* [PATCH 7/7] tg3: Remove 5750 PCI code
From: Matt Carlson @ 2011-03-10 2:58 UTC (permalink / raw)
To: davem; +Cc: netdev, mcarlson, stable
The 5750 ASIC rev was never released as a PCI device. It only exists as
a PCIe device. This patch removes the code that supports the former
configuration.
Signed-off-by: Matt Carlson <mcarlson@broadcom.com>
Reviewed-by: Michael Chan <mchan@broadcom.com>
---
drivers/net/tg3.c | 15 +++++----------
1 files changed, 5 insertions(+), 10 deletions(-)
diff --git a/drivers/net/tg3.c b/drivers/net/tg3.c
index 2c67cc9..ebec888 100644
--- a/drivers/net/tg3.c
+++ b/drivers/net/tg3.c
@@ -8193,10 +8193,8 @@ static int tg3_reset_hw(struct tg3 *tp, int reset_phy)
RDMAC_MODE_MBUF_RBD_CRPT_ENAB |
RDMAC_MODE_MBUF_SBD_CRPT_ENAB;
- /* If statement applies to 5705 and 5750 PCI devices only */
- if ((GET_ASIC_REV(tp->pci_chip_rev_id) == ASIC_REV_5705 &&
- tp->pci_chip_rev_id != CHIPREV_ID_5705_A0) ||
- (GET_ASIC_REV(tp->pci_chip_rev_id) == ASIC_REV_5750)) {
+ if (GET_ASIC_REV(tp->pci_chip_rev_id) == ASIC_REV_5705 &&
+ tp->pci_chip_rev_id != CHIPREV_ID_5705_A0) {
if (tp->tg3_flags2 & TG3_FLG2_TSO_CAPABLE &&
GET_ASIC_REV(tp->pci_chip_rev_id) == ASIC_REV_5705) {
rdmac_mode |= RDMAC_MODE_FIFO_SIZE_128;
@@ -8369,17 +8367,14 @@ static int tg3_reset_hw(struct tg3 *tp, int reset_phy)
WDMAC_MODE_FIFOURUN_ENAB | WDMAC_MODE_FIFOOREAD_ENAB |
WDMAC_MODE_LNGREAD_ENAB);
- /* If statement applies to 5705 and 5750 PCI devices only */
- if ((GET_ASIC_REV(tp->pci_chip_rev_id) == ASIC_REV_5705 &&
- tp->pci_chip_rev_id != CHIPREV_ID_5705_A0) ||
- GET_ASIC_REV(tp->pci_chip_rev_id) == ASIC_REV_5750) {
+ if (GET_ASIC_REV(tp->pci_chip_rev_id) == ASIC_REV_5705 &&
+ tp->pci_chip_rev_id != CHIPREV_ID_5705_A0) {
if ((tp->tg3_flags2 & TG3_FLG2_TSO_CAPABLE) &&
(tp->pci_chip_rev_id == CHIPREV_ID_5705_A1 ||
tp->pci_chip_rev_id == CHIPREV_ID_5705_A2)) {
/* nothing */
} else if (!(tr32(TG3PCI_PCISTATE) & PCISTATE_BUS_SPEED_HIGH) &&
- !(tp->tg3_flags2 & TG3_FLG2_IS_5788) &&
- !(tp->tg3_flags2 & TG3_FLG2_PCI_EXPRESS)) {
+ !(tp->tg3_flags2 & TG3_FLG2_IS_5788)) {
val |= WDMAC_MODE_RX_ACCEL;
}
}
--
1.7.3.4
^ permalink raw reply related
* [PATCH 4/7] tg3: cleanup pci device table vars
From: Matt Carlson @ 2011-03-10 2:58 UTC (permalink / raw)
To: davem; +Cc: netdev, mcarlson, stable
Commit 895950c2a6565d9eefda4a38b00fa28537e39fcb, entitled
"tg3: Use DEFINE_PCI_DEVICE_TABLE" moved two pci device tables into the
global address space, but didn't declare them static and didn't prefix
them with "tg3_". This patch fixes those problems.
Signed-off-by: Matt Carlson <mcarlson@broadcom.com>
Reviewed-by: Michael Chan <mchan@broadcom.com>
---
drivers/net/tg3.c | 8 ++++----
1 files changed, 4 insertions(+), 4 deletions(-)
diff --git a/drivers/net/tg3.c b/drivers/net/tg3.c
index ffb0979..73eacbd 100644
--- a/drivers/net/tg3.c
+++ b/drivers/net/tg3.c
@@ -13115,7 +13115,7 @@ static inline u32 tg3_rx_ret_ring_size(struct tg3 *tp)
return 512;
}
-DEFINE_PCI_DEVICE_TABLE(write_reorder_chipsets) = {
+static DEFINE_PCI_DEVICE_TABLE(tg3_write_reorder_chipsets) = {
{ PCI_DEVICE(PCI_VENDOR_ID_AMD, PCI_DEVICE_ID_AMD_FE_GATE_700C) },
{ PCI_DEVICE(PCI_VENDOR_ID_AMD, PCI_DEVICE_ID_AMD_8131_BRIDGE) },
{ PCI_DEVICE(PCI_VENDOR_ID_VIA, PCI_DEVICE_ID_VIA_8385_0) },
@@ -13469,7 +13469,7 @@ static int __devinit tg3_get_invariants(struct tg3 *tp)
* every mailbox register write to force the writes to be
* posted to the chip in order.
*/
- if (pci_dev_present(write_reorder_chipsets) &&
+ if (pci_dev_present(tg3_write_reorder_chipsets) &&
!(tp->tg3_flags2 & TG3_FLG2_PCI_EXPRESS))
tp->tg3_flags |= TG3_FLAG_MBOX_WRITE_REORDER;
@@ -14225,7 +14225,7 @@ static int __devinit tg3_do_test_dma(struct tg3 *tp, u32 *buf, dma_addr_t buf_dm
#define TEST_BUFFER_SIZE 0x2000
-DEFINE_PCI_DEVICE_TABLE(dma_wait_state_chipsets) = {
+static DEFINE_PCI_DEVICE_TABLE(tg3_dma_wait_state_chipsets) = {
{ PCI_DEVICE(PCI_VENDOR_ID_APPLE, PCI_DEVICE_ID_APPLE_UNI_N_PCI15) },
{ },
};
@@ -14404,7 +14404,7 @@ static int __devinit tg3_test_dma(struct tg3 *tp)
* now look for chipsets that are known to expose the
* DMA bug without failing the test.
*/
- if (pci_dev_present(dma_wait_state_chipsets)) {
+ if (pci_dev_present(tg3_dma_wait_state_chipsets)) {
tp->dma_rwctrl &= ~DMA_RWCTRL_WRITE_BNDRY_MASK;
tp->dma_rwctrl |= DMA_RWCTRL_WRITE_BNDRY_16;
} else {
--
1.7.3.4
^ permalink raw reply related
* [PATCH 6/7] tg3: Move tg3_init_link_config to tg3_phy_probe
From: Matt Carlson @ 2011-03-10 2:58 UTC (permalink / raw)
To: davem; +Cc: netdev, mcarlson, stable
This patch moves the function that initializes the link configuration
closer to the place where the rest of the phy code is initialized.
Signed-off-by: Matt Carlson <mcarlson@broadcom.com>
Reviewed-by: Michael Chan <mchan@broadcom.com>
---
drivers/net/tg3.c | 69 +++++++++++++++++++++++++++--------------------------
1 files changed, 35 insertions(+), 34 deletions(-)
diff --git a/drivers/net/tg3.c b/drivers/net/tg3.c
index 159eb23..2c67cc9 100644
--- a/drivers/net/tg3.c
+++ b/drivers/net/tg3.c
@@ -12557,12 +12557,45 @@ static u32 __devinit tg3_read_otp_phycfg(struct tg3 *tp)
return ((thalf_otp & 0x0000ffff) << 16) | (bhalf_otp >> 16);
}
+static void __devinit tg3_phy_init_link_config(struct tg3 *tp)
+{
+ u32 adv = ADVERTISED_Autoneg |
+ ADVERTISED_Pause;
+
+ if (!(tp->phy_flags & TG3_PHYFLG_10_100_ONLY))
+ adv |= ADVERTISED_1000baseT_Half |
+ ADVERTISED_1000baseT_Full;
+
+ if (!(tp->phy_flags & TG3_PHYFLG_ANY_SERDES))
+ adv |= ADVERTISED_100baseT_Half |
+ ADVERTISED_100baseT_Full |
+ ADVERTISED_10baseT_Half |
+ ADVERTISED_10baseT_Full |
+ ADVERTISED_TP;
+ else
+ adv |= ADVERTISED_FIBRE;
+
+ tp->link_config.advertising = adv;
+ tp->link_config.speed = SPEED_INVALID;
+ tp->link_config.duplex = DUPLEX_INVALID;
+ tp->link_config.autoneg = AUTONEG_ENABLE;
+ tp->link_config.active_speed = SPEED_INVALID;
+ tp->link_config.active_duplex = DUPLEX_INVALID;
+ tp->link_config.orig_speed = SPEED_INVALID;
+ tp->link_config.orig_duplex = DUPLEX_INVALID;
+ tp->link_config.orig_autoneg = AUTONEG_INVALID;
+}
+
static int __devinit tg3_phy_probe(struct tg3 *tp)
{
u32 hw_phy_id_1, hw_phy_id_2;
u32 hw_phy_id, hw_phy_id_masked;
int err;
+ /* flow control autonegotiation is default behavior */
+ tp->tg3_flags |= TG3_FLAG_PAUSE_AUTONEG;
+ tp->link_config.flowctrl = FLOW_CTRL_TX | FLOW_CTRL_RX;
+
if (tp->tg3_flags3 & TG3_FLG3_USE_PHYLIB)
return tg3_phy_init(tp);
@@ -12624,6 +12657,8 @@ static int __devinit tg3_phy_probe(struct tg3 *tp)
tp->pci_chip_rev_id != CHIPREV_ID_57765_A0)))
tp->phy_flags |= TG3_PHYFLG_EEE_CAP;
+ tg3_phy_init_link_config(tp);
+
if (!(tp->phy_flags & TG3_PHYFLG_ANY_SERDES) &&
!(tp->tg3_flags3 & TG3_FLG3_ENABLE_APE) &&
!(tp->tg3_flags & TG3_FLAG_ENABLE_ASF)) {
@@ -12679,17 +12714,6 @@ skip_phy_reset:
err = tg3_init_5401phy_dsp(tp);
}
- if (tp->phy_flags & TG3_PHYFLG_ANY_SERDES)
- tp->link_config.advertising =
- (ADVERTISED_1000baseT_Half |
- ADVERTISED_1000baseT_Full |
- ADVERTISED_Autoneg |
- ADVERTISED_FIBRE);
- if (tp->phy_flags & TG3_PHYFLG_10_100_ONLY)
- tp->link_config.advertising &=
- ~(ADVERTISED_1000baseT_Half |
- ADVERTISED_1000baseT_Full);
-
return err;
}
@@ -14422,23 +14446,6 @@ out_nofree:
return ret;
}
-static void __devinit tg3_init_link_config(struct tg3 *tp)
-{
- tp->link_config.advertising =
- (ADVERTISED_10baseT_Half | ADVERTISED_10baseT_Full |
- ADVERTISED_100baseT_Half | ADVERTISED_100baseT_Full |
- ADVERTISED_1000baseT_Half | ADVERTISED_1000baseT_Full |
- ADVERTISED_Autoneg | ADVERTISED_MII);
- tp->link_config.speed = SPEED_INVALID;
- tp->link_config.duplex = DUPLEX_INVALID;
- tp->link_config.autoneg = AUTONEG_ENABLE;
- tp->link_config.active_speed = SPEED_INVALID;
- tp->link_config.active_duplex = DUPLEX_INVALID;
- tp->link_config.orig_speed = SPEED_INVALID;
- tp->link_config.orig_duplex = DUPLEX_INVALID;
- tp->link_config.orig_autoneg = AUTONEG_INVALID;
-}
-
static void __devinit tg3_init_bufmgr_config(struct tg3 *tp)
{
if (tp->tg3_flags3 & TG3_FLG3_5717_PLUS) {
@@ -14742,8 +14749,6 @@ static int __devinit tg3_init_one(struct pci_dev *pdev,
goto err_out_free_dev;
}
- tg3_init_link_config(tp);
-
tp->rx_pending = TG3_DEF_RX_RING_PENDING;
tp->rx_jumbo_pending = TG3_DEF_RX_JUMBO_RING_PENDING;
@@ -14891,10 +14896,6 @@ static int __devinit tg3_init_one(struct pci_dev *pdev,
goto err_out_apeunmap;
}
- /* flow control autonegotiation is default behavior */
- tp->tg3_flags |= TG3_FLAG_PAUSE_AUTONEG;
- tp->link_config.flowctrl = FLOW_CTRL_TX | FLOW_CTRL_RX;
-
intmbx = MAILBOX_INTERRUPT_0 + TG3_64BIT_REG_LOW;
rcvmbx = MAILBOX_RCVRET_CON_IDX_0 + TG3_64BIT_REG_LOW;
sndmbx = MAILBOX_SNDHOST_PROD_IDX_0 + TG3_64BIT_REG_LOW;
--
1.7.3.4
^ permalink raw reply related
* [PATCH 3/7] tg3: Add code to verify RODATA checksum of VPD
From: Matt Carlson @ 2011-03-10 2:58 UTC (permalink / raw)
To: davem; +Cc: netdev, mcarlson, stable
This patch adds code to verify the checksum stored in the "RV" info
keyword of the RODATA VPD section.
Signed-off-by: Matt Carlson <mcarlson@broadcom.com>
Reviewed-by: Michael Chan <mchan@broadcom.com>
---
drivers/net/tg3.c | 35 +++++++++++++++++++++++++++++++++++
include/linux/pci.h | 1 +
2 files changed, 36 insertions(+), 0 deletions(-)
diff --git a/drivers/net/tg3.c b/drivers/net/tg3.c
index 8f71608..ffb0979 100644
--- a/drivers/net/tg3.c
+++ b/drivers/net/tg3.c
@@ -10499,6 +10499,41 @@ static int tg3_test_nvram(struct tg3 *tp)
if (csum != le32_to_cpu(buf[0xfc/4]))
goto out;
+ for (i = 0; i < TG3_NVM_VPD_LEN; i += 4) {
+ /* The data is in little-endian format in NVRAM.
+ * Use the big-endian read routines to preserve
+ * the byte order as it exists in NVRAM.
+ */
+ if (tg3_nvram_read_be32(tp, TG3_NVM_VPD_OFF + i, &buf[i/4]))
+ goto out;
+ }
+
+ i = pci_vpd_find_tag((u8 *)buf, 0, TG3_NVM_VPD_LEN,
+ PCI_VPD_LRDT_RO_DATA);
+ if (i > 0) {
+ j = pci_vpd_lrdt_size(&((u8 *)buf)[i]);
+ if (j < 0)
+ goto out;
+
+ if (i + PCI_VPD_LRDT_TAG_SIZE + j > TG3_NVM_VPD_LEN)
+ goto out;
+
+ i += PCI_VPD_LRDT_TAG_SIZE;
+ j = pci_vpd_find_info_keyword((u8 *)buf, i, j,
+ PCI_VPD_RO_KEYWORD_CHKSUM);
+ if (j > 0) {
+ u8 csum8 = 0;
+
+ j += PCI_VPD_INFO_FLD_HDR_SIZE;
+
+ for (i = 0; i <= j; i++)
+ csum8 += ((u8 *)buf)[i];
+
+ if (csum8)
+ goto out;
+ }
+ }
+
err = 0;
out:
diff --git a/include/linux/pci.h b/include/linux/pci.h
index 559d028..ff5bccb 100644
--- a/include/linux/pci.h
+++ b/include/linux/pci.h
@@ -1479,6 +1479,7 @@ void pci_request_acs(void);
#define PCI_VPD_RO_KEYWORD_PARTNO "PN"
#define PCI_VPD_RO_KEYWORD_MFR_ID "MN"
#define PCI_VPD_RO_KEYWORD_VENDOR0 "V0"
+#define PCI_VPD_RO_KEYWORD_CHKSUM "RV"
/**
* pci_vpd_lrdt_size - Extracts the Large Resource Data Type length
--
1.7.3.4
^ permalink raw reply related
* [PATCH net-next 0/7] tg3: Cleanups
From: Matt Carlson @ 2011-03-10 2:58 UTC (permalink / raw)
To: davem; +Cc: netdev, mcarlson, stable
This patchset adds a 5719 workaround, VPD RODATA checksum verification,
and some code cleanups
^ permalink raw reply
* [PATCH 1/7] tg3: Add missed 5719 workaround change
From: Matt Carlson @ 2011-03-10 2:58 UTC (permalink / raw)
To: davem; +Cc: netdev, mcarlson, stable
Commit 2866d956fe0ad8fc8d8a7c54104ccc879b49406d, entitled
"tg3: Expand 5719 workaround" extended a 5719 A0 workaround to all
revisions of the chip. There was a change that should have been a
part of that patch that was missed. This patch adds the missing
piece.
Signed-off-by: Matt Carlson <mcarlson@broadcom.com>
Reviewed-by: Michael Chan <mchan@broadcom.com>
---
drivers/net/tg3.c | 2 +-
1 files changed, 1 insertions(+), 1 deletions(-)
diff --git a/drivers/net/tg3.c b/drivers/net/tg3.c
index 6be4185..6fd5cf0 100644
--- a/drivers/net/tg3.c
+++ b/drivers/net/tg3.c
@@ -8103,7 +8103,7 @@ static int tg3_reset_hw(struct tg3 *tp, int reset_phy)
/* Program the jumbo buffer descriptor ring control
* blocks on those devices that have them.
*/
- if (tp->pci_chip_rev_id == CHIPREV_ID_5719_A0 ||
+ if (GET_ASIC_REV(tp->pci_chip_rev_id) == ASIC_REV_5719 ||
((tp->tg3_flags & TG3_FLAG_JUMBO_CAPABLE) &&
!(tp->tg3_flags2 & TG3_FLG2_5780_CLASS))) {
/* Setup replenish threshold. */
--
1.7.3.4
^ permalink raw reply related
* [PATCH 2/7] tg3: Fix NVRAM selftest
From: Matt Carlson @ 2011-03-10 2:58 UTC (permalink / raw)
To: davem; +Cc: netdev, mcarlson, stable
The tg3 NVRAM selftest actually fails when validating the checksum of
the legacy NVRAM format. However, the test still reported success
because the last update of the return code was a success from the NVRAM
reads. This patch fixes the code so that the error return code defaults
to a failure status. Then the patch fixes the reason why the checsum
validation failed.
Signed-off-by: Matt Carlson <mcarlson@broadcom.com>
Reviewed-by: Michael Chan <mchan@broadcom.com>
---
drivers/net/tg3.c | 6 ++++--
1 files changed, 4 insertions(+), 2 deletions(-)
diff --git a/drivers/net/tg3.c b/drivers/net/tg3.c
index 6fd5cf0..8f71608 100644
--- a/drivers/net/tg3.c
+++ b/drivers/net/tg3.c
@@ -10487,14 +10487,16 @@ static int tg3_test_nvram(struct tg3 *tp)
goto out;
}
+ err = -EIO;
+
/* Bootstrap checksum at offset 0x10 */
csum = calc_crc((unsigned char *) buf, 0x10);
- if (csum != be32_to_cpu(buf[0x10/4]))
+ if (csum != le32_to_cpu(buf[0x10/4]))
goto out;
/* Manufacturing block starts at offset 0x74, checksum at 0xfc */
csum = calc_crc((unsigned char *) &buf[0x74/4], 0x88);
- if (csum != be32_to_cpu(buf[0xfc/4]))
+ if (csum != le32_to_cpu(buf[0xfc/4]))
goto out;
err = 0;
--
1.7.3.4
^ permalink raw reply related
* [PATCH 5/7] tg3: Refine VAux decision process
From: Matt Carlson @ 2011-03-10 2:58 UTC (permalink / raw)
To: davem; +Cc: netdev, mcarlson, stable
In the near future, the VAux switching decision process is going to get
more complicated. This patch refines and consolidates the existing
algorithm in anticipation of the new scheme.
Signed-off-by: Matt Carlson <mcarlson@broadcom.com>
Reviewed-by: Michael Chan <mchan@broadcom.com>
---
drivers/net/tg3.c | 41 +++++++++++++++++++++--------------------
1 files changed, 21 insertions(+), 20 deletions(-)
diff --git a/drivers/net/tg3.c b/drivers/net/tg3.c
index 73eacbd..159eb23 100644
--- a/drivers/net/tg3.c
+++ b/drivers/net/tg3.c
@@ -2120,7 +2120,7 @@ out:
static void tg3_frob_aux_power(struct tg3 *tp)
{
- struct tg3 *tp_peer = tp;
+ bool need_vaux = false;
/* The GPIOs do something completely different on 57765. */
if ((tp->tg3_flags2 & TG3_FLG2_IS_NIC) == 0 ||
@@ -2128,23 +2128,32 @@ static void tg3_frob_aux_power(struct tg3 *tp)
GET_ASIC_REV(tp->pci_chip_rev_id) == ASIC_REV_57765)
return;
- if (GET_ASIC_REV(tp->pci_chip_rev_id) == ASIC_REV_5704 ||
- GET_ASIC_REV(tp->pci_chip_rev_id) == ASIC_REV_5714 ||
- GET_ASIC_REV(tp->pci_chip_rev_id) == ASIC_REV_5717) {
+ if ((GET_ASIC_REV(tp->pci_chip_rev_id) == ASIC_REV_5704 ||
+ GET_ASIC_REV(tp->pci_chip_rev_id) == ASIC_REV_5714 ||
+ GET_ASIC_REV(tp->pci_chip_rev_id) == ASIC_REV_5717) &&
+ tp->pdev_peer != tp->pdev) {
struct net_device *dev_peer;
dev_peer = pci_get_drvdata(tp->pdev_peer);
+
/* remove_one() may have been run on the peer. */
- if (!dev_peer)
- tp_peer = tp;
- else
- tp_peer = netdev_priv(dev_peer);
+ if (dev_peer) {
+ struct tg3 *tp_peer = netdev_priv(dev_peer);
+
+ if (tp_peer->tg3_flags & TG3_FLAG_INIT_COMPLETE)
+ return;
+
+ if ((tp_peer->tg3_flags & TG3_FLAG_WOL_ENABLE) ||
+ (tp_peer->tg3_flags & TG3_FLAG_ENABLE_ASF))
+ need_vaux = true;
+ }
}
- if ((tp->tg3_flags & TG3_FLAG_WOL_ENABLE) != 0 ||
- (tp->tg3_flags & TG3_FLAG_ENABLE_ASF) != 0 ||
- (tp_peer->tg3_flags & TG3_FLAG_WOL_ENABLE) != 0 ||
- (tp_peer->tg3_flags & TG3_FLAG_ENABLE_ASF) != 0) {
+ if ((tp->tg3_flags & TG3_FLAG_WOL_ENABLE) ||
+ (tp->tg3_flags & TG3_FLAG_ENABLE_ASF))
+ need_vaux = true;
+
+ if (need_vaux) {
if (GET_ASIC_REV(tp->pci_chip_rev_id) == ASIC_REV_5700 ||
GET_ASIC_REV(tp->pci_chip_rev_id) == ASIC_REV_5701) {
tw32_wait_f(GRC_LOCAL_CTRL, tp->grc_local_ctrl |
@@ -2174,10 +2183,6 @@ static void tg3_frob_aux_power(struct tg3 *tp)
u32 no_gpio2;
u32 grc_local_ctrl = 0;
- if (tp_peer != tp &&
- (tp_peer->tg3_flags & TG3_FLAG_INIT_COMPLETE) != 0)
- return;
-
/* Workaround to prevent overdrawing Amps. */
if (GET_ASIC_REV(tp->pci_chip_rev_id) ==
ASIC_REV_5714) {
@@ -2216,10 +2221,6 @@ static void tg3_frob_aux_power(struct tg3 *tp)
} else {
if (GET_ASIC_REV(tp->pci_chip_rev_id) != ASIC_REV_5700 &&
GET_ASIC_REV(tp->pci_chip_rev_id) != ASIC_REV_5701) {
- if (tp_peer != tp &&
- (tp_peer->tg3_flags & TG3_FLAG_INIT_COMPLETE) != 0)
- return;
-
tw32_wait_f(GRC_LOCAL_CTRL, tp->grc_local_ctrl |
(GRC_LCLCTRL_GPIO_OE1 |
GRC_LCLCTRL_GPIO_OUTPUT1), 100);
--
1.7.3.4
^ permalink raw reply related
* Re: [PATCH net-next 0/7] tg3: Cleanups
From: Matt Carlson @ 2011-03-10 3:01 UTC (permalink / raw)
To: Matt Carlson
Cc: davem@davemloft.net, netdev@vger.kernel.org, stable@kernel.org
In-Reply-To: <1299725905-8498-1-git-send-email-mcarlson@broadcom.com>
To stable, please disregard. That email address was appended by
mistake.
On Wed, Mar 09, 2011 at 06:58:18PM -0800, Matt Carlson wrote:
> This patchset adds a 5719 workaround, VPD RODATA checksum verification,
> and some code cleanups
>
^ permalink raw reply
* Re: [Bugme-new] [Bug 29252] New: IPv6 doesn't work in a kvm guest.
From: David Miller @ 2011-03-10 3:20 UTC (permalink / raw)
To: akpm; +Cc: netdev, bugzilla-daemon, bugme-daemon, slash, ernstp
In-Reply-To: <20110309.155818.212679516.davem@davemloft.net>
From: David Miller <davem@davemloft.net>
Date: Wed, 09 Mar 2011 15:58:18 -0800 (PST)
> Ok, the following should address both bugs, #29252 and #30462, please
> give it some testing.
>
> --------------------
> ipv6: Don't create clones of nonexthop routes forever.
Nevermind, this patch has problems, I'm still debugging and trying to
come up with a proper fix.
Thanks in advance for your patience.
^ permalink raw reply
* Re: [Bugme-new] [Bug 29252] New: IPv6 doesn't work in a kvm guest.
From: David Miller @ 2011-03-10 4:04 UTC (permalink / raw)
To: akpm; +Cc: netdev, bugzilla-daemon, bugme-daemon, slash, ernstp
In-Reply-To: <20110309.192012.193710171.davem@davemloft.net>
From: David Miller <davem@davemloft.net>
Date: Wed, 09 Mar 2011 19:20:12 -0800 (PST)
> From: David Miller <davem@davemloft.net>
> Date: Wed, 09 Mar 2011 15:58:18 -0800 (PST)
>
>> Ok, the following should address both bugs, #29252 and #30462, please
>> give it some testing.
>>
>> --------------------
>> ipv6: Don't create clones of nonexthop routes forever.
>
> Nevermind, this patch has problems, I'm still debugging and trying to
> come up with a proper fix.
>
> Thanks in advance for your patience.
Ok, I'm more confident in this version of the fix. It passes all of
my tests, and I've added instrumentation to make sure various cases
are performing the operations the way I expect them to.
--------------------
ipv6: Don't create clones of host routes.
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit
Addresses https://bugzilla.kernel.org/show_bug.cgi?id=29252
Addresses https://bugzilla.kernel.org/show_bug.cgi?id=30462
In commit d80bc0fd262ef840ed4e82593ad6416fa1ba3fc4 ("ipv6: Always
clone offlink routes.") we forced the kernel to always clone offlink
routes.
The reason we do that is to make sure we never bind an inetpeer to a
prefixed route.
The logic turned on here has existed in the tree for many years,
but was always off due to a protecting CPP define. So perhaps
it's no surprise that there is a logic bug here.
The problem is that we canot clone a route that is already a
host route (ie. has DST_HOST set). Because if we do, an identical
entry already exists in the routing tree and therefore the
ip6_rt_ins() call is going to fail.
This sets off a series of failures and high cpu usage, because when
ip6_rt_ins() fails we loop retrying this operation a few times in
order to handle a race between two threads trying to clone and insert
the same host route at the same time.
Fix this by simply using the route as-is when DST_HOST is set.
Reported-by: slash@ac.auone-net.jp
Reported-by: Ernst Sjöstrand <ernstp@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
net/ipv6/route.c | 4 +++-
1 files changed, 3 insertions(+), 1 deletions(-)
diff --git a/net/ipv6/route.c b/net/ipv6/route.c
index 904312e..e7db701 100644
--- a/net/ipv6/route.c
+++ b/net/ipv6/route.c
@@ -739,8 +739,10 @@ restart:
if (!rt->rt6i_nexthop && !(rt->rt6i_flags & RTF_NONEXTHOP))
nrt = rt6_alloc_cow(rt, &fl->fl6_dst, &fl->fl6_src);
- else
+ else if (!(rt->dst.flags & DST_HOST))
nrt = rt6_alloc_clone(rt, &fl->fl6_dst);
+ else
+ goto out2;
dst_release(&rt->dst);
rt = nrt ? : net->ipv6.ip6_null_entry;
--
1.7.4.1
^ permalink raw reply related
* Re: [PATCH 03/18] ipvs: zero percpu stats
From: Simon Horman @ 2011-03-10 4:27 UTC (permalink / raw)
To: David Miller
Cc: ja, eric.dumazet, netdev, netfilter-devel, netfilter, lvs-devel,
hans
In-Reply-To: <20110309.185344.193704334.davem@davemloft.net>
On Wed, Mar 09, 2011 at 06:53:44PM -0800, David Miller wrote:
> From: Simon Horman <horms@verge.net.au>
> Date: Thu, 10 Mar 2011 10:34:42 +0900
>
> > On Sun, Mar 06, 2011 at 02:18:35PM +0200, Julian Anastasov wrote:
> >
> > [ snip ]
> >
> >> Zero the new percpu stats because we copy from there.
> >> Use the stats spin lock to synchronize the percpu zeroing with
> >> the percpu reading, both in user context and not in a hot path.
> >>
> >> Signed-off-by: Julian Anastasov <ja@ssi.bg>
> >
> > Eric, do you have any thoughts on this?
> > It seems clean to me.
>
> Eric is away until this weekend, so don't be alarmed by a
> late response :-)
Thanks, I'll wait longer :-)
^ permalink raw reply
* [PATCH] ipv4: Optimize flow initialization in input route lookup.
From: David Miller @ 2011-03-10 4:42 UTC (permalink / raw)
To: netdev
Like in commit 44713b67db10c774f14280c129b0d5fd13c70cf2
("ipv4: Optimize flow initialization in output route lookup."
we can optimize the on-stack flow setup to only initialize
the members which are actually used.
Otherwise we bzero the entire structure, then initialize
explicitly the first half of it.
Signed-off-by: David S. Miller <davem@davemloft.net>
---
net/ipv4/route.c | 14 ++++++++------
1 files changed, 8 insertions(+), 6 deletions(-)
diff --git a/net/ipv4/route.c b/net/ipv4/route.c
index 92a24ea..ac32d8f 100644
--- a/net/ipv4/route.c
+++ b/net/ipv4/route.c
@@ -2081,12 +2081,7 @@ static int ip_route_input_slow(struct sk_buff *skb, __be32 daddr, __be32 saddr,
{
struct fib_result res;
struct in_device *in_dev = __in_dev_get_rcu(dev);
- struct flowi fl = { .fl4_dst = daddr,
- .fl4_src = saddr,
- .fl4_tos = tos,
- .fl4_scope = RT_SCOPE_UNIVERSE,
- .mark = skb->mark,
- .iif = dev->ifindex };
+ struct flowi fl;
unsigned flags = 0;
u32 itag = 0;
struct rtable * rth;
@@ -2123,6 +2118,13 @@ static int ip_route_input_slow(struct sk_buff *skb, __be32 daddr, __be32 saddr,
/*
* Now we are ready to route packet.
*/
+ fl.oif = 0;
+ fl.iif = dev->ifindex;
+ fl.mark = skb->mark;
+ fl.fl4_dst = daddr;
+ fl.fl4_src = saddr;
+ fl.fl4_tos = tos;
+ fl.fl4_scope = RT_SCOPE_UNIVERSE;
err = fib_lookup(net, &fl, &res);
if (err != 0) {
if (!IN_DEV_FORWARD(in_dev))
--
1.7.4.1
^ permalink raw reply related
* [PATCH] ipv4: Optimize flow initialization in fib_validate_source().
From: David Miller @ 2011-03-10 4:58 UTC (permalink / raw)
To: netdev
Like in commit 44713b67db10c774f14280c129b0d5fd13c70cf2
("ipv4: Optimize flow initialization in output route lookup."
we can optimize the on-stack flow setup to only initialize
the members which are actually used.
Otherwise we bzero the entire structure, then initialize
explicitly the first half of it.
Signed-off-by: David S. Miller <davem@davemloft.net>
---
net/ipv4/fib_frontend.c | 16 +++++++++-------
1 files changed, 9 insertions(+), 7 deletions(-)
diff --git a/net/ipv4/fib_frontend.c b/net/ipv4/fib_frontend.c
index 1d2233c..fe10bcd 100644
--- a/net/ipv4/fib_frontend.c
+++ b/net/ipv4/fib_frontend.c
@@ -193,19 +193,21 @@ int fib_validate_source(__be32 src, __be32 dst, u8 tos, int oif,
u32 *itag, u32 mark)
{
struct in_device *in_dev;
- struct flowi fl = {
- .fl4_dst = src,
- .fl4_src = dst,
- .fl4_tos = tos,
- .mark = mark,
- .iif = oif
- };
+ struct flowi fl;
struct fib_result res;
int no_addr, rpf, accept_local;
bool dev_match;
int ret;
struct net *net;
+ fl.oif = 0;
+ fl.iif = oif;
+ fl.mark = mark;
+ fl.fl4_dst = src;
+ fl.fl4_src = dst;
+ fl.fl4_tos = tos;
+ fl.fl4_scope = RT_SCOPE_UNIVERSE;
+
no_addr = rpf = accept_local = 0;
in_dev = __in_dev_get_rcu(dev);
if (in_dev) {
--
1.7.4.1
^ permalink raw reply related
* Re: [PATCH] Make CUBIC Hystart more robust to RTT variations
From: Bill Fink @ 2011-03-10 5:24 UTC (permalink / raw)
To: Lucas Nussbaum
Cc: Injong Rhee, Stephen Hemminger, David Miller, xiyou.wangcong,
netdev, sangtae.ha
In-Reply-To: <20110309065319.GA23740@xanadu.blop.info>
On Wed, 9 Mar 2011, Lucas Nussbaum wrote:
> On 08/03/11 at 20:30 -0500, Injong Rhee wrote:
> > Now, both tools can be wrong. But that is not catastrophic since
> > congestion avoidance can kick in to save the day. In a pipe where no
> > other flows are competing, then exiting slow start too early can
> > slow things down as the window can be still too small. But that is
> > in fact when delays are most reliable. So those tests that say bad
> > performance with hystart are in fact, where hystart is supposed to
> > perform well.
>
> Hi,
>
> In my setup, there is no congestion at all (except the buffer bloat).
> Without Hystart, transferring 8 Gb of data takes 9s, with CUBIC exiting
> slow start at ~2000 packets.
> With Hystart, transferring 8 Gb of data takes 19s, with CUBIC exiting
> slow start at ~20 packets.
> I don't think that this is "hystart performing well". We could just as
> well remove slow start completely, and only do congestion avoidance,
> then.
>
> While I see the value in Hystart, it's clear that there are some flaws
> in the current implementation. It probably makes sense to disable
> hystart by default until those problems are fixed.
Here are some tests I performed across real networks, where
congestion is generally not an issue, with a 2.6.35 kernel on
the transmit side.
8 GB transfer across an 18 ms RTT path with autotuning and hystart:
i7test7% nuttcp -n8g -i1 192.168.1.23
517.9375 MB / 1.00 sec = 4344.6096 Mbps 0 retrans
688.4375 MB / 1.00 sec = 5775.1998 Mbps 0 retrans
692.9375 MB / 1.00 sec = 5812.7462 Mbps 0 retrans
698.0625 MB / 1.00 sec = 5855.8078 Mbps 0 retrans
699.8750 MB / 1.00 sec = 5871.0123 Mbps 0 retrans
710.5625 MB / 1.00 sec = 5960.5707 Mbps 0 retrans
728.8125 MB / 1.00 sec = 6113.7652 Mbps 0 retrans
751.3750 MB / 1.00 sec = 6302.9210 Mbps 0 retrans
783.8750 MB / 1.00 sec = 6575.6201 Mbps 0 retrans
825.1875 MB / 1.00 sec = 6921.8145 Mbps 0 retrans
875.4375 MB / 1.00 sec = 7343.9811 Mbps 0 retrans
8192.0000 MB / 11.26 sec = 6102.4718 Mbps 11 %TX 28 %RX 0 retrans 18.92 msRTT
Ramps up quickly to a little under 6 Gbps, then increases more
slowly to 7+ Gbps, with no TCP retransmissions.
8 GB transfer across an 18 ms RTT path with 40 MB socket buffer and hystart:
i7test7% nuttcp -n8g -w40m -i1 192.168.1.23
970.0625 MB / 1.00 sec = 8136.8475 Mbps 0 retrans
1181.1875 MB / 1.00 sec = 9909.0045 Mbps 0 retrans
1181.2500 MB / 1.00 sec = 9908.6369 Mbps 0 retrans
1181.3125 MB / 1.00 sec = 9909.8747 Mbps 0 retrans
1181.2500 MB / 1.00 sec = 9909.0531 Mbps 0 retrans
1181.2500 MB / 1.00 sec = 9908.8153 Mbps 0 retrans
1181.2500 MB / 1.00 sec = 9909.0729 Mbps 0 retrans
8192.0000 MB / 7.13 sec = 9633.5814 Mbps 17 %TX 42 %RX 0 retrans 18.91 msRTT
Quickly ramps up to full 10-GigE line rate, with no TCP retrans.
8 GB transfer across an 18 ms RTT path with autotuning and no hystart:
i7test7% nuttcp -n8g -i1 192.168.1.23
845.4375 MB / 1.00 sec = 7091.5828 Mbps 0 retrans
1181.3125 MB / 1.00 sec = 9910.0134 Mbps 0 retrans
1181.0625 MB / 1.00 sec = 9907.1830 Mbps 0 retrans
1181.4375 MB / 1.00 sec = 9910.8936 Mbps 0 retrans
1181.1875 MB / 1.00 sec = 9908.1721 Mbps 0 retrans
1181.3125 MB / 1.00 sec = 9909.5774 Mbps 0 retrans
1181.1875 MB / 1.00 sec = 9908.6874 Mbps 0 retrans
8192.0000 MB / 7.25 sec = 9484.4524 Mbps 18 %TX 41 %RX 0 retrans 18.92 msRTT
Also quickly ramps up to full 10-GigE line rate, with no TCP retrans.
8 GB transfer across an 18 ms RTT path with 40 MB socket buffer and no hystart:
i7test7% nuttcp -n8g -w40m -i1 192.168.1.23
969.8750 MB / 1.00 sec = 8135.6571 Mbps 0 retrans
1181.3125 MB / 1.00 sec = 9909.3990 Mbps 0 retrans
1181.2500 MB / 1.00 sec = 9908.9342 Mbps 0 retrans
1181.2500 MB / 1.00 sec = 9909.4098 Mbps 0 retrans
1181.2500 MB / 1.00 sec = 9908.8252 Mbps 0 retrans
1181.2500 MB / 1.00 sec = 9909.0630 Mbps 0 retrans
1181.2500 MB / 1.00 sec = 9909.3504 Mbps 0 retrans
8192.0000 MB / 7.15 sec = 9611.8053 Mbps 18 %TX 42 %RX 0 retrans 18.95 msRTT
Basically the same as the case with 40 MB socket buffer and hystart enabled.
Now trying the same type of tests across an 80 ms RTT path.
8 GB transfer across an 80 ms RTT path with autotuning and hystart:
i7test7% nuttcp -n8g -i1 192.168.1.18
11.3125 MB / 1.00 sec = 94.8954 Mbps 0 retrans
441.5625 MB / 1.00 sec = 3704.1021 Mbps 0 retrans
687.3750 MB / 1.00 sec = 5765.8657 Mbps 0 retrans
715.5625 MB / 1.00 sec = 6002.6273 Mbps 0 retrans
709.9375 MB / 1.00 sec = 5955.5958 Mbps 0 retrans
691.3125 MB / 1.00 sec = 5799.0626 Mbps 0 retrans
718.6250 MB / 1.00 sec = 6028.3538 Mbps 0 retrans
718.0000 MB / 1.00 sec = 6023.0205 Mbps 0 retrans
704.0000 MB / 1.00 sec = 5905.5387 Mbps 0 retrans
733.3125 MB / 1.00 sec = 6151.4096 Mbps 0 retrans
738.8750 MB / 1.00 sec = 6198.2381 Mbps 0 retrans
731.8750 MB / 1.00 sec = 6139.3695 Mbps 0 retrans
8192.0000 MB / 12.85 sec = 5348.9677 Mbps 10 %TX 23 %RX 0 retrans 80.81 msRTT
Similar to the 20 ms RTT path, but achieving somewhat lower
performance levels, presumably due to the larger RTT. Ramps
up fairly quickly to a little under 6 Gbps, then increases
more slowly to 6+ Gbps, with no TCP retransmissions.
8 GB transfer across an 80 ms RTT path with 100 MB socket buffer and hystart:
i7test7% nuttcp -n8g -w100m -i1 192.168.1.18
103.9375 MB / 1.00 sec = 871.8378 Mbps 0 retrans
1086.5625 MB / 1.00 sec = 9114.6102 Mbps 0 retrans
1106.6875 MB / 1.00 sec = 9283.5583 Mbps 0 retrans
1109.3125 MB / 1.00 sec = 9305.5226 Mbps 0 retrans
1111.1875 MB / 1.00 sec = 9321.9596 Mbps 0 retrans
1112.8125 MB / 1.00 sec = 9334.8452 Mbps 0 retrans
1113.6875 MB / 1.00 sec = 9341.6620 Mbps 0 retrans
1120.2500 MB / 1.00 sec = 9398.0054 Mbps 0 retrans
8192.0000 MB / 8.37 sec = 8207.2049 Mbps 16 %TX 38 %RX 0 retrans 80.81 msRTT
Quickly ramps up to 9+ Gbps and then slowly increases further,
with no TCP retrans.
8 GB transfer across an 80 ms RTT path with autotuning and no hystart:
i7test7% nuttcp -n8g -i1 192.168.1.18
11.2500 MB / 1.00 sec = 94.3703 Mbps 0 retrans
519.0625 MB / 1.00 sec = 4354.1596 Mbps 0 retrans
861.2500 MB / 1.00 sec = 7224.7970 Mbps 0 retrans
871.0000 MB / 1.00 sec = 7306.4191 Mbps 0 retrans
860.7500 MB / 1.00 sec = 7220.4438 Mbps 0 retrans
869.0625 MB / 1.00 sec = 7290.3340 Mbps 0 retrans
863.4375 MB / 1.00 sec = 7242.7707 Mbps 0 retrans
860.4375 MB / 1.00 sec = 7218.0606 Mbps 0 retrans
875.5000 MB / 1.00 sec = 7344.3071 Mbps 0 retrans
863.1875 MB / 1.00 sec = 7240.8257 Mbps 0 retrans
8192.0000 MB / 10.98 sec = 6259.4379 Mbps 12 %TX 27 %RX 0 retrans 80.81 msRTT
Ramps up quickly to 7+ Gbps, then appears to stabilize at that
level, with no TCP retransmissions. Performance is somewhat
better than with autotuning enabled, but less than using a
manually set 100 MB socket buffer.
8 GB transfer across an 80 ms RTT path with 100 MB socket buffer and no hystart:
i7test7% nuttcp -n8g -w100m -i1 192.168.1.18
102.8750 MB / 1.00 sec = 862.9487 Mbps 0 retrans
522.8750 MB / 1.00 sec = 4386.2811 Mbps 414 retrans
881.5625 MB / 1.00 sec = 7394.6534 Mbps 0 retrans
1164.3125 MB / 1.00 sec = 9766.6682 Mbps 0 retrans
1170.5625 MB / 1.00 sec = 9819.7042 Mbps 0 retrans
1166.8125 MB / 1.00 sec = 9788.2067 Mbps 0 retrans
1159.8750 MB / 1.00 sec = 9729.1530 Mbps 0 retrans
811.1250 MB / 1.00 sec = 6804.8017 Mbps 21 retrans
73.2500 MB / 1.00 sec = 614.4674 Mbps 0 retrans
884.6250 MB / 1.00 sec = 7420.2900 Mbps 0 retrans
8192.0000 MB / 10.34 sec = 6647.9394 Mbps 13 %TX 31 %RX 435 retrans 80.81 msRTT
Disabling hystart on a large RTT path does not seem to play nice with
a manually specified socket buffer, resulting in TCP retransmissions
that limit the effective network performance.
This is a repeatable but extremely variable phenomenon.
i7test7% nuttcp -n8g -w100m -i1 192.168.1.18
103.7500 MB / 1.00 sec = 870.3015 Mbps 0 retrans
1146.3750 MB / 1.00 sec = 9616.4520 Mbps 0 retrans
1175.9375 MB / 1.00 sec = 9864.6070 Mbps 0 retrans
615.6875 MB / 1.00 sec = 5164.7353 Mbps 21 retrans
139.2500 MB / 1.00 sec = 1168.1253 Mbps 0 retrans
1090.0625 MB / 1.00 sec = 9143.8053 Mbps 0 retrans
1170.4375 MB / 1.00 sec = 9818.6654 Mbps 0 retrans
1174.5625 MB / 1.00 sec = 9852.8754 Mbps 0 retrans
1174.8750 MB / 1.00 sec = 9855.6052 Mbps 0 retrans
8192.0000 MB / 9.42 sec = 7292.9879 Mbps 14 %TX 34 %RX 21 retrans 80.81 msRTT
And:
i7test7% nuttcp -n8g -w100m -i1 192.168.1.18
102.8125 MB / 1.00 sec = 862.4227 Mbps 0 retrans
1148.4375 MB / 1.00 sec = 9633.6860 Mbps 0 retrans
1177.4375 MB / 1.00 sec = 9877.3086 Mbps 0 retrans
1168.1250 MB / 1.00 sec = 9798.9133 Mbps 11 retrans
133.1250 MB / 1.00 sec = 1116.7457 Mbps 0 retrans
479.8750 MB / 1.00 sec = 4025.4631 Mbps 0 retrans
1150.6875 MB / 1.00 sec = 9652.4830 Mbps 0 retrans
1177.3125 MB / 1.00 sec = 9876.0624 Mbps 0 retrans
1177.3750 MB / 1.00 sec = 9876.0139 Mbps 0 retrans
320.2500 MB / 1.00 sec = 2686.6452 Mbps 19 retrans
64.9375 MB / 1.00 sec = 544.7363 Mbps 0 retrans
73.6250 MB / 1.00 sec = 617.6113 Mbps 0 retrans
8192.0000 MB / 12.39 sec = 5545.7570 Mbps 12 %TX 26 %RX 30 retrans 80.80 msRTT
Re-enabling hystart immediately gives a clean test with no TCP retrans.
i7test7% nuttcp -n8g -w100m -i1 192.168.1.18
103.8750 MB / 1.00 sec = 871.3353 Mbps 0 retrans
1086.7500 MB / 1.00 sec = 9116.4474 Mbps 0 retrans
1105.8125 MB / 1.00 sec = 9276.2276 Mbps 0 retrans
1109.4375 MB / 1.00 sec = 9306.5339 Mbps 0 retrans
1111.3125 MB / 1.00 sec = 9322.5327 Mbps 0 retrans
1111.3750 MB / 1.00 sec = 9322.8053 Mbps 0 retrans
1113.7500 MB / 1.00 sec = 9342.8962 Mbps 0 retrans
1120.3125 MB / 1.00 sec = 9397.5711 Mbps 0 retrans
8192.0000 MB / 8.38 sec = 8204.8394 Mbps 16 %TX 39 %RX 0 retrans 80.80 msRTT
-Bill
^ permalink raw reply
* [PATCH net-next-2.6] ipv4: Fix PMTU update.
From: Hiroaki SHIMODA @ 2011-03-10 6:09 UTC (permalink / raw)
To: davem; +Cc: netdev
On current net-next-2.6, when Linux receives ICMP Type: 3, Code: 4
(Destination unreachable (Fragmentation needed)),
icmp_unreach
-> ip_rt_frag_needed
(peer->pmtu_expires is set here)
-> tcp_v4_err
-> do_pmtu_discovery
-> ip_rt_update_pmtu
(peer->pmtu_expires is already set,
so check_peer_pmtu is skipped.)
-> check_peer_pmtu
check_peer_pmtu is skipped and MTU is not updated.
To fix this, let check_peer_pmtu execute unconditionally.
And some minor fixes
1) Avoid potential peer->pmtu_expires set to be zero.
2) In check_peer_pmtu, argument of time_before is reversed.
3) check_peer_pmtu expects peer->pmtu_orig is initialized as zero,
but not initialized.
Signed-off-by: Hiroaki SHIMODA <shimoda.hiroaki@gmail.com>
---
net/ipv4/inetpeer.c | 1 +
net/ipv4/route.c | 22 +++++++++++++++++-----
2 files changed, 18 insertions(+), 5 deletions(-)
diff --git a/net/ipv4/inetpeer.c b/net/ipv4/inetpeer.c
index 6442c35..86b1d08 100644
--- a/net/ipv4/inetpeer.c
+++ b/net/ipv4/inetpeer.c
@@ -511,6 +511,7 @@ struct inet_peer *inet_getpeer(struct inetpeer_addr *daddr, int create)
p->rate_tokens = 0;
p->rate_last = 0;
p->pmtu_expires = 0;
+ p->pmtu_orig = 0;
memset(&p->redirect_learned, 0, sizeof(p->redirect_learned));
INIT_LIST_HEAD(&p->unused);
diff --git a/net/ipv4/route.c b/net/ipv4/route.c
index 92a24ea..3cf8001 100644
--- a/net/ipv4/route.c
+++ b/net/ipv4/route.c
@@ -1533,9 +1533,15 @@ unsigned short ip_rt_frag_needed(struct net *net, struct iphdr *iph,
if (mtu < ip_rt_min_pmtu)
mtu = ip_rt_min_pmtu;
if (!peer->pmtu_expires || mtu < peer->pmtu_learned) {
+ unsigned long pmtu_expires;
+
+ pmtu_expires = jiffies + ip_rt_mtu_expires;
+ if (!pmtu_expires)
+ pmtu_expires = 1UL;
+
est_mtu = mtu;
peer->pmtu_learned = mtu;
- peer->pmtu_expires = jiffies + ip_rt_mtu_expires;
+ peer->pmtu_expires = pmtu_expires;
}
inet_putpeer(peer);
@@ -1549,7 +1555,7 @@ static void check_peer_pmtu(struct dst_entry *dst, struct inet_peer *peer)
{
unsigned long expires = peer->pmtu_expires;
- if (time_before(expires, jiffies)) {
+ if (time_before(jiffies, expires)) {
u32 orig_dst_mtu = dst_mtu(dst);
if (peer->pmtu_learned < orig_dst_mtu) {
if (!peer->pmtu_orig)
@@ -1574,14 +1580,20 @@ static void ip_rt_update_pmtu(struct dst_entry *dst, u32 mtu)
if (mtu < ip_rt_min_pmtu)
mtu = ip_rt_min_pmtu;
if (!peer->pmtu_expires || mtu < peer->pmtu_learned) {
+ unsigned long pmtu_expires;
+
+ pmtu_expires = jiffies + ip_rt_mtu_expires;
+ if (!pmtu_expires)
+ pmtu_expires = 1UL;
+
peer->pmtu_learned = mtu;
- peer->pmtu_expires = jiffies + ip_rt_mtu_expires;
+ peer->pmtu_expires = pmtu_expires;
atomic_inc(&__rt_peer_genid);
rt->rt_peer_genid = rt_peer_genid();
-
- check_peer_pmtu(dst, peer);
}
+ check_peer_pmtu(dst, peer);
+
inet_putpeer(peer);
}
}
^ permalink raw reply related
* Re: [PATCH] Make CUBIC Hystart more robust to RTT variations
From: Stephen Hemminger @ 2011-03-10 6:17 UTC (permalink / raw)
To: Bill Fink
Cc: Injong Rhee, David Miller, xiyou wangcong, netdev, sangtae ha,
Lucas Nussbaum
In-Reply-To: <20110310002458.5a94f563.billfink@mindspring.com>
Bill what is the HZ in your kernel config.
I am concerned hystart doesn't work well with HZ=100
^ permalink raw reply
* Re: [patch net-next-2.6] net: reinject arps into bonding slave instead of master
From: Jiri Pirko @ 2011-03-10 6:48 UTC (permalink / raw)
To: Nicolas de Pesloüan
Cc: Andy Gospodarek, netdev, davem, shemminger, kaber, fubar,
eric.dumazet
In-Reply-To: <4D77FCC1.5050904@gmail.com>
>But for all others setups, where there exist some net_devices before
>the "untagging" one, you would face some troubles. For example, with
>eth0+eth1 -> br0 -> br0.100, you cannot untag before entering
>__netif_receive_skb. If you do so, the bridge would receive untagged
>frame and if the frame is not for the local host, the bridge would
>forward an untagged frame while it is expected to forward a tagged
>one. Even if the bridge is in a position to know the frame *was*
>tagged, we cannot expect the bridge to do special processing to
>handle this situation. Doing so would break layering.
I disagree.
eth0 -> untag on early __netif_receive_skb (sets up skb->vlan_tci)
->rx_handler of bridge
->br0 -> tag is detected by vlan_tx_tag_present()
-> reinject to __netif_receive_skb with skb->dev == br0.100
This way the flow would be very similar to vlan-hw-accel, am I right?
I have following patch in mind. Note it's raw DRAFT.
Signed-off-by: Jiri Pirko <jpirko@redhat.com>
---
include/linux/if_vlan.h | 5 ++
net/8021q/vlan.c | 8 --
net/8021q/vlan_core.c | 106 +++++++++++++++++++++++++++++
net/8021q/vlan_dev.c | 172 -----------------------------------------------
net/core/dev.c | 18 ++++-
5 files changed, 125 insertions(+), 184 deletions(-)
diff --git a/include/linux/if_vlan.h b/include/linux/if_vlan.h
index 635e1fa..dd914e2 100644
--- a/include/linux/if_vlan.h
+++ b/include/linux/if_vlan.h
@@ -133,6 +133,7 @@ extern u16 vlan_dev_vlan_id(const struct net_device *dev);
extern int __vlan_hwaccel_rx(struct sk_buff *skb, struct vlan_group *grp,
u16 vlan_tci, int polling);
extern bool vlan_hwaccel_do_receive(struct sk_buff **skb);
+extern void vlan_emulate_hwaccel(struct sk_buff **skbp);
extern gro_result_t
vlan_gro_receive(struct napi_struct *napi, struct vlan_group *grp,
unsigned int vlan_tci, struct sk_buff *skb);
@@ -173,6 +174,10 @@ static inline bool vlan_hwaccel_do_receive(struct sk_buff **skb)
return false;
}
+void vlan_emulate_hwaccel(struct sk_buff **skbp)
+{
+}
+
static inline gro_result_t
vlan_gro_receive(struct napi_struct *napi, struct vlan_group *grp,
unsigned int vlan_tci, struct sk_buff *skb)
diff --git a/net/8021q/vlan.c b/net/8021q/vlan.c
index 7850412..59f0a9d 100644
--- a/net/8021q/vlan.c
+++ b/net/8021q/vlan.c
@@ -49,11 +49,6 @@ const char vlan_version[] = DRV_VERSION;
static const char vlan_copyright[] = "Ben Greear <greearb@candelatech.com>";
static const char vlan_buggyright[] = "David S. Miller <davem@redhat.com>";
-static struct packet_type vlan_packet_type __read_mostly = {
- .type = cpu_to_be16(ETH_P_8021Q),
- .func = vlan_skb_recv, /* VLAN receive method */
-};
-
/* End of global variables definitions. */
static void vlan_group_free(struct vlan_group *grp)
@@ -688,7 +683,6 @@ static int __init vlan_proto_init(void)
if (err < 0)
goto err4;
- dev_add_pack(&vlan_packet_type);
vlan_ioctl_set(vlan_ioctl_handler);
return 0;
@@ -709,8 +703,6 @@ static void __exit vlan_cleanup_module(void)
unregister_netdevice_notifier(&vlan_notifier_block);
- dev_remove_pack(&vlan_packet_type);
-
unregister_pernet_subsys(&vlan_net_ops);
rcu_barrier(); /* Wait for completion of call_rcu()'s */
diff --git a/net/8021q/vlan_core.c b/net/8021q/vlan_core.c
index ce8e3ab..c324e4d 100644
--- a/net/8021q/vlan_core.c
+++ b/net/8021q/vlan_core.c
@@ -88,3 +88,109 @@ gro_result_t vlan_gro_frags(struct napi_struct *napi, struct vlan_group *grp,
return napi_gro_frags(napi);
}
EXPORT_SYMBOL(vlan_gro_frags);
+
+static inline struct sk_buff *vlan_check_reorder_header(struct sk_buff *skb)
+{
+ if (vlan_dev_info(skb->dev)->flags & VLAN_FLAG_REORDER_HDR) {
+ if (skb_cow(skb, skb_headroom(skb)) < 0)
+ skb = NULL;
+ if (skb) {
+ /* Lifted from Gleb's VLAN code... */
+ memmove(skb->data - ETH_HLEN,
+ skb->data - VLAN_ETH_HLEN, 12);
+ skb->mac_header += VLAN_HLEN;
+ }
+ }
+
+ return skb;
+}
+
+static inline void vlan_set_encap_proto(struct sk_buff *skb,
+ struct vlan_hdr *vhdr)
+{
+ __be16 proto;
+ unsigned char *rawp;
+
+ /*
+ * Was a VLAN packet, grab the encapsulated protocol, which the layer
+ * three protocols care about.
+ */
+
+ proto = vhdr->h_vlan_encapsulated_proto;
+ if (ntohs(proto) >= 1536) {
+ skb->protocol = proto;
+ return;
+ }
+
+ rawp = skb->data;
+ if (*(unsigned short *)rawp == 0xFFFF)
+ /*
+ * This is a magic hack to spot IPX packets. Older Novell
+ * breaks the protocol design and runs IPX over 802.3 without
+ * an 802.2 LLC layer. We look for FFFF which isn't a used
+ * 802.2 SSAP/DSAP. This won't work for fault tolerant netware
+ * but does for the rest.
+ */
+ skb->protocol = htons(ETH_P_802_3);
+ else
+ /*
+ * Real 802.2 LLC
+ */
+ skb->protocol = htons(ETH_P_802_2);
+}
+
+/*
+ * Determine the packet's protocol ID. The rule here is that we
+ * assume 802.3 if the type field is short enough to be a length.
+ * This is normal practice and works for any 'now in use' protocol.
+ *
+ * Also, at this point we assume that we ARE dealing exclusively with
+ * VLAN packets, or packets that should be made into VLAN packets based
+ * on a default VLAN ID.
+ *
+ * NOTE: Should be similar to ethernet/eth.c.
+ *
+ * SANITY NOTE: This method is called when a packet is moving up the stack
+ * towards userland. To get here, it would have already passed
+ * through the ethernet/eth.c eth_type_trans() method.
+ * SANITY NOTE 2: We are referencing to the VLAN_HDR frields, which MAY be
+ * stored UNALIGNED in the memory. RISC systems don't like
+ * such cases very much...
+ * SANITY NOTE 2a: According to Dave Miller & Alexey, it will always be
+ * aligned, so there doesn't need to be any of the unaligned
+ * stuff. It has been commented out now... --Ben
+ *
+ */
+void vlan_emulate_hwaccel(struct sk_buff **skbp)
+{
+ struct sk_buff *skb = *skbp;
+ struct vlan_hdr *vhdr;
+ u16 vlan_tci;
+
+ *skbp = skb = skb_share_check(skb, GFP_ATOMIC);
+ if (unlikely(!skb))
+ goto err_free;
+
+ if (unlikely(!pskb_may_pull(skb, VLAN_HLEN)))
+ goto err_free;
+
+ vhdr = (struct vlan_hdr *) skb->data;
+ vlan_tci = ntohs(vhdr->h_vlan_TCI);
+ __vlan_hwaccel_put_tag(skb, vlan_tci);
+
+ skb_pull_rcsum(skb, VLAN_HLEN);
+ vlan_set_encap_proto(skb, vhdr);
+
+ skb = vlan_check_reorder_header(skb);
+ if (unlikely(!skb)) {
+ goto err_free;
+ }
+
+ return;
+
+err_free:
+ kfree_skb(skb);
+ *skbp = NULL;
+ return;
+}
+
diff --git a/net/8021q/vlan_dev.c b/net/8021q/vlan_dev.c
index ae610f0..57d2f40 100644
--- a/net/8021q/vlan_dev.c
+++ b/net/8021q/vlan_dev.c
@@ -65,178 +65,6 @@ static int vlan_dev_rebuild_header(struct sk_buff *skb)
return 0;
}
-static inline struct sk_buff *vlan_check_reorder_header(struct sk_buff *skb)
-{
- if (vlan_dev_info(skb->dev)->flags & VLAN_FLAG_REORDER_HDR) {
- if (skb_cow(skb, skb_headroom(skb)) < 0)
- skb = NULL;
- if (skb) {
- /* Lifted from Gleb's VLAN code... */
- memmove(skb->data - ETH_HLEN,
- skb->data - VLAN_ETH_HLEN, 12);
- skb->mac_header += VLAN_HLEN;
- }
- }
-
- return skb;
-}
-
-static inline void vlan_set_encap_proto(struct sk_buff *skb,
- struct vlan_hdr *vhdr)
-{
- __be16 proto;
- unsigned char *rawp;
-
- /*
- * Was a VLAN packet, grab the encapsulated protocol, which the layer
- * three protocols care about.
- */
-
- proto = vhdr->h_vlan_encapsulated_proto;
- if (ntohs(proto) >= 1536) {
- skb->protocol = proto;
- return;
- }
-
- rawp = skb->data;
- if (*(unsigned short *)rawp == 0xFFFF)
- /*
- * This is a magic hack to spot IPX packets. Older Novell
- * breaks the protocol design and runs IPX over 802.3 without
- * an 802.2 LLC layer. We look for FFFF which isn't a used
- * 802.2 SSAP/DSAP. This won't work for fault tolerant netware
- * but does for the rest.
- */
- skb->protocol = htons(ETH_P_802_3);
- else
- /*
- * Real 802.2 LLC
- */
- skb->protocol = htons(ETH_P_802_2);
-}
-
-/*
- * Determine the packet's protocol ID. The rule here is that we
- * assume 802.3 if the type field is short enough to be a length.
- * This is normal practice and works for any 'now in use' protocol.
- *
- * Also, at this point we assume that we ARE dealing exclusively with
- * VLAN packets, or packets that should be made into VLAN packets based
- * on a default VLAN ID.
- *
- * NOTE: Should be similar to ethernet/eth.c.
- *
- * SANITY NOTE: This method is called when a packet is moving up the stack
- * towards userland. To get here, it would have already passed
- * through the ethernet/eth.c eth_type_trans() method.
- * SANITY NOTE 2: We are referencing to the VLAN_HDR frields, which MAY be
- * stored UNALIGNED in the memory. RISC systems don't like
- * such cases very much...
- * SANITY NOTE 2a: According to Dave Miller & Alexey, it will always be
- * aligned, so there doesn't need to be any of the unaligned
- * stuff. It has been commented out now... --Ben
- *
- */
-int vlan_skb_recv(struct sk_buff *skb, struct net_device *dev,
- struct packet_type *ptype, struct net_device *orig_dev)
-{
- struct vlan_hdr *vhdr;
- struct vlan_pcpu_stats *rx_stats;
- struct net_device *vlan_dev;
- u16 vlan_id;
- u16 vlan_tci;
-
- skb = skb_share_check(skb, GFP_ATOMIC);
- if (skb == NULL)
- goto err_free;
-
- if (unlikely(!pskb_may_pull(skb, VLAN_HLEN)))
- goto err_free;
-
- vhdr = (struct vlan_hdr *)skb->data;
- vlan_tci = ntohs(vhdr->h_vlan_TCI);
- vlan_id = vlan_tci & VLAN_VID_MASK;
-
- rcu_read_lock();
- vlan_dev = vlan_find_dev(dev, vlan_id);
-
- /* If the VLAN device is defined, we use it.
- * If not, and the VID is 0, it is a 802.1p packet (not
- * really a VLAN), so we will just netif_rx it later to the
- * original interface, but with the skb->proto set to the
- * wrapped proto: we do nothing here.
- */
-
- if (!vlan_dev) {
- if (vlan_id) {
- pr_debug("%s: ERROR: No net_device for VID: %u on dev: %s\n",
- __func__, vlan_id, dev->name);
- goto err_unlock;
- }
- rx_stats = NULL;
- } else {
- skb->dev = vlan_dev;
-
- rx_stats = this_cpu_ptr(vlan_dev_info(skb->dev)->vlan_pcpu_stats);
-
- u64_stats_update_begin(&rx_stats->syncp);
- rx_stats->rx_packets++;
- rx_stats->rx_bytes += skb->len;
-
- skb->priority = vlan_get_ingress_priority(skb->dev, vlan_tci);
-
- pr_debug("%s: priority: %u for TCI: %hu\n",
- __func__, skb->priority, vlan_tci);
-
- switch (skb->pkt_type) {
- case PACKET_BROADCAST:
- /* Yeah, stats collect these together.. */
- /* stats->broadcast ++; // no such counter :-( */
- break;
-
- case PACKET_MULTICAST:
- rx_stats->rx_multicast++;
- break;
-
- case PACKET_OTHERHOST:
- /* Our lower layer thinks this is not local, let's make
- * sure.
- * This allows the VLAN to have a different MAC than the
- * underlying device, and still route correctly.
- */
- if (!compare_ether_addr(eth_hdr(skb)->h_dest,
- skb->dev->dev_addr))
- skb->pkt_type = PACKET_HOST;
- break;
- default:
- break;
- }
- u64_stats_update_end(&rx_stats->syncp);
- }
-
- skb_pull_rcsum(skb, VLAN_HLEN);
- vlan_set_encap_proto(skb, vhdr);
-
- if (vlan_dev) {
- skb = vlan_check_reorder_header(skb);
- if (!skb) {
- rx_stats->rx_errors++;
- goto err_unlock;
- }
- }
-
- netif_rx(skb);
-
- rcu_read_unlock();
- return NET_RX_SUCCESS;
-
-err_unlock:
- rcu_read_unlock();
-err_free:
- atomic_long_inc(&dev->rx_dropped);
- kfree_skb(skb);
- return NET_RX_DROP;
-}
static inline u16
vlan_dev_get_egress_qos_mask(struct net_device *dev, struct sk_buff *skb)
diff --git a/net/core/dev.c b/net/core/dev.c
index 9f66de9..f3315ef 100644
--- a/net/core/dev.c
+++ b/net/core/dev.c
@@ -3133,10 +3133,6 @@ static int __netif_receive_skb(struct sk_buff *skb)
if (netpoll_receive_skb(skb))
return NET_RX_DROP;
- if (!skb->skb_iif)
- skb->skb_iif = skb->dev->ifindex;
- orig_dev = skb->dev;
-
skb_reset_network_header(skb);
skb_reset_transport_header(skb);
skb->mac_len = skb->network_header - skb->mac_header;
@@ -3145,6 +3141,20 @@ static int __netif_receive_skb(struct sk_buff *skb)
rcu_read_lock();
+ if (!skb->skb_iif) {
+ skb->skb_iif = skb->dev->ifindex;
+ /*
+ * frame is here for the first time so lets check if it's vlan
+ * one and emulate vlan hwaccel in that case
+ */
+ if (skb->protocol == cpu_to_be16(ETH_P_8021Q)) {
+ vlan_emulate_hwaccel(&skb);
+ if (!skb)
+ goto out;
+ }
+ }
+ orig_dev = skb->dev;
+
another_round:
__this_cpu_inc(softnet_data.processed);
--
1.7.4
^ permalink raw reply related
* Re: Network performance with small packets - continued
From: Michael S. Tsirkin @ 2011-03-10 6:54 UTC (permalink / raw)
To: Tom Lendacky
Cc: Shirley Ma, Rusty Russell, Krishna Kumar2, David Miller, kvm,
netdev, steved
In-Reply-To: <201103091725.12992.tahm@linux.vnet.ibm.com>
On Wed, Mar 09, 2011 at 05:25:11PM -0600, Tom Lendacky wrote:
> As for which CPU the interrupt gets pinned to, that doesn't matter - see
> below.
So what hurts us the most is that the IRQ jumps between the VCPUs?
^ permalink raw reply
* Re: [PATCH] Make CUBIC Hystart more robust to RTT variations
From: Bill Fink @ 2011-03-10 7:17 UTC (permalink / raw)
To: Stephen Hemminger
Cc: Injong Rhee, David Miller, xiyou wangcong, netdev, sangtae ha,
Lucas Nussbaum
In-Reply-To: <2049243270.17294.1299737824096.JavaMail.root@tahiti.vyatta.com>
On Wed, 9 Mar 2011, Stephen Hemminger wrote:
> Bill what is the HZ in your kernel config.
> I am concerned hystart doesn't work well with HZ=100
HZ=1000
But I did have tcp_timestamps disabled. Should I re-run
the tests with tcp_timestamps enabled?
-Bill
^ permalink raw reply
* [PATCH 1/3 V2] slub: automatically reserve bytes at the end of slab
From: Lai Jiangshan @ 2011-03-10 7:21 UTC (permalink / raw)
To: Ingo Molnar, Pekka Enberg
Cc: Paul E. McKenney, Christoph Lameter, Eric Dumazet,
David S. Miller, Matt Mackall, linux-mm, linux-kernel, netdev
In-Reply-To: <4D6CA843.3090103@cn.fujitsu.com>
There is no "struct" for slub's slab, it shares with struct page.
But struct page is very small, it is insufficient when we need
to add some metadata for slab.
So we add a field "reserved" to struct kmem_cache, when a slab
is allocated, kmem_cache->reserved bytes are automatically reserved
at the end of the slab for slab's metadata.
Changed from v1:
Export the reserved field via sysfs
Signed-off-by: Lai Jiangshan <laijs@cn.fujitsu.com>
---
include/linux/slub_def.h | 1 +
mm/slub.c | 47 +++++++++++++++++++++++++++++----------------
2 files changed, 31 insertions(+), 17 deletions(-)
diff --git a/include/linux/slub_def.h b/include/linux/slub_def.h
index 8b6e8ae..ae0093c 100644
--- a/include/linux/slub_def.h
+++ b/include/linux/slub_def.h
@@ -83,6 +83,7 @@ struct kmem_cache {
void (*ctor)(void *);
int inuse; /* Offset to metadata */
int align; /* Alignment */
+ int reserved; /* Reserved bytes at the end of slabs */
unsigned long min_partial;
const char *name; /* Name (only for display!) */
struct list_head list; /* List of slab caches */
diff --git a/mm/slub.c b/mm/slub.c
index e15aa7f..d3d1767 100644
--- a/mm/slub.c
+++ b/mm/slub.c
@@ -281,11 +281,16 @@ static inline int slab_index(void *p, struct kmem_cache *s, void *addr)
return (p - addr) / s->size;
}
+static inline int order_objects(int order, unsigned long size, int reserved)
+{
+ return ((PAGE_SIZE << order) - reserved) / size;
+}
+
static inline struct kmem_cache_order_objects oo_make(int order,
- unsigned long size)
+ unsigned long size, int reserved)
{
struct kmem_cache_order_objects x = {
- (order << OO_SHIFT) + (PAGE_SIZE << order) / size
+ (order << OO_SHIFT) + order_objects(order, size, reserved)
};
return x;
@@ -617,7 +622,7 @@ static int slab_pad_check(struct kmem_cache *s, struct page *page)
return 1;
start = page_address(page);
- length = (PAGE_SIZE << compound_order(page));
+ length = (PAGE_SIZE << compound_order(page)) - s->reserved;
end = start + length;
remainder = length % s->size;
if (!remainder)
@@ -698,7 +703,7 @@ static int check_slab(struct kmem_cache *s, struct page *page)
return 0;
}
- maxobj = (PAGE_SIZE << compound_order(page)) / s->size;
+ maxobj = order_objects(compound_order(page), s->size, s->reserved);
if (page->objects > maxobj) {
slab_err(s, page, "objects %u > max %u",
s->name, page->objects, maxobj);
@@ -748,7 +753,7 @@ static int on_freelist(struct kmem_cache *s, struct page *page, void *search)
nr++;
}
- max_objects = (PAGE_SIZE << compound_order(page)) / s->size;
+ max_objects = order_objects(compound_order(page), s->size, s->reserved);
if (max_objects > MAX_OBJS_PER_PAGE)
max_objects = MAX_OBJS_PER_PAGE;
@@ -1988,13 +1993,13 @@ static int slub_nomerge;
* the smallest order which will fit the object.
*/
static inline int slab_order(int size, int min_objects,
- int max_order, int fract_leftover)
+ int max_order, int fract_leftover, int reserved)
{
int order;
int rem;
int min_order = slub_min_order;
- if ((PAGE_SIZE << min_order) / size > MAX_OBJS_PER_PAGE)
+ if (order_objects(min_order, size, reserved) > MAX_OBJS_PER_PAGE)
return get_order(size * MAX_OBJS_PER_PAGE) - 1;
for (order = max(min_order,
@@ -2003,10 +2008,10 @@ static inline int slab_order(int size, int min_objects,
unsigned long slab_size = PAGE_SIZE << order;
- if (slab_size < min_objects * size)
+ if (slab_size < min_objects * size + reserved)
continue;
- rem = slab_size % size;
+ rem = (slab_size - reserved) % size;
if (rem <= slab_size / fract_leftover)
break;
@@ -2016,7 +2021,7 @@ static inline int slab_order(int size, int min_objects,
return order;
}
-static inline int calculate_order(int size)
+static inline int calculate_order(int size, int reserved)
{
int order;
int min_objects;
@@ -2034,14 +2039,14 @@ static inline int calculate_order(int size)
min_objects = slub_min_objects;
if (!min_objects)
min_objects = 4 * (fls(nr_cpu_ids) + 1);
- max_objects = (PAGE_SIZE << slub_max_order)/size;
+ max_objects = order_objects(slub_max_order, size, reserved);
min_objects = min(min_objects, max_objects);
while (min_objects > 1) {
fraction = 16;
while (fraction >= 4) {
order = slab_order(size, min_objects,
- slub_max_order, fraction);
+ slub_max_order, fraction, reserved);
if (order <= slub_max_order)
return order;
fraction /= 2;
@@ -2053,14 +2058,14 @@ static inline int calculate_order(int size)
* We were unable to place multiple objects in a slab. Now
* lets see if we can place a single object there.
*/
- order = slab_order(size, 1, slub_max_order, 1);
+ order = slab_order(size, 1, slub_max_order, 1, reserved);
if (order <= slub_max_order)
return order;
/*
* Doh this slab cannot be placed using slub_max_order.
*/
- order = slab_order(size, 1, MAX_ORDER, 1);
+ order = slab_order(size, 1, MAX_ORDER, 1, reserved);
if (order < MAX_ORDER)
return order;
return -ENOSYS;
@@ -2311,7 +2316,7 @@ static int calculate_sizes(struct kmem_cache *s, int forced_order)
if (forced_order >= 0)
order = forced_order;
else
- order = calculate_order(size);
+ order = calculate_order(size, s->reserved);
if (order < 0)
return 0;
@@ -2329,8 +2334,8 @@ static int calculate_sizes(struct kmem_cache *s, int forced_order)
/*
* Determine the number of objects per slab
*/
- s->oo = oo_make(order, size);
- s->min = oo_make(get_order(size), size);
+ s->oo = oo_make(order, size, s->reserved);
+ s->min = oo_make(get_order(size), size, s->reserved);
if (oo_objects(s->oo) > oo_objects(s->max))
s->max = s->oo;
@@ -2349,6 +2354,7 @@ static int kmem_cache_open(struct kmem_cache *s,
s->objsize = size;
s->align = align;
s->flags = kmem_cache_flags(size, flags, name, ctor);
+ s->reserved = 0;
if (!calculate_sizes(s, -1))
goto error;
@@ -4017,6 +4023,12 @@ static ssize_t destroy_by_rcu_show(struct kmem_cache *s, char *buf)
}
SLAB_ATTR_RO(destroy_by_rcu);
+static ssize_t reserved_show(struct kmem_cache *s, char *buf)
+{
+ return sprintf(buf, "%d\n", s->reserved);
+}
+SLAB_ATTR_RO(reserved);
+
#ifdef CONFIG_SLUB_DEBUG
static ssize_t slabs_show(struct kmem_cache *s, char *buf)
{
@@ -4303,6 +4315,7 @@ static struct attribute *slab_attrs[] = {
&reclaim_account_attr.attr,
&destroy_by_rcu_attr.attr,
&shrink_attr.attr,
+ &reserved_attr.attr,
#ifdef CONFIG_SLUB_DEBUG
&total_objects_attr.attr,
&slabs_attr.attr,
--
To unsubscribe, send a message with 'unsubscribe linux-mm' in
the body to majordomo@kvack.org. For more info on Linux MM,
see: http://www.linux-mm.org/ .
Fight unfair telecom internet charges in Canada: sign http://stopthemeter.ca/
Don't email: <a href=mailto:"dont@kvack.org"> email@kvack.org </a>
^ permalink raw reply related
* [PATCH 2/3 V2] slub,rcu: don't assume the size of struct rcu_head
From: Lai Jiangshan @ 2011-03-10 7:22 UTC (permalink / raw)
To: Ingo Molnar, Pekka Enberg
Cc: Paul E. McKenney, Christoph Lameter, Eric Dumazet,
David S. Miller, Matt Mackall, linux-mm, linux-kernel, netdev
In-Reply-To: <4D6CA843.3090103@cn.fujitsu.com>
The size of struct rcu_head may be changed. When it becomes larger,
it will pollute the page array.
We reserve some some bytes for struct rcu_head when a slab
is allocated in this situation.
Changed from V1:
use VM_BUG_ON instead BUG_ON
Signed-off-by: Lai Jiangshan <laijs@cn.fujitsu.com>
Acked-by: Christoph Lameter <cl@linux.com>
---
mm/slub.c | 30 +++++++++++++++++++++++++-----
1 files changed, 25 insertions(+), 5 deletions(-)
diff --git a/mm/slub.c b/mm/slub.c
index d3d1767..ebba3eb 100644
--- a/mm/slub.c
+++ b/mm/slub.c
@@ -1254,21 +1254,38 @@ static void __free_slab(struct kmem_cache *s, struct page *page)
__free_pages(page, order);
}
+#define need_reserve_slab_rcu \
+ (sizeof(((struct page *)NULL)->lru) < sizeof(struct rcu_head))
+
static void rcu_free_slab(struct rcu_head *h)
{
struct page *page;
- page = container_of((struct list_head *)h, struct page, lru);
+ if (need_reserve_slab_rcu)
+ page = virt_to_head_page(h);
+ else
+ page = container_of((struct list_head *)h, struct page, lru);
+
__free_slab(page->slab, page);
}
static void free_slab(struct kmem_cache *s, struct page *page)
{
if (unlikely(s->flags & SLAB_DESTROY_BY_RCU)) {
- /*
- * RCU free overloads the RCU head over the LRU
- */
- struct rcu_head *head = (void *)&page->lru;
+ struct rcu_head *head;
+
+ if (need_reserve_slab_rcu) {
+ int order = compound_order(page);
+ int offset = (PAGE_SIZE << order) - s->reserved;
+
+ VM_BUG_ON(s->reserved != sizeof(*head));
+ head = page_address(page) + offset;
+ } else {
+ /*
+ * RCU free overloads the RCU head over the LRU
+ */
+ head = (void *)&page->lru;
+ }
call_rcu(head, rcu_free_slab);
} else
@@ -2356,6 +2373,9 @@ static int kmem_cache_open(struct kmem_cache *s,
s->flags = kmem_cache_flags(size, flags, name, ctor);
s->reserved = 0;
+ if (need_reserve_slab_rcu && (s->flags & SLAB_DESTROY_BY_RCU))
+ s->reserved = sizeof(struct rcu_head);
+
if (!calculate_sizes(s, -1))
goto error;
if (disable_higher_order_debug) {
--
To unsubscribe, send a message with 'unsubscribe linux-mm' in
the body to majordomo@kvack.org. For more info on Linux MM,
see: http://www.linux-mm.org/ .
Fight unfair telecom internet charges in Canada: sign http://stopthemeter.ca/
Don't email: <a href=mailto:"dont@kvack.org"> email@kvack.org </a>
^ permalink raw reply related
* [PATCH 3/3 V2] slab,rcu: don't assume the size of struct rcu_head
From: Lai Jiangshan @ 2011-03-10 7:22 UTC (permalink / raw)
To: Pekka Enberg
Cc: Ingo Molnar, Paul E. McKenney, Christoph Lameter, Eric Dumazet,
David S. Miller, Matt Mackall, linux-mm, linux-kernel, netdev
In-Reply-To: <4D6CA843.3090103@cn.fujitsu.com>
The size of struct rcu_head may be changed. When it becomes larger,
it may pollute the data after struct slab.
Signed-off-by: Lai Jiangshan <laijs@cn.fujitsu.com>
---
diff --git a/mm/slab.c b/mm/slab.c
index 37961d1..52cf0b4 100644
--- a/mm/slab.c
+++ b/mm/slab.c
@@ -191,22 +191,6 @@ typedef unsigned int kmem_bufctl_t;
#define SLAB_LIMIT (((kmem_bufctl_t)(~0U))-3)
/*
- * struct slab
- *
- * Manages the objs in a slab. Placed either at the beginning of mem allocated
- * for a slab, or allocated from an general cache.
- * Slabs are chained into three list: fully used, partial, fully free slabs.
- */
-struct slab {
- struct list_head list;
- unsigned long colouroff;
- void *s_mem; /* including colour offset */
- unsigned int inuse; /* num of objs active in slab */
- kmem_bufctl_t free;
- unsigned short nodeid;
-};
-
-/*
* struct slab_rcu
*
* slab_destroy on a SLAB_DESTROY_BY_RCU cache uses this structure to
@@ -219,8 +203,6 @@ struct slab {
*
* rcu_read_lock before reading the address, then rcu_read_unlock after
* taking the spinlock within the structure expected at that address.
- *
- * We assume struct slab_rcu can overlay struct slab when destroying.
*/
struct slab_rcu {
struct rcu_head head;
@@ -229,6 +211,27 @@ struct slab_rcu {
};
/*
+ * struct slab
+ *
+ * Manages the objs in a slab. Placed either at the beginning of mem allocated
+ * for a slab, or allocated from an general cache.
+ * Slabs are chained into three list: fully used, partial, fully free slabs.
+ */
+struct slab {
+ union {
+ struct {
+ struct list_head list;
+ unsigned long colouroff;
+ void *s_mem; /* including colour offset */
+ unsigned int inuse; /* num of objs active in slab */
+ kmem_bufctl_t free;
+ unsigned short nodeid;
+ };
+ struct slab_rcu __slab_cover_slab_rcu;
+ };
+};
+
+/*
* struct array_cache
*
* Purpose:
--
--
To unsubscribe, send a message with 'unsubscribe linux-mm' in
the body to majordomo@kvack.org. For more info on Linux MM,
see: http://www.linux-mm.org/ .
Fight unfair telecom internet charges in Canada: sign http://stopthemeter.ca/
Don't email: <a href=mailto:"dont@kvack.org"> email@kvack.org </a>
^ permalink raw reply related
* [PATCH] net: add Faraday FTGMAC100 Gigabit Ethernet driver
From: Po-Yu Chuang @ 2011-03-10 8:08 UTC (permalink / raw)
To: netdev; +Cc: linux-kernel, Po-Yu Chuang
From: Po-Yu Chuang <ratbert@faraday-tech.com>
FTGMAC100 Ethernet Media Access Controller supports 10/100/1000 Mbps
and MII/GMII. This driver has been working on some ARM/NDS32 SoC's
including Faraday A369 and Andes AG102.
Signed-off-by: Po-Yu Chuang <ratbert@faraday-tech.com>
---
drivers/net/Kconfig | 9 +
drivers/net/Makefile | 1 +
drivers/net/ftgmac100.c | 1365 +++++++++++++++++++++++++++++++++++++++++++++++
drivers/net/ftgmac100.h | 246 +++++++++
4 files changed, 1621 insertions(+), 0 deletions(-)
create mode 100644 drivers/net/ftgmac100.c
create mode 100644 drivers/net/ftgmac100.h
diff --git a/drivers/net/Kconfig b/drivers/net/Kconfig
index 6b12274..b9da914 100644
--- a/drivers/net/Kconfig
+++ b/drivers/net/Kconfig
@@ -2560,6 +2560,15 @@ config PCH_GBE
to Gigabit Ethernet.
This driver enables Gigabit Ethernet function.
+config FTGMAC100
+ tristate "Faraday FTGMAC100 Gigabit Ethernet support"
+ depends on ARM
+ select PHYLIB
+ help
+ This driver supports the FTGMAC100 Gigabit Ethernet controller
+ from Faraday. It is used on Faraday A369, Andes AG102 and some
+ other ARM/NDS32 SoC's.
+
endif # NETDEV_1000
#
diff --git a/drivers/net/Makefile b/drivers/net/Makefile
index 7c21711..a349b26 100644
--- a/drivers/net/Makefile
+++ b/drivers/net/Makefile
@@ -147,6 +147,7 @@ obj-$(CONFIG_FORCEDETH) += forcedeth.o
obj-$(CONFIG_NE_H8300) += ne-h8300.o 8390.o
obj-$(CONFIG_AX88796) += ax88796.o
obj-$(CONFIG_BCM63XX_ENET) += bcm63xx_enet.o
+obj-$(CONFIG_FTGMAC100) += ftgmac100.o
obj-$(CONFIG_FTMAC100) += ftmac100.o
obj-$(CONFIG_TSI108_ETH) += tsi108_eth.o
diff --git a/drivers/net/ftgmac100.c b/drivers/net/ftgmac100.c
new file mode 100644
index 0000000..44699a3
--- /dev/null
+++ b/drivers/net/ftgmac100.c
@@ -0,0 +1,1365 @@
+/*
+ * Faraday FTGMAC100 Gigabit Ethernet
+ *
+ * (C) Copyright 2009-2011 Faraday Technology
+ * Po-Yu Chuang <ratbert@faraday-tech.com>
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License as published by
+ * the Free Software Foundation; either version 2 of the License, or
+ * (at your option) any later version.
+ *
+ * This program is distributed in the hope that it will be useful,
+ * but WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the
+ * GNU General Public License for more details.
+ *
+ * You should have received a copy of the GNU General Public License
+ * along with this program; if not, write to the Free Software
+ * Foundation, Inc., 675 Mass Ave, Cambridge, MA 02139, USA.
+ */
+
+#define pr_fmt(fmt) KBUILD_MODNAME ": " fmt
+
+#include <linux/dma-mapping.h>
+#include <linux/etherdevice.h>
+#include <linux/ethtool.h>
+#include <linux/init.h>
+#include <linux/io.h>
+#include <linux/module.h>
+#include <linux/netdevice.h>
+#include <linux/phy.h>
+#include <linux/platform_device.h>
+#include <net/ip.h>
+
+#include "ftgmac100.h"
+
+#define DRV_NAME "ftgmac100"
+#define DRV_VERSION "0.6"
+
+#define RX_QUEUE_ENTRIES 256 /* must be power of 2 */
+#define TX_QUEUE_ENTRIES 512 /* must be power of 2 */
+
+#define MAX_PKT_SIZE 1518
+#define RX_BUF_SIZE PAGE_SIZE /* must be smaller than 0x3fff */
+
+/******************************************************************************
+ * private data
+ *****************************************************************************/
+struct ftgmac100_descs {
+ struct ftgmac100_rxdes rxdes[RX_QUEUE_ENTRIES];
+ struct ftgmac100_txdes txdes[TX_QUEUE_ENTRIES];
+};
+
+struct ftgmac100 {
+ struct resource *res;
+ void __iomem *base;
+ int irq;
+
+ struct ftgmac100_descs *descs;
+ dma_addr_t descs_dma_addr;
+
+ unsigned int rx_pointer;
+ unsigned int tx_clean_pointer;
+ unsigned int tx_pointer;
+ unsigned int tx_pending;
+
+ spinlock_t tx_lock;
+
+ struct net_device *netdev;
+ struct device *dev;
+ struct napi_struct napi;
+
+ struct mii_bus *mii_bus;
+ int phy_irq[PHY_MAX_ADDR];
+ struct phy_device *phydev;
+ int old_speed;
+};
+
+static int ftgmac100_alloc_rx_page(struct ftgmac100 *priv,
+ struct ftgmac100_rxdes *rxdes);
+
+/******************************************************************************
+ * internal functions (hardware register access)
+ *****************************************************************************/
+#define INT_MASK_ALL_ENABLED (FTGMAC100_INT_RPKT_LOST | \
+ FTGMAC100_INT_XPKT_ETH | \
+ FTGMAC100_INT_XPKT_LOST | \
+ FTGMAC100_INT_AHB_ERR | \
+ FTGMAC100_INT_PHYSTS_CHG | \
+ FTGMAC100_INT_RPKT_BUF | \
+ FTGMAC100_INT_NO_RXBUF)
+
+static void ftgmac100_set_rx_ring_base(struct ftgmac100 *priv, dma_addr_t addr)
+{
+ iowrite32(addr, priv->base + FTGMAC100_OFFSET_RXR_BADR);
+}
+
+static void ftgmac100_set_rx_buffer_size(struct ftgmac100 *priv,
+ unsigned int size)
+{
+ size = FTGMAC100_RBSR_SIZE(size);
+ iowrite32(size, priv->base + FTGMAC100_OFFSET_RBSR);
+}
+
+static void ftgmac100_set_normal_prio_tx_ring_base(struct ftgmac100 *priv,
+ dma_addr_t addr)
+{
+ iowrite32(addr, priv->base + FTGMAC100_OFFSET_NPTXR_BADR);
+}
+
+static void ftgmac100_txdma_normal_prio_start_polling(struct ftgmac100 *priv)
+{
+ iowrite32(1, priv->base + FTGMAC100_OFFSET_NPTXPD);
+}
+
+static int ftgmac100_reset_hw(struct ftgmac100 *priv)
+{
+ struct net_device *netdev = priv->netdev;
+ int i;
+
+ /* NOTE: reset clears all registers */
+ iowrite32(FTGMAC100_MACCR_SW_RST, priv->base + FTGMAC100_OFFSET_MACCR);
+ for (i = 0; i < 5; i++) {
+ unsigned int maccr;
+
+ maccr = ioread32(priv->base + FTGMAC100_OFFSET_MACCR);
+ if (!(maccr & FTGMAC100_MACCR_SW_RST))
+ return 0;
+
+ usleep_range(1000, 10000);
+ }
+
+ netdev_err(netdev, "software reset failed\n");
+ return -EIO;
+}
+
+static void ftgmac100_set_mac(struct ftgmac100 *priv, const unsigned char *mac)
+{
+ unsigned int maddr = mac[0] << 8 | mac[1];
+ unsigned int laddr = mac[2] << 24 | mac[3] << 16 | mac[4] << 8 | mac[5];
+
+ iowrite32(maddr, priv->base + FTGMAC100_OFFSET_MAC_MADR);
+ iowrite32(laddr, priv->base + FTGMAC100_OFFSET_MAC_LADR);
+}
+
+static void ftgmac100_init_hw(struct ftgmac100 *priv)
+{
+ /* setup ring buffer base registers */
+ ftgmac100_set_rx_ring_base(priv,
+ priv->descs_dma_addr +
+ offsetof(struct ftgmac100_descs, rxdes));
+ ftgmac100_set_normal_prio_tx_ring_base(priv,
+ priv->descs_dma_addr +
+ offsetof(struct ftgmac100_descs, txdes));
+
+ ftgmac100_set_rx_buffer_size(priv, RX_BUF_SIZE);
+
+ iowrite32(FTGMAC100_APTC_RXPOLL_CNT(1), priv->base + FTGMAC100_OFFSET_APTC);
+
+ ftgmac100_set_mac(priv, priv->netdev->dev_addr);
+}
+
+#define MACCR_ENABLE_ALL (FTGMAC100_MACCR_TXDMA_EN | \
+ FTGMAC100_MACCR_RXDMA_EN | \
+ FTGMAC100_MACCR_TXMAC_EN | \
+ FTGMAC100_MACCR_RXMAC_EN | \
+ FTGMAC100_MACCR_FULLDUP | \
+ FTGMAC100_MACCR_CRC_APD | \
+ FTGMAC100_MACCR_RX_RUNT | \
+ FTGMAC100_MACCR_RX_BROADPKT)
+
+static void ftgmac100_start_hw(struct ftgmac100 *priv, int speed)
+{
+ int maccr = MACCR_ENABLE_ALL;
+
+ switch (speed) {
+ default:
+ case 10:
+ break;
+
+ case 100:
+ maccr |= FTGMAC100_MACCR_FAST_MODE;
+ break;
+
+ case 1000:
+ maccr |= FTGMAC100_MACCR_GIGA_MODE;
+ break;
+ }
+
+ iowrite32(maccr, priv->base + FTGMAC100_OFFSET_MACCR);
+}
+
+static void ftgmac100_stop_hw(struct ftgmac100 *priv)
+{
+ iowrite32(0, priv->base + FTGMAC100_OFFSET_MACCR);
+}
+
+/******************************************************************************
+ * internal functions (receive descriptor)
+ *****************************************************************************/
+static bool ftgmac100_rxdes_first_segment(struct ftgmac100_rxdes *rxdes)
+{
+ return rxdes->rxdes0 & cpu_to_le32(FTGMAC100_RXDES0_FRS);
+}
+
+static bool ftgmac100_rxdes_last_segment(struct ftgmac100_rxdes *rxdes)
+{
+ return rxdes->rxdes0 & cpu_to_le32(FTGMAC100_RXDES0_LRS);
+}
+
+static bool ftgmac100_rxdes_packet_ready(struct ftgmac100_rxdes *rxdes)
+{
+ return rxdes->rxdes0 & cpu_to_le32(FTGMAC100_RXDES0_RXPKT_RDY);
+}
+
+static void ftgmac100_rxdes_set_dma_own(struct ftgmac100_rxdes *rxdes)
+{
+ /* clear status bits */
+ rxdes->rxdes0 &= cpu_to_le32(FTGMAC100_RXDES0_EDORR);
+}
+
+static bool ftgmac100_rxdes_rx_error(struct ftgmac100_rxdes *rxdes)
+{
+ return rxdes->rxdes0 & cpu_to_le32(FTGMAC100_RXDES0_RX_ERR);
+}
+
+static bool ftgmac100_rxdes_crc_error(struct ftgmac100_rxdes *rxdes)
+{
+ return rxdes->rxdes0 & cpu_to_le32(FTGMAC100_RXDES0_CRC_ERR);
+}
+
+static bool ftgmac100_rxdes_frame_too_long(struct ftgmac100_rxdes *rxdes)
+{
+ return rxdes->rxdes0 & cpu_to_le32(FTGMAC100_RXDES0_FTL);
+}
+
+static bool ftgmac100_rxdes_runt(struct ftgmac100_rxdes *rxdes)
+{
+ return rxdes->rxdes0 & cpu_to_le32(FTGMAC100_RXDES0_RUNT);
+}
+
+static bool ftgmac100_rxdes_odd_nibble(struct ftgmac100_rxdes *rxdes)
+{
+ return rxdes->rxdes0 & cpu_to_le32(FTGMAC100_RXDES0_RX_ODD_NB);
+}
+
+static unsigned int ftgmac100_rxdes_data_length(struct ftgmac100_rxdes *rxdes)
+{
+ return le32_to_cpu(rxdes->rxdes0) & FTGMAC100_RXDES0_VDBC;
+}
+
+static bool ftgmac100_rxdes_multicast(struct ftgmac100_rxdes *rxdes)
+{
+ return rxdes->rxdes0 & cpu_to_le32(FTGMAC100_RXDES0_MULTICAST);
+}
+
+static void ftgmac100_rxdes_set_end_of_ring(struct ftgmac100_rxdes *rxdes)
+{
+ rxdes->rxdes0 |= cpu_to_le32(FTGMAC100_RXDES0_EDORR);
+}
+
+static void ftgmac100_rxdes_set_dma_addr(struct ftgmac100_rxdes *rxdes,
+ dma_addr_t addr)
+{
+ rxdes->rxdes3 = cpu_to_le32(addr);
+}
+
+static dma_addr_t ftgmac100_rxdes_get_dma_addr(struct ftgmac100_rxdes *rxdes)
+{
+ return le32_to_cpu(rxdes->rxdes3);
+}
+
+static bool ftgmac100_rxdes_is_tcp(struct ftgmac100_rxdes *rxdes)
+{
+ return (rxdes->rxdes1 & cpu_to_le32(FTGMAC100_RXDES1_PROT_MASK)) ==
+ cpu_to_le32(FTGMAC100_RXDES1_PROT_TCPIP);
+}
+
+static bool ftgmac100_rxdes_is_udp(struct ftgmac100_rxdes *rxdes)
+{
+ return (rxdes->rxdes1 & cpu_to_le32(FTGMAC100_RXDES1_PROT_MASK)) ==
+ cpu_to_le32(FTGMAC100_RXDES1_PROT_UDPIP);
+}
+
+static bool ftgmac100_rxdes_tcpcs_err(struct ftgmac100_rxdes *rxdes)
+{
+ return rxdes->rxdes1 & cpu_to_le32(FTGMAC100_RXDES1_TCP_CHKSUM_ERR);
+}
+
+static bool ftgmac100_rxdes_udpcs_err(struct ftgmac100_rxdes *rxdes)
+{
+ return rxdes->rxdes1 & cpu_to_le32(FTGMAC100_RXDES1_UDP_CHKSUM_ERR);
+}
+
+static bool ftgmac100_rxdes_ipcs_err(struct ftgmac100_rxdes *rxdes)
+{
+ return rxdes->rxdes1 & cpu_to_le32(FTGMAC100_RXDES1_IP_CHKSUM_ERR);
+}
+
+/*
+ * rxdes2 is not used by hardware. We use it to keep track of page.
+ * Since hardware does not touch it, we can skip cpu_to_le32()/le32_to_cpu().
+ */
+static void ftgmac100_rxdes_set_page(struct ftgmac100_rxdes *rxdes, struct page *page)
+{
+ rxdes->rxdes2 = (unsigned int)page;
+}
+
+static struct page *ftgmac100_rxdes_get_page(struct ftgmac100_rxdes *rxdes)
+{
+ return (struct page*)rxdes->rxdes2;
+}
+
+/******************************************************************************
+ * internal functions (receive)
+ *****************************************************************************/
+static int ftgmac100_next_rx_pointer(int pointer)
+{
+ return (pointer + 1) & (RX_QUEUE_ENTRIES - 1);
+}
+
+static void ftgmac100_rx_pointer_advance(struct ftgmac100 *priv)
+{
+ priv->rx_pointer = ftgmac100_next_rx_pointer(priv->rx_pointer);
+}
+
+static struct ftgmac100_rxdes *ftgmac100_current_rxdes(struct ftgmac100 *priv)
+{
+ return &priv->descs->rxdes[priv->rx_pointer];
+}
+
+static struct ftgmac100_rxdes *
+ftgmac100_rx_locate_first_segment(struct ftgmac100 *priv)
+{
+ struct ftgmac100_rxdes *rxdes = ftgmac100_current_rxdes(priv);
+
+ while (ftgmac100_rxdes_packet_ready(rxdes)) {
+ if (ftgmac100_rxdes_first_segment(rxdes))
+ return rxdes;
+
+ ftgmac100_rxdes_set_dma_own(rxdes);
+ ftgmac100_rx_pointer_advance(priv);
+ rxdes = ftgmac100_current_rxdes(priv);
+ }
+
+ return NULL;
+}
+
+static bool ftgmac100_rx_packet_error(struct ftgmac100 *priv,
+ struct ftgmac100_rxdes *rxdes)
+{
+ struct net_device *netdev = priv->netdev;
+ bool error = false;
+
+ if (unlikely(ftgmac100_rxdes_rx_error(rxdes))) {
+ if (net_ratelimit())
+ netdev_info(netdev, "rx err\n");
+
+ netdev->stats.rx_errors++;
+ error = true;
+ }
+
+ if (unlikely(ftgmac100_rxdes_crc_error(rxdes))) {
+ if (net_ratelimit())
+ netdev_info(netdev, "rx crc err\n");
+
+ netdev->stats.rx_crc_errors++;
+ error = true;
+ } else if (unlikely(ftgmac100_rxdes_ipcs_err(rxdes))) {
+ if (net_ratelimit())
+ netdev_info(netdev, "rx IP checksum err\n");
+
+ error = true;
+ }
+
+ if (unlikely(ftgmac100_rxdes_frame_too_long(rxdes))) {
+ if (net_ratelimit())
+ netdev_info(netdev, "rx frame too long\n");
+
+ netdev->stats.rx_length_errors++;
+ error = true;
+ } else if (unlikely(ftgmac100_rxdes_runt(rxdes))) {
+ if (net_ratelimit())
+ netdev_info(netdev, "rx runt\n");
+
+ netdev->stats.rx_length_errors++;
+ error = true;
+ } else if (unlikely(ftgmac100_rxdes_odd_nibble(rxdes))) {
+ if (net_ratelimit())
+ netdev_info(netdev, "rx odd nibble\n");
+
+ netdev->stats.rx_length_errors++;
+ error = true;
+ }
+
+ return error;
+}
+
+static void ftgmac100_rx_drop_packet(struct ftgmac100 *priv)
+{
+ struct net_device *netdev = priv->netdev;
+ struct ftgmac100_rxdes *rxdes = ftgmac100_current_rxdes(priv);
+ bool done = false;
+
+ if (net_ratelimit())
+ netdev_dbg(netdev, "drop packet %p\n", rxdes);
+
+ do {
+ if (ftgmac100_rxdes_last_segment(rxdes))
+ done = true;
+
+ ftgmac100_rxdes_set_dma_own(rxdes);
+ ftgmac100_rx_pointer_advance(priv);
+ rxdes = ftgmac100_current_rxdes(priv);
+ } while (!done && ftgmac100_rxdes_packet_ready(rxdes));
+
+ netdev->stats.rx_dropped++;
+}
+
+static bool ftgmac100_rx_packet(struct ftgmac100 *priv, int *processed)
+{
+ struct net_device *netdev = priv->netdev;
+ struct ftgmac100_rxdes *rxdes;
+ struct sk_buff *skb;
+ bool done = false;
+
+ rxdes = ftgmac100_rx_locate_first_segment(priv);
+ if (!rxdes)
+ return false;
+
+ if (unlikely(ftgmac100_rx_packet_error(priv, rxdes))) {
+ ftgmac100_rx_drop_packet(priv);
+ return true;
+ }
+
+ /* start processing */
+ skb = netdev_alloc_skb_ip_align(netdev, 128);
+ if (unlikely(!skb)) {
+ if (net_ratelimit())
+ netdev_err(netdev, "rx skb alloc failed\n");
+
+ ftgmac100_rx_drop_packet(priv);
+ return true;
+ }
+
+ if (unlikely(ftgmac100_rxdes_multicast(rxdes)))
+ netdev->stats.multicast++;
+
+ /*
+ * It seems that HW does checksum incorrectly with fragmented packets,
+ * so we are conservatively here - if HW checksum error, let software
+ * do the checksum again.
+ */
+ if ((ftgmac100_rxdes_is_tcp(rxdes) && !ftgmac100_rxdes_tcpcs_err(rxdes)) ||
+ (ftgmac100_rxdes_is_udp(rxdes) && !ftgmac100_rxdes_udpcs_err(rxdes)))
+ skb->ip_summed = CHECKSUM_UNNECESSARY;
+
+ do {
+ dma_addr_t map = ftgmac100_rxdes_get_dma_addr(rxdes);
+ struct page *page = ftgmac100_rxdes_get_page(rxdes);
+ unsigned int size;
+
+ dma_unmap_page(priv->dev, map, RX_BUF_SIZE, DMA_FROM_DEVICE);
+
+ size = ftgmac100_rxdes_data_length(rxdes);
+ skb_fill_page_desc(skb, skb_shinfo(skb)->nr_frags, page, 0, size);
+
+ skb->len += size;
+ skb->data_len += size;
+ skb->truesize += size;
+
+ if (ftgmac100_rxdes_last_segment(rxdes))
+ done = true;
+
+ ftgmac100_alloc_rx_page(priv, rxdes);
+
+ ftgmac100_rx_pointer_advance(priv);
+ rxdes = ftgmac100_current_rxdes(priv);
+ } while (!done);
+
+ __pskb_pull_tail(skb, min(skb->len, 64U));
+ skb->protocol = eth_type_trans(skb, netdev);
+
+ netdev->stats.rx_packets++;
+ netdev->stats.rx_bytes += skb->len;
+
+ /* push packet to protocol stack */
+ netif_receive_skb(skb);
+
+ (*processed)++;
+ return true;
+}
+
+/******************************************************************************
+ * internal functions (transmit descriptor)
+ *****************************************************************************/
+static void ftgmac100_txdes_reset(struct ftgmac100_txdes *txdes)
+{
+ /* clear all except end of ring bit */
+ txdes->txdes0 &= cpu_to_le32(FTGMAC100_TXDES0_EDOTR);
+ txdes->txdes1 = 0;
+ txdes->txdes2 = 0;
+ txdes->txdes3 = 0;
+}
+
+static bool ftgmac100_txdes_owned_by_dma(struct ftgmac100_txdes *txdes)
+{
+ return txdes->txdes0 & cpu_to_le32(FTGMAC100_TXDES0_TXDMA_OWN);
+}
+
+static void ftgmac100_txdes_set_dma_own(struct ftgmac100_txdes *txdes)
+{
+ /*
+ * Make sure dma own bit will not be set before any other
+ * descriptor fields.
+ */
+ wmb();
+ txdes->txdes0 |= cpu_to_le32(FTGMAC100_TXDES0_TXDMA_OWN);
+}
+
+static void ftgmac100_txdes_set_end_of_ring(struct ftgmac100_txdes *txdes)
+{
+ txdes->txdes0 |= cpu_to_le32(FTGMAC100_TXDES0_EDOTR);
+}
+
+static void ftgmac100_txdes_set_first_segment(struct ftgmac100_txdes *txdes)
+{
+ txdes->txdes0 |= cpu_to_le32(FTGMAC100_TXDES0_FTS);
+}
+
+static void ftgmac100_txdes_set_last_segment(struct ftgmac100_txdes *txdes)
+{
+ txdes->txdes0 |= cpu_to_le32(FTGMAC100_TXDES0_LTS);
+}
+
+static void ftgmac100_txdes_set_buffer_size(struct ftgmac100_txdes *txdes,
+ unsigned int len)
+{
+ txdes->txdes0 |= cpu_to_le32(FTGMAC100_TXDES0_TXBUF_SIZE(len));
+}
+
+static void ftgmac100_txdes_set_txint(struct ftgmac100_txdes *txdes)
+{
+ txdes->txdes1 |= cpu_to_le32(FTGMAC100_TXDES1_TXIC);
+}
+
+static void ftgmac100_txdes_set_tcpcs(struct ftgmac100_txdes *txdes)
+{
+ txdes->txdes1 |= cpu_to_le32(FTGMAC100_TXDES1_TCP_CHKSUM);
+}
+
+static void ftgmac100_txdes_set_udpcs(struct ftgmac100_txdes *txdes)
+{
+ txdes->txdes1 |= cpu_to_le32(FTGMAC100_TXDES1_UDP_CHKSUM);
+}
+
+static void ftgmac100_txdes_set_ipcs(struct ftgmac100_txdes *txdes)
+{
+ txdes->txdes1 |= cpu_to_le32(FTGMAC100_TXDES1_IP_CHKSUM);
+}
+
+static void ftgmac100_txdes_set_dma_addr(struct ftgmac100_txdes *txdes,
+ dma_addr_t addr)
+{
+ txdes->txdes3 = cpu_to_le32(addr);
+}
+
+static dma_addr_t ftgmac100_txdes_get_dma_addr(struct ftgmac100_txdes *txdes)
+{
+ return le32_to_cpu(txdes->txdes3);
+}
+
+/*
+ * txdes2 is not used by hardware. We use it to keep track of socket buffer.
+ * Since hardware does not touch it, we can skip cpu_to_le32()/le32_to_cpu().
+ */
+static void ftgmac100_txdes_set_skb(struct ftgmac100_txdes *txdes,
+ struct sk_buff *skb)
+{
+ txdes->txdes2 = (unsigned int)skb;
+}
+
+static struct sk_buff *ftgmac100_txdes_get_skb(struct ftgmac100_txdes *txdes)
+{
+ return (struct sk_buff *)txdes->txdes2;
+}
+
+/******************************************************************************
+ * internal functions (transmit)
+ *****************************************************************************/
+static int ftgmac100_next_tx_pointer(int pointer)
+{
+ return (pointer + 1) & (TX_QUEUE_ENTRIES - 1);
+}
+
+static void ftgmac100_tx_pointer_advance(struct ftgmac100 *priv)
+{
+ priv->tx_pointer = ftgmac100_next_tx_pointer(priv->tx_pointer);
+}
+
+static void ftgmac100_tx_clean_pointer_advance(struct ftgmac100 *priv)
+{
+ priv->tx_clean_pointer = ftgmac100_next_tx_pointer(priv->tx_clean_pointer);
+}
+
+static struct ftgmac100_txdes *ftgmac100_current_txdes(struct ftgmac100 *priv)
+{
+ return &priv->descs->txdes[priv->tx_pointer];
+}
+
+static struct ftgmac100_txdes *
+ftgmac100_current_clean_txdes(struct ftgmac100 *priv)
+{
+ return &priv->descs->txdes[priv->tx_clean_pointer];
+}
+
+static bool ftgmac100_tx_complete_packet(struct ftgmac100 *priv)
+{
+ struct net_device *netdev = priv->netdev;
+ struct ftgmac100_txdes *txdes;
+ struct sk_buff *skb;
+ dma_addr_t map;
+
+ if (priv->tx_pending == 0)
+ return false;
+
+ txdes = ftgmac100_current_clean_txdes(priv);
+
+ if (ftgmac100_txdes_owned_by_dma(txdes))
+ return false;
+
+ skb = ftgmac100_txdes_get_skb(txdes);
+ map = ftgmac100_txdes_get_dma_addr(txdes);
+
+ netdev->stats.tx_packets++;
+ netdev->stats.tx_bytes += skb->len;
+
+ dma_unmap_single(priv->dev, map, skb_headlen(skb), DMA_TO_DEVICE);
+
+ dev_kfree_skb(skb);
+
+ ftgmac100_txdes_reset(txdes);
+
+ ftgmac100_tx_clean_pointer_advance(priv);
+
+ spin_lock(&priv->tx_lock);
+ priv->tx_pending--;
+ spin_unlock(&priv->tx_lock);
+ netif_wake_queue(netdev);
+
+ return true;
+}
+
+static void ftgmac100_tx_complete(struct ftgmac100 *priv)
+{
+ while (ftgmac100_tx_complete_packet(priv))
+ ;
+}
+
+static int ftgmac100_xmit(struct ftgmac100 *priv, struct sk_buff *skb,
+ dma_addr_t map)
+{
+ struct net_device *netdev = priv->netdev;
+ struct ftgmac100_txdes *txdes;
+ unsigned int len = (skb->len < ETH_ZLEN) ? ETH_ZLEN : skb->len;
+
+ txdes = ftgmac100_current_txdes(priv);
+ ftgmac100_tx_pointer_advance(priv);
+
+ /* setup TX descriptor */
+ ftgmac100_txdes_set_skb(txdes, skb);
+ ftgmac100_txdes_set_dma_addr(txdes, map);
+ ftgmac100_txdes_set_buffer_size(txdes, len);
+
+ ftgmac100_txdes_set_first_segment(txdes);
+ ftgmac100_txdes_set_last_segment(txdes);
+ ftgmac100_txdes_set_txint(txdes);
+ if (skb->ip_summed == CHECKSUM_PARTIAL) {
+ __be16 protocol = skb->protocol;
+
+ if (protocol == cpu_to_be16(ETH_P_IP)) {
+ u8 ip_proto = ip_hdr(skb)->protocol;
+
+ ftgmac100_txdes_set_ipcs(txdes);
+ if (ip_proto == IPPROTO_TCP)
+ ftgmac100_txdes_set_tcpcs(txdes);
+ else if (ip_proto == IPPROTO_UDP)
+ ftgmac100_txdes_set_udpcs(txdes);
+ }
+ }
+
+ spin_lock(&priv->tx_lock);
+ priv->tx_pending++;
+ if (priv->tx_pending == TX_QUEUE_ENTRIES)
+ netif_stop_queue(netdev);
+
+ /* start transmit */
+ ftgmac100_txdes_set_dma_own(txdes);
+ spin_unlock(&priv->tx_lock);
+
+ ftgmac100_txdma_normal_prio_start_polling(priv);
+
+ return NETDEV_TX_OK;
+}
+
+/******************************************************************************
+ * internal functions (buffer)
+ *****************************************************************************/
+static int ftgmac100_alloc_rx_page(struct ftgmac100 *priv,
+ struct ftgmac100_rxdes *rxdes)
+{
+ struct net_device *netdev = priv->netdev;
+ struct page *page;
+ dma_addr_t map;
+
+ page = alloc_page(GFP_KERNEL);
+ if (!page) {
+ if (net_ratelimit())
+ netdev_err(netdev, "failed to allocate rx page\n");
+ return -ENOMEM;
+ }
+
+ map = dma_map_page(priv->dev, page, 0, RX_BUF_SIZE, DMA_FROM_DEVICE);
+ if (unlikely(dma_mapping_error(priv->dev, map))) {
+ if (net_ratelimit())
+ netdev_err(netdev, "failed to map rx page\n");
+ __free_page(page);
+ return -ENOMEM;
+ }
+
+ ftgmac100_rxdes_set_page(rxdes, page);
+ ftgmac100_rxdes_set_dma_addr(rxdes, map);
+ ftgmac100_rxdes_set_dma_own(rxdes);
+ return 0;
+}
+
+static void ftgmac100_free_buffers(struct ftgmac100 *priv)
+{
+ int i;
+
+ for (i = 0; i < RX_QUEUE_ENTRIES; i++) {
+ struct ftgmac100_rxdes *rxdes = &priv->descs->rxdes[i];
+ struct page *page = ftgmac100_rxdes_get_page(rxdes);
+ dma_addr_t map = ftgmac100_rxdes_get_dma_addr(rxdes);
+
+ if (!page)
+ continue;
+
+ dma_unmap_page(priv->dev, map, RX_BUF_SIZE, DMA_FROM_DEVICE);
+ __free_page(page);
+ }
+
+ for (i = 0; i < TX_QUEUE_ENTRIES; i++) {
+ struct ftgmac100_txdes *txdes = &priv->descs->txdes[i];
+ struct sk_buff *skb = ftgmac100_txdes_get_skb(txdes);
+ dma_addr_t map = ftgmac100_txdes_get_dma_addr(txdes);
+
+ if (!skb)
+ continue;
+
+ dma_unmap_single(priv->dev, map, skb_headlen(skb), DMA_TO_DEVICE);
+ dev_kfree_skb(skb);
+ }
+
+ dma_free_coherent(priv->dev, sizeof(struct ftgmac100_descs),
+ priv->descs, priv->descs_dma_addr);
+}
+
+static int ftgmac100_alloc_buffers(struct ftgmac100 *priv)
+{
+ int i;
+
+ priv->descs = dma_alloc_coherent(priv->dev,
+ sizeof(struct ftgmac100_descs),
+ &priv->descs_dma_addr, GFP_KERNEL);
+ if (!priv->descs)
+ return -ENOMEM;
+
+ memset(priv->descs, 0, sizeof(struct ftgmac100_descs));
+
+ /* initialize RX ring */
+ ftgmac100_rxdes_set_end_of_ring(&priv->descs->rxdes[RX_QUEUE_ENTRIES - 1]);
+
+ for (i = 0; i < RX_QUEUE_ENTRIES; i++) {
+ struct ftgmac100_rxdes *rxdes = &priv->descs->rxdes[i];
+
+ if (ftgmac100_alloc_rx_page(priv, rxdes))
+ goto err;
+ }
+
+ /* initialize TX ring */
+ ftgmac100_txdes_set_end_of_ring(&priv->descs->txdes[TX_QUEUE_ENTRIES - 1]);
+ return 0;
+
+err:
+ ftgmac100_free_buffers(priv);
+ return -ENOMEM;
+}
+
+/******************************************************************************
+ * internal functions (mdio)
+ *****************************************************************************/
+static void ftgmac100_adjust_link(struct net_device *netdev)
+{
+ struct ftgmac100 *priv = netdev_priv(netdev);
+ struct phy_device *phydev = priv->phydev;
+ int ier;
+
+ if (phydev->speed == priv->old_speed)
+ return;
+
+ priv->old_speed = phydev->speed;
+
+ ier = ioread32(priv->base + FTGMAC100_OFFSET_IER);
+
+ /* disable all interrupts */
+ iowrite32(0, priv->base + FTGMAC100_OFFSET_IER);
+
+ netif_stop_queue(netdev);
+ ftgmac100_stop_hw(priv);
+
+ netif_start_queue(netdev);
+ ftgmac100_init_hw(priv);
+ ftgmac100_start_hw(priv, phydev->speed);
+
+ /* re-enable interrupts */
+ iowrite32(ier, priv->base + FTGMAC100_OFFSET_IER);
+}
+
+static int ftgmac100_mii_probe(struct ftgmac100 *priv)
+{
+ struct net_device *netdev = priv->netdev;
+ struct phy_device *phydev = NULL;
+ int i;
+
+ /* search for connect PHY device */
+ for (i = 0; i < PHY_MAX_ADDR; i++) {
+ struct phy_device *tmp = priv->mii_bus->phy_map[i];
+
+ if (tmp) {
+ phydev = tmp;
+ break;
+ }
+ }
+
+ /* now we are supposed to have a proper phydev, to attach to... */
+ if (!phydev) {
+ netdev_info(netdev, "%s: no PHY found\n", netdev->name);
+ return -ENODEV;
+ }
+
+ phydev = phy_connect(netdev, dev_name(&phydev->dev),
+ &ftgmac100_adjust_link, 0,
+ PHY_INTERFACE_MODE_GMII);
+
+ if (IS_ERR(phydev)) {
+ netdev_err(netdev, "%s: Could not attach to PHY\n", netdev->name);
+ return PTR_ERR(phydev);
+ }
+
+ priv->phydev = phydev;
+ return 0;
+}
+
+/******************************************************************************
+ * struct mii_bus functions
+ *****************************************************************************/
+static int ftgmac100_mdiobus_read(struct mii_bus *bus, int phy_addr, int regnum)
+{
+ struct net_device *netdev = bus->priv;
+ struct ftgmac100 *priv = netdev_priv(netdev);
+ unsigned int phycr;
+ int i;
+
+ phycr = ioread32(priv->base + FTGMAC100_OFFSET_PHYCR);
+
+ /* preserve MDC cycle threshold */
+ phycr &= FTGMAC100_PHYCR_MDC_CYCTHR_MASK;
+
+ phycr |= FTGMAC100_PHYCR_PHYAD(phy_addr) |
+ FTGMAC100_PHYCR_REGAD(regnum) |
+ FTGMAC100_PHYCR_MIIRD;
+
+ iowrite32(phycr, priv->base + FTGMAC100_OFFSET_PHYCR);
+
+ for (i = 0; i < 10; i++) {
+ phycr = ioread32(priv->base + FTGMAC100_OFFSET_PHYCR);
+
+ if ((phycr & FTGMAC100_PHYCR_MIIRD) == 0) {
+ int data;
+
+ data = ioread32(priv->base + FTGMAC100_OFFSET_PHYDATA);
+ return FTGMAC100_PHYDATA_MIIRDATA(data);
+ }
+
+ usleep_range(100, 1000);
+ }
+
+ netdev_err(netdev, "mdio read timed out\n");
+ return -EIO;
+}
+
+static int ftgmac100_mdiobus_write(struct mii_bus *bus, int phy_addr,
+ int regnum, u16 value)
+{
+ struct net_device *netdev = bus->priv;
+ struct ftgmac100 *priv = netdev_priv(netdev);
+ unsigned int phycr;
+ int data;
+ int i;
+
+ phycr = ioread32(priv->base + FTGMAC100_OFFSET_PHYCR);
+
+ /* preserve MDC cycle threshold */
+ phycr &= FTGMAC100_PHYCR_MDC_CYCTHR_MASK;
+
+ phycr |= FTGMAC100_PHYCR_PHYAD(phy_addr) |
+ FTGMAC100_PHYCR_REGAD(regnum) |
+ FTGMAC100_PHYCR_MIIWR;
+
+ data = FTGMAC100_PHYDATA_MIIWDATA(value);
+
+ iowrite32(data, priv->base + FTGMAC100_OFFSET_PHYDATA);
+ iowrite32(phycr, priv->base + FTGMAC100_OFFSET_PHYCR);
+
+ for (i = 0; i < 10; i++) {
+ phycr = ioread32(priv->base + FTGMAC100_OFFSET_PHYCR);
+
+ if ((phycr & FTGMAC100_PHYCR_MIIWR) == 0)
+ return 0;
+
+ usleep_range(100, 1000);
+ }
+
+ netdev_err(netdev, "mdio write timed out\n");
+ return -EIO;
+}
+
+static int ftgmac100_mdiobus_reset(struct mii_bus *bus)
+{
+ return 0;
+}
+
+/******************************************************************************
+ * struct ethtool_ops functions
+ *****************************************************************************/
+static void ftgmac100_get_drvinfo(struct net_device *netdev,
+ struct ethtool_drvinfo *info)
+{
+ strcpy(info->driver, DRV_NAME);
+ strcpy(info->version, DRV_VERSION);
+ strcpy(info->bus_info, dev_name(&netdev->dev));
+}
+
+static int ftgmac100_get_settings(struct net_device *netdev,
+ struct ethtool_cmd *cmd)
+{
+ struct ftgmac100 *priv = netdev_priv(netdev);
+
+ return phy_ethtool_gset(priv->phydev, cmd);
+}
+
+static int ftgmac100_set_settings(struct net_device *netdev,
+ struct ethtool_cmd *cmd)
+{
+ struct ftgmac100 *priv = netdev_priv(netdev);
+
+ return phy_ethtool_sset(priv->phydev, cmd);
+}
+
+static const struct ethtool_ops ftgmac100_ethtool_ops = {
+ .set_settings = ftgmac100_set_settings,
+ .get_settings = ftgmac100_get_settings,
+ .get_drvinfo = ftgmac100_get_drvinfo,
+ .get_link = ethtool_op_get_link,
+};
+
+/******************************************************************************
+ * interrupt handler
+ *****************************************************************************/
+static irqreturn_t ftgmac100_interrupt(int irq, void *dev_id)
+{
+ struct net_device *netdev = dev_id;
+ struct ftgmac100 *priv = netdev_priv(netdev);
+
+ if (likely(netif_running(netdev))) {
+ /* Disable interrupts for polling */
+ iowrite32(0, priv->base + FTGMAC100_OFFSET_IER);
+ napi_schedule(&priv->napi);
+ }
+
+ return IRQ_HANDLED;
+}
+
+/******************************************************************************
+ * struct napi_struct functions
+ *****************************************************************************/
+static int ftgmac100_poll(struct napi_struct *napi, int budget)
+{
+ struct ftgmac100 *priv = container_of(napi, struct ftgmac100, napi);
+ struct net_device *netdev = priv->netdev;
+ unsigned int status;
+ bool completed = true;
+ int rx = 0;
+
+ status = ioread32(priv->base + FTGMAC100_OFFSET_ISR);
+ iowrite32(status, priv->base + FTGMAC100_OFFSET_ISR);
+
+ if (status & (FTGMAC100_INT_RPKT_BUF | FTGMAC100_INT_NO_RXBUF)) {
+ /*
+ * FTGMAC100_INT_RPKT_BUF:
+ * RX DMA has received packets into RX buffer successfully
+ *
+ * FTGMAC100_INT_NO_RXBUF:
+ * RX buffer unavailable
+ */
+ bool retry;
+
+ do {
+ retry = ftgmac100_rx_packet(priv, &rx);
+ } while (retry && rx < budget);
+
+ if (retry && rx == budget)
+ completed = false;
+ }
+
+ if (status & (FTGMAC100_INT_XPKT_ETH | FTGMAC100_INT_XPKT_LOST)) {
+ /*
+ * FTGMAC100_INT_XPKT_ETH:
+ * packet transmitted to ethernet successfully
+ *
+ * FTGMAC100_INT_XPKT_LOST:
+ * packet transmitted to ethernet lost due to late
+ * collision or excessive collision
+ */
+ ftgmac100_tx_complete(priv);
+ }
+
+ if (status & (FTGMAC100_INT_NO_RXBUF | FTGMAC100_INT_RPKT_LOST |
+ FTGMAC100_INT_AHB_ERR | FTGMAC100_INT_PHYSTS_CHG)) {
+ if (net_ratelimit())
+ netdev_info(netdev, "[ISR] = 0x%x: %s%s%s%s\n", status,
+ status & FTGMAC100_INT_NO_RXBUF ? "NO_RXBUF " : "",
+ status & FTGMAC100_INT_RPKT_LOST ? "RPKT_LOST " : "",
+ status & FTGMAC100_INT_AHB_ERR ? "AHB_ERR " : "",
+ status & FTGMAC100_INT_PHYSTS_CHG ? "PHYSTS_CHG" : "");
+
+ if (status & FTGMAC100_INT_NO_RXBUF) {
+ /* RX buffer unavailable */
+ netdev->stats.rx_over_errors++;
+ }
+
+ if (status & FTGMAC100_INT_RPKT_LOST) {
+ /* received packet lost due to RX FIFO full */
+ netdev->stats.rx_fifo_errors++;
+ }
+ }
+
+ if (completed) {
+ napi_complete(napi);
+
+ /* enable all interrupts */
+ iowrite32(INT_MASK_ALL_ENABLED, priv->base + FTGMAC100_OFFSET_IER);
+ }
+
+ return rx;
+}
+
+/******************************************************************************
+ * struct net_device_ops functions
+ *****************************************************************************/
+static int ftgmac100_open(struct net_device *netdev)
+{
+ struct ftgmac100 *priv = netdev_priv(netdev);
+ int err;
+
+ err = ftgmac100_alloc_buffers(priv);
+ if (err) {
+ netdev_err(netdev, "failed to allocate buffers\n");
+ goto err_alloc;
+ }
+
+ err = request_irq(priv->irq, ftgmac100_interrupt, 0, netdev->name, netdev);
+ if (err) {
+ netdev_err(netdev, "failed to request irq %d\n", priv->irq);
+ goto err_irq;
+ }
+
+ priv->rx_pointer = 0;
+ priv->tx_clean_pointer = 0;
+ priv->tx_pointer = 0;
+ priv->tx_pending = 0;
+
+ err = ftgmac100_reset_hw(priv);
+ if (err)
+ goto err_hw;
+
+ ftgmac100_init_hw(priv);
+ ftgmac100_start_hw(priv, 10);
+
+ phy_start(priv->phydev);
+
+ napi_enable(&priv->napi);
+ netif_start_queue(netdev);
+
+ /* enable all interrupts */
+ iowrite32(INT_MASK_ALL_ENABLED, priv->base + FTGMAC100_OFFSET_IER);
+ return 0;
+
+err_hw:
+ free_irq(priv->irq, netdev);
+err_irq:
+ ftgmac100_free_buffers(priv);
+err_alloc:
+ return err;
+}
+
+static int ftgmac100_stop(struct net_device *netdev)
+{
+ struct ftgmac100 *priv = netdev_priv(netdev);
+
+ /* disable all interrupts */
+ iowrite32(0, priv->base + FTGMAC100_OFFSET_IER);
+
+ netif_stop_queue(netdev);
+ napi_disable(&priv->napi);
+ phy_stop(priv->phydev);
+
+ ftgmac100_stop_hw(priv);
+ free_irq(priv->irq, netdev);
+ ftgmac100_free_buffers(priv);
+
+ return 0;
+}
+
+static int ftgmac100_hard_start_xmit(struct sk_buff *skb,
+ struct net_device *netdev)
+{
+ struct ftgmac100 *priv = netdev_priv(netdev);
+ dma_addr_t map;
+
+ if (unlikely(skb->len > MAX_PKT_SIZE)) {
+ if (net_ratelimit())
+ netdev_dbg(netdev, "tx packet too big\n");
+
+ netdev->stats.tx_dropped++;
+ dev_kfree_skb(skb);
+ return NETDEV_TX_OK;
+ }
+
+ map = dma_map_single(priv->dev, skb->data, skb_headlen(skb), DMA_TO_DEVICE);
+ if (unlikely(dma_mapping_error(priv->dev, map))) {
+ /* drop packet */
+ if (net_ratelimit())
+ netdev_err(netdev, "map socket buffer failed\n");
+
+ netdev->stats.tx_dropped++;
+ dev_kfree_skb(skb);
+ return NETDEV_TX_OK;
+ }
+
+ return ftgmac100_xmit(priv, skb, map);
+}
+
+/* optional */
+static int ftgmac100_do_ioctl(struct net_device *netdev, struct ifreq *ifr, int cmd)
+{
+ struct ftgmac100 *priv = netdev_priv(netdev);
+
+ return phy_mii_ioctl(priv->phydev, ifr, cmd);
+}
+
+static const struct net_device_ops ftgmac100_netdev_ops = {
+ .ndo_open = ftgmac100_open,
+ .ndo_stop = ftgmac100_stop,
+ .ndo_start_xmit = ftgmac100_hard_start_xmit,
+ .ndo_set_mac_address = eth_mac_addr,
+ .ndo_validate_addr = eth_validate_addr,
+ .ndo_do_ioctl = ftgmac100_do_ioctl,
+};
+
+/******************************************************************************
+ * struct platform_driver functions
+ *****************************************************************************/
+static int ftgmac100_probe(struct platform_device *pdev)
+{
+ struct resource *res;
+ int irq;
+ struct net_device *netdev;
+ struct ftgmac100 *priv;
+ int err;
+ int i;
+
+ if (!pdev)
+ return -ENODEV;
+
+ res = platform_get_resource(pdev, IORESOURCE_MEM, 0);
+ if (!res)
+ return -ENXIO;
+
+ irq = platform_get_irq(pdev, 0);
+ if (irq < 0)
+ return irq;
+
+ /* setup net_device */
+ netdev = alloc_etherdev(sizeof(*priv));
+ if (!netdev) {
+ err = -ENOMEM;
+ goto err_alloc_etherdev;
+ }
+
+ SET_NETDEV_DEV(netdev, &pdev->dev);
+
+ SET_ETHTOOL_OPS(netdev, &ftgmac100_ethtool_ops);
+ netdev->netdev_ops = &ftgmac100_netdev_ops;
+ netdev->features = NETIF_F_IP_CSUM;
+
+ platform_set_drvdata(pdev, netdev);
+
+ /* setup private data */
+ priv = netdev_priv(netdev);
+ priv->netdev = netdev;
+ priv->dev = &pdev->dev;
+
+ spin_lock_init(&priv->tx_lock);
+
+ /* initialize NAPI */
+ netif_napi_add(netdev, &priv->napi, ftgmac100_poll, 64);
+
+ /* map io memory */
+ priv->res = request_mem_region(res->start, resource_size(res),
+ dev_name(&pdev->dev));
+ if (!priv->res) {
+ dev_err(&pdev->dev, "Could not reserve memory region\n");
+ err = -ENOMEM;
+ goto err_req_mem;
+ }
+
+ priv->base = ioremap(res->start, res->end - res->start);
+ if (!priv->base) {
+ dev_err(&pdev->dev, "Failed to ioremap ethernet registers\n");
+ err = -EIO;
+ goto err_ioremap;
+ }
+
+ priv->irq = irq;
+
+ /* initialize mdio bus */
+ priv->mii_bus = mdiobus_alloc();
+ if (!priv->mii_bus) {
+ err = -EIO;
+ goto err_alloc_mdiobus;
+ }
+
+ priv->mii_bus->name = "ftgmac100_mdio";
+ snprintf(priv->mii_bus->id, MII_BUS_ID_SIZE, "ftgmac100_mii");
+
+ priv->mii_bus->priv = netdev;
+ priv->mii_bus->read = ftgmac100_mdiobus_read;
+ priv->mii_bus->write = ftgmac100_mdiobus_write;
+ priv->mii_bus->reset = ftgmac100_mdiobus_reset;
+ priv->mii_bus->irq = priv->phy_irq;
+
+ for (i = 0; i < PHY_MAX_ADDR; i++)
+ priv->mii_bus->irq[i] = PHY_POLL;
+
+ err = mdiobus_register(priv->mii_bus);
+ if (err) {
+ dev_err(&pdev->dev, "Cannot register MDIO bus!\n");
+ goto err_register_mdiobus;
+ }
+
+ err = ftgmac100_mii_probe(priv);
+ if (err) {
+ dev_err(&pdev->dev, "MII Probe failed!\n");
+ goto err_mii_probe;
+ }
+
+ /* register network device */
+ err = register_netdev(netdev);
+ if (err) {
+ dev_err(&pdev->dev, "Failed to register netdev\n");
+ goto err_register_netdev;
+ }
+
+ netdev_info(netdev, "irq %d, mapped at %p\n", priv->irq, priv->base);
+
+ if (!is_valid_ether_addr(netdev->dev_addr)) {
+ random_ether_addr(netdev->dev_addr);
+ netdev_info(netdev, "generated random MAC address %pM\n",
+ netdev->dev_addr);
+ }
+
+ return 0;
+
+err_register_netdev:
+ phy_disconnect(priv->phydev);
+err_mii_probe:
+ mdiobus_unregister(priv->mii_bus);
+err_register_mdiobus:
+ mdiobus_free(priv->mii_bus);
+err_alloc_mdiobus:
+ iounmap(priv->base);
+err_ioremap:
+ release_resource(priv->res);
+err_req_mem:
+ netif_napi_del(&priv->napi);
+ platform_set_drvdata(pdev, NULL);
+ free_netdev(netdev);
+err_alloc_etherdev:
+ return err;
+}
+
+static int __exit ftgmac100_remove(struct platform_device *pdev)
+{
+ struct net_device *netdev;
+ struct ftgmac100 *priv;
+
+ netdev = platform_get_drvdata(pdev);
+ priv = netdev_priv(netdev);
+
+ unregister_netdev(netdev);
+
+ phy_disconnect(priv->phydev);
+ mdiobus_unregister(priv->mii_bus);
+ mdiobus_free(priv->mii_bus);
+
+ iounmap(priv->base);
+ release_resource(priv->res);
+
+ netif_napi_del(&priv->napi);
+ platform_set_drvdata(pdev, NULL);
+ free_netdev(netdev);
+ return 0;
+}
+
+static struct platform_driver ftgmac100_driver = {
+ .probe = ftgmac100_probe,
+ .remove = __exit_p(ftgmac100_remove),
+ .driver = {
+ .name = DRV_NAME,
+ .owner = THIS_MODULE,
+ },
+};
+
+/******************************************************************************
+ * initialization / finalization
+ *****************************************************************************/
+static int __init ftgmac100_init(void)
+{
+ pr_info("Loading version " DRV_VERSION " ...\n");
+ return platform_driver_register(&ftgmac100_driver);
+}
+
+static void __exit ftgmac100_exit(void)
+{
+ platform_driver_unregister(&ftgmac100_driver);
+}
+
+module_init(ftgmac100_init);
+module_exit(ftgmac100_exit);
+
+MODULE_AUTHOR("Po-Yu Chuang <ratbert@faraday-tech.com>");
+MODULE_DESCRIPTION("FTGMAC100 driver");
+MODULE_LICENSE("GPL");
diff --git a/drivers/net/ftgmac100.h b/drivers/net/ftgmac100.h
new file mode 100644
index 0000000..13408d4
--- /dev/null
+++ b/drivers/net/ftgmac100.h
@@ -0,0 +1,246 @@
+/*
+ * Faraday FTGMAC100 Gigabit Ethernet
+ *
+ * (C) Copyright 2009-2011 Faraday Technology
+ * Po-Yu Chuang <ratbert@faraday-tech.com>
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License as published by
+ * the Free Software Foundation; either version 2 of the License, or
+ * (at your option) any later version.
+ *
+ * This program is distributed in the hope that it will be useful,
+ * but WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the
+ * GNU General Public License for more details.
+ *
+ * You should have received a copy of the GNU General Public License
+ * along with this program; if not, write to the Free Software
+ * Foundation, Inc., 675 Mass Ave, Cambridge, MA 02139, USA.
+ */
+
+#ifndef __FTGMAC100_H
+#define __FTGMAC100_H
+
+#define FTGMAC100_OFFSET_ISR 0x00
+#define FTGMAC100_OFFSET_IER 0x04
+#define FTGMAC100_OFFSET_MAC_MADR 0x08
+#define FTGMAC100_OFFSET_MAC_LADR 0x0c
+#define FTGMAC100_OFFSET_MAHT0 0x10
+#define FTGMAC100_OFFSET_MAHT1 0x14
+#define FTGMAC100_OFFSET_NPTXPD 0x18
+#define FTGMAC100_OFFSET_RXPD 0x1c
+#define FTGMAC100_OFFSET_NPTXR_BADR 0x20
+#define FTGMAC100_OFFSET_RXR_BADR 0x24
+#define FTGMAC100_OFFSET_HPTXPD 0x28
+#define FTGMAC100_OFFSET_HPTXR_BADR 0x2c
+#define FTGMAC100_OFFSET_ITC 0x30
+#define FTGMAC100_OFFSET_APTC 0x34
+#define FTGMAC100_OFFSET_DBLAC 0x38
+#define FTGMAC100_OFFSET_DMAFIFOS 0x3c
+#define FTGMAC100_OFFSET_REVR 0x40
+#define FTGMAC100_OFFSET_FEAR 0x44
+#define FTGMAC100_OFFSET_TPAFCR 0x48
+#define FTGMAC100_OFFSET_RBSR 0x4c
+#define FTGMAC100_OFFSET_MACCR 0x50
+#define FTGMAC100_OFFSET_MACSR 0x54
+#define FTGMAC100_OFFSET_TM 0x58
+#define FTGMAC100_OFFSET_PHYCR 0x60
+#define FTGMAC100_OFFSET_PHYDATA 0x64
+#define FTGMAC100_OFFSET_FCR 0x68
+#define FTGMAC100_OFFSET_BPR 0x6c
+#define FTGMAC100_OFFSET_WOLCR 0x70
+#define FTGMAC100_OFFSET_WOLSR 0x74
+#define FTGMAC100_OFFSET_WFCRC 0x78
+#define FTGMAC100_OFFSET_WFBM1 0x80
+#define FTGMAC100_OFFSET_WFBM2 0x84
+#define FTGMAC100_OFFSET_WFBM3 0x88
+#define FTGMAC100_OFFSET_WFBM4 0x8c
+#define FTGMAC100_OFFSET_NPTXR_PTR 0x90
+#define FTGMAC100_OFFSET_HPTXR_PTR 0x94
+#define FTGMAC100_OFFSET_RXR_PTR 0x98
+#define FTGMAC100_OFFSET_TX 0xa0
+#define FTGMAC100_OFFSET_TX_MCOL_SCOL 0xa4
+#define FTGMAC100_OFFSET_TX_ECOL_FAIL 0xa8
+#define FTGMAC100_OFFSET_TX_LCOL_UND 0xac
+#define FTGMAC100_OFFSET_RX 0xb0
+#define FTGMAC100_OFFSET_RX_BC 0xb4
+#define FTGMAC100_OFFSET_RX_MC 0xb8
+#define FTGMAC100_OFFSET_RX_PF_AEP 0xbc
+#define FTGMAC100_OFFSET_RX_RUNT 0xc0
+#define FTGMAC100_OFFSET_RX_CRCER_FTL 0xc4
+#define FTGMAC100_OFFSET_RX_COL_LOST 0xc8
+
+/*
+ * Interrupt status register & interrupt enable register
+ */
+#define FTGMAC100_INT_RPKT_BUF (1 << 0)
+#define FTGMAC100_INT_RPKT_FIFO (1 << 1)
+#define FTGMAC100_INT_NO_RXBUF (1 << 2)
+#define FTGMAC100_INT_RPKT_LOST (1 << 3)
+#define FTGMAC100_INT_XPKT_ETH (1 << 4)
+#define FTGMAC100_INT_XPKT_FIFO (1 << 5)
+#define FTGMAC100_INT_NO_NPTXBUF (1 << 6)
+#define FTGMAC100_INT_XPKT_LOST (1 << 7)
+#define FTGMAC100_INT_AHB_ERR (1 << 8)
+#define FTGMAC100_INT_PHYSTS_CHG (1 << 9)
+#define FTGMAC100_INT_NO_HPTXBUF (1 << 10)
+
+/*
+ * Interrupt timer control register
+ */
+#define FTGMAC100_ITC_RXINT_CNT(x) (((x) & 0xf) << 0)
+#define FTGMAC100_ITC_RXINT_THR(x) (((x) & 0x7) << 4)
+#define FTGMAC100_ITC_RXINT_TIME_SEL (1 << 7)
+#define FTGMAC100_ITC_TXINT_CNT(x) (((x) & 0xf) << 8)
+#define FTGMAC100_ITC_TXINT_THR(x) (((x) & 0x7) << 12)
+#define FTGMAC100_ITC_TXINT_TIME_SEL (1 << 15)
+
+/*
+ * Automatic polling timer control register
+ */
+#define FTGMAC100_APTC_RXPOLL_CNT(x) (((x) & 0xf) << 0)
+#define FTGMAC100_APTC_RXPOLL_TIME_SEL (1 << 4)
+#define FTGMAC100_APTC_TXPOLL_CNT(x) (((x) & 0xf) << 8)
+#define FTGMAC100_APTC_TXPOLL_TIME_SEL (1 << 12)
+
+/*
+ * DMA burst length and arbitration control register
+ */
+#define FTGMAC100_DBLAC_RXFIFO_LTHR(x) (((x) & 0x7) << 0)
+#define FTGMAC100_DBLAC_RXFIFO_HTHR(x) (((x) & 0x7) << 3)
+#define FTGMAC100_DBLAC_RX_THR_EN (1 << 6)
+#define FTGMAC100_DBLAC_RXBURST_SIZE(x) (((x) & 0x3) << 8)
+#define FTGMAC100_DBLAC_TXBURST_SIZE(x) (((x) & 0x3) << 10)
+#define FTGMAC100_DBLAC_RXDES_SIZE(x) (((x) & 0xf) << 12)
+#define FTGMAC100_DBLAC_TXDES_SIZE(x) (((x) & 0xf) << 16)
+#define FTGMAC100_DBLAC_IFG_CNT(x) (((x) & 0x7) << 20)
+#define FTGMAC100_DBLAC_IFG_INC (1 << 23)
+
+/*
+ * DMA FIFO status register
+ */
+#define FTGMAC100_DMAFIFOS_RXDMA1_SM(dmafifos) ((dmafifos) & 0xf)
+#define FTGMAC100_DMAFIFOS_RXDMA2_SM(dmafifos) (((dmafifos) >> 4) & 0xf)
+#define FTGMAC100_DMAFIFOS_RXDMA3_SM(dmafifos) (((dmafifos) >> 8) & 0x7)
+#define FTGMAC100_DMAFIFOS_TXDMA1_SM(dmafifos) (((dmafifos) >> 12) & 0xf)
+#define FTGMAC100_DMAFIFOS_TXDMA2_SM(dmafifos) (((dmafifos) >> 16) & 0x3)
+#define FTGMAC100_DMAFIFOS_TXDMA3_SM(dmafifos) (((dmafifos) >> 18) & 0xf)
+#define FTGMAC100_DMAFIFOS_RXFIFO_EMPTY (1 << 26)
+#define FTGMAC100_DMAFIFOS_TXFIFO_EMPTY (1 << 27)
+#define FTGMAC100_DMAFIFOS_RXDMA_GRANT (1 << 28)
+#define FTGMAC100_DMAFIFOS_TXDMA_GRANT (1 << 29)
+#define FTGMAC100_DMAFIFOS_RXDMA_REQ (1 << 30)
+#define FTGMAC100_DMAFIFOS_TXDMA_REQ (1 << 31)
+
+/*
+ * Receive buffer size register
+ */
+#define FTGMAC100_RBSR_SIZE(x) ((x) & 0x3fff)
+
+/*
+ * MAC control register
+ */
+#define FTGMAC100_MACCR_TXDMA_EN (1 << 0)
+#define FTGMAC100_MACCR_RXDMA_EN (1 << 1)
+#define FTGMAC100_MACCR_TXMAC_EN (1 << 2)
+#define FTGMAC100_MACCR_RXMAC_EN (1 << 3)
+#define FTGMAC100_MACCR_RM_VLAN (1 << 4)
+#define FTGMAC100_MACCR_HPTXR_EN (1 << 5)
+#define FTGMAC100_MACCR_LOOP_EN (1 << 6)
+#define FTGMAC100_MACCR_ENRX_IN_HALFTX (1 << 7)
+#define FTGMAC100_MACCR_FULLDUP (1 << 8)
+#define FTGMAC100_MACCR_GIGA_MODE (1 << 9)
+#define FTGMAC100_MACCR_CRC_APD (1 << 10)
+#define FTGMAC100_MACCR_RX_RUNT (1 << 12)
+#define FTGMAC100_MACCR_JUMBO_LF (1 << 13)
+#define FTGMAC100_MACCR_RX_ALL (1 << 14)
+#define FTGMAC100_MACCR_HT_MULTI_EN (1 << 15)
+#define FTGMAC100_MACCR_RX_MULTIPKT (1 << 16)
+#define FTGMAC100_MACCR_RX_BROADPKT (1 << 17)
+#define FTGMAC100_MACCR_DISCARD_CRCERR (1 << 18)
+#define FTGMAC100_MACCR_FAST_MODE (1 << 19)
+#define FTGMAC100_MACCR_SW_RST (1 << 31)
+
+/*
+ * PHY control register
+ */
+#define FTGMAC100_PHYCR_MDC_CYCTHR_MASK 0x3f
+#define FTGMAC100_PHYCR_MDC_CYCTHR(x) ((x) & 0x3f)
+#define FTGMAC100_PHYCR_PHYAD(x) (((x) & 0x1f) << 16)
+#define FTGMAC100_PHYCR_REGAD(x) (((x) & 0x1f) << 21)
+#define FTGMAC100_PHYCR_MIIRD (1 << 26)
+#define FTGMAC100_PHYCR_MIIWR (1 << 27)
+
+/*
+ * PHY data register
+ */
+#define FTGMAC100_PHYDATA_MIIWDATA(x) ((x) & 0xffff)
+#define FTGMAC100_PHYDATA_MIIRDATA(phydata) (((phydata) >> 16) & 0xffff)
+
+/*
+ * Transmit descriptor, aligned to 16 bytes
+ */
+struct ftgmac100_txdes {
+ unsigned int txdes0;
+ unsigned int txdes1;
+ unsigned int txdes2; /* not used by HW */
+ unsigned int txdes3; /* TXBUF_BADR */
+} __attribute__ ((aligned(16)));
+
+#define FTGMAC100_TXDES0_TXBUF_SIZE(x) ((x) & 0x3fff)
+#define FTGMAC100_TXDES0_EDOTR (1 << 15)
+#define FTGMAC100_TXDES0_CRC_ERR (1 << 19)
+#define FTGMAC100_TXDES0_LTS (1 << 28)
+#define FTGMAC100_TXDES0_FTS (1 << 29)
+#define FTGMAC100_TXDES0_TXDMA_OWN (1 << 31)
+
+#define FTGMAC100_TXDES1_VLANTAG_CI(x) ((x) & 0xffff)
+#define FTGMAC100_TXDES1_INS_VLANTAG (1 << 16)
+#define FTGMAC100_TXDES1_TCP_CHKSUM (1 << 17)
+#define FTGMAC100_TXDES1_UDP_CHKSUM (1 << 18)
+#define FTGMAC100_TXDES1_IP_CHKSUM (1 << 19)
+#define FTGMAC100_TXDES1_LLC (1 << 22)
+#define FTGMAC100_TXDES1_TX2FIC (1 << 30)
+#define FTGMAC100_TXDES1_TXIC (1 << 31)
+
+/*
+ * Receive descriptor, aligned to 16 bytes
+ */
+struct ftgmac100_rxdes {
+ unsigned int rxdes0;
+ unsigned int rxdes1;
+ unsigned int rxdes2; /* not used by HW */
+ unsigned int rxdes3; /* RXBUF_BADR */
+} __attribute__ ((aligned(16)));
+
+#define FTGMAC100_RXDES0_VDBC 0x3fff
+#define FTGMAC100_RXDES0_EDORR (1 << 15)
+#define FTGMAC100_RXDES0_MULTICAST (1 << 16)
+#define FTGMAC100_RXDES0_BROADCAST (1 << 17)
+#define FTGMAC100_RXDES0_RX_ERR (1 << 18)
+#define FTGMAC100_RXDES0_CRC_ERR (1 << 19)
+#define FTGMAC100_RXDES0_FTL (1 << 20)
+#define FTGMAC100_RXDES0_RUNT (1 << 21)
+#define FTGMAC100_RXDES0_RX_ODD_NB (1 << 22)
+#define FTGMAC100_RXDES0_FIFO_FULL (1 << 23)
+#define FTGMAC100_RXDES0_PAUSE_OPCODE (1 << 24)
+#define FTGMAC100_RXDES0_PAUSE_FRAME (1 << 25)
+#define FTGMAC100_RXDES0_LRS (1 << 28)
+#define FTGMAC100_RXDES0_FRS (1 << 29)
+#define FTGMAC100_RXDES0_RXPKT_RDY (1 << 31)
+
+#define FTGMAC100_RXDES1_VLANTAG_CI 0xffff
+#define FTGMAC100_RXDES1_PROT_MASK (0x3 << 20)
+#define FTGMAC100_RXDES1_PROT_NONIP (0x0 << 20)
+#define FTGMAC100_RXDES1_PROT_IP (0x1 << 20)
+#define FTGMAC100_RXDES1_PROT_TCPIP (0x2 << 20)
+#define FTGMAC100_RXDES1_PROT_UDPIP (0x3 << 20)
+#define FTGMAC100_RXDES1_LLC (1 << 22)
+#define FTGMAC100_RXDES1_DF (1 << 23)
+#define FTGMAC100_RXDES1_VLANTAG_AVAIL (1 << 24)
+#define FTGMAC100_RXDES1_TCP_CHKSUM_ERR (1 << 25)
+#define FTGMAC100_RXDES1_UDP_CHKSUM_ERR (1 << 26)
+#define FTGMAC100_RXDES1_IP_CHKSUM_ERR (1 << 27)
+
+#endif /* __FTGMAC100_H */
--
1.6.3.3
^ permalink raw reply related
* Re: [PATCH] tcp: mark tcp_congestion_ops read_mostly
From: David Miller @ 2011-03-10 8:40 UTC (permalink / raw)
To: shemminger; +Cc: dada1, netdev
In-Reply-To: <20110309160220.1a2db73e@nehalam>
From: Stephen Hemminger <shemminger@vyatta.com>
Date: Wed, 9 Mar 2011 16:02:20 -0800
> Signed-off-by: Stephen Hemminger <shemminger@vyatta.com>
Applied, thanks Stephen.
^ permalink raw reply
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