACE;
@@ -1871,10 +1865,10 @@ struct rt6_info *ip6_pol_route(struct net *net, struct fib6_table *table,
oif = 0;
redo_rt6_select:
- rt = rt6_select(net, fn, oif, strict);
- if (rt->rt6i_nsiblings)
- rt = rt6_multipath_select(net, rt, fl6, oif, skb, strict);
- if (rt == net->ipv6.fib6_null_entry) {
+ f6i = rt6_select(net, fn, oif, strict);
+ if (f6i->rt6i_nsiblings)
+ f6i = rt6_multipath_select(net, f6i, fl6, oif, skb, strict);
+ if (f6i == net->ipv6.fib6_null_entry) {
fn = fib6_backtrack(fn, &fl6->saddr);
if (fn)
goto redo_rt6_select;
@@ -1886,18 +1880,17 @@ struct rt6_info *ip6_pol_route(struct net *net, struct fib6_table *table,
}
}
- /*Search through exception table */
- rt_cache = rt6_find_cached_rt(rt, &fl6->daddr, &fl6->saddr);
- if (rt_cache)
- rt = rt_cache;
-
- if (rt == net->ipv6.fib6_null_entry) {
+ if (f6i == net->ipv6.fib6_null_entry) {
rt = net->ipv6.ip6_null_entry;
rcu_read_unlock();
dst_hold(&rt->dst);
trace_fib6_table_lookup(net, rt, table, fl6);
return rt;
- } else if (rt->rt6i_flags & RTF_CACHE) {
+ }
+
+ /*Search through exception table */
+ rt = rt6_find_cached_rt(f6i, &fl6->daddr, &fl6->saddr);
+ if (rt) {
if (ip6_hold_safe(net, &rt, true))
dst_use_noref(&rt->dst, jiffies);
@@ -1905,7 +1898,7 @@ struct rt6_info *ip6_pol_route(struct net *net, struct fib6_table *table,
trace_fib6_table_lookup(net, rt, table, fl6);
return rt;
} else if (unlikely((fl6->flowi6_flags & FLOWI_FLAG_KNOWN_NH) &&
- !(rt->rt6i_flags & RTF_GATEWAY))) {
+ !(f6i->rt6i_flags & RTF_GATEWAY))) {
/* Create a RTF_CACHE clone which will not be
* owned by the fib6 tree. It is for the special case where
* the daddr in the skb during the neighbor look-up is different
@@ -1914,16 +1907,16 @@ struct rt6_info *ip6_pol_route(struct net *net, struct fib6_table *table,
struct rt6_info *uncached_rt;
- if (ip6_hold_safe(net, &rt, true)) {
- dst_use_noref(&rt->dst, jiffies);
+ if (ip6_hold_safe(net, &f6i, true)) {
+ dst_use_noref(&f6i->dst, jiffies);
} else {
rcu_read_unlock();
- uncached_rt = rt;
+ uncached_rt = f6i;
goto uncached_rt_out;
}
rcu_read_unlock();
- uncached_rt = ip6_rt_cache_alloc(rt, &fl6->daddr, NULL);
+ uncached_rt = ip6_rt_cache_alloc(f6i, &fl6->daddr, NULL);
dst_release(&rt->dst);
if (uncached_rt) {
@@ -1946,18 +1939,18 @@ struct rt6_info *ip6_pol_route(struct net *net, struct fib6_table *table,
struct rt6_info *pcpu_rt;
- dst_use_noref(&rt->dst, jiffies);
+ dst_use_noref(&f6i->dst, jiffies);
local_bh_disable();
- pcpu_rt = rt6_get_pcpu_route(rt);
+ pcpu_rt = rt6_get_pcpu_route(f6i);
if (!pcpu_rt) {
/* atomic_inc_not_zero() is needed when using rcu */
- if (atomic_inc_not_zero(&rt->rt6i_ref)) {
+ if (atomic_inc_not_zero(&f6i->rt6i_ref)) {
/* No dst_hold() on rt is needed because grabbing
* rt->rt6i_ref makes sure rt can't be released.
*/
- pcpu_rt = rt6_make_pcpu_route(net, rt);
- rt6_release(rt);
+ pcpu_rt = rt6_make_pcpu_route(net, f6i);
+ rt6_release(f6i);
} else {
/* rt is already removed from tree */
pcpu_rt = net->ipv6.ip6_null_entry;
@@ -2419,7 +2412,8 @@ static struct rt6_info *__ip6_route_redirect(struct net *net,
int flags)
{
struct ip6rd_flowi *rdfl = (struct ip6rd_flowi *)fl6;
- struct rt6_info *rt, *rt_cache;
+ struct rt6_info *ret = NULL, *rt_cache;
+ struct rt6_info *rt;
struct fib6_node *fn;
/* Get the "current" route for this destination and
@@ -2458,7 +2452,7 @@ static struct rt6_info *__ip6_route_redirect(struct net *net,
if (rt_cache &&
ipv6_addr_equal(&rdfl->gateway,
&rt_cache->rt6i_gateway)) {
- rt = rt_cache;
+ ret = rt_cache;
break;
}
continue;
@@ -2469,7 +2463,7 @@ static struct rt6_info *__ip6_route_redirect(struct net *net,
if (!rt)
rt = net->ipv6.fib6_null_entry;
else if (rt->rt6i_flags & RTF_REJECT) {
- rt = net->ipv6.ip6_null_entry;
+ ret = net->ipv6.ip6_null_entry;
goto out;
}
@@ -2480,12 +2474,15 @@ static struct rt6_info *__ip6_route_redirect(struct net *net,
}
out:
- ip6_hold_safe(net, &rt, true);
+ if (ret)
+ dst_hold(&ret->dst);
+ else
+ ret = ip6_create_rt_rcu(rt);
rcu_read_unlock();
- trace_fib6_table_lookup(net, rt, table, fl6);
- return rt;
+ trace_fib6_table_lookup(net, ret, table, fl6);
+ return ret;
};
static struct dst_entry *ip6_route_redirect(struct net *net,
@@ -3182,6 +3179,22 @@ static int __ip6_del_rt_siblings(struct rt6_info *rt, struct fib6_config *cfg)
return err;
}
+static int ip6_del_cached_rt(struct rt6_info *rt, struct fib6_config *cfg)
+{
+ int rc = -ESRCH;
+
+ if (cfg->fc_ifindex && rt->dst.dev->ifindex != cfg->fc_ifindex)
+ goto out;
+
+ if (cfg->fc_flags & RTF_GATEWAY &&
+ !ipv6_addr_equal(&cfg->fc_gateway, &rt->rt6i_gateway))
+ goto out;
+ if (dst_hold_safe(&rt->dst))
+ rc = rt6_remove_exception_rt(rt);
+out:
+ return rc;
+}
+
static int ip6_route_del(struct fib6_config *cfg,
struct netlink_ext_ack *extack)
{
@@ -3206,11 +3219,16 @@ static int ip6_route_del(struct fib6_config *cfg,
if (fn) {
for_each_fib6_node_rt_rcu(fn) {
if (cfg->fc_flags & RTF_CACHE) {
+ int rc;
+
rt_cache = rt6_find_cached_rt(rt, &cfg->fc_dst,
&cfg->fc_src);
- if (!rt_cache)
- continue;
- rt = rt_cache;
+ if (rt_cache) {
+ rc = ip6_del_cached_rt(rt_cache, cfg);
+ if (rc != -ESRCH)
+ return rc;
+ }
+ continue;
}
if (cfg->fc_ifindex &&
(!rt->fib6_nh.nh_dev ||
@@ -3327,7 +3345,7 @@ static void rt6_do_redirect(struct dst_entry *dst, struct sock *sk, struct sk_bu
NEIGH_UPDATE_F_ISROUTER)),
NDISC_REDIRECT, &ndopts);
- nrt = ip6_rt_cache_alloc(rt, &msg->dest, NULL);
+ nrt = ip6_rt_cache_alloc(rt->from, &msg->dest, NULL);
if (!nrt)
goto out;
--
2.11.0
^ 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