Re: Linux 4.9.116

From: Greg KH
Date: Sat Jul 28 2018 - 02:26:30 EST


diff --git a/Makefile b/Makefile
index 889c58e39928..a6b011778960 100644
--- a/Makefile
+++ b/Makefile
@@ -1,6 +1,6 @@
VERSION = 4
PATCHLEVEL = 9
-SUBLEVEL = 115
+SUBLEVEL = 116
EXTRAVERSION =
NAME = Roaring Lionus

@@ -635,6 +635,7 @@ KBUILD_CFLAGS += $(call cc-disable-warning,frame-address,)
KBUILD_CFLAGS += $(call cc-disable-warning, format-truncation)
KBUILD_CFLAGS += $(call cc-disable-warning, format-overflow)
KBUILD_CFLAGS += $(call cc-disable-warning, int-in-bool-context)
+KBUILD_CFLAGS += $(call cc-disable-warning, attribute-alias)

ifdef CONFIG_LD_DEAD_CODE_DATA_ELIMINATION
KBUILD_CFLAGS += $(call cc-option,-ffunction-sections,)
diff --git a/arch/mips/ath79/common.c b/arch/mips/ath79/common.c
index d071a3a0f876..fc97a11c41c5 100644
--- a/arch/mips/ath79/common.c
+++ b/arch/mips/ath79/common.c
@@ -58,7 +58,7 @@ EXPORT_SYMBOL_GPL(ath79_ddr_ctrl_init);

void ath79_ddr_wb_flush(u32 reg)
{
- void __iomem *flush_reg = ath79_ddr_wb_flush_base + reg;
+ void __iomem *flush_reg = ath79_ddr_wb_flush_base + (reg * 4);

/* Flush the DDR write buffer. */
__raw_writel(0x1, flush_reg);
diff --git a/arch/mips/pci/pci.c b/arch/mips/pci/pci.c
index f6325fa657fb..64ae8c094a54 100644
--- a/arch/mips/pci/pci.c
+++ b/arch/mips/pci/pci.c
@@ -55,7 +55,7 @@ void pci_resource_to_user(const struct pci_dev *dev, int bar,
phys_addr_t size = resource_size(rsrc);

*start = fixup_bigphys_addr(rsrc->start, size);
- *end = rsrc->start + size;
+ *end = rsrc->start + size - 1;
}

int pci_mmap_page_range(struct pci_dev *dev, struct vm_area_struct *vma,
diff --git a/drivers/base/dd.c b/drivers/base/dd.c
index d76cd97a98b6..ee25a69630c3 100644
--- a/drivers/base/dd.c
+++ b/drivers/base/dd.c
@@ -363,14 +363,6 @@ static int really_probe(struct device *dev, struct device_driver *drv)
goto probe_failed;
}

- /*
- * Ensure devices are listed in devices_kset in correct order
- * It's important to move Dev to the end of devices_kset before
- * calling .probe, because it could be recursive and parent Dev
- * should always go first
- */
- devices_kset_move_last(dev);
-
if (dev->bus->probe) {
ret = dev->bus->probe(dev);
if (ret)
diff --git a/drivers/net/can/xilinx_can.c b/drivers/net/can/xilinx_can.c
index c71a03593595..e680bab27dd7 100644
--- a/drivers/net/can/xilinx_can.c
+++ b/drivers/net/can/xilinx_can.c
@@ -2,6 +2,7 @@
*
* Copyright (C) 2012 - 2014 Xilinx, Inc.
* Copyright (C) 2009 PetaLogix. All rights reserved.
+ * Copyright (C) 2017 Sandvik Mining and Construction Oy
*
* Description:
* This driver is developed for Axi CAN IP and for Zynq CANPS Controller.
@@ -25,8 +26,10 @@
#include <linux/module.h>
#include <linux/netdevice.h>
#include <linux/of.h>
+#include <linux/of_device.h>
#include <linux/platform_device.h>
#include <linux/skbuff.h>
+#include <linux/spinlock.h>
#include <linux/string.h>
#include <linux/types.h>
#include <linux/can/dev.h>
@@ -101,7 +104,7 @@ enum xcan_reg {
#define XCAN_INTR_ALL (XCAN_IXR_TXOK_MASK | XCAN_IXR_BSOFF_MASK |\
XCAN_IXR_WKUP_MASK | XCAN_IXR_SLP_MASK | \
XCAN_IXR_RXNEMP_MASK | XCAN_IXR_ERROR_MASK | \
- XCAN_IXR_ARBLST_MASK | XCAN_IXR_RXOK_MASK)
+ XCAN_IXR_RXOFLW_MASK | XCAN_IXR_ARBLST_MASK)

/* CAN register bit shift - XCAN_<REG>_<BIT>_SHIFT */
#define XCAN_BTR_SJW_SHIFT 7 /* Synchronous jump width */
@@ -118,6 +121,7 @@ enum xcan_reg {
/**
* struct xcan_priv - This definition define CAN driver instance
* @can: CAN private data structure.
+ * @tx_lock: Lock for synchronizing TX interrupt handling
* @tx_head: Tx CAN packets ready to send on the queue
* @tx_tail: Tx CAN packets successfully sended on the queue
* @tx_max: Maximum number packets the driver can send
@@ -132,6 +136,7 @@ enum xcan_reg {
*/
struct xcan_priv {
struct can_priv can;
+ spinlock_t tx_lock;
unsigned int tx_head;
unsigned int tx_tail;
unsigned int tx_max;
@@ -159,6 +164,11 @@ static const struct can_bittiming_const xcan_bittiming_const = {
.brp_inc = 1,
};

+#define XCAN_CAP_WATERMARK 0x0001
+struct xcan_devtype_data {
+ unsigned int caps;
+};
+
/**
* xcan_write_reg_le - Write a value to the device register little endian
* @priv: Driver private data structure
@@ -238,6 +248,10 @@ static int set_reset_mode(struct net_device *ndev)
usleep_range(500, 10000);
}

+ /* reset clears FIFOs */
+ priv->tx_head = 0;
+ priv->tx_tail = 0;
+
return 0;
}

@@ -392,6 +406,7 @@ static int xcan_start_xmit(struct sk_buff *skb, struct net_device *ndev)
struct net_device_stats *stats = &ndev->stats;
struct can_frame *cf = (struct can_frame *)skb->data;
u32 id, dlc, data[2] = {0, 0};
+ unsigned long flags;

if (can_dropped_invalid_skb(ndev, skb))
return NETDEV_TX_OK;
@@ -439,6 +454,9 @@ static int xcan_start_xmit(struct sk_buff *skb, struct net_device *ndev)
data[1] = be32_to_cpup((__be32 *)(cf->data + 4));

can_put_echo_skb(skb, ndev, priv->tx_head % priv->tx_max);
+
+ spin_lock_irqsave(&priv->tx_lock, flags);
+
priv->tx_head++;

/* Write the Frame to Xilinx CAN TX FIFO */
@@ -454,10 +472,16 @@ static int xcan_start_xmit(struct sk_buff *skb, struct net_device *ndev)
stats->tx_bytes += cf->can_dlc;
}

+ /* Clear TX-FIFO-empty interrupt for xcan_tx_interrupt() */
+ if (priv->tx_max > 1)
+ priv->write_reg(priv, XCAN_ICR_OFFSET, XCAN_IXR_TXFEMP_MASK);
+
/* Check if the TX buffer is full */
if ((priv->tx_head - priv->tx_tail) == priv->tx_max)
netif_stop_queue(ndev);

+ spin_unlock_irqrestore(&priv->tx_lock, flags);
+
return NETDEV_TX_OK;
}

@@ -529,6 +553,123 @@ static int xcan_rx(struct net_device *ndev)
return 1;
}

+/**
+ * xcan_current_error_state - Get current error state from HW
+ * @ndev: Pointer to net_device structure
+ *
+ * Checks the current CAN error state from the HW. Note that this
+ * only checks for ERROR_PASSIVE and ERROR_WARNING.
+ *
+ * Return:
+ * ERROR_PASSIVE or ERROR_WARNING if either is active, ERROR_ACTIVE
+ * otherwise.
+ */
+static enum can_state xcan_current_error_state(struct net_device *ndev)
+{
+ struct xcan_priv *priv = netdev_priv(ndev);
+ u32 status = priv->read_reg(priv, XCAN_SR_OFFSET);
+
+ if ((status & XCAN_SR_ESTAT_MASK) == XCAN_SR_ESTAT_MASK)
+ return CAN_STATE_ERROR_PASSIVE;
+ else if (status & XCAN_SR_ERRWRN_MASK)
+ return CAN_STATE_ERROR_WARNING;
+ else
+ return CAN_STATE_ERROR_ACTIVE;
+}
+
+/**
+ * xcan_set_error_state - Set new CAN error state
+ * @ndev: Pointer to net_device structure
+ * @new_state: The new CAN state to be set
+ * @cf: Error frame to be populated or NULL
+ *
+ * Set new CAN error state for the device, updating statistics and
+ * populating the error frame if given.
+ */
+static void xcan_set_error_state(struct net_device *ndev,
+ enum can_state new_state,
+ struct can_frame *cf)
+{
+ struct xcan_priv *priv = netdev_priv(ndev);
+ u32 ecr = priv->read_reg(priv, XCAN_ECR_OFFSET);
+ u32 txerr = ecr & XCAN_ECR_TEC_MASK;
+ u32 rxerr = (ecr & XCAN_ECR_REC_MASK) >> XCAN_ESR_REC_SHIFT;
+
+ priv->can.state = new_state;
+
+ if (cf) {
+ cf->can_id |= CAN_ERR_CRTL;
+ cf->data[6] = txerr;
+ cf->data[7] = rxerr;
+ }
+
+ switch (new_state) {
+ case CAN_STATE_ERROR_PASSIVE:
+ priv->can.can_stats.error_passive++;
+ if (cf)
+ cf->data[1] = (rxerr > 127) ?
+ CAN_ERR_CRTL_RX_PASSIVE :
+ CAN_ERR_CRTL_TX_PASSIVE;
+ break;
+ case CAN_STATE_ERROR_WARNING:
+ priv->can.can_stats.error_warning++;
+ if (cf)
+ cf->data[1] |= (txerr > rxerr) ?
+ CAN_ERR_CRTL_TX_WARNING :
+ CAN_ERR_CRTL_RX_WARNING;
+ break;
+ case CAN_STATE_ERROR_ACTIVE:
+ if (cf)
+ cf->data[1] |= CAN_ERR_CRTL_ACTIVE;
+ break;
+ default:
+ /* non-ERROR states are handled elsewhere */
+ WARN_ON(1);
+ break;
+ }
+}
+
+/**
+ * xcan_update_error_state_after_rxtx - Update CAN error state after RX/TX
+ * @ndev: Pointer to net_device structure
+ *
+ * If the device is in a ERROR-WARNING or ERROR-PASSIVE state, check if
+ * the performed RX/TX has caused it to drop to a lesser state and set
+ * the interface state accordingly.
+ */
+static void xcan_update_error_state_after_rxtx(struct net_device *ndev)
+{
+ struct xcan_priv *priv = netdev_priv(ndev);
+ enum can_state old_state = priv->can.state;
+ enum can_state new_state;
+
+ /* changing error state due to successful frame RX/TX can only
+ * occur from these states
+ */
+ if (old_state != CAN_STATE_ERROR_WARNING &&
+ old_state != CAN_STATE_ERROR_PASSIVE)
+ return;
+
+ new_state = xcan_current_error_state(ndev);
+
+ if (new_state != old_state) {
+ struct sk_buff *skb;
+ struct can_frame *cf;
+
+ skb = alloc_can_err_skb(ndev, &cf);
+
+ xcan_set_error_state(ndev, new_state, skb ? cf : NULL);
+
+ if (skb) {
+ struct net_device_stats *stats = &ndev->stats;
+
+ stats->rx_packets++;
+ stats->rx_bytes += cf->can_dlc;
+ netif_rx(skb);
+ }
+ }
+}
+
/**
* xcan_err_interrupt - error frame Isr
* @ndev: net_device pointer
@@ -544,16 +685,12 @@ static void xcan_err_interrupt(struct net_device *ndev, u32 isr)
struct net_device_stats *stats = &ndev->stats;
struct can_frame *cf;
struct sk_buff *skb;
- u32 err_status, status, txerr = 0, rxerr = 0;
+ u32 err_status;

skb = alloc_can_err_skb(ndev, &cf);

err_status = priv->read_reg(priv, XCAN_ESR_OFFSET);
priv->write_reg(priv, XCAN_ESR_OFFSET, err_status);
- txerr = priv->read_reg(priv, XCAN_ECR_OFFSET) & XCAN_ECR_TEC_MASK;
- rxerr = ((priv->read_reg(priv, XCAN_ECR_OFFSET) &
- XCAN_ECR_REC_MASK) >> XCAN_ESR_REC_SHIFT);
- status = priv->read_reg(priv, XCAN_SR_OFFSET);

if (isr & XCAN_IXR_BSOFF_MASK) {
priv->can.state = CAN_STATE_BUS_OFF;
@@ -563,28 +700,10 @@ static void xcan_err_interrupt(struct net_device *ndev, u32 isr)
can_bus_off(ndev);
if (skb)
cf->can_id |= CAN_ERR_BUSOFF;
- } else if ((status & XCAN_SR_ESTAT_MASK) == XCAN_SR_ESTAT_MASK) {
- priv->can.state = CAN_STATE_ERROR_PASSIVE;
- priv->can.can_stats.error_passive++;
- if (skb) {
- cf->can_id |= CAN_ERR_CRTL;
- cf->data[1] = (rxerr > 127) ?
- CAN_ERR_CRTL_RX_PASSIVE :
- CAN_ERR_CRTL_TX_PASSIVE;
- cf->data[6] = txerr;
- cf->data[7] = rxerr;
- }
- } else if (status & XCAN_SR_ERRWRN_MASK) {
- priv->can.state = CAN_STATE_ERROR_WARNING;
- priv->can.can_stats.error_warning++;
- if (skb) {
- cf->can_id |= CAN_ERR_CRTL;
- cf->data[1] |= (txerr > rxerr) ?
- CAN_ERR_CRTL_TX_WARNING :
- CAN_ERR_CRTL_RX_WARNING;
- cf->data[6] = txerr;
- cf->data[7] = rxerr;
- }
+ } else {
+ enum can_state new_state = xcan_current_error_state(ndev);
+
+ xcan_set_error_state(ndev, new_state, skb ? cf : NULL);
}

/* Check for Arbitration lost interrupt */
@@ -600,7 +719,6 @@ static void xcan_err_interrupt(struct net_device *ndev, u32 isr)
if (isr & XCAN_IXR_RXOFLW_MASK) {
stats->rx_over_errors++;
stats->rx_errors++;
- priv->write_reg(priv, XCAN_SRR_OFFSET, XCAN_SRR_RESET_MASK);
if (skb) {
cf->can_id |= CAN_ERR_CRTL;
cf->data[1] |= CAN_ERR_CRTL_RX_OVERFLOW;
@@ -709,26 +827,20 @@ static int xcan_rx_poll(struct napi_struct *napi, int quota)

isr = priv->read_reg(priv, XCAN_ISR_OFFSET);
while ((isr & XCAN_IXR_RXNEMP_MASK) && (work_done < quota)) {
- if (isr & XCAN_IXR_RXOK_MASK) {
- priv->write_reg(priv, XCAN_ICR_OFFSET,
- XCAN_IXR_RXOK_MASK);
- work_done += xcan_rx(ndev);
- } else {
- priv->write_reg(priv, XCAN_ICR_OFFSET,
- XCAN_IXR_RXNEMP_MASK);
- break;
- }
+ work_done += xcan_rx(ndev);
priv->write_reg(priv, XCAN_ICR_OFFSET, XCAN_IXR_RXNEMP_MASK);
isr = priv->read_reg(priv, XCAN_ISR_OFFSET);
}

- if (work_done)
+ if (work_done) {
can_led_event(ndev, CAN_LED_EVENT_RX);
+ xcan_update_error_state_after_rxtx(ndev);
+ }

if (work_done < quota) {
napi_complete(napi);
ier = priv->read_reg(priv, XCAN_IER_OFFSET);
- ier |= (XCAN_IXR_RXOK_MASK | XCAN_IXR_RXNEMP_MASK);
+ ier |= XCAN_IXR_RXNEMP_MASK;
priv->write_reg(priv, XCAN_IER_OFFSET, ier);
}
return work_done;
@@ -743,18 +855,71 @@ static void xcan_tx_interrupt(struct net_device *ndev, u32 isr)
{
struct xcan_priv *priv = netdev_priv(ndev);
struct net_device_stats *stats = &ndev->stats;
+ unsigned int frames_in_fifo;
+ int frames_sent = 1; /* TXOK => at least 1 frame was sent */
+ unsigned long flags;
+ int retries = 0;
+
+ /* Synchronize with xmit as we need to know the exact number
+ * of frames in the FIFO to stay in sync due to the TXFEMP
+ * handling.
+ * This also prevents a race between netif_wake_queue() and
+ * netif_stop_queue().
+ */
+ spin_lock_irqsave(&priv->tx_lock, flags);
+
+ frames_in_fifo = priv->tx_head - priv->tx_tail;
+
+ if (WARN_ON_ONCE(frames_in_fifo == 0)) {
+ /* clear TXOK anyway to avoid getting back here */
+ priv->write_reg(priv, XCAN_ICR_OFFSET, XCAN_IXR_TXOK_MASK);
+ spin_unlock_irqrestore(&priv->tx_lock, flags);
+ return;
+ }
+
+ /* Check if 2 frames were sent (TXOK only means that at least 1
+ * frame was sent).
+ */
+ if (frames_in_fifo > 1) {
+ WARN_ON(frames_in_fifo > priv->tx_max);
+
+ /* Synchronize TXOK and isr so that after the loop:
+ * (1) isr variable is up-to-date at least up to TXOK clear
+ * time. This avoids us clearing a TXOK of a second frame
+ * but not noticing that the FIFO is now empty and thus
+ * marking only a single frame as sent.
+ * (2) No TXOK is left. Having one could mean leaving a
+ * stray TXOK as we might process the associated frame
+ * via TXFEMP handling as we read TXFEMP *after* TXOK
+ * clear to satisfy (1).
+ */
+ while ((isr & XCAN_IXR_TXOK_MASK) && !WARN_ON(++retries == 100)) {
+ priv->write_reg(priv, XCAN_ICR_OFFSET, XCAN_IXR_TXOK_MASK);
+ isr = priv->read_reg(priv, XCAN_ISR_OFFSET);
+ }

- while ((priv->tx_head - priv->tx_tail > 0) &&
- (isr & XCAN_IXR_TXOK_MASK)) {
+ if (isr & XCAN_IXR_TXFEMP_MASK) {
+ /* nothing in FIFO anymore */
+ frames_sent = frames_in_fifo;
+ }
+ } else {
+ /* single frame in fifo, just clear TXOK */
priv->write_reg(priv, XCAN_ICR_OFFSET, XCAN_IXR_TXOK_MASK);
+ }
+
+ while (frames_sent--) {
can_get_echo_skb(ndev, priv->tx_tail %
priv->tx_max);
priv->tx_tail++;
stats->tx_packets++;
- isr = priv->read_reg(priv, XCAN_ISR_OFFSET);
}
- can_led_event(ndev, CAN_LED_EVENT_TX);
+
netif_wake_queue(ndev);
+
+ spin_unlock_irqrestore(&priv->tx_lock, flags);
+
+ can_led_event(ndev, CAN_LED_EVENT_TX);
+ xcan_update_error_state_after_rxtx(ndev);
}

/**
@@ -773,6 +938,7 @@ static irqreturn_t xcan_interrupt(int irq, void *dev_id)
struct net_device *ndev = (struct net_device *)dev_id;
struct xcan_priv *priv = netdev_priv(ndev);
u32 isr, ier;
+ u32 isr_errors;

/* Get the interrupt status from Xilinx CAN */
isr = priv->read_reg(priv, XCAN_ISR_OFFSET);
@@ -791,18 +957,17 @@ static irqreturn_t xcan_interrupt(int irq, void *dev_id)
xcan_tx_interrupt(ndev, isr);

/* Check for the type of error interrupt and Processing it */
- if (isr & (XCAN_IXR_ERROR_MASK | XCAN_IXR_RXOFLW_MASK |
- XCAN_IXR_BSOFF_MASK | XCAN_IXR_ARBLST_MASK)) {
- priv->write_reg(priv, XCAN_ICR_OFFSET, (XCAN_IXR_ERROR_MASK |
- XCAN_IXR_RXOFLW_MASK | XCAN_IXR_BSOFF_MASK |
- XCAN_IXR_ARBLST_MASK));
+ isr_errors = isr & (XCAN_IXR_ERROR_MASK | XCAN_IXR_RXOFLW_MASK |
+ XCAN_IXR_BSOFF_MASK | XCAN_IXR_ARBLST_MASK);
+ if (isr_errors) {
+ priv->write_reg(priv, XCAN_ICR_OFFSET, isr_errors);
xcan_err_interrupt(ndev, isr);
}

/* Check for the type of receive interrupt and Processing it */
- if (isr & (XCAN_IXR_RXNEMP_MASK | XCAN_IXR_RXOK_MASK)) {
+ if (isr & XCAN_IXR_RXNEMP_MASK) {
ier = priv->read_reg(priv, XCAN_IER_OFFSET);
- ier &= ~(XCAN_IXR_RXNEMP_MASK | XCAN_IXR_RXOK_MASK);
+ ier &= ~XCAN_IXR_RXNEMP_MASK;
priv->write_reg(priv, XCAN_IER_OFFSET, ier);
napi_schedule(&priv->napi);
}
@@ -819,13 +984,9 @@ static irqreturn_t xcan_interrupt(int irq, void *dev_id)
static void xcan_chip_stop(struct net_device *ndev)
{
struct xcan_priv *priv = netdev_priv(ndev);
- u32 ier;

/* Disable interrupts and leave the can in configuration mode */
- ier = priv->read_reg(priv, XCAN_IER_OFFSET);
- ier &= ~XCAN_INTR_ALL;
- priv->write_reg(priv, XCAN_IER_OFFSET, ier);
- priv->write_reg(priv, XCAN_SRR_OFFSET, XCAN_SRR_RESET_MASK);
+ set_reset_mode(ndev);
priv->can.state = CAN_STATE_STOPPED;
}

@@ -958,10 +1119,15 @@ static const struct net_device_ops xcan_netdev_ops = {
*/
static int __maybe_unused xcan_suspend(struct device *dev)
{
- if (!device_may_wakeup(dev))
- return pm_runtime_force_suspend(dev);
+ struct net_device *ndev = dev_get_drvdata(dev);

- return 0;
+ if (netif_running(ndev)) {
+ netif_stop_queue(ndev);
+ netif_device_detach(ndev);
+ xcan_chip_stop(ndev);
+ }
+
+ return pm_runtime_force_suspend(dev);
}

/**
@@ -973,11 +1139,27 @@ static int __maybe_unused xcan_suspend(struct device *dev)
*/
static int __maybe_unused xcan_resume(struct device *dev)
{
- if (!device_may_wakeup(dev))
- return pm_runtime_force_resume(dev);
+ struct net_device *ndev = dev_get_drvdata(dev);
+ int ret;

- return 0;
+ ret = pm_runtime_force_resume(dev);
+ if (ret) {
+ dev_err(dev, "pm_runtime_force_resume failed on resume\n");
+ return ret;
+ }
+
+ if (netif_running(ndev)) {
+ ret = xcan_chip_start(ndev);
+ if (ret) {
+ dev_err(dev, "xcan_chip_start failed on resume\n");
+ return ret;
+ }
+
+ netif_device_attach(ndev);
+ netif_start_queue(ndev);
+ }

+ return 0;
}

/**
@@ -992,14 +1174,6 @@ static int __maybe_unused xcan_runtime_suspend(struct device *dev)
struct net_device *ndev = dev_get_drvdata(dev);
struct xcan_priv *priv = netdev_priv(ndev);

- if (netif_running(ndev)) {
- netif_stop_queue(ndev);
- netif_device_detach(ndev);
- }
-
- priv->write_reg(priv, XCAN_MSR_OFFSET, XCAN_MSR_SLEEP_MASK);
- priv->can.state = CAN_STATE_SLEEPING;
-
clk_disable_unprepare(priv->bus_clk);
clk_disable_unprepare(priv->can_clk);

@@ -1018,7 +1192,6 @@ static int __maybe_unused xcan_runtime_resume(struct device *dev)
struct net_device *ndev = dev_get_drvdata(dev);
struct xcan_priv *priv = netdev_priv(ndev);
int ret;
- u32 isr, status;

ret = clk_prepare_enable(priv->bus_clk);
if (ret) {
@@ -1032,27 +1205,6 @@ static int __maybe_unused xcan_runtime_resume(struct device *dev)
return ret;
}

- priv->write_reg(priv, XCAN_SRR_OFFSET, XCAN_SRR_RESET_MASK);
- isr = priv->read_reg(priv, XCAN_ISR_OFFSET);
- status = priv->read_reg(priv, XCAN_SR_OFFSET);
-
- if (netif_running(ndev)) {
- if (isr & XCAN_IXR_BSOFF_MASK) {
- priv->can.state = CAN_STATE_BUS_OFF;
- priv->write_reg(priv, XCAN_SRR_OFFSET,
- XCAN_SRR_RESET_MASK);
- } else if ((status & XCAN_SR_ESTAT_MASK) ==
- XCAN_SR_ESTAT_MASK) {
- priv->can.state = CAN_STATE_ERROR_PASSIVE;
- } else if (status & XCAN_SR_ERRWRN_MASK) {
- priv->can.state = CAN_STATE_ERROR_WARNING;
- } else {
- priv->can.state = CAN_STATE_ERROR_ACTIVE;
- }
- netif_device_attach(ndev);
- netif_start_queue(ndev);
- }
-
return 0;
}

@@ -1061,6 +1213,18 @@ static const struct dev_pm_ops xcan_dev_pm_ops = {
SET_RUNTIME_PM_OPS(xcan_runtime_suspend, xcan_runtime_resume, NULL)
};

+static const struct xcan_devtype_data xcan_zynq_data = {
+ .caps = XCAN_CAP_WATERMARK,
+};
+
+/* Match table for OF platform binding */
+static const struct of_device_id xcan_of_match[] = {
+ { .compatible = "xlnx,zynq-can-1.0", .data = &xcan_zynq_data },
+ { .compatible = "xlnx,axi-can-1.00.a", },
+ { /* end of list */ },
+};
+MODULE_DEVICE_TABLE(of, xcan_of_match);
+
/**
* xcan_probe - Platform registration call
* @pdev: Handle to the platform device structure
@@ -1075,8 +1239,10 @@ static int xcan_probe(struct platform_device *pdev)
struct resource *res; /* IO mem resources */
struct net_device *ndev;
struct xcan_priv *priv;
+ const struct of_device_id *of_id;
+ int caps = 0;
void __iomem *addr;
- int ret, rx_max, tx_max;
+ int ret, rx_max, tx_max, tx_fifo_depth;

/* Get the virtual base address for the device */
res = platform_get_resource(pdev, IORESOURCE_MEM, 0);
@@ -1086,7 +1252,8 @@ static int xcan_probe(struct platform_device *pdev)
goto err;
}

- ret = of_property_read_u32(pdev->dev.of_node, "tx-fifo-depth", &tx_max);
+ ret = of_property_read_u32(pdev->dev.of_node, "tx-fifo-depth",
+ &tx_fifo_depth);
if (ret < 0)
goto err;

@@ -1094,6 +1261,30 @@ static int xcan_probe(struct platform_device *pdev)
if (ret < 0)
goto err;

+ of_id = of_match_device(xcan_of_match, &pdev->dev);
+ if (of_id) {
+ const struct xcan_devtype_data *devtype_data = of_id->data;
+
+ if (devtype_data)
+ caps = devtype_data->caps;
+ }
+
+ /* There is no way to directly figure out how many frames have been
+ * sent when the TXOK interrupt is processed. If watermark programming
+ * is supported, we can have 2 frames in the FIFO and use TXFEMP
+ * to determine if 1 or 2 frames have been sent.
+ * Theoretically we should be able to use TXFWMEMP to determine up
+ * to 3 frames, but it seems that after putting a second frame in the
+ * FIFO, with watermark at 2 frames, it can happen that TXFWMEMP (less
+ * than 2 frames in FIFO) is set anyway with no TXOK (a frame was
+ * sent), which is not a sensible state - possibly TXFWMEMP is not
+ * completely synchronized with the rest of the bits?
+ */
+ if (caps & XCAN_CAP_WATERMARK)
+ tx_max = min(tx_fifo_depth, 2);
+ else
+ tx_max = 1;
+
/* Create a CAN device instance */
ndev = alloc_candev(sizeof(struct xcan_priv), tx_max);
if (!ndev)
@@ -1108,6 +1299,7 @@ static int xcan_probe(struct platform_device *pdev)
CAN_CTRLMODE_BERR_REPORTING;
priv->reg_base = addr;
priv->tx_max = tx_max;
+ spin_lock_init(&priv->tx_lock);

/* Get IRQ for the device */
ndev->irq = platform_get_irq(pdev, 0);
@@ -1172,9 +1364,9 @@ static int xcan_probe(struct platform_device *pdev)

pm_runtime_put(&pdev->dev);

- netdev_dbg(ndev, "reg_base=0x%p irq=%d clock=%d, tx fifo depth:%d\n",
+ netdev_dbg(ndev, "reg_base=0x%p irq=%d clock=%d, tx fifo depth: actual %d, using %d\n",
priv->reg_base, ndev->irq, priv->can.clock.freq,
- priv->tx_max);
+ tx_fifo_depth, priv->tx_max);

return 0;

@@ -1208,14 +1400,6 @@ static int xcan_remove(struct platform_device *pdev)
return 0;
}

-/* Match table for OF platform binding */
-static const struct of_device_id xcan_of_match[] = {
- { .compatible = "xlnx,zynq-can-1.0", },
- { .compatible = "xlnx,axi-can-1.00.a", },
- { /* end of list */ },
-};
-MODULE_DEVICE_TABLE(of, xcan_of_match);
-
static struct platform_driver xcan_driver = {
.probe = xcan_probe,
.remove = xcan_remove,
diff --git a/drivers/net/ethernet/mellanox/mlx4/resource_tracker.c b/drivers/net/ethernet/mellanox/mlx4/resource_tracker.c
index d6b06bef1b69..9d1a7d5ae835 100644
--- a/drivers/net/ethernet/mellanox/mlx4/resource_tracker.c
+++ b/drivers/net/ethernet/mellanox/mlx4/resource_tracker.c
@@ -2916,7 +2916,7 @@ int mlx4_RST2INIT_QP_wrapper(struct mlx4_dev *dev, int slave,
u32 srqn = qp_get_srqn(qpc) & 0xffffff;
int use_srq = (qp_get_srqn(qpc) >> 24) & 1;
struct res_srq *srq;
- int local_qpn = be32_to_cpu(qpc->local_qpn) & 0xffffff;
+ int local_qpn = vhcr->in_modifier & 0xffffff;

err = adjust_qp_sched_queue(dev, slave, qpc, inbox);
if (err)
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_arfs.c b/drivers/net/ethernet/mellanox/mlx5/core/en_arfs.c
index a8cb38789774..4a51fc6908ad 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en_arfs.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en_arfs.c
@@ -383,14 +383,14 @@ static void arfs_may_expire_flow(struct mlx5e_priv *priv)
HLIST_HEAD(del_list);
spin_lock_bh(&priv->fs.arfs.arfs_lock);
mlx5e_for_each_arfs_rule(arfs_rule, htmp, priv->fs.arfs.arfs_tables, i, j) {
- if (quota++ > MLX5E_ARFS_EXPIRY_QUOTA)
- break;
if (!work_pending(&arfs_rule->arfs_work) &&
rps_may_expire_flow(priv->netdev,
arfs_rule->rxq, arfs_rule->flow_id,
arfs_rule->filter_id)) {
hlist_del_init(&arfs_rule->hlist);
hlist_add_head(&arfs_rule->hlist, &del_list);
+ if (quota++ > MLX5E_ARFS_EXPIRY_QUOTA)
+ break;
}
}
spin_unlock_bh(&priv->fs.arfs.arfs_lock);
@@ -715,6 +715,9 @@ int mlx5e_rx_flow_steer(struct net_device *dev, const struct sk_buff *skb,
skb->protocol != htons(ETH_P_IPV6))
return -EPROTONOSUPPORT;

+ if (skb->encapsulation)
+ return -EPROTONOSUPPORT;
+
arfs_t = arfs_get_table(arfs, arfs_get_ip_proto(skb), skb->protocol);
if (!arfs_t)
return -EPROTONOSUPPORT;
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_clock.c b/drivers/net/ethernet/mellanox/mlx5/core/en_clock.c
index 1612ec0d9103..f8b99d0b54d5 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en_clock.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en_clock.c
@@ -233,6 +233,7 @@ static void mlx5e_timestamp_init_config(struct mlx5e_tstamp *tstamp)
void mlx5e_timestamp_init(struct mlx5e_priv *priv)
{
struct mlx5e_tstamp *tstamp = &priv->tstamp;
+ u64 overflow_cycles;
u64 ns;
u64 frac = 0;
u32 dev_freq;
@@ -257,10 +258,17 @@ void mlx5e_timestamp_init(struct mlx5e_priv *priv)

/* Calculate period in seconds to call the overflow watchdog - to make
* sure counter is checked at least once every wrap around.
+ * The period is calculated as the minimum between max HW cycles count
+ * (The clock source mask) and max amount of cycles that can be
+ * multiplied by clock multiplier where the result doesn't exceed
+ * 64bits.
*/
- ns = cyclecounter_cyc2ns(&tstamp->cycles, tstamp->cycles.mask,
+ overflow_cycles = div64_u64(~0ULL >> 1, tstamp->cycles.mult);
+ overflow_cycles = min(overflow_cycles, tstamp->cycles.mask >> 1);
+
+ ns = cyclecounter_cyc2ns(&tstamp->cycles, overflow_cycles,
frac, &frac);
- do_div(ns, NSEC_PER_SEC / 2 / HZ);
+ do_div(ns, NSEC_PER_SEC / HZ);
tstamp->overflow_period = ns;

INIT_DELAYED_WORK(&tstamp->overflow_work, mlx5e_timestamp_overflow);
diff --git a/drivers/net/phy/phy.c b/drivers/net/phy/phy.c
index 4d217649c8b1..5fde8e335f13 100644
--- a/drivers/net/phy/phy.c
+++ b/drivers/net/phy/phy.c
@@ -598,7 +598,7 @@ static int phy_start_aneg_priv(struct phy_device *phydev, bool sync)
* negotiation may already be done and aneg interrupt may not be
* generated.
*/
- if (phy_interrupt_is_valid(phydev) && (phydev->state == PHY_AN)) {
+ if (phydev->irq != PHY_POLL && phydev->state == PHY_AN) {
err = phy_aneg_done(phydev);
if (err > 0) {
trigger = true;
diff --git a/drivers/usb/class/cdc-acm.c b/drivers/usb/class/cdc-acm.c
index 08bef18372ea..a9c950d29ce2 100644
--- a/drivers/usb/class/cdc-acm.c
+++ b/drivers/usb/class/cdc-acm.c
@@ -1785,6 +1785,9 @@ static const struct usb_device_id acm_ids[] = {
{ USB_DEVICE(0x09d8, 0x0320), /* Elatec GmbH TWN3 */
.driver_info = NO_UNION_NORMAL, /* has misplaced union descriptor */
},
+ { USB_DEVICE(0x0ca6, 0xa050), /* Castles VEGA3000 */
+ .driver_info = NO_UNION_NORMAL, /* reports zero length descriptor */
+ },

{ USB_DEVICE(0x2912, 0x0001), /* ATOL FPrint */
.driver_info = CLEAR_HALT_CONDITIONS,
diff --git a/drivers/usb/core/hub.c b/drivers/usb/core/hub.c
index 8bf0090218dd..bdb19db542a4 100644
--- a/drivers/usb/core/hub.c
+++ b/drivers/usb/core/hub.c
@@ -1139,10 +1139,14 @@ static void hub_activate(struct usb_hub *hub, enum hub_activation_type type)

if (!udev || udev->state == USB_STATE_NOTATTACHED) {
/* Tell hub_wq to disconnect the device or
- * check for a new connection
+ * check for a new connection or over current condition.
+ * Based on USB2.0 Spec Section 11.12.5,
+ * C_PORT_OVER_CURRENT could be set while
+ * PORT_OVER_CURRENT is not. So check for any of them.
*/
if (udev || (portstatus & USB_PORT_STAT_CONNECTION) ||
- (portstatus & USB_PORT_STAT_OVERCURRENT))
+ (portstatus & USB_PORT_STAT_OVERCURRENT) ||
+ (portchange & USB_PORT_STAT_C_OVERCURRENT))
set_bit(port1, hub->change_bits);

} else if (portstatus & USB_PORT_STAT_ENABLE) {
diff --git a/drivers/usb/gadget/function/f_fs.c b/drivers/usb/gadget/function/f_fs.c
index af72224f8ba2..04eb64381d92 100644
--- a/drivers/usb/gadget/function/f_fs.c
+++ b/drivers/usb/gadget/function/f_fs.c
@@ -3243,7 +3243,7 @@ static int ffs_func_setup(struct usb_function *f,
__ffs_event_add(ffs, FUNCTIONFS_SETUP);
spin_unlock_irqrestore(&ffs->ev.waitq.lock, flags);

- return USB_GADGET_DELAYED_STATUS;
+ return creq->wLength == 0 ? USB_GADGET_DELAYED_STATUS : 0;
}

static bool ffs_func_req_match(struct usb_function *f,
diff --git a/fs/exec.c b/fs/exec.c
index b8c43be24751..fcd8642ef2d2 100644
--- a/fs/exec.c
+++ b/fs/exec.c
@@ -1228,15 +1228,14 @@ static int de_thread(struct task_struct *tsk)
return -EAGAIN;
}

-char *get_task_comm(char *buf, struct task_struct *tsk)
+char *__get_task_comm(char *buf, size_t buf_size, struct task_struct *tsk)
{
- /* buf must be at least sizeof(tsk->comm) in size */
task_lock(tsk);
- strncpy(buf, tsk->comm, sizeof(tsk->comm));
+ strncpy(buf, tsk->comm, buf_size);
task_unlock(tsk);
return buf;
}
-EXPORT_SYMBOL_GPL(get_task_comm);
+EXPORT_SYMBOL_GPL(__get_task_comm);

/*
* These functions flushes out all traces of the currently running executable
diff --git a/include/linux/sched.h b/include/linux/sched.h
index 5ebef8c86c26..1cc5723a7821 100644
--- a/include/linux/sched.h
+++ b/include/linux/sched.h
@@ -2999,7 +2999,11 @@ static inline void set_task_comm(struct task_struct *tsk, const char *from)
{
__set_task_comm(tsk, from, false);
}
-extern char *get_task_comm(char *to, struct task_struct *tsk);
+extern char *__get_task_comm(char *to, size_t len, struct task_struct *tsk);
+#define get_task_comm(buf, tsk) ({ \
+ BUILD_BUG_ON(sizeof(buf) != TASK_COMM_LEN); \
+ __get_task_comm(buf, sizeof(buf), tsk); \
+})

#ifdef CONFIG_SMP
void scheduler_ipi(void);
diff --git a/include/linux/skbuff.h b/include/linux/skbuff.h
index b048d3d3b327..1f207dd22757 100644
--- a/include/linux/skbuff.h
+++ b/include/linux/skbuff.h
@@ -2982,6 +2982,8 @@ static inline int __skb_grow_rcsum(struct sk_buff *skb, unsigned int len)
return __skb_grow(skb, len);
}

+#define rb_to_skb(rb) rb_entry_safe(rb, struct sk_buff, rbnode)
+
#define skb_queue_walk(queue, skb) \
for (skb = (queue)->next; \
skb != (struct sk_buff *)(queue); \
diff --git a/include/net/tcp.h b/include/net/tcp.h
index 18f029bcb8c7..5d440bb0e409 100644
--- a/include/net/tcp.h
+++ b/include/net/tcp.h
@@ -363,6 +363,7 @@ ssize_t tcp_splice_read(struct socket *sk, loff_t *ppos,
struct pipe_inode_info *pipe, size_t len,
unsigned int flags);

+void tcp_enter_quickack_mode(struct sock *sk);
static inline void tcp_dec_quickack_mode(struct sock *sk,
const unsigned int pkts)
{
@@ -553,6 +554,7 @@ void tcp_send_fin(struct sock *sk);
void tcp_send_active_reset(struct sock *sk, gfp_t priority);
int tcp_send_synack(struct sock *);
void tcp_push_one(struct sock *, unsigned int mss_now);
+void __tcp_send_ack(struct sock *sk, u32 rcv_nxt);
void tcp_send_ack(struct sock *sk);
void tcp_send_delayed_ack(struct sock *sk);
void tcp_send_loss_probe(struct sock *sk);
diff --git a/net/core/rtnetlink.c b/net/core/rtnetlink.c
index f3a0ad14b454..194e844e1021 100644
--- a/net/core/rtnetlink.c
+++ b/net/core/rtnetlink.c
@@ -2339,9 +2339,12 @@ int rtnl_configure_link(struct net_device *dev, const struct ifinfomsg *ifm)
return err;
}

- dev->rtnl_link_state = RTNL_LINK_INITIALIZED;
-
- __dev_notify_flags(dev, old_flags, ~0U);
+ if (dev->rtnl_link_state == RTNL_LINK_INITIALIZED) {
+ __dev_notify_flags(dev, old_flags, 0U);
+ } else {
+ dev->rtnl_link_state = RTNL_LINK_INITIALIZED;
+ __dev_notify_flags(dev, old_flags, ~0U);
+ }
return 0;
}
EXPORT_SYMBOL(rtnl_configure_link);
diff --git a/net/core/skbuff.c b/net/core/skbuff.c
index 8cae7aa4a4ec..84c731aef0d8 100644
--- a/net/core/skbuff.c
+++ b/net/core/skbuff.c
@@ -3253,6 +3253,7 @@ struct sk_buff *skb_segment(struct sk_buff *head_skb,
net_warn_ratelimited(
"skb_segment: too many frags: %u %u\n",
pos, mss);
+ err = -EINVAL;
goto err;
}

@@ -3289,11 +3290,10 @@ struct sk_buff *skb_segment(struct sk_buff *head_skb,

perform_csum_check:
if (!csum) {
- if (skb_has_shared_frag(nskb)) {
- err = __skb_linearize(nskb);
- if (err)
- goto err;
- }
+ if (skb_has_shared_frag(nskb) &&
+ __skb_linearize(nskb))
+ goto err;
+
if (!nskb->remcsum_offload)
nskb->ip_summed = CHECKSUM_NONE;
SKB_GSO_CB(nskb)->csum =
diff --git a/net/ipv4/igmp.c b/net/ipv4/igmp.c
index 7f5fe07d0b13..f2e6e874e4ec 100644
--- a/net/ipv4/igmp.c
+++ b/net/ipv4/igmp.c
@@ -1193,8 +1193,7 @@ static void igmpv3_del_delrec(struct in_device *in_dev, struct ip_mc_list *im)
if (pmc) {
im->interface = pmc->interface;
im->crcount = in_dev->mr_qrv ?: net->ipv4.sysctl_igmp_qrv;
- im->sfmode = pmc->sfmode;
- if (pmc->sfmode == MCAST_INCLUDE) {
+ if (im->sfmode == MCAST_INCLUDE) {
im->tomb = pmc->tomb;
im->sources = pmc->sources;
for (psf = im->sources; psf; psf = psf->sf_next)
diff --git a/net/ipv4/ip_output.c b/net/ipv4/ip_output.c
index 3b1f3bc8becb..100c86f1f547 100644
--- a/net/ipv4/ip_output.c
+++ b/net/ipv4/ip_output.c
@@ -497,6 +497,8 @@ static void ip_copy_metadata(struct sk_buff *to, struct sk_buff *from)
to->dev = from->dev;
to->mark = from->mark;

+ skb_copy_hash(to, from);
+
/* Copy the flags to each fragment. */
IPCB(to)->flags = IPCB(from)->flags;

diff --git a/net/ipv4/ip_sockglue.c b/net/ipv4/ip_sockglue.c
index dd80276a8205..b21e435f428c 100644
--- a/net/ipv4/ip_sockglue.c
+++ b/net/ipv4/ip_sockglue.c
@@ -135,15 +135,18 @@ static void ip_cmsg_recv_dstaddr(struct msghdr *msg, struct sk_buff *skb)
{
struct sockaddr_in sin;
const struct iphdr *iph = ip_hdr(skb);
- __be16 *ports = (__be16 *)skb_transport_header(skb);
+ __be16 *ports;
+ int end;

- if (skb_transport_offset(skb) + 4 > (int)skb->len)
+ end = skb_transport_offset(skb) + 4;
+ if (end > 0 && !pskb_may_pull(skb, end))
return;

/* All current transport protocols have the port numbers in the
* first four bytes of the transport header and this function is
* written with this assumption in mind.
*/
+ ports = (__be16 *)skb_transport_header(skb);

sin.sin_family = AF_INET;
sin.sin_addr.s_addr = iph->daddr;
diff --git a/net/ipv4/tcp_dctcp.c b/net/ipv4/tcp_dctcp.c
index ab37c6775630..dd52ccb812ea 100644
--- a/net/ipv4/tcp_dctcp.c
+++ b/net/ipv4/tcp_dctcp.c
@@ -131,23 +131,14 @@ static void dctcp_ce_state_0_to_1(struct sock *sk)
struct dctcp *ca = inet_csk_ca(sk);
struct tcp_sock *tp = tcp_sk(sk);

- /* State has changed from CE=0 to CE=1 and delayed
- * ACK has not sent yet.
- */
- if (!ca->ce_state && ca->delayed_ack_reserved) {
- u32 tmp_rcv_nxt;
-
- /* Save current rcv_nxt. */
- tmp_rcv_nxt = tp->rcv_nxt;
-
- /* Generate previous ack with CE=0. */
- tp->ecn_flags &= ~TCP_ECN_DEMAND_CWR;
- tp->rcv_nxt = ca->prior_rcv_nxt;
-
- tcp_send_ack(sk);
-
- /* Recover current rcv_nxt. */
- tp->rcv_nxt = tmp_rcv_nxt;
+ if (!ca->ce_state) {
+ /* State has changed from CE=0 to CE=1, force an immediate
+ * ACK to reflect the new CE state. If an ACK was delayed,
+ * send that first to reflect the prior CE state.
+ */
+ if (inet_csk(sk)->icsk_ack.pending & ICSK_ACK_TIMER)
+ __tcp_send_ack(sk, ca->prior_rcv_nxt);
+ tcp_enter_quickack_mode(sk);
}

ca->prior_rcv_nxt = tp->rcv_nxt;
@@ -161,23 +152,14 @@ static void dctcp_ce_state_1_to_0(struct sock *sk)
struct dctcp *ca = inet_csk_ca(sk);
struct tcp_sock *tp = tcp_sk(sk);

- /* State has changed from CE=1 to CE=0 and delayed
- * ACK has not sent yet.
- */
- if (ca->ce_state && ca->delayed_ack_reserved) {
- u32 tmp_rcv_nxt;
-
- /* Save current rcv_nxt. */
- tmp_rcv_nxt = tp->rcv_nxt;
-
- /* Generate previous ack with CE=1. */
- tp->ecn_flags |= TCP_ECN_DEMAND_CWR;
- tp->rcv_nxt = ca->prior_rcv_nxt;
-
- tcp_send_ack(sk);
-
- /* Recover current rcv_nxt. */
- tp->rcv_nxt = tmp_rcv_nxt;
+ if (ca->ce_state) {
+ /* State has changed from CE=1 to CE=0, force an immediate
+ * ACK to reflect the new CE state. If an ACK was delayed,
+ * send that first to reflect the prior CE state.
+ */
+ if (inet_csk(sk)->icsk_ack.pending & ICSK_ACK_TIMER)
+ __tcp_send_ack(sk, ca->prior_rcv_nxt);
+ tcp_enter_quickack_mode(sk);
}

ca->prior_rcv_nxt = tp->rcv_nxt;
diff --git a/net/ipv4/tcp_input.c b/net/ipv4/tcp_input.c
index be453aa8fce8..44d136fd2af5 100644
--- a/net/ipv4/tcp_input.c
+++ b/net/ipv4/tcp_input.c
@@ -209,13 +209,14 @@ static void tcp_incr_quickack(struct sock *sk)
icsk->icsk_ack.quick = min(quickacks, TCP_MAX_QUICKACKS);
}

-static void tcp_enter_quickack_mode(struct sock *sk)
+void tcp_enter_quickack_mode(struct sock *sk)
{
struct inet_connection_sock *icsk = inet_csk(sk);
tcp_incr_quickack(sk);
icsk->icsk_ack.pingpong = 0;
icsk->icsk_ack.ato = TCP_ATO_MIN;
}
+EXPORT_SYMBOL(tcp_enter_quickack_mode);

/* Send ACKs quickly, if "quick" count is not exhausted
* and the session is not interactive.
@@ -4516,7 +4517,7 @@ static void tcp_data_queue_ofo(struct sock *sk, struct sk_buff *skb)
/* All the bits are present. Drop. */
NET_INC_STATS(sock_net(sk),
LINUX_MIB_TCPOFOMERGE);
- __kfree_skb(skb);
+ tcp_drop(sk, skb);
skb = NULL;
tcp_dsack_set(sk, seq, end_seq);
goto add_sack;
@@ -4535,7 +4536,7 @@ static void tcp_data_queue_ofo(struct sock *sk, struct sk_buff *skb)
TCP_SKB_CB(skb1)->end_seq);
NET_INC_STATS(sock_net(sk),
LINUX_MIB_TCPOFOMERGE);
- __kfree_skb(skb1);
+ tcp_drop(sk, skb1);
goto merge_right;
}
} else if (tcp_try_coalesce(sk, skb1, skb, &fragstolen)) {
@@ -4917,6 +4918,7 @@ tcp_collapse(struct sock *sk, struct sk_buff_head *list, struct rb_root *root,
static void tcp_collapse_ofo_queue(struct sock *sk)
{
struct tcp_sock *tp = tcp_sk(sk);
+ u32 range_truesize, sum_tiny = 0;
struct sk_buff *skb, *head;
struct rb_node *p;
u32 start, end;
@@ -4935,6 +4937,7 @@ static void tcp_collapse_ofo_queue(struct sock *sk)
}
start = TCP_SKB_CB(skb)->seq;
end = TCP_SKB_CB(skb)->end_seq;
+ range_truesize = skb->truesize;

for (head = skb;;) {
skb = tcp_skb_next(skb, NULL);
@@ -4945,11 +4948,20 @@ static void tcp_collapse_ofo_queue(struct sock *sk)
if (!skb ||
after(TCP_SKB_CB(skb)->seq, end) ||
before(TCP_SKB_CB(skb)->end_seq, start)) {
- tcp_collapse(sk, NULL, &tp->out_of_order_queue,
- head, skb, start, end);
+ /* Do not attempt collapsing tiny skbs */
+ if (range_truesize != head->truesize ||
+ end - start >= SKB_WITH_OVERHEAD(SK_MEM_QUANTUM)) {
+ tcp_collapse(sk, NULL, &tp->out_of_order_queue,
+ head, skb, start, end);
+ } else {
+ sum_tiny += range_truesize;
+ if (sum_tiny > sk->sk_rcvbuf >> 3)
+ return;
+ }
goto new_range;
}

+ range_truesize += skb->truesize;
if (unlikely(before(TCP_SKB_CB(skb)->seq, start)))
start = TCP_SKB_CB(skb)->seq;
if (after(TCP_SKB_CB(skb)->end_seq, end))
@@ -4964,6 +4976,7 @@ static void tcp_collapse_ofo_queue(struct sock *sk)
* 2) not add too big latencies if thousands of packets sit there.
* (But if application shrinks SO_RCVBUF, we could still end up
* freeing whole queue here)
+ * 3) Drop at least 12.5 % of sk_rcvbuf to avoid malicious attacks.
*
* Return true if queue has shrunk.
*/
@@ -4971,20 +4984,26 @@ static bool tcp_prune_ofo_queue(struct sock *sk)
{
struct tcp_sock *tp = tcp_sk(sk);
struct rb_node *node, *prev;
+ int goal;

if (RB_EMPTY_ROOT(&tp->out_of_order_queue))
return false;

NET_INC_STATS(sock_net(sk), LINUX_MIB_OFOPRUNED);
+ goal = sk->sk_rcvbuf >> 3;
node = &tp->ooo_last_skb->rbnode;
do {
prev = rb_prev(node);
rb_erase(node, &tp->out_of_order_queue);
+ goal -= rb_to_skb(node)->truesize;
tcp_drop(sk, rb_entry(node, struct sk_buff, rbnode));
- sk_mem_reclaim(sk);
- if (atomic_read(&sk->sk_rmem_alloc) <= sk->sk_rcvbuf &&
- !tcp_under_memory_pressure(sk))
- break;
+ if (!prev || goal <= 0) {
+ sk_mem_reclaim(sk);
+ if (atomic_read(&sk->sk_rmem_alloc) <= sk->sk_rcvbuf &&
+ !tcp_under_memory_pressure(sk))
+ break;
+ goal = sk->sk_rcvbuf >> 3;
+ }
node = prev;
} while (node);
tp->ooo_last_skb = rb_entry(prev, struct sk_buff, rbnode);
@@ -5019,6 +5038,9 @@ static int tcp_prune_queue(struct sock *sk)
else if (tcp_under_memory_pressure(sk))
tp->rcv_ssthresh = min(tp->rcv_ssthresh, 4U * tp->advmss);

+ if (atomic_read(&sk->sk_rmem_alloc) <= sk->sk_rcvbuf)
+ return 0;
+
tcp_collapse_ofo_queue(sk);
if (!skb_queue_empty(&sk->sk_receive_queue))
tcp_collapse(sk, &sk->sk_receive_queue, NULL,
diff --git a/net/ipv4/tcp_output.c b/net/ipv4/tcp_output.c
index f07a0a1c98ff..5f916953b28e 100644
--- a/net/ipv4/tcp_output.c
+++ b/net/ipv4/tcp_output.c
@@ -174,8 +174,13 @@ static void tcp_event_data_sent(struct tcp_sock *tp,
}

/* Account for an ACK we sent. */
-static inline void tcp_event_ack_sent(struct sock *sk, unsigned int pkts)
+static inline void tcp_event_ack_sent(struct sock *sk, unsigned int pkts,
+ u32 rcv_nxt)
{
+ struct tcp_sock *tp = tcp_sk(sk);
+
+ if (unlikely(rcv_nxt != tp->rcv_nxt))
+ return; /* Special ACK sent by DCTCP to reflect ECN */
tcp_dec_quickack_mode(sk, pkts);
inet_csk_clear_xmit_timer(sk, ICSK_TIME_DACK);
}
@@ -905,8 +910,8 @@ void tcp_wfree(struct sk_buff *skb)
* We are working here with either a clone of the original
* SKB, or a fresh unique copy made by the retransmit engine.
*/
-static int tcp_transmit_skb(struct sock *sk, struct sk_buff *skb, int clone_it,
- gfp_t gfp_mask)
+static int __tcp_transmit_skb(struct sock *sk, struct sk_buff *skb,
+ int clone_it, gfp_t gfp_mask, u32 rcv_nxt)
{
const struct inet_connection_sock *icsk = inet_csk(sk);
struct inet_sock *inet;
@@ -969,7 +974,7 @@ static int tcp_transmit_skb(struct sock *sk, struct sk_buff *skb, int clone_it,
th->source = inet->inet_sport;
th->dest = inet->inet_dport;
th->seq = htonl(tcb->seq);
- th->ack_seq = htonl(tp->rcv_nxt);
+ th->ack_seq = htonl(rcv_nxt);
*(((__be16 *)th) + 6) = htons(((tcp_header_size >> 2) << 12) |
tcb->tcp_flags);

@@ -1010,7 +1015,7 @@ static int tcp_transmit_skb(struct sock *sk, struct sk_buff *skb, int clone_it,
icsk->icsk_af_ops->send_check(sk, skb);

if (likely(tcb->tcp_flags & TCPHDR_ACK))
- tcp_event_ack_sent(sk, tcp_skb_pcount(skb));
+ tcp_event_ack_sent(sk, tcp_skb_pcount(skb), rcv_nxt);

if (skb->len != tcp_header_size) {
tcp_event_data_sent(tp, sk);
@@ -1046,6 +1051,13 @@ static int tcp_transmit_skb(struct sock *sk, struct sk_buff *skb, int clone_it,
return err;
}

+static int tcp_transmit_skb(struct sock *sk, struct sk_buff *skb, int clone_it,
+ gfp_t gfp_mask)
+{
+ return __tcp_transmit_skb(sk, skb, clone_it, gfp_mask,
+ tcp_sk(sk)->rcv_nxt);
+}
+
/* This routine just queues the buffer for sending.
*
* NOTE: probe0 timer is not checked, do not forget tcp_push_pending_frames,
@@ -3482,7 +3494,7 @@ void tcp_send_delayed_ack(struct sock *sk)
}

/* This routine sends an ack and also updates the window. */
-void tcp_send_ack(struct sock *sk)
+void __tcp_send_ack(struct sock *sk, u32 rcv_nxt)
{
struct sk_buff *buff;

@@ -3520,9 +3532,14 @@ void tcp_send_ack(struct sock *sk)

/* Send it off, this clears delayed acks for us. */
skb_mstamp_get(&buff->skb_mstamp);
- tcp_transmit_skb(sk, buff, 0, (__force gfp_t)0);
+ __tcp_transmit_skb(sk, buff, 0, (__force gfp_t)0, rcv_nxt);
+}
+EXPORT_SYMBOL_GPL(__tcp_send_ack);
+
+void tcp_send_ack(struct sock *sk)
+{
+ __tcp_send_ack(sk, tcp_sk(sk)->rcv_nxt);
}
-EXPORT_SYMBOL_GPL(tcp_send_ack);

/* This routine sends a packet with an out of date sequence
* number. It assumes the other end will try to ack it.
diff --git a/net/ipv6/datagram.c b/net/ipv6/datagram.c
index 38062f403ceb..2d3c8fe27583 100644
--- a/net/ipv6/datagram.c
+++ b/net/ipv6/datagram.c
@@ -694,13 +694,16 @@ void ip6_datagram_recv_specific_ctl(struct sock *sk, struct msghdr *msg,
}
if (np->rxopt.bits.rxorigdstaddr) {
struct sockaddr_in6 sin6;
- __be16 *ports = (__be16 *) skb_transport_header(skb);
+ __be16 *ports;
+ int end;

- if (skb_transport_offset(skb) + 4 <= (int)skb->len) {
+ end = skb_transport_offset(skb) + 4;
+ if (end <= 0 || pskb_may_pull(skb, end)) {
/* All current transport protocols have the port numbers in the
* first four bytes of the transport header and this function is
* written with this assumption in mind.
*/
+ ports = (__be16 *)skb_transport_header(skb);

sin6.sin6_family = AF_INET6;
sin6.sin6_addr = ipv6_hdr(skb)->daddr;
diff --git a/net/ipv6/ip6_output.c b/net/ipv6/ip6_output.c
index eb9046eae581..ea14466cdca8 100644
--- a/net/ipv6/ip6_output.c
+++ b/net/ipv6/ip6_output.c
@@ -576,6 +576,8 @@ static void ip6_copy_metadata(struct sk_buff *to, struct sk_buff *from)
to->dev = from->dev;
to->mark = from->mark;

+ skb_copy_hash(to, from);
+
#ifdef CONFIG_NET_SCHED
to->tc_index = from->tc_index;
#endif
diff --git a/net/ipv6/mcast.c b/net/ipv6/mcast.c
index ca8fac6e5a09..918c161e5b55 100644
--- a/net/ipv6/mcast.c
+++ b/net/ipv6/mcast.c
@@ -771,8 +771,7 @@ static void mld_del_delrec(struct inet6_dev *idev, struct ifmcaddr6 *im)
if (pmc) {
im->idev = pmc->idev;
im->mca_crcount = idev->mc_qrv;
- im->mca_sfmode = pmc->mca_sfmode;
- if (pmc->mca_sfmode == MCAST_INCLUDE) {
+ if (im->mca_sfmode == MCAST_INCLUDE) {
im->mca_tomb = pmc->mca_tomb;
im->mca_sources = pmc->mca_sources;
for (psf = im->mca_sources; psf; psf = psf->sf_next)