aboutsummaryrefslogtreecommitdiffstats
diff options
context:
space:
mode:
authorFelix Fietkau <nbd@nbd.name>2016-05-21 22:16:56 +0200
committerFelix Fietkau <nbd@nbd.name>2016-05-22 16:04:37 +0200
commitdf98acc6a1252456608958fc17f7da3ae4cfb46c (patch)
tree2ed792928e0aa18d5dc3a8031b670629fa175167
parente90245237c971cda70e9c1752e9bce4cc3cbef4f (diff)
downloadupstream-df98acc6a1252456608958fc17f7da3ae4cfb46c.tar.gz
upstream-df98acc6a1252456608958fc17f7da3ae4cfb46c.tar.bz2
upstream-df98acc6a1252456608958fc17f7da3ae4cfb46c.zip
mvebu: backport upstream ethernet driver improvements and enable buffer manager support
Signed-off-by: Felix Fietkau <nbd@nbd.name>
-rw-r--r--target/linux/mvebu/config-4.42
-rw-r--r--target/linux/mvebu/patches-4.4/021-mtd-pxa3xx_nand-Increase-the-initial-chunk-size.patch2
-rw-r--r--target/linux/mvebu/patches-4.4/022-mtd-pxa3xx_nand-Fix-initial-controller-configuration.patch8
-rw-r--r--target/linux/mvebu/patches-4.4/023-bus-mvebu-mbus-provide-api-for-obtaining-IO-and-DRAM.patch94
-rw-r--r--target/linux/mvebu/patches-4.4/030-mvneta-consolidate-autoneg-enabling.patch55
-rw-r--r--target/linux/mvebu/patches-4.4/031-mvneta-implement-ethtool-autonegotiation-control.patch165
-rw-r--r--target/linux/mvebu/patches-4.4/032-net-mvneta-Make-the-default-queue-related-for-each-p.patch131
-rw-r--r--target/linux/mvebu/patches-4.4/033-net-mvneta-Associate-RX-queues-with-each-CPU.patch278
-rw-r--r--target/linux/mvebu/patches-4.4/034-net-mvneta-Add-naive-RSS-support.patch191
-rw-r--r--target/linux/mvebu/patches-4.4/035-net-mvneta-Configure-XPS-support.patch124
-rw-r--r--target/linux/mvebu/patches-4.4/036-net-mvneta-fix-trivial-cut-off-issue-in-mvneta_ethto.patch46
-rw-r--r--target/linux/mvebu/patches-4.4/037-net-mvneta-Fix-for_each_present_cpu-usage.patch55
-rw-r--r--target/linux/mvebu/patches-4.4/038-net-mvneta-Fix-the-CPU-choice-in-mvneta_percpu_elect.patch57
-rw-r--r--target/linux/mvebu/patches-4.4/039-net-mvneta-Use-on_each_cpu-when-possible.patch68
-rw-r--r--target/linux/mvebu/patches-4.4/040-net-mvneta-Modify-the-queue-related-fields-from-each.patch179
-rw-r--r--target/linux/mvebu/patches-4.4/041-net-mvneta-The-mvneta_percpu_elect-function-should-b.patch68
-rw-r--r--target/linux/mvebu/patches-4.4/042-net-mvneta-Fix-race-condition-during-stopping.patch128
-rw-r--r--target/linux/mvebu/patches-4.4/043-net-mvneta-sort-the-headers-in-alphabetic-order.patch56
-rw-r--r--target/linux/mvebu/patches-4.4/044-net-add-a-hardware-buffer-management-helper-API.patch159
-rw-r--r--target/linux/mvebu/patches-4.4/045-net-mvneta-bm-add-support-for-hardware-buffer-manage.patch1684
-rw-r--r--target/linux/mvebu/patches-4.4/046-net-mvneta-Use-the-new-hwbm-framework.patch359
-rw-r--r--target/linux/mvebu/patches-4.4/047-net-mvneta-Fix-spinlock-usage.patch52
-rw-r--r--target/linux/mvebu/patches-4.4/048-net-mvneta-fix-error-messages-in-mvneta_port_down-fu.patch33
-rw-r--r--target/linux/mvebu/patches-4.4/049-net-mvneta-replace-MVNETA_CPU_D_CACHE_LINE_SIZE-with.patch56
-rw-r--r--target/linux/mvebu/patches-4.4/050-net-mvneta-fix-changing-MTU-when-using-per-cpu-proce.patch75
-rw-r--r--target/linux/mvebu/patches-4.4/051-ARM-dts-armada-38x-add-buffer-manager-nodes.patch53
-rw-r--r--target/linux/mvebu/patches-4.4/052-ARM-dts-armada-xp-add-buffer-manager-nodes.patch53
-rw-r--r--target/linux/mvebu/patches-4.4/106-enable-bm-on-linksys-devices.patch107
-rw-r--r--target/linux/mvebu/patches-4.4/206-mvebu_wrt1900ac_use_pwm-fan_rather_than_gpio-fan.patch2
29 files changed, 4334 insertions, 6 deletions
diff --git a/target/linux/mvebu/config-4.4 b/target/linux/mvebu/config-4.4
index 163af67347..f5b2346e44 100644
--- a/target/linux/mvebu/config-4.4
+++ b/target/linux/mvebu/config-4.4
@@ -209,6 +209,7 @@ CONFIG_HAVE_UID16=y
CONFIG_HAVE_VIRT_CPU_ACCOUNTING_GEN=y
CONFIG_HIGHMEM=y
# CONFIG_HIGHPTE is not set
+CONFIG_HWBM=y
CONFIG_HWMON=y
CONFIG_HZ_FIXED=0
CONFIG_HZ_PERIODIC=y
@@ -274,6 +275,7 @@ CONFIG_MVEBU_DEVBUS=y
CONFIG_MVEBU_MBUS=y
CONFIG_MVMDIO=y
CONFIG_MVNETA=y
+CONFIG_MVNETA_BM=y
CONFIG_MVSW61XX_PHY=y
CONFIG_MV_XOR=y
CONFIG_NEED_DMA_MAP_STATE=y
diff --git a/target/linux/mvebu/patches-4.4/021-mtd-pxa3xx_nand-Increase-the-initial-chunk-size.patch b/target/linux/mvebu/patches-4.4/021-mtd-pxa3xx_nand-Increase-the-initial-chunk-size.patch
index f928f46cc6..0b0e047c02 100644
--- a/target/linux/mvebu/patches-4.4/021-mtd-pxa3xx_nand-Increase-the-initial-chunk-size.patch
+++ b/target/linux/mvebu/patches-4.4/021-mtd-pxa3xx_nand-Increase-the-initial-chunk-size.patch
@@ -31,7 +31,7 @@ Signed-off-by: Brian Norris <computersforpeace@gmail.com>
--- a/drivers/mtd/nand/pxa3xx_nand.c
+++ b/drivers/mtd/nand/pxa3xx_nand.c
-@@ -1636,7 +1636,7 @@ static int pxa3xx_nand_scan(struct mtd_i
+@@ -1637,7 +1637,7 @@ static int pxa3xx_nand_scan(struct mtd_i
goto KEEP_CONFIG;
/* Set a default chunk size */
diff --git a/target/linux/mvebu/patches-4.4/022-mtd-pxa3xx_nand-Fix-initial-controller-configuration.patch b/target/linux/mvebu/patches-4.4/022-mtd-pxa3xx_nand-Fix-initial-controller-configuration.patch
index 260e7dc1bc..7d07fb9423 100644
--- a/target/linux/mvebu/patches-4.4/022-mtd-pxa3xx_nand-Fix-initial-controller-configuration.patch
+++ b/target/linux/mvebu/patches-4.4/022-mtd-pxa3xx_nand-Fix-initial-controller-configuration.patch
@@ -19,7 +19,7 @@ Signed-off-by: Brian Norris <computersforpeace@gmail.com>
--- a/drivers/mtd/nand/pxa3xx_nand.c
+++ b/drivers/mtd/nand/pxa3xx_nand.c
-@@ -1419,34 +1419,43 @@ static int pxa3xx_nand_waitfunc(struct m
+@@ -1420,34 +1420,43 @@ static int pxa3xx_nand_waitfunc(struct m
return NAND_STATUS_READY;
}
@@ -71,7 +71,7 @@ Signed-off-by: Brian Norris <computersforpeace@gmail.com>
info->ndtr0cs0 = nand_readl(info, NDTR0CS0);
info->ndtr1cs0 = nand_readl(info, NDTR1CS0);
return 0;
-@@ -1635,10 +1644,7 @@ static int pxa3xx_nand_scan(struct mtd_i
+@@ -1636,10 +1645,7 @@ static int pxa3xx_nand_scan(struct mtd_i
if (pdata->keep_config && !pxa3xx_nand_detect_config(info))
goto KEEP_CONFIG;
@@ -83,7 +83,7 @@ Signed-off-by: Brian Norris <computersforpeace@gmail.com>
if (ret)
return ret;
-@@ -1651,7 +1657,6 @@ static int pxa3xx_nand_scan(struct mtd_i
+@@ -1652,7 +1658,6 @@ static int pxa3xx_nand_scan(struct mtd_i
}
KEEP_CONFIG:
@@ -91,7 +91,7 @@ Signed-off-by: Brian Norris <computersforpeace@gmail.com>
if (info->reg_ndcr & NDCR_DWIDTH_M)
chip->options |= NAND_BUSWIDTH_16;
-@@ -1736,6 +1741,10 @@ KEEP_CONFIG:
+@@ -1737,6 +1742,10 @@ KEEP_CONFIG:
host->row_addr_cycles = 3;
else
host->row_addr_cycles = 2;
diff --git a/target/linux/mvebu/patches-4.4/023-bus-mvebu-mbus-provide-api-for-obtaining-IO-and-DRAM.patch b/target/linux/mvebu/patches-4.4/023-bus-mvebu-mbus-provide-api-for-obtaining-IO-and-DRAM.patch
new file mode 100644
index 0000000000..58687f36ad
--- /dev/null
+++ b/target/linux/mvebu/patches-4.4/023-bus-mvebu-mbus-provide-api-for-obtaining-IO-and-DRAM.patch
@@ -0,0 +1,94 @@
+From: Marcin Wojtas <mw@semihalf.com>
+Date: Mon, 14 Mar 2016 09:39:02 +0100
+Subject: [PATCH] bus: mvebu-mbus: provide api for obtaining IO and DRAM window
+ information
+
+This commit enables finding appropriate mbus window and obtaining its
+target id and attribute for given physical address in two separate
+routines, both for IO and DRAM windows. This functionality
+is needed for Armada XP/38x Network Controller's Buffer Manager and
+PnC configuration.
+
+[gregory.clement@free-electrons.com: Fix size test for
+mvebu_mbus_get_dram_win_info]
+
+Signed-off-by: Marcin Wojtas <mw@semihalf.com>
+[DRAM window information reference in LKv3.10]
+Signed-off-by: Evan Wang <xswang@marvell.com>
+Signed-off-by: Gregory CLEMENT <gregory.clement@free-electrons.com>
+Signed-off-by: David S. Miller <davem@davemloft.net>
+---
+
+--- a/drivers/bus/mvebu-mbus.c
++++ b/drivers/bus/mvebu-mbus.c
+@@ -948,6 +948,58 @@ void mvebu_mbus_get_pcie_io_aperture(str
+ *res = mbus_state.pcie_io_aperture;
+ }
+
++int mvebu_mbus_get_dram_win_info(phys_addr_t phyaddr, u8 *target, u8 *attr)
++{
++ const struct mbus_dram_target_info *dram;
++ int i;
++
++ /* Get dram info */
++ dram = mv_mbus_dram_info();
++ if (!dram) {
++ pr_err("missing DRAM information\n");
++ return -ENODEV;
++ }
++
++ /* Try to find matching DRAM window for phyaddr */
++ for (i = 0; i < dram->num_cs; i++) {
++ const struct mbus_dram_window *cs = dram->cs + i;
++
++ if (cs->base <= phyaddr &&
++ phyaddr <= (cs->base + cs->size - 1)) {
++ *target = dram->mbus_dram_target_id;
++ *attr = cs->mbus_attr;
++ return 0;
++ }
++ }
++
++ pr_err("invalid dram address 0x%x\n", phyaddr);
++ return -EINVAL;
++}
++EXPORT_SYMBOL_GPL(mvebu_mbus_get_dram_win_info);
++
++int mvebu_mbus_get_io_win_info(phys_addr_t phyaddr, u32 *size, u8 *target,
++ u8 *attr)
++{
++ int win;
++
++ for (win = 0; win < mbus_state.soc->num_wins; win++) {
++ u64 wbase;
++ int enabled;
++
++ mvebu_mbus_read_window(&mbus_state, win, &enabled, &wbase,
++ size, target, attr, NULL);
++
++ if (!enabled)
++ continue;
++
++ if (wbase <= phyaddr && phyaddr <= wbase + *size)
++ return win;
++ }
++
++ return -EINVAL;
++}
++EXPORT_SYMBOL_GPL(mvebu_mbus_get_io_win_info);
++
+ static __init int mvebu_mbus_debugfs_init(void)
+ {
+ struct mvebu_mbus_state *s = &mbus_state;
+--- a/include/linux/mbus.h
++++ b/include/linux/mbus.h
+@@ -69,6 +69,9 @@ static inline const struct mbus_dram_tar
+ int mvebu_mbus_save_cpu_target(u32 *store_addr);
+ void mvebu_mbus_get_pcie_mem_aperture(struct resource *res);
+ void mvebu_mbus_get_pcie_io_aperture(struct resource *res);
++int mvebu_mbus_get_dram_win_info(phys_addr_t phyaddr, u8 *target, u8 *attr);
++int mvebu_mbus_get_io_win_info(phys_addr_t phyaddr, u32 *size, u8 *target,
++ u8 *attr);
+ int mvebu_mbus_add_window_remap_by_id(unsigned int target,
+ unsigned int attribute,
+ phys_addr_t base, size_t size,
diff --git a/target/linux/mvebu/patches-4.4/030-mvneta-consolidate-autoneg-enabling.patch b/target/linux/mvebu/patches-4.4/030-mvneta-consolidate-autoneg-enabling.patch
new file mode 100644
index 0000000000..1d98c7decc
--- /dev/null
+++ b/target/linux/mvebu/patches-4.4/030-mvneta-consolidate-autoneg-enabling.patch
@@ -0,0 +1,55 @@
+From: Stas Sergeev <stsp@list.ru>
+Date: Wed, 2 Dec 2015 20:33:56 +0300
+Subject: [PATCH] mvneta: consolidate autoneg enabling
+
+This moves autoneg-related bit manipulations to the single place.
+
+CC: Thomas Petazzoni <thomas.petazzoni@free-electrons.com>
+CC: netdev@vger.kernel.org
+CC: linux-kernel@vger.kernel.org
+
+Signed-off-by: Stas Sergeev <stsp@users.sourceforge.net>
+Signed-off-by: David S. Miller <davem@davemloft.net>
+---
+
+--- a/drivers/net/ethernet/marvell/mvneta.c
++++ b/drivers/net/ethernet/marvell/mvneta.c
+@@ -1067,15 +1067,28 @@ static void mvneta_defaults_set(struct m
+ MVNETA_GMAC_AN_SPEED_EN |
+ MVNETA_GMAC_AN_DUPLEX_EN;
+ mvreg_write(pp, MVNETA_GMAC_AUTONEG_CONFIG, val);
++
+ val = mvreg_read(pp, MVNETA_GMAC_CLOCK_DIVIDER);
+ val |= MVNETA_GMAC_1MS_CLOCK_ENABLE;
+ mvreg_write(pp, MVNETA_GMAC_CLOCK_DIVIDER, val);
++
++ val = mvreg_read(pp, MVNETA_GMAC_CTRL_2);
++ val |= MVNETA_GMAC2_INBAND_AN_ENABLE;
++ mvreg_write(pp, MVNETA_GMAC_CTRL_2, val);
+ } else {
+ val = mvreg_read(pp, MVNETA_GMAC_AUTONEG_CONFIG);
+ val &= ~(MVNETA_GMAC_INBAND_AN_ENABLE |
+ MVNETA_GMAC_AN_SPEED_EN |
+ MVNETA_GMAC_AN_DUPLEX_EN);
+ mvreg_write(pp, MVNETA_GMAC_AUTONEG_CONFIG, val);
++
++ val = mvreg_read(pp, MVNETA_GMAC_CLOCK_DIVIDER);
++ val &= ~MVNETA_GMAC_1MS_CLOCK_ENABLE;
++ mvreg_write(pp, MVNETA_GMAC_CLOCK_DIVIDER, val);
++
++ val = mvreg_read(pp, MVNETA_GMAC_CTRL_2);
++ val &= ~MVNETA_GMAC2_INBAND_AN_ENABLE;
++ mvreg_write(pp, MVNETA_GMAC_CTRL_2, val);
+ }
+
+ mvneta_set_ucast_table(pp, -1);
+@@ -3230,9 +3243,6 @@ static int mvneta_port_power_up(struct m
+ return -EINVAL;
+ }
+
+- if (pp->use_inband_status)
+- ctrl |= MVNETA_GMAC2_INBAND_AN_ENABLE;
+-
+ /* Cancel Port Reset */
+ ctrl &= ~MVNETA_GMAC2_PORT_RESET;
+ mvreg_write(pp, MVNETA_GMAC_CTRL_2, ctrl);
diff --git a/target/linux/mvebu/patches-4.4/031-mvneta-implement-ethtool-autonegotiation-control.patch b/target/linux/mvebu/patches-4.4/031-mvneta-implement-ethtool-autonegotiation-control.patch
new file mode 100644
index 0000000000..626b511c45
--- /dev/null
+++ b/target/linux/mvebu/patches-4.4/031-mvneta-implement-ethtool-autonegotiation-control.patch
@@ -0,0 +1,165 @@
+From: Stas Sergeev <stsp@list.ru>
+Date: Wed, 2 Dec 2015 20:35:11 +0300
+Subject: [PATCH] mvneta: implement ethtool autonegotiation control
+
+This patch allows to do
+ethtool -s eth0 autoneg off
+ethtool -s eth0 autoneg on
+to disable or enable autonegotiation at run-time.
+Without that functionality, the only way to control the autonegotiation
+is to modify the device tree.
+
+This is needed if you plan to use the same kernel with
+different ethernet switches, the ones that support the in-band
+status and the ones that not.
+
+CC: Thomas Petazzoni <thomas.petazzoni@free-electrons.com>
+CC: netdev@vger.kernel.org
+CC: linux-kernel@vger.kernel.org
+
+Signed-off-by: Stas Sergeev <stsp@users.sourceforge.net>
+Signed-off-by: David S. Miller <davem@davemloft.net>
+---
+
+--- a/drivers/net/ethernet/marvell/mvneta.c
++++ b/drivers/net/ethernet/marvell/mvneta.c
+@@ -371,7 +371,7 @@ struct mvneta_port {
+ unsigned int duplex;
+ unsigned int speed;
+ unsigned int tx_csum_limit;
+- int use_inband_status:1;
++ unsigned int use_inband_status:1;
+
+ u64 ethtool_stats[ARRAY_SIZE(mvneta_statistics)];
+ };
+@@ -973,6 +973,44 @@ static void mvneta_set_other_mcast_table
+ mvreg_write(pp, MVNETA_DA_FILT_OTH_MCAST + offset, val);
+ }
+
++static void mvneta_set_autoneg(struct mvneta_port *pp, int enable)
++{
++ u32 val;
++
++ if (enable) {
++ val = mvreg_read(pp, MVNETA_GMAC_AUTONEG_CONFIG);
++ val &= ~(MVNETA_GMAC_FORCE_LINK_PASS |
++ MVNETA_GMAC_FORCE_LINK_DOWN |
++ MVNETA_GMAC_AN_FLOW_CTRL_EN);
++ val |= MVNETA_GMAC_INBAND_AN_ENABLE |
++ MVNETA_GMAC_AN_SPEED_EN |
++ MVNETA_GMAC_AN_DUPLEX_EN;
++ mvreg_write(pp, MVNETA_GMAC_AUTONEG_CONFIG, val);
++
++ val = mvreg_read(pp, MVNETA_GMAC_CLOCK_DIVIDER);
++ val |= MVNETA_GMAC_1MS_CLOCK_ENABLE;
++ mvreg_write(pp, MVNETA_GMAC_CLOCK_DIVIDER, val);
++
++ val = mvreg_read(pp, MVNETA_GMAC_CTRL_2);
++ val |= MVNETA_GMAC2_INBAND_AN_ENABLE;
++ mvreg_write(pp, MVNETA_GMAC_CTRL_2, val);
++ } else {
++ val = mvreg_read(pp, MVNETA_GMAC_AUTONEG_CONFIG);
++ val &= ~(MVNETA_GMAC_INBAND_AN_ENABLE |
++ MVNETA_GMAC_AN_SPEED_EN |
++ MVNETA_GMAC_AN_DUPLEX_EN);
++ mvreg_write(pp, MVNETA_GMAC_AUTONEG_CONFIG, val);
++
++ val = mvreg_read(pp, MVNETA_GMAC_CLOCK_DIVIDER);
++ val &= ~MVNETA_GMAC_1MS_CLOCK_ENABLE;
++ mvreg_write(pp, MVNETA_GMAC_CLOCK_DIVIDER, val);
++
++ val = mvreg_read(pp, MVNETA_GMAC_CTRL_2);
++ val &= ~MVNETA_GMAC2_INBAND_AN_ENABLE;
++ mvreg_write(pp, MVNETA_GMAC_CTRL_2, val);
++ }
++}
++
+ /* This method sets defaults to the NETA port:
+ * Clears interrupt Cause and Mask registers.
+ * Clears all MAC tables.
+@@ -1058,39 +1096,7 @@ static void mvneta_defaults_set(struct m
+ val &= ~MVNETA_PHY_POLLING_ENABLE;
+ mvreg_write(pp, MVNETA_UNIT_CONTROL, val);
+
+- if (pp->use_inband_status) {
+- val = mvreg_read(pp, MVNETA_GMAC_AUTONEG_CONFIG);
+- val &= ~(MVNETA_GMAC_FORCE_LINK_PASS |
+- MVNETA_GMAC_FORCE_LINK_DOWN |
+- MVNETA_GMAC_AN_FLOW_CTRL_EN);
+- val |= MVNETA_GMAC_INBAND_AN_ENABLE |
+- MVNETA_GMAC_AN_SPEED_EN |
+- MVNETA_GMAC_AN_DUPLEX_EN;
+- mvreg_write(pp, MVNETA_GMAC_AUTONEG_CONFIG, val);
+-
+- val = mvreg_read(pp, MVNETA_GMAC_CLOCK_DIVIDER);
+- val |= MVNETA_GMAC_1MS_CLOCK_ENABLE;
+- mvreg_write(pp, MVNETA_GMAC_CLOCK_DIVIDER, val);
+-
+- val = mvreg_read(pp, MVNETA_GMAC_CTRL_2);
+- val |= MVNETA_GMAC2_INBAND_AN_ENABLE;
+- mvreg_write(pp, MVNETA_GMAC_CTRL_2, val);
+- } else {
+- val = mvreg_read(pp, MVNETA_GMAC_AUTONEG_CONFIG);
+- val &= ~(MVNETA_GMAC_INBAND_AN_ENABLE |
+- MVNETA_GMAC_AN_SPEED_EN |
+- MVNETA_GMAC_AN_DUPLEX_EN);
+- mvreg_write(pp, MVNETA_GMAC_AUTONEG_CONFIG, val);
+-
+- val = mvreg_read(pp, MVNETA_GMAC_CLOCK_DIVIDER);
+- val &= ~MVNETA_GMAC_1MS_CLOCK_ENABLE;
+- mvreg_write(pp, MVNETA_GMAC_CLOCK_DIVIDER, val);
+-
+- val = mvreg_read(pp, MVNETA_GMAC_CTRL_2);
+- val &= ~MVNETA_GMAC2_INBAND_AN_ENABLE;
+- mvreg_write(pp, MVNETA_GMAC_CTRL_2, val);
+- }
+-
++ mvneta_set_autoneg(pp, pp->use_inband_status);
+ mvneta_set_ucast_table(pp, -1);
+ mvneta_set_special_mcast_table(pp, -1);
+ mvneta_set_other_mcast_table(pp, -1);
+@@ -2956,10 +2962,43 @@ int mvneta_ethtool_get_settings(struct n
+ int mvneta_ethtool_set_settings(struct net_device *dev, struct ethtool_cmd *cmd)
+ {
+ struct mvneta_port *pp = netdev_priv(dev);
++ struct phy_device *phydev = pp->phy_dev;
+
+- if (!pp->phy_dev)
++ if (!phydev)
+ return -ENODEV;
+
++ if ((cmd->autoneg == AUTONEG_ENABLE) != pp->use_inband_status) {
++ u32 val;
++
++ mvneta_set_autoneg(pp, cmd->autoneg == AUTONEG_ENABLE);
++
++ if (cmd->autoneg == AUTONEG_DISABLE) {
++ val = mvreg_read(pp, MVNETA_GMAC_AUTONEG_CONFIG);
++ val &= ~(MVNETA_GMAC_CONFIG_MII_SPEED |
++ MVNETA_GMAC_CONFIG_GMII_SPEED |
++ MVNETA_GMAC_CONFIG_FULL_DUPLEX);
++
++ if (phydev->duplex)
++ val |= MVNETA_GMAC_CONFIG_FULL_DUPLEX;
++
++ if (phydev->speed == SPEED_1000)
++ val |= MVNETA_GMAC_CONFIG_GMII_SPEED;
++ else if (phydev->speed == SPEED_100)
++ val |= MVNETA_GMAC_CONFIG_MII_SPEED;
++
++ mvreg_write(pp, MVNETA_GMAC_AUTONEG_CONFIG, val);
++ }
++
++ pp->use_inband_status = (cmd->autoneg == AUTONEG_ENABLE);
++ netdev_info(pp->dev, "autoneg status set to %i\n",
++ pp->use_inband_status);
++
++ if (netif_running(dev)) {
++ mvneta_port_down(pp);
++ mvneta_port_up(pp);
++ }
++ }
++
+ return phy_ethtool_sset(pp->phy_dev, cmd);
+ }
+
diff --git a/target/linux/mvebu/patches-4.4/032-net-mvneta-Make-the-default-queue-related-for-each-p.patch b/target/linux/mvebu/patches-4.4/032-net-mvneta-Make-the-default-queue-related-for-each-p.patch
new file mode 100644
index 0000000000..54c93998f6
--- /dev/null
+++ b/target/linux/mvebu/patches-4.4/032-net-mvneta-Make-the-default-queue-related-for-each-p.patch
@@ -0,0 +1,131 @@
+From: Gregory CLEMENT <gregory.clement@free-electrons.com>
+Date: Wed, 9 Dec 2015 18:23:48 +0100
+Subject: [PATCH] net: mvneta: Make the default queue related for each port
+
+Instead of using the same default queue for all the port. Move it in the
+port struct. It will allow have a different default queue for each port.
+
+Signed-off-by: Gregory CLEMENT <gregory.clement@free-electrons.com>
+Signed-off-by: David S. Miller <davem@davemloft.net>
+---
+
+--- a/drivers/net/ethernet/marvell/mvneta.c
++++ b/drivers/net/ethernet/marvell/mvneta.c
+@@ -356,6 +356,7 @@ struct mvneta_port {
+ struct mvneta_tx_queue *txqs;
+ struct net_device *dev;
+ struct notifier_block cpu_notifier;
++ int rxq_def;
+
+ /* Core clock */
+ struct clk *clk;
+@@ -819,7 +820,7 @@ static void mvneta_port_up(struct mvneta
+ mvreg_write(pp, MVNETA_TXQ_CMD, q_map);
+
+ /* Enable all initialized RXQs. */
+- mvreg_write(pp, MVNETA_RXQ_CMD, BIT(rxq_def));
++ mvreg_write(pp, MVNETA_RXQ_CMD, BIT(pp->rxq_def));
+ }
+
+ /* Stop the Ethernet port activity */
+@@ -1067,7 +1068,7 @@ static void mvneta_defaults_set(struct m
+ mvreg_write(pp, MVNETA_ACC_MODE, val);
+
+ /* Update val of portCfg register accordingly with all RxQueue types */
+- val = MVNETA_PORT_CONFIG_DEFL_VALUE(rxq_def);
++ val = MVNETA_PORT_CONFIG_DEFL_VALUE(pp->rxq_def);
+ mvreg_write(pp, MVNETA_PORT_CONFIG, val);
+
+ val = 0;
+@@ -2101,19 +2102,19 @@ static void mvneta_set_rx_mode(struct ne
+ if (dev->flags & IFF_PROMISC) {
+ /* Accept all: Multicast + Unicast */
+ mvneta_rx_unicast_promisc_set(pp, 1);
+- mvneta_set_ucast_table(pp, rxq_def);
+- mvneta_set_special_mcast_table(pp, rxq_def);
+- mvneta_set_other_mcast_table(pp, rxq_def);
++ mvneta_set_ucast_table(pp, pp->rxq_def);
++ mvneta_set_special_mcast_table(pp, pp->rxq_def);
++ mvneta_set_other_mcast_table(pp, pp->rxq_def);
+ } else {
+ /* Accept single Unicast */
+ mvneta_rx_unicast_promisc_set(pp, 0);
+ mvneta_set_ucast_table(pp, -1);
+- mvneta_mac_addr_set(pp, dev->dev_addr, rxq_def);
++ mvneta_mac_addr_set(pp, dev->dev_addr, pp->rxq_def);
+
+ if (dev->flags & IFF_ALLMULTI) {
+ /* Accept all multicast */
+- mvneta_set_special_mcast_table(pp, rxq_def);
+- mvneta_set_other_mcast_table(pp, rxq_def);
++ mvneta_set_special_mcast_table(pp, pp->rxq_def);
++ mvneta_set_other_mcast_table(pp, pp->rxq_def);
+ } else {
+ /* Accept only initialized multicast */
+ mvneta_set_special_mcast_table(pp, -1);
+@@ -2122,7 +2123,7 @@ static void mvneta_set_rx_mode(struct ne
+ if (!netdev_mc_empty(dev)) {
+ netdev_for_each_mc_addr(ha, dev) {
+ mvneta_mcast_addr_set(pp, ha->addr,
+- rxq_def);
++ pp->rxq_def);
+ }
+ }
+ }
+@@ -2205,7 +2206,7 @@ static int mvneta_poll(struct napi_struc
+ * RX packets
+ */
+ cause_rx_tx |= port->cause_rx_tx;
+- rx_done = mvneta_rx(pp, budget, &pp->rxqs[rxq_def]);
++ rx_done = mvneta_rx(pp, budget, &pp->rxqs[pp->rxq_def]);
+ budget -= rx_done;
+
+ if (budget > 0) {
+@@ -2418,17 +2419,17 @@ static void mvneta_cleanup_txqs(struct m
+ /* Cleanup all Rx queues */
+ static void mvneta_cleanup_rxqs(struct mvneta_port *pp)
+ {
+- mvneta_rxq_deinit(pp, &pp->rxqs[rxq_def]);
++ mvneta_rxq_deinit(pp, &pp->rxqs[pp->rxq_def]);
+ }
+
+
+ /* Init all Rx queues */
+ static int mvneta_setup_rxqs(struct mvneta_port *pp)
+ {
+- int err = mvneta_rxq_init(pp, &pp->rxqs[rxq_def]);
++ int err = mvneta_rxq_init(pp, &pp->rxqs[pp->rxq_def]);
+ if (err) {
+ netdev_err(pp->dev, "%s: can't create rxq=%d\n",
+- __func__, rxq_def);
++ __func__, pp->rxq_def);
+ mvneta_cleanup_rxqs(pp);
+ return err;
+ }
+@@ -2634,7 +2635,7 @@ static int mvneta_set_mac_addr(struct ne
+ mvneta_mac_addr_set(pp, dev->dev_addr, -1);
+
+ /* Set new addr in hw */
+- mvneta_mac_addr_set(pp, sockaddr->sa_data, rxq_def);
++ mvneta_mac_addr_set(pp, sockaddr->sa_data, pp->rxq_def);
+
+ eth_commit_mac_addr_change(dev, addr);
+ return 0;
+@@ -2753,7 +2754,7 @@ static void mvneta_percpu_elect(struct m
+ {
+ int online_cpu_idx, cpu, i = 0;
+
+- online_cpu_idx = rxq_def % num_online_cpus();
++ online_cpu_idx = pp->rxq_def % num_online_cpus();
+
+ for_each_online_cpu(cpu) {
+ if (i == online_cpu_idx)
+@@ -3363,6 +3364,8 @@ static int mvneta_probe(struct platform_
+ strcmp(managed, "in-band-status") == 0);
+ pp->cpu_notifier.notifier_call = mvneta_percpu_notifier;
+
++ pp->rxq_def = rxq_def;
++
+ pp->clk = devm_clk_get(&pdev->dev, NULL);
+ if (IS_ERR(pp->clk)) {
+ err = PTR_ERR(pp->clk);
diff --git a/target/linux/mvebu/patches-4.4/033-net-mvneta-Associate-RX-queues-with-each-CPU.patch b/target/linux/mvebu/patches-4.4/033-net-mvneta-Associate-RX-queues-with-each-CPU.patch
new file mode 100644
index 0000000000..636c6cf364
--- /dev/null
+++ b/target/linux/mvebu/patches-4.4/033-net-mvneta-Associate-RX-queues-with-each-CPU.patch
@@ -0,0 +1,278 @@
+From: Gregory CLEMENT <gregory.clement@free-electrons.com>
+Date: Wed, 9 Dec 2015 18:23:49 +0100
+Subject: [PATCH] net: mvneta: Associate RX queues with each CPU
+
+We enable the percpu interrupt for all the CPU and we just associate a
+CPU to a few queue at the neta level. The mapping between the CPUs and
+the queues is static. The queues are associated to the CPU module the
+number of CPUs. However currently we only use on RX queue for a given
+Ethernet port.
+
+Signed-off-by: Gregory CLEMENT <gregory.clement@free-electrons.com>
+Signed-off-by: David S. Miller <davem@davemloft.net>
+---
+
+--- a/drivers/net/ethernet/marvell/mvneta.c
++++ b/drivers/net/ethernet/marvell/mvneta.c
+@@ -110,9 +110,16 @@
+ #define MVNETA_CPU_MAP(cpu) (0x2540 + ((cpu) << 2))
+ #define MVNETA_CPU_RXQ_ACCESS_ALL_MASK 0x000000ff
+ #define MVNETA_CPU_TXQ_ACCESS_ALL_MASK 0x0000ff00
++#define MVNETA_CPU_RXQ_ACCESS(rxq) BIT(rxq)
+ #define MVNETA_RXQ_TIME_COAL_REG(q) (0x2580 + ((q) << 2))
+
+-/* Exception Interrupt Port/Queue Cause register */
++/* Exception Interrupt Port/Queue Cause register
++ *
++ * Their behavior depend of the mapping done using the PCPX2Q
++ * registers. For a given CPU if the bit associated to a queue is not
++ * set, then for the register a read from this CPU will always return
++ * 0 and a write won't do anything
++ */
+
+ #define MVNETA_INTR_NEW_CAUSE 0x25a0
+ #define MVNETA_INTR_NEW_MASK 0x25a4
+@@ -820,7 +827,13 @@ static void mvneta_port_up(struct mvneta
+ mvreg_write(pp, MVNETA_TXQ_CMD, q_map);
+
+ /* Enable all initialized RXQs. */
+- mvreg_write(pp, MVNETA_RXQ_CMD, BIT(pp->rxq_def));
++ for (queue = 0; queue < rxq_number; queue++) {
++ struct mvneta_rx_queue *rxq = &pp->rxqs[queue];
++
++ if (rxq->descs != NULL)
++ q_map |= (1 << queue);
++ }
++ mvreg_write(pp, MVNETA_RXQ_CMD, q_map);
+ }
+
+ /* Stop the Ethernet port activity */
+@@ -1026,6 +1039,7 @@ static void mvneta_defaults_set(struct m
+ int cpu;
+ int queue;
+ u32 val;
++ int max_cpu = num_present_cpus();
+
+ /* Clear all Cause registers */
+ mvreg_write(pp, MVNETA_INTR_NEW_CAUSE, 0);
+@@ -1041,13 +1055,23 @@ static void mvneta_defaults_set(struct m
+ /* Enable MBUS Retry bit16 */
+ mvreg_write(pp, MVNETA_MBUS_RETRY, 0x20);
+
+- /* Set CPU queue access map - all CPUs have access to all RX
+- * queues and to all TX queues
++ /* Set CPU queue access map. CPUs are assigned to the RX
++ * queues modulo their number and all the TX queues are
++ * assigned to the CPU associated to the default RX queue.
+ */
+- for_each_present_cpu(cpu)
+- mvreg_write(pp, MVNETA_CPU_MAP(cpu),
+- (MVNETA_CPU_RXQ_ACCESS_ALL_MASK |
+- MVNETA_CPU_TXQ_ACCESS_ALL_MASK));
++ for_each_present_cpu(cpu) {
++ int rxq_map = 0, txq_map = 0;
++ int rxq;
++
++ for (rxq = 0; rxq < rxq_number; rxq++)
++ if ((rxq % max_cpu) == cpu)
++ rxq_map |= MVNETA_CPU_RXQ_ACCESS(rxq);
++
++ if (cpu == rxq_def)
++ txq_map = MVNETA_CPU_TXQ_ACCESS_ALL_MASK;
++
++ mvreg_write(pp, MVNETA_CPU_MAP(cpu), rxq_map | txq_map);
++ }
+
+ /* Reset RX and TX DMAs */
+ mvreg_write(pp, MVNETA_PORT_RX_RESET, MVNETA_PORT_RX_DMA_RESET);
+@@ -2174,6 +2198,7 @@ static int mvneta_poll(struct napi_struc
+ {
+ int rx_done = 0;
+ u32 cause_rx_tx;
++ int rx_queue;
+ struct mvneta_port *pp = netdev_priv(napi->dev);
+ struct mvneta_pcpu_port *port = this_cpu_ptr(pp->ports);
+
+@@ -2205,8 +2230,15 @@ static int mvneta_poll(struct napi_struc
+ /* For the case where the last mvneta_poll did not process all
+ * RX packets
+ */
++ rx_queue = fls(((cause_rx_tx >> 8) & 0xff));
++
+ cause_rx_tx |= port->cause_rx_tx;
+- rx_done = mvneta_rx(pp, budget, &pp->rxqs[pp->rxq_def]);
++
++ if (rx_queue) {
++ rx_queue = rx_queue - 1;
++ rx_done = mvneta_rx(pp, budget, &pp->rxqs[rx_queue]);
++ }
++
+ budget -= rx_done;
+
+ if (budget > 0) {
+@@ -2419,19 +2451,27 @@ static void mvneta_cleanup_txqs(struct m
+ /* Cleanup all Rx queues */
+ static void mvneta_cleanup_rxqs(struct mvneta_port *pp)
+ {
+- mvneta_rxq_deinit(pp, &pp->rxqs[pp->rxq_def]);
++ int queue;
++
++ for (queue = 0; queue < txq_number; queue++)
++ mvneta_rxq_deinit(pp, &pp->rxqs[queue]);
+ }
+
+
+ /* Init all Rx queues */
+ static int mvneta_setup_rxqs(struct mvneta_port *pp)
+ {
+- int err = mvneta_rxq_init(pp, &pp->rxqs[pp->rxq_def]);
+- if (err) {
+- netdev_err(pp->dev, "%s: can't create rxq=%d\n",
+- __func__, pp->rxq_def);
+- mvneta_cleanup_rxqs(pp);
+- return err;
++ int queue;
++
++ for (queue = 0; queue < rxq_number; queue++) {
++ int err = mvneta_rxq_init(pp, &pp->rxqs[queue]);
++
++ if (err) {
++ netdev_err(pp->dev, "%s: can't create rxq=%d\n",
++ __func__, queue);
++ mvneta_cleanup_rxqs(pp);
++ return err;
++ }
+ }
+
+ return 0;
+@@ -2455,6 +2495,19 @@ static int mvneta_setup_txqs(struct mvne
+ return 0;
+ }
+
++static void mvneta_percpu_unmask_interrupt(void *arg)
++{
++ struct mvneta_port *pp = arg;
++
++ /* All the queue are unmasked, but actually only the ones
++ * maped to this CPU will be unmasked
++ */
++ mvreg_write(pp, MVNETA_INTR_NEW_MASK,
++ MVNETA_RX_INTR_MASK_ALL |
++ MVNETA_TX_INTR_MASK_ALL |
++ MVNETA_MISCINTR_INTR_MASK);
++}
++
+ static void mvneta_start_dev(struct mvneta_port *pp)
+ {
+ unsigned int cpu;
+@@ -2472,11 +2525,10 @@ static void mvneta_start_dev(struct mvne
+ napi_enable(&port->napi);
+ }
+
+- /* Unmask interrupts */
+- mvreg_write(pp, MVNETA_INTR_NEW_MASK,
+- MVNETA_RX_INTR_MASK(rxq_number) |
+- MVNETA_TX_INTR_MASK(txq_number) |
+- MVNETA_MISCINTR_INTR_MASK);
++ /* Unmask interrupts. It has to be done from each CPU */
++ for_each_online_cpu(cpu)
++ smp_call_function_single(cpu, mvneta_percpu_unmask_interrupt,
++ pp, true);
+ mvreg_write(pp, MVNETA_INTR_MISC_MASK,
+ MVNETA_CAUSE_PHY_STATUS_CHANGE |
+ MVNETA_CAUSE_LINK_CHANGE |
+@@ -2752,22 +2804,35 @@ static void mvneta_percpu_disable(void *
+
+ static void mvneta_percpu_elect(struct mvneta_port *pp)
+ {
+- int online_cpu_idx, cpu, i = 0;
++ int online_cpu_idx, max_cpu, cpu, i = 0;
+
+ online_cpu_idx = pp->rxq_def % num_online_cpus();
++ max_cpu = num_present_cpus();
+
+ for_each_online_cpu(cpu) {
+- if (i == online_cpu_idx)
+- /* Enable per-CPU interrupt on the one CPU we
+- * just elected
++ int rxq_map = 0, txq_map = 0;
++ int rxq;
++
++ for (rxq = 0; rxq < rxq_number; rxq++)
++ if ((rxq % max_cpu) == cpu)
++ rxq_map |= MVNETA_CPU_RXQ_ACCESS(rxq);
++
++ if (i == online_cpu_idx) {
++ /* Map the default receive queue and transmit
++ * queue to the elected CPU
+ */
+- smp_call_function_single(cpu, mvneta_percpu_enable,
+- pp, true);
+- else
+- /* Disable per-CPU interrupt on all the other CPU */
+- smp_call_function_single(cpu, mvneta_percpu_disable,
+- pp, true);
++ rxq_map |= MVNETA_CPU_RXQ_ACCESS(pp->rxq_def);
++ txq_map = MVNETA_CPU_TXQ_ACCESS_ALL_MASK;
++ }
++ mvreg_write(pp, MVNETA_CPU_MAP(cpu), rxq_map | txq_map);
++
++ /* Update the interrupt mask on each CPU according the
++ * new mapping
++ */
++ smp_call_function_single(cpu, mvneta_percpu_unmask_interrupt,
++ pp, true);
+ i++;
++
+ }
+ };
+
+@@ -2802,12 +2867,22 @@ static int mvneta_percpu_notifier(struct
+ mvreg_write(pp, MVNETA_INTR_MISC_MASK, 0);
+ napi_enable(&port->napi);
+
++
++ /* Enable per-CPU interrupts on the CPU that is
++ * brought up.
++ */
++ smp_call_function_single(cpu, mvneta_percpu_enable,
++ pp, true);
++
+ /* Enable per-CPU interrupt on the one CPU we care
+ * about.
+ */
+ mvneta_percpu_elect(pp);
+
+- /* Unmask all ethernet port interrupts */
++ /* Unmask all ethernet port interrupts, as this
++ * notifier is called for each CPU then the CPU to
++ * Queue mapping is applied
++ */
+ mvreg_write(pp, MVNETA_INTR_NEW_MASK,
+ MVNETA_RX_INTR_MASK(rxq_number) |
+ MVNETA_TX_INTR_MASK(txq_number) |
+@@ -2858,7 +2933,7 @@ static int mvneta_percpu_notifier(struct
+ static int mvneta_open(struct net_device *dev)
+ {
+ struct mvneta_port *pp = netdev_priv(dev);
+- int ret;
++ int ret, cpu;
+
+ pp->pkt_size = MVNETA_RX_PKT_SIZE(pp->dev->mtu);
+ pp->frag_size = SKB_DATA_ALIGN(MVNETA_RX_BUF_SIZE(pp->pkt_size)) +
+@@ -2888,8 +2963,13 @@ static int mvneta_open(struct net_device
+ */
+ mvneta_percpu_disable(pp);
+
+- /* Elect a CPU to handle our RX queue interrupt */
+- mvneta_percpu_elect(pp);
++ /* Enable per-CPU interrupt on all the CPU to handle our RX
++ * queue interrupts
++ */
++ for_each_online_cpu(cpu)
++ smp_call_function_single(cpu, mvneta_percpu_enable,
++ pp, true);
++
+
+ /* Register a CPU notifier to handle the case where our CPU
+ * might be taken offline.
diff --git a/target/linux/mvebu/patches-4.4/034-net-mvneta-Add-naive-RSS-support.patch b/target/linux/mvebu/patches-4.4/034-net-mvneta-Add-naive-RSS-support.patch
new file mode 100644
index 0000000000..629c44c8a1
--- /dev/null
+++ b/target/linux/mvebu/patches-4.4/034-net-mvneta-Add-naive-RSS-support.patch
@@ -0,0 +1,191 @@
+From: Gregory CLEMENT <gregory.clement@free-electrons.com>
+Date: Wed, 9 Dec 2015 18:23:50 +0100
+Subject: [PATCH] net: mvneta: Add naive RSS support
+
+This patch adds the support for the RSS related ethtool
+function. Currently it only uses one entry in the indirection table which
+allows associating an mvneta interface to a given CPU.
+
+Signed-off-by: Gregory CLEMENT <gregory.clement@free-electrons.com>
+Tested-by: Marcin Wojtas <mw@semihalf.com>
+Signed-off-by: David S. Miller <davem@davemloft.net>
+---
+
+--- a/drivers/net/ethernet/marvell/mvneta.c
++++ b/drivers/net/ethernet/marvell/mvneta.c
+@@ -261,6 +261,11 @@
+
+ #define MVNETA_TX_MTU_MAX 0x3ffff
+
++/* The RSS lookup table actually has 256 entries but we do not use
++ * them yet
++ */
++#define MVNETA_RSS_LU_TABLE_SIZE 1
++
+ /* TSO header size */
+ #define TSO_HEADER_SIZE 128
+
+@@ -382,6 +387,8 @@ struct mvneta_port {
+ unsigned int use_inband_status:1;
+
+ u64 ethtool_stats[ARRAY_SIZE(mvneta_statistics)];
++
++ u32 indir[MVNETA_RSS_LU_TABLE_SIZE];
+ };
+
+ /* The mvneta_tx_desc and mvneta_rx_desc structures describe the
+@@ -1067,7 +1074,7 @@ static void mvneta_defaults_set(struct m
+ if ((rxq % max_cpu) == cpu)
+ rxq_map |= MVNETA_CPU_RXQ_ACCESS(rxq);
+
+- if (cpu == rxq_def)
++ if (cpu == pp->rxq_def)
+ txq_map = MVNETA_CPU_TXQ_ACCESS_ALL_MASK;
+
+ mvreg_write(pp, MVNETA_CPU_MAP(cpu), rxq_map | txq_map);
+@@ -2508,6 +2515,18 @@ static void mvneta_percpu_unmask_interru
+ MVNETA_MISCINTR_INTR_MASK);
+ }
+
++static void mvneta_percpu_mask_interrupt(void *arg)
++{
++ struct mvneta_port *pp = arg;
++
++ /* All the queue are masked, but actually only the ones
++ * maped to this CPU will be masked
++ */
++ mvreg_write(pp, MVNETA_INTR_NEW_MASK, 0);
++ mvreg_write(pp, MVNETA_INTR_OLD_MASK, 0);
++ mvreg_write(pp, MVNETA_INTR_MISC_MASK, 0);
++}
++
+ static void mvneta_start_dev(struct mvneta_port *pp)
+ {
+ unsigned int cpu;
+@@ -3231,6 +3250,106 @@ static int mvneta_ethtool_get_sset_count
+ return -EOPNOTSUPP;
+ }
+
++static u32 mvneta_ethtool_get_rxfh_indir_size(struct net_device *dev)
++{
++ return MVNETA_RSS_LU_TABLE_SIZE;
++}
++
++static int mvneta_ethtool_get_rxnfc(struct net_device *dev,
++ struct ethtool_rxnfc *info,
++ u32 *rules __always_unused)
++{
++ switch (info->cmd) {
++ case ETHTOOL_GRXRINGS:
++ info->data = rxq_number;
++ return 0;
++ case ETHTOOL_GRXFH:
++ return -EOPNOTSUPP;
++ default:
++ return -EOPNOTSUPP;
++ }
++}
++
++static int mvneta_config_rss(struct mvneta_port *pp)
++{
++ int cpu;
++ u32 val;
++
++ netif_tx_stop_all_queues(pp->dev);
++
++ for_each_online_cpu(cpu)
++ smp_call_function_single(cpu, mvneta_percpu_mask_interrupt,
++ pp, true);
++
++ /* We have to synchronise on the napi of each CPU */
++ for_each_online_cpu(cpu) {
++ struct mvneta_pcpu_port *pcpu_port =
++ per_cpu_ptr(pp->ports, cpu);
++
++ napi_synchronize(&pcpu_port->napi);
++ napi_disable(&pcpu_port->napi);
++ }
++
++ pp->rxq_def = pp->indir[0];
++
++ /* Update unicast mapping */
++ mvneta_set_rx_mode(pp->dev);
++
++ /* Update val of portCfg register accordingly with all RxQueue types */
++ val = MVNETA_PORT_CONFIG_DEFL_VALUE(pp->rxq_def);
++ mvreg_write(pp, MVNETA_PORT_CONFIG, val);
++
++ /* Update the elected CPU matching the new rxq_def */
++ mvneta_percpu_elect(pp);
++
++ /* We have to synchronise on the napi of each CPU */
++ for_each_online_cpu(cpu) {
++ struct mvneta_pcpu_port *pcpu_port =
++ per_cpu_ptr(pp->ports, cpu);
++
++ napi_enable(&pcpu_port->napi);
++ }
++
++ netif_tx_start_all_queues(pp->dev);
++
++ return 0;
++}
++
++static int mvneta_ethtool_set_rxfh(struct net_device *dev, const u32 *indir,
++ const u8 *key, const u8 hfunc)
++{
++ struct mvneta_port *pp = netdev_priv(dev);
++ /* We require at least one supported parameter to be changed
++ * and no change in any of the unsupported parameters
++ */
++ if (key ||
++ (hfunc != ETH_RSS_HASH_NO_CHANGE && hfunc != ETH_RSS_HASH_TOP))
++ return -EOPNOTSUPP;
++
++ if (!indir)
++ return 0;
++
++ memcpy(pp->indir, indir, MVNETA_RSS_LU_TABLE_SIZE);
++
++ return mvneta_config_rss(pp);
++}
++
++static int mvneta_ethtool_get_rxfh(struct net_device *dev, u32 *indir, u8 *key,
++ u8 *hfunc)
++{
++ struct mvneta_port *pp = netdev_priv(dev);
++
++ if (hfunc)
++ *hfunc = ETH_RSS_HASH_TOP;
++
++ if (!indir)
++ return 0;
++
++ memcpy(indir, pp->indir, MVNETA_RSS_LU_TABLE_SIZE);
++
++ return 0;
++}
++
+ static const struct net_device_ops mvneta_netdev_ops = {
+ .ndo_open = mvneta_open,
+ .ndo_stop = mvneta_stop,
+@@ -3255,6 +3374,10 @@ const struct ethtool_ops mvneta_eth_tool
+ .get_strings = mvneta_ethtool_get_strings,
+ .get_ethtool_stats = mvneta_ethtool_get_stats,
+ .get_sset_count = mvneta_ethtool_get_sset_count,
++ .get_rxfh_indir_size = mvneta_ethtool_get_rxfh_indir_size,
++ .get_rxnfc = mvneta_ethtool_get_rxnfc,
++ .get_rxfh = mvneta_ethtool_get_rxfh,
++ .set_rxfh = mvneta_ethtool_set_rxfh,
+ };
+
+ /* Initialize hw */
+@@ -3446,6 +3569,8 @@ static int mvneta_probe(struct platform_
+
+ pp->rxq_def = rxq_def;
+
++ pp->indir[0] = rxq_def;
++
+ pp->clk = devm_clk_get(&pdev->dev, NULL);
+ if (IS_ERR(pp->clk)) {
+ err = PTR_ERR(pp->clk);
diff --git a/target/linux/mvebu/patches-4.4/035-net-mvneta-Configure-XPS-support.patch b/target/linux/mvebu/patches-4.4/035-net-mvneta-Configure-XPS-support.patch
new file mode 100644
index 0000000000..5b35b6442b
--- /dev/null
+++ b/target/linux/mvebu/patches-4.4/035-net-mvneta-Configure-XPS-support.patch
@@ -0,0 +1,124 @@
+From: Gregory CLEMENT <gregory.clement@free-electrons.com>
+Date: Wed, 9 Dec 2015 18:23:51 +0100
+Subject: [PATCH] net: mvneta: Configure XPS support
+
+With this patch each CPU is associated with its own set of TX queues.
+
+It also setup the XPS with an initial configuration which set the
+affinity matching the hardware configuration.
+
+Suggested-by: Arnd Bergmann <arnd@arndb.de>
+Signed-off-by: Gregory CLEMENT <gregory.clement@free-electrons.com>
+Signed-off-by: David S. Miller <davem@davemloft.net>
+---
+
+--- a/drivers/net/ethernet/marvell/mvneta.c
++++ b/drivers/net/ethernet/marvell/mvneta.c
+@@ -111,6 +111,7 @@
+ #define MVNETA_CPU_RXQ_ACCESS_ALL_MASK 0x000000ff
+ #define MVNETA_CPU_TXQ_ACCESS_ALL_MASK 0x0000ff00
+ #define MVNETA_CPU_RXQ_ACCESS(rxq) BIT(rxq)
++#define MVNETA_CPU_TXQ_ACCESS(txq) BIT(txq + 8)
+ #define MVNETA_RXQ_TIME_COAL_REG(q) (0x2580 + ((q) << 2))
+
+ /* Exception Interrupt Port/Queue Cause register
+@@ -514,6 +515,9 @@ struct mvneta_tx_queue {
+
+ /* DMA address of TSO headers */
+ dma_addr_t tso_hdrs_phys;
++
++ /* Affinity mask for CPUs*/
++ cpumask_t affinity_mask;
+ };
+
+ struct mvneta_rx_queue {
+@@ -1062,20 +1066,30 @@ static void mvneta_defaults_set(struct m
+ /* Enable MBUS Retry bit16 */
+ mvreg_write(pp, MVNETA_MBUS_RETRY, 0x20);
+
+- /* Set CPU queue access map. CPUs are assigned to the RX
+- * queues modulo their number and all the TX queues are
+- * assigned to the CPU associated to the default RX queue.
++ /* Set CPU queue access map. CPUs are assigned to the RX and
++ * TX queues modulo their number. If there is only one TX
++ * queue then it is assigned to the CPU associated to the
++ * default RX queue.
+ */
+ for_each_present_cpu(cpu) {
+ int rxq_map = 0, txq_map = 0;
+- int rxq;
++ int rxq, txq;
+
+ for (rxq = 0; rxq < rxq_number; rxq++)
+ if ((rxq % max_cpu) == cpu)
+ rxq_map |= MVNETA_CPU_RXQ_ACCESS(rxq);
+
+- if (cpu == pp->rxq_def)
+- txq_map = MVNETA_CPU_TXQ_ACCESS_ALL_MASK;
++ for (txq = 0; txq < txq_number; txq++)
++ if ((txq % max_cpu) == cpu)
++ txq_map |= MVNETA_CPU_TXQ_ACCESS(txq);
++
++ /* With only one TX queue we configure a special case
++ * which will allow to get all the irq on a single
++ * CPU
++ */
++ if (txq_number == 1)
++ txq_map = (cpu == pp->rxq_def) ?
++ MVNETA_CPU_TXQ_ACCESS(1) : 0;
+
+ mvreg_write(pp, MVNETA_CPU_MAP(cpu), rxq_map | txq_map);
+ }
+@@ -2362,6 +2376,8 @@ static void mvneta_rxq_deinit(struct mvn
+ static int mvneta_txq_init(struct mvneta_port *pp,
+ struct mvneta_tx_queue *txq)
+ {
++ int cpu;
++
+ txq->size = pp->tx_ring_size;
+
+ /* A queue must always have room for at least one skb.
+@@ -2414,6 +2430,14 @@ static int mvneta_txq_init(struct mvneta
+ }
+ mvneta_tx_done_pkts_coal_set(pp, txq, txq->done_pkts_coal);
+
++ /* Setup XPS mapping */
++ if (txq_number > 1)
++ cpu = txq->id % num_present_cpus();
++ else
++ cpu = pp->rxq_def % num_present_cpus();
++ cpumask_set_cpu(cpu, &txq->affinity_mask);
++ netif_set_xps_queue(pp->dev, &txq->affinity_mask, txq->id);
++
+ return 0;
+ }
+
+@@ -2836,13 +2860,23 @@ static void mvneta_percpu_elect(struct m
+ if ((rxq % max_cpu) == cpu)
+ rxq_map |= MVNETA_CPU_RXQ_ACCESS(rxq);
+
+- if (i == online_cpu_idx) {
+- /* Map the default receive queue and transmit
+- * queue to the elected CPU
++ if (i == online_cpu_idx)
++ /* Map the default receive queue queue to the
++ * elected CPU
+ */
+ rxq_map |= MVNETA_CPU_RXQ_ACCESS(pp->rxq_def);
+- txq_map = MVNETA_CPU_TXQ_ACCESS_ALL_MASK;
+- }
++
++ /* We update the TX queue map only if we have one
++ * queue. In this case we associate the TX queue to
++ * the CPU bound to the default RX queue
++ */
++ if (txq_number == 1)
++ txq_map = (i == online_cpu_idx) ?
++ MVNETA_CPU_TXQ_ACCESS(1) : 0;
++ else
++ txq_map = mvreg_read(pp, MVNETA_CPU_MAP(cpu)) &
++ MVNETA_CPU_TXQ_ACCESS_ALL_MASK;
++
+ mvreg_write(pp, MVNETA_CPU_MAP(cpu), rxq_map | txq_map);
+
+ /* Update the interrupt mask on each CPU according the
diff --git a/target/linux/mvebu/patches-4.4/036-net-mvneta-fix-trivial-cut-off-issue-in-mvneta_ethto.patch b/target/linux/mvebu/patches-4.4/036-net-mvneta-fix-trivial-cut-off-issue-in-mvneta_ethto.patch
new file mode 100644
index 0000000000..2bd7a88032
--- /dev/null
+++ b/target/linux/mvebu/patches-4.4/036-net-mvneta-fix-trivial-cut-off-issue-in-mvneta_ethto.patch
@@ -0,0 +1,46 @@
+From: Jisheng Zhang <jszhang@marvell.com>
+Date: Wed, 20 Jan 2016 16:36:25 +0800
+Subject: [PATCH] net: mvneta: fix trivial cut-off issue in
+ mvneta_ethtool_update_stats
+
+When s->type is T_REG_64, the high 32bits are lost in val. This patch
+fixes this trivial issue.
+
+Signed-off-by: Jisheng Zhang <jszhang@marvell.com>
+Fixes: 9b0cdefa4cd5 ("net: mvneta: add ethtool statistics")
+Signed-off-by: David S. Miller <davem@davemloft.net>
+---
+
+--- a/drivers/net/ethernet/marvell/mvneta.c
++++ b/drivers/net/ethernet/marvell/mvneta.c
+@@ -3242,26 +3242,25 @@ static void mvneta_ethtool_update_stats(
+ const struct mvneta_statistic *s;
+ void __iomem *base = pp->base;
+ u32 high, low, val;
++ u64 val64;
+ int i;
+
+ for (i = 0, s = mvneta_statistics;
+ s < mvneta_statistics + ARRAY_SIZE(mvneta_statistics);
+ s++, i++) {
+- val = 0;
+-
+ switch (s->type) {
+ case T_REG_32:
+ val = readl_relaxed(base + s->offset);
++ pp->ethtool_stats[i] += val;
+ break;
+ case T_REG_64:
+ /* Docs say to read low 32-bit then high */
+ low = readl_relaxed(base + s->offset);
+ high = readl_relaxed(base + s->offset + 4);
+- val = (u64)high << 32 | low;
++ val64 = (u64)high << 32 | low;
++ pp->ethtool_stats[i] += val64;
+ break;
+ }
+-
+- pp->ethtool_stats[i] += val;
+ }
+ }
+
diff --git a/target/linux/mvebu/patches-4.4/037-net-mvneta-Fix-for_each_present_cpu-usage.patch b/target/linux/mvebu/patches-4.4/037-net-mvneta-Fix-for_each_present_cpu-usage.patch
new file mode 100644
index 0000000000..9ded5b71fe
--- /dev/null
+++ b/target/linux/mvebu/patches-4.4/037-net-mvneta-Fix-for_each_present_cpu-usage.patch
@@ -0,0 +1,55 @@
+From: Gregory CLEMENT <gregory.clement@free-electrons.com>
+Date: Thu, 4 Feb 2016 22:09:23 +0100
+Subject: [PATCH] net: mvneta: Fix for_each_present_cpu usage
+
+This patch convert the for_each_present in on_each_cpu, instead of
+applying on the present cpus it will be applied only on the online cpus.
+This fix a bug reported on
+http://thread.gmane.org/gmane.linux.ports.arm.kernel/468173.
+
+Using the macro on_each_cpu (instead of a for_each_* loop) also ensures
+that all the calls will be done all at once.
+
+Fixes: f86428854480 ("net: mvneta: Statically assign queues to CPUs")
+Reported-by: Stefan Roese <stefan.roese@gmail.com>
+Suggested-by: Jisheng Zhang <jszhang@marvell.com>
+Suggested-by: Russell King <rmk+kernel@arm.linux.org.uk>
+Signed-off-by: Gregory CLEMENT <gregory.clement@free-electrons.com>
+Signed-off-by: David S. Miller <davem@davemloft.net>
+---
+
+--- a/drivers/net/ethernet/marvell/mvneta.c
++++ b/drivers/net/ethernet/marvell/mvneta.c
+@@ -2562,7 +2562,7 @@ static void mvneta_start_dev(struct mvne
+ mvneta_port_enable(pp);
+
+ /* Enable polling on the port */
+- for_each_present_cpu(cpu) {
++ for_each_online_cpu(cpu) {
+ struct mvneta_pcpu_port *port = per_cpu_ptr(pp->ports, cpu);
+
+ napi_enable(&port->napi);
+@@ -2587,7 +2587,7 @@ static void mvneta_stop_dev(struct mvnet
+
+ phy_stop(pp->phy_dev);
+
+- for_each_present_cpu(cpu) {
++ for_each_online_cpu(cpu) {
+ struct mvneta_pcpu_port *port = per_cpu_ptr(pp->ports, cpu);
+
+ napi_disable(&port->napi);
+@@ -3055,13 +3055,11 @@ err_cleanup_rxqs:
+ static int mvneta_stop(struct net_device *dev)
+ {
+ struct mvneta_port *pp = netdev_priv(dev);
+- int cpu;
+
+ mvneta_stop_dev(pp);
+ mvneta_mdio_remove(pp);
+ unregister_cpu_notifier(&pp->cpu_notifier);
+- for_each_present_cpu(cpu)
+- smp_call_function_single(cpu, mvneta_percpu_disable, pp, true);
++ on_each_cpu(mvneta_percpu_disable, pp, true);
+ free_percpu_irq(dev->irq, pp->ports);
+ mvneta_cleanup_rxqs(pp);
+ mvneta_cleanup_txqs(pp);
diff --git a/target/linux/mvebu/patches-4.4/038-net-mvneta-Fix-the-CPU-choice-in-mvneta_percpu_elect.patch b/target/linux/mvebu/patches-4.4/038-net-mvneta-Fix-the-CPU-choice-in-mvneta_percpu_elect.patch
new file mode 100644
index 0000000000..4fc9ccc76a
--- /dev/null
+++ b/target/linux/mvebu/patches-4.4/038-net-mvneta-Fix-the-CPU-choice-in-mvneta_percpu_elect.patch
@@ -0,0 +1,57 @@
+From: Gregory CLEMENT <gregory.clement@free-electrons.com>
+Date: Thu, 4 Feb 2016 22:09:24 +0100
+Subject: [PATCH] net: mvneta: Fix the CPU choice in mvneta_percpu_elect
+
+When passing to the management of multiple RX queue, the
+mvneta_percpu_elect function was broken. The use of the modulo can lead
+to elect the wrong cpu. For example with rxq_def=2, if the CPU 2 goes
+offline and then online, we ended with the third RX queue activated in
+the same time on CPU 0 and CPU2, which lead to a kernel crash.
+
+With this fix, we don't try to get "the closer" CPU if the default CPU is
+gone, now we just use CPU 0 which always be there. Thanks to this, the
+code becomes more readable, easier to maintain and more predicable.
+
+Cc: stable@vger.kernel.org
+Fixes: 2dcf75e2793c ("net: mvneta: Associate RX queues with each CPU")
+Signed-off-by: Gregory CLEMENT <gregory.clement@free-electrons.com>
+Signed-off-by: David S. Miller <davem@davemloft.net>
+---
+
+--- a/drivers/net/ethernet/marvell/mvneta.c
++++ b/drivers/net/ethernet/marvell/mvneta.c
+@@ -2847,9 +2847,14 @@ static void mvneta_percpu_disable(void *
+
+ static void mvneta_percpu_elect(struct mvneta_port *pp)
+ {
+- int online_cpu_idx, max_cpu, cpu, i = 0;
++ int elected_cpu = 0, max_cpu, cpu, i = 0;
++
++ /* Use the cpu associated to the rxq when it is online, in all
++ * the other cases, use the cpu 0 which can't be offline.
++ */
++ if (cpu_online(pp->rxq_def))
++ elected_cpu = pp->rxq_def;
+
+- online_cpu_idx = pp->rxq_def % num_online_cpus();
+ max_cpu = num_present_cpus();
+
+ for_each_online_cpu(cpu) {
+@@ -2860,7 +2865,7 @@ static void mvneta_percpu_elect(struct m
+ if ((rxq % max_cpu) == cpu)
+ rxq_map |= MVNETA_CPU_RXQ_ACCESS(rxq);
+
+- if (i == online_cpu_idx)
++ if (cpu == elected_cpu)
+ /* Map the default receive queue queue to the
+ * elected CPU
+ */
+@@ -2871,7 +2876,7 @@ static void mvneta_percpu_elect(struct m
+ * the CPU bound to the default RX queue
+ */
+ if (txq_number == 1)
+- txq_map = (i == online_cpu_idx) ?
++ txq_map = (cpu == elected_cpu) ?
+ MVNETA_CPU_TXQ_ACCESS(1) : 0;
+ else
+ txq_map = mvreg_read(pp, MVNETA_CPU_MAP(cpu)) &
diff --git a/target/linux/mvebu/patches-4.4/039-net-mvneta-Use-on_each_cpu-when-possible.patch b/target/linux/mvebu/patches-4.4/039-net-mvneta-Use-on_each_cpu-when-possible.patch
new file mode 100644
index 0000000000..76257a2a71
--- /dev/null
+++ b/target/linux/mvebu/patches-4.4/039-net-mvneta-Use-on_each_cpu-when-possible.patch
@@ -0,0 +1,68 @@
+From: Gregory CLEMENT <gregory.clement@free-electrons.com>
+Date: Thu, 4 Feb 2016 22:09:25 +0100
+Subject: [PATCH] net: mvneta: Use on_each_cpu when possible
+
+Instead of using a for_each_* loop in which we just call the
+smp_call_function_single macro, it is more simple to directly use the
+on_each_cpu macro. Moreover, this macro ensures that the calls will be
+done all at once.
+
+Suggested-by: Russell King <rmk+kernel@arm.linux.org.uk>
+Signed-off-by: Gregory CLEMENT <gregory.clement@free-electrons.com>
+Signed-off-by: David S. Miller <davem@davemloft.net>
+---
+
+--- a/drivers/net/ethernet/marvell/mvneta.c
++++ b/drivers/net/ethernet/marvell/mvneta.c
+@@ -2553,7 +2553,7 @@ static void mvneta_percpu_mask_interrupt
+
+ static void mvneta_start_dev(struct mvneta_port *pp)
+ {
+- unsigned int cpu;
++ int cpu;
+
+ mvneta_max_rx_size_set(pp, pp->pkt_size);
+ mvneta_txq_max_tx_size_set(pp, pp->pkt_size);
+@@ -2569,9 +2569,8 @@ static void mvneta_start_dev(struct mvne
+ }
+
+ /* Unmask interrupts. It has to be done from each CPU */
+- for_each_online_cpu(cpu)
+- smp_call_function_single(cpu, mvneta_percpu_unmask_interrupt,
+- pp, true);
++ on_each_cpu(mvneta_percpu_unmask_interrupt, pp, true);
++
+ mvreg_write(pp, MVNETA_INTR_MISC_MASK,
+ MVNETA_CAUSE_PHY_STATUS_CHANGE |
+ MVNETA_CAUSE_LINK_CHANGE |
+@@ -2991,7 +2990,7 @@ static int mvneta_percpu_notifier(struct
+ static int mvneta_open(struct net_device *dev)
+ {
+ struct mvneta_port *pp = netdev_priv(dev);
+- int ret, cpu;
++ int ret;
+
+ pp->pkt_size = MVNETA_RX_PKT_SIZE(pp->dev->mtu);
+ pp->frag_size = SKB_DATA_ALIGN(MVNETA_RX_BUF_SIZE(pp->pkt_size)) +
+@@ -3024,9 +3023,7 @@ static int mvneta_open(struct net_device
+ /* Enable per-CPU interrupt on all the CPU to handle our RX
+ * queue interrupts
+ */
+- for_each_online_cpu(cpu)
+- smp_call_function_single(cpu, mvneta_percpu_enable,
+- pp, true);
++ on_each_cpu(mvneta_percpu_enable, pp, true);
+
+
+ /* Register a CPU notifier to handle the case where our CPU
+@@ -3313,9 +3310,7 @@ static int mvneta_config_rss(struct mvn
+
+ netif_tx_stop_all_queues(pp->dev);
+
+- for_each_online_cpu(cpu)
+- smp_call_function_single(cpu, mvneta_percpu_mask_interrupt,
+- pp, true);
++ on_each_cpu(mvneta_percpu_mask_interrupt, pp, true);
+
+ /* We have to synchronise on the napi of each CPU */
+ for_each_online_cpu(cpu) {
diff --git a/target/linux/mvebu/patches-4.4/040-net-mvneta-Modify-the-queue-related-fields-from-each.patch b/target/linux/mvebu/patches-4.4/040-net-mvneta-Modify-the-queue-related-fields-from-each.patch
new file mode 100644
index 0000000000..b025777df9
--- /dev/null
+++ b/target/linux/mvebu/patches-4.4/040-net-mvneta-Modify-the-queue-related-fields-from-each.patch
@@ -0,0 +1,179 @@
+From: Gregory CLEMENT <gregory.clement@free-electrons.com>
+Date: Thu, 4 Feb 2016 22:09:27 +0100
+Subject: [PATCH] net: mvneta: Modify the queue related fields from each cpu
+
+In the MVNETA_INTR_* registers, the queues related fields are per cpu,
+according to the datasheet (comment in [] are added by me):
+"In a multi-CPU system, bits of RX[or TX] queues for which the access by
+the reading[or writing] CPU is disabled are read as 0, and cannot be
+cleared[or written]."
+
+That means that each time we want to manipulate these bits we had to do
+it on each cpu and not only on the current cpu.
+
+Signed-off-by: Gregory CLEMENT <gregory.clement@free-electrons.com>
+Signed-off-by: David S. Miller <davem@davemloft.net>
+---
+
+--- a/drivers/net/ethernet/marvell/mvneta.c
++++ b/drivers/net/ethernet/marvell/mvneta.c
+@@ -1036,6 +1036,43 @@ static void mvneta_set_autoneg(struct mv
+ }
+ }
+
++static void mvneta_percpu_unmask_interrupt(void *arg)
++{
++ struct mvneta_port *pp = arg;
++
++ /* All the queue are unmasked, but actually only the ones
++ * mapped to this CPU will be unmasked
++ */
++ mvreg_write(pp, MVNETA_INTR_NEW_MASK,
++ MVNETA_RX_INTR_MASK_ALL |
++ MVNETA_TX_INTR_MASK_ALL |
++ MVNETA_MISCINTR_INTR_MASK);
++}
++
++static void mvneta_percpu_mask_interrupt(void *arg)
++{
++ struct mvneta_port *pp = arg;
++
++ /* All the queue are masked, but actually only the ones
++ * mapped to this CPU will be masked
++ */
++ mvreg_write(pp, MVNETA_INTR_NEW_MASK, 0);
++ mvreg_write(pp, MVNETA_INTR_OLD_MASK, 0);
++ mvreg_write(pp, MVNETA_INTR_MISC_MASK, 0);
++}
++
++static void mvneta_percpu_clear_intr_cause(void *arg)
++{
++ struct mvneta_port *pp = arg;
++
++ /* All the queue are cleared, but actually only the ones
++ * mapped to this CPU will be cleared
++ */
++ mvreg_write(pp, MVNETA_INTR_NEW_CAUSE, 0);
++ mvreg_write(pp, MVNETA_INTR_MISC_CAUSE, 0);
++ mvreg_write(pp, MVNETA_INTR_OLD_CAUSE, 0);
++}
++
+ /* This method sets defaults to the NETA port:
+ * Clears interrupt Cause and Mask registers.
+ * Clears all MAC tables.
+@@ -1053,14 +1090,10 @@ static void mvneta_defaults_set(struct m
+ int max_cpu = num_present_cpus();
+
+ /* Clear all Cause registers */
+- mvreg_write(pp, MVNETA_INTR_NEW_CAUSE, 0);
+- mvreg_write(pp, MVNETA_INTR_OLD_CAUSE, 0);
+- mvreg_write(pp, MVNETA_INTR_MISC_CAUSE, 0);
++ on_each_cpu(mvneta_percpu_clear_intr_cause, pp, true);
+
+ /* Mask all interrupts */
+- mvreg_write(pp, MVNETA_INTR_NEW_MASK, 0);
+- mvreg_write(pp, MVNETA_INTR_OLD_MASK, 0);
+- mvreg_write(pp, MVNETA_INTR_MISC_MASK, 0);
++ on_each_cpu(mvneta_percpu_mask_interrupt, pp, true);
+ mvreg_write(pp, MVNETA_INTR_ENABLE, 0);
+
+ /* Enable MBUS Retry bit16 */
+@@ -2526,31 +2559,6 @@ static int mvneta_setup_txqs(struct mvne
+ return 0;
+ }
+
+-static void mvneta_percpu_unmask_interrupt(void *arg)
+-{
+- struct mvneta_port *pp = arg;
+-
+- /* All the queue are unmasked, but actually only the ones
+- * maped to this CPU will be unmasked
+- */
+- mvreg_write(pp, MVNETA_INTR_NEW_MASK,
+- MVNETA_RX_INTR_MASK_ALL |
+- MVNETA_TX_INTR_MASK_ALL |
+- MVNETA_MISCINTR_INTR_MASK);
+-}
+-
+-static void mvneta_percpu_mask_interrupt(void *arg)
+-{
+- struct mvneta_port *pp = arg;
+-
+- /* All the queue are masked, but actually only the ones
+- * maped to this CPU will be masked
+- */
+- mvreg_write(pp, MVNETA_INTR_NEW_MASK, 0);
+- mvreg_write(pp, MVNETA_INTR_OLD_MASK, 0);
+- mvreg_write(pp, MVNETA_INTR_MISC_MASK, 0);
+-}
+-
+ static void mvneta_start_dev(struct mvneta_port *pp)
+ {
+ int cpu;
+@@ -2601,13 +2609,10 @@ static void mvneta_stop_dev(struct mvnet
+ mvneta_port_disable(pp);
+
+ /* Clear all ethernet port interrupts */
+- mvreg_write(pp, MVNETA_INTR_MISC_CAUSE, 0);
+- mvreg_write(pp, MVNETA_INTR_OLD_CAUSE, 0);
++ on_each_cpu(mvneta_percpu_clear_intr_cause, pp, true);
+
+ /* Mask all ethernet port interrupts */
+- mvreg_write(pp, MVNETA_INTR_NEW_MASK, 0);
+- mvreg_write(pp, MVNETA_INTR_OLD_MASK, 0);
+- mvreg_write(pp, MVNETA_INTR_MISC_MASK, 0);
++ on_each_cpu(mvneta_percpu_mask_interrupt, pp, true);
+
+ mvneta_tx_reset(pp);
+ mvneta_rx_reset(pp);
+@@ -2919,9 +2924,7 @@ static int mvneta_percpu_notifier(struct
+ }
+
+ /* Mask all ethernet port interrupts */
+- mvreg_write(pp, MVNETA_INTR_NEW_MASK, 0);
+- mvreg_write(pp, MVNETA_INTR_OLD_MASK, 0);
+- mvreg_write(pp, MVNETA_INTR_MISC_MASK, 0);
++ on_each_cpu(mvneta_percpu_mask_interrupt, pp, true);
+ napi_enable(&port->napi);
+
+
+@@ -2936,14 +2939,8 @@ static int mvneta_percpu_notifier(struct
+ */
+ mvneta_percpu_elect(pp);
+
+- /* Unmask all ethernet port interrupts, as this
+- * notifier is called for each CPU then the CPU to
+- * Queue mapping is applied
+- */
+- mvreg_write(pp, MVNETA_INTR_NEW_MASK,
+- MVNETA_RX_INTR_MASK(rxq_number) |
+- MVNETA_TX_INTR_MASK(txq_number) |
+- MVNETA_MISCINTR_INTR_MASK);
++ /* Unmask all ethernet port interrupts */
++ on_each_cpu(mvneta_percpu_unmask_interrupt, pp, true);
+ mvreg_write(pp, MVNETA_INTR_MISC_MASK,
+ MVNETA_CAUSE_PHY_STATUS_CHANGE |
+ MVNETA_CAUSE_LINK_CHANGE |
+@@ -2954,9 +2951,7 @@ static int mvneta_percpu_notifier(struct
+ case CPU_DOWN_PREPARE_FROZEN:
+ netif_tx_stop_all_queues(pp->dev);
+ /* Mask all ethernet port interrupts */
+- mvreg_write(pp, MVNETA_INTR_NEW_MASK, 0);
+- mvreg_write(pp, MVNETA_INTR_OLD_MASK, 0);
+- mvreg_write(pp, MVNETA_INTR_MISC_MASK, 0);
++ on_each_cpu(mvneta_percpu_mask_interrupt, pp, true);
+
+ napi_synchronize(&port->napi);
+ napi_disable(&port->napi);
+@@ -2972,10 +2967,7 @@ static int mvneta_percpu_notifier(struct
+ /* Check if a new CPU must be elected now this on is down */
+ mvneta_percpu_elect(pp);
+ /* Unmask all ethernet port interrupts */
+- mvreg_write(pp, MVNETA_INTR_NEW_MASK,
+- MVNETA_RX_INTR_MASK(rxq_number) |
+- MVNETA_TX_INTR_MASK(txq_number) |
+- MVNETA_MISCINTR_INTR_MASK);
++ on_each_cpu(mvneta_percpu_unmask_interrupt, pp, true);
+ mvreg_write(pp, MVNETA_INTR_MISC_MASK,
+ MVNETA_CAUSE_PHY_STATUS_CHANGE |
+ MVNETA_CAUSE_LINK_CHANGE |
diff --git a/target/linux/mvebu/patches-4.4/041-net-mvneta-The-mvneta_percpu_elect-function-should-b.patch b/target/linux/mvebu/patches-4.4/041-net-mvneta-The-mvneta_percpu_elect-function-should-b.patch
new file mode 100644
index 0000000000..a77bef44e4
--- /dev/null
+++ b/target/linux/mvebu/patches-4.4/041-net-mvneta-The-mvneta_percpu_elect-function-should-b.patch
@@ -0,0 +1,68 @@
+From: Gregory CLEMENT <gregory.clement@free-electrons.com>
+Date: Thu, 4 Feb 2016 22:09:28 +0100
+Subject: [PATCH] net: mvneta: The mvneta_percpu_elect function should be
+ atomic
+
+Electing a CPU must be done in an atomic way: it should be done after or
+before the removal/insertion of a CPU and this function is not reentrant.
+
+During the loop of mvneta_percpu_elect we associates the queues to the
+CPUs, if there is a topology change during this loop, then the mapping
+between the CPUs and the queues could be wrong. During this loop the
+interrupt mask is also updating for each CPUs, It should not be changed
+in the same time by other part of the driver.
+
+This patch adds spinlock to create the needed critical sections.
+
+Signed-off-by: Gregory CLEMENT <gregory.clement@free-electrons.com>
+Signed-off-by: David S. Miller <davem@davemloft.net>
+---
+
+--- a/drivers/net/ethernet/marvell/mvneta.c
++++ b/drivers/net/ethernet/marvell/mvneta.c
+@@ -370,6 +370,10 @@ struct mvneta_port {
+ struct net_device *dev;
+ struct notifier_block cpu_notifier;
+ int rxq_def;
++ /* Protect the access to the percpu interrupt registers,
++ * ensuring that the configuration remains coherent.
++ */
++ spinlock_t lock;
+
+ /* Core clock */
+ struct clk *clk;
+@@ -2853,6 +2857,12 @@ static void mvneta_percpu_elect(struct m
+ {
+ int elected_cpu = 0, max_cpu, cpu, i = 0;
+
++ /* Electing a CPU must be done in an atomic way: it should be
++ * done after or before the removal/insertion of a CPU and
++ * this function is not reentrant.
++ */
++ spin_lock(&pp->lock);
++
+ /* Use the cpu associated to the rxq when it is online, in all
+ * the other cases, use the cpu 0 which can't be offline.
+ */
+@@ -2896,6 +2906,7 @@ static void mvneta_percpu_elect(struct m
+ i++;
+
+ }
++ spin_unlock(&pp->lock);
+ };
+
+ static int mvneta_percpu_notifier(struct notifier_block *nfb,
+@@ -2950,8 +2961,13 @@ static int mvneta_percpu_notifier(struct
+ case CPU_DOWN_PREPARE:
+ case CPU_DOWN_PREPARE_FROZEN:
+ netif_tx_stop_all_queues(pp->dev);
++ /* Thanks to this lock we are sure that any pending
++ * cpu election is done
++ */
++ spin_lock(&pp->lock);
+ /* Mask all ethernet port interrupts */
+ on_each_cpu(mvneta_percpu_mask_interrupt, pp, true);
++ spin_unlock(&pp->lock);
+
+ napi_synchronize(&port->napi);
+ napi_disable(&port->napi);
diff --git a/target/linux/mvebu/patches-4.4/042-net-mvneta-Fix-race-condition-during-stopping.patch b/target/linux/mvebu/patches-4.4/042-net-mvneta-Fix-race-condition-during-stopping.patch
new file mode 100644
index 0000000000..9936ebf320
--- /dev/null
+++ b/target/linux/mvebu/patches-4.4/042-net-mvneta-Fix-race-condition-during-stopping.patch
@@ -0,0 +1,128 @@
+From: Gregory CLEMENT <gregory.clement@free-electrons.com>
+Date: Thu, 4 Feb 2016 22:09:29 +0100
+Subject: [PATCH] net: mvneta: Fix race condition during stopping
+
+When stopping the port, the CPU notifier are still there whereas the
+mvneta_stop_dev function calls mvneta_percpu_disable() on each CPUs.
+It was possible to have a new CPU coming at this point which could be
+racy.
+
+This patch adds a flag preventing executing the code notifier for a new
+CPU when the port is stopping. It also uses the spinlock introduces
+previously. To avoid the deadlock, the lock has been moved outside the
+mvneta_percpu_elect function.
+
+Signed-off-by: Gregory CLEMENT <gregory.clement@free-electrons.com>
+Signed-off-by: David S. Miller <davem@davemloft.net>
+---
+
+--- a/drivers/net/ethernet/marvell/mvneta.c
++++ b/drivers/net/ethernet/marvell/mvneta.c
+@@ -374,6 +374,7 @@ struct mvneta_port {
+ * ensuring that the configuration remains coherent.
+ */
+ spinlock_t lock;
++ bool is_stopped;
+
+ /* Core clock */
+ struct clk *clk;
+@@ -2853,16 +2854,14 @@ static void mvneta_percpu_disable(void *
+ disable_percpu_irq(pp->dev->irq);
+ }
+
++/* Electing a CPU must be done in an atomic way: it should be done
++ * after or before the removal/insertion of a CPU and this function is
++ * not reentrant.
++ */
+ static void mvneta_percpu_elect(struct mvneta_port *pp)
+ {
+ int elected_cpu = 0, max_cpu, cpu, i = 0;
+
+- /* Electing a CPU must be done in an atomic way: it should be
+- * done after or before the removal/insertion of a CPU and
+- * this function is not reentrant.
+- */
+- spin_lock(&pp->lock);
+-
+ /* Use the cpu associated to the rxq when it is online, in all
+ * the other cases, use the cpu 0 which can't be offline.
+ */
+@@ -2906,7 +2905,6 @@ static void mvneta_percpu_elect(struct m
+ i++;
+
+ }
+- spin_unlock(&pp->lock);
+ };
+
+ static int mvneta_percpu_notifier(struct notifier_block *nfb,
+@@ -2920,6 +2918,14 @@ static int mvneta_percpu_notifier(struct
+ switch (action) {
+ case CPU_ONLINE:
+ case CPU_ONLINE_FROZEN:
++ spin_lock(&pp->lock);
++ /* Configuring the driver for a new CPU while the
++ * driver is stopping is racy, so just avoid it.
++ */
++ if (pp->is_stopped) {
++ spin_unlock(&pp->lock);
++ break;
++ }
+ netif_tx_stop_all_queues(pp->dev);
+
+ /* We have to synchronise on tha napi of each CPU
+@@ -2957,6 +2963,7 @@ static int mvneta_percpu_notifier(struct
+ MVNETA_CAUSE_LINK_CHANGE |
+ MVNETA_CAUSE_PSC_SYNC_CHANGE);
+ netif_tx_start_all_queues(pp->dev);
++ spin_unlock(&pp->lock);
+ break;
+ case CPU_DOWN_PREPARE:
+ case CPU_DOWN_PREPARE_FROZEN:
+@@ -2981,7 +2988,9 @@ static int mvneta_percpu_notifier(struct
+ case CPU_DEAD:
+ case CPU_DEAD_FROZEN:
+ /* Check if a new CPU must be elected now this on is down */
++ spin_lock(&pp->lock);
+ mvneta_percpu_elect(pp);
++ spin_unlock(&pp->lock);
+ /* Unmask all ethernet port interrupts */
+ on_each_cpu(mvneta_percpu_unmask_interrupt, pp, true);
+ mvreg_write(pp, MVNETA_INTR_MISC_MASK,
+@@ -3033,7 +3042,7 @@ static int mvneta_open(struct net_device
+ */
+ on_each_cpu(mvneta_percpu_enable, pp, true);
+
+-
++ pp->is_stopped = false;
+ /* Register a CPU notifier to handle the case where our CPU
+ * might be taken offline.
+ */
+@@ -3066,9 +3075,18 @@ static int mvneta_stop(struct net_device
+ {
+ struct mvneta_port *pp = netdev_priv(dev);
+
++ /* Inform that we are stopping so we don't want to setup the
++ * driver for new CPUs in the notifiers
++ */
++ spin_lock(&pp->lock);
++ pp->is_stopped = true;
+ mvneta_stop_dev(pp);
+ mvneta_mdio_remove(pp);
+ unregister_cpu_notifier(&pp->cpu_notifier);
++ /* Now that the notifier are unregistered, we can release le
++ * lock
++ */
++ spin_unlock(&pp->lock);
+ on_each_cpu(mvneta_percpu_disable, pp, true);
+ free_percpu_irq(dev->irq, pp->ports);
+ mvneta_cleanup_rxqs(pp);
+@@ -3339,7 +3357,9 @@ static int mvneta_config_rss(struct mvn
+ mvreg_write(pp, MVNETA_PORT_CONFIG, val);
+
+ /* Update the elected CPU matching the new rxq_def */
++ spin_lock(&pp->lock);
+ mvneta_percpu_elect(pp);
++ spin_unlock(&pp->lock);
+
+ /* We have to synchronise on the napi of each CPU */
+ for_each_online_cpu(cpu) {
diff --git a/target/linux/mvebu/patches-4.4/043-net-mvneta-sort-the-headers-in-alphabetic-order.patch b/target/linux/mvebu/patches-4.4/043-net-mvneta-sort-the-headers-in-alphabetic-order.patch
new file mode 100644
index 0000000000..502c2584d9
--- /dev/null
+++ b/target/linux/mvebu/patches-4.4/043-net-mvneta-sort-the-headers-in-alphabetic-order.patch
@@ -0,0 +1,56 @@
+From: Jisheng Zhang <jszhang@marvell.com>
+Date: Wed, 20 Jan 2016 19:27:22 +0800
+Subject: [PATCH] net: mvneta: sort the headers in alphabetic order
+
+Sorting the headers in alphabetic order will help to reduce the conflict
+when adding new headers in the future.
+
+Signed-off-by: Jisheng Zhang <jszhang@marvell.com>
+Acked-by: Thomas Petazzoni <thomas.petazzoni@free-electrons.com>
+Signed-off-by: David S. Miller <davem@davemloft.net>
+---
+
+--- a/drivers/net/ethernet/marvell/mvneta.c
++++ b/drivers/net/ethernet/marvell/mvneta.c
+@@ -11,28 +11,28 @@
+ * warranty of any kind, whether express or implied.
+ */
+
+-#include <linux/kernel.h>
+-#include <linux/netdevice.h>
++#include <linux/clk.h>
++#include <linux/cpu.h>
+ #include <linux/etherdevice.h>
+-#include <linux/platform_device.h>
+-#include <linux/skbuff.h>
++#include <linux/if_vlan.h>
+ #include <linux/inetdevice.h>
+-#include <linux/mbus.h>
+-#include <linux/module.h>
+ #include <linux/interrupt.h>
+-#include <linux/if_vlan.h>
+-#include <net/ip.h>
+-#include <net/ipv6.h>
+ #include <linux/io.h>
+-#include <net/tso.h>
++#include <linux/kernel.h>
++#include <linux/mbus.h>
++#include <linux/module.h>
++#include <linux/netdevice.h>
+ #include <linux/of.h>
++#include <linux/of_address.h>
+ #include <linux/of_irq.h>
+ #include <linux/of_mdio.h>
+ #include <linux/of_net.h>
+-#include <linux/of_address.h>
+ #include <linux/phy.h>
+-#include <linux/clk.h>
+-#include <linux/cpu.h>
++#include <linux/platform_device.h>
++#include <linux/skbuff.h>
++#include <net/ip.h>
++#include <net/ipv6.h>
++#include <net/tso.h>
+
+ /* Registers */
+ #define MVNETA_RXQ_CONFIG_REG(q) (0x1400 + ((q) << 2))
diff --git a/target/linux/mvebu/patches-4.4/044-net-add-a-hardware-buffer-management-helper-API.patch b/target/linux/mvebu/patches-4.4/044-net-add-a-hardware-buffer-management-helper-API.patch
new file mode 100644
index 0000000000..d4bc6a0088
--- /dev/null
+++ b/target/linux/mvebu/patches-4.4/044-net-add-a-hardware-buffer-management-helper-API.patch
@@ -0,0 +1,159 @@
+From: Gregory CLEMENT <gregory.clement@free-electrons.com>
+Date: Mon, 14 Mar 2016 09:39:04 +0100
+Subject: [PATCH] net: add a hardware buffer management helper API
+
+This basic implementation allows to share code between driver using
+hardware buffer management. As the code is hardware agnostic, there is
+few helpers, most of the optimization brought by the an HW BM has to be
+done at driver level.
+
+Tested-by: Sebastian Careba <nitroshift@yahoo.com>
+Signed-off-by: Gregory CLEMENT <gregory.clement@free-electrons.com>
+Signed-off-by: David S. Miller <davem@davemloft.net>
+---
+ create mode 100644 include/net/hwbm.h
+ create mode 100644 net/core/hwbm.c
+
+--- /dev/null
++++ b/include/net/hwbm.h
+@@ -0,0 +1,28 @@
++#ifndef _HWBM_H
++#define _HWBM_H
++
++struct hwbm_pool {
++ /* Capacity of the pool */
++ int size;
++ /* Size of the buffers managed */
++ int frag_size;
++ /* Number of buffers currently used by this pool */
++ int buf_num;
++ /* constructor called during alocation */
++ int (*construct)(struct hwbm_pool *bm_pool, void *buf);
++ /* protect acces to the buffer counter*/
++ spinlock_t lock;
++ /* private data */
++ void *priv;
++};
++#ifdef CONFIG_HWBM
++void hwbm_buf_free(struct hwbm_pool *bm_pool, void *buf);
++int hwbm_pool_refill(struct hwbm_pool *bm_pool, gfp_t gfp);
++int hwbm_pool_add(struct hwbm_pool *bm_pool, unsigned int buf_num, gfp_t gfp);
++#else
++void hwbm_buf_free(struct hwbm_pool *bm_pool, void *buf) {}
++int hwbm_pool_refill(struct hwbm_pool *bm_pool, gfp_t gfp) { return 0; }
++int hwbm_pool_add(struct hwbm_pool *bm_pool, unsigned int buf_num, gfp_t gfp)
++{ return 0; }
++#endif /* CONFIG_HWBM */
++#endif /* _HWBM_H */
+--- a/net/Kconfig
++++ b/net/Kconfig
+@@ -259,6 +259,9 @@ config XPS
+ depends on SMP
+ default y
+
++config HWBM
++ bool
++
+ config CGROUP_NET_PRIO
+ bool "Network priority cgroup"
+ depends on CGROUPS
+--- a/net/core/Makefile
++++ b/net/core/Makefile
+@@ -14,6 +14,7 @@ obj-y += dev.o ethtool.o dev_addr_
+ obj-$(CONFIG_SOCK_DIAG) += sock_diag.o
+ obj-$(CONFIG_XFRM) += flow.o
+ obj-y += net-sysfs.o
++obj-$(CONFIG_HWBM) += hwbm.o
+ obj-$(CONFIG_PROC_FS) += net-procfs.o
+ obj-$(CONFIG_NET_PKTGEN) += pktgen.o
+ obj-$(CONFIG_NETPOLL) += netpoll.o
+--- /dev/null
++++ b/net/core/hwbm.c
+@@ -0,0 +1,87 @@
++/* Support for hardware buffer manager.
++ *
++ * Copyright (C) 2016 Marvell
++ *
++ * Gregory CLEMENT <gregory.clement@free-electrons.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.
++ */
++#include <linux/kernel.h>
++#include <linux/printk.h>
++#include <linux/skbuff.h>
++#include <net/hwbm.h>
++
++void hwbm_buf_free(struct hwbm_pool *bm_pool, void *buf)
++{
++ if (likely(bm_pool->frag_size <= PAGE_SIZE))
++ skb_free_frag(buf);
++ else
++ kfree(buf);
++}
++EXPORT_SYMBOL_GPL(hwbm_buf_free);
++
++/* Refill processing for HW buffer management */
++int hwbm_pool_refill(struct hwbm_pool *bm_pool, gfp_t gfp)
++{
++ int frag_size = bm_pool->frag_size;
++ void *buf;
++
++ if (likely(frag_size <= PAGE_SIZE))
++ buf = netdev_alloc_frag(frag_size);
++ else
++ buf = kmalloc(frag_size, gfp);
++
++ if (!buf)
++ return -ENOMEM;
++
++ if (bm_pool->construct)
++ if (bm_pool->construct(bm_pool, buf)) {
++ hwbm_buf_free(bm_pool, buf);
++ return -ENOMEM;
++ }
++
++ return 0;
++}
++EXPORT_SYMBOL_GPL(hwbm_pool_refill);
++
++int hwbm_pool_add(struct hwbm_pool *bm_pool, unsigned int buf_num, gfp_t gfp)
++{
++ int err, i;
++ unsigned long flags;
++
++ spin_lock_irqsave(&bm_pool->lock, flags);
++ if (bm_pool->buf_num == bm_pool->size) {
++ pr_warn("pool already filled\n");
++ return bm_pool->buf_num;
++ }
++
++ if (buf_num + bm_pool->buf_num > bm_pool->size) {
++ pr_warn("cannot allocate %d buffers for pool\n",
++ buf_num);
++ return 0;
++ }
++
++ if ((buf_num + bm_pool->buf_num) < bm_pool->buf_num) {
++ pr_warn("Adding %d buffers to the %d current buffers will overflow\n",
++ buf_num, bm_pool->buf_num);
++ return 0;
++ }
++
++ for (i = 0; i < buf_num; i++) {
++ err = hwbm_pool_refill(bm_pool, gfp);
++ if (err < 0)
++ break;
++ }
++
++ /* Update BM driver with number of buffers added to pool */
++ bm_pool->buf_num += i;
++
++ pr_debug("hwpm pool: %d of %d buffers added\n", i, buf_num);
++ spin_unlock_irqrestore(&bm_pool->lock, flags);
++
++ return i;
++}
++EXPORT_SYMBOL_GPL(hwbm_pool_add);
diff --git a/target/linux/mvebu/patches-4.4/045-net-mvneta-bm-add-support-for-hardware-buffer-manage.patch b/target/linux/mvebu/patches-4.4/045-net-mvneta-bm-add-support-for-hardware-buffer-manage.patch
new file mode 100644
index 0000000000..d343b3983f
--- /dev/null
+++ b/target/linux/mvebu/patches-4.4/045-net-mvneta-bm-add-support-for-hardware-buffer-manage.patch
@@ -0,0 +1,1684 @@
+From: Marcin Wojtas <mw@semihalf.com>
+Date: Mon, 14 Mar 2016 09:39:03 +0100
+Subject: [PATCH] net: mvneta: bm: add support for hardware buffer management
+
+Buffer manager (BM) is a dedicated hardware unit that can be used by all
+ethernet ports of Armada XP and 38x SoC's. It allows to offload CPU on RX
+path by sparing DRAM access on refilling buffer pool, hardware-based
+filling of descriptor ring data and better memory utilization due to HW
+arbitration for using 'short' pools for small packets.
+
+Tests performed with A388 SoC working as a network bridge between two
+packet generators showed increase of maximum processed 64B packets by
+~20k (~555k packets with BM enabled vs ~535 packets without BM). Also
+when pushing 1500B-packets with a line rate achieved, CPU load decreased
+from around 25% without BM to 20% with BM.
+
+BM comprise up to 4 buffer pointers' (BP) rings kept in DRAM, which
+are called external BP pools - BPPE. Allocating and releasing buffer
+pointers (BP) to/from BPPE is performed indirectly by write/read access
+to a dedicated internal SRAM, where internal BP pools (BPPI) are placed.
+BM hardware controls status of BPPE automatically, as well as assigning
+proper buffers to RX descriptors. For more details please refer to
+Functional Specification of Armada XP or 38x SoC.
+
+In order to enable support for a separate hardware block, common for all
+ports, a new driver has to be implemented ('mvneta_bm'). It provides
+initialization sequence of address space, clocks, registers, SRAM,
+empty pools' structures and also obtaining optional configuration
+from DT (please refer to device tree binding documentation). mvneta_bm
+exposes also a necessary API to mvneta driver, as well as a dedicated
+structure with BM information (bm_priv), whose presence is used as a
+flag notifying of BM usage by port. It has to be ensured that mvneta_bm
+probe is executed prior to the ones in ports' driver. In case BM is not
+used or its probe fails, mvneta falls back to use software buffer
+management.
+
+A sequence executed in mvneta_probe function is modified in order to have
+an access to needed resources before possible port's BM initialization is
+done. According to port-pools mapping provided by DT appropriate registers
+are configured and the buffer pools are filled. RX path is modified
+accordingly. Becaues the hardware allows a wide variety of configuration
+options, following assumptions are made:
+* using BM mechanisms can be selectively disabled/enabled basing
+ on DT configuration among the ports
+* 'long' pool's single buffer size is tied to port's MTU
+* using 'long' pool by port is obligatory and it cannot be shared
+* using 'short' pool for smaller packets is optional
+* one 'short' pool can be shared among all ports
+
+This commit enables hardware buffer management operation cooperating with
+existing mvneta driver. New device tree binding documentation is added and
+the one of mvneta is updated accordingly.
+
+[gregory.clement@free-electrons.com: removed the suspend/resume part]
+
+Signed-off-by: Marcin Wojtas <mw@semihalf.com>
+Signed-off-by: Gregory CLEMENT <gregory.clement@free-electrons.com>
+Signed-off-by: David S. Miller <davem@davemloft.net>
+---
+ create mode 100644 Documentation/devicetree/bindings/net/marvell-neta-bm.txt
+ create mode 100644 drivers/net/ethernet/marvell/mvneta_bm.c
+ create mode 100644 drivers/net/ethernet/marvell/mvneta_bm.h
+
+--- a/Documentation/devicetree/bindings/net/marvell-armada-370-neta.txt
++++ b/Documentation/devicetree/bindings/net/marvell-armada-370-neta.txt
+@@ -13,15 +13,30 @@ Optional properties:
+ Value is presented in bytes. If not used, by default 1600B is set for
+ "marvell,armada-370-neta" and 9800B for others.
+
++Optional properties (valid only for Armada XP/38x):
++
++- buffer-manager: a phandle to a buffer manager node. Please refer to
++ Documentation/devicetree/bindings/net/marvell-neta-bm.txt
++- bm,pool-long: ID of a pool, that will accept all packets of a size
++ higher than 'short' pool's threshold (if set) and up to MTU value.
++ Obligatory, when the port is supposed to use hardware
++ buffer management.
++- bm,pool-short: ID of a pool, that will be used for accepting
++ packets of a size lower than given threshold. If not set, the port
++ will use a single 'long' pool for all packets, as defined above.
++
+ Example:
+
+-ethernet@d0070000 {
++ethernet@70000 {
+ compatible = "marvell,armada-370-neta";
+- reg = <0xd0070000 0x2500>;
++ reg = <0x70000 0x2500>;
+ interrupts = <8>;
+ clocks = <&gate_clk 4>;
+ tx-csum-limit = <9800>
+ status = "okay";
+ phy = <&phy0>;
+ phy-mode = "rgmii-id";
++ buffer-manager = <&bm>;
++ bm,pool-long = <0>;
++ bm,pool-short = <1>;
+ };
+--- /dev/null
++++ b/Documentation/devicetree/bindings/net/marvell-neta-bm.txt
+@@ -0,0 +1,49 @@
++* Marvell Armada 380/XP Buffer Manager driver (BM)
++
++Required properties:
++
++- compatible: should be "marvell,armada-380-neta-bm".
++- reg: address and length of the register set for the device.
++- clocks: a pointer to the reference clock for this device.
++- internal-mem: a phandle to BM internal SRAM definition.
++
++Optional properties (port):
++
++- pool<0 : 3>,capacity: size of external buffer pointers' ring maintained
++ in DRAM. Can be set for each pool (id 0 : 3) separately. The value has
++ to be chosen between 128 and 16352 and it also has to be aligned to 32.
++ Otherwise the driver would adjust a given number or choose default if
++ not set.
++- pool<0 : 3>,pkt-size: maximum size of a packet accepted by a given buffer
++ pointers' pool (id 0 : 3). It will be taken into consideration only when pool
++ type is 'short'. For 'long' ones it would be overridden by port's MTU.
++ If not set a driver will choose a default value.
++
++In order to see how to hook the BM to a given ethernet port, please
++refer to Documentation/devicetree/bindings/net/marvell-armada-370-neta.txt.
++
++Example:
++
++- main node:
++
++bm: bm@c8000 {
++ compatible = "marvell,armada-380-neta-bm";
++ reg = <0xc8000 0xac>;
++ clocks = <&gateclk 13>;
++ internal-mem = <&bm_bppi>;
++ status = "okay";
++ pool2,capacity = <4096>;
++ pool1,pkt-size = <512>;
++};
++
++- internal SRAM node:
++
++bm_bppi: bm-bppi {
++ compatible = "mmio-sram";
++ reg = <MBUS_ID(0x0c, 0x04) 0 0x100000>;
++ ranges = <0 MBUS_ID(0x0c, 0x04) 0 0x100000>;
++ #address-cells = <1>;
++ #size-cells = <1>;
++ clocks = <&gateclk 13>;
++ status = "okay";
++};
+--- a/drivers/net/ethernet/marvell/Kconfig
++++ b/drivers/net/ethernet/marvell/Kconfig
+@@ -40,6 +40,19 @@ config MVMDIO
+
+ This driver is used by the MV643XX_ETH and MVNETA drivers.
+
++config MVNETA_BM
++ tristate "Marvell Armada 38x/XP network interface BM support"
++ depends on MVNETA
++ ---help---
++ This driver supports auxiliary block of the network
++ interface units in the Marvell ARMADA XP and ARMADA 38x SoC
++ family, which is called buffer manager.
++
++ This driver, when enabled, strictly cooperates with mvneta
++ driver and is common for all network ports of the devices,
++ even for Armada 370 SoC, which doesn't support hardware
++ buffer management.
++
+ config MVNETA
+ tristate "Marvell Armada 370/38x/XP network interface support"
+ depends on PLAT_ORION
+--- a/drivers/net/ethernet/marvell/Makefile
++++ b/drivers/net/ethernet/marvell/Makefile
+@@ -4,6 +4,7 @@
+
+ obj-$(CONFIG_MVMDIO) += mvmdio.o
+ obj-$(CONFIG_MV643XX_ETH) += mv643xx_eth.o
++obj-$(CONFIG_MVNETA_BM) += mvneta_bm.o
+ obj-$(CONFIG_MVNETA) += mvneta.o
+ obj-$(CONFIG_MVPP2) += mvpp2.o
+ obj-$(CONFIG_PXA168_ETH) += pxa168_eth.o
+--- a/drivers/net/ethernet/marvell/mvneta.c
++++ b/drivers/net/ethernet/marvell/mvneta.c
+@@ -30,6 +30,7 @@
+ #include <linux/phy.h>
+ #include <linux/platform_device.h>
+ #include <linux/skbuff.h>
++#include "mvneta_bm.h"
+ #include <net/ip.h>
+ #include <net/ipv6.h>
+ #include <net/tso.h>
+@@ -37,6 +38,10 @@
+ /* Registers */
+ #define MVNETA_RXQ_CONFIG_REG(q) (0x1400 + ((q) << 2))
+ #define MVNETA_RXQ_HW_BUF_ALLOC BIT(0)
++#define MVNETA_RXQ_SHORT_POOL_ID_SHIFT 4
++#define MVNETA_RXQ_SHORT_POOL_ID_MASK 0x30
++#define MVNETA_RXQ_LONG_POOL_ID_SHIFT 6
++#define MVNETA_RXQ_LONG_POOL_ID_MASK 0xc0
+ #define MVNETA_RXQ_PKT_OFFSET_ALL_MASK (0xf << 8)
+ #define MVNETA_RXQ_PKT_OFFSET_MASK(offs) ((offs) << 8)
+ #define MVNETA_RXQ_THRESHOLD_REG(q) (0x14c0 + ((q) << 2))
+@@ -50,6 +55,9 @@
+ #define MVNETA_RXQ_STATUS_UPDATE_REG(q) (0x1500 + ((q) << 2))
+ #define MVNETA_RXQ_ADD_NON_OCCUPIED_SHIFT 16
+ #define MVNETA_RXQ_ADD_NON_OCCUPIED_MAX 255
++#define MVNETA_PORT_POOL_BUFFER_SZ_REG(pool) (0x1700 + ((pool) << 2))
++#define MVNETA_PORT_POOL_BUFFER_SZ_SHIFT 3
++#define MVNETA_PORT_POOL_BUFFER_SZ_MASK 0xfff8
+ #define MVNETA_PORT_RX_RESET 0x1cc0
+ #define MVNETA_PORT_RX_DMA_RESET BIT(0)
+ #define MVNETA_PHY_ADDR 0x2000
+@@ -107,6 +115,7 @@
+ #define MVNETA_GMAC_CLOCK_DIVIDER 0x24f4
+ #define MVNETA_GMAC_1MS_CLOCK_ENABLE BIT(31)
+ #define MVNETA_ACC_MODE 0x2500
++#define MVNETA_BM_ADDRESS 0x2504
+ #define MVNETA_CPU_MAP(cpu) (0x2540 + ((cpu) << 2))
+ #define MVNETA_CPU_RXQ_ACCESS_ALL_MASK 0x000000ff
+ #define MVNETA_CPU_TXQ_ACCESS_ALL_MASK 0x0000ff00
+@@ -253,7 +262,10 @@
+ #define MVNETA_CPU_D_CACHE_LINE_SIZE 32
+ #define MVNETA_TX_CSUM_DEF_SIZE 1600
+ #define MVNETA_TX_CSUM_MAX_SIZE 9800
+-#define MVNETA_ACC_MODE_EXT 1
++#define MVNETA_ACC_MODE_EXT1 1
++#define MVNETA_ACC_MODE_EXT2 2
++
++#define MVNETA_MAX_DECODE_WIN 6
+
+ /* Timeout constants */
+ #define MVNETA_TX_DISABLE_TIMEOUT_MSEC 1000
+@@ -293,7 +305,8 @@
+ ((addr >= txq->tso_hdrs_phys) && \
+ (addr < txq->tso_hdrs_phys + txq->size * TSO_HEADER_SIZE))
+
+-#define MVNETA_RX_BUF_SIZE(pkt_size) ((pkt_size) + NET_SKB_PAD)
++#define MVNETA_RX_GET_BM_POOL_ID(rxd) \
++ (((rxd)->status & MVNETA_RXD_BM_POOL_MASK) >> MVNETA_RXD_BM_POOL_SHIFT)
+
+ struct mvneta_statistic {
+ unsigned short offset;
+@@ -359,6 +372,7 @@ struct mvneta_pcpu_port {
+ };
+
+ struct mvneta_port {
++ u8 id;
+ struct mvneta_pcpu_port __percpu *ports;
+ struct mvneta_pcpu_stats __percpu *stats;
+
+@@ -392,6 +406,11 @@ struct mvneta_port {
+ unsigned int tx_csum_limit;
+ unsigned int use_inband_status:1;
+
++ struct mvneta_bm *bm_priv;
++ struct mvneta_bm_pool *pool_long;
++ struct mvneta_bm_pool *pool_short;
++ int bm_win_id;
++
+ u64 ethtool_stats[ARRAY_SIZE(mvneta_statistics)];
+
+ u32 indir[MVNETA_RSS_LU_TABLE_SIZE];
+@@ -417,6 +436,8 @@ struct mvneta_port {
+ #define MVNETA_TX_L4_CSUM_NOT BIT(31)
+
+ #define MVNETA_RXD_ERR_CRC 0x0
++#define MVNETA_RXD_BM_POOL_SHIFT 13
++#define MVNETA_RXD_BM_POOL_MASK (BIT(13) | BIT(14))
+ #define MVNETA_RXD_ERR_SUMMARY BIT(16)
+ #define MVNETA_RXD_ERR_OVERRUN BIT(17)
+ #define MVNETA_RXD_ERR_LEN BIT(18)
+@@ -561,6 +582,9 @@ static int rxq_def;
+
+ static int rx_copybreak __read_mostly = 256;
+
++/* HW BM need that each port be identify by a unique ID */
++static int global_port_id;
++
+ #define MVNETA_DRIVER_NAME "mvneta"
+ #define MVNETA_DRIVER_VERSION "1.0"
+
+@@ -827,6 +851,214 @@ static void mvneta_rxq_bm_disable(struct
+ mvreg_write(pp, MVNETA_RXQ_CONFIG_REG(rxq->id), val);
+ }
+
++/* Enable buffer management (BM) */
++static void mvneta_rxq_bm_enable(struct mvneta_port *pp,
++ struct mvneta_rx_queue *rxq)
++{
++ u32 val;
++
++ val = mvreg_read(pp, MVNETA_RXQ_CONFIG_REG(rxq->id));
++ val |= MVNETA_RXQ_HW_BUF_ALLOC;
++ mvreg_write(pp, MVNETA_RXQ_CONFIG_REG(rxq->id), val);
++}
++
++/* Notify HW about port's assignment of pool for bigger packets */
++static void mvneta_rxq_long_pool_set(struct mvneta_port *pp,
++ struct mvneta_rx_queue *rxq)
++{
++ u32 val;
++
++ val = mvreg_read(pp, MVNETA_RXQ_CONFIG_REG(rxq->id));
++ val &= ~MVNETA_RXQ_LONG_POOL_ID_MASK;
++ val |= (pp->pool_long->id << MVNETA_RXQ_LONG_POOL_ID_SHIFT);
++
++ mvreg_write(pp, MVNETA_RXQ_CONFIG_REG(rxq->id), val);
++}
++
++/* Notify HW about port's assignment of pool for smaller packets */
++static void mvneta_rxq_short_pool_set(struct mvneta_port *pp,
++ struct mvneta_rx_queue *rxq)
++{
++ u32 val;
++
++ val = mvreg_read(pp, MVNETA_RXQ_CONFIG_REG(rxq->id));
++ val &= ~MVNETA_RXQ_SHORT_POOL_ID_MASK;
++ val |= (pp->pool_short->id << MVNETA_RXQ_SHORT_POOL_ID_SHIFT);
++
++ mvreg_write(pp, MVNETA_RXQ_CONFIG_REG(rxq->id), val);
++}
++
++/* Set port's receive buffer size for assigned BM pool */
++static inline void mvneta_bm_pool_bufsize_set(struct mvneta_port *pp,
++ int buf_size,
++ u8 pool_id)
++{
++ u32 val;
++
++ if (!IS_ALIGNED(buf_size, 8)) {
++ dev_warn(pp->dev->dev.parent,
++ "illegal buf_size value %d, round to %d\n",
++ buf_size, ALIGN(buf_size, 8));
++ buf_size = ALIGN(buf_size, 8);
++ }
++
++ val = mvreg_read(pp, MVNETA_PORT_POOL_BUFFER_SZ_REG(pool_id));
++ val |= buf_size & MVNETA_PORT_POOL_BUFFER_SZ_MASK;
++ mvreg_write(pp, MVNETA_PORT_POOL_BUFFER_SZ_REG(pool_id), val);
++}
++
++/* Configure MBUS window in order to enable access BM internal SRAM */
++static int mvneta_mbus_io_win_set(struct mvneta_port *pp, u32 base, u32 wsize,
++ u8 target, u8 attr)
++{
++ u32 win_enable, win_protect;
++ int i;
++
++ win_enable = mvreg_read(pp, MVNETA_BASE_ADDR_ENABLE);
++
++ if (pp->bm_win_id < 0) {
++ /* Find first not occupied window */
++ for (i = 0; i < MVNETA_MAX_DECODE_WIN; i++) {
++ if (win_enable & (1 << i)) {
++ pp->bm_win_id = i;
++ break;
++ }
++ }
++ if (i == MVNETA_MAX_DECODE_WIN)
++ return -ENOMEM;
++ } else {
++ i = pp->bm_win_id;
++ }
++
++ mvreg_write(pp, MVNETA_WIN_BASE(i), 0);
++ mvreg_write(pp, MVNETA_WIN_SIZE(i), 0);
++
++ if (i < 4)
++ mvreg_write(pp, MVNETA_WIN_REMAP(i), 0);
++
++ mvreg_write(pp, MVNETA_WIN_BASE(i), (base & 0xffff0000) |
++ (attr << 8) | target);
++
++ mvreg_write(pp, MVNETA_WIN_SIZE(i), (wsize - 1) & 0xffff0000);
++
++ win_protect = mvreg_read(pp, MVNETA_ACCESS_PROTECT_ENABLE);
++ win_protect |= 3 << (2 * i);
++ mvreg_write(pp, MVNETA_ACCESS_PROTECT_ENABLE, win_protect);
++
++ win_enable &= ~(1 << i);
++ mvreg_write(pp, MVNETA_BASE_ADDR_ENABLE, win_enable);
++
++ return 0;
++}
++
++/* Assign and initialize pools for port. In case of fail
++ * buffer manager will remain disabled for current port.
++ */
++static int mvneta_bm_port_init(struct platform_device *pdev,
++ struct mvneta_port *pp)
++{
++ struct device_node *dn = pdev->dev.of_node;
++ u32 long_pool_id, short_pool_id, wsize;
++ u8 target, attr;
++ int err;
++
++ /* Get BM window information */
++ err = mvebu_mbus_get_io_win_info(pp->bm_priv->bppi_phys_addr, &wsize,
++ &target, &attr);
++ if (err < 0)
++ return err;
++
++ pp->bm_win_id = -1;
++
++ /* Open NETA -> BM window */
++ err = mvneta_mbus_io_win_set(pp, pp->bm_priv->bppi_phys_addr, wsize,
++ target, attr);
++ if (err < 0) {
++ netdev_info(pp->dev, "fail to configure mbus window to BM\n");
++ return err;
++ }
++
++ if (of_property_read_u32(dn, "bm,pool-long", &long_pool_id)) {
++ netdev_info(pp->dev, "missing long pool id\n");
++ return -EINVAL;
++ }
++
++ /* Create port's long pool depending on mtu */
++ pp->pool_long = mvneta_bm_pool_use(pp->bm_priv, long_pool_id,
++ MVNETA_BM_LONG, pp->id,
++ MVNETA_RX_PKT_SIZE(pp->dev->mtu));
++ if (!pp->pool_long) {
++ netdev_info(pp->dev, "fail to obtain long pool for port\n");
++ return -ENOMEM;
++ }
++
++ pp->pool_long->port_map |= 1 << pp->id;
++
++ mvneta_bm_pool_bufsize_set(pp, pp->pool_long->buf_size,
++ pp->pool_long->id);
++
++ /* If short pool id is not defined, assume using single pool */
++ if (of_property_read_u32(dn, "bm,pool-short", &short_pool_id))
++ short_pool_id = long_pool_id;
++
++ /* Create port's short pool */
++ pp->pool_short = mvneta_bm_pool_use(pp->bm_priv, short_pool_id,
++ MVNETA_BM_SHORT, pp->id,
++ MVNETA_BM_SHORT_PKT_SIZE);
++ if (!pp->pool_short) {
++ netdev_info(pp->dev, "fail to obtain short pool for port\n");
++ mvneta_bm_pool_destroy(pp->bm_priv, pp->pool_long, 1 << pp->id);
++ return -ENOMEM;
++ }
++
++ if (short_pool_id != long_pool_id) {
++ pp->pool_short->port_map |= 1 << pp->id;
++ mvneta_bm_pool_bufsize_set(pp, pp->pool_short->buf_size,
++ pp->pool_short->id);
++ }
++
++ return 0;
++}
++
++/* Update settings of a pool for bigger packets */
++static void mvneta_bm_update_mtu(struct mvneta_port *pp, int mtu)
++{
++ struct mvneta_bm_pool *bm_pool = pp->pool_long;
++ int num;
++
++ /* Release all buffers from long pool */
++ mvneta_bm_bufs_free(pp->bm_priv, bm_pool, 1 << pp->id);
++ if (bm_pool->buf_num) {
++ WARN(1, "cannot free all buffers in pool %d\n",
++ bm_pool->id);
++ goto bm_mtu_err;
++ }
++
++ bm_pool->pkt_size = MVNETA_RX_PKT_SIZE(mtu);
++ bm_pool->buf_size = MVNETA_RX_BUF_SIZE(bm_pool->pkt_size);
++ bm_pool->frag_size = SKB_DATA_ALIGN(sizeof(struct skb_shared_info)) +
++ SKB_DATA_ALIGN(MVNETA_RX_BUF_SIZE(bm_pool->pkt_size));
++
++ /* Fill entire long pool */
++ num = mvneta_bm_bufs_add(pp->bm_priv, bm_pool, bm_pool->size);
++ if (num != bm_pool->size) {
++ WARN(1, "pool %d: %d of %d allocated\n",
++ bm_pool->id, num, bm_pool->size);
++ goto bm_mtu_err;
++ }
++ mvneta_bm_pool_bufsize_set(pp, bm_pool->buf_size, bm_pool->id);
++
++ return;
++
++bm_mtu_err:
++ mvneta_bm_pool_destroy(pp->bm_priv, pp->pool_long, 1 << pp->id);
++ mvneta_bm_pool_destroy(pp->bm_priv, pp->pool_short, 1 << pp->id);
++
++ pp->bm_priv = NULL;
++ mvreg_write(pp, MVNETA_ACC_MODE, MVNETA_ACC_MODE_EXT1);
++ netdev_info(pp->dev, "fail to update MTU, fall back to software BM\n");
++}
++
+ /* Start the Ethernet port RX and TX activity */
+ static void mvneta_port_up(struct mvneta_port *pp)
+ {
+@@ -1147,9 +1379,17 @@ static void mvneta_defaults_set(struct m
+ mvreg_write(pp, MVNETA_PORT_RX_RESET, 0);
+
+ /* Set Port Acceleration Mode */
+- val = MVNETA_ACC_MODE_EXT;
++ if (pp->bm_priv)
++ /* HW buffer management + legacy parser */
++ val = MVNETA_ACC_MODE_EXT2;
++ else
++ /* SW buffer management + legacy parser */
++ val = MVNETA_ACC_MODE_EXT1;
+ mvreg_write(pp, MVNETA_ACC_MODE, val);
+
++ if (pp->bm_priv)
++ mvreg_write(pp, MVNETA_BM_ADDRESS, pp->bm_priv->bppi_phys_addr);
++
+ /* Update val of portCfg register accordingly with all RxQueue types */
+ val = MVNETA_PORT_CONFIG_DEFL_VALUE(pp->rxq_def);
+ mvreg_write(pp, MVNETA_PORT_CONFIG, val);
+@@ -1516,23 +1756,25 @@ static void mvneta_txq_done(struct mvnet
+ }
+ }
+
+-static void *mvneta_frag_alloc(const struct mvneta_port *pp)
++void *mvneta_frag_alloc(unsigned int frag_size)
+ {
+- if (likely(pp->frag_size <= PAGE_SIZE))
+- return netdev_alloc_frag(pp->frag_size);
++ if (likely(frag_size <= PAGE_SIZE))
++ return netdev_alloc_frag(frag_size);
+ else
+- return kmalloc(pp->frag_size, GFP_ATOMIC);
++ return kmalloc(frag_size, GFP_ATOMIC);
+ }
++EXPORT_SYMBOL_GPL(mvneta_frag_alloc);
+
+-static void mvneta_frag_free(const struct mvneta_port *pp, void *data)
++void mvneta_frag_free(unsigned int frag_size, void *data)
+ {
+- if (likely(pp->frag_size <= PAGE_SIZE))
++ if (likely(frag_size <= PAGE_SIZE))
+ skb_free_frag(data);
+ else
+ kfree(data);
+ }
++EXPORT_SYMBOL_GPL(mvneta_frag_free);
+
+-/* Refill processing */
++/* Refill processing for SW buffer management */
+ static int mvneta_rx_refill(struct mvneta_port *pp,
+ struct mvneta_rx_desc *rx_desc)
+
+@@ -1540,7 +1782,7 @@ static int mvneta_rx_refill(struct mvnet
+ dma_addr_t phys_addr;
+ void *data;
+
+- data = mvneta_frag_alloc(pp);
++ data = mvneta_frag_alloc(pp->frag_size);
+ if (!data)
+ return -ENOMEM;
+
+@@ -1548,7 +1790,7 @@ static int mvneta_rx_refill(struct mvnet
+ MVNETA_RX_BUF_SIZE(pp->pkt_size),
+ DMA_FROM_DEVICE);
+ if (unlikely(dma_mapping_error(pp->dev->dev.parent, phys_addr))) {
+- mvneta_frag_free(pp, data);
++ mvneta_frag_free(pp->frag_size, data);
+ return -ENOMEM;
+ }
+
+@@ -1594,22 +1836,156 @@ static void mvneta_rxq_drop_pkts(struct
+ int rx_done, i;
+
+ rx_done = mvneta_rxq_busy_desc_num_get(pp, rxq);
++ if (rx_done)
++ mvneta_rxq_desc_num_update(pp, rxq, rx_done, rx_done);
++
++ if (pp->bm_priv) {
++ for (i = 0; i < rx_done; i++) {
++ struct mvneta_rx_desc *rx_desc =
++ mvneta_rxq_next_desc_get(rxq);
++ u8 pool_id = MVNETA_RX_GET_BM_POOL_ID(rx_desc);
++ struct mvneta_bm_pool *bm_pool;
++
++ bm_pool = &pp->bm_priv->bm_pools[pool_id];
++ /* Return dropped buffer to the pool */
++ mvneta_bm_pool_put_bp(pp->bm_priv, bm_pool,
++ rx_desc->buf_phys_addr);
++ }
++ return;
++ }
++
+ for (i = 0; i < rxq->size; i++) {
+ struct mvneta_rx_desc *rx_desc = rxq->descs + i;
+ void *data = (void *)rx_desc->buf_cookie;
+
+ dma_unmap_single(pp->dev->dev.parent, rx_desc->buf_phys_addr,
+ MVNETA_RX_BUF_SIZE(pp->pkt_size), DMA_FROM_DEVICE);
+- mvneta_frag_free(pp, data);
++ mvneta_frag_free(pp->frag_size, data);
+ }
++}
+
+- if (rx_done)
+- mvneta_rxq_desc_num_update(pp, rxq, rx_done, rx_done);
++/* Main rx processing when using software buffer management */
++static int mvneta_rx_swbm(struct mvneta_port *pp, int rx_todo,
++ struct mvneta_rx_queue *rxq)
++{
++ struct mvneta_pcpu_port *port = this_cpu_ptr(pp->ports);
++ struct net_device *dev = pp->dev;
++ int rx_done;
++ u32 rcvd_pkts = 0;
++ u32 rcvd_bytes = 0;
++
++ /* Get number of received packets */
++ rx_done = mvneta_rxq_busy_desc_num_get(pp, rxq);
++
++ if (rx_todo > rx_done)
++ rx_todo = rx_done;
++
++ rx_done = 0;
++
++ /* Fairness NAPI loop */
++ while (rx_done < rx_todo) {
++ struct mvneta_rx_desc *rx_desc = mvneta_rxq_next_desc_get(rxq);
++ struct sk_buff *skb;
++ unsigned char *data;
++ dma_addr_t phys_addr;
++ u32 rx_status, frag_size;
++ int rx_bytes, err;
++
++ rx_done++;
++ rx_status = rx_desc->status;
++ rx_bytes = rx_desc->data_size - (ETH_FCS_LEN + MVNETA_MH_SIZE);
++ data = (unsigned char *)rx_desc->buf_cookie;
++ phys_addr = rx_desc->buf_phys_addr;
++
++ if (!mvneta_rxq_desc_is_first_last(rx_status) ||
++ (rx_status & MVNETA_RXD_ERR_SUMMARY)) {
++err_drop_frame:
++ dev->stats.rx_errors++;
++ mvneta_rx_error(pp, rx_desc);
++ /* leave the descriptor untouched */
++ continue;
++ }
++
++ if (rx_bytes <= rx_copybreak) {
++ /* better copy a small frame and not unmap the DMA region */
++ skb = netdev_alloc_skb_ip_align(dev, rx_bytes);
++ if (unlikely(!skb))
++ goto err_drop_frame;
++
++ dma_sync_single_range_for_cpu(dev->dev.parent,
++ rx_desc->buf_phys_addr,
++ MVNETA_MH_SIZE + NET_SKB_PAD,
++ rx_bytes,
++ DMA_FROM_DEVICE);
++ memcpy(skb_put(skb, rx_bytes),
++ data + MVNETA_MH_SIZE + NET_SKB_PAD,
++ rx_bytes);
++
++ skb->protocol = eth_type_trans(skb, dev);
++ mvneta_rx_csum(pp, rx_status, skb);
++ napi_gro_receive(&port->napi, skb);
++
++ rcvd_pkts++;
++ rcvd_bytes += rx_bytes;
++
++ /* leave the descriptor and buffer untouched */
++ continue;
++ }
++
++ /* Refill processing */
++ err = mvneta_rx_refill(pp, rx_desc);
++ if (err) {
++ netdev_err(dev, "Linux processing - Can't refill\n");
++ rxq->missed++;
++ goto err_drop_frame;
++ }
++
++ frag_size = pp->frag_size;
++
++ skb = build_skb(data, frag_size > PAGE_SIZE ? 0 : frag_size);
++
++ /* After refill old buffer has to be unmapped regardless
++ * the skb is successfully built or not.
++ */
++ dma_unmap_single(dev->dev.parent, phys_addr,
++ MVNETA_RX_BUF_SIZE(pp->pkt_size),
++ DMA_FROM_DEVICE);
++
++ if (!skb)
++ goto err_drop_frame;
++
++ rcvd_pkts++;
++ rcvd_bytes += rx_bytes;
++
++ /* Linux processing */
++ skb_reserve(skb, MVNETA_MH_SIZE + NET_SKB_PAD);
++ skb_put(skb, rx_bytes);
++
++ skb->protocol = eth_type_trans(skb, dev);
++
++ mvneta_rx_csum(pp, rx_status, skb);
++
++ napi_gro_receive(&port->napi, skb);
++ }
++
++ if (rcvd_pkts) {
++ struct mvneta_pcpu_stats *stats = this_cpu_ptr(pp->stats);
++
++ u64_stats_update_begin(&stats->syncp);
++ stats->rx_packets += rcvd_pkts;
++ stats->rx_bytes += rcvd_bytes;
++ u64_stats_update_end(&stats->syncp);
++ }
++
++ /* Update rxq management counters */
++ mvneta_rxq_desc_num_update(pp, rxq, rx_done, rx_done);
++
++ return rx_done;
+ }
+
+-/* Main rx processing */
+-static int mvneta_rx(struct mvneta_port *pp, int rx_todo,
+- struct mvneta_rx_queue *rxq)
++/* Main rx processing when using hardware buffer management */
++static int mvneta_rx_hwbm(struct mvneta_port *pp, int rx_todo,
++ struct mvneta_rx_queue *rxq)
+ {
+ struct mvneta_pcpu_port *port = this_cpu_ptr(pp->ports);
+ struct net_device *dev = pp->dev;
+@@ -1628,21 +2004,29 @@ static int mvneta_rx(struct mvneta_port
+ /* Fairness NAPI loop */
+ while (rx_done < rx_todo) {
+ struct mvneta_rx_desc *rx_desc = mvneta_rxq_next_desc_get(rxq);
++ struct mvneta_bm_pool *bm_pool = NULL;
+ struct sk_buff *skb;
+ unsigned char *data;
+ dma_addr_t phys_addr;
+- u32 rx_status;
++ u32 rx_status, frag_size;
+ int rx_bytes, err;
++ u8 pool_id;
+
+ rx_done++;
+ rx_status = rx_desc->status;
+ rx_bytes = rx_desc->data_size - (ETH_FCS_LEN + MVNETA_MH_SIZE);
+ data = (unsigned char *)rx_desc->buf_cookie;
+ phys_addr = rx_desc->buf_phys_addr;
++ pool_id = MVNETA_RX_GET_BM_POOL_ID(rx_desc);
++ bm_pool = &pp->bm_priv->bm_pools[pool_id];
+
+ if (!mvneta_rxq_desc_is_first_last(rx_status) ||
+ (rx_status & MVNETA_RXD_ERR_SUMMARY)) {
+- err_drop_frame:
++err_drop_frame_ret_pool:
++ /* Return the buffer to the pool */
++ mvneta_bm_pool_put_bp(pp->bm_priv, bm_pool,
++ rx_desc->buf_phys_addr);
++err_drop_frame:
+ dev->stats.rx_errors++;
+ mvneta_rx_error(pp, rx_desc);
+ /* leave the descriptor untouched */
+@@ -1653,7 +2037,7 @@ static int mvneta_rx(struct mvneta_port
+ /* better copy a small frame and not unmap the DMA region */
+ skb = netdev_alloc_skb_ip_align(dev, rx_bytes);
+ if (unlikely(!skb))
+- goto err_drop_frame;
++ goto err_drop_frame_ret_pool;
+
+ dma_sync_single_range_for_cpu(dev->dev.parent,
+ rx_desc->buf_phys_addr,
+@@ -1671,26 +2055,31 @@ static int mvneta_rx(struct mvneta_port
+ rcvd_pkts++;
+ rcvd_bytes += rx_bytes;
+
++ /* Return the buffer to the pool */
++ mvneta_bm_pool_put_bp(pp->bm_priv, bm_pool,
++ rx_desc->buf_phys_addr);
++
+ /* leave the descriptor and buffer untouched */
+ continue;
+ }
+
+ /* Refill processing */
+- err = mvneta_rx_refill(pp, rx_desc);
++ err = mvneta_bm_pool_refill(pp->bm_priv, bm_pool);
+ if (err) {
+ netdev_err(dev, "Linux processing - Can't refill\n");
+ rxq->missed++;
+- goto err_drop_frame;
++ goto err_drop_frame_ret_pool;
+ }
+
+- skb = build_skb(data, pp->frag_size > PAGE_SIZE ? 0 : pp->frag_size);
++ frag_size = bm_pool->frag_size;
++
++ skb = build_skb(data, frag_size > PAGE_SIZE ? 0 : frag_size);
+
+ /* After refill old buffer has to be unmapped regardless
+ * the skb is successfully built or not.
+ */
+- dma_unmap_single(dev->dev.parent, phys_addr,
+- MVNETA_RX_BUF_SIZE(pp->pkt_size), DMA_FROM_DEVICE);
+-
++ dma_unmap_single(&pp->bm_priv->pdev->dev, phys_addr,
++ bm_pool->buf_size, DMA_FROM_DEVICE);
+ if (!skb)
+ goto err_drop_frame;
+
+@@ -2295,7 +2684,10 @@ static int mvneta_poll(struct napi_struc
+
+ if (rx_queue) {
+ rx_queue = rx_queue - 1;
+- rx_done = mvneta_rx(pp, budget, &pp->rxqs[rx_queue]);
++ if (pp->bm_priv)
++ rx_done = mvneta_rx_hwbm(pp, budget, &pp->rxqs[rx_queue]);
++ else
++ rx_done = mvneta_rx_swbm(pp, budget, &pp->rxqs[rx_queue]);
+ }
+
+ budget -= rx_done;
+@@ -2384,9 +2776,17 @@ static int mvneta_rxq_init(struct mvneta
+ mvneta_rx_pkts_coal_set(pp, rxq, rxq->pkts_coal);
+ mvneta_rx_time_coal_set(pp, rxq, rxq->time_coal);
+
+- /* Fill RXQ with buffers from RX pool */
+- mvneta_rxq_buf_size_set(pp, rxq, MVNETA_RX_BUF_SIZE(pp->pkt_size));
+- mvneta_rxq_bm_disable(pp, rxq);
++ if (!pp->bm_priv) {
++ /* Fill RXQ with buffers from RX pool */
++ mvneta_rxq_buf_size_set(pp, rxq,
++ MVNETA_RX_BUF_SIZE(pp->pkt_size));
++ mvneta_rxq_bm_disable(pp, rxq);
++ } else {
++ mvneta_rxq_bm_enable(pp, rxq);
++ mvneta_rxq_long_pool_set(pp, rxq);
++ mvneta_rxq_short_pool_set(pp, rxq);
++ }
++
+ mvneta_rxq_fill(pp, rxq, rxq->size);
+
+ return 0;
+@@ -2659,6 +3059,9 @@ static int mvneta_change_mtu(struct net_
+ dev->mtu = mtu;
+
+ if (!netif_running(dev)) {
++ if (pp->bm_priv)
++ mvneta_bm_update_mtu(pp, mtu);
++
+ netdev_update_features(dev);
+ return 0;
+ }
+@@ -2671,6 +3074,9 @@ static int mvneta_change_mtu(struct net_
+ mvneta_cleanup_txqs(pp);
+ mvneta_cleanup_rxqs(pp);
+
++ if (pp->bm_priv)
++ mvneta_bm_update_mtu(pp, mtu);
++
+ pp->pkt_size = MVNETA_RX_PKT_SIZE(dev->mtu);
+ pp->frag_size = SKB_DATA_ALIGN(MVNETA_RX_BUF_SIZE(pp->pkt_size)) +
+ SKB_DATA_ALIGN(sizeof(struct skb_shared_info));
+@@ -3563,6 +3969,7 @@ static int mvneta_probe(struct platform_
+ struct resource *res;
+ struct device_node *dn = pdev->dev.of_node;
+ struct device_node *phy_node;
++ struct device_node *bm_node;
+ struct mvneta_port *pp;
+ struct net_device *dev;
+ const char *dt_mac_addr;
+@@ -3690,26 +4097,39 @@ static int mvneta_probe(struct platform_
+
+ pp->tx_csum_limit = tx_csum_limit;
+
++ dram_target_info = mv_mbus_dram_info();
++ if (dram_target_info)
++ mvneta_conf_mbus_windows(pp, dram_target_info);
++
+ pp->tx_ring_size = MVNETA_MAX_TXD;
+ pp->rx_ring_size = MVNETA_MAX_RXD;
+
+ pp->dev = dev;
+ SET_NETDEV_DEV(dev, &pdev->dev);
+
++ pp->id = global_port_id++;
++
++ /* Obtain access to BM resources if enabled and already initialized */
++ bm_node = of_parse_phandle(dn, "buffer-manager", 0);
++ if (bm_node && bm_node->data) {
++ pp->bm_priv = bm_node->data;
++ err = mvneta_bm_port_init(pdev, pp);
++ if (err < 0) {
++ dev_info(&pdev->dev, "use SW buffer management\n");
++ pp->bm_priv = NULL;
++ }
++ }
++
+ err = mvneta_init(&pdev->dev, pp);
+ if (err < 0)
+- goto err_free_stats;
++ goto err_netdev;
+
+ err = mvneta_port_power_up(pp, phy_mode);
+ if (err < 0) {
+ dev_err(&pdev->dev, "can't power up port\n");
+- goto err_free_stats;
++ goto err_netdev;
+ }
+
+- dram_target_info = mv_mbus_dram_info();
+- if (dram_target_info)
+- mvneta_conf_mbus_windows(pp, dram_target_info);
+-
+ for_each_present_cpu(cpu) {
+ struct mvneta_pcpu_port *port = per_cpu_ptr(pp->ports, cpu);
+
+@@ -3744,6 +4164,13 @@ static int mvneta_probe(struct platform_
+
+ return 0;
+
++err_netdev:
++ unregister_netdev(dev);
++ if (pp->bm_priv) {
++ mvneta_bm_pool_destroy(pp->bm_priv, pp->pool_long, 1 << pp->id);
++ mvneta_bm_pool_destroy(pp->bm_priv, pp->pool_short,
++ 1 << pp->id);
++ }
+ err_free_stats:
+ free_percpu(pp->stats);
+ err_free_ports:
+@@ -3773,6 +4200,12 @@ static int mvneta_remove(struct platform
+ of_node_put(pp->phy_node);
+ free_netdev(dev);
+
++ if (pp->bm_priv) {
++ mvneta_bm_pool_destroy(pp->bm_priv, pp->pool_long, 1 << pp->id);
++ mvneta_bm_pool_destroy(pp->bm_priv, pp->pool_short,
++ 1 << pp->id);
++ }
++
+ return 0;
+ }
+
+--- /dev/null
++++ b/drivers/net/ethernet/marvell/mvneta_bm.c
+@@ -0,0 +1,546 @@
++/*
++ * Driver for Marvell NETA network controller Buffer Manager.
++ *
++ * Copyright (C) 2015 Marvell
++ *
++ * Marcin Wojtas <mw@semihalf.com>
++ *
++ * This file is licensed under the terms of the GNU General Public
++ * License version 2. This program is licensed "as is" without any
++ * warranty of any kind, whether express or implied.
++ */
++
++#include <linux/kernel.h>
++#include <linux/genalloc.h>
++#include <linux/platform_device.h>
++#include <linux/netdevice.h>
++#include <linux/skbuff.h>
++#include <linux/mbus.h>
++#include <linux/module.h>
++#include <linux/io.h>
++#include <linux/of.h>
++#include <linux/clk.h>
++#include "mvneta_bm.h"
++
++#define MVNETA_BM_DRIVER_NAME "mvneta_bm"
++#define MVNETA_BM_DRIVER_VERSION "1.0"
++
++static void mvneta_bm_write(struct mvneta_bm *priv, u32 offset, u32 data)
++{
++ writel(data, priv->reg_base + offset);
++}
++
++static u32 mvneta_bm_read(struct mvneta_bm *priv, u32 offset)
++{
++ return readl(priv->reg_base + offset);
++}
++
++static void mvneta_bm_pool_enable(struct mvneta_bm *priv, int pool_id)
++{
++ u32 val;
++
++ val = mvneta_bm_read(priv, MVNETA_BM_POOL_BASE_REG(pool_id));
++ val |= MVNETA_BM_POOL_ENABLE_MASK;
++ mvneta_bm_write(priv, MVNETA_BM_POOL_BASE_REG(pool_id), val);
++
++ /* Clear BM cause register */
++ mvneta_bm_write(priv, MVNETA_BM_INTR_CAUSE_REG, 0);
++}
++
++static void mvneta_bm_pool_disable(struct mvneta_bm *priv, int pool_id)
++{
++ u32 val;
++
++ val = mvneta_bm_read(priv, MVNETA_BM_POOL_BASE_REG(pool_id));
++ val &= ~MVNETA_BM_POOL_ENABLE_MASK;
++ mvneta_bm_write(priv, MVNETA_BM_POOL_BASE_REG(pool_id), val);
++}
++
++static inline void mvneta_bm_config_set(struct mvneta_bm *priv, u32 mask)
++{
++ u32 val;
++
++ val = mvneta_bm_read(priv, MVNETA_BM_CONFIG_REG);
++ val |= mask;
++ mvneta_bm_write(priv, MVNETA_BM_CONFIG_REG, val);
++}
++
++static inline void mvneta_bm_config_clear(struct mvneta_bm *priv, u32 mask)
++{
++ u32 val;
++
++ val = mvneta_bm_read(priv, MVNETA_BM_CONFIG_REG);
++ val &= ~mask;
++ mvneta_bm_write(priv, MVNETA_BM_CONFIG_REG, val);
++}
++
++static void mvneta_bm_pool_target_set(struct mvneta_bm *priv, int pool_id,
++ u8 target_id, u8 attr)
++{
++ u32 val;
++
++ val = mvneta_bm_read(priv, MVNETA_BM_XBAR_POOL_REG(pool_id));
++ val &= ~MVNETA_BM_TARGET_ID_MASK(pool_id);
++ val &= ~MVNETA_BM_XBAR_ATTR_MASK(pool_id);
++ val |= MVNETA_BM_TARGET_ID_VAL(pool_id, target_id);
++ val |= MVNETA_BM_XBAR_ATTR_VAL(pool_id, attr);
++
++ mvneta_bm_write(priv, MVNETA_BM_XBAR_POOL_REG(pool_id), val);
++}
++
++/* Allocate skb for BM pool */
++void *mvneta_buf_alloc(struct mvneta_bm *priv, struct mvneta_bm_pool *bm_pool,
++ dma_addr_t *buf_phys_addr)
++{
++ void *buf;
++ dma_addr_t phys_addr;
++
++ buf = mvneta_frag_alloc(bm_pool->frag_size);
++ if (!buf)
++ return NULL;
++
++ /* In order to update buf_cookie field of RX descriptor properly,
++ * BM hardware expects buf virtual address to be placed in the
++ * first four bytes of mapped buffer.
++ */
++ *(u32 *)buf = (u32)buf;
++ phys_addr = dma_map_single(&priv->pdev->dev, buf, bm_pool->buf_size,
++ DMA_FROM_DEVICE);
++ if (unlikely(dma_mapping_error(&priv->pdev->dev, phys_addr))) {
++ mvneta_frag_free(bm_pool->frag_size, buf);
++ return NULL;
++ }
++ *buf_phys_addr = phys_addr;
++
++ return buf;
++}
++
++/* Refill processing for HW buffer management */
++int mvneta_bm_pool_refill(struct mvneta_bm *priv,
++ struct mvneta_bm_pool *bm_pool)
++{
++ dma_addr_t buf_phys_addr;
++ void *buf;
++
++ buf = mvneta_buf_alloc(priv, bm_pool, &buf_phys_addr);
++ if (!buf)
++ return -ENOMEM;
++
++ mvneta_bm_pool_put_bp(priv, bm_pool, buf_phys_addr);
++
++ return 0;
++}
++EXPORT_SYMBOL_GPL(mvneta_bm_pool_refill);
++
++/* Allocate buffers for the pool */
++int mvneta_bm_bufs_add(struct mvneta_bm *priv, struct mvneta_bm_pool *bm_pool,
++ int buf_num)
++{
++ int err, i;
++
++ if (bm_pool->buf_num == bm_pool->size) {
++ dev_dbg(&priv->pdev->dev, "pool %d already filled\n",
++ bm_pool->id);
++ return bm_pool->buf_num;
++ }
++
++ if (buf_num < 0 ||
++ (buf_num + bm_pool->buf_num > bm_pool->size)) {
++ dev_err(&priv->pdev->dev,
++ "cannot allocate %d buffers for pool %d\n",
++ buf_num, bm_pool->id);
++ return 0;
++ }
++
++ for (i = 0; i < buf_num; i++) {
++ err = mvneta_bm_pool_refill(priv, bm_pool);
++ if (err < 0)
++ break;
++ }
++
++ /* Update BM driver with number of buffers added to pool */
++ bm_pool->buf_num += i;
++
++ dev_dbg(&priv->pdev->dev,
++ "%s pool %d: pkt_size=%4d, buf_size=%4d, frag_size=%4d\n",
++ bm_pool->type == MVNETA_BM_SHORT ? "short" : "long",
++ bm_pool->id, bm_pool->pkt_size, bm_pool->buf_size,
++ bm_pool->frag_size);
++
++ dev_dbg(&priv->pdev->dev,
++ "%s pool %d: %d of %d buffers added\n",
++ bm_pool->type == MVNETA_BM_SHORT ? "short" : "long",
++ bm_pool->id, i, buf_num);
++
++ return i;
++}
++EXPORT_SYMBOL_GPL(mvneta_bm_bufs_add);
++
++/* Create pool */
++static int mvneta_bm_pool_create(struct mvneta_bm *priv,
++ struct mvneta_bm_pool *bm_pool)
++{
++ struct platform_device *pdev = priv->pdev;
++ u8 target_id, attr;
++ int size_bytes, err;
++
++ size_bytes = sizeof(u32) * bm_pool->size;
++ bm_pool->virt_addr = dma_alloc_coherent(&pdev->dev, size_bytes,
++ &bm_pool->phys_addr,
++ GFP_KERNEL);
++ if (!bm_pool->virt_addr)
++ return -ENOMEM;
++
++ if (!IS_ALIGNED((u32)bm_pool->virt_addr, MVNETA_BM_POOL_PTR_ALIGN)) {
++ dma_free_coherent(&pdev->dev, size_bytes, bm_pool->virt_addr,
++ bm_pool->phys_addr);
++ dev_err(&pdev->dev, "BM pool %d is not %d bytes aligned\n",
++ bm_pool->id, MVNETA_BM_POOL_PTR_ALIGN);
++ return -ENOMEM;
++ }
++
++ err = mvebu_mbus_get_dram_win_info(bm_pool->phys_addr, &target_id,
++ &attr);
++ if (err < 0) {
++ dma_free_coherent(&pdev->dev, size_bytes, bm_pool->virt_addr,
++ bm_pool->phys_addr);
++ return err;
++ }
++
++ /* Set pool address */
++ mvneta_bm_write(priv, MVNETA_BM_POOL_BASE_REG(bm_pool->id),
++ bm_pool->phys_addr);
++
++ mvneta_bm_pool_target_set(priv, bm_pool->id, target_id, attr);
++ mvneta_bm_pool_enable(priv, bm_pool->id);
++
++ return 0;
++}
++
++/* Notify the driver that BM pool is being used as specific type and return the
++ * pool pointer on success
++ */
++struct mvneta_bm_pool *mvneta_bm_pool_use(struct mvneta_bm *priv, u8 pool_id,
++ enum mvneta_bm_type type, u8 port_id,
++ int pkt_size)
++{
++ struct mvneta_bm_pool *new_pool = &priv->bm_pools[pool_id];
++ int num, err;
++
++ if (new_pool->type == MVNETA_BM_LONG &&
++ new_pool->port_map != 1 << port_id) {
++ dev_err(&priv->pdev->dev,
++ "long pool cannot be shared by the ports\n");
++ return NULL;
++ }
++
++ if (new_pool->type == MVNETA_BM_SHORT && new_pool->type != type) {
++ dev_err(&priv->pdev->dev,
++ "mixing pools' types between the ports is forbidden\n");
++ return NULL;
++ }
++
++ if (new_pool->pkt_size == 0 || type != MVNETA_BM_SHORT)
++ new_pool->pkt_size = pkt_size;
++
++ /* Allocate buffers in case BM pool hasn't been used yet */
++ if (new_pool->type == MVNETA_BM_FREE) {
++ new_pool->type = type;
++ new_pool->buf_size = MVNETA_RX_BUF_SIZE(new_pool->pkt_size);
++ new_pool->frag_size =
++ SKB_DATA_ALIGN(MVNETA_RX_BUF_SIZE(new_pool->pkt_size)) +
++ SKB_DATA_ALIGN(sizeof(struct skb_shared_info));
++
++ /* Create new pool */
++ err = mvneta_bm_pool_create(priv, new_pool);
++ if (err) {
++ dev_err(&priv->pdev->dev, "fail to create pool %d\n",
++ new_pool->id);
++ return NULL;
++ }
++
++ /* Allocate buffers for this pool */
++ num = mvneta_bm_bufs_add(priv, new_pool, new_pool->size);
++ if (num != new_pool->size) {
++ WARN(1, "pool %d: %d of %d allocated\n",
++ new_pool->id, num, new_pool->size);
++ return NULL;
++ }
++ }
++
++ return new_pool;
++}
++EXPORT_SYMBOL_GPL(mvneta_bm_pool_use);
++
++/* Free all buffers from the pool */
++void mvneta_bm_bufs_free(struct mvneta_bm *priv, struct mvneta_bm_pool *bm_pool,
++ u8 port_map)
++{
++ int i;
++
++ bm_pool->port_map &= ~port_map;
++ if (bm_pool->port_map)
++ return;
++
++ mvneta_bm_config_set(priv, MVNETA_BM_EMPTY_LIMIT_MASK);
++
++ for (i = 0; i < bm_pool->buf_num; i++) {
++ dma_addr_t buf_phys_addr;
++ u32 *vaddr;
++
++ /* Get buffer physical address (indirect access) */
++ buf_phys_addr = mvneta_bm_pool_get_bp(priv, bm_pool);
++
++ /* Work-around to the problems when destroying the pool,
++ * when it occurs that a read access to BPPI returns 0.
++ */
++ if (buf_phys_addr == 0)
++ continue;
++
++ vaddr = phys_to_virt(buf_phys_addr);
++ if (!vaddr)
++ break;
++
++ dma_unmap_single(&priv->pdev->dev, buf_phys_addr,
++ bm_pool->buf_size, DMA_FROM_DEVICE);
++ mvneta_frag_free(bm_pool->frag_size, vaddr);
++ }
++
++ mvneta_bm_config_clear(priv, MVNETA_BM_EMPTY_LIMIT_MASK);
++
++ /* Update BM driver with number of buffers removed from pool */
++ bm_pool->buf_num -= i;
++}
++EXPORT_SYMBOL_GPL(mvneta_bm_bufs_free);
++
++/* Cleanup pool */
++void mvneta_bm_pool_destroy(struct mvneta_bm *priv,
++ struct mvneta_bm_pool *bm_pool, u8 port_map)
++{
++ bm_pool->port_map &= ~port_map;
++ if (bm_pool->port_map)
++ return;
++
++ bm_pool->type = MVNETA_BM_FREE;
++
++ mvneta_bm_bufs_free(priv, bm_pool, port_map);
++ if (bm_pool->buf_num)
++ WARN(1, "cannot free all buffers in pool %d\n", bm_pool->id);
++
++ if (bm_pool->virt_addr) {
++ dma_free_coherent(&priv->pdev->dev, sizeof(u32) * bm_pool->size,
++ bm_pool->virt_addr, bm_pool->phys_addr);
++ bm_pool->virt_addr = NULL;
++ }
++
++ mvneta_bm_pool_disable(priv, bm_pool->id);
++}
++EXPORT_SYMBOL_GPL(mvneta_bm_pool_destroy);
++
++static void mvneta_bm_pools_init(struct mvneta_bm *priv)
++{
++ struct device_node *dn = priv->pdev->dev.of_node;
++ struct mvneta_bm_pool *bm_pool;
++ char prop[15];
++ u32 size;
++ int i;
++
++ /* Activate BM unit */
++ mvneta_bm_write(priv, MVNETA_BM_COMMAND_REG, MVNETA_BM_START_MASK);
++
++ /* Create all pools with maximum size */
++ for (i = 0; i < MVNETA_BM_POOLS_NUM; i++) {
++ bm_pool = &priv->bm_pools[i];
++ bm_pool->id = i;
++ bm_pool->type = MVNETA_BM_FREE;
++
++ /* Reset read pointer */
++ mvneta_bm_write(priv, MVNETA_BM_POOL_READ_PTR_REG(i), 0);
++
++ /* Reset write pointer */
++ mvneta_bm_write(priv, MVNETA_BM_POOL_WRITE_PTR_REG(i), 0);
++
++ /* Configure pool size according to DT or use default value */
++ sprintf(prop, "pool%d,capacity", i);
++ if (of_property_read_u32(dn, prop, &size)) {
++ size = MVNETA_BM_POOL_CAP_DEF;
++ } else if (size > MVNETA_BM_POOL_CAP_MAX) {
++ dev_warn(&priv->pdev->dev,
++ "Illegal pool %d capacity %d, set to %d\n",
++ i, size, MVNETA_BM_POOL_CAP_MAX);
++ size = MVNETA_BM_POOL_CAP_MAX;
++ } else if (size < MVNETA_BM_POOL_CAP_MIN) {
++ dev_warn(&priv->pdev->dev,
++ "Illegal pool %d capacity %d, set to %d\n",
++ i, size, MVNETA_BM_POOL_CAP_MIN);
++ size = MVNETA_BM_POOL_CAP_MIN;
++ } else if (!IS_ALIGNED(size, MVNETA_BM_POOL_CAP_ALIGN)) {
++ dev_warn(&priv->pdev->dev,
++ "Illegal pool %d capacity %d, round to %d\n",
++ i, size, ALIGN(size,
++ MVNETA_BM_POOL_CAP_ALIGN));
++ size = ALIGN(size, MVNETA_BM_POOL_CAP_ALIGN);
++ }
++ bm_pool->size = size;
++
++ mvneta_bm_write(priv, MVNETA_BM_POOL_SIZE_REG(i),
++ bm_pool->size);
++
++ /* Obtain custom pkt_size from DT */
++ sprintf(prop, "pool%d,pkt-size", i);
++ if (of_property_read_u32(dn, prop, &bm_pool->pkt_size))
++ bm_pool->pkt_size = 0;
++ }
++}
++
++static void mvneta_bm_default_set(struct mvneta_bm *priv)
++{
++ u32 val;
++
++ /* Mask BM all interrupts */
++ mvneta_bm_write(priv, MVNETA_BM_INTR_MASK_REG, 0);
++
++ /* Clear BM cause register */
++ mvneta_bm_write(priv, MVNETA_BM_INTR_CAUSE_REG, 0);
++
++ /* Set BM configuration register */
++ val = mvneta_bm_read(priv, MVNETA_BM_CONFIG_REG);
++
++ /* Reduce MaxInBurstSize from 32 BPs to 16 BPs */
++ val &= ~MVNETA_BM_MAX_IN_BURST_SIZE_MASK;
++ val |= MVNETA_BM_MAX_IN_BURST_SIZE_16BP;
++ mvneta_bm_write(priv, MVNETA_BM_CONFIG_REG, val);
++}
++
++static int mvneta_bm_init(struct mvneta_bm *priv)
++{
++ mvneta_bm_default_set(priv);
++
++ /* Allocate and initialize BM pools structures */
++ priv->bm_pools = devm_kcalloc(&priv->pdev->dev, MVNETA_BM_POOLS_NUM,
++ sizeof(struct mvneta_bm_pool),
++ GFP_KERNEL);
++ if (!priv->bm_pools)
++ return -ENOMEM;
++
++ mvneta_bm_pools_init(priv);
++
++ return 0;
++}
++
++static int mvneta_bm_get_sram(struct device_node *dn,
++ struct mvneta_bm *priv)
++{
++ priv->bppi_pool = of_gen_pool_get(dn, "internal-mem", 0);
++ if (!priv->bppi_pool)
++ return -ENOMEM;
++
++ priv->bppi_virt_addr = gen_pool_dma_alloc(priv->bppi_pool,
++ MVNETA_BM_BPPI_SIZE,
++ &priv->bppi_phys_addr);
++ if (!priv->bppi_virt_addr)
++ return -ENOMEM;
++
++ return 0;
++}
++
++static void mvneta_bm_put_sram(struct mvneta_bm *priv)
++{
++ gen_pool_free(priv->bppi_pool, priv->bppi_phys_addr,
++ MVNETA_BM_BPPI_SIZE);
++}
++
++static int mvneta_bm_probe(struct platform_device *pdev)
++{
++ struct device_node *dn = pdev->dev.of_node;
++ struct mvneta_bm *priv;
++ struct resource *res;
++ int err;
++
++ priv = devm_kzalloc(&pdev->dev, sizeof(struct mvneta_bm), GFP_KERNEL);
++ if (!priv)
++ return -ENOMEM;
++
++ res = platform_get_resource(pdev, IORESOURCE_MEM, 0);
++ priv->reg_base = devm_ioremap_resource(&pdev->dev, res);
++ if (IS_ERR(priv->reg_base))
++ return PTR_ERR(priv->reg_base);
++
++ priv->clk = devm_clk_get(&pdev->dev, NULL);
++ if (IS_ERR(priv->clk))
++ return PTR_ERR(priv->clk);
++ err = clk_prepare_enable(priv->clk);
++ if (err < 0)
++ return err;
++
++ err = mvneta_bm_get_sram(dn, priv);
++ if (err < 0) {
++ dev_err(&pdev->dev, "failed to allocate internal memory\n");
++ goto err_clk;
++ }
++
++ priv->pdev = pdev;
++
++ /* Initialize buffer manager internals */
++ err = mvneta_bm_init(priv);
++ if (err < 0) {
++ dev_err(&pdev->dev, "failed to initialize controller\n");
++ goto err_sram;
++ }
++
++ dn->data = priv;
++ platform_set_drvdata(pdev, priv);
++
++ dev_info(&pdev->dev, "Buffer Manager for network controller enabled\n");
++
++ return 0;
++
++err_sram:
++ mvneta_bm_put_sram(priv);
++err_clk:
++ clk_disable_unprepare(priv->clk);
++ return err;
++}
++
++static int mvneta_bm_remove(struct platform_device *pdev)
++{
++ struct mvneta_bm *priv = platform_get_drvdata(pdev);
++ u8 all_ports_map = 0xff;
++ int i = 0;
++
++ for (i = 0; i < MVNETA_BM_POOLS_NUM; i++) {
++ struct mvneta_bm_pool *bm_pool = &priv->bm_pools[i];
++
++ mvneta_bm_pool_destroy(priv, bm_pool, all_ports_map);
++ }
++
++ mvneta_bm_put_sram(priv);
++
++ /* Dectivate BM unit */
++ mvneta_bm_write(priv, MVNETA_BM_COMMAND_REG, MVNETA_BM_STOP_MASK);
++
++ clk_disable_unprepare(priv->clk);
++
++ return 0;
++}
++
++static const struct of_device_id mvneta_bm_match[] = {
++ { .compatible = "marvell,armada-380-neta-bm" },
++ { }
++};
++MODULE_DEVICE_TABLE(of, mvneta_bm_match);
++
++static struct platform_driver mvneta_bm_driver = {
++ .probe = mvneta_bm_probe,
++ .remove = mvneta_bm_remove,
++ .driver = {
++ .name = MVNETA_BM_DRIVER_NAME,
++ .of_match_table = mvneta_bm_match,
++ },
++};
++
++module_platform_driver(mvneta_bm_driver);
++
++MODULE_DESCRIPTION("Marvell NETA Buffer Manager Driver - www.marvell.com");
++MODULE_AUTHOR("Marcin Wojtas <mw@semihalf.com>");
++MODULE_LICENSE("GPL v2");
+--- /dev/null
++++ b/drivers/net/ethernet/marvell/mvneta_bm.h
+@@ -0,0 +1,189 @@
++/*
++ * Driver for Marvell NETA network controller Buffer Manager.
++ *
++ * Copyright (C) 2015 Marvell
++ *
++ * Marcin Wojtas <mw@semihalf.com>
++ *
++ * This file is licensed under the terms of the GNU General Public
++ * License version 2. This program is licensed "as is" without any
++ * warranty of any kind, whether express or implied.
++ */
++
++#ifndef _MVNETA_BM_H_
++#define _MVNETA_BM_H_
++
++/* BM Configuration Register */
++#define MVNETA_BM_CONFIG_REG 0x0
++#define MVNETA_BM_STATUS_MASK 0x30
++#define MVNETA_BM_ACTIVE_MASK BIT(4)
++#define MVNETA_BM_MAX_IN_BURST_SIZE_MASK 0x60000
++#define MVNETA_BM_MAX_IN_BURST_SIZE_16BP BIT(18)
++#define MVNETA_BM_EMPTY_LIMIT_MASK BIT(19)
++
++/* BM Activation Register */
++#define MVNETA_BM_COMMAND_REG 0x4
++#define MVNETA_BM_START_MASK BIT(0)
++#define MVNETA_BM_STOP_MASK BIT(1)
++#define MVNETA_BM_PAUSE_MASK BIT(2)
++
++/* BM Xbar interface Register */
++#define MVNETA_BM_XBAR_01_REG 0x8
++#define MVNETA_BM_XBAR_23_REG 0xc
++#define MVNETA_BM_XBAR_POOL_REG(pool) \
++ (((pool) < 2) ? MVNETA_BM_XBAR_01_REG : MVNETA_BM_XBAR_23_REG)
++#define MVNETA_BM_TARGET_ID_OFFS(pool) (((pool) & 1) ? 16 : 0)
++#define MVNETA_BM_TARGET_ID_MASK(pool) \
++ (0xf << MVNETA_BM_TARGET_ID_OFFS(pool))
++#define MVNETA_BM_TARGET_ID_VAL(pool, id) \
++ ((id) << MVNETA_BM_TARGET_ID_OFFS(pool))
++#define MVNETA_BM_XBAR_ATTR_OFFS(pool) (((pool) & 1) ? 20 : 4)
++#define MVNETA_BM_XBAR_ATTR_MASK(pool) \
++ (0xff << MVNETA_BM_XBAR_ATTR_OFFS(pool))
++#define MVNETA_BM_XBAR_ATTR_VAL(pool, attr) \
++ ((attr) << MVNETA_BM_XBAR_ATTR_OFFS(pool))
++
++/* Address of External Buffer Pointers Pool Register */
++#define MVNETA_BM_POOL_BASE_REG(pool) (0x10 + ((pool) << 4))
++#define MVNETA_BM_POOL_ENABLE_MASK BIT(0)
++
++/* External Buffer Pointers Pool RD pointer Register */
++#define MVNETA_BM_POOL_READ_PTR_REG(pool) (0x14 + ((pool) << 4))
++#define MVNETA_BM_POOL_SET_READ_PTR_MASK 0xfffc
++#define MVNETA_BM_POOL_GET_READ_PTR_OFFS 16
++#define MVNETA_BM_POOL_GET_READ_PTR_MASK 0xfffc0000
++
++/* External Buffer Pointers Pool WR pointer */
++#define MVNETA_BM_POOL_WRITE_PTR_REG(pool) (0x18 + ((pool) << 4))
++#define MVNETA_BM_POOL_SET_WRITE_PTR_OFFS 0
++#define MVNETA_BM_POOL_SET_WRITE_PTR_MASK 0xfffc
++#define MVNETA_BM_POOL_GET_WRITE_PTR_OFFS 16
++#define MVNETA_BM_POOL_GET_WRITE_PTR_MASK 0xfffc0000
++
++/* External Buffer Pointers Pool Size Register */
++#define MVNETA_BM_POOL_SIZE_REG(pool) (0x1c + ((pool) << 4))
++#define MVNETA_BM_POOL_SIZE_MASK 0x3fff
++
++/* BM Interrupt Cause Register */
++#define MVNETA_BM_INTR_CAUSE_REG (0x50)
++
++/* BM interrupt Mask Register */
++#define MVNETA_BM_INTR_MASK_REG (0x54)
++
++/* Other definitions */
++#define MVNETA_BM_SHORT_PKT_SIZE 256
++#define MVNETA_BM_POOLS_NUM 4
++#define MVNETA_BM_POOL_CAP_MIN 128
++#define MVNETA_BM_POOL_CAP_DEF 2048
++#define MVNETA_BM_POOL_CAP_MAX \
++ (16 * 1024 - MVNETA_BM_POOL_CAP_ALIGN)
++#define MVNETA_BM_POOL_CAP_ALIGN 32
++#define MVNETA_BM_POOL_PTR_ALIGN 32
++
++#define MVNETA_BM_POOL_ACCESS_OFFS 8
++
++#define MVNETA_BM_BPPI_SIZE 0x100000
++
++#define MVNETA_RX_BUF_SIZE(pkt_size) ((pkt_size) + NET_SKB_PAD)
++
++enum mvneta_bm_type {
++ MVNETA_BM_FREE,
++ MVNETA_BM_LONG,
++ MVNETA_BM_SHORT
++};
++
++struct mvneta_bm {
++ void __iomem *reg_base;
++ struct clk *clk;
++ struct platform_device *pdev;
++
++ struct gen_pool *bppi_pool;
++ /* BPPI virtual base address */
++ void __iomem *bppi_virt_addr;
++ /* BPPI physical base address */
++ dma_addr_t bppi_phys_addr;
++
++ /* BM pools */
++ struct mvneta_bm_pool *bm_pools;
++};
++
++struct mvneta_bm_pool {
++ /* Pool number in the range 0-3 */
++ u8 id;
++ enum mvneta_bm_type type;
++
++ /* Buffer Pointers Pool External (BPPE) size in number of bytes */
++ int size;
++ /* Number of buffers used by this pool */
++ int buf_num;
++ /* Pool buffer size */
++ int buf_size;
++ /* Packet size */
++ int pkt_size;
++ /* Single frag size */
++ u32 frag_size;
++
++ /* BPPE virtual base address */
++ u32 *virt_addr;
++ /* BPPE physical base address */
++ dma_addr_t phys_addr;
++
++ /* Ports using BM pool */
++ u8 port_map;
++
++ struct mvneta_bm *priv;
++};
++
++/* Declarations and definitions */
++void *mvneta_frag_alloc(unsigned int frag_size);
++void mvneta_frag_free(unsigned int frag_size, void *data);
++
++#if defined(CONFIG_MVNETA_BM) || defined(CONFIG_MVNETA_BM_MODULE)
++void mvneta_bm_pool_destroy(struct mvneta_bm *priv,
++ struct mvneta_bm_pool *bm_pool, u8 port_map);
++void mvneta_bm_bufs_free(struct mvneta_bm *priv, struct mvneta_bm_pool *bm_pool,
++ u8 port_map);
++int mvneta_bm_bufs_add(struct mvneta_bm *priv, struct mvneta_bm_pool *bm_pool,
++ int buf_num);
++int mvneta_bm_pool_refill(struct mvneta_bm *priv,
++ struct mvneta_bm_pool *bm_pool);
++struct mvneta_bm_pool *mvneta_bm_pool_use(struct mvneta_bm *priv, u8 pool_id,
++ enum mvneta_bm_type type, u8 port_id,
++ int pkt_size);
++
++static inline void mvneta_bm_pool_put_bp(struct mvneta_bm *priv,
++ struct mvneta_bm_pool *bm_pool,
++ dma_addr_t buf_phys_addr)
++{
++ writel_relaxed(buf_phys_addr, priv->bppi_virt_addr +
++ (bm_pool->id << MVNETA_BM_POOL_ACCESS_OFFS));
++}
++
++static inline u32 mvneta_bm_pool_get_bp(struct mvneta_bm *priv,
++ struct mvneta_bm_pool *bm_pool)
++{
++ return readl_relaxed(priv->bppi_virt_addr +
++ (bm_pool->id << MVNETA_BM_POOL_ACCESS_OFFS));
++}
++#else
++void mvneta_bm_pool_destroy(struct mvneta_bm *priv,
++ struct mvneta_bm_pool *bm_pool, u8 port_map) {}
++void mvneta_bm_bufs_free(struct mvneta_bm *priv, struct mvneta_bm_pool *bm_pool,
++ u8 port_map) {}
++int mvneta_bm_bufs_add(struct mvneta_bm *priv, struct mvneta_bm_pool *bm_pool,
++ int buf_num) { return 0; }
++int mvneta_bm_pool_refill(struct mvneta_bm *priv,
++ struct mvneta_bm_pool *bm_pool) {return 0; }
++struct mvneta_bm_pool *mvneta_bm_pool_use(struct mvneta_bm *priv, u8 pool_id,
++ enum mvneta_bm_type type, u8 port_id,
++ int pkt_size) { return NULL; }
++
++static inline void mvneta_bm_pool_put_bp(struct mvneta_bm *priv,
++ struct mvneta_bm_pool *bm_pool,
++ dma_addr_t buf_phys_addr) {}
++
++static inline u32 mvneta_bm_pool_get_bp(struct mvneta_bm *priv,
++ struct mvneta_bm_pool *bm_pool)
++{ return 0; }
++#endif /* CONFIG_MVNETA_BM */
++#endif
diff --git a/target/linux/mvebu/patches-4.4/046-net-mvneta-Use-the-new-hwbm-framework.patch b/target/linux/mvebu/patches-4.4/046-net-mvneta-Use-the-new-hwbm-framework.patch
new file mode 100644
index 0000000000..210504c39e
--- /dev/null
+++ b/target/linux/mvebu/patches-4.4/046-net-mvneta-Use-the-new-hwbm-framework.patch
@@ -0,0 +1,359 @@
+From: Gregory CLEMENT <gregory.clement@free-electrons.com>
+Date: Mon, 14 Mar 2016 09:39:05 +0100
+Subject: [PATCH] net: mvneta: Use the new hwbm framework
+
+Now that the hardware buffer management framework had been introduced,
+let's use it.
+
+Tested-by: Sebastian Careba <nitroshift@yahoo.com>
+Signed-off-by: Gregory CLEMENT <gregory.clement@free-electrons.com>
+Signed-off-by: David S. Miller <davem@davemloft.net>
+---
+
+--- a/drivers/net/ethernet/marvell/Kconfig
++++ b/drivers/net/ethernet/marvell/Kconfig
+@@ -43,6 +43,7 @@ config MVMDIO
+ config MVNETA_BM
+ tristate "Marvell Armada 38x/XP network interface BM support"
+ depends on MVNETA
++ select HWBM
+ ---help---
+ This driver supports auxiliary block of the network
+ interface units in the Marvell ARMADA XP and ARMADA 38x SoC
+--- a/drivers/net/ethernet/marvell/mvneta.c
++++ b/drivers/net/ethernet/marvell/mvneta.c
+@@ -30,6 +30,7 @@
+ #include <linux/phy.h>
+ #include <linux/platform_device.h>
+ #include <linux/skbuff.h>
++#include <net/hwbm.h>
+ #include "mvneta_bm.h"
+ #include <net/ip.h>
+ #include <net/ipv6.h>
+@@ -1024,11 +1025,12 @@ static int mvneta_bm_port_init(struct pl
+ static void mvneta_bm_update_mtu(struct mvneta_port *pp, int mtu)
+ {
+ struct mvneta_bm_pool *bm_pool = pp->pool_long;
++ struct hwbm_pool *hwbm_pool = &bm_pool->hwbm_pool;
+ int num;
+
+ /* Release all buffers from long pool */
+ mvneta_bm_bufs_free(pp->bm_priv, bm_pool, 1 << pp->id);
+- if (bm_pool->buf_num) {
++ if (hwbm_pool->buf_num) {
+ WARN(1, "cannot free all buffers in pool %d\n",
+ bm_pool->id);
+ goto bm_mtu_err;
+@@ -1036,14 +1038,14 @@ static void mvneta_bm_update_mtu(struct
+
+ bm_pool->pkt_size = MVNETA_RX_PKT_SIZE(mtu);
+ bm_pool->buf_size = MVNETA_RX_BUF_SIZE(bm_pool->pkt_size);
+- bm_pool->frag_size = SKB_DATA_ALIGN(sizeof(struct skb_shared_info)) +
+- SKB_DATA_ALIGN(MVNETA_RX_BUF_SIZE(bm_pool->pkt_size));
++ hwbm_pool->frag_size = SKB_DATA_ALIGN(sizeof(struct skb_shared_info)) +
++ SKB_DATA_ALIGN(MVNETA_RX_BUF_SIZE(bm_pool->pkt_size));
+
+ /* Fill entire long pool */
+- num = mvneta_bm_bufs_add(pp->bm_priv, bm_pool, bm_pool->size);
+- if (num != bm_pool->size) {
++ num = hwbm_pool_add(hwbm_pool, hwbm_pool->size, GFP_ATOMIC);
++ if (num != hwbm_pool->size) {
+ WARN(1, "pool %d: %d of %d allocated\n",
+- bm_pool->id, num, bm_pool->size);
++ bm_pool->id, num, hwbm_pool->size);
+ goto bm_mtu_err;
+ }
+ mvneta_bm_pool_bufsize_set(pp, bm_pool->buf_size, bm_pool->id);
+@@ -2064,14 +2066,14 @@ err_drop_frame:
+ }
+
+ /* Refill processing */
+- err = mvneta_bm_pool_refill(pp->bm_priv, bm_pool);
++ err = hwbm_pool_refill(&bm_pool->hwbm_pool, GFP_ATOMIC);
+ if (err) {
+ netdev_err(dev, "Linux processing - Can't refill\n");
+ rxq->missed++;
+ goto err_drop_frame_ret_pool;
+ }
+
+- frag_size = bm_pool->frag_size;
++ frag_size = bm_pool->hwbm_pool.frag_size;
+
+ skb = build_skb(data, frag_size > PAGE_SIZE ? 0 : frag_size);
+
+--- a/drivers/net/ethernet/marvell/mvneta_bm.c
++++ b/drivers/net/ethernet/marvell/mvneta_bm.c
+@@ -10,16 +10,17 @@
+ * warranty of any kind, whether express or implied.
+ */
+
+-#include <linux/kernel.h>
++#include <linux/clk.h>
+ #include <linux/genalloc.h>
+-#include <linux/platform_device.h>
+-#include <linux/netdevice.h>
+-#include <linux/skbuff.h>
++#include <linux/io.h>
++#include <linux/kernel.h>
+ #include <linux/mbus.h>
+ #include <linux/module.h>
+-#include <linux/io.h>
++#include <linux/netdevice.h>
+ #include <linux/of.h>
+-#include <linux/clk.h>
++#include <linux/platform_device.h>
++#include <linux/skbuff.h>
++#include <net/hwbm.h>
+ #include "mvneta_bm.h"
+
+ #define MVNETA_BM_DRIVER_NAME "mvneta_bm"
+@@ -88,17 +89,13 @@ static void mvneta_bm_pool_target_set(st
+ mvneta_bm_write(priv, MVNETA_BM_XBAR_POOL_REG(pool_id), val);
+ }
+
+-/* Allocate skb for BM pool */
+-void *mvneta_buf_alloc(struct mvneta_bm *priv, struct mvneta_bm_pool *bm_pool,
+- dma_addr_t *buf_phys_addr)
++int mvneta_bm_construct(struct hwbm_pool *hwbm_pool, void *buf)
+ {
+- void *buf;
++ struct mvneta_bm_pool *bm_pool =
++ (struct mvneta_bm_pool *)hwbm_pool->priv;
++ struct mvneta_bm *priv = bm_pool->priv;
+ dma_addr_t phys_addr;
+
+- buf = mvneta_frag_alloc(bm_pool->frag_size);
+- if (!buf)
+- return NULL;
+-
+ /* In order to update buf_cookie field of RX descriptor properly,
+ * BM hardware expects buf virtual address to be placed in the
+ * first four bytes of mapped buffer.
+@@ -106,75 +103,13 @@ void *mvneta_buf_alloc(struct mvneta_bm
+ *(u32 *)buf = (u32)buf;
+ phys_addr = dma_map_single(&priv->pdev->dev, buf, bm_pool->buf_size,
+ DMA_FROM_DEVICE);
+- if (unlikely(dma_mapping_error(&priv->pdev->dev, phys_addr))) {
+- mvneta_frag_free(bm_pool->frag_size, buf);
+- return NULL;
+- }
+- *buf_phys_addr = phys_addr;
+-
+- return buf;
+-}
+-
+-/* Refill processing for HW buffer management */
+-int mvneta_bm_pool_refill(struct mvneta_bm *priv,
+- struct mvneta_bm_pool *bm_pool)
+-{
+- dma_addr_t buf_phys_addr;
+- void *buf;
+-
+- buf = mvneta_buf_alloc(priv, bm_pool, &buf_phys_addr);
+- if (!buf)
++ if (unlikely(dma_mapping_error(&priv->pdev->dev, phys_addr)))
+ return -ENOMEM;
+
+- mvneta_bm_pool_put_bp(priv, bm_pool, buf_phys_addr);
+-
++ mvneta_bm_pool_put_bp(priv, bm_pool, phys_addr);
+ return 0;
+ }
+-EXPORT_SYMBOL_GPL(mvneta_bm_pool_refill);
+-
+-/* Allocate buffers for the pool */
+-int mvneta_bm_bufs_add(struct mvneta_bm *priv, struct mvneta_bm_pool *bm_pool,
+- int buf_num)
+-{
+- int err, i;
+-
+- if (bm_pool->buf_num == bm_pool->size) {
+- dev_dbg(&priv->pdev->dev, "pool %d already filled\n",
+- bm_pool->id);
+- return bm_pool->buf_num;
+- }
+-
+- if (buf_num < 0 ||
+- (buf_num + bm_pool->buf_num > bm_pool->size)) {
+- dev_err(&priv->pdev->dev,
+- "cannot allocate %d buffers for pool %d\n",
+- buf_num, bm_pool->id);
+- return 0;
+- }
+-
+- for (i = 0; i < buf_num; i++) {
+- err = mvneta_bm_pool_refill(priv, bm_pool);
+- if (err < 0)
+- break;
+- }
+-
+- /* Update BM driver with number of buffers added to pool */
+- bm_pool->buf_num += i;
+-
+- dev_dbg(&priv->pdev->dev,
+- "%s pool %d: pkt_size=%4d, buf_size=%4d, frag_size=%4d\n",
+- bm_pool->type == MVNETA_BM_SHORT ? "short" : "long",
+- bm_pool->id, bm_pool->pkt_size, bm_pool->buf_size,
+- bm_pool->frag_size);
+-
+- dev_dbg(&priv->pdev->dev,
+- "%s pool %d: %d of %d buffers added\n",
+- bm_pool->type == MVNETA_BM_SHORT ? "short" : "long",
+- bm_pool->id, i, buf_num);
+-
+- return i;
+-}
+-EXPORT_SYMBOL_GPL(mvneta_bm_bufs_add);
++EXPORT_SYMBOL_GPL(mvneta_bm_construct);
+
+ /* Create pool */
+ static int mvneta_bm_pool_create(struct mvneta_bm *priv,
+@@ -183,8 +118,7 @@ static int mvneta_bm_pool_create(struct
+ struct platform_device *pdev = priv->pdev;
+ u8 target_id, attr;
+ int size_bytes, err;
+-
+- size_bytes = sizeof(u32) * bm_pool->size;
++ size_bytes = sizeof(u32) * bm_pool->hwbm_pool.size;
+ bm_pool->virt_addr = dma_alloc_coherent(&pdev->dev, size_bytes,
+ &bm_pool->phys_addr,
+ GFP_KERNEL);
+@@ -245,11 +179,16 @@ struct mvneta_bm_pool *mvneta_bm_pool_us
+
+ /* Allocate buffers in case BM pool hasn't been used yet */
+ if (new_pool->type == MVNETA_BM_FREE) {
++ struct hwbm_pool *hwbm_pool = &new_pool->hwbm_pool;
++
++ new_pool->priv = priv;
+ new_pool->type = type;
+ new_pool->buf_size = MVNETA_RX_BUF_SIZE(new_pool->pkt_size);
+- new_pool->frag_size =
++ hwbm_pool->frag_size =
+ SKB_DATA_ALIGN(MVNETA_RX_BUF_SIZE(new_pool->pkt_size)) +
+ SKB_DATA_ALIGN(sizeof(struct skb_shared_info));
++ hwbm_pool->construct = mvneta_bm_construct;
++ hwbm_pool->priv = new_pool;
+
+ /* Create new pool */
+ err = mvneta_bm_pool_create(priv, new_pool);
+@@ -260,10 +199,10 @@ struct mvneta_bm_pool *mvneta_bm_pool_us
+ }
+
+ /* Allocate buffers for this pool */
+- num = mvneta_bm_bufs_add(priv, new_pool, new_pool->size);
+- if (num != new_pool->size) {
++ num = hwbm_pool_add(hwbm_pool, hwbm_pool->size, GFP_ATOMIC);
++ if (num != hwbm_pool->size) {
+ WARN(1, "pool %d: %d of %d allocated\n",
+- new_pool->id, num, new_pool->size);
++ new_pool->id, num, hwbm_pool->size);
+ return NULL;
+ }
+ }
+@@ -284,7 +223,7 @@ void mvneta_bm_bufs_free(struct mvneta_b
+
+ mvneta_bm_config_set(priv, MVNETA_BM_EMPTY_LIMIT_MASK);
+
+- for (i = 0; i < bm_pool->buf_num; i++) {
++ for (i = 0; i < bm_pool->hwbm_pool.buf_num; i++) {
+ dma_addr_t buf_phys_addr;
+ u32 *vaddr;
+
+@@ -303,13 +242,13 @@ void mvneta_bm_bufs_free(struct mvneta_b
+
+ dma_unmap_single(&priv->pdev->dev, buf_phys_addr,
+ bm_pool->buf_size, DMA_FROM_DEVICE);
+- mvneta_frag_free(bm_pool->frag_size, vaddr);
++ hwbm_buf_free(&bm_pool->hwbm_pool, vaddr);
+ }
+
+ mvneta_bm_config_clear(priv, MVNETA_BM_EMPTY_LIMIT_MASK);
+
+ /* Update BM driver with number of buffers removed from pool */
+- bm_pool->buf_num -= i;
++ bm_pool->hwbm_pool.buf_num -= i;
+ }
+ EXPORT_SYMBOL_GPL(mvneta_bm_bufs_free);
+
+@@ -317,6 +256,7 @@ EXPORT_SYMBOL_GPL(mvneta_bm_bufs_free);
+ void mvneta_bm_pool_destroy(struct mvneta_bm *priv,
+ struct mvneta_bm_pool *bm_pool, u8 port_map)
+ {
++ struct hwbm_pool *hwbm_pool = &bm_pool->hwbm_pool;
+ bm_pool->port_map &= ~port_map;
+ if (bm_pool->port_map)
+ return;
+@@ -324,11 +264,12 @@ void mvneta_bm_pool_destroy(struct mvnet
+ bm_pool->type = MVNETA_BM_FREE;
+
+ mvneta_bm_bufs_free(priv, bm_pool, port_map);
+- if (bm_pool->buf_num)
++ if (hwbm_pool->buf_num)
+ WARN(1, "cannot free all buffers in pool %d\n", bm_pool->id);
+
+ if (bm_pool->virt_addr) {
+- dma_free_coherent(&priv->pdev->dev, sizeof(u32) * bm_pool->size,
++ dma_free_coherent(&priv->pdev->dev,
++ sizeof(u32) * hwbm_pool->size,
+ bm_pool->virt_addr, bm_pool->phys_addr);
+ bm_pool->virt_addr = NULL;
+ }
+@@ -381,10 +322,10 @@ static void mvneta_bm_pools_init(struct
+ MVNETA_BM_POOL_CAP_ALIGN));
+ size = ALIGN(size, MVNETA_BM_POOL_CAP_ALIGN);
+ }
+- bm_pool->size = size;
++ bm_pool->hwbm_pool.size = size;
+
+ mvneta_bm_write(priv, MVNETA_BM_POOL_SIZE_REG(i),
+- bm_pool->size);
++ bm_pool->hwbm_pool.size);
+
+ /* Obtain custom pkt_size from DT */
+ sprintf(prop, "pool%d,pkt-size", i);
+--- a/drivers/net/ethernet/marvell/mvneta_bm.h
++++ b/drivers/net/ethernet/marvell/mvneta_bm.h
+@@ -108,20 +108,15 @@ struct mvneta_bm {
+ };
+
+ struct mvneta_bm_pool {
++ struct hwbm_pool hwbm_pool;
+ /* Pool number in the range 0-3 */
+ u8 id;
+ enum mvneta_bm_type type;
+
+- /* Buffer Pointers Pool External (BPPE) size in number of bytes */
+- int size;
+- /* Number of buffers used by this pool */
+- int buf_num;
+- /* Pool buffer size */
+- int buf_size;
+ /* Packet size */
+ int pkt_size;
+- /* Single frag size */
+- u32 frag_size;
++ /* Size of the buffer acces through DMA*/
++ u32 buf_size;
+
+ /* BPPE virtual base address */
+ u32 *virt_addr;
+@@ -143,8 +138,7 @@ void mvneta_bm_pool_destroy(struct mvnet
+ struct mvneta_bm_pool *bm_pool, u8 port_map);
+ void mvneta_bm_bufs_free(struct mvneta_bm *priv, struct mvneta_bm_pool *bm_pool,
+ u8 port_map);
+-int mvneta_bm_bufs_add(struct mvneta_bm *priv, struct mvneta_bm_pool *bm_pool,
+- int buf_num);
++int mvneta_bm_construct(struct hwbm_pool *hwbm_pool, void *buf);
+ int mvneta_bm_pool_refill(struct mvneta_bm *priv,
+ struct mvneta_bm_pool *bm_pool);
+ struct mvneta_bm_pool *mvneta_bm_pool_use(struct mvneta_bm *priv, u8 pool_id,
+@@ -170,8 +164,7 @@ void mvneta_bm_pool_destroy(struct mvnet
+ struct mvneta_bm_pool *bm_pool, u8 port_map) {}
+ void mvneta_bm_bufs_free(struct mvneta_bm *priv, struct mvneta_bm_pool *bm_pool,
+ u8 port_map) {}
+-int mvneta_bm_bufs_add(struct mvneta_bm *priv, struct mvneta_bm_pool *bm_pool,
+- int buf_num) { return 0; }
++int mvneta_bm_construct(struct hwbm_pool *hwbm_pool, void *buf) { return 0; }
+ int mvneta_bm_pool_refill(struct mvneta_bm *priv,
+ struct mvneta_bm_pool *bm_pool) {return 0; }
+ struct mvneta_bm_pool *mvneta_bm_pool_use(struct mvneta_bm *priv, u8 pool_id,
diff --git a/target/linux/mvebu/patches-4.4/047-net-mvneta-Fix-spinlock-usage.patch b/target/linux/mvebu/patches-4.4/047-net-mvneta-Fix-spinlock-usage.patch
new file mode 100644
index 0000000000..a8e78df2e9
--- /dev/null
+++ b/target/linux/mvebu/patches-4.4/047-net-mvneta-Fix-spinlock-usage.patch
@@ -0,0 +1,52 @@
+From: Gregory CLEMENT <gregory.clement@free-electrons.com>
+Date: Sat, 12 Mar 2016 18:44:17 +0100
+Subject: [PATCH] net: mvneta: Fix spinlock usage
+
+In the previous patch, the spinlock was not initialized. While it didn't
+cause any trouble yet it could be a problem to use it uninitialized.
+
+The most annoying part was the critical section protected by the spinlock
+in mvneta_stop(). Some of the functions could sleep as pointed when
+activated CONFIG_DEBUG_ATOMIC_SLEEP. Actually, in mvneta_stop() we only
+need to protect the is_stopped flagged, indeed the code of the notifier
+for CPU online is protected by the same spinlock, so when we get the
+lock, the notifer work is done.
+
+Reported-by: Patrick Uiterwijk <patrick@puiterwijk.org>
+Signed-off-by: Gregory CLEMENT <gregory.clement@free-electrons.com>
+Signed-off-by: David S. Miller <davem@davemloft.net>
+---
+
+--- a/drivers/net/ethernet/marvell/mvneta.c
++++ b/drivers/net/ethernet/marvell/mvneta.c
+@@ -3484,17 +3484,17 @@ static int mvneta_stop(struct net_device
+ struct mvneta_port *pp = netdev_priv(dev);
+
+ /* Inform that we are stopping so we don't want to setup the
+- * driver for new CPUs in the notifiers
++ * driver for new CPUs in the notifiers. The code of the
++ * notifier for CPU online is protected by the same spinlock,
++ * so when we get the lock, the notifer work is done.
+ */
+ spin_lock(&pp->lock);
+ pp->is_stopped = true;
++ spin_unlock(&pp->lock);
++
+ mvneta_stop_dev(pp);
+ mvneta_mdio_remove(pp);
+ unregister_cpu_notifier(&pp->cpu_notifier);
+- /* Now that the notifier are unregistered, we can release le
+- * lock
+- */
+- spin_unlock(&pp->lock);
+ on_each_cpu(mvneta_percpu_disable, pp, true);
+ free_percpu_irq(dev->irq, pp->ports);
+ mvneta_cleanup_rxqs(pp);
+@@ -4027,6 +4027,7 @@ static int mvneta_probe(struct platform_
+ dev->ethtool_ops = &mvneta_eth_tool_ops;
+
+ pp = netdev_priv(dev);
++ spin_lock_init(&pp->lock);
+ pp->phy_node = phy_node;
+ pp->phy_interface = phy_mode;
+
diff --git a/target/linux/mvebu/patches-4.4/048-net-mvneta-fix-error-messages-in-mvneta_port_down-fu.patch b/target/linux/mvebu/patches-4.4/048-net-mvneta-fix-error-messages-in-mvneta_port_down-fu.patch
new file mode 100644
index 0000000000..fd1f1ae203
--- /dev/null
+++ b/target/linux/mvebu/patches-4.4/048-net-mvneta-fix-error-messages-in-mvneta_port_down-fu.patch
@@ -0,0 +1,33 @@
+From: Dmitri Epshtein <dima@marvell.com>
+Date: Sat, 12 Mar 2016 18:44:19 +0100
+Subject: [PATCH] net: mvneta: fix error messages in mvneta_port_down function
+
+This commit corrects error printing when shutting down the port.
+
+[gregory.clement@free-electrons.com: split initial commit in two
+individual changes]
+Signed-off-by: Dmitri Epshtein <dima@marvell.com>
+Signed-off-by: Gregory CLEMENT <gregory.clement@free-electrons.com>
+Signed-off-by: David S. Miller <davem@davemloft.net>
+---
+
+--- a/drivers/net/ethernet/marvell/mvneta.c
++++ b/drivers/net/ethernet/marvell/mvneta.c
+@@ -1105,7 +1105,7 @@ static void mvneta_port_down(struct mvne
+ do {
+ if (count++ >= MVNETA_RX_DISABLE_TIMEOUT_MSEC) {
+ netdev_warn(pp->dev,
+- "TIMEOUT for RX stopped ! rx_queue_cmd: 0x08%x\n",
++ "TIMEOUT for RX stopped ! rx_queue_cmd: 0x%08x\n",
+ val);
+ break;
+ }
+@@ -1144,7 +1144,7 @@ static void mvneta_port_down(struct mvne
+ do {
+ if (count++ >= MVNETA_TX_FIFO_EMPTY_TIMEOUT) {
+ netdev_warn(pp->dev,
+- "TX FIFO empty timeout status=0x08%x\n",
++ "TX FIFO empty timeout status=0x%08x\n",
+ val);
+ break;
+ }
diff --git a/target/linux/mvebu/patches-4.4/049-net-mvneta-replace-MVNETA_CPU_D_CACHE_LINE_SIZE-with.patch b/target/linux/mvebu/patches-4.4/049-net-mvneta-replace-MVNETA_CPU_D_CACHE_LINE_SIZE-with.patch
new file mode 100644
index 0000000000..c12d98a4e2
--- /dev/null
+++ b/target/linux/mvebu/patches-4.4/049-net-mvneta-replace-MVNETA_CPU_D_CACHE_LINE_SIZE-with.patch
@@ -0,0 +1,56 @@
+From: Jisheng Zhang <jszhang@marvell.com>
+Date: Wed, 30 Mar 2016 19:55:21 +0800
+Subject: [PATCH] net: mvneta: replace MVNETA_CPU_D_CACHE_LINE_SIZE with
+ L1_CACHE_BYTES
+
+The mvneta is also used in some Marvell berlin family SoCs which may
+have 64bytes cacheline size. Replace the MVNETA_CPU_D_CACHE_LINE_SIZE
+usage with L1_CACHE_BYTES.
+
+And since dma_alloc_coherent() is always cacheline size aligned, so
+remove the align checks.
+
+Signed-off-by: Jisheng Zhang <jszhang@marvell.com>
+Signed-off-by: David S. Miller <davem@davemloft.net>
+---
+
+--- a/drivers/net/ethernet/marvell/mvneta.c
++++ b/drivers/net/ethernet/marvell/mvneta.c
+@@ -260,7 +260,6 @@
+
+ #define MVNETA_VLAN_TAG_LEN 4
+
+-#define MVNETA_CPU_D_CACHE_LINE_SIZE 32
+ #define MVNETA_TX_CSUM_DEF_SIZE 1600
+ #define MVNETA_TX_CSUM_MAX_SIZE 9800
+ #define MVNETA_ACC_MODE_EXT1 1
+@@ -300,7 +299,7 @@
+ #define MVNETA_RX_PKT_SIZE(mtu) \
+ ALIGN((mtu) + MVNETA_MH_SIZE + MVNETA_VLAN_TAG_LEN + \
+ ETH_HLEN + ETH_FCS_LEN, \
+- MVNETA_CPU_D_CACHE_LINE_SIZE)
++ L1_CACHE_BYTES)
+
+ #define IS_TSO_HEADER(txq, addr) \
+ ((addr >= txq->tso_hdrs_phys) && \
+@@ -2762,9 +2761,6 @@ static int mvneta_rxq_init(struct mvneta
+ if (rxq->descs == NULL)
+ return -ENOMEM;
+
+- BUG_ON(rxq->descs !=
+- PTR_ALIGN(rxq->descs, MVNETA_CPU_D_CACHE_LINE_SIZE));
+-
+ rxq->last_desc = rxq->size - 1;
+
+ /* Set Rx descriptors queue starting address */
+@@ -2835,10 +2831,6 @@ static int mvneta_txq_init(struct mvneta
+ if (txq->descs == NULL)
+ return -ENOMEM;
+
+- /* Make sure descriptor address is cache line size aligned */
+- BUG_ON(txq->descs !=
+- PTR_ALIGN(txq->descs, MVNETA_CPU_D_CACHE_LINE_SIZE));
+-
+ txq->last_desc = txq->size - 1;
+
+ /* Set maximum bandwidth for enabled TXQs */
diff --git a/target/linux/mvebu/patches-4.4/050-net-mvneta-fix-changing-MTU-when-using-per-cpu-proce.patch b/target/linux/mvebu/patches-4.4/050-net-mvneta-fix-changing-MTU-when-using-per-cpu-proce.patch
new file mode 100644
index 0000000000..07862008a7
--- /dev/null
+++ b/target/linux/mvebu/patches-4.4/050-net-mvneta-fix-changing-MTU-when-using-per-cpu-proce.patch
@@ -0,0 +1,75 @@
+From: Marcin Wojtas <mw@semihalf.com>
+Date: Fri, 1 Apr 2016 15:21:18 +0200
+Subject: [PATCH] net: mvneta: fix changing MTU when using per-cpu processing
+
+After enabling per-cpu processing it appeared that under heavy load
+changing MTU can result in blocking all port's interrupts and
+transmitting data is not possible after the change.
+
+This commit fixes above issue by disabling percpu interrupts for the
+time, when TXQs and RXQs are reconfigured.
+
+Signed-off-by: Marcin Wojtas <mw@semihalf.com>
+Signed-off-by: David S. Miller <davem@davemloft.net>
+---
+
+--- a/drivers/net/ethernet/marvell/mvneta.c
++++ b/drivers/net/ethernet/marvell/mvneta.c
+@@ -3040,6 +3040,20 @@ static int mvneta_check_mtu_valid(struct
+ return mtu;
+ }
+
++static void mvneta_percpu_enable(void *arg)
++{
++ struct mvneta_port *pp = arg;
++
++ enable_percpu_irq(pp->dev->irq, IRQ_TYPE_NONE);
++}
++
++static void mvneta_percpu_disable(void *arg)
++{
++ struct mvneta_port *pp = arg;
++
++ disable_percpu_irq(pp->dev->irq);
++}
++
+ /* Change the device mtu */
+ static int mvneta_change_mtu(struct net_device *dev, int mtu)
+ {
+@@ -3064,6 +3078,7 @@ static int mvneta_change_mtu(struct net_
+ * reallocation of the queues
+ */
+ mvneta_stop_dev(pp);
++ on_each_cpu(mvneta_percpu_disable, pp, true);
+
+ mvneta_cleanup_txqs(pp);
+ mvneta_cleanup_rxqs(pp);
+@@ -3087,6 +3102,7 @@ static int mvneta_change_mtu(struct net_
+ return ret;
+ }
+
++ on_each_cpu(mvneta_percpu_enable, pp, true);
+ mvneta_start_dev(pp);
+ mvneta_port_up(pp);
+
+@@ -3240,20 +3256,6 @@ static void mvneta_mdio_remove(struct mv
+ pp->phy_dev = NULL;
+ }
+
+-static void mvneta_percpu_enable(void *arg)
+-{
+- struct mvneta_port *pp = arg;
+-
+- enable_percpu_irq(pp->dev->irq, IRQ_TYPE_NONE);
+-}
+-
+-static void mvneta_percpu_disable(void *arg)
+-{
+- struct mvneta_port *pp = arg;
+-
+- disable_percpu_irq(pp->dev->irq);
+-}
+-
+ /* Electing a CPU must be done in an atomic way: it should be done
+ * after or before the removal/insertion of a CPU and this function is
+ * not reentrant.
diff --git a/target/linux/mvebu/patches-4.4/051-ARM-dts-armada-38x-add-buffer-manager-nodes.patch b/target/linux/mvebu/patches-4.4/051-ARM-dts-armada-38x-add-buffer-manager-nodes.patch
new file mode 100644
index 0000000000..b56de94e3d
--- /dev/null
+++ b/target/linux/mvebu/patches-4.4/051-ARM-dts-armada-38x-add-buffer-manager-nodes.patch
@@ -0,0 +1,53 @@
+From: Marcin Wojtas <mw@semihalf.com>
+Date: Mon, 14 Mar 2016 09:38:57 +0100
+Subject: [PATCH] ARM: dts: armada-38x: add buffer manager nodes
+
+Armada 38x network controller supports hardware buffer management (BM).
+Since it is now enabled in mvneta driver, appropriate nodes can be added
+to armada-38x.dtsi - for the actual common BM unit (bm@c8000) and its
+internal SRAM (bm-bppi), which is used for indirect access to buffer
+pointer ring residing in DRAM.
+
+Pools - ports mapping, bm-bppi entry in 'soc' node's ranges and optional
+parameters are supposed to be set in board files.
+
+Signed-off-by: Marcin Wojtas <mw@semihalf.com>
+Signed-off-by: Gregory CLEMENT <gregory.clement@free-electrons.com>
+Signed-off-by: David S. Miller <davem@davemloft.net>
+---
+
+--- a/arch/arm/boot/dts/armada-38x.dtsi
++++ b/arch/arm/boot/dts/armada-38x.dtsi
+@@ -540,6 +540,14 @@
+ status = "disabled";
+ };
+
++ bm: bm@c8000 {
++ compatible = "marvell,armada-380-neta-bm";
++ reg = <0xc8000 0xac>;
++ clocks = <&gateclk 13>;
++ internal-mem = <&bm_bppi>;
++ status = "disabled";
++ };
++
+ sata@e0000 {
+ compatible = "marvell,armada-380-ahci";
+ reg = <0xe0000 0x2000>;
+@@ -618,6 +626,17 @@
+ #size-cells = <1>;
+ ranges = <0 MBUS_ID(0x09, 0x15) 0 0x800>;
+ };
++
++ bm_bppi: bm-bppi {
++ compatible = "mmio-sram";
++ reg = <MBUS_ID(0x0c, 0x04) 0 0x100000>;
++ ranges = <0 MBUS_ID(0x0c, 0x04) 0 0x100000>;
++ #address-cells = <1>;
++ #size-cells = <1>;
++ clocks = <&gateclk 13>;
++ no-memory-wc;
++ status = "disabled";
++ };
+ };
+
+ clocks {
diff --git a/target/linux/mvebu/patches-4.4/052-ARM-dts-armada-xp-add-buffer-manager-nodes.patch b/target/linux/mvebu/patches-4.4/052-ARM-dts-armada-xp-add-buffer-manager-nodes.patch
new file mode 100644
index 0000000000..65fafd7101
--- /dev/null
+++ b/target/linux/mvebu/patches-4.4/052-ARM-dts-armada-xp-add-buffer-manager-nodes.patch
@@ -0,0 +1,53 @@
+From: Marcin Wojtas <mw@semihalf.com>
+Date: Mon, 14 Mar 2016 09:38:59 +0100
+Subject: [PATCH] ARM: dts: armada-xp: add buffer manager nodes
+
+Armada XP network controller supports hardware buffer management (BM).
+Since it is now enabled in mvneta driver, appropriate nodes can be added
+to armada-xp.dtsi - for the actual common BM unit (bm@c0000) and its
+internal SRAM (bm-bppi), which is used for indirect access to buffer
+pointer ring residing in DRAM.
+
+Pools - ports mapping, bm-bppi entry in 'soc' node's ranges and optional
+parameters are supposed to be set in board files.
+
+Signed-off-by: Marcin Wojtas <mw@semihalf.com>
+Signed-off-by: Gregory CLEMENT <gregory.clement@free-electrons.com>
+Signed-off-by: David S. Miller <davem@davemloft.net>
+---
+
+--- a/arch/arm/boot/dts/armada-xp.dtsi
++++ b/arch/arm/boot/dts/armada-xp.dtsi
+@@ -253,6 +253,14 @@
+ marvell,crypto-sram-size = <0x800>;
+ };
+
++ bm: bm@c0000 {
++ compatible = "marvell,armada-380-neta-bm";
++ reg = <0xc0000 0xac>;
++ clocks = <&gateclk 13>;
++ internal-mem = <&bm_bppi>;
++ status = "disabled";
++ };
++
+ xor@f0900 {
+ compatible = "marvell,orion-xor";
+ reg = <0xF0900 0x100
+@@ -291,6 +299,17 @@
+ #size-cells = <1>;
+ ranges = <0 MBUS_ID(0x09, 0x05) 0 0x800>;
+ };
++
++ bm_bppi: bm-bppi {
++ compatible = "mmio-sram";
++ reg = <MBUS_ID(0x0c, 0x04) 0 0x100000>;
++ ranges = <0 MBUS_ID(0x0c, 0x04) 0 0x100000>;
++ #address-cells = <1>;
++ #size-cells = <1>;
++ clocks = <&gateclk 13>;
++ no-memory-wc;
++ status = "disabled";
++ };
+ };
+
+ clocks {
diff --git a/target/linux/mvebu/patches-4.4/106-enable-bm-on-linksys-devices.patch b/target/linux/mvebu/patches-4.4/106-enable-bm-on-linksys-devices.patch
new file mode 100644
index 0000000000..e80bc39a69
--- /dev/null
+++ b/target/linux/mvebu/patches-4.4/106-enable-bm-on-linksys-devices.patch
@@ -0,0 +1,107 @@
+--- a/arch/arm/boot/dts/armada-385-linksys.dtsi
++++ b/arch/arm/boot/dts/armada-385-linksys.dtsi
+@@ -59,7 +59,8 @@
+ ranges = <MBUS_ID(0xf0, 0x01) 0 0xf1000000 0x100000
+ MBUS_ID(0x01, 0x1d) 0 0xfff00000 0x100000
+ MBUS_ID(0x09, 0x19) 0 0xf1100000 0x10000
+- MBUS_ID(0x09, 0x15) 0 0xf1110000 0x10000>;
++ MBUS_ID(0x09, 0x15) 0 0xf1110000 0x10000
++ MBUS_ID(0x0c, 0x04) 0 0xf1200000 0x100000>;
+
+ internal-regs {
+
+@@ -93,6 +94,9 @@
+ ethernet@70000 {
+ status = "okay";
+ phy-mode = "rgmii-id";
++ buffer-manager = <&bm>;
++ bm,pool-long = <0>;
++ bm,pool-short = <3>;
+ fixed-link {
+ speed = <1000>;
+ full-duplex;
+@@ -102,6 +106,9 @@
+ ethernet@34000 {
+ status = "okay";
+ phy-mode = "sgmii";
++ buffer-manager = <&bm>;
++ bm,pool-long = <2>;
++ bm,pool-short = <3>;
+ fixed-link {
+ speed = <1000>;
+ full-duplex;
+@@ -112,6 +119,10 @@
+ status = "okay";
+ };
+
++ bm@c8000 {
++ status = "okay";
++ };
++
+ sata@a8000 {
+ status = "okay";
+ };
+@@ -198,6 +209,10 @@
+ };
+ };
+
++ bm-bppi {
++ status = "okay";
++ };
++
+ pcie-controller {
+ status = "okay";
+
+--- a/arch/arm/boot/dts/armada-xp-linksys-mamba.dts
++++ b/arch/arm/boot/dts/armada-xp-linksys-mamba.dts
+@@ -71,7 +71,8 @@
+ ranges = <MBUS_ID(0xf0, 0x01) 0 0 0xf1000000 0x100000
+ MBUS_ID(0x01, 0x1d) 0 0 0xfff00000 0x100000
+ MBUS_ID(0x09, 0x09) 0 0 0xf1100000 0x10000
+- MBUS_ID(0x09, 0x05) 0 0 0xf1110000 0x10000>;
++ MBUS_ID(0x09, 0x05) 0 0 0xf1110000 0x10000
++ MBUS_ID(0x0c, 0x04) 0 0 0xf1200000 0x100000>;
+
+ pcie-controller {
+ status = "okay";
+@@ -205,6 +206,9 @@
+ pinctrl-names = "default";
+ status = "okay";
+ phy-mode = "rgmii-id";
++ buffer-manager = <&bm>;
++ bm,pool-long = <0>;
++ bm,pool-short = <3>;
+ fixed-link {
+ speed = <1000>;
+ full-duplex;
+@@ -216,12 +220,19 @@
+ pinctrl-names = "default";
+ status = "okay";
+ phy-mode = "rgmii-id";
++ buffer-manager = <&bm>;
++ bm,pool-long = <1>;
++ bm,pool-short = <3>;
+ fixed-link {
+ speed = <1000>;
+ full-duplex;
+ };
+ };
+
++ bm@c0000 {
++ status = "okay";
++ };
++
+ /* USB part of the eSATA/USB 2.0 port */
+ usb@50000 {
+ status = "okay";
+@@ -379,6 +390,10 @@
+ };
+ };
+ };
++
++ bm-bppi {
++ status = "okay";
++ };
+ };
+
+ gpio_keys {
diff --git a/target/linux/mvebu/patches-4.4/206-mvebu_wrt1900ac_use_pwm-fan_rather_than_gpio-fan.patch b/target/linux/mvebu/patches-4.4/206-mvebu_wrt1900ac_use_pwm-fan_rather_than_gpio-fan.patch
index 740fdcf8cf..bff58e9b75 100644
--- a/target/linux/mvebu/patches-4.4/206-mvebu_wrt1900ac_use_pwm-fan_rather_than_gpio-fan.patch
+++ b/target/linux/mvebu/patches-4.4/206-mvebu_wrt1900ac_use_pwm-fan_rather_than_gpio-fan.patch
@@ -9,7 +9,7 @@ Signed-off-by: Andrew Lunn <andrew@lunn.ch>
--- a/arch/arm/boot/dts/armada-xp-linksys-mamba.dts
+++ b/arch/arm/boot/dts/armada-xp-linksys-mamba.dts
-@@ -414,13 +414,11 @@
+@@ -428,13 +428,11 @@
};
};