* [net-next 3/3] bna: Eliminate Small Race Condition Window in RX Path
From: Rasesh Mody @ 2011-09-17 1:06 UTC (permalink / raw)
To: davem, netdev; +Cc: adapter_linux_open_src_team, Rasesh Mody, Gurunatha Karaje
In-Reply-To: <1316221608-21392-1-git-send-email-rmody@brocade.com>
Change details:
- In a continuous sequence of ifconfig up/down operations, there is a small
window of race between bnad_set_rx_mode() and bnad_cleanup_rx() while the
former tries to access rx_info->rx & the latter sets it to NULL. This race
could lead to bna_rx_mode_set() being called with a NULL (rx_info->rx)
pointer and a crash.
- Hold bnad->bna_lock while setting / unsetting rx_info->rx in bnad_setup_rx()
& bnad_cleanup_rx(), thereby eliminating the race described above.
Signed-off-by: Gurunatha Karaje <gkaraje@brocade.com>
Signed-off-by: Rasesh Mody <rmody@brocade.com>
---
drivers/net/ethernet/brocade/bna/bnad.c | 5 +++--
1 files changed, 3 insertions(+), 2 deletions(-)
diff --git a/drivers/net/ethernet/brocade/bna/bnad.c b/drivers/net/ethernet/brocade/bna/bnad.c
index 33ab1f8..abca139 100644
--- a/drivers/net/ethernet/brocade/bna/bnad.c
+++ b/drivers/net/ethernet/brocade/bna/bnad.c
@@ -1875,10 +1875,10 @@ bnad_cleanup_rx(struct bnad *bnad, u32 rx_id)
spin_lock_irqsave(&bnad->bna_lock, flags);
bna_rx_destroy(rx_info->rx);
- spin_unlock_irqrestore(&bnad->bna_lock, flags);
rx_info->rx = NULL;
rx_info->rx_id = 0;
+ spin_unlock_irqrestore(&bnad->bna_lock, flags);
bnad_rx_res_free(bnad, res_info);
}
@@ -1932,12 +1932,13 @@ bnad_setup_rx(struct bnad *bnad, u32 rx_id)
spin_lock_irqsave(&bnad->bna_lock, flags);
rx = bna_rx_create(&bnad->bna, bnad, rx_config, &rx_cbfn, res_info,
rx_info);
- spin_unlock_irqrestore(&bnad->bna_lock, flags);
if (!rx) {
err = -ENOMEM;
+ spin_unlock_irqrestore(&bnad->bna_lock, flags);
goto err_return;
}
rx_info->rx = rx;
+ spin_unlock_irqrestore(&bnad->bna_lock, flags);
/*
* Init NAPI, so that state is set to NAPI_STATE_SCHED,
--
1.7.1
^ permalink raw reply related
* [net-next 1/3] bna: Semaphore Lock Fix
From: Rasesh Mody @ 2011-09-17 1:06 UTC (permalink / raw)
To: davem, netdev; +Cc: adapter_linux_open_src_team, Rasesh Mody, Gurunatha Karaje
Remove a BUG_ON() as it is not required.
Change the unconditional write to release a semaphore to read sem first
and then write. This will eliminate the possibility of sem getting locked
while trying to release it in case if previous sem_get operation failed.
Signed-off-by: Gurunatha Karaje <gkaraje@brocade.com>
Signed-off-by: Rasesh Mody <rmody@brocade.com>
---
drivers/net/ethernet/brocade/bna/bfa_ioc.c | 2 +-
1 files changed, 1 insertions(+), 1 deletions(-)
diff --git a/drivers/net/ethernet/brocade/bna/bfa_ioc.c b/drivers/net/ethernet/brocade/bna/bfa_ioc.c
index 029fb52..4282fef 100644
--- a/drivers/net/ethernet/brocade/bna/bfa_ioc.c
+++ b/drivers/net/ethernet/brocade/bna/bfa_ioc.c
@@ -1201,13 +1201,13 @@ bfa_nw_ioc_sem_get(void __iomem *sem_reg)
if (!(r32 & 1))
return true;
- BUG_ON(!(cnt < BFA_SEM_SPINCNT));
return false;
}
void
bfa_nw_ioc_sem_release(void __iomem *sem_reg)
{
+ readl(sem_reg);
writel(1, sem_reg);
}
--
1.7.1
^ permalink raw reply related
* [net-next 00/11][pull request] Intel Wired LAN Driver Updates
From: Jeff Kirsher @ 2011-09-17 2:15 UTC (permalink / raw)
To: davem; +Cc: Jeff Kirsher, netdev, gospo
The following series contains updates to ixgb and ixgbe. The ixgb patch
does the conversion to ndo_fix_features. The remaining patches are for
ixgbe to do the following:
- cleanup register reads, comments, memory allocations
- add SFP support for 82598 PHY and overheat sensor code
- fix register dump for X50
The following are changes since commit f78a5fda9116525809d088917638be912b85f838:
Revert "Scm: Remove unnecessary pid & credential references in Unix socket's send and receive path"
and are available in the git repository at:
git://github.com/Jkirsher/net-next.git
Alexander Duyck (7):
ixgbe: remove redundant configuration of tx_sample_rate
v2 ixgbe: Update packet buffer reservation to correct fdir headroom
size
ixgbe: make ixgbe_up and ixgbe_up_complete void functions
ixgbe: Add missing code for enabling overheat sensor interrupt
ixgbe: Add SFP support for missed 82598 PHY
ixgbe: drop adapter from ixgbe_fso call documentation
ixgbe: Make better use of memory allocations in one-buffer mode w/
RSC
Emil Tantilov (3):
ixgbe: cleanup some register reads
ixgbe: fix FCRTL/H register dump for X540
ixgbe: remove duplicate netif_tx_start_all_queues
Michał Mirosław (1):
ixgb: convert to ndo_fix_features
drivers/net/ethernet/intel/ixgb/ixgb.h | 2 +
drivers/net/ethernet/intel/ixgb/ixgb_ethtool.c | 59 +----------
drivers/net/ethernet/intel/ixgb/ixgb_main.c | 31 +++++-
drivers/net/ethernet/intel/ixgbe/ixgbe.h | 13 ++-
drivers/net/ethernet/intel/ixgbe/ixgbe_ethtool.c | 3 +-
drivers/net/ethernet/intel/ixgbe/ixgbe_fcoe.c | 1 -
drivers/net/ethernet/intel/ixgbe/ixgbe_main.c | 126 ++++++++++++----------
7 files changed, 112 insertions(+), 123 deletions(-)
--
1.7.6
^ permalink raw reply
* [net-next 01/11] ixgb: convert to ndo_fix_features
From: Jeff Kirsher @ 2011-09-17 2:15 UTC (permalink / raw)
To: davem; +Cc: Michał Mirosław, netdev, gospo, Jeff Kirsher
In-Reply-To: <1316225752-1709-1-git-send-email-jeffrey.t.kirsher@intel.com>
From: Michał Mirosław <mirq-linux@rere.qmqm.pl>
Private rx_csum flags are now duplicate of netdev->features & NETIF_F_RXCSUM.
Removing this needs deeper surgery.
Things noticed:
- ixgb has RX csum disabled by default
- HW VLAN acceleration probably can be toggled, but it's left as is
- the resets on RX csum offload change can probably be avoided
- there is A LOT of copy-and-pasted code here
Signed-off-by: Michał Mirosław <mirq-linux@rere.qmqm.pl>
Signed-off-by: Jeff Kirsher <jeffrey.t.kirsher@intel.com>
---
drivers/net/ethernet/intel/ixgb/ixgb.h | 2 +
drivers/net/ethernet/intel/ixgb/ixgb_ethtool.c | 59 +-----------------------
drivers/net/ethernet/intel/ixgb/ixgb_main.c | 31 +++++++++++-
3 files changed, 31 insertions(+), 61 deletions(-)
diff --git a/drivers/net/ethernet/intel/ixgb/ixgb.h b/drivers/net/ethernet/intel/ixgb/ixgb.h
index 49e8408..cb23448 100644
--- a/drivers/net/ethernet/intel/ixgb/ixgb.h
+++ b/drivers/net/ethernet/intel/ixgb/ixgb.h
@@ -204,6 +204,8 @@ extern void ixgb_set_ethtool_ops(struct net_device *netdev);
extern char ixgb_driver_name[];
extern const char ixgb_driver_version[];
+extern void ixgb_set_speed_duplex(struct net_device *netdev);
+
extern int ixgb_up(struct ixgb_adapter *adapter);
extern void ixgb_down(struct ixgb_adapter *adapter, bool kill_watchdog);
extern void ixgb_reset(struct ixgb_adapter *adapter);
diff --git a/drivers/net/ethernet/intel/ixgb/ixgb_ethtool.c b/drivers/net/ethernet/intel/ixgb/ixgb_ethtool.c
index 6da890b..fdb30cc 100644
--- a/drivers/net/ethernet/intel/ixgb/ixgb_ethtool.c
+++ b/drivers/net/ethernet/intel/ixgb/ixgb_ethtool.c
@@ -115,7 +115,7 @@ ixgb_get_settings(struct net_device *netdev, struct ethtool_cmd *ecmd)
return 0;
}
-static void ixgb_set_speed_duplex(struct net_device *netdev)
+void ixgb_set_speed_duplex(struct net_device *netdev)
{
struct ixgb_adapter *adapter = netdev_priv(netdev);
/* be optimistic about our link, since we were up before */
@@ -195,57 +195,6 @@ ixgb_set_pauseparam(struct net_device *netdev,
}
static u32
-ixgb_get_rx_csum(struct net_device *netdev)
-{
- struct ixgb_adapter *adapter = netdev_priv(netdev);
-
- return adapter->rx_csum;
-}
-
-static int
-ixgb_set_rx_csum(struct net_device *netdev, u32 data)
-{
- struct ixgb_adapter *adapter = netdev_priv(netdev);
-
- adapter->rx_csum = data;
-
- if (netif_running(netdev)) {
- ixgb_down(adapter, true);
- ixgb_up(adapter);
- ixgb_set_speed_duplex(netdev);
- } else
- ixgb_reset(adapter);
- return 0;
-}
-
-static u32
-ixgb_get_tx_csum(struct net_device *netdev)
-{
- return (netdev->features & NETIF_F_HW_CSUM) != 0;
-}
-
-static int
-ixgb_set_tx_csum(struct net_device *netdev, u32 data)
-{
- if (data)
- netdev->features |= NETIF_F_HW_CSUM;
- else
- netdev->features &= ~NETIF_F_HW_CSUM;
-
- return 0;
-}
-
-static int
-ixgb_set_tso(struct net_device *netdev, u32 data)
-{
- if (data)
- netdev->features |= NETIF_F_TSO;
- else
- netdev->features &= ~NETIF_F_TSO;
- return 0;
-}
-
-static u32
ixgb_get_msglevel(struct net_device *netdev)
{
struct ixgb_adapter *adapter = netdev_priv(netdev);
@@ -736,14 +685,8 @@ static const struct ethtool_ops ixgb_ethtool_ops = {
.set_ringparam = ixgb_set_ringparam,
.get_pauseparam = ixgb_get_pauseparam,
.set_pauseparam = ixgb_set_pauseparam,
- .get_rx_csum = ixgb_get_rx_csum,
- .set_rx_csum = ixgb_set_rx_csum,
- .get_tx_csum = ixgb_get_tx_csum,
- .set_tx_csum = ixgb_set_tx_csum,
- .set_sg = ethtool_op_set_sg,
.get_msglevel = ixgb_get_msglevel,
.set_msglevel = ixgb_set_msglevel,
- .set_tso = ixgb_set_tso,
.get_strings = ixgb_get_strings,
.set_phys_id = ixgb_set_phys_id,
.get_sset_count = ixgb_get_sset_count,
diff --git a/drivers/net/ethernet/intel/ixgb/ixgb_main.c b/drivers/net/ethernet/intel/ixgb/ixgb_main.c
index c8b9c90..b8fb163 100644
--- a/drivers/net/ethernet/intel/ixgb/ixgb_main.c
+++ b/drivers/net/ethernet/intel/ixgb/ixgb_main.c
@@ -325,6 +325,28 @@ ixgb_reset(struct ixgb_adapter *adapter)
}
}
+static int
+ixgb_set_features(struct net_device *netdev, u32 features)
+{
+ struct ixgb_adapter *adapter = netdev_priv(netdev);
+ u32 changed = features ^ netdev->features;
+
+ if (!(changed & NETIF_F_RXCSUM))
+ return 0;
+
+ adapter->rx_csum = !!(features & NETIF_F_RXCSUM);
+
+ if (netif_running(netdev)) {
+ ixgb_down(adapter, true);
+ ixgb_up(adapter);
+ ixgb_set_speed_duplex(netdev);
+ } else
+ ixgb_reset(adapter);
+
+ return 0;
+}
+
+
static const struct net_device_ops ixgb_netdev_ops = {
.ndo_open = ixgb_open,
.ndo_stop = ixgb_close,
@@ -340,6 +362,7 @@ static const struct net_device_ops ixgb_netdev_ops = {
#ifdef CONFIG_NET_POLL_CONTROLLER
.ndo_poll_controller = ixgb_netpoll,
#endif
+ .ndo_set_features = ixgb_set_features,
};
/**
@@ -439,12 +462,14 @@ ixgb_probe(struct pci_dev *pdev, const struct pci_device_id *ent)
if (err)
goto err_sw_init;
- netdev->features = NETIF_F_SG |
- NETIF_F_HW_CSUM |
+ netdev->hw_features = NETIF_F_SG |
+ NETIF_F_TSO |
+ NETIF_F_HW_CSUM;
+ netdev->features = netdev->hw_features |
NETIF_F_HW_VLAN_TX |
NETIF_F_HW_VLAN_RX |
NETIF_F_HW_VLAN_FILTER;
- netdev->features |= NETIF_F_TSO;
+ netdev->hw_features |= NETIF_F_RXCSUM;
if (pci_using_dac) {
netdev->features |= NETIF_F_HIGHDMA;
--
1.7.6
^ permalink raw reply related
* [net-next 02/11] ixgbe: remove redundant configuration of tx_sample_rate
From: Jeff Kirsher @ 2011-09-17 2:15 UTC (permalink / raw)
To: davem; +Cc: Alexander Duyck, netdev, gospo, Jeff Kirsher
In-Reply-To: <1316225752-1709-1-git-send-email-jeffrey.t.kirsher@intel.com>
From: Alexander Duyck <alexander.h.duyck@intel.com>
This change fixes a minor redundancy in that tx_sample_rate was set twice.
Signed-off-by: Alexander Duyck <alexander.h.duyck@intel.com>
Tested-by: Phil Schmitt <phillip.j.schmitt@intel.com>
Signed-off-by: Jeff Kirsher <jeffrey.t.kirsher@intel.com>
---
drivers/net/ethernet/intel/ixgbe/ixgbe_main.c | 13 ++++---------
1 files changed, 4 insertions(+), 9 deletions(-)
diff --git a/drivers/net/ethernet/intel/ixgbe/ixgbe_main.c b/drivers/net/ethernet/intel/ixgbe/ixgbe_main.c
index bb069bc..fec49e6 100644
--- a/drivers/net/ethernet/intel/ixgbe/ixgbe_main.c
+++ b/drivers/net/ethernet/intel/ixgbe/ixgbe_main.c
@@ -3409,16 +3409,12 @@ static void ixgbe_fdir_filter_restore(struct ixgbe_adapter *adapter)
static void ixgbe_configure(struct ixgbe_adapter *adapter)
{
- struct net_device *netdev = adapter->netdev;
- struct ixgbe_hw *hw = &adapter->hw;
- int i;
-
ixgbe_configure_pb(adapter);
#ifdef CONFIG_IXGBE_DCB
ixgbe_configure_dcb(adapter);
#endif
- ixgbe_set_rx_mode(netdev);
+ ixgbe_set_rx_mode(adapter->netdev);
ixgbe_restore_vlan(adapter);
#ifdef IXGBE_FCOE
@@ -3427,15 +3423,14 @@ static void ixgbe_configure(struct ixgbe_adapter *adapter)
#endif /* IXGBE_FCOE */
if (adapter->flags & IXGBE_FLAG_FDIR_HASH_CAPABLE) {
- for (i = 0; i < adapter->num_tx_queues; i++)
- adapter->tx_ring[i]->atr_sample_rate =
- adapter->atr_sample_rate;
- ixgbe_init_fdir_signature_82599(hw, adapter->fdir_pballoc);
+ ixgbe_init_fdir_signature_82599(&adapter->hw,
+ adapter->fdir_pballoc);
} else if (adapter->flags & IXGBE_FLAG_FDIR_PERFECT_CAPABLE) {
ixgbe_init_fdir_perfect_82599(&adapter->hw,
adapter->fdir_pballoc);
ixgbe_fdir_filter_restore(adapter);
}
+
ixgbe_configure_virtualization(adapter);
ixgbe_configure_tx(adapter);
--
1.7.6
^ permalink raw reply related
* [net-next 03/11] v2 ixgbe: Update packet buffer reservation to correct fdir headroom size
From: Jeff Kirsher @ 2011-09-17 2:15 UTC (permalink / raw)
To: davem; +Cc: Alexander Duyck, netdev, gospo, Jeff Kirsher
In-Reply-To: <1316225752-1709-1-git-send-email-jeffrey.t.kirsher@intel.com>
From: Alexander Duyck <alexander.h.duyck@intel.com>
This change fixes an issue in which the incorrect amount of headroom was
being reserved for flow director filters.
Signed-off-by: Alexander Duyck <alexander.h.duyck@intel.com>
Tested-by: Phil Schmitt <phillip.j.schmitt@intel.com>
Signed-off-by: Jeff Kirsher <jeffrey.t.kirsher@intel.com>
---
drivers/net/ethernet/intel/ixgbe/ixgbe_main.c | 10 ++++++----
1 files changed, 6 insertions(+), 4 deletions(-)
diff --git a/drivers/net/ethernet/intel/ixgbe/ixgbe_main.c b/drivers/net/ethernet/intel/ixgbe/ixgbe_main.c
index fec49e6..0283e12 100644
--- a/drivers/net/ethernet/intel/ixgbe/ixgbe_main.c
+++ b/drivers/net/ethernet/intel/ixgbe/ixgbe_main.c
@@ -3372,15 +3372,17 @@ static void ixgbe_configure_dcb(struct ixgbe_adapter *adapter)
static void ixgbe_configure_pb(struct ixgbe_adapter *adapter)
{
- int hdrm = 0;
- int num_tc = netdev_get_num_tc(adapter->netdev);
struct ixgbe_hw *hw = &adapter->hw;
+ int hdrm;
+ u8 tc = netdev_get_num_tc(adapter->netdev);
if (adapter->flags & IXGBE_FLAG_FDIR_HASH_CAPABLE ||
adapter->flags & IXGBE_FLAG_FDIR_PERFECT_CAPABLE)
- hdrm = 64 << adapter->fdir_pballoc;
+ hdrm = 32 << adapter->fdir_pballoc;
+ else
+ hdrm = 0;
- hw->mac.ops.set_rxpba(&adapter->hw, num_tc, hdrm, PBA_STRATEGY_EQUAL);
+ hw->mac.ops.set_rxpba(hw, tc, hdrm, PBA_STRATEGY_EQUAL);
}
static void ixgbe_fdir_filter_restore(struct ixgbe_adapter *adapter)
--
1.7.6
^ permalink raw reply related
* [net-next 04/11] ixgbe: make ixgbe_up and ixgbe_up_complete void functions
From: Jeff Kirsher @ 2011-09-17 2:15 UTC (permalink / raw)
To: davem; +Cc: Alexander Duyck, netdev, gospo, Jeff Kirsher
In-Reply-To: <1316225752-1709-1-git-send-email-jeffrey.t.kirsher@intel.com>
From: Alexander Duyck <alexander.h.duyck@intel.com>
ixgbe_up and ixgbe_up_complete will always return 0. Since this doesn't
provide any useful information we might as well just make them both void
and save ourselves from having to return an unused value.
Signed-off-by: Alexander Duyck <alexander.h.duyck@intel.com>
Tested-by: Phil Schmitt <phillip.j.schmitt@intel.com>
Signed-off-by: Jeff Kirsher <jeffrey.t.kirsher@intel.com>
---
drivers/net/ethernet/intel/ixgbe/ixgbe.h | 2 +-
drivers/net/ethernet/intel/ixgbe/ixgbe_main.c | 23 ++++++-----------------
2 files changed, 7 insertions(+), 18 deletions(-)
diff --git a/drivers/net/ethernet/intel/ixgbe/ixgbe.h b/drivers/net/ethernet/intel/ixgbe/ixgbe.h
index bfdd42b..209286c 100644
--- a/drivers/net/ethernet/intel/ixgbe/ixgbe.h
+++ b/drivers/net/ethernet/intel/ixgbe/ixgbe.h
@@ -547,7 +547,7 @@ extern int ixgbe_copy_dcb_cfg(struct ixgbe_dcb_config *src_dcb_cfg,
extern char ixgbe_driver_name[];
extern const char ixgbe_driver_version[];
-extern int ixgbe_up(struct ixgbe_adapter *adapter);
+extern void ixgbe_up(struct ixgbe_adapter *adapter);
extern void ixgbe_down(struct ixgbe_adapter *adapter);
extern void ixgbe_reinit_locked(struct ixgbe_adapter *adapter);
extern void ixgbe_reset(struct ixgbe_adapter *adapter);
diff --git a/drivers/net/ethernet/intel/ixgbe/ixgbe_main.c b/drivers/net/ethernet/intel/ixgbe/ixgbe_main.c
index 0283e12..df1ea20 100644
--- a/drivers/net/ethernet/intel/ixgbe/ixgbe_main.c
+++ b/drivers/net/ethernet/intel/ixgbe/ixgbe_main.c
@@ -3555,7 +3555,7 @@ static void ixgbe_setup_gpie(struct ixgbe_adapter *adapter)
IXGBE_WRITE_REG(hw, IXGBE_GPIE, gpie);
}
-static int ixgbe_up_complete(struct ixgbe_adapter *adapter)
+static void ixgbe_up_complete(struct ixgbe_adapter *adapter)
{
struct ixgbe_hw *hw = &adapter->hw;
int err;
@@ -3614,8 +3614,6 @@ static int ixgbe_up_complete(struct ixgbe_adapter *adapter)
ctrl_ext = IXGBE_READ_REG(hw, IXGBE_CTRL_EXT);
ctrl_ext |= IXGBE_CTRL_EXT_PFRSTD;
IXGBE_WRITE_REG(hw, IXGBE_CTRL_EXT, ctrl_ext);
-
- return 0;
}
void ixgbe_reinit_locked(struct ixgbe_adapter *adapter)
@@ -3639,12 +3637,12 @@ void ixgbe_reinit_locked(struct ixgbe_adapter *adapter)
clear_bit(__IXGBE_RESETTING, &adapter->state);
}
-int ixgbe_up(struct ixgbe_adapter *adapter)
+void ixgbe_up(struct ixgbe_adapter *adapter)
{
/* hardware has been reset, we need to reload some things */
ixgbe_configure(adapter);
- return ixgbe_up_complete(adapter);
+ ixgbe_up_complete(adapter);
}
void ixgbe_reset(struct ixgbe_adapter *adapter)
@@ -5186,17 +5184,12 @@ static int ixgbe_open(struct net_device *netdev)
if (err)
goto err_req_irq;
- err = ixgbe_up_complete(adapter);
- if (err)
- goto err_up;
+ ixgbe_up_complete(adapter);
netif_tx_start_all_queues(netdev);
return 0;
-err_up:
- ixgbe_release_hw_control(adapter);
- ixgbe_free_irq(adapter);
err_req_irq:
err_setup_rx:
ixgbe_free_all_rx_resources(adapter);
@@ -7653,12 +7646,8 @@ static void ixgbe_io_resume(struct pci_dev *pdev)
struct ixgbe_adapter *adapter = pci_get_drvdata(pdev);
struct net_device *netdev = adapter->netdev;
- if (netif_running(netdev)) {
- if (ixgbe_up(adapter)) {
- e_info(probe, "ixgbe_up failed after reset\n");
- return;
- }
- }
+ if (netif_running(netdev))
+ ixgbe_up(adapter);
netif_device_attach(netdev);
}
--
1.7.6
^ permalink raw reply related
* [net-next 05/11] ixgbe: Add missing code for enabling overheat sensor interrupt
From: Jeff Kirsher @ 2011-09-17 2:15 UTC (permalink / raw)
To: davem; +Cc: Alexander Duyck, netdev, gospo, Jeff Kirsher
In-Reply-To: <1316225752-1709-1-git-send-email-jeffrey.t.kirsher@intel.com>
From: Alexander Duyck <alexander.h.duyck@intel.com>
This change adds a small bit of missing code for enabling the overheat sensor
Signed-off-by: Alexander Duyck <alexander.h.duyck@intel.com>
Signed-off-by: Jeff Kirsher <jeffrey.t.kirsher@intel.com>
---
drivers/net/ethernet/intel/ixgbe/ixgbe_main.c | 4 ++++
1 files changed, 4 insertions(+), 0 deletions(-)
diff --git a/drivers/net/ethernet/intel/ixgbe/ixgbe_main.c b/drivers/net/ethernet/intel/ixgbe/ixgbe_main.c
index df1ea20..0533bc4 100644
--- a/drivers/net/ethernet/intel/ixgbe/ixgbe_main.c
+++ b/drivers/net/ethernet/intel/ixgbe/ixgbe_main.c
@@ -3543,6 +3543,10 @@ static void ixgbe_setup_gpie(struct ixgbe_adapter *adapter)
gpie |= IXGBE_GPIE_VTMODE_64;
}
+ /* Enable Thermal over heat sensor interrupt */
+ if (adapter->flags2 & IXGBE_FLAG2_TEMP_SENSOR_CAPABLE)
+ gpie |= IXGBE_SDP0_GPIEN;
+
/* Enable fan failure interrupt */
if (adapter->flags & IXGBE_FLAG_FAN_FAIL_CAPABLE)
gpie |= IXGBE_SDP1_GPIEN;
--
1.7.6
^ permalink raw reply related
* [net-next 06/11] ixgbe: Add SFP support for missed 82598 PHY
From: Jeff Kirsher @ 2011-09-17 2:15 UTC (permalink / raw)
To: davem; +Cc: Alexander Duyck, netdev, gospo, Jeff Kirsher
In-Reply-To: <1316225752-1709-1-git-send-email-jeffrey.t.kirsher@intel.com>
From: Alexander Duyck <alexander.h.duyck@intel.com>
One of the 82598 phys was not being correctly identified as being SFP.
This change corrects that.
Signed-off-by: Alexander Duyck <alexander.h.duyck@intel.com>
Tested-by: Phil Schmitt <phillip.j.schmitt@intel.com>
Signed-off-by: Jeff Kirsher <jeffrey.t.kirsher@intel.com>
---
drivers/net/ethernet/intel/ixgbe/ixgbe_main.c | 3 +++
1 files changed, 3 insertions(+), 0 deletions(-)
diff --git a/drivers/net/ethernet/intel/ixgbe/ixgbe_main.c b/drivers/net/ethernet/intel/ixgbe/ixgbe_main.c
index 0533bc4..ce59dc6 100644
--- a/drivers/net/ethernet/intel/ixgbe/ixgbe_main.c
+++ b/drivers/net/ethernet/intel/ixgbe/ixgbe_main.c
@@ -3451,6 +3451,9 @@ static inline bool ixgbe_is_sfp(struct ixgbe_hw *hw)
case ixgbe_phy_sfp_active_unknown:
case ixgbe_phy_sfp_ftl_active:
return true;
+ case ixgbe_phy_nl:
+ if (hw->mac.type == ixgbe_mac_82598EB)
+ return true;
default:
return false;
}
--
1.7.6
^ permalink raw reply related
* [net-next 07/11] ixgbe: drop adapter from ixgbe_fso call documentation
From: Jeff Kirsher @ 2011-09-17 2:15 UTC (permalink / raw)
To: davem; +Cc: Alexander Duyck, netdev, gospo, Jeff Kirsher
In-Reply-To: <1316225752-1709-1-git-send-email-jeffrey.t.kirsher@intel.com>
From: Alexander Duyck <alexander.h.duyck@intel.com>
The adapter structure was removed from the call so it can be dropped from
the ixgbe_fso documentation.
Signed-off-by: Alexander Duyck <alexander.h.duyck@intel.com>
Tested-by: Ross Brattain <ross.b.brattain@intel.com>
Signed-off-by: Jeff Kirsher <jeffrey.t.kirsher@intel.com>
---
drivers/net/ethernet/intel/ixgbe/ixgbe_fcoe.c | 1 -
1 files changed, 0 insertions(+), 1 deletions(-)
diff --git a/drivers/net/ethernet/intel/ixgbe/ixgbe_fcoe.c b/drivers/net/ethernet/intel/ixgbe/ixgbe_fcoe.c
index e9b992f..cae766d 100644
--- a/drivers/net/ethernet/intel/ixgbe/ixgbe_fcoe.c
+++ b/drivers/net/ethernet/intel/ixgbe/ixgbe_fcoe.c
@@ -440,7 +440,6 @@ ddp_out:
/**
* ixgbe_fso - ixgbe FCoE Sequence Offload (FSO)
- * @adapter: ixgbe adapter
* @tx_ring: tx desc ring
* @skb: associated skb
* @tx_flags: tx flags
--
1.7.6
^ permalink raw reply related
* [net-next 08/11] ixgbe: Make better use of memory allocations in one-buffer mode w/ RSC
From: Jeff Kirsher @ 2011-09-17 2:15 UTC (permalink / raw)
To: davem; +Cc: Alexander Duyck, netdev, gospo, Jeff Kirsher
In-Reply-To: <1316225752-1709-1-git-send-email-jeffrey.t.kirsher@intel.com>
From: Alexander Duyck <alexander.h.duyck@intel.com>
This patch improves the memory utilization with RSC when in one-buffer
mode. This is accomplished by making the default buffer sizes match up
with the standard memory allocation sizes minus 1K for shared info and
padding overhead. By doing this CPU utilization when doing large receives
can be reduced by as much as 8%.
Signed-off-by: Alexander Duyck <alexander.h.duyck@intel.com>
Tested-by: Phil Schmitt <phillip.j.schmitt@intel.com>
Signed-off-by: Jeff Kirsher <jeffrey.t.kirsher@intel.com>
---
drivers/net/ethernet/intel/ixgbe/ixgbe.h | 11 ++++--
drivers/net/ethernet/intel/ixgbe/ixgbe_ethtool.c | 2 +-
drivers/net/ethernet/intel/ixgbe/ixgbe_main.c | 41 ++++++++++++++-------
3 files changed, 35 insertions(+), 19 deletions(-)
diff --git a/drivers/net/ethernet/intel/ixgbe/ixgbe.h b/drivers/net/ethernet/intel/ixgbe/ixgbe.h
index 209286c..2c9fdf8 100644
--- a/drivers/net/ethernet/intel/ixgbe/ixgbe.h
+++ b/drivers/net/ethernet/intel/ixgbe/ixgbe.h
@@ -72,10 +72,13 @@
/* Supported Rx Buffer Sizes */
#define IXGBE_RXBUFFER_512 512 /* Used for packet split */
-#define IXGBE_RXBUFFER_2048 2048
-#define IXGBE_RXBUFFER_4096 4096
-#define IXGBE_RXBUFFER_8192 8192
-#define IXGBE_MAX_RXBUFFER 16384 /* largest size for a single descriptor */
+#define IXGBE_RXBUFFER_2K 2048
+#define IXGBE_RXBUFFER_3K 3072
+#define IXGBE_RXBUFFER_4K 4096
+#define IXGBE_RXBUFFER_7K 7168
+#define IXGBE_RXBUFFER_8K 8192
+#define IXGBE_RXBUFFER_15K 15360
+#define IXGBE_MAX_RXBUFFER 16384 /* largest size for a single descriptor */
/*
* NOTE: netdev_alloc_skb reserves up to 64 bytes, NET_IP_ALIGN mans we
diff --git a/drivers/net/ethernet/intel/ixgbe/ixgbe_ethtool.c b/drivers/net/ethernet/intel/ixgbe/ixgbe_ethtool.c
index b8410bc..46f4ecf 100644
--- a/drivers/net/ethernet/intel/ixgbe/ixgbe_ethtool.c
+++ b/drivers/net/ethernet/intel/ixgbe/ixgbe_ethtool.c
@@ -1539,7 +1539,7 @@ static int ixgbe_setup_desc_rings(struct ixgbe_adapter *adapter)
rx_ring->dev = &adapter->pdev->dev;
rx_ring->netdev = adapter->netdev;
rx_ring->reg_idx = adapter->rx_ring[0]->reg_idx;
- rx_ring->rx_buf_len = IXGBE_RXBUFFER_2048;
+ rx_ring->rx_buf_len = IXGBE_RXBUFFER_2K;
rx_ring->numa_node = adapter->node;
err = ixgbe_setup_rx_resources(rx_ring);
diff --git a/drivers/net/ethernet/intel/ixgbe/ixgbe_main.c b/drivers/net/ethernet/intel/ixgbe/ixgbe_main.c
index ce59dc6..a4103ef 100644
--- a/drivers/net/ethernet/intel/ixgbe/ixgbe_main.c
+++ b/drivers/net/ethernet/intel/ixgbe/ixgbe_main.c
@@ -499,7 +499,7 @@ rx_ring_summary:
rx_ring->rx_buf_len, true);
if (rx_ring->rx_buf_len
- < IXGBE_RXBUFFER_2048)
+ < IXGBE_RXBUFFER_2K)
print_hex_dump(KERN_INFO, "",
DUMP_PREFIX_ADDRESS, 16, 1,
phys_to_virt(
@@ -2644,9 +2644,9 @@ static void ixgbe_configure_rscctl(struct ixgbe_adapter *adapter,
rscctrl |= IXGBE_RSCCTL_MAXDESC_1;
#endif
} else {
- if (rx_buf_len < IXGBE_RXBUFFER_4096)
+ if (rx_buf_len < IXGBE_RXBUFFER_4K)
rscctrl |= IXGBE_RSCCTL_MAXDESC_16;
- else if (rx_buf_len < IXGBE_RXBUFFER_8192)
+ else if (rx_buf_len < IXGBE_RXBUFFER_8K)
rscctrl |= IXGBE_RSCCTL_MAXDESC_8;
else
rscctrl |= IXGBE_RSCCTL_MAXDESC_4;
@@ -2879,17 +2879,6 @@ static void ixgbe_set_rx_buffer_len(struct ixgbe_adapter *adapter)
if (hw->mac.type == ixgbe_mac_82599EB)
adapter->flags &= ~IXGBE_FLAG_RX_PS_ENABLED;
- /* Set the RX buffer length according to the mode */
- if (adapter->flags & IXGBE_FLAG_RX_PS_ENABLED) {
- rx_buf_len = IXGBE_RX_HDR_SIZE;
- } else {
- if (!(adapter->flags2 & IXGBE_FLAG2_RSC_ENABLED) &&
- (netdev->mtu <= ETH_DATA_LEN))
- rx_buf_len = MAXIMUM_ETHERNET_VLAN_SIZE;
- else
- rx_buf_len = ALIGN(max_frame + VLAN_HLEN, 1024);
- }
-
#ifdef IXGBE_FCOE
/* adjust max frame to be able to do baby jumbo for FCoE */
if ((adapter->flags & IXGBE_FLAG_FCOE_ENABLED) &&
@@ -2905,6 +2894,30 @@ static void ixgbe_set_rx_buffer_len(struct ixgbe_adapter *adapter)
IXGBE_WRITE_REG(hw, IXGBE_MHADD, mhadd);
}
+ /* MHADD will allow an extra 4 bytes past for vlan tagged frames */
+ max_frame += VLAN_HLEN;
+
+ /* Set the RX buffer length according to the mode */
+ if (adapter->flags & IXGBE_FLAG_RX_PS_ENABLED) {
+ rx_buf_len = IXGBE_RX_HDR_SIZE;
+ } else {
+ if (!(adapter->flags2 & IXGBE_FLAG2_RSC_ENABLED) &&
+ (netdev->mtu <= ETH_DATA_LEN))
+ rx_buf_len = MAXIMUM_ETHERNET_VLAN_SIZE;
+ /*
+ * Make best use of allocation by using all but 1K of a
+ * power of 2 allocation that will be used for skb->head.
+ */
+ else if (max_frame <= IXGBE_RXBUFFER_3K)
+ rx_buf_len = IXGBE_RXBUFFER_3K;
+ else if (max_frame <= IXGBE_RXBUFFER_7K)
+ rx_buf_len = IXGBE_RXBUFFER_7K;
+ else if (max_frame <= IXGBE_RXBUFFER_15K)
+ rx_buf_len = IXGBE_RXBUFFER_15K;
+ else
+ rx_buf_len = IXGBE_MAX_RXBUFFER;
+ }
+
hlreg0 = IXGBE_READ_REG(hw, IXGBE_HLREG0);
/* set jumbo enable since MHADD.MFS is keeping size locked at max_frame */
hlreg0 |= IXGBE_HLREG0_JUMBOEN;
--
1.7.6
^ permalink raw reply related
* [net-next 09/11] ixgbe: cleanup some register reads
From: Jeff Kirsher @ 2011-09-17 2:15 UTC (permalink / raw)
To: davem; +Cc: Emil Tantilov, netdev, gospo, Jonathan Lynch, Jeff Kirsher
In-Reply-To: <1316225752-1709-1-git-send-email-jeffrey.t.kirsher@intel.com>
From: Emil Tantilov <emil.s.tantilov@intel.com>
Remove duplicate inc of hwstats->ruc
Introduce separate loops for 8 and 16 register reads.
Consolidate mac checks under one case.
Make sure registers are cleared on read.
Reported-by: Jonathan Lynch <jonathan.lynch@thenowfactory.com>
Signed-off-by: Emil Tantilov <emil.s.tantilov@intel.com>
CC: Jonathan Lynch <jonathan.lynch@thenowfactory.com>
Tested-by: Phil Schmitt <phillip.j.schmitt@intel.com>
Signed-off-by: Jeff Kirsher <jeffrey.t.kirsher@intel.com>
---
drivers/net/ethernet/intel/ixgbe/ixgbe_main.c | 30 +++++++++++++++++-------
1 files changed, 21 insertions(+), 9 deletions(-)
diff --git a/drivers/net/ethernet/intel/ixgbe/ixgbe_main.c b/drivers/net/ethernet/intel/ixgbe/ixgbe_main.c
index a4103ef..1e72c00 100644
--- a/drivers/net/ethernet/intel/ixgbe/ixgbe_main.c
+++ b/drivers/net/ethernet/intel/ixgbe/ixgbe_main.c
@@ -5463,20 +5463,21 @@ void ixgbe_update_stats(struct ixgbe_adapter *adapter)
netdev->stats.tx_packets = packets;
hwstats->crcerrs += IXGBE_READ_REG(hw, IXGBE_CRCERRS);
+
+ /* 8 register reads */
for (i = 0; i < 8; i++) {
/* for packet buffers not used, the register should read 0 */
mpc = IXGBE_READ_REG(hw, IXGBE_MPC(i));
missed_rx += mpc;
hwstats->mpc[i] += mpc;
total_mpc += hwstats->mpc[i];
- if (hw->mac.type == ixgbe_mac_82598EB)
- hwstats->rnbc[i] += IXGBE_READ_REG(hw, IXGBE_RNBC(i));
- hwstats->qptc[i] += IXGBE_READ_REG(hw, IXGBE_QPTC(i));
- hwstats->qbtc[i] += IXGBE_READ_REG(hw, IXGBE_QBTC(i));
- hwstats->qprc[i] += IXGBE_READ_REG(hw, IXGBE_QPRC(i));
- hwstats->qbrc[i] += IXGBE_READ_REG(hw, IXGBE_QBRC(i));
+ hwstats->pxontxc[i] += IXGBE_READ_REG(hw, IXGBE_PXONTXC(i));
+ hwstats->pxofftxc[i] += IXGBE_READ_REG(hw, IXGBE_PXOFFTXC(i));
switch (hw->mac.type) {
case ixgbe_mac_82598EB:
+ hwstats->rnbc[i] += IXGBE_READ_REG(hw, IXGBE_RNBC(i));
+ hwstats->qbtc[i] += IXGBE_READ_REG(hw, IXGBE_QBTC(i));
+ hwstats->qbrc[i] += IXGBE_READ_REG(hw, IXGBE_QBRC(i));
hwstats->pxonrxc[i] +=
IXGBE_READ_REG(hw, IXGBE_PXONRXC(i));
break;
@@ -5488,9 +5489,21 @@ void ixgbe_update_stats(struct ixgbe_adapter *adapter)
default:
break;
}
- hwstats->pxontxc[i] += IXGBE_READ_REG(hw, IXGBE_PXONTXC(i));
- hwstats->pxofftxc[i] += IXGBE_READ_REG(hw, IXGBE_PXOFFTXC(i));
}
+
+ /*16 register reads */
+ for (i = 0; i < 16; i++) {
+ hwstats->qptc[i] += IXGBE_READ_REG(hw, IXGBE_QPTC(i));
+ hwstats->qprc[i] += IXGBE_READ_REG(hw, IXGBE_QPRC(i));
+ if ((hw->mac.type == ixgbe_mac_82599EB) ||
+ (hw->mac.type == ixgbe_mac_X540)) {
+ hwstats->qbtc[i] += IXGBE_READ_REG(hw, IXGBE_QBTC_L(i));
+ IXGBE_READ_REG(hw, IXGBE_QBTC_H(i)); /* to clear */
+ hwstats->qbrc[i] += IXGBE_READ_REG(hw, IXGBE_QBRC_L(i));
+ IXGBE_READ_REG(hw, IXGBE_QBRC_H(i)); /* to clear */
+ }
+ }
+
hwstats->gprc += IXGBE_READ_REG(hw, IXGBE_GPRC);
/* work around hardware counting issue */
hwstats->gprc -= missed_rx;
@@ -5550,7 +5563,6 @@ void ixgbe_update_stats(struct ixgbe_adapter *adapter)
hwstats->lxontxc += lxon;
lxoff = IXGBE_READ_REG(hw, IXGBE_LXOFFTXC);
hwstats->lxofftxc += lxoff;
- hwstats->ruc += IXGBE_READ_REG(hw, IXGBE_RUC);
hwstats->gptc += IXGBE_READ_REG(hw, IXGBE_GPTC);
hwstats->mptc += IXGBE_READ_REG(hw, IXGBE_MPTC);
/*
--
1.7.6
^ permalink raw reply related
* [net-next 10/11] ixgbe: fix FCRTL/H register dump for X540
From: Jeff Kirsher @ 2011-09-17 2:15 UTC (permalink / raw)
To: davem; +Cc: Emil Tantilov, netdev, gospo, Jeff Kirsher
In-Reply-To: <1316225752-1709-1-git-send-email-jeffrey.t.kirsher@intel.com>
From: Emil Tantilov <emil.s.tantilov@intel.com>
Signed-off-by: Emil Tantilov <emil.s.tantilov@intel.com>
Tested-by: Phil Schmitt <phillip.j.schmitt@intel.com>
Signed-off-by: Jeff Kirsher <jeffrey.t.kirsher@intel.com>
---
drivers/net/ethernet/intel/ixgbe/ixgbe_ethtool.c | 1 +
1 files changed, 1 insertions(+), 0 deletions(-)
diff --git a/drivers/net/ethernet/intel/ixgbe/ixgbe_ethtool.c b/drivers/net/ethernet/intel/ixgbe/ixgbe_ethtool.c
index 46f4ecf..63cd2a1 100644
--- a/drivers/net/ethernet/intel/ixgbe/ixgbe_ethtool.c
+++ b/drivers/net/ethernet/intel/ixgbe/ixgbe_ethtool.c
@@ -529,6 +529,7 @@ static void ixgbe_get_regs(struct net_device *netdev,
regs_buff[43 + i] = IXGBE_READ_REG(hw, IXGBE_FCRTH(i));
break;
case ixgbe_mac_82599EB:
+ case ixgbe_mac_X540:
regs_buff[35 + i] = IXGBE_READ_REG(hw, IXGBE_FCRTL_82599(i));
regs_buff[43 + i] = IXGBE_READ_REG(hw, IXGBE_FCRTH_82599(i));
break;
--
1.7.6
^ permalink raw reply related
* [net-next 11/11] ixgbe: remove duplicate netif_tx_start_all_queues
From: Jeff Kirsher @ 2011-09-17 2:15 UTC (permalink / raw)
To: davem; +Cc: Emil Tantilov, netdev, gospo, Jeff Kirsher
In-Reply-To: <1316225752-1709-1-git-send-email-jeffrey.t.kirsher@intel.com>
From: Emil Tantilov <emil.s.tantilov@intel.com>
netif_tx_start_all_queues() is already called in ixgbe_up_complete, no need
to do it twice.
Signed-off-by: Emil Tantilov <emil.s.tantilov@intel.com>
Tested-by: Phil Schmitt <phillip.j.schmitt@intel.com>
Signed-off-by: Jeff Kirsher <jeffrey.t.kirsher@intel.com>
---
drivers/net/ethernet/intel/ixgbe/ixgbe_main.c | 2 --
1 files changed, 0 insertions(+), 2 deletions(-)
diff --git a/drivers/net/ethernet/intel/ixgbe/ixgbe_main.c b/drivers/net/ethernet/intel/ixgbe/ixgbe_main.c
index 1e72c00..49e82de 100644
--- a/drivers/net/ethernet/intel/ixgbe/ixgbe_main.c
+++ b/drivers/net/ethernet/intel/ixgbe/ixgbe_main.c
@@ -5206,8 +5206,6 @@ static int ixgbe_open(struct net_device *netdev)
ixgbe_up_complete(adapter);
- netif_tx_start_all_queues(netdev);
-
return 0;
err_req_irq:
--
1.7.6
^ permalink raw reply related
* Re: [net-next 01/11] ixgb: convert to ndo_fix_features
From: Joe Perches @ 2011-09-17 2:50 UTC (permalink / raw)
To: Jeff Kirsher; +Cc: davem, Michał Mirosław, netdev, gospo
In-Reply-To: <1316225752-1709-2-git-send-email-jeffrey.t.kirsher@intel.com>
On Fri, 2011-09-16 at 19:15 -0700, Jeff Kirsher wrote:
> Private rx_csum flags are now duplicate of netdev->features & NETIF_F_RXCSUM.
> Removing this needs deeper surgery.
> diff --git a/drivers/net/ethernet/intel/ixgb/ixgb_main.c b/drivers/net/ethernet/intel/ixgb/ixgb_main.c
[]
> @@ -439,12 +462,14 @@ ixgb_probe(struct pci_dev *pdev, const struct pci_device_id *ent)
> if (err)
> goto err_sw_init;
>
> - netdev->features = NETIF_F_SG |
> - NETIF_F_HW_CSUM |
> + netdev->hw_features = NETIF_F_SG |
> + NETIF_F_TSO |
> + NETIF_F_HW_CSUM;
> + netdev->features = netdev->hw_features |
> NETIF_F_HW_VLAN_TX |
> NETIF_F_HW_VLAN_RX |
> NETIF_F_HW_VLAN_FILTER;
> - netdev->features |= NETIF_F_TSO;
> + netdev->hw_features |= NETIF_F_RXCSUM;
Is there any real reason to do this?
It looks overly complicated for no benefit.
Why not just use something like:
netdev->hw_features = foo;
netdev->features = bar;
or maybe use #defines like:
#define FEATURES_DEFAULT (NETIF_F_NETIF_F_SG | NETIF_F_TSO | NETIF_F_HW_CSUM)
#define FEATURES_HW_VLAN (NETIF_F_HW_VLAN_TX | NETIF_F_HW_VLAN_RX | NETIF_F_HW_VLAN_FILTER)
and
netdev->features = FEATURES_DEFAULT | FEATURES_HW_VLAN;
netdev->hw_features = FEATURES_DEFAULT | NETIF_F_RXCSUM;
^ permalink raw reply
* Re: [PATCH] sctp: deal with multiple COOKIE_ECHO chunks
From: Max Matveev @ 2011-09-17 4:38 UTC (permalink / raw)
To: David Miller; +Cc: linux-sctp, netdev, vladislav.yasevich
In-Reply-To: <20110916.171747.406895441960738806.davem@davemloft.net>
On Fri, 16 Sep 2011 17:17:47 -0400 (EDT), David Miller wrote:
davem> From: Max Matveev <makc@redhat.com>
davem> Date: Tue, 30 Aug 2011 17:02:24 +1000
>> Attempt to reduce the number of IP packets emitted in response to single
>> SCTP packet (2e3216cd) introduced a complication - if a packet contains
>> two COOKIE_ECHO chunks and nothing else then SCTP state machine corks the
>> socket while processing first COOKIE_ECHO and then loses the association
>> and forgets to uncork the socket. To deal with the issue add new SCTP
>> command which can be used to set association explictly. Use this new
>> command when processing second COOKIE_ECHO chunk to restore the context
>> for SCTP state machine.
>>
>> Signed-off-by: Max Matveev <makc@redhat.com>
davem> Applied, but there were a ton of whitespace errors that GIT complained
davem> about and I had to fix up.
Sorry about it - I did check it with checkpatch.pl and it was happy:
must've been the mailer.
max
^ permalink raw reply
* Re: [net-next 1/3] bna: Semaphore Lock Fix
From: David Miller @ 2011-09-17 4:48 UTC (permalink / raw)
To: rmody; +Cc: netdev, adapter_linux_open_src_team, gkaraje
In-Reply-To: <1316221608-21392-1-git-send-email-rmody@brocade.com>
From: Rasesh Mody <rmody@brocade.com>
Date: Fri, 16 Sep 2011 18:06:46 -0700
> Remove a BUG_ON() as it is not required.
>
> Change the unconditional write to release a semaphore to read sem first
> and then write. This will eliminate the possibility of sem getting locked
> while trying to release it in case if previous sem_get operation failed.
>
> Signed-off-by: Gurunatha Karaje <gkaraje@brocade.com>
> Signed-off-by: Rasesh Mody <rmody@brocade.com>
Applied.
^ permalink raw reply
* Re: [net-next 2/3] bna: Set Ring Param Fix
From: David Miller @ 2011-09-17 4:48 UTC (permalink / raw)
To: rmody; +Cc: netdev, adapter_linux_open_src_team, gkaraje
In-Reply-To: <1316221608-21392-2-git-send-email-rmody@brocade.com>
From: Rasesh Mody <rmody@brocade.com>
Date: Fri, 16 Sep 2011 18:06:47 -0700
> When Rx queue size is changed, queues are torn down and setup with the new queue
> size. During this operation, clear promiscuous mode and restore the original
> VLAN filter.
>
> Signed-off-by: Gurunatha Karaje <gkaraje@brocade.com>
> Signed-off-by: Rasesh Mody <rmody@brocade.com>
Applied.
^ permalink raw reply
* Re: [net-next 3/3] bna: Eliminate Small Race Condition Window in RX Path
From: David Miller @ 2011-09-17 4:48 UTC (permalink / raw)
To: rmody; +Cc: netdev, adapter_linux_open_src_team, gkaraje
In-Reply-To: <1316221608-21392-3-git-send-email-rmody@brocade.com>
From: Rasesh Mody <rmody@brocade.com>
Date: Fri, 16 Sep 2011 18:06:48 -0700
> Change details:
> - In a continuous sequence of ifconfig up/down operations, there is a small
> window of race between bnad_set_rx_mode() and bnad_cleanup_rx() while the
> former tries to access rx_info->rx & the latter sets it to NULL. This race
> could lead to bna_rx_mode_set() being called with a NULL (rx_info->rx)
> pointer and a crash.
> - Hold bnad->bna_lock while setting / unsetting rx_info->rx in bnad_setup_rx()
> & bnad_cleanup_rx(), thereby eliminating the race described above.
>
> Signed-off-by: Gurunatha Karaje <gkaraje@brocade.com>
> Signed-off-by: Rasesh Mody <rmody@brocade.com>
Applied.
^ permalink raw reply
* Re: [PATCH] ipv6: don't use inetpeer to store metrics for routes.
From: David Miller @ 2011-09-17 4:57 UTC (permalink / raw)
To: zheng.z.yan; +Cc: netdev, eric.dumazet
In-Reply-To: <4E65CD06.2080903@intel.com>
From: "Yan, Zheng" <zheng.z.yan@intel.com>
Date: Tue, 06 Sep 2011 15:34:30 +0800
> Current IPv6 implementation uses inetpeer to store metrics for
> routes. The problem of inetpeer is that it doesn't take subnet
> prefix length in to consideration. If two routes have the same
> address but different prefix length, they share same inetpeer.
> So changing metrics of one route also affects the other. The
> fix is to allocate separate metrics storage for each route.
>
> Signed-off-by: Zheng Yan <zheng.z.yan@intel.com>
Applied, thanks for fixing this bug.
^ permalink raw reply
* Re: [PATCH] sctp: deal with multiple COOKIE_ECHO chunks
From: David Miller @ 2011-09-17 5:02 UTC (permalink / raw)
To: makc; +Cc: linux-sctp, netdev, vladislav.yasevich
In-Reply-To: <20084.9283.714998.398630@regina.usersys.redhat.com>
From: Max Matveev <makc@redhat.com>
Date: Sat, 17 Sep 2011 14:38:27 +1000
> Sorry about it - I did check it with checkpatch.pl and it was happy:
checkpatch doesn't look thoroughly for these things, use
something like "git apply --check --whitespace=error-all"
for validation instead.
^ permalink raw reply
* Re: [PATCH net-next] tcp: md5: remove one indirection level in tcp_md5sig_pool
From: David Miller @ 2011-09-17 5:15 UTC (permalink / raw)
To: eric.dumazet; +Cc: netdev
In-Reply-To: <1315895317.2556.28.camel@edumazet-laptop>
From: Eric Dumazet <eric.dumazet@gmail.com>
Date: Tue, 13 Sep 2011 08:28:37 +0200
> tcp_md5sig_pool is currently an 'array' (a percpu object) of pointers to
> struct tcp_md5sig_pool. Only the pointers are NUMA aware, but objects
> themselves are all allocated on a single node.
>
> Remove this extra indirection to get proper percpu memory (NUMA aware)
> and make code simpler.
>
> Signed-off-by: Eric Dumazet <eric.dumazet@gmail.com>
Applied, thanks.
^ permalink raw reply
* Re: [PATCH RFC 0/11] netlink: memory mapped I/O
From: David Miller @ 2011-09-17 5:48 UTC (permalink / raw)
To: kaber; +Cc: netfilter-devel, netdev
In-Reply-To: <1315070771-18576-1-git-send-email-kaber@trash.net>
From: kaber@trash.net
Date: Sat, 3 Sep 2011 19:26:00 +0200
> Comments and rewiew highly welcome!
Looks great to me, I look forward to integrating the final version
of this stuff.
^ permalink raw reply
* [net-next RFC V2 PATCH 0/5] Multiqueue support in tun/tap
From: Jason Wang @ 2011-09-17 6:02 UTC (permalink / raw)
To: krkumar2, eric.dumazet, mst, netdev, linux-kernel, virtualization,
davem
Cc: kvm, rusty, qemu-devel, mirq-linux, joe, shemminger
Hello all:
This series brings the V2 of multiqueue tun/tap (V1 in
http://www.mail-archive.com/kvm@vger.kernel.org/msg59479.html), an
approach to let tun/tap can benefit from the multicore/multiqueue
environment by spreading the network loads into differnet
sockets/queues.
Some quick overview of the design:
- Allowing multiple sockets to be attached to a tun/tap devices.
- Use RCU to synchronize the data path and system call
- A simple hash based queue selecting algorithm is used to choose the
tx queue.
- Two new ioctls were added for the usespace to attach and detach
socket to the device.
- ABI compatibility were maintained, and multiqueue is only enabled
for tap as kvm is the only user as far as I can see. But it maybe used
by tun also.
In order to use the multiqueue virio-net in guest, changes of qemu and
guest driver are also needed. Please refer
http://www.spinics.net/lists/kvm/msg52808.html for guest drivers
http://www.spinics.net/lists/kvm/msg52808.html and qemu changes.
I would also post the a new version of qemu changes soon.
A wiki-page was created to narrate the detail design of all parts
involved in the multi queue implementation:
http://www.linux-kvm.org/page/Multiqueue and some basic tests result
could be seen in this page
http://www.linux-kvm.org/page/Multiqueue-performance-Sep-13. I would
post the detail numbers in attachment as the reply of this thread.
Changes from V1:
1 Simplify the sockets array management by not leaving NULL in the
slot.
2 Optimization on the tx queue selecting.
3 Fix the bug in tun_deatch_all()
Some notes on the test result:
The results shows a very well scale for guest receiving and large
packets sending, but met some regressions at specific conditions:
1 Current implementation suffers from the regression of multiple
sessions of small packet transmission from guest, this regression
becomes severs when test it between localhost and guest.
>From the test result, we can see more pio exit were measured, the
reason is the small number of co-current sessions may not even
overload a single queue and may brings extra overhead when using
multiple queues. When we are trying to use multiple connections to
transmit small packets through single queue, the queue is almost full
and vhost thread is busy with tx. So guest have more chances to met a
notification disabled tx queue when it want to transmit packets (high
number of tx packets per pio exit). But when we transmit packets
through multiple queue, each queue is not fully utilized and so guest
have less chance to see a notification disabled queue when
transmitting packets, so more pio_exits and more vhost thread
wakup/sleep were found.
As Michael point out, other feature such as PLE may also have help in
the performance, when we are using single queue, multiple guest vcpus
may contend on the tx lock which may be captured by PLE and save the
cpu utilization. But multiple queue can not benefit from it as it
could get lees lock contention.
The solution for this still needs to be investigated, any suggestions
are welcomed.
2 Current implementation may also get regression for single session
packet transmission.
The reason is packets from each flow were not handled by the same
queue/vhost thread.
Various method could be done to handle this:
2.1 hack the guest driver, and store the queue index into the rxhash and
use it when choosing tx in guest. This need some hack to store the
rxhash into sk and pass it in to skb again in
skb_orphan_try(). sk_rxhash is only used by RPS now, so some more
clean method is needed.
2.2 hack the tun/tap, add a hash to queue table, and use the hash of the
skb to store the queue index. This method would introduce more
overhead and the rxhash would be calculated during each skb reception
or transmission.
I've tried both 1 and 2, both of them could solve the problem, but
both of it may introduces regression for multiple sessions. More
reasonable method is needed.
Please comment, thanks. Any suggestions are welcomed.
---
Jason Wang (5):
tuntap: move socket to tun_file
tuntap: categorize ioctl
tuntap: introduce multiqueue flags
tuntap: multiqueue support
tuntap: add ioctls to attach or detach a file form tap device
drivers/net/tun.c | 718 ++++++++++++++++++++++++++++--------------------
include/linux/if_tun.h | 5
2 files changed, 430 insertions(+), 293 deletions(-)
--
Jason Wang
^ permalink raw reply
* [net-next RFC V2 PATCH 1/5] tuntap: move socket to tun_file
From: Jason Wang @ 2011-09-17 6:02 UTC (permalink / raw)
To: krkumar2, eric.dumazet, mst, netdev, linux-kernel, virtualization,
davem
Cc: kvm, rusty, qemu-devel, mirq-linux, joe, shemminger
In-Reply-To: <20110917055639.32666.89940.stgit@dhcp-91-7.nay.redhat.com.englab.nay.redhat.com>
In order to let tap can transmit skbs to multiple sockets, the first
step is to move socket from tun_device to tun_file. The reference
between tap device and socket was setup during TUNSETIFF as
usual. After this we can go ahead to allow multiple files to be
attached to tap device.
Signed-off-by: Jason Wang <jasowang@redhat.com>
---
drivers/net/tun.c | 347 +++++++++++++++++++++++++++--------------------------
1 files changed, 178 insertions(+), 169 deletions(-)
diff --git a/drivers/net/tun.c b/drivers/net/tun.c
index 7bea9c6..b64ad05 100644
--- a/drivers/net/tun.c
+++ b/drivers/net/tun.c
@@ -109,9 +109,16 @@ struct tap_filter {
};
struct tun_file {
+ struct sock sk;
+ struct socket socket;
+ struct socket_wq wq;
+ int vnet_hdr_sz;
+ struct tap_filter txflt;
atomic_t count;
struct tun_struct *tun;
struct net *net;
+ struct fasync_struct *fasync;
+ unsigned int flags;
};
struct tun_sock;
@@ -126,29 +133,12 @@ struct tun_struct {
u32 set_features;
#define TUN_USER_FEATURES (NETIF_F_HW_CSUM|NETIF_F_TSO_ECN|NETIF_F_TSO| \
NETIF_F_TSO6|NETIF_F_UFO)
- struct fasync_struct *fasync;
-
- struct tap_filter txflt;
- struct socket socket;
- struct socket_wq wq;
-
- int vnet_hdr_sz;
#ifdef TUN_DEBUG
int debug;
#endif
};
-struct tun_sock {
- struct sock sk;
- struct tun_struct *tun;
-};
-
-static inline struct tun_sock *tun_sk(struct sock *sk)
-{
- return container_of(sk, struct tun_sock, sk);
-}
-
static int tun_attach(struct tun_struct *tun, struct file *file)
{
struct tun_file *tfile = file->private_data;
@@ -169,10 +159,9 @@ static int tun_attach(struct tun_struct *tun, struct file *file)
err = 0;
tfile->tun = tun;
tun->tfile = tfile;
- tun->socket.file = file;
netif_carrier_on(tun->dev);
dev_hold(tun->dev);
- sock_hold(tun->socket.sk);
+ sock_hold(&tfile->sk);
atomic_inc(&tfile->count);
out:
@@ -182,15 +171,15 @@ out:
static void __tun_detach(struct tun_struct *tun)
{
+ struct tun_file *tfile = tun->tfile;
/* Detach from net device */
netif_tx_lock_bh(tun->dev);
netif_carrier_off(tun->dev);
tun->tfile = NULL;
- tun->socket.file = NULL;
netif_tx_unlock_bh(tun->dev);
/* Drop read queue */
- skb_queue_purge(&tun->socket.sk->sk_receive_queue);
+ skb_queue_purge(&tfile->socket.sk->sk_receive_queue);
/* Drop the extra count on the net device */
dev_put(tun->dev);
@@ -349,19 +338,12 @@ static void tun_net_uninit(struct net_device *dev)
/* Inform the methods they need to stop using the dev.
*/
if (tfile) {
- wake_up_all(&tun->wq.wait);
+ wake_up_all(&tfile->wq.wait);
if (atomic_dec_and_test(&tfile->count))
__tun_detach(tun);
}
}
-static void tun_free_netdev(struct net_device *dev)
-{
- struct tun_struct *tun = netdev_priv(dev);
-
- sock_put(tun->socket.sk);
-}
-
/* Net device open. */
static int tun_net_open(struct net_device *dev)
{
@@ -380,24 +362,25 @@ static int tun_net_close(struct net_device *dev)
static netdev_tx_t tun_net_xmit(struct sk_buff *skb, struct net_device *dev)
{
struct tun_struct *tun = netdev_priv(dev);
+ struct tun_file *tfile = tun->tfile;
tun_debug(KERN_INFO, tun, "tun_net_xmit %d\n", skb->len);
/* Drop packet if interface is not attached */
- if (!tun->tfile)
+ if (!tfile)
goto drop;
/* Drop if the filter does not like it.
* This is a noop if the filter is disabled.
* Filter can be enabled only for the TAP devices. */
- if (!check_filter(&tun->txflt, skb))
+ if (!check_filter(&tfile->txflt, skb))
goto drop;
- if (tun->socket.sk->sk_filter &&
- sk_filter(tun->socket.sk, skb))
+ if (tfile->socket.sk->sk_filter &&
+ sk_filter(tfile->socket.sk, skb))
goto drop;
- if (skb_queue_len(&tun->socket.sk->sk_receive_queue) >= dev->tx_queue_len) {
+ if (skb_queue_len(&tfile->socket.sk->sk_receive_queue) >= dev->tx_queue_len) {
if (!(tun->flags & TUN_ONE_QUEUE)) {
/* Normal queueing mode. */
/* Packet scheduler handles dropping of further packets. */
@@ -418,12 +401,12 @@ static netdev_tx_t tun_net_xmit(struct sk_buff *skb, struct net_device *dev)
skb_orphan(skb);
/* Enqueue packet */
- skb_queue_tail(&tun->socket.sk->sk_receive_queue, skb);
+ skb_queue_tail(&tfile->socket.sk->sk_receive_queue, skb);
/* Notify and wake up reader process */
- if (tun->flags & TUN_FASYNC)
- kill_fasync(&tun->fasync, SIGIO, POLL_IN);
- wake_up_interruptible_poll(&tun->wq.wait, POLLIN |
+ if (tfile->flags & TUN_FASYNC)
+ kill_fasync(&tfile->fasync, SIGIO, POLL_IN);
+ wake_up_interruptible_poll(&tfile->wq.wait, POLLIN |
POLLRDNORM | POLLRDBAND);
return NETDEV_TX_OK;
@@ -550,11 +533,11 @@ static unsigned int tun_chr_poll(struct file *file, poll_table * wait)
if (!tun)
return POLLERR;
- sk = tun->socket.sk;
+ sk = tfile->socket.sk;
tun_debug(KERN_INFO, tun, "tun_chr_poll\n");
- poll_wait(file, &tun->wq.wait, wait);
+ poll_wait(file, &tfile->wq.wait, wait);
if (!skb_queue_empty(&sk->sk_receive_queue))
mask |= POLLIN | POLLRDNORM;
@@ -573,11 +556,11 @@ static unsigned int tun_chr_poll(struct file *file, poll_table * wait)
/* prepad is the amount to reserve at front. len is length after that.
* linear is a hint as to how much to copy (usually headers). */
-static struct sk_buff *tun_alloc_skb(struct tun_struct *tun,
+static struct sk_buff *tun_alloc_skb(struct tun_file *tfile,
size_t prepad, size_t len,
size_t linear, int noblock)
{
- struct sock *sk = tun->socket.sk;
+ struct sock *sk = tfile->socket.sk;
struct sk_buff *skb;
int err;
@@ -601,7 +584,7 @@ static struct sk_buff *tun_alloc_skb(struct tun_struct *tun,
}
/* Get packet from user space buffer */
-static ssize_t tun_get_user(struct tun_struct *tun,
+static ssize_t tun_get_user(struct tun_file *tfile,
const struct iovec *iv, size_t count,
int noblock)
{
@@ -610,8 +593,10 @@ static ssize_t tun_get_user(struct tun_struct *tun,
size_t len = count, align = NET_SKB_PAD;
struct virtio_net_hdr gso = { 0 };
int offset = 0;
+ struct tun_struct *tun = NULL;
+ bool drop = false, error = false;
- if (!(tun->flags & TUN_NO_PI)) {
+ if (!(tfile->flags & TUN_NO_PI)) {
if ((len -= sizeof(pi)) > count)
return -EINVAL;
@@ -620,8 +605,8 @@ static ssize_t tun_get_user(struct tun_struct *tun,
offset += sizeof(pi);
}
- if (tun->flags & TUN_VNET_HDR) {
- if ((len -= tun->vnet_hdr_sz) > count)
+ if (tfile->flags & TUN_VNET_HDR) {
+ if ((len -= tfile->vnet_hdr_sz) > count)
return -EINVAL;
if (memcpy_fromiovecend((void *)&gso, iv, offset, sizeof(gso)))
@@ -633,41 +618,43 @@ static ssize_t tun_get_user(struct tun_struct *tun,
if (gso.hdr_len > len)
return -EINVAL;
- offset += tun->vnet_hdr_sz;
+ offset += tfile->vnet_hdr_sz;
}
- if ((tun->flags & TUN_TYPE_MASK) == TUN_TAP_DEV) {
+ if ((tfile->flags & TUN_TYPE_MASK) == TUN_TAP_DEV) {
align += NET_IP_ALIGN;
if (unlikely(len < ETH_HLEN ||
(gso.hdr_len && gso.hdr_len < ETH_HLEN)))
return -EINVAL;
}
- skb = tun_alloc_skb(tun, align, len, gso.hdr_len, noblock);
+ skb = tun_alloc_skb(tfile, align, len, gso.hdr_len, noblock);
+
if (IS_ERR(skb)) {
if (PTR_ERR(skb) != -EAGAIN)
- tun->dev->stats.rx_dropped++;
- return PTR_ERR(skb);
+ drop = true;
+ count = PTR_ERR(skb);
+ goto err;
}
if (skb_copy_datagram_from_iovec(skb, 0, iv, offset, len)) {
- tun->dev->stats.rx_dropped++;
+ drop = true;
kfree_skb(skb);
- return -EFAULT;
+ count = -EFAULT;
+ goto err;
}
if (gso.flags & VIRTIO_NET_HDR_F_NEEDS_CSUM) {
if (!skb_partial_csum_set(skb, gso.csum_start,
gso.csum_offset)) {
- tun->dev->stats.rx_frame_errors++;
- kfree_skb(skb);
- return -EINVAL;
+ error = true;
+ goto err_free;
}
}
- switch (tun->flags & TUN_TYPE_MASK) {
+ switch (tfile->flags & TUN_TYPE_MASK) {
case TUN_TUN_DEV:
- if (tun->flags & TUN_NO_PI) {
+ if (tfile->flags & TUN_NO_PI) {
switch (skb->data[0] & 0xf0) {
case 0x40:
pi.proto = htons(ETH_P_IP);
@@ -676,18 +663,15 @@ static ssize_t tun_get_user(struct tun_struct *tun,
pi.proto = htons(ETH_P_IPV6);
break;
default:
- tun->dev->stats.rx_dropped++;
- kfree_skb(skb);
- return -EINVAL;
+ drop = true;
+ goto err_free;
}
}
skb_reset_mac_header(skb);
skb->protocol = pi.proto;
- skb->dev = tun->dev;
break;
case TUN_TAP_DEV:
- skb->protocol = eth_type_trans(skb, tun->dev);
break;
}
@@ -704,9 +688,8 @@ static ssize_t tun_get_user(struct tun_struct *tun,
skb_shinfo(skb)->gso_type = SKB_GSO_UDP;
break;
default:
- tun->dev->stats.rx_frame_errors++;
- kfree_skb(skb);
- return -EINVAL;
+ error = true;
+ goto err_free;
}
if (gso.gso_type & VIRTIO_NET_HDR_GSO_ECN)
@@ -714,9 +697,8 @@ static ssize_t tun_get_user(struct tun_struct *tun,
skb_shinfo(skb)->gso_size = gso.gso_size;
if (skb_shinfo(skb)->gso_size == 0) {
- tun->dev->stats.rx_frame_errors++;
- kfree_skb(skb);
- return -EINVAL;
+ error = true;
+ goto err_free;
}
/* Header must be checked, and gso_segs computed. */
@@ -724,11 +706,40 @@ static ssize_t tun_get_user(struct tun_struct *tun,
skb_shinfo(skb)->gso_segs = 0;
}
- netif_rx_ni(skb);
+ tun = __tun_get(tfile);
+ if (!tun) {
+ return -EBADFD;
+ }
+
+ switch (tfile->flags & TUN_TYPE_MASK) {
+ case TUN_TUN_DEV:
+ skb->dev = tun->dev;
+ break;
+ case TUN_TAP_DEV:
+ skb->protocol = eth_type_trans(skb, tun->dev);
+ break;
+ }
+ netif_rx_ni(skb);
tun->dev->stats.rx_packets++;
tun->dev->stats.rx_bytes += len;
+ tun_put(tun);
+ return count;
+err_free:
+ count = -EINVAL;
+ kfree_skb(skb);
+err:
+ tun = __tun_get(tfile);
+ if (!tun) {
+ return -EBADFD;
+ }
+
+ if (drop)
+ tun->dev->stats.rx_dropped++;
+ if (error)
+ tun->dev->stats.rx_frame_errors++;
+ tun_put(tun);
return count;
}
@@ -736,30 +747,25 @@ static ssize_t tun_chr_aio_write(struct kiocb *iocb, const struct iovec *iv,
unsigned long count, loff_t pos)
{
struct file *file = iocb->ki_filp;
- struct tun_struct *tun = tun_get(file);
+ struct tun_file *tfile = file->private_data;
ssize_t result;
- if (!tun)
- return -EBADFD;
-
- tun_debug(KERN_INFO, tun, "tun_chr_write %ld\n", count);
-
- result = tun_get_user(tun, iv, iov_length(iv, count),
+ result = tun_get_user(tfile, iv, iov_length(iv, count),
file->f_flags & O_NONBLOCK);
- tun_put(tun);
return result;
}
/* Put packet to the user space buffer */
-static ssize_t tun_put_user(struct tun_struct *tun,
+static ssize_t tun_put_user(struct tun_file *tfile,
struct sk_buff *skb,
const struct iovec *iv, int len)
{
+ struct tun_struct *tun = NULL;
struct tun_pi pi = { 0, skb->protocol };
ssize_t total = 0;
- if (!(tun->flags & TUN_NO_PI)) {
+ if (!(tfile->flags & TUN_NO_PI)) {
if ((len -= sizeof(pi)) < 0)
return -EINVAL;
@@ -773,9 +779,9 @@ static ssize_t tun_put_user(struct tun_struct *tun,
total += sizeof(pi);
}
- if (tun->flags & TUN_VNET_HDR) {
+ if (tfile->flags & TUN_VNET_HDR) {
struct virtio_net_hdr gso = { 0 }; /* no info leak */
- if ((len -= tun->vnet_hdr_sz) < 0)
+ if ((len -= tfile->vnet_hdr_sz) < 0)
return -EINVAL;
if (skb_is_gso(skb)) {
@@ -818,7 +824,7 @@ static ssize_t tun_put_user(struct tun_struct *tun,
if (unlikely(memcpy_toiovecend(iv, (void *)&gso, total,
sizeof(gso))))
return -EFAULT;
- total += tun->vnet_hdr_sz;
+ total += tfile->vnet_hdr_sz;
}
len = min_t(int, skb->len, len);
@@ -826,29 +832,32 @@ static ssize_t tun_put_user(struct tun_struct *tun,
skb_copy_datagram_const_iovec(skb, 0, iv, total, len);
total += skb->len;
- tun->dev->stats.tx_packets++;
- tun->dev->stats.tx_bytes += len;
+ tun = __tun_get(tfile);
+ if (tun) {
+ tun->dev->stats.tx_packets++;
+ tun->dev->stats.tx_bytes += len;
+ tun_put(tun);
+ }
return total;
}
-static ssize_t tun_do_read(struct tun_struct *tun,
+static ssize_t tun_do_read(struct tun_file *tfile,
struct kiocb *iocb, const struct iovec *iv,
ssize_t len, int noblock)
{
DECLARE_WAITQUEUE(wait, current);
struct sk_buff *skb;
ssize_t ret = 0;
-
- tun_debug(KERN_INFO, tun, "tun_chr_read\n");
+ struct tun_struct *tun = NULL;
if (unlikely(!noblock))
- add_wait_queue(&tun->wq.wait, &wait);
+ add_wait_queue(&tfile->wq.wait, &wait);
while (len) {
current->state = TASK_INTERRUPTIBLE;
/* Read frames from the queue */
- if (!(skb=skb_dequeue(&tun->socket.sk->sk_receive_queue))) {
+ if (!(skb=skb_dequeue(&tfile->socket.sk->sk_receive_queue))) {
if (noblock) {
ret = -EAGAIN;
break;
@@ -857,25 +866,38 @@ static ssize_t tun_do_read(struct tun_struct *tun,
ret = -ERESTARTSYS;
break;
}
+
+ tun = __tun_get(tfile);
+ if (!tun) {
+ ret = -EIO;
+ break;
+ }
if (tun->dev->reg_state != NETREG_REGISTERED) {
ret = -EIO;
+ tun_put(tun);
break;
}
+ tun_put(tun);
/* Nothing to read, let's sleep */
schedule();
continue;
}
- netif_wake_queue(tun->dev);
- ret = tun_put_user(tun, skb, iv, len);
+ tun = __tun_get(tfile);
+ if (tun) {
+ netif_wake_queue(tun->dev);
+ tun_put(tun);
+ }
+
+ ret = tun_put_user(tfile, skb, iv, len);
kfree_skb(skb);
break;
}
current->state = TASK_RUNNING;
if (unlikely(!noblock))
- remove_wait_queue(&tun->wq.wait, &wait);
+ remove_wait_queue(&tfile->wq.wait, &wait);
return ret;
}
@@ -885,21 +907,17 @@ static ssize_t tun_chr_aio_read(struct kiocb *iocb, const struct iovec *iv,
{
struct file *file = iocb->ki_filp;
struct tun_file *tfile = file->private_data;
- struct tun_struct *tun = __tun_get(tfile);
ssize_t len, ret;
- if (!tun)
- return -EBADFD;
len = iov_length(iv, count);
if (len < 0) {
ret = -EINVAL;
goto out;
}
- ret = tun_do_read(tun, iocb, iv, len, file->f_flags & O_NONBLOCK);
+ ret = tun_do_read(tfile, iocb, iv, len, file->f_flags & O_NONBLOCK);
ret = min_t(ssize_t, ret, len);
out:
- tun_put(tun);
return ret;
}
@@ -911,7 +929,7 @@ static void tun_setup(struct net_device *dev)
tun->group = -1;
dev->ethtool_ops = &tun_ethtool_ops;
- dev->destructor = tun_free_netdev;
+ dev->destructor = free_netdev;
}
/* Trivial set of netlink ops to allow deleting tun or tap
@@ -931,7 +949,7 @@ static struct rtnl_link_ops tun_link_ops __read_mostly = {
static void tun_sock_write_space(struct sock *sk)
{
- struct tun_struct *tun;
+ struct tun_file *tfile = NULL;
wait_queue_head_t *wqueue;
if (!sock_writeable(sk))
@@ -945,37 +963,38 @@ static void tun_sock_write_space(struct sock *sk)
wake_up_interruptible_sync_poll(wqueue, POLLOUT |
POLLWRNORM | POLLWRBAND);
- tun = tun_sk(sk)->tun;
- kill_fasync(&tun->fasync, SIGIO, POLL_OUT);
-}
-
-static void tun_sock_destruct(struct sock *sk)
-{
- free_netdev(tun_sk(sk)->tun->dev);
+ tfile = container_of(sk, struct tun_file, sk);
+ kill_fasync(&tfile->fasync, SIGIO, POLL_OUT);
}
static int tun_sendmsg(struct kiocb *iocb, struct socket *sock,
struct msghdr *m, size_t total_len)
{
- struct tun_struct *tun = container_of(sock, struct tun_struct, socket);
- return tun_get_user(tun, m->msg_iov, total_len,
- m->msg_flags & MSG_DONTWAIT);
+ struct tun_file *tfile = container_of(sock, struct tun_file, socket);
+ ssize_t result;
+
+ result= tun_get_user(tfile, m->msg_iov, total_len,
+ m->msg_flags & MSG_DONTWAIT);
+ return result;
}
static int tun_recvmsg(struct kiocb *iocb, struct socket *sock,
struct msghdr *m, size_t total_len,
int flags)
{
- struct tun_struct *tun = container_of(sock, struct tun_struct, socket);
+ struct tun_file *tfile = container_of(sock, struct tun_file, socket);
int ret;
+
if (flags & ~(MSG_DONTWAIT|MSG_TRUNC))
return -EINVAL;
- ret = tun_do_read(tun, iocb, m->msg_iov, total_len,
+
+ ret = tun_do_read(tfile, iocb, m->msg_iov, total_len,
flags & MSG_DONTWAIT);
if (ret > total_len) {
m->msg_flags |= MSG_TRUNC;
ret = flags & MSG_TRUNC ? ret : total_len;
}
+
return ret;
}
@@ -988,7 +1007,7 @@ static const struct proto_ops tun_socket_ops = {
static struct proto tun_proto = {
.name = "tun",
.owner = THIS_MODULE,
- .obj_size = sizeof(struct tun_sock),
+ .obj_size = sizeof(struct tun_file),
};
static int tun_flags(struct tun_struct *tun)
@@ -1039,8 +1058,8 @@ static DEVICE_ATTR(group, 0444, tun_show_group, NULL);
static int tun_set_iff(struct net *net, struct file *file, struct ifreq *ifr)
{
- struct sock *sk;
struct tun_struct *tun;
+ struct tun_file *tfile = file->private_data;
struct net_device *dev;
int err;
@@ -1061,7 +1080,7 @@ static int tun_set_iff(struct net *net, struct file *file, struct ifreq *ifr)
(tun->group != -1 && !in_egroup_p(tun->group))) &&
!capable(CAP_NET_ADMIN))
return -EPERM;
- err = security_tun_dev_attach(tun->socket.sk);
+ err = security_tun_dev_attach(tfile->socket.sk);
if (err < 0)
return err;
@@ -1105,24 +1124,8 @@ static int tun_set_iff(struct net *net, struct file *file, struct ifreq *ifr)
tun = netdev_priv(dev);
tun->dev = dev;
tun->flags = flags;
- tun->txflt.count = 0;
- tun->vnet_hdr_sz = sizeof(struct virtio_net_hdr);
- err = -ENOMEM;
- sk = sk_alloc(net, AF_UNSPEC, GFP_KERNEL, &tun_proto);
- if (!sk)
- goto err_free_dev;
-
- tun->socket.wq = &tun->wq;
- init_waitqueue_head(&tun->wq.wait);
- tun->socket.ops = &tun_socket_ops;
- sock_init_data(&tun->socket, sk);
- sk->sk_write_space = tun_sock_write_space;
- sk->sk_sndbuf = INT_MAX;
-
- tun_sk(sk)->tun = tun;
-
- security_tun_dev_post_create(sk);
+ security_tun_dev_post_create(&tfile->sk);
tun_net_init(dev);
@@ -1132,15 +1135,13 @@ static int tun_set_iff(struct net *net, struct file *file, struct ifreq *ifr)
err = register_netdevice(tun->dev);
if (err < 0)
- goto err_free_sk;
+ goto err_free_dev;
if (device_create_file(&tun->dev->dev, &dev_attr_tun_flags) ||
device_create_file(&tun->dev->dev, &dev_attr_owner) ||
device_create_file(&tun->dev->dev, &dev_attr_group))
pr_err("Failed to create tun sysfs files\n");
- sk->sk_destruct = tun_sock_destruct;
-
err = tun_attach(tun, file);
if (err < 0)
goto failed;
@@ -1163,6 +1164,8 @@ static int tun_set_iff(struct net *net, struct file *file, struct ifreq *ifr)
else
tun->flags &= ~TUN_VNET_HDR;
+ /* Cache flags from tun device */
+ tfile->flags = tun->flags;
/* Make sure persistent devices do not get stuck in
* xoff state.
*/
@@ -1172,11 +1175,9 @@ static int tun_set_iff(struct net *net, struct file *file, struct ifreq *ifr)
strcpy(ifr->ifr_name, tun->dev->name);
return 0;
- err_free_sk:
- sock_put(sk);
- err_free_dev:
+err_free_dev:
free_netdev(dev);
- failed:
+failed:
return err;
}
@@ -1348,9 +1349,9 @@ static long __tun_chr_ioctl(struct file *file, unsigned int cmd,
case TUNSETTXFILTER:
/* Can be set only for TAPs */
ret = -EINVAL;
- if ((tun->flags & TUN_TYPE_MASK) != TUN_TAP_DEV)
+ if ((tfile->flags & TUN_TYPE_MASK) != TUN_TAP_DEV)
break;
- ret = update_filter(&tun->txflt, (void __user *)arg);
+ ret = update_filter(&tfile->txflt, (void __user *)arg);
break;
case SIOCGIFHWADDR:
@@ -1370,7 +1371,7 @@ static long __tun_chr_ioctl(struct file *file, unsigned int cmd,
break;
case TUNGETSNDBUF:
- sndbuf = tun->socket.sk->sk_sndbuf;
+ sndbuf = tfile->socket.sk->sk_sndbuf;
if (copy_to_user(argp, &sndbuf, sizeof(sndbuf)))
ret = -EFAULT;
break;
@@ -1381,11 +1382,11 @@ static long __tun_chr_ioctl(struct file *file, unsigned int cmd,
break;
}
- tun->socket.sk->sk_sndbuf = sndbuf;
+ tfile->socket.sk->sk_sndbuf = sndbuf;
break;
case TUNGETVNETHDRSZ:
- vnet_hdr_sz = tun->vnet_hdr_sz;
+ vnet_hdr_sz = tfile->vnet_hdr_sz;
if (copy_to_user(argp, &vnet_hdr_sz, sizeof(vnet_hdr_sz)))
ret = -EFAULT;
break;
@@ -1400,27 +1401,27 @@ static long __tun_chr_ioctl(struct file *file, unsigned int cmd,
break;
}
- tun->vnet_hdr_sz = vnet_hdr_sz;
+ tfile->vnet_hdr_sz = vnet_hdr_sz;
break;
case TUNATTACHFILTER:
/* Can be set only for TAPs */
ret = -EINVAL;
- if ((tun->flags & TUN_TYPE_MASK) != TUN_TAP_DEV)
+ if ((tfile->flags & TUN_TYPE_MASK) != TUN_TAP_DEV)
break;
ret = -EFAULT;
if (copy_from_user(&fprog, argp, sizeof(fprog)))
break;
- ret = sk_attach_filter(&fprog, tun->socket.sk);
+ ret = sk_attach_filter(&fprog, tfile->socket.sk);
break;
case TUNDETACHFILTER:
/* Can be set only for TAPs */
ret = -EINVAL;
- if ((tun->flags & TUN_TYPE_MASK) != TUN_TAP_DEV)
+ if ((tfile->flags & TUN_TYPE_MASK) != TUN_TAP_DEV)
break;
- ret = sk_detach_filter(tun->socket.sk);
+ ret = sk_detach_filter(tfile->socket.sk);
break;
default:
@@ -1472,43 +1473,50 @@ static long tun_chr_compat_ioctl(struct file *file,
static int tun_chr_fasync(int fd, struct file *file, int on)
{
- struct tun_struct *tun = tun_get(file);
+ struct tun_file *tfile = file->private_data;
int ret;
- if (!tun)
- return -EBADFD;
-
- tun_debug(KERN_INFO, tun, "tun_chr_fasync %d\n", on);
-
- if ((ret = fasync_helper(fd, file, on, &tun->fasync)) < 0)
+ if ((ret = fasync_helper(fd, file, on, &tfile->fasync)) < 0)
goto out;
if (on) {
ret = __f_setown(file, task_pid(current), PIDTYPE_PID, 0);
if (ret)
goto out;
- tun->flags |= TUN_FASYNC;
+ tfile->flags |= TUN_FASYNC;
} else
- tun->flags &= ~TUN_FASYNC;
+ tfile->flags &= ~TUN_FASYNC;
ret = 0;
out:
- tun_put(tun);
return ret;
}
static int tun_chr_open(struct inode *inode, struct file * file)
{
+ struct net *net = current->nsproxy->net_ns;
struct tun_file *tfile;
DBG1(KERN_INFO, "tunX: tun_chr_open\n");
- tfile = kmalloc(sizeof(*tfile), GFP_KERNEL);
+ tfile = (struct tun_file *)sk_alloc(net, AF_UNSPEC, GFP_KERNEL,
+ &tun_proto);
if (!tfile)
return -ENOMEM;
- atomic_set(&tfile->count, 0);
+
tfile->tun = NULL;
- tfile->net = get_net(current->nsproxy->net_ns);
+ tfile->net = net;
+ tfile->txflt.count = 0;
+ tfile->vnet_hdr_sz = sizeof(struct virtio_net_hdr);
+ tfile->socket.wq = &tfile->wq;
+ init_waitqueue_head(&tfile->wq.wait);
+ tfile->socket.file = file;
+ tfile->socket.ops = &tun_socket_ops;
+ sock_init_data(&tfile->socket, &tfile->sk);
+
+ tfile->sk.sk_write_space = tun_sock_write_space;
+ tfile->sk.sk_sndbuf = INT_MAX;
file->private_data = tfile;
+
return 0;
}
@@ -1532,14 +1540,14 @@ static int tun_chr_close(struct inode *inode, struct file *file)
unregister_netdevice(dev);
rtnl_unlock();
}
- }
- tun = tfile->tun;
- if (tun)
- sock_put(tun->socket.sk);
+ /* drop the reference that netdevice holds */
+ sock_put(&tfile->sk);
- put_net(tfile->net);
- kfree(tfile);
+ }
+
+ /* drop the reference that file holds */
+ sock_put(&tfile->sk);
return 0;
}
@@ -1668,13 +1676,14 @@ static void tun_cleanup(void)
struct socket *tun_get_socket(struct file *file)
{
struct tun_struct *tun;
+ struct tun_file *tfile = file->private_data;
if (file->f_op != &tun_fops)
return ERR_PTR(-EINVAL);
tun = tun_get(file);
if (!tun)
return ERR_PTR(-EBADFD);
tun_put(tun);
- return &tun->socket;
+ return &tfile->socket;
}
EXPORT_SYMBOL_GPL(tun_get_socket);
^ 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