* [PATCH 12/12] ethernet: Use ether_zero_addr instead of local statics
From: Joe Perches @ 2018-03-31 7:05 UTC (permalink / raw)
To: Michael Chan, Claudiu Manoil; +Cc: netdev, linux-kernel
In-Reply-To: <cover.1522479607.git.joe@perches.com>
This saves a small amount of object code.
Miscellanea:
o __b44_cam_write now use const u8 *data instead of unsigned char *
to avoid compiler warnings as it doesn't modify data
Signed-off-by: Joe Perches <joe@perches.com>
---
drivers/net/ethernet/broadcom/b44.c | 5 ++---
drivers/net/ethernet/freescale/gianfar.c | 3 +--
2 files changed, 3 insertions(+), 5 deletions(-)
diff --git a/drivers/net/ethernet/broadcom/b44.c b/drivers/net/ethernet/broadcom/b44.c
index e445ab724827..30879ff7de19 100644
--- a/drivers/net/ethernet/broadcom/b44.c
+++ b/drivers/net/ethernet/broadcom/b44.c
@@ -220,7 +220,7 @@ static inline void __b44_cam_read(struct b44 *bp, unsigned char *data, int index
data[1] = (val >> 0) & 0xFF;
}
-static inline void __b44_cam_write(struct b44 *bp, unsigned char *data, int index)
+static inline void __b44_cam_write(struct b44 *bp, const u8 *data, int index)
{
u32 val;
@@ -1744,7 +1744,6 @@ static void __b44_set_rx_mode(struct net_device *dev)
val |= RXCONFIG_PROMISC;
bw32(bp, B44_RXCONFIG, val);
} else {
- unsigned char zero[6] = {0, 0, 0, 0, 0, 0};
int i = 1;
__b44_set_mac_addr(bp);
@@ -1756,7 +1755,7 @@ static void __b44_set_rx_mode(struct net_device *dev)
i = __b44_load_mcast(bp, dev);
for (; i < 64; i++)
- __b44_cam_write(bp, zero, i);
+ __b44_cam_write(bp, ether_zero_addr, i);
bw32(bp, B44_RXCONFIG, val);
val = br32(bp, B44_CAM_CTRL);
diff --git a/drivers/net/ethernet/freescale/gianfar.c b/drivers/net/ethernet/freescale/gianfar.c
index f27f9bae1a4a..24d8c85f8f4e 100644
--- a/drivers/net/ethernet/freescale/gianfar.c
+++ b/drivers/net/ethernet/freescale/gianfar.c
@@ -3501,10 +3501,9 @@ static void gfar_set_multi(struct net_device *dev)
static void gfar_clear_exact_match(struct net_device *dev)
{
int idx;
- static const u8 zero_arr[ETH_ALEN] = {0, 0, 0, 0, 0, 0};
for (idx = 1; idx < GFAR_EM_NUM + 1; idx++)
- gfar_set_mac_for_addr(dev, idx, zero_arr);
+ gfar_set_mac_for_addr(dev, idx, ether_zero_addr);
}
/* Set the appropriate hash bit for the given addr */
--
2.15.0
^ permalink raw reply related
* [PATCH 11/12] qlogic: Convert local bcast_addr to global ether_broadcast_addr
From: Joe Perches @ 2018-03-31 7:05 UTC (permalink / raw)
To: Manish Chopra, Rahul Verma, Dept-GELinuxNICDev, Harish Patil
Cc: netdev, linux-kernel
In-Reply-To: <cover.1522479607.git.joe@perches.com>
Use the new global instead of local statics to save a bit of object code.
Signed-off-by: Joe Perches <joe@perches.com>
---
drivers/net/ethernet/qlogic/netxen/netxen_nic_hw.c | 5 +----
drivers/net/ethernet/qlogic/qlcnic/qlcnic_hw.c | 6 ++----
drivers/net/ethernet/qlogic/qlcnic/qlcnic_sriov_common.c | 6 ++----
3 files changed, 5 insertions(+), 12 deletions(-)
diff --git a/drivers/net/ethernet/qlogic/netxen/netxen_nic_hw.c b/drivers/net/ethernet/qlogic/netxen/netxen_nic_hw.c
index 1cd39c9a0345..bd21aa3d5833 100644
--- a/drivers/net/ethernet/qlogic/netxen/netxen_nic_hw.c
+++ b/drivers/net/ethernet/qlogic/netxen/netxen_nic_hw.c
@@ -668,9 +668,6 @@ static void netxen_p3_nic_set_multi(struct net_device *netdev)
{
struct netxen_adapter *adapter = netdev_priv(netdev);
struct netdev_hw_addr *ha;
- static const u8 bcast_addr[ETH_ALEN] = {
- 0xff, 0xff, 0xff, 0xff, 0xff, 0xff
- };
u32 mode = VPORT_MISS_MODE_DROP;
LIST_HEAD(del_list);
struct list_head *head;
@@ -682,7 +679,7 @@ static void netxen_p3_nic_set_multi(struct net_device *netdev)
list_splice_tail_init(&adapter->mac_list, &del_list);
nx_p3_nic_add_mac(adapter, adapter->mac_addr, &del_list);
- nx_p3_nic_add_mac(adapter, bcast_addr, &del_list);
+ nx_p3_nic_add_mac(adapter, ether_broadcast_addr, &del_list);
if (netdev->flags & IFF_PROMISC) {
mode = VPORT_MISS_MODE_ACCEPT_ALL;
diff --git a/drivers/net/ethernet/qlogic/qlcnic/qlcnic_hw.c b/drivers/net/ethernet/qlogic/qlcnic/qlcnic_hw.c
index 7848cf04b29a..948cb7ae9758 100644
--- a/drivers/net/ethernet/qlogic/qlcnic/qlcnic_hw.c
+++ b/drivers/net/ethernet/qlogic/qlcnic/qlcnic_hw.c
@@ -542,9 +542,6 @@ static void __qlcnic_set_multi(struct net_device *netdev, u16 vlan)
struct qlcnic_adapter *adapter = netdev_priv(netdev);
struct qlcnic_hardware_context *ahw = adapter->ahw;
struct netdev_hw_addr *ha;
- static const u8 bcast_addr[ETH_ALEN] = {
- 0xff, 0xff, 0xff, 0xff, 0xff, 0xff
- };
u32 mode = VPORT_MISS_MODE_DROP;
if (!test_bit(__QLCNIC_FW_ATTACHED, &adapter->state))
@@ -552,7 +549,8 @@ static void __qlcnic_set_multi(struct net_device *netdev, u16 vlan)
qlcnic_nic_add_mac(adapter, adapter->mac_addr, vlan,
QLCNIC_UNICAST_MAC);
- qlcnic_nic_add_mac(adapter, bcast_addr, vlan, QLCNIC_BROADCAST_MAC);
+ qlcnic_nic_add_mac(adapter, ether_broadcast_addr, vlan,
+ QLCNIC_BROADCAST_MAC);
if (netdev->flags & IFF_PROMISC) {
if (!(adapter->flags & QLCNIC_PROMISC_DISABLED))
diff --git a/drivers/net/ethernet/qlogic/qlcnic/qlcnic_sriov_common.c b/drivers/net/ethernet/qlogic/qlcnic/qlcnic_sriov_common.c
index c58180f40844..17dd0a1353f2 100644
--- a/drivers/net/ethernet/qlogic/qlcnic/qlcnic_sriov_common.c
+++ b/drivers/net/ethernet/qlogic/qlcnic/qlcnic_sriov_common.c
@@ -1546,9 +1546,6 @@ void qlcnic_sriov_vf_set_multi(struct net_device *netdev)
{
struct qlcnic_adapter *adapter = netdev_priv(netdev);
struct qlcnic_hardware_context *ahw = adapter->ahw;
- static const u8 bcast_addr[ETH_ALEN] = {
- 0xff, 0xff, 0xff, 0xff, 0xff, 0xff
- };
struct netdev_hw_addr *ha;
u32 mode = VPORT_MISS_MODE_DROP;
@@ -1562,7 +1559,8 @@ void qlcnic_sriov_vf_set_multi(struct net_device *netdev)
(netdev_mc_count(netdev) > ahw->max_mc_count)) {
mode = VPORT_MISS_MODE_ACCEPT_MULTI;
} else {
- qlcnic_vf_add_mc_list(netdev, bcast_addr, QLCNIC_BROADCAST_MAC);
+ qlcnic_vf_add_mc_list(netdev, ether_broadcast_addr,
+ QLCNIC_BROADCAST_MAC);
if (!netdev_mc_empty(netdev)) {
qlcnic_flush_mcast_mac(adapter);
netdev_for_each_mc_addr(ha, netdev)
--
2.15.0
^ permalink raw reply related
* [PATCH 10/12] mvpp2: Use ether_broadcast_addr instead of a local array
From: Joe Perches @ 2018-03-31 7:05 UTC (permalink / raw)
To: linux-kernel; +Cc: netdev
In-Reply-To: <cover.1522479607.git.joe@perches.com>
Save a small bit of object code by using the new global instead.
Signed-off-by: Joe Perches <joe@perches.com>
---
drivers/net/ethernet/marvell/mvpp2.c | 4 +---
1 file changed, 1 insertion(+), 3 deletions(-)
diff --git a/drivers/net/ethernet/marvell/mvpp2.c b/drivers/net/ethernet/marvell/mvpp2.c
index 7fc1bbf51c44..a848b92f5961 100644
--- a/drivers/net/ethernet/marvell/mvpp2.c
+++ b/drivers/net/ethernet/marvell/mvpp2.c
@@ -7345,11 +7345,9 @@ static int mvpp2_open(struct net_device *dev)
{
struct mvpp2_port *port = netdev_priv(dev);
struct mvpp2 *priv = port->priv;
- unsigned char mac_bcast[ETH_ALEN] = {
- 0xff, 0xff, 0xff, 0xff, 0xff, 0xff };
int err;
- err = mvpp2_prs_mac_da_accept(port, mac_bcast, true);
+ err = mvpp2_prs_mac_da_accept(port, ether_broadcast_addr, true);
if (err) {
netdev_err(dev, "mvpp2_prs_mac_da_accept BC failed\n");
return err;
--
2.15.0
^ permalink raw reply related
* [PATCH 09/12] iwlwifi: Remove local iwl_bcast_addr and use ether_broadcast_addr
From: Joe Perches @ 2018-03-31 7:05 UTC (permalink / raw)
To: linux-kernel
Cc: Johannes Berg, Emmanuel Grumbach, Luca Coelho,
Intel Linux Wireless, Kalle Valo, linux-wireless, netdev
In-Reply-To: <cover.1522479607.git.joe@perches.com>
Use the new global to save a little bit of object code.
Signed-off-by: Joe Perches <joe@perches.com>
---
drivers/net/wireless/intel/iwlwifi/dvm/dev.h | 1 -
drivers/net/wireless/intel/iwlwifi/dvm/scan.c | 2 +-
drivers/net/wireless/intel/iwlwifi/dvm/sta.c | 4 +---
3 files changed, 2 insertions(+), 5 deletions(-)
diff --git a/drivers/net/wireless/intel/iwlwifi/dvm/dev.h b/drivers/net/wireless/intel/iwlwifi/dvm/dev.h
index cceb4cd8e501..157cc21c5dfb 100644
--- a/drivers/net/wireless/intel/iwlwifi/dvm/dev.h
+++ b/drivers/net/wireless/intel/iwlwifi/dvm/dev.h
@@ -271,7 +271,6 @@ struct iwl_sensitivity_ranges {
*
****************************************************************************/
void iwl_update_chain_flags(struct iwl_priv *priv);
-extern const u8 iwl_bcast_addr[ETH_ALEN];
#define IWL_OPERATION_MODE_AUTO 0
#define IWL_OPERATION_MODE_HT_ONLY 1
diff --git a/drivers/net/wireless/intel/iwlwifi/dvm/scan.c b/drivers/net/wireless/intel/iwlwifi/dvm/scan.c
index 17e6a32384d3..e40d9b9fc4a9 100644
--- a/drivers/net/wireless/intel/iwlwifi/dvm/scan.c
+++ b/drivers/net/wireless/intel/iwlwifi/dvm/scan.c
@@ -871,7 +871,7 @@ static int iwlagn_request_scan(struct iwl_priv *priv, struct ieee80211_vif *vif)
/* use bcast addr, will not be transmitted but must be valid */
cmd_len = iwl_fill_probe_req(
(struct ieee80211_mgmt *)scan->data,
- iwl_bcast_addr, NULL, 0,
+ ether_broadcast_addr, NULL, 0,
NULL, 0,
scan_cmd_size - sizeof(*scan));
break;
diff --git a/drivers/net/wireless/intel/iwlwifi/dvm/sta.c b/drivers/net/wireless/intel/iwlwifi/dvm/sta.c
index de6ec9b7ace4..177a366f7ad3 100644
--- a/drivers/net/wireless/intel/iwlwifi/dvm/sta.c
+++ b/drivers/net/wireless/intel/iwlwifi/dvm/sta.c
@@ -32,8 +32,6 @@
#include "dev.h"
#include "agn.h"
-const u8 iwl_bcast_addr[ETH_ALEN] = { 0xFF, 0xFF, 0xFF, 0xFF, 0xFF, 0xFF };
-
static int iwl_sta_ucode_activate(struct iwl_priv *priv, u8 sta_id)
{
lockdep_assert_held(&priv->sta_lock);
@@ -1287,7 +1285,7 @@ int iwlagn_alloc_bcast_station(struct iwl_priv *priv,
u8 sta_id;
spin_lock_bh(&priv->sta_lock);
- sta_id = iwl_prep_station(priv, ctx, iwl_bcast_addr, false, NULL);
+ sta_id = iwl_prep_station(priv, ctx, ether_broadcast_addr, false, NULL);
if (sta_id == IWL_INVALID_STATION) {
IWL_ERR(priv, "Unable to prepare broadcast station\n");
spin_unlock_bh(&priv->sta_lock);
--
2.15.0
^ permalink raw reply related
* [PATCH 08/12] iwlegacy: Remove EXPORT_SYMBOL(il_bcast_addr) and use ether_broadcast_addr
From: Joe Perches @ 2018-03-31 7:05 UTC (permalink / raw)
To: Stanislaw Gruszka; +Cc: Kalle Valo, linux-wireless, netdev, linux-kernel
In-Reply-To: <cover.1522479607.git.joe@perches.com>
Remove the local array and use the new global instead to save some small
amount of object code.
Signed-off-by: Joe Perches <joe@perches.com>
---
drivers/net/wireless/intel/iwlegacy/3945-mac.c | 2 +-
drivers/net/wireless/intel/iwlegacy/4965-mac.c | 2 +-
drivers/net/wireless/intel/iwlegacy/common.c | 3 ---
drivers/net/wireless/intel/iwlegacy/common.h | 1 -
4 files changed, 2 insertions(+), 6 deletions(-)
diff --git a/drivers/net/wireless/intel/iwlegacy/3945-mac.c b/drivers/net/wireless/intel/iwlegacy/3945-mac.c
index 62a9794f952b..770c7aa13434 100644
--- a/drivers/net/wireless/intel/iwlegacy/3945-mac.c
+++ b/drivers/net/wireless/intel/iwlegacy/3945-mac.c
@@ -2352,7 +2352,7 @@ il3945_alloc_bcast_station(struct il_priv *il)
u8 sta_id;
spin_lock_irqsave(&il->sta_lock, flags);
- sta_id = il_prep_station(il, il_bcast_addr, false, NULL);
+ sta_id = il_prep_station(il, ether_broadcast_addr, false, NULL);
if (sta_id == IL_INVALID_STATION) {
IL_ERR("Unable to prepare broadcast station\n");
spin_unlock_irqrestore(&il->sta_lock, flags);
diff --git a/drivers/net/wireless/intel/iwlegacy/4965-mac.c b/drivers/net/wireless/intel/iwlegacy/4965-mac.c
index 562e94870a9c..5772cbd9291c 100644
--- a/drivers/net/wireless/intel/iwlegacy/4965-mac.c
+++ b/drivers/net/wireless/intel/iwlegacy/4965-mac.c
@@ -3536,7 +3536,7 @@ il4965_alloc_bcast_station(struct il_priv *il)
u8 sta_id;
spin_lock_irqsave(&il->sta_lock, flags);
- sta_id = il_prep_station(il, il_bcast_addr, false, NULL);
+ sta_id = il_prep_station(il, ether_broadcast_addr, false, NULL);
if (sta_id == IL_INVALID_STATION) {
IL_ERR("Unable to prepare broadcast station\n");
spin_unlock_irqrestore(&il->sta_lock, flags);
diff --git a/drivers/net/wireless/intel/iwlegacy/common.c b/drivers/net/wireless/intel/iwlegacy/common.c
index 063e19ced7c8..5853b1dedea1 100644
--- a/drivers/net/wireless/intel/iwlegacy/common.c
+++ b/drivers/net/wireless/intel/iwlegacy/common.c
@@ -3378,9 +3378,6 @@ MODULE_PARM_DESC(bt_coex_active, "enable wifi/bluetooth co-exist");
u32 il_debug_level;
EXPORT_SYMBOL(il_debug_level);
-const u8 il_bcast_addr[ETH_ALEN] = { 0xFF, 0xFF, 0xFF, 0xFF, 0xFF, 0xFF };
-EXPORT_SYMBOL(il_bcast_addr);
-
#define MAX_BIT_RATE_40_MHZ 150 /* Mbps */
#define MAX_BIT_RATE_20_MHZ 72 /* Mbps */
static void
diff --git a/drivers/net/wireless/intel/iwlegacy/common.h b/drivers/net/wireless/intel/iwlegacy/common.h
index dc6a74a05983..6a6b43c5e4d7 100644
--- a/drivers/net/wireless/intel/iwlegacy/common.h
+++ b/drivers/net/wireless/intel/iwlegacy/common.h
@@ -860,7 +860,6 @@ struct il_hw_params {
*
****************************************************************************/
void il4965_update_chain_flags(struct il_priv *il);
-extern const u8 il_bcast_addr[ETH_ALEN];
int il_queue_space(const struct il_queue *q);
static inline int
il_queue_used(const struct il_queue *q, int i)
--
2.15.0
^ permalink raw reply related
* [PATCH 07/12] brcmfmac: Convert ALLFFMAC to ether_broadcast_addr
From: Joe Perches @ 2018-03-31 7:05 UTC (permalink / raw)
To: linux-kernel
Cc: Arend van Spriel, Franky Lin, Hante Meuleman, Chi-Hsien Lin,
Wright Feng, Kalle Valo, linux-wireless, brcm80211-dev-list.pdl,
brcm80211-dev-list, netdev
In-Reply-To: <cover.1522479607.git.joe@perches.com>
Remove the local ALLFFMAC extern array and use the new global instead.
Miscellanea:
o Convert char *mac to const char *mac as it can't be modified
Signed-off-by: Joe Perches <joe@perches.com>
---
drivers/net/wireless/broadcom/brcm80211/brcmfmac/common.c | 2 --
drivers/net/wireless/broadcom/brcm80211/brcmfmac/common.h | 2 --
drivers/net/wireless/broadcom/brcm80211/brcmfmac/flowring.c | 8 ++++----
3 files changed, 4 insertions(+), 8 deletions(-)
diff --git a/drivers/net/wireless/broadcom/brcm80211/brcmfmac/common.c b/drivers/net/wireless/broadcom/brcm80211/brcmfmac/common.c
index 105b8774fca9..cd3651069d0c 100644
--- a/drivers/net/wireless/broadcom/brcm80211/brcmfmac/common.c
+++ b/drivers/net/wireless/broadcom/brcm80211/brcmfmac/common.c
@@ -36,8 +36,6 @@ MODULE_AUTHOR("Broadcom Corporation");
MODULE_DESCRIPTION("Broadcom 802.11 wireless LAN fullmac driver.");
MODULE_LICENSE("Dual BSD/GPL");
-const u8 ALLFFMAC[ETH_ALEN] = { 0xff, 0xff, 0xff, 0xff, 0xff, 0xff };
-
#define BRCMF_DEFAULT_SCAN_CHANNEL_TIME 40
#define BRCMF_DEFAULT_SCAN_UNASSOC_TIME 40
diff --git a/drivers/net/wireless/broadcom/brcm80211/brcmfmac/common.h b/drivers/net/wireless/broadcom/brcm80211/brcmfmac/common.h
index ef914619e8e1..a34642cb4d2f 100644
--- a/drivers/net/wireless/broadcom/brcm80211/brcmfmac/common.h
+++ b/drivers/net/wireless/broadcom/brcm80211/brcmfmac/common.h
@@ -19,8 +19,6 @@
#include <linux/platform_data/brcmfmac.h>
#include "fwil_types.h"
-extern const u8 ALLFFMAC[ETH_ALEN];
-
#define BRCMF_FW_ALTPATH_LEN 256
/* Definitions for the module global and device specific settings are defined
diff --git a/drivers/net/wireless/broadcom/brcm80211/brcmfmac/flowring.c b/drivers/net/wireless/broadcom/brcm80211/brcmfmac/flowring.c
index d0b738da2458..f042531dd43c 100644
--- a/drivers/net/wireless/broadcom/brcm80211/brcmfmac/flowring.c
+++ b/drivers/net/wireless/broadcom/brcm80211/brcmfmac/flowring.c
@@ -73,13 +73,13 @@ u32 brcmf_flowring_lookup(struct brcmf_flowring *flow, u8 da[ETH_ALEN],
bool found;
bool sta;
u8 fifo;
- u8 *mac;
+ const u8 *mac;
fifo = brcmf_flowring_prio2fifo[prio];
sta = (flow->addr_mode[ifidx] == ADDR_INDIRECT);
mac = da;
if ((!sta) && (is_multicast_ether_addr(da))) {
- mac = (u8 *)ALLFFMAC;
+ mac = ether_broadcast_addr;
fifo = 0;
}
if ((sta) && (flow->tdls_active) &&
@@ -118,13 +118,13 @@ u32 brcmf_flowring_create(struct brcmf_flowring *flow, u8 da[ETH_ALEN],
bool found;
u8 fifo;
bool sta;
- u8 *mac;
+ const u8 *mac;
fifo = brcmf_flowring_prio2fifo[prio];
sta = (flow->addr_mode[ifidx] == ADDR_INDIRECT);
mac = da;
if ((!sta) && (is_multicast_ether_addr(da))) {
- mac = (u8 *)ALLFFMAC;
+ mac = ether_broadcast_addr;
fifo = 0;
}
if ((sta) && (flow->tdls_active) &&
--
2.15.0
^ permalink raw reply related
* [PATCH 05/12] net: atm: Use ether_broadcast_addr
From: Joe Perches @ 2018-03-31 7:05 UTC (permalink / raw)
To: linux-kernel; +Cc: David S. Miller, netdev
In-Reply-To: <cover.1522479607.git.joe@perches.com>
Use the new global instead of a local static to reduce object code size
a tiny bit.
Signed-off-by: Joe Perches <joe@perches.com>
---
net/atm/lec.c | 12 +++++-------
1 file changed, 5 insertions(+), 7 deletions(-)
diff --git a/net/atm/lec.c b/net/atm/lec.c
index 01d5d20a6eb1..ec47b45bd836 100644
--- a/net/atm/lec.c
+++ b/net/atm/lec.c
@@ -116,8 +116,6 @@ static struct lane2_ops lane2_ops = {
.associate_indicator = NULL /* spec 3.1.5 */
};
-static unsigned char bus_mac[ETH_ALEN] = { 0xff, 0xff, 0xff, 0xff, 0xff, 0xff };
-
/* Device structures */
static struct net_device *dev_lec[MAX_LEC_ITF];
@@ -1726,7 +1724,7 @@ static struct atm_vcc *lec_arp_resolve(struct lec_priv *priv,
case 1:
return priv->mcast_vcc;
case 2: /* LANE2 wants arp for multicast addresses */
- if (ether_addr_equal(mac_to_find, bus_mac))
+ if (ether_addr_equal(mac_to_find, ether_broadcast_addr))
return priv->mcast_vcc;
break;
default:
@@ -1954,7 +1952,7 @@ lec_vcc_added(struct lec_priv *priv, const struct atmlec_ioc *ioc_data,
if (ioc_data->receive == 2) {
pr_debug("LEC_ARP: Attaching mcast forward\n");
#if 0
- entry = lec_arp_find(priv, bus_mac);
+ entry = lec_arp_find(priv, ether_broadcast_addr);
if (!entry) {
pr_info("LEC_ARP: Multicast entry not found!\n");
goto out;
@@ -1963,7 +1961,7 @@ lec_vcc_added(struct lec_priv *priv, const struct atmlec_ioc *ioc_data,
entry->recv_vcc = vcc;
entry->old_recv_push = old_push;
#endif
- entry = make_entry(priv, bus_mac);
+ entry = make_entry(priv, ether_broadcast_addr);
if (entry == NULL)
goto out;
del_timer(&entry->timer);
@@ -1988,7 +1986,7 @@ lec_vcc_added(struct lec_priv *priv, const struct atmlec_ioc *ioc_data,
ioc_data->atm_addr[14], ioc_data->atm_addr[15],
ioc_data->atm_addr[16], ioc_data->atm_addr[17],
ioc_data->atm_addr[18], ioc_data->atm_addr[19]);
- entry = make_entry(priv, bus_mac);
+ entry = make_entry(priv, ether_broadcast_addr);
if (entry == NULL)
goto out;
memcpy(entry->atm_addr, ioc_data->atm_addr, ATM_ESA_LEN);
@@ -2071,7 +2069,7 @@ lec_vcc_added(struct lec_priv *priv, const struct atmlec_ioc *ioc_data,
* Not found, snatch address from first data packet that arrives
* from this vcc
*/
- entry = make_entry(priv, bus_mac);
+ entry = make_entry(priv, ether_broadcast_addr);
if (!entry)
goto out;
entry->vcc = vcc;
--
2.15.0
^ permalink raw reply related
* [PATCH 04/12] bridge: netfilter: Use the new global ether_<foo>_addr arrays
From: Joe Perches @ 2018-03-31 7:05 UTC (permalink / raw)
To: Pablo Neira Ayuso, Jozsef Kadlecsik, Florian Westphal
Cc: Stephen Hemminger, David S. Miller, netfilter-devel, coreteam,
bridge, netdev, linux-kernel
In-Reply-To: <cover.1522479607.git.joe@perches.com>
Remove the local consts and use the new globals.
Signed-off-by: Joe Perches <joe@perches.com>
---
net/bridge/netfilter/ebt_stp.c | 6 ++----
1 file changed, 2 insertions(+), 4 deletions(-)
diff --git a/net/bridge/netfilter/ebt_stp.c b/net/bridge/netfilter/ebt_stp.c
index 3140eb912d7e..2b7479cc0140 100644
--- a/net/bridge/netfilter/ebt_stp.c
+++ b/net/bridge/netfilter/ebt_stp.c
@@ -153,8 +153,6 @@ ebt_stp_mt(const struct sk_buff *skb, struct xt_action_param *par)
static int ebt_stp_mt_check(const struct xt_mtchk_param *par)
{
const struct ebt_stp_info *info = par->matchinfo;
- const u8 bridge_ula[6] = {0x01, 0x80, 0xc2, 0x00, 0x00, 0x00};
- const u8 msk[6] = {0xff, 0xff, 0xff, 0xff, 0xff, 0xff};
const struct ebt_entry *e = par->entryinfo;
if (info->bitmask & ~EBT_STP_MASK || info->invflags & ~EBT_STP_MASK ||
@@ -162,8 +160,8 @@ static int ebt_stp_mt_check(const struct xt_mtchk_param *par)
return -EINVAL;
/* Make sure the match only receives stp frames */
if (!par->nft_compat &&
- (!ether_addr_equal(e->destmac, bridge_ula) ||
- !ether_addr_equal(e->destmsk, msk) ||
+ (!ether_addr_equal(e->destmac, ether_stp_addr) ||
+ !ether_addr_equal(e->destmsk, ether_broadcast_addr) ||
!(e->bitmask & EBT_DESTMAC)))
return -EINVAL;
--
2.15.0
^ permalink raw reply related
* [PATCH 03/12] net: mac80211: Use global ether_broadcast_addr
From: Joe Perches @ 2018-03-31 7:05 UTC (permalink / raw)
To: Johannes Berg; +Cc: David S. Miller, linux-wireless, netdev, linux-kernel
In-Reply-To: <cover.1522479607.git.joe@perches.com>
Remove statics and use the new global ether_broadcast_addr instead
to save some overall object code size.
Signed-off-by: Joe Perches <joe@perches.com>
---
net/mac80211/iface.c | 5 +----
net/mac80211/key.c | 6 ++----
net/mac80211/mesh_hwmp.c | 19 ++++++++++---------
net/mac80211/mesh_pathtbl.c | 8 ++++----
4 files changed, 17 insertions(+), 21 deletions(-)
diff --git a/net/mac80211/iface.c b/net/mac80211/iface.c
index d13ba064951f..f203efc3c532 100644
--- a/net/mac80211/iface.c
+++ b/net/mac80211/iface.c
@@ -1387,9 +1387,6 @@ static void ieee80211_recalc_smps_work(struct work_struct *work)
static void ieee80211_setup_sdata(struct ieee80211_sub_if_data *sdata,
enum nl80211_iftype type)
{
- static const u8 bssid_wildcard[ETH_ALEN] = {0xff, 0xff, 0xff,
- 0xff, 0xff, 0xff};
-
/* clear type-dependent union */
memset(&sdata->u, 0, sizeof(sdata->u));
@@ -1442,7 +1439,7 @@ static void ieee80211_setup_sdata(struct ieee80211_sub_if_data *sdata,
ieee80211_sta_setup_sdata(sdata);
break;
case NL80211_IFTYPE_OCB:
- sdata->vif.bss_conf.bssid = bssid_wildcard;
+ sdata->vif.bss_conf.bssid = ether_broadcast_addr;
ieee80211_ocb_setup_sdata(sdata);
break;
case NL80211_IFTYPE_ADHOC:
diff --git a/net/mac80211/key.c b/net/mac80211/key.c
index aee05ec3f7ea..429f0f4bdc0d 100644
--- a/net/mac80211/key.c
+++ b/net/mac80211/key.c
@@ -53,8 +53,6 @@
* remove the key which waits for an RCU grace period.
*/
-static const u8 bcast_addr[ETH_ALEN] = { 0xFF, 0xFF, 0xFF, 0xFF, 0xFF, 0xFF };
-
static void assert_key_lock(struct ieee80211_local *local)
{
lockdep_assert_held(&local->key_mtx);
@@ -196,7 +194,7 @@ static int ieee80211_key_enable_hw_accel(struct ieee80211_key *key)
sdata_err(sdata,
"failed to set key (%d, %pM) to hardware (%d)\n",
key->conf.keyidx,
- sta ? sta->sta.addr : bcast_addr, ret);
+ sta ? sta->sta.addr : ether_broadcast_addr, ret);
out_unsupported:
switch (key->conf.cipher) {
@@ -253,7 +251,7 @@ static void ieee80211_key_disable_hw_accel(struct ieee80211_key *key)
sdata_err(sdata,
"failed to remove key (%d, %pM) from hardware (%d)\n",
key->conf.keyidx,
- sta ? sta->sta.addr : bcast_addr, ret);
+ sta ? sta->sta.addr : ether_broadcast_addr, ret);
key->flags &= ~KEY_FLAG_UPLOADED_TO_HARDWARE;
}
diff --git a/net/mac80211/mesh_hwmp.c b/net/mac80211/mesh_hwmp.c
index 35ad3983ae4b..23027ea80593 100644
--- a/net/mac80211/mesh_hwmp.c
+++ b/net/mac80211/mesh_hwmp.c
@@ -97,8 +97,6 @@ enum mpath_frame_type {
MPATH_RANN
};
-static const u8 broadcast_addr[ETH_ALEN] = {0xff, 0xff, 0xff, 0xff, 0xff, 0xff};
-
static int mesh_path_sel_frame_tx(enum mpath_frame_type action, u8 flags,
const u8 *orig_addr, u32 orig_sn,
u8 target_flags, const u8 *target,
@@ -645,7 +643,7 @@ static void hwmp_preq_frame_process(struct ieee80211_sub_if_data *sdata,
preq_id = PREQ_IE_PREQ_ID(preq_elem);
hopcount = PREQ_IE_HOPCOUNT(preq_elem) + 1;
da = (mpath && mpath->is_root) ?
- mpath->rann_snd_addr : broadcast_addr;
+ mpath->rann_snd_addr : ether_broadcast_addr;
if (flags & IEEE80211_PREQ_PROACTIVE_PREP_FLAG) {
target_addr = PREQ_IE_TARGET_ADDR(preq_elem);
@@ -779,7 +777,7 @@ static void hwmp_perr_frame_process(struct ieee80211_sub_if_data *sdata,
goto endperr;
mesh_path_error_tx(sdata, ttl, target_addr,
target_sn, target_rcode,
- broadcast_addr);
+ ether_broadcast_addr);
} else
spin_unlock_bh(&mpath->state_lock);
}
@@ -877,7 +875,8 @@ static void hwmp_rann_frame_process(struct ieee80211_sub_if_data *sdata,
if (ifmsh->mshcfg.dot11MeshForwarding) {
mesh_path_sel_frame_tx(MPATH_RANN, flags, orig_addr,
- orig_sn, 0, NULL, 0, broadcast_addr,
+ orig_sn, 0, NULL, 0,
+ ether_broadcast_addr,
hopcount, ttl, interval,
new_metric, 0, sdata);
}
@@ -1080,7 +1079,7 @@ void mesh_path_start_discovery(struct ieee80211_sub_if_data *sdata)
target_flags &= ~IEEE80211_PREQ_TO_FLAG;
spin_unlock_bh(&mpath->state_lock);
- da = (mpath->is_root) ? mpath->rann_snd_addr : broadcast_addr;
+ da = (mpath->is_root) ? mpath->rann_snd_addr : ether_broadcast_addr;
mesh_path_sel_frame_tx(MPATH_PREQ, 0, sdata->vif.addr, ifmsh->sn,
target_flags, mpath->dst, mpath->sn, da, 0,
ttl, lifetime, 0, ifmsh->preq_id++, sdata);
@@ -1244,7 +1243,8 @@ void mesh_path_tx_root_frame(struct ieee80211_sub_if_data *sdata)
switch (ifmsh->mshcfg.dot11MeshHWMPRootMode) {
case IEEE80211_PROACTIVE_RANN:
mesh_path_sel_frame_tx(MPATH_RANN, flags, sdata->vif.addr,
- ++ifmsh->sn, 0, NULL, 0, broadcast_addr,
+ ++ifmsh->sn, 0, NULL, 0,
+ ether_broadcast_addr,
0, ifmsh->mshcfg.element_ttl,
interval, 0, 0, sdata);
break;
@@ -1257,8 +1257,9 @@ void mesh_path_tx_root_frame(struct ieee80211_sub_if_data *sdata)
IEEE80211_PREQ_USN_FLAG;
mesh_path_sel_frame_tx(MPATH_PREQ, flags, sdata->vif.addr,
++ifmsh->sn, target_flags,
- (u8 *) broadcast_addr, 0, broadcast_addr,
- 0, ifmsh->mshcfg.element_ttl, interval,
+ ether_broadcast_addr, 0,
+ ether_broadcast_addr, 0,
+ ifmsh->mshcfg.element_ttl, interval,
0, ifmsh->preq_id++, sdata);
break;
default:
diff --git a/net/mac80211/mesh_pathtbl.c b/net/mac80211/mesh_pathtbl.c
index a5125624a76d..8b16f7315fac 100644
--- a/net/mac80211/mesh_pathtbl.c
+++ b/net/mac80211/mesh_pathtbl.c
@@ -501,7 +501,6 @@ void mesh_plink_broken(struct sta_info *sta)
{
struct ieee80211_sub_if_data *sdata = sta->sdata;
struct mesh_table *tbl = sdata->u.mesh.mesh_paths;
- static const u8 bcast[ETH_ALEN] = {0xff, 0xff, 0xff, 0xff, 0xff, 0xff};
struct mesh_path *mpath;
struct rhashtable_iter iter;
int ret;
@@ -525,9 +524,10 @@ void mesh_plink_broken(struct sta_info *sta)
++mpath->sn;
spin_unlock_bh(&mpath->state_lock);
mesh_path_error_tx(sdata,
- sdata->u.mesh.mshcfg.element_ttl,
- mpath->dst, mpath->sn,
- WLAN_REASON_MESH_PATH_DEST_UNREACHABLE, bcast);
+ sdata->u.mesh.mshcfg.element_ttl,
+ mpath->dst, mpath->sn,
+ WLAN_REASON_MESH_PATH_DEST_UNREACHABLE,
+ ether_broadcast_addr);
}
}
rhashtable_walk_stop(&iter);
--
2.15.0
^ permalink raw reply related
* [PATCH 02/12] treewide/net: Rename eth_stp_addr to ether_stp_addr
From: Joe Perches @ 2018-03-31 7:05 UTC (permalink / raw)
To: Andrew Lunn, Vivien Didelot, Florian Fainelli, Stephen Hemminger
Cc: David S. Miller, netdev, linux-kernel, bridge
In-Reply-To: <cover.1522479607.git.joe@perches.com>
eth_stp_addr is not in the same form as the other global ether_<foo>_addr
addresses like ether_broadcast_addr.
Convert it treewide.
Miscellanea:
o Add comment to the ether_stp_addr define to show it's for spanning-tree
Signed-off-by: Joe Perches <joe@perches.com>
---
drivers/net/dsa/lan9303-core.c | 4 ++--
include/linux/etherdevice.h | 3 ++-
net/bridge/br_device.c | 4 ++--
3 files changed, 6 insertions(+), 5 deletions(-)
diff --git a/drivers/net/dsa/lan9303-core.c b/drivers/net/dsa/lan9303-core.c
index fefa454f3e56..a6f015ef251a 100644
--- a/drivers/net/dsa/lan9303-core.c
+++ b/drivers/net/dsa/lan9303-core.c
@@ -789,7 +789,7 @@ static int lan9303_separate_ports(struct lan9303 *chip)
{
int ret;
- lan9303_alr_del_port(chip, eth_stp_addr, 0);
+ lan9303_alr_del_port(chip, ether_stp_addr, 0);
ret = lan9303_write_switch_reg(chip, LAN9303_SWE_PORT_MIRROR,
LAN9303_SWE_PORT_MIRROR_SNIFFER_PORT0 |
LAN9303_SWE_PORT_MIRROR_MIRRORED_PORT1 |
@@ -814,7 +814,7 @@ static void lan9303_bridge_ports(struct lan9303 *chip)
lan9303_write_switch_reg(chip, LAN9303_SWE_PORT_STATE,
chip->swe_port_state);
- lan9303_alr_add_port(chip, eth_stp_addr, 0, true);
+ lan9303_alr_add_port(chip, ether_stp_addr, 0, true);
}
static void lan9303_handle_reset(struct lan9303 *chip)
diff --git a/include/linux/etherdevice.h b/include/linux/etherdevice.h
index 85d2486b2959..142da8043b24 100644
--- a/include/linux/etherdevice.h
+++ b/include/linux/etherdevice.h
@@ -70,7 +70,8 @@ extern const u8 ether_zero_addr[ETH_ALEN]; /* all zeros */
/* Reserved Ethernet Addresses per IEEE 802.1Q */
extern const u8 ether_reserved_addr_base[ETH_ALEN];
-#define eth_stp_addr ether_reserved_addr_base
+/* Ethernet bridge - spanning tree protocol */
+#define ether_stp_addr ether_reserved_addr_base
/**
* is_link_local_ether_addr - Determine if given Ethernet address is link-local
diff --git a/net/bridge/br_device.c b/net/bridge/br_device.c
index 278fc999d355..3abcf69d1976 100644
--- a/net/bridge/br_device.c
+++ b/net/bridge/br_device.c
@@ -1,4 +1,4 @@
-/*
+gg/*
* Device handling code
* Linux ethernet bridge
*
@@ -431,7 +431,7 @@ void br_dev_setup(struct net_device *dev)
br->bridge_id.prio[0] = 0x80;
br->bridge_id.prio[1] = 0x00;
- ether_addr_copy(br->group_addr, eth_stp_addr);
+ ether_addr_copy(br->group_addr, ether_stp_addr);
br->stp_enabled = BR_NO_STP;
br->group_fwd_mask = BR_GROUPFWD_DEFAULT;
--
2.15.0
^ permalink raw reply related
* [PATCH 01/12] ethernet: Add generic ether_<foo>_addr addresses
From: Joe Perches @ 2018-03-31 7:05 UTC (permalink / raw)
To: linux-kernel; +Cc: David S. Miller, netdev
In-Reply-To: <cover.1522479607.git.joe@perches.com>
Treewide there are ~60 declarations of Ethernet broadcast or zero address
use as a 6 byte array that are later used as either an output for vsprintf
extension %pM or as a source array to copy or compare.
Create const globals for these uses with EXPORT_SYMBOL for modules.
Miscellanea:
o Rename and move static const eth_reservd_addr_base from etherdevice.h
to this new ether_addrs.c file so it is no longer oddly declared
as static const in a .h file
Signed-off-by: Joe Perches <joe@perches.com>
---
include/linux/etherdevice.h | 12 ++++++++----
net/ethernet/Makefile | 2 +-
net/ethernet/ether_addrs.c | 19 +++++++++++++++++++
3 files changed, 28 insertions(+), 5 deletions(-)
create mode 100644 net/ethernet/ether_addrs.c
diff --git a/include/linux/etherdevice.h b/include/linux/etherdevice.h
index 79563840c295..85d2486b2959 100644
--- a/include/linux/etherdevice.h
+++ b/include/linux/etherdevice.h
@@ -63,10 +63,14 @@ struct sk_buff **eth_gro_receive(struct sk_buff **head,
struct sk_buff *skb);
int eth_gro_complete(struct sk_buff *skb, int nhoff);
+/* Generic Ethernet addresses */
+extern const u8 ether_broadcast_addr[ETH_ALEN]; /* all 0xff */
+extern const u8 ether_zero_addr[ETH_ALEN]; /* all zeros */
+
/* Reserved Ethernet Addresses per IEEE 802.1Q */
-static const u8 eth_reserved_addr_base[ETH_ALEN] __aligned(2) =
-{ 0x01, 0x80, 0xc2, 0x00, 0x00, 0x00 };
-#define eth_stp_addr eth_reserved_addr_base
+extern const u8 ether_reserved_addr_base[ETH_ALEN];
+
+#define eth_stp_addr ether_reserved_addr_base
/**
* is_link_local_ether_addr - Determine if given Ethernet address is link-local
@@ -80,7 +84,7 @@ static const u8 eth_reserved_addr_base[ETH_ALEN] __aligned(2) =
static inline bool is_link_local_ether_addr(const u8 *addr)
{
__be16 *a = (__be16 *)addr;
- static const __be16 *b = (const __be16 *)eth_reserved_addr_base;
+ static const __be16 *b = (const __be16 *)ether_reserved_addr_base;
static const __be16 m = cpu_to_be16(0xfff0);
#if defined(CONFIG_HAVE_EFFICIENT_UNALIGNED_ACCESS)
diff --git a/net/ethernet/Makefile b/net/ethernet/Makefile
index 323177505404..fbbcfec2ba10 100644
--- a/net/ethernet/Makefile
+++ b/net/ethernet/Makefile
@@ -2,4 +2,4 @@
# Makefile for the Linux Ethernet layer.
#
-obj-y += eth.o
+obj-y += eth.o ether_addrs.o
diff --git a/net/ethernet/ether_addrs.c b/net/ethernet/ether_addrs.c
new file mode 100644
index 000000000000..e0b7a57628e8
--- /dev/null
+++ b/net/ethernet/ether_addrs.c
@@ -0,0 +1,19 @@
+// SPDX-License-Identifier: GPL-2.0
+/* Various const global Ethernet addresses */
+
+#include <linux/etherdevice.h>
+
+const u8 ether_broadcast_addr[ETH_ALEN] __aligned(2) = {
+ 0xff, 0xff, 0xff, 0xff, 0xff, 0xff
+};
+EXPORT_SYMBOL(ether_broadcast_addr);
+
+const u8 ether_zero_addr[ETH_ALEN] __aligned(2) = {
+ 0x00, 0x00, 0x00, 0x00, 0x00, 0x00
+};
+EXPORT_SYMBOL(ether_zero_addr);
+
+const u8 ether_reserved_addr_base[ETH_ALEN] __aligned(2) = {
+ 0x01, 0x80, 0xc2, 0x00, 0x00, 0x00
+};
+EXPORT_SYMBOL(ether_reserved_addr_base);
--
2.15.0
^ permalink raw reply related
* [PATCH 00/12] Ethernet: Add and use ether_<type>_addr globals
From: Joe Perches @ 2018-03-31 7:05 UTC (permalink / raw)
To: netdev, linux-wireless, b43-dev, bridge, netfilter-devel,
coreteam
Cc: linux-kernel, brcm80211-dev-list.pdl, brcm80211-dev-list
There are many local static and non-static arrays that are used for
Ethernet broadcast address output or comparison.
Centralize the array into a single separate file and remove the local
arrays.
Joe Perches (12):
ethernet: Add generic ether_<foo>_addr addresses
treewide/net: Rename eth_stp_addr to ether_stp_addr
net: mac80211: Use global ether_broadcast_addr
bridge: netfilter: Use the new global ether_<foo>_addr arrays
net: atm: Use ether_broadcast_addr
wireless: Convert simple uses of a static const Ethernet broadcast address
brcmfmac: Convert ALLFFMAC to ether_broadcast_addr
iwlegacy: Remove EXPORT_SYMBOL(il_bcast_addr) and use ether_broadcast_addr
iwlwifi: Remove local iwl_bcast_addr and use ether_broadcast_addr
mvpp2: Use ether_broadcast_addr instead of a local array
qlogic: Convert local bcast_addr to global ether_broadcast_addr
ethernet: Use ether_zero_addr instead of local statics
drivers/net/dsa/lan9303-core.c | 4 ++--
drivers/net/ethernet/broadcom/b44.c | 5 ++---
drivers/net/ethernet/freescale/gianfar.c | 3 +--
drivers/net/ethernet/marvell/mvpp2.c | 4 +---
drivers/net/ethernet/qlogic/netxen/netxen_nic_hw.c | 5 +----
drivers/net/ethernet/qlogic/qlcnic/qlcnic_hw.c | 6 ++----
.../net/ethernet/qlogic/qlcnic/qlcnic_sriov_common.c | 6 ++----
drivers/net/wireless/admtek/adm8211.c | 3 +--
drivers/net/wireless/ath/carl9170/mac.c | 4 +---
drivers/net/wireless/broadcom/b43/main.c | 3 +--
.../net/wireless/broadcom/brcm80211/brcmfmac/common.c | 2 --
.../net/wireless/broadcom/brcm80211/brcmfmac/common.h | 2 --
.../wireless/broadcom/brcm80211/brcmfmac/flowring.c | 8 ++++----
drivers/net/wireless/intel/iwlegacy/3945-mac.c | 2 +-
drivers/net/wireless/intel/iwlegacy/4965-mac.c | 2 +-
drivers/net/wireless/intel/iwlegacy/common.c | 3 ---
drivers/net/wireless/intel/iwlegacy/common.h | 1 -
drivers/net/wireless/intel/iwlwifi/dvm/dev.h | 1 -
drivers/net/wireless/intel/iwlwifi/dvm/scan.c | 2 +-
drivers/net/wireless/intel/iwlwifi/dvm/sta.c | 4 +---
drivers/net/wireless/marvell/mwifiex/cfg80211.c | 3 +--
drivers/net/wireless/realtek/rtlwifi/core.c | 5 ++---
drivers/net/wireless/rndis_wlan.c | 6 +-----
drivers/net/wireless/ti/wl1251/main.c | 5 +----
drivers/net/wireless/ti/wlcore/main.c | 5 +----
include/linux/etherdevice.h | 13 +++++++++----
net/atm/lec.c | 12 +++++-------
net/bridge/br_device.c | 4 ++--
net/bridge/netfilter/ebt_stp.c | 6 ++----
net/ethernet/Makefile | 2 +-
net/ethernet/ether_addrs.c | 19 +++++++++++++++++++
net/mac80211/iface.c | 5 +----
net/mac80211/key.c | 6 ++----
net/mac80211/mesh_hwmp.c | 19 ++++++++++---------
net/mac80211/mesh_pathtbl.c | 8 ++++----
35 files changed, 83 insertions(+), 105 deletions(-)
create mode 100644 net/ethernet/ether_addrs.c
--
2.15.0
^ permalink raw reply
* Re: [PATCH] mt7601u: phy: mark expected switch fall-through
From: Jakub Kicinski @ 2018-03-31 6:17 UTC (permalink / raw)
To: Gustavo A. R. Silva; +Cc: Kalle Valo, linux-wireless, netdev, linux-kernel
In-Reply-To: <20180330211223.GA22497@embeddedgus>
On Fri, 30 Mar 2018 16:12:23 -0500, Gustavo A. R. Silva wrote:
> In preparation to enabling -Wimplicit-fallthrough, mark switch cases
> where we are expecting to fall through.
>
> Signed-off-by: Gustavo A. R. Silva <gustavo@embeddedor.com>
Acked-by: Jakub Kicinski <kubakici@wp.pl>
^ permalink raw reply
* Re: [PATCH net-next] netdevsim: Change nsim_devlink_setup to return error to caller
From: Jakub Kicinski @ 2018-03-31 6:15 UTC (permalink / raw)
To: David Ahern; +Cc: netdev
In-Reply-To: <20180330162851.3709-1-dsa@cumulusnetworks.com>
On Fri, 30 Mar 2018 09:28:51 -0700, David Ahern wrote:
> Change nsim_devlink_setup to return any error back to the caller and
> update nsim_init to handle it.
>
> Requested-by: Jakub Kicinski <jakub.kicinski@netronome.com>
> Signed-off-by: David Ahern <dsa@cumulusnetworks.com>
Acked-by: Jakub Kicinski <jakub.kicinski@netronome.com>
Thank you!
^ permalink raw reply
* Re: [PATCH net-next 0/9] devlink: Add support for region access
From: Alex Vesker @ 2018-03-31 6:11 UTC (permalink / raw)
To: David Ahern, Andrew Lunn
Cc: David S. Miller, netdev, Tariq Toukan, Jiri Pirko
In-Reply-To: <86ebf2c1-dcdf-bfad-f1b8-cf73acf08ddc@gmail.com>
On 3/31/2018 1:26 AM, David Ahern wrote:
> On 3/30/18 1:39 PM, Alex Vesker wrote:
>>
>> On 3/30/2018 7:57 PM, David Ahern wrote:
>>> On 3/30/18 8:34 AM, Andrew Lunn wrote:
>>>>>> And it seems to want contiguous pages. How well does that work after
>>>>>> the system has been running for a while and memory is fragmented?
>>>>> The allocation can be changed, there is no read need for contiguous
>>>>> pages.
>>>>> It is important to note that we the amount of snapshots is limited
>>>>> by the
>>>>> driver
>>>>> this can be based on the dump size or expected frequency of collection.
>>>>> I also prefer not to pre-allocate this memory.
>>>> The driver code also asks for a 1MB contiguous chunk of memory! You
>>>> really should think about this API, how can you avoid double memory
>>>> allocations. And can kvmalloc be used. But then you get into the
>>>> problem for DMA'ing the memory from the device...
>>>>
>>>> This API also does not scale. 1MB is actually quite small. I'm sure
>>>> there is firmware running on CPUs with a lot more than 1MB of RAM.
>>>> How well does with API work with 64MB? Say i wanted to snapshot my
>>>> GPU? Or the MC/BMC?
>>>>
>>> That and the drivers control the number of snapshots. The user should be
>>> able to control the number of snapshots, and an option to remove all
>>> snapshots to free up that memory.
>> There is an option to free up this memory, using a delete command.
>> The reason I added the option to control the number of snapshots from
>> the driver side only is because the driver knows the size of the snapshots
>> and when/why they will be taken.
>> For example in our mlx4 driver the snapshots are taken on rare failures,
>> the snapshot is quite large and from past analyses the first dump is
>> usually
>> the important one, this means that 8 is more than enough in my case.
>> If a user wants more than that he can always monitor notification read
>> the snapshot and delete once backup-ed, there is no reason for keeping
>> all of this data in the kernel.
>>
>>
> I was thinking less. ie., a user says keep only 1 or 2 snapshots or
> disable snapshots altogether.
Devlink configuration is not persistent if the driver is reloaded, currently
there is no way to sync this. One or two might not be enough time to
read, delete and make room for the next one, as I said each driver should
do its calculations here based on frequency, size and even the time it takes
capturing it. The user can't know if one snapshot is enough for debug
I saw cases in which debug requires more than one snapshot to make
sure a health clock is incremented and the FW is alive.
I want to be able to login to a customer and accessing this snapshot
without any previous configuration from the user and not asking for
enabling the feature and then waiting for a repro...this will help
debugging issues that are hard to reproduce, I don't see any reason
to disable this.
^ permalink raw reply
* [PATCH net-next] vlan: vlan_hw_filter_capable() can be static
From: Wei Yongjun @ 2018-03-31 6:11 UTC (permalink / raw)
To: Vishakha Narvekar, Toshiaki Makita, Kate Stewart, Tariq Toukan,
Gal Pressman
Cc: Wei Yongjun, netdev, kernel-janitors
Fixes the following sparse warning:
net/8021q/vlan_core.c:168:6: warning:
symbol 'vlan_hw_filter_capable' was not declared. Should it be static?
Signed-off-by: Wei Yongjun <weiyongjun1@huawei.com>
---
net/8021q/vlan_core.c | 2 +-
1 file changed, 1 insertion(+), 1 deletion(-)
diff --git a/net/8021q/vlan_core.c b/net/8021q/vlan_core.c
index c8d7abd..4f60e86 100644
--- a/net/8021q/vlan_core.c
+++ b/net/8021q/vlan_core.c
@@ -165,7 +165,7 @@ struct vlan_vid_info {
int refcount;
};
-bool vlan_hw_filter_capable(const struct net_device *dev, __be16 proto)
+static bool vlan_hw_filter_capable(const struct net_device *dev, __be16 proto)
{
if (proto == htons(ETH_P_8021Q) &&
dev->features & NETIF_F_HW_VLAN_CTAG_FILTER)
^ permalink raw reply related
* Re: [PATCH v3 net-next 07/12] rhashtable: add schedule points
From: Herbert Xu @ 2018-03-31 4:21 UTC (permalink / raw)
To: Eric Dumazet
Cc: David S . Miller, netdev, Florian Westphal, Thomas Graf,
Jesper Dangaard Brouer, Alexander Aring, Stefan Schmidt,
Kirill Tkhai, Eric Dumazet
In-Reply-To: <20180331005309.179376-8-edumazet@google.com>
On Fri, Mar 30, 2018 at 05:53:04PM -0700, Eric Dumazet wrote:
> Rehashing and destroying large hash table takes a lot of time,
> and happens in process context. It is safe to add cond_resched()
> in rhashtable_rehash_table() and rhashtable_free_and_destroy()
>
> Signed-off-by: Eric Dumazet <edumazet@google.com>
Acked-by: Herbert Xu <herbert@gondor.apana.org.au>
Thanks,
--
Email: Herbert Xu <herbert@gondor.apana.org.au>
Home Page: http://gondor.apana.org.au/~herbert/
PGP Key: http://gondor.apana.org.au/~herbert/pubkey.txt
^ permalink raw reply
* [PATCH iproute2-next 1/1] tc: jsonify sample action
From: Roman Mashak @ 2018-03-31 4:20 UTC (permalink / raw)
To: dsahern; +Cc: stephen, netdev, kernel, jhs, xiyou.wangcong, jiri, Roman Mashak
Signed-off-by: Roman Mashak <mrv@mojatatu.com>
---
tc/m_sample.c | 22 +++++++++++++---------
1 file changed, 13 insertions(+), 9 deletions(-)
diff --git a/tc/m_sample.c b/tc/m_sample.c
index 1e18c5154fe6..39a99246a8ea 100644
--- a/tc/m_sample.c
+++ b/tc/m_sample.c
@@ -149,23 +149,27 @@ static int print_sample(struct action_util *au, FILE *f, struct rtattr *arg)
if (!tb[TCA_SAMPLE_PARMS] || !tb[TCA_SAMPLE_RATE] ||
!tb[TCA_SAMPLE_PSAMPLE_GROUP]) {
- fprintf(f, "[NULL sample parameters]");
+ print_string(PRINT_FP, NULL, "%s", "[NULL sample parameters]");
return -1;
}
p = RTA_DATA(tb[TCA_SAMPLE_PARMS]);
- fprintf(f, "sample rate 1/%d group %d",
- rta_getattr_u32(tb[TCA_SAMPLE_RATE]),
- rta_getattr_u32(tb[TCA_SAMPLE_PSAMPLE_GROUP]));
+ print_string(PRINT_ANY, "kind", "%s ", "sample");
+ print_uint(PRINT_ANY, "rate", "rate 1/%u ",
+ rta_getattr_u32(tb[TCA_SAMPLE_RATE]));
+ print_uint(PRINT_ANY, "group", "group %u",
+ rta_getattr_u32(tb[TCA_SAMPLE_PSAMPLE_GROUP]));
if (tb[TCA_SAMPLE_TRUNC_SIZE])
- fprintf(f, " trunc_size %d",
- rta_getattr_u32(tb[TCA_SAMPLE_TRUNC_SIZE]));
+ print_uint(PRINT_ANY, "trunc_size", " trunc_size %u",
+ rta_getattr_u32(tb[TCA_SAMPLE_TRUNC_SIZE]));
print_action_control(f, " ", p->action, "");
- fprintf(f, "\n\tindex %d ref %d bind %d", p->index, p->refcnt,
- p->bindcnt);
+ print_string(PRINT_FP, NULL, "%s", _SL_);
+ print_uint(PRINT_ANY, "index", "\t index %u", p->index);
+ print_int(PRINT_ANY, "ref", " ref %d", p->refcnt);
+ print_int(PRINT_ANY, "bind", " bind %d", p->bindcnt);
if (show_stats) {
if (tb[TCA_SAMPLE_TM]) {
@@ -174,7 +178,7 @@ static int print_sample(struct action_util *au, FILE *f, struct rtattr *arg)
print_tm(f, tm);
}
}
- fprintf(f, "\n");
+ print_string(PRINT_FP, NULL, "%s", _SL_);
return 0;
}
--
2.7.4
^ permalink raw reply related
* Re: [PATCH v2 net-next 07/12] rhashtable: add schedule points
From: Herbert Xu @ 2018-03-31 4:19 UTC (permalink / raw)
To: Eric Dumazet
Cc: David S . Miller, netdev, Florian Westphal, Thomas Graf,
Jesper Dangaard Brouer, Alexander Aring, Stefan Schmidt,
Kirill Tkhai, Eric Dumazet
In-Reply-To: <20180330204236.43675-8-edumazet@google.com>
On Fri, Mar 30, 2018 at 01:42:31PM -0700, Eric Dumazet wrote:
> Rehashing and destroying large hash table takes a lot of time,
> and happens in process context. It is safe to add cond_resched()
> in rhashtable_rehash_table() and rhashtable_free_and_destroy()
>
> Signed-off-by: Eric Dumazet <edumazet@google.com>
Acked-by: Herbert Xu <herbert@gondor.apana.org.au>
Thanks,
--
Email: Herbert Xu <herbert@gondor.apana.org.au>
Home Page: http://gondor.apana.org.au/~herbert/
PGP Key: http://gondor.apana.org.au/~herbert/pubkey.txt
^ permalink raw reply
* [PATCH iproute2-next 1/1] tc: support oneline mode in action generic printer functions
From: Roman Mashak @ 2018-03-31 4:16 UTC (permalink / raw)
To: dsahern; +Cc: stephen, netdev, kernel, jhs, xiyou.wangcong, jiri, Roman Mashak
Signed-off-by: Roman Mashak <mrv@mojatatu.com>
---
tc/m_action.c | 12 ++++++++----
1 file changed, 8 insertions(+), 4 deletions(-)
diff --git a/tc/m_action.c b/tc/m_action.c
index 8891659ae15a..2f85d353279a 100644
--- a/tc/m_action.c
+++ b/tc/m_action.c
@@ -301,19 +301,21 @@ static int tc_print_one_action(FILE *f, struct rtattr *arg)
return err;
if (show_stats && tb[TCA_ACT_STATS]) {
- print_string(PRINT_FP, NULL, "\tAction statistics:\n", NULL);
+ print_string(PRINT_FP, NULL, "\tAction statistics:", NULL);
+ print_string(PRINT_FP, NULL, "%s", _SL_);
open_json_object("stats");
print_tcstats2_attr(f, tb[TCA_ACT_STATS], "\t", NULL);
close_json_object();
- print_string(PRINT_FP, NULL, "\n", NULL);
+ print_string(PRINT_FP, NULL, "%s", _SL_);
}
if (tb[TCA_ACT_COOKIE]) {
int strsz = RTA_PAYLOAD(tb[TCA_ACT_COOKIE]);
char b1[strsz * 2 + 1];
- print_string(PRINT_ANY, "cookie", "\tcookie %s\n",
+ print_string(PRINT_ANY, "cookie", "\tcookie %s",
hexstring_n2a(RTA_DATA(tb[TCA_ACT_COOKIE]),
strsz, b1, sizeof(b1)));
+ print_string(PRINT_FP, NULL, "%s", _SL_);
}
return 0;
@@ -369,8 +371,9 @@ tc_print_action(FILE *f, const struct rtattr *arg, unsigned short tot_acts)
for (i = 0; i <= tot_acts; i++) {
if (tb[i]) {
open_json_object(NULL);
+ print_string(PRINT_FP, NULL, "%s", _SL_);
print_uint(PRINT_ANY, "order",
- "\n\taction order %u: ", i);
+ "\taction order %u: ", i);
if (tc_print_one_action(f, tb[i]) < 0) {
print_string(PRINT_FP, NULL,
"Error printing action\n", NULL);
@@ -410,6 +413,7 @@ int print_action(const struct sockaddr_nl *who,
open_json_object(NULL);
print_uint(PRINT_ANY, "total acts", "total acts %u",
tot_acts ? *tot_acts : 0);
+ print_string(PRINT_FP, NULL, "%s", _SL_);
close_json_object();
if (tb[TCA_ACT_TAB] == NULL) {
if (n->nlmsg_type != RTM_GETACTION)
--
2.7.4
^ permalink raw reply related
* [PATCH v3 net-next 12/12] inet: frags: break the 2GB limit for frags storage
From: Eric Dumazet @ 2018-03-31 0:53 UTC (permalink / raw)
To: David S . Miller
Cc: netdev, Florian Westphal, Herbert Xu, Thomas Graf,
Jesper Dangaard Brouer, Alexander Aring, Stefan Schmidt,
Kirill Tkhai, Eric Dumazet, Eric Dumazet
In-Reply-To: <20180331005309.179376-1-edumazet@google.com>
Some users are willing to provision huge amounts of memory to be able
to perform reassembly reasonnably well under pressure.
Current memory tracking is using one atomic_t and integers.
Switch to atomic_long_t so that 64bit arches can use more than 2GB,
without any cost for 32bit arches.
Note that this patch avoids an overflow error, if high_thresh was set
to ~2GB, since this test in inet_frag_alloc() was never true :
if (... || frag_mem_limit(nf) > nf->high_thresh)
Tested:
$ echo 16000000000 >/proc/sys/net/ipv4/ipfrag_high_thresh
<frag DDOS>
$ grep FRAG /proc/net/sockstat
FRAG: inuse 14705885 memory 16000002880
$ nstat -n ; sleep 1 ; nstat | grep Reas
IpReasmReqds 3317150 0.0
IpReasmFails 3317112 0.0
Signed-off-by: Eric Dumazet <edumazet@google.com>
---
Documentation/networking/ip-sysctl.txt | 4 ++--
include/net/inet_frag.h | 20 ++++++++++----------
net/ieee802154/6lowpan/reassembly.c | 10 +++++-----
net/ipv4/ip_fragment.c | 10 +++++-----
net/ipv4/proc.c | 2 +-
net/ipv6/netfilter/nf_conntrack_reasm.c | 10 +++++-----
net/ipv6/proc.c | 2 +-
net/ipv6/reassembly.c | 6 +++---
8 files changed, 32 insertions(+), 32 deletions(-)
diff --git a/Documentation/networking/ip-sysctl.txt b/Documentation/networking/ip-sysctl.txt
index 6f2a3670e44b6662ce53c16cb7ca1e4f61274c15..5dc1a040a2f1db610873de26c2d79bc57ac5a1a2 100644
--- a/Documentation/networking/ip-sysctl.txt
+++ b/Documentation/networking/ip-sysctl.txt
@@ -133,10 +133,10 @@ min_adv_mss - INTEGER
IP Fragmentation:
-ipfrag_high_thresh - INTEGER
+ipfrag_high_thresh - LONG INTEGER
Maximum memory used to reassemble IP fragments.
-ipfrag_low_thresh - INTEGER
+ipfrag_low_thresh - LONG INTEGER
(Obsolete since linux-4.17)
Maximum memory used to reassemble IP fragments before the kernel
begins to remove incomplete fragment queues to free up resources.
diff --git a/include/net/inet_frag.h b/include/net/inet_frag.h
index 95e353e3305b43253084d972e32538138bcc5454..a52e7273e7a59bc8ce47b21d29235a740add8db0 100644
--- a/include/net/inet_frag.h
+++ b/include/net/inet_frag.h
@@ -8,11 +8,11 @@ struct netns_frags {
struct rhashtable rhashtable ____cacheline_aligned_in_smp;
/* Keep atomic mem on separate cachelines in structs that include it */
- atomic_t mem ____cacheline_aligned_in_smp;
+ atomic_long_t mem ____cacheline_aligned_in_smp;
/* sysctls */
+ long high_thresh;
+ long low_thresh;
int timeout;
- int high_thresh;
- int low_thresh;
int max_dist;
struct inet_frags *f;
};
@@ -102,7 +102,7 @@ void inet_frags_fini(struct inet_frags *);
static inline int inet_frags_init_net(struct netns_frags *nf)
{
- atomic_set(&nf->mem, 0);
+ atomic_long_set(&nf->mem, 0);
return rhashtable_init(&nf->rhashtable, &nf->f->rhash_params);
}
void inet_frags_exit_net(struct netns_frags *nf);
@@ -119,19 +119,19 @@ static inline void inet_frag_put(struct inet_frag_queue *q)
/* Memory Tracking Functions. */
-static inline int frag_mem_limit(struct netns_frags *nf)
+static inline long frag_mem_limit(const struct netns_frags *nf)
{
- return atomic_read(&nf->mem);
+ return atomic_long_read(&nf->mem);
}
-static inline void sub_frag_mem_limit(struct netns_frags *nf, int i)
+static inline void sub_frag_mem_limit(struct netns_frags *nf, long val)
{
- atomic_sub(i, &nf->mem);
+ atomic_long_sub(val, &nf->mem);
}
-static inline void add_frag_mem_limit(struct netns_frags *nf, int i)
+static inline void add_frag_mem_limit(struct netns_frags *nf, long val)
{
- atomic_add(i, &nf->mem);
+ atomic_long_add(val, &nf->mem);
}
/* RFC 3168 support :
diff --git a/net/ieee802154/6lowpan/reassembly.c b/net/ieee802154/6lowpan/reassembly.c
index 7eaa0617e277b829b801aee4e75f0ec61b2daf41..1f0857937ad187b48ff2af5e9c8570cf2b133fd2 100644
--- a/net/ieee802154/6lowpan/reassembly.c
+++ b/net/ieee802154/6lowpan/reassembly.c
@@ -411,23 +411,23 @@ int lowpan_frag_rcv(struct sk_buff *skb, u8 frag_type)
}
#ifdef CONFIG_SYSCTL
-static int zero;
+static long zero;
static struct ctl_table lowpan_frags_ns_ctl_table[] = {
{
.procname = "6lowpanfrag_high_thresh",
.data = &init_net.ieee802154_lowpan.frags.high_thresh,
- .maxlen = sizeof(int),
+ .maxlen = sizeof(unsigned long),
.mode = 0644,
- .proc_handler = proc_dointvec_minmax,
+ .proc_handler = proc_doulongvec_minmax,
.extra1 = &init_net.ieee802154_lowpan.frags.low_thresh
},
{
.procname = "6lowpanfrag_low_thresh",
.data = &init_net.ieee802154_lowpan.frags.low_thresh,
- .maxlen = sizeof(int),
+ .maxlen = sizeof(unsigned long),
.mode = 0644,
- .proc_handler = proc_dointvec_minmax,
+ .proc_handler = proc_doulongvec_minmax,
.extra1 = &zero,
.extra2 = &init_net.ieee802154_lowpan.frags.high_thresh
},
diff --git a/net/ipv4/ip_fragment.c b/net/ipv4/ip_fragment.c
index b0366224f314ae521d8c1f8fe04c53e419292b4c..053869f2c49b9fd7a87316f1ef1416568b1bf508 100644
--- a/net/ipv4/ip_fragment.c
+++ b/net/ipv4/ip_fragment.c
@@ -678,23 +678,23 @@ struct sk_buff *ip_check_defrag(struct net *net, struct sk_buff *skb, u32 user)
EXPORT_SYMBOL(ip_check_defrag);
#ifdef CONFIG_SYSCTL
-static int zero;
+static long zero;
static struct ctl_table ip4_frags_ns_ctl_table[] = {
{
.procname = "ipfrag_high_thresh",
.data = &init_net.ipv4.frags.high_thresh,
- .maxlen = sizeof(int),
+ .maxlen = sizeof(unsigned long),
.mode = 0644,
- .proc_handler = proc_dointvec_minmax,
+ .proc_handler = proc_doulongvec_minmax,
.extra1 = &init_net.ipv4.frags.low_thresh
},
{
.procname = "ipfrag_low_thresh",
.data = &init_net.ipv4.frags.low_thresh,
- .maxlen = sizeof(int),
+ .maxlen = sizeof(unsigned long),
.mode = 0644,
- .proc_handler = proc_dointvec_minmax,
+ .proc_handler = proc_doulongvec_minmax,
.extra1 = &zero,
.extra2 = &init_net.ipv4.frags.high_thresh
},
diff --git a/net/ipv4/proc.c b/net/ipv4/proc.c
index aacfce0d7d82cf59269a69ef4d6ac8d9955b0bdc..a058de677e947846eb93020e0788148827c8f3cd 100644
--- a/net/ipv4/proc.c
+++ b/net/ipv4/proc.c
@@ -71,7 +71,7 @@ static int sockstat_seq_show(struct seq_file *seq, void *v)
sock_prot_inuse_get(net, &udplite_prot));
seq_printf(seq, "RAW: inuse %d\n",
sock_prot_inuse_get(net, &raw_prot));
- seq_printf(seq, "FRAG: inuse %u memory %u\n",
+ seq_printf(seq, "FRAG: inuse %u memory %lu\n",
atomic_read(&net->ipv4.frags.rhashtable.nelems),
frag_mem_limit(&net->ipv4.frags));
return 0;
diff --git a/net/ipv6/netfilter/nf_conntrack_reasm.c b/net/ipv6/netfilter/nf_conntrack_reasm.c
index d866412b8f6c432f04c0968f08f820fdc561262b..603a395928593a071aff28105578d3bfdbf1b31e 100644
--- a/net/ipv6/netfilter/nf_conntrack_reasm.c
+++ b/net/ipv6/netfilter/nf_conntrack_reasm.c
@@ -63,7 +63,7 @@ struct nf_ct_frag6_skb_cb
static struct inet_frags nf_frags;
#ifdef CONFIG_SYSCTL
-static int zero;
+static long zero;
static struct ctl_table nf_ct_frag6_sysctl_table[] = {
{
@@ -76,18 +76,18 @@ static struct ctl_table nf_ct_frag6_sysctl_table[] = {
{
.procname = "nf_conntrack_frag6_low_thresh",
.data = &init_net.nf_frag.frags.low_thresh,
- .maxlen = sizeof(unsigned int),
+ .maxlen = sizeof(unsigned long),
.mode = 0644,
- .proc_handler = proc_dointvec_minmax,
+ .proc_handler = proc_doulongvec_minmax,
.extra1 = &zero,
.extra2 = &init_net.nf_frag.frags.high_thresh
},
{
.procname = "nf_conntrack_frag6_high_thresh",
.data = &init_net.nf_frag.frags.high_thresh,
- .maxlen = sizeof(unsigned int),
+ .maxlen = sizeof(unsigned long),
.mode = 0644,
- .proc_handler = proc_dointvec_minmax,
+ .proc_handler = proc_doulongvec_minmax,
.extra1 = &init_net.nf_frag.frags.low_thresh
},
{ }
diff --git a/net/ipv6/proc.c b/net/ipv6/proc.c
index 8befeb91e0712ecc4d05c4c0a6ecca1808dcbcac..a85f7e0b14b10f59fdd2ea6901f8e9a95c13654f 100644
--- a/net/ipv6/proc.c
+++ b/net/ipv6/proc.c
@@ -47,7 +47,7 @@ static int sockstat6_seq_show(struct seq_file *seq, void *v)
sock_prot_inuse_get(net, &udplitev6_prot));
seq_printf(seq, "RAW6: inuse %d\n",
sock_prot_inuse_get(net, &rawv6_prot));
- seq_printf(seq, "FRAG6: inuse %u memory %u\n",
+ seq_printf(seq, "FRAG6: inuse %u memory %lu\n",
atomic_read(&net->ipv6.frags.rhashtable.nelems),
frag_mem_limit(&net->ipv6.frags));
return 0;
diff --git a/net/ipv6/reassembly.c b/net/ipv6/reassembly.c
index 2a77fda5e3bca1b6ce8c24df11e741653a15c665..905a8aee2671fd76b47d9cc6b6b0c17c9691d224 100644
--- a/net/ipv6/reassembly.c
+++ b/net/ipv6/reassembly.c
@@ -552,15 +552,15 @@ static struct ctl_table ip6_frags_ns_ctl_table[] = {
{
.procname = "ip6frag_high_thresh",
.data = &init_net.ipv6.frags.high_thresh,
- .maxlen = sizeof(int),
+ .maxlen = sizeof(unsigned long),
.mode = 0644,
- .proc_handler = proc_dointvec_minmax,
+ .proc_handler = proc_doulongvec_minmax,
.extra1 = &init_net.ipv6.frags.low_thresh
},
{
.procname = "ip6frag_low_thresh",
.data = &init_net.ipv6.frags.low_thresh,
- .maxlen = sizeof(int),
+ .maxlen = sizeof(unsigned long),
.mode = 0644,
.proc_handler = proc_dointvec_minmax,
.extra1 = &zero,
--
2.17.0.rc1.321.gba9d0f2565-goog
^ permalink raw reply related
* [PATCH v3 net-next 11/12] inet: frags: remove inet_frag_maybe_warn_overflow()
From: Eric Dumazet @ 2018-03-31 0:53 UTC (permalink / raw)
To: David S . Miller
Cc: netdev, Florian Westphal, Herbert Xu, Thomas Graf,
Jesper Dangaard Brouer, Alexander Aring, Stefan Schmidt,
Kirill Tkhai, Eric Dumazet, Eric Dumazet
In-Reply-To: <20180331005309.179376-1-edumazet@google.com>
This function is obsolete, after rhashtable addition to inet defrag.
Signed-off-by: Eric Dumazet <edumazet@google.com>
---
include/net/inet_frag.h | 2 --
net/ieee802154/6lowpan/reassembly.c | 5 ++---
net/ipv4/inet_fragment.c | 11 -----------
net/ipv4/ip_fragment.c | 5 ++---
net/ipv6/netfilter/nf_conntrack_reasm.c | 5 ++---
net/ipv6/reassembly.c | 5 ++---
6 files changed, 8 insertions(+), 25 deletions(-)
diff --git a/include/net/inet_frag.h b/include/net/inet_frag.h
index 0e8e159d88f7f77254fae5a49f1c7ba07b967e11..95e353e3305b43253084d972e32538138bcc5454 100644
--- a/include/net/inet_frag.h
+++ b/include/net/inet_frag.h
@@ -110,8 +110,6 @@ void inet_frags_exit_net(struct netns_frags *nf);
void inet_frag_kill(struct inet_frag_queue *q);
void inet_frag_destroy(struct inet_frag_queue *q);
struct inet_frag_queue *inet_frag_find(struct netns_frags *nf, void *key);
-void inet_frag_maybe_warn_overflow(struct inet_frag_queue *q,
- const char *prefix);
static inline void inet_frag_put(struct inet_frag_queue *q)
{
diff --git a/net/ieee802154/6lowpan/reassembly.c b/net/ieee802154/6lowpan/reassembly.c
index dd743c287bc229b1ba354e834af7bec34dcb8643..7eaa0617e277b829b801aee4e75f0ec61b2daf41 100644
--- a/net/ieee802154/6lowpan/reassembly.c
+++ b/net/ieee802154/6lowpan/reassembly.c
@@ -84,10 +84,9 @@ fq_find(struct net *net, const struct lowpan_802154_cb *cb,
struct inet_frag_queue *q;
q = inet_frag_find(&ieee802154_lowpan->frags, &key);
- if (IS_ERR_OR_NULL(q)) {
- inet_frag_maybe_warn_overflow(q, pr_fmt());
+ if (!q)
return NULL;
- }
+
return container_of(q, struct lowpan_frag_queue, q);
}
diff --git a/net/ipv4/inet_fragment.c b/net/ipv4/inet_fragment.c
index ebb8f411e0db16478e861105b1926e97fbf07b06..c9e35b81d0931df8429a33e8d03e719b87da0747 100644
--- a/net/ipv4/inet_fragment.c
+++ b/net/ipv4/inet_fragment.c
@@ -218,14 +218,3 @@ struct inet_frag_queue *inet_frag_find(struct netns_frags *nf, void *key)
return inet_frag_create(nf, key);
}
EXPORT_SYMBOL(inet_frag_find);
-
-void inet_frag_maybe_warn_overflow(struct inet_frag_queue *q,
- const char *prefix)
-{
- static const char msg[] = "inet_frag_find: Fragment hash bucket"
- " list length grew over limit. Dropping fragment.\n";
-
- if (PTR_ERR(q) == -ENOBUFS)
- net_dbg_ratelimited("%s%s", prefix, msg);
-}
-EXPORT_SYMBOL(inet_frag_maybe_warn_overflow);
diff --git a/net/ipv4/ip_fragment.c b/net/ipv4/ip_fragment.c
index b844f517b75bd6a52538e9f7687e039e22c93bc7..b0366224f314ae521d8c1f8fe04c53e419292b4c 100644
--- a/net/ipv4/ip_fragment.c
+++ b/net/ipv4/ip_fragment.c
@@ -221,10 +221,9 @@ static struct ipq *ip_find(struct net *net, struct iphdr *iph,
struct inet_frag_queue *q;
q = inet_frag_find(&net->ipv4.frags, &key);
- if (IS_ERR_OR_NULL(q)) {
- inet_frag_maybe_warn_overflow(q, pr_fmt());
+ if (!q)
return NULL;
- }
+
return container_of(q, struct ipq, q);
}
diff --git a/net/ipv6/netfilter/nf_conntrack_reasm.c b/net/ipv6/netfilter/nf_conntrack_reasm.c
index 0ad3df551d9884ba30f2d40658ee81a61720e947..d866412b8f6c432f04c0968f08f820fdc561262b 100644
--- a/net/ipv6/netfilter/nf_conntrack_reasm.c
+++ b/net/ipv6/netfilter/nf_conntrack_reasm.c
@@ -178,10 +178,9 @@ static struct frag_queue *fq_find(struct net *net, __be32 id, u32 user,
struct inet_frag_queue *q;
q = inet_frag_find(&net->nf_frag.frags, &key);
- if (IS_ERR_OR_NULL(q)) {
- inet_frag_maybe_warn_overflow(q, pr_fmt());
+ if (!q)
return NULL;
- }
+
return container_of(q, struct frag_queue, q);
}
diff --git a/net/ipv6/reassembly.c b/net/ipv6/reassembly.c
index 70acad126d044a0f6a1efc63f307805fcf7b1df9..2a77fda5e3bca1b6ce8c24df11e741653a15c665 100644
--- a/net/ipv6/reassembly.c
+++ b/net/ipv6/reassembly.c
@@ -155,10 +155,9 @@ fq_find(struct net *net, __be32 id, const struct ipv6hdr *hdr, int iif)
key.iif = 0;
q = inet_frag_find(&net->ipv6.frags, &key);
- if (IS_ERR_OR_NULL(q)) {
- inet_frag_maybe_warn_overflow(q, pr_fmt());
+ if (!q)
return NULL;
- }
+
return container_of(q, struct frag_queue, q);
}
--
2.17.0.rc1.321.gba9d0f2565-goog
^ permalink raw reply related
* [PATCH v3 net-next 10/12] inet: frags: get rif of inet_frag_evicting()
From: Eric Dumazet @ 2018-03-31 0:53 UTC (permalink / raw)
To: David S . Miller
Cc: netdev, Florian Westphal, Herbert Xu, Thomas Graf,
Jesper Dangaard Brouer, Alexander Aring, Stefan Schmidt,
Kirill Tkhai, Eric Dumazet, Eric Dumazet
In-Reply-To: <20180331005309.179376-1-edumazet@google.com>
This refactors ip_expire() since one indentation level is removed.
Note: in the future, we should try hard to avoid the skb_clone()
since this is a serious performance cost.
Under DDOS, the ICMP message wont be sent because of rate limits.
Fact that ip6_expire_frag_queue() does not use skb_clone() is
disturbing too. Presumably IPv6 should have the same
issue than the one we fixed in commit ec4fbd64751d
("inet: frag: release spinlock before calling icmp_send()")
Signed-off-by: Eric Dumazet <edumazet@google.com>
---
include/net/inet_frag.h | 5 ----
net/ipv4/ip_fragment.c | 61 ++++++++++++++++++++---------------------
net/ipv6/reassembly.c | 4 ---
3 files changed, 30 insertions(+), 40 deletions(-)
diff --git a/include/net/inet_frag.h b/include/net/inet_frag.h
index 4b5449df0aadf1f75144c98317bf5305ec91d88b..0e8e159d88f7f77254fae5a49f1c7ba07b967e11 100644
--- a/include/net/inet_frag.h
+++ b/include/net/inet_frag.h
@@ -119,11 +119,6 @@ static inline void inet_frag_put(struct inet_frag_queue *q)
inet_frag_destroy(q);
}
-static inline bool inet_frag_evicting(struct inet_frag_queue *q)
-{
- return false;
-}
-
/* Memory Tracking Functions. */
static inline int frag_mem_limit(struct netns_frags *nf)
diff --git a/net/ipv4/ip_fragment.c b/net/ipv4/ip_fragment.c
index 44f4fa306e224a6f76183b1c04935f01ceb4fe2b..b844f517b75bd6a52538e9f7687e039e22c93bc7 100644
--- a/net/ipv4/ip_fragment.c
+++ b/net/ipv4/ip_fragment.c
@@ -143,8 +143,11 @@ static bool frag_expire_skip_icmp(u32 user)
static void ip_expire(struct timer_list *t)
{
struct inet_frag_queue *frag = from_timer(frag, t, timer);
- struct ipq *qp;
+ struct sk_buff *clone, *head;
+ const struct iphdr *iph;
struct net *net;
+ struct ipq *qp;
+ int err;
qp = container_of(frag, struct ipq, q);
net = container_of(qp->q.net, struct net, ipv4.frags);
@@ -158,45 +161,41 @@ static void ip_expire(struct timer_list *t)
ipq_kill(qp);
__IP_INC_STATS(net, IPSTATS_MIB_REASMFAILS);
- if (!inet_frag_evicting(&qp->q)) {
- struct sk_buff *clone, *head = qp->q.fragments;
- const struct iphdr *iph;
- int err;
+ head = qp->q.fragments;
- __IP_INC_STATS(net, IPSTATS_MIB_REASMTIMEOUT);
+ __IP_INC_STATS(net, IPSTATS_MIB_REASMTIMEOUT);
- if (!(qp->q.flags & INET_FRAG_FIRST_IN) || !qp->q.fragments)
- goto out;
+ if (!(qp->q.flags & INET_FRAG_FIRST_IN) || !head)
+ goto out;
- head->dev = dev_get_by_index_rcu(net, qp->iif);
- if (!head->dev)
- goto out;
+ head->dev = dev_get_by_index_rcu(net, qp->iif);
+ if (!head->dev)
+ goto out;
- /* skb has no dst, perform route lookup again */
- iph = ip_hdr(head);
- err = ip_route_input_noref(head, iph->daddr, iph->saddr,
+ /* skb has no dst, perform route lookup again */
+ iph = ip_hdr(head);
+ err = ip_route_input_noref(head, iph->daddr, iph->saddr,
iph->tos, head->dev);
- if (err)
- goto out;
+ if (err)
+ goto out;
- /* Only an end host needs to send an ICMP
- * "Fragment Reassembly Timeout" message, per RFC792.
- */
- if (frag_expire_skip_icmp(qp->q.key.v4.user) &&
- (skb_rtable(head)->rt_type != RTN_LOCAL))
- goto out;
+ /* Only an end host needs to send an ICMP
+ * "Fragment Reassembly Timeout" message, per RFC792.
+ */
+ if (frag_expire_skip_icmp(qp->q.key.v4.user) &&
+ (skb_rtable(head)->rt_type != RTN_LOCAL))
+ goto out;
- clone = skb_clone(head, GFP_ATOMIC);
+ clone = skb_clone(head, GFP_ATOMIC);
- /* Send an ICMP "Fragment Reassembly Timeout" message. */
- if (clone) {
- spin_unlock(&qp->q.lock);
- icmp_send(clone, ICMP_TIME_EXCEEDED,
- ICMP_EXC_FRAGTIME, 0);
- consume_skb(clone);
- goto out_rcu_unlock;
- }
+ /* Send an ICMP "Fragment Reassembly Timeout" message. */
+ if (clone) {
+ spin_unlock(&qp->q.lock);
+ icmp_send(clone, ICMP_TIME_EXCEEDED,
+ ICMP_EXC_FRAGTIME, 0);
+ consume_skb(clone);
+ goto out_rcu_unlock;
}
out:
spin_unlock(&qp->q.lock);
diff --git a/net/ipv6/reassembly.c b/net/ipv6/reassembly.c
index 3fc853e4492abb109062d662296c0b470763042a..70acad126d044a0f6a1efc63f307805fcf7b1df9 100644
--- a/net/ipv6/reassembly.c
+++ b/net/ipv6/reassembly.c
@@ -106,10 +106,6 @@ void ip6_expire_frag_queue(struct net *net, struct frag_queue *fq)
goto out_rcu_unlock;
__IP6_INC_STATS(net, __in6_dev_get(dev), IPSTATS_MIB_REASMFAILS);
-
- if (inet_frag_evicting(&fq->q))
- goto out_rcu_unlock;
-
__IP6_INC_STATS(net, __in6_dev_get(dev), IPSTATS_MIB_REASMTIMEOUT);
/* Don't send error if the first segment did not arrive. */
--
2.17.0.rc1.321.gba9d0f2565-goog
^ permalink raw reply related
* [PATCH v3 net-next 09/12] inet: frags: remove some helpers
From: Eric Dumazet @ 2018-03-31 0:53 UTC (permalink / raw)
To: David S . Miller
Cc: netdev, Florian Westphal, Herbert Xu, Thomas Graf,
Jesper Dangaard Brouer, Alexander Aring, Stefan Schmidt,
Kirill Tkhai, Eric Dumazet, Eric Dumazet
In-Reply-To: <20180331005309.179376-1-edumazet@google.com>
Remove sum_frag_mem_limit(), ip_frag_mem() & ip6_frag_mem()
Also since we use rhashtable we can bring back the number of fragments
in "grep FRAG /proc/net/sockstat /proc/net/sockstat6" that was
removed in commit 434d305405ab ("inet: frag: don't account number
of fragment queues")
Signed-off-by: Eric Dumazet <edumazet@google.com>
---
include/net/inet_frag.h | 5 -----
include/net/ip.h | 1 -
include/net/ipv6.h | 7 -------
net/ipv4/ip_fragment.c | 5 -----
net/ipv4/proc.c | 6 +++---
net/ipv6/proc.c | 5 +++--
6 files changed, 6 insertions(+), 23 deletions(-)
diff --git a/include/net/inet_frag.h b/include/net/inet_frag.h
index 3fec0d3a0d0186e98afb951784e1fe7329ba6d77..4b5449df0aadf1f75144c98317bf5305ec91d88b 100644
--- a/include/net/inet_frag.h
+++ b/include/net/inet_frag.h
@@ -141,11 +141,6 @@ static inline void add_frag_mem_limit(struct netns_frags *nf, int i)
atomic_add(i, &nf->mem);
}
-static inline int sum_frag_mem_limit(struct netns_frags *nf)
-{
- return atomic_read(&nf->mem);
-}
-
/* RFC 3168 support :
* We want to check ECN values of all fragments, do detect invalid combinations.
* In ipq->ecn, we store the OR value of each ip4_frag_ecn() fragment value.
diff --git a/include/net/ip.h b/include/net/ip.h
index 36f8f7811093c37de06194dc7410b7596f8bf9fa..ecffd843e7b896a83416847fdaa452be6223f3dc 100644
--- a/include/net/ip.h
+++ b/include/net/ip.h
@@ -588,7 +588,6 @@ static inline struct sk_buff *ip_check_defrag(struct net *net, struct sk_buff *s
return skb;
}
#endif
-int ip_frag_mem(struct net *net);
/*
* Functions provided by ip_forward.c
diff --git a/include/net/ipv6.h b/include/net/ipv6.h
index 6fa9a2bc589665dfa9ce84813f33e5e86e12fd74..37455e84034779fab96c231fa069957a6dcf2b42 100644
--- a/include/net/ipv6.h
+++ b/include/net/ipv6.h
@@ -379,13 +379,6 @@ static inline bool ipv6_accept_ra(struct inet6_dev *idev)
idev->cnf.accept_ra;
}
-#if IS_ENABLED(CONFIG_IPV6)
-static inline int ip6_frag_mem(struct net *net)
-{
- return sum_frag_mem_limit(&net->ipv6.frags);
-}
-#endif
-
#define IPV6_FRAG_HIGH_THRESH (4 * 1024*1024) /* 4194304 */
#define IPV6_FRAG_LOW_THRESH (3 * 1024*1024) /* 3145728 */
#define IPV6_FRAG_TIMEOUT (60 * HZ) /* 60 seconds */
diff --git a/net/ipv4/ip_fragment.c b/net/ipv4/ip_fragment.c
index 4021820db6f291b255cc53aeca91dd74aef29934..44f4fa306e224a6f76183b1c04935f01ceb4fe2b 100644
--- a/net/ipv4/ip_fragment.c
+++ b/net/ipv4/ip_fragment.c
@@ -83,11 +83,6 @@ static u8 ip4_frag_ecn(u8 tos)
static struct inet_frags ip4_frags;
-int ip_frag_mem(struct net *net)
-{
- return sum_frag_mem_limit(&net->ipv4.frags);
-}
-
static int ip_frag_reasm(struct ipq *qp, struct sk_buff *prev,
struct net_device *dev);
diff --git a/net/ipv4/proc.c b/net/ipv4/proc.c
index adfb75340275d240487574257c10feb295df44fe..aacfce0d7d82cf59269a69ef4d6ac8d9955b0bdc 100644
--- a/net/ipv4/proc.c
+++ b/net/ipv4/proc.c
@@ -54,7 +54,6 @@
static int sockstat_seq_show(struct seq_file *seq, void *v)
{
struct net *net = seq->private;
- unsigned int frag_mem;
int orphans, sockets;
orphans = percpu_counter_sum_positive(&tcp_orphan_count);
@@ -72,8 +71,9 @@ static int sockstat_seq_show(struct seq_file *seq, void *v)
sock_prot_inuse_get(net, &udplite_prot));
seq_printf(seq, "RAW: inuse %d\n",
sock_prot_inuse_get(net, &raw_prot));
- frag_mem = ip_frag_mem(net);
- seq_printf(seq, "FRAG: inuse %u memory %u\n", !!frag_mem, frag_mem);
+ seq_printf(seq, "FRAG: inuse %u memory %u\n",
+ atomic_read(&net->ipv4.frags.rhashtable.nelems),
+ frag_mem_limit(&net->ipv4.frags));
return 0;
}
diff --git a/net/ipv6/proc.c b/net/ipv6/proc.c
index 6e57028d2e9160be264d07f9312658fcb677a568..8befeb91e0712ecc4d05c4c0a6ecca1808dcbcac 100644
--- a/net/ipv6/proc.c
+++ b/net/ipv6/proc.c
@@ -38,7 +38,6 @@
static int sockstat6_seq_show(struct seq_file *seq, void *v)
{
struct net *net = seq->private;
- unsigned int frag_mem = ip6_frag_mem(net);
seq_printf(seq, "TCP6: inuse %d\n",
sock_prot_inuse_get(net, &tcpv6_prot));
@@ -48,7 +47,9 @@ static int sockstat6_seq_show(struct seq_file *seq, void *v)
sock_prot_inuse_get(net, &udplitev6_prot));
seq_printf(seq, "RAW6: inuse %d\n",
sock_prot_inuse_get(net, &rawv6_prot));
- seq_printf(seq, "FRAG6: inuse %u memory %u\n", !!frag_mem, frag_mem);
+ seq_printf(seq, "FRAG6: inuse %u memory %u\n",
+ atomic_read(&net->ipv6.frags.rhashtable.nelems),
+ frag_mem_limit(&net->ipv6.frags));
return 0;
}
--
2.17.0.rc1.321.gba9d0f2565-goog
^ permalink raw reply related
* [PATCH v3 net-next 08/12] inet: frags: use rhashtables for reassembly units
From: Eric Dumazet @ 2018-03-31 0:53 UTC (permalink / raw)
To: David S . Miller
Cc: netdev, Florian Westphal, Herbert Xu, Thomas Graf,
Jesper Dangaard Brouer, Alexander Aring, Stefan Schmidt,
Kirill Tkhai, Eric Dumazet, Eric Dumazet
In-Reply-To: <20180331005309.179376-1-edumazet@google.com>
Some applications still rely on IP fragmentation, and to be fair linux
reassembly unit is not working under any serious load.
It uses static hash tables of 1024 buckets, and up to 128 items per bucket (!!!)
A work queue is supposed to garbage collect items when host is under memory
pressure, and doing a hash rebuild, changing seed used in hash computations.
This work queue blocks softirqs for up to 25 ms when doing a hash rebuild,
occurring every 5 seconds if host is under fire.
Then there is the problem of sharing this hash table for all netns.
It is time to switch to rhashtables, and allocate one of them per netns
to speedup netns dismantle, since this is a critical metric these days.
Lookup is now using RCU. A followup patch will even remove
the refcount hold/release left from prior implementation and save
a couple of atomic operations.
Before this patch, 16 cpus (16 RX queue NIC) could not handle more
than 1 Mpps frags DDOS.
After the patch, I reach 9 Mpps without any tuning, and can use up to 2GB
of storage for the fragments (exact number depends on frags being evicted
after timeout)
$ grep FRAG /proc/net/sockstat
FRAG: inuse 1966916 memory 2140004608
A followup patch will change the limits for 64bit arches.
Signed-off-by: Eric Dumazet <edumazet@google.com>
Cc: Kirill Tkhai <ktkhai@virtuozzo.com>
Cc: Herbert Xu <herbert@gondor.apana.org.au>
Cc: Florian Westphal <fw@strlen.de>
Cc: Jesper Dangaard Brouer <brouer@redhat.com>
Cc: Alexander Aring <alex.aring@gmail.com>
Cc: Stefan Schmidt <stefan@osg.samsung.com>
---
Documentation/networking/ip-sysctl.txt | 7 +-
include/net/inet_frag.h | 81 +++---
include/net/ipv6.h | 16 +-
net/ieee802154/6lowpan/6lowpan_i.h | 26 +-
net/ieee802154/6lowpan/reassembly.c | 93 +++----
net/ipv4/inet_fragment.c | 354 +++++-------------------
net/ipv4/ip_fragment.c | 112 ++++----
net/ipv6/netfilter/nf_conntrack_reasm.c | 51 +---
net/ipv6/reassembly.c | 110 ++++----
9 files changed, 271 insertions(+), 579 deletions(-)
diff --git a/Documentation/networking/ip-sysctl.txt b/Documentation/networking/ip-sysctl.txt
index 33f35f049ad57ad6c06ed6e089966e346d72d108..6f2a3670e44b6662ce53c16cb7ca1e4f61274c15 100644
--- a/Documentation/networking/ip-sysctl.txt
+++ b/Documentation/networking/ip-sysctl.txt
@@ -134,13 +134,10 @@ min_adv_mss - INTEGER
IP Fragmentation:
ipfrag_high_thresh - INTEGER
- Maximum memory used to reassemble IP fragments. When
- ipfrag_high_thresh bytes of memory is allocated for this purpose,
- the fragment handler will toss packets until ipfrag_low_thresh
- is reached. This also serves as a maximum limit to namespaces
- different from the initial one.
+ Maximum memory used to reassemble IP fragments.
ipfrag_low_thresh - INTEGER
+ (Obsolete since linux-4.17)
Maximum memory used to reassemble IP fragments before the kernel
begins to remove incomplete fragment queues to free up resources.
The kernel still accepts new fragments for defragmentation.
diff --git a/include/net/inet_frag.h b/include/net/inet_frag.h
index 69e531ed81894393e07cac9e953825fcb55ef42a..3fec0d3a0d0186e98afb951784e1fe7329ba6d77 100644
--- a/include/net/inet_frag.h
+++ b/include/net/inet_frag.h
@@ -2,7 +2,11 @@
#ifndef __NET_FRAG_H__
#define __NET_FRAG_H__
+#include <linux/rhashtable.h>
+
struct netns_frags {
+ struct rhashtable rhashtable ____cacheline_aligned_in_smp;
+
/* Keep atomic mem on separate cachelines in structs that include it */
atomic_t mem ____cacheline_aligned_in_smp;
/* sysctls */
@@ -26,12 +30,30 @@ enum {
INET_FRAG_COMPLETE = BIT(2),
};
+struct frag_v4_compare_key {
+ __be32 saddr;
+ __be32 daddr;
+ u32 user;
+ u32 vif;
+ __be16 id;
+ u16 protocol;
+};
+
+struct frag_v6_compare_key {
+ struct in6_addr saddr;
+ struct in6_addr daddr;
+ u32 user;
+ __be32 id;
+ u32 iif;
+};
+
/**
* struct inet_frag_queue - fragment queue
*
- * @lock: spinlock protecting the queue
+ * @node: rhash node
+ * @key: keys identifying this frag.
* @timer: queue expiration timer
- * @list: hash bucket list
+ * @lock: spinlock protecting this frag
* @refcnt: reference count of the queue
* @fragments: received fragments head
* @fragments_tail: received fragments tail
@@ -41,12 +63,16 @@ enum {
* @flags: fragment queue flags
* @max_size: maximum received fragment size
* @net: namespace that this frag belongs to
- * @list_evictor: list of queues to forcefully evict (e.g. due to low memory)
+ * @rcu: rcu head for freeing deferall
*/
struct inet_frag_queue {
- spinlock_t lock;
+ struct rhash_head node;
+ union {
+ struct frag_v4_compare_key v4;
+ struct frag_v6_compare_key v6;
+ } key;
struct timer_list timer;
- struct hlist_node list;
+ spinlock_t lock;
refcount_t refcnt;
struct sk_buff *fragments;
struct sk_buff *fragments_tail;
@@ -55,51 +81,20 @@ struct inet_frag_queue {
int meat;
__u8 flags;
u16 max_size;
- struct netns_frags *net;
- struct hlist_node list_evictor;
-};
-
-#define INETFRAGS_HASHSZ 1024
-
-/* averaged:
- * max_depth = default ipfrag_high_thresh / INETFRAGS_HASHSZ /
- * rounded up (SKB_TRUELEN(0) + sizeof(struct ipq or
- * struct frag_queue))
- */
-#define INETFRAGS_MAXDEPTH 128
-
-struct inet_frag_bucket {
- struct hlist_head chain;
- spinlock_t chain_lock;
+ struct netns_frags *net;
+ struct rcu_head rcu;
};
struct inet_frags {
- struct inet_frag_bucket hash[INETFRAGS_HASHSZ];
-
- struct work_struct frags_work;
- unsigned int next_bucket;
- unsigned long last_rebuild_jiffies;
- bool rebuild;
-
- /* The first call to hashfn is responsible to initialize
- * rnd. This is best done with net_get_random_once.
- *
- * rnd_seqlock is used to let hash insertion detect
- * when it needs to re-lookup the hash chain to use.
- */
- u32 rnd;
- seqlock_t rnd_seqlock;
unsigned int qsize;
- unsigned int (*hashfn)(const struct inet_frag_queue *);
- bool (*match)(const struct inet_frag_queue *q,
- const void *arg);
void (*constructor)(struct inet_frag_queue *q,
const void *arg);
void (*destructor)(struct inet_frag_queue *);
void (*frag_expire)(struct timer_list *t);
struct kmem_cache *frags_cachep;
const char *frags_cache_name;
+ struct rhashtable_params rhash_params;
};
int inet_frags_init(struct inet_frags *);
@@ -108,15 +103,13 @@ void inet_frags_fini(struct inet_frags *);
static inline int inet_frags_init_net(struct netns_frags *nf)
{
atomic_set(&nf->mem, 0);
- return 0;
+ return rhashtable_init(&nf->rhashtable, &nf->f->rhash_params);
}
void inet_frags_exit_net(struct netns_frags *nf);
void inet_frag_kill(struct inet_frag_queue *q);
void inet_frag_destroy(struct inet_frag_queue *q);
-struct inet_frag_queue *inet_frag_find(struct netns_frags *nf,
- struct inet_frags *f, void *key, unsigned int hash);
-
+struct inet_frag_queue *inet_frag_find(struct netns_frags *nf, void *key);
void inet_frag_maybe_warn_overflow(struct inet_frag_queue *q,
const char *prefix);
@@ -128,7 +121,7 @@ static inline void inet_frag_put(struct inet_frag_queue *q)
static inline bool inet_frag_evicting(struct inet_frag_queue *q)
{
- return !hlist_unhashed(&q->list_evictor);
+ return false;
}
/* Memory Tracking Functions. */
diff --git a/include/net/ipv6.h b/include/net/ipv6.h
index 57b7fe43d2ab8e0ef3d663b7a5ee201affd5ca1f..6fa9a2bc589665dfa9ce84813f33e5e86e12fd74 100644
--- a/include/net/ipv6.h
+++ b/include/net/ipv6.h
@@ -579,17 +579,8 @@ enum ip6_defrag_users {
__IP6_DEFRAG_CONNTRACK_BRIDGE_IN = IP6_DEFRAG_CONNTRACK_BRIDGE_IN + USHRT_MAX,
};
-struct ip6_create_arg {
- __be32 id;
- u32 user;
- const struct in6_addr *src;
- const struct in6_addr *dst;
- int iif;
- u8 ecn;
-};
-
void ip6_frag_init(struct inet_frag_queue *q, const void *a);
-bool ip6_frag_match(const struct inet_frag_queue *q, const void *a);
+extern const struct rhashtable_params ip6_rhash_params;
/*
* Equivalent of ipv4 struct ip
@@ -597,11 +588,6 @@ bool ip6_frag_match(const struct inet_frag_queue *q, const void *a);
struct frag_queue {
struct inet_frag_queue q;
- __be32 id; /* fragment id */
- u32 user;
- struct in6_addr saddr;
- struct in6_addr daddr;
-
int iif;
__u16 nhoffset;
u8 ecn;
diff --git a/net/ieee802154/6lowpan/6lowpan_i.h b/net/ieee802154/6lowpan/6lowpan_i.h
index d8de3bcfb1032a1133402cb2a4c50a2448133846..b8d95cb71c25dd69c8a88b2c886a3f0d2ce1174f 100644
--- a/net/ieee802154/6lowpan/6lowpan_i.h
+++ b/net/ieee802154/6lowpan/6lowpan_i.h
@@ -17,37 +17,19 @@ typedef unsigned __bitwise lowpan_rx_result;
#define LOWPAN_DISPATCH_FRAG1 0xc0
#define LOWPAN_DISPATCH_FRAGN 0xe0
-struct lowpan_create_arg {
+struct frag_lowpan_compare_key {
u16 tag;
u16 d_size;
- const struct ieee802154_addr *src;
- const struct ieee802154_addr *dst;
+ const struct ieee802154_addr src;
+ const struct ieee802154_addr dst;
};
-/* Equivalent of ipv4 struct ip
+/* Equivalent of ipv4 struct ipq
*/
struct lowpan_frag_queue {
struct inet_frag_queue q;
-
- u16 tag;
- u16 d_size;
- struct ieee802154_addr saddr;
- struct ieee802154_addr daddr;
};
-static inline u32 ieee802154_addr_hash(const struct ieee802154_addr *a)
-{
- switch (a->mode) {
- case IEEE802154_ADDR_LONG:
- return (((__force u64)a->extended_addr) >> 32) ^
- (((__force u64)a->extended_addr) & 0xffffffff);
- case IEEE802154_ADDR_SHORT:
- return (__force u32)(a->short_addr + (a->pan_id << 16));
- default:
- return 0;
- }
-}
-
int lowpan_frag_rcv(struct sk_buff *skb, const u8 frag_type);
void lowpan_net_frag_exit(void);
int lowpan_net_frag_init(void);
diff --git a/net/ieee802154/6lowpan/reassembly.c b/net/ieee802154/6lowpan/reassembly.c
index ddada12a044de293f904a1dc7a5ff398d089d101..dd743c287bc229b1ba354e834af7bec34dcb8643 100644
--- a/net/ieee802154/6lowpan/reassembly.c
+++ b/net/ieee802154/6lowpan/reassembly.c
@@ -37,47 +37,15 @@ static struct inet_frags lowpan_frags;
static int lowpan_frag_reasm(struct lowpan_frag_queue *fq,
struct sk_buff *prev, struct net_device *ldev);
-static unsigned int lowpan_hash_frag(u16 tag, u16 d_size,
- const struct ieee802154_addr *saddr,
- const struct ieee802154_addr *daddr)
-{
- net_get_random_once(&lowpan_frags.rnd, sizeof(lowpan_frags.rnd));
- return jhash_3words(ieee802154_addr_hash(saddr),
- ieee802154_addr_hash(daddr),
- (__force u32)(tag + (d_size << 16)),
- lowpan_frags.rnd);
-}
-
-static unsigned int lowpan_hashfn(const struct inet_frag_queue *q)
-{
- const struct lowpan_frag_queue *fq;
-
- fq = container_of(q, struct lowpan_frag_queue, q);
- return lowpan_hash_frag(fq->tag, fq->d_size, &fq->saddr, &fq->daddr);
-}
-
-static bool lowpan_frag_match(const struct inet_frag_queue *q, const void *a)
-{
- const struct lowpan_frag_queue *fq;
- const struct lowpan_create_arg *arg = a;
-
- fq = container_of(q, struct lowpan_frag_queue, q);
- return fq->tag == arg->tag && fq->d_size == arg->d_size &&
- ieee802154_addr_equal(&fq->saddr, arg->src) &&
- ieee802154_addr_equal(&fq->daddr, arg->dst);
-}
-
static void lowpan_frag_init(struct inet_frag_queue *q, const void *a)
{
- const struct lowpan_create_arg *arg = a;
+ const struct frag_lowpan_compare_key *key = a;
struct lowpan_frag_queue *fq;
fq = container_of(q, struct lowpan_frag_queue, q);
- fq->tag = arg->tag;
- fq->d_size = arg->d_size;
- fq->saddr = *arg->src;
- fq->daddr = *arg->dst;
+ BUILD_BUG_ON(sizeof(*key) > sizeof(q->key));
+ memcpy(&q->key, key, sizeof(*key));
}
static void lowpan_frag_expire(struct timer_list *t)
@@ -105,21 +73,17 @@ fq_find(struct net *net, const struct lowpan_802154_cb *cb,
const struct ieee802154_addr *src,
const struct ieee802154_addr *dst)
{
+ struct netns_ieee802154_lowpan *ieee802154_lowpan =
+ net_ieee802154_lowpan(net);
+ struct frag_lowpan_compare_key key = {
+ .tag = cb->d_tag,
+ .d_size = cb->d_size,
+ .src = *src,
+ .dst = *dst,
+ };
struct inet_frag_queue *q;
- struct lowpan_create_arg arg;
- unsigned int hash;
- struct netns_ieee802154_lowpan *ieee802154_lowpan =
- net_ieee802154_lowpan(net);
- arg.tag = cb->d_tag;
- arg.d_size = cb->d_size;
- arg.src = src;
- arg.dst = dst;
-
- hash = lowpan_hash_frag(cb->d_tag, cb->d_size, src, dst);
-
- q = inet_frag_find(&ieee802154_lowpan->frags,
- &lowpan_frags, &arg, hash);
+ q = inet_frag_find(&ieee802154_lowpan->frags, &key);
if (IS_ERR_OR_NULL(q)) {
inet_frag_maybe_warn_overflow(q, pr_fmt());
return NULL;
@@ -611,17 +575,46 @@ static struct pernet_operations lowpan_frags_ops = {
.exit = lowpan_frags_exit_net,
};
+static u32 lowpan_key_hashfn(const void *data, u32 len, u32 seed)
+{
+ return jhash2(data,
+ sizeof(struct frag_lowpan_compare_key) / sizeof(u32), seed);
+}
+
+static u32 lowpan_obj_hashfn(const void *data, u32 len, u32 seed)
+{
+ const struct inet_frag_queue *fq = data;
+
+ return jhash2((const u32 *)&fq->key,
+ sizeof(struct frag_lowpan_compare_key) / sizeof(u32), seed);
+}
+
+static int lowpan_obj_cmpfn(struct rhashtable_compare_arg *arg, const void *ptr)
+{
+ const struct frag_lowpan_compare_key *key = arg->key;
+ const struct inet_frag_queue *fq = ptr;
+
+ return !!memcmp(&fq->key, key, sizeof(*key));
+}
+
+const struct rhashtable_params lowpan_rhash_params = {
+ .head_offset = offsetof(struct inet_frag_queue, node),
+ .hashfn = lowpan_key_hashfn,
+ .obj_hashfn = lowpan_obj_hashfn,
+ .obj_cmpfn = lowpan_obj_cmpfn,
+ .automatic_shrinking = true,
+};
+
int __init lowpan_net_frag_init(void)
{
int ret;
- lowpan_frags.hashfn = lowpan_hashfn;
lowpan_frags.constructor = lowpan_frag_init;
lowpan_frags.destructor = NULL;
lowpan_frags.qsize = sizeof(struct frag_queue);
- lowpan_frags.match = lowpan_frag_match;
lowpan_frags.frag_expire = lowpan_frag_expire;
lowpan_frags.frags_cache_name = lowpan_frags_cache_name;
+ lowpan_frags.rhash_params = lowpan_rhash_params;
ret = inet_frags_init(&lowpan_frags);
if (ret)
goto out;
diff --git a/net/ipv4/inet_fragment.c b/net/ipv4/inet_fragment.c
index 1ac69f65d0dee600d0ab4db20ff5942952932c40..ebb8f411e0db16478e861105b1926e97fbf07b06 100644
--- a/net/ipv4/inet_fragment.c
+++ b/net/ipv4/inet_fragment.c
@@ -25,12 +25,6 @@
#include <net/inet_frag.h>
#include <net/inet_ecn.h>
-#define INETFRAGS_EVICT_BUCKETS 128
-#define INETFRAGS_EVICT_MAX 512
-
-/* don't rebuild inetfrag table with new secret more often than this */
-#define INETFRAGS_MIN_REBUILD_INTERVAL (5 * HZ)
-
/* Given the OR values of all fragments, apply RFC 3168 5.3 requirements
* Value : 0xff if frame should be dropped.
* 0 or INET_ECN_CE value, to be ORed in to final iph->tos field
@@ -52,157 +46,8 @@ const u8 ip_frag_ecn_table[16] = {
};
EXPORT_SYMBOL(ip_frag_ecn_table);
-static unsigned int
-inet_frag_hashfn(const struct inet_frags *f, const struct inet_frag_queue *q)
-{
- return f->hashfn(q) & (INETFRAGS_HASHSZ - 1);
-}
-
-static bool inet_frag_may_rebuild(struct inet_frags *f)
-{
- return time_after(jiffies,
- f->last_rebuild_jiffies + INETFRAGS_MIN_REBUILD_INTERVAL);
-}
-
-static void inet_frag_secret_rebuild(struct inet_frags *f)
-{
- int i;
-
- write_seqlock_bh(&f->rnd_seqlock);
-
- if (!inet_frag_may_rebuild(f))
- goto out;
-
- get_random_bytes(&f->rnd, sizeof(u32));
-
- for (i = 0; i < INETFRAGS_HASHSZ; i++) {
- struct inet_frag_bucket *hb;
- struct inet_frag_queue *q;
- struct hlist_node *n;
-
- hb = &f->hash[i];
- spin_lock(&hb->chain_lock);
-
- hlist_for_each_entry_safe(q, n, &hb->chain, list) {
- unsigned int hval = inet_frag_hashfn(f, q);
-
- if (hval != i) {
- struct inet_frag_bucket *hb_dest;
-
- hlist_del(&q->list);
-
- /* Relink to new hash chain. */
- hb_dest = &f->hash[hval];
-
- /* This is the only place where we take
- * another chain_lock while already holding
- * one. As this will not run concurrently,
- * we cannot deadlock on hb_dest lock below, if its
- * already locked it will be released soon since
- * other caller cannot be waiting for hb lock
- * that we've taken above.
- */
- spin_lock_nested(&hb_dest->chain_lock,
- SINGLE_DEPTH_NESTING);
- hlist_add_head(&q->list, &hb_dest->chain);
- spin_unlock(&hb_dest->chain_lock);
- }
- }
- spin_unlock(&hb->chain_lock);
- }
-
- f->rebuild = false;
- f->last_rebuild_jiffies = jiffies;
-out:
- write_sequnlock_bh(&f->rnd_seqlock);
-}
-
-static bool inet_fragq_should_evict(const struct inet_frag_queue *q)
-{
- if (!hlist_unhashed(&q->list_evictor))
- return false;
-
- return q->net->low_thresh == 0 ||
- frag_mem_limit(q->net) >= q->net->low_thresh;
-}
-
-static unsigned int
-inet_evict_bucket(struct inet_frags *f, struct inet_frag_bucket *hb)
-{
- struct inet_frag_queue *fq;
- struct hlist_node *n;
- unsigned int evicted = 0;
- HLIST_HEAD(expired);
-
- spin_lock(&hb->chain_lock);
-
- hlist_for_each_entry_safe(fq, n, &hb->chain, list) {
- if (!inet_fragq_should_evict(fq))
- continue;
-
- if (!del_timer(&fq->timer))
- continue;
-
- hlist_add_head(&fq->list_evictor, &expired);
- ++evicted;
- }
-
- spin_unlock(&hb->chain_lock);
-
- hlist_for_each_entry_safe(fq, n, &expired, list_evictor)
- f->frag_expire(&fq->timer);
-
- return evicted;
-}
-
-static void inet_frag_worker(struct work_struct *work)
-{
- unsigned int budget = INETFRAGS_EVICT_BUCKETS;
- unsigned int i, evicted = 0;
- struct inet_frags *f;
-
- f = container_of(work, struct inet_frags, frags_work);
-
- BUILD_BUG_ON(INETFRAGS_EVICT_BUCKETS >= INETFRAGS_HASHSZ);
-
- local_bh_disable();
-
- for (i = READ_ONCE(f->next_bucket); budget; --budget) {
- evicted += inet_evict_bucket(f, &f->hash[i]);
- i = (i + 1) & (INETFRAGS_HASHSZ - 1);
- if (evicted > INETFRAGS_EVICT_MAX)
- break;
- }
-
- f->next_bucket = i;
-
- local_bh_enable();
-
- if (f->rebuild && inet_frag_may_rebuild(f))
- inet_frag_secret_rebuild(f);
-}
-
-static void inet_frag_schedule_worker(struct inet_frags *f)
-{
- if (unlikely(!work_pending(&f->frags_work)))
- schedule_work(&f->frags_work);
-}
-
int inet_frags_init(struct inet_frags *f)
{
- int i;
-
- INIT_WORK(&f->frags_work, inet_frag_worker);
-
- for (i = 0; i < INETFRAGS_HASHSZ; i++) {
- struct inet_frag_bucket *hb = &f->hash[i];
-
- spin_lock_init(&hb->chain_lock);
- INIT_HLIST_HEAD(&hb->chain);
- }
-
- seqlock_init(&f->rnd_seqlock);
- f->last_rebuild_jiffies = 0;
f->frags_cachep = kmem_cache_create(f->frags_cache_name, f->qsize, 0, 0,
NULL);
if (!f->frags_cachep)
@@ -214,79 +59,69 @@ EXPORT_SYMBOL(inet_frags_init);
void inet_frags_fini(struct inet_frags *f)
{
- cancel_work_sync(&f->frags_work);
+ /* We must wait that all inet_frag_destroy_rcu() have completed. */
+ rcu_barrier();
+
kmem_cache_destroy(f->frags_cachep);
+ f->frags_cachep = NULL;
}
EXPORT_SYMBOL(inet_frags_fini);
+static void inet_frags_free_cb(void *ptr, void *arg)
+{
+ struct inet_frag_queue *fq = ptr;
+
+ /* If we can not cancel the timer, it means this frag_queue
+ * is already disappearing, we have nothing to do.
+ * Otherwise, we own a refcount until the end of this function.
+ */
+ if (!del_timer(&fq->timer))
+ return;
+
+ spin_lock_bh(&fq->lock);
+ if (!(fq->flags & INET_FRAG_COMPLETE)) {
+ fq->flags |= INET_FRAG_COMPLETE;
+ refcount_dec(&fq->refcnt);
+ }
+ spin_unlock_bh(&fq->lock);
+
+ inet_frag_put(fq);
+}
+
void inet_frags_exit_net(struct netns_frags *nf)
{
- struct inet_frags *f =nf->f;
- unsigned int seq;
- int i;
+ nf->low_thresh = 0; /* prevent creation of new frags */
- nf->low_thresh = 0;
-
-evict_again:
- local_bh_disable();
- seq = read_seqbegin(&f->rnd_seqlock);
-
- for (i = 0; i < INETFRAGS_HASHSZ ; i++)
- inet_evict_bucket(f, &f->hash[i]);
-
- local_bh_enable();
- cond_resched();
-
- if (read_seqretry(&f->rnd_seqlock, seq) ||
- sum_frag_mem_limit(nf))
- goto evict_again;
+ rhashtable_free_and_destroy(&nf->rhashtable, inet_frags_free_cb, NULL);
}
EXPORT_SYMBOL(inet_frags_exit_net);
-static struct inet_frag_bucket *
-get_frag_bucket_locked(struct inet_frag_queue *fq, struct inet_frags *f)
-__acquires(hb->chain_lock)
-{
- struct inet_frag_bucket *hb;
- unsigned int seq, hash;
-
- restart:
- seq = read_seqbegin(&f->rnd_seqlock);
-
- hash = inet_frag_hashfn(f, fq);
- hb = &f->hash[hash];
-
- spin_lock(&hb->chain_lock);
- if (read_seqretry(&f->rnd_seqlock, seq)) {
- spin_unlock(&hb->chain_lock);
- goto restart;
- }
-
- return hb;
-}
-
-static inline void fq_unlink(struct inet_frag_queue *fq)
-{
- struct inet_frag_bucket *hb;
-
- hb = get_frag_bucket_locked(fq, fq->net->f);
- hlist_del(&fq->list);
- fq->flags |= INET_FRAG_COMPLETE;
- spin_unlock(&hb->chain_lock);
-}
-
void inet_frag_kill(struct inet_frag_queue *fq)
{
if (del_timer(&fq->timer))
refcount_dec(&fq->refcnt);
if (!(fq->flags & INET_FRAG_COMPLETE)) {
- fq_unlink(fq);
+ struct netns_frags *nf = fq->net;
+
+ fq->flags |= INET_FRAG_COMPLETE;
+ rhashtable_remove_fast(&nf->rhashtable, &fq->node, nf->f->rhash_params);
refcount_dec(&fq->refcnt);
}
}
EXPORT_SYMBOL(inet_frag_kill);
+static void inet_frag_destroy_rcu(struct rcu_head *head)
+{
+ struct inet_frag_queue *q = container_of(head, struct inet_frag_queue,
+ rcu);
+ struct inet_frags *f = q->net->f;
+
+ if (f->destructor)
+ f->destructor(q);
+ kmem_cache_free(f->frags_cachep, q);
+}
+
void inet_frag_destroy(struct inet_frag_queue *q)
{
struct sk_buff *fp;
@@ -310,59 +145,20 @@ void inet_frag_destroy(struct inet_frag_queue *q)
}
sum = sum_truesize + f->qsize;
- if (f->destructor)
- f->destructor(q);
- kmem_cache_free(f->frags_cachep, q);
+ call_rcu(&q->rcu, inet_frag_destroy_rcu);
sub_frag_mem_limit(nf, sum);
}
EXPORT_SYMBOL(inet_frag_destroy);
-static struct inet_frag_queue *inet_frag_intern(struct netns_frags *nf,
- struct inet_frag_queue *qp_in,
- struct inet_frags *f,
- void *arg)
-{
- struct inet_frag_bucket *hb = get_frag_bucket_locked(qp_in, f);
- struct inet_frag_queue *qp;
-
-#ifdef CONFIG_SMP
- /* With SMP race we have to recheck hash table, because
- * such entry could have been created on other cpu before
- * we acquired hash bucket lock.
- */
- hlist_for_each_entry(qp, &hb->chain, list) {
- if (qp->net == nf && f->match(qp, arg)) {
- refcount_inc(&qp->refcnt);
- spin_unlock(&hb->chain_lock);
- qp_in->flags |= INET_FRAG_COMPLETE;
- inet_frag_put(qp_in);
- return qp;
- }
- }
-#endif
- qp = qp_in;
- if (!mod_timer(&qp->timer, jiffies + nf->timeout))
- refcount_inc(&qp->refcnt);
-
- refcount_inc(&qp->refcnt);
- hlist_add_head(&qp->list, &hb->chain);
-
- spin_unlock(&hb->chain_lock);
-
- return qp;
-}
-
static struct inet_frag_queue *inet_frag_alloc(struct netns_frags *nf,
struct inet_frags *f,
void *arg)
{
struct inet_frag_queue *q;
- if (!nf->high_thresh || frag_mem_limit(nf) > nf->high_thresh) {
- inet_frag_schedule_worker(f);
+ if (!nf->high_thresh || frag_mem_limit(nf) > nf->high_thresh)
return NULL;
- }
q = kmem_cache_zalloc(f->frags_cachep, GFP_ATOMIC);
if (!q)
@@ -374,59 +170,52 @@ static struct inet_frag_queue *inet_frag_alloc(struct netns_frags *nf,
timer_setup(&q->timer, f->frag_expire, 0);
spin_lock_init(&q->lock);
- refcount_set(&q->refcnt, 1);
+ refcount_set(&q->refcnt, 3);
return q;
}
static struct inet_frag_queue *inet_frag_create(struct netns_frags *nf,
- struct inet_frags *f,
void *arg)
{
+ struct inet_frags *f = nf->f;
struct inet_frag_queue *q;
+ int err;
q = inet_frag_alloc(nf, f, arg);
if (!q)
return NULL;
- return inet_frag_intern(nf, q, f, arg);
+ mod_timer(&q->timer, jiffies + nf->timeout);
+
+ err = rhashtable_insert_fast(&nf->rhashtable, &q->node,
+ f->rhash_params);
+ if (err < 0) {
+ q->flags |= INET_FRAG_COMPLETE;
+ inet_frag_kill(q);
+ inet_frag_destroy(q);
+ return NULL;
+ }
+ return q;
}
-struct inet_frag_queue *inet_frag_find(struct netns_frags *nf,
- struct inet_frags *f, void *key,
- unsigned int hash)
+/* TODO : call from rcu_read_lock() and no longer use refcount_inc_not_zero() */
+struct inet_frag_queue *inet_frag_find(struct netns_frags *nf, void *key)
{
- struct inet_frag_bucket *hb;
- struct inet_frag_queue *q;
- int depth = 0;
+ struct inet_frag_queue *fq;
- if (frag_mem_limit(nf) > nf->low_thresh)
- inet_frag_schedule_worker(f);
+ rcu_read_lock();
- hash &= (INETFRAGS_HASHSZ - 1);
- hb = &f->hash[hash];
-
- spin_lock(&hb->chain_lock);
- hlist_for_each_entry(q, &hb->chain, list) {
- if (q->net == nf && f->match(q, key)) {
- refcount_inc(&q->refcnt);
- spin_unlock(&hb->chain_lock);
- return q;
- }
- depth++;
- }
- spin_unlock(&hb->chain_lock);
-
- if (depth <= INETFRAGS_MAXDEPTH)
- return inet_frag_create(nf, f, key);
-
- if (inet_frag_may_rebuild(f)) {
- if (!f->rebuild)
- f->rebuild = true;
- inet_frag_schedule_worker(f);
+ fq = rhashtable_lookup(&nf->rhashtable, key, nf->f->rhash_params);
+ if (fq) {
+ if (!refcount_inc_not_zero(&fq->refcnt))
+ fq = NULL;
+ rcu_read_unlock();
+ return fq;
}
+ rcu_read_unlock();
- return ERR_PTR(-ENOBUFS);
+ return inet_frag_create(nf, key);
}
EXPORT_SYMBOL(inet_frag_find);
@@ -434,8 +223,7 @@ void inet_frag_maybe_warn_overflow(struct inet_frag_queue *q,
const char *prefix)
{
static const char msg[] = "inet_frag_find: Fragment hash bucket"
- " list length grew over limit " __stringify(INETFRAGS_MAXDEPTH)
- ". Dropping fragment.\n";
+ " list length grew over limit. Dropping fragment.\n";
if (PTR_ERR(q) == -ENOBUFS)
net_dbg_ratelimited("%s%s", prefix, msg);
diff --git a/net/ipv4/ip_fragment.c b/net/ipv4/ip_fragment.c
index 1a3bc85d6f5ea8f36b8f3d221cad632906b317a2..4021820db6f291b255cc53aeca91dd74aef29934 100644
--- a/net/ipv4/ip_fragment.c
+++ b/net/ipv4/ip_fragment.c
@@ -69,15 +69,9 @@ struct ipfrag_skb_cb
struct ipq {
struct inet_frag_queue q;
- u32 user;
- __be32 saddr;
- __be32 daddr;
- __be16 id;
- u8 protocol;
u8 ecn; /* RFC3168 support */
u16 max_df_size; /* largest frag with DF set seen */
int iif;
- int vif; /* L3 master device index */
unsigned int rid;
struct inet_peer *peer;
};
@@ -97,41 +91,6 @@ int ip_frag_mem(struct net *net)
static int ip_frag_reasm(struct ipq *qp, struct sk_buff *prev,
struct net_device *dev);
-struct ip4_create_arg {
- struct iphdr *iph;
- u32 user;
- int vif;
-};
-
-static unsigned int ipqhashfn(__be16 id, __be32 saddr, __be32 daddr, u8 prot)
-{
- net_get_random_once(&ip4_frags.rnd, sizeof(ip4_frags.rnd));
- return jhash_3words((__force u32)id << 16 | prot,
- (__force u32)saddr, (__force u32)daddr,
- ip4_frags.rnd);
-}
-
-static unsigned int ip4_hashfn(const struct inet_frag_queue *q)
-{
- const struct ipq *ipq;
-
- ipq = container_of(q, struct ipq, q);
- return ipqhashfn(ipq->id, ipq->saddr, ipq->daddr, ipq->protocol);
-}
-
-static bool ip4_frag_match(const struct inet_frag_queue *q, const void *a)
-{
- const struct ipq *qp;
- const struct ip4_create_arg *arg = a;
-
- qp = container_of(q, struct ipq, q);
- return qp->id == arg->iph->id &&
- qp->saddr == arg->iph->saddr &&
- qp->daddr == arg->iph->daddr &&
- qp->protocol == arg->iph->protocol &&
- qp->user == arg->user &&
- qp->vif == arg->vif;
-}
static void ip4_frag_init(struct inet_frag_queue *q, const void *a)
{
@@ -140,17 +99,12 @@ static void ip4_frag_init(struct inet_frag_queue *q, const void *a)
frags);
struct net *net = container_of(ipv4, struct net, ipv4);
- const struct ip4_create_arg *arg = a;
+ const struct frag_v4_compare_key *key = a;
- qp->protocol = arg->iph->protocol;
- qp->id = arg->iph->id;
- qp->ecn = ip4_frag_ecn(arg->iph->tos);
- qp->saddr = arg->iph->saddr;
- qp->daddr = arg->iph->daddr;
- qp->vif = arg->vif;
- qp->user = arg->user;
+ q->key.v4 = *key;
+ qp->ecn = 0;
qp->peer = q->net->max_dist ?
- inet_getpeer_v4(net->ipv4.peers, arg->iph->saddr, arg->vif, 1) :
+ inet_getpeer_v4(net->ipv4.peers, key->saddr, key->vif, 1) :
NULL;
}
@@ -234,7 +188,7 @@ static void ip_expire(struct timer_list *t)
/* Only an end host needs to send an ICMP
* "Fragment Reassembly Timeout" message, per RFC792.
*/
- if (frag_expire_skip_icmp(qp->user) &&
+ if (frag_expire_skip_icmp(qp->q.key.v4.user) &&
(skb_rtable(head)->rt_type != RTN_LOCAL))
goto out;
@@ -262,17 +216,17 @@ static void ip_expire(struct timer_list *t)
static struct ipq *ip_find(struct net *net, struct iphdr *iph,
u32 user, int vif)
{
+ struct frag_v4_compare_key key = {
+ .saddr = iph->saddr,
+ .daddr = iph->daddr,
+ .user = user,
+ .vif = vif,
+ .id = iph->id,
+ .protocol = iph->protocol,
+ };
struct inet_frag_queue *q;
- struct ip4_create_arg arg;
- unsigned int hash;
- arg.iph = iph;
- arg.user = user;
- arg.vif = vif;
-
- hash = ipqhashfn(iph->id, iph->saddr, iph->daddr, iph->protocol);
-
- q = inet_frag_find(&net->ipv4.frags, &ip4_frags, &arg, hash);
+ q = inet_frag_find(&net->ipv4.frags, &key);
if (IS_ERR_OR_NULL(q)) {
inet_frag_maybe_warn_overflow(q, pr_fmt());
return NULL;
@@ -656,7 +610,7 @@ static int ip_frag_reasm(struct ipq *qp, struct sk_buff *prev,
err = -ENOMEM;
goto out_fail;
out_oversize:
- net_info_ratelimited("Oversized IP packet from %pI4\n", &qp->saddr);
+ net_info_ratelimited("Oversized IP packet from %pI4\n", &qp->q.key.v4.saddr);
out_fail:
__IP_INC_STATS(net, IPSTATS_MIB_REASMFAILS);
return err;
@@ -894,15 +848,47 @@ static struct pernet_operations ip4_frags_ops = {
.exit = ipv4_frags_exit_net,
};
+
+static u32 ip4_key_hashfn(const void *data, u32 len, u32 seed)
+{
+ return jhash2(data,
+ sizeof(struct frag_v4_compare_key) / sizeof(u32), seed);
+}
+
+static u32 ip4_obj_hashfn(const void *data, u32 len, u32 seed)
+{
+ const struct inet_frag_queue *fq = data;
+
+ return jhash2((const u32 *)&fq->key.v4,
+ sizeof(struct frag_v4_compare_key) / sizeof(u32), seed);
+}
+
+static int ip4_obj_cmpfn(struct rhashtable_compare_arg *arg, const void *ptr)
+{
+ const struct frag_v4_compare_key *key = arg->key;
+ const struct inet_frag_queue *fq = ptr;
+
+ return !!memcmp(&fq->key, key, sizeof(*key));
+}
+
+static const struct rhashtable_params ip4_rhash_params = {
+ .head_offset = offsetof(struct inet_frag_queue, node),
+ .key_offset = offsetof(struct inet_frag_queue, key),
+ .key_len = sizeof(struct frag_v4_compare_key),
+ .hashfn = ip4_key_hashfn,
+ .obj_hashfn = ip4_obj_hashfn,
+ .obj_cmpfn = ip4_obj_cmpfn,
+ .automatic_shrinking = true,
+};
+
void __init ipfrag_init(void)
{
- ip4_frags.hashfn = ip4_hashfn;
ip4_frags.constructor = ip4_frag_init;
ip4_frags.destructor = ip4_frag_free;
ip4_frags.qsize = sizeof(struct ipq);
- ip4_frags.match = ip4_frag_match;
ip4_frags.frag_expire = ip_expire;
ip4_frags.frags_cache_name = ip_frag_cache_name;
+ ip4_frags.rhash_params = ip4_rhash_params;
if (inet_frags_init(&ip4_frags))
panic("IP: failed to allocate ip4_frags cache\n");
ip4_frags_ctl_register();
diff --git a/net/ipv6/netfilter/nf_conntrack_reasm.c b/net/ipv6/netfilter/nf_conntrack_reasm.c
index c4b40fdee838300f3723cece1e6b5b9d03fa9249..0ad3df551d9884ba30f2d40658ee81a61720e947 100644
--- a/net/ipv6/netfilter/nf_conntrack_reasm.c
+++ b/net/ipv6/netfilter/nf_conntrack_reasm.c
@@ -152,23 +152,6 @@ static inline u8 ip6_frag_ecn(const struct ipv6hdr *ipv6h)
return 1 << (ipv6_get_dsfield(ipv6h) & INET_ECN_MASK);
}
-static unsigned int nf_hash_frag(__be32 id, const struct in6_addr *saddr,
- const struct in6_addr *daddr)
-{
- net_get_random_once(&nf_frags.rnd, sizeof(nf_frags.rnd));
- return jhash_3words(ipv6_addr_hash(saddr), ipv6_addr_hash(daddr),
- (__force u32)id, nf_frags.rnd);
-}
-
-
-static unsigned int nf_hashfn(const struct inet_frag_queue *q)
-{
- const struct frag_queue *nq;
-
- nq = container_of(q, struct frag_queue, q);
- return nf_hash_frag(nq->id, &nq->saddr, &nq->daddr);
-}
-
static void nf_ct_frag6_expire(struct timer_list *t)
{
struct inet_frag_queue *frag = from_timer(frag, t, timer);
@@ -182,26 +165,19 @@ static void nf_ct_frag6_expire(struct timer_list *t)
}
/* Creation primitives. */
-static inline struct frag_queue *fq_find(struct net *net, __be32 id,
- u32 user, struct in6_addr *src,
- struct in6_addr *dst, int iif, u8 ecn)
+static struct frag_queue *fq_find(struct net *net, __be32 id, u32 user,
+ const struct ipv6hdr *hdr, int iif)
{
+ struct frag_v6_compare_key key = {
+ .id = id,
+ .saddr = hdr->saddr,
+ .daddr = hdr->daddr,
+ .user = user,
+ .iif = iif,
+ };
struct inet_frag_queue *q;
- struct ip6_create_arg arg;
- unsigned int hash;
- arg.id = id;
- arg.user = user;
- arg.src = src;
- arg.dst = dst;
- arg.iif = iif;
- arg.ecn = ecn;
-
- local_bh_disable();
- hash = nf_hash_frag(id, src, dst);
-
- q = inet_frag_find(&net->nf_frag.frags, &nf_frags, &arg, hash);
- local_bh_enable();
+ q = inet_frag_find(&net->nf_frag.frags, &key);
if (IS_ERR_OR_NULL(q)) {
inet_frag_maybe_warn_overflow(q, pr_fmt());
return NULL;
@@ -593,8 +569,8 @@ int nf_ct_frag6_gather(struct net *net, struct sk_buff *skb, u32 user)
fhdr = (struct frag_hdr *)skb_transport_header(skb);
skb_orphan(skb);
- fq = fq_find(net, fhdr->identification, user, &hdr->saddr, &hdr->daddr,
- skb->dev ? skb->dev->ifindex : 0, ip6_frag_ecn(hdr));
+ fq = fq_find(net, fhdr->identification, user, hdr,
+ skb->dev ? skb->dev->ifindex : 0);
if (fq == NULL) {
pr_debug("Can't find and can't create new queue\n");
return -ENOMEM;
@@ -660,13 +636,12 @@ int nf_ct_frag6_init(void)
{
int ret = 0;
- nf_frags.hashfn = nf_hashfn;
nf_frags.constructor = ip6_frag_init;
nf_frags.destructor = NULL;
nf_frags.qsize = sizeof(struct frag_queue);
- nf_frags.match = ip6_frag_match;
nf_frags.frag_expire = nf_ct_frag6_expire;
nf_frags.frags_cache_name = nf_frags_cache_name;
+ nf_frags.rhash_params = ip6_rhash_params;
ret = inet_frags_init(&nf_frags);
if (ret)
goto out;
diff --git a/net/ipv6/reassembly.c b/net/ipv6/reassembly.c
index f0071b113a92fcff15ac57610170c12b17cb59ba..3fc853e4492abb109062d662296c0b470763042a 100644
--- a/net/ipv6/reassembly.c
+++ b/net/ipv6/reassembly.c
@@ -79,52 +79,13 @@ static struct inet_frags ip6_frags;
static int ip6_frag_reasm(struct frag_queue *fq, struct sk_buff *prev,
struct net_device *dev);
-/*
- * callers should be careful not to use the hash value outside the ipfrag_lock
- * as doing so could race with ipfrag_hash_rnd being recalculated.
- */
-static unsigned int inet6_hash_frag(__be32 id, const struct in6_addr *saddr,
- const struct in6_addr *daddr)
-{
- net_get_random_once(&ip6_frags.rnd, sizeof(ip6_frags.rnd));
- return jhash_3words(ipv6_addr_hash(saddr), ipv6_addr_hash(daddr),
- (__force u32)id, ip6_frags.rnd);
-}
-
-static unsigned int ip6_hashfn(const struct inet_frag_queue *q)
-{
- const struct frag_queue *fq;
-
- fq = container_of(q, struct frag_queue, q);
- return inet6_hash_frag(fq->id, &fq->saddr, &fq->daddr);
-}
-
-bool ip6_frag_match(const struct inet_frag_queue *q, const void *a)
-{
- const struct frag_queue *fq;
- const struct ip6_create_arg *arg = a;
-
- fq = container_of(q, struct frag_queue, q);
- return fq->id == arg->id &&
- fq->user == arg->user &&
- ipv6_addr_equal(&fq->saddr, arg->src) &&
- ipv6_addr_equal(&fq->daddr, arg->dst) &&
- (arg->iif == fq->iif ||
- !(ipv6_addr_type(arg->dst) & (IPV6_ADDR_MULTICAST |
- IPV6_ADDR_LINKLOCAL)));
-}
-EXPORT_SYMBOL(ip6_frag_match);
-
void ip6_frag_init(struct inet_frag_queue *q, const void *a)
{
struct frag_queue *fq = container_of(q, struct frag_queue, q);
- const struct ip6_create_arg *arg = a;
+ const struct frag_v6_compare_key *key = a;
- fq->id = arg->id;
- fq->user = arg->user;
- fq->saddr = *arg->src;
- fq->daddr = *arg->dst;
- fq->ecn = arg->ecn;
+ q->key.v6 = *key;
+ fq->ecn = 0;
}
EXPORT_SYMBOL(ip6_frag_init);
@@ -182,23 +143,22 @@ static void ip6_frag_expire(struct timer_list *t)
}
static struct frag_queue *
-fq_find(struct net *net, __be32 id, const struct in6_addr *src,
- const struct in6_addr *dst, int iif, u8 ecn)
+fq_find(struct net *net, __be32 id, const struct ipv6hdr *hdr, int iif)
{
+ struct frag_v6_compare_key key = {
+ .id = id,
+ .saddr = hdr->saddr,
+ .daddr = hdr->daddr,
+ .user = IP6_DEFRAG_LOCAL_DELIVER,
+ .iif = iif,
+ };
struct inet_frag_queue *q;
- struct ip6_create_arg arg;
- unsigned int hash;
- arg.id = id;
- arg.user = IP6_DEFRAG_LOCAL_DELIVER;
- arg.src = src;
- arg.dst = dst;
- arg.iif = iif;
- arg.ecn = ecn;
+ if (!(ipv6_addr_type(&hdr->daddr) & (IPV6_ADDR_MULTICAST |
+ IPV6_ADDR_LINKLOCAL)))
+ key.iif = 0;
- hash = inet6_hash_frag(id, src, dst);
-
- q = inet_frag_find(&net->ipv6.frags, &ip6_frags, &arg, hash);
+ q = inet_frag_find(&net->ipv6.frags, &key);
if (IS_ERR_OR_NULL(q)) {
inet_frag_maybe_warn_overflow(q, pr_fmt());
return NULL;
@@ -530,6 +490,7 @@ static int ipv6_frag_rcv(struct sk_buff *skb)
struct frag_queue *fq;
const struct ipv6hdr *hdr = ipv6_hdr(skb);
struct net *net = dev_net(skb_dst(skb)->dev);
+ int iif;
if (IP6CB(skb)->flags & IP6SKB_FRAGMENTED)
goto fail_hdr;
@@ -558,13 +519,14 @@ static int ipv6_frag_rcv(struct sk_buff *skb)
return 1;
}
- fq = fq_find(net, fhdr->identification, &hdr->saddr, &hdr->daddr,
- skb->dev ? skb->dev->ifindex : 0, ip6_frag_ecn(hdr));
+ iif = skb->dev ? skb->dev->ifindex : 0;
+ fq = fq_find(net, fhdr->identification, hdr, iif);
if (fq) {
int ret;
spin_lock(&fq->q.lock);
+ fq->iif = iif;
ret = ip6_frag_queue(fq, skb, fhdr, IP6CB(skb)->nhoff);
spin_unlock(&fq->q.lock);
@@ -738,17 +700,47 @@ static struct pernet_operations ip6_frags_ops = {
.exit = ipv6_frags_exit_net,
};
+static u32 ip6_key_hashfn(const void *data, u32 len, u32 seed)
+{
+ return jhash2(data,
+ sizeof(struct frag_v6_compare_key) / sizeof(u32), seed);
+}
+
+static u32 ip6_obj_hashfn(const void *data, u32 len, u32 seed)
+{
+ const struct inet_frag_queue *fq = data;
+
+ return jhash2((const u32 *)&fq->key.v6,
+ sizeof(struct frag_v6_compare_key) / sizeof(u32), seed);
+}
+
+static int ip6_obj_cmpfn(struct rhashtable_compare_arg *arg, const void *ptr)
+{
+ const struct frag_v6_compare_key *key = arg->key;
+ const struct inet_frag_queue *fq = ptr;
+
+ return !!memcmp(&fq->key, key, sizeof(*key));
+}
+
+const struct rhashtable_params ip6_rhash_params = {
+ .head_offset = offsetof(struct inet_frag_queue, node),
+ .hashfn = ip6_key_hashfn,
+ .obj_hashfn = ip6_obj_hashfn,
+ .obj_cmpfn = ip6_obj_cmpfn,
+ .automatic_shrinking = true,
+};
+EXPORT_SYMBOL(ip6_rhash_params);
+
int __init ipv6_frag_init(void)
{
int ret;
- ip6_frags.hashfn = ip6_hashfn;
ip6_frags.constructor = ip6_frag_init;
ip6_frags.destructor = NULL;
ip6_frags.qsize = sizeof(struct frag_queue);
- ip6_frags.match = ip6_frag_match;
ip6_frags.frag_expire = ip6_frag_expire;
ip6_frags.frags_cache_name = ip6_frag_cache_name;
+ ip6_frags.rhash_params = ip6_rhash_params;
ret = inet_frags_init(&ip6_frags);
if (ret)
goto out;
--
2.17.0.rc1.321.gba9d0f2565-goog
^ 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