aboutsummaryrefslogtreecommitdiff
path: root/drivers/usb/serial/quatech2.c
diff options
context:
space:
mode:
Diffstat (limited to 'drivers/usb/serial/quatech2.c')
-rw-r--r--drivers/usb/serial/quatech2.c1036
1 files changed, 1036 insertions, 0 deletions
diff --git a/drivers/usb/serial/quatech2.c b/drivers/usb/serial/quatech2.c
new file mode 100644
index 00000000000..504f5bff79c
--- /dev/null
+++ b/drivers/usb/serial/quatech2.c
@@ -0,0 +1,1036 @@
+/*
+ * usb-serial driver for Quatech USB 2 devices
+ *
+ * Copyright (C) 2012 Bill Pemberton (wfp5p@virginia.edu)
+ *
+ * This program is free software; you can redistribute it and/or
+ * modify it under the terms of the GNU General Public License version 2
+ * as published by the Free Software Foundation.
+ *
+ *
+ * These devices all have only 1 bulk in and 1 bulk out that is shared
+ * for all serial ports.
+ *
+ */
+
+#include <asm/unaligned.h>
+#include <linux/errno.h>
+#include <linux/slab.h>
+#include <linux/tty.h>
+#include <linux/tty_driver.h>
+#include <linux/tty_flip.h>
+#include <linux/module.h>
+#include <linux/serial.h>
+#include <linux/usb.h>
+#include <linux/usb/serial.h>
+#include <linux/serial_reg.h>
+#include <linux/uaccess.h>
+
+/* default urb timeout for usb operations */
+#define QT2_USB_TIMEOUT USB_CTRL_SET_TIMEOUT
+
+#define QT_OPEN_CLOSE_CHANNEL 0xca
+#define QT_SET_GET_DEVICE 0xc2
+#define QT_SET_GET_REGISTER 0xc0
+#define QT_GET_SET_PREBUF_TRIG_LVL 0xcc
+#define QT_SET_ATF 0xcd
+#define QT_TRANSFER_IN 0xc0
+#define QT_HW_FLOW_CONTROL_MASK 0xc5
+#define QT_SW_FLOW_CONTROL_MASK 0xc6
+#define QT2_BREAK_CONTROL 0xc8
+#define QT2_GET_SET_UART 0xc1
+#define QT2_FLUSH_DEVICE 0xc4
+#define QT2_GET_SET_QMCR 0xe1
+#define QT2_QMCR_RS232 0x40
+#define QT2_QMCR_RS422 0x10
+
+#define SERIAL_CRTSCTS ((UART_MCR_RTS << 8) | UART_MSR_CTS)
+
+#define SERIAL_EVEN_PARITY (UART_LCR_PARITY | UART_LCR_EPAR)
+
+/* status bytes for the device */
+#define QT2_CONTROL_BYTE 0x1b
+#define QT2_LINE_STATUS 0x00 /* following 1 byte is line status */
+#define QT2_MODEM_STATUS 0x01 /* following 1 byte is modem status */
+#define QT2_XMIT_HOLD 0x02 /* following 2 bytes are ?? */
+#define QT2_CHANGE_PORT 0x03 /* following 1 byte is port to change to */
+#define QT2_REC_FLUSH 0x04 /* no following info */
+#define QT2_XMIT_FLUSH 0x05 /* no following info */
+#define QT2_CONTROL_ESCAPE 0xff /* pass through previous 2 control bytes */
+
+#define MAX_BAUD_RATE 921600
+#define DEFAULT_BAUD_RATE 9600
+
+#define QT2_READ_BUFFER_SIZE 512 /* size of read buffer */
+#define QT2_WRITE_BUFFER_SIZE 512 /* size of write buffer */
+#define QT2_WRITE_CONTROL_SIZE 5 /* control bytes used for a write */
+
+#define DRIVER_DESC "Quatech 2nd gen USB to Serial Driver"
+
+#define USB_VENDOR_ID_QUATECH 0x061d
+#define QUATECH_SSU2_100 0xC120 /* RS232 single port */
+#define QUATECH_DSU2_100 0xC140 /* RS232 dual port */
+#define QUATECH_DSU2_400 0xC150 /* RS232/422/485 dual port */
+#define QUATECH_QSU2_100 0xC160 /* RS232 four port */
+#define QUATECH_QSU2_400 0xC170 /* RS232/422/485 four port */
+#define QUATECH_ESU2_100 0xC1A0 /* RS232 eight port */
+#define QUATECH_ESU2_400 0xC180 /* RS232/422/485 eight port */
+
+struct qt2_device_detail {
+ int product_id;
+ int num_ports;
+};
+
+#define QT_DETAILS(prod, ports) \
+ .product_id = (prod), \
+ .num_ports = (ports)
+
+static const struct qt2_device_detail qt2_device_details[] = {
+ {QT_DETAILS(QUATECH_SSU2_100, 1)},
+ {QT_DETAILS(QUATECH_DSU2_400, 2)},
+ {QT_DETAILS(QUATECH_DSU2_100, 2)},
+ {QT_DETAILS(QUATECH_QSU2_400, 4)},
+ {QT_DETAILS(QUATECH_QSU2_100, 4)},
+ {QT_DETAILS(QUATECH_ESU2_400, 8)},
+ {QT_DETAILS(QUATECH_ESU2_100, 8)},
+ {QT_DETAILS(0, 0)} /* Terminating entry */
+};
+
+static const struct usb_device_id id_table[] = {
+ {USB_DEVICE(USB_VENDOR_ID_QUATECH, QUATECH_SSU2_100)},
+ {USB_DEVICE(USB_VENDOR_ID_QUATECH, QUATECH_DSU2_100)},
+ {USB_DEVICE(USB_VENDOR_ID_QUATECH, QUATECH_DSU2_400)},
+ {USB_DEVICE(USB_VENDOR_ID_QUATECH, QUATECH_QSU2_100)},
+ {USB_DEVICE(USB_VENDOR_ID_QUATECH, QUATECH_QSU2_400)},
+ {USB_DEVICE(USB_VENDOR_ID_QUATECH, QUATECH_ESU2_100)},
+ {USB_DEVICE(USB_VENDOR_ID_QUATECH, QUATECH_ESU2_400)},
+ {} /* Terminating entry */
+};
+MODULE_DEVICE_TABLE(usb, id_table);
+
+struct qt2_serial_private {
+ unsigned char current_port; /* current port for incoming data */
+
+ struct urb *read_urb; /* shared among all ports */
+ char *read_buffer;
+};
+
+struct qt2_port_private {
+ u8 device_port;
+
+ spinlock_t urb_lock;
+ bool urb_in_use;
+ struct urb *write_urb;
+ char *write_buffer;
+
+ spinlock_t lock;
+ u8 shadowLSR;
+ u8 shadowMSR;
+
+ struct usb_serial_port *port;
+};
+
+static void qt2_update_lsr(struct usb_serial_port *port, unsigned char *ch);
+static void qt2_update_msr(struct usb_serial_port *port, unsigned char *ch);
+static void qt2_write_bulk_callback(struct urb *urb);
+static void qt2_read_bulk_callback(struct urb *urb);
+
+static void qt2_release(struct usb_serial *serial)
+{
+ struct qt2_serial_private *serial_priv;
+
+ serial_priv = usb_get_serial_data(serial);
+
+ usb_free_urb(serial_priv->read_urb);
+ kfree(serial_priv->read_buffer);
+ kfree(serial_priv);
+}
+
+static inline int calc_baud_divisor(int baudrate)
+{
+ int divisor, rem;
+
+ divisor = MAX_BAUD_RATE / baudrate;
+ rem = MAX_BAUD_RATE % baudrate;
+ /* Round to nearest divisor */
+ if (((rem * 2) >= baudrate) && (baudrate != 110))
+ divisor++;
+
+ return divisor;
+}
+
+static inline int qt2_set_port_config(struct usb_device *dev,
+ unsigned char port_number,
+ u16 baudrate, u16 lcr)
+{
+ int divisor = calc_baud_divisor(baudrate);
+ u16 index = ((u16) (lcr << 8) | (u16) (port_number));
+
+ return usb_control_msg(dev, usb_sndctrlpipe(dev, 0),
+ QT2_GET_SET_UART, 0x40,
+ divisor, index, NULL, 0, QT2_USB_TIMEOUT);
+}
+
+static inline int qt2_control_msg(struct usb_device *dev,
+ u8 request, u16 data, u16 index)
+{
+ return usb_control_msg(dev, usb_sndctrlpipe(dev, 0),
+ request, 0x40, data, index,
+ NULL, 0, QT2_USB_TIMEOUT);
+}
+
+static inline int qt2_setdevice(struct usb_device *dev, u8 *data)
+{
+ u16 x = ((u16) (data[1] << 8) | (u16) (data[0]));
+
+ return qt2_control_msg(dev, QT_SET_GET_DEVICE, x, 0);
+}
+
+
+static inline int qt2_getdevice(struct usb_device *dev, u8 *data)
+{
+ return usb_control_msg(dev, usb_rcvctrlpipe(dev, 0),
+ QT_SET_GET_DEVICE, 0xc0, 0, 0,
+ data, 3, QT2_USB_TIMEOUT);
+}
+
+static inline int qt2_getregister(struct usb_device *dev,
+ u8 uart,
+ u8 reg,
+ u8 *data)
+{
+ return usb_control_msg(dev, usb_rcvctrlpipe(dev, 0),
+ QT_SET_GET_REGISTER, 0xc0, reg,
+ uart, data, sizeof(*data), QT2_USB_TIMEOUT);
+
+}
+
+static inline int qt2_setregister(struct usb_device *dev,
+ u8 uart, u8 reg, u16 data)
+{
+ u16 value = (data << 8) | reg;
+
+ return usb_control_msg(dev, usb_sndctrlpipe(dev, 0),
+ QT_SET_GET_REGISTER, 0x40, value, uart,
+ NULL, 0, QT2_USB_TIMEOUT);
+}
+
+static inline int update_mctrl(struct qt2_port_private *port_priv,
+ unsigned int set, unsigned int clear)
+{
+ struct usb_serial_port *port = port_priv->port;
+ struct usb_device *dev = port->serial->dev;
+ unsigned urb_value;
+ int status;
+
+ if (((set | clear) & (TIOCM_DTR | TIOCM_RTS)) == 0) {
+ dev_dbg(&port->dev,
+ "update_mctrl - DTR|RTS not being set|cleared\n");
+ return 0; /* no change */
+ }
+
+ clear &= ~set; /* 'set' takes precedence over 'clear' */
+ urb_value = 0;
+ if (set & TIOCM_DTR)
+ urb_value |= UART_MCR_DTR;
+ if (set & TIOCM_RTS)
+ urb_value |= UART_MCR_RTS;
+
+ status = qt2_setregister(dev, port_priv->device_port, UART_MCR,
+ urb_value);
+ if (status < 0)
+ dev_err(&port->dev,
+ "update_mctrl - Error from MODEM_CTRL urb: %i\n",
+ status);
+ return status;
+}
+
+static int qt2_calc_num_ports(struct usb_serial *serial)
+{
+ struct qt2_device_detail d;
+ int i;
+
+ for (i = 0; d = qt2_device_details[i], d.product_id != 0; i++) {
+ if (d.product_id == le16_to_cpu(serial->dev->descriptor.idProduct))
+ return d.num_ports;
+ }
+
+ /* we didn't recognize the device */
+ dev_err(&serial->dev->dev,
+ "don't know the number of ports, assuming 1\n");
+
+ return 1;
+}
+
+static void qt2_set_termios(struct tty_struct *tty,
+ struct usb_serial_port *port,
+ struct ktermios *old_termios)
+{
+ struct usb_device *dev = port->serial->dev;
+ struct qt2_port_private *port_priv;
+ struct ktermios *termios = &tty->termios;
+ u16 baud;
+ unsigned int cflag = termios->c_cflag;
+ u16 new_lcr = 0;
+ int status;
+
+ port_priv = usb_get_serial_port_data(port);
+
+ if (cflag & PARENB) {
+ if (cflag & PARODD)
+ new_lcr |= UART_LCR_PARITY;
+ else
+ new_lcr |= SERIAL_EVEN_PARITY;
+ }
+
+ switch (cflag & CSIZE) {
+ case CS5:
+ new_lcr |= UART_LCR_WLEN5;
+ break;
+ case CS6:
+ new_lcr |= UART_LCR_WLEN6;
+ break;
+ case CS7:
+ new_lcr |= UART_LCR_WLEN7;
+ break;
+ default:
+ case CS8:
+ new_lcr |= UART_LCR_WLEN8;
+ break;
+ }
+
+ baud = tty_get_baud_rate(tty);
+ if (!baud)
+ baud = 9600;
+
+ status = qt2_set_port_config(dev, port_priv->device_port, baud,
+ new_lcr);
+ if (status < 0)
+ dev_err(&port->dev, "%s - qt2_set_port_config failed: %i\n",
+ __func__, status);
+
+ if (cflag & CRTSCTS)
+ status = qt2_control_msg(dev, QT_HW_FLOW_CONTROL_MASK,
+ SERIAL_CRTSCTS,
+ port_priv->device_port);
+ else
+ status = qt2_control_msg(dev, QT_HW_FLOW_CONTROL_MASK,
+ 0, port_priv->device_port);
+ if (status < 0)
+ dev_err(&port->dev, "%s - set HW flow control failed: %i\n",
+ __func__, status);
+
+ if (I_IXOFF(tty) || I_IXON(tty)) {
+ u16 x = ((u16) (START_CHAR(tty) << 8) | (u16) (STOP_CHAR(tty)));
+
+ status = qt2_control_msg(dev, QT_SW_FLOW_CONTROL_MASK,
+ x, port_priv->device_port);
+ } else
+ status = qt2_control_msg(dev, QT_SW_FLOW_CONTROL_MASK,
+ 0, port_priv->device_port);
+
+ if (status < 0)
+ dev_err(&port->dev, "%s - set SW flow control failed: %i\n",
+ __func__, status);
+
+}
+
+static int qt2_open(struct tty_struct *tty, struct usb_serial_port *port)
+{
+ struct usb_serial *serial;
+ struct qt2_port_private *port_priv;
+ u8 *data;
+ u16 device_port;
+ int status;
+ unsigned long flags;
+
+ device_port = port->port_number;
+
+ serial = port->serial;
+
+ port_priv = usb_get_serial_port_data(port);
+
+ /* set the port to RS232 mode */
+ status = qt2_control_msg(serial->dev, QT2_GET_SET_QMCR,
+ QT2_QMCR_RS232, device_port);
+ if (status < 0) {
+ dev_err(&port->dev,
+ "%s failed to set RS232 mode for port %i error %i\n",
+ __func__, device_port, status);
+ return status;
+ }
+
+ data = kzalloc(2, GFP_KERNEL);
+ if (!data)
+ return -ENOMEM;
+
+ /* open the port */
+ status = usb_control_msg(serial->dev,
+ usb_rcvctrlpipe(serial->dev, 0),
+ QT_OPEN_CLOSE_CHANNEL,
+ 0xc0, 0,
+ device_port, data, 2, QT2_USB_TIMEOUT);
+
+ if (status < 0) {
+ dev_err(&port->dev, "%s - open port failed %i\n", __func__,
+ status);
+ kfree(data);
+ return status;
+ }
+
+ spin_lock_irqsave(&port_priv->lock, flags);
+ port_priv->shadowLSR = data[0];
+ port_priv->shadowMSR = data[1];
+ spin_unlock_irqrestore(&port_priv->lock, flags);
+
+ kfree(data);
+
+ /* set to default speed and 8bit word size */
+ status = qt2_set_port_config(serial->dev, device_port,
+ DEFAULT_BAUD_RATE, UART_LCR_WLEN8);
+ if (status < 0) {
+ dev_err(&port->dev, "%s - initial setup failed (%i)\n",
+ __func__, device_port);
+ return status;
+ }
+
+ port_priv->device_port = (u8) device_port;
+
+ if (tty)
+ qt2_set_termios(tty, port, &tty->termios);
+
+ return 0;
+
+}
+
+static void qt2_close(struct usb_serial_port *port)
+{
+ struct usb_serial *serial;
+ struct qt2_port_private *port_priv;
+ unsigned long flags;
+ int i;
+
+ serial = port->serial;
+ port_priv = usb_get_serial_port_data(port);
+
+ spin_lock_irqsave(&port_priv->urb_lock, flags);
+ usb_kill_urb(port_priv->write_urb);
+ port_priv->urb_in_use = false;
+ spin_unlock_irqrestore(&port_priv->urb_lock, flags);
+
+ /* flush the port transmit buffer */
+ i = usb_control_msg(serial->dev,
+ usb_rcvctrlpipe(serial->dev, 0),
+ QT2_FLUSH_DEVICE, 0x40, 1,
+ port_priv->device_port, NULL, 0, QT2_USB_TIMEOUT);
+
+ if (i < 0)
+ dev_err(&port->dev, "%s - transmit buffer flush failed: %i\n",
+ __func__, i);
+
+ /* flush the port receive buffer */
+ i = usb_control_msg(serial->dev,
+ usb_rcvctrlpipe(serial->dev, 0),
+ QT2_FLUSH_DEVICE, 0x40, 0,
+ port_priv->device_port, NULL, 0, QT2_USB_TIMEOUT);
+
+ if (i < 0)
+ dev_err(&port->dev, "%s - receive buffer flush failed: %i\n",
+ __func__, i);
+
+ /* close the port */
+ i = usb_control_msg(serial->dev,
+ usb_sndctrlpipe(serial->dev, 0),
+ QT_OPEN_CLOSE_CHANNEL,
+ 0x40, 0,
+ port_priv->device_port, NULL, 0, QT2_USB_TIMEOUT);
+
+ if (i < 0)
+ dev_err(&port->dev, "%s - close port failed %i\n",
+ __func__, i);
+}
+
+static void qt2_disconnect(struct usb_serial *serial)
+{
+ struct qt2_serial_private *serial_priv = usb_get_serial_data(serial);
+
+ usb_kill_urb(serial_priv->read_urb);
+}
+
+static int get_serial_info(struct usb_serial_port *port,
+ struct serial_struct __user *retinfo)
+{
+ struct serial_struct tmp;
+
+ if (!retinfo)
+ return -EFAULT;
+
+ memset(&tmp, 0, sizeof(tmp));
+ tmp.line = port->minor;
+ tmp.port = 0;
+ tmp.irq = 0;
+ tmp.flags = ASYNC_SKIP_TEST | ASYNC_AUTO_IRQ;
+ tmp.xmit_fifo_size = port->bulk_out_size;
+ tmp.baud_base = 9600;
+ tmp.close_delay = 5*HZ;
+ tmp.closing_wait = 30*HZ;
+
+ if (copy_to_user(retinfo, &tmp, sizeof(*retinfo)))
+ return -EFAULT;
+ return 0;
+}
+
+static int qt2_ioctl(struct tty_struct *tty,
+ unsigned int cmd, unsigned long arg)
+{
+ struct usb_serial_port *port = tty->driver_data;
+
+ switch (cmd) {
+ case TIOCGSERIAL:
+ return get_serial_info(port,
+ (struct serial_struct __user *)arg);
+ default:
+ break;
+ }
+
+ return -ENOIOCTLCMD;
+}
+
+static void qt2_process_status(struct usb_serial_port *port, unsigned char *ch)
+{
+ switch (*ch) {
+ case QT2_LINE_STATUS:
+ qt2_update_lsr(port, ch + 1);
+ break;
+ case QT2_MODEM_STATUS:
+ qt2_update_msr(port, ch + 1);
+ break;
+ }
+}
+
+/* not needed, kept to document functionality */
+static void qt2_process_xmit_empty(struct usb_serial_port *port,
+ unsigned char *ch)
+{
+ int bytes_written;
+
+ bytes_written = (int)(*ch) + (int)(*(ch + 1) << 4);
+}
+
+/* not needed, kept to document functionality */
+static void qt2_process_flush(struct usb_serial_port *port, unsigned char *ch)
+{
+ return;
+}
+
+static void qt2_process_read_urb(struct urb *urb)
+{
+ struct usb_serial *serial;
+ struct qt2_serial_private *serial_priv;
+ struct usb_serial_port *port;
+ struct qt2_port_private *port_priv;
+ bool escapeflag;
+ unsigned char *ch;
+ int i;
+ unsigned char newport;
+ int len = urb->actual_length;
+
+ if (!len)
+ return;
+
+ ch = urb->transfer_buffer;
+ serial = urb->context;
+ serial_priv = usb_get_serial_data(serial);
+ port = serial->port[serial_priv->current_port];
+ port_priv = usb_get_serial_port_data(port);
+
+ for (i = 0; i < urb->actual_length; i++) {
+ ch = (unsigned char *)urb->transfer_buffer + i;
+ if ((i <= (len - 3)) &&
+ (*ch == QT2_CONTROL_BYTE) &&
+ (*(ch + 1) == QT2_CONTROL_BYTE)) {
+ escapeflag = false;
+ switch (*(ch + 2)) {
+ case QT2_LINE_STATUS:
+ case QT2_MODEM_STATUS:
+ if (i > (len - 4)) {
+ dev_warn(&port->dev,
+ "%s - status message too short\n",
+ __func__);
+ break;
+ }
+ qt2_process_status(port, ch + 2);
+ i += 3;
+ escapeflag = true;
+ break;
+ case QT2_XMIT_HOLD:
+ if (i > (len - 5)) {
+ dev_warn(&port->dev,
+ "%s - xmit_empty message too short\n",
+ __func__);
+ break;
+ }
+ qt2_process_xmit_empty(port, ch + 3);
+ i += 4;
+ escapeflag = true;
+ break;
+ case QT2_CHANGE_PORT:
+ if (i > (len - 4)) {
+ dev_warn(&port->dev,
+ "%s - change_port message too short\n",
+ __func__);
+ break;
+ }
+ tty_flip_buffer_push(&port->port);
+
+ newport = *(ch + 3);
+
+ if (newport > serial->num_ports) {
+ dev_err(&port->dev,
+ "%s - port change to invalid port: %i\n",
+ __func__, newport);
+ break;
+ }
+
+ serial_priv->current_port = newport;
+ port = serial->port[serial_priv->current_port];
+ port_priv = usb_get_serial_port_data(port);
+ i += 3;
+ escapeflag = true;
+ break;
+ case QT2_REC_FLUSH:
+ case QT2_XMIT_FLUSH:
+ qt2_process_flush(port, ch + 2);
+ i += 2;
+ escapeflag = true;
+ break;
+ case QT2_CONTROL_ESCAPE:
+ tty_buffer_request_room(&port->port, 2);
+ tty_insert_flip_string(&port->port, ch, 2);
+ i += 2;
+ escapeflag = true;
+ break;
+ default:
+ dev_warn(&port->dev,
+ "%s - unsupported command %i\n",
+ __func__, *(ch + 2));
+ break;
+ }
+ if (escapeflag)
+ continue;
+ }
+
+ tty_buffer_request_room(&port->port, 1);
+ tty_insert_flip_string(&port->port, ch, 1);
+ }
+
+ tty_flip_buffer_push(&port->port);
+}
+
+static void qt2_write_bulk_callback(struct urb *urb)
+{
+ struct usb_serial_port *port;
+ struct qt2_port_private *port_priv;
+
+ port = urb->context;
+ port_priv = usb_get_serial_port_data(port);
+
+ spin_lock(&port_priv->urb_lock);
+
+ port_priv->urb_in_use = false;
+ usb_serial_port_softint(port);
+
+ spin_unlock(&port_priv->urb_lock);
+
+}
+
+static void qt2_read_bulk_callback(struct urb *urb)
+{
+ struct usb_serial *serial = urb->context;
+ int status;
+
+ if (urb->status) {
+ dev_warn(&serial->dev->dev,
+ "%s - non-zero urb status: %i\n", __func__,
+ urb->status);
+ return;
+ }
+
+ qt2_process_read_urb(urb);
+
+ status = usb_submit_urb(urb, GFP_ATOMIC);
+ if (status != 0)
+ dev_err(&serial->dev->dev,
+ "%s - resubmit read urb failed: %i\n",
+ __func__, status);
+}
+
+static int qt2_setup_urbs(struct usb_serial *serial)
+{
+ struct usb_serial_port *port0;
+ struct qt2_serial_private *serial_priv;
+ int status;
+
+ port0 = serial->port[0];
+
+ serial_priv = usb_get_serial_data(serial);
+ serial_priv->read_urb = usb_alloc_urb(0, GFP_KERNEL);
+ if (!serial_priv->read_urb)
+ return -ENOMEM;
+
+ usb_fill_bulk_urb(serial_priv->read_urb, serial->dev,
+ usb_rcvbulkpipe(serial->dev,
+ port0->bulk_in_endpointAddress),
+ serial_priv->read_buffer,
+ QT2_READ_BUFFER_SIZE,
+ qt2_read_bulk_callback, serial);
+
+ status = usb_submit_urb(serial_priv->read_urb, GFP_KERNEL);
+ if (status != 0) {
+ dev_err(&serial->dev->dev,
+ "%s - submit read urb failed %i\n", __func__, status);
+ usb_free_urb(serial_priv->read_urb);
+ return status;
+ }
+
+ return 0;
+}
+
+static int qt2_attach(struct usb_serial *serial)
+{
+ struct qt2_serial_private *serial_priv;
+ int status;
+
+ /* power on unit */
+ status = usb_control_msg(serial->dev, usb_rcvctrlpipe(serial->dev, 0),
+ 0xc2, 0x40, 0x8000, 0, NULL, 0,
+ QT2_USB_TIMEOUT);
+ if (status < 0) {
+ dev_err(&serial->dev->dev,
+ "%s - failed to power on unit: %i\n", __func__, status);
+ return status;
+ }
+
+ serial_priv = kzalloc(sizeof(*serial_priv), GFP_KERNEL);
+ if (!serial_priv)
+ return -ENOMEM;
+
+ serial_priv->read_buffer = kmalloc(QT2_READ_BUFFER_SIZE, GFP_KERNEL);
+ if (!serial_priv->read_buffer) {
+ status = -ENOMEM;
+ goto err_buf;
+ }
+
+ usb_set_serial_data(serial, serial_priv);
+
+ status = qt2_setup_urbs(serial);
+ if (status != 0)
+ goto attach_failed;
+
+ return 0;
+
+attach_failed:
+ kfree(serial_priv->read_buffer);
+err_buf:
+ kfree(serial_priv);
+ return status;
+}
+
+static int qt2_port_probe(struct usb_serial_port *port)
+{
+ struct usb_serial *serial = port->serial;
+ struct qt2_port_private *port_priv;
+ u8 bEndpointAddress;
+
+ port_priv = kzalloc(sizeof(*port_priv), GFP_KERNEL);
+ if (!port_priv)
+ return -ENOMEM;
+
+ spin_lock_init(&port_priv->lock);
+ spin_lock_init(&port_priv->urb_lock);
+ port_priv->port = port;
+
+ port_priv->write_buffer = kmalloc(QT2_WRITE_BUFFER_SIZE, GFP_KERNEL);
+ if (!port_priv->write_buffer)
+ goto err_buf;
+
+ port_priv->write_urb = usb_alloc_urb(0, GFP_KERNEL);
+ if (!port_priv->write_urb)
+ goto err_urb;
+
+ bEndpointAddress = serial->port[0]->bulk_out_endpointAddress;
+ usb_fill_bulk_urb(port_priv->write_urb, serial->dev,
+ usb_sndbulkpipe(serial->dev, bEndpointAddress),
+ port_priv->write_buffer,
+ QT2_WRITE_BUFFER_SIZE,
+ qt2_write_bulk_callback, port);
+
+ usb_set_serial_port_data(port, port_priv);
+
+ return 0;
+err_urb:
+ kfree(port_priv->write_buffer);
+err_buf:
+ kfree(port_priv);
+ return -ENOMEM;
+}
+
+static int qt2_port_remove(struct usb_serial_port *port)
+{
+ struct qt2_port_private *port_priv;
+
+ port_priv = usb_get_serial_port_data(port);
+ usb_free_urb(port_priv->write_urb);
+ kfree(port_priv->write_buffer);
+ kfree(port_priv);
+
+ return 0;
+}
+
+static int qt2_tiocmget(struct tty_struct *tty)
+{
+ struct usb_serial_port *port = tty->driver_data;
+ struct usb_device *dev = port->serial->dev;
+ struct qt2_port_private *port_priv = usb_get_serial_port_data(port);
+ u8 *d;
+ int r;
+
+ d = kzalloc(2, GFP_KERNEL);
+ if (!d)
+ return -ENOMEM;
+
+ r = qt2_getregister(dev, port_priv->device_port, UART_MCR, d);
+ if (r < 0)
+ goto mget_out;
+
+ r = qt2_getregister(dev, port_priv->device_port, UART_MSR, d + 1);
+ if (r < 0)
+ goto mget_out;
+
+ r = (d[0] & UART_MCR_DTR ? TIOCM_DTR : 0) |
+ (d[0] & UART_MCR_RTS ? TIOCM_RTS : 0) |
+ (d[1] & UART_MSR_CTS ? TIOCM_CTS : 0) |
+ (d[1] & UART_MSR_DCD ? TIOCM_CAR : 0) |
+ (d[1] & UART_MSR_RI ? TIOCM_RI : 0) |
+ (d[1] & UART_MSR_DSR ? TIOCM_DSR : 0);
+
+mget_out:
+ kfree(d);
+ return r;
+}
+
+static int qt2_tiocmset(struct tty_struct *tty,
+ unsigned int set, unsigned int clear)
+{
+ struct qt2_port_private *port_priv;
+
+ port_priv = usb_get_serial_port_data(tty->driver_data);
+ return update_mctrl(port_priv, set, clear);
+}
+
+static void qt2_break_ctl(struct tty_struct *tty, int break_state)
+{
+ struct usb_serial_port *port = tty->driver_data;
+ struct qt2_port_private *port_priv;
+ int status;
+ u16 val;
+
+ port_priv = usb_get_serial_port_data(port);
+
+ val = (break_state == -1) ? 1 : 0;
+
+ status = qt2_control_msg(port->serial->dev, QT2_BREAK_CONTROL,
+ val, port_priv->device_port);
+ if (status < 0)
+ dev_warn(&port->dev,
+ "%s - failed to send control message: %i\n", __func__,
+ status);
+}
+
+
+
+static void qt2_dtr_rts(struct usb_serial_port *port, int on)
+{
+ struct usb_device *dev = port->serial->dev;
+ struct qt2_port_private *port_priv = usb_get_serial_port_data(port);
+
+ /* Disable flow control */
+ if (!on) {
+ if (qt2_setregister(dev, port_priv->device_port,
+ UART_MCR, 0) < 0)
+ dev_warn(&port->dev, "error from flowcontrol urb\n");
+ }
+ /* drop RTS and DTR */
+ if (on)
+ update_mctrl(port_priv, TIOCM_DTR | TIOCM_RTS, 0);
+ else
+ update_mctrl(port_priv, 0, TIOCM_DTR | TIOCM_RTS);
+}
+
+static void qt2_update_msr(struct usb_serial_port *port, unsigned char *ch)
+{
+ struct qt2_port_private *port_priv;
+ u8 newMSR = (u8) *ch;
+ unsigned long flags;
+
+ port_priv = usb_get_serial_port_data(port);
+
+ spin_lock_irqsave(&port_priv->lock, flags);
+ port_priv->shadowMSR = newMSR;
+ spin_unlock_irqrestore(&port_priv->lock, flags);
+
+ if (newMSR & UART_MSR_ANY_DELTA) {
+ /* update input line counters */
+ if (newMSR & UART_MSR_DCTS)
+ port->icount.cts++;
+ if (newMSR & UART_MSR_DDSR)
+ port->icount.dsr++;
+ if (newMSR & UART_MSR_DDCD)
+ port->icount.dcd++;
+ if (newMSR & UART_MSR_TERI)
+ port->icount.rng++;
+
+ wake_up_interruptible(&port->port.delta_msr_wait);
+ }
+}
+
+static void qt2_update_lsr(struct usb_serial_port *port, unsigned char *ch)
+{
+ struct qt2_port_private *port_priv;
+ struct async_icount *icount;
+ unsigned long flags;
+ u8 newLSR = (u8) *ch;
+
+ port_priv = usb_get_serial_port_data(port);
+
+ if (newLSR & UART_LSR_BI)
+ newLSR &= (u8) (UART_LSR_OE | UART_LSR_BI);
+
+ spin_lock_irqsave(&port_priv->lock, flags);
+ port_priv->shadowLSR = newLSR;
+ spin_unlock_irqrestore(&port_priv->lock, flags);
+
+ icount = &port->icount;
+
+ if (newLSR & UART_LSR_BRK_ERROR_BITS) {
+
+ if (newLSR & UART_LSR_BI)
+ icount->brk++;
+
+ if (newLSR & UART_LSR_OE)
+ icount->overrun++;
+
+ if (newLSR & UART_LSR_PE)
+ icount->parity++;
+
+ if (newLSR & UART_LSR_FE)
+ icount->frame++;
+ }
+
+}
+
+static int qt2_write_room(struct tty_struct *tty)
+{
+ struct usb_serial_port *port = tty->driver_data;
+ struct qt2_port_private *port_priv;
+ unsigned long flags = 0;
+ int r;
+
+ port_priv = usb_get_serial_port_data(port);
+
+ spin_lock_irqsave(&port_priv->urb_lock, flags);
+
+ if (port_priv->urb_in_use)
+ r = 0;
+ else
+ r = QT2_WRITE_BUFFER_SIZE - QT2_WRITE_CONTROL_SIZE;
+
+ spin_unlock_irqrestore(&port_priv->urb_lock, flags);
+
+ return r;
+}
+
+static int qt2_write(struct tty_struct *tty,
+ struct usb_serial_port *port,
+ const unsigned char *buf, int count)
+{
+ struct qt2_port_private *port_priv;
+ struct urb *write_urb;
+ unsigned char *data;
+ unsigned long flags;
+ int status;
+ int bytes_out = 0;
+
+ port_priv = usb_get_serial_port_data(port);
+
+ if (port_priv->write_urb == NULL) {
+ dev_err(&port->dev, "%s - no output urb\n", __func__);
+ return 0;
+ }
+ write_urb = port_priv->write_urb;
+
+ count = min(count, QT2_WRITE_BUFFER_SIZE - QT2_WRITE_CONTROL_SIZE);
+
+ data = write_urb->transfer_buffer;
+ spin_lock_irqsave(&port_priv->urb_lock, flags);
+ if (port_priv->urb_in_use == true) {
+ dev_err(&port->dev, "qt2_write - urb is in use\n");
+ goto write_out;
+ }
+
+ *data++ = QT2_CONTROL_BYTE;
+ *data++ = QT2_CONTROL_BYTE;
+ *data++ = port_priv->device_port;
+ put_unaligned_le16(count, data);
+ data += 2;
+ memcpy(data, buf, count);
+
+ write_urb->transfer_buffer_length = count + QT2_WRITE_CONTROL_SIZE;
+
+ status = usb_submit_urb(write_urb, GFP_ATOMIC);
+ if (status == 0) {
+ port_priv->urb_in_use = true;
+ bytes_out += count;
+ }
+
+write_out:
+ spin_unlock_irqrestore(&port_priv->urb_lock, flags);
+ return bytes_out;
+}
+
+
+static struct usb_serial_driver qt2_device = {
+ .driver = {
+ .owner = THIS_MODULE,
+ .name = "quatech-serial",
+ },
+ .description = DRIVER_DESC,
+ .id_table = id_table,
+ .open = qt2_open,
+ .close = qt2_close,
+ .write = qt2_write,
+ .write_room = qt2_write_room,
+ .calc_num_ports = qt2_calc_num_ports,
+ .attach = qt2_attach,
+ .release = qt2_release,
+ .disconnect = qt2_disconnect,
+ .port_probe = qt2_port_probe,
+ .port_remove = qt2_port_remove,
+ .dtr_rts = qt2_dtr_rts,
+ .break_ctl = qt2_break_ctl,
+ .tiocmget = qt2_tiocmget,
+ .tiocmset = qt2_tiocmset,
+ .tiocmiwait = usb_serial_generic_tiocmiwait,
+ .get_icount = usb_serial_generic_get_icount,
+ .ioctl = qt2_ioctl,
+ .set_termios = qt2_set_termios,
+};
+
+static struct usb_serial_driver *const serial_drivers[] = {
+ &qt2_device, NULL
+};
+
+module_usb_serial_driver(serial_drivers, id_table);
+
+MODULE_DESCRIPTION(DRIVER_DESC);
+MODULE_LICENSE("GPL");
-rw-r--r--net/netfilter/xt_NFLOG.c3
-rw-r--r--net/netfilter/xt_NFQUEUE.c102
-rw-r--r--net/netfilter/xt_RATEEST.c3
-rw-r--r--net/netfilter/xt_TCPMSS.c124
-rw-r--r--net/netfilter/xt_TCPOPTSTRIP.c25
-rw-r--r--net/netfilter/xt_TEE.c2
-rw-r--r--net/netfilter/xt_TPROXY.c169
-rw-r--r--net/netfilter/xt_addrtype.c29
-rw-r--r--net/netfilter/xt_bpf.c74
-rw-r--r--net/netfilter/xt_cgroup.c72
-rw-r--r--net/netfilter/xt_connbytes.c6
-rw-r--r--net/netfilter/xt_connlabel.c99
-rw-r--r--net/netfilter/xt_connlimit.c320
-rw-r--r--net/netfilter/xt_connmark.c3
-rw-r--r--net/netfilter/xt_conntrack.c1
-rw-r--r--net/netfilter/xt_hashlimit.c62
-rw-r--r--net/netfilter/xt_ipcomp.c111
-rw-r--r--net/netfilter/xt_l2tp.c354
-rw-r--r--net/netfilter/xt_limit.c1
-rw-r--r--net/netfilter/xt_nfacct.c5
-rw-r--r--net/netfilter/xt_osf.c11
-rw-r--r--net/netfilter/xt_rateest.c2
-rw-r--r--net/netfilter/xt_recent.c16
-rw-r--r--net/netfilter/xt_repldata.h22
-rw-r--r--net/netfilter/xt_set.c220
-rw-r--r--net/netfilter/xt_socket.c175
-rw-r--r--net/netfilter/xt_statistic.c2
151 files changed, 21766 insertions, 8792 deletions
diff --git a/net/netfilter/Kconfig b/net/netfilter/Kconfig
index 49e96df5fbc..e9410d17619 100644
--- a/net/netfilter/Kconfig
+++ b/net/netfilter/Kconfig
@@ -124,9 +124,14 @@ config NF_CONNTRACK_TIMESTAMP
If unsure, say `N'.
+config NF_CONNTRACK_LABELS
+ bool
+ help
+ This option enables support for assigning user-defined flag bits
+ to connection tracking entries. It selected by the connlabel match.
+
config NF_CT_PROTO_DCCP
- tristate 'DCCP protocol connection tracking support (EXPERIMENTAL)'
- depends on EXPERIMENTAL
+ tristate 'DCCP protocol connection tracking support'
depends on NETFILTER_ADVANCED
default IP_DCCP
help
@@ -139,8 +144,7 @@ config NF_CT_PROTO_GRE
tristate
config NF_CT_PROTO_SCTP
- tristate 'SCTP protocol connection tracking support (EXPERIMENTAL)'
- depends on EXPERIMENTAL
+ tristate 'SCTP protocol connection tracking support'
depends on NETFILTER_ADVANCED
default IP_SCTP
help
@@ -281,8 +285,7 @@ config NF_CONNTRACK_PPTP
To compile it as a module, choose M here. If unsure, say N.
config NF_CONNTRACK_SANE
- tristate "SANE protocol support (EXPERIMENTAL)"
- depends on EXPERIMENTAL
+ tristate "SANE protocol support"
depends on NETFILTER_ADVANCED
help
SANE is a protocol for remote access to scanners as implemented
@@ -405,22 +408,131 @@ config NF_NAT_TFTP
depends on NF_CONNTRACK && NF_NAT
default NF_NAT && NF_CONNTRACK_TFTP
+config NETFILTER_SYNPROXY
+ tristate
+
endif # NF_CONNTRACK
-# transparent proxy support
-config NETFILTER_TPROXY
- tristate "Transparent proxying support (EXPERIMENTAL)"
- depends on EXPERIMENTAL
- depends on IP_NF_MANGLE
- depends on NETFILTER_ADVANCED
+config NF_TABLES
+ select NETFILTER_NETLINK
+ tristate "Netfilter nf_tables support"
help
- This option enables transparent proxying support, that is,
- support for handling non-locally bound IPv4 TCP and UDP sockets.
- For it to work you will have to configure certain iptables rules
- and use policy routing. For more information on how to set it up
- see Documentation/networking/tproxy.txt.
+ nftables is the new packet classification framework that intends to
+ replace the existing {ip,ip6,arp,eb}_tables infrastructure. It
+ provides a pseudo-state machine with an extensible instruction-set
+ (also known as expressions) that the userspace 'nft' utility
+ (http://www.netfilter.org/projects/nftables) uses to build the
+ rule-set. It also comes with the generic set infrastructure that
+ allows you to construct mappings between matchings and actions
+ for performance lookups.
- To compile it as a module, choose M here. If unsure, say N.
+ To compile it as a module, choose M here.
+
+config NF_TABLES_INET
+ depends on NF_TABLES && IPV6
+ select NF_TABLES_IPV4
+ select NF_TABLES_IPV6
+ tristate "Netfilter nf_tables mixed IPv4/IPv6 tables support"
+ help
+ This option enables support for a mixed IPv4/IPv6 "inet" table.
+
+config NFT_EXTHDR
+ depends on NF_TABLES
+ tristate "Netfilter nf_tables IPv6 exthdr module"
+ help
+ This option adds the "exthdr" expression that you can use to match
+ IPv6 extension headers.
+
+config NFT_META
+ depends on NF_TABLES
+ tristate "Netfilter nf_tables meta module"
+ help
+ This option adds the "meta" expression that you can use to match and
+ to set packet metainformation such as the packet mark.
+
+config NFT_CT
+ depends on NF_TABLES
+ depends on NF_CONNTRACK
+ tristate "Netfilter nf_tables conntrack module"
+ help
+ This option adds the "meta" expression that you can use to match
+ connection tracking information such as the flow state.
+
+config NFT_RBTREE
+ depends on NF_TABLES
+ tristate "Netfilter nf_tables rbtree set module"
+ help
+ This option adds the "rbtree" set type (Red Black tree) that is used
+ to build interval-based sets.
+
+config NFT_HASH
+ depends on NF_TABLES
+ tristate "Netfilter nf_tables hash set module"
+ help
+ This option adds the "hash" set type that is used to build one-way
+ mappings between matchings and actions.
+
+config NFT_COUNTER
+ depends on NF_TABLES
+ tristate "Netfilter nf_tables counter module"
+ help
+ This option adds the "counter" expression that you can use to
+ include packet and byte counters in a rule.
+
+config NFT_LOG
+ depends on NF_TABLES
+ tristate "Netfilter nf_tables log module"
+ help
+ This option adds the "log" expression that you can use to log
+ packets matching some criteria.
+
+config NFT_LIMIT
+ depends on NF_TABLES
+ tristate "Netfilter nf_tables limit module"
+ help
+ This option adds the "limit" expression that you can use to
+ ratelimit rule matchings.
+
+config NFT_NAT
+ depends on NF_TABLES
+ depends on NF_CONNTRACK
+ depends on NF_NAT
+ tristate "Netfilter nf_tables nat module"
+ help
+ This option adds the "nat" expression that you can use to perform
+ typical Network Address Translation (NAT) packet transformations.
+
+config NFT_QUEUE
+ depends on NF_TABLES
+ depends on NETFILTER_XTABLES
+ depends on NETFILTER_NETLINK_QUEUE
+ tristate "Netfilter nf_tables queue module"
+ help
+ This is required if you intend to use the userspace queueing
+ infrastructure (also known as NFQUEUE) from nftables.
+
+config NFT_REJECT
+ depends on NF_TABLES
+ default m if NETFILTER_ADVANCED=n
+ tristate "Netfilter nf_tables reject support"
+ help
+ This option adds the "reject" expression that you can use to
+ explicitly deny and notify via TCP reset/ICMP informational errors
+ unallowed traffic.
+
+config NFT_REJECT_INET
+ depends on NF_TABLES_INET
+ default NFT_REJECT
+ tristate
+
+config NFT_COMPAT
+ depends on NF_TABLES
+ depends on NETFILTER_XTABLES
+ tristate "Netfilter x_tables over nf_tables module"
+ help
+ This is required if you intend to use any of existing
+ x_tables match/target extensions over the nf_tables
+ framework.
config NETFILTER_XTABLES
tristate "Netfilter Xtables support (required for ip_tables)"
@@ -718,11 +830,10 @@ config NETFILTER_XT_TARGET_TEE
this clone be rerouted to another nexthop.
config NETFILTER_XT_TARGET_TPROXY
- tristate '"TPROXY" target support (EXPERIMENTAL)'
- depends on EXPERIMENTAL
- depends on NETFILTER_TPROXY
+ tristate '"TPROXY" target transparent proxying support'
depends on NETFILTER_XTABLES
depends on NETFILTER_ADVANCED
+ depends on IP_NF_MANGLE
select NF_DEFRAG_IPV4
select NF_DEFRAG_IPV6 if IP6_NF_IPTABLES
help
@@ -730,6 +841,9 @@ config NETFILTER_XT_TARGET_TPROXY
REDIRECT. It can only be used in the mangle table and is useful
to redirect traffic to a transparent proxy. It does _not_ depend
on Netfilter connection tracking and NAT, unlike REDIRECT.
+ For it to work you will have to configure certain iptables rules
+ and use policy routing. For more information on how to set it up
+ see Documentation/networking/tproxy.txt.
To compile it as a module, choose M here. If unsure, say N.
@@ -783,8 +897,7 @@ config NETFILTER_XT_TARGET_TCPMSS
To compile it as a module, choose M here. If unsure, say N.
config NETFILTER_XT_TARGET_TCPOPTSTRIP
- tristate '"TCPOPTSTRIP" target support (EXPERIMENTAL)'
- depends on EXPERIMENTAL
+ tristate '"TCPOPTSTRIP" target support'
depends on IP_NF_MANGLE || IP6_NF_MANGLE
depends on NETFILTER_ADVANCED
help
@@ -805,6 +918,25 @@ config NETFILTER_XT_MATCH_ADDRTYPE
If you want to compile it as a module, say M here and read
<file:Documentation/kbuild/modules.txt>. If unsure, say `N'.
+config NETFILTER_XT_MATCH_BPF
+ tristate '"bpf" match support'
+ depends on NETFILTER_ADVANCED
+ help
+ BPF matching applies a linux socket filter to each packet and
+ accepts those for which the filter returns non-zero.
+
+ To compile it as a module, choose M here. If unsure, say N.
+
+config NETFILTER_XT_MATCH_CGROUP
+ tristate '"control group" match support'
+ depends on NETFILTER_ADVANCED
+ depends on CGROUPS
+ select CGROUP_NET_CLASSID
+ ---help---
+ Socket/process control group matching allows you to match locally
+ generated packets based on which net_cls control group processes
+ belong to.
+
config NETFILTER_XT_MATCH_CLUSTER
tristate '"cluster" match support'
depends on NF_CONNTRACK
@@ -842,8 +974,21 @@ config NETFILTER_XT_MATCH_CONNBYTES
If you want to compile it as a module, say M here and read
<file:Documentation/kbuild/modules.txt>. If unsure, say `N'.
+config NETFILTER_XT_MATCH_CONNLABEL
+ tristate '"connlabel" match support'
+ select NF_CONNTRACK_LABELS
+ depends on NF_CONNTRACK
+ depends on NETFILTER_ADVANCED
+ ---help---
+ This match allows you to test and assign userspace-defined labels names
+ to a connection. The kernel only stores bit values - mapping
+ names to bits is done by userspace.
+
+ Unlike connmark, more than 32 flag bits may be assigned to a
+ connection simultaneously.
+
config NETFILTER_XT_MATCH_CONNLIMIT
- tristate '"connlimit" match support"'
+ tristate '"connlimit" match support'
depends on NF_CONNTRACK
depends on NETFILTER_ADVANCED
---help---
@@ -969,6 +1114,15 @@ config NETFILTER_XT_MATCH_HL
in the IPv6 header, or the time-to-live field in the IPv4
header of the packet.
+config NETFILTER_XT_MATCH_IPCOMP
+ tristate '"ipcomp" match support'
+ depends on NETFILTER_ADVANCED
+ help
+ This match extension allows you to match a range of CPIs(16 bits)
+ inside IPComp header of IPSec packets.
+
+ To compile it as a module, choose M here. If unsure, say N.
+
config NETFILTER_XT_MATCH_IPRANGE
tristate '"iprange" address range match support'
depends on NETFILTER_ADVANCED
@@ -989,6 +1143,16 @@ config NETFILTER_XT_MATCH_IPVS
If unsure, say N.
+config NETFILTER_XT_MATCH_L2TP
+ tristate '"l2tp" match support'
+ depends on NETFILTER_ADVANCED
+ default L2TP
+ ---help---
+ This option adds an "L2TP" match, which allows you to match against
+ L2TP protocol header fields.
+
+ To compile it as a module, choose M here. If unsure, say N.
+
config NETFILTER_XT_MATCH_LENGTH
tristate '"length" match support'
depends on NETFILTER_ADVANCED
@@ -1145,8 +1309,7 @@ config NETFILTER_XT_MATCH_RECENT
Official Website: <http://snowman.net/projects/ipt_recent/>
config NETFILTER_XT_MATCH_SCTP
- tristate '"sctp" protocol match support (EXPERIMENTAL)'
- depends on EXPERIMENTAL
+ tristate '"sctp" protocol match support'
depends on NETFILTER_ADVANCED
default IP_SCTP
help
@@ -1158,12 +1321,11 @@ config NETFILTER_XT_MATCH_SCTP
<file:Documentation/kbuild/modules.txt>. If unsure, say `N'.
config NETFILTER_XT_MATCH_SOCKET
- tristate '"socket" match support (EXPERIMENTAL)'
- depends on EXPERIMENTAL
- depends on NETFILTER_TPROXY
+ tristate '"socket" match support'
depends on NETFILTER_XTABLES
depends on NETFILTER_ADVANCED
depends on !NF_CONNTRACK || NF_CONNTRACK
+ depends on (IPV6 || IPV6=n)
select NF_DEFRAG_IPV4
select NF_DEFRAG_IPV6 if IP6_NF_IPTABLES
help
diff --git a/net/netfilter/Makefile b/net/netfilter/Makefile
index 32596978df1..bffdad774da 100644
--- a/net/netfilter/Makefile
+++ b/net/netfilter/Makefile
@@ -1,9 +1,10 @@
netfilter-objs := core.o nf_log.o nf_queue.o nf_sockopt.o
-nf_conntrack-y := nf_conntrack_core.o nf_conntrack_standalone.o nf_conntrack_expect.o nf_conntrack_helper.o nf_conntrack_proto.o nf_conntrack_l3proto_generic.o nf_conntrack_proto_generic.o nf_conntrack_proto_tcp.o nf_conntrack_proto_udp.o nf_conntrack_extend.o nf_conntrack_acct.o
+nf_conntrack-y := nf_conntrack_core.o nf_conntrack_standalone.o nf_conntrack_expect.o nf_conntrack_helper.o nf_conntrack_proto.o nf_conntrack_l3proto_generic.o nf_conntrack_proto_generic.o nf_conntrack_proto_tcp.o nf_conntrack_proto_udp.o nf_conntrack_extend.o nf_conntrack_acct.o nf_conntrack_seqadj.o
nf_conntrack-$(CONFIG_NF_CONNTRACK_TIMEOUT) += nf_conntrack_timeout.o
nf_conntrack-$(CONFIG_NF_CONNTRACK_TIMESTAMP) += nf_conntrack_timestamp.o
nf_conntrack-$(CONFIG_NF_CONNTRACK_EVENTS) += nf_conntrack_ecache.o
+nf_conntrack-$(CONFIG_NF_CONNTRACK_LABELS) += nf_conntrack_labels.o
obj-$(CONFIG_NETFILTER) = netfilter.o
@@ -60,8 +61,29 @@ obj-$(CONFIG_NF_NAT_IRC) += nf_nat_irc.o
obj-$(CONFIG_NF_NAT_SIP) += nf_nat_sip.o
obj-$(CONFIG_NF_NAT_TFTP) += nf_nat_tftp.o
-# transparent proxy support
-obj-$(CONFIG_NETFILTER_TPROXY) += nf_tproxy_core.o
+# SYNPROXY
+obj-$(CONFIG_NETFILTER_SYNPROXY) += nf_synproxy_core.o
+
+# nf_tables
+nf_tables-objs += nf_tables_core.o nf_tables_api.o
+nf_tables-objs += nft_immediate.o nft_cmp.o nft_lookup.o
+nf_tables-objs += nft_bitwise.o nft_byteorder.o nft_payload.o
+
+obj-$(CONFIG_NF_TABLES) += nf_tables.o
+obj-$(CONFIG_NF_TABLES_INET) += nf_tables_inet.o
+obj-$(CONFIG_NFT_COMPAT) += nft_compat.o
+obj-$(CONFIG_NFT_EXTHDR) += nft_exthdr.o
+obj-$(CONFIG_NFT_META) += nft_meta.o
+obj-$(CONFIG_NFT_CT) += nft_ct.o
+obj-$(CONFIG_NFT_LIMIT) += nft_limit.o
+obj-$(CONFIG_NFT_NAT) += nft_nat.o
+obj-$(CONFIG_NFT_QUEUE) += nft_queue.o
+obj-$(CONFIG_NFT_REJECT) += nft_reject.o
+obj-$(CONFIG_NFT_REJECT_INET) += nft_reject_inet.o
+obj-$(CONFIG_NFT_RBTREE) += nft_rbtree.o
+obj-$(CONFIG_NFT_HASH) += nft_hash.o
+obj-$(CONFIG_NFT_COUNTER) += nft_counter.o
+obj-$(CONFIG_NFT_LOG) += nft_log.o
# generic X tables
obj-$(CONFIG_NETFILTER_XTABLES) += x_tables.o xt_tcpudp.o
@@ -98,9 +120,11 @@ obj-$(CONFIG_NETFILTER_XT_TARGET_IDLETIMER) += xt_IDLETIMER.o
# matches
obj-$(CONFIG_NETFILTER_XT_MATCH_ADDRTYPE) += xt_addrtype.o
+obj-$(CONFIG_NETFILTER_XT_MATCH_BPF) += xt_bpf.o
obj-$(CONFIG_NETFILTER_XT_MATCH_CLUSTER) += xt_cluster.o
obj-$(CONFIG_NETFILTER_XT_MATCH_COMMENT) += xt_comment.o
obj-$(CONFIG_NETFILTER_XT_MATCH_CONNBYTES) += xt_connbytes.o
+obj-$(CONFIG_NETFILTER_XT_MATCH_CONNLABEL) += xt_connlabel.o
obj-$(CONFIG_NETFILTER_XT_MATCH_CONNLIMIT) += xt_connlimit.o
obj-$(CONFIG_NETFILTER_XT_MATCH_CONNTRACK) += xt_conntrack.o
obj-$(CONFIG_NETFILTER_XT_MATCH_CPU) += xt_cpu.o
@@ -112,8 +136,10 @@ obj-$(CONFIG_NETFILTER_XT_MATCH_ESP) += xt_esp.o
obj-$(CONFIG_NETFILTER_XT_MATCH_HASHLIMIT) += xt_hashlimit.o
obj-$(CONFIG_NETFILTER_XT_MATCH_HELPER) += xt_helper.o
obj-$(CONFIG_NETFILTER_XT_MATCH_HL) += xt_hl.o
+obj-$(CONFIG_NETFILTER_XT_MATCH_IPCOMP) += xt_ipcomp.o
obj-$(CONFIG_NETFILTER_XT_MATCH_IPRANGE) += xt_iprange.o
obj-$(CONFIG_NETFILTER_XT_MATCH_IPVS) += xt_ipvs.o
+obj-$(CONFIG_NETFILTER_XT_MATCH_L2TP) += xt_l2tp.o
obj-$(CONFIG_NETFILTER_XT_MATCH_LENGTH) += xt_length.o
obj-$(CONFIG_NETFILTER_XT_MATCH_LIMIT) += xt_limit.o
obj-$(CONFIG_NETFILTER_XT_MATCH_MAC) += xt_mac.o
@@ -121,6 +147,7 @@ obj-$(CONFIG_NETFILTER_XT_MATCH_MULTIPORT) += xt_multiport.o
obj-$(CONFIG_NETFILTER_XT_MATCH_NFACCT) += xt_nfacct.o
obj-$(CONFIG_NETFILTER_XT_MATCH_OSF) += xt_osf.o
obj-$(CONFIG_NETFILTER_XT_MATCH_OWNER) += xt_owner.o
+obj-$(CONFIG_NETFILTER_XT_MATCH_CGROUP) += xt_cgroup.o
obj-$(CONFIG_NETFILTER_XT_MATCH_PHYSDEV) += xt_physdev.o
obj-$(CONFIG_NETFILTER_XT_MATCH_PKTTYPE) += xt_pkttype.o
obj-$(CONFIG_NETFILTER_XT_MATCH_POLICY) += xt_policy.o
diff --git a/net/netfilter/core.c b/net/netfilter/core.c
index a9c488b6c50..1fbab0cdd30 100644
--- a/net/netfilter/core.c
+++ b/net/netfilter/core.c
@@ -5,6 +5,7 @@
* way.
*
* Rusty Russell (C)2000 -- This code is GPL.
+ * Patrick McHardy (c) 2006-2012
*/
#include <linux/kernel.h>
#include <linux/netfilter.h>
@@ -29,6 +30,8 @@ static DEFINE_MUTEX(afinfo_mutex);
const struct nf_afinfo __rcu *nf_afinfo[NFPROTO_NUMPROTO] __read_mostly;
EXPORT_SYMBOL(nf_afinfo);
+const struct nf_ipv6_ops __rcu *nf_ipv6_ops __read_mostly;
+EXPORT_SYMBOL_GPL(nf_ipv6_ops);
int nf_register_afinfo(const struct nf_afinfo *afinfo)
{
@@ -143,7 +146,7 @@ unsigned int nf_iterate(struct list_head *head,
/* Optimization: we don't need to hold module
reference here, since function can't sleep. --RR */
repeat:
- verdict = (*elemp)->hook(hook, skb, indev, outdev, okfn);
+ verdict = (*elemp)->hook(*elemp, skb, indev, outdev, okfn);
if (verdict != NF_ACCEPT) {
#ifdef CONFIG_NETFILTER_DEBUG
if (unlikely((verdict & NF_VERDICT_MASK)
@@ -231,12 +234,13 @@ EXPORT_SYMBOL(skb_make_writable);
/* This does not belong here, but locally generated errors need it if connection
tracking in use: without this, connection may not be in hash table, and hence
manufactured ICMP or RST packets will not be associated with it. */
-void (*ip_ct_attach)(struct sk_buff *, struct sk_buff *) __rcu __read_mostly;
+void (*ip_ct_attach)(struct sk_buff *, const struct sk_buff *)
+ __rcu __read_mostly;
EXPORT_SYMBOL(ip_ct_attach);
-void nf_ct_attach(struct sk_buff *new, struct sk_buff *skb)
+void nf_ct_attach(struct sk_buff *new, const struct sk_buff *skb)
{
- void (*attach)(struct sk_buff *, struct sk_buff *);
+ void (*attach)(struct sk_buff *, const struct sk_buff *);
if (skb->nfct) {
rcu_read_lock();
@@ -276,25 +280,51 @@ void (*nf_nat_decode_session_hook)(struct sk_buff *, struct flowi *);
EXPORT_SYMBOL(nf_nat_decode_session_hook);
#endif
+static int __net_init netfilter_net_init(struct net *net)
+{
#ifdef CONFIG_PROC_FS
-struct proc_dir_entry *proc_net_netfilter;
-EXPORT_SYMBOL(proc_net_netfilter);
+ net->nf.proc_netfilter = proc_net_mkdir(net, "netfilter",
+ net->proc_net);
+ if (!net->nf.proc_netfilter) {
+ if (!net_eq(net, &init_net))
+ pr_err("cannot create netfilter proc entry");
+
+ return -ENOMEM;
+ }
#endif
+ return 0;
+}
+
+static void __net_exit netfilter_net_exit(struct net *net)
+{
+ remove_proc_entry("netfilter", net->proc_net);
+}
-void __init netfilter_init(void)
+static struct pernet_operations netfilter_net_ops = {
+ .init = netfilter_net_init,
+ .exit = netfilter_net_exit,
+};
+
+int __init netfilter_init(void)
{
- int i, h;
+ int i, h, ret;
+
for (i = 0; i < ARRAY_SIZE(nf_hooks); i++) {
for (h = 0; h < NF_MAX_HOOKS; h++)
INIT_LIST_HEAD(&nf_hooks[i][h]);
}
-#ifdef CONFIG_PROC_FS
- proc_net_netfilter = proc_mkdir("netfilter", init_net.proc_net);
- if (!proc_net_netfilter)
- panic("cannot create netfilter proc entry");
-#endif
+ ret = register_pernet_subsys(&netfilter_net_ops);
+ if (ret < 0)
+ goto err;
- if (netfilter_log_init() < 0)
- panic("cannot initialize nf_log");
+ ret = netfilter_log_init();
+ if (ret < 0)
+ goto err_pernet;
+
+ return 0;
+err_pernet:
+ unregister_pernet_subsys(&netfilter_net_ops);
+err:
+ return ret;
}
diff --git a/net/netfilter/ipset/Kconfig b/net/netfilter/ipset/Kconfig
index ba36c283d83..2f7f5c32c6f 100644
--- a/net/netfilter/ipset/Kconfig
+++ b/net/netfilter/ipset/Kconfig
@@ -1,7 +1,7 @@
menuconfig IP_SET
tristate "IP set support"
depends on INET && NETFILTER
- depends on NETFILTER_NETLINK
+ select NETFILTER_NETLINK
help
This option adds IP set support to the kernel.
In order to define and use the sets, you need the userspace utility
@@ -21,7 +21,7 @@ config IP_SET_MAX
You can define here default value of the maximum number
of IP sets for the kernel.
- The value can be overriden by the 'max_sets' module
+ The value can be overridden by the 'max_sets' module
parameter of the 'ip_set' module.
config IP_SET_BITMAP_IP
@@ -61,6 +61,15 @@ config IP_SET_HASH_IP
To compile it as a module, choose M here. If unsure, say N.
+config IP_SET_HASH_IPMARK
+ tristate "hash:ip,mark set support"
+ depends on IP_SET
+ help
+ This option adds the hash:ip,mark set type support, by which one
+ can store IPv4/IPv6 address and mark pairs.
+
+ To compile it as a module, choose M here. If unsure, say N.
+
config IP_SET_HASH_IPPORT
tristate "hash:ip,port set support"
depends on IP_SET
@@ -90,6 +99,15 @@ config IP_SET_HASH_IPPORTNET
To compile it as a module, choose M here. If unsure, say N.
+config IP_SET_HASH_NETPORTNET
+ tristate "hash:net,port,net set support"
+ depends on IP_SET
+ help
+ This option adds the hash:net,port,net set type support, by which
+ one can store two IPv4/IPv6 subnets, and a protocol/port in a set.
+
+ To compile it as a module, choose M here. If unsure, say N.
+
config IP_SET_HASH_NET
tristate "hash:net set support"
depends on IP_SET
@@ -99,6 +117,15 @@ config IP_SET_HASH_NET
To compile it as a module, choose M here. If unsure, say N.
+config IP_SET_HASH_NETNET
+ tristate "hash:net,net set support"
+ depends on IP_SET
+ help
+ This option adds the hash:net,net set type support, by which
+ one can store IPv4/IPv6 network address/prefix pairs in a set.
+
+ To compile it as a module, choose M here. If unsure, say N.
+
config IP_SET_HASH_NETPORT
tristate "hash:net,port set support"
depends on IP_SET
diff --git a/net/netfilter/ipset/Makefile b/net/netfilter/ipset/Makefile
index 6e965ecd544..231f10196cb 100644
--- a/net/netfilter/ipset/Makefile
+++ b/net/netfilter/ipset/Makefile
@@ -14,12 +14,15 @@ obj-$(CONFIG_IP_SET_BITMAP_PORT) += ip_set_bitmap_port.o
# hash types
obj-$(CONFIG_IP_SET_HASH_IP) += ip_set_hash_ip.o
+obj-$(CONFIG_IP_SET_HASH_IPMARK) += ip_set_hash_ipmark.o
obj-$(CONFIG_IP_SET_HASH_IPPORT) += ip_set_hash_ipport.o
obj-$(CONFIG_IP_SET_HASH_IPPORTIP) += ip_set_hash_ipportip.o
obj-$(CONFIG_IP_SET_HASH_IPPORTNET) += ip_set_hash_ipportnet.o
obj-$(CONFIG_IP_SET_HASH_NET) += ip_set_hash_net.o
obj-$(CONFIG_IP_SET_HASH_NETPORT) += ip_set_hash_netport.o
obj-$(CONFIG_IP_SET_HASH_NETIFACE) += ip_set_hash_netiface.o
+obj-$(CONFIG_IP_SET_HASH_NETNET) += ip_set_hash_netnet.o
+obj-$(CONFIG_IP_SET_HASH_NETPORTNET) += ip_set_hash_netportnet.o
# list types
obj-$(CONFIG_IP_SET_LIST_SET) += ip_set_list_set.o
diff --git a/net/netfilter/ipset/ip_set_bitmap_gen.h b/net/netfilter/ipset/ip_set_bitmap_gen.h
new file mode 100644
index 00000000000..f2c7d83dc23
--- /dev/null
+++ b/net/netfilter/ipset/ip_set_bitmap_gen.h
@@ -0,0 +1,289 @@
+/* Copyright (C) 2013 Jozsef Kadlecsik <kadlec@blackhole.kfki.hu>
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2 as
+ * published by the Free Software Foundation.
+ */
+
+#ifndef __IP_SET_BITMAP_IP_GEN_H
+#define __IP_SET_BITMAP_IP_GEN_H
+
+#define mtype_do_test IPSET_TOKEN(MTYPE, _do_test)
+#define mtype_gc_test IPSET_TOKEN(MTYPE, _gc_test)
+#define mtype_is_filled IPSET_TOKEN(MTYPE, _is_filled)
+#define mtype_do_add IPSET_TOKEN(MTYPE, _do_add)
+#define mtype_ext_cleanup IPSET_TOKEN(MTYPE, _ext_cleanup)
+#define mtype_do_del IPSET_TOKEN(MTYPE, _do_del)
+#define mtype_do_list IPSET_TOKEN(MTYPE, _do_list)
+#define mtype_do_head IPSET_TOKEN(MTYPE, _do_head)
+#define mtype_adt_elem IPSET_TOKEN(MTYPE, _adt_elem)
+#define mtype_add_timeout IPSET_TOKEN(MTYPE, _add_timeout)
+#define mtype_gc_init IPSET_TOKEN(MTYPE, _gc_init)
+#define mtype_kadt IPSET_TOKEN(MTYPE, _kadt)
+#define mtype_uadt IPSET_TOKEN(MTYPE, _uadt)
+#define mtype_destroy IPSET_TOKEN(MTYPE, _destroy)
+#define mtype_flush IPSET_TOKEN(MTYPE, _flush)
+#define mtype_head IPSET_TOKEN(MTYPE, _head)
+#define mtype_same_set IPSET_TOKEN(MTYPE, _same_set)
+#define mtype_elem IPSET_TOKEN(MTYPE, _elem)
+#define mtype_test IPSET_TOKEN(MTYPE, _test)
+#define mtype_add IPSET_TOKEN(MTYPE, _add)
+#define mtype_del IPSET_TOKEN(MTYPE, _del)
+#define mtype_list IPSET_TOKEN(MTYPE, _list)
+#define mtype_gc IPSET_TOKEN(MTYPE, _gc)
+#define mtype MTYPE
+
+#define get_ext(set, map, id) ((map)->extensions + (set)->dsize * (id))
+
+static void
+mtype_gc_init(struct ip_set *set, void (*gc)(unsigned long ul_set))
+{
+ struct mtype *map = set->data;
+
+ init_timer(&map->gc);
+ map->gc.data = (unsigned long) set;
+ map->gc.function = gc;
+ map->gc.expires = jiffies + IPSET_GC_PERIOD(set->timeout) * HZ;
+ add_timer(&map->gc);
+}
+
+static void
+mtype_ext_cleanup(struct ip_set *set)
+{
+ struct mtype *map = set->data;
+ u32 id;
+
+ for (id = 0; id < map->elements; id++)
+ if (test_bit(id, map->members))
+ ip_set_ext_destroy(set, get_ext(set, map, id));
+}
+
+static void
+mtype_destroy(struct ip_set *set)
+{
+ struct mtype *map = set->data;
+
+ if (SET_WITH_TIMEOUT(set))
+ del_timer_sync(&map->gc);
+
+ ip_set_free(map->members);
+ if (set->dsize) {
+ if (set->extensions & IPSET_EXT_DESTROY)
+ mtype_ext_cleanup(set);
+ ip_set_free(map->extensions);
+ }
+ kfree(map);
+
+ set->data = NULL;
+}
+
+static void
+mtype_flush(struct ip_set *set)
+{
+ struct mtype *map = set->data;
+
+ if (set->extensions & IPSET_EXT_DESTROY)
+ mtype_ext_cleanup(set);
+ memset(map->members, 0, map->memsize);
+}
+
+static int
+mtype_head(struct ip_set *set, struct sk_buff *skb)
+{
+ const struct mtype *map = set->data;
+ struct nlattr *nested;
+
+ nested = ipset_nest_start(skb, IPSET_ATTR_DATA);
+ if (!nested)
+ goto nla_put_failure;
+ if (mtype_do_head(skb, map) ||
+ nla_put_net32(skb, IPSET_ATTR_REFERENCES, htonl(set->ref - 1)) ||
+ nla_put_net32(skb, IPSET_ATTR_MEMSIZE,
+ htonl(sizeof(*map) +
+ map->memsize +
+ set->dsize * map->elements)))
+ goto nla_put_failure;
+ if (unlikely(ip_set_put_flags(skb, set)))
+ goto nla_put_failure;
+ ipset_nest_end(skb, nested);
+
+ return 0;
+nla_put_failure:
+ return -EMSGSIZE;
+}
+
+static int
+mtype_test(struct ip_set *set, void *value, const struct ip_set_ext *ext,
+ struct ip_set_ext *mext, u32 flags)
+{
+ struct mtype *map = set->data;
+ const struct mtype_adt_elem *e = value;
+ void *x = get_ext(set, map, e->id);
+ int ret = mtype_do_test(e, map, set->dsize);
+
+ if (ret <= 0)
+ return ret;
+ if (SET_WITH_TIMEOUT(set) &&
+ ip_set_timeout_expired(ext_timeout(x, set)))
+ return 0;
+ if (SET_WITH_COUNTER(set))
+ ip_set_update_counter(ext_counter(x, set), ext, mext, flags);
+ return 1;
+}
+
+static int
+mtype_add(struct ip_set *set, void *value, const struct ip_set_ext *ext,
+ struct ip_set_ext *mext, u32 flags)
+{
+ struct mtype *map = set->data;
+ const struct mtype_adt_elem *e = value;
+ void *x = get_ext(set, map, e->id);
+ int ret = mtype_do_add(e, map, flags, set->dsize);
+
+ if (ret == IPSET_ADD_FAILED) {
+ if (SET_WITH_TIMEOUT(set) &&
+ ip_set_timeout_expired(ext_timeout(x, set)))
+ ret = 0;
+ else if (!(flags & IPSET_FLAG_EXIST))
+ return -IPSET_ERR_EXIST;
+ /* Element is re-added, cleanup extensions */
+ ip_set_ext_destroy(set, x);
+ }
+
+ if (SET_WITH_TIMEOUT(set))
+#ifdef IP_SET_BITMAP_STORED_TIMEOUT
+ mtype_add_timeout(ext_timeout(x, set), e, ext, set, map, ret);
+#else
+ ip_set_timeout_set(ext_timeout(x, set), ext->timeout);
+#endif
+
+ if (SET_WITH_COUNTER(set))
+ ip_set_init_counter(ext_counter(x, set), ext);
+ if (SET_WITH_COMMENT(set))
+ ip_set_init_comment(ext_comment(x, set), ext);
+ return 0;
+}
+
+static int
+mtype_del(struct ip_set *set, void *value, const struct ip_set_ext *ext,
+ struct ip_set_ext *mext, u32 flags)
+{
+ struct mtype *map = set->data;
+ const struct mtype_adt_elem *e = value;
+ void *x = get_ext(set, map, e->id);
+
+ if (mtype_do_del(e, map))
+ return -IPSET_ERR_EXIST;
+
+ ip_set_ext_destroy(set, x);
+ if (SET_WITH_TIMEOUT(set) &&
+ ip_set_timeout_expired(ext_timeout(x, set)))
+ return -IPSET_ERR_EXIST;
+
+ return 0;
+}
+
+#ifndef IP_SET_BITMAP_STORED_TIMEOUT
+static inline bool
+mtype_is_filled(const struct mtype_elem *x)
+{
+ return true;
+}
+#endif
+
+static int
+mtype_list(const struct ip_set *set,
+ struct sk_buff *skb, struct netlink_callback *cb)
+{
+ struct mtype *map = set->data;
+ struct nlattr *adt, *nested;
+ void *x;
+ u32 id, first = cb->args[IPSET_CB_ARG0];
+
+ adt = ipset_nest_start(skb, IPSET_ATTR_ADT);
+ if (!adt)
+ return -EMSGSIZE;
+ for (; cb->args[IPSET_CB_ARG0] < map->elements;
+ cb->args[IPSET_CB_ARG0]++) {
+ id = cb->args[IPSET_CB_ARG0];
+ x = get_ext(set, map, id);
+ if (!test_bit(id, map->members) ||
+ (SET_WITH_TIMEOUT(set) &&
+#ifdef IP_SET_BITMAP_STORED_TIMEOUT
+ mtype_is_filled((const struct mtype_elem *) x) &&
+#endif
+ ip_set_timeout_expired(ext_timeout(x, set))))
+ continue;
+ nested = ipset_nest_start(skb, IPSET_ATTR_DATA);
+ if (!nested) {
+ if (id == first) {
+ nla_nest_cancel(skb, adt);
+ return -EMSGSIZE;
+ } else
+ goto nla_put_failure;
+ }
+ if (mtype_do_list(skb, map, id, set->dsize))
+ goto nla_put_failure;
+ if (ip_set_put_extensions(skb, set, x,
+ mtype_is_filled((const struct mtype_elem *) x)))
+ goto nla_put_failure;
+ ipset_nest_end(skb, nested);
+ }
+ ipset_nest_end(skb, adt);
+
+ /* Set listing finished */
+ cb->args[IPSET_CB_ARG0] = 0;
+
+ return 0;
+
+nla_put_failure:
+ nla_nest_cancel(skb, nested);
+ if (unlikely(id == first)) {
+ cb->args[IPSET_CB_ARG0] = 0;
+ return -EMSGSIZE;
+ }
+ ipset_nest_end(skb, adt);
+ return 0;
+}
+
+static void
+mtype_gc(unsigned long ul_set)
+{
+ struct ip_set *set = (struct ip_set *) ul_set;
+ struct mtype *map = set->data;
+ void *x;
+ u32 id;
+
+ /* We run parallel with other readers (test element)
+ * but adding/deleting new entries is locked out */
+ read_lock_bh(&set->lock);
+ for (id = 0; id < map->elements; id++)
+ if (mtype_gc_test(id, map, set->dsize)) {
+ x = get_ext(set, map, id);
+ if (ip_set_timeout_expired(ext_timeout(x, set))) {
+ clear_bit(id, map->members);
+ ip_set_ext_destroy(set, x);
+ }
+ }
+ read_unlock_bh(&set->lock);
+
+ map->gc.expires = jiffies + IPSET_GC_PERIOD(set->timeout) * HZ;
+ add_timer(&map->gc);
+}
+
+static const struct ip_set_type_variant mtype = {
+ .kadt = mtype_kadt,
+ .uadt = mtype_uadt,
+ .adt = {
+ [IPSET_ADD] = mtype_add,
+ [IPSET_DEL] = mtype_del,
+ [IPSET_TEST] = mtype_test,
+ },
+ .destroy = mtype_destroy,
+ .flush = mtype_flush,
+ .head = mtype_head,
+ .list = mtype_list,
+ .same_set = mtype_same_set,
+};
+
+#endif /* __IP_SET_BITMAP_IP_GEN_H */
diff --git a/net/netfilter/ipset/ip_set_bitmap_ip.c b/net/netfilter/ipset/ip_set_bitmap_ip.c
index 4a92fd47bd4..6f1f9f49480 100644
--- a/net/netfilter/ipset/ip_set_bitmap_ip.c
+++ b/net/netfilter/ipset/ip_set_bitmap_ip.c
@@ -1,6 +1,6 @@
/* Copyright (C) 2000-2002 Joakim Axelsson <gozem@linux.nu>
* Patrick Schaaf <bof@bof.de>
- * Copyright (C) 2003-2011 Jozsef Kadlecsik <kadlec@blackhole.kfki.hu>
+ * Copyright (C) 2003-2013 Jozsef Kadlecsik <kadlec@blackhole.kfki.hu>
*
* This program is free software; you can redistribute it and/or modify
* it under the terms of the GNU General Public License version 2 as
@@ -24,31 +24,35 @@
#include <linux/netfilter/ipset/pfxlen.h>
#include <linux/netfilter/ipset/ip_set.h>
#include <linux/netfilter/ipset/ip_set_bitmap.h>
-#define IP_SET_BITMAP_TIMEOUT
-#include <linux/netfilter/ipset/ip_set_timeout.h>
-#define REVISION_MIN 0
-#define REVISION_MAX 0
+#define IPSET_TYPE_REV_MIN 0
+/* 1 Counter support added */
+#define IPSET_TYPE_REV_MAX 2 /* Comment support added */
MODULE_LICENSE("GPL");
MODULE_AUTHOR("Jozsef Kadlecsik <kadlec@blackhole.kfki.hu>");
-IP_SET_MODULE_DESC("bitmap:ip", REVISION_MIN, REVISION_MAX);
+IP_SET_MODULE_DESC("bitmap:ip", IPSET_TYPE_REV_MIN, IPSET_TYPE_REV_MAX);
MODULE_ALIAS("ip_set_bitmap:ip");
+#define MTYPE bitmap_ip
+
/* Type structure */
struct bitmap_ip {
void *members; /* the set members */
+ void *extensions; /* data extensions */
u32 first_ip; /* host byte order, included in range */
u32 last_ip; /* host byte order, included in range */
u32 elements; /* number of max elements in the set */
u32 hosts; /* number of hosts in a subnet */
size_t memsize; /* members size */
u8 netmask; /* subnet netmask */
- u32 timeout; /* timeout parameter */
struct timer_list gc; /* garbage collection */
};
-/* Base variant */
+/* ADT structure for generic function args */
+struct bitmap_ip_adt_elem {
+ u16 id;
+};
static inline u32
ip_to_id(const struct bitmap_ip *m, u32 ip)
@@ -56,188 +60,69 @@ ip_to_id(const struct bitmap_ip *m, u32 ip)
return ((ip & ip_set_hostmask(m->netmask)) - m->first_ip)/m->hosts;
}
-static int
-bitmap_ip_test(struct ip_set *set, void *value, u32 timeout, u32 flags)
-{
- const struct bitmap_ip *map = set->data;
- u16 id = *(u16 *)value;
-
- return !!test_bit(id, map->members);
-}
+/* Common functions */
-static int
-bitmap_ip_add(struct ip_set *set, void *value, u32 timeout, u32 flags)
+static inline int
+bitmap_ip_do_test(const struct bitmap_ip_adt_elem *e,
+ struct bitmap_ip *map, size_t dsize)
{
- struct bitmap_ip *map = set->data;
- u16 id = *(u16 *)value;
-
- if (test_and_set_bit(id, map->members))
- return -IPSET_ERR_EXIST;
-
- return 0;
+ return !!test_bit(e->id, map->members);
}
-static int
-bitmap_ip_del(struct ip_set *set, void *value, u32 timeout, u32 flags)
+static inline int
+bitmap_ip_gc_test(u16 id, const struct bitmap_ip *map, size_t dsize)
{
- struct bitmap_ip *map = set->data;
- u16 id = *(u16 *)value;
-
- if (!test_and_clear_bit(id, map->members))
- return -IPSET_ERR_EXIST;
-
- return 0;
+ return !!test_bit(id, map->members);
}
-static int
-bitmap_ip_list(const struct ip_set *set,
- struct sk_buff *skb, struct netlink_callback *cb)
+static inline int
+bitmap_ip_do_add(const struct bitmap_ip_adt_elem *e, struct bitmap_ip *map,
+ u32 flags, size_t dsize)
{
- const struct bitmap_ip *map = set->data;
- struct nlattr *atd, *nested;
- u32 id, first = cb->args[2];
-
- atd = ipset_nest_start(skb, IPSET_ATTR_ADT);
- if (!atd)
- return -EMSGSIZE;
- for (; cb->args[2] < map->elements; cb->args[2]++) {
- id = cb->args[2];
- if (!test_bit(id, map->members))
- continue;
- nested = ipset_nest_start(skb, IPSET_ATTR_DATA);
- if (!nested) {
- if (id == first) {
- nla_nest_cancel(skb, atd);
- return -EMSGSIZE;
- } else
- goto nla_put_failure;
- }
- if (nla_put_ipaddr4(skb, IPSET_ATTR_IP,
- htonl(map->first_ip + id * map->hosts)))
- goto nla_put_failure;
- ipset_nest_end(skb, nested);
- }
- ipset_nest_end(skb, atd);
- /* Set listing finished */
- cb->args[2] = 0;
- return 0;
-
-nla_put_failure:
- nla_nest_cancel(skb, nested);
- ipset_nest_end(skb, atd);
- if (unlikely(id == first)) {
- cb->args[2] = 0;
- return -EMSGSIZE;
- }
- return 0;
+ return !!test_and_set_bit(e->id, map->members);
}
-/* Timeout variant */
-
-static int
-bitmap_ip_ttest(struct ip_set *set, void *value, u32 timeout, u32 flags)
+static inline int
+bitmap_ip_do_del(const struct bitmap_ip_adt_elem *e, struct bitmap_ip *map)
{
- const struct bitmap_ip *map = set->data;
- const unsigned long *members = map->members;
- u16 id = *(u16 *)value;
-
- return ip_set_timeout_test(members[id]);
+ return !test_and_clear_bit(e->id, map->members);
}
-static int
-bitmap_ip_tadd(struct ip_set *set, void *value, u32 timeout, u32 flags)
+static inline int
+bitmap_ip_do_list(struct sk_buff *skb, const struct bitmap_ip *map, u32 id,
+ size_t dsize)
{
- struct bitmap_ip *map = set->data;
- unsigned long *members = map->members;
- u16 id = *(u16 *)value;
-
- if (ip_set_timeout_test(members[id]) && !(flags & IPSET_FLAG_EXIST))
- return -IPSET_ERR_EXIST;
-
- members[id] = ip_set_timeout_set(timeout);
-
- return 0;
+ return nla_put_ipaddr4(skb, IPSET_ATTR_IP,
+ htonl(map->first_ip + id * map->hosts));
}
-static int
-bitmap_ip_tdel(struct ip_set *set, void *value, u32 timeout, u32 flags)
+static inline int
+bitmap_ip_do_head(struct sk_buff *skb, const struct bitmap_ip *map)
{
- struct bitmap_ip *map = set->data;
- unsigned long *members = map->members;
- u16 id = *(u16 *)value;
- int ret = -IPSET_ERR_EXIST;
-
- if (ip_set_timeout_test(members[id]))
- ret = 0;
-
- members[id] = IPSET_ELEM_UNSET;
- return ret;
-}
-
-static int
-bitmap_ip_tlist(const struct ip_set *set,
- struct sk_buff *skb, struct netlink_callback *cb)
-{
- const struct bitmap_ip *map = set->data;
- struct nlattr *adt, *nested;
- u32 id, first = cb->args[2];
- const unsigned long *members = map->members;
-
- adt = ipset_nest_start(skb, IPSET_ATTR_ADT);
- if (!adt)
- return -EMSGSIZE;
- for (; cb->args[2] < map->elements; cb->args[2]++) {
- id = cb->args[2];
- if (!ip_set_timeout_test(members[id]))
- continue;
- nested = ipset_nest_start(skb, IPSET_ATTR_DATA);
- if (!nested) {
- if (id == first) {
- nla_nest_cancel(skb, adt);
- return -EMSGSIZE;
- } else
- goto nla_put_failure;
- }
- if (nla_put_ipaddr4(skb, IPSET_ATTR_IP,
- htonl(map->first_ip + id * map->hosts)) ||
- nla_put_net32(skb, IPSET_ATTR_TIMEOUT,
- htonl(ip_set_timeout_get(members[id]))))
- goto nla_put_failure;
- ipset_nest_end(skb, nested);
- }
- ipset_nest_end(skb, adt);
-
- /* Set listing finished */
- cb->args[2] = 0;
-
- return 0;
-
-nla_put_failure:
- nla_nest_cancel(skb, nested);
- ipset_nest_end(skb, adt);
- if (unlikely(id == first)) {
- cb->args[2] = 0;
- return -EMSGSIZE;
- }
- return 0;
+ return nla_put_ipaddr4(skb, IPSET_ATTR_IP, htonl(map->first_ip)) ||
+ nla_put_ipaddr4(skb, IPSET_ATTR_IP_TO, htonl(map->last_ip)) ||
+ (map->netmask != 32 &&
+ nla_put_u8(skb, IPSET_ATTR_NETMASK, map->netmask));
}
static int
bitmap_ip_kadt(struct ip_set *set, const struct sk_buff *skb,
const struct xt_action_param *par,
- enum ipset_adt adt, const struct ip_set_adt_opt *opt)
+ enum ipset_adt adt, struct ip_set_adt_opt *opt)
{
struct bitmap_ip *map = set->data;
ipset_adtfn adtfn = set->variant->adt[adt];
+ struct bitmap_ip_adt_elem e = { };
+ struct ip_set_ext ext = IP_SET_INIT_KEXT(skb, opt, set);
u32 ip;
ip = ntohl(ip4addr(skb, opt->flags & IPSET_DIM_ONE_SRC));
if (ip < map->first_ip || ip > map->last_ip)
return -IPSET_ERR_BITMAP_RANGE;
- ip = ip_to_id(map, ip);
+ e.id = ip_to_id(map, ip);
- return adtfn(set, &ip, opt_timeout(opt, map), opt->cmdflags);
+ return adtfn(set, &e, &ext, &opt->ext, opt->cmdflags);
}
static int
@@ -246,33 +131,31 @@ bitmap_ip_uadt(struct ip_set *set, struct nlattr *tb[],
{
struct bitmap_ip *map = set->data;
ipset_adtfn adtfn = set->variant->adt[adt];
- u32 timeout = map->timeout;
- u32 ip, ip_to, id;
+ u32 ip = 0, ip_to = 0;
+ struct bitmap_ip_adt_elem e = { };
+ struct ip_set_ext ext = IP_SET_INIT_UEXT(set);
int ret = 0;
if (unlikely(!tb[IPSET_ATTR_IP] ||
- !ip_set_optattr_netorder(tb, IPSET_ATTR_TIMEOUT)))
+ !ip_set_optattr_netorder(tb, IPSET_ATTR_TIMEOUT) ||
+ !ip_set_optattr_netorder(tb, IPSET_ATTR_PACKETS) ||
+ !ip_set_optattr_netorder(tb, IPSET_ATTR_BYTES)))
return -IPSET_ERR_PROTOCOL;
if (tb[IPSET_ATTR_LINENO])
*lineno = nla_get_u32(tb[IPSET_ATTR_LINENO]);
- ret = ip_set_get_hostipaddr4(tb[IPSET_ATTR_IP], &ip);
+ ret = ip_set_get_hostipaddr4(tb[IPSET_ATTR_IP], &ip) ||
+ ip_set_get_extensions(set, tb, &ext);
if (ret)
return ret;
if (ip < map->first_ip || ip > map->last_ip)
return -IPSET_ERR_BITMAP_RANGE;
- if (tb[IPSET_ATTR_TIMEOUT]) {
- if (!with_timeout(map->timeout))
- return -IPSET_ERR_TIMEOUT;
- timeout = ip_set_timeout_uget(tb[IPSET_ATTR_TIMEOUT]);
- }
-
if (adt == IPSET_TEST) {
- id = ip_to_id(map, ip);
- return adtfn(set, &id, timeout, flags);
+ e.id = ip_to_id(map, ip);
+ return adtfn(set, &e, &ext, &ext, flags);
}
if (tb[IPSET_ATTR_IP_TO]) {
@@ -297,8 +180,8 @@ bitmap_ip_uadt(struct ip_set *set, struct nlattr *tb[],
return -IPSET_ERR_BITMAP_RANGE;
for (; !before(ip_to, ip); ip += map->hosts) {
- id = ip_to_id(map, ip);
- ret = adtfn(set, &id, timeout, flags);
+ e.id = ip_to_id(map, ip);
+ ret = adtfn(set, &e, &ext, &ext, flags);
if (ret && !ip_set_eexist(ret, flags))
return ret;
@@ -308,54 +191,6 @@ bitmap_ip_uadt(struct ip_set *set, struct nlattr *tb[],
return ret;
}
-static void
-bitmap_ip_destroy(struct ip_set *set)
-{
- struct bitmap_ip *map = set->data;
-
- if (with_timeout(map->timeout))
- del_timer_sync(&map->gc);
-
- ip_set_free(map->members);
- kfree(map);
-
- set->data = NULL;
-}
-
-static void
-bitmap_ip_flush(struct ip_set *set)
-{
- struct bitmap_ip *map = set->data;
-
- memset(map->members, 0, map->memsize);
-}
-
-static int
-bitmap_ip_head(struct ip_set *set, struct sk_buff *skb)
-{
- const struct bitmap_ip *map = set->data;
- struct nlattr *nested;
-
- nested = ipset_nest_start(skb, IPSET_ATTR_DATA);
- if (!nested)
- goto nla_put_failure;
- if (nla_put_ipaddr4(skb, IPSET_ATTR_IP, htonl(map->first_ip)) ||
- nla_put_ipaddr4(skb, IPSET_ATTR_IP_TO, htonl(map->last_ip)) ||
- (map->netmask != 32 &&
- nla_put_u8(skb, IPSET_ATTR_NETMASK, map->netmask)) ||
- nla_put_net32(skb, IPSET_ATTR_REFERENCES, htonl(set->ref - 1)) ||
- nla_put_net32(skb, IPSET_ATTR_MEMSIZE,
- htonl(sizeof(*map) + map->memsize)) ||
- (with_timeout(map->timeout) &&
- nla_put_net32(skb, IPSET_ATTR_TIMEOUT, htonl(map->timeout))))
- goto nla_put_failure;
- ipset_nest_end(skb, nested);
-
- return 0;
-nla_put_failure:
- return -EMSGSIZE;
-}
-
static bool
bitmap_ip_same_set(const struct ip_set *a, const struct ip_set *b)
{
@@ -365,70 +200,16 @@ bitmap_ip_same_set(const struct ip_set *a, const struct ip_set *b)
return x->first_ip == y->first_ip &&
x->last_ip == y->last_ip &&
x->netmask == y->netmask &&
- x->timeout == y->timeout;
+ a->timeout == b->timeout &&
+ a->extensions == b->extensions;
}
-static const struct ip_set_type_variant bitmap_ip = {
- .kadt = bitmap_ip_kadt,
- .uadt = bitmap_ip_uadt,
- .adt = {
- [IPSET_ADD] = bitmap_ip_add,
- [IPSET_DEL] = bitmap_ip_del,
- [IPSET_TEST] = bitmap_ip_test,
- },
- .destroy = bitmap_ip_destroy,
- .flush = bitmap_ip_flush,
- .head = bitmap_ip_head,
- .list = bitmap_ip_list,
- .same_set = bitmap_ip_same_set,
-};
+/* Plain variant */
-static const struct ip_set_type_variant bitmap_tip = {
- .kadt = bitmap_ip_kadt,
- .uadt = bitmap_ip_uadt,
- .adt = {
- [IPSET_ADD] = bitmap_ip_tadd,
- [IPSET_DEL] = bitmap_ip_tdel,
- [IPSET_TEST] = bitmap_ip_ttest,
- },
- .destroy = bitmap_ip_destroy,
- .flush = bitmap_ip_flush,
- .head = bitmap_ip_head,
- .list = bitmap_ip_tlist,
- .same_set = bitmap_ip_same_set,
+struct bitmap_ip_elem {
};
-static void
-bitmap_ip_gc(unsigned long ul_set)
-{
- struct ip_set *set = (struct ip_set *) ul_set;
- struct bitmap_ip *map = set->data;
- unsigned long *table = map->members;
- u32 id;
-
- /* We run parallel with other readers (test element)
- * but adding/deleting new entries is locked out */
- read_lock_bh(&set->lock);
- for (id = 0; id < map->elements; id++)
- if (ip_set_timeout_expired(table[id]))
- table[id] = IPSET_ELEM_UNSET;
- read_unlock_bh(&set->lock);
-
- map->gc.expires = jiffies + IPSET_GC_PERIOD(map->timeout) * HZ;
- add_timer(&map->gc);
-}
-
-static void
-bitmap_ip_gc_init(struct ip_set *set)
-{
- struct bitmap_ip *map = set->data;
-
- init_timer(&map->gc);
- map->gc.data = (unsigned long) set;
- map->gc.function = bitmap_ip_gc;
- map->gc.expires = jiffies + IPSET_GC_PERIOD(map->timeout) * HZ;
- add_timer(&map->gc);
-}
+#include "ip_set_bitmap_gen.h"
/* Create bitmap:ip type of sets */
@@ -440,12 +221,19 @@ init_map_ip(struct ip_set *set, struct bitmap_ip *map,
map->members = ip_set_alloc(map->memsize);
if (!map->members)
return false;
+ if (set->dsize) {
+ map->extensions = ip_set_alloc(set->dsize * elements);
+ if (!map->extensions) {
+ kfree(map->members);
+ return false;
+ }
+ }
map->first_ip = first_ip;
map->last_ip = last_ip;
map->elements = elements;
map->hosts = hosts;
map->netmask = netmask;
- map->timeout = IPSET_NO_TIMEOUT;
+ set->timeout = IPSET_NO_TIMEOUT;
set->data = map;
set->family = NFPROTO_IPV4;
@@ -454,16 +242,18 @@ init_map_ip(struct ip_set *set, struct bitmap_ip *map,
}
static int
-bitmap_ip_create(struct ip_set *set, struct nlattr *tb[], u32 flags)
+bitmap_ip_create(struct net *net, struct ip_set *set, struct nlattr *tb[],
+ u32 flags)
{
struct bitmap_ip *map;
- u32 first_ip, last_ip, hosts;
+ u32 first_ip = 0, last_ip = 0, hosts;
u64 elements;
u8 netmask = 32;
int ret;
if (unlikely(!tb[IPSET_ATTR_IP] ||
- !ip_set_optattr_netorder(tb, IPSET_ATTR_TIMEOUT)))
+ !ip_set_optattr_netorder(tb, IPSET_ATTR_TIMEOUT) ||
+ !ip_set_optattr_netorder(tb, IPSET_ATTR_CADT_FLAGS)))
return -IPSET_ERR_PROTOCOL;
ret = ip_set_get_hostipaddr4(tb[IPSET_ATTR_IP], &first_ip);
@@ -526,29 +316,17 @@ bitmap_ip_create(struct ip_set *set, struct nlattr *tb[], u32 flags)
if (!map)
return -ENOMEM;
+ map->memsize = bitmap_bytes(0, elements - 1);
+ set->variant = &bitmap_ip;
+ set->dsize = ip_set_elem_len(set, tb, 0);
+ if (!init_map_ip(set, map, first_ip, last_ip,
+ elements, hosts, netmask)) {
+ kfree(map);
+ return -ENOMEM;
+ }
if (tb[IPSET_ATTR_TIMEOUT]) {
- map->memsize = elements * sizeof(unsigned long);
-
- if (!init_map_ip(set, map, first_ip, last_ip,
- elements, hosts, netmask)) {
- kfree(map);
- return -ENOMEM;
- }
-
- map->timeout = ip_set_timeout_uget(tb[IPSET_ATTR_TIMEOUT]);
- set->variant = &bitmap_tip;
-
- bitmap_ip_gc_init(set);
- } else {
- map->memsize = bitmap_bytes(0, elements - 1);
-
- if (!init_map_ip(set, map, first_ip, last_ip,
- elements, hosts, netmask)) {
- kfree(map);
- return -ENOMEM;
- }
-
- set->variant = &bitmap_ip;
+ set->timeout = ip_set_timeout_uget(tb[IPSET_ATTR_TIMEOUT]);
+ bitmap_ip_gc_init(set, bitmap_ip_gc);
}
return 0;
}
@@ -559,8 +337,8 @@ static struct ip_set_type bitmap_ip_type __read_mostly = {
.features = IPSET_TYPE_IP,
.dimension = IPSET_DIM_ONE,
.family = NFPROTO_IPV4,
- .revision_min = REVISION_MIN,
- .revision_max = REVISION_MAX,
+ .revision_min = IPSET_TYPE_REV_MIN,
+ .revision_max = IPSET_TYPE_REV_MAX,
.create = bitmap_ip_create,
.create_policy = {
[IPSET_ATTR_IP] = { .type = NLA_NESTED },
@@ -568,6 +346,7 @@ static struct ip_set_type bitmap_ip_type __read_mostly = {
[IPSET_ATTR_CIDR] = { .type = NLA_U8 },
[IPSET_ATTR_NETMASK] = { .type = NLA_U8 },
[IPSET_ATTR_TIMEOUT] = { .type = NLA_U32 },
+ [IPSET_ATTR_CADT_FLAGS] = { .type = NLA_U32 },
},
.adt_policy = {
[IPSET_ATTR_IP] = { .type = NLA_NESTED },
@@ -575,6 +354,9 @@ static struct ip_set_type bitmap_ip_type __read_mostly = {
[IPSET_ATTR_CIDR] = { .type = NLA_U8 },
[IPSET_ATTR_TIMEOUT] = { .type = NLA_U32 },
[IPSET_ATTR_LINENO] = { .type = NLA_U32 },
+ [IPSET_ATTR_BYTES] = { .type = NLA_U64 },
+ [IPSET_ATTR_PACKETS] = { .type = NLA_U64 },
+ [IPSET_ATTR_COMMENT] = { .type = NLA_NUL_STRING },
},
.me = THIS_MODULE,
};
diff --git a/net/netfilter/ipset/ip_set_bitmap_ipmac.c b/net/netfilter/ipset/ip_set_bitmap_ipmac.c
index 0f92dc24cb8..740eabededd 100644
--- a/net/netfilter/ipset/ip_set_bitmap_ipmac.c
+++ b/net/netfilter/ipset/ip_set_bitmap_ipmac.c
@@ -1,7 +1,7 @@
/* Copyright (C) 2000-2002 Joakim Axelsson <gozem@linux.nu>
* Patrick Schaaf <bof@bof.de>
* Martin Josefsson <gandalf@wlug.westbo.se>
- * Copyright (C) 2003-2011 Jozsef Kadlecsik <kadlec@blackhole.kfki.hu>
+ * Copyright (C) 2003-2013 Jozsef Kadlecsik <kadlec@blackhole.kfki.hu>
*
* This program is free software; you can redistribute it and/or modify
* it under the terms of the GNU General Public License version 2 as
@@ -23,340 +23,196 @@
#include <linux/netfilter/ipset/pfxlen.h>
#include <linux/netfilter/ipset/ip_set.h>
-#include <linux/netfilter/ipset/ip_set_timeout.h>
#include <linux/netfilter/ipset/ip_set_bitmap.h>
-#define REVISION_MIN 0
-#define REVISION_MAX 0
+#define IPSET_TYPE_REV_MIN 0
+/* 1 Counter support added */
+#define IPSET_TYPE_REV_MAX 2 /* Comment support added */
MODULE_LICENSE("GPL");
MODULE_AUTHOR("Jozsef Kadlecsik <kadlec@blackhole.kfki.hu>");
-IP_SET_MODULE_DESC("bitmap:ip,mac", REVISION_MIN, REVISION_MAX);
+IP_SET_MODULE_DESC("bitmap:ip,mac", IPSET_TYPE_REV_MIN, IPSET_TYPE_REV_MAX);
MODULE_ALIAS("ip_set_bitmap:ip,mac");
+#define MTYPE bitmap_ipmac
+#define IP_SET_BITMAP_STORED_TIMEOUT
+
enum {
- MAC_EMPTY, /* element is not set */
- MAC_FILLED, /* element is set with MAC */
MAC_UNSET, /* element is set, without MAC */
+ MAC_FILLED, /* element is set with MAC */
};
/* Type structure */
struct bitmap_ipmac {
void *members; /* the set members */
+ void *extensions; /* MAC + data extensions */
u32 first_ip; /* host byte order, included in range */
u32 last_ip; /* host byte order, included in range */
- u32 timeout; /* timeout value */
+ u32 elements; /* number of max elements in the set */
+ size_t memsize; /* members size */
struct timer_list gc; /* garbage collector */
- size_t dsize; /* size of element */
};
/* ADT structure for generic function args */
-struct ipmac {
- u32 id; /* id in array */
- unsigned char *ether; /* ethernet address */
+struct bitmap_ipmac_adt_elem {
+ u16 id;
+ unsigned char *ether;
};
-/* Member element without and with timeout */
-
-struct ipmac_elem {
+struct bitmap_ipmac_elem {
unsigned char ether[ETH_ALEN];
- unsigned char match;
+ unsigned char filled;
} __attribute__ ((aligned));
-struct ipmac_telem {
- unsigned char ether[ETH_ALEN];
- unsigned char match;
- unsigned long timeout;
-} __attribute__ ((aligned));
-
-static inline void *
-bitmap_ipmac_elem(const struct bitmap_ipmac *map, u32 id)
+static inline u32
+ip_to_id(const struct bitmap_ipmac *m, u32 ip)
{
- return (void *)((char *)map->members + id * map->dsize);
+ return ip - m->first_ip;
}
-static inline bool
-bitmap_timeout(const struct bitmap_ipmac *map, u32 id)
+static inline struct bitmap_ipmac_elem *
+get_elem(void *extensions, u16 id, size_t dsize)
{
- const struct ipmac_telem *elem = bitmap_ipmac_elem(map, id);
-
- return ip_set_timeout_test(elem->timeout);
+ return (struct bitmap_ipmac_elem *)(extensions + id * dsize);
}
-static inline bool
-bitmap_expired(const struct bitmap_ipmac *map, u32 id)
-{
- const struct ipmac_telem *elem = bitmap_ipmac_elem(map, id);
-
- return ip_set_timeout_expired(elem->timeout);
-}
+/* Common functions */
static inline int
-bitmap_ipmac_exist(const struct ipmac_telem *elem)
-{
- return elem->match == MAC_UNSET ||
- (elem->match == MAC_FILLED &&
- !ip_set_timeout_expired(elem->timeout));
-}
-
-/* Base variant */
-
-static int
-bitmap_ipmac_test(struct ip_set *set, void *value, u32 timeout, u32 flags)
-{
- const struct bitmap_ipmac *map = set->data;
- const struct ipmac *data = value;
- const struct ipmac_elem *elem = bitmap_ipmac_elem(map, data->id);
-
- switch (elem->match) {
- case MAC_UNSET:
- /* Trigger kernel to fill out the ethernet address */
- return -EAGAIN;
- case MAC_FILLED:
- return data->ether == NULL ||
- ether_addr_equal(data->ether, elem->ether);
- }
- return 0;
-}
-
-static int
-bitmap_ipmac_add(struct ip_set *set, void *value, u32 timeout, u32 flags)
+bitmap_ipmac_do_test(const struct bitmap_ipmac_adt_elem *e,
+ const struct bitmap_ipmac *map, size_t dsize)
{
- struct bitmap_ipmac *map = set->data;
- const struct ipmac *data = value;
- struct ipmac_elem *elem = bitmap_ipmac_elem(map, data->id);
-
- switch (elem->match) {
- case MAC_UNSET:
- if (!data->ether)
- /* Already added without ethernet address */
- return -IPSET_ERR_EXIST;
- /* Fill the MAC address */
- memcpy(elem->ether, data->ether, ETH_ALEN);
- elem->match = MAC_FILLED;
- break;
- case MAC_FILLED:
- return -IPSET_ERR_EXIST;
- case MAC_EMPTY:
- if (data->ether) {
- memcpy(elem->ether, data->ether, ETH_ALEN);
- elem->match = MAC_FILLED;
- } else
- elem->match = MAC_UNSET;
- }
-
- return 0;
-}
-
-static int
-bitmap_ipmac_del(struct ip_set *set, void *value, u32 timeout, u32 flags)
-{
- struct bitmap_ipmac *map = set->data;
- const struct ipmac *data = value;
- struct ipmac_elem *elem = bitmap_ipmac_elem(map, data->id);
+ const struct bitmap_ipmac_elem *elem;
- if (elem->match == MAC_EMPTY)
- return -IPSET_ERR_EXIST;
-
- elem->match = MAC_EMPTY;
-
- return 0;
+ if (!test_bit(e->id, map->members))
+ return 0;
+ elem = get_elem(map->extensions, e->id, dsize);
+ if (elem->filled == MAC_FILLED)
+ return e->ether == NULL ||
+ ether_addr_equal(e->ether, elem->ether);
+ /* Trigger kernel to fill out the ethernet address */
+ return -EAGAIN;
}
-static int
-bitmap_ipmac_list(const struct ip_set *set,
- struct sk_buff *skb, struct netlink_callback *cb)
+static inline int
+bitmap_ipmac_gc_test(u16 id, const struct bitmap_ipmac *map, size_t dsize)
{
- const struct bitmap_ipmac *map = set->data;
- const struct ipmac_elem *elem;
- struct nlattr *atd, *nested;
- u32 id, first = cb->args[2];
- u32 last = map->last_ip - map->first_ip;
-
- atd = ipset_nest_start(skb, IPSET_ATTR_ADT);
- if (!atd)
- return -EMSGSIZE;
- for (; cb->args[2] <= last; cb->args[2]++) {
- id = cb->args[2];
- elem = bitmap_ipmac_elem(map, id);
- if (elem->match == MAC_EMPTY)
- continue;
- nested = ipset_nest_start(skb, IPSET_ATTR_DATA);
- if (!nested) {
- if (id == first) {
- nla_nest_cancel(skb, atd);
- return -EMSGSIZE;
- } else
- goto nla_put_failure;
- }
- if (nla_put_ipaddr4(skb, IPSET_ATTR_IP,
- htonl(map->first_ip + id)) ||
- (elem->match == MAC_FILLED &&
- nla_put(skb, IPSET_ATTR_ETHER, ETH_ALEN,
- elem->ether)))
- goto nla_put_failure;
- ipset_nest_end(skb, nested);
- }
- ipset_nest_end(skb, atd);
- /* Set listing finished */
- cb->args[2] = 0;
+ const struct bitmap_ipmac_elem *elem;
- return 0;
-
-nla_put_failure:
- nla_nest_cancel(skb, nested);
- ipset_nest_end(skb, atd);
- if (unlikely(id == first)) {
- cb->args[2] = 0;
- return -EMSGSIZE;
- }
- return 0;
+ if (!test_bit(id, map->members))
+ return 0;
+ elem = get_elem(map->extensions, id, dsize);
+ /* Timer not started for the incomplete elements */
+ return elem->filled == MAC_FILLED;
}
-/* Timeout variant */
-
-static int
-bitmap_ipmac_ttest(struct ip_set *set, void *value, u32 timeout, u32 flags)
+static inline int
+bitmap_ipmac_is_filled(const struct bitmap_ipmac_elem *elem)
{
- const struct bitmap_ipmac *map = set->data;
- const struct ipmac *data = value;
- const struct ipmac_elem *elem = bitmap_ipmac_elem(map, data->id);
-
- switch (elem->match) {
- case MAC_UNSET:
- /* Trigger kernel to fill out the ethernet address */
- return -EAGAIN;
- case MAC_FILLED:
- return (data->ether == NULL ||
- ether_addr_equal(data->ether, elem->ether)) &&
- !bitmap_expired(map, data->id);
- }
- return 0;
+ return elem->filled == MAC_FILLED;
}
-static int
-bitmap_ipmac_tadd(struct ip_set *set, void *value, u32 timeout, u32 flags)
+static inline int
+bitmap_ipmac_add_timeout(unsigned long *timeout,
+ const struct bitmap_ipmac_adt_elem *e,
+ const struct ip_set_ext *ext, struct ip_set *set,
+ struct bitmap_ipmac *map, int mode)
{
- struct bitmap_ipmac *map = set->data;
- const struct ipmac *data = value;
- struct ipmac_telem *elem = bitmap_ipmac_elem(map, data->id);
- bool flag_exist = flags & IPSET_FLAG_EXIST;
+ u32 t = ext->timeout;
- switch (elem->match) {
- case MAC_UNSET:
- if (!(data->ether || flag_exist))
- /* Already added without ethernet address */
- return -IPSET_ERR_EXIST;
- /* Fill the MAC address and activate the timer */
- memcpy(elem->ether, data->ether, ETH_ALEN);
- elem->match = MAC_FILLED;
- if (timeout == map->timeout)
+ if (mode == IPSET_ADD_START_STORED_TIMEOUT) {
+ if (t == set->timeout)
/* Timeout was not specified, get stored one */
- timeout = elem->timeout;
- elem->timeout = ip_set_timeout_set(timeout);
- break;
- case MAC_FILLED:
- if (!(bitmap_expired(map, data->id) || flag_exist))
- return -IPSET_ERR_EXIST;
- /* Fall through */
- case MAC_EMPTY:
- if (data->ether) {
- memcpy(elem->ether, data->ether, ETH_ALEN);
- elem->match = MAC_FILLED;
- } else
- elem->match = MAC_UNSET;
+ t = *timeout;
+ ip_set_timeout_set(timeout, t);
+ } else {
/* If MAC is unset yet, we store plain timeout value
* because the timer is not activated yet
* and we can reuse it later when MAC is filled out,
* possibly by the kernel */
- elem->timeout = data->ether ? ip_set_timeout_set(timeout)
- : timeout;
- break;
+ if (e->ether)
+ ip_set_timeout_set(timeout, t);
+ else
+ *timeout = t;
}
-
return 0;
}
-static int
-bitmap_ipmac_tdel(struct ip_set *set, void *value, u32 timeout, u32 flags)
+static inline int
+bitmap_ipmac_do_add(const struct bitmap_ipmac_adt_elem *e,
+ struct bitmap_ipmac *map, u32 flags, size_t dsize)
{
- struct bitmap_ipmac *map = set->data;
- const struct ipmac *data = value;
- struct ipmac_telem *elem = bitmap_ipmac_elem(map, data->id);
-
- if (elem->match == MAC_EMPTY || bitmap_expired(map, data->id))
- return -IPSET_ERR_EXIST;
-
- elem->match = MAC_EMPTY;
+ struct bitmap_ipmac_elem *elem;
+
+ elem = get_elem(map->extensions, e->id, dsize);
+ if (test_and_set_bit(e->id, map->members)) {
+ if (elem->filled == MAC_FILLED) {
+ if (e->ether && (flags & IPSET_FLAG_EXIST))
+ memcpy(elem->ether, e->ether, ETH_ALEN);
+ return IPSET_ADD_FAILED;
+ } else if (!e->ether)
+ /* Already added without ethernet address */
+ return IPSET_ADD_FAILED;
+ /* Fill the MAC address and trigger the timer activation */
+ memcpy(elem->ether, e->ether, ETH_ALEN);
+ elem->filled = MAC_FILLED;
+ return IPSET_ADD_START_STORED_TIMEOUT;
+ } else if (e->ether) {
+ /* We can store MAC too */
+ memcpy(elem->ether, e->ether, ETH_ALEN);
+ elem->filled = MAC_FILLED;
+ return 0;
+ } else {
+ elem->filled = MAC_UNSET;
+ /* MAC is not stored yet, don't start timer */
+ return IPSET_ADD_STORE_PLAIN_TIMEOUT;
+ }
+}
- return 0;
+static inline int
+bitmap_ipmac_do_del(const struct bitmap_ipmac_adt_elem *e,
+ struct bitmap_ipmac *map)
+{
+ return !test_and_clear_bit(e->id, map->members);
}
-static int
-bitmap_ipmac_tlist(const struct ip_set *set,
- struct sk_buff *skb, struct netlink_callback *cb)
+static inline int
+bitmap_ipmac_do_list(struct sk_buff *skb, const struct bitmap_ipmac *map,
+ u32 id, size_t dsize)
{
- const struct bitmap_ipmac *map = set->data;
- const struct ipmac_telem *elem;
- struct nlattr *atd, *nested;
- u32 id, first = cb->args[2];
- u32 timeout, last = map->last_ip - map->first_ip;
-
- atd = ipset_nest_start(skb, IPSET_ATTR_ADT);
- if (!atd)
- return -EMSGSIZE;
- for (; cb->args[2] <= last; cb->args[2]++) {
- id = cb->args[2];
- elem = bitmap_ipmac_elem(map, id);
- if (!bitmap_ipmac_exist(elem))
- continue;
- nested = ipset_nest_start(skb, IPSET_ATTR_DATA);
- if (!nested) {
- if (id == first) {
- nla_nest_cancel(skb, atd);
- return -EMSGSIZE;
- } else
- goto nla_put_failure;
- }
- if (nla_put_ipaddr4(skb, IPSET_ATTR_IP,
- htonl(map->first_ip + id)) ||
- (elem->match == MAC_FILLED &&
- nla_put(skb, IPSET_ATTR_ETHER, ETH_ALEN,
- elem->ether)))
- goto nla_put_failure;
- timeout = elem->match == MAC_UNSET ? elem->timeout
- : ip_set_timeout_get(elem->timeout);
- if (nla_put_net32(skb, IPSET_ATTR_TIMEOUT, htonl(timeout)))
- goto nla_put_failure;
- ipset_nest_end(skb, nested);
- }
- ipset_nest_end(skb, atd);
- /* Set listing finished */
- cb->args[2] = 0;
+ const struct bitmap_ipmac_elem *elem =
+ get_elem(map->extensions, id, dsize);
- return 0;
+ return nla_put_ipaddr4(skb, IPSET_ATTR_IP,
+ htonl(map->first_ip + id)) ||
+ (elem->filled == MAC_FILLED &&
+ nla_put(skb, IPSET_ATTR_ETHER, ETH_ALEN, elem->ether));
+}
-nla_put_failure:
- nla_nest_cancel(skb, nested);
- ipset_nest_end(skb, atd);
- return -EMSGSIZE;
+static inline int
+bitmap_ipmac_do_head(struct sk_buff *skb, const struct bitmap_ipmac *map)
+{
+ return nla_put_ipaddr4(skb, IPSET_ATTR_IP, htonl(map->first_ip)) ||
+ nla_put_ipaddr4(skb, IPSET_ATTR_IP_TO, htonl(map->last_ip));
}
static int
bitmap_ipmac_kadt(struct ip_set *set, const struct sk_buff *skb,
const struct xt_action_param *par,
- enum ipset_adt adt, const struct ip_set_adt_opt *opt)
+ enum ipset_adt adt, struct ip_set_adt_opt *opt)
{
struct bitmap_ipmac *map = set->data;
ipset_adtfn adtfn = set->variant->adt[adt];
- struct ipmac data;
+ struct bitmap_ipmac_adt_elem e = {};
+ struct ip_set_ext ext = IP_SET_INIT_KEXT(skb, opt, set);
+ u32 ip;
/* MAC can be src only */
if (!(opt->flags & IPSET_DIM_TWO_SRC))
return 0;
- data.id = ntohl(ip4addr(skb, opt->flags & IPSET_DIM_ONE_SRC));
- if (data.id < map->first_ip || data.id > map->last_ip)
+ ip = ntohl(ip4addr(skb, opt->flags & IPSET_DIM_ONE_SRC));
+ if (ip < map->first_ip || ip > map->last_ip)
return -IPSET_ERR_BITMAP_RANGE;
/* Backward compatibility: we don't check the second flag */
@@ -364,10 +220,10 @@ bitmap_ipmac_kadt(struct ip_set *set, const struct sk_buff *skb,
(skb_mac_header(skb) + ETH_HLEN) > skb->data)
return -EINVAL;
- data.id -= map->first_ip;
- data.ether = eth_hdr(skb)->h_source;
+ e.id = ip_to_id(map, ip);
+ e.ether = eth_hdr(skb)->h_source;
- return adtfn(set, &data, opt_timeout(opt, map), opt->cmdflags);
+ return adtfn(set, &e, &ext, &opt->ext, opt->cmdflags);
}
static int
@@ -376,91 +232,39 @@ bitmap_ipmac_uadt(struct ip_set *set, struct nlattr *tb[],
{
const struct bitmap_ipmac *map = set->data;
ipset_adtfn adtfn = set->variant->adt[adt];
- struct ipmac data;
- u32 timeout = map->timeout;
+ struct bitmap_ipmac_adt_elem e = {};
+ struct ip_set_ext ext = IP_SET_INIT_UEXT(set);
+ u32 ip = 0;
int ret = 0;
if (unlikely(!tb[IPSET_ATTR_IP] ||
- !ip_set_optattr_netorder(tb, IPSET_ATTR_TIMEOUT)))
+ !ip_set_optattr_netorder(tb, IPSET_ATTR_TIMEOUT) ||
+ !ip_set_optattr_netorder(tb, IPSET_ATTR_PACKETS) ||
+ !ip_set_optattr_netorder(tb, IPSET_ATTR_BYTES)))
return -IPSET_ERR_PROTOCOL;
if (tb[IPSET_ATTR_LINENO])
*lineno = nla_get_u32(tb[IPSET_ATTR_LINENO]);
- ret = ip_set_get_hostipaddr4(tb[IPSET_ATTR_IP], &data.id);
+ ret = ip_set_get_hostipaddr4(tb[IPSET_ATTR_IP], &ip) ||
+ ip_set_get_extensions(set, tb, &ext);
if (ret)
return ret;
- if (data.id < map->first_ip || data.id > map->last_ip)
+ if (ip < map->first_ip || ip > map->last_ip)
return -IPSET_ERR_BITMAP_RANGE;
+ e.id = ip_to_id(map, ip);
if (tb[IPSET_ATTR_ETHER])
- data.ether = nla_data(tb[IPSET_ATTR_ETHER]);
+ e.ether = nla_data(tb[IPSET_ATTR_ETHER]);
else
- data.ether = NULL;
+ e.ether = NULL;
- if (tb[IPSET_ATTR_TIMEOUT]) {
- if (!with_timeout(map->timeout))
- return -IPSET_ERR_TIMEOUT;
- timeout = ip_set_timeout_uget(tb[IPSET_ATTR_TIMEOUT]);
- }
-
- data.id -= map->first_ip;
-
- ret = adtfn(set, &data, timeout, flags);
+ ret = adtfn(set, &e, &ext, &ext, flags);
return ip_set_eexist(ret, flags) ? 0 : ret;
}
-static void
-bitmap_ipmac_destroy(struct ip_set *set)
-{
- struct bitmap_ipmac *map = set->data;
-
- if (with_timeout(map->timeout))
- del_timer_sync(&map->gc);
-
- ip_set_free(map->members);
- kfree(map);
-
- set->data = NULL;
-}
-
-static void
-bitmap_ipmac_flush(struct ip_set *set)
-{
- struct bitmap_ipmac *map = set->data;
-
- memset(map->members, 0,
- (map->last_ip - map->first_ip + 1) * map->dsize);
-}
-
-static int
-bitmap_ipmac_head(struct ip_set *set, struct sk_buff *skb)
-{
- const struct bitmap_ipmac *map = set->data;
- struct nlattr *nested;
-
- nested = ipset_nest_start(skb, IPSET_ATTR_DATA);
- if (!nested)
- goto nla_put_failure;
- if (nla_put_ipaddr4(skb, IPSET_ATTR_IP, htonl(map->first_ip)) ||
- nla_put_ipaddr4(skb, IPSET_ATTR_IP_TO, htonl(map->last_ip)) ||
- nla_put_net32(skb, IPSET_ATTR_REFERENCES, htonl(set->ref - 1)) ||
- nla_put_net32(skb, IPSET_ATTR_MEMSIZE,
- htonl(sizeof(*map) +
- ((map->last_ip - map->first_ip + 1) *
- map->dsize))) ||
- (with_timeout(map->timeout) &&
- nla_put_net32(skb, IPSET_ATTR_TIMEOUT, htonl(map->timeout))))
- goto nla_put_failure;
- ipset_nest_end(skb, nested);
-
- return 0;
-nla_put_failure:
- return -EMSGSIZE;
-}
-
static bool
bitmap_ipmac_same_set(const struct ip_set *a, const struct ip_set *b)
{
@@ -469,86 +273,34 @@ bitmap_ipmac_same_set(const struct ip_set *a, const struct ip_set *b)
return x->first_ip == y->first_ip &&
x->last_ip == y->last_ip &&
- x->timeout == y->timeout;
+ a->timeout == b->timeout &&
+ a->extensions == b->extensions;
}
-static const struct ip_set_type_variant bitmap_ipmac = {
- .kadt = bitmap_ipmac_kadt,
- .uadt = bitmap_ipmac_uadt,
- .adt = {
- [IPSET_ADD] = bitmap_ipmac_add,
- [IPSET_DEL] = bitmap_ipmac_del,
- [IPSET_TEST] = bitmap_ipmac_test,
- },
- .destroy = bitmap_ipmac_destroy,
- .flush = bitmap_ipmac_flush,
- .head = bitmap_ipmac_head,
- .list = bitmap_ipmac_list,
- .same_set = bitmap_ipmac_same_set,
-};
+/* Plain variant */
-static const struct ip_set_type_variant bitmap_tipmac = {
- .kadt = bitmap_ipmac_kadt,
- .uadt = bitmap_ipmac_uadt,
- .adt = {
- [IPSET_ADD] = bitmap_ipmac_tadd,
- [IPSET_DEL] = bitmap_ipmac_tdel,
- [IPSET_TEST] = bitmap_ipmac_ttest,
- },
- .destroy = bitmap_ipmac_destroy,
- .flush = bitmap_ipmac_flush,
- .head = bitmap_ipmac_head,
- .list = bitmap_ipmac_tlist,
- .same_set = bitmap_ipmac_same_set,
-};
-
-static void
-bitmap_ipmac_gc(unsigned long ul_set)
-{
- struct ip_set *set = (struct ip_set *) ul_set;
- struct bitmap_ipmac *map = set->data;
- struct ipmac_telem *elem;
- u32 id, last = map->last_ip - map->first_ip;
-
- /* We run parallel with other readers (test element)
- * but adding/deleting new entries is locked out */
- read_lock_bh(&set->lock);
- for (id = 0; id <= last; id++) {
- elem = bitmap_ipmac_elem(map, id);
- if (elem->match == MAC_FILLED &&
- ip_set_timeout_expired(elem->timeout))
- elem->match = MAC_EMPTY;
- }
- read_unlock_bh(&set->lock);
-
- map->gc.expires = jiffies + IPSET_GC_PERIOD(map->timeout) * HZ;
- add_timer(&map->gc);
-}
-
-static void
-bitmap_ipmac_gc_init(struct ip_set *set)
-{
- struct bitmap_ipmac *map = set->data;
-
- init_timer(&map->gc);
- map->gc.data = (unsigned long) set;
- map->gc.function = bitmap_ipmac_gc;
- map->gc.expires = jiffies + IPSET_GC_PERIOD(map->timeout) * HZ;
- add_timer(&map->gc);
-}
+#include "ip_set_bitmap_gen.h"
/* Create bitmap:ip,mac type of sets */
static bool
init_map_ipmac(struct ip_set *set, struct bitmap_ipmac *map,
- u32 first_ip, u32 last_ip)
+ u32 first_ip, u32 last_ip, u32 elements)
{
- map->members = ip_set_alloc((last_ip - first_ip + 1) * map->dsize);
+ map->members = ip_set_alloc(map->memsize);
if (!map->members)
return false;
+ if (set->dsize) {
+ map->extensions = ip_set_alloc(set->dsize * elements);
+ if (!map->extensions) {
+ kfree(map->members);
+ return false;
+ }
+ }
map->first_ip = first_ip;
map->last_ip = last_ip;
- map->timeout = IPSET_NO_TIMEOUT;
+ map->elements = elements;
+ set->timeout = IPSET_NO_TIMEOUT;
set->data = map;
set->family = NFPROTO_IPV4;
@@ -557,16 +309,17 @@ init_map_ipmac(struct ip_set *set, struct bitmap_ipmac *map,
}
static int
-bitmap_ipmac_create(struct ip_set *set, struct nlattr *tb[],
+bitmap_ipmac_create(struct net *net, struct ip_set *set, struct nlattr *tb[],
u32 flags)
{
- u32 first_ip, last_ip;
+ u32 first_ip = 0, last_ip = 0;
u64 elements;
struct bitmap_ipmac *map;
int ret;
if (unlikely(!tb[IPSET_ATTR_IP] ||
- !ip_set_optattr_netorder(tb, IPSET_ATTR_TIMEOUT)))
+ !ip_set_optattr_netorder(tb, IPSET_ATTR_TIMEOUT) ||
+ !ip_set_optattr_netorder(tb, IPSET_ATTR_CADT_FLAGS)))
return -IPSET_ERR_PROTOCOL;
ret = ip_set_get_hostipaddr4(tb[IPSET_ATTR_IP], &first_ip);
@@ -601,28 +354,17 @@ bitmap_ipmac_create(struct ip_set *set, struct nlattr *tb[],
if (!map)
return -ENOMEM;
+ map->memsize = bitmap_bytes(0, elements - 1);
+ set->variant = &bitmap_ipmac;
+ set->dsize = ip_set_elem_len(set, tb,
+ sizeof(struct bitmap_ipmac_elem));
+ if (!init_map_ipmac(set, map, first_ip, last_ip, elements)) {
+ kfree(map);
+ return -ENOMEM;
+ }
if (tb[IPSET_ATTR_TIMEOUT]) {
- map->dsize = sizeof(struct ipmac_telem);
-
- if (!init_map_ipmac(set, map, first_ip, last_ip)) {
- kfree(map);
- return -ENOMEM;
- }
-
- map->timeout = ip_set_timeout_uget(tb[IPSET_ATTR_TIMEOUT]);
-
- set->variant = &bitmap_tipmac;
-
- bitmap_ipmac_gc_init(set);
- } else {
- map->dsize = sizeof(struct ipmac_elem);
-
- if (!init_map_ipmac(set, map, first_ip, last_ip)) {
- kfree(map);
- return -ENOMEM;
- }
- set->variant = &bitmap_ipmac;
-
+ set->timeout = ip_set_timeout_uget(tb[IPSET_ATTR_TIMEOUT]);
+ bitmap_ipmac_gc_init(set, bitmap_ipmac_gc);
}
return 0;
}
@@ -633,14 +375,15 @@ static struct ip_set_type bitmap_ipmac_type = {
.features = IPSET_TYPE_IP | IPSET_TYPE_MAC,
.dimension = IPSET_DIM_TWO,
.family = NFPROTO_IPV4,
- .revision_min = REVISION_MIN,
- .revision_max = REVISION_MAX,
+ .revision_min = IPSET_TYPE_REV_MIN,
+ .revision_max = IPSET_TYPE_REV_MAX,
.create = bitmap_ipmac_create,
.create_policy = {
[IPSET_ATTR_IP] = { .type = NLA_NESTED },
[IPSET_ATTR_IP_TO] = { .type = NLA_NESTED },
[IPSET_ATTR_CIDR] = { .type = NLA_U8 },
[IPSET_ATTR_TIMEOUT] = { .type = NLA_U32 },
+ [IPSET_ATTR_CADT_FLAGS] = { .type = NLA_U32 },
},
.adt_policy = {
[IPSET_ATTR_IP] = { .type = NLA_NESTED },
@@ -648,6 +391,9 @@ static struct ip_set_type bitmap_ipmac_type = {
.len = ETH_ALEN },
[IPSET_ATTR_TIMEOUT] = { .type = NLA_U32 },
[IPSET_ATTR_LINENO] = { .type = NLA_U32 },
+ [IPSET_ATTR_BYTES] = { .type = NLA_U64 },
+ [IPSET_ATTR_PACKETS] = { .type = NLA_U64 },
+ [IPSET_ATTR_COMMENT] = { .type = NLA_NUL_STRING },
},
.me = THIS_MODULE,
};
diff --git a/net/netfilter/ipset/ip_set_bitmap_port.c b/net/netfilter/ipset/ip_set_bitmap_port.c
index e6b2db76f4c..cf99676e69f 100644
--- a/net/netfilter/ipset/ip_set_bitmap_port.c
+++ b/net/netfilter/ipset/ip_set_bitmap_port.c
@@ -1,4 +1,4 @@
-/* Copyright (C) 2003-2011 Jozsef Kadlecsik <kadlec@blackhole.kfki.hu>
+/* Copyright (C) 2003-2013 Jozsef Kadlecsik <kadlec@blackhole.kfki.hu>
*
* This program is free software; you can redistribute it and/or modify
* it under the terms of the GNU General Public License version 2 as
@@ -19,205 +19,93 @@
#include <linux/netfilter/ipset/ip_set.h>
#include <linux/netfilter/ipset/ip_set_bitmap.h>
#include <linux/netfilter/ipset/ip_set_getport.h>
-#define IP_SET_BITMAP_TIMEOUT
-#include <linux/netfilter/ipset/ip_set_timeout.h>
-#define REVISION_MIN 0
-#define REVISION_MAX 0
+#define IPSET_TYPE_REV_MIN 0
+/* 1 Counter support added */
+#define IPSET_TYPE_REV_MAX 2 /* Comment support added */
MODULE_LICENSE("GPL");
MODULE_AUTHOR("Jozsef Kadlecsik <kadlec@blackhole.kfki.hu>");
-IP_SET_MODULE_DESC("bitmap:port", REVISION_MIN, REVISION_MAX);
+IP_SET_MODULE_DESC("bitmap:port", IPSET_TYPE_REV_MIN, IPSET_TYPE_REV_MAX);
MODULE_ALIAS("ip_set_bitmap:port");
+#define MTYPE bitmap_port
+
/* Type structure */
struct bitmap_port {
void *members; /* the set members */
+ void *extensions; /* data extensions */
u16 first_port; /* host byte order, included in range */
u16 last_port; /* host byte order, included in range */
+ u32 elements; /* number of max elements in the set */
size_t memsize; /* members size */
- u32 timeout; /* timeout parameter */
struct timer_list gc; /* garbage collection */
};
-/* Base variant */
+/* ADT structure for generic function args */
+struct bitmap_port_adt_elem {
+ u16 id;
+};
-static int
-bitmap_port_test(struct ip_set *set, void *value, u32 timeout, u32 flags)
+static inline u16
+port_to_id(const struct bitmap_port *m, u16 port)
{
- const struct bitmap_port *map = set->data;
- u16 id = *(u16 *)value;
-
- return !!test_bit(id, map->members);
+ return port - m->first_port;
}
-static int
-bitmap_port_add(struct ip_set *set, void *value, u32 timeout, u32 flags)
-{
- struct bitmap_port *map = set->data;
- u16 id = *(u16 *)value;
-
- if (test_and_set_bit(id, map->members))
- return -IPSET_ERR_EXIST;
-
- return 0;
-}
+/* Common functions */
-static int
-bitmap_port_del(struct ip_set *set, void *value, u32 timeout, u32 flags)
+static inline int
+bitmap_port_do_test(const struct bitmap_port_adt_elem *e,
+ const struct bitmap_port *map, size_t dsize)
{
- struct bitmap_port *map = set->data;
- u16 id = *(u16 *)value;
-
- if (!test_and_clear_bit(id, map->members))
- return -IPSET_ERR_EXIST;
-
- return 0;
+ return !!test_bit(e->id, map->members);
}
-static int
-bitmap_port_list(const struct ip_set *set,
- struct sk_buff *skb, struct netlink_callback *cb)
+static inline int
+bitmap_port_gc_test(u16 id, const struct bitmap_port *map, size_t dsize)
{
- const struct bitmap_port *map = set->data;
- struct nlattr *atd, *nested;
- u16 id, first = cb->args[2];
- u16 last = map->last_port - map->first_port;
-
- atd = ipset_nest_start(skb, IPSET_ATTR_ADT);
- if (!atd)
- return -EMSGSIZE;
- for (; cb->args[2] <= last; cb->args[2]++) {
- id = cb->args[2];
- if (!test_bit(id, map->members))
- continue;
- nested = ipset_nest_start(skb, IPSET_ATTR_DATA);
- if (!nested) {
- if (id == first) {
- nla_nest_cancel(skb, atd);
- return -EMSGSIZE;
- } else
- goto nla_put_failure;
- }
- if (nla_put_net16(skb, IPSET_ATTR_PORT,
- htons(map->first_port + id)))
- goto nla_put_failure;
- ipset_nest_end(skb, nested);
- }
- ipset_nest_end(skb, atd);
- /* Set listing finished */
- cb->args[2] = 0;
-
- return 0;
-
-nla_put_failure:
- nla_nest_cancel(skb, nested);
- ipset_nest_end(skb, atd);
- if (unlikely(id == first)) {
- cb->args[2] = 0;
- return -EMSGSIZE;
- }
- return 0;
+ return !!test_bit(id, map->members);
}
-/* Timeout variant */
-
-static int
-bitmap_port_ttest(struct ip_set *set, void *value, u32 timeout, u32 flags)
+static inline int
+bitmap_port_do_add(const struct bitmap_port_adt_elem *e,
+ struct bitmap_port *map, u32 flags, size_t dsize)
{
- const struct bitmap_port *map = set->data;
- const unsigned long *members = map->members;
- u16 id = *(u16 *)value;
-
- return ip_set_timeout_test(members[id]);
+ return !!test_and_set_bit(e->id, map->members);
}
-static int
-bitmap_port_tadd(struct ip_set *set, void *value, u32 timeout, u32 flags)
+static inline int
+bitmap_port_do_del(const struct bitmap_port_adt_elem *e,
+ struct bitmap_port *map)
{
- struct bitmap_port *map = set->data;
- unsigned long *members = map->members;
- u16 id = *(u16 *)value;
-
- if (ip_set_timeout_test(members[id]) && !(flags & IPSET_FLAG_EXIST))
- return -IPSET_ERR_EXIST;
-
- members[id] = ip_set_timeout_set(timeout);
-
- return 0;
+ return !test_and_clear_bit(e->id, map->members);
}
-static int
-bitmap_port_tdel(struct ip_set *set, void *value, u32 timeout, u32 flags)
+static inline int
+bitmap_port_do_list(struct sk_buff *skb, const struct bitmap_port *map, u32 id,
+ size_t dsize)
{
- struct bitmap_port *map = set->data;
- unsigned long *members = map->members;
- u16 id = *(u16 *)value;
- int ret = -IPSET_ERR_EXIST;
-
- if (ip_set_timeout_test(members[id]))
- ret = 0;
-
- members[id] = IPSET_ELEM_UNSET;
- return ret;
+ return nla_put_net16(skb, IPSET_ATTR_PORT,
+ htons(map->first_port + id));
}
-static int
-bitmap_port_tlist(const struct ip_set *set,
- struct sk_buff *skb, struct netlink_callback *cb)
+static inline int
+bitmap_port_do_head(struct sk_buff *skb, const struct bitmap_port *map)
{
- const struct bitmap_port *map = set->data;
- struct nlattr *adt, *nested;
- u16 id, first = cb->args[2];
- u16 last = map->last_port - map->first_port;
- const unsigned long *members = map->members;
-
- adt = ipset_nest_start(skb, IPSET_ATTR_ADT);
- if (!adt)
- return -EMSGSIZE;
- for (; cb->args[2] <= last; cb->args[2]++) {
- id = cb->args[2];
- if (!ip_set_timeout_test(members[id]))
- continue;
- nested = ipset_nest_start(skb, IPSET_ATTR_DATA);
- if (!nested) {
- if (id == first) {
- nla_nest_cancel(skb, adt);
- return -EMSGSIZE;
- } else
- goto nla_put_failure;
- }
- if (nla_put_net16(skb, IPSET_ATTR_PORT,
- htons(map->first_port + id)) ||
- nla_put_net32(skb, IPSET_ATTR_TIMEOUT,
- htonl(ip_set_timeout_get(members[id]))))
- goto nla_put_failure;
- ipset_nest_end(skb, nested);
- }
- ipset_nest_end(skb, adt);
-
- /* Set listing finished */
- cb->args[2] = 0;
-
- return 0;
-
-nla_put_failure:
- nla_nest_cancel(skb, nested);
- ipset_nest_end(skb, adt);
- if (unlikely(id == first)) {
- cb->args[2] = 0;
- return -EMSGSIZE;
- }
- return 0;
+ return nla_put_net16(skb, IPSET_ATTR_PORT, htons(map->first_port)) ||
+ nla_put_net16(skb, IPSET_ATTR_PORT_TO, htons(map->last_port));
}
static int
bitmap_port_kadt(struct ip_set *set, const struct sk_buff *skb,
const struct xt_action_param *par,
- enum ipset_adt adt, const struct ip_set_adt_opt *opt)
+ enum ipset_adt adt, struct ip_set_adt_opt *opt)
{
struct bitmap_port *map = set->data;
ipset_adtfn adtfn = set->variant->adt[adt];
+ struct bitmap_port_adt_elem e = {};
+ struct ip_set_ext ext = IP_SET_INIT_KEXT(skb, opt, set);
__be16 __port;
u16 port = 0;
@@ -230,9 +118,9 @@ bitmap_port_kadt(struct ip_set *set, const struct sk_buff *skb,
if (port < map->first_port || port > map->last_port)
return -IPSET_ERR_BITMAP_RANGE;
- port -= map->first_port;
+ e.id = port_to_id(map, port);
- return adtfn(set, &port, opt_timeout(opt, map), opt->cmdflags);
+ return adtfn(set, &e, &ext, &opt->ext, opt->cmdflags);
}
static int
@@ -241,14 +129,17 @@ bitmap_port_uadt(struct ip_set *set, struct nlattr *tb[],
{
struct bitmap_port *map = set->data;
ipset_adtfn adtfn = set->variant->adt[adt];
- u32 timeout = map->timeout;
+ struct bitmap_port_adt_elem e = {};
+ struct ip_set_ext ext = IP_SET_INIT_UEXT(set);
u32 port; /* wraparound */
- u16 id, port_to;
+ u16 port_to;
int ret = 0;
if (unlikely(!ip_set_attr_netorder(tb, IPSET_ATTR_PORT) ||
!ip_set_optattr_netorder(tb, IPSET_ATTR_PORT_TO) ||
- !ip_set_optattr_netorder(tb, IPSET_ATTR_TIMEOUT)))
+ !ip_set_optattr_netorder(tb, IPSET_ATTR_TIMEOUT) ||
+ !ip_set_optattr_netorder(tb, IPSET_ATTR_PACKETS) ||
+ !ip_set_optattr_netorder(tb, IPSET_ATTR_BYTES)))
return -IPSET_ERR_PROTOCOL;
if (tb[IPSET_ATTR_LINENO])
@@ -257,16 +148,13 @@ bitmap_port_uadt(struct ip_set *set, struct nlattr *tb[],
port = ip_set_get_h16(tb[IPSET_ATTR_PORT]);
if (port < map->first_port || port > map->last_port)
return -IPSET_ERR_BITMAP_RANGE;
-
- if (tb[IPSET_ATTR_TIMEOUT]) {
- if (!with_timeout(map->timeout))
- return -IPSET_ERR_TIMEOUT;
- timeout = ip_set_timeout_uget(tb[IPSET_ATTR_TIMEOUT]);
- }
+ ret = ip_set_get_extensions(set, tb, &ext);
+ if (ret)
+ return ret;
if (adt == IPSET_TEST) {
- id = port - map->first_port;
- return adtfn(set, &id, timeout, flags);
+ e.id = port_to_id(map, port);
+ return adtfn(set, &e, &ext, &ext, flags);
}
if (tb[IPSET_ATTR_PORT_TO]) {
@@ -283,8 +171,8 @@ bitmap_port_uadt(struct ip_set *set, struct nlattr *tb[],
return -IPSET_ERR_BITMAP_RANGE;
for (; port <= port_to; port++) {
- id = port - map->first_port;
- ret = adtfn(set, &id, timeout, flags);
+ e.id = port_to_id(map, port);
+ ret = adtfn(set, &e, &ext, &ext, flags);
if (ret && !ip_set_eexist(ret, flags))
return ret;
@@ -294,52 +182,6 @@ bitmap_port_uadt(struct ip_set *set, struct nlattr *tb[],
return ret;
}
-static void
-bitmap_port_destroy(struct ip_set *set)
-{
- struct bitmap_port *map = set->data;
-
- if (with_timeout(map->timeout))
- del_timer_sync(&map->gc);
-
- ip_set_free(map->members);
- kfree(map);
-
- set->data = NULL;
-}
-
-static void
-bitmap_port_flush(struct ip_set *set)
-{
- struct bitmap_port *map = set->data;
-
- memset(map->members, 0, map->memsize);
-}
-
-static int
-bitmap_port_head(struct ip_set *set, struct sk_buff *skb)
-{
- const struct bitmap_port *map = set->data;
- struct nlattr *nested;
-
- nested = ipset_nest_start(skb, IPSET_ATTR_DATA);
- if (!nested)
- goto nla_put_failure;
- if (nla_put_net16(skb, IPSET_ATTR_PORT, htons(map->first_port)) ||
- nla_put_net16(skb, IPSET_ATTR_PORT_TO, htons(map->last_port)) ||
- nla_put_net32(skb, IPSET_ATTR_REFERENCES, htonl(set->ref - 1)) ||
- nla_put_net32(skb, IPSET_ATTR_MEMSIZE,
- htonl(sizeof(*map) + map->memsize)) ||
- (with_timeout(map->timeout) &&
- nla_put_net32(skb, IPSET_ATTR_TIMEOUT, htonl(map->timeout))))
- goto nla_put_failure;
- ipset_nest_end(skb, nested);
-
- return 0;
-nla_put_failure:
- return -EMSGSIZE;
-}
-
static bool
bitmap_port_same_set(const struct ip_set *a, const struct ip_set *b)
{
@@ -348,71 +190,16 @@ bitmap_port_same_set(const struct ip_set *a, const struct ip_set *b)
return x->first_port == y->first_port &&
x->last_port == y->last_port &&
- x->timeout == y->timeout;
+ a->timeout == b->timeout &&
+ a->extensions == b->extensions;
}
-static const struct ip_set_type_variant bitmap_port = {
- .kadt = bitmap_port_kadt,
- .uadt = bitmap_port_uadt,
- .adt = {
- [IPSET_ADD] = bitmap_port_add,
- [IPSET_DEL] = bitmap_port_del,
- [IPSET_TEST] = bitmap_port_test,
- },
- .destroy = bitmap_port_destroy,
- .flush = bitmap_port_flush,
- .head = bitmap_port_head,
- .list = bitmap_port_list,
- .same_set = bitmap_port_same_set,
-};
+/* Plain variant */
-static const struct ip_set_type_variant bitmap_tport = {
- .kadt = bitmap_port_kadt,
- .uadt = bitmap_port_uadt,
- .adt = {
- [IPSET_ADD] = bitmap_port_tadd,
- [IPSET_DEL] = bitmap_port_tdel,
- [IPSET_TEST] = bitmap_port_ttest,
- },
- .destroy = bitmap_port_destroy,
- .flush = bitmap_port_flush,
- .head = bitmap_port_head,
- .list = bitmap_port_tlist,
- .same_set = bitmap_port_same_set,
+struct bitmap_port_elem {
};
-static void
-bitmap_port_gc(unsigned long ul_set)
-{
- struct ip_set *set = (struct ip_set *) ul_set;
- struct bitmap_port *map = set->data;
- unsigned long *table = map->members;
- u32 id; /* wraparound */
- u16 last = map->last_port - map->first_port;
-
- /* We run parallel with other readers (test element)
- * but adding/deleting new entries is locked out */
- read_lock_bh(&set->lock);
- for (id = 0; id <= last; id++)
- if (ip_set_timeout_expired(table[id]))
- table[id] = IPSET_ELEM_UNSET;
- read_unlock_bh(&set->lock);
-
- map->gc.expires = jiffies + IPSET_GC_PERIOD(map->timeout) * HZ;
- add_timer(&map->gc);
-}
-
-static void
-bitmap_port_gc_init(struct ip_set *set)
-{
- struct bitmap_port *map = set->data;
-
- init_timer(&map->gc);
- map->gc.data = (unsigned long) set;
- map->gc.function = bitmap_port_gc;
- map->gc.expires = jiffies + IPSET_GC_PERIOD(map->timeout) * HZ;
- add_timer(&map->gc);
-}
+#include "ip_set_bitmap_gen.h"
/* Create bitmap:ip type of sets */
@@ -423,9 +210,16 @@ init_map_port(struct ip_set *set, struct bitmap_port *map,
map->members = ip_set_alloc(map->memsize);
if (!map->members)
return false;
+ if (set->dsize) {
+ map->extensions = ip_set_alloc(set->dsize * map->elements);
+ if (!map->extensions) {
+ kfree(map->members);
+ return false;
+ }
+ }
map->first_port = first_port;
map->last_port = last_port;
- map->timeout = IPSET_NO_TIMEOUT;
+ set->timeout = IPSET_NO_TIMEOUT;
set->data = map;
set->family = NFPROTO_UNSPEC;
@@ -434,15 +228,16 @@ init_map_port(struct ip_set *set, struct bitmap_port *map,
}
static int
-bitmap_port_create(struct ip_set *set, struct nlattr *tb[],
- u32 flags)
+bitmap_port_create(struct net *net, struct ip_set *set, struct nlattr *tb[],
+ u32 flags)
{
struct bitmap_port *map;
u16 first_port, last_port;
if (unlikely(!ip_set_attr_netorder(tb, IPSET_ATTR_PORT) ||
!ip_set_attr_netorder(tb, IPSET_ATTR_PORT_TO) ||
- !ip_set_optattr_netorder(tb, IPSET_ATTR_TIMEOUT)))
+ !ip_set_optattr_netorder(tb, IPSET_ATTR_TIMEOUT) ||
+ !ip_set_optattr_netorder(tb, IPSET_ATTR_CADT_FLAGS)))
return -IPSET_ERR_PROTOCOL;
first_port = ip_set_get_h16(tb[IPSET_ATTR_PORT]);
@@ -458,28 +253,17 @@ bitmap_port_create(struct ip_set *set, struct nlattr *tb[],
if (!map)
return -ENOMEM;
+ map->elements = last_port - first_port + 1;
+ map->memsize = bitmap_bytes(0, map->elements);
+ set->variant = &bitmap_port;
+ set->dsize = ip_set_elem_len(set, tb, 0);
+ if (!init_map_port(set, map, first_port, last_port)) {
+ kfree(map);
+ return -ENOMEM;
+ }
if (tb[IPSET_ATTR_TIMEOUT]) {
- map->memsize = (last_port - first_port + 1)
- * sizeof(unsigned long);
-
- if (!init_map_port(set, map, first_port, last_port)) {
- kfree(map);
- return -ENOMEM;
- }
-
- map->timeout = ip_set_timeout_uget(tb[IPSET_ATTR_TIMEOUT]);
- set->variant = &bitmap_tport;
-
- bitmap_port_gc_init(set);
- } else {
- map->memsize = bitmap_bytes(0, last_port - first_port);
- pr_debug("memsize: %zu\n", map->memsize);
- if (!init_map_port(set, map, first_port, last_port)) {
- kfree(map);
- return -ENOMEM;
- }
-
- set->variant = &bitmap_port;
+ set->timeout = ip_set_timeout_uget(tb[IPSET_ATTR_TIMEOUT]);
+ bitmap_port_gc_init(set, bitmap_port_gc);
}
return 0;
}
@@ -490,19 +274,23 @@ static struct ip_set_type bitmap_port_type = {
.features = IPSET_TYPE_PORT,
.dimension = IPSET_DIM_ONE,
.family = NFPROTO_UNSPEC,
- .revision_min = REVISION_MIN,
- .revision_max = REVISION_MAX,
+ .revision_min = IPSET_TYPE_REV_MIN,
+ .revision_max = IPSET_TYPE_REV_MAX,
.create = bitmap_port_create,
.create_policy = {
[IPSET_ATTR_PORT] = { .type = NLA_U16 },
[IPSET_ATTR_PORT_TO] = { .type = NLA_U16 },
[IPSET_ATTR_TIMEOUT] = { .type = NLA_U32 },
+ [IPSET_ATTR_CADT_FLAGS] = { .type = NLA_U32 },
},
.adt_policy = {
[IPSET_ATTR_PORT] = { .type = NLA_U16 },
[IPSET_ATTR_PORT_TO] = { .type = NLA_U16 },
[IPSET_ATTR_TIMEOUT] = { .type = NLA_U32 },
[IPSET_ATTR_LINENO] = { .type = NLA_U32 },
+ [IPSET_ATTR_BYTES] = { .type = NLA_U64 },
+ [IPSET_ATTR_PACKETS] = { .type = NLA_U64 },
+ [IPSET_ATTR_COMMENT] = { .type = NLA_NUL_STRING },
},
.me = THIS_MODULE,
};
diff --git a/net/netfilter/ipset/ip_set_core.c b/net/netfilter/ipset/ip_set_core.c
index 6d6d8f2b033..ec8114fae50 100644
--- a/net/netfilter/ipset/ip_set_core.c
+++ b/net/netfilter/ipset/ip_set_core.c
@@ -1,6 +1,6 @@
/* Copyright (C) 2000-2002 Joakim Axelsson <gozem@linux.nu>
* Patrick Schaaf <bof@bof.de>
- * Copyright (C) 2003-2011 Jozsef Kadlecsik <kadlec@blackhole.kfki.hu>
+ * Copyright (C) 2003-2013 Jozsef Kadlecsik <kadlec@blackhole.kfki.hu>
*
* This program is free software; you can redistribute it and/or modify
* it under the terms of the GNU General Public License version 2 as
@@ -15,9 +15,10 @@
#include <linux/ip.h>
#include <linux/skbuff.h>
#include <linux/spinlock.h>
-#include <linux/netlink.h>
#include <linux/rculist.h>
#include <net/netlink.h>
+#include <net/net_namespace.h>
+#include <net/netns/generic.h>
#include <linux/netfilter.h>
#include <linux/netfilter/x_tables.h>
@@ -28,8 +29,17 @@ static LIST_HEAD(ip_set_type_list); /* all registered set types */
static DEFINE_MUTEX(ip_set_type_mutex); /* protects ip_set_type_list */
static DEFINE_RWLOCK(ip_set_ref_lock); /* protects the set refs */
-static struct ip_set * __rcu *ip_set_list; /* all individual sets */
-static ip_set_id_t ip_set_max = CONFIG_IP_SET_MAX; /* max number of sets */
+struct ip_set_net {
+ struct ip_set * __rcu *ip_set_list; /* all individual sets */
+ ip_set_id_t ip_set_max; /* max number of sets */
+ int is_deleted; /* deleted by ip_set_net_exit */
+};
+static int ip_set_net_id __read_mostly;
+
+static inline struct ip_set_net *ip_set_pernet(struct net *net)
+{
+ return net_generic(net, ip_set_net_id);
+}
#define IP_SET_INC 64
#define STREQ(a, b) (strncmp(a, b, IPSET_MAXNAMELEN) == 0)
@@ -44,10 +54,10 @@ MODULE_DESCRIPTION("core IP set support");
MODULE_ALIAS_NFNL_SUBSYS(NFNL_SUBSYS_IPSET);
/* When the nfnl mutex is held: */
-#define nfnl_dereference(p) \
+#define ip_set_dereference(p) \
rcu_dereference_protected(p, 1)
-#define nfnl_set(id) \
- nfnl_dereference(ip_set_list)[id]
+#define ip_set(inst, id) \
+ ip_set_dereference((inst)->ip_set_list)[id]
/*
* The set types are implemented in modules and registered set types
@@ -88,14 +98,14 @@ find_set_type(const char *name, u8 family, u8 revision)
static bool
load_settype(const char *name)
{
- nfnl_unlock();
+ nfnl_unlock(NFNL_SUBSYS_IPSET);
pr_debug("try to load ip_set_%s\n", name);
if (request_module("ip_set_%s", name) < 0) {
pr_warning("Can't find ip_set type %s\n", name);
- nfnl_lock();
+ nfnl_lock(NFNL_SUBSYS_IPSET);
return false;
}
- nfnl_lock();
+ nfnl_lock(NFNL_SUBSYS_IPSET);
return true;
}
@@ -261,10 +271,7 @@ ip_set_free(void *members)
{
pr_debug("%p: free with %s\n", members,
is_vmalloc_addr(members) ? "vfree" : "kfree");
- if (is_vmalloc_addr(members))
- vfree(members);
- else
- kfree(members);
+ kvfree(members);
}
EXPORT_SYMBOL_GPL(ip_set_free);
@@ -316,6 +323,91 @@ ip_set_get_ipaddr6(struct nlattr *nla, union nf_inet_addr *ipaddr)
}
EXPORT_SYMBOL_GPL(ip_set_get_ipaddr6);
+typedef void (*destroyer)(void *);
+/* ipset data extension types, in size order */
+
+const struct ip_set_ext_type ip_set_extensions[] = {
+ [IPSET_EXT_ID_COUNTER] = {
+ .type = IPSET_EXT_COUNTER,
+ .flag = IPSET_FLAG_WITH_COUNTERS,
+ .len = sizeof(struct ip_set_counter),
+ .align = __alignof__(struct ip_set_counter),
+ },
+ [IPSET_EXT_ID_TIMEOUT] = {
+ .type = IPSET_EXT_TIMEOUT,
+ .len = sizeof(unsigned long),
+ .align = __alignof__(unsigned long),
+ },
+ [IPSET_EXT_ID_COMMENT] = {
+ .type = IPSET_EXT_COMMENT | IPSET_EXT_DESTROY,
+ .flag = IPSET_FLAG_WITH_COMMENT,
+ .len = sizeof(struct ip_set_comment),
+ .align = __alignof__(struct ip_set_comment),
+ .destroy = (destroyer) ip_set_comment_free,
+ },
+};
+EXPORT_SYMBOL_GPL(ip_set_extensions);
+
+static inline bool
+add_extension(enum ip_set_ext_id id, u32 flags, struct nlattr *tb[])
+{
+ return ip_set_extensions[id].flag ?
+ (flags & ip_set_extensions[id].flag) :
+ !!tb[IPSET_ATTR_TIMEOUT];
+}
+
+size_t
+ip_set_elem_len(struct ip_set *set, struct nlattr *tb[], size_t len)
+{
+ enum ip_set_ext_id id;
+ size_t offset = 0;
+ u32 cadt_flags = 0;
+
+ if (tb[IPSET_ATTR_CADT_FLAGS])
+ cadt_flags = ip_set_get_h32(tb[IPSET_ATTR_CADT_FLAGS]);
+ if (cadt_flags & IPSET_FLAG_WITH_FORCEADD)
+ set->flags |= IPSET_CREATE_FLAG_FORCEADD;
+ for (id = 0; id < IPSET_EXT_ID_MAX; id++) {
+ if (!add_extension(id, cadt_flags, tb))
+ continue;
+ offset += ALIGN(len + offset, ip_set_extensions[id].align);
+ set->offset[id] = offset;
+ set->extensions |= ip_set_extensions[id].type;
+ offset += ip_set_extensions[id].len;
+ }
+ return len + offset;
+}
+EXPORT_SYMBOL_GPL(ip_set_elem_len);
+
+int
+ip_set_get_extensions(struct ip_set *set, struct nlattr *tb[],
+ struct ip_set_ext *ext)
+{
+ if (tb[IPSET_ATTR_TIMEOUT]) {
+ if (!(set->extensions & IPSET_EXT_TIMEOUT))
+ return -IPSET_ERR_TIMEOUT;
+ ext->timeout = ip_set_timeout_uget(tb[IPSET_ATTR_TIMEOUT]);
+ }
+ if (tb[IPSET_ATTR_BYTES] || tb[IPSET_ATTR_PACKETS]) {
+ if (!(set->extensions & IPSET_EXT_COUNTER))
+ return -IPSET_ERR_COUNTER;
+ if (tb[IPSET_ATTR_BYTES])
+ ext->bytes = be64_to_cpu(nla_get_be64(
+ tb[IPSET_ATTR_BYTES]));
+ if (tb[IPSET_ATTR_PACKETS])
+ ext->packets = be64_to_cpu(nla_get_be64(
+ tb[IPSET_ATTR_PACKETS]));
+ }
+ if (tb[IPSET_ATTR_COMMENT]) {
+ if (!(set->extensions & IPSET_EXT_COMMENT))
+ return -IPSET_ERR_COMMENT;
+ ext->comment = ip_set_comment_uget(tb[IPSET_ATTR_COMMENT]);
+ }
+
+ return 0;
+}
+EXPORT_SYMBOL_GPL(ip_set_get_extensions);
+
/*
* Creating/destroying/renaming/swapping affect the existence and
* the properties of a set. All of these can be executed from userspace
@@ -352,13 +444,14 @@ __ip_set_put(struct ip_set *set)
*/
static inline struct ip_set *
-ip_set_rcu_get(ip_set_id_t index)
+ip_set_rcu_get(struct net *net, ip_set_id_t index)
{
struct ip_set *set;
+ struct ip_set_net *inst = ip_set_pernet(net);
rcu_read_lock();
/* ip_set_list itself needs to be protected */
- set = rcu_dereference(ip_set_list)[index];
+ set = rcu_dereference(inst->ip_set_list)[index];
rcu_read_unlock();
return set;
@@ -366,10 +459,10 @@ ip_set_rcu_get(ip_set_id_t index)
int
ip_set_test(ip_set_id_t index, const struct sk_buff *skb,
- const struct xt_action_param *par,
- const struct ip_set_adt_opt *opt)
+ const struct xt_action_param *par, struct ip_set_adt_opt *opt)
{
- struct ip_set *set = ip_set_rcu_get(index);
+ struct ip_set *set = ip_set_rcu_get(
+ dev_net(par->in ? par->in : par->out), index);
int ret = 0;
BUG_ON(set == NULL);
@@ -392,7 +485,7 @@ ip_set_test(ip_set_id_t index, const struct sk_buff *skb,
ret = 1;
} else {
/* --return-nomatch: invert matched element */
- if ((opt->flags & IPSET_RETURN_NOMATCH) &&
+ if ((opt->cmdflags & IPSET_FLAG_RETURN_NOMATCH) &&
(set->type->features & IPSET_TYPE_NOMATCH) &&
(ret > 0 || ret == -ENOTEMPTY))
ret = -ret;
@@ -405,10 +498,10 @@ EXPORT_SYMBOL_GPL(ip_set_test);
int
ip_set_add(ip_set_id_t index, const struct sk_buff *skb,
- const struct xt_action_param *par,
- const struct ip_set_adt_opt *opt)
+ const struct xt_action_param *par, struct ip_set_adt_opt *opt)
{
- struct ip_set *set = ip_set_rcu_get(index);
+ struct ip_set *set = ip_set_rcu_get(
+ dev_net(par->in ? par->in : par->out), index);
int ret;
BUG_ON(set == NULL);
@@ -416,7 +509,7 @@ ip_set_add(ip_set_id_t index, const struct sk_buff *skb,
if (opt->dim < set->type->dimension ||
!(opt->family == set->family || set->family == NFPROTO_UNSPEC))
- return 0;
+ return -IPSET_ERR_TYPE_MISMATCH;
write_lock_bh(&set->lock);
ret = set->variant->kadt(set, skb, par, IPSET_ADD, opt);
@@ -428,10 +521,10 @@ EXPORT_SYMBOL_GPL(ip_set_add);
int
ip_set_del(ip_set_id_t index, const struct sk_buff *skb,
- const struct xt_action_param *par,
- const struct ip_set_adt_opt *opt)
+ const struct xt_action_param *par, struct ip_set_adt_opt *opt)
{
- struct ip_set *set = ip_set_rcu_get(index);
+ struct ip_set *set = ip_set_rcu_get(
+ dev_net(par->in ? par->in : par->out), index);
int ret = 0;
BUG_ON(set == NULL);
@@ -439,7 +532,7 @@ ip_set_del(ip_set_id_t index, const struct sk_buff *skb,
if (opt->dim < set->type->dimension ||
!(opt->family == set->family || set->family == NFPROTO_UNSPEC))
- return 0;
+ return -IPSET_ERR_TYPE_MISMATCH;
write_lock_bh(&set->lock);
ret = set->variant->kadt(set, skb, par, IPSET_DEL, opt);
@@ -455,14 +548,15 @@ EXPORT_SYMBOL_GPL(ip_set_del);
*
*/
ip_set_id_t
-ip_set_get_byname(const char *name, struct ip_set **set)
+ip_set_get_byname(struct net *net, const char *name, struct ip_set **set)
{
ip_set_id_t i, index = IPSET_INVALID_ID;
struct ip_set *s;
+ struct ip_set_net *inst = ip_set_pernet(net);
rcu_read_lock();
- for (i = 0; i < ip_set_max; i++) {
- s = rcu_dereference(ip_set_list)[i];
+ for (i = 0; i < inst->ip_set_max; i++) {
+ s = rcu_dereference(inst->ip_set_list)[i];
if (s != NULL && STREQ(s->name, name)) {
__ip_set_get(s);
index = i;
@@ -482,17 +576,26 @@ EXPORT_SYMBOL_GPL(ip_set_get_byname);
* to be valid, after calling this function.
*
*/
-void
-ip_set_put_byindex(ip_set_id_t index)
+
+static inline void
+__ip_set_put_byindex(struct ip_set_net *inst, ip_set_id_t index)
{
struct ip_set *set;
rcu_read_lock();
- set = rcu_dereference(ip_set_list)[index];
+ set = rcu_dereference(inst->ip_set_list)[index];
if (set != NULL)
__ip_set_put(set);
rcu_read_unlock();
}
+
+void
+ip_set_put_byindex(struct net *net, ip_set_id_t index)
+{
+ struct ip_set_net *inst = ip_set_pernet(net);
+
+ __ip_set_put_byindex(inst, index);
+}
EXPORT_SYMBOL_GPL(ip_set_put_byindex);
/*
@@ -503,9 +606,9 @@ EXPORT_SYMBOL_GPL(ip_set_put_byindex);
*
*/
const char *
-ip_set_name_byindex(ip_set_id_t index)
+ip_set_name_byindex(struct net *net, ip_set_id_t index)
{
- const struct ip_set *set = ip_set_rcu_get(index);
+ const struct ip_set *set = ip_set_rcu_get(net, index);
BUG_ON(set == NULL);
BUG_ON(set->ref == 0);
@@ -521,53 +624,27 @@ EXPORT_SYMBOL_GPL(ip_set_name_byindex);
*/
/*
- * Find set by name, reference it once. The reference makes sure the
- * thing pointed to, does not go away under our feet.
- *
- * The nfnl mutex is used in the function.
- */
-ip_set_id_t
-ip_set_nfnl_get(const char *name)
-{
- ip_set_id_t i, index = IPSET_INVALID_ID;
- struct ip_set *s;
-
- nfnl_lock();
- for (i = 0; i < ip_set_max; i++) {
- s = nfnl_set(i);
- if (s != NULL && STREQ(s->name, name)) {
- __ip_set_get(s);
- index = i;
- break;
- }
- }
- nfnl_unlock();
-
- return index;
-}
-EXPORT_SYMBOL_GPL(ip_set_nfnl_get);
-
-/*
* Find set by index, reference it once. The reference makes sure the
* thing pointed to, does not go away under our feet.
*
* The nfnl mutex is used in the function.
*/
ip_set_id_t
-ip_set_nfnl_get_byindex(ip_set_id_t index)
+ip_set_nfnl_get_byindex(struct net *net, ip_set_id_t index)
{
struct ip_set *set;
+ struct ip_set_net *inst = ip_set_pernet(net);
- if (index > ip_set_max)
+ if (index > inst->ip_set_max)
return IPSET_INVALID_ID;
- nfnl_lock();
- set = nfnl_set(index);
+ nfnl_lock(NFNL_SUBSYS_IPSET);
+ set = ip_set(inst, index);
if (set)
__ip_set_get(set);
else
index = IPSET_INVALID_ID;
- nfnl_unlock();
+ nfnl_unlock(NFNL_SUBSYS_IPSET);
return index;
}
@@ -581,14 +658,18 @@ EXPORT_SYMBOL_GPL(ip_set_nfnl_get_byindex);
* The nfnl mutex is used in the function.
*/
void
-ip_set_nfnl_put(ip_set_id_t index)
+ip_set_nfnl_put(struct net *net, ip_set_id_t index)
{
struct ip_set *set;
- nfnl_lock();
- set = nfnl_set(index);
- if (set != NULL)
- __ip_set_put(set);
- nfnl_unlock();
+ struct ip_set_net *inst = ip_set_pernet(net);
+
+ nfnl_lock(NFNL_SUBSYS_IPSET);
+ if (!inst->is_deleted) { /* already deleted from ip_set_net_exit() */
+ set = ip_set(inst, index);
+ if (set != NULL)
+ __ip_set_put(set);
+ }
+ nfnl_unlock(NFNL_SUBSYS_IPSET);
}
EXPORT_SYMBOL_GPL(ip_set_nfnl_put);
@@ -645,14 +726,14 @@ static const struct nla_policy ip_set_create_policy[IPSET_ATTR_CMD_MAX + 1] = {
};
static struct ip_set *
-find_set_and_id(const char *name, ip_set_id_t *id)
+find_set_and_id(struct ip_set_net *inst, const char *name, ip_set_id_t *id)
{
struct ip_set *set = NULL;
ip_set_id_t i;
*id = IPSET_INVALID_ID;
- for (i = 0; i < ip_set_max; i++) {
- set = nfnl_set(i);
+ for (i = 0; i < inst->ip_set_max; i++) {
+ set = ip_set(inst, i);
if (set != NULL && STREQ(set->name, name)) {
*id = i;
break;
@@ -662,22 +743,23 @@ find_set_and_id(const char *name, ip_set_id_t *id)
}
static inline struct ip_set *
-find_set(const char *name)
+find_set(struct ip_set_net *inst, const char *name)
{
ip_set_id_t id;
- return find_set_and_id(name, &id);
+ return find_set_and_id(inst, name, &id);
}
static int
-find_free_id(const char *name, ip_set_id_t *index, struct ip_set **set)
+find_free_id(struct ip_set_net *inst, const char *name, ip_set_id_t *index,
+ struct ip_set **set)
{
struct ip_set *s;
ip_set_id_t i;
*index = IPSET_INVALID_ID;
- for (i = 0; i < ip_set_max; i++) {
- s = nfnl_set(i);
+ for (i = 0; i < inst->ip_set_max; i++) {
+ s = ip_set(inst, i);
if (s == NULL) {
if (*index == IPSET_INVALID_ID)
*index = i;
@@ -706,6 +788,8 @@ ip_set_create(struct sock *ctnl, struct sk_buff *skb,
const struct nlmsghdr *nlh,
const struct nlattr * const attr[])
{
+ struct net *net = sock_net(ctnl);
+ struct ip_set_net *inst = ip_set_pernet(net);
struct ip_set *set, *clash = NULL;
ip_set_id_t index = IPSET_INVALID_ID;
struct nlattr *tb[IPSET_ATTR_CREATE_MAX+1] = {};
@@ -764,7 +848,7 @@ ip_set_create(struct sock *ctnl, struct sk_buff *skb,
goto put_out;
}
- ret = set->type->create(set, tb, flags);
+ ret = set->type->create(net, set, tb, flags);
if (ret != 0)
goto put_out;
@@ -775,7 +859,7 @@ ip_set_create(struct sock *ctnl, struct sk_buff *skb,
* by the nfnl mutex. Find the first free index in ip_set_list
* and check clashing.
*/
- ret = find_free_id(set->name, &index, &clash);
+ ret = find_free_id(inst, set->name, &index, &clash);
if (ret == -EEXIST) {
/* If this is the same set and requested, ignore error */
if ((flags & IPSET_FLAG_EXIST) &&
@@ -788,9 +872,9 @@ ip_set_create(struct sock *ctnl, struct sk_buff *skb,
goto cleanup;
} else if (ret == -IPSET_ERR_MAX_SETS) {
struct ip_set **list, **tmp;
- ip_set_id_t i = ip_set_max + IP_SET_INC;
+ ip_set_id_t i = inst->ip_set_max + IP_SET_INC;
- if (i < ip_set_max || i == IPSET_INVALID_ID)
+ if (i < inst->ip_set_max || i == IPSET_INVALID_ID)
/* Wraparound */
goto cleanup;
@@ -798,14 +882,14 @@ ip_set_create(struct sock *ctnl, struct sk_buff *skb,
if (!list)
goto cleanup;
/* nfnl mutex is held, both lists are valid */
- tmp = nfnl_dereference(ip_set_list);
- memcpy(list, tmp, sizeof(struct ip_set *) * ip_set_max);
- rcu_assign_pointer(ip_set_list, list);
+ tmp = ip_set_dereference(inst->ip_set_list);
+ memcpy(list, tmp, sizeof(struct ip_set *) * inst->ip_set_max);
+ rcu_assign_pointer(inst->ip_set_list, list);
/* Make sure all current packets have passed through */
synchronize_net();
/* Use new list */
- index = ip_set_max;
- ip_set_max = i;
+ index = inst->ip_set_max;
+ inst->ip_set_max = i;
kfree(tmp);
ret = 0;
} else if (ret)
@@ -815,7 +899,7 @@ ip_set_create(struct sock *ctnl, struct sk_buff *skb,
* Finally! Add our shiny new set to the list, and be done.
*/
pr_debug("create: '%s' created with index %u!\n", set->name, index);
- nfnl_set(index) = set;
+ ip_set(inst, index) = set;
return ret;
@@ -838,12 +922,12 @@ ip_set_setname_policy[IPSET_ATTR_CMD_MAX + 1] = {
};
static void
-ip_set_destroy_set(ip_set_id_t index)
+ip_set_destroy_set(struct ip_set_net *inst, ip_set_id_t index)
{
- struct ip_set *set = nfnl_set(index);
+ struct ip_set *set = ip_set(inst, index);
pr_debug("set: %s\n", set->name);
- nfnl_set(index) = NULL;
+ ip_set(inst, index) = NULL;
/* Must call it without holding any lock */
set->variant->destroy(set);
@@ -856,6 +940,7 @@ ip_set_destroy(struct sock *ctnl, struct sk_buff *skb,
const struct nlmsghdr *nlh,
const struct nlattr * const attr[])
{
+ struct ip_set_net *inst = ip_set_pernet(sock_net(ctnl));
struct ip_set *s;
ip_set_id_t i;
int ret = 0;
@@ -875,21 +960,22 @@ ip_set_destroy(struct sock *ctnl, struct sk_buff *skb,
*/
read_lock_bh(&ip_set_ref_lock);
if (!attr[IPSET_ATTR_SETNAME]) {
- for (i = 0; i < ip_set_max; i++) {
- s = nfnl_set(i);
+ for (i = 0; i < inst->ip_set_max; i++) {
+ s = ip_set(inst, i);
if (s != NULL && s->ref) {
ret = -IPSET_ERR_BUSY;
goto out;
}
}
read_unlock_bh(&ip_set_ref_lock);
- for (i = 0; i < ip_set_max; i++) {
- s = nfnl_set(i);
+ for (i = 0; i < inst->ip_set_max; i++) {
+ s = ip_set(inst, i);
if (s != NULL)
- ip_set_destroy_set(i);
+ ip_set_destroy_set(inst, i);
}
} else {
- s = find_set_and_id(nla_data(attr[IPSET_ATTR_SETNAME]), &i);
+ s = find_set_and_id(inst, nla_data(attr[IPSET_ATTR_SETNAME]),
+ &i);
if (s == NULL) {
ret = -ENOENT;
goto out;
@@ -899,7 +985,7 @@ ip_set_destroy(struct sock *ctnl, struct sk_buff *skb,
}
read_unlock_bh(&ip_set_ref_lock);
- ip_set_destroy_set(i);
+ ip_set_destroy_set(inst, i);
}
return 0;
out:
@@ -924,6 +1010,7 @@ ip_set_flush(struct sock *ctnl, struct sk_buff *skb,
const struct nlmsghdr *nlh,
const struct nlattr * const attr[])
{
+ struct ip_set_net *inst = ip_set_pernet(sock_net(ctnl));
struct ip_set *s;
ip_set_id_t i;
@@ -931,13 +1018,13 @@ ip_set_flush(struct sock *ctnl, struct sk_buff *skb,
return -IPSET_ERR_PROTOCOL;
if (!attr[IPSET_ATTR_SETNAME]) {
- for (i = 0; i < ip_set_max; i++) {
- s = nfnl_set(i);
+ for (i = 0; i < inst->ip_set_max; i++) {
+ s = ip_set(inst, i);
if (s != NULL)
ip_set_flush_set(s);
}
} else {
- s = find_set(nla_data(attr[IPSET_ATTR_SETNAME]));
+ s = find_set(inst, nla_data(attr[IPSET_ATTR_SETNAME]));
if (s == NULL)
return -ENOENT;
@@ -963,6 +1050,7 @@ ip_set_rename(struct sock *ctnl, struct sk_buff *skb,
const struct nlmsghdr *nlh,
const struct nlattr * const attr[])
{
+ struct ip_set_net *inst = ip_set_pernet(sock_net(ctnl));
struct ip_set *set, *s;
const char *name2;
ip_set_id_t i;
@@ -973,7 +1061,7 @@ ip_set_rename(struct sock *ctnl, struct sk_buff *skb,
attr[IPSET_ATTR_SETNAME2] == NULL))
return -IPSET_ERR_PROTOCOL;
- set = find_set(nla_data(attr[IPSET_ATTR_SETNAME]));
+ set = find_set(inst, nla_data(attr[IPSET_ATTR_SETNAME]));
if (set == NULL)
return -ENOENT;
@@ -984,8 +1072,8 @@ ip_set_rename(struct sock *ctnl, struct sk_buff *skb,
}
name2 = nla_data(attr[IPSET_ATTR_SETNAME2]);
- for (i = 0; i < ip_set_max; i++) {
- s = nfnl_set(i);
+ for (i = 0; i < inst->ip_set_max; i++) {
+ s = ip_set(inst, i);
if (s != NULL && STREQ(s->name, name2)) {
ret = -IPSET_ERR_EXIST_SETNAME2;
goto out;
@@ -1012,6 +1100,7 @@ ip_set_swap(struct sock *ctnl, struct sk_buff *skb,
const struct nlmsghdr *nlh,
const struct nlattr * const attr[])
{
+ struct ip_set_net *inst = ip_set_pernet(sock_net(ctnl));
struct ip_set *from, *to;
ip_set_id_t from_id, to_id;
char from_name[IPSET_MAXNAMELEN];
@@ -1021,11 +1110,13 @@ ip_set_swap(struct sock *ctnl, struct sk_buff *skb,
attr[IPSET_ATTR_SETNAME2] == NULL))
return -IPSET_ERR_PROTOCOL;
- from = find_set_and_id(nla_data(attr[IPSET_ATTR_SETNAME]), &from_id);
+ from = find_set_and_id(inst, nla_data(attr[IPSET_ATTR_SETNAME]),
+ &from_id);
if (from == NULL)
return -ENOENT;
- to = find_set_and_id(nla_data(attr[IPSET_ATTR_SETNAME2]), &to_id);
+ to = find_set_and_id(inst, nla_data(attr[IPSET_ATTR_SETNAME2]),
+ &to_id);
if (to == NULL)
return -IPSET_ERR_EXIST_SETNAME2;
@@ -1033,7 +1124,7 @@ ip_set_swap(struct sock *ctnl, struct sk_buff *skb,
* Not an artificial restriction anymore, as we must prevent
* possible loops created by swapping in setlist type of sets. */
if (!(from->type->features == to->type->features &&
- from->type->family == to->type->family))
+ from->family == to->family))
return -IPSET_ERR_TYPE_MISMATCH;
strncpy(from_name, from->name, IPSET_MAXNAMELEN);
@@ -1042,8 +1133,8 @@ ip_set_swap(struct sock *ctnl, struct sk_buff *skb,
write_lock_bh(&ip_set_ref_lock);
swap(from->ref, to->ref);
- nfnl_set(from_id) = to;
- nfnl_set(to_id) = from;
+ ip_set(inst, from_id) = to;
+ ip_set(inst, to_id) = from;
write_unlock_bh(&ip_set_ref_lock);
return 0;
@@ -1062,9 +1153,12 @@ ip_set_swap(struct sock *ctnl, struct sk_buff *skb,
static int
ip_set_dump_done(struct netlink_callback *cb)
{
- if (cb->args[2]) {
- pr_debug("release set %s\n", nfnl_set(cb->args[1])->name);
- ip_set_put_byindex((ip_set_id_t) cb->args[1]);
+ struct ip_set_net *inst = (struct ip_set_net *)cb->args[IPSET_CB_NET];
+ if (cb->args[IPSET_CB_ARG0]) {
+ pr_debug("release set %s\n",
+ ip_set(inst, cb->args[IPSET_CB_INDEX])->name);
+ __ip_set_put_byindex(inst,
+ (ip_set_id_t) cb->args[IPSET_CB_INDEX]);
}
return 0;
}
@@ -1082,10 +1176,10 @@ dump_attrs(struct nlmsghdr *nlh)
}
static int
-dump_init(struct netlink_callback *cb)
+dump_init(struct netlink_callback *cb, struct ip_set_net *inst)
{
struct nlmsghdr *nlh = nlmsg_hdr(cb->skb);
- int min_len = NLMSG_SPACE(sizeof(struct nfgenmsg));
+ int min_len = nlmsg_total_size(sizeof(struct nfgenmsg));
struct nlattr *cda[IPSET_ATTR_CMD_MAX+1];
struct nlattr *attr = (void *)nlh + min_len;
u32 dump_type;
@@ -1095,21 +1189,22 @@ dump_init(struct netlink_callback *cb)
nla_parse(cda, IPSET_ATTR_CMD_MAX,
attr, nlh->nlmsg_len - min_len, ip_set_setname_policy);
- /* cb->args[0] : dump single set/all sets
- * [1] : set index
- * [..]: type specific
+ /* cb->args[IPSET_CB_NET]: net namespace
+ * [IPSET_CB_DUMP]: dump single set/all sets
+ * [IPSET_CB_INDEX]: set index
+ * [IPSET_CB_ARG0]: type specific
*/
if (cda[IPSET_ATTR_SETNAME]) {
struct ip_set *set;
- set = find_set_and_id(nla_data(cda[IPSET_ATTR_SETNAME]),
+ set = find_set_and_id(inst, nla_data(cda[IPSET_ATTR_SETNAME]),
&index);
if (set == NULL)
return -ENOENT;
dump_type = DUMP_ONE;
- cb->args[1] = index;
+ cb->args[IPSET_CB_INDEX] = index;
} else
dump_type = DUMP_ALL;
@@ -1117,7 +1212,8 @@ dump_init(struct netlink_callback *cb)
u32 f = ip_set_get_h32(cda[IPSET_ATTR_FLAGS]);
dump_type |= (f << 16);
}
- cb->args[0] = dump_type;
+ cb->args[IPSET_CB_NET] = (unsigned long)inst;
+ cb->args[IPSET_CB_DUMP] = dump_type;
return 0;
}
@@ -1129,11 +1225,12 @@ ip_set_dump_start(struct sk_buff *skb, struct netlink_callback *cb)
struct ip_set *set = NULL;
struct nlmsghdr *nlh = NULL;
unsigned int flags = NETLINK_CB(cb->skb).portid ? NLM_F_MULTI : 0;
+ struct ip_set_net *inst = ip_set_pernet(sock_net(skb->sk));
u32 dump_type, dump_flags;
int ret = 0;
- if (!cb->args[0]) {
- ret = dump_init(cb);
+ if (!cb->args[IPSET_CB_DUMP]) {
+ ret = dump_init(cb, inst);
if (ret < 0) {
nlh = nlmsg_hdr(cb->skb);
/* We have to create and send the error message
@@ -1144,18 +1241,19 @@ ip_set_dump_start(struct sk_buff *skb, struct netlink_callback *cb)
}
}
- if (cb->args[1] >= ip_set_max)
+ if (cb->args[IPSET_CB_INDEX] >= inst->ip_set_max)
goto out;
- dump_type = DUMP_TYPE(cb->args[0]);
- dump_flags = DUMP_FLAGS(cb->args[0]);
- max = dump_type == DUMP_ONE ? cb->args[1] + 1 : ip_set_max;
+ dump_type = DUMP_TYPE(cb->args[IPSET_CB_DUMP]);
+ dump_flags = DUMP_FLAGS(cb->args[IPSET_CB_DUMP]);
+ max = dump_type == DUMP_ONE ? cb->args[IPSET_CB_INDEX] + 1
+ : inst->ip_set_max;
dump_last:
- pr_debug("args[0]: %u %u args[1]: %ld\n",
- dump_type, dump_flags, cb->args[1]);
- for (; cb->args[1] < max; cb->args[1]++) {
- index = (ip_set_id_t) cb->args[1];
- set = nfnl_set(index);
+ pr_debug("dump type, flag: %u %u index: %ld\n",
+ dump_type, dump_flags, cb->args[IPSET_CB_INDEX]);
+ for (; cb->args[IPSET_CB_INDEX] < max; cb->args[IPSET_CB_INDEX]++) {
+ index = (ip_set_id_t) cb->args[IPSET_CB_INDEX];
+ set = ip_set(inst, index);
if (set == NULL) {
if (dump_type == DUMP_ONE) {
ret = -ENOENT;
@@ -1171,7 +1269,7 @@ dump_last:
!!(set->type->features & IPSET_DUMP_LAST)))
continue;
pr_debug("List set: %s\n", set->name);
- if (!cb->args[2]) {
+ if (!cb->args[IPSET_CB_ARG0]) {
/* Start listing: make sure set won't be destroyed */
pr_debug("reference set\n");
__ip_set_get(set);
@@ -1188,7 +1286,7 @@ dump_last:
goto nla_put_failure;
if (dump_flags & IPSET_FLAG_LIST_SETNAME)
goto next_set;
- switch (cb->args[2]) {
+ switch (cb->args[IPSET_CB_ARG0]) {
case 0:
/* Core header data */
if (nla_put_string(skb, IPSET_ATTR_TYPENAME,
@@ -1208,7 +1306,7 @@ dump_last:
read_lock_bh(&set->lock);
ret = set->variant->list(set, skb, cb);
read_unlock_bh(&set->lock);
- if (!cb->args[2])
+ if (!cb->args[IPSET_CB_ARG0])
/* Set is done, proceed with next one */
goto next_set;
goto release_refcount;
@@ -1217,8 +1315,8 @@ dump_last:
/* If we dump all sets, continue with dumping last ones */
if (dump_type == DUMP_ALL) {
dump_type = DUMP_LAST;
- cb->args[0] = dump_type | (dump_flags << 16);
- cb->args[1] = 0;
+ cb->args[IPSET_CB_DUMP] = dump_type | (dump_flags << 16);
+ cb->args[IPSET_CB_INDEX] = 0;
goto dump_last;
}
goto out;
@@ -1227,15 +1325,15 @@ nla_put_failure:
ret = -EFAULT;
next_set:
if (dump_type == DUMP_ONE)
- cb->args[1] = IPSET_INVALID_ID;
+ cb->args[IPSET_CB_INDEX] = IPSET_INVALID_ID;
else
- cb->args[1]++;
+ cb->args[IPSET_CB_INDEX]++;
release_refcount:
/* If there was an error or set is done, release set */
- if (ret || !cb->args[2]) {
- pr_debug("release set %s\n", nfnl_set(index)->name);
- ip_set_put_byindex(index);
- cb->args[2] = 0;
+ if (ret || !cb->args[IPSET_CB_ARG0]) {
+ pr_debug("release set %s\n", ip_set(inst, index)->name);
+ __ip_set_put_byindex(inst, index);
+ cb->args[IPSET_CB_ARG0] = 0;
}
out:
if (nlh) {
@@ -1301,7 +1399,7 @@ call_ad(struct sock *ctnl, struct sk_buff *skb, struct ip_set *set,
struct sk_buff *skb2;
struct nlmsgerr *errmsg;
size_t payload = sizeof(*errmsg) + nlmsg_len(nlh);
- int min_len = NLMSG_SPACE(sizeof(struct nfgenmsg));
+ int min_len = nlmsg_total_size(sizeof(struct nfgenmsg));
struct nlattr *cda[IPSET_ATTR_CMD_MAX+1];
struct nlattr *cmdattr;
u32 *errline;
@@ -1337,6 +1435,7 @@ ip_set_uadd(struct sock *ctnl, struct sk_buff *skb,
const struct nlmsghdr *nlh,
const struct nlattr * const attr[])
{
+ struct ip_set_net *inst = ip_set_pernet(sock_net(ctnl));
struct ip_set *set;
struct nlattr *tb[IPSET_ATTR_ADT_MAX+1] = {};
const struct nlattr *nla;
@@ -1355,7 +1454,7 @@ ip_set_uadd(struct sock *ctnl, struct sk_buff *skb,
attr[IPSET_ATTR_LINENO] == NULL))))
return -IPSET_ERR_PROTOCOL;
- set = find_set(nla_data(attr[IPSET_ATTR_SETNAME]));
+ set = find_set(inst, nla_data(attr[IPSET_ATTR_SETNAME]));
if (set == NULL)
return -ENOENT;
@@ -1391,6 +1490,7 @@ ip_set_udel(struct sock *ctnl, struct sk_buff *skb,
const struct nlmsghdr *nlh,
const struct nlattr * const attr[])
{
+ struct ip_set_net *inst = ip_set_pernet(sock_net(ctnl));
struct ip_set *set;
struct nlattr *tb[IPSET_ATTR_ADT_MAX+1] = {};
const struct nlattr *nla;
@@ -1409,7 +1509,7 @@ ip_set_udel(struct sock *ctnl, struct sk_buff *skb,
attr[IPSET_ATTR_LINENO] == NULL))))
return -IPSET_ERR_PROTOCOL;
- set = find_set(nla_data(attr[IPSET_ATTR_SETNAME]));
+ set = find_set(inst, nla_data(attr[IPSET_ATTR_SETNAME]));
if (set == NULL)
return -ENOENT;
@@ -1445,6 +1545,7 @@ ip_set_utest(struct sock *ctnl, struct sk_buff *skb,
const struct nlmsghdr *nlh,
const struct nlattr * const attr[])
{
+ struct ip_set_net *inst = ip_set_pernet(sock_net(ctnl));
struct ip_set *set;
struct nlattr *tb[IPSET_ATTR_ADT_MAX+1] = {};
int ret = 0;
@@ -1455,7 +1556,7 @@ ip_set_utest(struct sock *ctnl, struct sk_buff *skb,
!flag_nested(attr[IPSET_ATTR_DATA])))
return -IPSET_ERR_PROTOCOL;
- set = find_set(nla_data(attr[IPSET_ATTR_SETNAME]));
+ set = find_set(inst, nla_data(attr[IPSET_ATTR_SETNAME]));
if (set == NULL)
return -ENOENT;
@@ -1470,7 +1571,7 @@ ip_set_utest(struct sock *ctnl, struct sk_buff *skb,
if (ret == -EAGAIN)
ret = 1;
- return ret < 0 ? ret : ret > 0 ? 0 : -IPSET_ERR_EXIST;
+ return ret > 0 ? 0 : -IPSET_ERR_EXIST;
}
/* Get headed data of a set */
@@ -1480,6 +1581,7 @@ ip_set_header(struct sock *ctnl, struct sk_buff *skb,
const struct nlmsghdr *nlh,
const struct nlattr * const attr[])
{
+ struct ip_set_net *inst = ip_set_pernet(sock_net(ctnl));
const struct ip_set *set;
struct sk_buff *skb2;
struct nlmsghdr *nlh2;
@@ -1489,7 +1591,7 @@ ip_set_header(struct sock *ctnl, struct sk_buff *skb,
attr[IPSET_ATTR_SETNAME] == NULL))
return -IPSET_ERR_PROTOCOL;
- set = find_set(nla_data(attr[IPSET_ATTR_SETNAME]));
+ set = find_set(inst, nla_data(attr[IPSET_ATTR_SETNAME]));
if (set == NULL)
return -ENOENT;
@@ -1714,8 +1816,10 @@ ip_set_sockfn_get(struct sock *sk, int optval, void __user *user, int *len)
unsigned int *op;
void *data;
int copylen = *len, ret = 0;
+ struct net *net = sock_net(sk);
+ struct ip_set_net *inst = ip_set_pernet(net);
- if (!ns_capable(sock_net(sk)->user_ns, CAP_NET_ADMIN))
+ if (!ns_capable(net->user_ns, CAP_NET_ADMIN))
return -EPERM;
if (optval != SO_IP_SET)
return -EBADF;
@@ -1763,10 +1867,27 @@ ip_set_sockfn_get(struct sock *sk, int optval, void __user *user, int *len)
goto done;
}
req_get->set.name[IPSET_MAXNAMELEN - 1] = '\0';
- nfnl_lock();
- find_set_and_id(req_get->set.name, &id);
+ nfnl_lock(NFNL_SUBSYS_IPSET);
+ find_set_and_id(inst, req_get->set.name, &id);
+ req_get->set.index = id;
+ nfnl_unlock(NFNL_SUBSYS_IPSET);
+ goto copy;
+ }
+ case IP_SET_OP_GET_FNAME: {
+ struct ip_set_req_get_set_family *req_get = data;
+ ip_set_id_t id;
+
+ if (*len != sizeof(struct ip_set_req_get_set_family)) {
+ ret = -EINVAL;
+ goto done;
+ }
+ req_get->set.name[IPSET_MAXNAMELEN - 1] = '\0';
+ nfnl_lock(NFNL_SUBSYS_IPSET);
+ find_set_and_id(inst, req_get->set.name, &id);
req_get->set.index = id;
- nfnl_unlock();
+ if (id != IPSET_INVALID_ID)
+ req_get->family = ip_set(inst, id)->family;
+ nfnl_unlock(NFNL_SUBSYS_IPSET);
goto copy;
}
case IP_SET_OP_GET_BYINDEX: {
@@ -1774,15 +1895,15 @@ ip_set_sockfn_get(struct sock *sk, int optval, void __user *user, int *len)
struct ip_set *set;
if (*len != sizeof(struct ip_set_req_get_set) ||
- req_get->set.index >= ip_set_max) {
+ req_get->set.index >= inst->ip_set_max) {
ret = -EINVAL;
goto done;
}
- nfnl_lock();
- set = nfnl_set(req_get->set.index);
+ nfnl_lock(NFNL_SUBSYS_IPSET);
+ set = ip_set(inst, req_get->set.index);
strncpy(req_get->set.name, set ? set->name : "",
IPSET_MAXNAMELEN);
- nfnl_unlock();
+ nfnl_unlock(NFNL_SUBSYS_IPSET);
goto copy;
}
default:
@@ -1808,49 +1929,81 @@ static struct nf_sockopt_ops so_set __read_mostly = {
.owner = THIS_MODULE,
};
-static int __init
-ip_set_init(void)
+static int __net_init
+ip_set_net_init(struct net *net)
{
+ struct ip_set_net *inst = ip_set_pernet(net);
struct ip_set **list;
- int ret;
- if (max_sets)
- ip_set_max = max_sets;
- if (ip_set_max >= IPSET_INVALID_ID)
- ip_set_max = IPSET_INVALID_ID - 1;
+ inst->ip_set_max = max_sets ? max_sets : CONFIG_IP_SET_MAX;
+ if (inst->ip_set_max >= IPSET_INVALID_ID)
+ inst->ip_set_max = IPSET_INVALID_ID - 1;
- list = kzalloc(sizeof(struct ip_set *) * ip_set_max, GFP_KERNEL);
+ list = kzalloc(sizeof(struct ip_set *) * inst->ip_set_max, GFP_KERNEL);
if (!list)
return -ENOMEM;
+ inst->is_deleted = 0;
+ rcu_assign_pointer(inst->ip_set_list, list);
+ return 0;
+}
+
+static void __net_exit
+ip_set_net_exit(struct net *net)
+{
+ struct ip_set_net *inst = ip_set_pernet(net);
- rcu_assign_pointer(ip_set_list, list);
- ret = nfnetlink_subsys_register(&ip_set_netlink_subsys);
+ struct ip_set *set = NULL;
+ ip_set_id_t i;
+
+ inst->is_deleted = 1; /* flag for ip_set_nfnl_put */
+
+ for (i = 0; i < inst->ip_set_max; i++) {
+ set = ip_set(inst, i);
+ if (set != NULL)
+ ip_set_destroy_set(inst, i);
+ }
+ kfree(rcu_dereference_protected(inst->ip_set_list, 1));
+}
+
+static struct pernet_operations ip_set_net_ops = {
+ .init = ip_set_net_init,
+ .exit = ip_set_net_exit,
+ .id = &ip_set_net_id,
+ .size = sizeof(struct ip_set_net)
+};
+
+
+static int __init
+ip_set_init(void)
+{
+ int ret = nfnetlink_subsys_register(&ip_set_netlink_subsys);
if (ret != 0) {
pr_err("ip_set: cannot register with nfnetlink.\n");
- kfree(list);
return ret;
}
ret = nf_register_sockopt(&so_set);
if (ret != 0) {
pr_err("SO_SET registry failed: %d\n", ret);
nfnetlink_subsys_unregister(&ip_set_netlink_subsys);
- kfree(list);
return ret;
}
-
- pr_notice("ip_set: protocol %u\n", IPSET_PROTOCOL);
+ ret = register_pernet_subsys(&ip_set_net_ops);
+ if (ret) {
+ pr_err("ip_set: cannot register pernet_subsys.\n");
+ nf_unregister_sockopt(&so_set);
+ nfnetlink_subsys_unregister(&ip_set_netlink_subsys);
+ return ret;
+ }
+ pr_info("ip_set: protocol %u\n", IPSET_PROTOCOL);
return 0;
}
static void __exit
ip_set_fini(void)
{
- struct ip_set **list = rcu_dereference_protected(ip_set_list, 1);
-
- /* There can't be any existing set */
+ unregister_pernet_subsys(&ip_set_net_ops);
nf_unregister_sockopt(&so_set);
nfnetlink_subsys_unregister(&ip_set_netlink_subsys);
- kfree(list);
pr_debug("these are the famous last words\n");
}
diff --git a/net/netfilter/ipset/ip_set_getport.c b/net/netfilter/ipset/ip_set_getport.c
index 6fdf88ae235..29fb01ddff9 100644
--- a/net/netfilter/ipset/ip_set_getport.c
+++ b/net/netfilter/ipset/ip_set_getport.c
@@ -102,9 +102,25 @@ ip_set_get_ip4_port(const struct sk_buff *skb, bool src,
int protocol = iph->protocol;
/* See comments at tcp_match in ip_tables.c */
- if (protocol <= 0 || (ntohs(iph->frag_off) & IP_OFFSET))
+ if (protocol <= 0)
return false;
+ if (ntohs(iph->frag_off) & IP_OFFSET)
+ switch (protocol) {
+ case IPPROTO_TCP:
+ case IPPROTO_SCTP:
+ case IPPROTO_UDP:
+ case IPPROTO_UDPLITE:
+ case IPPROTO_ICMP:
+ /* Port info not available for fragment offset > 0 */
+ return false;
+ default:
+ /* Other protocols doesn't have ports,
+ so we can match fragments */
+ *proto = protocol;
+ return true;
+ }
+
return get_port(skb, protocol, protooff, src, port, proto);
}
EXPORT_SYMBOL_GPL(ip_set_get_ip4_port);
@@ -116,12 +132,12 @@ ip_set_get_ip6_port(const struct sk_buff *skb, bool src,
{
int protoff;
u8 nexthdr;
- __be16 frag_off;
+ __be16 frag_off = 0;
nexthdr = ipv6_hdr(skb)->nexthdr;
protoff = ipv6_skip_exthdr(skb, sizeof(struct ipv6hdr), &nexthdr,
&frag_off);
- if (protoff < 0)
+ if (protoff < 0 || (frag_off & htons(~0x7)) != 0)
return false;
return get_port(skb, nexthdr, protoff, src, port, proto);
diff --git a/net/netfilter/ipset/ip_set_hash_gen.h b/net/netfilter/ipset/ip_set_hash_gen.h
new file mode 100644
index 00000000000..61c7fb05280
--- /dev/null
+++ b/net/netfilter/ipset/ip_set_hash_gen.h
@@ -0,0 +1,1160 @@
+/* Copyright (C) 2013 Jozsef Kadlecsik <kadlec@blackhole.kfki.hu>
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2 as
+ * published by the Free Software Foundation.
+ */
+
+#ifndef _IP_SET_HASH_GEN_H
+#define _IP_SET_HASH_GEN_H
+
+#include <linux/rcupdate.h>
+#include <linux/jhash.h>
+#include <linux/netfilter/ipset/ip_set_timeout.h>
+#ifndef rcu_dereference_bh
+#define rcu_dereference_bh(p) rcu_dereference(p)
+#endif
+
+#define rcu_dereference_bh_nfnl(p) rcu_dereference_bh_check(p, 1)
+
+/* Hashing which uses arrays to resolve clashing. The hash table is resized
+ * (doubled) when searching becomes too long.
+ * Internally jhash is used with the assumption that the size of the
+ * stored data is a multiple of sizeof(u32). If storage supports timeout,
+ * the timeout field must be the last one in the data structure - that field
+ * is ignored when computing the hash key.
+ *
+ * Readers and resizing
+ *
+ * Resizing can be triggered by userspace command only, and those
+ * are serialized by the nfnl mutex. During resizing the set is
+ * read-locked, so the only possible concurrent operations are
+ * the kernel side readers. Those must be protected by proper RCU locking.
+ */
+
+/* Number of elements to store in an initial array block */
+#define AHASH_INIT_SIZE 4
+/* Max number of elements to store in an array block */
+#define AHASH_MAX_SIZE (3*AHASH_INIT_SIZE)
+
+/* Max number of elements can be tuned */
+#ifdef IP_SET_HASH_WITH_MULTI
+#define AHASH_MAX(h) ((h)->ahash_max)
+
+static inline u8
+tune_ahash_max(u8 curr, u32 multi)
+{
+ u32 n;
+
+ if (multi < curr)
+ return curr;
+
+ n = curr + AHASH_INIT_SIZE;
+ /* Currently, at listing one hash bucket must fit into a message.
+ * Therefore we have a hard limit here.
+ */
+ return n > curr && n <= 64 ? n : curr;
+}
+#define TUNE_AHASH_MAX(h, multi) \
+ ((h)->ahash_max = tune_ahash_max((h)->ahash_max, multi))
+#else
+#define AHASH_MAX(h) AHASH_MAX_SIZE
+#define TUNE_AHASH_MAX(h, multi)
+#endif
+
+/* A hash bucket */
+struct hbucket {
+ void *value; /* the array of the values */
+ u8 size; /* size of the array */
+ u8 pos; /* position of the first free entry */
+};
+
+/* The hash table: the table size stored here in order to make resizing easy */
+struct htable {
+ u8 htable_bits; /* size of hash table == 2^htable_bits */
+ struct hbucket bucket[0]; /* hashtable buckets */
+};
+
+#define hbucket(h, i) (&((h)->bucket[i]))
+
+#ifndef IPSET_NET_COUNT
+#define IPSET_NET_COUNT 1
+#endif
+
+/* Book-keeping of the prefixes added to the set */
+struct net_prefixes {
+ u32 nets[IPSET_NET_COUNT]; /* number of elements per cidr */
+ u8 cidr[IPSET_NET_COUNT]; /* the different cidr values in the set */
+};
+
+/* Compute the hash table size */
+static size_t
+htable_size(u8 hbits)
+{
+ size_t hsize;
+
+ /* We must fit both into u32 in jhash and size_t */
+ if (hbits > 31)
+ return 0;
+ hsize = jhash_size(hbits);
+ if ((((size_t)-1) - sizeof(struct htable))/sizeof(struct hbucket)
+ < hsize)
+ return 0;
+
+ return hsize * sizeof(struct hbucket) + sizeof(struct htable);
+}
+
+/* Compute htable_bits from the user input parameter hashsize */
+static u8
+htable_bits(u32 hashsize)
+{
+ /* Assume that hashsize == 2^htable_bits */
+ u8 bits = fls(hashsize - 1);
+ if (jhash_size(bits) != hashsize)
+ /* Round up to the first 2^n value */
+ bits = fls(hashsize);
+
+ return bits;
+}
+
+static int
+hbucket_elem_add(struct hbucket *n, u8 ahash_max, size_t dsize)
+{
+ if (n->pos >= n->size) {
+ void *tmp;
+
+ if (n->size >= ahash_max)
+ /* Trigger rehashing */
+ return -EAGAIN;
+
+ tmp = kzalloc((n->size + AHASH_INIT_SIZE) * dsize,
+ GFP_ATOMIC);
+ if (!tmp)
+ return -ENOMEM;
+ if (n->size) {
+ memcpy(tmp, n->value, n->size * dsize);
+ kfree(n->value);
+ }
+ n->value = tmp;
+ n->size += AHASH_INIT_SIZE;
+ }
+ return 0;
+}
+
+#ifdef IP_SET_HASH_WITH_NETS
+#if IPSET_NET_COUNT > 1
+#define __CIDR(cidr, i) (cidr[i])
+#else
+#define __CIDR(cidr, i) (cidr)
+#endif
+#ifdef IP_SET_HASH_WITH_NETS_PACKED
+/* When cidr is packed with nomatch, cidr - 1 is stored in the entry */
+#define CIDR(cidr, i) (__CIDR(cidr, i) + 1)
+#else
+#define CIDR(cidr, i) (__CIDR(cidr, i))
+#endif
+
+#define SET_HOST_MASK(family) (family == AF_INET ? 32 : 128)
+
+#ifdef IP_SET_HASH_WITH_MULTI
+#define NLEN(family) (SET_HOST_MASK(family) + 1)
+#else
+#define NLEN(family) SET_HOST_MASK(family)
+#endif
+
+#else
+#define NLEN(family) 0
+#endif /* IP_SET_HASH_WITH_NETS */
+
+#endif /* _IP_SET_HASH_GEN_H */
+
+/* Family dependent templates */
+
+#undef ahash_data
+#undef mtype_data_equal
+#undef mtype_do_data_match
+#undef mtype_data_set_flags
+#undef mtype_data_reset_flags
+#undef mtype_data_netmask
+#undef mtype_data_list
+#undef mtype_data_next
+#undef mtype_elem
+
+#undef mtype_ahash_destroy
+#undef mtype_ext_cleanup
+#undef mtype_add_cidr
+#undef mtype_del_cidr
+#undef mtype_ahash_memsize
+#undef mtype_flush
+#undef mtype_destroy
+#undef mtype_gc_init
+#undef mtype_same_set
+#undef mtype_kadt
+#undef mtype_uadt
+#undef mtype
+
+#undef mtype_add
+#undef mtype_del
+#undef mtype_test_cidrs
+#undef mtype_test
+#undef mtype_expire
+#undef mtype_resize
+#undef mtype_head
+#undef mtype_list
+#undef mtype_gc
+#undef mtype_gc_init
+#undef mtype_variant
+#undef mtype_data_match
+
+#undef HKEY
+
+#define mtype_data_equal IPSET_TOKEN(MTYPE, _data_equal)
+#ifdef IP_SET_HASH_WITH_NETS
+#define mtype_do_data_match IPSET_TOKEN(MTYPE, _do_data_match)
+#else
+#define mtype_do_data_match(d) 1
+#endif
+#define mtype_data_set_flags IPSET_TOKEN(MTYPE, _data_set_flags)
+#define mtype_data_reset_elem IPSET_TOKEN(MTYPE, _data_reset_elem)
+#define mtype_data_reset_flags IPSET_TOKEN(MTYPE, _data_reset_flags)
+#define mtype_data_netmask IPSET_TOKEN(MTYPE, _data_netmask)
+#define mtype_data_list IPSET_TOKEN(MTYPE, _data_list)
+#define mtype_data_next IPSET_TOKEN(MTYPE, _data_next)
+#define mtype_elem IPSET_TOKEN(MTYPE, _elem)
+#define mtype_ahash_destroy IPSET_TOKEN(MTYPE, _ahash_destroy)
+#define mtype_ext_cleanup IPSET_TOKEN(MTYPE, _ext_cleanup)
+#define mtype_add_cidr IPSET_TOKEN(MTYPE, _add_cidr)
+#define mtype_del_cidr IPSET_TOKEN(MTYPE, _del_cidr)
+#define mtype_ahash_memsize IPSET_TOKEN(MTYPE, _ahash_memsize)
+#define mtype_flush IPSET_TOKEN(MTYPE, _flush)
+#define mtype_destroy IPSET_TOKEN(MTYPE, _destroy)
+#define mtype_gc_init IPSET_TOKEN(MTYPE, _gc_init)
+#define mtype_same_set IPSET_TOKEN(MTYPE, _same_set)
+#define mtype_kadt IPSET_TOKEN(MTYPE, _kadt)
+#define mtype_uadt IPSET_TOKEN(MTYPE, _uadt)
+#define mtype MTYPE
+
+#define mtype_add IPSET_TOKEN(MTYPE, _add)
+#define mtype_del IPSET_TOKEN(MTYPE, _del)
+#define mtype_test_cidrs IPSET_TOKEN(MTYPE, _test_cidrs)
+#define mtype_test IPSET_TOKEN(MTYPE, _test)
+#define mtype_expire IPSET_TOKEN(MTYPE, _expire)
+#define mtype_resize IPSET_TOKEN(MTYPE, _resize)
+#define mtype_head IPSET_TOKEN(MTYPE, _head)
+#define mtype_list IPSET_TOKEN(MTYPE, _list)
+#define mtype_gc IPSET_TOKEN(MTYPE, _gc)
+#define mtype_variant IPSET_TOKEN(MTYPE, _variant)
+#define mtype_data_match IPSET_TOKEN(MTYPE, _data_match)
+
+#ifndef HKEY_DATALEN
+#define HKEY_DATALEN sizeof(struct mtype_elem)
+#endif
+
+#define HKEY(data, initval, htable_bits) \
+(jhash2((u32 *)(data), HKEY_DATALEN/sizeof(u32), initval) \
+ & jhash_mask(htable_bits))
+
+#ifndef htype
+#define htype HTYPE
+
+/* The generic hash structure */
+struct htype {
+ struct htable __rcu *table; /* the hash table */
+ u32 maxelem; /* max elements in the hash */
+ u32 elements; /* current element (vs timeout) */
+ u32 initval; /* random jhash init value */
+#ifdef IP_SET_HASH_WITH_MARKMASK
+ u32 markmask; /* markmask value for mark mask to store */
+#endif
+ struct timer_list gc; /* garbage collection when timeout enabled */
+ struct mtype_elem next; /* temporary storage for uadd */
+#ifdef IP_SET_HASH_WITH_MULTI
+ u8 ahash_max; /* max elements in an array block */
+#endif
+#ifdef IP_SET_HASH_WITH_NETMASK
+ u8 netmask; /* netmask value for subnets to store */
+#endif
+#ifdef IP_SET_HASH_WITH_RBTREE
+ struct rb_root rbtree;
+#endif
+#ifdef IP_SET_HASH_WITH_NETS
+ struct net_prefixes nets[0]; /* book-keeping of prefixes */
+#endif
+};
+#endif
+
+#ifdef IP_SET_HASH_WITH_NETS
+/* Network cidr size book keeping when the hash stores different
+ * sized networks */
+static void
+mtype_add_cidr(struct htype *h, u8 cidr, u8 nets_length, u8 n)
+{
+ int i, j;
+
+ /* Add in increasing prefix order, so larger cidr first */
+ for (i = 0, j = -1; i < nets_length && h->nets[i].nets[n]; i++) {
+ if (j != -1)
+ continue;
+ else if (h->nets[i].cidr[n] < cidr)
+ j = i;
+ else if (h->nets[i].cidr[n] == cidr) {
+ h->nets[i].nets[n]++;
+ return;
+ }
+ }
+ if (j != -1) {
+ for (; i > j; i--) {
+ h->nets[i].cidr[n] = h->nets[i - 1].cidr[n];
+ h->nets[i].nets[n] = h->nets[i - 1].nets[n];
+ }
+ }
+ h->nets[i].cidr[n] = cidr;
+ h->nets[i].nets[n] = 1;
+}
+
+static void
+mtype_del_cidr(struct htype *h, u8 cidr, u8 nets_length, u8 n)
+{
+ u8 i, j, net_end = nets_length - 1;
+
+ for (i = 0; i < nets_length; i++) {
+ if (h->nets[i].cidr[n] != cidr)
+ continue;
+ if (h->nets[i].nets[n] > 1 || i == net_end ||
+ h->nets[i + 1].nets[n] == 0) {
+ h->nets[i].nets[n]--;
+ return;
+ }
+ for (j = i; j < net_end && h->nets[j].nets[n]; j++) {
+ h->nets[j].cidr[n] = h->nets[j + 1].cidr[n];
+ h->nets[j].nets[n] = h->nets[j + 1].nets[n];
+ }
+ h->nets[j].nets[n] = 0;
+ return;
+ }
+}
+#endif
+
+/* Calculate the actual memory size of the set data */
+static size_t
+mtype_ahash_memsize(const struct htype *h, const struct htable *t,
+ u8 nets_length, size_t dsize)
+{
+ u32 i;
+ size_t memsize = sizeof(*h)
+ + sizeof(*t)
+#ifdef IP_SET_HASH_WITH_NETS
+ + sizeof(struct net_prefixes) * nets_length
+#endif
+ + jhash_size(t->htable_bits) * sizeof(struct hbucket);
+
+ for (i = 0; i < jhash_size(t->htable_bits); i++)
+ memsize += t->bucket[i].size * dsize;
+
+ return memsize;
+}
+
+/* Get the ith element from the array block n */
+#define ahash_data(n, i, dsize) \
+ ((struct mtype_elem *)((n)->value + ((i) * (dsize))))
+
+static void
+mtype_ext_cleanup(struct ip_set *set, struct hbucket *n)
+{
+ int i;
+
+ for (i = 0; i < n->pos; i++)
+ ip_set_ext_destroy(set, ahash_data(n, i, set->dsize));
+}
+
+/* Flush a hash type of set: destroy all elements */
+static void
+mtype_flush(struct ip_set *set)
+{
+ struct htype *h = set->data;
+ struct htable *t;
+ struct hbucket *n;
+ u32 i;
+
+ t = rcu_dereference_bh_nfnl(h->table);
+ for (i = 0; i < jhash_size(t->htable_bits); i++) {
+ n = hbucket(t, i);
+ if (n->size) {
+ if (set->extensions & IPSET_EXT_DESTROY)
+ mtype_ext_cleanup(set, n);
+ n->size = n->pos = 0;
+ /* FIXME: use slab cache */
+ kfree(n->value);
+ }
+ }
+#ifdef IP_SET_HASH_WITH_NETS
+ memset(h->nets, 0, sizeof(struct net_prefixes) * NLEN(set->family));
+#endif
+ h->elements = 0;
+}
+
+/* Destroy the hashtable part of the set */
+static void
+mtype_ahash_destroy(struct ip_set *set, struct htable *t, bool ext_destroy)
+{
+ struct hbucket *n;
+ u32 i;
+
+ for (i = 0; i < jhash_size(t->htable_bits); i++) {
+ n = hbucket(t, i);
+ if (n->size) {
+ if (set->extensions & IPSET_EXT_DESTROY && ext_destroy)
+ mtype_ext_cleanup(set, n);
+ /* FIXME: use slab cache */
+ kfree(n->value);
+ }
+ }
+
+ ip_set_free(t);
+}
+
+/* Destroy a hash type of set */
+static void
+mtype_destroy(struct ip_set *set)
+{
+ struct htype *h = set->data;
+
+ if (set->extensions & IPSET_EXT_TIMEOUT)
+ del_timer_sync(&h->gc);
+
+ mtype_ahash_destroy(set, rcu_dereference_bh_nfnl(h->table), true);
+#ifdef IP_SET_HASH_WITH_RBTREE
+ rbtree_destroy(&h->rbtree);
+#endif
+ kfree(h);
+
+ set->data = NULL;
+}
+
+static void
+mtype_gc_init(struct ip_set *set, void (*gc)(unsigned long ul_set))
+{
+ struct htype *h = set->data;
+
+ init_timer(&h->gc);
+ h->gc.data = (unsigned long) set;
+ h->gc.function = gc;
+ h->gc.expires = jiffies + IPSET_GC_PERIOD(set->timeout) * HZ;
+ add_timer(&h->gc);
+ pr_debug("gc initialized, run in every %u\n",
+ IPSET_GC_PERIOD(set->timeout));
+}
+
+static bool
+mtype_same_set(const struct ip_set *a, const struct ip_set *b)
+{
+ const struct htype *x = a->data;
+ const struct htype *y = b->data;
+
+ /* Resizing changes htable_bits, so we ignore it */
+ return x->maxelem == y->maxelem &&
+ a->timeout == b->timeout &&
+#ifdef IP_SET_HASH_WITH_NETMASK
+ x->netmask == y->netmask &&
+#endif
+#ifdef IP_SET_HASH_WITH_MARKMASK
+ x->markmask == y->markmask &&
+#endif
+ a->extensions == b->extensions;
+}
+
+/* Delete expired elements from the hashtable */
+static void
+mtype_expire(struct ip_set *set, struct htype *h, u8 nets_length, size_t dsize)
+{
+ struct htable *t;
+ struct hbucket *n;
+ struct mtype_elem *data;
+ u32 i;
+ int j;
+#ifdef IP_SET_HASH_WITH_NETS
+ u8 k;
+#endif
+
+ rcu_read_lock_bh();
+ t = rcu_dereference_bh(h->table);
+ for (i = 0; i < jhash_size(t->htable_bits); i++) {
+ n = hbucket(t, i);
+ for (j = 0; j < n->pos; j++) {
+ data = ahash_data(n, j, dsize);
+ if (ip_set_timeout_expired(ext_timeout(data, set))) {
+ pr_debug("expired %u/%u\n", i, j);
+#ifdef IP_SET_HASH_WITH_NETS
+ for (k = 0; k < IPSET_NET_COUNT; k++)
+ mtype_del_cidr(h, CIDR(data->cidr, k),
+ nets_length, k);
+#endif
+ ip_set_ext_destroy(set, data);
+ if (j != n->pos - 1)
+ /* Not last one */
+ memcpy(data,
+ ahash_data(n, n->pos - 1, dsize),
+ dsize);
+ n->pos--;
+ h->elements--;
+ }
+ }
+ if (n->pos + AHASH_INIT_SIZE < n->size) {
+ void *tmp = kzalloc((n->size - AHASH_INIT_SIZE)
+ * dsize,
+ GFP_ATOMIC);
+ if (!tmp)
+ /* Still try to delete expired elements */
+ continue;
+ n->size -= AHASH_INIT_SIZE;
+ memcpy(tmp, n->value, n->size * dsize);
+ kfree(n->value);
+ n->value = tmp;
+ }
+ }
+ rcu_read_unlock_bh();
+}
+
+static void
+mtype_gc(unsigned long ul_set)
+{
+ struct ip_set *set = (struct ip_set *) ul_set;
+ struct htype *h = set->data;
+
+ pr_debug("called\n");
+ write_lock_bh(&set->lock);
+ mtype_expire(set, h, NLEN(set->family), set->dsize);
+ write_unlock_bh(&set->lock);
+
+ h->gc.expires = jiffies + IPSET_GC_PERIOD(set->timeout) * HZ;
+ add_timer(&h->gc);
+}
+
+/* Resize a hash: create a new hash table with doubling the hashsize
+ * and inserting the elements to it. Repeat until we succeed or
+ * fail due to memory pressures. */
+static int
+mtype_resize(struct ip_set *set, bool retried)
+{
+ struct htype *h = set->data;
+ struct htable *t, *orig = rcu_dereference_bh_nfnl(h->table);
+ u8 htable_bits = orig->htable_bits;
+#ifdef IP_SET_HASH_WITH_NETS
+ u8 flags;
+#endif
+ struct mtype_elem *data;
+ struct mtype_elem *d;
+ struct hbucket *n, *m;
+ u32 i, j;
+ int ret;
+
+ /* Try to cleanup once */
+ if (SET_WITH_TIMEOUT(set) && !retried) {
+ i = h->elements;
+ write_lock_bh(&set->lock);
+ mtype_expire(set, set->data, NLEN(set->family), set->dsize);
+ write_unlock_bh(&set->lock);
+ if (h->elements < i)
+ return 0;
+ }
+
+retry:
+ ret = 0;
+ htable_bits++;
+ pr_debug("attempt to resize set %s from %u to %u, t %p\n",
+ set->name, orig->htable_bits, htable_bits, orig);
+ if (!htable_bits) {
+ /* In case we have plenty of memory :-) */
+ pr_warning("Cannot increase the hashsize of set %s further\n",
+ set->name);
+ return -IPSET_ERR_HASH_FULL;
+ }
+ t = ip_set_alloc(sizeof(*t)
+ + jhash_size(htable_bits) * sizeof(struct hbucket));
+ if (!t)
+ return -ENOMEM;
+ t->htable_bits = htable_bits;
+
+ read_lock_bh(&set->lock);
+ for (i = 0; i < jhash_size(orig->htable_bits); i++) {
+ n = hbucket(orig, i);
+ for (j = 0; j < n->pos; j++) {
+ data = ahash_data(n, j, set->dsize);
+#ifdef IP_SET_HASH_WITH_NETS
+ flags = 0;
+ mtype_data_reset_flags(data, &flags);
+#endif
+ m = hbucket(t, HKEY(data, h->initval, htable_bits));
+ ret = hbucket_elem_add(m, AHASH_MAX(h), set->dsize);
+ if (ret < 0) {
+#ifdef IP_SET_HASH_WITH_NETS
+ mtype_data_reset_flags(data, &flags);
+#endif
+ read_unlock_bh(&set->lock);
+ mtype_ahash_destroy(set, t, false);
+ if (ret == -EAGAIN)
+ goto retry;
+ return ret;
+ }
+ d = ahash_data(m, m->pos++, set->dsize);
+ memcpy(d, data, set->dsize);
+#ifdef IP_SET_HASH_WITH_NETS
+ mtype_data_reset_flags(d, &flags);
+#endif
+ }
+ }
+
+ rcu_assign_pointer(h->table, t);
+ read_unlock_bh(&set->lock);
+
+ /* Give time to other readers of the set */
+ synchronize_rcu_bh();
+
+ pr_debug("set %s resized from %u (%p) to %u (%p)\n", set->name,
+ orig->htable_bits, orig, t->htable_bits, t);
+ mtype_ahash_destroy(set, orig, false);
+
+ return 0;
+}
+
+/* Add an element to a hash and update the internal counters when succeeded,
+ * otherwise report the proper error code. */
+static int
+mtype_add(struct ip_set *set, void *value, const struct ip_set_ext *ext,
+ struct ip_set_ext *mext, u32 flags)
+{
+ struct htype *h = set->data;
+ struct htable *t;
+ const struct mtype_elem *d = value;
+ struct mtype_elem *data;
+ struct hbucket *n;
+ int i, ret = 0;
+ int j = AHASH_MAX(h) + 1;
+ bool flag_exist = flags & IPSET_FLAG_EXIST;
+ u32 key, multi = 0;
+
+ if (h->elements >= h->maxelem && SET_WITH_FORCEADD(set)) {
+ rcu_read_lock_bh();
+ t = rcu_dereference_bh(h->table);
+ key = HKEY(value, h->initval, t->htable_bits);
+ n = hbucket(t,key);
+ if (n->pos) {
+ /* Choosing the first entry in the array to replace */
+ j = 0;
+ goto reuse_slot;
+ }
+ rcu_read_unlock_bh();
+ }
+ if (SET_WITH_TIMEOUT(set) && h->elements >= h->maxelem)
+ /* FIXME: when set is full, we slow down here */
+ mtype_expire(set, h, NLEN(set->family), set->dsize);
+
+ if (h->elements >= h->maxelem) {
+ if (net_ratelimit())
+ pr_warning("Set %s is full, maxelem %u reached\n",
+ set->name, h->maxelem);
+ return -IPSET_ERR_HASH_FULL;
+ }
+
+ rcu_read_lock_bh();
+ t = rcu_dereference_bh(h->table);
+ key = HKEY(value, h->initval, t->htable_bits);
+ n = hbucket(t, key);
+ for (i = 0; i < n->pos; i++) {
+ data = ahash_data(n, i, set->dsize);
+ if (mtype_data_equal(data, d, &multi)) {
+ if (flag_exist ||
+ (SET_WITH_TIMEOUT(set) &&
+ ip_set_timeout_expired(ext_timeout(data, set)))) {
+ /* Just the extensions could be overwritten */
+ j = i;
+ goto reuse_slot;
+ } else {
+ ret = -IPSET_ERR_EXIST;
+ goto out;
+ }
+ }
+ /* Reuse first timed out entry */
+ if (SET_WITH_TIMEOUT(set) &&
+ ip_set_timeout_expired(ext_timeout(data, set)) &&
+ j != AHASH_MAX(h) + 1)
+ j = i;
+ }
+reuse_slot:
+ if (j != AHASH_MAX(h) + 1) {
+ /* Fill out reused slot */
+ data = ahash_data(n, j, set->dsize);
+#ifdef IP_SET_HASH_WITH_NETS
+ for (i = 0; i < IPSET_NET_COUNT; i++) {
+ mtype_del_cidr(h, CIDR(data->cidr, i),
+ NLEN(set->family), i);
+ mtype_add_cidr(h, CIDR(d->cidr, i),
+ NLEN(set->family), i);
+ }
+#endif
+ ip_set_ext_destroy(set, data);
+ } else {
+ /* Use/create a new slot */
+ TUNE_AHASH_MAX(h, multi);
+ ret = hbucket_elem_add(n, AHASH_MAX(h), set->dsize);
+ if (ret != 0) {
+ if (ret == -EAGAIN)
+ mtype_data_next(&h->next, d);
+ goto out;
+ }
+ data = ahash_data(n, n->pos++, set->dsize);
+#ifdef IP_SET_HASH_WITH_NETS
+ for (i = 0; i < IPSET_NET_COUNT; i++)
+ mtype_add_cidr(h, CIDR(d->cidr, i), NLEN(set->family),
+ i);
+#endif
+ h->elements++;
+ }
+ memcpy(data, d, sizeof(struct mtype_elem));
+#ifdef IP_SET_HASH_WITH_NETS
+ mtype_data_set_flags(data, flags);
+#endif
+ if (SET_WITH_TIMEOUT(set))
+ ip_set_timeout_set(ext_timeout(data, set), ext->timeout);
+ if (SET_WITH_COUNTER(set))
+ ip_set_init_counter(ext_counter(data, set), ext);
+ if (SET_WITH_COMMENT(set))
+ ip_set_init_comment(ext_comment(data, set), ext);
+
+out:
+ rcu_read_unlock_bh();
+ return ret;
+}
+
+/* Delete an element from the hash: swap it with the last element
+ * and free up space if possible.
+ */
+static int
+mtype_del(struct ip_set *set, void *value, const struct ip_set_ext *ext,
+ struct ip_set_ext *mext, u32 flags)
+{
+ struct htype *h = set->data;
+ struct htable *t;
+ const struct mtype_elem *d = value;
+ struct mtype_elem *data;
+ struct hbucket *n;
+ int i, ret = -IPSET_ERR_EXIST;
+#ifdef IP_SET_HASH_WITH_NETS
+ u8 j;
+#endif
+ u32 key, multi = 0;
+
+ rcu_read_lock_bh();
+ t = rcu_dereference_bh(h->table);
+ key = HKEY(value, h->initval, t->htable_bits);
+ n = hbucket(t, key);
+ for (i = 0; i < n->pos; i++) {
+ data = ahash_data(n, i, set->dsize);
+ if (!mtype_data_equal(data, d, &multi))
+ continue;
+ if (SET_WITH_TIMEOUT(set) &&
+ ip_set_timeout_expired(ext_timeout(data, set)))
+ goto out;
+ if (i != n->pos - 1)
+ /* Not last one */
+ memcpy(data, ahash_data(n, n->pos - 1, set->dsize),
+ set->dsize);
+
+ n->pos--;
+ h->elements--;
+#ifdef IP_SET_HASH_WITH_NETS
+ for (j = 0; j < IPSET_NET_COUNT; j++)
+ mtype_del_cidr(h, CIDR(d->cidr, j), NLEN(set->family),
+ j);
+#endif
+ ip_set_ext_destroy(set, data);
+ if (n->pos + AHASH_INIT_SIZE < n->size) {
+ void *tmp = kzalloc((n->size - AHASH_INIT_SIZE)
+ * set->dsize,
+ GFP_ATOMIC);
+ if (!tmp) {
+ ret = 0;
+ goto out;
+ }
+ n->size -= AHASH_INIT_SIZE;
+ memcpy(tmp, n->value, n->size * set->dsize);
+ kfree(n->value);
+ n->value = tmp;
+ }
+ ret = 0;
+ goto out;
+ }
+
+out:
+ rcu_read_unlock_bh();
+ return ret;
+}
+
+static inline int
+mtype_data_match(struct mtype_elem *data, const struct ip_set_ext *ext,
+ struct ip_set_ext *mext, struct ip_set *set, u32 flags)
+{
+ if (SET_WITH_COUNTER(set))
+ ip_set_update_counter(ext_counter(data, set),
+ ext, mext, flags);
+ return mtype_do_data_match(data);
+}
+
+#ifdef IP_SET_HASH_WITH_NETS
+/* Special test function which takes into account the different network
+ * sizes added to the set */
+static int
+mtype_test_cidrs(struct ip_set *set, struct mtype_elem *d,
+ const struct ip_set_ext *ext,
+ struct ip_set_ext *mext, u32 flags)
+{
+ struct htype *h = set->data;
+ struct htable *t = rcu_dereference_bh(h->table);
+ struct hbucket *n;
+ struct mtype_elem *data;
+#if IPSET_NET_COUNT == 2
+ struct mtype_elem orig = *d;
+ int i, j = 0, k;
+#else
+ int i, j = 0;
+#endif
+ u32 key, multi = 0;
+ u8 nets_length = NLEN(set->family);
+
+ pr_debug("test by nets\n");
+ for (; j < nets_length && h->nets[j].nets[0] && !multi; j++) {
+#if IPSET_NET_COUNT == 2
+ mtype_data_reset_elem(d, &orig);
+ mtype_data_netmask(d, h->nets[j].cidr[0], false);
+ for (k = 0; k < nets_length && h->nets[k].nets[1] && !multi;
+ k++) {
+ mtype_data_netmask(d, h->nets[k].cidr[1], true);
+#else
+ mtype_data_netmask(d, h->nets[j].cidr[0]);
+#endif
+ key = HKEY(d, h->initval, t->htable_bits);
+ n = hbucket(t, key);
+ for (i = 0; i < n->pos; i++) {
+ data = ahash_data(n, i, set->dsize);
+ if (!mtype_data_equal(data, d, &multi))
+ continue;
+ if (SET_WITH_TIMEOUT(set)) {
+ if (!ip_set_timeout_expired(
+ ext_timeout(data, set)))
+ return mtype_data_match(data, ext,
+ mext, set,
+ flags);
+#ifdef IP_SET_HASH_WITH_MULTI
+ multi = 0;
+#endif
+ } else
+ return mtype_data_match(data, ext,
+ mext, set, flags);
+ }
+#if IPSET_NET_COUNT == 2
+ }
+#endif
+ }
+ return 0;
+}
+#endif
+
+/* Test whether the element is added to the set */
+static int
+mtype_test(struct ip_set *set, void *value, const struct ip_set_ext *ext,
+ struct ip_set_ext *mext, u32 flags)
+{
+ struct htype *h = set->data;
+ struct htable *t;
+ struct mtype_elem *d = value;
+ struct hbucket *n;
+ struct mtype_elem *data;
+ int i, ret = 0;
+ u32 key, multi = 0;
+
+ rcu_read_lock_bh();
+ t = rcu_dereference_bh(h->table);
+#ifdef IP_SET_HASH_WITH_NETS
+ /* If we test an IP address and not a network address,
+ * try all possible network sizes */
+ for (i = 0; i < IPSET_NET_COUNT; i++)
+ if (CIDR(d->cidr, i) != SET_HOST_MASK(set->family))
+ break;
+ if (i == IPSET_NET_COUNT) {
+ ret = mtype_test_cidrs(set, d, ext, mext, flags);
+ goto out;
+ }
+#endif
+
+ key = HKEY(d, h->initval, t->htable_bits);
+ n = hbucket(t, key);
+ for (i = 0; i < n->pos; i++) {
+ data = ahash_data(n, i, set->dsize);
+ if (mtype_data_equal(data, d, &multi) &&
+ !(SET_WITH_TIMEOUT(set) &&
+ ip_set_timeout_expired(ext_timeout(data, set)))) {
+ ret = mtype_data_match(data, ext, mext, set, flags);
+ goto out;
+ }
+ }
+out:
+ rcu_read_unlock_bh();
+ return ret;
+}
+
+/* Reply a HEADER request: fill out the header part of the set */
+static int
+mtype_head(struct ip_set *set, struct sk_buff *skb)
+{
+ const struct htype *h = set->data;
+ const struct htable *t;
+ struct nlattr *nested;
+ size_t memsize;
+
+ t = rcu_dereference_bh_nfnl(h->table);
+ memsize = mtype_ahash_memsize(h, t, NLEN(set->family), set->dsize);
+
+ nested = ipset_nest_start(skb, IPSET_ATTR_DATA);
+ if (!nested)
+ goto nla_put_failure;
+ if (nla_put_net32(skb, IPSET_ATTR_HASHSIZE,
+ htonl(jhash_size(t->htable_bits))) ||
+ nla_put_net32(skb, IPSET_ATTR_MAXELEM, htonl(h->maxelem)))
+ goto nla_put_failure;
+#ifdef IP_SET_HASH_WITH_NETMASK
+ if (h->netmask != HOST_MASK &&
+ nla_put_u8(skb, IPSET_ATTR_NETMASK, h->netmask))
+ goto nla_put_failure;
+#endif
+#ifdef IP_SET_HASH_WITH_MARKMASK
+ if (nla_put_u32(skb, IPSET_ATTR_MARKMASK, h->markmask))
+ goto nla_put_failure;
+#endif
+ if (nla_put_net32(skb, IPSET_ATTR_REFERENCES, htonl(set->ref - 1)) ||
+ nla_put_net32(skb, IPSET_ATTR_MEMSIZE, htonl(memsize)))
+ goto nla_put_failure;
+ if (unlikely(ip_set_put_flags(skb, set)))
+ goto nla_put_failure;
+ ipset_nest_end(skb, nested);
+
+ return 0;
+nla_put_failure:
+ return -EMSGSIZE;
+}
+
+/* Reply a LIST/SAVE request: dump the elements of the specified set */
+static int
+mtype_list(const struct ip_set *set,
+ struct sk_buff *skb, struct netlink_callback *cb)
+{
+ const struct htype *h = set->data;
+ const struct htable *t = rcu_dereference_bh_nfnl(h->table);
+ struct nlattr *atd, *nested;
+ const struct hbucket *n;
+ const struct mtype_elem *e;
+ u32 first = cb->args[IPSET_CB_ARG0];
+ /* We assume that one hash bucket fills into one page */
+ void *incomplete;
+ int i;
+
+ atd = ipset_nest_start(skb, IPSET_ATTR_ADT);
+ if (!atd)
+ return -EMSGSIZE;
+ pr_debug("list hash set %s\n", set->name);
+ for (; cb->args[IPSET_CB_ARG0] < jhash_size(t->htable_bits);
+ cb->args[IPSET_CB_ARG0]++) {
+ incomplete = skb_tail_pointer(skb);
+ n = hbucket(t, cb->args[IPSET_CB_ARG0]);
+ pr_debug("cb->arg bucket: %lu, t %p n %p\n",
+ cb->args[IPSET_CB_ARG0], t, n);
+ for (i = 0; i < n->pos; i++) {
+ e = ahash_data(n, i, set->dsize);
+ if (SET_WITH_TIMEOUT(set) &&
+ ip_set_timeout_expired(ext_timeout(e, set)))
+ continue;
+ pr_debug("list hash %lu hbucket %p i %u, data %p\n",
+ cb->args[IPSET_CB_ARG0], n, i, e);
+ nested = ipset_nest_start(skb, IPSET_ATTR_DATA);
+ if (!nested) {
+ if (cb->args[IPSET_CB_ARG0] == first) {
+ nla_nest_cancel(skb, atd);
+ return -EMSGSIZE;
+ } else
+ goto nla_put_failure;
+ }
+ if (mtype_data_list(skb, e))
+ goto nla_put_failure;
+ if (ip_set_put_extensions(skb, set, e, true))
+ goto nla_put_failure;
+ ipset_nest_end(skb, nested);
+ }
+ }
+ ipset_nest_end(skb, atd);
+ /* Set listing finished */
+ cb->args[IPSET_CB_ARG0] = 0;
+
+ return 0;
+
+nla_put_failure:
+ nlmsg_trim(skb, incomplete);
+ if (unlikely(first == cb->args[IPSET_CB_ARG0])) {
+ pr_warning("Can't list set %s: one bucket does not fit into "
+ "a message. Please report it!\n", set->name);
+ cb->args[IPSET_CB_ARG0] = 0;
+ return -EMSGSIZE;
+ }
+ ipset_nest_end(skb, atd);
+ return 0;
+}
+
+static int
+IPSET_TOKEN(MTYPE, _kadt)(struct ip_set *set, const struct sk_buff *skb,
+ const struct xt_action_param *par,
+ enum ipset_adt adt, struct ip_set_adt_opt *opt);
+
+static int
+IPSET_TOKEN(MTYPE, _uadt)(struct ip_set *set, struct nlattr *tb[],
+ enum ipset_adt adt, u32 *lineno, u32 flags, bool retried);
+
+static const struct ip_set_type_variant mtype_variant = {
+ .kadt = mtype_kadt,
+ .uadt = mtype_uadt,
+ .adt = {
+ [IPSET_ADD] = mtype_add,
+ [IPSET_DEL] = mtype_del,
+ [IPSET_TEST] = mtype_test,
+ },
+ .destroy = mtype_destroy,
+ .flush = mtype_flush,
+ .head = mtype_head,
+ .list = mtype_list,
+ .resize = mtype_resize,
+ .same_set = mtype_same_set,
+};
+
+#ifdef IP_SET_EMIT_CREATE
+static int
+IPSET_TOKEN(HTYPE, _create)(struct net *net, struct ip_set *set,
+ struct nlattr *tb[], u32 flags)
+{
+ u32 hashsize = IPSET_DEFAULT_HASHSIZE, maxelem = IPSET_DEFAULT_MAXELEM;
+#ifdef IP_SET_HASH_WITH_MARKMASK
+ u32 markmask;
+#endif
+ u8 hbits;
+#ifdef IP_SET_HASH_WITH_NETMASK
+ u8 netmask;
+#endif
+ size_t hsize;
+ struct HTYPE *h;
+ struct htable *t;
+
+ if (!(set->family == NFPROTO_IPV4 || set->family == NFPROTO_IPV6))
+ return -IPSET_ERR_INVALID_FAMILY;
+
+#ifdef IP_SET_HASH_WITH_MARKMASK
+ markmask = 0xffffffff;
+#endif
+#ifdef IP_SET_HASH_WITH_NETMASK
+ netmask = set->family == NFPROTO_IPV4 ? 32 : 128;
+ pr_debug("Create set %s with family %s\n",
+ set->name, set->family == NFPROTO_IPV4 ? "inet" : "inet6");
+#endif
+
+ if (unlikely(!ip_set_optattr_netorder(tb, IPSET_ATTR_HASHSIZE) ||
+ !ip_set_optattr_netorder(tb, IPSET_ATTR_MAXELEM) ||
+#ifdef IP_SET_HASH_WITH_MARKMASK
+ !ip_set_optattr_netorder(tb, IPSET_ATTR_MARKMASK) ||
+#endif
+ !ip_set_optattr_netorder(tb, IPSET_ATTR_TIMEOUT) ||
+ !ip_set_optattr_netorder(tb, IPSET_ATTR_CADT_FLAGS)))
+ return -IPSET_ERR_PROTOCOL;
+
+ if (tb[IPSET_ATTR_HASHSIZE]) {
+ hashsize = ip_set_get_h32(tb[IPSET_ATTR_HASHSIZE]);
+ if (hashsize < IPSET_MIMINAL_HASHSIZE)
+ hashsize = IPSET_MIMINAL_HASHSIZE;
+ }
+
+ if (tb[IPSET_ATTR_MAXELEM])
+ maxelem = ip_set_get_h32(tb[IPSET_ATTR_MAXELEM]);
+
+#ifdef IP_SET_HASH_WITH_NETMASK
+ if (tb[IPSET_ATTR_NETMASK]) {
+ netmask = nla_get_u8(tb[IPSET_ATTR_NETMASK]);
+
+ if ((set->family == NFPROTO_IPV4 && netmask > 32) ||
+ (set->family == NFPROTO_IPV6 && netmask > 128) ||
+ netmask == 0)
+ return -IPSET_ERR_INVALID_NETMASK;
+ }
+#endif
+#ifdef IP_SET_HASH_WITH_MARKMASK
+ if (tb[IPSET_ATTR_MARKMASK]) {
+ markmask = ntohl(nla_get_u32(tb[IPSET_ATTR_MARKMASK]));
+
+ if ((markmask > 4294967295u) || markmask == 0)
+ return -IPSET_ERR_INVALID_MARKMASK;
+ }
+#endif
+
+ hsize = sizeof(*h);
+#ifdef IP_SET_HASH_WITH_NETS
+ hsize += sizeof(struct net_prefixes) *
+ (set->family == NFPROTO_IPV4 ? 32 : 128);
+#endif
+ h = kzalloc(hsize, GFP_KERNEL);
+ if (!h)
+ return -ENOMEM;
+
+ h->maxelem = maxelem;
+#ifdef IP_SET_HASH_WITH_NETMASK
+ h->netmask = netmask;
+#endif
+#ifdef IP_SET_HASH_WITH_MARKMASK
+ h->markmask = markmask;
+#endif
+ get_random_bytes(&h->initval, sizeof(h->initval));
+ set->timeout = IPSET_NO_TIMEOUT;
+
+ hbits = htable_bits(hashsize);
+ hsize = htable_size(hbits);
+ if (hsize == 0) {
+ kfree(h);
+ return -ENOMEM;
+ }
+ t = ip_set_alloc(hsize);
+ if (!t) {
+ kfree(h);
+ return -ENOMEM;
+ }
+ t->htable_bits = hbits;
+ rcu_assign_pointer(h->table, t);
+
+ set->data = h;
+ if (set->family == NFPROTO_IPV4) {
+ set->variant = &IPSET_TOKEN(HTYPE, 4_variant);
+ set->dsize = ip_set_elem_len(set, tb,
+ sizeof(struct IPSET_TOKEN(HTYPE, 4_elem)));
+ } else {
+ set->variant = &IPSET_TOKEN(HTYPE, 6_variant);
+ set->dsize = ip_set_elem_len(set, tb,
+ sizeof(struct IPSET_TOKEN(HTYPE, 6_elem)));
+ }
+ if (tb[IPSET_ATTR_TIMEOUT]) {
+ set->timeout = ip_set_timeout_uget(tb[IPSET_ATTR_TIMEOUT]);
+ if (set->family == NFPROTO_IPV4)
+ IPSET_TOKEN(HTYPE, 4_gc_init)(set,
+ IPSET_TOKEN(HTYPE, 4_gc));
+ else
+ IPSET_TOKEN(HTYPE, 6_gc_init)(set,
+ IPSET_TOKEN(HTYPE, 6_gc));
+ }
+
+ pr_debug("create %s hashsize %u (%u) maxelem %u: %p(%p)\n",
+ set->name, jhash_size(t->htable_bits),
+ t->htable_bits, h->maxelem, set->data, t);
+
+ return 0;
+}
+#endif /* IP_SET_EMIT_CREATE */
diff --git a/net/netfilter/ipset/ip_set_hash_ip.c b/net/netfilter/ipset/ip_set_hash_ip.c
index 5c0b78528e5..dd40607f878 100644
--- a/net/netfilter/ipset/ip_set_hash_ip.c
+++ b/net/netfilter/ipset/ip_set_hash_ip.c
@@ -1,4 +1,4 @@
-/* Copyright (C) 2003-2011 Jozsef Kadlecsik <kadlec@blackhole.kfki.hu>
+/* Copyright (C) 2003-2013 Jozsef Kadlecsik <kadlec@blackhole.kfki.hu>
*
* This program is free software; you can redistribute it and/or modify
* it under the terms of the GNU General Public License version 2 as
@@ -21,70 +21,44 @@
#include <linux/netfilter.h>
#include <linux/netfilter/ipset/pfxlen.h>
#include <linux/netfilter/ipset/ip_set.h>
-#include <linux/netfilter/ipset/ip_set_timeout.h>
#include <linux/netfilter/ipset/ip_set_hash.h>
-#define REVISION_MIN 0
-#define REVISION_MAX 0
+#define IPSET_TYPE_REV_MIN 0
+/* 1 Counters support */
+/* 2 Comments support */
+#define IPSET_TYPE_REV_MAX 3 /* Forceadd support */
MODULE_LICENSE("GPL");
MODULE_AUTHOR("Jozsef Kadlecsik <kadlec@blackhole.kfki.hu>");
-IP_SET_MODULE_DESC("hash:ip", REVISION_MIN, REVISION_MAX);
+IP_SET_MODULE_DESC("hash:ip", IPSET_TYPE_REV_MIN, IPSET_TYPE_REV_MAX);
MODULE_ALIAS("ip_set_hash:ip");
/* Type specific function prefix */
-#define TYPE hash_ip
-
-static bool
-hash_ip_same_set(const struct ip_set *a, const struct ip_set *b);
-
-#define hash_ip4_same_set hash_ip_same_set
-#define hash_ip6_same_set hash_ip_same_set
+#define HTYPE hash_ip
+#define IP_SET_HASH_WITH_NETMASK
-/* The type variant functions: IPv4 */
+/* IPv4 variant */
-/* Member elements without timeout */
+/* Member elements */
struct hash_ip4_elem {
+ /* Zero valued IP addresses cannot be stored */
__be32 ip;
};
-/* Member elements with timeout support */
-struct hash_ip4_telem {
- __be32 ip;
- unsigned long timeout;
-};
+/* Common functions */
static inline bool
-hash_ip4_data_equal(const struct hash_ip4_elem *ip1,
- const struct hash_ip4_elem *ip2,
+hash_ip4_data_equal(const struct hash_ip4_elem *e1,
+ const struct hash_ip4_elem *e2,
u32 *multi)
{
- return ip1->ip == ip2->ip;
+ return e1->ip == e2->ip;
}
static inline bool
-hash_ip4_data_isnull(const struct hash_ip4_elem *elem)
+hash_ip4_data_list(struct sk_buff *skb, const struct hash_ip4_elem *e)
{
- return elem->ip == 0;
-}
-
-static inline void
-hash_ip4_data_copy(struct hash_ip4_elem *dst, const struct hash_ip4_elem *src)
-{
- dst->ip = src->ip;
-}
-
-/* Zero valued IP addresses cannot be stored */
-static inline void
-hash_ip4_data_zero_out(struct hash_ip4_elem *elem)
-{
- elem->ip = 0;
-}
-
-static inline bool
-hash_ip4_data_list(struct sk_buff *skb, const struct hash_ip4_elem *data)
-{
- if (nla_put_ipaddr4(skb, IPSET_ATTR_IP, data->ip))
+ if (nla_put_ipaddr4(skb, IPSET_ATTR_IP, e->ip))
goto nla_put_failure;
return 0;
@@ -92,41 +66,26 @@ nla_put_failure:
return 1;
}
-static bool
-hash_ip4_data_tlist(struct sk_buff *skb, const struct hash_ip4_elem *data)
+static inline void
+hash_ip4_data_next(struct hash_ip4_elem *next, const struct hash_ip4_elem *e)
{
- const struct hash_ip4_telem *tdata =
- (const struct hash_ip4_telem *)data;
-
- if (nla_put_ipaddr4(skb, IPSET_ATTR_IP, tdata->ip) ||
- nla_put_net32(skb, IPSET_ATTR_TIMEOUT,
- htonl(ip_set_timeout_get(tdata->timeout))))
- goto nla_put_failure;
-
- return 0;
-
-nla_put_failure:
- return 1;
+ next->ip = e->ip;
}
-#define IP_SET_HASH_WITH_NETMASK
+#define MTYPE hash_ip4
#define PF 4
#define HOST_MASK 32
-#include <linux/netfilter/ipset/ip_set_ahash.h>
-
-static inline void
-hash_ip4_data_next(struct ip_set_hash *h, const struct hash_ip4_elem *d)
-{
- h->next.ip = d->ip;
-}
+#include "ip_set_hash_gen.h"
static int
hash_ip4_kadt(struct ip_set *set, const struct sk_buff *skb,
const struct xt_action_param *par,
- enum ipset_adt adt, const struct ip_set_adt_opt *opt)
+ enum ipset_adt adt, struct ip_set_adt_opt *opt)
{
- const struct ip_set_hash *h = set->data;
+ const struct hash_ip *h = set->data;
ipset_adtfn adtfn = set->variant->adt[adt];
+ struct hash_ip4_elem e = {};
+ struct ip_set_ext ext = IP_SET_INIT_KEXT(skb, opt, set);
__be32 ip;
ip4addrptr(skb, opt->flags & IPSET_DIM_ONE_SRC, &ip);
@@ -134,43 +93,42 @@ hash_ip4_kadt(struct ip_set *set, const struct sk_buff *skb,
if (ip == 0)
return -EINVAL;
- return adtfn(set, &ip, opt_timeout(opt, h), opt->cmdflags);
+ e.ip = ip;
+ return adtfn(set, &e, &ext, &opt->ext, opt->cmdflags);
}
static int
hash_ip4_uadt(struct ip_set *set, struct nlattr *tb[],
enum ipset_adt adt, u32 *lineno, u32 flags, bool retried)
{
- const struct ip_set_hash *h = set->data;
+ const struct hash_ip *h = set->data;
ipset_adtfn adtfn = set->variant->adt[adt];
- u32 ip, ip_to, hosts, timeout = h->timeout;
- __be32 nip;
+ struct hash_ip4_elem e = {};
+ struct ip_set_ext ext = IP_SET_INIT_UEXT(set);
+ u32 ip = 0, ip_to = 0, hosts;
int ret = 0;
if (unlikely(!tb[IPSET_ATTR_IP] ||
- !ip_set_optattr_netorder(tb, IPSET_ATTR_TIMEOUT)))
+ !ip_set_optattr_netorder(tb, IPSET_ATTR_TIMEOUT) ||
+ !ip_set_optattr_netorder(tb, IPSET_ATTR_PACKETS) ||
+ !ip_set_optattr_netorder(tb, IPSET_ATTR_BYTES)))
return -IPSET_ERR_PROTOCOL;
if (tb[IPSET_ATTR_LINENO])
*lineno = nla_get_u32(tb[IPSET_ATTR_LINENO]);
- ret = ip_set_get_hostipaddr4(tb[IPSET_ATTR_IP], &ip);
+ ret = ip_set_get_hostipaddr4(tb[IPSET_ATTR_IP], &ip) ||
+ ip_set_get_extensions(set, tb, &ext);
if (ret)
return ret;
ip &= ip_set_hostmask(h->netmask);
- if (tb[IPSET_ATTR_TIMEOUT]) {
- if (!with_timeout(h->timeout))
- return -IPSET_ERR_TIMEOUT;
- timeout = ip_set_timeout_uget(tb[IPSET_ATTR_TIMEOUT]);
- }
-
if (adt == IPSET_TEST) {
- nip = htonl(ip);
- if (nip == 0)
+ e.ip = htonl(ip);
+ if (e.ip == 0)
return -IPSET_ERR_HASH_ELEM;
- return adtfn(set, &nip, timeout, flags);
+ return adtfn(set, &e, &ext, &ext, flags);
}
ip_to = ip;
@@ -193,10 +151,10 @@ hash_ip4_uadt(struct ip_set *set, struct nlattr *tb[],
if (retried)
ip = ntohl(h->next.ip);
for (; !before(ip_to, ip); ip += hosts) {
- nip = htonl(ip);
- if (nip == 0)
+ e.ip = htonl(ip);
+ if (e.ip == 0)
return -IPSET_ERR_HASH_ELEM;
- ret = adtfn(set, &nip, timeout, flags);
+ ret = adtfn(set, &e, &ext, &ext, flags);
if (ret && !ip_set_eexist(ret, flags))
return ret;
@@ -206,68 +164,33 @@ hash_ip4_uadt(struct ip_set *set, struct nlattr *tb[],
return ret;
}
-static bool
-hash_ip_same_set(const struct ip_set *a, const struct ip_set *b)
-{
- const struct ip_set_hash *x = a->data;
- const struct ip_set_hash *y = b->data;
-
- /* Resizing changes htable_bits, so we ignore it */
- return x->maxelem == y->maxelem &&
- x->timeout == y->timeout &&
- x->netmask == y->netmask;
-}
-
-/* The type variant functions: IPv6 */
+/* IPv6 variant */
+/* Member elements */
struct hash_ip6_elem {
union nf_inet_addr ip;
};
-struct hash_ip6_telem {
- union nf_inet_addr ip;
- unsigned long timeout;
-};
+/* Common functions */
static inline bool
hash_ip6_data_equal(const struct hash_ip6_elem *ip1,
const struct hash_ip6_elem *ip2,
u32 *multi)
{
- return ipv6_addr_cmp(&ip1->ip.in6, &ip2->ip.in6) == 0;
-}
-
-static inline bool
-hash_ip6_data_isnull(const struct hash_ip6_elem *elem)
-{
- return ipv6_addr_any(&elem->ip.in6);
+ return ipv6_addr_equal(&ip1->ip.in6, &ip2->ip.in6);
}
static inline void
-hash_ip6_data_copy(struct hash_ip6_elem *dst, const struct hash_ip6_elem *src)
+hash_ip6_netmask(union nf_inet_addr *ip, u8 prefix)
{
- dst->ip.in6 = src->ip.in6;
-}
-
-static inline void
-hash_ip6_data_zero_out(struct hash_ip6_elem *elem)
-{
- ipv6_addr_set(&elem->ip.in6, 0, 0, 0, 0);
-}
-
-static inline void
-ip6_netmask(union nf_inet_addr *ip, u8 prefix)
-{
- ip->ip6[0] &= ip_set_netmask6(prefix)[0];
- ip->ip6[1] &= ip_set_netmask6(prefix)[1];
- ip->ip6[2] &= ip_set_netmask6(prefix)[2];
- ip->ip6[3] &= ip_set_netmask6(prefix)[3];
+ ip6_netmask(ip, prefix);
}
static bool
-hash_ip6_data_list(struct sk_buff *skb, const struct hash_ip6_elem *data)
+hash_ip6_data_list(struct sk_buff *skb, const struct hash_ip6_elem *e)
{
- if (nla_put_ipaddr6(skb, IPSET_ATTR_IP, &data->ip.in6))
+ if (nla_put_ipaddr6(skb, IPSET_ATTR_IP, &e->ip.in6))
goto nla_put_failure;
return 0;
@@ -275,69 +198,55 @@ nla_put_failure:
return 1;
}
-static bool
-hash_ip6_data_tlist(struct sk_buff *skb, const struct hash_ip6_elem *data)
+static inline void
+hash_ip6_data_next(struct hash_ip4_elem *next, const struct hash_ip6_elem *e)
{
- const struct hash_ip6_telem *e =
- (const struct hash_ip6_telem *)data;
-
- if (nla_put_ipaddr6(skb, IPSET_ATTR_IP, &e->ip.in6) ||
- nla_put_net32(skb, IPSET_ATTR_TIMEOUT,
- htonl(ip_set_timeout_get(e->timeout))))
- goto nla_put_failure;
- return 0;
-
-nla_put_failure:
- return 1;
}
+#undef MTYPE
#undef PF
#undef HOST_MASK
+#undef HKEY_DATALEN
+#define MTYPE hash_ip6
#define PF 6
#define HOST_MASK 128
-#include <linux/netfilter/ipset/ip_set_ahash.h>
-static inline void
-hash_ip6_data_next(struct ip_set_hash *h, const struct hash_ip6_elem *d)
-{
-}
+#define IP_SET_EMIT_CREATE
+#include "ip_set_hash_gen.h"
static int
hash_ip6_kadt(struct ip_set *set, const struct sk_buff *skb,
const struct xt_action_param *par,
- enum ipset_adt adt, const struct ip_set_adt_opt *opt)
+ enum ipset_adt adt, struct ip_set_adt_opt *opt)
{
- const struct ip_set_hash *h = set->data;
+ const struct hash_ip *h = set->data;
ipset_adtfn adtfn = set->variant->adt[adt];
- union nf_inet_addr ip;
+ struct hash_ip6_elem e = {};
+ struct ip_set_ext ext = IP_SET_INIT_KEXT(skb, opt, set);
- ip6addrptr(skb, opt->flags & IPSET_DIM_ONE_SRC, &ip.in6);
- ip6_netmask(&ip, h->netmask);
- if (ipv6_addr_any(&ip.in6))
+ ip6addrptr(skb, opt->flags & IPSET_DIM_ONE_SRC, &e.ip.in6);
+ hash_ip6_netmask(&e.ip, h->netmask);
+ if (ipv6_addr_any(&e.ip.in6))
return -EINVAL;
- return adtfn(set, &ip, opt_timeout(opt, h), opt->cmdflags);
+ return adtfn(set, &e, &ext, &opt->ext, opt->cmdflags);
}
-static const struct nla_policy hash_ip6_adt_policy[IPSET_ATTR_ADT_MAX + 1] = {
- [IPSET_ATTR_IP] = { .type = NLA_NESTED },
- [IPSET_ATTR_TIMEOUT] = { .type = NLA_U32 },
- [IPSET_ATTR_LINENO] = { .type = NLA_U32 },
-};
-
static int
hash_ip6_uadt(struct ip_set *set, struct nlattr *tb[],
enum ipset_adt adt, u32 *lineno, u32 flags, bool retried)
{
- const struct ip_set_hash *h = set->data;
+ const struct hash_ip *h = set->data;
ipset_adtfn adtfn = set->variant->adt[adt];
- union nf_inet_addr ip;
- u32 timeout = h->timeout;
+ struct hash_ip6_elem e = {};
+ struct ip_set_ext ext = IP_SET_INIT_UEXT(set);
int ret;
if (unlikely(!tb[IPSET_ATTR_IP] ||
!ip_set_optattr_netorder(tb, IPSET_ATTR_TIMEOUT) ||
+ !ip_set_optattr_netorder(tb, IPSET_ATTR_PACKETS) ||
+ !ip_set_optattr_netorder(tb, IPSET_ATTR_BYTES) ||
tb[IPSET_ATTR_IP_TO] ||
tb[IPSET_ATTR_CIDR]))
return -IPSET_ERR_PROTOCOL;
@@ -345,118 +254,28 @@ hash_ip6_uadt(struct ip_set *set, struct nlattr *tb[],
if (tb[IPSET_ATTR_LINENO])
*lineno = nla_get_u32(tb[IPSET_ATTR_LINENO]);
- ret = ip_set_get_ipaddr6(tb[IPSET_ATTR_IP], &ip);
+ ret = ip_set_get_ipaddr6(tb[IPSET_ATTR_IP], &e.ip) ||
+ ip_set_get_extensions(set, tb, &ext);
if (ret)
return ret;
- ip6_netmask(&ip, h->netmask);
- if (ipv6_addr_any(&ip.in6))
+ hash_ip6_netmask(&e.ip, h->netmask);
+ if (ipv6_addr_any(&e.ip.in6))
return -IPSET_ERR_HASH_ELEM;
- if (tb[IPSET_ATTR_TIMEOUT]) {
- if (!with_timeout(h->timeout))
- return -IPSET_ERR_TIMEOUT;
- timeout = ip_set_timeout_uget(tb[IPSET_ATTR_TIMEOUT]);
- }
-
- ret = adtfn(set, &ip, timeout, flags);
+ ret = adtfn(set, &e, &ext, &ext, flags);
return ip_set_eexist(ret, flags) ? 0 : ret;
}
-/* Create hash:ip type of sets */
-
-static int
-hash_ip_create(struct ip_set *set, struct nlattr *tb[], u32 flags)
-{
- u32 hashsize = IPSET_DEFAULT_HASHSIZE, maxelem = IPSET_DEFAULT_MAXELEM;
- u8 netmask, hbits;
- size_t hsize;
- struct ip_set_hash *h;
-
- if (!(set->family == NFPROTO_IPV4 || set->family == NFPROTO_IPV6))
- return -IPSET_ERR_INVALID_FAMILY;
- netmask = set->family == NFPROTO_IPV4 ? 32 : 128;
- pr_debug("Create set %s with family %s\n",
- set->name, set->family == NFPROTO_IPV4 ? "inet" : "inet6");
-
- if (unlikely(!ip_set_optattr_netorder(tb, IPSET_ATTR_HASHSIZE) ||
- !ip_set_optattr_netorder(tb, IPSET_ATTR_MAXELEM) ||
- !ip_set_optattr_netorder(tb, IPSET_ATTR_TIMEOUT)))
- return -IPSET_ERR_PROTOCOL;
-
- if (tb[IPSET_ATTR_HASHSIZE]) {
- hashsize = ip_set_get_h32(tb[IPSET_ATTR_HASHSIZE]);
- if (hashsize < IPSET_MIMINAL_HASHSIZE)
- hashsize = IPSET_MIMINAL_HASHSIZE;
- }
-
- if (tb[IPSET_ATTR_MAXELEM])
- maxelem = ip_set_get_h32(tb[IPSET_ATTR_MAXELEM]);
-
- if (tb[IPSET_ATTR_NETMASK]) {
- netmask = nla_get_u8(tb[IPSET_ATTR_NETMASK]);
-
- if ((set->family == NFPROTO_IPV4 && netmask > 32) ||
- (set->family == NFPROTO_IPV6 && netmask > 128) ||
- netmask == 0)
- return -IPSET_ERR_INVALID_NETMASK;
- }
-
- h = kzalloc(sizeof(*h), GFP_KERNEL);
- if (!h)
- return -ENOMEM;
-
- h->maxelem = maxelem;
- h->netmask = netmask;
- get_random_bytes(&h->initval, sizeof(h->initval));
- h->timeout = IPSET_NO_TIMEOUT;
-
- hbits = htable_bits(hashsize);
- hsize = htable_size(hbits);
- if (hsize == 0) {
- kfree(h);
- return -ENOMEM;
- }
- h->table = ip_set_alloc(hsize);
- if (!h->table) {
- kfree(h);
- return -ENOMEM;
- }
- h->table->htable_bits = hbits;
-
- set->data = h;
-
- if (tb[IPSET_ATTR_TIMEOUT]) {
- h->timeout = ip_set_timeout_uget(tb[IPSET_ATTR_TIMEOUT]);
-
- set->variant = set->family == NFPROTO_IPV4
- ? &hash_ip4_tvariant : &hash_ip6_tvariant;
-
- if (set->family == NFPROTO_IPV4)
- hash_ip4_gc_init(set);
- else
- hash_ip6_gc_init(set);
- } else {
- set->variant = set->family == NFPROTO_IPV4
- ? &hash_ip4_variant : &hash_ip6_variant;
- }
-
- pr_debug("create %s hashsize %u (%u) maxelem %u: %p(%p)\n",
- set->name, jhash_size(h->table->htable_bits),
- h->table->htable_bits, h->maxelem, set->data, h->table);
-
- return 0;
-}
-
static struct ip_set_type hash_ip_type __read_mostly = {
.name = "hash:ip",
.protocol = IPSET_PROTOCOL,
.features = IPSET_TYPE_IP,
.dimension = IPSET_DIM_ONE,
.family = NFPROTO_UNSPEC,
- .revision_min = REVISION_MIN,
- .revision_max = REVISION_MAX,
+ .revision_min = IPSET_TYPE_REV_MIN,
+ .revision_max = IPSET_TYPE_REV_MAX,
.create = hash_ip_create,
.create_policy = {
[IPSET_ATTR_HASHSIZE] = { .type = NLA_U32 },
@@ -465,6 +284,7 @@ static struct ip_set_type hash_ip_type __read_mostly = {
[IPSET_ATTR_RESIZE] = { .type = NLA_U8 },
[IPSET_ATTR_TIMEOUT] = { .type = NLA_U32 },
[IPSET_ATTR_NETMASK] = { .type = NLA_U8 },
+ [IPSET_ATTR_CADT_FLAGS] = { .type = NLA_U32 },
},
.adt_policy = {
[IPSET_ATTR_IP] = { .type = NLA_NESTED },
@@ -472,6 +292,9 @@ static struct ip_set_type hash_ip_type __read_mostly = {
[IPSET_ATTR_CIDR] = { .type = NLA_U8 },
[IPSET_ATTR_TIMEOUT] = { .type = NLA_U32 },
[IPSET_ATTR_LINENO] = { .type = NLA_U32 },
+ [IPSET_ATTR_BYTES] = { .type = NLA_U64 },
+ [IPSET_ATTR_PACKETS] = { .type = NLA_U64 },
+ [IPSET_ATTR_COMMENT] = { .type = NLA_NUL_STRING },
},
.me = THIS_MODULE,
};
diff --git a/net/netfilter/ipset/ip_set_hash_ipmark.c b/net/netfilter/ipset/ip_set_hash_ipmark.c
new file mode 100644
index 00000000000..4eff0a29725
--- /dev/null
+++ b/net/netfilter/ipset/ip_set_hash_ipmark.c
@@ -0,0 +1,321 @@
+/* Copyright (C) 2003-2013 Jozsef Kadlecsik <kadlec@blackhole.kfki.hu>
+ * Copyright (C) 2013 Smoothwall Ltd. <vytas.dauksa@smoothwall.net>
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2 as
+ * published by the Free Software Foundation.
+ */
+
+/* Kernel module implementing an IP set type: the hash:ip,mark type */
+
+#include <linux/jhash.h>
+#include <linux/module.h>
+#include <linux/ip.h>
+#include <linux/skbuff.h>
+#include <linux/errno.h>
+#include <linux/random.h>
+#include <net/ip.h>
+#include <net/ipv6.h>
+#include <net/netlink.h>
+#include <net/tcp.h>
+
+#include <linux/netfilter.h>
+#include <linux/netfilter/ipset/pfxlen.h>
+#include <linux/netfilter/ipset/ip_set.h>
+#include <linux/netfilter/ipset/ip_set_hash.h>
+
+#define IPSET_TYPE_REV_MIN 0
+#define IPSET_TYPE_REV_MAX 1 /* Forceadd support */
+
+MODULE_LICENSE("GPL");
+MODULE_AUTHOR("Vytas Dauksa <vytas.dauksa@smoothwall.net>");
+IP_SET_MODULE_DESC("hash:ip,mark", IPSET_TYPE_REV_MIN, IPSET_TYPE_REV_MAX);
+MODULE_ALIAS("ip_set_hash:ip,mark");
+
+/* Type specific function prefix */
+#define HTYPE hash_ipmark
+#define IP_SET_HASH_WITH_MARKMASK
+
+/* IPv4 variant */
+
+/* Member elements */
+struct hash_ipmark4_elem {
+ __be32 ip;
+ __u32 mark;
+};
+
+/* Common functions */
+
+static inline bool
+hash_ipmark4_data_equal(const struct hash_ipmark4_elem *ip1,
+ const struct hash_ipmark4_elem *ip2,
+ u32 *multi)
+{
+ return ip1->ip == ip2->ip &&
+ ip1->mark == ip2->mark;
+}
+
+static bool
+hash_ipmark4_data_list(struct sk_buff *skb,
+ const struct hash_ipmark4_elem *data)
+{
+ if (nla_put_ipaddr4(skb, IPSET_ATTR_IP, data->ip) ||
+ nla_put_net32(skb, IPSET_ATTR_MARK, htonl(data->mark)))
+ goto nla_put_failure;
+ return 0;
+
+nla_put_failure:
+ return 1;
+}
+
+static inline void
+hash_ipmark4_data_next(struct hash_ipmark4_elem *next,
+ const struct hash_ipmark4_elem *d)
+{
+ next->ip = d->ip;
+}
+
+#define MTYPE hash_ipmark4
+#define PF 4
+#define HOST_MASK 32
+#define HKEY_DATALEN sizeof(struct hash_ipmark4_elem)
+#include "ip_set_hash_gen.h"
+
+static int
+hash_ipmark4_kadt(struct ip_set *set, const struct sk_buff *skb,
+ const struct xt_action_param *par,
+ enum ipset_adt adt, struct ip_set_adt_opt *opt)
+{
+ const struct hash_ipmark *h = set->data;
+ ipset_adtfn adtfn = set->variant->adt[adt];
+ struct hash_ipmark4_elem e = { };
+ struct ip_set_ext ext = IP_SET_INIT_KEXT(skb, opt, set);
+
+ e.mark = skb->mark;
+ e.mark &= h->markmask;
+
+ ip4addrptr(skb, opt->flags & IPSET_DIM_ONE_SRC, &e.ip);
+ return adtfn(set, &e, &ext, &opt->ext, opt->cmdflags);
+}
+
+static int
+hash_ipmark4_uadt(struct ip_set *set, struct nlattr *tb[],
+ enum ipset_adt adt, u32 *lineno, u32 flags, bool retried)
+{
+ const struct hash_ipmark *h = set->data;
+ ipset_adtfn adtfn = set->variant->adt[adt];
+ struct hash_ipmark4_elem e = { };
+ struct ip_set_ext ext = IP_SET_INIT_UEXT(set);
+ u32 ip, ip_to = 0;
+ int ret;
+
+ if (unlikely(!tb[IPSET_ATTR_IP] ||
+ !ip_set_attr_netorder(tb, IPSET_ATTR_MARK) ||
+ !ip_set_optattr_netorder(tb, IPSET_ATTR_TIMEOUT) ||
+ !ip_set_optattr_netorder(tb, IPSET_ATTR_PACKETS) ||
+ !ip_set_optattr_netorder(tb, IPSET_ATTR_BYTES)))
+ return -IPSET_ERR_PROTOCOL;
+
+ if (tb[IPSET_ATTR_LINENO])
+ *lineno = nla_get_u32(tb[IPSET_ATTR_LINENO]);
+
+ ret = ip_set_get_ipaddr4(tb[IPSET_ATTR_IP], &e.ip) ||
+ ip_set_get_extensions(set, tb, &ext);
+ if (ret)
+ return ret;
+
+ e.mark = ntohl(nla_get_u32(tb[IPSET_ATTR_MARK]));
+ e.mark &= h->markmask;
+
+ if (adt == IPSET_TEST ||
+ !(tb[IPSET_ATTR_IP_TO] || tb[IPSET_ATTR_CIDR])) {
+ ret = adtfn(set, &e, &ext, &ext, flags);
+ return ip_set_eexist(ret, flags) ? 0 : ret;
+ }
+
+ ip_to = ip = ntohl(e.ip);
+ if (tb[IPSET_ATTR_IP_TO]) {
+ ret = ip_set_get_hostipaddr4(tb[IPSET_ATTR_IP_TO], &ip_to);
+ if (ret)
+ return ret;
+ if (ip > ip_to)
+ swap(ip, ip_to);
+ } else if (tb[IPSET_ATTR_CIDR]) {
+ u8 cidr = nla_get_u8(tb[IPSET_ATTR_CIDR]);
+
+ if (!cidr || cidr > 32)
+ return -IPSET_ERR_INVALID_CIDR;
+ ip_set_mask_from_to(ip, ip_to, cidr);
+ }
+
+ if (retried)
+ ip = ntohl(h->next.ip);
+ for (; !before(ip_to, ip); ip++) {
+ e.ip = htonl(ip);
+ ret = adtfn(set, &e, &ext, &ext, flags);
+
+ if (ret && !ip_set_eexist(ret, flags))
+ return ret;
+ else
+ ret = 0;
+ }
+ return ret;
+}
+
+/* IPv6 variant */
+
+struct hash_ipmark6_elem {
+ union nf_inet_addr ip;
+ __u32 mark;
+};
+
+/* Common functions */
+
+static inline bool
+hash_ipmark6_data_equal(const struct hash_ipmark6_elem *ip1,
+ const struct hash_ipmark6_elem *ip2,
+ u32 *multi)
+{
+ return ipv6_addr_equal(&ip1->ip.in6, &ip2->ip.in6) &&
+ ip1->mark == ip2->mark;
+}
+
+static bool
+hash_ipmark6_data_list(struct sk_buff *skb,
+ const struct hash_ipmark6_elem *data)
+{
+ if (nla_put_ipaddr6(skb, IPSET_ATTR_IP, &data->ip.in6) ||
+ nla_put_net32(skb, IPSET_ATTR_MARK, htonl(data->mark)))
+ goto nla_put_failure;
+ return 0;
+
+nla_put_failure:
+ return 1;
+}
+
+static inline void
+hash_ipmark6_data_next(struct hash_ipmark4_elem *next,
+ const struct hash_ipmark6_elem *d)
+{
+}
+
+#undef MTYPE
+#undef PF
+#undef HOST_MASK
+#undef HKEY_DATALEN
+
+#define MTYPE hash_ipmark6
+#define PF 6
+#define HOST_MASK 128
+#define HKEY_DATALEN sizeof(struct hash_ipmark6_elem)
+#define IP_SET_EMIT_CREATE
+#include "ip_set_hash_gen.h"
+
+
+static int
+hash_ipmark6_kadt(struct ip_set *set, const struct sk_buff *skb,
+ const struct xt_action_param *par,
+ enum ipset_adt adt, struct ip_set_adt_opt *opt)
+{
+ const struct hash_ipmark *h = set->data;
+ ipset_adtfn adtfn = set->variant->adt[adt];
+ struct hash_ipmark6_elem e = { };
+ struct ip_set_ext ext = IP_SET_INIT_KEXT(skb, opt, set);
+
+ e.mark = skb->mark;
+ e.mark &= h->markmask;
+
+ ip6addrptr(skb, opt->flags & IPSET_DIM_ONE_SRC, &e.ip.in6);
+ return adtfn(set, &e, &ext, &opt->ext, opt->cmdflags);
+}
+
+static int
+hash_ipmark6_uadt(struct ip_set *set, struct nlattr *tb[],
+ enum ipset_adt adt, u32 *lineno, u32 flags, bool retried)
+{
+ const struct hash_ipmark *h = set->data;
+ ipset_adtfn adtfn = set->variant->adt[adt];
+ struct hash_ipmark6_elem e = { };
+ struct ip_set_ext ext = IP_SET_INIT_UEXT(set);
+ int ret;
+
+ if (unlikely(!tb[IPSET_ATTR_IP] ||
+ !ip_set_attr_netorder(tb, IPSET_ATTR_MARK) ||
+ !ip_set_optattr_netorder(tb, IPSET_ATTR_TIMEOUT) ||
+ !ip_set_optattr_netorder(tb, IPSET_ATTR_PACKETS) ||
+ !ip_set_optattr_netorder(tb, IPSET_ATTR_BYTES) ||
+ tb[IPSET_ATTR_IP_TO] ||
+ tb[IPSET_ATTR_CIDR]))
+ return -IPSET_ERR_PROTOCOL;
+
+ if (tb[IPSET_ATTR_LINENO])
+ *lineno = nla_get_u32(tb[IPSET_ATTR_LINENO]);
+
+ ret = ip_set_get_ipaddr6(tb[IPSET_ATTR_IP], &e.ip) ||
+ ip_set_get_extensions(set, tb, &ext);
+ if (ret)
+ return ret;
+
+ e.mark = ntohl(nla_get_u32(tb[IPSET_ATTR_MARK]));
+ e.mark &= h->markmask;
+
+ if (adt == IPSET_TEST) {
+ ret = adtfn(set, &e, &ext, &ext, flags);
+ return ip_set_eexist(ret, flags) ? 0 : ret;
+ }
+
+ ret = adtfn(set, &e, &ext, &ext, flags);
+ if (ret && !ip_set_eexist(ret, flags))
+ return ret;
+ else
+ ret = 0;
+
+ return ret;
+}
+
+static struct ip_set_type hash_ipmark_type __read_mostly = {
+ .name = "hash:ip,mark",
+ .protocol = IPSET_PROTOCOL,
+ .features = IPSET_TYPE_IP | IPSET_TYPE_MARK,
+ .dimension = IPSET_DIM_TWO,
+ .family = NFPROTO_UNSPEC,
+ .revision_min = IPSET_TYPE_REV_MIN,
+ .revision_max = IPSET_TYPE_REV_MAX,
+ .create = hash_ipmark_create,
+ .create_policy = {
+ [IPSET_ATTR_MARKMASK] = { .type = NLA_U32 },
+ [IPSET_ATTR_HASHSIZE] = { .type = NLA_U32 },
+ [IPSET_ATTR_MAXELEM] = { .type = NLA_U32 },
+ [IPSET_ATTR_PROBES] = { .type = NLA_U8 },
+ [IPSET_ATTR_RESIZE] = { .type = NLA_U8 },
+ [IPSET_ATTR_TIMEOUT] = { .type = NLA_U32 },
+ [IPSET_ATTR_CADT_FLAGS] = { .type = NLA_U32 },
+ },
+ .adt_policy = {
+ [IPSET_ATTR_IP] = { .type = NLA_NESTED },
+ [IPSET_ATTR_IP_TO] = { .type = NLA_NESTED },
+ [IPSET_ATTR_MARK] = { .type = NLA_U32 },
+ [IPSET_ATTR_CIDR] = { .type = NLA_U8 },
+ [IPSET_ATTR_TIMEOUT] = { .type = NLA_U32 },
+ [IPSET_ATTR_LINENO] = { .type = NLA_U32 },
+ [IPSET_ATTR_BYTES] = { .type = NLA_U64 },
+ [IPSET_ATTR_PACKETS] = { .type = NLA_U64 },
+ [IPSET_ATTR_COMMENT] = { .type = NLA_NUL_STRING },
+ },
+ .me = THIS_MODULE,
+};
+
+static int __init
+hash_ipmark_init(void)
+{
+ return ip_set_type_register(&hash_ipmark_type);
+}
+
+static void __exit
+hash_ipmark_fini(void)
+{
+ ip_set_type_unregister(&hash_ipmark_type);
+}
+
+module_init(hash_ipmark_init);
+module_exit(hash_ipmark_fini);
diff --git a/net/netfilter/ipset/ip_set_hash_ipport.c b/net/netfilter/ipset/ip_set_hash_ipport.c
index 6283351f4ee..7597b82a8b0 100644
--- a/net/netfilter/ipset/ip_set_hash_ipport.c
+++ b/net/netfilter/ipset/ip_set_hash_ipport.c
@@ -1,4 +1,4 @@
-/* Copyright (C) 2003-2011 Jozsef Kadlecsik <kadlec@blackhole.kfki.hu>
+/* Copyright (C) 2003-2013 Jozsef Kadlecsik <kadlec@blackhole.kfki.hu>
*
* This program is free software; you can redistribute it and/or modify
* it under the terms of the GNU General Public License version 2 as
@@ -21,30 +21,26 @@
#include <linux/netfilter.h>
#include <linux/netfilter/ipset/pfxlen.h>
#include <linux/netfilter/ipset/ip_set.h>
-#include <linux/netfilter/ipset/ip_set_timeout.h>
#include <linux/netfilter/ipset/ip_set_getport.h>
#include <linux/netfilter/ipset/ip_set_hash.h>
-#define REVISION_MIN 0
-#define REVISION_MAX 1 /* SCTP and UDPLITE support added */
+#define IPSET_TYPE_REV_MIN 0
+/* 1 SCTP and UDPLITE support added */
+/* 2 Counters support added */
+/* 3 Comments support added */
+#define IPSET_TYPE_REV_MAX 4 /* Forceadd support added */
MODULE_LICENSE("GPL");
MODULE_AUTHOR("Jozsef Kadlecsik <kadlec@blackhole.kfki.hu>");
-IP_SET_MODULE_DESC("hash:ip,port", REVISION_MIN, REVISION_MAX);
+IP_SET_MODULE_DESC("hash:ip,port", IPSET_TYPE_REV_MIN, IPSET_TYPE_REV_MAX);
MODULE_ALIAS("ip_set_hash:ip,port");
/* Type specific function prefix */
-#define TYPE hash_ipport
+#define HTYPE hash_ipport
-static bool
-hash_ipport_same_set(const struct ip_set *a, const struct ip_set *b);
-
-#define hash_ipport4_same_set hash_ipport_same_set
-#define hash_ipport6_same_set hash_ipport_same_set
+/* IPv4 variant */
-/* The type variant functions: IPv4 */
-
-/* Member elements without timeout */
+/* Member elements */
struct hash_ipport4_elem {
__be32 ip;
__be16 port;
@@ -52,14 +48,7 @@ struct hash_ipport4_elem {
u8 padding;
};
-/* Member elements with timeout support */
-struct hash_ipport4_telem {
- __be32 ip;
- __be16 port;
- u8 proto;
- u8 padding;
- unsigned long timeout;
-};
+/* Common functions */
static inline bool
hash_ipport4_data_equal(const struct hash_ipport4_elem *ip1,
@@ -71,27 +60,6 @@ hash_ipport4_data_equal(const struct hash_ipport4_elem *ip1,
ip1->proto == ip2->proto;
}
-static inline bool
-hash_ipport4_data_isnull(const struct hash_ipport4_elem *elem)
-{
- return elem->proto == 0;
-}
-
-static inline void
-hash_ipport4_data_copy(struct hash_ipport4_elem *dst,
- const struct hash_ipport4_elem *src)
-{
- dst->ip = src->ip;
- dst->port = src->port;
- dst->proto = src->proto;
-}
-
-static inline void
-hash_ipport4_data_zero_out(struct hash_ipport4_elem *elem)
-{
- elem->proto = 0;
-}
-
static bool
hash_ipport4_data_list(struct sk_buff *skb,
const struct hash_ipport4_elem *data)
@@ -106,111 +74,90 @@ nla_put_failure:
return 1;
}
-static bool
-hash_ipport4_data_tlist(struct sk_buff *skb,
- const struct hash_ipport4_elem *data)
-{
- const struct hash_ipport4_telem *tdata =
- (const struct hash_ipport4_telem *)data;
-
- if (nla_put_ipaddr4(skb, IPSET_ATTR_IP, tdata->ip) ||
- nla_put_net16(skb, IPSET_ATTR_PORT, tdata->port) ||
- nla_put_u8(skb, IPSET_ATTR_PROTO, data->proto) ||
- nla_put_net32(skb, IPSET_ATTR_TIMEOUT,
- htonl(ip_set_timeout_get(tdata->timeout))))
- goto nla_put_failure;
- return 0;
-
-nla_put_failure:
- return 1;
-}
-
-#define PF 4
-#define HOST_MASK 32
-#include <linux/netfilter/ipset/ip_set_ahash.h>
-
static inline void
-hash_ipport4_data_next(struct ip_set_hash *h,
+hash_ipport4_data_next(struct hash_ipport4_elem *next,
const struct hash_ipport4_elem *d)
{
- h->next.ip = d->ip;
- h->next.port = d->port;
+ next->ip = d->ip;
+ next->port = d->port;
}
+#define MTYPE hash_ipport4
+#define PF 4
+#define HOST_MASK 32
+#define HKEY_DATALEN sizeof(struct hash_ipport4_elem)
+#include "ip_set_hash_gen.h"
+
static int
hash_ipport4_kadt(struct ip_set *set, const struct sk_buff *skb,
const struct xt_action_param *par,
- enum ipset_adt adt, const struct ip_set_adt_opt *opt)
+ enum ipset_adt adt, struct ip_set_adt_opt *opt)
{
- const struct ip_set_hash *h = set->data;
ipset_adtfn adtfn = set->variant->adt[adt];
- struct hash_ipport4_elem data = { };
+ struct hash_ipport4_elem e = { };
+ struct ip_set_ext ext = IP_SET_INIT_KEXT(skb, opt, set);
if (!ip_set_get_ip4_port(skb, opt->flags & IPSET_DIM_TWO_SRC,
- &data.port, &data.proto))
+ &e.port, &e.proto))
return -EINVAL;
- ip4addrptr(skb, opt->flags & IPSET_DIM_ONE_SRC, &data.ip);
-
- return adtfn(set, &data, opt_timeout(opt, h), opt->cmdflags);
+ ip4addrptr(skb, opt->flags & IPSET_DIM_ONE_SRC, &e.ip);
+ return adtfn(set, &e, &ext, &opt->ext, opt->cmdflags);
}
static int
hash_ipport4_uadt(struct ip_set *set, struct nlattr *tb[],
enum ipset_adt adt, u32 *lineno, u32 flags, bool retried)
{
- const struct ip_set_hash *h = set->data;
+ const struct hash_ipport *h = set->data;
ipset_adtfn adtfn = set->variant->adt[adt];
- struct hash_ipport4_elem data = { };
- u32 ip, ip_to, p = 0, port, port_to;
- u32 timeout = h->timeout;
+ struct hash_ipport4_elem e = { };
+ struct ip_set_ext ext = IP_SET_INIT_UEXT(set);
+ u32 ip, ip_to = 0, p = 0, port, port_to;
bool with_ports = false;
int ret;
if (unlikely(!tb[IPSET_ATTR_IP] ||
!ip_set_attr_netorder(tb, IPSET_ATTR_PORT) ||
!ip_set_optattr_netorder(tb, IPSET_ATTR_PORT_TO) ||
- !ip_set_optattr_netorder(tb, IPSET_ATTR_TIMEOUT)))
+ !ip_set_optattr_netorder(tb, IPSET_ATTR_TIMEOUT) ||
+ !ip_set_optattr_netorder(tb, IPSET_ATTR_PACKETS) ||
+ !ip_set_optattr_netorder(tb, IPSET_ATTR_BYTES)))
return -IPSET_ERR_PROTOCOL;
if (tb[IPSET_ATTR_LINENO])
*lineno = nla_get_u32(tb[IPSET_ATTR_LINENO]);
- ret = ip_set_get_ipaddr4(tb[IPSET_ATTR_IP], &data.ip);
+ ret = ip_set_get_ipaddr4(tb[IPSET_ATTR_IP], &e.ip) ||
+ ip_set_get_extensions(set, tb, &ext);
if (ret)
return ret;
if (tb[IPSET_ATTR_PORT])
- data.port = nla_get_be16(tb[IPSET_ATTR_PORT]);
+ e.port = nla_get_be16(tb[IPSET_ATTR_PORT]);
else
return -IPSET_ERR_PROTOCOL;
if (tb[IPSET_ATTR_PROTO]) {
- data.proto = nla_get_u8(tb[IPSET_ATTR_PROTO]);
- with_ports = ip_set_proto_with_ports(data.proto);
+ e.proto = nla_get_u8(tb[IPSET_ATTR_PROTO]);
+ with_ports = ip_set_proto_with_ports(e.proto);
- if (data.proto == 0)
+ if (e.proto == 0)
return -IPSET_ERR_INVALID_PROTO;
} else
return -IPSET_ERR_MISSING_PROTO;
- if (!(with_ports || data.proto == IPPROTO_ICMP))
- data.port = 0;
-
- if (tb[IPSET_ATTR_TIMEOUT]) {
- if (!with_timeout(h->timeout))
- return -IPSET_ERR_TIMEOUT;
- timeout = ip_set_timeout_uget(tb[IPSET_ATTR_TIMEOUT]);
- }
+ if (!(with_ports || e.proto == IPPROTO_ICMP))
+ e.port = 0;
if (adt == IPSET_TEST ||
!(tb[IPSET_ATTR_IP_TO] || tb[IPSET_ATTR_CIDR] ||
tb[IPSET_ATTR_PORT_TO])) {
- ret = adtfn(set, &data, timeout, flags);
+ ret = adtfn(set, &e, &ext, &ext, flags);
return ip_set_eexist(ret, flags) ? 0 : ret;
}
- ip_to = ip = ntohl(data.ip);
+ ip_to = ip = ntohl(e.ip);
if (tb[IPSET_ATTR_IP_TO]) {
ret = ip_set_get_hostipaddr4(tb[IPSET_ATTR_IP_TO], &ip_to);
if (ret)
@@ -225,7 +172,7 @@ hash_ipport4_uadt(struct ip_set *set, struct nlattr *tb[],
ip_set_mask_from_to(ip, ip_to, cidr);
}
- port_to = port = ntohs(data.port);
+ port_to = port = ntohs(e.port);
if (with_ports && tb[IPSET_ATTR_PORT_TO]) {
port_to = ip_set_get_h16(tb[IPSET_ATTR_PORT_TO]);
if (port > port_to)
@@ -238,9 +185,9 @@ hash_ipport4_uadt(struct ip_set *set, struct nlattr *tb[],
p = retried && ip == ntohl(h->next.ip) ? ntohs(h->next.port)
: port;
for (; p <= port_to; p++) {
- data.ip = htonl(ip);
- data.port = htons(p);
- ret = adtfn(set, &data, timeout, flags);
+ e.ip = htonl(ip);
+ e.port = htons(p);
+ ret = adtfn(set, &e, &ext, &ext, flags);
if (ret && !ip_set_eexist(ret, flags))
return ret;
@@ -251,18 +198,7 @@ hash_ipport4_uadt(struct ip_set *set, struct nlattr *tb[],
return ret;
}
-static bool
-hash_ipport_same_set(const struct ip_set *a, const struct ip_set *b)
-{
- const struct ip_set_hash *x = a->data;
- const struct ip_set_hash *y = b->data;
-
- /* Resizing changes htable_bits, so we ignore it */
- return x->maxelem == y->maxelem &&
- x->timeout == y->timeout;
-}
-
-/* The type variant functions: IPv6 */
+/* IPv6 variant */
struct hash_ipport6_elem {
union nf_inet_addr ip;
@@ -271,43 +207,18 @@ struct hash_ipport6_elem {
u8 padding;
};
-struct hash_ipport6_telem {
- union nf_inet_addr ip;
- __be16 port;
- u8 proto;
- u8 padding;
- unsigned long timeout;
-};
+/* Common functions */
static inline bool
hash_ipport6_data_equal(const struct hash_ipport6_elem *ip1,
const struct hash_ipport6_elem *ip2,
u32 *multi)
{
- return ipv6_addr_cmp(&ip1->ip.in6, &ip2->ip.in6) == 0 &&
+ return ipv6_addr_equal(&ip1->ip.in6, &ip2->ip.in6) &&
ip1->port == ip2->port &&
ip1->proto == ip2->proto;
}
-static inline bool
-hash_ipport6_data_isnull(const struct hash_ipport6_elem *elem)
-{
- return elem->proto == 0;
-}
-
-static inline void
-hash_ipport6_data_copy(struct hash_ipport6_elem *dst,
- const struct hash_ipport6_elem *src)
-{
- memcpy(dst, src, sizeof(*dst));
-}
-
-static inline void
-hash_ipport6_data_zero_out(struct hash_ipport6_elem *elem)
-{
- elem->proto = 0;
-}
-
static bool
hash_ipport6_data_list(struct sk_buff *skb,
const struct hash_ipport6_elem *data)
@@ -322,66 +233,51 @@ nla_put_failure:
return 1;
}
-static bool
-hash_ipport6_data_tlist(struct sk_buff *skb,
- const struct hash_ipport6_elem *data)
+static inline void
+hash_ipport6_data_next(struct hash_ipport4_elem *next,
+ const struct hash_ipport6_elem *d)
{
- const struct hash_ipport6_telem *e =
- (const struct hash_ipport6_telem *)data;
-
- if (nla_put_ipaddr6(skb, IPSET_ATTR_IP, &e->ip.in6) ||
- nla_put_net16(skb, IPSET_ATTR_PORT, data->port) ||
- nla_put_u8(skb, IPSET_ATTR_PROTO, data->proto) ||
- nla_put_net32(skb, IPSET_ATTR_TIMEOUT,
- htonl(ip_set_timeout_get(e->timeout))))
- goto nla_put_failure;
- return 0;
-
-nla_put_failure:
- return 1;
+ next->port = d->port;
}
+#undef MTYPE
#undef PF
#undef HOST_MASK
+#undef HKEY_DATALEN
+#define MTYPE hash_ipport6
#define PF 6
#define HOST_MASK 128
-#include <linux/netfilter/ipset/ip_set_ahash.h>
-
-static inline void
-hash_ipport6_data_next(struct ip_set_hash *h,
- const struct hash_ipport6_elem *d)
-{
- h->next.port = d->port;
-}
+#define HKEY_DATALEN sizeof(struct hash_ipport6_elem)
+#define IP_SET_EMIT_CREATE
+#include "ip_set_hash_gen.h"
static int
hash_ipport6_kadt(struct ip_set *set, const struct sk_buff *skb,
const struct xt_action_param *par,
- enum ipset_adt adt, const struct ip_set_adt_opt *opt)
+ enum ipset_adt adt, struct ip_set_adt_opt *opt)
{
- const struct ip_set_hash *h = set->data;
ipset_adtfn adtfn = set->variant->adt[adt];
- struct hash_ipport6_elem data = { };
+ struct hash_ipport6_elem e = { };
+ struct ip_set_ext ext = IP_SET_INIT_KEXT(skb, opt, set);
if (!ip_set_get_ip6_port(skb, opt->flags & IPSET_DIM_TWO_SRC,
- &data.port, &data.proto))
+ &e.port, &e.proto))
return -EINVAL;
- ip6addrptr(skb, opt->flags & IPSET_DIM_ONE_SRC, &data.ip.in6);
-
- return adtfn(set, &data, opt_timeout(opt, h), opt->cmdflags);
+ ip6addrptr(skb, opt->flags & IPSET_DIM_ONE_SRC, &e.ip.in6);
+ return adtfn(set, &e, &ext, &opt->ext, opt->cmdflags);
}
static int
hash_ipport6_uadt(struct ip_set *set, struct nlattr *tb[],
enum ipset_adt adt, u32 *lineno, u32 flags, bool retried)
{
- const struct ip_set_hash *h = set->data;
+ const struct hash_ipport *h = set->data;
ipset_adtfn adtfn = set->variant->adt[adt];
- struct hash_ipport6_elem data = { };
+ struct hash_ipport6_elem e = { };
+ struct ip_set_ext ext = IP_SET_INIT_UEXT(set);
u32 port, port_to;
- u32 timeout = h->timeout;
bool with_ports = false;
int ret;
@@ -389,6 +285,8 @@ hash_ipport6_uadt(struct ip_set *set, struct nlattr *tb[],
!ip_set_attr_netorder(tb, IPSET_ATTR_PORT) ||
!ip_set_optattr_netorder(tb, IPSET_ATTR_PORT_TO) ||
!ip_set_optattr_netorder(tb, IPSET_ATTR_TIMEOUT) ||
+ !ip_set_optattr_netorder(tb, IPSET_ATTR_PACKETS) ||
+ !ip_set_optattr_netorder(tb, IPSET_ATTR_BYTES) ||
tb[IPSET_ATTR_IP_TO] ||
tb[IPSET_ATTR_CIDR]))
return -IPSET_ERR_PROTOCOL;
@@ -396,39 +294,34 @@ hash_ipport6_uadt(struct ip_set *set, struct nlattr *tb[],
if (tb[IPSET_ATTR_LINENO])
*lineno = nla_get_u32(tb[IPSET_ATTR_LINENO]);
- ret = ip_set_get_ipaddr6(tb[IPSET_ATTR_IP], &data.ip);
+ ret = ip_set_get_ipaddr6(tb[IPSET_ATTR_IP], &e.ip) ||
+ ip_set_get_extensions(set, tb, &ext);
if (ret)
return ret;
if (tb[IPSET_ATTR_PORT])
- data.port = nla_get_be16(tb[IPSET_ATTR_PORT]);
+ e.port = nla_get_be16(tb[IPSET_ATTR_PORT]);
else
return -IPSET_ERR_PROTOCOL;
if (tb[IPSET_ATTR_PROTO]) {
- data.proto = nla_get_u8(tb[IPSET_ATTR_PROTO]);
- with_ports = ip_set_proto_with_ports(data.proto);
+ e.proto = nla_get_u8(tb[IPSET_ATTR_PROTO]);
+ with_ports = ip_set_proto_with_ports(e.proto);
- if (data.proto == 0)
+ if (e.proto == 0)
return -IPSET_ERR_INVALID_PROTO;
} else
return -IPSET_ERR_MISSING_PROTO;
- if (!(with_ports || data.proto == IPPROTO_ICMPV6))
- data.port = 0;
-
- if (tb[IPSET_ATTR_TIMEOUT]) {
- if (!with_timeout(h->timeout))
- return -IPSET_ERR_TIMEOUT;
- timeout = ip_set_timeout_uget(tb[IPSET_ATTR_TIMEOUT]);
- }
+ if (!(with_ports || e.proto == IPPROTO_ICMPV6))
+ e.port = 0;
if (adt == IPSET_TEST || !with_ports || !tb[IPSET_ATTR_PORT_TO]) {
- ret = adtfn(set, &data, timeout, flags);
+ ret = adtfn(set, &e, &ext, &ext, flags);
return ip_set_eexist(ret, flags) ? 0 : ret;
}
- port = ntohs(data.port);
+ port = ntohs(e.port);
port_to = ip_set_get_h16(tb[IPSET_ATTR_PORT_TO]);
if (port > port_to)
swap(port, port_to);
@@ -436,8 +329,8 @@ hash_ipport6_uadt(struct ip_set *set, struct nlattr *tb[],
if (retried)
port = ntohs(h->next.port);
for (; port <= port_to; port++) {
- data.port = htons(port);
- ret = adtfn(set, &data, timeout, flags);
+ e.port = htons(port);
+ ret = adtfn(set, &e, &ext, &ext, flags);
if (ret && !ip_set_eexist(ret, flags))
return ret;
@@ -447,86 +340,14 @@ hash_ipport6_uadt(struct ip_set *set, struct nlattr *tb[],
return ret;
}
-/* Create hash:ip type of sets */
-
-static int
-hash_ipport_create(struct ip_set *set, struct nlattr *tb[], u32 flags)
-{
- struct ip_set_hash *h;
- u32 hashsize = IPSET_DEFAULT_HASHSIZE, maxelem = IPSET_DEFAULT_MAXELEM;
- u8 hbits;
- size_t hsize;
-
- if (!(set->family == NFPROTO_IPV4 || set->family == NFPROTO_IPV6))
- return -IPSET_ERR_INVALID_FAMILY;
-
- if (unlikely(!ip_set_optattr_netorder(tb, IPSET_ATTR_HASHSIZE) ||
- !ip_set_optattr_netorder(tb, IPSET_ATTR_MAXELEM) ||
- !ip_set_optattr_netorder(tb, IPSET_ATTR_TIMEOUT)))
- return -IPSET_ERR_PROTOCOL;
-
- if (tb[IPSET_ATTR_HASHSIZE]) {
- hashsize = ip_set_get_h32(tb[IPSET_ATTR_HASHSIZE]);
- if (hashsize < IPSET_MIMINAL_HASHSIZE)
- hashsize = IPSET_MIMINAL_HASHSIZE;
- }
-
- if (tb[IPSET_ATTR_MAXELEM])
- maxelem = ip_set_get_h32(tb[IPSET_ATTR_MAXELEM]);
-
- h = kzalloc(sizeof(*h), GFP_KERNEL);
- if (!h)
- return -ENOMEM;
-
- h->maxelem = maxelem;
- get_random_bytes(&h->initval, sizeof(h->initval));
- h->timeout = IPSET_NO_TIMEOUT;
-
- hbits = htable_bits(hashsize);
- hsize = htable_size(hbits);
- if (hsize == 0) {
- kfree(h);
- return -ENOMEM;
- }
- h->table = ip_set_alloc(hsize);
- if (!h->table) {
- kfree(h);
- return -ENOMEM;
- }
- h->table->htable_bits = hbits;
-
- set->data = h;
-
- if (tb[IPSET_ATTR_TIMEOUT]) {
- h->timeout = ip_set_timeout_uget(tb[IPSET_ATTR_TIMEOUT]);
-
- set->variant = set->family == NFPROTO_IPV4
- ? &hash_ipport4_tvariant : &hash_ipport6_tvariant;
-
- if (set->family == NFPROTO_IPV4)
- hash_ipport4_gc_init(set);
- else
- hash_ipport6_gc_init(set);
- } else {
- set->variant = set->family == NFPROTO_IPV4
- ? &hash_ipport4_variant : &hash_ipport6_variant;
- }
-
- pr_debug("create %s hashsize %u (%u) maxelem %u: %p(%p)\n",
- set->name, jhash_size(h->table->htable_bits),
- h->table->htable_bits, h->maxelem, set->data, h->table);
-
- return 0;
-}
-
static struct ip_set_type hash_ipport_type __read_mostly = {
.name = "hash:ip,port",
.protocol = IPSET_PROTOCOL,
.features = IPSET_TYPE_IP | IPSET_TYPE_PORT,
.dimension = IPSET_DIM_TWO,
.family = NFPROTO_UNSPEC,
- .revision_min = REVISION_MIN,
- .revision_max = REVISION_MAX,
+ .revision_min = IPSET_TYPE_REV_MIN,
+ .revision_max = IPSET_TYPE_REV_MAX,
.create = hash_ipport_create,
.create_policy = {
[IPSET_ATTR_HASHSIZE] = { .type = NLA_U32 },
@@ -535,6 +356,7 @@ static struct ip_set_type hash_ipport_type __read_mostly = {
[IPSET_ATTR_RESIZE] = { .type = NLA_U8 },
[IPSET_ATTR_PROTO] = { .type = NLA_U8 },
[IPSET_ATTR_TIMEOUT] = { .type = NLA_U32 },
+ [IPSET_ATTR_CADT_FLAGS] = { .type = NLA_U32 },
},
.adt_policy = {
[IPSET_ATTR_IP] = { .type = NLA_NESTED },
@@ -545,6 +367,9 @@ static struct ip_set_type hash_ipport_type __read_mostly = {
[IPSET_ATTR_PROTO] = { .type = NLA_U8 },
[IPSET_ATTR_TIMEOUT] = { .type = NLA_U32 },
[IPSET_ATTR_LINENO] = { .type = NLA_U32 },
+ [IPSET_ATTR_BYTES] = { .type = NLA_U64 },
+ [IPSET_ATTR_PACKETS] = { .type = NLA_U64 },
+ [IPSET_ATTR_COMMENT] = { .type = NLA_NUL_STRING },
},
.me = THIS_MODULE,
};
diff --git a/net/netfilter/ipset/ip_set_hash_ipportip.c b/net/netfilter/ipset/ip_set_hash_ipportip.c
index 6a21271c8d5..672655ffd57 100644
--- a/net/netfilter/ipset/ip_set_hash_ipportip.c
+++ b/net/netfilter/ipset/ip_set_hash_ipportip.c
@@ -1,4 +1,4 @@
-/* Copyright (C) 2003-2011 Jozsef Kadlecsik <kadlec@blackhole.kfki.hu>
+/* Copyright (C) 2003-2013 Jozsef Kadlecsik <kadlec@blackhole.kfki.hu>
*
* This program is free software; you can redistribute it and/or modify
* it under the terms of the GNU General Public License version 2 as
@@ -21,30 +21,26 @@
#include <linux/netfilter.h>
#include <linux/netfilter/ipset/pfxlen.h>
#include <linux/netfilter/ipset/ip_set.h>
-#include <linux/netfilter/ipset/ip_set_timeout.h>
#include <linux/netfilter/ipset/ip_set_getport.h>
#include <linux/netfilter/ipset/ip_set_hash.h>
-#define REVISION_MIN 0
-#define REVISION_MAX 1 /* SCTP and UDPLITE support added */
+#define IPSET_TYPE_REV_MIN 0
+/* 1 SCTP and UDPLITE support added */
+/* 2 Counters support added */
+/* 3 Comments support added */
+#define IPSET_TYPE_REV_MAX 4 /* Forceadd support added */
MODULE_LICENSE("GPL");
MODULE_AUTHOR("Jozsef Kadlecsik <kadlec@blackhole.kfki.hu>");
-IP_SET_MODULE_DESC("hash:ip,port,ip", REVISION_MIN, REVISION_MAX);
+IP_SET_MODULE_DESC("hash:ip,port,ip", IPSET_TYPE_REV_MIN, IPSET_TYPE_REV_MAX);
MODULE_ALIAS("ip_set_hash:ip,port,ip");
/* Type specific function prefix */
-#define TYPE hash_ipportip
+#define HTYPE hash_ipportip
-static bool
-hash_ipportip_same_set(const struct ip_set *a, const struct ip_set *b);
-
-#define hash_ipportip4_same_set hash_ipportip_same_set
-#define hash_ipportip6_same_set hash_ipportip_same_set
+/* IPv4 variant */
-/* The type variant functions: IPv4 */
-
-/* Member elements without timeout */
+/* Member elements */
struct hash_ipportip4_elem {
__be32 ip;
__be32 ip2;
@@ -53,16 +49,6 @@ struct hash_ipportip4_elem {
u8 padding;
};
-/* Member elements with timeout support */
-struct hash_ipportip4_telem {
- __be32 ip;
- __be32 ip2;
- __be16 port;
- u8 proto;
- u8 padding;
- unsigned long timeout;
-};
-
static inline bool
hash_ipportip4_data_equal(const struct hash_ipportip4_elem *ip1,
const struct hash_ipportip4_elem *ip2,
@@ -74,25 +60,6 @@ hash_ipportip4_data_equal(const struct hash_ipportip4_elem *ip1,
ip1->proto == ip2->proto;
}
-static inline bool
-hash_ipportip4_data_isnull(const struct hash_ipportip4_elem *elem)
-{
- return elem->proto == 0;
-}
-
-static inline void
-hash_ipportip4_data_copy(struct hash_ipportip4_elem *dst,
- const struct hash_ipportip4_elem *src)
-{
- memcpy(dst, src, sizeof(*dst));
-}
-
-static inline void
-hash_ipportip4_data_zero_out(struct hash_ipportip4_elem *elem)
-{
- elem->proto = 0;
-}
-
static bool
hash_ipportip4_data_list(struct sk_buff *skb,
const struct hash_ipportip4_elem *data)
@@ -108,117 +75,95 @@ nla_put_failure:
return 1;
}
-static bool
-hash_ipportip4_data_tlist(struct sk_buff *skb,
- const struct hash_ipportip4_elem *data)
+static inline void
+hash_ipportip4_data_next(struct hash_ipportip4_elem *next,
+ const struct hash_ipportip4_elem *d)
{
- const struct hash_ipportip4_telem *tdata =
- (const struct hash_ipportip4_telem *)data;
-
- if (nla_put_ipaddr4(skb, IPSET_ATTR_IP, tdata->ip) ||
- nla_put_ipaddr4(skb, IPSET_ATTR_IP2, tdata->ip2) ||
- nla_put_net16(skb, IPSET_ATTR_PORT, tdata->port) ||
- nla_put_u8(skb, IPSET_ATTR_PROTO, data->proto) ||
- nla_put_net32(skb, IPSET_ATTR_TIMEOUT,
- htonl(ip_set_timeout_get(tdata->timeout))))
- goto nla_put_failure;
- return 0;
-
-nla_put_failure:
- return 1;
+ next->ip = d->ip;
+ next->port = d->port;
}
+/* Common functions */
+#define MTYPE hash_ipportip4
#define PF 4
#define HOST_MASK 32
-#include <linux/netfilter/ipset/ip_set_ahash.h>
-
-static inline void
-hash_ipportip4_data_next(struct ip_set_hash *h,
- const struct hash_ipportip4_elem *d)
-{
- h->next.ip = d->ip;
- h->next.port = d->port;
-}
+#include "ip_set_hash_gen.h"
static int
hash_ipportip4_kadt(struct ip_set *set, const struct sk_buff *skb,
const struct xt_action_param *par,
- enum ipset_adt adt, const struct ip_set_adt_opt *opt)
+ enum ipset_adt adt, struct ip_set_adt_opt *opt)
{
- const struct ip_set_hash *h = set->data;
ipset_adtfn adtfn = set->variant->adt[adt];
- struct hash_ipportip4_elem data = { };
+ struct hash_ipportip4_elem e = { };
+ struct ip_set_ext ext = IP_SET_INIT_KEXT(skb, opt, set);
if (!ip_set_get_ip4_port(skb, opt->flags & IPSET_DIM_TWO_SRC,
- &data.port, &data.proto))
+ &e.port, &e.proto))
return -EINVAL;
- ip4addrptr(skb, opt->flags & IPSET_DIM_ONE_SRC, &data.ip);
- ip4addrptr(skb, opt->flags & IPSET_DIM_THREE_SRC, &data.ip2);
-
- return adtfn(set, &data, opt_timeout(opt, h), opt->cmdflags);
+ ip4addrptr(skb, opt->flags & IPSET_DIM_ONE_SRC, &e.ip);
+ ip4addrptr(skb, opt->flags & IPSET_DIM_THREE_SRC, &e.ip2);
+ return adtfn(set, &e, &ext, &opt->ext, opt->cmdflags);
}
static int
hash_ipportip4_uadt(struct ip_set *set, struct nlattr *tb[],
enum ipset_adt adt, u32 *lineno, u32 flags, bool retried)
{
- const struct ip_set_hash *h = set->data;
+ const struct hash_ipportip *h = set->data;
ipset_adtfn adtfn = set->variant->adt[adt];
- struct hash_ipportip4_elem data = { };
- u32 ip, ip_to, p = 0, port, port_to;
- u32 timeout = h->timeout;
+ struct hash_ipportip4_elem e = { };
+ struct ip_set_ext ext = IP_SET_INIT_UEXT(set);
+ u32 ip, ip_to = 0, p = 0, port, port_to;
bool with_ports = false;
int ret;
if (unlikely(!tb[IPSET_ATTR_IP] || !tb[IPSET_ATTR_IP2] ||
!ip_set_attr_netorder(tb, IPSET_ATTR_PORT) ||
!ip_set_optattr_netorder(tb, IPSET_ATTR_PORT_TO) ||
- !ip_set_optattr_netorder(tb, IPSET_ATTR_TIMEOUT)))
+ !ip_set_optattr_netorder(tb, IPSET_ATTR_TIMEOUT) ||
+ !ip_set_optattr_netorder(tb, IPSET_ATTR_PACKETS) ||
+ !ip_set_optattr_netorder(tb, IPSET_ATTR_BYTES)))
return -IPSET_ERR_PROTOCOL;
if (tb[IPSET_ATTR_LINENO])
*lineno = nla_get_u32(tb[IPSET_ATTR_LINENO]);
- ret = ip_set_get_ipaddr4(tb[IPSET_ATTR_IP], &data.ip);
+ ret = ip_set_get_ipaddr4(tb[IPSET_ATTR_IP], &e.ip) ||
+ ip_set_get_extensions(set, tb, &ext);
if (ret)
return ret;
- ret = ip_set_get_ipaddr4(tb[IPSET_ATTR_IP2], &data.ip2);
+ ret = ip_set_get_ipaddr4(tb[IPSET_ATTR_IP2], &e.ip2);
if (ret)
return ret;
if (tb[IPSET_ATTR_PORT])
- data.port = nla_get_be16(tb[IPSET_ATTR_PORT]);
+ e.port = nla_get_be16(tb[IPSET_ATTR_PORT]);
else
return -IPSET_ERR_PROTOCOL;
if (tb[IPSET_ATTR_PROTO]) {
- data.proto = nla_get_u8(tb[IPSET_ATTR_PROTO]);
- with_ports = ip_set_proto_with_ports(data.proto);
+ e.proto = nla_get_u8(tb[IPSET_ATTR_PROTO]);
+ with_ports = ip_set_proto_with_ports(e.proto);
- if (data.proto == 0)
+ if (e.proto == 0)
return -IPSET_ERR_INVALID_PROTO;
} else
return -IPSET_ERR_MISSING_PROTO;
- if (!(with_ports || data.proto == IPPROTO_ICMP))
- data.port = 0;
-
- if (tb[IPSET_ATTR_TIMEOUT]) {
- if (!with_timeout(h->timeout))
- return -IPSET_ERR_TIMEOUT;
- timeout = ip_set_timeout_uget(tb[IPSET_ATTR_TIMEOUT]);
- }
+ if (!(with_ports || e.proto == IPPROTO_ICMP))
+ e.port = 0;
if (adt == IPSET_TEST ||
!(tb[IPSET_ATTR_IP_TO] || tb[IPSET_ATTR_CIDR] ||
tb[IPSET_ATTR_PORT_TO])) {
- ret = adtfn(set, &data, timeout, flags);
+ ret = adtfn(set, &e, &ext, &ext, flags);
return ip_set_eexist(ret, flags) ? 0 : ret;
}
- ip_to = ip = ntohl(data.ip);
+ ip_to = ip = ntohl(e.ip);
if (tb[IPSET_ATTR_IP_TO]) {
ret = ip_set_get_hostipaddr4(tb[IPSET_ATTR_IP_TO], &ip_to);
if (ret)
@@ -233,7 +178,7 @@ hash_ipportip4_uadt(struct ip_set *set, struct nlattr *tb[],
ip_set_mask_from_to(ip, ip_to, cidr);
}
- port_to = port = ntohs(data.port);
+ port_to = port = ntohs(e.port);
if (with_ports && tb[IPSET_ATTR_PORT_TO]) {
port_to = ip_set_get_h16(tb[IPSET_ATTR_PORT_TO]);
if (port > port_to)
@@ -246,9 +191,9 @@ hash_ipportip4_uadt(struct ip_set *set, struct nlattr *tb[],
p = retried && ip == ntohl(h->next.ip) ? ntohs(h->next.port)
: port;
for (; p <= port_to; p++) {
- data.ip = htonl(ip);
- data.port = htons(p);
- ret = adtfn(set, &data, timeout, flags);
+ e.ip = htonl(ip);
+ e.port = htons(p);
+ ret = adtfn(set, &e, &ext, &ext, flags);
if (ret && !ip_set_eexist(ret, flags))
return ret;
@@ -259,18 +204,7 @@ hash_ipportip4_uadt(struct ip_set *set, struct nlattr *tb[],
return ret;
}
-static bool
-hash_ipportip_same_set(const struct ip_set *a, const struct ip_set *b)
-{
- const struct ip_set_hash *x = a->data;
- const struct ip_set_hash *y = b->data;
-
- /* Resizing changes htable_bits, so we ignore it */
- return x->maxelem == y->maxelem &&
- x->timeout == y->timeout;
-}
-
-/* The type variant functions: IPv6 */
+/* IPv6 variant */
struct hash_ipportip6_elem {
union nf_inet_addr ip;
@@ -280,45 +214,19 @@ struct hash_ipportip6_elem {
u8 padding;
};
-struct hash_ipportip6_telem {
- union nf_inet_addr ip;
- union nf_inet_addr ip2;
- __be16 port;
- u8 proto;
- u8 padding;
- unsigned long timeout;
-};
+/* Common functions */
static inline bool
hash_ipportip6_data_equal(const struct hash_ipportip6_elem *ip1,
const struct hash_ipportip6_elem *ip2,
u32 *multi)
{
- return ipv6_addr_cmp(&ip1->ip.in6, &ip2->ip.in6) == 0 &&
- ipv6_addr_cmp(&ip1->ip2.in6, &ip2->ip2.in6) == 0 &&
+ return ipv6_addr_equal(&ip1->ip.in6, &ip2->ip.in6) &&
+ ipv6_addr_equal(&ip1->ip2.in6, &ip2->ip2.in6) &&
ip1->port == ip2->port &&
ip1->proto == ip2->proto;
}
-static inline bool
-hash_ipportip6_data_isnull(const struct hash_ipportip6_elem *elem)
-{
- return elem->proto == 0;
-}
-
-static inline void
-hash_ipportip6_data_copy(struct hash_ipportip6_elem *dst,
- const struct hash_ipportip6_elem *src)
-{
- memcpy(dst, src, sizeof(*dst));
-}
-
-static inline void
-hash_ipportip6_data_zero_out(struct hash_ipportip6_elem *elem)
-{
- elem->proto = 0;
-}
-
static bool
hash_ipportip6_data_list(struct sk_buff *skb,
const struct hash_ipportip6_elem *data)
@@ -334,68 +242,50 @@ nla_put_failure:
return 1;
}
-static bool
-hash_ipportip6_data_tlist(struct sk_buff *skb,
- const struct hash_ipportip6_elem *data)
+static inline void
+hash_ipportip6_data_next(struct hash_ipportip4_elem *next,
+ const struct hash_ipportip6_elem *d)
{
- const struct hash_ipportip6_telem *e =
- (const struct hash_ipportip6_telem *)data;
-
- if (nla_put_ipaddr6(skb, IPSET_ATTR_IP, &e->ip.in6) ||
- nla_put_ipaddr6(skb, IPSET_ATTR_IP2, &data->ip2.in6) ||
- nla_put_net16(skb, IPSET_ATTR_PORT, data->port) ||
- nla_put_u8(skb, IPSET_ATTR_PROTO, data->proto) ||
- nla_put_net32(skb, IPSET_ATTR_TIMEOUT,
- htonl(ip_set_timeout_get(e->timeout))))
- goto nla_put_failure;
- return 0;
-
-nla_put_failure:
- return 1;
+ next->port = d->port;
}
+#undef MTYPE
#undef PF
#undef HOST_MASK
+#define MTYPE hash_ipportip6
#define PF 6
#define HOST_MASK 128
-#include <linux/netfilter/ipset/ip_set_ahash.h>
-
-static inline void
-hash_ipportip6_data_next(struct ip_set_hash *h,
- const struct hash_ipportip6_elem *d)
-{
- h->next.port = d->port;
-}
+#define IP_SET_EMIT_CREATE
+#include "ip_set_hash_gen.h"
static int
hash_ipportip6_kadt(struct ip_set *set, const struct sk_buff *skb,
const struct xt_action_param *par,
- enum ipset_adt adt, const struct ip_set_adt_opt *opt)
+ enum ipset_adt adt, struct ip_set_adt_opt *opt)
{
- const struct ip_set_hash *h = set->data;
ipset_adtfn adtfn = set->variant->adt[adt];
- struct hash_ipportip6_elem data = { };
+ struct hash_ipportip6_elem e = { };
+ struct ip_set_ext ext = IP_SET_INIT_KEXT(skb, opt, set);
if (!ip_set_get_ip6_port(skb, opt->flags & IPSET_DIM_TWO_SRC,
- &data.port, &data.proto))
+ &e.port, &e.proto))
return -EINVAL;
- ip6addrptr(skb, opt->flags & IPSET_DIM_ONE_SRC, &data.ip.in6);
- ip6addrptr(skb, opt->flags & IPSET_DIM_THREE_SRC, &data.ip2.in6);
-
- return adtfn(set, &data, opt_timeout(opt, h), opt->cmdflags);
+ ip6addrptr(skb, opt->flags & IPSET_DIM_ONE_SRC, &e.ip.in6);
+ ip6addrptr(skb, opt->flags & IPSET_DIM_THREE_SRC, &e.ip2.in6);
+ return adtfn(set, &e, &ext, &opt->ext, opt->cmdflags);
}
static int
hash_ipportip6_uadt(struct ip_set *set, struct nlattr *tb[],
enum ipset_adt adt, u32 *lineno, u32 flags, bool retried)
{
- const struct ip_set_hash *h = set->data;
+ const struct hash_ipportip *h = set->data;
ipset_adtfn adtfn = set->variant->adt[adt];
- struct hash_ipportip6_elem data = { };
+ struct hash_ipportip6_elem e = { };
+ struct ip_set_ext ext = IP_SET_INIT_UEXT(set);
u32 port, port_to;
- u32 timeout = h->timeout;
bool with_ports = false;
int ret;
@@ -403,6 +293,8 @@ hash_ipportip6_uadt(struct ip_set *set, struct nlattr *tb[],
!ip_set_attr_netorder(tb, IPSET_ATTR_PORT) ||
!ip_set_optattr_netorder(tb, IPSET_ATTR_PORT_TO) ||
!ip_set_optattr_netorder(tb, IPSET_ATTR_TIMEOUT) ||
+ !ip_set_optattr_netorder(tb, IPSET_ATTR_PACKETS) ||
+ !ip_set_optattr_netorder(tb, IPSET_ATTR_BYTES) ||
tb[IPSET_ATTR_IP_TO] ||
tb[IPSET_ATTR_CIDR]))
return -IPSET_ERR_PROTOCOL;
@@ -410,43 +302,38 @@ hash_ipportip6_uadt(struct ip_set *set, struct nlattr *tb[],
if (tb[IPSET_ATTR_LINENO])
*lineno = nla_get_u32(tb[IPSET_ATTR_LINENO]);
- ret = ip_set_get_ipaddr6(tb[IPSET_ATTR_IP], &data.ip);
+ ret = ip_set_get_ipaddr6(tb[IPSET_ATTR_IP], &e.ip) ||
+ ip_set_get_extensions(set, tb, &ext);
if (ret)
return ret;
- ret = ip_set_get_ipaddr6(tb[IPSET_ATTR_IP2], &data.ip2);
+ ret = ip_set_get_ipaddr6(tb[IPSET_ATTR_IP2], &e.ip2);
if (ret)
return ret;
if (tb[IPSET_ATTR_PORT])
- data.port = nla_get_be16(tb[IPSET_ATTR_PORT]);
+ e.port = nla_get_be16(tb[IPSET_ATTR_PORT]);
else
return -IPSET_ERR_PROTOCOL;
if (tb[IPSET_ATTR_PROTO]) {
- data.proto = nla_get_u8(tb[IPSET_ATTR_PROTO]);
- with_ports = ip_set_proto_with_ports(data.proto);
+ e.proto = nla_get_u8(tb[IPSET_ATTR_PROTO]);
+ with_ports = ip_set_proto_with_ports(e.proto);
- if (data.proto == 0)
+ if (e.proto == 0)
return -IPSET_ERR_INVALID_PROTO;
} else
return -IPSET_ERR_MISSING_PROTO;
- if (!(with_ports || data.proto == IPPROTO_ICMPV6))
- data.port = 0;
-
- if (tb[IPSET_ATTR_TIMEOUT]) {
- if (!with_timeout(h->timeout))
- return -IPSET_ERR_TIMEOUT;
- timeout = ip_set_timeout_uget(tb[IPSET_ATTR_TIMEOUT]);
- }
+ if (!(with_ports || e.proto == IPPROTO_ICMPV6))
+ e.port = 0;
if (adt == IPSET_TEST || !with_ports || !tb[IPSET_ATTR_PORT_TO]) {
- ret = adtfn(set, &data, timeout, flags);
+ ret = adtfn(set, &e, &ext, &ext, flags);
return ip_set_eexist(ret, flags) ? 0 : ret;
}
- port = ntohs(data.port);
+ port = ntohs(e.port);
port_to = ip_set_get_h16(tb[IPSET_ATTR_PORT_TO]);
if (port > port_to)
swap(port, port_to);
@@ -454,8 +341,8 @@ hash_ipportip6_uadt(struct ip_set *set, struct nlattr *tb[],
if (retried)
port = ntohs(h->next.port);
for (; port <= port_to; port++) {
- data.port = htons(port);
- ret = adtfn(set, &data, timeout, flags);
+ e.port = htons(port);
+ ret = adtfn(set, &e, &ext, &ext, flags);
if (ret && !ip_set_eexist(ret, flags))
return ret;
@@ -465,86 +352,14 @@ hash_ipportip6_uadt(struct ip_set *set, struct nlattr *tb[],
return ret;
}
-/* Create hash:ip type of sets */
-
-static int
-hash_ipportip_create(struct ip_set *set, struct nlattr *tb[], u32 flags)
-{
- struct ip_set_hash *h;
- u32 hashsize = IPSET_DEFAULT_HASHSIZE, maxelem = IPSET_DEFAULT_MAXELEM;
- u8 hbits;
- size_t hsize;
-
- if (!(set->family == NFPROTO_IPV4 || set->family == NFPROTO_IPV6))
- return -IPSET_ERR_INVALID_FAMILY;
-
- if (unlikely(!ip_set_optattr_netorder(tb, IPSET_ATTR_HASHSIZE) ||
- !ip_set_optattr_netorder(tb, IPSET_ATTR_MAXELEM) ||
- !ip_set_optattr_netorder(tb, IPSET_ATTR_TIMEOUT)))
- return -IPSET_ERR_PROTOCOL;
-
- if (tb[IPSET_ATTR_HASHSIZE]) {
- hashsize = ip_set_get_h32(tb[IPSET_ATTR_HASHSIZE]);
- if (hashsize < IPSET_MIMINAL_HASHSIZE)
- hashsize = IPSET_MIMINAL_HASHSIZE;
- }
-
- if (tb[IPSET_ATTR_MAXELEM])
- maxelem = ip_set_get_h32(tb[IPSET_ATTR_MAXELEM]);
-
- h = kzalloc(sizeof(*h), GFP_KERNEL);
- if (!h)
- return -ENOMEM;
-
- h->maxelem = maxelem;
- get_random_bytes(&h->initval, sizeof(h->initval));
- h->timeout = IPSET_NO_TIMEOUT;
-
- hbits = htable_bits(hashsize);
- hsize = htable_size(hbits);
- if (hsize == 0) {
- kfree(h);
- return -ENOMEM;
- }
- h->table = ip_set_alloc(hsize);
- if (!h->table) {
- kfree(h);
- return -ENOMEM;
- }
- h->table->htable_bits = hbits;
-
- set->data = h;
-
- if (tb[IPSET_ATTR_TIMEOUT]) {
- h->timeout = ip_set_timeout_uget(tb[IPSET_ATTR_TIMEOUT]);
-
- set->variant = set->family == NFPROTO_IPV4
- ? &hash_ipportip4_tvariant : &hash_ipportip6_tvariant;
-
- if (set->family == NFPROTO_IPV4)
- hash_ipportip4_gc_init(set);
- else
- hash_ipportip6_gc_init(set);
- } else {
- set->variant = set->family == NFPROTO_IPV4
- ? &hash_ipportip4_variant : &hash_ipportip6_variant;
- }
-
- pr_debug("create %s hashsize %u (%u) maxelem %u: %p(%p)\n",
- set->name, jhash_size(h->table->htable_bits),
- h->table->htable_bits, h->maxelem, set->data, h->table);
-
- return 0;
-}
-
static struct ip_set_type hash_ipportip_type __read_mostly = {
.name = "hash:ip,port,ip",
.protocol = IPSET_PROTOCOL,
.features = IPSET_TYPE_IP | IPSET_TYPE_PORT | IPSET_TYPE_IP2,
.dimension = IPSET_DIM_THREE,
.family = NFPROTO_UNSPEC,
- .revision_min = REVISION_MIN,
- .revision_max = REVISION_MAX,
+ .revision_min = IPSET_TYPE_REV_MIN,
+ .revision_max = IPSET_TYPE_REV_MAX,
.create = hash_ipportip_create,
.create_policy = {
[IPSET_ATTR_HASHSIZE] = { .type = NLA_U32 },
@@ -552,6 +367,7 @@ static struct ip_set_type hash_ipportip_type __read_mostly = {
[IPSET_ATTR_PROBES] = { .type = NLA_U8 },
[IPSET_ATTR_RESIZE] = { .type = NLA_U8 },
[IPSET_ATTR_TIMEOUT] = { .type = NLA_U32 },
+ [IPSET_ATTR_CADT_FLAGS] = { .type = NLA_U32 },
},
.adt_policy = {
[IPSET_ATTR_IP] = { .type = NLA_NESTED },
@@ -563,6 +379,9 @@ static struct ip_set_type hash_ipportip_type __read_mostly = {
[IPSET_ATTR_PROTO] = { .type = NLA_U8 },
[IPSET_ATTR_TIMEOUT] = { .type = NLA_U32 },
[IPSET_ATTR_LINENO] = { .type = NLA_U32 },
+ [IPSET_ATTR_BYTES] = { .type = NLA_U64 },
+ [IPSET_ATTR_PACKETS] = { .type = NLA_U64 },
+ [IPSET_ATTR_COMMENT] = { .type = NLA_NUL_STRING },
},
.me = THIS_MODULE,
};
diff --git a/net/netfilter/ipset/ip_set_hash_ipportnet.c b/net/netfilter/ipset/ip_set_hash_ipportnet.c
index 2d5cd4ee30e..7308d84f927 100644
--- a/net/netfilter/ipset/ip_set_hash_ipportnet.c
+++ b/net/netfilter/ipset/ip_set_hash_ipportnet.c
@@ -1,4 +1,4 @@
-/* Copyright (C) 2003-2011 Jozsef Kadlecsik <kadlec@blackhole.kfki.hu>
+/* Copyright (C) 2003-2013 Jozsef Kadlecsik <kadlec@blackhole.kfki.hu>
*
* This program is free software; you can redistribute it and/or modify
* it under the terms of the GNU General Public License version 2 as
@@ -21,38 +21,36 @@
#include <linux/netfilter.h>
#include <linux/netfilter/ipset/pfxlen.h>
#include <linux/netfilter/ipset/ip_set.h>
-#include <linux/netfilter/ipset/ip_set_timeout.h>
#include <linux/netfilter/ipset/ip_set_getport.h>
#include <linux/netfilter/ipset/ip_set_hash.h>
-#define REVISION_MIN 0
-/* 1 SCTP and UDPLITE support added */
-/* 2 Range as input support for IPv4 added */
-#define REVISION_MAX 3 /* nomatch flag support added */
+#define IPSET_TYPE_REV_MIN 0
+/* 1 SCTP and UDPLITE support added */
+/* 2 Range as input support for IPv4 added */
+/* 3 nomatch flag support added */
+/* 4 Counters support added */
+/* 5 Comments support added */
+#define IPSET_TYPE_REV_MAX 6 /* Forceadd support added */
MODULE_LICENSE("GPL");
MODULE_AUTHOR("Jozsef Kadlecsik <kadlec@blackhole.kfki.hu>");
-IP_SET_MODULE_DESC("hash:ip,port,net", REVISION_MIN, REVISION_MAX);
+IP_SET_MODULE_DESC("hash:ip,port,net", IPSET_TYPE_REV_MIN, IPSET_TYPE_REV_MAX);
MODULE_ALIAS("ip_set_hash:ip,port,net");
/* Type specific function prefix */
-#define TYPE hash_ipportnet
-
-static bool
-hash_ipportnet_same_set(const struct ip_set *a, const struct ip_set *b);
-
-#define hash_ipportnet4_same_set hash_ipportnet_same_set
-#define hash_ipportnet6_same_set hash_ipportnet_same_set
-
-/* The type variant functions: IPv4 */
+#define HTYPE hash_ipportnet
/* We squeeze the "nomatch" flag into cidr: we don't support cidr == 0
* However this way we have to store internally cidr - 1,
* dancing back and forth.
*/
#define IP_SET_HASH_WITH_NETS_PACKED
+#define IP_SET_HASH_WITH_PROTO
+#define IP_SET_HASH_WITH_NETS
-/* Member elements without timeout */
+/* IPv4 variant */
+
+/* Member elements */
struct hash_ipportnet4_elem {
__be32 ip;
__be32 ip2;
@@ -62,16 +60,7 @@ struct hash_ipportnet4_elem {
u8 proto;
};
-/* Member elements with timeout support */
-struct hash_ipportnet4_telem {
- __be32 ip;
- __be32 ip2;
- __be16 port;
- u8 cidr:7;
- u8 nomatch:1;
- u8 proto;
- unsigned long timeout;
-};
+/* Common functions */
static inline bool
hash_ipportnet4_data_equal(const struct hash_ipportnet4_elem *ip1,
@@ -85,29 +74,22 @@ hash_ipportnet4_data_equal(const struct hash_ipportnet4_elem *ip1,
ip1->proto == ip2->proto;
}
-static inline bool
-hash_ipportnet4_data_isnull(const struct hash_ipportnet4_elem *elem)
+static inline int
+hash_ipportnet4_do_data_match(const struct hash_ipportnet4_elem *elem)
{
- return elem->proto == 0;
+ return elem->nomatch ? -ENOTEMPTY : 1;
}
static inline void
-hash_ipportnet4_data_copy(struct hash_ipportnet4_elem *dst,
- const struct hash_ipportnet4_elem *src)
+hash_ipportnet4_data_set_flags(struct hash_ipportnet4_elem *elem, u32 flags)
{
- memcpy(dst, src, sizeof(*dst));
+ elem->nomatch = !!((flags >> 16) & IPSET_FLAG_NOMATCH);
}
static inline void
-hash_ipportnet4_data_flags(struct hash_ipportnet4_elem *dst, u32 flags)
-{
- dst->nomatch = !!(flags & IPSET_FLAG_NOMATCH);
-}
-
-static inline int
-hash_ipportnet4_data_match(const struct hash_ipportnet4_elem *elem)
+hash_ipportnet4_data_reset_flags(struct hash_ipportnet4_elem *elem, u8 *flags)
{
- return elem->nomatch ? -ENOTEMPTY : 1;
+ swap(*flags, elem->nomatch);
}
static inline void
@@ -117,12 +99,6 @@ hash_ipportnet4_data_netmask(struct hash_ipportnet4_elem *elem, u8 cidr)
elem->cidr = cidr - 1;
}
-static inline void
-hash_ipportnet4_data_zero_out(struct hash_ipportnet4_elem *elem)
-{
- elem->proto = 0;
-}
-
static bool
hash_ipportnet4_data_list(struct sk_buff *skb,
const struct hash_ipportnet4_elem *data)
@@ -143,81 +119,56 @@ nla_put_failure:
return 1;
}
-static bool
-hash_ipportnet4_data_tlist(struct sk_buff *skb,
- const struct hash_ipportnet4_elem *data)
+static inline void
+hash_ipportnet4_data_next(struct hash_ipportnet4_elem *next,
+ const struct hash_ipportnet4_elem *d)
{
- const struct hash_ipportnet4_telem *tdata =
- (const struct hash_ipportnet4_telem *)data;
- u32 flags = data->nomatch ? IPSET_FLAG_NOMATCH : 0;
-
- if (nla_put_ipaddr4(skb, IPSET_ATTR_IP, tdata->ip) ||
- nla_put_ipaddr4(skb, IPSET_ATTR_IP2, tdata->ip2) ||
- nla_put_net16(skb, IPSET_ATTR_PORT, tdata->port) ||
- nla_put_u8(skb, IPSET_ATTR_CIDR2, data->cidr + 1) ||
- nla_put_u8(skb, IPSET_ATTR_PROTO, data->proto) ||
- nla_put_net32(skb, IPSET_ATTR_TIMEOUT,
- htonl(ip_set_timeout_get(tdata->timeout))) ||
- (flags &&
- nla_put_net32(skb, IPSET_ATTR_CADT_FLAGS, htonl(flags))))
- goto nla_put_failure;
- return 0;
-
-nla_put_failure:
- return 1;
+ next->ip = d->ip;
+ next->port = d->port;
+ next->ip2 = d->ip2;
}
-#define IP_SET_HASH_WITH_PROTO
-#define IP_SET_HASH_WITH_NETS
-
+#define MTYPE hash_ipportnet4
#define PF 4
#define HOST_MASK 32
-#include <linux/netfilter/ipset/ip_set_ahash.h>
-
-static inline void
-hash_ipportnet4_data_next(struct ip_set_hash *h,
- const struct hash_ipportnet4_elem *d)
-{
- h->next.ip = d->ip;
- h->next.port = d->port;
- h->next.ip2 = d->ip2;
-}
+#include "ip_set_hash_gen.h"
static int
hash_ipportnet4_kadt(struct ip_set *set, const struct sk_buff *skb,
const struct xt_action_param *par,
- enum ipset_adt adt, const struct ip_set_adt_opt *opt)
+ enum ipset_adt adt, struct ip_set_adt_opt *opt)
{
- const struct ip_set_hash *h = set->data;
+ const struct hash_ipportnet *h = set->data;
ipset_adtfn adtfn = set->variant->adt[adt];
- struct hash_ipportnet4_elem data = {
- .cidr = h->nets[0].cidr ? h->nets[0].cidr - 1 : HOST_MASK - 1
+ struct hash_ipportnet4_elem e = {
+ .cidr = IP_SET_INIT_CIDR(h->nets[0].cidr[0], HOST_MASK) - 1,
};
+ struct ip_set_ext ext = IP_SET_INIT_KEXT(skb, opt, set);
if (adt == IPSET_TEST)
- data.cidr = HOST_MASK - 1;
+ e.cidr = HOST_MASK - 1;
if (!ip_set_get_ip4_port(skb, opt->flags & IPSET_DIM_TWO_SRC,
- &data.port, &data.proto))
+ &e.port, &e.proto))
return -EINVAL;
- ip4addrptr(skb, opt->flags & IPSET_DIM_ONE_SRC, &data.ip);
- ip4addrptr(skb, opt->flags & IPSET_DIM_THREE_SRC, &data.ip2);
- data.ip2 &= ip_set_netmask(data.cidr + 1);
+ ip4addrptr(skb, opt->flags & IPSET_DIM_ONE_SRC, &e.ip);
+ ip4addrptr(skb, opt->flags & IPSET_DIM_THREE_SRC, &e.ip2);
+ e.ip2 &= ip_set_netmask(e.cidr + 1);
- return adtfn(set, &data, opt_timeout(opt, h), opt->cmdflags);
+ return adtfn(set, &e, &ext, &opt->ext, opt->cmdflags);
}
static int
hash_ipportnet4_uadt(struct ip_set *set, struct nlattr *tb[],
enum ipset_adt adt, u32 *lineno, u32 flags, bool retried)
{
- const struct ip_set_hash *h = set->data;
+ const struct hash_ipportnet *h = set->data;
ipset_adtfn adtfn = set->variant->adt[adt];
- struct hash_ipportnet4_elem data = { .cidr = HOST_MASK - 1 };
- u32 ip, ip_to, p = 0, port, port_to;
- u32 ip2_from, ip2_to, ip2_last, ip2;
- u32 timeout = h->timeout;
+ struct hash_ipportnet4_elem e = { .cidr = HOST_MASK - 1 };
+ struct ip_set_ext ext = IP_SET_INIT_UEXT(set);
+ u32 ip = 0, ip_to = 0, p = 0, port, port_to;
+ u32 ip2_from = 0, ip2_to = 0, ip2_last, ip2;
bool with_ports = false;
u8 cidr;
int ret;
@@ -226,13 +177,16 @@ hash_ipportnet4_uadt(struct ip_set *set, struct nlattr *tb[],
!ip_set_attr_netorder(tb, IPSET_ATTR_PORT) ||
!ip_set_optattr_netorder(tb, IPSET_ATTR_PORT_TO) ||
!ip_set_optattr_netorder(tb, IPSET_ATTR_TIMEOUT) ||
- !ip_set_optattr_netorder(tb, IPSET_ATTR_CADT_FLAGS)))
+ !ip_set_optattr_netorder(tb, IPSET_ATTR_CADT_FLAGS) ||
+ !ip_set_optattr_netorder(tb, IPSET_ATTR_PACKETS) ||
+ !ip_set_optattr_netorder(tb, IPSET_ATTR_BYTES)))
return -IPSET_ERR_PROTOCOL;
if (tb[IPSET_ATTR_LINENO])
*lineno = nla_get_u32(tb[IPSET_ATTR_LINENO]);
- ret = ip_set_get_hostipaddr4(tb[IPSET_ATTR_IP], &ip);
+ ret = ip_set_get_hostipaddr4(tb[IPSET_ATTR_IP], &ip) ||
+ ip_set_get_extensions(set, tb, &ext);
if (ret)
return ret;
@@ -244,46 +198,41 @@ hash_ipportnet4_uadt(struct ip_set *set, struct nlattr *tb[],
cidr = nla_get_u8(tb[IPSET_ATTR_CIDR2]);
if (!cidr || cidr > HOST_MASK)
return -IPSET_ERR_INVALID_CIDR;
- data.cidr = cidr - 1;
+ e.cidr = cidr - 1;
}
if (tb[IPSET_ATTR_PORT])
- data.port = nla_get_be16(tb[IPSET_ATTR_PORT]);
+ e.port = nla_get_be16(tb[IPSET_ATTR_PORT]);
else
return -IPSET_ERR_PROTOCOL;
if (tb[IPSET_ATTR_PROTO]) {
- data.proto = nla_get_u8(tb[IPSET_ATTR_PROTO]);
- with_ports = ip_set_proto_with_ports(data.proto);
+ e.proto = nla_get_u8(tb[IPSET_ATTR_PROTO]);
+ with_ports = ip_set_proto_with_ports(e.proto);
- if (data.proto == 0)
+ if (e.proto == 0)
return -IPSET_ERR_INVALID_PROTO;
} else
return -IPSET_ERR_MISSING_PROTO;
- if (!(with_ports || data.proto == IPPROTO_ICMP))
- data.port = 0;
-
- if (tb[IPSET_ATTR_TIMEOUT]) {
- if (!with_timeout(h->timeout))
- return -IPSET_ERR_TIMEOUT;
- timeout = ip_set_timeout_uget(tb[IPSET_ATTR_TIMEOUT]);
- }
+ if (!(with_ports || e.proto == IPPROTO_ICMP))
+ e.port = 0;
- if (tb[IPSET_ATTR_CADT_FLAGS] && adt == IPSET_ADD) {
+ if (tb[IPSET_ATTR_CADT_FLAGS]) {
u32 cadt_flags = ip_set_get_h32(tb[IPSET_ATTR_CADT_FLAGS]);
if (cadt_flags & IPSET_FLAG_NOMATCH)
- flags |= (cadt_flags << 16);
+ flags |= (IPSET_FLAG_NOMATCH << 16);
}
with_ports = with_ports && tb[IPSET_ATTR_PORT_TO];
if (adt == IPSET_TEST ||
!(tb[IPSET_ATTR_CIDR] || tb[IPSET_ATTR_IP_TO] || with_ports ||
tb[IPSET_ATTR_IP2_TO])) {
- data.ip = htonl(ip);
- data.ip2 = htonl(ip2_from & ip_set_hostmask(data.cidr + 1));
- ret = adtfn(set, &data, timeout, flags);
- return ip_set_eexist(ret, flags) ? 0 : ret;
+ e.ip = htonl(ip);
+ e.ip2 = htonl(ip2_from & ip_set_hostmask(e.cidr + 1));
+ ret = adtfn(set, &e, &ext, &ext, flags);
+ return ip_set_enomatch(ret, flags, adt, set) ? -ret :
+ ip_set_eexist(ret, flags) ? 0 : ret;
}
ip_to = ip;
@@ -294,14 +243,14 @@ hash_ipportnet4_uadt(struct ip_set *set, struct nlattr *tb[],
if (ip > ip_to)
swap(ip, ip_to);
} else if (tb[IPSET_ATTR_CIDR]) {
- u8 cidr = nla_get_u8(tb[IPSET_ATTR_CIDR]);
+ cidr = nla_get_u8(tb[IPSET_ATTR_CIDR]);
if (!cidr || cidr > 32)
return -IPSET_ERR_INVALID_CIDR;
ip_set_mask_from_to(ip, ip_to, cidr);
}
- port_to = port = ntohs(data.port);
+ port_to = port = ntohs(e.port);
if (tb[IPSET_ATTR_PORT_TO]) {
port_to = ip_set_get_h16(tb[IPSET_ATTR_PORT_TO]);
if (port > port_to)
@@ -317,28 +266,27 @@ hash_ipportnet4_uadt(struct ip_set *set, struct nlattr *tb[],
swap(ip2_from, ip2_to);
if (ip2_from + UINT_MAX == ip2_to)
return -IPSET_ERR_HASH_RANGE;
- } else {
- ip_set_mask_from_to(ip2_from, ip2_to, data.cidr + 1);
- }
+ } else
+ ip_set_mask_from_to(ip2_from, ip2_to, e.cidr + 1);
if (retried)
ip = ntohl(h->next.ip);
for (; !before(ip_to, ip); ip++) {
- data.ip = htonl(ip);
+ e.ip = htonl(ip);
p = retried && ip == ntohl(h->next.ip) ? ntohs(h->next.port)
: port;
for (; p <= port_to; p++) {
- data.port = htons(p);
- ip2 = retried
- && ip == ntohl(h->next.ip)
- && p == ntohs(h->next.port)
+ e.port = htons(p);
+ ip2 = retried &&
+ ip == ntohl(h->next.ip) &&
+ p == ntohs(h->next.port)
? ntohl(h->next.ip2) : ip2_from;
while (!after(ip2, ip2_to)) {
- data.ip2 = htonl(ip2);
+ e.ip2 = htonl(ip2);
ip2_last = ip_set_range_to_cidr(ip2, ip2_to,
&cidr);
- data.cidr = cidr - 1;
- ret = adtfn(set, &data, timeout, flags);
+ e.cidr = cidr - 1;
+ ret = adtfn(set, &e, &ext, &ext, flags);
if (ret && !ip_set_eexist(ret, flags))
return ret;
@@ -351,18 +299,7 @@ hash_ipportnet4_uadt(struct ip_set *set, struct nlattr *tb[],
return ret;
}
-static bool
-hash_ipportnet_same_set(const struct ip_set *a, const struct ip_set *b)
-{
- const struct ip_set_hash *x = a->data;
- const struct ip_set_hash *y = b->data;
-
- /* Resizing changes htable_bits, so we ignore it */
- return x->maxelem == y->maxelem &&
- x->timeout == y->timeout;
-}
-
-/* The type variant functions: IPv6 */
+/* IPv6 variant */
struct hash_ipportnet6_elem {
union nf_inet_addr ip;
@@ -373,66 +310,36 @@ struct hash_ipportnet6_elem {
u8 proto;
};
-struct hash_ipportnet6_telem {
- union nf_inet_addr ip;
- union nf_inet_addr ip2;
- __be16 port;
- u8 cidr:7;
- u8 nomatch:1;
- u8 proto;
- unsigned long timeout;
-};
+/* Common functions */
static inline bool
hash_ipportnet6_data_equal(const struct hash_ipportnet6_elem *ip1,
const struct hash_ipportnet6_elem *ip2,
u32 *multi)
{
- return ipv6_addr_cmp(&ip1->ip.in6, &ip2->ip.in6) == 0 &&
- ipv6_addr_cmp(&ip1->ip2.in6, &ip2->ip2.in6) == 0 &&
+ return ipv6_addr_equal(&ip1->ip.in6, &ip2->ip.in6) &&
+ ipv6_addr_equal(&ip1->ip2.in6, &ip2->ip2.in6) &&
ip1->cidr == ip2->cidr &&
ip1->port == ip2->port &&
ip1->proto == ip2->proto;
}
-static inline bool
-hash_ipportnet6_data_isnull(const struct hash_ipportnet6_elem *elem)
-{
- return elem->proto == 0;
-}
-
-static inline void
-hash_ipportnet6_data_copy(struct hash_ipportnet6_elem *dst,
- const struct hash_ipportnet6_elem *src)
-{
- memcpy(dst, src, sizeof(*dst));
-}
-
-static inline void
-hash_ipportnet6_data_flags(struct hash_ipportnet6_elem *dst, u32 flags)
-{
- dst->nomatch = !!(flags & IPSET_FLAG_NOMATCH);
-}
-
static inline int
-hash_ipportnet6_data_match(const struct hash_ipportnet6_elem *elem)
+hash_ipportnet6_do_data_match(const struct hash_ipportnet6_elem *elem)
{
return elem->nomatch ? -ENOTEMPTY : 1;
}
static inline void
-hash_ipportnet6_data_zero_out(struct hash_ipportnet6_elem *elem)
+hash_ipportnet6_data_set_flags(struct hash_ipportnet6_elem *elem, u32 flags)
{
- elem->proto = 0;
+ elem->nomatch = !!((flags >> 16) & IPSET_FLAG_NOMATCH);
}
static inline void
-ip6_netmask(union nf_inet_addr *ip, u8 prefix)
+hash_ipportnet6_data_reset_flags(struct hash_ipportnet6_elem *elem, u8 *flags)
{
- ip->ip6[0] &= ip_set_netmask6(prefix)[0];
- ip->ip6[1] &= ip_set_netmask6(prefix)[1];
- ip->ip6[2] &= ip_set_netmask6(prefix)[2];
- ip->ip6[3] &= ip_set_netmask6(prefix)[3];
+ swap(*flags, elem->nomatch);
}
static inline void
@@ -462,78 +369,58 @@ nla_put_failure:
return 1;
}
-static bool
-hash_ipportnet6_data_tlist(struct sk_buff *skb,
- const struct hash_ipportnet6_elem *data)
+static inline void
+hash_ipportnet6_data_next(struct hash_ipportnet4_elem *next,
+ const struct hash_ipportnet6_elem *d)
{
- const struct hash_ipportnet6_telem *e =
- (const struct hash_ipportnet6_telem *)data;
- u32 flags = data->nomatch ? IPSET_FLAG_NOMATCH : 0;
-
- if (nla_put_ipaddr6(skb, IPSET_ATTR_IP, &e->ip.in6) ||
- nla_put_ipaddr6(skb, IPSET_ATTR_IP2, &data->ip2.in6) ||
- nla_put_net16(skb, IPSET_ATTR_PORT, data->port) ||
- nla_put_u8(skb, IPSET_ATTR_CIDR2, data->cidr + 1) ||
- nla_put_u8(skb, IPSET_ATTR_PROTO, data->proto) ||
- nla_put_net32(skb, IPSET_ATTR_TIMEOUT,
- htonl(ip_set_timeout_get(e->timeout))) ||
- (flags &&
- nla_put_net32(skb, IPSET_ATTR_CADT_FLAGS, htonl(flags))))
- goto nla_put_failure;
- return 0;
-
-nla_put_failure:
- return 1;
+ next->port = d->port;
}
+#undef MTYPE
#undef PF
#undef HOST_MASK
+#define MTYPE hash_ipportnet6
#define PF 6
#define HOST_MASK 128
-#include <linux/netfilter/ipset/ip_set_ahash.h>
-
-static inline void
-hash_ipportnet6_data_next(struct ip_set_hash *h,
- const struct hash_ipportnet6_elem *d)
-{
- h->next.port = d->port;
-}
+#define IP_SET_EMIT_CREATE
+#include "ip_set_hash_gen.h"
static int
hash_ipportnet6_kadt(struct ip_set *set, const struct sk_buff *skb,
const struct xt_action_param *par,
- enum ipset_adt adt, const struct ip_set_adt_opt *opt)
+ enum ipset_adt adt, struct ip_set_adt_opt *opt)
{
- const struct ip_set_hash *h = set->data;
+ const struct hash_ipportnet *h = set->data;
ipset_adtfn adtfn = set->variant->adt[adt];
- struct hash_ipportnet6_elem data = {
- .cidr = h->nets[0].cidr ? h->nets[0].cidr - 1 : HOST_MASK - 1
+ struct hash_ipportnet6_elem e = {
+ .cidr = IP_SET_INIT_CIDR(h->nets[0].cidr[0], HOST_MASK) - 1,
};
+ struct ip_set_ext ext = IP_SET_INIT_KEXT(skb, opt, set);
if (adt == IPSET_TEST)
- data.cidr = HOST_MASK - 1;
+ e.cidr = HOST_MASK - 1;
if (!ip_set_get_ip6_port(skb, opt->flags & IPSET_DIM_TWO_SRC,
- &data.port, &data.proto))
+ &e.port, &e.proto))
return -EINVAL;
- ip6addrptr(skb, opt->flags & IPSET_DIM_ONE_SRC, &data.ip.in6);
- ip6addrptr(skb, opt->flags & IPSET_DIM_THREE_SRC, &data.ip2.in6);
- ip6_netmask(&data.ip2, data.cidr + 1);
+ ip6addrptr(skb, opt->flags & IPSET_DIM_ONE_SRC, &e.ip.in6);
+ ip6addrptr(skb, opt->flags & IPSET_DIM_THREE_SRC, &e.ip2.in6);
+ ip6_netmask(&e.ip2, e.cidr + 1);
- return adtfn(set, &data, opt_timeout(opt, h), opt->cmdflags);
+ return adtfn(set, &e, &ext, &opt->ext, opt->cmdflags);
}
static int
hash_ipportnet6_uadt(struct ip_set *set, struct nlattr *tb[],
enum ipset_adt adt, u32 *lineno, u32 flags, bool retried)
{
- const struct ip_set_hash *h = set->data;
+ const struct hash_ipportnet *h = set->data;
ipset_adtfn adtfn = set->variant->adt[adt];
- struct hash_ipportnet6_elem data = { .cidr = HOST_MASK - 1 };
+ struct hash_ipportnet6_elem e = { .cidr = HOST_MASK - 1 };
+ struct ip_set_ext ext = IP_SET_INIT_UEXT(set);
u32 port, port_to;
- u32 timeout = h->timeout;
bool with_ports = false;
u8 cidr;
int ret;
@@ -543,6 +430,8 @@ hash_ipportnet6_uadt(struct ip_set *set, struct nlattr *tb[],
!ip_set_optattr_netorder(tb, IPSET_ATTR_PORT_TO) ||
!ip_set_optattr_netorder(tb, IPSET_ATTR_TIMEOUT) ||
!ip_set_optattr_netorder(tb, IPSET_ATTR_CADT_FLAGS) ||
+ !ip_set_optattr_netorder(tb, IPSET_ATTR_PACKETS) ||
+ !ip_set_optattr_netorder(tb, IPSET_ATTR_BYTES) ||
tb[IPSET_ATTR_IP_TO] ||
tb[IPSET_ATTR_CIDR]))
return -IPSET_ERR_PROTOCOL;
@@ -552,11 +441,12 @@ hash_ipportnet6_uadt(struct ip_set *set, struct nlattr *tb[],
if (tb[IPSET_ATTR_LINENO])
*lineno = nla_get_u32(tb[IPSET_ATTR_LINENO]);
- ret = ip_set_get_ipaddr6(tb[IPSET_ATTR_IP], &data.ip);
+ ret = ip_set_get_ipaddr6(tb[IPSET_ATTR_IP], &e.ip) ||
+ ip_set_get_extensions(set, tb, &ext);
if (ret)
return ret;
- ret = ip_set_get_ipaddr6(tb[IPSET_ATTR_IP2], &data.ip2);
+ ret = ip_set_get_ipaddr6(tb[IPSET_ATTR_IP2], &e.ip2);
if (ret)
return ret;
@@ -564,46 +454,41 @@ hash_ipportnet6_uadt(struct ip_set *set, struct nlattr *tb[],
cidr = nla_get_u8(tb[IPSET_ATTR_CIDR2]);
if (!cidr || cidr > HOST_MASK)
return -IPSET_ERR_INVALID_CIDR;
- data.cidr = cidr - 1;
+ e.cidr = cidr - 1;
}
- ip6_netmask(&data.ip2, data.cidr + 1);
+ ip6_netmask(&e.ip2, e.cidr + 1);
if (tb[IPSET_ATTR_PORT])
- data.port = nla_get_be16(tb[IPSET_ATTR_PORT]);
+ e.port = nla_get_be16(tb[IPSET_ATTR_PORT]);
else
return -IPSET_ERR_PROTOCOL;
if (tb[IPSET_ATTR_PROTO]) {
- data.proto = nla_get_u8(tb[IPSET_ATTR_PROTO]);
- with_ports = ip_set_proto_with_ports(data.proto);
+ e.proto = nla_get_u8(tb[IPSET_ATTR_PROTO]);
+ with_ports = ip_set_proto_with_ports(e.proto);
- if (data.proto == 0)
+ if (e.proto == 0)
return -IPSET_ERR_INVALID_PROTO;
} else
return -IPSET_ERR_MISSING_PROTO;
- if (!(with_ports || data.proto == IPPROTO_ICMPV6))
- data.port = 0;
-
- if (tb[IPSET_ATTR_TIMEOUT]) {
- if (!with_timeout(h->timeout))
- return -IPSET_ERR_TIMEOUT;
- timeout = ip_set_timeout_uget(tb[IPSET_ATTR_TIMEOUT]);
- }
+ if (!(with_ports || e.proto == IPPROTO_ICMPV6))
+ e.port = 0;
- if (tb[IPSET_ATTR_CADT_FLAGS] && adt == IPSET_ADD) {
+ if (tb[IPSET_ATTR_CADT_FLAGS]) {
u32 cadt_flags = ip_set_get_h32(tb[IPSET_ATTR_CADT_FLAGS]);
if (cadt_flags & IPSET_FLAG_NOMATCH)
- flags |= (cadt_flags << 16);
+ flags |= (IPSET_FLAG_NOMATCH << 16);
}
if (adt == IPSET_TEST || !with_ports || !tb[IPSET_ATTR_PORT_TO]) {
- ret = adtfn(set, &data, timeout, flags);
- return ip_set_eexist(ret, flags) ? 0 : ret;
+ ret = adtfn(set, &e, &ext, &ext, flags);
+ return ip_set_enomatch(ret, flags, adt, set) ? -ret :
+ ip_set_eexist(ret, flags) ? 0 : ret;
}
- port = ntohs(data.port);
+ port = ntohs(e.port);
port_to = ip_set_get_h16(tb[IPSET_ATTR_PORT_TO]);
if (port > port_to)
swap(port, port_to);
@@ -611,8 +496,8 @@ hash_ipportnet6_uadt(struct ip_set *set, struct nlattr *tb[],
if (retried)
port = ntohs(h->next.port);
for (; port <= port_to; port++) {
- data.port = htons(port);
- ret = adtfn(set, &data, timeout, flags);
+ e.port = htons(port);
+ ret = adtfn(set, &e, &ext, &ext, flags);
if (ret && !ip_set_eexist(ret, flags))
return ret;
@@ -622,81 +507,6 @@ hash_ipportnet6_uadt(struct ip_set *set, struct nlattr *tb[],
return ret;
}
-/* Create hash:ip type of sets */
-
-static int
-hash_ipportnet_create(struct ip_set *set, struct nlattr *tb[], u32 flags)
-{
- struct ip_set_hash *h;
- u32 hashsize = IPSET_DEFAULT_HASHSIZE, maxelem = IPSET_DEFAULT_MAXELEM;
- u8 hbits;
- size_t hsize;
-
- if (!(set->family == NFPROTO_IPV4 || set->family == NFPROTO_IPV6))
- return -IPSET_ERR_INVALID_FAMILY;
-
- if (unlikely(!ip_set_optattr_netorder(tb, IPSET_ATTR_HASHSIZE) ||
- !ip_set_optattr_netorder(tb, IPSET_ATTR_MAXELEM) ||
- !ip_set_optattr_netorder(tb, IPSET_ATTR_TIMEOUT)))
- return -IPSET_ERR_PROTOCOL;
-
- if (tb[IPSET_ATTR_HASHSIZE]) {
- hashsize = ip_set_get_h32(tb[IPSET_ATTR_HASHSIZE]);
- if (hashsize < IPSET_MIMINAL_HASHSIZE)
- hashsize = IPSET_MIMINAL_HASHSIZE;
- }
-
- if (tb[IPSET_ATTR_MAXELEM])
- maxelem = ip_set_get_h32(tb[IPSET_ATTR_MAXELEM]);
-
- h = kzalloc(sizeof(*h)
- + sizeof(struct ip_set_hash_nets)
- * (set->family == NFPROTO_IPV4 ? 32 : 128), GFP_KERNEL);
- if (!h)
- return -ENOMEM;
-
- h->maxelem = maxelem;
- get_random_bytes(&h->initval, sizeof(h->initval));
- h->timeout = IPSET_NO_TIMEOUT;
-
- hbits = htable_bits(hashsize);
- hsize = htable_size(hbits);
- if (hsize == 0) {
- kfree(h);
- return -ENOMEM;
- }
- h->table = ip_set_alloc(hsize);
- if (!h->table) {
- kfree(h);
- return -ENOMEM;
- }
- h->table->htable_bits = hbits;
-
- set->data = h;
-
- if (tb[IPSET_ATTR_TIMEOUT]) {
- h->timeout = ip_set_timeout_uget(tb[IPSET_ATTR_TIMEOUT]);
-
- set->variant = set->family == NFPROTO_IPV4
- ? &hash_ipportnet4_tvariant
- : &hash_ipportnet6_tvariant;
-
- if (set->family == NFPROTO_IPV4)
- hash_ipportnet4_gc_init(set);
- else
- hash_ipportnet6_gc_init(set);
- } else {
- set->variant = set->family == NFPROTO_IPV4
- ? &hash_ipportnet4_variant : &hash_ipportnet6_variant;
- }
-
- pr_debug("create %s hashsize %u (%u) maxelem %u: %p(%p)\n",
- set->name, jhash_size(h->table->htable_bits),
- h->table->htable_bits, h->maxelem, set->data, h->table);
-
- return 0;
-}
-
static struct ip_set_type hash_ipportnet_type __read_mostly = {
.name = "hash:ip,port,net",
.protocol = IPSET_PROTOCOL,
@@ -704,8 +514,8 @@ static struct ip_set_type hash_ipportnet_type __read_mostly = {
IPSET_TYPE_NOMATCH,
.dimension = IPSET_DIM_THREE,
.family = NFPROTO_UNSPEC,
- .revision_min = REVISION_MIN,
- .revision_max = REVISION_MAX,
+ .revision_min = IPSET_TYPE_REV_MIN,
+ .revision_max = IPSET_TYPE_REV_MAX,
.create = hash_ipportnet_create,
.create_policy = {
[IPSET_ATTR_HASHSIZE] = { .type = NLA_U32 },
@@ -713,6 +523,7 @@ static struct ip_set_type hash_ipportnet_type __read_mostly = {
[IPSET_ATTR_PROBES] = { .type = NLA_U8 },
[IPSET_ATTR_RESIZE] = { .type = NLA_U8 },
[IPSET_ATTR_TIMEOUT] = { .type = NLA_U32 },
+ [IPSET_ATTR_CADT_FLAGS] = { .type = NLA_U32 },
},
.adt_policy = {
[IPSET_ATTR_IP] = { .type = NLA_NESTED },
@@ -727,6 +538,9 @@ static struct ip_set_type hash_ipportnet_type __read_mostly = {
[IPSET_ATTR_CADT_FLAGS] = { .type = NLA_U32 },
[IPSET_ATTR_TIMEOUT] = { .type = NLA_U32 },
[IPSET_ATTR_LINENO] = { .type = NLA_U32 },
+ [IPSET_ATTR_BYTES] = { .type = NLA_U64 },
+ [IPSET_ATTR_PACKETS] = { .type = NLA_U64 },
+ [IPSET_ATTR_COMMENT] = { .type = NLA_NUL_STRING },
},
.me = THIS_MODULE,
};
diff --git a/net/netfilter/ipset/ip_set_hash_net.c b/net/netfilter/ipset/ip_set_hash_net.c
index 29e94b981f3..4c7d495783a 100644
--- a/net/netfilter/ipset/ip_set_hash_net.c
+++ b/net/netfilter/ipset/ip_set_hash_net.c
@@ -1,4 +1,4 @@
-/* Copyright (C) 2003-2011 Jozsef Kadlecsik <kadlec@blackhole.kfki.hu>
+/* Copyright (C) 2003-2013 Jozsef Kadlecsik <kadlec@blackhole.kfki.hu>
*
* This program is free software; you can redistribute it and/or modify
* it under the terms of the GNU General Public License version 2 as
@@ -20,30 +20,27 @@
#include <linux/netfilter.h>
#include <linux/netfilter/ipset/pfxlen.h>
#include <linux/netfilter/ipset/ip_set.h>
-#include <linux/netfilter/ipset/ip_set_timeout.h>
#include <linux/netfilter/ipset/ip_set_hash.h>
-#define REVISION_MIN 0
-/* 1 Range as input support for IPv4 added */
-#define REVISION_MAX 2 /* nomatch flag support added */
+#define IPSET_TYPE_REV_MIN 0
+/* 1 Range as input support for IPv4 added */
+/* 2 nomatch flag support added */
+/* 3 Counters support added */
+/* 4 Comments support added */
+#define IPSET_TYPE_REV_MAX 5 /* Forceadd support added */
MODULE_LICENSE("GPL");
MODULE_AUTHOR("Jozsef Kadlecsik <kadlec@blackhole.kfki.hu>");
-IP_SET_MODULE_DESC("hash:net", REVISION_MIN, REVISION_MAX);
+IP_SET_MODULE_DESC("hash:net", IPSET_TYPE_REV_MIN, IPSET_TYPE_REV_MAX);
MODULE_ALIAS("ip_set_hash:net");
/* Type specific function prefix */
-#define TYPE hash_net
-
-static bool
-hash_net_same_set(const struct ip_set *a, const struct ip_set *b);
-
-#define hash_net4_same_set hash_net_same_set
-#define hash_net6_same_set hash_net_same_set
+#define HTYPE hash_net
+#define IP_SET_HASH_WITH_NETS
-/* The type variant functions: IPv4 */
+/* IPv4 variant */
-/* Member elements without timeout */
+/* Member elements */
struct hash_net4_elem {
__be32 ip;
u16 padding0;
@@ -51,14 +48,7 @@ struct hash_net4_elem {
u8 cidr;
};
-/* Member elements with timeout support */
-struct hash_net4_telem {
- __be32 ip;
- u16 padding0;
- u8 nomatch;
- u8 cidr;
- unsigned long timeout;
-};
+/* Common functions */
static inline bool
hash_net4_data_equal(const struct hash_net4_elem *ip1,
@@ -69,31 +59,22 @@ hash_net4_data_equal(const struct hash_net4_elem *ip1,
ip1->cidr == ip2->cidr;
}
-static inline bool
-hash_net4_data_isnull(const struct hash_net4_elem *elem)
+static inline int
+hash_net4_do_data_match(const struct hash_net4_elem *elem)
{
- return elem->cidr == 0;
+ return elem->nomatch ? -ENOTEMPTY : 1;
}
static inline void
-hash_net4_data_copy(struct hash_net4_elem *dst,
- const struct hash_net4_elem *src)
+hash_net4_data_set_flags(struct hash_net4_elem *elem, u32 flags)
{
- dst->ip = src->ip;
- dst->cidr = src->cidr;
- dst->nomatch = src->nomatch;
+ elem->nomatch = (flags >> 16) & IPSET_FLAG_NOMATCH;
}
static inline void
-hash_net4_data_flags(struct hash_net4_elem *dst, u32 flags)
-{
- dst->nomatch = flags & IPSET_FLAG_NOMATCH;
-}
-
-static inline int
-hash_net4_data_match(const struct hash_net4_elem *elem)
+hash_net4_data_reset_flags(struct hash_net4_elem *elem, u8 *flags)
{
- return elem->nomatch ? -ENOTEMPTY : 1;
+ swap(*flags, elem->nomatch);
}
static inline void
@@ -103,13 +84,6 @@ hash_net4_data_netmask(struct hash_net4_elem *elem, u8 cidr)
elem->cidr = cidr;
}
-/* Zero CIDR values cannot be stored */
-static inline void
-hash_net4_data_zero_out(struct hash_net4_elem *elem)
-{
- elem->cidr = 0;
-}
-
static bool
hash_net4_data_list(struct sk_buff *skb, const struct hash_net4_elem *data)
{
@@ -126,106 +100,84 @@ nla_put_failure:
return 1;
}
-static bool
-hash_net4_data_tlist(struct sk_buff *skb, const struct hash_net4_elem *data)
+static inline void
+hash_net4_data_next(struct hash_net4_elem *next,
+ const struct hash_net4_elem *d)
{
- const struct hash_net4_telem *tdata =
- (const struct hash_net4_telem *)data;
- u32 flags = data->nomatch ? IPSET_FLAG_NOMATCH : 0;
-
- if (nla_put_ipaddr4(skb, IPSET_ATTR_IP, tdata->ip) ||
- nla_put_u8(skb, IPSET_ATTR_CIDR, tdata->cidr) ||
- nla_put_net32(skb, IPSET_ATTR_TIMEOUT,
- htonl(ip_set_timeout_get(tdata->timeout))) ||
- (flags &&
- nla_put_net32(skb, IPSET_ATTR_CADT_FLAGS, htonl(flags))))
- goto nla_put_failure;
- return 0;
-
-nla_put_failure:
- return 1;
+ next->ip = d->ip;
}
-#define IP_SET_HASH_WITH_NETS
-
+#define MTYPE hash_net4
#define PF 4
#define HOST_MASK 32
-#include <linux/netfilter/ipset/ip_set_ahash.h>
-
-static inline void
-hash_net4_data_next(struct ip_set_hash *h,
- const struct hash_net4_elem *d)
-{
- h->next.ip = d->ip;
-}
+#include "ip_set_hash_gen.h"
static int
hash_net4_kadt(struct ip_set *set, const struct sk_buff *skb,
const struct xt_action_param *par,
- enum ipset_adt adt, const struct ip_set_adt_opt *opt)
+ enum ipset_adt adt, struct ip_set_adt_opt *opt)
{
- const struct ip_set_hash *h = set->data;
+ const struct hash_net *h = set->data;
ipset_adtfn adtfn = set->variant->adt[adt];
- struct hash_net4_elem data = {
- .cidr = h->nets[0].cidr ? h->nets[0].cidr : HOST_MASK
+ struct hash_net4_elem e = {
+ .cidr = IP_SET_INIT_CIDR(h->nets[0].cidr[0], HOST_MASK),
};
+ struct ip_set_ext ext = IP_SET_INIT_KEXT(skb, opt, set);
- if (data.cidr == 0)
+ if (e.cidr == 0)
return -EINVAL;
if (adt == IPSET_TEST)
- data.cidr = HOST_MASK;
+ e.cidr = HOST_MASK;
- ip4addrptr(skb, opt->flags & IPSET_DIM_ONE_SRC, &data.ip);
- data.ip &= ip_set_netmask(data.cidr);
+ ip4addrptr(skb, opt->flags & IPSET_DIM_ONE_SRC, &e.ip);
+ e.ip &= ip_set_netmask(e.cidr);
- return adtfn(set, &data, opt_timeout(opt, h), opt->cmdflags);
+ return adtfn(set, &e, &ext, &opt->ext, opt->cmdflags);
}
static int
hash_net4_uadt(struct ip_set *set, struct nlattr *tb[],
enum ipset_adt adt, u32 *lineno, u32 flags, bool retried)
{
- const struct ip_set_hash *h = set->data;
+ const struct hash_net *h = set->data;
ipset_adtfn adtfn = set->variant->adt[adt];
- struct hash_net4_elem data = { .cidr = HOST_MASK };
- u32 timeout = h->timeout;
- u32 ip = 0, ip_to, last;
+ struct hash_net4_elem e = { .cidr = HOST_MASK };
+ struct ip_set_ext ext = IP_SET_INIT_UEXT(set);
+ u32 ip = 0, ip_to = 0, last;
int ret;
if (unlikely(!tb[IPSET_ATTR_IP] ||
!ip_set_optattr_netorder(tb, IPSET_ATTR_TIMEOUT) ||
- !ip_set_optattr_netorder(tb, IPSET_ATTR_CADT_FLAGS)))
+ !ip_set_optattr_netorder(tb, IPSET_ATTR_CADT_FLAGS) ||
+ !ip_set_optattr_netorder(tb, IPSET_ATTR_PACKETS) ||
+ !ip_set_optattr_netorder(tb, IPSET_ATTR_BYTES)))
return -IPSET_ERR_PROTOCOL;
if (tb[IPSET_ATTR_LINENO])
*lineno = nla_get_u32(tb[IPSET_ATTR_LINENO]);
- ret = ip_set_get_hostipaddr4(tb[IPSET_ATTR_IP], &ip);
+ ret = ip_set_get_hostipaddr4(tb[IPSET_ATTR_IP], &ip) ||
+ ip_set_get_extensions(set, tb, &ext);
if (ret)
return ret;
if (tb[IPSET_ATTR_CIDR]) {
- data.cidr = nla_get_u8(tb[IPSET_ATTR_CIDR]);
- if (!data.cidr || data.cidr > HOST_MASK)
+ e.cidr = nla_get_u8(tb[IPSET_ATTR_CIDR]);
+ if (!e.cidr || e.cidr > HOST_MASK)
return -IPSET_ERR_INVALID_CIDR;
}
- if (tb[IPSET_ATTR_TIMEOUT]) {
- if (!with_timeout(h->timeout))
- return -IPSET_ERR_TIMEOUT;
- timeout = ip_set_timeout_uget(tb[IPSET_ATTR_TIMEOUT]);
- }
-
- if (tb[IPSET_ATTR_CADT_FLAGS] && adt == IPSET_ADD) {
+ if (tb[IPSET_ATTR_CADT_FLAGS]) {
u32 cadt_flags = ip_set_get_h32(tb[IPSET_ATTR_CADT_FLAGS]);
if (cadt_flags & IPSET_FLAG_NOMATCH)
- flags |= (cadt_flags << 16);
+ flags |= (IPSET_FLAG_NOMATCH << 16);
}
if (adt == IPSET_TEST || !tb[IPSET_ATTR_IP_TO]) {
- data.ip = htonl(ip & ip_set_hostmask(data.cidr));
- ret = adtfn(set, &data, timeout, flags);
- return ip_set_eexist(ret, flags) ? 0 : ret;
+ e.ip = htonl(ip & ip_set_hostmask(e.cidr));
+ ret = adtfn(set, &e, &ext, &ext, flags);
+ return ip_set_enomatch(ret, flags, adt, set) ? -ret:
+ ip_set_eexist(ret, flags) ? 0 : ret;
}
ip_to = ip;
@@ -241,9 +193,9 @@ hash_net4_uadt(struct ip_set *set, struct nlattr *tb[],
if (retried)
ip = ntohl(h->next.ip);
while (!after(ip, ip_to)) {
- data.ip = htonl(ip);
- last = ip_set_range_to_cidr(ip, ip_to, &data.cidr);
- ret = adtfn(set, &data, timeout, flags);
+ e.ip = htonl(ip);
+ last = ip_set_range_to_cidr(ip, ip_to, &e.cidr);
+ ret = adtfn(set, &e, &ext, &ext, flags);
if (ret && !ip_set_eexist(ret, flags))
return ret;
else
@@ -253,18 +205,7 @@ hash_net4_uadt(struct ip_set *set, struct nlattr *tb[],
return ret;
}
-static bool
-hash_net_same_set(const struct ip_set *a, const struct ip_set *b)
-{
- const struct ip_set_hash *x = a->data;
- const struct ip_set_hash *y = b->data;
-
- /* Resizing changes htable_bits, so we ignore it */
- return x->maxelem == y->maxelem &&
- x->timeout == y->timeout;
-}
-
-/* The type variant functions: IPv6 */
+/* IPv6 variant */
struct hash_net6_elem {
union nf_inet_addr ip;
@@ -273,63 +214,33 @@ struct hash_net6_elem {
u8 cidr;
};
-struct hash_net6_telem {
- union nf_inet_addr ip;
- u16 padding0;
- u8 nomatch;
- u8 cidr;
- unsigned long timeout;
-};
+/* Common functions */
static inline bool
hash_net6_data_equal(const struct hash_net6_elem *ip1,
const struct hash_net6_elem *ip2,
u32 *multi)
{
- return ipv6_addr_cmp(&ip1->ip.in6, &ip2->ip.in6) == 0 &&
+ return ipv6_addr_equal(&ip1->ip.in6, &ip2->ip.in6) &&
ip1->cidr == ip2->cidr;
}
-static inline bool
-hash_net6_data_isnull(const struct hash_net6_elem *elem)
-{
- return elem->cidr == 0;
-}
-
-static inline void
-hash_net6_data_copy(struct hash_net6_elem *dst,
- const struct hash_net6_elem *src)
-{
- dst->ip.in6 = src->ip.in6;
- dst->cidr = src->cidr;
- dst->nomatch = src->nomatch;
-}
-
-static inline void
-hash_net6_data_flags(struct hash_net6_elem *dst, u32 flags)
-{
- dst->nomatch = flags & IPSET_FLAG_NOMATCH;
-}
-
static inline int
-hash_net6_data_match(const struct hash_net6_elem *elem)
+hash_net6_do_data_match(const struct hash_net6_elem *elem)
{
return elem->nomatch ? -ENOTEMPTY : 1;
}
static inline void
-hash_net6_data_zero_out(struct hash_net6_elem *elem)
+hash_net6_data_set_flags(struct hash_net6_elem *elem, u32 flags)
{
- elem->cidr = 0;
+ elem->nomatch = (flags >> 16) & IPSET_FLAG_NOMATCH;
}
static inline void
-ip6_netmask(union nf_inet_addr *ip, u8 prefix)
+hash_net6_data_reset_flags(struct hash_net6_elem *elem, u8 *flags)
{
- ip->ip6[0] &= ip_set_netmask6(prefix)[0];
- ip->ip6[1] &= ip_set_netmask6(prefix)[1];
- ip->ip6[2] &= ip_set_netmask6(prefix)[2];
- ip->ip6[3] &= ip_set_netmask6(prefix)[3];
+ swap(*flags, elem->nomatch);
}
static inline void
@@ -355,74 +266,59 @@ nla_put_failure:
return 1;
}
-static bool
-hash_net6_data_tlist(struct sk_buff *skb, const struct hash_net6_elem *data)
+static inline void
+hash_net6_data_next(struct hash_net4_elem *next,
+ const struct hash_net6_elem *d)
{
- const struct hash_net6_telem *e =
- (const struct hash_net6_telem *)data;
- u32 flags = data->nomatch ? IPSET_FLAG_NOMATCH : 0;
-
- if (nla_put_ipaddr6(skb, IPSET_ATTR_IP, &e->ip.in6) ||
- nla_put_u8(skb, IPSET_ATTR_CIDR, e->cidr) ||
- nla_put_net32(skb, IPSET_ATTR_TIMEOUT,
- htonl(ip_set_timeout_get(e->timeout))) ||
- (flags &&
- nla_put_net32(skb, IPSET_ATTR_CADT_FLAGS, htonl(flags))))
- goto nla_put_failure;
- return 0;
-
-nla_put_failure:
- return 1;
}
+#undef MTYPE
#undef PF
#undef HOST_MASK
+#define MTYPE hash_net6
#define PF 6
#define HOST_MASK 128
-#include <linux/netfilter/ipset/ip_set_ahash.h>
-
-static inline void
-hash_net6_data_next(struct ip_set_hash *h,
- const struct hash_net6_elem *d)
-{
-}
+#define IP_SET_EMIT_CREATE
+#include "ip_set_hash_gen.h"
static int
hash_net6_kadt(struct ip_set *set, const struct sk_buff *skb,
const struct xt_action_param *par,
- enum ipset_adt adt, const struct ip_set_adt_opt *opt)
+ enum ipset_adt adt, struct ip_set_adt_opt *opt)
{
- const struct ip_set_hash *h = set->data;
+ const struct hash_net *h = set->data;
ipset_adtfn adtfn = set->variant->adt[adt];
- struct hash_net6_elem data = {
- .cidr = h->nets[0].cidr ? h->nets[0].cidr : HOST_MASK
+ struct hash_net6_elem e = {
+ .cidr = IP_SET_INIT_CIDR(h->nets[0].cidr[0], HOST_MASK),
};
+ struct ip_set_ext ext = IP_SET_INIT_KEXT(skb, opt, set);
- if (data.cidr == 0)
+ if (e.cidr == 0)
return -EINVAL;
if (adt == IPSET_TEST)
- data.cidr = HOST_MASK;
+ e.cidr = HOST_MASK;
- ip6addrptr(skb, opt->flags & IPSET_DIM_ONE_SRC, &data.ip.in6);
- ip6_netmask(&data.ip, data.cidr);
+ ip6addrptr(skb, opt->flags & IPSET_DIM_ONE_SRC, &e.ip.in6);
+ ip6_netmask(&e.ip, e.cidr);
- return adtfn(set, &data, opt_timeout(opt, h), opt->cmdflags);
+ return adtfn(set, &e, &ext, &opt->ext, opt->cmdflags);
}
static int
hash_net6_uadt(struct ip_set *set, struct nlattr *tb[],
enum ipset_adt adt, u32 *lineno, u32 flags, bool retried)
{
- const struct ip_set_hash *h = set->data;
ipset_adtfn adtfn = set->variant->adt[adt];
- struct hash_net6_elem data = { .cidr = HOST_MASK };
- u32 timeout = h->timeout;
+ struct hash_net6_elem e = { .cidr = HOST_MASK };
+ struct ip_set_ext ext = IP_SET_INIT_UEXT(set);
int ret;
if (unlikely(!tb[IPSET_ATTR_IP] ||
!ip_set_optattr_netorder(tb, IPSET_ATTR_TIMEOUT) ||
- !ip_set_optattr_netorder(tb, IPSET_ATTR_CADT_FLAGS)))
+ !ip_set_optattr_netorder(tb, IPSET_ATTR_CADT_FLAGS) ||
+ !ip_set_optattr_netorder(tb, IPSET_ATTR_PACKETS) ||
+ !ip_set_optattr_netorder(tb, IPSET_ATTR_BYTES)))
return -IPSET_ERR_PROTOCOL;
if (unlikely(tb[IPSET_ATTR_IP_TO]))
return -IPSET_ERR_HASH_RANGE_UNSUPPORTED;
@@ -430,107 +326,29 @@ hash_net6_uadt(struct ip_set *set, struct nlattr *tb[],
if (tb[IPSET_ATTR_LINENO])
*lineno = nla_get_u32(tb[IPSET_ATTR_LINENO]);
- ret = ip_set_get_ipaddr6(tb[IPSET_ATTR_IP], &data.ip);
+ ret = ip_set_get_ipaddr6(tb[IPSET_ATTR_IP], &e.ip) ||
+ ip_set_get_extensions(set, tb, &ext);
if (ret)
return ret;
if (tb[IPSET_ATTR_CIDR])
- data.cidr = nla_get_u8(tb[IPSET_ATTR_CIDR]);
+ e.cidr = nla_get_u8(tb[IPSET_ATTR_CIDR]);
- if (!data.cidr || data.cidr > HOST_MASK)
+ if (!e.cidr || e.cidr > HOST_MASK)
return -IPSET_ERR_INVALID_CIDR;
- ip6_netmask(&data.ip, data.cidr);
-
- if (tb[IPSET_ATTR_TIMEOUT]) {
- if (!with_timeout(h->timeout))
- return -IPSET_ERR_TIMEOUT;
- timeout = ip_set_timeout_uget(tb[IPSET_ATTR_TIMEOUT]);
- }
+ ip6_netmask(&e.ip, e.cidr);
- if (tb[IPSET_ATTR_CADT_FLAGS] && adt == IPSET_ADD) {
+ if (tb[IPSET_ATTR_CADT_FLAGS]) {
u32 cadt_flags = ip_set_get_h32(tb[IPSET_ATTR_CADT_FLAGS]);
if (cadt_flags & IPSET_FLAG_NOMATCH)
- flags |= (cadt_flags << 16);
+ flags |= (IPSET_FLAG_NOMATCH << 16);
}
- ret = adtfn(set, &data, timeout, flags);
+ ret = adtfn(set, &e, &ext, &ext, flags);
- return ip_set_eexist(ret, flags) ? 0 : ret;
-}
-
-/* Create hash:ip type of sets */
-
-static int
-hash_net_create(struct ip_set *set, struct nlattr *tb[], u32 flags)
-{
- u32 hashsize = IPSET_DEFAULT_HASHSIZE, maxelem = IPSET_DEFAULT_MAXELEM;
- struct ip_set_hash *h;
- u8 hbits;
- size_t hsize;
-
- if (!(set->family == NFPROTO_IPV4 || set->family == NFPROTO_IPV6))
- return -IPSET_ERR_INVALID_FAMILY;
-
- if (unlikely(!ip_set_optattr_netorder(tb, IPSET_ATTR_HASHSIZE) ||
- !ip_set_optattr_netorder(tb, IPSET_ATTR_MAXELEM) ||
- !ip_set_optattr_netorder(tb, IPSET_ATTR_TIMEOUT)))
- return -IPSET_ERR_PROTOCOL;
-
- if (tb[IPSET_ATTR_HASHSIZE]) {
- hashsize = ip_set_get_h32(tb[IPSET_ATTR_HASHSIZE]);
- if (hashsize < IPSET_MIMINAL_HASHSIZE)
- hashsize = IPSET_MIMINAL_HASHSIZE;
- }
-
- if (tb[IPSET_ATTR_MAXELEM])
- maxelem = ip_set_get_h32(tb[IPSET_ATTR_MAXELEM]);
-
- h = kzalloc(sizeof(*h)
- + sizeof(struct ip_set_hash_nets)
- * (set->family == NFPROTO_IPV4 ? 32 : 128), GFP_KERNEL);
- if (!h)
- return -ENOMEM;
-
- h->maxelem = maxelem;
- get_random_bytes(&h->initval, sizeof(h->initval));
- h->timeout = IPSET_NO_TIMEOUT;
-
- hbits = htable_bits(hashsize);
- hsize = htable_size(hbits);
- if (hsize == 0) {
- kfree(h);
- return -ENOMEM;
- }
- h->table = ip_set_alloc(hsize);
- if (!h->table) {
- kfree(h);
- return -ENOMEM;
- }
- h->table->htable_bits = hbits;
-
- set->data = h;
-
- if (tb[IPSET_ATTR_TIMEOUT]) {
- h->timeout = ip_set_timeout_uget(tb[IPSET_ATTR_TIMEOUT]);
-
- set->variant = set->family == NFPROTO_IPV4
- ? &hash_net4_tvariant : &hash_net6_tvariant;
-
- if (set->family == NFPROTO_IPV4)
- hash_net4_gc_init(set);
- else
- hash_net6_gc_init(set);
- } else {
- set->variant = set->family == NFPROTO_IPV4
- ? &hash_net4_variant : &hash_net6_variant;
- }
-
- pr_debug("create %s hashsize %u (%u) maxelem %u: %p(%p)\n",
- set->name, jhash_size(h->table->htable_bits),
- h->table->htable_bits, h->maxelem, set->data, h->table);
-
- return 0;
+ return ip_set_enomatch(ret, flags, adt, set) ? -ret :
+ ip_set_eexist(ret, flags) ? 0 : ret;
}
static struct ip_set_type hash_net_type __read_mostly = {
@@ -539,8 +357,8 @@ static struct ip_set_type hash_net_type __read_mostly = {
.features = IPSET_TYPE_IP | IPSET_TYPE_NOMATCH,
.dimension = IPSET_DIM_ONE,
.family = NFPROTO_UNSPEC,
- .revision_min = REVISION_MIN,
- .revision_max = REVISION_MAX,
+ .revision_min = IPSET_TYPE_REV_MIN,
+ .revision_max = IPSET_TYPE_REV_MAX,
.create = hash_net_create,
.create_policy = {
[IPSET_ATTR_HASHSIZE] = { .type = NLA_U32 },
@@ -548,6 +366,7 @@ static struct ip_set_type hash_net_type __read_mostly = {
[IPSET_ATTR_PROBES] = { .type = NLA_U8 },
[IPSET_ATTR_RESIZE] = { .type = NLA_U8 },
[IPSET_ATTR_TIMEOUT] = { .type = NLA_U32 },
+ [IPSET_ATTR_CADT_FLAGS] = { .type = NLA_U32 },
},
.adt_policy = {
[IPSET_ATTR_IP] = { .type = NLA_NESTED },
@@ -555,6 +374,9 @@ static struct ip_set_type hash_net_type __read_mostly = {
[IPSET_ATTR_CIDR] = { .type = NLA_U8 },
[IPSET_ATTR_TIMEOUT] = { .type = NLA_U32 },
[IPSET_ATTR_CADT_FLAGS] = { .type = NLA_U32 },
+ [IPSET_ATTR_BYTES] = { .type = NLA_U64 },
+ [IPSET_ATTR_PACKETS] = { .type = NLA_U64 },
+ [IPSET_ATTR_COMMENT] = { .type = NLA_NUL_STRING },
},
.me = THIS_MODULE,
};
diff --git a/net/netfilter/ipset/ip_set_hash_netiface.c b/net/netfilter/ipset/ip_set_hash_netiface.c
index 45a101439bc..db2606805b3 100644
--- a/net/netfilter/ipset/ip_set_hash_netiface.c
+++ b/net/netfilter/ipset/ip_set_hash_netiface.c
@@ -1,4 +1,4 @@
-/* Copyright (C) 2011 Jozsef Kadlecsik <kadlec@blackhole.kfki.hu>
+/* Copyright (C) 2011-2013 Jozsef Kadlecsik <kadlec@blackhole.kfki.hu>
*
* This program is free software; you can redistribute it and/or modify
* it under the terms of the GNU General Public License version 2 as
@@ -21,16 +21,18 @@
#include <linux/netfilter.h>
#include <linux/netfilter/ipset/pfxlen.h>
#include <linux/netfilter/ipset/ip_set.h>
-#include <linux/netfilter/ipset/ip_set_timeout.h>
#include <linux/netfilter/ipset/ip_set_hash.h>
-#define REVISION_MIN 0
-/* 1 nomatch flag support added */
-#define REVISION_MAX 2 /* /0 support added */
+#define IPSET_TYPE_REV_MIN 0
+/* 1 nomatch flag support added */
+/* 2 /0 support added */
+/* 3 Counters support added */
+/* 4 Comments support added */
+#define IPSET_TYPE_REV_MAX 5 /* Forceadd support added */
MODULE_LICENSE("GPL");
MODULE_AUTHOR("Jozsef Kadlecsik <kadlec@blackhole.kfki.hu>");
-IP_SET_MODULE_DESC("hash:net,iface", REVISION_MIN, REVISION_MAX);
+IP_SET_MODULE_DESC("hash:net,iface", IPSET_TYPE_REV_MIN, IPSET_TYPE_REV_MAX);
MODULE_ALIAS("ip_set_hash:net,iface");
/* Interface name rbtree */
@@ -45,31 +47,12 @@ struct iface_node {
static void
rbtree_destroy(struct rb_root *root)
{
- struct rb_node *p, *n = root->rb_node;
- struct iface_node *node;
-
- /* Non-recursive destroy, like in ext3 */
- while (n) {
- if (n->rb_left) {
- n = n->rb_left;
- continue;
- }
- if (n->rb_right) {
- n = n->rb_right;
- continue;
- }
- p = rb_parent(n);
- node = rb_entry(n, struct iface_node, node);
- if (!p)
- *root = RB_ROOT;
- else if (p->rb_left == n)
- p->rb_left = NULL;
- else if (p->rb_right == n)
- p->rb_right = NULL;
+ struct iface_node *node, *next;
+ rbtree_postorder_for_each_entry_safe(node, next, root, node)
kfree(node);
- n = p;
- }
+
+ *root = RB_ROOT;
}
static int
@@ -127,17 +110,14 @@ iface_add(struct rb_root *root, const char **iface)
}
/* Type specific function prefix */
-#define TYPE hash_netiface
-
-static bool
-hash_netiface_same_set(const struct ip_set *a, const struct ip_set *b);
-
-#define hash_netiface4_same_set hash_netiface_same_set
-#define hash_netiface6_same_set hash_netiface_same_set
+#define HTYPE hash_netiface
+#define IP_SET_HASH_WITH_NETS
+#define IP_SET_HASH_WITH_RBTREE
+#define IP_SET_HASH_WITH_MULTI
#define STREQ(a, b) (strcmp(a, b) == 0)
-/* The type variant functions: IPv4 */
+/* IPv4 variant */
struct hash_netiface4_elem_hashed {
__be32 ip;
@@ -147,9 +127,7 @@ struct hash_netiface4_elem_hashed {
u8 elem;
};
-#define HKEY_DATALEN sizeof(struct hash_netiface4_elem_hashed)
-
-/* Member elements without timeout */
+/* Member elements */
struct hash_netiface4_elem {
__be32 ip;
u8 physdev;
@@ -159,16 +137,7 @@ struct hash_netiface4_elem {
const char *iface;
};
-/* Member elements with timeout support */
-struct hash_netiface4_telem {
- __be32 ip;
- u8 physdev;
- u8 cidr;
- u8 nomatch;
- u8 elem;
- const char *iface;
- unsigned long timeout;
-};
+/* Common functions */
static inline bool
hash_netiface4_data_equal(const struct hash_netiface4_elem *ip1,
@@ -182,29 +151,22 @@ hash_netiface4_data_equal(const struct hash_netiface4_elem *ip1,
ip1->iface == ip2->iface;
}
-static inline bool
-hash_netiface4_data_isnull(const struct hash_netiface4_elem *elem)
+static inline int
+hash_netiface4_do_data_match(const struct hash_netiface4_elem *elem)
{
- return elem->elem == 0;
+ return elem->nomatch ? -ENOTEMPTY : 1;
}
static inline void
-hash_netiface4_data_copy(struct hash_netiface4_elem *dst,
- const struct hash_netiface4_elem *src)
+hash_netiface4_data_set_flags(struct hash_netiface4_elem *elem, u32 flags)
{
- memcpy(dst, src, sizeof(*dst));
+ elem->nomatch = (flags >> 16) & IPSET_FLAG_NOMATCH;
}
static inline void
-hash_netiface4_data_flags(struct hash_netiface4_elem *dst, u32 flags)
-{
- dst->nomatch = flags & IPSET_FLAG_NOMATCH;
-}
-
-static inline int
-hash_netiface4_data_match(const struct hash_netiface4_elem *elem)
+hash_netiface4_data_reset_flags(struct hash_netiface4_elem *elem, u8 *flags)
{
- return elem->nomatch ? -ENOTEMPTY : 1;
+ swap(*flags, elem->nomatch);
}
static inline void
@@ -214,12 +176,6 @@ hash_netiface4_data_netmask(struct hash_netiface4_elem *elem, u8 cidr)
elem->cidr = cidr;
}
-static inline void
-hash_netiface4_data_zero_out(struct hash_netiface4_elem *elem)
-{
- elem->elem = 0;
-}
-
static bool
hash_netiface4_data_list(struct sk_buff *skb,
const struct hash_netiface4_elem *data)
@@ -240,66 +196,40 @@ nla_put_failure:
return 1;
}
-static bool
-hash_netiface4_data_tlist(struct sk_buff *skb,
- const struct hash_netiface4_elem *data)
+static inline void
+hash_netiface4_data_next(struct hash_netiface4_elem *next,
+ const struct hash_netiface4_elem *d)
{
- const struct hash_netiface4_telem *tdata =
- (const struct hash_netiface4_telem *)data;
- u32 flags = data->physdev ? IPSET_FLAG_PHYSDEV : 0;
-
- if (data->nomatch)
- flags |= IPSET_FLAG_NOMATCH;
- if (nla_put_ipaddr4(skb, IPSET_ATTR_IP, data->ip) ||
- nla_put_u8(skb, IPSET_ATTR_CIDR, data->cidr) ||
- nla_put_string(skb, IPSET_ATTR_IFACE, data->iface) ||
- (flags &&
- nla_put_net32(skb, IPSET_ATTR_CADT_FLAGS, htonl(flags))) ||
- nla_put_net32(skb, IPSET_ATTR_TIMEOUT,
- htonl(ip_set_timeout_get(tdata->timeout))))
- goto nla_put_failure;
-
- return 0;
-
-nla_put_failure:
- return 1;
+ next->ip = d->ip;
}
-#define IP_SET_HASH_WITH_NETS
-#define IP_SET_HASH_WITH_RBTREE
-#define IP_SET_HASH_WITH_MULTI
-
+#define MTYPE hash_netiface4
#define PF 4
#define HOST_MASK 32
-#include <linux/netfilter/ipset/ip_set_ahash.h>
-
-static inline void
-hash_netiface4_data_next(struct ip_set_hash *h,
- const struct hash_netiface4_elem *d)
-{
- h->next.ip = d->ip;
-}
+#define HKEY_DATALEN sizeof(struct hash_netiface4_elem_hashed)
+#include "ip_set_hash_gen.h"
static int
hash_netiface4_kadt(struct ip_set *set, const struct sk_buff *skb,
const struct xt_action_param *par,
- enum ipset_adt adt, const struct ip_set_adt_opt *opt)
+ enum ipset_adt adt, struct ip_set_adt_opt *opt)
{
- struct ip_set_hash *h = set->data;
+ struct hash_netiface *h = set->data;
ipset_adtfn adtfn = set->variant->adt[adt];
- struct hash_netiface4_elem data = {
- .cidr = h->nets[0].cidr ? h->nets[0].cidr : HOST_MASK,
+ struct hash_netiface4_elem e = {
+ .cidr = IP_SET_INIT_CIDR(h->nets[0].cidr[0], HOST_MASK),
.elem = 1,
};
+ struct ip_set_ext ext = IP_SET_INIT_KEXT(skb, opt, set);
int ret;
- if (data.cidr == 0)
+ if (e.cidr == 0)
return -EINVAL;
if (adt == IPSET_TEST)
- data.cidr = HOST_MASK;
+ e.cidr = HOST_MASK;
- ip4addrptr(skb, opt->flags & IPSET_DIM_ONE_SRC, &data.ip);
- data.ip &= ip_set_netmask(data.cidr);
+ ip4addrptr(skb, opt->flags & IPSET_DIM_ONE_SRC, &e.ip);
+ e.ip &= ip_set_netmask(e.cidr);
#define IFACE(dir) (par->dir ? par->dir->name : NULL)
#define PHYSDEV(dir) (nf_bridge->dir ? nf_bridge->dir->name : NULL)
@@ -311,72 +241,69 @@ hash_netiface4_kadt(struct ip_set *set, const struct sk_buff *skb,
if (!nf_bridge)
return -EINVAL;
- data.iface = SRCDIR ? PHYSDEV(physindev) : PHYSDEV(physoutdev);
- data.physdev = 1;
+ e.iface = SRCDIR ? PHYSDEV(physindev) : PHYSDEV(physoutdev);
+ e.physdev = 1;
#else
- data.iface = NULL;
+ e.iface = NULL;
#endif
} else
- data.iface = SRCDIR ? IFACE(in) : IFACE(out);
+ e.iface = SRCDIR ? IFACE(in) : IFACE(out);
- if (!data.iface)
+ if (!e.iface)
return -EINVAL;
- ret = iface_test(&h->rbtree, &data.iface);
+ ret = iface_test(&h->rbtree, &e.iface);
if (adt == IPSET_ADD) {
if (!ret) {
- ret = iface_add(&h->rbtree, &data.iface);
+ ret = iface_add(&h->rbtree, &e.iface);
if (ret)
return ret;
}
} else if (!ret)
return ret;
- return adtfn(set, &data, opt_timeout(opt, h), opt->cmdflags);
+ return adtfn(set, &e, &ext, &opt->ext, opt->cmdflags);
}
static int
hash_netiface4_uadt(struct ip_set *set, struct nlattr *tb[],
enum ipset_adt adt, u32 *lineno, u32 flags, bool retried)
{
- struct ip_set_hash *h = set->data;
+ struct hash_netiface *h = set->data;
ipset_adtfn adtfn = set->variant->adt[adt];
- struct hash_netiface4_elem data = { .cidr = HOST_MASK, .elem = 1 };
- u32 ip = 0, ip_to, last;
- u32 timeout = h->timeout;
+ struct hash_netiface4_elem e = { .cidr = HOST_MASK, .elem = 1 };
+ struct ip_set_ext ext = IP_SET_INIT_UEXT(set);
+ u32 ip = 0, ip_to = 0, last;
char iface[IFNAMSIZ];
int ret;
if (unlikely(!tb[IPSET_ATTR_IP] ||
!tb[IPSET_ATTR_IFACE] ||
!ip_set_optattr_netorder(tb, IPSET_ATTR_TIMEOUT) ||
- !ip_set_optattr_netorder(tb, IPSET_ATTR_CADT_FLAGS)))
+ !ip_set_optattr_netorder(tb, IPSET_ATTR_CADT_FLAGS) ||
+ !ip_set_optattr_netorder(tb, IPSET_ATTR_PACKETS) ||
+ !ip_set_optattr_netorder(tb, IPSET_ATTR_BYTES)))
return -IPSET_ERR_PROTOCOL;
if (tb[IPSET_ATTR_LINENO])
*lineno = nla_get_u32(tb[IPSET_ATTR_LINENO]);
- ret = ip_set_get_hostipaddr4(tb[IPSET_ATTR_IP], &ip);
+ ret = ip_set_get_hostipaddr4(tb[IPSET_ATTR_IP], &ip) ||
+ ip_set_get_extensions(set, tb, &ext);
if (ret)
return ret;
if (tb[IPSET_ATTR_CIDR]) {
- data.cidr = nla_get_u8(tb[IPSET_ATTR_CIDR]);
- if (data.cidr > HOST_MASK)
+ e.cidr = nla_get_u8(tb[IPSET_ATTR_CIDR]);
+ if (e.cidr > HOST_MASK)
return -IPSET_ERR_INVALID_CIDR;
}
- if (tb[IPSET_ATTR_TIMEOUT]) {
- if (!with_timeout(h->timeout))
- return -IPSET_ERR_TIMEOUT;
- timeout = ip_set_timeout_uget(tb[IPSET_ATTR_TIMEOUT]);
- }
-
strcpy(iface, nla_data(tb[IPSET_ATTR_IFACE]));
- data.iface = iface;
- ret = iface_test(&h->rbtree, &data.iface);
+ e.iface = iface;
+ ret = iface_test(&h->rbtree, &e.iface);
if (adt == IPSET_ADD) {
if (!ret) {
- ret = iface_add(&h->rbtree, &data.iface);
+ ret = iface_add(&h->rbtree, &e.iface);
if (ret)
return ret;
}
@@ -386,14 +313,15 @@ hash_netiface4_uadt(struct ip_set *set, struct nlattr *tb[],
if (tb[IPSET_ATTR_CADT_FLAGS]) {
u32 cadt_flags = ip_set_get_h32(tb[IPSET_ATTR_CADT_FLAGS]);
if (cadt_flags & IPSET_FLAG_PHYSDEV)
- data.physdev = 1;
- if (adt == IPSET_ADD && (cadt_flags & IPSET_FLAG_NOMATCH))
- flags |= (cadt_flags << 16);
+ e.physdev = 1;
+ if (cadt_flags & IPSET_FLAG_NOMATCH)
+ flags |= (IPSET_FLAG_NOMATCH << 16);
}
if (adt == IPSET_TEST || !tb[IPSET_ATTR_IP_TO]) {
- data.ip = htonl(ip & ip_set_hostmask(data.cidr));
- ret = adtfn(set, &data, timeout, flags);
- return ip_set_eexist(ret, flags) ? 0 : ret;
+ e.ip = htonl(ip & ip_set_hostmask(e.cidr));
+ ret = adtfn(set, &e, &ext, &ext, flags);
+ return ip_set_enomatch(ret, flags, adt, set) ? -ret :
+ ip_set_eexist(ret, flags) ? 0 : ret;
}
if (tb[IPSET_ATTR_IP_TO]) {
@@ -404,16 +332,15 @@ hash_netiface4_uadt(struct ip_set *set, struct nlattr *tb[],
swap(ip, ip_to);
if (ip + UINT_MAX == ip_to)
return -IPSET_ERR_HASH_RANGE;
- } else {
- ip_set_mask_from_to(ip, ip_to, data.cidr);
- }
+ } else
+ ip_set_mask_from_to(ip, ip_to, e.cidr);
if (retried)
ip = ntohl(h->next.ip);
while (!after(ip, ip_to)) {
- data.ip = htonl(ip);
- last = ip_set_range_to_cidr(ip, ip_to, &data.cidr);
- ret = adtfn(set, &data, timeout, flags);
+ e.ip = htonl(ip);
+ last = ip_set_range_to_cidr(ip, ip_to, &e.cidr);
+ ret = adtfn(set, &e, &ext, &ext, flags);
if (ret && !ip_set_eexist(ret, flags))
return ret;
@@ -424,18 +351,7 @@ hash_netiface4_uadt(struct ip_set *set, struct nlattr *tb[],
return ret;
}
-static bool
-hash_netiface_same_set(const struct ip_set *a, const struct ip_set *b)
-{
- const struct ip_set_hash *x = a->data;
- const struct ip_set_hash *y = b->data;
-
- /* Resizing changes htable_bits, so we ignore it */
- return x->maxelem == y->maxelem &&
- x->timeout == y->timeout;
-}
-
-/* The type variant functions: IPv6 */
+/* IPv6 variant */
struct hash_netiface6_elem_hashed {
union nf_inet_addr ip;
@@ -445,8 +361,6 @@ struct hash_netiface6_elem_hashed {
u8 elem;
};
-#define HKEY_DATALEN sizeof(struct hash_netiface6_elem_hashed)
-
struct hash_netiface6_elem {
union nf_inet_addr ip;
u8 physdev;
@@ -456,66 +370,36 @@ struct hash_netiface6_elem {
const char *iface;
};
-struct hash_netiface6_telem {
- union nf_inet_addr ip;
- u8 physdev;
- u8 cidr;
- u8 nomatch;
- u8 elem;
- const char *iface;
- unsigned long timeout;
-};
+/* Common functions */
static inline bool
hash_netiface6_data_equal(const struct hash_netiface6_elem *ip1,
const struct hash_netiface6_elem *ip2,
u32 *multi)
{
- return ipv6_addr_cmp(&ip1->ip.in6, &ip2->ip.in6) == 0 &&
+ return ipv6_addr_equal(&ip1->ip.in6, &ip2->ip.in6) &&
ip1->cidr == ip2->cidr &&
(++*multi) &&
ip1->physdev == ip2->physdev &&
ip1->iface == ip2->iface;
}
-static inline bool
-hash_netiface6_data_isnull(const struct hash_netiface6_elem *elem)
-{
- return elem->elem == 0;
-}
-
-static inline void
-hash_netiface6_data_copy(struct hash_netiface6_elem *dst,
- const struct hash_netiface6_elem *src)
-{
- memcpy(dst, src, sizeof(*dst));
-}
-
-static inline void
-hash_netiface6_data_flags(struct hash_netiface6_elem *dst, u32 flags)
-{
- dst->nomatch = flags & IPSET_FLAG_NOMATCH;
-}
-
static inline int
-hash_netiface6_data_match(const struct hash_netiface6_elem *elem)
+hash_netiface6_do_data_match(const struct hash_netiface6_elem *elem)
{
return elem->nomatch ? -ENOTEMPTY : 1;
}
static inline void
-hash_netiface6_data_zero_out(struct hash_netiface6_elem *elem)
+hash_netiface6_data_set_flags(struct hash_netiface6_elem *elem, u32 flags)
{
- elem->elem = 0;
+ elem->nomatch = (flags >> 16) & IPSET_FLAG_NOMATCH;
}
static inline void
-ip6_netmask(union nf_inet_addr *ip, u8 prefix)
+hash_netiface6_data_reset_flags(struct hash_netiface6_elem *elem, u8 *flags)
{
- ip->ip6[0] &= ip_set_netmask6(prefix)[0];
- ip->ip6[1] &= ip_set_netmask6(prefix)[1];
- ip->ip6[2] &= ip_set_netmask6(prefix)[2];
- ip->ip6[3] &= ip_set_netmask6(prefix)[3];
+ swap(*flags, elem->nomatch);
}
static inline void
@@ -545,63 +429,45 @@ nla_put_failure:
return 1;
}
-static bool
-hash_netiface6_data_tlist(struct sk_buff *skb,
- const struct hash_netiface6_elem *data)
+static inline void
+hash_netiface6_data_next(struct hash_netiface4_elem *next,
+ const struct hash_netiface6_elem *d)
{
- const struct hash_netiface6_telem *e =
- (const struct hash_netiface6_telem *)data;
- u32 flags = data->physdev ? IPSET_FLAG_PHYSDEV : 0;
-
- if (data->nomatch)
- flags |= IPSET_FLAG_NOMATCH;
- if (nla_put_ipaddr6(skb, IPSET_ATTR_IP, &e->ip.in6) ||
- nla_put_u8(skb, IPSET_ATTR_CIDR, data->cidr) ||
- nla_put_string(skb, IPSET_ATTR_IFACE, data->iface) ||
- (flags &&
- nla_put_net32(skb, IPSET_ATTR_CADT_FLAGS, htonl(flags))) ||
- nla_put_net32(skb, IPSET_ATTR_TIMEOUT,
- htonl(ip_set_timeout_get(e->timeout))))
- goto nla_put_failure;
- return 0;
-
-nla_put_failure:
- return 1;
}
+#undef MTYPE
#undef PF
#undef HOST_MASK
+#undef HKEY_DATALEN
+#define MTYPE hash_netiface6
#define PF 6
#define HOST_MASK 128
-#include <linux/netfilter/ipset/ip_set_ahash.h>
-
-static inline void
-hash_netiface6_data_next(struct ip_set_hash *h,
- const struct hash_netiface6_elem *d)
-{
-}
+#define HKEY_DATALEN sizeof(struct hash_netiface6_elem_hashed)
+#define IP_SET_EMIT_CREATE
+#include "ip_set_hash_gen.h"
static int
hash_netiface6_kadt(struct ip_set *set, const struct sk_buff *skb,
const struct xt_action_param *par,
- enum ipset_adt adt, const struct ip_set_adt_opt *opt)
+ enum ipset_adt adt, struct ip_set_adt_opt *opt)
{
- struct ip_set_hash *h = set->data;
+ struct hash_netiface *h = set->data;
ipset_adtfn adtfn = set->variant->adt[adt];
- struct hash_netiface6_elem data = {
- .cidr = h->nets[0].cidr ? h->nets[0].cidr : HOST_MASK,
+ struct hash_netiface6_elem e = {
+ .cidr = IP_SET_INIT_CIDR(h->nets[0].cidr[0], HOST_MASK),
.elem = 1,
};
+ struct ip_set_ext ext = IP_SET_INIT_KEXT(skb, opt, set);
int ret;
- if (data.cidr == 0)
+ if (e.cidr == 0)
return -EINVAL;
if (adt == IPSET_TEST)
- data.cidr = HOST_MASK;
+ e.cidr = HOST_MASK;
- ip6addrptr(skb, opt->flags & IPSET_DIM_ONE_SRC, &data.ip.in6);
- ip6_netmask(&data.ip, data.cidr);
+ ip6addrptr(skb, opt->flags & IPSET_DIM_ONE_SRC, &e.ip.in6);
+ ip6_netmask(&e.ip, e.cidr);
if (opt->cmdflags & IPSET_FLAG_PHYSDEV) {
#ifdef CONFIG_BRIDGE_NETFILTER
@@ -609,44 +475,46 @@ hash_netiface6_kadt(struct ip_set *set, const struct sk_buff *skb,
if (!nf_bridge)
return -EINVAL;
- data.iface = SRCDIR ? PHYSDEV(physindev) : PHYSDEV(physoutdev);
- data.physdev = 1;
+ e.iface = SRCDIR ? PHYSDEV(physindev) : PHYSDEV(physoutdev);
+ e.physdev = 1;
#else
- data.iface = NULL;
+ e.iface = NULL;
#endif
} else
- data.iface = SRCDIR ? IFACE(in) : IFACE(out);
+ e.iface = SRCDIR ? IFACE(in) : IFACE(out);
- if (!data.iface)
+ if (!e.iface)
return -EINVAL;
- ret = iface_test(&h->rbtree, &data.iface);
+ ret = iface_test(&h->rbtree, &e.iface);
if (adt == IPSET_ADD) {
if (!ret) {
- ret = iface_add(&h->rbtree, &data.iface);
+ ret = iface_add(&h->rbtree, &e.iface);
if (ret)
return ret;
}
} else if (!ret)
return ret;
- return adtfn(set, &data, opt_timeout(opt, h), opt->cmdflags);
+ return adtfn(set, &e, &ext, &opt->ext, opt->cmdflags);
}
static int
hash_netiface6_uadt(struct ip_set *set, struct nlattr *tb[],
enum ipset_adt adt, u32 *lineno, u32 flags, bool retried)
{
- struct ip_set_hash *h = set->data;
+ struct hash_netiface *h = set->data;
ipset_adtfn adtfn = set->variant->adt[adt];
- struct hash_netiface6_elem data = { .cidr = HOST_MASK, .elem = 1 };
- u32 timeout = h->timeout;
+ struct hash_netiface6_elem e = { .cidr = HOST_MASK, .elem = 1 };
+ struct ip_set_ext ext = IP_SET_INIT_UEXT(set);
char iface[IFNAMSIZ];
int ret;
if (unlikely(!tb[IPSET_ATTR_IP] ||
!tb[IPSET_ATTR_IFACE] ||
!ip_set_optattr_netorder(tb, IPSET_ATTR_TIMEOUT) ||
- !ip_set_optattr_netorder(tb, IPSET_ATTR_CADT_FLAGS)))
+ !ip_set_optattr_netorder(tb, IPSET_ATTR_CADT_FLAGS) ||
+ !ip_set_optattr_netorder(tb, IPSET_ATTR_PACKETS) ||
+ !ip_set_optattr_netorder(tb, IPSET_ATTR_BYTES)))
return -IPSET_ERR_PROTOCOL;
if (unlikely(tb[IPSET_ATTR_IP_TO]))
return -IPSET_ERR_HASH_RANGE_UNSUPPORTED;
@@ -654,28 +522,23 @@ hash_netiface6_uadt(struct ip_set *set, struct nlattr *tb[],
if (tb[IPSET_ATTR_LINENO])
*lineno = nla_get_u32(tb[IPSET_ATTR_LINENO]);
- ret = ip_set_get_ipaddr6(tb[IPSET_ATTR_IP], &data.ip);
+ ret = ip_set_get_ipaddr6(tb[IPSET_ATTR_IP], &e.ip) ||
+ ip_set_get_extensions(set, tb, &ext);
if (ret)
return ret;
if (tb[IPSET_ATTR_CIDR])
- data.cidr = nla_get_u8(tb[IPSET_ATTR_CIDR]);
- if (data.cidr > HOST_MASK)
+ e.cidr = nla_get_u8(tb[IPSET_ATTR_CIDR]);
+ if (e.cidr > HOST_MASK)
return -IPSET_ERR_INVALID_CIDR;
- ip6_netmask(&data.ip, data.cidr);
-
- if (tb[IPSET_ATTR_TIMEOUT]) {
- if (!with_timeout(h->timeout))
- return -IPSET_ERR_TIMEOUT;
- timeout = ip_set_timeout_uget(tb[IPSET_ATTR_TIMEOUT]);
- }
+ ip6_netmask(&e.ip, e.cidr);
strcpy(iface, nla_data(tb[IPSET_ATTR_IFACE]));
- data.iface = iface;
- ret = iface_test(&h->rbtree, &data.iface);
+ e.iface = iface;
+ ret = iface_test(&h->rbtree, &e.iface);
if (adt == IPSET_ADD) {
if (!ret) {
- ret = iface_add(&h->rbtree, &data.iface);
+ ret = iface_add(&h->rbtree, &e.iface);
if (ret)
return ret;
}
@@ -685,90 +548,15 @@ hash_netiface6_uadt(struct ip_set *set, struct nlattr *tb[],
if (tb[IPSET_ATTR_CADT_FLAGS]) {
u32 cadt_flags = ip_set_get_h32(tb[IPSET_ATTR_CADT_FLAGS]);
if (cadt_flags & IPSET_FLAG_PHYSDEV)
- data.physdev = 1;
- if (adt == IPSET_ADD && (cadt_flags & IPSET_FLAG_NOMATCH))
- flags |= (cadt_flags << 16);
- }
-
- ret = adtfn(set, &data, timeout, flags);
-
- return ip_set_eexist(ret, flags) ? 0 : ret;
-}
-
-/* Create hash:ip type of sets */
-
-static int
-hash_netiface_create(struct ip_set *set, struct nlattr *tb[], u32 flags)
-{
- struct ip_set_hash *h;
- u32 hashsize = IPSET_DEFAULT_HASHSIZE, maxelem = IPSET_DEFAULT_MAXELEM;
- u8 hbits;
- size_t hsize;
-
- if (!(set->family == NFPROTO_IPV4 || set->family == NFPROTO_IPV6))
- return -IPSET_ERR_INVALID_FAMILY;
-
- if (unlikely(!ip_set_optattr_netorder(tb, IPSET_ATTR_HASHSIZE) ||
- !ip_set_optattr_netorder(tb, IPSET_ATTR_MAXELEM) ||
- !ip_set_optattr_netorder(tb, IPSET_ATTR_TIMEOUT)))
- return -IPSET_ERR_PROTOCOL;
-
- if (tb[IPSET_ATTR_HASHSIZE]) {
- hashsize = ip_set_get_h32(tb[IPSET_ATTR_HASHSIZE]);
- if (hashsize < IPSET_MIMINAL_HASHSIZE)
- hashsize = IPSET_MIMINAL_HASHSIZE;
- }
-
- if (tb[IPSET_ATTR_MAXELEM])
- maxelem = ip_set_get_h32(tb[IPSET_ATTR_MAXELEM]);
-
- h = kzalloc(sizeof(*h)
- + sizeof(struct ip_set_hash_nets)
- * (set->family == NFPROTO_IPV4 ? 32 : 128), GFP_KERNEL);
- if (!h)
- return -ENOMEM;
-
- h->maxelem = maxelem;
- get_random_bytes(&h->initval, sizeof(h->initval));
- h->timeout = IPSET_NO_TIMEOUT;
- h->ahash_max = AHASH_MAX_SIZE;
-
- hbits = htable_bits(hashsize);
- hsize = htable_size(hbits);
- if (hsize == 0) {
- kfree(h);
- return -ENOMEM;
- }
- h->table = ip_set_alloc(hsize);
- if (!h->table) {
- kfree(h);
- return -ENOMEM;
+ e.physdev = 1;
+ if (cadt_flags & IPSET_FLAG_NOMATCH)
+ flags |= (IPSET_FLAG_NOMATCH << 16);
}
- h->table->htable_bits = hbits;
- h->rbtree = RB_ROOT;
-
- set->data = h;
-
- if (tb[IPSET_ATTR_TIMEOUT]) {
- h->timeout = ip_set_timeout_uget(tb[IPSET_ATTR_TIMEOUT]);
- set->variant = set->family == NFPROTO_IPV4
- ? &hash_netiface4_tvariant : &hash_netiface6_tvariant;
+ ret = adtfn(set, &e, &ext, &ext, flags);
- if (set->family == NFPROTO_IPV4)
- hash_netiface4_gc_init(set);
- else
- hash_netiface6_gc_init(set);
- } else {
- set->variant = set->family == NFPROTO_IPV4
- ? &hash_netiface4_variant : &hash_netiface6_variant;
- }
-
- pr_debug("create %s hashsize %u (%u) maxelem %u: %p(%p)\n",
- set->name, jhash_size(h->table->htable_bits),
- h->table->htable_bits, h->maxelem, set->data, h->table);
-
- return 0;
+ return ip_set_enomatch(ret, flags, adt, set) ? -ret :
+ ip_set_eexist(ret, flags) ? 0 : ret;
}
static struct ip_set_type hash_netiface_type __read_mostly = {
@@ -778,8 +566,8 @@ static struct ip_set_type hash_netiface_type __read_mostly = {
IPSET_TYPE_NOMATCH,
.dimension = IPSET_DIM_TWO,
.family = NFPROTO_UNSPEC,
- .revision_min = REVISION_MIN,
- .revision_max = REVISION_MAX,
+ .revision_min = IPSET_TYPE_REV_MIN,
+ .revision_max = IPSET_TYPE_REV_MAX,
.create = hash_netiface_create,
.create_policy = {
[IPSET_ATTR_HASHSIZE] = { .type = NLA_U32 },
@@ -788,6 +576,7 @@ static struct ip_set_type hash_netiface_type __read_mostly = {
[IPSET_ATTR_RESIZE] = { .type = NLA_U8 },
[IPSET_ATTR_PROTO] = { .type = NLA_U8 },
[IPSET_ATTR_TIMEOUT] = { .type = NLA_U32 },
+ [IPSET_ATTR_CADT_FLAGS] = { .type = NLA_U32 },
},
.adt_policy = {
[IPSET_ATTR_IP] = { .type = NLA_NESTED },
@@ -798,6 +587,9 @@ static struct ip_set_type hash_netiface_type __read_mostly = {
[IPSET_ATTR_CIDR] = { .type = NLA_U8 },
[IPSET_ATTR_TIMEOUT] = { .type = NLA_U32 },
[IPSET_ATTR_LINENO] = { .type = NLA_U32 },
+ [IPSET_ATTR_BYTES] = { .type = NLA_U64 },
+ [IPSET_ATTR_PACKETS] = { .type = NLA_U64 },
+ [IPSET_ATTR_COMMENT] = { .type = NLA_NUL_STRING },
},
.me = THIS_MODULE,
};
diff --git a/net/netfilter/ipset/ip_set_hash_netnet.c b/net/netfilter/ipset/ip_set_hash_netnet.c
new file mode 100644
index 00000000000..3e99987e4bf
--- /dev/null
+++ b/net/netfilter/ipset/ip_set_hash_netnet.c
@@ -0,0 +1,481 @@
+/* Copyright (C) 2003-2013 Jozsef Kadlecsik <kadlec@blackhole.kfki.hu>
+ * Copyright (C) 2013 Oliver Smith <oliver@8.c.9.b.0.7.4.0.1.0.0.2.ip6.arpa>
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2 as
+ * published by the Free Software Foundation.
+ */
+
+/* Kernel module implementing an IP set type: the hash:net type */
+
+#include <linux/jhash.h>
+#include <linux/module.h>
+#include <linux/ip.h>
+#include <linux/skbuff.h>
+#include <linux/errno.h>
+#include <linux/random.h>
+#include <net/ip.h>
+#include <net/ipv6.h>
+#include <net/netlink.h>
+
+#include <linux/netfilter.h>
+#include <linux/netfilter/ipset/pfxlen.h>
+#include <linux/netfilter/ipset/ip_set.h>
+#include <linux/netfilter/ipset/ip_set_hash.h>
+
+#define IPSET_TYPE_REV_MIN 0
+#define IPSET_TYPE_REV_MAX 1 /* Forceadd support added */
+
+MODULE_LICENSE("GPL");
+MODULE_AUTHOR("Oliver Smith <oliver@8.c.9.b.0.7.4.0.1.0.0.2.ip6.arpa>");
+IP_SET_MODULE_DESC("hash:net,net", IPSET_TYPE_REV_MIN, IPSET_TYPE_REV_MAX);
+MODULE_ALIAS("ip_set_hash:net,net");
+
+/* Type specific function prefix */
+#define HTYPE hash_netnet
+#define IP_SET_HASH_WITH_NETS
+#define IPSET_NET_COUNT 2
+
+/* IPv4 variants */
+
+/* Member elements */
+struct hash_netnet4_elem {
+ union {
+ __be32 ip[2];
+ __be64 ipcmp;
+ };
+ u8 nomatch;
+ union {
+ u8 cidr[2];
+ u16 ccmp;
+ };
+};
+
+/* Common functions */
+
+static inline bool
+hash_netnet4_data_equal(const struct hash_netnet4_elem *ip1,
+ const struct hash_netnet4_elem *ip2,
+ u32 *multi)
+{
+ return ip1->ipcmp == ip2->ipcmp &&
+ ip1->ccmp == ip2->ccmp;
+}
+
+static inline int
+hash_netnet4_do_data_match(const struct hash_netnet4_elem *elem)
+{
+ return elem->nomatch ? -ENOTEMPTY : 1;
+}
+
+static inline void
+hash_netnet4_data_set_flags(struct hash_netnet4_elem *elem, u32 flags)
+{
+ elem->nomatch = (flags >> 16) & IPSET_FLAG_NOMATCH;
+}
+
+static inline void
+hash_netnet4_data_reset_flags(struct hash_netnet4_elem *elem, u8 *flags)
+{
+ swap(*flags, elem->nomatch);
+}
+
+static inline void
+hash_netnet4_data_reset_elem(struct hash_netnet4_elem *elem,
+ struct hash_netnet4_elem *orig)
+{
+ elem->ip[1] = orig->ip[1];
+}
+
+static inline void
+hash_netnet4_data_netmask(struct hash_netnet4_elem *elem, u8 cidr, bool inner)
+{
+ if (inner) {
+ elem->ip[1] &= ip_set_netmask(cidr);
+ elem->cidr[1] = cidr;
+ } else {
+ elem->ip[0] &= ip_set_netmask(cidr);
+ elem->cidr[0] = cidr;
+ }
+}
+
+static bool
+hash_netnet4_data_list(struct sk_buff *skb,
+ const struct hash_netnet4_elem *data)
+{
+ u32 flags = data->nomatch ? IPSET_FLAG_NOMATCH : 0;
+
+ if (nla_put_ipaddr4(skb, IPSET_ATTR_IP, data->ip[0]) ||
+ nla_put_ipaddr4(skb, IPSET_ATTR_IP2, data->ip[1]) ||
+ nla_put_u8(skb, IPSET_ATTR_CIDR, data->cidr[0]) ||
+ nla_put_u8(skb, IPSET_ATTR_CIDR2, data->cidr[1]) ||
+ (flags &&
+ nla_put_net32(skb, IPSET_ATTR_CADT_FLAGS, htonl(flags))))
+ goto nla_put_failure;
+ return false;
+
+nla_put_failure:
+ return true;
+}
+
+static inline void
+hash_netnet4_data_next(struct hash_netnet4_elem *next,
+ const struct hash_netnet4_elem *d)
+{
+ next->ipcmp = d->ipcmp;
+}
+
+#define MTYPE hash_netnet4
+#define PF 4
+#define HOST_MASK 32
+#include "ip_set_hash_gen.h"
+
+static int
+hash_netnet4_kadt(struct ip_set *set, const struct sk_buff *skb,
+ const struct xt_action_param *par,
+ enum ipset_adt adt, struct ip_set_adt_opt *opt)
+{
+ const struct hash_netnet *h = set->data;
+ ipset_adtfn adtfn = set->variant->adt[adt];
+ struct hash_netnet4_elem e = { };
+ struct ip_set_ext ext = IP_SET_INIT_KEXT(skb, opt, set);
+
+ e.cidr[0] = IP_SET_INIT_CIDR(h->nets[0].cidr[0], HOST_MASK);
+ e.cidr[1] = IP_SET_INIT_CIDR(h->nets[0].cidr[1], HOST_MASK);
+ if (adt == IPSET_TEST)
+ e.ccmp = (HOST_MASK << (sizeof(e.cidr[0]) * 8)) | HOST_MASK;
+
+ ip4addrptr(skb, opt->flags & IPSET_DIM_ONE_SRC, &e.ip[0]);
+ ip4addrptr(skb, opt->flags & IPSET_DIM_TWO_SRC, &e.ip[1]);
+ e.ip[0] &= ip_set_netmask(e.cidr[0]);
+ e.ip[1] &= ip_set_netmask(e.cidr[1]);
+
+ return adtfn(set, &e, &ext, &opt->ext, opt->cmdflags);
+}
+
+static int
+hash_netnet4_uadt(struct ip_set *set, struct nlattr *tb[],
+ enum ipset_adt adt, u32 *lineno, u32 flags, bool retried)
+{
+ const struct hash_netnet *h = set->data;
+ ipset_adtfn adtfn = set->variant->adt[adt];
+ struct hash_netnet4_elem e = { };
+ struct ip_set_ext ext = IP_SET_INIT_UEXT(set);
+ u32 ip = 0, ip_to = 0, last;
+ u32 ip2 = 0, ip2_from = 0, ip2_to = 0, last2;
+ u8 cidr, cidr2;
+ int ret;
+
+ e.cidr[0] = e.cidr[1] = HOST_MASK;
+ if (unlikely(!tb[IPSET_ATTR_IP] || !tb[IPSET_ATTR_IP2] ||
+ !ip_set_optattr_netorder(tb, IPSET_ATTR_TIMEOUT) ||
+ !ip_set_optattr_netorder(tb, IPSET_ATTR_CADT_FLAGS) ||
+ !ip_set_optattr_netorder(tb, IPSET_ATTR_PACKETS) ||
+ !ip_set_optattr_netorder(tb, IPSET_ATTR_BYTES)))
+ return -IPSET_ERR_PROTOCOL;
+
+ if (tb[IPSET_ATTR_LINENO])
+ *lineno = nla_get_u32(tb[IPSET_ATTR_LINENO]);
+
+ ret = ip_set_get_hostipaddr4(tb[IPSET_ATTR_IP], &ip) ||
+ ip_set_get_hostipaddr4(tb[IPSET_ATTR_IP2], &ip2_from) ||
+ ip_set_get_extensions(set, tb, &ext);
+ if (ret)
+ return ret;
+
+ if (tb[IPSET_ATTR_CIDR]) {
+ cidr = nla_get_u8(tb[IPSET_ATTR_CIDR]);
+ if (!cidr || cidr > HOST_MASK)
+ return -IPSET_ERR_INVALID_CIDR;
+ e.cidr[0] = cidr;
+ }
+
+ if (tb[IPSET_ATTR_CIDR2]) {
+ cidr2 = nla_get_u8(tb[IPSET_ATTR_CIDR2]);
+ if (!cidr2 || cidr2 > HOST_MASK)
+ return -IPSET_ERR_INVALID_CIDR;
+ e.cidr[1] = cidr2;
+ }
+
+ if (tb[IPSET_ATTR_CADT_FLAGS]) {
+ u32 cadt_flags = ip_set_get_h32(tb[IPSET_ATTR_CADT_FLAGS]);
+ if (cadt_flags & IPSET_FLAG_NOMATCH)
+ flags |= (IPSET_FLAG_NOMATCH << 16);
+ }
+
+ if (adt == IPSET_TEST || !(tb[IPSET_ATTR_IP_TO] &&
+ tb[IPSET_ATTR_IP2_TO])) {
+ e.ip[0] = htonl(ip & ip_set_hostmask(e.cidr[0]));
+ e.ip[1] = htonl(ip2_from & ip_set_hostmask(e.cidr[1]));
+ ret = adtfn(set, &e, &ext, &ext, flags);
+ return ip_set_enomatch(ret, flags, adt, set) ? -ret :
+ ip_set_eexist(ret, flags) ? 0 : ret;
+ }
+
+ ip_to = ip;
+ if (tb[IPSET_ATTR_IP_TO]) {
+ ret = ip_set_get_hostipaddr4(tb[IPSET_ATTR_IP_TO], &ip_to);
+ if (ret)
+ return ret;
+ if (ip_to < ip)
+ swap(ip, ip_to);
+ if (ip + UINT_MAX == ip_to)
+ return -IPSET_ERR_HASH_RANGE;
+ }
+
+ ip2_to = ip2_from;
+ if (tb[IPSET_ATTR_IP2_TO]) {
+ ret = ip_set_get_hostipaddr4(tb[IPSET_ATTR_IP2_TO], &ip2_to);
+ if (ret)
+ return ret;
+ if (ip2_to < ip2_from)
+ swap(ip2_from, ip2_to);
+ if (ip2_from + UINT_MAX == ip2_to)
+ return -IPSET_ERR_HASH_RANGE;
+
+ }
+
+ if (retried)
+ ip = ntohl(h->next.ip[0]);
+
+ while (!after(ip, ip_to)) {
+ e.ip[0] = htonl(ip);
+ last = ip_set_range_to_cidr(ip, ip_to, &cidr);
+ e.cidr[0] = cidr;
+ ip2 = (retried &&
+ ip == ntohl(h->next.ip[0])) ? ntohl(h->next.ip[1])
+ : ip2_from;
+ while (!after(ip2, ip2_to)) {
+ e.ip[1] = htonl(ip2);
+ last2 = ip_set_range_to_cidr(ip2, ip2_to, &cidr2);
+ e.cidr[1] = cidr2;
+ ret = adtfn(set, &e, &ext, &ext, flags);
+ if (ret && !ip_set_eexist(ret, flags))
+ return ret;
+ else
+ ret = 0;
+ ip2 = last2 + 1;
+ }
+ ip = last + 1;
+ }
+ return ret;
+}
+
+/* IPv6 variants */
+
+struct hash_netnet6_elem {
+ union nf_inet_addr ip[2];
+ u8 nomatch;
+ union {
+ u8 cidr[2];
+ u16 ccmp;
+ };
+};
+
+/* Common functions */
+
+static inline bool
+hash_netnet6_data_equal(const struct hash_netnet6_elem *ip1,
+ const struct hash_netnet6_elem *ip2,
+ u32 *multi)
+{
+ return ipv6_addr_equal(&ip1->ip[0].in6, &ip2->ip[0].in6) &&
+ ipv6_addr_equal(&ip1->ip[1].in6, &ip2->ip[1].in6) &&
+ ip1->ccmp == ip2->ccmp;
+}
+
+static inline int
+hash_netnet6_do_data_match(const struct hash_netnet6_elem *elem)
+{
+ return elem->nomatch ? -ENOTEMPTY : 1;
+}
+
+static inline void
+hash_netnet6_data_set_flags(struct hash_netnet6_elem *elem, u32 flags)
+{
+ elem->nomatch = (flags >> 16) & IPSET_FLAG_NOMATCH;
+}
+
+static inline void
+hash_netnet6_data_reset_flags(struct hash_netnet6_elem *elem, u8 *flags)
+{
+ swap(*flags, elem->nomatch);
+}
+
+static inline void
+hash_netnet6_data_reset_elem(struct hash_netnet6_elem *elem,
+ struct hash_netnet6_elem *orig)
+{
+ elem->ip[1] = orig->ip[1];
+}
+
+static inline void
+hash_netnet6_data_netmask(struct hash_netnet6_elem *elem, u8 cidr, bool inner)
+{
+ if (inner) {
+ ip6_netmask(&elem->ip[1], cidr);
+ elem->cidr[1] = cidr;
+ } else {
+ ip6_netmask(&elem->ip[0], cidr);
+ elem->cidr[0] = cidr;
+ }
+}
+
+static bool
+hash_netnet6_data_list(struct sk_buff *skb,
+ const struct hash_netnet6_elem *data)
+{
+ u32 flags = data->nomatch ? IPSET_FLAG_NOMATCH : 0;
+
+ if (nla_put_ipaddr6(skb, IPSET_ATTR_IP, &data->ip[0].in6) ||
+ nla_put_ipaddr6(skb, IPSET_ATTR_IP2, &data->ip[1].in6) ||
+ nla_put_u8(skb, IPSET_ATTR_CIDR, data->cidr[0]) ||
+ nla_put_u8(skb, IPSET_ATTR_CIDR2, data->cidr[1]) ||
+ (flags &&
+ nla_put_net32(skb, IPSET_ATTR_CADT_FLAGS, htonl(flags))))
+ goto nla_put_failure;
+ return false;
+
+nla_put_failure:
+ return true;
+}
+
+static inline void
+hash_netnet6_data_next(struct hash_netnet4_elem *next,
+ const struct hash_netnet6_elem *d)
+{
+}
+
+#undef MTYPE
+#undef PF
+#undef HOST_MASK
+
+#define MTYPE hash_netnet6
+#define PF 6
+#define HOST_MASK 128
+#define IP_SET_EMIT_CREATE
+#include "ip_set_hash_gen.h"
+
+static int
+hash_netnet6_kadt(struct ip_set *set, const struct sk_buff *skb,
+ const struct xt_action_param *par,
+ enum ipset_adt adt, struct ip_set_adt_opt *opt)
+{
+ const struct hash_netnet *h = set->data;
+ ipset_adtfn adtfn = set->variant->adt[adt];
+ struct hash_netnet6_elem e = { };
+ struct ip_set_ext ext = IP_SET_INIT_KEXT(skb, opt, set);
+
+ e.cidr[0] = IP_SET_INIT_CIDR(h->nets[0].cidr[0], HOST_MASK);
+ e.cidr[1] = IP_SET_INIT_CIDR(h->nets[0].cidr[1], HOST_MASK);
+ if (adt == IPSET_TEST)
+ e.ccmp = (HOST_MASK << (sizeof(u8)*8)) | HOST_MASK;
+
+ ip6addrptr(skb, opt->flags & IPSET_DIM_ONE_SRC, &e.ip[0].in6);
+ ip6addrptr(skb, opt->flags & IPSET_DIM_TWO_SRC, &e.ip[1].in6);
+ ip6_netmask(&e.ip[0], e.cidr[0]);
+ ip6_netmask(&e.ip[1], e.cidr[1]);
+
+ return adtfn(set, &e, &ext, &opt->ext, opt->cmdflags);
+}
+
+static int
+hash_netnet6_uadt(struct ip_set *set, struct nlattr *tb[],
+ enum ipset_adt adt, u32 *lineno, u32 flags, bool retried)
+{
+ ipset_adtfn adtfn = set->variant->adt[adt];
+ struct hash_netnet6_elem e = { };
+ struct ip_set_ext ext = IP_SET_INIT_UEXT(set);
+ int ret;
+
+ e.cidr[0] = e.cidr[1] = HOST_MASK;
+ if (unlikely(!tb[IPSET_ATTR_IP] || !tb[IPSET_ATTR_IP2] ||
+ !ip_set_optattr_netorder(tb, IPSET_ATTR_TIMEOUT) ||
+ !ip_set_optattr_netorder(tb, IPSET_ATTR_CADT_FLAGS) ||
+ !ip_set_optattr_netorder(tb, IPSET_ATTR_PACKETS) ||
+ !ip_set_optattr_netorder(tb, IPSET_ATTR_BYTES)))
+ return -IPSET_ERR_PROTOCOL;
+ if (unlikely(tb[IPSET_ATTR_IP_TO] || tb[IPSET_ATTR_IP2_TO]))
+ return -IPSET_ERR_HASH_RANGE_UNSUPPORTED;
+
+ if (tb[IPSET_ATTR_LINENO])
+ *lineno = nla_get_u32(tb[IPSET_ATTR_LINENO]);
+
+ ret = ip_set_get_ipaddr6(tb[IPSET_ATTR_IP], &e.ip[0]) ||
+ ip_set_get_ipaddr6(tb[IPSET_ATTR_IP2], &e.ip[1]) ||
+ ip_set_get_extensions(set, tb, &ext);
+ if (ret)
+ return ret;
+
+ if (tb[IPSET_ATTR_CIDR])
+ e.cidr[0] = nla_get_u8(tb[IPSET_ATTR_CIDR]);
+
+ if (tb[IPSET_ATTR_CIDR2])
+ e.cidr[1] = nla_get_u8(tb[IPSET_ATTR_CIDR2]);
+
+ if (!e.cidr[0] || e.cidr[0] > HOST_MASK || !e.cidr[1] ||
+ e.cidr[1] > HOST_MASK)
+ return -IPSET_ERR_INVALID_CIDR;
+
+ ip6_netmask(&e.ip[0], e.cidr[0]);
+ ip6_netmask(&e.ip[1], e.cidr[1]);
+
+ if (tb[IPSET_ATTR_CADT_FLAGS]) {
+ u32 cadt_flags = ip_set_get_h32(tb[IPSET_ATTR_CADT_FLAGS]);
+ if (cadt_flags & IPSET_FLAG_NOMATCH)
+ flags |= (IPSET_FLAG_NOMATCH << 16);
+ }
+
+ ret = adtfn(set, &e, &ext, &ext, flags);
+
+ return ip_set_enomatch(ret, flags, adt, set) ? -ret :
+ ip_set_eexist(ret, flags) ? 0 : ret;
+}
+
+static struct ip_set_type hash_netnet_type __read_mostly = {
+ .name = "hash:net,net",
+ .protocol = IPSET_PROTOCOL,
+ .features = IPSET_TYPE_IP | IPSET_TYPE_IP2 | IPSET_TYPE_NOMATCH,
+ .dimension = IPSET_DIM_TWO,
+ .family = NFPROTO_UNSPEC,
+ .revision_min = IPSET_TYPE_REV_MIN,
+ .revision_max = IPSET_TYPE_REV_MAX,
+ .create = hash_netnet_create,
+ .create_policy = {
+ [IPSET_ATTR_HASHSIZE] = { .type = NLA_U32 },
+ [IPSET_ATTR_MAXELEM] = { .type = NLA_U32 },
+ [IPSET_ATTR_PROBES] = { .type = NLA_U8 },
+ [IPSET_ATTR_RESIZE] = { .type = NLA_U8 },
+ [IPSET_ATTR_TIMEOUT] = { .type = NLA_U32 },
+ [IPSET_ATTR_CADT_FLAGS] = { .type = NLA_U32 },
+ },
+ .adt_policy = {
+ [IPSET_ATTR_IP] = { .type = NLA_NESTED },
+ [IPSET_ATTR_IP_TO] = { .type = NLA_NESTED },
+ [IPSET_ATTR_IP2] = { .type = NLA_NESTED },
+ [IPSET_ATTR_IP2_TO] = { .type = NLA_NESTED },
+ [IPSET_ATTR_CIDR] = { .type = NLA_U8 },
+ [IPSET_ATTR_CIDR2] = { .type = NLA_U8 },
+ [IPSET_ATTR_TIMEOUT] = { .type = NLA_U32 },
+ [IPSET_ATTR_CADT_FLAGS] = { .type = NLA_U32 },
+ [IPSET_ATTR_BYTES] = { .type = NLA_U64 },
+ [IPSET_ATTR_PACKETS] = { .type = NLA_U64 },
+ [IPSET_ATTR_COMMENT] = { .type = NLA_NUL_STRING },
+ },
+ .me = THIS_MODULE,
+};
+
+static int __init
+hash_netnet_init(void)
+{
+ return ip_set_type_register(&hash_netnet_type);
+}
+
+static void __exit
+hash_netnet_fini(void)
+{
+ ip_set_type_unregister(&hash_netnet_type);
+}
+
+module_init(hash_netnet_init);
+module_exit(hash_netnet_fini);
diff --git a/net/netfilter/ipset/ip_set_hash_netport.c b/net/netfilter/ipset/ip_set_hash_netport.c
index 7ef700de596..1c645fbd09c 100644
--- a/net/netfilter/ipset/ip_set_hash_netport.c
+++ b/net/netfilter/ipset/ip_set_hash_netport.c
@@ -1,4 +1,4 @@
-/* Copyright (C) 2003-2011 Jozsef Kadlecsik <kadlec@blackhole.kfki.hu>
+/* Copyright (C) 2003-2013 Jozsef Kadlecsik <kadlec@blackhole.kfki.hu>
*
* This program is free software; you can redistribute it and/or modify
* it under the terms of the GNU General Public License version 2 as
@@ -20,30 +20,26 @@
#include <linux/netfilter.h>
#include <linux/netfilter/ipset/pfxlen.h>
#include <linux/netfilter/ipset/ip_set.h>
-#include <linux/netfilter/ipset/ip_set_timeout.h>
#include <linux/netfilter/ipset/ip_set_getport.h>
#include <linux/netfilter/ipset/ip_set_hash.h>
-#define REVISION_MIN 0
-/* 1 SCTP and UDPLITE support added */
-/* 2 Range as input support for IPv4 added */
-#define REVISION_MAX 3 /* nomatch flag support added */
+#define IPSET_TYPE_REV_MIN 0
+/* 1 SCTP and UDPLITE support added */
+/* 2 Range as input support for IPv4 added */
+/* 3 nomatch flag support added */
+/* 4 Counters support added */
+/* 5 Comments support added */
+#define IPSET_TYPE_REV_MAX 6 /* Forceadd support added */
MODULE_LICENSE("GPL");
MODULE_AUTHOR("Jozsef Kadlecsik <kadlec@blackhole.kfki.hu>");
-IP_SET_MODULE_DESC("hash:net,port", REVISION_MIN, REVISION_MAX);
+IP_SET_MODULE_DESC("hash:net,port", IPSET_TYPE_REV_MIN, IPSET_TYPE_REV_MAX);
MODULE_ALIAS("ip_set_hash:net,port");
/* Type specific function prefix */
-#define TYPE hash_netport
-
-static bool
-hash_netport_same_set(const struct ip_set *a, const struct ip_set *b);
-
-#define hash_netport4_same_set hash_netport_same_set
-#define hash_netport6_same_set hash_netport_same_set
-
-/* The type variant functions: IPv4 */
+#define HTYPE hash_netport
+#define IP_SET_HASH_WITH_PROTO
+#define IP_SET_HASH_WITH_NETS
/* We squeeze the "nomatch" flag into cidr: we don't support cidr == 0
* However this way we have to store internally cidr - 1,
@@ -51,7 +47,9 @@ hash_netport_same_set(const struct ip_set *a, const struct ip_set *b);
*/
#define IP_SET_HASH_WITH_NETS_PACKED
-/* Member elements without timeout */
+/* IPv4 variant */
+
+/* Member elements */
struct hash_netport4_elem {
__be32 ip;
__be16 port;
@@ -60,15 +58,7 @@ struct hash_netport4_elem {
u8 nomatch:1;
};
-/* Member elements with timeout support */
-struct hash_netport4_telem {
- __be32 ip;
- __be16 port;
- u8 proto;
- u8 cidr:7;
- u8 nomatch:1;
- unsigned long timeout;
-};
+/* Common functions */
static inline bool
hash_netport4_data_equal(const struct hash_netport4_elem *ip1,
@@ -81,33 +71,22 @@ hash_netport4_data_equal(const struct hash_netport4_elem *ip1,
ip1->cidr == ip2->cidr;
}
-static inline bool
-hash_netport4_data_isnull(const struct hash_netport4_elem *elem)
+static inline int
+hash_netport4_do_data_match(const struct hash_netport4_elem *elem)
{
- return elem->proto == 0;
+ return elem->nomatch ? -ENOTEMPTY : 1;
}
static inline void
-hash_netport4_data_copy(struct hash_netport4_elem *dst,
- const struct hash_netport4_elem *src)
+hash_netport4_data_set_flags(struct hash_netport4_elem *elem, u32 flags)
{
- dst->ip = src->ip;
- dst->port = src->port;
- dst->proto = src->proto;
- dst->cidr = src->cidr;
- dst->nomatch = src->nomatch;
+ elem->nomatch = !!((flags >> 16) & IPSET_FLAG_NOMATCH);
}
static inline void
-hash_netport4_data_flags(struct hash_netport4_elem *dst, u32 flags)
+hash_netport4_data_reset_flags(struct hash_netport4_elem *elem, u8 *flags)
{
- dst->nomatch = !!(flags & IPSET_FLAG_NOMATCH);
-}
-
-static inline int
-hash_netport4_data_match(const struct hash_netport4_elem *elem)
-{
- return elem->nomatch ? -ENOTEMPTY : 1;
+ swap(*flags, elem->nomatch);
}
static inline void
@@ -117,12 +96,6 @@ hash_netport4_data_netmask(struct hash_netport4_elem *elem, u8 cidr)
elem->cidr = cidr - 1;
}
-static inline void
-hash_netport4_data_zero_out(struct hash_netport4_elem *elem)
-{
- elem->proto = 0;
-}
-
static bool
hash_netport4_data_list(struct sk_buff *skb,
const struct hash_netport4_elem *data)
@@ -142,77 +115,53 @@ nla_put_failure:
return 1;
}
-static bool
-hash_netport4_data_tlist(struct sk_buff *skb,
- const struct hash_netport4_elem *data)
+static inline void
+hash_netport4_data_next(struct hash_netport4_elem *next,
+ const struct hash_netport4_elem *d)
{
- const struct hash_netport4_telem *tdata =
- (const struct hash_netport4_telem *)data;
- u32 flags = data->nomatch ? IPSET_FLAG_NOMATCH : 0;
-
- if (nla_put_ipaddr4(skb, IPSET_ATTR_IP, tdata->ip) ||
- nla_put_net16(skb, IPSET_ATTR_PORT, tdata->port) ||
- nla_put_u8(skb, IPSET_ATTR_CIDR, data->cidr + 1) ||
- nla_put_u8(skb, IPSET_ATTR_PROTO, data->proto) ||
- nla_put_net32(skb, IPSET_ATTR_TIMEOUT,
- htonl(ip_set_timeout_get(tdata->timeout))) ||
- (flags &&
- nla_put_net32(skb, IPSET_ATTR_CADT_FLAGS, htonl(flags))))
- goto nla_put_failure;
- return 0;
-
-nla_put_failure:
- return 1;
+ next->ip = d->ip;
+ next->port = d->port;
}
-#define IP_SET_HASH_WITH_PROTO
-#define IP_SET_HASH_WITH_NETS
-
+#define MTYPE hash_netport4
#define PF 4
#define HOST_MASK 32
-#include <linux/netfilter/ipset/ip_set_ahash.h>
-
-static inline void
-hash_netport4_data_next(struct ip_set_hash *h,
- const struct hash_netport4_elem *d)
-{
- h->next.ip = d->ip;
- h->next.port = d->port;
-}
+#include "ip_set_hash_gen.h"
static int
hash_netport4_kadt(struct ip_set *set, const struct sk_buff *skb,
const struct xt_action_param *par,
- enum ipset_adt adt, const struct ip_set_adt_opt *opt)
+ enum ipset_adt adt, struct ip_set_adt_opt *opt)
{
- const struct ip_set_hash *h = set->data;
+ const struct hash_netport *h = set->data;
ipset_adtfn adtfn = set->variant->adt[adt];
- struct hash_netport4_elem data = {
- .cidr = h->nets[0].cidr ? h->nets[0].cidr - 1 : HOST_MASK - 1
+ struct hash_netport4_elem e = {
+ .cidr = IP_SET_INIT_CIDR(h->nets[0].cidr[0], HOST_MASK) - 1,
};
+ struct ip_set_ext ext = IP_SET_INIT_KEXT(skb, opt, set);
if (adt == IPSET_TEST)
- data.cidr = HOST_MASK - 1;
+ e.cidr = HOST_MASK - 1;
if (!ip_set_get_ip4_port(skb, opt->flags & IPSET_DIM_TWO_SRC,
- &data.port, &data.proto))
+ &e.port, &e.proto))
return -EINVAL;
- ip4addrptr(skb, opt->flags & IPSET_DIM_ONE_SRC, &data.ip);
- data.ip &= ip_set_netmask(data.cidr + 1);
+ ip4addrptr(skb, opt->flags & IPSET_DIM_ONE_SRC, &e.ip);
+ e.ip &= ip_set_netmask(e.cidr + 1);
- return adtfn(set, &data, opt_timeout(opt, h), opt->cmdflags);
+ return adtfn(set, &e, &ext, &opt->ext, opt->cmdflags);
}
static int
hash_netport4_uadt(struct ip_set *set, struct nlattr *tb[],
enum ipset_adt adt, u32 *lineno, u32 flags, bool retried)
{
- const struct ip_set_hash *h = set->data;
+ const struct hash_netport *h = set->data;
ipset_adtfn adtfn = set->variant->adt[adt];
- struct hash_netport4_elem data = { .cidr = HOST_MASK - 1 };
- u32 port, port_to, p = 0, ip = 0, ip_to, last;
- u32 timeout = h->timeout;
+ struct hash_netport4_elem e = { .cidr = HOST_MASK - 1 };
+ struct ip_set_ext ext = IP_SET_INIT_UEXT(set);
+ u32 port, port_to, p = 0, ip = 0, ip_to = 0, last;
bool with_ports = false;
u8 cidr;
int ret;
@@ -221,13 +170,16 @@ hash_netport4_uadt(struct ip_set *set, struct nlattr *tb[],
!ip_set_attr_netorder(tb, IPSET_ATTR_PORT) ||
!ip_set_optattr_netorder(tb, IPSET_ATTR_PORT_TO) ||
!ip_set_optattr_netorder(tb, IPSET_ATTR_TIMEOUT) ||
- !ip_set_optattr_netorder(tb, IPSET_ATTR_CADT_FLAGS)))
+ !ip_set_optattr_netorder(tb, IPSET_ATTR_CADT_FLAGS) ||
+ !ip_set_optattr_netorder(tb, IPSET_ATTR_PACKETS) ||
+ !ip_set_optattr_netorder(tb, IPSET_ATTR_BYTES)))
return -IPSET_ERR_PROTOCOL;
if (tb[IPSET_ATTR_LINENO])
*lineno = nla_get_u32(tb[IPSET_ATTR_LINENO]);
- ret = ip_set_get_hostipaddr4(tb[IPSET_ATTR_IP], &ip);
+ ret = ip_set_get_hostipaddr4(tb[IPSET_ATTR_IP], &ip) ||
+ ip_set_get_extensions(set, tb, &ext);
if (ret)
return ret;
@@ -235,47 +187,42 @@ hash_netport4_uadt(struct ip_set *set, struct nlattr *tb[],
cidr = nla_get_u8(tb[IPSET_ATTR_CIDR]);
if (!cidr || cidr > HOST_MASK)
return -IPSET_ERR_INVALID_CIDR;
- data.cidr = cidr - 1;
+ e.cidr = cidr - 1;
}
if (tb[IPSET_ATTR_PORT])
- data.port = nla_get_be16(tb[IPSET_ATTR_PORT]);
+ e.port = nla_get_be16(tb[IPSET_ATTR_PORT]);
else
return -IPSET_ERR_PROTOCOL;
if (tb[IPSET_ATTR_PROTO]) {
- data.proto = nla_get_u8(tb[IPSET_ATTR_PROTO]);
- with_ports = ip_set_proto_with_ports(data.proto);
+ e.proto = nla_get_u8(tb[IPSET_ATTR_PROTO]);
+ with_ports = ip_set_proto_with_ports(e.proto);
- if (data.proto == 0)
+ if (e.proto == 0)
return -IPSET_ERR_INVALID_PROTO;
} else
return -IPSET_ERR_MISSING_PROTO;
- if (!(with_ports || data.proto == IPPROTO_ICMP))
- data.port = 0;
-
- if (tb[IPSET_ATTR_TIMEOUT]) {
- if (!with_timeout(h->timeout))
- return -IPSET_ERR_TIMEOUT;
- timeout = ip_set_timeout_uget(tb[IPSET_ATTR_TIMEOUT]);
- }
+ if (!(with_ports || e.proto == IPPROTO_ICMP))
+ e.port = 0;
with_ports = with_ports && tb[IPSET_ATTR_PORT_TO];
- if (tb[IPSET_ATTR_CADT_FLAGS] && adt == IPSET_ADD) {
+ if (tb[IPSET_ATTR_CADT_FLAGS]) {
u32 cadt_flags = ip_set_get_h32(tb[IPSET_ATTR_CADT_FLAGS]);
if (cadt_flags & IPSET_FLAG_NOMATCH)
- flags |= (cadt_flags << 16);
+ flags |= (IPSET_FLAG_NOMATCH << 16);
}
if (adt == IPSET_TEST || !(with_ports || tb[IPSET_ATTR_IP_TO])) {
- data.ip = htonl(ip & ip_set_hostmask(data.cidr + 1));
- ret = adtfn(set, &data, timeout, flags);
- return ip_set_eexist(ret, flags) ? 0 : ret;
+ e.ip = htonl(ip & ip_set_hostmask(e.cidr + 1));
+ ret = adtfn(set, &e, &ext, &ext, flags);
+ return ip_set_enomatch(ret, flags, adt, set) ? -ret :
+ ip_set_eexist(ret, flags) ? 0 : ret;
}
- port = port_to = ntohs(data.port);
+ port = port_to = ntohs(e.port);
if (tb[IPSET_ATTR_PORT_TO]) {
port_to = ip_set_get_h16(tb[IPSET_ATTR_PORT_TO]);
if (port_to < port)
@@ -289,21 +236,20 @@ hash_netport4_uadt(struct ip_set *set, struct nlattr *tb[],
swap(ip, ip_to);
if (ip + UINT_MAX == ip_to)
return -IPSET_ERR_HASH_RANGE;
- } else {
- ip_set_mask_from_to(ip, ip_to, data.cidr + 1);
- }
+ } else
+ ip_set_mask_from_to(ip, ip_to, e.cidr + 1);
if (retried)
ip = ntohl(h->next.ip);
while (!after(ip, ip_to)) {
- data.ip = htonl(ip);
+ e.ip = htonl(ip);
last = ip_set_range_to_cidr(ip, ip_to, &cidr);
- data.cidr = cidr - 1;
+ e.cidr = cidr - 1;
p = retried && ip == ntohl(h->next.ip) ? ntohs(h->next.port)
: port;
for (; p <= port_to; p++) {
- data.port = htons(p);
- ret = adtfn(set, &data, timeout, flags);
+ e.port = htons(p);
+ ret = adtfn(set, &e, &ext, &ext, flags);
if (ret && !ip_set_eexist(ret, flags))
return ret;
@@ -315,18 +261,7 @@ hash_netport4_uadt(struct ip_set *set, struct nlattr *tb[],
return ret;
}
-static bool
-hash_netport_same_set(const struct ip_set *a, const struct ip_set *b)
-{
- const struct ip_set_hash *x = a->data;
- const struct ip_set_hash *y = b->data;
-
- /* Resizing changes htable_bits, so we ignore it */
- return x->maxelem == y->maxelem &&
- x->timeout == y->timeout;
-}
-
-/* The type variant functions: IPv6 */
+/* IPv6 variant */
struct hash_netport6_elem {
union nf_inet_addr ip;
@@ -336,64 +271,35 @@ struct hash_netport6_elem {
u8 nomatch:1;
};
-struct hash_netport6_telem {
- union nf_inet_addr ip;
- __be16 port;
- u8 proto;
- u8 cidr:7;
- u8 nomatch:1;
- unsigned long timeout;
-};
+/* Common functions */
static inline bool
hash_netport6_data_equal(const struct hash_netport6_elem *ip1,
const struct hash_netport6_elem *ip2,
u32 *multi)
{
- return ipv6_addr_cmp(&ip1->ip.in6, &ip2->ip.in6) == 0 &&
+ return ipv6_addr_equal(&ip1->ip.in6, &ip2->ip.in6) &&
ip1->port == ip2->port &&
ip1->proto == ip2->proto &&
ip1->cidr == ip2->cidr;
}
-static inline bool
-hash_netport6_data_isnull(const struct hash_netport6_elem *elem)
-{
- return elem->proto == 0;
-}
-
-static inline void
-hash_netport6_data_copy(struct hash_netport6_elem *dst,
- const struct hash_netport6_elem *src)
-{
- memcpy(dst, src, sizeof(*dst));
-}
-
-static inline void
-hash_netport6_data_flags(struct hash_netport6_elem *dst, u32 flags)
-{
- dst->nomatch = !!(flags & IPSET_FLAG_NOMATCH);
-}
-
static inline int
-hash_netport6_data_match(const struct hash_netport6_elem *elem)
+hash_netport6_do_data_match(const struct hash_netport6_elem *elem)
{
return elem->nomatch ? -ENOTEMPTY : 1;
}
static inline void
-hash_netport6_data_zero_out(struct hash_netport6_elem *elem)
+hash_netport6_data_set_flags(struct hash_netport6_elem *elem, u32 flags)
{
- elem->proto = 0;
+ elem->nomatch = !!((flags >> 16) & IPSET_FLAG_NOMATCH);
}
static inline void
-ip6_netmask(union nf_inet_addr *ip, u8 prefix)
+hash_netport6_data_reset_flags(struct hash_netport6_elem *elem, u8 *flags)
{
- ip->ip6[0] &= ip_set_netmask6(prefix)[0];
- ip->ip6[1] &= ip_set_netmask6(prefix)[1];
- ip->ip6[2] &= ip_set_netmask6(prefix)[2];
- ip->ip6[3] &= ip_set_netmask6(prefix)[3];
+ swap(*flags, elem->nomatch);
}
static inline void
@@ -422,76 +328,57 @@ nla_put_failure:
return 1;
}
-static bool
-hash_netport6_data_tlist(struct sk_buff *skb,
- const struct hash_netport6_elem *data)
+static inline void
+hash_netport6_data_next(struct hash_netport4_elem *next,
+ const struct hash_netport6_elem *d)
{
- const struct hash_netport6_telem *e =
- (const struct hash_netport6_telem *)data;
- u32 flags = data->nomatch ? IPSET_FLAG_NOMATCH : 0;
-
- if (nla_put_ipaddr6(skb, IPSET_ATTR_IP, &e->ip.in6) ||
- nla_put_net16(skb, IPSET_ATTR_PORT, data->port) ||
- nla_put_u8(skb, IPSET_ATTR_CIDR, data->cidr + 1) ||
- nla_put_u8(skb, IPSET_ATTR_PROTO, data->proto) ||
- nla_put_net32(skb, IPSET_ATTR_TIMEOUT,
- htonl(ip_set_timeout_get(e->timeout))) ||
- (flags &&
- nla_put_net32(skb, IPSET_ATTR_CADT_FLAGS, htonl(flags))))
- goto nla_put_failure;
- return 0;
-
-nla_put_failure:
- return 1;
+ next->port = d->port;
}
+#undef MTYPE
#undef PF
#undef HOST_MASK
+#define MTYPE hash_netport6
#define PF 6
#define HOST_MASK 128
-#include <linux/netfilter/ipset/ip_set_ahash.h>
-
-static inline void
-hash_netport6_data_next(struct ip_set_hash *h,
- const struct hash_netport6_elem *d)
-{
- h->next.port = d->port;
-}
+#define IP_SET_EMIT_CREATE
+#include "ip_set_hash_gen.h"
static int
hash_netport6_kadt(struct ip_set *set, const struct sk_buff *skb,
const struct xt_action_param *par,
- enum ipset_adt adt, const struct ip_set_adt_opt *opt)
+ enum ipset_adt adt, struct ip_set_adt_opt *opt)
{
- const struct ip_set_hash *h = set->data;
+ const struct hash_netport *h = set->data;
ipset_adtfn adtfn = set->variant->adt[adt];
- struct hash_netport6_elem data = {
- .cidr = h->nets[0].cidr ? h->nets[0].cidr - 1 : HOST_MASK - 1,
+ struct hash_netport6_elem e = {
+ .cidr = IP_SET_INIT_CIDR(h->nets[0].cidr[0], HOST_MASK) - 1,
};
+ struct ip_set_ext ext = IP_SET_INIT_KEXT(skb, opt, set);
if (adt == IPSET_TEST)
- data.cidr = HOST_MASK - 1;
+ e.cidr = HOST_MASK - 1;
if (!ip_set_get_ip6_port(skb, opt->flags & IPSET_DIM_TWO_SRC,
- &data.port, &data.proto))
+ &e.port, &e.proto))
return -EINVAL;
- ip6addrptr(skb, opt->flags & IPSET_DIM_ONE_SRC, &data.ip.in6);
- ip6_netmask(&data.ip, data.cidr + 1);
+ ip6addrptr(skb, opt->flags & IPSET_DIM_ONE_SRC, &e.ip.in6);
+ ip6_netmask(&e.ip, e.cidr + 1);
- return adtfn(set, &data, opt_timeout(opt, h), opt->cmdflags);
+ return adtfn(set, &e, &ext, &opt->ext, opt->cmdflags);
}
static int
hash_netport6_uadt(struct ip_set *set, struct nlattr *tb[],
enum ipset_adt adt, u32 *lineno, u32 flags, bool retried)
{
- const struct ip_set_hash *h = set->data;
+ const struct hash_netport *h = set->data;
ipset_adtfn adtfn = set->variant->adt[adt];
- struct hash_netport6_elem data = { .cidr = HOST_MASK - 1 };
+ struct hash_netport6_elem e = { .cidr = HOST_MASK - 1 };
+ struct ip_set_ext ext = IP_SET_INIT_UEXT(set);
u32 port, port_to;
- u32 timeout = h->timeout;
bool with_ports = false;
u8 cidr;
int ret;
@@ -500,7 +387,9 @@ hash_netport6_uadt(struct ip_set *set, struct nlattr *tb[],
!ip_set_attr_netorder(tb, IPSET_ATTR_PORT) ||
!ip_set_optattr_netorder(tb, IPSET_ATTR_PORT_TO) ||
!ip_set_optattr_netorder(tb, IPSET_ATTR_TIMEOUT) ||
- !ip_set_optattr_netorder(tb, IPSET_ATTR_CADT_FLAGS)))
+ !ip_set_optattr_netorder(tb, IPSET_ATTR_CADT_FLAGS) ||
+ !ip_set_optattr_netorder(tb, IPSET_ATTR_PACKETS) ||
+ !ip_set_optattr_netorder(tb, IPSET_ATTR_BYTES)))
return -IPSET_ERR_PROTOCOL;
if (unlikely(tb[IPSET_ATTR_IP_TO]))
return -IPSET_ERR_HASH_RANGE_UNSUPPORTED;
@@ -508,7 +397,8 @@ hash_netport6_uadt(struct ip_set *set, struct nlattr *tb[],
if (tb[IPSET_ATTR_LINENO])
*lineno = nla_get_u32(tb[IPSET_ATTR_LINENO]);
- ret = ip_set_get_ipaddr6(tb[IPSET_ATTR_IP], &data.ip);
+ ret = ip_set_get_ipaddr6(tb[IPSET_ATTR_IP], &e.ip) ||
+ ip_set_get_extensions(set, tb, &ext);
if (ret)
return ret;
@@ -516,45 +406,40 @@ hash_netport6_uadt(struct ip_set *set, struct nlattr *tb[],
cidr = nla_get_u8(tb[IPSET_ATTR_CIDR]);
if (!cidr || cidr > HOST_MASK)
return -IPSET_ERR_INVALID_CIDR;
- data.cidr = cidr - 1;
+ e.cidr = cidr - 1;
}
- ip6_netmask(&data.ip, data.cidr + 1);
+ ip6_netmask(&e.ip, e.cidr + 1);
if (tb[IPSET_ATTR_PORT])
- data.port = nla_get_be16(tb[IPSET_ATTR_PORT]);
+ e.port = nla_get_be16(tb[IPSET_ATTR_PORT]);
else
return -IPSET_ERR_PROTOCOL;
if (tb[IPSET_ATTR_PROTO]) {
- data.proto = nla_get_u8(tb[IPSET_ATTR_PROTO]);
- with_ports = ip_set_proto_with_ports(data.proto);
+ e.proto = nla_get_u8(tb[IPSET_ATTR_PROTO]);
+ with_ports = ip_set_proto_with_ports(e.proto);
- if (data.proto == 0)
+ if (e.proto == 0)
return -IPSET_ERR_INVALID_PROTO;
} else
return -IPSET_ERR_MISSING_PROTO;
- if (!(with_ports || data.proto == IPPROTO_ICMPV6))
- data.port = 0;
-
- if (tb[IPSET_ATTR_TIMEOUT]) {
- if (!with_timeout(h->timeout))
- return -IPSET_ERR_TIMEOUT;
- timeout = ip_set_timeout_uget(tb[IPSET_ATTR_TIMEOUT]);
- }
+ if (!(with_ports || e.proto == IPPROTO_ICMPV6))
+ e.port = 0;
- if (tb[IPSET_ATTR_CADT_FLAGS] && adt == IPSET_ADD) {
+ if (tb[IPSET_ATTR_CADT_FLAGS]) {
u32 cadt_flags = ip_set_get_h32(tb[IPSET_ATTR_CADT_FLAGS]);
if (cadt_flags & IPSET_FLAG_NOMATCH)
- flags |= (cadt_flags << 16);
+ flags |= (IPSET_FLAG_NOMATCH << 16);
}
if (adt == IPSET_TEST || !with_ports || !tb[IPSET_ATTR_PORT_TO]) {
- ret = adtfn(set, &data, timeout, flags);
- return ip_set_eexist(ret, flags) ? 0 : ret;
+ ret = adtfn(set, &e, &ext, &ext, flags);
+ return ip_set_enomatch(ret, flags, adt, set) ? -ret :
+ ip_set_eexist(ret, flags) ? 0 : ret;
}
- port = ntohs(data.port);
+ port = ntohs(e.port);
port_to = ip_set_get_h16(tb[IPSET_ATTR_PORT_TO]);
if (port > port_to)
swap(port, port_to);
@@ -562,8 +447,8 @@ hash_netport6_uadt(struct ip_set *set, struct nlattr *tb[],
if (retried)
port = ntohs(h->next.port);
for (; port <= port_to; port++) {
- data.port = htons(port);
- ret = adtfn(set, &data, timeout, flags);
+ e.port = htons(port);
+ ret = adtfn(set, &e, &ext, &ext, flags);
if (ret && !ip_set_eexist(ret, flags))
return ret;
@@ -573,88 +458,14 @@ hash_netport6_uadt(struct ip_set *set, struct nlattr *tb[],
return ret;
}
-/* Create hash:ip type of sets */
-
-static int
-hash_netport_create(struct ip_set *set, struct nlattr *tb[], u32 flags)
-{
- struct ip_set_hash *h;
- u32 hashsize = IPSET_DEFAULT_HASHSIZE, maxelem = IPSET_DEFAULT_MAXELEM;
- u8 hbits;
- size_t hsize;
-
- if (!(set->family == NFPROTO_IPV4 || set->family == NFPROTO_IPV6))
- return -IPSET_ERR_INVALID_FAMILY;
-
- if (unlikely(!ip_set_optattr_netorder(tb, IPSET_ATTR_HASHSIZE) ||
- !ip_set_optattr_netorder(tb, IPSET_ATTR_MAXELEM) ||
- !ip_set_optattr_netorder(tb, IPSET_ATTR_TIMEOUT)))
- return -IPSET_ERR_PROTOCOL;
-
- if (tb[IPSET_ATTR_HASHSIZE]) {
- hashsize = ip_set_get_h32(tb[IPSET_ATTR_HASHSIZE]);
- if (hashsize < IPSET_MIMINAL_HASHSIZE)
- hashsize = IPSET_MIMINAL_HASHSIZE;
- }
-
- if (tb[IPSET_ATTR_MAXELEM])
- maxelem = ip_set_get_h32(tb[IPSET_ATTR_MAXELEM]);
-
- h = kzalloc(sizeof(*h)
- + sizeof(struct ip_set_hash_nets)
- * (set->family == NFPROTO_IPV4 ? 32 : 128), GFP_KERNEL);
- if (!h)
- return -ENOMEM;
-
- h->maxelem = maxelem;
- get_random_bytes(&h->initval, sizeof(h->initval));
- h->timeout = IPSET_NO_TIMEOUT;
-
- hbits = htable_bits(hashsize);
- hsize = htable_size(hbits);
- if (hsize == 0) {
- kfree(h);
- return -ENOMEM;
- }
- h->table = ip_set_alloc(hsize);
- if (!h->table) {
- kfree(h);
- return -ENOMEM;
- }
- h->table->htable_bits = hbits;
-
- set->data = h;
-
- if (tb[IPSET_ATTR_TIMEOUT]) {
- h->timeout = ip_set_timeout_uget(tb[IPSET_ATTR_TIMEOUT]);
-
- set->variant = set->family == NFPROTO_IPV4
- ? &hash_netport4_tvariant : &hash_netport6_tvariant;
-
- if (set->family == NFPROTO_IPV4)
- hash_netport4_gc_init(set);
- else
- hash_netport6_gc_init(set);
- } else {
- set->variant = set->family == NFPROTO_IPV4
- ? &hash_netport4_variant : &hash_netport6_variant;
- }
-
- pr_debug("create %s hashsize %u (%u) maxelem %u: %p(%p)\n",
- set->name, jhash_size(h->table->htable_bits),
- h->table->htable_bits, h->maxelem, set->data, h->table);
-
- return 0;
-}
-
static struct ip_set_type hash_netport_type __read_mostly = {
.name = "hash:net,port",
.protocol = IPSET_PROTOCOL,
.features = IPSET_TYPE_IP | IPSET_TYPE_PORT | IPSET_TYPE_NOMATCH,
.dimension = IPSET_DIM_TWO,
.family = NFPROTO_UNSPEC,
- .revision_min = REVISION_MIN,
- .revision_max = REVISION_MAX,
+ .revision_min = IPSET_TYPE_REV_MIN,
+ .revision_max = IPSET_TYPE_REV_MAX,
.create = hash_netport_create,
.create_policy = {
[IPSET_ATTR_HASHSIZE] = { .type = NLA_U32 },
@@ -663,6 +474,7 @@ static struct ip_set_type hash_netport_type __read_mostly = {
[IPSET_ATTR_RESIZE] = { .type = NLA_U8 },
[IPSET_ATTR_PROTO] = { .type = NLA_U8 },
[IPSET_ATTR_TIMEOUT] = { .type = NLA_U32 },
+ [IPSET_ATTR_CADT_FLAGS] = { .type = NLA_U32 },
},
.adt_policy = {
[IPSET_ATTR_IP] = { .type = NLA_NESTED },
@@ -674,6 +486,9 @@ static struct ip_set_type hash_netport_type __read_mostly = {
[IPSET_ATTR_TIMEOUT] = { .type = NLA_U32 },
[IPSET_ATTR_LINENO] = { .type = NLA_U32 },
[IPSET_ATTR_CADT_FLAGS] = { .type = NLA_U32 },
+ [IPSET_ATTR_BYTES] = { .type = NLA_U64 },
+ [IPSET_ATTR_PACKETS] = { .type = NLA_U64 },
+ [IPSET_ATTR_COMMENT] = { .type = NLA_NUL_STRING },
},
.me = THIS_MODULE,
};
diff --git a/net/netfilter/ipset/ip_set_hash_netportnet.c b/net/netfilter/ipset/ip_set_hash_netportnet.c
new file mode 100644
index 00000000000..c0d2ba73f8b
--- /dev/null
+++ b/net/netfilter/ipset/ip_set_hash_netportnet.c
@@ -0,0 +1,587 @@
+/* Copyright (C) 2003-2013 Jozsef Kadlecsik <kadlec@blackhole.kfki.hu>
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2 as
+ * published by the Free Software Foundation.
+ */
+
+/* Kernel module implementing an IP set type: the hash:ip,port,net type */
+
+#include <linux/jhash.h>
+#include <linux/module.h>
+#include <linux/ip.h>
+#include <linux/skbuff.h>
+#include <linux/errno.h>
+#include <linux/random.h>
+#include <net/ip.h>
+#include <net/ipv6.h>
+#include <net/netlink.h>
+#include <net/tcp.h>
+
+#include <linux/netfilter.h>
+#include <linux/netfilter/ipset/pfxlen.h>
+#include <linux/netfilter/ipset/ip_set.h>
+#include <linux/netfilter/ipset/ip_set_getport.h>
+#include <linux/netfilter/ipset/ip_set_hash.h>
+
+#define IPSET_TYPE_REV_MIN 0
+/* 0 Comments support added */
+#define IPSET_TYPE_REV_MAX 1 /* Forceadd support added */
+
+MODULE_LICENSE("GPL");
+MODULE_AUTHOR("Oliver Smith <oliver@8.c.9.b.0.7.4.0.1.0.0.2.ip6.arpa>");
+IP_SET_MODULE_DESC("hash:net,port,net", IPSET_TYPE_REV_MIN, IPSET_TYPE_REV_MAX);
+MODULE_ALIAS("ip_set_hash:net,port,net");
+
+/* Type specific function prefix */
+#define HTYPE hash_netportnet
+#define IP_SET_HASH_WITH_PROTO
+#define IP_SET_HASH_WITH_NETS
+#define IPSET_NET_COUNT 2
+
+/* IPv4 variant */
+
+/* Member elements */
+struct hash_netportnet4_elem {
+ union {
+ __be32 ip[2];
+ __be64 ipcmp;
+ };
+ __be16 port;
+ union {
+ u8 cidr[2];
+ u16 ccmp;
+ };
+ u8 nomatch:1;
+ u8 proto;
+};
+
+/* Common functions */
+
+static inline bool
+hash_netportnet4_data_equal(const struct hash_netportnet4_elem *ip1,
+ const struct hash_netportnet4_elem *ip2,
+ u32 *multi)
+{
+ return ip1->ipcmp == ip2->ipcmp &&
+ ip1->ccmp == ip2->ccmp &&
+ ip1->port == ip2->port &&
+ ip1->proto == ip2->proto;
+}
+
+static inline int
+hash_netportnet4_do_data_match(const struct hash_netportnet4_elem *elem)
+{
+ return elem->nomatch ? -ENOTEMPTY : 1;
+}
+
+static inline void
+hash_netportnet4_data_set_flags(struct hash_netportnet4_elem *elem, u32 flags)
+{
+ elem->nomatch = !!((flags >> 16) & IPSET_FLAG_NOMATCH);
+}
+
+static inline void
+hash_netportnet4_data_reset_flags(struct hash_netportnet4_elem *elem, u8 *flags)
+{
+ swap(*flags, elem->nomatch);
+}
+
+static inline void
+hash_netportnet4_data_reset_elem(struct hash_netportnet4_elem *elem,
+ struct hash_netportnet4_elem *orig)
+{
+ elem->ip[1] = orig->ip[1];
+}
+
+static inline void
+hash_netportnet4_data_netmask(struct hash_netportnet4_elem *elem,
+ u8 cidr, bool inner)
+{
+ if (inner) {
+ elem->ip[1] &= ip_set_netmask(cidr);
+ elem->cidr[1] = cidr;
+ } else {
+ elem->ip[0] &= ip_set_netmask(cidr);
+ elem->cidr[0] = cidr;
+ }
+}
+
+static bool
+hash_netportnet4_data_list(struct sk_buff *skb,
+ const struct hash_netportnet4_elem *data)
+{
+ u32 flags = data->nomatch ? IPSET_FLAG_NOMATCH : 0;
+
+ if (nla_put_ipaddr4(skb, IPSET_ATTR_IP, data->ip[0]) ||
+ nla_put_ipaddr4(skb, IPSET_ATTR_IP2, data->ip[1]) ||
+ nla_put_net16(skb, IPSET_ATTR_PORT, data->port) ||
+ nla_put_u8(skb, IPSET_ATTR_CIDR, data->cidr[0]) ||
+ nla_put_u8(skb, IPSET_ATTR_CIDR2, data->cidr[1]) ||
+ nla_put_u8(skb, IPSET_ATTR_PROTO, data->proto) ||
+ (flags &&
+ nla_put_net32(skb, IPSET_ATTR_CADT_FLAGS, htonl(flags))))
+ goto nla_put_failure;
+ return 0;
+
+nla_put_failure:
+ return 1;
+}
+
+static inline void
+hash_netportnet4_data_next(struct hash_netportnet4_elem *next,
+ const struct hash_netportnet4_elem *d)
+{
+ next->ipcmp = d->ipcmp;
+ next->port = d->port;
+}
+
+#define MTYPE hash_netportnet4
+#define PF 4
+#define HOST_MASK 32
+#include "ip_set_hash_gen.h"
+
+static int
+hash_netportnet4_kadt(struct ip_set *set, const struct sk_buff *skb,
+ const struct xt_action_param *par,
+ enum ipset_adt adt, struct ip_set_adt_opt *opt)
+{
+ const struct hash_netportnet *h = set->data;
+ ipset_adtfn adtfn = set->variant->adt[adt];
+ struct hash_netportnet4_elem e = { };
+ struct ip_set_ext ext = IP_SET_INIT_KEXT(skb, opt, set);
+
+ e.cidr[0] = IP_SET_INIT_CIDR(h->nets[0].cidr[0], HOST_MASK);
+ e.cidr[1] = IP_SET_INIT_CIDR(h->nets[0].cidr[1], HOST_MASK);
+ if (adt == IPSET_TEST)
+ e.ccmp = (HOST_MASK << (sizeof(e.cidr[0]) * 8)) | HOST_MASK;
+
+ if (!ip_set_get_ip4_port(skb, opt->flags & IPSET_DIM_TWO_SRC,
+ &e.port, &e.proto))
+ return -EINVAL;
+
+ ip4addrptr(skb, opt->flags & IPSET_DIM_ONE_SRC, &e.ip[0]);
+ ip4addrptr(skb, opt->flags & IPSET_DIM_THREE_SRC, &e.ip[1]);
+ e.ip[0] &= ip_set_netmask(e.cidr[0]);
+ e.ip[1] &= ip_set_netmask(e.cidr[1]);
+
+ return adtfn(set, &e, &ext, &opt->ext, opt->cmdflags);
+}
+
+static int
+hash_netportnet4_uadt(struct ip_set *set, struct nlattr *tb[],
+ enum ipset_adt adt, u32 *lineno, u32 flags, bool retried)
+{
+ const struct hash_netportnet *h = set->data;
+ ipset_adtfn adtfn = set->variant->adt[adt];
+ struct hash_netportnet4_elem e = { };
+ struct ip_set_ext ext = IP_SET_INIT_UEXT(set);
+ u32 ip = 0, ip_to = 0, ip_last, p = 0, port, port_to;
+ u32 ip2_from = 0, ip2_to = 0, ip2_last, ip2;
+ bool with_ports = false;
+ u8 cidr, cidr2;
+ int ret;
+
+ e.cidr[0] = e.cidr[1] = HOST_MASK;
+ if (unlikely(!tb[IPSET_ATTR_IP] || !tb[IPSET_ATTR_IP2] ||
+ !ip_set_attr_netorder(tb, IPSET_ATTR_PORT) ||
+ !ip_set_optattr_netorder(tb, IPSET_ATTR_PORT_TO) ||
+ !ip_set_optattr_netorder(tb, IPSET_ATTR_TIMEOUT) ||
+ !ip_set_optattr_netorder(tb, IPSET_ATTR_CADT_FLAGS) ||
+ !ip_set_optattr_netorder(tb, IPSET_ATTR_PACKETS) ||
+ !ip_set_optattr_netorder(tb, IPSET_ATTR_BYTES)))
+ return -IPSET_ERR_PROTOCOL;
+
+ if (tb[IPSET_ATTR_LINENO])
+ *lineno = nla_get_u32(tb[IPSET_ATTR_LINENO]);
+
+ ret = ip_set_get_hostipaddr4(tb[IPSET_ATTR_IP], &ip) ||
+ ip_set_get_hostipaddr4(tb[IPSET_ATTR_IP2], &ip2_from) ||
+ ip_set_get_extensions(set, tb, &ext);
+ if (ret)
+ return ret;
+
+ if (tb[IPSET_ATTR_CIDR]) {
+ cidr = nla_get_u8(tb[IPSET_ATTR_CIDR]);
+ if (!cidr || cidr > HOST_MASK)
+ return -IPSET_ERR_INVALID_CIDR;
+ e.cidr[0] = cidr;
+ }
+
+ if (tb[IPSET_ATTR_CIDR2]) {
+ cidr = nla_get_u8(tb[IPSET_ATTR_CIDR2]);
+ if (!cidr || cidr > HOST_MASK)
+ return -IPSET_ERR_INVALID_CIDR;
+ e.cidr[1] = cidr;
+ }
+
+ if (tb[IPSET_ATTR_PORT])
+ e.port = nla_get_be16(tb[IPSET_ATTR_PORT]);
+ else
+ return -IPSET_ERR_PROTOCOL;
+
+ if (tb[IPSET_ATTR_PROTO]) {
+ e.proto = nla_get_u8(tb[IPSET_ATTR_PROTO]);
+ with_ports = ip_set_proto_with_ports(e.proto);
+
+ if (e.proto == 0)
+ return -IPSET_ERR_INVALID_PROTO;
+ } else
+ return -IPSET_ERR_MISSING_PROTO;
+
+ if (!(with_ports || e.proto == IPPROTO_ICMP))
+ e.port = 0;
+
+ if (tb[IPSET_ATTR_CADT_FLAGS]) {
+ u32 cadt_flags = ip_set_get_h32(tb[IPSET_ATTR_CADT_FLAGS]);
+ if (cadt_flags & IPSET_FLAG_NOMATCH)
+ flags |= (IPSET_FLAG_NOMATCH << 16);
+ }
+
+ with_ports = with_ports && tb[IPSET_ATTR_PORT_TO];
+ if (adt == IPSET_TEST ||
+ !(tb[IPSET_ATTR_IP_TO] || with_ports || tb[IPSET_ATTR_IP2_TO])) {
+ e.ip[0] = htonl(ip & ip_set_hostmask(e.cidr[0]));
+ e.ip[1] = htonl(ip2_from & ip_set_hostmask(e.cidr[1]));
+ ret = adtfn(set, &e, &ext, &ext, flags);
+ return ip_set_enomatch(ret, flags, adt, set) ? -ret :
+ ip_set_eexist(ret, flags) ? 0 : ret;
+ }
+
+ ip_to = ip;
+ if (tb[IPSET_ATTR_IP_TO]) {
+ ret = ip_set_get_hostipaddr4(tb[IPSET_ATTR_IP_TO], &ip_to);
+ if (ret)
+ return ret;
+ if (ip > ip_to)
+ swap(ip, ip_to);
+ if (unlikely(ip + UINT_MAX == ip_to))
+ return -IPSET_ERR_HASH_RANGE;
+ }
+
+ port_to = port = ntohs(e.port);
+ if (tb[IPSET_ATTR_PORT_TO]) {
+ port_to = ip_set_get_h16(tb[IPSET_ATTR_PORT_TO]);
+ if (port > port_to)
+ swap(port, port_to);
+ }
+
+ ip2_to = ip2_from;
+ if (tb[IPSET_ATTR_IP2_TO]) {
+ ret = ip_set_get_hostipaddr4(tb[IPSET_ATTR_IP2_TO], &ip2_to);
+ if (ret)
+ return ret;
+ if (ip2_from > ip2_to)
+ swap(ip2_from, ip2_to);
+ if (unlikely(ip2_from + UINT_MAX == ip2_to))
+ return -IPSET_ERR_HASH_RANGE;
+ }
+
+ if (retried)
+ ip = ntohl(h->next.ip[0]);
+
+ while (!after(ip, ip_to)) {
+ e.ip[0] = htonl(ip);
+ ip_last = ip_set_range_to_cidr(ip, ip_to, &cidr);
+ e.cidr[0] = cidr;
+ p = retried && ip == ntohl(h->next.ip[0]) ? ntohs(h->next.port)
+ : port;
+ for (; p <= port_to; p++) {
+ e.port = htons(p);
+ ip2 = (retried && ip == ntohl(h->next.ip[0]) &&
+ p == ntohs(h->next.port)) ? ntohl(h->next.ip[1])
+ : ip2_from;
+ while (!after(ip2, ip2_to)) {
+ e.ip[1] = htonl(ip2);
+ ip2_last = ip_set_range_to_cidr(ip2, ip2_to,
+ &cidr2);
+ e.cidr[1] = cidr2;
+ ret = adtfn(set, &e, &ext, &ext, flags);
+ if (ret && !ip_set_eexist(ret, flags))
+ return ret;
+ else
+ ret = 0;
+ ip2 = ip2_last + 1;
+ }
+ }
+ ip = ip_last + 1;
+ }
+ return ret;
+}
+
+/* IPv6 variant */
+
+struct hash_netportnet6_elem {
+ union nf_inet_addr ip[2];
+ __be16 port;
+ union {
+ u8 cidr[2];
+ u16 ccmp;
+ };
+ u8 nomatch:1;
+ u8 proto;
+};
+
+/* Common functions */
+
+static inline bool
+hash_netportnet6_data_equal(const struct hash_netportnet6_elem *ip1,
+ const struct hash_netportnet6_elem *ip2,
+ u32 *multi)
+{
+ return ipv6_addr_equal(&ip1->ip[0].in6, &ip2->ip[0].in6) &&
+ ipv6_addr_equal(&ip1->ip[1].in6, &ip2->ip[1].in6) &&
+ ip1->ccmp == ip2->ccmp &&
+ ip1->port == ip2->port &&
+ ip1->proto == ip2->proto;
+}
+
+static inline int
+hash_netportnet6_do_data_match(const struct hash_netportnet6_elem *elem)
+{
+ return elem->nomatch ? -ENOTEMPTY : 1;
+}
+
+static inline void
+hash_netportnet6_data_set_flags(struct hash_netportnet6_elem *elem, u32 flags)
+{
+ elem->nomatch = !!((flags >> 16) & IPSET_FLAG_NOMATCH);
+}
+
+static inline void
+hash_netportnet6_data_reset_flags(struct hash_netportnet6_elem *elem, u8 *flags)
+{
+ swap(*flags, elem->nomatch);
+}
+
+static inline void
+hash_netportnet6_data_reset_elem(struct hash_netportnet6_elem *elem,
+ struct hash_netportnet6_elem *orig)
+{
+ elem->ip[1] = orig->ip[1];
+}
+
+static inline void
+hash_netportnet6_data_netmask(struct hash_netportnet6_elem *elem,
+ u8 cidr, bool inner)
+{
+ if (inner) {
+ ip6_netmask(&elem->ip[1], cidr);
+ elem->cidr[1] = cidr;
+ } else {
+ ip6_netmask(&elem->ip[0], cidr);
+ elem->cidr[0] = cidr;
+ }
+}
+
+static bool
+hash_netportnet6_data_list(struct sk_buff *skb,
+ const struct hash_netportnet6_elem *data)
+{
+ u32 flags = data->nomatch ? IPSET_FLAG_NOMATCH : 0;
+
+ if (nla_put_ipaddr6(skb, IPSET_ATTR_IP, &data->ip[0].in6) ||
+ nla_put_ipaddr6(skb, IPSET_ATTR_IP2, &data->ip[1].in6) ||
+ nla_put_net16(skb, IPSET_ATTR_PORT, data->port) ||
+ nla_put_u8(skb, IPSET_ATTR_CIDR, data->cidr[0]) ||
+ nla_put_u8(skb, IPSET_ATTR_CIDR2, data->cidr[1]) ||
+ nla_put_u8(skb, IPSET_ATTR_PROTO, data->proto) ||
+ (flags &&
+ nla_put_net32(skb, IPSET_ATTR_CADT_FLAGS, htonl(flags))))
+ goto nla_put_failure;
+ return 0;
+
+nla_put_failure:
+ return 1;
+}
+
+static inline void
+hash_netportnet6_data_next(struct hash_netportnet4_elem *next,
+ const struct hash_netportnet6_elem *d)
+{
+ next->port = d->port;
+}
+
+#undef MTYPE
+#undef PF
+#undef HOST_MASK
+
+#define MTYPE hash_netportnet6
+#define PF 6
+#define HOST_MASK 128
+#define IP_SET_EMIT_CREATE
+#include "ip_set_hash_gen.h"
+
+static int
+hash_netportnet6_kadt(struct ip_set *set, const struct sk_buff *skb,
+ const struct xt_action_param *par,
+ enum ipset_adt adt, struct ip_set_adt_opt *opt)
+{
+ const struct hash_netportnet *h = set->data;
+ ipset_adtfn adtfn = set->variant->adt[adt];
+ struct hash_netportnet6_elem e = { };
+ struct ip_set_ext ext = IP_SET_INIT_KEXT(skb, opt, set);
+
+ e.cidr[0] = IP_SET_INIT_CIDR(h->nets[0].cidr[0], HOST_MASK);
+ e.cidr[1] = IP_SET_INIT_CIDR(h->nets[0].cidr[1], HOST_MASK);
+ if (adt == IPSET_TEST)
+ e.ccmp = (HOST_MASK << (sizeof(u8) * 8)) | HOST_MASK;
+
+ if (!ip_set_get_ip6_port(skb, opt->flags & IPSET_DIM_TWO_SRC,
+ &e.port, &e.proto))
+ return -EINVAL;
+
+ ip6addrptr(skb, opt->flags & IPSET_DIM_ONE_SRC, &e.ip[0].in6);
+ ip6addrptr(skb, opt->flags & IPSET_DIM_THREE_SRC, &e.ip[1].in6);
+ ip6_netmask(&e.ip[0], e.cidr[0]);
+ ip6_netmask(&e.ip[1], e.cidr[1]);
+
+ return adtfn(set, &e, &ext, &opt->ext, opt->cmdflags);
+}
+
+static int
+hash_netportnet6_uadt(struct ip_set *set, struct nlattr *tb[],
+ enum ipset_adt adt, u32 *lineno, u32 flags, bool retried)
+{
+ const struct hash_netportnet *h = set->data;
+ ipset_adtfn adtfn = set->variant->adt[adt];
+ struct hash_netportnet6_elem e = { };
+ struct ip_set_ext ext = IP_SET_INIT_UEXT(set);
+ u32 port, port_to;
+ bool with_ports = false;
+ int ret;
+
+ e.cidr[0] = e.cidr[1] = HOST_MASK;
+ if (unlikely(!tb[IPSET_ATTR_IP] || !tb[IPSET_ATTR_IP2] ||
+ !ip_set_attr_netorder(tb, IPSET_ATTR_PORT) ||
+ !ip_set_optattr_netorder(tb, IPSET_ATTR_PORT_TO) ||
+ !ip_set_optattr_netorder(tb, IPSET_ATTR_TIMEOUT) ||
+ !ip_set_optattr_netorder(tb, IPSET_ATTR_CADT_FLAGS) ||
+ !ip_set_optattr_netorder(tb, IPSET_ATTR_PACKETS) ||
+ !ip_set_optattr_netorder(tb, IPSET_ATTR_BYTES)))
+ return -IPSET_ERR_PROTOCOL;
+ if (unlikely(tb[IPSET_ATTR_IP_TO] || tb[IPSET_ATTR_IP2_TO]))
+ return -IPSET_ERR_HASH_RANGE_UNSUPPORTED;
+
+ if (tb[IPSET_ATTR_LINENO])
+ *lineno = nla_get_u32(tb[IPSET_ATTR_LINENO]);
+
+ ret = ip_set_get_ipaddr6(tb[IPSET_ATTR_IP], &e.ip[0]) ||
+ ip_set_get_ipaddr6(tb[IPSET_ATTR_IP2], &e.ip[1]) ||
+ ip_set_get_extensions(set, tb, &ext);
+ if (ret)
+ return ret;
+
+ if (tb[IPSET_ATTR_CIDR])
+ e.cidr[0] = nla_get_u8(tb[IPSET_ATTR_CIDR]);
+
+ if (tb[IPSET_ATTR_CIDR2])
+ e.cidr[1] = nla_get_u8(tb[IPSET_ATTR_CIDR2]);
+
+ if (unlikely(!e.cidr[0] || e.cidr[0] > HOST_MASK || !e.cidr[1] ||
+ e.cidr[1] > HOST_MASK))
+ return -IPSET_ERR_INVALID_CIDR;
+
+ ip6_netmask(&e.ip[0], e.cidr[0]);
+ ip6_netmask(&e.ip[1], e.cidr[1]);
+
+ if (tb[IPSET_ATTR_PORT])
+ e.port = nla_get_be16(tb[IPSET_ATTR_PORT]);
+ else
+ return -IPSET_ERR_PROTOCOL;
+
+ if (tb[IPSET_ATTR_PROTO]) {
+ e.proto = nla_get_u8(tb[IPSET_ATTR_PROTO]);
+ with_ports = ip_set_proto_with_ports(e.proto);
+
+ if (e.proto == 0)
+ return -IPSET_ERR_INVALID_PROTO;
+ } else
+ return -IPSET_ERR_MISSING_PROTO;
+
+ if (!(with_ports || e.proto == IPPROTO_ICMPV6))
+ e.port = 0;
+
+ if (tb[IPSET_ATTR_CADT_FLAGS]) {
+ u32 cadt_flags = ip_set_get_h32(tb[IPSET_ATTR_CADT_FLAGS]);
+ if (cadt_flags & IPSET_FLAG_NOMATCH)
+ flags |= (IPSET_FLAG_NOMATCH << 16);
+ }
+
+ if (adt == IPSET_TEST || !with_ports || !tb[IPSET_ATTR_PORT_TO]) {
+ ret = adtfn(set, &e, &ext, &ext, flags);
+ return ip_set_enomatch(ret, flags, adt, set) ? -ret :
+ ip_set_eexist(ret, flags) ? 0 : ret;
+ }
+
+ port = ntohs(e.port);
+ port_to = ip_set_get_h16(tb[IPSET_ATTR_PORT_TO]);
+ if (port > port_to)
+ swap(port, port_to);
+
+ if (retried)
+ port = ntohs(h->next.port);
+ for (; port <= port_to; port++) {
+ e.port = htons(port);
+ ret = adtfn(set, &e, &ext, &ext, flags);
+
+ if (ret && !ip_set_eexist(ret, flags))
+ return ret;
+ else
+ ret = 0;
+ }
+ return ret;
+}
+
+static struct ip_set_type hash_netportnet_type __read_mostly = {
+ .name = "hash:net,port,net",
+ .protocol = IPSET_PROTOCOL,
+ .features = IPSET_TYPE_IP | IPSET_TYPE_PORT | IPSET_TYPE_IP2 |
+ IPSET_TYPE_NOMATCH,
+ .dimension = IPSET_DIM_THREE,
+ .family = NFPROTO_UNSPEC,
+ .revision_min = IPSET_TYPE_REV_MIN,
+ .revision_max = IPSET_TYPE_REV_MAX,
+ .create = hash_netportnet_create,
+ .create_policy = {
+ [IPSET_ATTR_HASHSIZE] = { .type = NLA_U32 },
+ [IPSET_ATTR_MAXELEM] = { .type = NLA_U32 },
+ [IPSET_ATTR_PROBES] = { .type = NLA_U8 },
+ [IPSET_ATTR_RESIZE] = { .type = NLA_U8 },
+ [IPSET_ATTR_TIMEOUT] = { .type = NLA_U32 },
+ [IPSET_ATTR_CADT_FLAGS] = { .type = NLA_U32 },
+ },
+ .adt_policy = {
+ [IPSET_ATTR_IP] = { .type = NLA_NESTED },
+ [IPSET_ATTR_IP_TO] = { .type = NLA_NESTED },
+ [IPSET_ATTR_IP2] = { .type = NLA_NESTED },
+ [IPSET_ATTR_IP2_TO] = { .type = NLA_NESTED },
+ [IPSET_ATTR_PORT] = { .type = NLA_U16 },
+ [IPSET_ATTR_PORT_TO] = { .type = NLA_U16 },
+ [IPSET_ATTR_CIDR] = { .type = NLA_U8 },
+ [IPSET_ATTR_CIDR2] = { .type = NLA_U8 },
+ [IPSET_ATTR_PROTO] = { .type = NLA_U8 },
+ [IPSET_ATTR_CADT_FLAGS] = { .type = NLA_U32 },
+ [IPSET_ATTR_TIMEOUT] = { .type = NLA_U32 },
+ [IPSET_ATTR_LINENO] = { .type = NLA_U32 },
+ [IPSET_ATTR_BYTES] = { .type = NLA_U64 },
+ [IPSET_ATTR_PACKETS] = { .type = NLA_U64 },
+ [IPSET_ATTR_COMMENT] = { .type = NLA_NUL_STRING },
+ },
+ .me = THIS_MODULE,
+};
+
+static int __init
+hash_netportnet_init(void)
+{
+ return ip_set_type_register(&hash_netportnet_type);
+}
+
+static void __exit
+hash_netportnet_fini(void)
+{
+ ip_set_type_unregister(&hash_netportnet_type);
+}
+
+module_init(hash_netportnet_init);
+module_exit(hash_netportnet_fini);
diff --git a/net/netfilter/ipset/ip_set_list_set.c b/net/netfilter/ipset/ip_set_list_set.c
index 8371c2bac2e..3e2317f3cf6 100644
--- a/net/netfilter/ipset/ip_set_list_set.c
+++ b/net/netfilter/ipset/ip_set_list_set.c
@@ -1,4 +1,4 @@
-/* Copyright (C) 2008-2011 Jozsef Kadlecsik <kadlec@blackhole.kfki.hu>
+/* Copyright (C) 2008-2013 Jozsef Kadlecsik <kadlec@blackhole.kfki.hu>
*
* This program is free software; you can redistribute it and/or modify
* it under the terms of the GNU General Public License version 2 as
@@ -13,211 +13,354 @@
#include <linux/errno.h>
#include <linux/netfilter/ipset/ip_set.h>
-#include <linux/netfilter/ipset/ip_set_timeout.h>
#include <linux/netfilter/ipset/ip_set_list.h>
-#define REVISION_MIN 0
-#define REVISION_MAX 0
+#define IPSET_TYPE_REV_MIN 0
+/* 1 Counters support added */
+#define IPSET_TYPE_REV_MAX 2 /* Comments support added */
MODULE_LICENSE("GPL");
MODULE_AUTHOR("Jozsef Kadlecsik <kadlec@blackhole.kfki.hu>");
-IP_SET_MODULE_DESC("list:set", REVISION_MIN, REVISION_MAX);
+IP_SET_MODULE_DESC("list:set", IPSET_TYPE_REV_MIN, IPSET_TYPE_REV_MAX);
MODULE_ALIAS("ip_set_list:set");
-/* Member elements without and with timeout */
+/* Member elements */
struct set_elem {
ip_set_id_t id;
};
-struct set_telem {
+struct set_adt_elem {
ip_set_id_t id;
- unsigned long timeout;
+ ip_set_id_t refid;
+ int before;
};
/* Type structure */
struct list_set {
- size_t dsize; /* element size */
u32 size; /* size of set list array */
- u32 timeout; /* timeout value */
struct timer_list gc; /* garbage collection */
+ struct net *net; /* namespace */
struct set_elem members[0]; /* the set members */
};
-static inline struct set_elem *
-list_set_elem(const struct list_set *map, u32 id)
-{
- return (struct set_elem *)((void *)map->members + id * map->dsize);
-}
-
-static inline struct set_telem *
-list_set_telem(const struct list_set *map, u32 id)
-{
- return (struct set_telem *)((void *)map->members + id * map->dsize);
-}
+#define list_set_elem(set, map, id) \
+ (struct set_elem *)((void *)(map)->members + (id) * (set)->dsize)
-static inline bool
-list_set_timeout(const struct list_set *map, u32 id)
+static int
+list_set_ktest(struct ip_set *set, const struct sk_buff *skb,
+ const struct xt_action_param *par,
+ struct ip_set_adt_opt *opt, const struct ip_set_ext *ext)
{
- const struct set_telem *elem = list_set_telem(map, id);
+ struct list_set *map = set->data;
+ struct set_elem *e;
+ u32 i, cmdflags = opt->cmdflags;
+ int ret;
- return ip_set_timeout_test(elem->timeout);
+ /* Don't lookup sub-counters at all */
+ opt->cmdflags &= ~IPSET_FLAG_MATCH_COUNTERS;
+ if (opt->cmdflags & IPSET_FLAG_SKIP_SUBCOUNTER_UPDATE)
+ opt->cmdflags &= ~IPSET_FLAG_SKIP_COUNTER_UPDATE;
+ for (i = 0; i < map->size; i++) {
+ e = list_set_elem(set, map, i);
+ if (e->id == IPSET_INVALID_ID)
+ return 0;
+ if (SET_WITH_TIMEOUT(set) &&
+ ip_set_timeout_expired(ext_timeout(e, set)))
+ continue;
+ ret = ip_set_test(e->id, skb, par, opt);
+ if (ret > 0) {
+ if (SET_WITH_COUNTER(set))
+ ip_set_update_counter(ext_counter(e, set),
+ ext, &opt->ext,
+ cmdflags);
+ return ret;
+ }
+ }
+ return 0;
}
-static inline bool
-list_set_expired(const struct list_set *map, u32 id)
+static int
+list_set_kadd(struct ip_set *set, const struct sk_buff *skb,
+ const struct xt_action_param *par,
+ struct ip_set_adt_opt *opt, const struct ip_set_ext *ext)
{
- const struct set_telem *elem = list_set_telem(map, id);
+ struct list_set *map = set->data;
+ struct set_elem *e;
+ u32 i;
+ int ret;
- return ip_set_timeout_expired(elem->timeout);
+ for (i = 0; i < map->size; i++) {
+ e = list_set_elem(set, map, i);
+ if (e->id == IPSET_INVALID_ID)
+ return 0;
+ if (SET_WITH_TIMEOUT(set) &&
+ ip_set_timeout_expired(ext_timeout(e, set)))
+ continue;
+ ret = ip_set_add(e->id, skb, par, opt);
+ if (ret == 0)
+ return ret;
+ }
+ return 0;
}
-/* Set list without and with timeout */
-
static int
-list_set_kadt(struct ip_set *set, const struct sk_buff *skb,
+list_set_kdel(struct ip_set *set, const struct sk_buff *skb,
const struct xt_action_param *par,
- enum ipset_adt adt, const struct ip_set_adt_opt *opt)
+ struct ip_set_adt_opt *opt, const struct ip_set_ext *ext)
{
struct list_set *map = set->data;
- struct set_elem *elem;
+ struct set_elem *e;
u32 i;
int ret;
for (i = 0; i < map->size; i++) {
- elem = list_set_elem(map, i);
- if (elem->id == IPSET_INVALID_ID)
+ e = list_set_elem(set, map, i);
+ if (e->id == IPSET_INVALID_ID)
return 0;
- if (with_timeout(map->timeout) && list_set_expired(map, i))
+ if (SET_WITH_TIMEOUT(set) &&
+ ip_set_timeout_expired(ext_timeout(e, set)))
continue;
- switch (adt) {
- case IPSET_TEST:
- ret = ip_set_test(elem->id, skb, par, opt);
- if (ret > 0)
- return ret;
- break;
- case IPSET_ADD:
- ret = ip_set_add(elem->id, skb, par, opt);
- if (ret == 0)
- return ret;
- break;
- case IPSET_DEL:
- ret = ip_set_del(elem->id, skb, par, opt);
- if (ret == 0)
- return ret;
- break;
- default:
- break;
- }
+ ret = ip_set_del(e->id, skb, par, opt);
+ if (ret == 0)
+ return ret;
+ }
+ return 0;
+}
+
+static int
+list_set_kadt(struct ip_set *set, const struct sk_buff *skb,
+ const struct xt_action_param *par,
+ enum ipset_adt adt, struct ip_set_adt_opt *opt)
+{
+ struct ip_set_ext ext = IP_SET_INIT_KEXT(skb, opt, set);
+
+ switch (adt) {
+ case IPSET_TEST:
+ return list_set_ktest(set, skb, par, opt, &ext);
+ case IPSET_ADD:
+ return list_set_kadd(set, skb, par, opt, &ext);
+ case IPSET_DEL:
+ return list_set_kdel(set, skb, par, opt, &ext);
+ default:
+ break;
}
return -EINVAL;
}
static bool
-id_eq(const struct list_set *map, u32 i, ip_set_id_t id)
+id_eq(const struct ip_set *set, u32 i, ip_set_id_t id)
{
- const struct set_elem *elem;
+ const struct list_set *map = set->data;
+ const struct set_elem *e;
+
+ if (i >= map->size)
+ return 0;
+
+ e = list_set_elem(set, map, i);
+ return !!(e->id == id &&
+ !(SET_WITH_TIMEOUT(set) &&
+ ip_set_timeout_expired(ext_timeout(e, set))));
+}
- if (i < map->size) {
- elem = list_set_elem(map, i);
- return elem->id == id;
+static int
+list_set_add(struct ip_set *set, u32 i, struct set_adt_elem *d,
+ const struct ip_set_ext *ext)
+{
+ struct list_set *map = set->data;
+ struct set_elem *e = list_set_elem(set, map, i);
+
+ if (e->id != IPSET_INVALID_ID) {
+ if (i == map->size - 1) {
+ /* Last element replaced: e.g. add new,before,last */
+ ip_set_put_byindex(map->net, e->id);
+ ip_set_ext_destroy(set, e);
+ } else {
+ struct set_elem *x = list_set_elem(set, map,
+ map->size - 1);
+
+ /* Last element pushed off */
+ if (x->id != IPSET_INVALID_ID) {
+ ip_set_put_byindex(map->net, x->id);
+ ip_set_ext_destroy(set, x);
+ }
+ memmove(list_set_elem(set, map, i + 1), e,
+ set->dsize * (map->size - (i + 1)));
+ /* Extensions must be initialized to zero */
+ memset(e, 0, set->dsize);
+ }
}
+ e->id = d->id;
+ if (SET_WITH_TIMEOUT(set))
+ ip_set_timeout_set(ext_timeout(e, set), ext->timeout);
+ if (SET_WITH_COUNTER(set))
+ ip_set_init_counter(ext_counter(e, set), ext);
+ if (SET_WITH_COMMENT(set))
+ ip_set_init_comment(ext_comment(e, set), ext);
return 0;
}
-static bool
-id_eq_timeout(const struct list_set *map, u32 i, ip_set_id_t id)
+static int
+list_set_del(struct ip_set *set, u32 i)
{
- const struct set_elem *elem;
+ struct list_set *map = set->data;
+ struct set_elem *e = list_set_elem(set, map, i);
- if (i < map->size) {
- elem = list_set_elem(map, i);
- return !!(elem->id == id &&
- !(with_timeout(map->timeout) &&
- list_set_expired(map, i)));
- }
+ ip_set_put_byindex(map->net, e->id);
+ ip_set_ext_destroy(set, e);
+
+ if (i < map->size - 1)
+ memmove(e, list_set_elem(set, map, i + 1),
+ set->dsize * (map->size - (i + 1)));
+ /* Last element */
+ e = list_set_elem(set, map, map->size - 1);
+ e->id = IPSET_INVALID_ID;
return 0;
}
static void
-list_elem_add(struct list_set *map, u32 i, ip_set_id_t id)
+set_cleanup_entries(struct ip_set *set)
{
+ struct list_set *map = set->data;
struct set_elem *e;
-
- for (; i < map->size; i++) {
- e = list_set_elem(map, i);
- swap(e->id, id);
- if (e->id == IPSET_INVALID_ID)
- break;
+ u32 i = 0;
+
+ while (i < map->size) {
+ e = list_set_elem(set, map, i);
+ if (e->id != IPSET_INVALID_ID &&
+ ip_set_timeout_expired(ext_timeout(e, set)))
+ list_set_del(set, i);
+ /* Check element moved to position i in next loop */
+ else
+ i++;
}
}
-static void
-list_elem_tadd(struct list_set *map, u32 i, ip_set_id_t id,
- unsigned long timeout)
+static int
+list_set_utest(struct ip_set *set, void *value, const struct ip_set_ext *ext,
+ struct ip_set_ext *mext, u32 flags)
{
- struct set_telem *e;
+ struct list_set *map = set->data;
+ struct set_adt_elem *d = value;
+ struct set_elem *e;
+ u32 i;
+ int ret;
- for (; i < map->size; i++) {
- e = list_set_telem(map, i);
- swap(e->id, id);
- swap(e->timeout, timeout);
+ for (i = 0; i < map->size; i++) {
+ e = list_set_elem(set, map, i);
if (e->id == IPSET_INVALID_ID)
- break;
+ return 0;
+ else if (SET_WITH_TIMEOUT(set) &&
+ ip_set_timeout_expired(ext_timeout(e, set)))
+ continue;
+ else if (e->id != d->id)
+ continue;
+
+ if (d->before == 0)
+ return 1;
+ else if (d->before > 0)
+ ret = id_eq(set, i + 1, d->refid);
+ else
+ ret = i > 0 && id_eq(set, i - 1, d->refid);
+ return ret;
}
+ return 0;
}
+
static int
-list_set_add(struct list_set *map, u32 i, ip_set_id_t id,
- unsigned long timeout)
+list_set_uadd(struct ip_set *set, void *value, const struct ip_set_ext *ext,
+ struct ip_set_ext *mext, u32 flags)
{
- const struct set_elem *e = list_set_elem(map, i);
+ struct list_set *map = set->data;
+ struct set_adt_elem *d = value;
+ struct set_elem *e;
+ bool flag_exist = flags & IPSET_FLAG_EXIST;
+ u32 i, ret = 0;
- if (i == map->size - 1 && e->id != IPSET_INVALID_ID)
- /* Last element replaced: e.g. add new,before,last */
- ip_set_put_byindex(e->id);
- if (with_timeout(map->timeout))
- list_elem_tadd(map, i, id, ip_set_timeout_set(timeout));
- else
- list_elem_add(map, i, id);
+ if (SET_WITH_TIMEOUT(set))
+ set_cleanup_entries(set);
- return 0;
-}
+ /* Check already added element */
+ for (i = 0; i < map->size; i++) {
+ e = list_set_elem(set, map, i);
+ if (e->id == IPSET_INVALID_ID)
+ goto insert;
+ else if (e->id != d->id)
+ continue;
-static int
-list_set_del(struct list_set *map, u32 i)
-{
- struct set_elem *a = list_set_elem(map, i), *b;
-
- ip_set_put_byindex(a->id);
-
- for (; i < map->size - 1; i++) {
- b = list_set_elem(map, i + 1);
- a->id = b->id;
- if (with_timeout(map->timeout))
- ((struct set_telem *)a)->timeout =
- ((struct set_telem *)b)->timeout;
- a = b;
- if (a->id == IPSET_INVALID_ID)
- break;
+ if ((d->before > 1 && !id_eq(set, i + 1, d->refid)) ||
+ (d->before < 0 &&
+ (i == 0 || !id_eq(set, i - 1, d->refid))))
+ /* Before/after doesn't match */
+ return -IPSET_ERR_REF_EXIST;
+ if (!flag_exist)
+ /* Can't re-add */
+ return -IPSET_ERR_EXIST;
+ /* Update extensions */
+ ip_set_ext_destroy(set, e);
+
+ if (SET_WITH_TIMEOUT(set))
+ ip_set_timeout_set(ext_timeout(e, set), ext->timeout);
+ if (SET_WITH_COUNTER(set))
+ ip_set_init_counter(ext_counter(e, set), ext);
+ if (SET_WITH_COMMENT(set))
+ ip_set_init_comment(ext_comment(e, set), ext);
+ /* Set is already added to the list */
+ ip_set_put_byindex(map->net, d->id);
+ return 0;
}
- /* Last element */
- a->id = IPSET_INVALID_ID;
- return 0;
+insert:
+ ret = -IPSET_ERR_LIST_FULL;
+ for (i = 0; i < map->size && ret == -IPSET_ERR_LIST_FULL; i++) {
+ e = list_set_elem(set, map, i);
+ if (e->id == IPSET_INVALID_ID)
+ ret = d->before != 0 ? -IPSET_ERR_REF_EXIST
+ : list_set_add(set, i, d, ext);
+ else if (e->id != d->refid)
+ continue;
+ else if (d->before > 0)
+ ret = list_set_add(set, i, d, ext);
+ else if (i + 1 < map->size)
+ ret = list_set_add(set, i + 1, d, ext);
+ }
+
+ return ret;
}
-static void
-cleanup_entries(struct list_set *map)
+static int
+list_set_udel(struct ip_set *set, void *value, const struct ip_set_ext *ext,
+ struct ip_set_ext *mext, u32 flags)
{
- struct set_telem *e;
+ struct list_set *map = set->data;
+ struct set_adt_elem *d = value;
+ struct set_elem *e;
u32 i;
for (i = 0; i < map->size; i++) {
- e = list_set_telem(map, i);
- if (e->id != IPSET_INVALID_ID && list_set_expired(map, i))
- list_set_del(map, i);
+ e = list_set_elem(set, map, i);
+ if (e->id == IPSET_INVALID_ID)
+ return d->before != 0 ? -IPSET_ERR_REF_EXIST
+ : -IPSET_ERR_EXIST;
+ else if (SET_WITH_TIMEOUT(set) &&
+ ip_set_timeout_expired(ext_timeout(e, set)))
+ continue;
+ else if (e->id != d->id)
+ continue;
+
+ if (d->before == 0)
+ return list_set_del(set, i);
+ else if (d->before > 0) {
+ if (!id_eq(set, i + 1, d->refid))
+ return -IPSET_ERR_REF_EXIST;
+ return list_set_del(set, i);
+ } else if (i == 0 || !id_eq(set, i - 1, d->refid))
+ return -IPSET_ERR_REF_EXIST;
+ else
+ return list_set_del(set, i);
}
+ return -IPSET_ERR_EXIST;
}
static int
@@ -225,26 +368,27 @@ list_set_uadt(struct ip_set *set, struct nlattr *tb[],
enum ipset_adt adt, u32 *lineno, u32 flags, bool retried)
{
struct list_set *map = set->data;
- bool with_timeout = with_timeout(map->timeout);
- bool flag_exist = flags & IPSET_FLAG_EXIST;
- int before = 0;
- u32 timeout = map->timeout;
- ip_set_id_t id, refid = IPSET_INVALID_ID;
- const struct set_elem *elem;
+ ipset_adtfn adtfn = set->variant->adt[adt];
+ struct set_adt_elem e = { .refid = IPSET_INVALID_ID };
+ struct ip_set_ext ext = IP_SET_INIT_UEXT(set);
struct ip_set *s;
- u32 i;
int ret = 0;
if (unlikely(!tb[IPSET_ATTR_NAME] ||
!ip_set_optattr_netorder(tb, IPSET_ATTR_TIMEOUT) ||
- !ip_set_optattr_netorder(tb, IPSET_ATTR_CADT_FLAGS)))
+ !ip_set_optattr_netorder(tb, IPSET_ATTR_CADT_FLAGS) ||
+ !ip_set_optattr_netorder(tb, IPSET_ATTR_PACKETS) ||
+ !ip_set_optattr_netorder(tb, IPSET_ATTR_BYTES)))
return -IPSET_ERR_PROTOCOL;
if (tb[IPSET_ATTR_LINENO])
*lineno = nla_get_u32(tb[IPSET_ATTR_LINENO]);
- id = ip_set_get_byname(nla_data(tb[IPSET_ATTR_NAME]), &s);
- if (id == IPSET_INVALID_ID)
+ ret = ip_set_get_extensions(set, tb, &ext);
+ if (ret)
+ return ret;
+ e.id = ip_set_get_byname(map->net, nla_data(tb[IPSET_ATTR_NAME]), &s);
+ if (e.id == IPSET_INVALID_ID)
return -IPSET_ERR_NAME;
/* "Loop detection" */
if (s->type->features & IPSET_TYPE_NAME) {
@@ -254,115 +398,35 @@ list_set_uadt(struct ip_set *set, struct nlattr *tb[],
if (tb[IPSET_ATTR_CADT_FLAGS]) {
u32 f = ip_set_get_h32(tb[IPSET_ATTR_CADT_FLAGS]);
- before = f & IPSET_FLAG_BEFORE;
+ e.before = f & IPSET_FLAG_BEFORE;
}
- if (before && !tb[IPSET_ATTR_NAMEREF]) {
+ if (e.before && !tb[IPSET_ATTR_NAMEREF]) {
ret = -IPSET_ERR_BEFORE;
goto finish;
}
if (tb[IPSET_ATTR_NAMEREF]) {
- refid = ip_set_get_byname(nla_data(tb[IPSET_ATTR_NAMEREF]),
- &s);
- if (refid == IPSET_INVALID_ID) {
+ e.refid = ip_set_get_byname(map->net,
+ nla_data(tb[IPSET_ATTR_NAMEREF]),
+ &s);
+ if (e.refid == IPSET_INVALID_ID) {
ret = -IPSET_ERR_NAMEREF;
goto finish;
}
- if (!before)
- before = -1;
+ if (!e.before)
+ e.before = -1;
}
- if (tb[IPSET_ATTR_TIMEOUT]) {
- if (!with_timeout) {
- ret = -IPSET_ERR_TIMEOUT;
- goto finish;
- }
- timeout = ip_set_timeout_uget(tb[IPSET_ATTR_TIMEOUT]);
- }
- if (with_timeout && adt != IPSET_TEST)
- cleanup_entries(map);
+ if (adt != IPSET_TEST && SET_WITH_TIMEOUT(set))
+ set_cleanup_entries(set);
- switch (adt) {
- case IPSET_TEST:
- for (i = 0; i < map->size && !ret; i++) {
- elem = list_set_elem(map, i);
- if (elem->id == IPSET_INVALID_ID ||
- (before != 0 && i + 1 >= map->size))
- break;
- else if (with_timeout && list_set_expired(map, i))
- continue;
- else if (before > 0 && elem->id == id)
- ret = id_eq_timeout(map, i + 1, refid);
- else if (before < 0 && elem->id == refid)
- ret = id_eq_timeout(map, i + 1, id);
- else if (before == 0 && elem->id == id)
- ret = 1;
- }
- break;
- case IPSET_ADD:
- for (i = 0; i < map->size; i++) {
- elem = list_set_elem(map, i);
- if (elem->id != id)
- continue;
- if (!(with_timeout && flag_exist)) {
- ret = -IPSET_ERR_EXIST;
- goto finish;
- } else {
- struct set_telem *e = list_set_telem(map, i);
-
- if ((before > 1 &&
- !id_eq(map, i + 1, refid)) ||
- (before < 0 &&
- (i == 0 || !id_eq(map, i - 1, refid)))) {
- ret = -IPSET_ERR_EXIST;
- goto finish;
- }
- e->timeout = ip_set_timeout_set(timeout);
- ip_set_put_byindex(id);
- ret = 0;
- goto finish;
- }
- }
- ret = -IPSET_ERR_LIST_FULL;
- for (i = 0; i < map->size && ret == -IPSET_ERR_LIST_FULL; i++) {
- elem = list_set_elem(map, i);
- if (elem->id == IPSET_INVALID_ID)
- ret = before != 0 ? -IPSET_ERR_REF_EXIST
- : list_set_add(map, i, id, timeout);
- else if (elem->id != refid)
- continue;
- else if (before > 0)
- ret = list_set_add(map, i, id, timeout);
- else if (i + 1 < map->size)
- ret = list_set_add(map, i + 1, id, timeout);
- }
- break;
- case IPSET_DEL:
- ret = -IPSET_ERR_EXIST;
- for (i = 0; i < map->size && ret == -IPSET_ERR_EXIST; i++) {
- elem = list_set_elem(map, i);
- if (elem->id == IPSET_INVALID_ID) {
- ret = before != 0 ? -IPSET_ERR_REF_EXIST
- : -IPSET_ERR_EXIST;
- break;
- } else if (elem->id == id &&
- (before == 0 ||
- (before > 0 && id_eq(map, i + 1, refid))))
- ret = list_set_del(map, i);
- else if (elem->id == refid &&
- before < 0 && id_eq(map, i + 1, id))
- ret = list_set_del(map, i + 1);
- }
- break;
- default:
- break;
- }
+ ret = adtfn(set, &e, &ext, &ext, flags);
finish:
- if (refid != IPSET_INVALID_ID)
- ip_set_put_byindex(refid);
+ if (e.refid != IPSET_INVALID_ID)
+ ip_set_put_byindex(map->net, e.refid);
if (adt != IPSET_ADD || ret)
- ip_set_put_byindex(id);
+ ip_set_put_byindex(map->net, e.id);
return ip_set_eexist(ret, flags) ? 0 : ret;
}
@@ -371,14 +435,15 @@ static void
list_set_flush(struct ip_set *set)
{
struct list_set *map = set->data;
- struct set_elem *elem;
+ struct set_elem *e;
u32 i;
for (i = 0; i < map->size; i++) {
- elem = list_set_elem(map, i);
- if (elem->id != IPSET_INVALID_ID) {
- ip_set_put_byindex(elem->id);
- elem->id = IPSET_INVALID_ID;
+ e = list_set_elem(set, map, i);
+ if (e->id != IPSET_INVALID_ID) {
+ ip_set_put_byindex(map->net, e->id);
+ ip_set_ext_destroy(set, e);
+ e->id = IPSET_INVALID_ID;
}
}
}
@@ -388,7 +453,7 @@ list_set_destroy(struct ip_set *set)
{
struct list_set *map = set->data;
- if (with_timeout(map->timeout))
+ if (SET_WITH_TIMEOUT(set))
del_timer_sync(&map->gc);
list_set_flush(set);
kfree(map);
@@ -406,11 +471,11 @@ list_set_head(struct ip_set *set, struct sk_buff *skb)
if (!nested)
goto nla_put_failure;
if (nla_put_net32(skb, IPSET_ATTR_SIZE, htonl(map->size)) ||
- (with_timeout(map->timeout) &&
- nla_put_net32(skb, IPSET_ATTR_TIMEOUT, htonl(map->timeout))) ||
nla_put_net32(skb, IPSET_ATTR_REFERENCES, htonl(set->ref - 1)) ||
nla_put_net32(skb, IPSET_ATTR_MEMSIZE,
- htonl(sizeof(*map) + map->size * map->dsize)))
+ htonl(sizeof(*map) + map->size * set->dsize)))
+ goto nla_put_failure;
+ if (unlikely(ip_set_put_flags(skb, set)))
goto nla_put_failure;
ipset_nest_end(skb, nested);
@@ -425,18 +490,20 @@ list_set_list(const struct ip_set *set,
{
const struct list_set *map = set->data;
struct nlattr *atd, *nested;
- u32 i, first = cb->args[2];
+ u32 i, first = cb->args[IPSET_CB_ARG0];
const struct set_elem *e;
atd = ipset_nest_start(skb, IPSET_ATTR_ADT);
if (!atd)
return -EMSGSIZE;
- for (; cb->args[2] < map->size; cb->args[2]++) {
- i = cb->args[2];
- e = list_set_elem(map, i);
+ for (; cb->args[IPSET_CB_ARG0] < map->size;
+ cb->args[IPSET_CB_ARG0]++) {
+ i = cb->args[IPSET_CB_ARG0];
+ e = list_set_elem(set, map, i);
if (e->id == IPSET_INVALID_ID)
goto finish;
- if (with_timeout(map->timeout) && list_set_expired(map, i))
+ if (SET_WITH_TIMEOUT(set) &&
+ ip_set_timeout_expired(ext_timeout(e, set)))
continue;
nested = ipset_nest_start(skb, IPSET_ATTR_DATA);
if (!nested) {
@@ -447,30 +514,25 @@ list_set_list(const struct ip_set *set,
goto nla_put_failure;
}
if (nla_put_string(skb, IPSET_ATTR_NAME,
- ip_set_name_byindex(e->id)))
+ ip_set_name_byindex(map->net, e->id)))
+ goto nla_put_failure;
+ if (ip_set_put_extensions(skb, set, e, true))
goto nla_put_failure;
- if (with_timeout(map->timeout)) {
- const struct set_telem *te =
- (const struct set_telem *) e;
- __be32 to = htonl(ip_set_timeout_get(te->timeout));
- if (nla_put_net32(skb, IPSET_ATTR_TIMEOUT, to))
- goto nla_put_failure;
- }
ipset_nest_end(skb, nested);
}
finish:
ipset_nest_end(skb, atd);
/* Set listing finished */
- cb->args[2] = 0;
+ cb->args[IPSET_CB_ARG0] = 0;
return 0;
nla_put_failure:
nla_nest_cancel(skb, nested);
- ipset_nest_end(skb, atd);
if (unlikely(i == first)) {
- cb->args[2] = 0;
+ cb->args[IPSET_CB_ARG0] = 0;
return -EMSGSIZE;
}
+ ipset_nest_end(skb, atd);
return 0;
}
@@ -481,12 +543,18 @@ list_set_same_set(const struct ip_set *a, const struct ip_set *b)
const struct list_set *y = b->data;
return x->size == y->size &&
- x->timeout == y->timeout;
+ a->timeout == b->timeout &&
+ a->extensions == b->extensions;
}
-static const struct ip_set_type_variant list_set = {
+static const struct ip_set_type_variant set_variant = {
.kadt = list_set_kadt,
.uadt = list_set_uadt,
+ .adt = {
+ [IPSET_ADD] = list_set_uadd,
+ [IPSET_DEL] = list_set_udel,
+ [IPSET_TEST] = list_set_utest,
+ },
.destroy = list_set_destroy,
.flush = list_set_flush,
.head = list_set_head,
@@ -501,46 +569,44 @@ list_set_gc(unsigned long ul_set)
struct list_set *map = set->data;
write_lock_bh(&set->lock);
- cleanup_entries(map);
+ set_cleanup_entries(set);
write_unlock_bh(&set->lock);
- map->gc.expires = jiffies + IPSET_GC_PERIOD(map->timeout) * HZ;
+ map->gc.expires = jiffies + IPSET_GC_PERIOD(set->timeout) * HZ;
add_timer(&map->gc);
}
static void
-list_set_gc_init(struct ip_set *set)
+list_set_gc_init(struct ip_set *set, void (*gc)(unsigned long ul_set))
{
struct list_set *map = set->data;
init_timer(&map->gc);
map->gc.data = (unsigned long) set;
- map->gc.function = list_set_gc;
- map->gc.expires = jiffies + IPSET_GC_PERIOD(map->timeout) * HZ;
+ map->gc.function = gc;
+ map->gc.expires = jiffies + IPSET_GC_PERIOD(set->timeout) * HZ;
add_timer(&map->gc);
}
/* Create list:set type of sets */
static bool
-init_list_set(struct ip_set *set, u32 size, size_t dsize,
- unsigned long timeout)
+init_list_set(struct net *net, struct ip_set *set, u32 size)
{
struct list_set *map;
struct set_elem *e;
u32 i;
- map = kzalloc(sizeof(*map) + size * dsize, GFP_KERNEL);
+ map = kzalloc(sizeof(*map) + size * set->dsize, GFP_KERNEL);
if (!map)
return false;
map->size = size;
- map->dsize = dsize;
- map->timeout = timeout;
+ map->net = net;
set->data = map;
for (i = 0; i < size; i++) {
- e = list_set_elem(map, i);
+ e = list_set_elem(set, map, i);
e->id = IPSET_INVALID_ID;
}
@@ -548,12 +614,14 @@ init_list_set(struct ip_set *set, u32 size, size_t dsize,
}
static int
-list_set_create(struct ip_set *set, struct nlattr *tb[], u32 flags)
+list_set_create(struct net *net, struct ip_set *set, struct nlattr *tb[],
+ u32 flags)
{
u32 size = IP_SET_LIST_DEFAULT_SIZE;
if (unlikely(!ip_set_optattr_netorder(tb, IPSET_ATTR_SIZE) ||
- !ip_set_optattr_netorder(tb, IPSET_ATTR_TIMEOUT)))
+ !ip_set_optattr_netorder(tb, IPSET_ATTR_TIMEOUT) ||
+ !ip_set_optattr_netorder(tb, IPSET_ATTR_CADT_FLAGS)))
return -IPSET_ERR_PROTOCOL;
if (tb[IPSET_ATTR_SIZE])
@@ -561,18 +629,14 @@ list_set_create(struct ip_set *set, struct nlattr *tb[], u32 flags)
if (size < IP_SET_LIST_MIN_SIZE)
size = IP_SET_LIST_MIN_SIZE;
+ set->variant = &set_variant;
+ set->dsize = ip_set_elem_len(set, tb, sizeof(struct set_elem));
+ if (!init_list_set(net, set, size))
+ return -ENOMEM;
if (tb[IPSET_ATTR_TIMEOUT]) {
- if (!init_list_set(set, size, sizeof(struct set_telem),
- ip_set_timeout_uget(tb[IPSET_ATTR_TIMEOUT])))
- return -ENOMEM;
-
- list_set_gc_init(set);
- } else {
- if (!init_list_set(set, size, sizeof(struct set_elem),
- IPSET_NO_TIMEOUT))
- return -ENOMEM;
+ set->timeout = ip_set_timeout_uget(tb[IPSET_ATTR_TIMEOUT]);
+ list_set_gc_init(set, list_set_gc);
}
- set->variant = &list_set;
return 0;
}
@@ -582,12 +646,13 @@ static struct ip_set_type list_set_type __read_mostly = {
.features = IPSET_TYPE_NAME | IPSET_DUMP_LAST,
.dimension = IPSET_DIM_ONE,
.family = NFPROTO_UNSPEC,
- .revision_min = REVISION_MIN,
- .revision_max = REVISION_MAX,
+ .revision_min = IPSET_TYPE_REV_MIN,
+ .revision_max = IPSET_TYPE_REV_MAX,
.create = list_set_create,
.create_policy = {
[IPSET_ATTR_SIZE] = { .type = NLA_U32 },
[IPSET_ATTR_TIMEOUT] = { .type = NLA_U32 },
+ [IPSET_ATTR_CADT_FLAGS] = { .type = NLA_U32 },
},
.adt_policy = {
[IPSET_ATTR_NAME] = { .type = NLA_STRING,
@@ -597,6 +662,9 @@ static struct ip_set_type list_set_type __read_mostly = {
[IPSET_ATTR_TIMEOUT] = { .type = NLA_U32 },
[IPSET_ATTR_LINENO] = { .type = NLA_U32 },
[IPSET_ATTR_CADT_FLAGS] = { .type = NLA_U32 },
+ [IPSET_ATTR_BYTES] = { .type = NLA_U64 },
+ [IPSET_ATTR_PACKETS] = { .type = NLA_U64 },
+ [IPSET_ATTR_COMMENT] = { .type = NLA_NUL_STRING },
},
.me = THIS_MODULE,
};
diff --git a/net/netfilter/ipset/pfxlen.c b/net/netfilter/ipset/pfxlen.c
index 4f29fa97044..04d15fdc99e 100644
--- a/net/netfilter/ipset/pfxlen.c
+++ b/net/netfilter/ipset/pfxlen.c
@@ -7,8 +7,8 @@
#define E(a, b, c, d) \
{.ip6 = { \
- __constant_htonl(a), __constant_htonl(b), \
- __constant_htonl(c), __constant_htonl(d), \
+ htonl(a), htonl(b), \
+ htonl(c), htonl(d), \
} }
/*
diff --git a/net/netfilter/ipvs/ip_vs_app.c b/net/netfilter/ipvs/ip_vs_app.c
index 9713e6e86d4..dfd7b65b3d2 100644
--- a/net/netfilter/ipvs/ip_vs_app.c
+++ b/net/netfilter/ipvs/ip_vs_app.c
@@ -58,6 +58,18 @@ static inline void ip_vs_app_put(struct ip_vs_app *app)
module_put(app->module);
}
+static void ip_vs_app_inc_destroy(struct ip_vs_app *inc)
+{
+ kfree(inc->timeout_table);
+ kfree(inc);
+}
+
+static void ip_vs_app_inc_rcu_free(struct rcu_head *head)
+{
+ struct ip_vs_app *inc = container_of(head, struct ip_vs_app, rcu_head);
+
+ ip_vs_app_inc_destroy(inc);
+}
/*
* Allocate/initialize app incarnation and register it in proto apps.
@@ -106,8 +118,7 @@ ip_vs_app_inc_new(struct net *net, struct ip_vs_app *app, __u16 proto,
return 0;
out:
- kfree(inc->timeout_table);
- kfree(inc);
+ ip_vs_app_inc_destroy(inc);
return ret;
}
@@ -131,8 +142,7 @@ ip_vs_app_inc_release(struct net *net, struct ip_vs_app *inc)
list_del(&inc->a_list);
- kfree(inc->timeout_table);
- kfree(inc);
+ call_rcu(&inc->rcu_head, ip_vs_app_inc_rcu_free);
}
@@ -144,9 +154,9 @@ int ip_vs_app_inc_get(struct ip_vs_app *inc)
{
int result;
- atomic_inc(&inc->usecnt);
- if (unlikely((result = ip_vs_app_get(inc->app)) != 1))
- atomic_dec(&inc->usecnt);
+ result = ip_vs_app_get(inc->app);
+ if (result)
+ atomic_inc(&inc->usecnt);
return result;
}
@@ -156,8 +166,8 @@ int ip_vs_app_inc_get(struct ip_vs_app *inc)
*/
void ip_vs_app_inc_put(struct ip_vs_app *inc)
{
- ip_vs_app_put(inc->app);
atomic_dec(&inc->usecnt);
+ ip_vs_app_put(inc->app);
}
@@ -218,6 +228,7 @@ out_unlock:
/*
* ip_vs_app unregistration routine
* We are sure there are no app incarnations attached to services
+ * Caller should use synchronize_rcu() or rcu_barrier()
*/
void unregister_ip_vs_app(struct net *net, struct ip_vs_app *app)
{
@@ -341,14 +352,14 @@ static inline void vs_seq_update(struct ip_vs_conn *cp, struct ip_vs_seq *vseq,
unsigned int flag, __u32 seq, int diff)
{
/* spinlock is to keep updating cp->flags atomic */
- spin_lock(&cp->lock);
+ spin_lock_bh(&cp->lock);
if (!(cp->flags & flag) || after(seq, vseq->init_seq)) {
vseq->previous_delta = vseq->delta;
vseq->delta += diff;
vseq->init_seq = seq;
cp->flags |= flag;
}
- spin_unlock(&cp->lock);
+ spin_unlock_bh(&cp->lock);
}
static inline int app_tcp_pkt_out(struct ip_vs_conn *cp, struct sk_buff *skb,
@@ -605,12 +616,12 @@ int __net_init ip_vs_app_net_init(struct net *net)
struct netns_ipvs *ipvs = net_ipvs(net);
INIT_LIST_HEAD(&ipvs->app_list);
- proc_net_fops_create(net, "ip_vs_app", 0, &ip_vs_app_fops);
+ proc_create("ip_vs_app", 0, net->proc_net, &ip_vs_app_fops);
return 0;
}
void __net_exit ip_vs_app_net_cleanup(struct net *net)
{
unregister_ip_vs_app(net, NULL /* all */);
- proc_net_remove(net, "ip_vs_app");
+ remove_proc_entry("ip_vs_app", net->proc_net);
}
diff --git a/net/netfilter/ipvs/ip_vs_conn.c b/net/netfilter/ipvs/ip_vs_conn.c
index 30e764ad021..610e19c0e13 100644
--- a/net/netfilter/ipvs/ip_vs_conn.c
+++ b/net/netfilter/ipvs/ip_vs_conn.c
@@ -79,51 +79,21 @@ static unsigned int ip_vs_conn_rnd __read_mostly;
struct ip_vs_aligned_lock
{
- rwlock_t l;
+ spinlock_t l;
} __attribute__((__aligned__(SMP_CACHE_BYTES)));
/* lock array for conn table */
static struct ip_vs_aligned_lock
__ip_vs_conntbl_lock_array[CT_LOCKARRAY_SIZE] __cacheline_aligned;
-static inline void ct_read_lock(unsigned int key)
-{
- read_lock(&__ip_vs_conntbl_lock_array[key&CT_LOCKARRAY_MASK].l);
-}
-
-static inline void ct_read_unlock(unsigned int key)
-{
- read_unlock(&__ip_vs_conntbl_lock_array[key&CT_LOCKARRAY_MASK].l);
-}
-
-static inline void ct_write_lock(unsigned int key)
-{
- write_lock(&__ip_vs_conntbl_lock_array[key&CT_LOCKARRAY_MASK].l);
-}
-
-static inline void ct_write_unlock(unsigned int key)
-{
- write_unlock(&__ip_vs_conntbl_lock_array[key&CT_LOCKARRAY_MASK].l);
-}
-
-static inline void ct_read_lock_bh(unsigned int key)
-{
- read_lock_bh(&__ip_vs_conntbl_lock_array[key&CT_LOCKARRAY_MASK].l);
-}
-
-static inline void ct_read_unlock_bh(unsigned int key)
-{
- read_unlock_bh(&__ip_vs_conntbl_lock_array[key&CT_LOCKARRAY_MASK].l);
-}
-
static inline void ct_write_lock_bh(unsigned int key)
{
- write_lock_bh(&__ip_vs_conntbl_lock_array[key&CT_LOCKARRAY_MASK].l);
+ spin_lock_bh(&__ip_vs_conntbl_lock_array[key&CT_LOCKARRAY_MASK].l);
}
static inline void ct_write_unlock_bh(unsigned int key)
{
- write_unlock_bh(&__ip_vs_conntbl_lock_array[key&CT_LOCKARRAY_MASK].l);
+ spin_unlock_bh(&__ip_vs_conntbl_lock_array[key&CT_LOCKARRAY_MASK].l);
}
@@ -197,13 +167,13 @@ static inline int ip_vs_conn_hash(struct ip_vs_conn *cp)
/* Hash by protocol, client address and port */
hash = ip_vs_conn_hashkey_conn(cp);
- ct_write_lock(hash);
+ ct_write_lock_bh(hash);
spin_lock(&cp->lock);
if (!(cp->flags & IP_VS_CONN_F_HASHED)) {
- hlist_add_head(&cp->c_list, &ip_vs_conn_tab[hash]);
cp->flags |= IP_VS_CONN_F_HASHED;
atomic_inc(&cp->refcnt);
+ hlist_add_head_rcu(&cp->c_list, &ip_vs_conn_tab[hash]);
ret = 1;
} else {
pr_err("%s(): request for already hashed, called from %pF\n",
@@ -212,7 +182,7 @@ static inline int ip_vs_conn_hash(struct ip_vs_conn *cp)
}
spin_unlock(&cp->lock);
- ct_write_unlock(hash);
+ ct_write_unlock_bh(hash);
return ret;
}
@@ -220,7 +190,7 @@ static inline int ip_vs_conn_hash(struct ip_vs_conn *cp)
/*
* UNhashes ip_vs_conn from ip_vs_conn_tab.
- * returns bool success.
+ * returns bool success. Caller should hold conn reference.
*/
static inline int ip_vs_conn_unhash(struct ip_vs_conn *cp)
{
@@ -230,11 +200,11 @@ static inline int ip_vs_conn_unhash(struct ip_vs_conn *cp)
/* unhash it and decrease its reference counter */
hash = ip_vs_conn_hashkey_conn(cp);
- ct_write_lock(hash);
+ ct_write_lock_bh(hash);
spin_lock(&cp->lock);
if (cp->flags & IP_VS_CONN_F_HASHED) {
- hlist_del(&cp->c_list);
+ hlist_del_rcu(&cp->c_list);
cp->flags &= ~IP_VS_CONN_F_HASHED;
atomic_dec(&cp->refcnt);
ret = 1;
@@ -242,7 +212,37 @@ static inline int ip_vs_conn_unhash(struct ip_vs_conn *cp)
ret = 0;
spin_unlock(&cp->lock);
- ct_write_unlock(hash);
+ ct_write_unlock_bh(hash);
+
+ return ret;
+}
+
+/* Try to unlink ip_vs_conn from ip_vs_conn_tab.
+ * returns bool success.
+ */
+static inline bool ip_vs_conn_unlink(struct ip_vs_conn *cp)
+{
+ unsigned int hash;
+ bool ret;
+
+ hash = ip_vs_conn_hashkey_conn(cp);
+
+ ct_write_lock_bh(hash);
+ spin_lock(&cp->lock);
+
+ if (cp->flags & IP_VS_CONN_F_HASHED) {
+ ret = false;
+ /* Decrease refcnt and unlink conn only if we are last user */
+ if (atomic_cmpxchg(&cp->refcnt, 1, 0) == 1) {
+ hlist_del_rcu(&cp->c_list);
+ cp->flags &= ~IP_VS_CONN_F_HASHED;
+ ret = true;
+ }
+ } else
+ ret = atomic_read(&cp->refcnt) ? false : true;
+
+ spin_unlock(&cp->lock);
+ ct_write_unlock_bh(hash);
return ret;
}
@@ -259,28 +259,28 @@ __ip_vs_conn_in_get(const struct ip_vs_conn_param *p)
{
unsigned int hash;
struct ip_vs_conn *cp;
- struct hlist_node *n;
hash = ip_vs_conn_hashkey_param(p, false);
- ct_read_lock(hash);
+ rcu_read_lock();
- hlist_for_each_entry(cp, n, &ip_vs_conn_tab[hash], c_list) {
- if (cp->af == p->af &&
- p->cport == cp->cport && p->vport == cp->vport &&
+ hlist_for_each_entry_rcu(cp, &ip_vs_conn_tab[hash], c_list) {
+ if (p->cport == cp->cport && p->vport == cp->vport &&
+ cp->af == p->af &&
ip_vs_addr_equal(p->af, p->caddr, &cp->caddr) &&
ip_vs_addr_equal(p->af, p->vaddr, &cp->vaddr) &&
((!p->cport) ^ (!(cp->flags & IP_VS_CONN_F_NO_CPORT))) &&
p->protocol == cp->protocol &&
ip_vs_conn_net_eq(cp, p->net)) {
+ if (!__ip_vs_conn_get(cp))
+ continue;
/* HIT */
- atomic_inc(&cp->refcnt);
- ct_read_unlock(hash);
+ rcu_read_unlock();
return cp;
}
}
- ct_read_unlock(hash);
+ rcu_read_unlock();
return NULL;
}
@@ -344,18 +344,19 @@ struct ip_vs_conn *ip_vs_ct_in_get(const struct ip_vs_conn_param *p)
{
unsigned int hash;
struct ip_vs_conn *cp;
- struct hlist_node *n;
hash = ip_vs_conn_hashkey_param(p, false);
- ct_read_lock(hash);
+ rcu_read_lock();
- hlist_for_each_entry(cp, n, &ip_vs_conn_tab[hash], c_list) {
- if (!ip_vs_conn_net_eq(cp, p->net))
- continue;
- if (p->pe_data && p->pe->ct_match) {
- if (p->pe == cp->pe && p->pe->ct_match(p, cp))
- goto out;
+ hlist_for_each_entry_rcu(cp, &ip_vs_conn_tab[hash], c_list) {
+ if (unlikely(p->pe_data && p->pe->ct_match)) {
+ if (!ip_vs_conn_net_eq(cp, p->net))
+ continue;
+ if (p->pe == cp->pe && p->pe->ct_match(p, cp)) {
+ if (__ip_vs_conn_get(cp))
+ goto out;
+ }
continue;
}
@@ -365,17 +366,18 @@ struct ip_vs_conn *ip_vs_ct_in_get(const struct ip_vs_conn_param *p)
* p->vaddr is a fwmark */
ip_vs_addr_equal(p->protocol == IPPROTO_IP ? AF_UNSPEC :
p->af, p->vaddr, &cp->vaddr) &&
- p->cport == cp->cport && p->vport == cp->vport &&
+ p->vport == cp->vport && p->cport == cp->cport &&
cp->flags & IP_VS_CONN_F_TEMPLATE &&
- p->protocol == cp->protocol)
- goto out;
+ p->protocol == cp->protocol &&
+ ip_vs_conn_net_eq(cp, p->net)) {
+ if (__ip_vs_conn_get(cp))
+ goto out;
+ }
}
cp = NULL;
out:
- if (cp)
- atomic_inc(&cp->refcnt);
- ct_read_unlock(hash);
+ rcu_read_unlock();
IP_VS_DBG_BUF(9, "template lookup/in %s %s:%d->%s:%d %s\n",
ip_vs_proto_name(p->protocol),
@@ -394,30 +396,30 @@ struct ip_vs_conn *ip_vs_conn_out_get(const struct ip_vs_conn_param *p)
{
unsigned int hash;
struct ip_vs_conn *cp, *ret=NULL;
- struct hlist_node *n;
/*
* Check for "full" addressed entries
*/
hash = ip_vs_conn_hashkey_param(p, true);
- ct_read_lock(hash);
+ rcu_read_lock();
- hlist_for_each_entry(cp, n, &ip_vs_conn_tab[hash], c_list) {
- if (cp->af == p->af &&
- p->vport == cp->cport && p->cport == cp->dport &&
+ hlist_for_each_entry_rcu(cp, &ip_vs_conn_tab[hash], c_list) {
+ if (p->vport == cp->cport && p->cport == cp->dport &&
+ cp->af == p->af &&
ip_vs_addr_equal(p->af, p->vaddr, &cp->caddr) &&
ip_vs_addr_equal(p->af, p->caddr, &cp->daddr) &&
p->protocol == cp->protocol &&
ip_vs_conn_net_eq(cp, p->net)) {
+ if (!__ip_vs_conn_get(cp))
+ continue;
/* HIT */
- atomic_inc(&cp->refcnt);
ret = cp;
break;
}
}
- ct_read_unlock(hash);
+ rcu_read_unlock();
IP_VS_DBG_BUF(9, "lookup/out %s %s:%d->%s:%d %s\n",
ip_vs_proto_name(p->protocol),
@@ -460,13 +462,13 @@ void ip_vs_conn_put(struct ip_vs_conn *cp)
void ip_vs_conn_fill_cport(struct ip_vs_conn *cp, __be16 cport)
{
if (ip_vs_conn_unhash(cp)) {
- spin_lock(&cp->lock);
+ spin_lock_bh(&cp->lock);
if (cp->flags & IP_VS_CONN_F_NO_CPORT) {
atomic_dec(&ip_vs_conn_no_cport_cnt);
cp->flags &= ~IP_VS_CONN_F_NO_CPORT;
cp->cport = cport;
}
- spin_unlock(&cp->lock);
+ spin_unlock_bh(&cp->lock);
/* hash on new dport */
ip_vs_conn_hash(cp);
@@ -552,7 +554,7 @@ ip_vs_bind_dest(struct ip_vs_conn *cp, struct ip_vs_dest *dest)
return;
/* Increase the refcnt counter of the dest */
- atomic_inc(&dest->refcnt);
+ ip_vs_dest_hold(dest);
conn_flags = atomic_read(&dest->conn_flags);
if (cp->protocol != IPPROTO_UDP)
@@ -609,20 +611,22 @@ ip_vs_bind_dest(struct ip_vs_conn *cp, struct ip_vs_dest *dest)
* Check if there is a destination for the connection, if so
* bind the connection to the destination.
*/
-struct ip_vs_dest *ip_vs_try_bind_dest(struct ip_vs_conn *cp)
+void ip_vs_try_bind_dest(struct ip_vs_conn *cp)
{
struct ip_vs_dest *dest;
+ rcu_read_lock();
dest = ip_vs_find_dest(ip_vs_conn_net(cp), cp->af, &cp->daddr,
cp->dport, &cp->vaddr, cp->vport,
cp->protocol, cp->fwmark, cp->flags);
if (dest) {
struct ip_vs_proto_data *pd;
- spin_lock(&cp->lock);
+ spin_lock_bh(&cp->lock);
if (cp->dest) {
- spin_unlock(&cp->lock);
- return dest;
+ spin_unlock_bh(&cp->lock);
+ rcu_read_unlock();
+ return;
}
/* Applications work depending on the forwarding method
@@ -631,7 +635,7 @@ struct ip_vs_dest *ip_vs_try_bind_dest(struct ip_vs_conn *cp)
ip_vs_unbind_app(cp);
ip_vs_bind_dest(cp, dest);
- spin_unlock(&cp->lock);
+ spin_unlock_bh(&cp->lock);
/* Update its packet transmitter */
cp->packet_xmit = NULL;
@@ -646,7 +650,7 @@ struct ip_vs_dest *ip_vs_try_bind_dest(struct ip_vs_conn *cp)
if (pd && atomic_read(&pd->appcnt))
ip_vs_bind_app(cp, pd->pp);
}
- return dest;
+ rcu_read_unlock();
}
@@ -698,12 +702,7 @@ static inline void ip_vs_unbind_dest(struct ip_vs_conn *cp)
dest->flags &= ~IP_VS_DEST_F_OVERLOAD;
}
- /*
- * Simply decrease the refcnt of the dest, because the
- * dest will be either in service's destination list
- * or in the trash.
- */
- atomic_dec(&dest->refcnt);
+ ip_vs_dest_put(dest);
}
static int expire_quiescent_template(struct netns_ipvs *ipvs,
@@ -760,51 +759,44 @@ int ip_vs_check_template(struct ip_vs_conn *ct)
* Simply decrease the refcnt of the template,
* don't restart its timer.
*/
- atomic_dec(&ct->refcnt);
+ __ip_vs_conn_put(ct);
return 0;
}
return 1;
}
+static void ip_vs_conn_rcu_free(struct rcu_head *head)
+{
+ struct ip_vs_conn *cp = container_of(head, struct ip_vs_conn,
+ rcu_head);
+
+ ip_vs_pe_put(cp->pe);
+ kfree(cp->pe_data);
+ kmem_cache_free(ip_vs_conn_cachep, cp);
+}
+
static void ip_vs_conn_expire(unsigned long data)
{
struct ip_vs_conn *cp = (struct ip_vs_conn *)data;
struct net *net = ip_vs_conn_net(cp);
struct netns_ipvs *ipvs = net_ipvs(net);
- cp->timeout = 60*HZ;
-
- /*
- * hey, I'm using it
- */
- atomic_inc(&cp->refcnt);
-
/*
* do I control anybody?
*/
if (atomic_read(&cp->n_control))
goto expire_later;
- /*
- * unhash it if it is hashed in the conn table
- */
- if (!ip_vs_conn_unhash(cp) && !(cp->flags & IP_VS_CONN_F_ONE_PACKET))
- goto expire_later;
-
- /*
- * refcnt==1 implies I'm the only one referrer
- */
- if (likely(atomic_read(&cp->refcnt) == 1)) {
+ /* Unlink conn if not referenced anymore */
+ if (likely(ip_vs_conn_unlink(cp))) {
/* delete the timer if it is activated by other users */
- if (timer_pending(&cp->timer))
- del_timer(&cp->timer);
+ del_timer(&cp->timer);
/* does anybody control me? */
if (cp->control)
ip_vs_control_del(cp);
if (cp->flags & IP_VS_CONN_F_NFCT) {
- ip_vs_conn_drop_conntrack(cp);
/* Do not access conntracks during subsys cleanup
* because nf_conntrack_find_get can not be used after
* conntrack cleanup for the net.
@@ -814,38 +806,41 @@ static void ip_vs_conn_expire(unsigned long data)
ip_vs_conn_drop_conntrack(cp);
}
- ip_vs_pe_put(cp->pe);
- kfree(cp->pe_data);
if (unlikely(cp->app != NULL))
ip_vs_unbind_app(cp);
ip_vs_unbind_dest(cp);
if (cp->flags & IP_VS_CONN_F_NO_CPORT)
atomic_dec(&ip_vs_conn_no_cport_cnt);
+ call_rcu(&cp->rcu_head, ip_vs_conn_rcu_free);
atomic_dec(&ipvs->conn_count);
-
- kmem_cache_free(ip_vs_conn_cachep, cp);
return;
}
- /* hash it back to the table */
- ip_vs_conn_hash(cp);
-
expire_later:
- IP_VS_DBG(7, "delayed: conn->refcnt-1=%d conn->n_control=%d\n",
- atomic_read(&cp->refcnt)-1,
+ IP_VS_DBG(7, "delayed: conn->refcnt=%d conn->n_control=%d\n",
+ atomic_read(&cp->refcnt),
atomic_read(&cp->n_control));
+ atomic_inc(&cp->refcnt);
+ cp->timeout = 60*HZ;
+
if (ipvs->sync_state & IP_VS_STATE_MASTER)
ip_vs_sync_conn(net, cp, sysctl_sync_threshold(ipvs));
ip_vs_conn_put(cp);
}
-
+/* Modify timer, so that it expires as soon as possible.
+ * Can be called without reference only if under RCU lock.
+ */
void ip_vs_conn_expire_now(struct ip_vs_conn *cp)
{
- if (del_timer(&cp->timer))
- mod_timer(&cp->timer, jiffies);
+ /* Using mod_timer_pending will ensure the timer is not
+ * modified after the final del_timer in ip_vs_conn_expire.
+ */
+ if (timer_pending(&cp->timer) &&
+ time_after(cp->timer.expires, jiffies))
+ mod_timer_pending(&cp->timer, jiffies);
}
@@ -862,7 +857,7 @@ ip_vs_conn_new(const struct ip_vs_conn_param *p,
struct ip_vs_proto_data *pd = ip_vs_proto_data_get(p->net,
p->protocol);
- cp = kmem_cache_zalloc(ip_vs_conn_cachep, GFP_ATOMIC);
+ cp = kmem_cache_alloc(ip_vs_conn_cachep, GFP_ATOMIC);
if (cp == NULL) {
IP_VS_ERR_RL("%s(): no memory\n", __func__);
return NULL;
@@ -873,13 +868,13 @@ ip_vs_conn_new(const struct ip_vs_conn_param *p,
ip_vs_conn_net_set(cp, p->net);
cp->af = p->af;
cp->protocol = p->protocol;
- ip_vs_addr_copy(p->af, &cp->caddr, p->caddr);
+ ip_vs_addr_set(p->af, &cp->caddr, p->caddr);
cp->cport = p->cport;
- ip_vs_addr_copy(p->af, &cp->vaddr, p->vaddr);
+ /* proto should only be IPPROTO_IP if p->vaddr is a fwmark */
+ ip_vs_addr_set(p->protocol == IPPROTO_IP ? AF_UNSPEC : p->af,
+ &cp->vaddr, p->vaddr);
cp->vport = p->vport;
- /* proto should only be IPPROTO_IP if d_addr is a fwmark */
- ip_vs_addr_copy(p->protocol == IPPROTO_IP ? AF_UNSPEC : p->af,
- &cp->daddr, daddr);
+ ip_vs_addr_set(p->af, &cp->daddr, daddr);
cp->dport = dport;
cp->flags = flags;
cp->fwmark = fwmark;
@@ -888,6 +883,10 @@ ip_vs_conn_new(const struct ip_vs_conn_param *p,
cp->pe = p->pe;
cp->pe_data = p->pe_data;
cp->pe_data_len = p->pe_data_len;
+ } else {
+ cp->pe = NULL;
+ cp->pe_data = NULL;
+ cp->pe_data_len = 0;
}
spin_lock_init(&cp->lock);
@@ -898,18 +897,28 @@ ip_vs_conn_new(const struct ip_vs_conn_param *p,
*/
atomic_set(&cp->refcnt, 1);
+ cp->control = NULL;
atomic_set(&cp->n_control, 0);
atomic_set(&cp->in_pkts, 0);
+ cp->packet_xmit = NULL;
+ cp->app = NULL;
+ cp->app_data = NULL;
+ /* reset struct ip_vs_seq */
+ cp->in_seq.delta = 0;
+ cp->out_seq.delta = 0;
+
atomic_inc(&ipvs->conn_count);
if (flags & IP_VS_CONN_F_NO_CPORT)
atomic_inc(&ip_vs_conn_no_cport_cnt);
/* Bind the connection with a destination server */
+ cp->dest = NULL;
ip_vs_bind_dest(cp, dest);
/* Set its state and timeout */
cp->state = 0;
+ cp->old_state = 0;
cp->timeout = 3*HZ;
cp->sync_endtime = jiffies & ~3UL;
@@ -954,27 +963,30 @@ static void *ip_vs_conn_array(struct seq_file *seq, loff_t pos)
int idx;
struct ip_vs_conn *cp;
struct ip_vs_iter_state *iter = seq->private;
- struct hlist_node *n;
for (idx = 0; idx < ip_vs_conn_tab_size; idx++) {
- ct_read_lock_bh(idx);
- hlist_for_each_entry(cp, n, &ip_vs_conn_tab[idx], c_list) {
+ hlist_for_each_entry_rcu(cp, &ip_vs_conn_tab[idx], c_list) {
+ /* __ip_vs_conn_get() is not needed by
+ * ip_vs_conn_seq_show and ip_vs_conn_sync_seq_show
+ */
if (pos-- == 0) {
iter->l = &ip_vs_conn_tab[idx];
return cp;
}
}
- ct_read_unlock_bh(idx);
+ cond_resched_rcu();
}
return NULL;
}
static void *ip_vs_conn_seq_start(struct seq_file *seq, loff_t *pos)
+ __acquires(RCU)
{
struct ip_vs_iter_state *iter = seq->private;
iter->l = NULL;
+ rcu_read_lock();
return *pos ? ip_vs_conn_array(seq, *pos - 1) :SEQ_START_TOKEN;
}
@@ -991,31 +1003,26 @@ static void *ip_vs_conn_seq_next(struct seq_file *seq, void *v, loff_t *pos)
return ip_vs_conn_array(seq, 0);
/* more on same hash chain? */
- if ((e = cp->c_list.next))
+ e = rcu_dereference(hlist_next_rcu(&cp->c_list));
+ if (e)
return hlist_entry(e, struct ip_vs_conn, c_list);
idx = l - ip_vs_conn_tab;
- ct_read_unlock_bh(idx);
-
while (++idx < ip_vs_conn_tab_size) {
- ct_read_lock_bh(idx);
- hlist_for_each_entry(cp, e, &ip_vs_conn_tab[idx], c_list) {
+ hlist_for_each_entry_rcu(cp, &ip_vs_conn_tab[idx], c_list) {
iter->l = &ip_vs_conn_tab[idx];
return cp;
}
- ct_read_unlock_bh(idx);
+ cond_resched_rcu();
}
iter->l = NULL;
return NULL;
}
static void ip_vs_conn_seq_stop(struct seq_file *seq, void *v)
+ __releases(RCU)
{
- struct ip_vs_iter_state *iter = seq->private;
- struct hlist_head *l = iter->l;
-
- if (l)
- ct_read_unlock_bh(l - ip_vs_conn_tab);
+ rcu_read_unlock();
}
static int ip_vs_conn_seq_show(struct seq_file *seq, void *v)
@@ -1194,21 +1201,16 @@ static inline int todrop_entry(struct ip_vs_conn *cp)
void ip_vs_random_dropentry(struct net *net)
{
int idx;
- struct ip_vs_conn *cp;
+ struct ip_vs_conn *cp, *cp_c;
+ rcu_read_lock();
/*
* Randomly scan 1/32 of the whole table every second
*/
for (idx = 0; idx < (ip_vs_conn_tab_size>>5); idx++) {
- unsigned int hash = net_random() & ip_vs_conn_tab_mask;
- struct hlist_node *n;
-
- /*
- * Lock is actually needed in this loop.
- */
- ct_write_lock_bh(hash);
+ unsigned int hash = prandom_u32() & ip_vs_conn_tab_mask;
- hlist_for_each_entry(cp, n, &ip_vs_conn_tab[hash], c_list) {
+ hlist_for_each_entry_rcu(cp, &ip_vs_conn_tab[hash], c_list) {
if (cp->flags & IP_VS_CONN_F_TEMPLATE)
/* connection template */
continue;
@@ -1228,6 +1230,18 @@ void ip_vs_random_dropentry(struct net *net)
default:
continue;
}
+ } else if (cp->protocol == IPPROTO_SCTP) {
+ switch (cp->state) {
+ case IP_VS_SCTP_S_INIT1:
+ case IP_VS_SCTP_S_INIT:
+ break;
+ case IP_VS_SCTP_S_ESTABLISHED:
+ if (todrop_entry(cp))
+ break;
+ continue;
+ default:
+ continue;
+ }
} else {
if (!todrop_entry(cp))
continue;
@@ -1235,13 +1249,17 @@ void ip_vs_random_dropentry(struct net *net)
IP_VS_DBG(4, "del connection\n");
ip_vs_conn_expire_now(cp);
- if (cp->control) {
+ cp_c = cp->control;
+ /* cp->control is valid only with reference to cp */
+ if (cp_c && __ip_vs_conn_get(cp)) {
IP_VS_DBG(4, "del conn template\n");
- ip_vs_conn_expire_now(cp->control);
+ ip_vs_conn_expire_now(cp_c);
+ __ip_vs_conn_put(cp);
}
}
- ct_write_unlock_bh(hash);
+ cond_resched_rcu();
}
+ rcu_read_unlock();
}
@@ -1251,30 +1269,29 @@ void ip_vs_random_dropentry(struct net *net)
static void ip_vs_conn_flush(struct net *net)
{
int idx;
- struct ip_vs_conn *cp;
+ struct ip_vs_conn *cp, *cp_c;
struct netns_ipvs *ipvs = net_ipvs(net);
flush_again:
+ rcu_read_lock();
for (idx = 0; idx < ip_vs_conn_tab_size; idx++) {
- struct hlist_node *n;
-
- /*
- * Lock is actually needed in this loop.
- */
- ct_write_lock_bh(idx);
- hlist_for_each_entry(cp, n, &ip_vs_conn_tab[idx], c_list) {
+ hlist_for_each_entry_rcu(cp, &ip_vs_conn_tab[idx], c_list) {
if (!ip_vs_conn_net_eq(cp, net))
continue;
IP_VS_DBG(4, "del connection\n");
ip_vs_conn_expire_now(cp);
- if (cp->control) {
+ cp_c = cp->control;
+ /* cp->control is valid only with reference to cp */
+ if (cp_c && __ip_vs_conn_get(cp)) {
IP_VS_DBG(4, "del conn template\n");
- ip_vs_conn_expire_now(cp->control);
+ ip_vs_conn_expire_now(cp_c);
+ __ip_vs_conn_put(cp);
}
}
- ct_write_unlock_bh(idx);
+ cond_resched_rcu();
}
+ rcu_read_unlock();
/* the counter may be not NULL, because maybe some conn entries
are run by slow timer handler or unhashed but still referred */
@@ -1292,8 +1309,8 @@ int __net_init ip_vs_conn_net_init(struct net *net)
atomic_set(&ipvs->conn_count, 0);
- proc_net_fops_create(net, "ip_vs_conn", 0, &ip_vs_conn_fops);
- proc_net_fops_create(net, "ip_vs_conn_sync", 0, &ip_vs_conn_sync_fops);
+ proc_create("ip_vs_conn", 0, net->proc_net, &ip_vs_conn_fops);
+ proc_create("ip_vs_conn_sync", 0, net->proc_net, &ip_vs_conn_sync_fops);
return 0;
}
@@ -1301,8 +1318,8 @@ void __net_exit ip_vs_conn_net_cleanup(struct net *net)
{
/* flush all the connection entries first */
ip_vs_conn_flush(net);
- proc_net_remove(net, "ip_vs_conn");
- proc_net_remove(net, "ip_vs_conn_sync");
+ remove_proc_entry("ip_vs_conn", net->proc_net);
+ remove_proc_entry("ip_vs_conn_sync", net->proc_net);
}
int __init ip_vs_conn_init(void)
@@ -1340,7 +1357,7 @@ int __init ip_vs_conn_init(void)
INIT_HLIST_HEAD(&ip_vs_conn_tab[idx]);
for (idx = 0; idx < CT_LOCKARRAY_SIZE; idx++) {
- rwlock_init(&__ip_vs_conntbl_lock_array[idx].l);
+ spin_lock_init(&__ip_vs_conntbl_lock_array[idx].l);
}
/* calculate the random value for connection hash */
@@ -1351,6 +1368,8 @@ int __init ip_vs_conn_init(void)
void ip_vs_conn_cleanup(void)
{
+ /* Wait all ip_vs_conn_rcu_free() callbacks to complete */
+ rcu_barrier();
/* Release the empty cache */
kmem_cache_destroy(ip_vs_conn_cachep);
vfree(ip_vs_conn_tab);
diff --git a/net/netfilter/ipvs/ip_vs_core.c b/net/netfilter/ipvs/ip_vs_core.c
index 47edf5a40a5..e6836755c45 100644
--- a/net/netfilter/ipvs/ip_vs_core.c
+++ b/net/netfilter/ipvs/ip_vs_core.c
@@ -69,10 +69,7 @@ EXPORT_SYMBOL(ip_vs_conn_put);
EXPORT_SYMBOL(ip_vs_get_debug_level);
#endif
-int ip_vs_net_id __read_mostly;
-#ifdef IP_VS_GENERIC_NETNS
-EXPORT_SYMBOL(ip_vs_net_id);
-#endif
+static int ip_vs_net_id __read_mostly;
/* netns cnt used for uniqueness */
static atomic_t ipvs_netns_cnt = ATOMIC_INIT(0);
@@ -100,7 +97,7 @@ const char *ip_vs_proto_name(unsigned int proto)
return "ICMPv6";
#endif
default:
- sprintf(buf, "IP_%d", proto);
+ sprintf(buf, "IP_%u", proto);
return buf;
}
}
@@ -119,6 +116,7 @@ ip_vs_in_stats(struct ip_vs_conn *cp, struct sk_buff *skb)
if (dest && (dest->flags & IP_VS_DEST_F_AVAILABLE)) {
struct ip_vs_cpu_stats *s;
+ struct ip_vs_service *svc;
s = this_cpu_ptr(dest->stats.cpustats);
s->ustats.inpkts++;
@@ -126,11 +124,14 @@ ip_vs_in_stats(struct ip_vs_conn *cp, struct sk_buff *skb)
s->ustats.inbytes += skb->len;
u64_stats_update_end(&s->syncp);
- s = this_cpu_ptr(dest->svc->stats.cpustats);
+ rcu_read_lock();
+ svc = rcu_dereference(dest->svc);
+ s = this_cpu_ptr(svc->stats.cpustats);
s->ustats.inpkts++;
u64_stats_update_begin(&s->syncp);
s->ustats.inbytes += skb->len;
u64_stats_update_end(&s->syncp);
+ rcu_read_unlock();
s = this_cpu_ptr(ipvs->tot_stats.cpustats);
s->ustats.inpkts++;
@@ -149,6 +150,7 @@ ip_vs_out_stats(struct ip_vs_conn *cp, struct sk_buff *skb)
if (dest && (dest->flags & IP_VS_DEST_F_AVAILABLE)) {
struct ip_vs_cpu_stats *s;
+ struct ip_vs_service *svc;
s = this_cpu_ptr(dest->stats.cpustats);
s->ustats.outpkts++;
@@ -156,11 +158,14 @@ ip_vs_out_stats(struct ip_vs_conn *cp, struct sk_buff *skb)
s->ustats.outbytes += skb->len;
u64_stats_update_end(&s->syncp);
- s = this_cpu_ptr(dest->svc->stats.cpustats);
+ rcu_read_lock();
+ svc = rcu_dereference(dest->svc);
+ s = this_cpu_ptr(svc->stats.cpustats);
s->ustats.outpkts++;
u64_stats_update_begin(&s->syncp);
s->ustats.outbytes += skb->len;
u64_stats_update_end(&s->syncp);
+ rcu_read_unlock();
s = this_cpu_ptr(ipvs->tot_stats.cpustats);
s->ustats.outpkts++;
@@ -206,7 +211,7 @@ ip_vs_conn_fill_param_persist(const struct ip_vs_service *svc,
{
ip_vs_conn_fill_param(svc->net, svc->af, protocol, caddr, cport, vaddr,
vport, p);
- p->pe = svc->pe;
+ p->pe = rcu_dereference(svc->pe);
if (p->pe && p->pe->fill_param)
return p->pe->fill_param(p, skb);
@@ -238,7 +243,8 @@ ip_vs_sched_persist(struct ip_vs_service *svc,
/* Mask saddr with the netmask to adjust template granularity */
#ifdef CONFIG_IP_VS_IPV6
if (svc->af == AF_INET6)
- ipv6_addr_prefix(&snet.in6, &iph->saddr.in6, svc->netmask);
+ ipv6_addr_prefix(&snet.in6, &iph->saddr.in6,
+ (__force __u32) svc->netmask);
else
#endif
snet.ip = iph->saddr.ip & svc->netmask;
@@ -299,12 +305,15 @@ ip_vs_sched_persist(struct ip_vs_service *svc,
/* Check if a template already exists */
ct = ip_vs_ct_in_get(&param);
if (!ct || !ip_vs_check_template(ct)) {
+ struct ip_vs_scheduler *sched;
+
/*
* No template found or the dest of the connection
* template is not available.
* return *ignored=0 i.e. ICMP and NF_DROP
*/
- dest = svc->scheduler->schedule(svc, skb);
+ sched = rcu_dereference(svc->scheduler);
+ dest = sched->schedule(svc, skb, iph);
if (!dest) {
IP_VS_DBG(1, "p-schedule: no dest found.\n");
kfree(param.pe_data);
@@ -394,6 +403,7 @@ ip_vs_schedule(struct ip_vs_service *svc, struct sk_buff *skb,
{
struct ip_vs_protocol *pp = pd->pp;
struct ip_vs_conn *cp = NULL;
+ struct ip_vs_scheduler *sched;
struct ip_vs_dest *dest;
__be16 _ports[2], *pptr;
unsigned int flags;
@@ -449,7 +459,8 @@ ip_vs_schedule(struct ip_vs_service *svc, struct sk_buff *skb,
return NULL;
}
- dest = svc->scheduler->schedule(svc, skb);
+ sched = rcu_dereference(svc->scheduler);
+ dest = sched->schedule(svc, skb, iph);
if (dest == NULL) {
IP_VS_DBG(1, "Schedule: no dest found.\n");
return NULL;
@@ -507,7 +518,6 @@ int ip_vs_leave(struct ip_vs_service *svc, struct sk_buff *skb,
pptr = frag_safe_skb_hp(skb, iph->len, sizeof(_ports), _ports, iph);
if (pptr == NULL) {
- ip_vs_service_put(svc);
return NF_DROP;
}
@@ -533,8 +543,6 @@ int ip_vs_leave(struct ip_vs_service *svc, struct sk_buff *skb,
IP_VS_CONN_F_ONE_PACKET : 0;
union nf_inet_addr daddr = { .all = { 0, 0, 0, 0 } };
- ip_vs_service_put(svc);
-
/* create a new connection entry */
IP_VS_DBG(6, "%s(): create a cache_bypass entry\n", __func__);
{
@@ -571,12 +579,8 @@ int ip_vs_leave(struct ip_vs_service *svc, struct sk_buff *skb,
* listed in the ipvs table), pass the packets, because it is
* not ipvs job to decide to drop the packets.
*/
- if ((svc->port == FTPPORT) && (pptr[1] != FTPPORT)) {
- ip_vs_service_put(svc);
+ if ((svc->port == FTPPORT) && (pptr[1] != FTPPORT))
return NF_ACCEPT;
- }
-
- ip_vs_service_put(svc);
/*
* Notify the client that the destination is unreachable, and
@@ -588,9 +592,9 @@ int ip_vs_leave(struct ip_vs_service *svc, struct sk_buff *skb,
#ifdef CONFIG_IP_VS_IPV6
if (svc->af == AF_INET6) {
if (!skb->dev) {
- struct net *net = dev_net(skb_dst(skb)->dev);
+ struct net *net_ = dev_net(skb_dst(skb)->dev);
- skb->dev = net->loopback_dev;
+ skb->dev = net_->loopback_dev;
}
icmpv6_send(skb, ICMPV6_DEST_UNREACH, ICMPV6_PORT_UNREACH, 0);
} else
@@ -643,8 +647,11 @@ static inline enum ip_defrag_users ip_vs_defrag_user(unsigned int hooknum)
static inline int ip_vs_gather_frags(struct sk_buff *skb, u_int32_t user)
{
- int err = ip_defrag(skb, user);
+ int err;
+ local_bh_disable();
+ err = ip_defrag(skb, user);
+ local_bh_enable();
if (!err)
ip_send_check(ip_hdr(skb));
@@ -1002,6 +1009,32 @@ static inline int is_tcp_reset(const struct sk_buff *skb, int nh_len)
return th->rst;
}
+static inline bool is_new_conn(const struct sk_buff *skb,
+ struct ip_vs_iphdr *iph)
+{
+ switch (iph->protocol) {
+ case IPPROTO_TCP: {
+ struct tcphdr _tcph, *th;
+
+ th = skb_header_pointer(skb, iph->len, sizeof(_tcph), &_tcph);
+ if (th == NULL)
+ return false;
+ return th->syn;
+ }
+ case IPPROTO_SCTP: {
+ sctp_chunkhdr_t *sch, schunk;
+
+ sch = skb_header_pointer(skb, iph->len + sizeof(sctp_sctphdr_t),
+ sizeof(schunk), &schunk);
+ if (sch == NULL)
+ return false;
+ return sch->type == SCTP_CID_INIT;
+ }
+ default:
+ return false;
+ }
+}
+
/* Handle response packets: rewrite addresses and send away...
*/
static unsigned int
@@ -1106,12 +1139,6 @@ ip_vs_out(unsigned int hooknum, struct sk_buff *skb, int af)
ip_vs_fill_iph_skb(af, skb, &iph);
#ifdef CONFIG_IP_VS_IPV6
if (af == AF_INET6) {
- if (!iph.fragoffs && skb_nfct_reasm(skb)) {
- struct sk_buff *reasm = skb_nfct_reasm(skb);
- /* Save fw mark for coming frags */
- reasm->ipvs_property = 1;
- reasm->mark = skb->mark;
- }
if (unlikely(iph.protocol == IPPROTO_ICMPV6)) {
int related;
int verdict = ip_vs_out_icmp_v6(skb, &related,
@@ -1164,9 +1191,8 @@ ip_vs_out(unsigned int hooknum, struct sk_buff *skb, int af)
sizeof(_ports), _ports, &iph);
if (pptr == NULL)
return NF_ACCEPT; /* Not for me */
- if (ip_vs_lookup_real_service(net, af, iph.protocol,
- &iph.saddr,
- pptr[0])) {
+ if (ip_vs_has_real_service(net, af, iph.protocol, &iph.saddr,
+ pptr[0])) {
/*
* Notify the real server: there is no
* existing entry if it is not RST
@@ -1181,9 +1207,6 @@ ip_vs_out(unsigned int hooknum, struct sk_buff *skb, int af)
iph.len)))) {
#ifdef CONFIG_IP_VS_IPV6
if (af == AF_INET6) {
- struct net *net =
- dev_net(skb_dst(skb)->dev);
-
if (!skb->dev)
skb->dev = net->loopback_dev;
icmpv6_send(skb,
@@ -1210,11 +1233,11 @@ ip_vs_out(unsigned int hooknum, struct sk_buff *skb, int af)
* Check if packet is reply for established ip_vs_conn.
*/
static unsigned int
-ip_vs_reply4(unsigned int hooknum, struct sk_buff *skb,
+ip_vs_reply4(const struct nf_hook_ops *ops, struct sk_buff *skb,
const struct net_device *in, const struct net_device *out,
int (*okfn)(struct sk_buff *))
{
- return ip_vs_out(hooknum, skb, AF_INET);
+ return ip_vs_out(ops->hooknum, skb, AF_INET);
}
/*
@@ -1222,17 +1245,11 @@ ip_vs_reply4(unsigned int hooknum, struct sk_buff *skb,
* Check if packet is reply for established ip_vs_conn.
*/
static unsigned int
-ip_vs_local_reply4(unsigned int hooknum, struct sk_buff *skb,
+ip_vs_local_reply4(const struct nf_hook_ops *ops, struct sk_buff *skb,
const struct net_device *in, const struct net_device *out,
int (*okfn)(struct sk_buff *))
{
- unsigned int verdict;
-
- /* Disable BH in LOCAL_OUT until all places are fixed */
- local_bh_disable();
- verdict = ip_vs_out(hooknum, skb, AF_INET);
- local_bh_enable();
- return verdict;
+ return ip_vs_out(ops->hooknum, skb, AF_INET);
}
#ifdef CONFIG_IP_VS_IPV6
@@ -1243,11 +1260,11 @@ ip_vs_local_reply4(unsigned int hooknum, struct sk_buff *skb,
* Check if packet is reply for established ip_vs_conn.
*/
static unsigned int
-ip_vs_reply6(unsigned int hooknum, struct sk_buff *skb,
+ip_vs_reply6(const struct nf_hook_ops *ops, struct sk_buff *skb,
const struct net_device *in, const struct net_device *out,
int (*okfn)(struct sk_buff *))
{
- return ip_vs_out(hooknum, skb, AF_INET6);
+ return ip_vs_out(ops->hooknum, skb, AF_INET6);
}
/*
@@ -1255,17 +1272,11 @@ ip_vs_reply6(unsigned int hooknum, struct sk_buff *skb,
* Check if packet is reply for established ip_vs_conn.
*/
static unsigned int
-ip_vs_local_reply6(unsigned int hooknum, struct sk_buff *skb,
+ip_vs_local_reply6(const struct nf_hook_ops *ops, struct sk_buff *skb,
const struct net_device *in, const struct net_device *out,
int (*okfn)(struct sk_buff *))
{
- unsigned int verdict;
-
- /* Disable BH in LOCAL_OUT until all places are fixed */
- local_bh_disable();
- verdict = ip_vs_out(hooknum, skb, AF_INET6);
- local_bh_enable();
- return verdict;
+ return ip_vs_out(ops->hooknum, skb, AF_INET6);
}
#endif
@@ -1381,32 +1392,37 @@ ip_vs_in_icmp(struct sk_buff *skb, int *related, unsigned int hooknum)
if (ipip) {
__be32 info = ic->un.gateway;
+ __u8 type = ic->type;
+ __u8 code = ic->code;
/* Update the MTU */
if (ic->type == ICMP_DEST_UNREACH &&
ic->code == ICMP_FRAG_NEEDED) {
struct ip_vs_dest *dest = cp->dest;
u32 mtu = ntohs(ic->un.frag.mtu);
+ __be16 frag_off = cih->frag_off;
/* Strip outer IP and ICMP, go to IPIP header */
- __skb_pull(skb, ihl + sizeof(_icmph));
+ if (pskb_pull(skb, ihl + sizeof(_icmph)) == NULL)
+ goto ignore_ipip;
offset2 -= ihl + sizeof(_icmph);
skb_reset_network_header(skb);
IP_VS_DBG(12, "ICMP for IPIP %pI4->%pI4: mtu=%u\n",
&ip_hdr(skb)->saddr, &ip_hdr(skb)->daddr, mtu);
- rcu_read_lock();
ipv4_update_pmtu(skb, dev_net(skb->dev),
mtu, 0, 0, 0, 0);
- rcu_read_unlock();
/* Client uses PMTUD? */
- if (!(cih->frag_off & htons(IP_DF)))
+ if (!(frag_off & htons(IP_DF)))
goto ignore_ipip;
/* Prefer the resulting PMTU */
if (dest) {
- spin_lock(&dest->dst_lock);
- if (dest->dst_cache)
- mtu = dst_mtu(dest->dst_cache);
- spin_unlock(&dest->dst_lock);
+ struct ip_vs_dest_dst *dest_dst;
+
+ rcu_read_lock();
+ dest_dst = rcu_dereference(dest->dest_dst);
+ if (dest_dst)
+ mtu = dst_mtu(dest_dst->dst_cache);
+ rcu_read_unlock();
}
if (mtu > 68 + sizeof(struct iphdr))
mtu -= sizeof(struct iphdr);
@@ -1415,12 +1431,13 @@ ip_vs_in_icmp(struct sk_buff *skb, int *related, unsigned int hooknum)
/* Strip outer IP, ICMP and IPIP, go to IP header of
* original request.
*/
- __skb_pull(skb, offset2);
+ if (pskb_pull(skb, offset2) == NULL)
+ goto ignore_ipip;
skb_reset_network_header(skb);
IP_VS_DBG(12, "Sending ICMP for %pI4->%pI4: t=%u, c=%u, i=%u\n",
&ip_hdr(skb)->saddr, &ip_hdr(skb)->daddr,
- ic->type, ic->code, ntohl(info));
- icmp_send(skb, ic->type, ic->code, info);
+ type, code, ntohl(info));
+ icmp_send(skb, type, code, info);
/* ICMP can be shorter but anyways, account it */
ip_vs_out_stats(cp, skb);
@@ -1432,7 +1449,8 @@ ignore_ipip:
/* do the statistics and put it back */
ip_vs_in_stats(cp, skb);
- if (IPPROTO_TCP == cih->protocol || IPPROTO_UDP == cih->protocol)
+ if (IPPROTO_TCP == cih->protocol || IPPROTO_UDP == cih->protocol ||
+ IPPROTO_SCTP == cih->protocol)
offset += 2 * sizeof(__u16);
verdict = ip_vs_icmp_xmit(skb, cp, pp, offset, hooknum, &ciph);
@@ -1577,7 +1595,8 @@ ip_vs_in(unsigned int hooknum, struct sk_buff *skb, int af)
}
/* ipvs enabled in this netns ? */
net = skb_net(skb);
- if (!net_ipvs(net)->enable)
+ ipvs = net_ipvs(net);
+ if (unlikely(sysctl_backup_only(ipvs) || !ipvs->enable))
return NF_ACCEPT;
ip_vs_fill_iph_skb(af, skb, &iph);
@@ -1594,12 +1613,6 @@ ip_vs_in(unsigned int hooknum, struct sk_buff *skb, int af)
#ifdef CONFIG_IP_VS_IPV6
if (af == AF_INET6) {
- if (!iph.fragoffs && skb_nfct_reasm(skb)) {
- struct sk_buff *reasm = skb_nfct_reasm(skb);
- /* Save fw mark for coming frags. */
- reasm->ipvs_property = 1;
- reasm->mark = skb->mark;
- }
if (unlikely(iph.protocol == IPPROTO_ICMPV6)) {
int related;
int verdict = ip_vs_in_icmp_v6(skb, &related, hooknum,
@@ -1627,6 +1640,15 @@ ip_vs_in(unsigned int hooknum, struct sk_buff *skb, int af)
* Check if the packet belongs to an existing connection entry
*/
cp = pp->conn_in_get(af, skb, &iph, 0);
+
+ if (unlikely(sysctl_expire_nodest_conn(ipvs)) && cp && cp->dest &&
+ unlikely(!atomic_read(&cp->dest->weight)) && !iph.fragoffs &&
+ is_new_conn(skb, &iph)) {
+ ip_vs_conn_expire_now(cp);
+ __ip_vs_conn_put(cp);
+ cp = NULL;
+ }
+
if (unlikely(!cp) && !iph.fragoffs) {
/* No (second) fragments need to enter here, as nf_defrag_ipv6
* replayed fragment zero will already have created the cp
@@ -1642,9 +1664,8 @@ ip_vs_in(unsigned int hooknum, struct sk_buff *skb, int af)
/* sorry, all this trouble for a no-hit :) */
IP_VS_DBG_PKT(12, af, pp, skb, 0,
"ip_vs_in: packet continues traversal as normal");
- if (iph.fragoffs && !skb_nfct_reasm(skb)) {
+ if (iph.fragoffs) {
/* Fragment that couldn't be mapped to a conn entry
- * and don't have any pointer to a reasm skb
* is missing module nf_defrag_ipv6
*/
IP_VS_DBG_RL("Unhandled frag, load nf_defrag_ipv6\n");
@@ -1654,7 +1675,6 @@ ip_vs_in(unsigned int hooknum, struct sk_buff *skb, int af)
}
IP_VS_DBG_PKT(11, af, pp, skb, 0, "Incoming packet");
- ipvs = net_ipvs(net);
/* Check the server status */
if (cp->dest && !(cp->dest->flags & IP_VS_DEST_F_AVAILABLE)) {
/* the destination server is not available */
@@ -1705,12 +1725,12 @@ ip_vs_in(unsigned int hooknum, struct sk_buff *skb, int af)
* Schedule and forward packets from remote clients
*/
static unsigned int
-ip_vs_remote_request4(unsigned int hooknum, struct sk_buff *skb,
+ip_vs_remote_request4(const struct nf_hook_ops *ops, struct sk_buff *skb,
const struct net_device *in,
const struct net_device *out,
int (*okfn)(struct sk_buff *))
{
- return ip_vs_in(hooknum, skb, AF_INET);
+ return ip_vs_in(ops->hooknum, skb, AF_INET);
}
/*
@@ -1718,64 +1738,26 @@ ip_vs_remote_request4(unsigned int hooknum, struct sk_buff *skb,
* Schedule and forward packets from local clients
*/
static unsigned int
-ip_vs_local_request4(unsigned int hooknum, struct sk_buff *skb,
+ip_vs_local_request4(const struct nf_hook_ops *ops, struct sk_buff *skb,
const struct net_device *in, const struct net_device *out,
int (*okfn)(struct sk_buff *))
{
- unsigned int verdict;
-
- /* Disable BH in LOCAL_OUT until all places are fixed */
- local_bh_disable();
- verdict = ip_vs_in(hooknum, skb, AF_INET);
- local_bh_enable();
- return verdict;
+ return ip_vs_in(ops->hooknum, skb, AF_INET);
}
#ifdef CONFIG_IP_VS_IPV6
/*
- * AF_INET6 fragment handling
- * Copy info from first fragment, to the rest of them.
- */
-static unsigned int
-ip_vs_preroute_frag6(unsigned int hooknum, struct sk_buff *skb,
- const struct net_device *in,
- const struct net_device *out,
- int (*okfn)(struct sk_buff *))
-{
- struct sk_buff *reasm = skb_nfct_reasm(skb);
- struct net *net;
-
- /* Skip if not a "replay" from nf_ct_frag6_output or first fragment.
- * ipvs_property is set when checking first fragment
- * in ip_vs_in() and ip_vs_out().
- */
- if (reasm)
- IP_VS_DBG(2, "Fragment recv prop:%d\n", reasm->ipvs_property);
- if (!reasm || !reasm->ipvs_property)
- return NF_ACCEPT;
-
- net = skb_net(skb);
- if (!net_ipvs(net)->enable)
- return NF_ACCEPT;
-
- /* Copy stored fw mark, saved in ip_vs_{in,out} */
- skb->mark = reasm->mark;
-
- return NF_ACCEPT;
-}
-
-/*
* AF_INET6 handler in NF_INET_LOCAL_IN chain
* Schedule and forward packets from remote clients
*/
static unsigned int
-ip_vs_remote_request6(unsigned int hooknum, struct sk_buff *skb,
+ip_vs_remote_request6(const struct nf_hook_ops *ops, struct sk_buff *skb,
const struct net_device *in,
const struct net_device *out,
int (*okfn)(struct sk_buff *))
{
- return ip_vs_in(hooknum, skb, AF_INET6);
+ return ip_vs_in(ops->hooknum, skb, AF_INET6);
}
/*
@@ -1783,17 +1765,11 @@ ip_vs_remote_request6(unsigned int hooknum, struct sk_buff *skb,
* Schedule and forward packets from local clients
*/
static unsigned int
-ip_vs_local_request6(unsigned int hooknum, struct sk_buff *skb,
+ip_vs_local_request6(const struct nf_hook_ops *ops, struct sk_buff *skb,
const struct net_device *in, const struct net_device *out,
int (*okfn)(struct sk_buff *))
{
- unsigned int verdict;
-
- /* Disable BH in LOCAL_OUT until all places are fixed */
- local_bh_disable();
- verdict = ip_vs_in(hooknum, skb, AF_INET6);
- local_bh_enable();
- return verdict;
+ return ip_vs_in(ops->hooknum, skb, AF_INET6);
}
#endif
@@ -1809,32 +1785,35 @@ ip_vs_local_request6(unsigned int hooknum, struct sk_buff *skb,
* and send them to ip_vs_in_icmp.
*/
static unsigned int
-ip_vs_forward_icmp(unsigned int hooknum, struct sk_buff *skb,
+ip_vs_forward_icmp(const struct nf_hook_ops *ops, struct sk_buff *skb,
const struct net_device *in, const struct net_device *out,
int (*okfn)(struct sk_buff *))
{
int r;
struct net *net;
+ struct netns_ipvs *ipvs;
if (ip_hdr(skb)->protocol != IPPROTO_ICMP)
return NF_ACCEPT;
/* ipvs enabled in this netns ? */
net = skb_net(skb);
- if (!net_ipvs(net)->enable)
+ ipvs = net_ipvs(net);
+ if (unlikely(sysctl_backup_only(ipvs) || !ipvs->enable))
return NF_ACCEPT;
- return ip_vs_in_icmp(skb, &r, hooknum);
+ return ip_vs_in_icmp(skb, &r, ops->hooknum);
}
#ifdef CONFIG_IP_VS_IPV6
static unsigned int
-ip_vs_forward_icmp_v6(unsigned int hooknum, struct sk_buff *skb,
+ip_vs_forward_icmp_v6(const struct nf_hook_ops *ops, struct sk_buff *skb,
const struct net_device *in, const struct net_device *out,
int (*okfn)(struct sk_buff *))
{
int r;
struct net *net;
+ struct netns_ipvs *ipvs;
struct ip_vs_iphdr iphdr;
ip_vs_fill_iph_skb(AF_INET6, skb, &iphdr);
@@ -1843,10 +1822,11 @@ ip_vs_forward_icmp_v6(unsigned int hooknum, struct sk_buff *skb,
/* ipvs enabled in this netns ? */
net = skb_net(skb);
- if (!net_ipvs(net)->enable)
+ ipvs = net_ipvs(net);
+ if (unlikely(sysctl_backup_only(ipvs) || !ipvs->enable))
return NF_ACCEPT;
- return ip_vs_in_icmp_v6(skb, &r, hooknum, &iphdr);
+ return ip_vs_in_icmp_v6(skb, &r, ops->hooknum, &iphdr);
}
#endif
@@ -1904,14 +1884,6 @@ static struct nf_hook_ops ip_vs_ops[] __read_mostly = {
.priority = 100,
},
#ifdef CONFIG_IP_VS_IPV6
- /* After mangle & nat fetch 2:nd fragment and following */
- {
- .hook = ip_vs_preroute_frag6,
- .owner = THIS_MODULE,
- .pf = NFPROTO_IPV6,
- .hooknum = NF_INET_PRE_ROUTING,
- .priority = NF_IP6_PRI_NAT_DST + 1,
- },
/* After packet filtering, change source only for VS/NAT */
{
.hook = ip_vs_reply6,
diff --git a/net/netfilter/ipvs/ip_vs_ctl.c b/net/netfilter/ipvs/ip_vs_ctl.c
index ec664cbb119..581a6584ed0 100644
--- a/net/netfilter/ipvs/ip_vs_ctl.c
+++ b/net/netfilter/ipvs/ip_vs_ctl.c
@@ -55,9 +55,6 @@
/* semaphore for IPVS sockopts. And, [gs]etsockopt may sleep. */
static DEFINE_MUTEX(__ip_vs_mutex);
-/* lock for service table */
-static DEFINE_RWLOCK(__ip_vs_svc_lock);
-
/* sysctl variables */
#ifdef CONFIG_IP_VS_DEBUG
@@ -71,7 +68,7 @@ int ip_vs_get_debug_level(void)
/* Protos */
-static void __ip_vs_del_service(struct ip_vs_service *svc);
+static void __ip_vs_del_service(struct ip_vs_service *svc, bool cleanup);
#ifdef CONFIG_IP_VS_IPV6
@@ -257,9 +254,9 @@ ip_vs_use_count_dec(void)
#define IP_VS_SVC_TAB_MASK (IP_VS_SVC_TAB_SIZE - 1)
/* the service table hashed by <protocol, addr, port> */
-static struct list_head ip_vs_svc_table[IP_VS_SVC_TAB_SIZE];
+static struct hlist_head ip_vs_svc_table[IP_VS_SVC_TAB_SIZE];
/* the service table hashed by fwmark */
-static struct list_head ip_vs_svc_fwm_table[IP_VS_SVC_TAB_SIZE];
+static struct hlist_head ip_vs_svc_fwm_table[IP_VS_SVC_TAB_SIZE];
/*
@@ -271,16 +268,18 @@ ip_vs_svc_hashkey(struct net *net, int af, unsigned int proto,
{
register unsigned int porth = ntohs(port);
__be32 addr_fold = addr->ip;
+ __u32 ahash;
#ifdef CONFIG_IP_VS_IPV6
if (af == AF_INET6)
addr_fold = addr->ip6[0]^addr->ip6[1]^
addr->ip6[2]^addr->ip6[3];
#endif
- addr_fold ^= ((size_t)net>>8);
+ ahash = ntohl(addr_fold);
+ ahash ^= ((size_t) net >> 8);
- return (proto^ntohl(addr_fold)^(porth>>IP_VS_SVC_TAB_BITS)^porth)
- & IP_VS_SVC_TAB_MASK;
+ return (proto ^ ahash ^ (porth >> IP_VS_SVC_TAB_BITS) ^ porth) &
+ IP_VS_SVC_TAB_MASK;
}
/*
@@ -312,13 +311,13 @@ static int ip_vs_svc_hash(struct ip_vs_service *svc)
*/
hash = ip_vs_svc_hashkey(svc->net, svc->af, svc->protocol,
&svc->addr, svc->port);
- list_add(&svc->s_list, &ip_vs_svc_table[hash]);
+ hlist_add_head_rcu(&svc->s_list, &ip_vs_svc_table[hash]);
} else {
/*
* Hash it by fwmark in svc_fwm_table
*/
hash = ip_vs_svc_fwm_hashkey(svc->net, svc->fwmark);
- list_add(&svc->f_list, &ip_vs_svc_fwm_table[hash]);
+ hlist_add_head_rcu(&svc->f_list, &ip_vs_svc_fwm_table[hash]);
}
svc->flags |= IP_VS_SVC_F_HASHED;
@@ -342,10 +341,10 @@ static int ip_vs_svc_unhash(struct ip_vs_service *svc)
if (svc->fwmark == 0) {
/* Remove it from the svc_table table */
- list_del(&svc->s_list);
+ hlist_del_rcu(&svc->s_list);
} else {
/* Remove it from the svc_fwm_table table */
- list_del(&svc->f_list);
+ hlist_del_rcu(&svc->f_list);
}
svc->flags &= ~IP_VS_SVC_F_HASHED;
@@ -367,7 +366,7 @@ __ip_vs_service_find(struct net *net, int af, __u16 protocol,
/* Check for "full" addressed entries */
hash = ip_vs_svc_hashkey(net, af, protocol, vaddr, vport);
- list_for_each_entry(svc, &ip_vs_svc_table[hash], s_list){
+ hlist_for_each_entry_rcu(svc, &ip_vs_svc_table[hash], s_list) {
if ((svc->af == af)
&& ip_vs_addr_equal(af, &svc->addr, vaddr)
&& (svc->port == vport)
@@ -394,7 +393,7 @@ __ip_vs_svc_fwm_find(struct net *net, int af, __u32 fwmark)
/* Check for fwmark addressed entries */
hash = ip_vs_svc_fwm_hashkey(net, fwmark);
- list_for_each_entry(svc, &ip_vs_svc_fwm_table[hash], f_list) {
+ hlist_for_each_entry_rcu(svc, &ip_vs_svc_fwm_table[hash], f_list) {
if (svc->fwmark == fwmark && svc->af == af
&& net_eq(svc->net, net)) {
/* HIT */
@@ -405,15 +404,14 @@ __ip_vs_svc_fwm_find(struct net *net, int af, __u32 fwmark)
return NULL;
}
+/* Find service, called under RCU lock */
struct ip_vs_service *
-ip_vs_service_get(struct net *net, int af, __u32 fwmark, __u16 protocol,
- const union nf_inet_addr *vaddr, __be16 vport)
+ip_vs_service_find(struct net *net, int af, __u32 fwmark, __u16 protocol,
+ const union nf_inet_addr *vaddr, __be16 vport)
{
struct ip_vs_service *svc;
struct netns_ipvs *ipvs = net_ipvs(net);
- read_lock(&__ip_vs_svc_lock);
-
/*
* Check the table hashed by fwmark first
*/
@@ -449,10 +447,6 @@ ip_vs_service_get(struct net *net, int af, __u32 fwmark, __u16 protocol,
}
out:
- if (svc)
- atomic_inc(&svc->usecnt);
- read_unlock(&__ip_vs_svc_lock);
-
IP_VS_DBG_BUF(9, "lookup service: fwm %u %s %s:%u %s\n",
fwmark, ip_vs_proto_name(protocol),
IP_VS_DBG_ADDR(af, vaddr), ntohs(vport),
@@ -466,22 +460,35 @@ static inline void
__ip_vs_bind_svc(struct ip_vs_dest *dest, struct ip_vs_service *svc)
{
atomic_inc(&svc->refcnt);
- dest->svc = svc;
+ rcu_assign_pointer(dest->svc, svc);
}
-static void
-__ip_vs_unbind_svc(struct ip_vs_dest *dest)
+static void ip_vs_service_free(struct ip_vs_service *svc)
{
- struct ip_vs_service *svc = dest->svc;
+ if (svc->stats.cpustats)
+ free_percpu(svc->stats.cpustats);
+ kfree(svc);
+}
- dest->svc = NULL;
+static void ip_vs_service_rcu_free(struct rcu_head *head)
+{
+ struct ip_vs_service *svc;
+
+ svc = container_of(head, struct ip_vs_service, rcu_head);
+ ip_vs_service_free(svc);
+}
+
+static void __ip_vs_svc_put(struct ip_vs_service *svc, bool do_delay)
+{
if (atomic_dec_and_test(&svc->refcnt)) {
- IP_VS_DBG_BUF(3, "Removing service %u/%s:%u usecnt=%d\n",
+ IP_VS_DBG_BUF(3, "Removing service %u/%s:%u\n",
svc->fwmark,
IP_VS_DBG_ADDR(svc->af, &svc->addr),
- ntohs(svc->port), atomic_read(&svc->usecnt));
- free_percpu(svc->stats.cpustats);
- kfree(svc);
+ ntohs(svc->port));
+ if (do_delay)
+ call_rcu(&svc->rcu_head, ip_vs_service_rcu_free);
+ else
+ ip_vs_service_free(svc);
}
}
@@ -506,17 +513,13 @@ static inline unsigned int ip_vs_rs_hashkey(int af,
& IP_VS_RTAB_MASK;
}
-/*
- * Hashes ip_vs_dest in rs_table by <proto,addr,port>.
- * should be called with locked tables.
- */
-static int ip_vs_rs_hash(struct netns_ipvs *ipvs, struct ip_vs_dest *dest)
+/* Hash ip_vs_dest in rs_table by <proto,addr,port>. */
+static void ip_vs_rs_hash(struct netns_ipvs *ipvs, struct ip_vs_dest *dest)
{
unsigned int hash;
- if (!list_empty(&dest->d_list)) {
- return 0;
- }
+ if (dest->in_rs_table)
+ return;
/*
* Hash by proto,addr,port,
@@ -524,64 +527,51 @@ static int ip_vs_rs_hash(struct netns_ipvs *ipvs, struct ip_vs_dest *dest)
*/
hash = ip_vs_rs_hashkey(dest->af, &dest->addr, dest->port);
- list_add(&dest->d_list, &ipvs->rs_table[hash]);
-
- return 1;
+ hlist_add_head_rcu(&dest->d_list, &ipvs->rs_table[hash]);
+ dest->in_rs_table = 1;
}
-/*
- * UNhashes ip_vs_dest from rs_table.
- * should be called with locked tables.
- */
-static int ip_vs_rs_unhash(struct ip_vs_dest *dest)
+/* Unhash ip_vs_dest from rs_table. */
+static void ip_vs_rs_unhash(struct ip_vs_dest *dest)
{
/*
* Remove it from the rs_table table.
*/
- if (!list_empty(&dest->d_list)) {
- list_del_init(&dest->d_list);
+ if (dest->in_rs_table) {
+ hlist_del_rcu(&dest->d_list);
+ dest->in_rs_table = 0;
}
-
- return 1;
}
-/*
- * Lookup real service by <proto,addr,port> in the real service table.
- */
-struct ip_vs_dest *
-ip_vs_lookup_real_service(struct net *net, int af, __u16 protocol,
- const union nf_inet_addr *daddr,
- __be16 dport)
+/* Check if real service by <proto,addr,port> is present */
+bool ip_vs_has_real_service(struct net *net, int af, __u16 protocol,
+ const union nf_inet_addr *daddr, __be16 dport)
{
struct netns_ipvs *ipvs = net_ipvs(net);
unsigned int hash;
struct ip_vs_dest *dest;
- /*
- * Check for "full" addressed entries
- * Return the first found entry
- */
+ /* Check for "full" addressed entries */
hash = ip_vs_rs_hashkey(af, daddr, dport);
- read_lock(&ipvs->rs_lock);
- list_for_each_entry(dest, &ipvs->rs_table[hash], d_list) {
- if ((dest->af == af)
- && ip_vs_addr_equal(af, &dest->addr, daddr)
- && (dest->port == dport)
- && ((dest->protocol == protocol) ||
- dest->vfwmark)) {
+ rcu_read_lock();
+ hlist_for_each_entry_rcu(dest, &ipvs->rs_table[hash], d_list) {
+ if (dest->port == dport &&
+ dest->af == af &&
+ ip_vs_addr_equal(af, &dest->addr, daddr) &&
+ (dest->protocol == protocol || dest->vfwmark)) {
/* HIT */
- read_unlock(&ipvs->rs_lock);
- return dest;
+ rcu_read_unlock();
+ return true;
}
}
- read_unlock(&ipvs->rs_lock);
+ rcu_read_unlock();
- return NULL;
+ return false;
}
-/*
- * Lookup destination by {addr,port} in the given service
+/* Lookup destination by {addr,port} in the given service
+ * Called under RCU lock.
*/
static struct ip_vs_dest *
ip_vs_lookup_dest(struct ip_vs_service *svc, const union nf_inet_addr *daddr,
@@ -592,7 +582,7 @@ ip_vs_lookup_dest(struct ip_vs_service *svc, const union nf_inet_addr *daddr,
/*
* Find the destination for the given service
*/
- list_for_each_entry(dest, &svc->destinations, n_list) {
+ list_for_each_entry_rcu(dest, &svc->destinations, n_list) {
if ((dest->af == svc->af)
&& ip_vs_addr_equal(svc->af, &dest->addr, daddr)
&& (dest->port == dport)) {
@@ -606,13 +596,11 @@ ip_vs_lookup_dest(struct ip_vs_service *svc, const union nf_inet_addr *daddr,
/*
* Find destination by {daddr,dport,vaddr,protocol}
- * Cretaed to be used in ip_vs_process_message() in
+ * Created to be used in ip_vs_process_message() in
* the backup synchronization daemon. It finds the
* destination to be bound to the received connection
* on the backup.
- *
- * ip_vs_lookup_real_service() looked promissing, but
- * seems not working as expected.
+ * Called under RCU lock, no refcnt is returned.
*/
struct ip_vs_dest *ip_vs_find_dest(struct net *net, int af,
const union nf_inet_addr *daddr,
@@ -625,7 +613,7 @@ struct ip_vs_dest *ip_vs_find_dest(struct net *net, int af,
struct ip_vs_service *svc;
__be16 port = dport;
- svc = ip_vs_service_get(net, af, fwmark, protocol, vaddr, vport);
+ svc = ip_vs_service_find(net, af, fwmark, protocol, vaddr, vport);
if (!svc)
return NULL;
if (fwmark && (flags & IP_VS_CONN_F_FWD_MASK) != IP_VS_CONN_F_MASQ)
@@ -633,12 +621,31 @@ struct ip_vs_dest *ip_vs_find_dest(struct net *net, int af,
dest = ip_vs_lookup_dest(svc, daddr, port);
if (!dest)
dest = ip_vs_lookup_dest(svc, daddr, port ^ dport);
- if (dest)
- atomic_inc(&dest->refcnt);
- ip_vs_service_put(svc);
return dest;
}
+void ip_vs_dest_dst_rcu_free(struct rcu_head *head)
+{
+ struct ip_vs_dest_dst *dest_dst = container_of(head,
+ struct ip_vs_dest_dst,
+ rcu_head);
+
+ dst_release(dest_dst->dst_cache);
+ kfree(dest_dst);
+}
+
+/* Release dest_dst and dst_cache for dest in user context */
+static void __ip_vs_dst_cache_reset(struct ip_vs_dest *dest)
+{
+ struct ip_vs_dest_dst *old;
+
+ old = rcu_dereference_protected(dest->dest_dst, 1);
+ if (old) {
+ RCU_INIT_POINTER(dest->dest_dst, NULL);
+ call_rcu(&old->rcu_head, ip_vs_dest_dst_rcu_free);
+ }
+}
+
/*
* Lookup dest by {svc,addr,port} in the destination trash.
* The destination trash is used to hold the destinations that are removed
@@ -653,13 +660,14 @@ static struct ip_vs_dest *
ip_vs_trash_get_dest(struct ip_vs_service *svc, const union nf_inet_addr *daddr,
__be16 dport)
{
- struct ip_vs_dest *dest, *nxt;
+ struct ip_vs_dest *dest;
struct netns_ipvs *ipvs = net_ipvs(svc->net);
/*
* Find the destination in trash
*/
- list_for_each_entry_safe(dest, nxt, &ipvs->dest_trash, n_list) {
+ spin_lock_bh(&ipvs->dest_trash_lock);
+ list_for_each_entry(dest, &ipvs->dest_trash, t_list) {
IP_VS_DBG_BUF(3, "Destination %u/%s:%u still in trash, "
"dest->refcnt=%d\n",
dest->vfwmark,
@@ -675,29 +683,29 @@ ip_vs_trash_get_dest(struct ip_vs_service *svc, const union nf_inet_addr *daddr,
(ip_vs_addr_equal(svc->af, &dest->vaddr, &svc->addr) &&
dest->vport == svc->port))) {
/* HIT */
- return dest;
- }
-
- /*
- * Try to purge the destination from trash if not referenced
- */
- if (atomic_read(&dest->refcnt) == 1) {
- IP_VS_DBG_BUF(3, "Removing destination %u/%s:%u "
- "from trash\n",
- dest->vfwmark,
- IP_VS_DBG_ADDR(svc->af, &dest->addr),
- ntohs(dest->port));
- list_del(&dest->n_list);
- ip_vs_dst_reset(dest);
- __ip_vs_unbind_svc(dest);
- free_percpu(dest->stats.cpustats);
- kfree(dest);
+ list_del(&dest->t_list);
+ ip_vs_dest_hold(dest);
+ goto out;
}
}
- return NULL;
+ dest = NULL;
+
+out:
+ spin_unlock_bh(&ipvs->dest_trash_lock);
+
+ return dest;
}
+static void ip_vs_dest_free(struct ip_vs_dest *dest)
+{
+ struct ip_vs_service *svc = rcu_dereference_protected(dest->svc, 1);
+
+ __ip_vs_dst_cache_reset(dest);
+ __ip_vs_svc_put(svc, false);
+ free_percpu(dest->stats.cpustats);
+ ip_vs_dest_put_and_free(dest);
+}
/*
* Clean up all the destinations in the trash
@@ -706,19 +714,18 @@ ip_vs_trash_get_dest(struct ip_vs_service *svc, const union nf_inet_addr *daddr,
* When the ip_vs_control_clearup is activated by ipvs module exit,
* the service tables must have been flushed and all the connections
* are expired, and the refcnt of each destination in the trash must
- * be 1, so we simply release them here.
+ * be 0, so we simply release them here.
*/
static void ip_vs_trash_cleanup(struct net *net)
{
struct ip_vs_dest *dest, *nxt;
struct netns_ipvs *ipvs = net_ipvs(net);
- list_for_each_entry_safe(dest, nxt, &ipvs->dest_trash, n_list) {
- list_del(&dest->n_list);
- ip_vs_dst_reset(dest);
- __ip_vs_unbind_svc(dest);
- free_percpu(dest->stats.cpustats);
- kfree(dest);
+ del_timer_sync(&ipvs->dest_trash_timer);
+ /* No need to use dest_trash_lock */
+ list_for_each_entry_safe(dest, nxt, &ipvs->dest_trash, t_list) {
+ list_del(&dest->t_list);
+ ip_vs_dest_free(dest);
}
}
@@ -768,6 +775,8 @@ __ip_vs_update_dest(struct ip_vs_service *svc, struct ip_vs_dest *dest,
struct ip_vs_dest_user_kern *udest, int add)
{
struct netns_ipvs *ipvs = net_ipvs(svc->net);
+ struct ip_vs_service *old_svc;
+ struct ip_vs_scheduler *sched;
int conn_flags;
/* set the weight and the flags */
@@ -783,20 +792,19 @@ __ip_vs_update_dest(struct ip_vs_service *svc, struct ip_vs_dest *dest,
* Put the real service in rs_table if not present.
* For now only for NAT!
*/
- write_lock_bh(&ipvs->rs_lock);
ip_vs_rs_hash(ipvs, dest);
- write_unlock_bh(&ipvs->rs_lock);
}
atomic_set(&dest->conn_flags, conn_flags);
/* bind the service */
- if (!dest->svc) {
+ old_svc = rcu_dereference_protected(dest->svc, 1);
+ if (!old_svc) {
__ip_vs_bind_svc(dest, svc);
} else {
- if (dest->svc != svc) {
- __ip_vs_unbind_svc(dest);
+ if (old_svc != svc) {
ip_vs_zero_stats(&dest->stats);
__ip_vs_bind_svc(dest, svc);
+ __ip_vs_svc_put(old_svc, true);
}
}
@@ -809,27 +817,20 @@ __ip_vs_update_dest(struct ip_vs_service *svc, struct ip_vs_dest *dest,
dest->l_threshold = udest->l_threshold;
spin_lock_bh(&dest->dst_lock);
- ip_vs_dst_reset(dest);
+ __ip_vs_dst_cache_reset(dest);
spin_unlock_bh(&dest->dst_lock);
- if (add)
- ip_vs_start_estimator(svc->net, &dest->stats);
-
- write_lock_bh(&__ip_vs_svc_lock);
-
- /* Wait until all other svc users go away */
- IP_VS_WAIT_WHILE(atomic_read(&svc->usecnt) > 0);
-
+ sched = rcu_dereference_protected(svc->scheduler, 1);
if (add) {
- list_add(&dest->n_list, &svc->destinations);
+ ip_vs_start_estimator(svc->net, &dest->stats);
+ list_add_rcu(&dest->n_list, &svc->destinations);
svc->num_dests++;
+ if (sched->add_dest)
+ sched->add_dest(svc, dest);
+ } else {
+ if (sched->upd_dest)
+ sched->upd_dest(svc, dest);
}
-
- /* call the update_service, because server weight may be changed */
- if (svc->scheduler->update_service)
- svc->scheduler->update_service(svc);
-
- write_unlock_bh(&__ip_vs_svc_lock);
}
@@ -841,7 +842,7 @@ ip_vs_new_dest(struct ip_vs_service *svc, struct ip_vs_dest_user_kern *udest,
struct ip_vs_dest **dest_p)
{
struct ip_vs_dest *dest;
- unsigned int atype;
+ unsigned int atype, i;
EnterFunction(2);
@@ -868,6 +869,12 @@ ip_vs_new_dest(struct ip_vs_service *svc, struct ip_vs_dest_user_kern *udest,
if (!dest->stats.cpustats)
goto err_alloc;
+ for_each_possible_cpu(i) {
+ struct ip_vs_cpu_stats *ip_vs_dest_stats;
+ ip_vs_dest_stats = per_cpu_ptr(dest->stats.cpustats, i);
+ u64_stats_init(&ip_vs_dest_stats->syncp);
+ }
+
dest->af = svc->af;
dest->protocol = svc->protocol;
dest->vaddr = svc->addr;
@@ -881,7 +888,7 @@ ip_vs_new_dest(struct ip_vs_service *svc, struct ip_vs_dest_user_kern *udest,
atomic_set(&dest->persistconns, 0);
atomic_set(&dest->refcnt, 1);
- INIT_LIST_HEAD(&dest->d_list);
+ INIT_HLIST_NODE(&dest->d_list);
spin_lock_init(&dest->dst_lock);
spin_lock_init(&dest->stats.lock);
__ip_vs_update_dest(svc, dest, udest, 1);
@@ -923,10 +930,10 @@ ip_vs_add_dest(struct ip_vs_service *svc, struct ip_vs_dest_user_kern *udest)
ip_vs_addr_copy(svc->af, &daddr, &udest->addr);
- /*
- * Check if the dest already exists in the list
- */
+ /* We use function that requires RCU lock */
+ rcu_read_lock();
dest = ip_vs_lookup_dest(svc, &daddr, dport);
+ rcu_read_unlock();
if (dest != NULL) {
IP_VS_DBG(1, "%s(): dest already exists\n", __func__);
@@ -948,11 +955,6 @@ ip_vs_add_dest(struct ip_vs_service *svc, struct ip_vs_dest_user_kern *udest)
IP_VS_DBG_ADDR(svc->af, &dest->vaddr),
ntohs(dest->vport));
- /*
- * Get the destination from the trash
- */
- list_del(&dest->n_list);
-
__ip_vs_update_dest(svc, dest, udest, 1);
ret = 0;
} else {
@@ -992,10 +994,10 @@ ip_vs_edit_dest(struct ip_vs_service *svc, struct ip_vs_dest_user_kern *udest)
ip_vs_addr_copy(svc->af, &daddr, &udest->addr);
- /*
- * Lookup the destination list
- */
+ /* We use function that requires RCU lock */
+ rcu_read_lock();
dest = ip_vs_lookup_dest(svc, &daddr, dport);
+ rcu_read_unlock();
if (dest == NULL) {
IP_VS_DBG(1, "%s(): dest doesn't exist\n", __func__);
@@ -1008,11 +1010,11 @@ ip_vs_edit_dest(struct ip_vs_service *svc, struct ip_vs_dest_user_kern *udest)
return 0;
}
-
/*
* Delete a destination (must be already unlinked from the service)
*/
-static void __ip_vs_del_dest(struct net *net, struct ip_vs_dest *dest)
+static void __ip_vs_del_dest(struct net *net, struct ip_vs_dest *dest,
+ bool cleanup)
{
struct netns_ipvs *ipvs = net_ipvs(net);
@@ -1021,38 +1023,20 @@ static void __ip_vs_del_dest(struct net *net, struct ip_vs_dest *dest)
/*
* Remove it from the d-linked list with the real services.
*/
- write_lock_bh(&ipvs->rs_lock);
ip_vs_rs_unhash(dest);
- write_unlock_bh(&ipvs->rs_lock);
- /*
- * Decrease the refcnt of the dest, and free the dest
- * if nobody refers to it (refcnt=0). Otherwise, throw
- * the destination into the trash.
- */
- if (atomic_dec_and_test(&dest->refcnt)) {
- IP_VS_DBG_BUF(3, "Removing destination %u/%s:%u\n",
- dest->vfwmark,
- IP_VS_DBG_ADDR(dest->af, &dest->addr),
- ntohs(dest->port));
- ip_vs_dst_reset(dest);
- /* simply decrease svc->refcnt here, let the caller check
- and release the service if nobody refers to it.
- Only user context can release destination and service,
- and only one user context can update virtual service at a
- time, so the operation here is OK */
- atomic_dec(&dest->svc->refcnt);
- free_percpu(dest->stats.cpustats);
- kfree(dest);
- } else {
- IP_VS_DBG_BUF(3, "Moving dest %s:%u into trash, "
- "dest->refcnt=%d\n",
- IP_VS_DBG_ADDR(dest->af, &dest->addr),
- ntohs(dest->port),
- atomic_read(&dest->refcnt));
- list_add(&dest->n_list, &ipvs->dest_trash);
- atomic_inc(&dest->refcnt);
- }
+ spin_lock_bh(&ipvs->dest_trash_lock);
+ IP_VS_DBG_BUF(3, "Moving dest %s:%u into trash, dest->refcnt=%d\n",
+ IP_VS_DBG_ADDR(dest->af, &dest->addr), ntohs(dest->port),
+ atomic_read(&dest->refcnt));
+ if (list_empty(&ipvs->dest_trash) && !cleanup)
+ mod_timer(&ipvs->dest_trash_timer,
+ jiffies + (IP_VS_DEST_TRASH_PERIOD >> 1));
+ /* dest lives in trash without reference */
+ list_add(&dest->t_list, &ipvs->dest_trash);
+ dest->idle_start = 0;
+ spin_unlock_bh(&ipvs->dest_trash_lock);
+ ip_vs_dest_put(dest);
}
@@ -1068,14 +1052,16 @@ static void __ip_vs_unlink_dest(struct ip_vs_service *svc,
/*
* Remove it from the d-linked destination list.
*/
- list_del(&dest->n_list);
+ list_del_rcu(&dest->n_list);
svc->num_dests--;
- /*
- * Call the update_service function of its scheduler
- */
- if (svcupd && svc->scheduler->update_service)
- svc->scheduler->update_service(svc);
+ if (svcupd) {
+ struct ip_vs_scheduler *sched;
+
+ sched = rcu_dereference_protected(svc->scheduler, 1);
+ if (sched->del_dest)
+ sched->del_dest(svc, dest);
+ }
}
@@ -1090,37 +1076,62 @@ ip_vs_del_dest(struct ip_vs_service *svc, struct ip_vs_dest_user_kern *udest)
EnterFunction(2);
+ /* We use function that requires RCU lock */
+ rcu_read_lock();
dest = ip_vs_lookup_dest(svc, &udest->addr, dport);
+ rcu_read_unlock();
if (dest == NULL) {
IP_VS_DBG(1, "%s(): destination not found!\n", __func__);
return -ENOENT;
}
- write_lock_bh(&__ip_vs_svc_lock);
-
- /*
- * Wait until all other svc users go away.
- */
- IP_VS_WAIT_WHILE(atomic_read(&svc->usecnt) > 0);
-
/*
* Unlink dest from the service
*/
__ip_vs_unlink_dest(svc, dest, 1);
- write_unlock_bh(&__ip_vs_svc_lock);
-
/*
* Delete the destination
*/
- __ip_vs_del_dest(svc->net, dest);
+ __ip_vs_del_dest(svc->net, dest, false);
LeaveFunction(2);
return 0;
}
+static void ip_vs_dest_trash_expire(unsigned long data)
+{
+ struct net *net = (struct net *) data;
+ struct netns_ipvs *ipvs = net_ipvs(net);
+ struct ip_vs_dest *dest, *next;
+ unsigned long now = jiffies;
+
+ spin_lock(&ipvs->dest_trash_lock);
+ list_for_each_entry_safe(dest, next, &ipvs->dest_trash, t_list) {
+ if (atomic_read(&dest->refcnt) > 0)
+ continue;
+ if (dest->idle_start) {
+ if (time_before(now, dest->idle_start +
+ IP_VS_DEST_TRASH_PERIOD))
+ continue;
+ } else {
+ dest->idle_start = max(1UL, now);
+ continue;
+ }
+ IP_VS_DBG_BUF(3, "Removing destination %u/%s:%u from trash\n",
+ dest->vfwmark,
+ IP_VS_DBG_ADDR(dest->af, &dest->addr),
+ ntohs(dest->port));
+ list_del(&dest->t_list);
+ ip_vs_dest_free(dest);
+ }
+ if (!list_empty(&ipvs->dest_trash))
+ mod_timer(&ipvs->dest_trash_timer,
+ jiffies + (IP_VS_DEST_TRASH_PERIOD >> 1));
+ spin_unlock(&ipvs->dest_trash_lock);
+}
/*
* Add a service into the service hash table
@@ -1129,7 +1140,7 @@ static int
ip_vs_add_service(struct net *net, struct ip_vs_service_user_kern *u,
struct ip_vs_service **svc_p)
{
- int ret = 0;
+ int ret = 0, i;
struct ip_vs_scheduler *sched = NULL;
struct ip_vs_pe *pe = NULL;
struct ip_vs_service *svc = NULL;
@@ -1157,9 +1168,13 @@ ip_vs_add_service(struct net *net, struct ip_vs_service_user_kern *u,
}
#ifdef CONFIG_IP_VS_IPV6
- if (u->af == AF_INET6 && (u->netmask < 1 || u->netmask > 128)) {
- ret = -EINVAL;
- goto out_err;
+ if (u->af == AF_INET6) {
+ __u32 plen = (__force __u32) u->netmask;
+
+ if (plen < 1 || plen > 128) {
+ ret = -EINVAL;
+ goto out_err;
+ }
}
#endif
@@ -1175,8 +1190,14 @@ ip_vs_add_service(struct net *net, struct ip_vs_service_user_kern *u,
goto out_err;
}
+ for_each_possible_cpu(i) {
+ struct ip_vs_cpu_stats *ip_vs_stats;
+ ip_vs_stats = per_cpu_ptr(svc->stats.cpustats, i);
+ u64_stats_init(&ip_vs_stats->syncp);
+ }
+
+
/* I'm the first user of the service */
- atomic_set(&svc->usecnt, 0);
atomic_set(&svc->refcnt, 0);
svc->af = u->af;
@@ -1190,7 +1211,7 @@ ip_vs_add_service(struct net *net, struct ip_vs_service_user_kern *u,
svc->net = net;
INIT_LIST_HEAD(&svc->destinations);
- rwlock_init(&svc->sched_lock);
+ spin_lock_init(&svc->sched_lock);
spin_lock_init(&svc->stats.lock);
/* Bind the scheduler */
@@ -1200,7 +1221,7 @@ ip_vs_add_service(struct net *net, struct ip_vs_service_user_kern *u,
sched = NULL;
/* Bind the ct retriever */
- ip_vs_bind_pe(svc, pe);
+ RCU_INIT_POINTER(svc->pe, pe);
pe = NULL;
/* Update the virtual service counters */
@@ -1216,9 +1237,7 @@ ip_vs_add_service(struct net *net, struct ip_vs_service_user_kern *u,
ipvs->num_services++;
/* Hash the service into the service table */
- write_lock_bh(&__ip_vs_svc_lock);
ip_vs_svc_hash(svc);
- write_unlock_bh(&__ip_vs_svc_lock);
*svc_p = svc;
/* Now there is a service - full throttle */
@@ -1228,15 +1247,8 @@ ip_vs_add_service(struct net *net, struct ip_vs_service_user_kern *u,
out_err:
if (svc != NULL) {
- ip_vs_unbind_scheduler(svc);
- if (svc->inc) {
- local_bh_disable();
- ip_vs_app_inc_put(svc->inc);
- local_bh_enable();
- }
- if (svc->stats.cpustats)
- free_percpu(svc->stats.cpustats);
- kfree(svc);
+ ip_vs_unbind_scheduler(svc, sched);
+ ip_vs_service_free(svc);
}
ip_vs_scheduler_put(sched);
ip_vs_pe_put(pe);
@@ -1280,18 +1292,27 @@ ip_vs_edit_service(struct ip_vs_service *svc, struct ip_vs_service_user_kern *u)
}
#ifdef CONFIG_IP_VS_IPV6
- if (u->af == AF_INET6 && (u->netmask < 1 || u->netmask > 128)) {
- ret = -EINVAL;
- goto out;
+ if (u->af == AF_INET6) {
+ __u32 plen = (__force __u32) u->netmask;
+
+ if (plen < 1 || plen > 128) {
+ ret = -EINVAL;
+ goto out;
+ }
}
#endif
- write_lock_bh(&__ip_vs_svc_lock);
-
- /*
- * Wait until all other svc users go away.
- */
- IP_VS_WAIT_WHILE(atomic_read(&svc->usecnt) > 0);
+ old_sched = rcu_dereference_protected(svc->scheduler, 1);
+ if (sched != old_sched) {
+ /* Bind the new scheduler */
+ ret = ip_vs_bind_scheduler(svc, sched);
+ if (ret) {
+ old_sched = sched;
+ goto out;
+ }
+ /* Unbind the old scheduler on success */
+ ip_vs_unbind_scheduler(svc, old_sched);
+ }
/*
* Set the flags and timeout value
@@ -1300,57 +1321,22 @@ ip_vs_edit_service(struct ip_vs_service *svc, struct ip_vs_service_user_kern *u)
svc->timeout = u->timeout * HZ;
svc->netmask = u->netmask;
- old_sched = svc->scheduler;
- if (sched != old_sched) {
- /*
- * Unbind the old scheduler
- */
- if ((ret = ip_vs_unbind_scheduler(svc))) {
- old_sched = sched;
- goto out_unlock;
- }
-
- /*
- * Bind the new scheduler
- */
- if ((ret = ip_vs_bind_scheduler(svc, sched))) {
- /*
- * If ip_vs_bind_scheduler fails, restore the old
- * scheduler.
- * The main reason of failure is out of memory.
- *
- * The question is if the old scheduler can be
- * restored all the time. TODO: if it cannot be
- * restored some time, we must delete the service,
- * otherwise the system may crash.
- */
- ip_vs_bind_scheduler(svc, old_sched);
- old_sched = sched;
- goto out_unlock;
- }
- }
-
- old_pe = svc->pe;
- if (pe != old_pe) {
- ip_vs_unbind_pe(svc);
- ip_vs_bind_pe(svc, pe);
- }
+ old_pe = rcu_dereference_protected(svc->pe, 1);
+ if (pe != old_pe)
+ rcu_assign_pointer(svc->pe, pe);
-out_unlock:
- write_unlock_bh(&__ip_vs_svc_lock);
out:
ip_vs_scheduler_put(old_sched);
ip_vs_pe_put(old_pe);
return ret;
}
-
/*
* Delete a service from the service list
* - The service must be unlinked, unlocked and not referenced!
* - We are called under _bh lock
*/
-static void __ip_vs_del_service(struct ip_vs_service *svc)
+static void __ip_vs_del_service(struct ip_vs_service *svc, bool cleanup)
{
struct ip_vs_dest *dest, *nxt;
struct ip_vs_scheduler *old_sched;
@@ -1366,27 +1352,20 @@ static void __ip_vs_del_service(struct ip_vs_service *svc)
ip_vs_stop_estimator(svc->net, &svc->stats);
/* Unbind scheduler */
- old_sched = svc->scheduler;
- ip_vs_unbind_scheduler(svc);
+ old_sched = rcu_dereference_protected(svc->scheduler, 1);
+ ip_vs_unbind_scheduler(svc, old_sched);
ip_vs_scheduler_put(old_sched);
- /* Unbind persistence engine */
- old_pe = svc->pe;
- ip_vs_unbind_pe(svc);
+ /* Unbind persistence engine, keep svc->pe */
+ old_pe = rcu_dereference_protected(svc->pe, 1);
ip_vs_pe_put(old_pe);
- /* Unbind app inc */
- if (svc->inc) {
- ip_vs_app_inc_put(svc->inc);
- svc->inc = NULL;
- }
-
/*
* Unlink the whole destination list
*/
list_for_each_entry_safe(dest, nxt, &svc->destinations, n_list) {
__ip_vs_unlink_dest(svc, dest, 0);
- __ip_vs_del_dest(svc->net, dest);
+ __ip_vs_del_dest(svc->net, dest, cleanup);
}
/*
@@ -1400,14 +1379,7 @@ static void __ip_vs_del_service(struct ip_vs_service *svc)
/*
* Free the service if nobody refers to it
*/
- if (atomic_read(&svc->refcnt) == 0) {
- IP_VS_DBG_BUF(3, "Removing service %u/%s:%u usecnt=%d\n",
- svc->fwmark,
- IP_VS_DBG_ADDR(svc->af, &svc->addr),
- ntohs(svc->port), atomic_read(&svc->usecnt));
- free_percpu(svc->stats.cpustats);
- kfree(svc);
- }
+ __ip_vs_svc_put(svc, true);
/* decrease the module use count */
ip_vs_use_count_dec();
@@ -1416,23 +1388,16 @@ static void __ip_vs_del_service(struct ip_vs_service *svc)
/*
* Unlink a service from list and try to delete it if its refcnt reached 0
*/
-static void ip_vs_unlink_service(struct ip_vs_service *svc)
+static void ip_vs_unlink_service(struct ip_vs_service *svc, bool cleanup)
{
+ /* Hold svc to avoid double release from dest_trash */
+ atomic_inc(&svc->refcnt);
/*
* Unhash it from the service table
*/
- write_lock_bh(&__ip_vs_svc_lock);
-
ip_vs_svc_unhash(svc);
- /*
- * Wait until all the svc users go away.
- */
- IP_VS_WAIT_WHILE(atomic_read(&svc->usecnt) > 0);
-
- __ip_vs_del_service(svc);
-
- write_unlock_bh(&__ip_vs_svc_lock);
+ __ip_vs_del_service(svc, cleanup);
}
/*
@@ -1442,7 +1407,7 @@ static int ip_vs_del_service(struct ip_vs_service *svc)
{
if (svc == NULL)
return -EEXIST;
- ip_vs_unlink_service(svc);
+ ip_vs_unlink_service(svc, false);
return 0;
}
@@ -1451,19 +1416,20 @@ static int ip_vs_del_service(struct ip_vs_service *svc)
/*
* Flush all the virtual services
*/
-static int ip_vs_flush(struct net *net)
+static int ip_vs_flush(struct net *net, bool cleanup)
{
int idx;
- struct ip_vs_service *svc, *nxt;
+ struct ip_vs_service *svc;
+ struct hlist_node *n;
/*
* Flush the service table hashed by <netns,protocol,addr,port>
*/
for(idx = 0; idx < IP_VS_SVC_TAB_SIZE; idx++) {
- list_for_each_entry_safe(svc, nxt, &ip_vs_svc_table[idx],
- s_list) {
+ hlist_for_each_entry_safe(svc, n, &ip_vs_svc_table[idx],
+ s_list) {
if (net_eq(svc->net, net))
- ip_vs_unlink_service(svc);
+ ip_vs_unlink_service(svc, cleanup);
}
}
@@ -1471,10 +1437,10 @@ static int ip_vs_flush(struct net *net)
* Flush the service table hashed by fwmark
*/
for(idx = 0; idx < IP_VS_SVC_TAB_SIZE; idx++) {
- list_for_each_entry_safe(svc, nxt,
- &ip_vs_svc_fwm_table[idx], f_list) {
+ hlist_for_each_entry_safe(svc, n, &ip_vs_svc_fwm_table[idx],
+ f_list) {
if (net_eq(svc->net, net))
- ip_vs_unlink_service(svc);
+ ip_vs_unlink_service(svc, cleanup);
}
}
@@ -1490,72 +1456,74 @@ void ip_vs_service_net_cleanup(struct net *net)
EnterFunction(2);
/* Check for "full" addressed entries */
mutex_lock(&__ip_vs_mutex);
- ip_vs_flush(net);
+ ip_vs_flush(net, true);
mutex_unlock(&__ip_vs_mutex);
LeaveFunction(2);
}
-/*
- * Release dst hold by dst_cache
- */
+
+/* Put all references for device (dst_cache) */
static inline void
-__ip_vs_dev_reset(struct ip_vs_dest *dest, struct net_device *dev)
+ip_vs_forget_dev(struct ip_vs_dest *dest, struct net_device *dev)
{
+ struct ip_vs_dest_dst *dest_dst;
+
spin_lock_bh(&dest->dst_lock);
- if (dest->dst_cache && dest->dst_cache->dev == dev) {
+ dest_dst = rcu_dereference_protected(dest->dest_dst, 1);
+ if (dest_dst && dest_dst->dst_cache->dev == dev) {
IP_VS_DBG_BUF(3, "Reset dev:%s dest %s:%u ,dest->refcnt=%d\n",
dev->name,
IP_VS_DBG_ADDR(dest->af, &dest->addr),
ntohs(dest->port),
atomic_read(&dest->refcnt));
- ip_vs_dst_reset(dest);
+ __ip_vs_dst_cache_reset(dest);
}
spin_unlock_bh(&dest->dst_lock);
}
-/*
- * Netdev event receiver
- * Currently only NETDEV_UNREGISTER is handled, i.e. if we hold a reference to
- * a device that is "unregister" it must be released.
+/* Netdev event receiver
+ * Currently only NETDEV_DOWN is handled to release refs to cached dsts
*/
static int ip_vs_dst_event(struct notifier_block *this, unsigned long event,
- void *ptr)
+ void *ptr)
{
- struct net_device *dev = ptr;
+ struct net_device *dev = netdev_notifier_info_to_dev(ptr);
struct net *net = dev_net(dev);
struct netns_ipvs *ipvs = net_ipvs(net);
struct ip_vs_service *svc;
struct ip_vs_dest *dest;
unsigned int idx;
- if (event != NETDEV_UNREGISTER || !ipvs)
+ if (event != NETDEV_DOWN || !ipvs)
return NOTIFY_DONE;
IP_VS_DBG(3, "%s() dev=%s\n", __func__, dev->name);
EnterFunction(2);
mutex_lock(&__ip_vs_mutex);
for (idx = 0; idx < IP_VS_SVC_TAB_SIZE; idx++) {
- list_for_each_entry(svc, &ip_vs_svc_table[idx], s_list) {
+ hlist_for_each_entry(svc, &ip_vs_svc_table[idx], s_list) {
if (net_eq(svc->net, net)) {
list_for_each_entry(dest, &svc->destinations,
n_list) {
- __ip_vs_dev_reset(dest, dev);
+ ip_vs_forget_dev(dest, dev);
}
}
}
- list_for_each_entry(svc, &ip_vs_svc_fwm_table[idx], f_list) {
+ hlist_for_each_entry(svc, &ip_vs_svc_fwm_table[idx], f_list) {
if (net_eq(svc->net, net)) {
list_for_each_entry(dest, &svc->destinations,
n_list) {
- __ip_vs_dev_reset(dest, dev);
+ ip_vs_forget_dev(dest, dev);
}
}
}
}
- list_for_each_entry(dest, &ipvs->dest_trash, n_list) {
- __ip_vs_dev_reset(dest, dev);
+ spin_lock_bh(&ipvs->dest_trash_lock);
+ list_for_each_entry(dest, &ipvs->dest_trash, t_list) {
+ ip_vs_forget_dev(dest, dev);
}
+ spin_unlock_bh(&ipvs->dest_trash_lock);
mutex_unlock(&__ip_vs_mutex);
LeaveFunction(2);
return NOTIFY_DONE;
@@ -1568,12 +1536,10 @@ static int ip_vs_zero_service(struct ip_vs_service *svc)
{
struct ip_vs_dest *dest;
- write_lock_bh(&__ip_vs_svc_lock);
list_for_each_entry(dest, &svc->destinations, n_list) {
ip_vs_zero_stats(&dest->stats);
}
ip_vs_zero_stats(&svc->stats);
- write_unlock_bh(&__ip_vs_svc_lock);
return 0;
}
@@ -1583,14 +1549,14 @@ static int ip_vs_zero_all(struct net *net)
struct ip_vs_service *svc;
for(idx = 0; idx < IP_VS_SVC_TAB_SIZE; idx++) {
- list_for_each_entry(svc, &ip_vs_svc_table[idx], s_list) {
+ hlist_for_each_entry(svc, &ip_vs_svc_table[idx], s_list) {
if (net_eq(svc->net, net))
ip_vs_zero_service(svc);
}
}
for(idx = 0; idx < IP_VS_SVC_TAB_SIZE; idx++) {
- list_for_each_entry(svc, &ip_vs_svc_fwm_table[idx], f_list) {
+ hlist_for_each_entry(svc, &ip_vs_svc_fwm_table[idx], f_list) {
if (net_eq(svc->net, net))
ip_vs_zero_service(svc);
}
@@ -1606,7 +1572,7 @@ static int zero;
static int three = 3;
static int
-proc_do_defense_mode(ctl_table *table, int write,
+proc_do_defense_mode(struct ctl_table *table, int write,
void __user *buffer, size_t *lenp, loff_t *ppos)
{
struct net *net = current->nsproxy->net_ns;
@@ -1627,7 +1593,7 @@ proc_do_defense_mode(ctl_table *table, int write,
}
static int
-proc_do_sync_threshold(ctl_table *table, int write,
+proc_do_sync_threshold(struct ctl_table *table, int write,
void __user *buffer, size_t *lenp, loff_t *ppos)
{
int *valp = table->data;
@@ -1647,7 +1613,7 @@ proc_do_sync_threshold(ctl_table *table, int write,
}
static int
-proc_do_sync_mode(ctl_table *table, int write,
+proc_do_sync_mode(struct ctl_table *table, int write,
void __user *buffer, size_t *lenp, loff_t *ppos)
{
int *valp = table->data;
@@ -1665,7 +1631,7 @@ proc_do_sync_mode(ctl_table *table, int write,
}
static int
-proc_do_sync_ports(ctl_table *table, int write,
+proc_do_sync_ports(struct ctl_table *table, int write,
void __user *buffer, size_t *lenp, loff_t *ppos)
{
int *valp = table->data;
@@ -1746,12 +1712,18 @@ static struct ctl_table vs_vars[] = {
.proc_handler = &proc_do_sync_ports,
},
{
- .procname = "sync_qlen_max",
+ .procname = "sync_persist_mode",
.maxlen = sizeof(int),
.mode = 0644,
.proc_handler = proc_dointvec,
},
{
+ .procname = "sync_qlen_max",
+ .maxlen = sizeof(unsigned long),
+ .mode = 0644,
+ .proc_handler = proc_doulongvec_minmax,
+ },
+ {
.procname = "sync_sock_size",
.maxlen = sizeof(int),
.mode = 0644,
@@ -1770,6 +1742,18 @@ static struct ctl_table vs_vars[] = {
.proc_handler = proc_dointvec,
},
{
+ .procname = "sloppy_tcp",
+ .maxlen = sizeof(int),
+ .mode = 0644,
+ .proc_handler = proc_dointvec,
+ },
+ {
+ .procname = "sloppy_sctp",
+ .maxlen = sizeof(int),
+ .mode = 0644,
+ .proc_handler = proc_dointvec,
+ },
+ {
.procname = "expire_quiescent_template",
.maxlen = sizeof(int),
.mode = 0644,
@@ -1808,6 +1792,12 @@ static struct ctl_table vs_vars[] = {
.mode = 0644,
.proc_handler = proc_dointvec,
},
+ {
+ .procname = "backup_only",
+ .maxlen = sizeof(int),
+ .mode = 0644,
+ .proc_handler = proc_dointvec,
+ },
#ifdef CONFIG_IP_VS_DEBUG
{
.procname = "debug_level",
@@ -1912,7 +1902,7 @@ static struct ctl_table vs_vars[] = {
struct ip_vs_iter {
struct seq_net_private p; /* Do not move this, netns depends upon it*/
- struct list_head *table;
+ struct hlist_head *table;
int bucket;
};
@@ -1945,7 +1935,7 @@ static struct ip_vs_service *ip_vs_info_array(struct seq_file *seq, loff_t pos)
/* look in hash by protocol */
for (idx = 0; idx < IP_VS_SVC_TAB_SIZE; idx++) {
- list_for_each_entry(svc, &ip_vs_svc_table[idx], s_list) {
+ hlist_for_each_entry_rcu(svc, &ip_vs_svc_table[idx], s_list) {
if (net_eq(svc->net, net) && pos-- == 0) {
iter->table = ip_vs_svc_table;
iter->bucket = idx;
@@ -1956,7 +1946,8 @@ static struct ip_vs_service *ip_vs_info_array(struct seq_file *seq, loff_t pos)
/* keep looking in fwmark */
for (idx = 0; idx < IP_VS_SVC_TAB_SIZE; idx++) {
- list_for_each_entry(svc, &ip_vs_svc_fwm_table[idx], f_list) {
+ hlist_for_each_entry_rcu(svc, &ip_vs_svc_fwm_table[idx],
+ f_list) {
if (net_eq(svc->net, net) && pos-- == 0) {
iter->table = ip_vs_svc_fwm_table;
iter->bucket = idx;
@@ -1969,17 +1960,16 @@ static struct ip_vs_service *ip_vs_info_array(struct seq_file *seq, loff_t pos)
}
static void *ip_vs_info_seq_start(struct seq_file *seq, loff_t *pos)
-__acquires(__ip_vs_svc_lock)
+ __acquires(RCU)
{
-
- read_lock_bh(&__ip_vs_svc_lock);
+ rcu_read_lock();
return *pos ? ip_vs_info_array(seq, *pos - 1) : SEQ_START_TOKEN;
}
static void *ip_vs_info_seq_next(struct seq_file *seq, void *v, loff_t *pos)
{
- struct list_head *e;
+ struct hlist_node *e;
struct ip_vs_iter *iter;
struct ip_vs_service *svc;
@@ -1992,13 +1982,14 @@ static void *ip_vs_info_seq_next(struct seq_file *seq, void *v, loff_t *pos)
if (iter->table == ip_vs_svc_table) {
/* next service in table hashed by protocol */
- if ((e = svc->s_list.next) != &ip_vs_svc_table[iter->bucket])
- return list_entry(e, struct ip_vs_service, s_list);
-
+ e = rcu_dereference(hlist_next_rcu(&svc->s_list));
+ if (e)
+ return hlist_entry(e, struct ip_vs_service, s_list);
while (++iter->bucket < IP_VS_SVC_TAB_SIZE) {
- list_for_each_entry(svc,&ip_vs_svc_table[iter->bucket],
- s_list) {
+ hlist_for_each_entry_rcu(svc,
+ &ip_vs_svc_table[iter->bucket],
+ s_list) {
return svc;
}
}
@@ -2009,13 +2000,15 @@ static void *ip_vs_info_seq_next(struct seq_file *seq, void *v, loff_t *pos)
}
/* next service in hashed by fwmark */
- if ((e = svc->f_list.next) != &ip_vs_svc_fwm_table[iter->bucket])
- return list_entry(e, struct ip_vs_service, f_list);
+ e = rcu_dereference(hlist_next_rcu(&svc->f_list));
+ if (e)
+ return hlist_entry(e, struct ip_vs_service, f_list);
scan_fwmark:
while (++iter->bucket < IP_VS_SVC_TAB_SIZE) {
- list_for_each_entry(svc, &ip_vs_svc_fwm_table[iter->bucket],
- f_list)
+ hlist_for_each_entry_rcu(svc,
+ &ip_vs_svc_fwm_table[iter->bucket],
+ f_list)
return svc;
}
@@ -2023,9 +2016,9 @@ static void *ip_vs_info_seq_next(struct seq_file *seq, void *v, loff_t *pos)
}
static void ip_vs_info_seq_stop(struct seq_file *seq, void *v)
-__releases(__ip_vs_svc_lock)
+ __releases(RCU)
{
- read_unlock_bh(&__ip_vs_svc_lock);
+ rcu_read_unlock();
}
@@ -2043,6 +2036,7 @@ static int ip_vs_info_seq_show(struct seq_file *seq, void *v)
const struct ip_vs_service *svc = v;
const struct ip_vs_iter *iter = seq->private;
const struct ip_vs_dest *dest;
+ struct ip_vs_scheduler *sched = rcu_dereference(svc->scheduler);
if (iter->table == ip_vs_svc_table) {
#ifdef CONFIG_IP_VS_IPV6
@@ -2051,18 +2045,18 @@ static int ip_vs_info_seq_show(struct seq_file *seq, void *v)
ip_vs_proto_name(svc->protocol),
&svc->addr.in6,
ntohs(svc->port),
- svc->scheduler->name);
+ sched->name);
else
#endif
seq_printf(seq, "%s %08X:%04X %s %s ",
ip_vs_proto_name(svc->protocol),
ntohl(svc->addr.ip),
ntohs(svc->port),
- svc->scheduler->name,
+ sched->name,
(svc->flags & IP_VS_SVC_F_ONEPACKET)?"ops ":"");
} else {
seq_printf(seq, "FWM %08X %s %s",
- svc->fwmark, svc->scheduler->name,
+ svc->fwmark, sched->name,
(svc->flags & IP_VS_SVC_F_ONEPACKET)?"ops ":"");
}
@@ -2073,7 +2067,7 @@ static int ip_vs_info_seq_show(struct seq_file *seq, void *v)
else
seq_putc(seq, '\n');
- list_for_each_entry(dest, &svc->destinations, n_list) {
+ list_for_each_entry_rcu(dest, &svc->destinations, n_list) {
#ifdef CONFIG_IP_VS_IPV6
if (dest->af == AF_INET6)
seq_printf(seq,
@@ -2167,7 +2161,7 @@ static int ip_vs_stats_percpu_show(struct seq_file *seq, void *v)
{
struct net *net = seq_file_single_net(seq);
struct ip_vs_stats *tot_stats = &net_ipvs(net)->tot_stats;
- struct ip_vs_cpu_stats *cpustats = tot_stats->cpustats;
+ struct ip_vs_cpu_stats __percpu *cpustats = tot_stats->cpustats;
struct ip_vs_stats_user rates;
int i;
@@ -2183,10 +2177,10 @@ static int ip_vs_stats_percpu_show(struct seq_file *seq, void *v)
__u64 inbytes, outbytes;
do {
- start = u64_stats_fetch_begin_bh(&u->syncp);
+ start = u64_stats_fetch_begin_irq(&u->syncp);
inbytes = u->ustats.inbytes;
outbytes = u->ustats.outbytes;
- } while (u64_stats_fetch_retry_bh(&u->syncp, start));
+ } while (u64_stats_fetch_retry_irq(&u->syncp, start));
seq_printf(seq, "%3X %8X %8X %8X %16LX %16LX\n",
i, u->ustats.conns, u->ustats.inpkts,
@@ -2383,7 +2377,7 @@ do_ip_vs_set_ctl(struct sock *sk, int cmd, void __user *user, unsigned int len)
if (cmd == IP_VS_SO_SET_FLUSH) {
/* Flush the virtual service */
- ret = ip_vs_flush(net);
+ ret = ip_vs_flush(net, false);
goto out_unlock;
} else if (cmd == IP_VS_SO_SET_TIMEOUT) {
/* Set timeout values for (tcp tcpfin udp) */
@@ -2418,11 +2412,13 @@ do_ip_vs_set_ctl(struct sock *sk, int cmd, void __user *user, unsigned int len)
}
/* Lookup the exact service by <protocol, addr, port> or fwmark */
+ rcu_read_lock();
if (usvc.fwmark == 0)
svc = __ip_vs_service_find(net, usvc.af, usvc.protocol,
&usvc.addr, usvc.port);
else
svc = __ip_vs_svc_fwm_find(net, usvc.af, usvc.fwmark);
+ rcu_read_unlock();
if (cmd != IP_VS_SO_SET_ADD
&& (svc == NULL || svc->protocol != usvc.protocol)) {
@@ -2474,11 +2470,14 @@ do_ip_vs_set_ctl(struct sock *sk, int cmd, void __user *user, unsigned int len)
static void
ip_vs_copy_service(struct ip_vs_service_entry *dst, struct ip_vs_service *src)
{
+ struct ip_vs_scheduler *sched;
+
+ sched = rcu_dereference_protected(src->scheduler, 1);
dst->protocol = src->protocol;
dst->addr = src->addr.ip;
dst->port = src->port;
dst->fwmark = src->fwmark;
- strlcpy(dst->sched_name, src->scheduler->name, sizeof(dst->sched_name));
+ strlcpy(dst->sched_name, sched->name, sizeof(dst->sched_name));
dst->flags = src->flags;
dst->timeout = src->timeout / HZ;
dst->netmask = src->netmask;
@@ -2497,7 +2496,7 @@ __ip_vs_get_service_entries(struct net *net,
int ret = 0;
for (idx = 0; idx < IP_VS_SVC_TAB_SIZE; idx++) {
- list_for_each_entry(svc, &ip_vs_svc_table[idx], s_list) {
+ hlist_for_each_entry(svc, &ip_vs_svc_table[idx], s_list) {
/* Only expose IPv4 entries to old interface */
if (svc->af != AF_INET || !net_eq(svc->net, net))
continue;
@@ -2516,7 +2515,7 @@ __ip_vs_get_service_entries(struct net *net,
}
for (idx = 0; idx < IP_VS_SVC_TAB_SIZE; idx++) {
- list_for_each_entry(svc, &ip_vs_svc_fwm_table[idx], f_list) {
+ hlist_for_each_entry(svc, &ip_vs_svc_fwm_table[idx], f_list) {
/* Only expose IPv4 entries to old interface */
if (svc->af != AF_INET || !net_eq(svc->net, net))
continue;
@@ -2545,17 +2544,20 @@ __ip_vs_get_dest_entries(struct net *net, const struct ip_vs_get_dests *get,
union nf_inet_addr addr = { .ip = get->addr };
int ret = 0;
+ rcu_read_lock();
if (get->fwmark)
svc = __ip_vs_svc_fwm_find(net, AF_INET, get->fwmark);
else
svc = __ip_vs_service_find(net, AF_INET, get->protocol, &addr,
get->port);
+ rcu_read_unlock();
if (svc) {
int count = 0;
struct ip_vs_dest *dest;
struct ip_vs_dest_entry entry;
+ memset(&entry, 0, sizeof(entry));
list_for_each_entry(dest, &svc->destinations, n_list) {
if (count >= get->num_dests)
break;
@@ -2732,12 +2734,14 @@ do_ip_vs_get_ctl(struct sock *sk, int cmd, void __user *user, int *len)
entry = (struct ip_vs_service_entry *)arg;
addr.ip = entry->addr;
+ rcu_read_lock();
if (entry->fwmark)
svc = __ip_vs_svc_fwm_find(net, AF_INET, entry->fwmark);
else
svc = __ip_vs_service_find(net, AF_INET,
entry->protocol, &addr,
entry->port);
+ rcu_read_unlock();
if (svc) {
ip_vs_copy_service(entry, svc);
if (copy_to_user(user, entry, sizeof(*entry)) != 0)
@@ -2894,6 +2898,8 @@ nla_put_failure:
static int ip_vs_genl_fill_service(struct sk_buff *skb,
struct ip_vs_service *svc)
{
+ struct ip_vs_scheduler *sched;
+ struct ip_vs_pe *pe;
struct nlattr *nl_service;
struct ip_vs_flags flags = { .flags = svc->flags,
.mask = ~0 };
@@ -2910,16 +2916,17 @@ static int ip_vs_genl_fill_service(struct sk_buff *skb,
} else {
if (nla_put_u16(skb, IPVS_SVC_ATTR_PROTOCOL, svc->protocol) ||
nla_put(skb, IPVS_SVC_ATTR_ADDR, sizeof(svc->addr), &svc->addr) ||
- nla_put_u16(skb, IPVS_SVC_ATTR_PORT, svc->port))
+ nla_put_be16(skb, IPVS_SVC_ATTR_PORT, svc->port))
goto nla_put_failure;
}
- if (nla_put_string(skb, IPVS_SVC_ATTR_SCHED_NAME, svc->scheduler->name) ||
- (svc->pe &&
- nla_put_string(skb, IPVS_SVC_ATTR_PE_NAME, svc->pe->name)) ||
+ sched = rcu_dereference_protected(svc->scheduler, 1);
+ pe = rcu_dereference_protected(svc->pe, 1);
+ if (nla_put_string(skb, IPVS_SVC_ATTR_SCHED_NAME, sched->name) ||
+ (pe && nla_put_string(skb, IPVS_SVC_ATTR_PE_NAME, pe->name)) ||
nla_put(skb, IPVS_SVC_ATTR_FLAGS, sizeof(flags), &flags) ||
nla_put_u32(skb, IPVS_SVC_ATTR_TIMEOUT, svc->timeout / HZ) ||
- nla_put_u32(skb, IPVS_SVC_ATTR_NETMASK, svc->netmask))
+ nla_put_be32(skb, IPVS_SVC_ATTR_NETMASK, svc->netmask))
goto nla_put_failure;
if (ip_vs_genl_fill_stats(skb, IPVS_SVC_ATTR_STATS, &svc->stats))
goto nla_put_failure;
@@ -2965,7 +2972,7 @@ static int ip_vs_genl_dump_services(struct sk_buff *skb,
mutex_lock(&__ip_vs_mutex);
for (i = 0; i < IP_VS_SVC_TAB_SIZE; i++) {
- list_for_each_entry(svc, &ip_vs_svc_table[i], s_list) {
+ hlist_for_each_entry(svc, &ip_vs_svc_table[i], s_list) {
if (++idx <= start || !net_eq(svc->net, net))
continue;
if (ip_vs_genl_dump_service(skb, svc, cb) < 0) {
@@ -2976,7 +2983,7 @@ static int ip_vs_genl_dump_services(struct sk_buff *skb,
}
for (i = 0; i < IP_VS_SVC_TAB_SIZE; i++) {
- list_for_each_entry(svc, &ip_vs_svc_fwm_table[i], f_list) {
+ hlist_for_each_entry(svc, &ip_vs_svc_fwm_table[i], f_list) {
if (++idx <= start || !net_eq(svc->net, net))
continue;
if (ip_vs_genl_dump_service(skb, svc, cb) < 0) {
@@ -3032,15 +3039,17 @@ static int ip_vs_genl_parse_service(struct net *net,
} else {
usvc->protocol = nla_get_u16(nla_protocol);
nla_memcpy(&usvc->addr, nla_addr, sizeof(usvc->addr));
- usvc->port = nla_get_u16(nla_port);
+ usvc->port = nla_get_be16(nla_port);
usvc->fwmark = 0;
}
+ rcu_read_lock();
if (usvc->fwmark)
svc = __ip_vs_svc_fwm_find(net, usvc->af, usvc->fwmark);
else
svc = __ip_vs_service_find(net, usvc->af, usvc->protocol,
&usvc->addr, usvc->port);
+ rcu_read_unlock();
*ret_svc = svc;
/* If a full entry was requested, check for the additional fields */
@@ -3070,7 +3079,7 @@ static int ip_vs_genl_parse_service(struct net *net,
usvc->sched_name = nla_data(nla_sched);
usvc->pe_name = nla_pe ? nla_data(nla_pe) : NULL;
usvc->timeout = nla_get_u32(nla_timeout);
- usvc->netmask = nla_get_u32(nla_netmask);
+ usvc->netmask = nla_get_be32(nla_netmask);
}
return 0;
@@ -3096,7 +3105,7 @@ static int ip_vs_genl_fill_dest(struct sk_buff *skb, struct ip_vs_dest *dest)
return -EMSGSIZE;
if (nla_put(skb, IPVS_DEST_ATTR_ADDR, sizeof(dest->addr), &dest->addr) ||
- nla_put_u16(skb, IPVS_DEST_ATTR_PORT, dest->port) ||
+ nla_put_be16(skb, IPVS_DEST_ATTR_PORT, dest->port) ||
nla_put_u32(skb, IPVS_DEST_ATTR_FWD_METHOD,
(atomic_read(&dest->conn_flags) &
IP_VS_CONN_F_FWD_MASK)) ||
@@ -3205,7 +3214,7 @@ static int ip_vs_genl_parse_dest(struct ip_vs_dest_user_kern *udest,
memset(udest, 0, sizeof(*udest));
nla_memcpy(&udest->addr, nla_addr, sizeof(udest->addr));
- udest->port = nla_get_u16(nla_port);
+ udest->port = nla_get_be16(nla_port);
/* If a full entry was requested, check for the additional fields */
if (full_entry) {
@@ -3230,8 +3239,8 @@ static int ip_vs_genl_parse_dest(struct ip_vs_dest_user_kern *udest,
return 0;
}
-static int ip_vs_genl_fill_daemon(struct sk_buff *skb, __be32 state,
- const char *mcast_ifn, __be32 syncid)
+static int ip_vs_genl_fill_daemon(struct sk_buff *skb, __u32 state,
+ const char *mcast_ifn, __u32 syncid)
{
struct nlattr *nl_daemon;
@@ -3252,8 +3261,8 @@ nla_put_failure:
return -EMSGSIZE;
}
-static int ip_vs_genl_dump_daemon(struct sk_buff *skb, __be32 state,
- const char *mcast_ifn, __be32 syncid,
+static int ip_vs_genl_dump_daemon(struct sk_buff *skb, __u32 state,
+ const char *mcast_ifn, __u32 syncid,
struct netlink_callback *cb)
{
void *hdr;
@@ -3392,7 +3401,7 @@ static int ip_vs_genl_set_cmd(struct sk_buff *skb, struct genl_info *info)
mutex_lock(&__ip_vs_mutex);
if (cmd == IPVS_CMD_FLUSH) {
- ret = ip_vs_flush(net);
+ ret = ip_vs_flush(net, false);
goto out;
} else if (cmd == IPVS_CMD_SET_CONFIG) {
ret = ip_vs_genl_set_config(net, info->attrs);
@@ -3571,7 +3580,7 @@ out:
}
-static struct genl_ops ip_vs_genl_ops[] __read_mostly = {
+static const struct genl_ops ip_vs_genl_ops[] = {
{
.cmd = IPVS_CMD_NEW_SERVICE,
.flags = GENL_ADMIN_PERM,
@@ -3670,7 +3679,7 @@ static struct genl_ops ip_vs_genl_ops[] __read_mostly = {
static int __init ip_vs_genl_register(void)
{
return genl_register_family_with_ops(&ip_vs_genl_family,
- ip_vs_genl_ops, ARRAY_SIZE(ip_vs_genl_ops));
+ ip_vs_genl_ops);
}
static void ip_vs_genl_unregister(void)
@@ -3723,12 +3732,15 @@ static int __net_init ip_vs_control_net_init_sysctl(struct net *net)
tbl[idx++].data = &ipvs->sysctl_sync_ver;
ipvs->sysctl_sync_ports = 1;
tbl[idx++].data = &ipvs->sysctl_sync_ports;
+ tbl[idx++].data = &ipvs->sysctl_sync_persist_mode;
ipvs->sysctl_sync_qlen_max = nr_free_buffer_pages() / 32;
tbl[idx++].data = &ipvs->sysctl_sync_qlen_max;
ipvs->sysctl_sync_sock_size = 0;
tbl[idx++].data = &ipvs->sysctl_sync_sock_size;
tbl[idx++].data = &ipvs->sysctl_cache_bypass;
tbl[idx++].data = &ipvs->sysctl_expire_nodest_conn;
+ tbl[idx++].data = &ipvs->sysctl_sloppy_tcp;
+ tbl[idx++].data = &ipvs->sysctl_sloppy_sctp;
tbl[idx++].data = &ipvs->sysctl_expire_quiescent_template;
ipvs->sysctl_sync_threshold[0] = DEFAULT_SYNC_THRESHOLD;
ipvs->sysctl_sync_threshold[1] = DEFAULT_SYNC_PERIOD;
@@ -3741,6 +3753,7 @@ static int __net_init ip_vs_control_net_init_sysctl(struct net *net)
tbl[idx++].data = &ipvs->sysctl_nat_icmp_send;
ipvs->sysctl_pmtu_disc = 1;
tbl[idx++].data = &ipvs->sysctl_pmtu_disc;
+ tbl[idx++].data = &ipvs->sysctl_backup_only;
ipvs->sysctl_hdr = register_net_sysctl(net, "net/ipv4/vs", tbl);
@@ -3765,6 +3778,7 @@ static void __net_exit ip_vs_control_net_cleanup_sysctl(struct net *net)
cancel_delayed_work_sync(&ipvs->defense_work);
cancel_work_sync(&ipvs->defense_work.work);
unregister_net_sysctl_table(ipvs->sysctl_hdr);
+ ip_vs_stop_estimator(net, &ipvs->tot_stats);
}
#else
@@ -3780,16 +3794,17 @@ static struct notifier_block ip_vs_dst_notifier = {
int __net_init ip_vs_control_net_init(struct net *net)
{
- int idx;
+ int i, idx;
struct netns_ipvs *ipvs = net_ipvs(net);
- rwlock_init(&ipvs->rs_lock);
-
/* Initialize rs_table */
for (idx = 0; idx < IP_VS_RTAB_SIZE; idx++)
- INIT_LIST_HEAD(&ipvs->rs_table[idx]);
+ INIT_HLIST_HEAD(&ipvs->rs_table[idx]);
INIT_LIST_HEAD(&ipvs->dest_trash);
+ spin_lock_init(&ipvs->dest_trash_lock);
+ setup_timer(&ipvs->dest_trash_timer, ip_vs_dest_trash_expire,
+ (unsigned long) net);
atomic_set(&ipvs->ftpsvc_counter, 0);
atomic_set(&ipvs->nullsvc_counter, 0);
@@ -3798,12 +3813,18 @@ int __net_init ip_vs_control_net_init(struct net *net)
if (!ipvs->tot_stats.cpustats)
return -ENOMEM;
+ for_each_possible_cpu(i) {
+ struct ip_vs_cpu_stats *ipvs_tot_stats;
+ ipvs_tot_stats = per_cpu_ptr(ipvs->tot_stats.cpustats, i);
+ u64_stats_init(&ipvs_tot_stats->syncp);
+ }
+
spin_lock_init(&ipvs->tot_stats.lock);
- proc_net_fops_create(net, "ip_vs", 0, &ip_vs_info_fops);
- proc_net_fops_create(net, "ip_vs_stats", 0, &ip_vs_stats_fops);
- proc_net_fops_create(net, "ip_vs_stats_percpu", 0,
- &ip_vs_stats_percpu_fops);
+ proc_create("ip_vs", 0, net->proc_net, &ip_vs_info_fops);
+ proc_create("ip_vs_stats", 0, net->proc_net, &ip_vs_stats_fops);
+ proc_create("ip_vs_stats_percpu", 0, net->proc_net,
+ &ip_vs_stats_percpu_fops);
if (ip_vs_control_net_init_sysctl(net))
goto err;
@@ -3820,11 +3841,10 @@ void __net_exit ip_vs_control_net_cleanup(struct net *net)
struct netns_ipvs *ipvs = net_ipvs(net);
ip_vs_trash_cleanup(net);
- ip_vs_stop_estimator(net, &ipvs->tot_stats);
ip_vs_control_net_cleanup_sysctl(net);
- proc_net_remove(net, "ip_vs_stats_percpu");
- proc_net_remove(net, "ip_vs_stats");
- proc_net_remove(net, "ip_vs");
+ remove_proc_entry("ip_vs_stats_percpu", net->proc_net);
+ remove_proc_entry("ip_vs_stats", net->proc_net);
+ remove_proc_entry("ip_vs", net->proc_net);
free_percpu(ipvs->tot_stats.cpustats);
}
@@ -3864,10 +3884,10 @@ int __init ip_vs_control_init(void)
EnterFunction(2);
- /* Initialize svc_table, ip_vs_svc_fwm_table, rs_table */
+ /* Initialize svc_table, ip_vs_svc_fwm_table */
for (idx = 0; idx < IP_VS_SVC_TAB_SIZE; idx++) {
- INIT_LIST_HEAD(&ip_vs_svc_table[idx]);
- INIT_LIST_HEAD(&ip_vs_svc_fwm_table[idx]);
+ INIT_HLIST_HEAD(&ip_vs_svc_table[idx]);
+ INIT_HLIST_HEAD(&ip_vs_svc_fwm_table[idx]);
}
smp_wmb(); /* Do we really need it now ? */
diff --git a/net/netfilter/ipvs/ip_vs_dh.c b/net/netfilter/ipvs/ip_vs_dh.c
index 7f3b0cc00b7..c3b84546ea9 100644
--- a/net/netfilter/ipvs/ip_vs_dh.c
+++ b/net/netfilter/ipvs/ip_vs_dh.c
@@ -51,7 +51,7 @@
* IPVS DH bucket
*/
struct ip_vs_dh_bucket {
- struct ip_vs_dest *dest; /* real server (cache) */
+ struct ip_vs_dest __rcu *dest; /* real server (cache) */
};
/*
@@ -64,6 +64,10 @@ struct ip_vs_dh_bucket {
#define IP_VS_DH_TAB_SIZE (1 << IP_VS_DH_TAB_BITS)
#define IP_VS_DH_TAB_MASK (IP_VS_DH_TAB_SIZE - 1)
+struct ip_vs_dh_state {
+ struct ip_vs_dh_bucket buckets[IP_VS_DH_TAB_SIZE];
+ struct rcu_head rcu_head;
+};
/*
* Returns hash value for IPVS DH entry
@@ -85,10 +89,9 @@ static inline unsigned int ip_vs_dh_hashkey(int af, const union nf_inet_addr *ad
* Get ip_vs_dest associated with supplied parameters.
*/
static inline struct ip_vs_dest *
-ip_vs_dh_get(int af, struct ip_vs_dh_bucket *tbl,
- const union nf_inet_addr *addr)
+ip_vs_dh_get(int af, struct ip_vs_dh_state *s, const union nf_inet_addr *addr)
{
- return (tbl[ip_vs_dh_hashkey(af, addr)]).dest;
+ return rcu_dereference(s->buckets[ip_vs_dh_hashkey(af, addr)].dest);
}
@@ -96,25 +99,30 @@ ip_vs_dh_get(int af, struct ip_vs_dh_bucket *tbl,
* Assign all the hash buckets of the specified table with the service.
*/
static int
-ip_vs_dh_assign(struct ip_vs_dh_bucket *tbl, struct ip_vs_service *svc)
+ip_vs_dh_reassign(struct ip_vs_dh_state *s, struct ip_vs_service *svc)
{
int i;
struct ip_vs_dh_bucket *b;
struct list_head *p;
struct ip_vs_dest *dest;
+ bool empty;
- b = tbl;
+ b = &s->buckets[0];
p = &svc->destinations;
+ empty = list_empty(p);
for (i=0; i<IP_VS_DH_TAB_SIZE; i++) {
- if (list_empty(p)) {
- b->dest = NULL;
- } else {
+ dest = rcu_dereference_protected(b->dest, 1);
+ if (dest)
+ ip_vs_dest_put(dest);
+ if (empty)
+ RCU_INIT_POINTER(b->dest, NULL);
+ else {
if (p == &svc->destinations)
p = p->next;
dest = list_entry(p, struct ip_vs_dest, n_list);
- atomic_inc(&dest->refcnt);
- b->dest = dest;
+ ip_vs_dest_hold(dest);
+ RCU_INIT_POINTER(b->dest, dest);
p = p->next;
}
@@ -127,16 +135,18 @@ ip_vs_dh_assign(struct ip_vs_dh_bucket *tbl, struct ip_vs_service *svc)
/*
* Flush all the hash buckets of the specified table.
*/
-static void ip_vs_dh_flush(struct ip_vs_dh_bucket *tbl)
+static void ip_vs_dh_flush(struct ip_vs_dh_state *s)
{
int i;
struct ip_vs_dh_bucket *b;
+ struct ip_vs_dest *dest;
- b = tbl;
+ b = &s->buckets[0];
for (i=0; i<IP_VS_DH_TAB_SIZE; i++) {
- if (b->dest) {
- atomic_dec(&b->dest->refcnt);
- b->dest = NULL;
+ dest = rcu_dereference_protected(b->dest, 1);
+ if (dest) {
+ ip_vs_dest_put(dest);
+ RCU_INIT_POINTER(b->dest, NULL);
}
b++;
}
@@ -145,51 +155,46 @@ static void ip_vs_dh_flush(struct ip_vs_dh_bucket *tbl)
static int ip_vs_dh_init_svc(struct ip_vs_service *svc)
{
- struct ip_vs_dh_bucket *tbl;
+ struct ip_vs_dh_state *s;
/* allocate the DH table for this service */
- tbl = kmalloc(sizeof(struct ip_vs_dh_bucket)*IP_VS_DH_TAB_SIZE,
- GFP_KERNEL);
- if (tbl == NULL)
+ s = kzalloc(sizeof(struct ip_vs_dh_state), GFP_KERNEL);
+ if (s == NULL)
return -ENOMEM;
- svc->sched_data = tbl;
+ svc->sched_data = s;
IP_VS_DBG(6, "DH hash table (memory=%Zdbytes) allocated for "
"current service\n",
sizeof(struct ip_vs_dh_bucket)*IP_VS_DH_TAB_SIZE);
- /* assign the hash buckets with the updated service */
- ip_vs_dh_assign(tbl, svc);
+ /* assign the hash buckets with current dests */
+ ip_vs_dh_reassign(s, svc);
return 0;
}
-static int ip_vs_dh_done_svc(struct ip_vs_service *svc)
+static void ip_vs_dh_done_svc(struct ip_vs_service *svc)
{
- struct ip_vs_dh_bucket *tbl = svc->sched_data;
+ struct ip_vs_dh_state *s = svc->sched_data;
/* got to clean up hash buckets here */
- ip_vs_dh_flush(tbl);
+ ip_vs_dh_flush(s);
/* release the table itself */
- kfree(svc->sched_data);
+ kfree_rcu(s, rcu_head);
IP_VS_DBG(6, "DH hash table (memory=%Zdbytes) released\n",
sizeof(struct ip_vs_dh_bucket)*IP_VS_DH_TAB_SIZE);
-
- return 0;
}
-static int ip_vs_dh_update_svc(struct ip_vs_service *svc)
+static int ip_vs_dh_dest_changed(struct ip_vs_service *svc,
+ struct ip_vs_dest *dest)
{
- struct ip_vs_dh_bucket *tbl = svc->sched_data;
-
- /* got to clean up hash buckets here */
- ip_vs_dh_flush(tbl);
+ struct ip_vs_dh_state *s = svc->sched_data;
/* assign the hash buckets with the updated service */
- ip_vs_dh_assign(tbl, svc);
+ ip_vs_dh_reassign(s, svc);
return 0;
}
@@ -209,27 +214,26 @@ static inline int is_overloaded(struct ip_vs_dest *dest)
* Destination hashing scheduling
*/
static struct ip_vs_dest *
-ip_vs_dh_schedule(struct ip_vs_service *svc, const struct sk_buff *skb)
+ip_vs_dh_schedule(struct ip_vs_service *svc, const struct sk_buff *skb,
+ struct ip_vs_iphdr *iph)
{
struct ip_vs_dest *dest;
- struct ip_vs_dh_bucket *tbl;
- struct ip_vs_iphdr iph;
-
- ip_vs_fill_iph_addr_only(svc->af, skb, &iph);
+ struct ip_vs_dh_state *s;
IP_VS_DBG(6, "%s(): Scheduling...\n", __func__);
- tbl = (struct ip_vs_dh_bucket *)svc->sched_data;
- dest = ip_vs_dh_get(svc->af, tbl, &iph.daddr);
+ s = (struct ip_vs_dh_state *) svc->sched_data;
+ dest = ip_vs_dh_get(svc->af, s, &iph->daddr);
if (!dest
|| !(dest->flags & IP_VS_DEST_F_AVAILABLE)
|| atomic_read(&dest->weight) <= 0
|| is_overloaded(dest)) {
+ ip_vs_scheduler_err(svc, "no destination available");
return NULL;
}
IP_VS_DBG_BUF(6, "DH: destination IP address %s --> server %s:%d\n",
- IP_VS_DBG_ADDR(svc->af, &iph.daddr),
+ IP_VS_DBG_ADDR(svc->af, &iph->daddr),
IP_VS_DBG_ADDR(svc->af, &dest->addr),
ntohs(dest->port));
@@ -248,7 +252,8 @@ static struct ip_vs_scheduler ip_vs_dh_scheduler =
.n_list = LIST_HEAD_INIT(ip_vs_dh_scheduler.n_list),
.init_service = ip_vs_dh_init_svc,
.done_service = ip_vs_dh_done_svc,
- .update_service = ip_vs_dh_update_svc,
+ .add_dest = ip_vs_dh_dest_changed,
+ .del_dest = ip_vs_dh_dest_changed,
.schedule = ip_vs_dh_schedule,
};
@@ -262,6 +267,7 @@ static int __init ip_vs_dh_init(void)
static void __exit ip_vs_dh_cleanup(void)
{
unregister_ip_vs_scheduler(&ip_vs_dh_scheduler);
+ synchronize_rcu();
}
diff --git a/net/netfilter/ipvs/ip_vs_est.c b/net/netfilter/ipvs/ip_vs_est.c
index 0fac6017b6f..1425e9a924c 100644
--- a/net/netfilter/ipvs/ip_vs_est.c
+++ b/net/netfilter/ipvs/ip_vs_est.c
@@ -56,15 +56,16 @@
* Make a summary from each cpu
*/
static void ip_vs_read_cpu_stats(struct ip_vs_stats_user *sum,
- struct ip_vs_cpu_stats *stats)
+ struct ip_vs_cpu_stats __percpu *stats)
{
int i;
+ bool add = false;
for_each_possible_cpu(i) {
struct ip_vs_cpu_stats *s = per_cpu_ptr(stats, i);
unsigned int start;
__u64 inbytes, outbytes;
- if (i) {
+ if (add) {
sum->conns += s->ustats.conns;
sum->inpkts += s->ustats.inpkts;
sum->outpkts += s->ustats.outpkts;
@@ -76,6 +77,7 @@ static void ip_vs_read_cpu_stats(struct ip_vs_stats_user *sum,
sum->inbytes += inbytes;
sum->outbytes += outbytes;
} else {
+ add = true;
sum->conns = s->ustats.conns;
sum->inpkts = s->ustats.inpkts;
sum->outpkts = s->ustats.outpkts;
diff --git a/net/netfilter/ipvs/ip_vs_ftp.c b/net/netfilter/ipvs/ip_vs_ftp.c
index 4f53a5f0443..77c173282f3 100644
--- a/net/netfilter/ipvs/ip_vs_ftp.c
+++ b/net/netfilter/ipvs/ip_vs_ftp.c
@@ -267,10 +267,12 @@ static int ip_vs_ftp_out(struct ip_vs_app *app, struct ip_vs_conn *cp,
* hopefully it will succeed on the retransmitted
* packet.
*/
+ rcu_read_lock();
ret = nf_nat_mangle_tcp_packet(skb, ct, ctinfo,
iph->ihl * 4,
start-data, end-start,
buf, buf_len);
+ rcu_read_unlock();
if (ret) {
ip_vs_nfct_expect_related(skb, ct, n_cp,
IPPROTO_TCP, 0, 0);
@@ -480,6 +482,7 @@ static int __init ip_vs_ftp_init(void)
int rv;
rv = register_pernet_subsys(&ip_vs_ftp_ops);
+ /* rcu_barrier() is called by netns on error */
return rv;
}
@@ -489,6 +492,7 @@ static int __init ip_vs_ftp_init(void)
static void __exit ip_vs_ftp_exit(void)
{
unregister_pernet_subsys(&ip_vs_ftp_ops);
+ /* rcu_barrier() is called by netns */
}
diff --git a/net/netfilter/ipvs/ip_vs_lblc.c b/net/netfilter/ipvs/ip_vs_lblc.c
index fdd89b9564e..547ff33c1ef 100644
--- a/net/netfilter/ipvs/ip_vs_lblc.c
+++ b/net/netfilter/ipvs/ip_vs_lblc.c
@@ -90,11 +90,12 @@
* IP address and its destination server
*/
struct ip_vs_lblc_entry {
- struct list_head list;
+ struct hlist_node list;
int af; /* address family */
union nf_inet_addr addr; /* destination IP address */
- struct ip_vs_dest *dest; /* real server (cache) */
+ struct ip_vs_dest *dest; /* real server (cache) */
unsigned long lastuse; /* last used time */
+ struct rcu_head rcu_head;
};
@@ -102,12 +103,14 @@ struct ip_vs_lblc_entry {
* IPVS lblc hash table
*/
struct ip_vs_lblc_table {
- struct list_head bucket[IP_VS_LBLC_TAB_SIZE]; /* hash bucket */
+ struct rcu_head rcu_head;
+ struct hlist_head bucket[IP_VS_LBLC_TAB_SIZE]; /* hash bucket */
+ struct timer_list periodic_timer; /* collect stale entries */
atomic_t entries; /* number of entries */
int max_size; /* maximum size of entries */
- struct timer_list periodic_timer; /* collect stale entries */
int rover; /* rover for expire check */
int counter; /* counter for no expire */
+ bool dead;
};
@@ -115,7 +118,7 @@ struct ip_vs_lblc_table {
* IPVS LBLC sysctl table
*/
#ifdef CONFIG_SYSCTL
-static ctl_table vs_vars_table[] = {
+static struct ctl_table vs_vars_table[] = {
{
.procname = "lblc_expiration",
.data = NULL,
@@ -127,17 +130,21 @@ static ctl_table vs_vars_table[] = {
};
#endif
-static inline void ip_vs_lblc_free(struct ip_vs_lblc_entry *en)
+static void ip_vs_lblc_rcu_free(struct rcu_head *head)
{
- list_del(&en->list);
- /*
- * We don't kfree dest because it is referred either by its service
- * or the trash dest list.
- */
- atomic_dec(&en->dest->refcnt);
+ struct ip_vs_lblc_entry *en = container_of(head,
+ struct ip_vs_lblc_entry,
+ rcu_head);
+
+ ip_vs_dest_put_and_free(en->dest);
kfree(en);
}
+static inline void ip_vs_lblc_del(struct ip_vs_lblc_entry *en)
+{
+ hlist_del_rcu(&en->list);
+ call_rcu(&en->rcu_head, ip_vs_lblc_rcu_free);
+}
/*
* Returns hash value for IPVS LBLC entry
@@ -165,15 +172,12 @@ ip_vs_lblc_hash(struct ip_vs_lblc_table *tbl, struct ip_vs_lblc_entry *en)
{
unsigned int hash = ip_vs_lblc_hashkey(en->af, &en->addr);
- list_add(&en->list, &tbl->bucket[hash]);
+ hlist_add_head_rcu(&en->list, &tbl->bucket[hash]);
atomic_inc(&tbl->entries);
}
-/*
- * Get ip_vs_lblc_entry associated with supplied parameters. Called under read
- * lock
- */
+/* Get ip_vs_lblc_entry associated with supplied parameters. */
static inline struct ip_vs_lblc_entry *
ip_vs_lblc_get(int af, struct ip_vs_lblc_table *tbl,
const union nf_inet_addr *addr)
@@ -181,7 +185,7 @@ ip_vs_lblc_get(int af, struct ip_vs_lblc_table *tbl,
unsigned int hash = ip_vs_lblc_hashkey(af, addr);
struct ip_vs_lblc_entry *en;
- list_for_each_entry(en, &tbl->bucket[hash], list)
+ hlist_for_each_entry_rcu(en, &tbl->bucket[hash], list)
if (ip_vs_addr_equal(af, &en->addr, addr))
return en;
@@ -191,7 +195,7 @@ ip_vs_lblc_get(int af, struct ip_vs_lblc_table *tbl,
/*
* Create or update an ip_vs_lblc_entry, which is a mapping of a destination IP
- * address to a server. Called under write lock.
+ * address to a server. Called under spin lock.
*/
static inline struct ip_vs_lblc_entry *
ip_vs_lblc_new(struct ip_vs_lblc_table *tbl, const union nf_inet_addr *daddr,
@@ -200,24 +204,23 @@ ip_vs_lblc_new(struct ip_vs_lblc_table *tbl, const union nf_inet_addr *daddr,
struct ip_vs_lblc_entry *en;
en = ip_vs_lblc_get(dest->af, tbl, daddr);
- if (!en) {
- en = kmalloc(sizeof(*en), GFP_ATOMIC);
- if (!en)
- return NULL;
+ if (en) {
+ if (en->dest == dest)
+ return en;
+ ip_vs_lblc_del(en);
+ }
+ en = kmalloc(sizeof(*en), GFP_ATOMIC);
+ if (!en)
+ return NULL;
- en->af = dest->af;
- ip_vs_addr_copy(dest->af, &en->addr, daddr);
- en->lastuse = jiffies;
+ en->af = dest->af;
+ ip_vs_addr_copy(dest->af, &en->addr, daddr);
+ en->lastuse = jiffies;
- atomic_inc(&dest->refcnt);
- en->dest = dest;
+ ip_vs_dest_hold(dest);
+ en->dest = dest;
- ip_vs_lblc_hash(tbl, en);
- } else if (en->dest != dest) {
- atomic_dec(&en->dest->refcnt);
- atomic_inc(&dest->refcnt);
- en->dest = dest;
- }
+ ip_vs_lblc_hash(tbl, en);
return en;
}
@@ -226,17 +229,22 @@ ip_vs_lblc_new(struct ip_vs_lblc_table *tbl, const union nf_inet_addr *daddr,
/*
* Flush all the entries of the specified table.
*/
-static void ip_vs_lblc_flush(struct ip_vs_lblc_table *tbl)
+static void ip_vs_lblc_flush(struct ip_vs_service *svc)
{
- struct ip_vs_lblc_entry *en, *nxt;
+ struct ip_vs_lblc_table *tbl = svc->sched_data;
+ struct ip_vs_lblc_entry *en;
+ struct hlist_node *next;
int i;
- for (i=0; i<IP_VS_LBLC_TAB_SIZE; i++) {
- list_for_each_entry_safe(en, nxt, &tbl->bucket[i], list) {
- ip_vs_lblc_free(en);
+ spin_lock_bh(&svc->sched_lock);
+ tbl->dead = 1;
+ for (i = 0; i < IP_VS_LBLC_TAB_SIZE; i++) {
+ hlist_for_each_entry_safe(en, next, &tbl->bucket[i], list) {
+ ip_vs_lblc_del(en);
atomic_dec(&tbl->entries);
}
}
+ spin_unlock_bh(&svc->sched_lock);
}
static int sysctl_lblc_expiration(struct ip_vs_service *svc)
@@ -252,24 +260,25 @@ static int sysctl_lblc_expiration(struct ip_vs_service *svc)
static inline void ip_vs_lblc_full_check(struct ip_vs_service *svc)
{
struct ip_vs_lblc_table *tbl = svc->sched_data;
- struct ip_vs_lblc_entry *en, *nxt;
+ struct ip_vs_lblc_entry *en;
+ struct hlist_node *next;
unsigned long now = jiffies;
int i, j;
- for (i=0, j=tbl->rover; i<IP_VS_LBLC_TAB_SIZE; i++) {
+ for (i = 0, j = tbl->rover; i < IP_VS_LBLC_TAB_SIZE; i++) {
j = (j + 1) & IP_VS_LBLC_TAB_MASK;
- write_lock(&svc->sched_lock);
- list_for_each_entry_safe(en, nxt, &tbl->bucket[j], list) {
+ spin_lock(&svc->sched_lock);
+ hlist_for_each_entry_safe(en, next, &tbl->bucket[j], list) {
if (time_before(now,
en->lastuse +
sysctl_lblc_expiration(svc)))
continue;
- ip_vs_lblc_free(en);
+ ip_vs_lblc_del(en);
atomic_dec(&tbl->entries);
}
- write_unlock(&svc->sched_lock);
+ spin_unlock(&svc->sched_lock);
}
tbl->rover = j;
}
@@ -293,7 +302,8 @@ static void ip_vs_lblc_check_expire(unsigned long data)
unsigned long now = jiffies;
int goal;
int i, j;
- struct ip_vs_lblc_entry *en, *nxt;
+ struct ip_vs_lblc_entry *en;
+ struct hlist_node *next;
if ((tbl->counter % COUNT_FOR_FULL_EXPIRATION) == 0) {
/* do full expiration check */
@@ -311,26 +321,26 @@ static void ip_vs_lblc_check_expire(unsigned long data)
if (goal > tbl->max_size/2)
goal = tbl->max_size/2;
- for (i=0, j=tbl->rover; i<IP_VS_LBLC_TAB_SIZE; i++) {
+ for (i = 0, j = tbl->rover; i < IP_VS_LBLC_TAB_SIZE; i++) {
j = (j + 1) & IP_VS_LBLC_TAB_MASK;
- write_lock(&svc->sched_lock);
- list_for_each_entry_safe(en, nxt, &tbl->bucket[j], list) {
+ spin_lock(&svc->sched_lock);
+ hlist_for_each_entry_safe(en, next, &tbl->bucket[j], list) {
if (time_before(now, en->lastuse + ENTRY_TIMEOUT))
continue;
- ip_vs_lblc_free(en);
+ ip_vs_lblc_del(en);
atomic_dec(&tbl->entries);
goal--;
}
- write_unlock(&svc->sched_lock);
+ spin_unlock(&svc->sched_lock);
if (goal <= 0)
break;
}
tbl->rover = j;
out:
- mod_timer(&tbl->periodic_timer, jiffies+CHECK_EXPIRE_INTERVAL);
+ mod_timer(&tbl->periodic_timer, jiffies + CHECK_EXPIRE_INTERVAL);
}
@@ -353,12 +363,13 @@ static int ip_vs_lblc_init_svc(struct ip_vs_service *svc)
/*
* Initialize the hash buckets
*/
- for (i=0; i<IP_VS_LBLC_TAB_SIZE; i++) {
- INIT_LIST_HEAD(&tbl->bucket[i]);
+ for (i = 0; i < IP_VS_LBLC_TAB_SIZE; i++) {
+ INIT_HLIST_HEAD(&tbl->bucket[i]);
}
tbl->max_size = IP_VS_LBLC_TAB_SIZE*16;
tbl->rover = 0;
tbl->counter = 1;
+ tbl->dead = 0;
/*
* Hook periodic timer for garbage collection
@@ -371,7 +382,7 @@ static int ip_vs_lblc_init_svc(struct ip_vs_service *svc)
}
-static int ip_vs_lblc_done_svc(struct ip_vs_service *svc)
+static void ip_vs_lblc_done_svc(struct ip_vs_service *svc)
{
struct ip_vs_lblc_table *tbl = svc->sched_data;
@@ -379,14 +390,12 @@ static int ip_vs_lblc_done_svc(struct ip_vs_service *svc)
del_timer_sync(&tbl->periodic_timer);
/* got to clean up table entries here */
- ip_vs_lblc_flush(tbl);
+ ip_vs_lblc_flush(svc);
/* release the table itself */
- kfree(tbl);
+ kfree_rcu(tbl, rcu_head);
IP_VS_DBG(6, "LBLC hash table (memory=%Zdbytes) released\n",
sizeof(*tbl));
-
- return 0;
}
@@ -408,7 +417,7 @@ __ip_vs_lblc_schedule(struct ip_vs_service *svc)
* The server with weight=0 is quiesced and will not receive any
* new connection.
*/
- list_for_each_entry(dest, &svc->destinations, n_list) {
+ list_for_each_entry_rcu(dest, &svc->destinations, n_list) {
if (dest->flags & IP_VS_DEST_F_OVERLOAD)
continue;
if (atomic_read(&dest->weight) > 0) {
@@ -423,13 +432,13 @@ __ip_vs_lblc_schedule(struct ip_vs_service *svc)
* Find the destination with the least load.
*/
nextstage:
- list_for_each_entry_continue(dest, &svc->destinations, n_list) {
+ list_for_each_entry_continue_rcu(dest, &svc->destinations, n_list) {
if (dest->flags & IP_VS_DEST_F_OVERLOAD)
continue;
doh = ip_vs_dest_conn_overhead(dest);
- if (loh * atomic_read(&dest->weight) >
- doh * atomic_read(&least->weight)) {
+ if ((__s64)loh * atomic_read(&dest->weight) >
+ (__s64)doh * atomic_read(&least->weight)) {
least = dest;
loh = doh;
}
@@ -457,7 +466,7 @@ is_overloaded(struct ip_vs_dest *dest, struct ip_vs_service *svc)
if (atomic_read(&dest->activeconns) > atomic_read(&dest->weight)) {
struct ip_vs_dest *d;
- list_for_each_entry(d, &svc->destinations, n_list) {
+ list_for_each_entry_rcu(d, &svc->destinations, n_list) {
if (atomic_read(&d->activeconns)*2
< atomic_read(&d->weight)) {
return 1;
@@ -472,20 +481,17 @@ is_overloaded(struct ip_vs_dest *dest, struct ip_vs_service *svc)
* Locality-Based (weighted) Least-Connection scheduling
*/
static struct ip_vs_dest *
-ip_vs_lblc_schedule(struct ip_vs_service *svc, const struct sk_buff *skb)
+ip_vs_lblc_schedule(struct ip_vs_service *svc, const struct sk_buff *skb,
+ struct ip_vs_iphdr *iph)
{
struct ip_vs_lblc_table *tbl = svc->sched_data;
- struct ip_vs_iphdr iph;
struct ip_vs_dest *dest = NULL;
struct ip_vs_lblc_entry *en;
- ip_vs_fill_iph_addr_only(svc->af, skb, &iph);
-
IP_VS_DBG(6, "%s(): Scheduling...\n", __func__);
/* First look in our cache */
- read_lock(&svc->sched_lock);
- en = ip_vs_lblc_get(svc->af, tbl, &iph.daddr);
+ en = ip_vs_lblc_get(svc->af, tbl, &iph->daddr);
if (en) {
/* We only hold a read lock, but this is atomic */
en->lastuse = jiffies;
@@ -499,14 +505,11 @@ ip_vs_lblc_schedule(struct ip_vs_service *svc, const struct sk_buff *skb)
* free up entries from the trash at any time.
*/
- if (en->dest->flags & IP_VS_DEST_F_AVAILABLE)
- dest = en->dest;
+ dest = en->dest;
+ if ((dest->flags & IP_VS_DEST_F_AVAILABLE) &&
+ atomic_read(&dest->weight) > 0 && !is_overloaded(dest, svc))
+ goto out;
}
- read_unlock(&svc->sched_lock);
-
- /* If the destination has a weight and is not overloaded, use it */
- if (dest && atomic_read(&dest->weight) > 0 && !is_overloaded(dest, svc))
- goto out;
/* No cache entry or it is invalid, time to schedule */
dest = __ip_vs_lblc_schedule(svc);
@@ -516,13 +519,14 @@ ip_vs_lblc_schedule(struct ip_vs_service *svc, const struct sk_buff *skb)
}
/* If we fail to create a cache entry, we'll just use the valid dest */
- write_lock(&svc->sched_lock);
- ip_vs_lblc_new(tbl, &iph.daddr, dest);
- write_unlock(&svc->sched_lock);
+ spin_lock_bh(&svc->sched_lock);
+ if (!tbl->dead)
+ ip_vs_lblc_new(tbl, &iph->daddr, dest);
+ spin_unlock_bh(&svc->sched_lock);
out:
IP_VS_DBG_BUF(6, "LBLC: destination IP address %s --> server %s:%d\n",
- IP_VS_DBG_ADDR(svc->af, &iph.daddr),
+ IP_VS_DBG_ADDR(svc->af, &iph->daddr),
IP_VS_DBG_ADDR(svc->af, &dest->addr), ntohs(dest->port));
return dest;
@@ -532,8 +536,7 @@ out:
/*
* IPVS LBLC Scheduler structure
*/
-static struct ip_vs_scheduler ip_vs_lblc_scheduler =
-{
+static struct ip_vs_scheduler ip_vs_lblc_scheduler = {
.name = "lblc",
.refcnt = ATOMIC_INIT(0),
.module = THIS_MODULE,
@@ -621,6 +624,7 @@ static void __exit ip_vs_lblc_cleanup(void)
{
unregister_ip_vs_scheduler(&ip_vs_lblc_scheduler);
unregister_pernet_subsys(&ip_vs_lblc_ops);
+ rcu_barrier();
}
diff --git a/net/netfilter/ipvs/ip_vs_lblcr.c b/net/netfilter/ipvs/ip_vs_lblcr.c
index c03b6a3ade2..3f21a2f47de 100644
--- a/net/netfilter/ipvs/ip_vs_lblcr.c
+++ b/net/netfilter/ipvs/ip_vs_lblcr.c
@@ -89,40 +89,49 @@
*/
struct ip_vs_dest_set_elem {
struct list_head list; /* list link */
- struct ip_vs_dest *dest; /* destination server */
+ struct ip_vs_dest *dest; /* destination server */
+ struct rcu_head rcu_head;
};
struct ip_vs_dest_set {
atomic_t size; /* set size */
unsigned long lastmod; /* last modified time */
struct list_head list; /* destination list */
- rwlock_t lock; /* lock for this list */
};
-static struct ip_vs_dest_set_elem *
-ip_vs_dest_set_insert(struct ip_vs_dest_set *set, struct ip_vs_dest *dest)
+static void ip_vs_dest_set_insert(struct ip_vs_dest_set *set,
+ struct ip_vs_dest *dest, bool check)
{
struct ip_vs_dest_set_elem *e;
- list_for_each_entry(e, &set->list, list) {
- if (e->dest == dest)
- /* already existed */
- return NULL;
+ if (check) {
+ list_for_each_entry(e, &set->list, list) {
+ if (e->dest == dest)
+ return;
+ }
}
e = kmalloc(sizeof(*e), GFP_ATOMIC);
if (e == NULL)
- return NULL;
+ return;
- atomic_inc(&dest->refcnt);
+ ip_vs_dest_hold(dest);
e->dest = dest;
- list_add(&e->list, &set->list);
+ list_add_rcu(&e->list, &set->list);
atomic_inc(&set->size);
set->lastmod = jiffies;
- return e;
+}
+
+static void ip_vs_lblcr_elem_rcu_free(struct rcu_head *head)
+{
+ struct ip_vs_dest_set_elem *e;
+
+ e = container_of(head, struct ip_vs_dest_set_elem, rcu_head);
+ ip_vs_dest_put_and_free(e->dest);
+ kfree(e);
}
static void
@@ -135,9 +144,8 @@ ip_vs_dest_set_erase(struct ip_vs_dest_set *set, struct ip_vs_dest *dest)
/* HIT */
atomic_dec(&set->size);
set->lastmod = jiffies;
- atomic_dec(&e->dest->refcnt);
- list_del(&e->list);
- kfree(e);
+ list_del_rcu(&e->list);
+ call_rcu(&e->rcu_head, ip_vs_lblcr_elem_rcu_free);
break;
}
}
@@ -147,17 +155,10 @@ static void ip_vs_dest_set_eraseall(struct ip_vs_dest_set *set)
{
struct ip_vs_dest_set_elem *e, *ep;
- write_lock(&set->lock);
list_for_each_entry_safe(e, ep, &set->list, list) {
- /*
- * We don't kfree dest because it is referred either
- * by its service or by the trash dest list.
- */
- atomic_dec(&e->dest->refcnt);
- list_del(&e->list);
- kfree(e);
+ list_del_rcu(&e->list);
+ call_rcu(&e->rcu_head, ip_vs_lblcr_elem_rcu_free);
}
- write_unlock(&set->lock);
}
/* get weighted least-connection node in the destination set */
@@ -167,11 +168,8 @@ static inline struct ip_vs_dest *ip_vs_dest_set_min(struct ip_vs_dest_set *set)
struct ip_vs_dest *dest, *least;
int loh, doh;
- if (set == NULL)
- return NULL;
-
/* select the first destination server, whose weight > 0 */
- list_for_each_entry(e, &set->list, list) {
+ list_for_each_entry_rcu(e, &set->list, list) {
least = e->dest;
if (least->flags & IP_VS_DEST_F_OVERLOAD)
continue;
@@ -186,14 +184,14 @@ static inline struct ip_vs_dest *ip_vs_dest_set_min(struct ip_vs_dest_set *set)
/* find the destination with the weighted least load */
nextstage:
- list_for_each_entry(e, &set->list, list) {
+ list_for_each_entry_continue_rcu(e, &set->list, list) {
dest = e->dest;
if (dest->flags & IP_VS_DEST_F_OVERLOAD)
continue;
doh = ip_vs_dest_conn_overhead(dest);
- if ((loh * atomic_read(&dest->weight) >
- doh * atomic_read(&least->weight))
+ if (((__s64)loh * atomic_read(&dest->weight) >
+ (__s64)doh * atomic_read(&least->weight))
&& (dest->flags & IP_VS_DEST_F_AVAILABLE)) {
least = dest;
loh = doh;
@@ -234,12 +232,12 @@ static inline struct ip_vs_dest *ip_vs_dest_set_max(struct ip_vs_dest_set *set)
/* find the destination with the weighted most load */
nextstage:
- list_for_each_entry(e, &set->list, list) {
+ list_for_each_entry_continue(e, &set->list, list) {
dest = e->dest;
doh = ip_vs_dest_conn_overhead(dest);
/* moh/mw < doh/dw ==> moh*dw < doh*mw, where mw,dw>0 */
- if ((moh * atomic_read(&dest->weight) <
- doh * atomic_read(&most->weight))
+ if (((__s64)moh * atomic_read(&dest->weight) <
+ (__s64)doh * atomic_read(&most->weight))
&& (atomic_read(&dest->weight) > 0)) {
most = dest;
moh = doh;
@@ -262,11 +260,12 @@ static inline struct ip_vs_dest *ip_vs_dest_set_max(struct ip_vs_dest_set *set)
* IP address and its destination server set
*/
struct ip_vs_lblcr_entry {
- struct list_head list;
+ struct hlist_node list;
int af; /* address family */
union nf_inet_addr addr; /* destination IP address */
struct ip_vs_dest_set set; /* destination server set */
unsigned long lastuse; /* last used time */
+ struct rcu_head rcu_head;
};
@@ -274,12 +273,14 @@ struct ip_vs_lblcr_entry {
* IPVS lblcr hash table
*/
struct ip_vs_lblcr_table {
- struct list_head bucket[IP_VS_LBLCR_TAB_SIZE]; /* hash bucket */
+ struct rcu_head rcu_head;
+ struct hlist_head bucket[IP_VS_LBLCR_TAB_SIZE]; /* hash bucket */
atomic_t entries; /* number of entries */
int max_size; /* maximum size of entries */
struct timer_list periodic_timer; /* collect stale entries */
int rover; /* rover for expire check */
int counter; /* counter for no expire */
+ bool dead;
};
@@ -288,7 +289,7 @@ struct ip_vs_lblcr_table {
* IPVS LBLCR sysctl table
*/
-static ctl_table vs_vars_table[] = {
+static struct ctl_table vs_vars_table[] = {
{
.procname = "lblcr_expiration",
.data = NULL,
@@ -302,9 +303,9 @@ static ctl_table vs_vars_table[] = {
static inline void ip_vs_lblcr_free(struct ip_vs_lblcr_entry *en)
{
- list_del(&en->list);
+ hlist_del_rcu(&en->list);
ip_vs_dest_set_eraseall(&en->set);
- kfree(en);
+ kfree_rcu(en, rcu_head);
}
@@ -334,15 +335,12 @@ ip_vs_lblcr_hash(struct ip_vs_lblcr_table *tbl, struct ip_vs_lblcr_entry *en)
{
unsigned int hash = ip_vs_lblcr_hashkey(en->af, &en->addr);
- list_add(&en->list, &tbl->bucket[hash]);
+ hlist_add_head_rcu(&en->list, &tbl->bucket[hash]);
atomic_inc(&tbl->entries);
}
-/*
- * Get ip_vs_lblcr_entry associated with supplied parameters. Called under
- * read lock.
- */
+/* Get ip_vs_lblcr_entry associated with supplied parameters. */
static inline struct ip_vs_lblcr_entry *
ip_vs_lblcr_get(int af, struct ip_vs_lblcr_table *tbl,
const union nf_inet_addr *addr)
@@ -350,7 +348,7 @@ ip_vs_lblcr_get(int af, struct ip_vs_lblcr_table *tbl,
unsigned int hash = ip_vs_lblcr_hashkey(af, addr);
struct ip_vs_lblcr_entry *en;
- list_for_each_entry(en, &tbl->bucket[hash], list)
+ hlist_for_each_entry_rcu(en, &tbl->bucket[hash], list)
if (ip_vs_addr_equal(af, &en->addr, addr))
return en;
@@ -360,7 +358,7 @@ ip_vs_lblcr_get(int af, struct ip_vs_lblcr_table *tbl,
/*
* Create or update an ip_vs_lblcr_entry, which is a mapping of a destination
- * IP address to a server. Called under write lock.
+ * IP address to a server. Called under spin lock.
*/
static inline struct ip_vs_lblcr_entry *
ip_vs_lblcr_new(struct ip_vs_lblcr_table *tbl, const union nf_inet_addr *daddr,
@@ -381,14 +379,14 @@ ip_vs_lblcr_new(struct ip_vs_lblcr_table *tbl, const union nf_inet_addr *daddr,
/* initialize its dest set */
atomic_set(&(en->set.size), 0);
INIT_LIST_HEAD(&en->set.list);
- rwlock_init(&en->set.lock);
+
+ ip_vs_dest_set_insert(&en->set, dest, false);
ip_vs_lblcr_hash(tbl, en);
+ return en;
}
- write_lock(&en->set.lock);
- ip_vs_dest_set_insert(&en->set, dest);
- write_unlock(&en->set.lock);
+ ip_vs_dest_set_insert(&en->set, dest, true);
return en;
}
@@ -397,17 +395,21 @@ ip_vs_lblcr_new(struct ip_vs_lblcr_table *tbl, const union nf_inet_addr *daddr,
/*
* Flush all the entries of the specified table.
*/
-static void ip_vs_lblcr_flush(struct ip_vs_lblcr_table *tbl)
+static void ip_vs_lblcr_flush(struct ip_vs_service *svc)
{
+ struct ip_vs_lblcr_table *tbl = svc->sched_data;
int i;
- struct ip_vs_lblcr_entry *en, *nxt;
+ struct ip_vs_lblcr_entry *en;
+ struct hlist_node *next;
- /* No locking required, only called during cleanup. */
- for (i=0; i<IP_VS_LBLCR_TAB_SIZE; i++) {
- list_for_each_entry_safe(en, nxt, &tbl->bucket[i], list) {
+ spin_lock_bh(&svc->sched_lock);
+ tbl->dead = 1;
+ for (i = 0; i < IP_VS_LBLCR_TAB_SIZE; i++) {
+ hlist_for_each_entry_safe(en, next, &tbl->bucket[i], list) {
ip_vs_lblcr_free(en);
}
}
+ spin_unlock_bh(&svc->sched_lock);
}
static int sysctl_lblcr_expiration(struct ip_vs_service *svc)
@@ -425,13 +427,14 @@ static inline void ip_vs_lblcr_full_check(struct ip_vs_service *svc)
struct ip_vs_lblcr_table *tbl = svc->sched_data;
unsigned long now = jiffies;
int i, j;
- struct ip_vs_lblcr_entry *en, *nxt;
+ struct ip_vs_lblcr_entry *en;
+ struct hlist_node *next;
- for (i=0, j=tbl->rover; i<IP_VS_LBLCR_TAB_SIZE; i++) {
+ for (i = 0, j = tbl->rover; i < IP_VS_LBLCR_TAB_SIZE; i++) {
j = (j + 1) & IP_VS_LBLCR_TAB_MASK;
- write_lock(&svc->sched_lock);
- list_for_each_entry_safe(en, nxt, &tbl->bucket[j], list) {
+ spin_lock(&svc->sched_lock);
+ hlist_for_each_entry_safe(en, next, &tbl->bucket[j], list) {
if (time_after(en->lastuse +
sysctl_lblcr_expiration(svc), now))
continue;
@@ -439,7 +442,7 @@ static inline void ip_vs_lblcr_full_check(struct ip_vs_service *svc)
ip_vs_lblcr_free(en);
atomic_dec(&tbl->entries);
}
- write_unlock(&svc->sched_lock);
+ spin_unlock(&svc->sched_lock);
}
tbl->rover = j;
}
@@ -463,7 +466,8 @@ static void ip_vs_lblcr_check_expire(unsigned long data)
unsigned long now = jiffies;
int goal;
int i, j;
- struct ip_vs_lblcr_entry *en, *nxt;
+ struct ip_vs_lblcr_entry *en;
+ struct hlist_node *next;
if ((tbl->counter % COUNT_FOR_FULL_EXPIRATION) == 0) {
/* do full expiration check */
@@ -481,11 +485,11 @@ static void ip_vs_lblcr_check_expire(unsigned long data)
if (goal > tbl->max_size/2)
goal = tbl->max_size/2;
- for (i=0, j=tbl->rover; i<IP_VS_LBLCR_TAB_SIZE; i++) {
+ for (i = 0, j = tbl->rover; i < IP_VS_LBLCR_TAB_SIZE; i++) {
j = (j + 1) & IP_VS_LBLCR_TAB_MASK;
- write_lock(&svc->sched_lock);
- list_for_each_entry_safe(en, nxt, &tbl->bucket[j], list) {
+ spin_lock(&svc->sched_lock);
+ hlist_for_each_entry_safe(en, next, &tbl->bucket[j], list) {
if (time_before(now, en->lastuse+ENTRY_TIMEOUT))
continue;
@@ -493,7 +497,7 @@ static void ip_vs_lblcr_check_expire(unsigned long data)
atomic_dec(&tbl->entries);
goal--;
}
- write_unlock(&svc->sched_lock);
+ spin_unlock(&svc->sched_lock);
if (goal <= 0)
break;
}
@@ -522,12 +526,13 @@ static int ip_vs_lblcr_init_svc(struct ip_vs_service *svc)
/*
* Initialize the hash buckets
*/
- for (i=0; i<IP_VS_LBLCR_TAB_SIZE; i++) {
- INIT_LIST_HEAD(&tbl->bucket[i]);
+ for (i = 0; i < IP_VS_LBLCR_TAB_SIZE; i++) {
+ INIT_HLIST_HEAD(&tbl->bucket[i]);
}
tbl->max_size = IP_VS_LBLCR_TAB_SIZE*16;
tbl->rover = 0;
tbl->counter = 1;
+ tbl->dead = 0;
/*
* Hook periodic timer for garbage collection
@@ -540,7 +545,7 @@ static int ip_vs_lblcr_init_svc(struct ip_vs_service *svc)
}
-static int ip_vs_lblcr_done_svc(struct ip_vs_service *svc)
+static void ip_vs_lblcr_done_svc(struct ip_vs_service *svc)
{
struct ip_vs_lblcr_table *tbl = svc->sched_data;
@@ -548,14 +553,12 @@ static int ip_vs_lblcr_done_svc(struct ip_vs_service *svc)
del_timer_sync(&tbl->periodic_timer);
/* got to clean up table entries here */
- ip_vs_lblcr_flush(tbl);
+ ip_vs_lblcr_flush(svc);
/* release the table itself */
- kfree(tbl);
+ kfree_rcu(tbl, rcu_head);
IP_VS_DBG(6, "LBLCR hash table (memory=%Zdbytes) released\n",
sizeof(*tbl));
-
- return 0;
}
@@ -577,7 +580,7 @@ __ip_vs_lblcr_schedule(struct ip_vs_service *svc)
* The server with weight=0 is quiesced and will not receive any
* new connection.
*/
- list_for_each_entry(dest, &svc->destinations, n_list) {
+ list_for_each_entry_rcu(dest, &svc->destinations, n_list) {
if (dest->flags & IP_VS_DEST_F_OVERLOAD)
continue;
@@ -593,13 +596,13 @@ __ip_vs_lblcr_schedule(struct ip_vs_service *svc)
* Find the destination with the least load.
*/
nextstage:
- list_for_each_entry_continue(dest, &svc->destinations, n_list) {
+ list_for_each_entry_continue_rcu(dest, &svc->destinations, n_list) {
if (dest->flags & IP_VS_DEST_F_OVERLOAD)
continue;
doh = ip_vs_dest_conn_overhead(dest);
- if (loh * atomic_read(&dest->weight) >
- doh * atomic_read(&least->weight)) {
+ if ((__s64)loh * atomic_read(&dest->weight) >
+ (__s64)doh * atomic_read(&least->weight)) {
least = dest;
loh = doh;
}
@@ -627,7 +630,7 @@ is_overloaded(struct ip_vs_dest *dest, struct ip_vs_service *svc)
if (atomic_read(&dest->activeconns) > atomic_read(&dest->weight)) {
struct ip_vs_dest *d;
- list_for_each_entry(d, &svc->destinations, n_list) {
+ list_for_each_entry_rcu(d, &svc->destinations, n_list) {
if (atomic_read(&d->activeconns)*2
< atomic_read(&d->weight)) {
return 1;
@@ -642,65 +645,56 @@ is_overloaded(struct ip_vs_dest *dest, struct ip_vs_service *svc)
* Locality-Based (weighted) Least-Connection scheduling
*/
static struct ip_vs_dest *
-ip_vs_lblcr_schedule(struct ip_vs_service *svc, const struct sk_buff *skb)
+ip_vs_lblcr_schedule(struct ip_vs_service *svc, const struct sk_buff *skb,
+ struct ip_vs_iphdr *iph)
{
struct ip_vs_lblcr_table *tbl = svc->sched_data;
- struct ip_vs_iphdr iph;
- struct ip_vs_dest *dest = NULL;
+ struct ip_vs_dest *dest;
struct ip_vs_lblcr_entry *en;
- ip_vs_fill_iph_addr_only(svc->af, skb, &iph);
-
IP_VS_DBG(6, "%s(): Scheduling...\n", __func__);
/* First look in our cache */
- read_lock(&svc->sched_lock);
- en = ip_vs_lblcr_get(svc->af, tbl, &iph.daddr);
+ en = ip_vs_lblcr_get(svc->af, tbl, &iph->daddr);
if (en) {
- /* We only hold a read lock, but this is atomic */
en->lastuse = jiffies;
/* Get the least loaded destination */
- read_lock(&en->set.lock);
dest = ip_vs_dest_set_min(&en->set);
- read_unlock(&en->set.lock);
/* More than one destination + enough time passed by, cleanup */
if (atomic_read(&en->set.size) > 1 &&
- time_after(jiffies, en->set.lastmod +
+ time_after(jiffies, en->set.lastmod +
sysctl_lblcr_expiration(svc))) {
- struct ip_vs_dest *m;
+ spin_lock_bh(&svc->sched_lock);
+ if (atomic_read(&en->set.size) > 1) {
+ struct ip_vs_dest *m;
- write_lock(&en->set.lock);
- m = ip_vs_dest_set_max(&en->set);
- if (m)
- ip_vs_dest_set_erase(&en->set, m);
- write_unlock(&en->set.lock);
+ m = ip_vs_dest_set_max(&en->set);
+ if (m)
+ ip_vs_dest_set_erase(&en->set, m);
+ }
+ spin_unlock_bh(&svc->sched_lock);
}
/* If the destination is not overloaded, use it */
- if (dest && !is_overloaded(dest, svc)) {
- read_unlock(&svc->sched_lock);
+ if (dest && !is_overloaded(dest, svc))
goto out;
- }
/* The cache entry is invalid, time to schedule */
dest = __ip_vs_lblcr_schedule(svc);
if (!dest) {
ip_vs_scheduler_err(svc, "no destination available");
- read_unlock(&svc->sched_lock);
return NULL;
}
/* Update our cache entry */
- write_lock(&en->set.lock);
- ip_vs_dest_set_insert(&en->set, dest);
- write_unlock(&en->set.lock);
- }
- read_unlock(&svc->sched_lock);
-
- if (dest)
+ spin_lock_bh(&svc->sched_lock);
+ if (!tbl->dead)
+ ip_vs_dest_set_insert(&en->set, dest, true);
+ spin_unlock_bh(&svc->sched_lock);
goto out;
+ }
/* No cache entry, time to schedule */
dest = __ip_vs_lblcr_schedule(svc);
@@ -710,13 +704,14 @@ ip_vs_lblcr_schedule(struct ip_vs_service *svc, const struct sk_buff *skb)
}
/* If we fail to create a cache entry, we'll just use the valid dest */
- write_lock(&svc->sched_lock);
- ip_vs_lblcr_new(tbl, &iph.daddr, dest);
- write_unlock(&svc->sched_lock);
+ spin_lock_bh(&svc->sched_lock);
+ if (!tbl->dead)
+ ip_vs_lblcr_new(tbl, &iph->daddr, dest);
+ spin_unlock_bh(&svc->sched_lock);
out:
IP_VS_DBG_BUF(6, "LBLCR: destination IP address %s --> server %s:%d\n",
- IP_VS_DBG_ADDR(svc->af, &iph.daddr),
+ IP_VS_DBG_ADDR(svc->af, &iph->daddr),
IP_VS_DBG_ADDR(svc->af, &dest->addr), ntohs(dest->port));
return dest;
@@ -814,6 +809,7 @@ static void __exit ip_vs_lblcr_cleanup(void)
{
unregister_ip_vs_scheduler(&ip_vs_lblcr_scheduler);
unregister_pernet_subsys(&ip_vs_lblcr_ops);
+ rcu_barrier();
}
diff --git a/net/netfilter/ipvs/ip_vs_lc.c b/net/netfilter/ipvs/ip_vs_lc.c
index f391819c0cc..2bdcb1cf212 100644
--- a/net/netfilter/ipvs/ip_vs_lc.c
+++ b/net/netfilter/ipvs/ip_vs_lc.c
@@ -26,7 +26,8 @@
* Least Connection scheduling
*/
static struct ip_vs_dest *
-ip_vs_lc_schedule(struct ip_vs_service *svc, const struct sk_buff *skb)
+ip_vs_lc_schedule(struct ip_vs_service *svc, const struct sk_buff *skb,
+ struct ip_vs_iphdr *iph)
{
struct ip_vs_dest *dest, *least = NULL;
unsigned int loh = 0, doh;
@@ -42,7 +43,7 @@ ip_vs_lc_schedule(struct ip_vs_service *svc, const struct sk_buff *skb)
* served, but no new connection is assigned to the server.
*/
- list_for_each_entry(dest, &svc->destinations, n_list) {
+ list_for_each_entry_rcu(dest, &svc->destinations, n_list) {
if ((dest->flags & IP_VS_DEST_F_OVERLOAD) ||
atomic_read(&dest->weight) == 0)
continue;
@@ -84,6 +85,7 @@ static int __init ip_vs_lc_init(void)
static void __exit ip_vs_lc_cleanup(void)
{
unregister_ip_vs_scheduler(&ip_vs_lc_scheduler);
+ synchronize_rcu();
}
module_init(ip_vs_lc_init);
diff --git a/net/netfilter/ipvs/ip_vs_nfct.c b/net/netfilter/ipvs/ip_vs_nfct.c
index c8beafd401a..5882bbfd198 100644
--- a/net/netfilter/ipvs/ip_vs_nfct.c
+++ b/net/netfilter/ipvs/ip_vs_nfct.c
@@ -19,8 +19,7 @@
* GNU General Public License for more details.
*
* You should have received a copy of the GNU General Public License
- * along with this program; if not, write to the Free Software
- * Foundation, Inc., 59 Temple Place, Suite 330, Boston, MA 02111-1307 USA
+ * along with this program; if not, see <http://www.gnu.org/licenses/>.
*
*
* Authors:
@@ -63,6 +62,7 @@
#include <net/ip_vs.h>
#include <net/netfilter/nf_conntrack_core.h>
#include <net/netfilter/nf_conntrack_expect.h>
+#include <net/netfilter/nf_conntrack_seqadj.h>
#include <net/netfilter/nf_conntrack_helper.h>
#include <net/netfilter/nf_conntrack_zones.h>
@@ -97,6 +97,11 @@ ip_vs_update_conntrack(struct sk_buff *skb, struct ip_vs_conn *cp, int outin)
if (CTINFO2DIR(ctinfo) != IP_CT_DIR_ORIGINAL)
return;
+ /* Applications may adjust TCP seqs */
+ if (cp->app && nf_ct_protonum(ct) == IPPROTO_TCP &&
+ !nfct_seqadj(ct) && !nfct_seqadj_ext_add(ct))
+ return;
+
/*
* The connection is not yet in the hashtable, so we update it.
* CIP->VIP will remain the same, so leave the tuple in
diff --git a/net/netfilter/ipvs/ip_vs_nq.c b/net/netfilter/ipvs/ip_vs_nq.c
index 984d9c137d8..961a6de9bb2 100644
--- a/net/netfilter/ipvs/ip_vs_nq.c
+++ b/net/netfilter/ipvs/ip_vs_nq.c
@@ -40,7 +40,7 @@
#include <net/ip_vs.h>
-static inline unsigned int
+static inline int
ip_vs_nq_dest_overhead(struct ip_vs_dest *dest)
{
/*
@@ -55,10 +55,11 @@ ip_vs_nq_dest_overhead(struct ip_vs_dest *dest)
* Weighted Least Connection scheduling
*/
static struct ip_vs_dest *
-ip_vs_nq_schedule(struct ip_vs_service *svc, const struct sk_buff *skb)
+ip_vs_nq_schedule(struct ip_vs_service *svc, const struct sk_buff *skb,
+ struct ip_vs_iphdr *iph)
{
struct ip_vs_dest *dest, *least = NULL;
- unsigned int loh = 0, doh;
+ int loh = 0, doh;
IP_VS_DBG(6, "%s(): Scheduling...\n", __func__);
@@ -75,7 +76,7 @@ ip_vs_nq_schedule(struct ip_vs_service *svc, const struct sk_buff *skb)
* new connections.
*/
- list_for_each_entry(dest, &svc->destinations, n_list) {
+ list_for_each_entry_rcu(dest, &svc->destinations, n_list) {
if (dest->flags & IP_VS_DEST_F_OVERLOAD ||
!atomic_read(&dest->weight))
@@ -91,8 +92,8 @@ ip_vs_nq_schedule(struct ip_vs_service *svc, const struct sk_buff *skb)
}
if (!least ||
- (loh * atomic_read(&dest->weight) >
- doh * atomic_read(&least->weight))) {
+ ((__s64)loh * atomic_read(&dest->weight) >
+ (__s64)doh * atomic_read(&least->weight))) {
least = dest;
loh = doh;
}
@@ -133,6 +134,7 @@ static int __init ip_vs_nq_init(void)
static void __exit ip_vs_nq_cleanup(void)
{
unregister_ip_vs_scheduler(&ip_vs_nq_scheduler);
+ synchronize_rcu();
}
module_init(ip_vs_nq_init);
diff --git a/net/netfilter/ipvs/ip_vs_pe.c b/net/netfilter/ipvs/ip_vs_pe.c
index 5cf859ccb31..1a82b29ce8e 100644
--- a/net/netfilter/ipvs/ip_vs_pe.c
+++ b/net/netfilter/ipvs/ip_vs_pe.c
@@ -13,20 +13,8 @@
/* IPVS pe list */
static LIST_HEAD(ip_vs_pe);
-/* lock for service table */
-static DEFINE_SPINLOCK(ip_vs_pe_lock);
-
-/* Bind a service with a pe */
-void ip_vs_bind_pe(struct ip_vs_service *svc, struct ip_vs_pe *pe)
-{
- svc->pe = pe;
-}
-
-/* Unbind a service from its pe */
-void ip_vs_unbind_pe(struct ip_vs_service *svc)
-{
- svc->pe = NULL;
-}
+/* semaphore for IPVS PEs. */
+static DEFINE_MUTEX(ip_vs_pe_mutex);
/* Get pe in the pe list by name */
struct ip_vs_pe *__ip_vs_pe_getbyname(const char *pe_name)
@@ -36,9 +24,8 @@ struct ip_vs_pe *__ip_vs_pe_getbyname(const char *pe_name)
IP_VS_DBG(10, "%s(): pe_name \"%s\"\n", __func__,
pe_name);
- spin_lock_bh(&ip_vs_pe_lock);
-
- list_for_each_entry(pe, &ip_vs_pe, n_list) {
+ rcu_read_lock();
+ list_for_each_entry_rcu(pe, &ip_vs_pe, n_list) {
/* Test and get the modules atomically */
if (pe->module &&
!try_module_get(pe->module)) {
@@ -47,14 +34,14 @@ struct ip_vs_pe *__ip_vs_pe_getbyname(const char *pe_name)
}
if (strcmp(pe_name, pe->name)==0) {
/* HIT */
- spin_unlock_bh(&ip_vs_pe_lock);
+ rcu_read_unlock();
return pe;
}
if (pe->module)
module_put(pe->module);
}
+ rcu_read_unlock();
- spin_unlock_bh(&ip_vs_pe_lock);
return NULL;
}
@@ -83,22 +70,13 @@ int register_ip_vs_pe(struct ip_vs_pe *pe)
/* increase the module use count */
ip_vs_use_count_inc();
- spin_lock_bh(&ip_vs_pe_lock);
-
- if (!list_empty(&pe->n_list)) {
- spin_unlock_bh(&ip_vs_pe_lock);
- ip_vs_use_count_dec();
- pr_err("%s(): [%s] pe already linked\n",
- __func__, pe->name);
- return -EINVAL;
- }
-
+ mutex_lock(&ip_vs_pe_mutex);
/* Make sure that the pe with this name doesn't exist
* in the pe list.
*/
list_for_each_entry(tmp, &ip_vs_pe, n_list) {
if (strcmp(tmp->name, pe->name) == 0) {
- spin_unlock_bh(&ip_vs_pe_lock);
+ mutex_unlock(&ip_vs_pe_mutex);
ip_vs_use_count_dec();
pr_err("%s(): [%s] pe already existed "
"in the system\n", __func__, pe->name);
@@ -106,8 +84,8 @@ int register_ip_vs_pe(struct ip_vs_pe *pe)
}
}
/* Add it into the d-linked pe list */
- list_add(&pe->n_list, &ip_vs_pe);
- spin_unlock_bh(&ip_vs_pe_lock);
+ list_add_rcu(&pe->n_list, &ip_vs_pe);
+ mutex_unlock(&ip_vs_pe_mutex);
pr_info("[%s] pe registered.\n", pe->name);
@@ -118,17 +96,10 @@ EXPORT_SYMBOL_GPL(register_ip_vs_pe);
/* Unregister a pe from the pe list */
int unregister_ip_vs_pe(struct ip_vs_pe *pe)
{
- spin_lock_bh(&ip_vs_pe_lock);
- if (list_empty(&pe->n_list)) {
- spin_unlock_bh(&ip_vs_pe_lock);
- pr_err("%s(): [%s] pe is not in the list. failed\n",
- __func__, pe->name);
- return -EINVAL;
- }
-
+ mutex_lock(&ip_vs_pe_mutex);
/* Remove it from the d-linked pe list */
- list_del(&pe->n_list);
- spin_unlock_bh(&ip_vs_pe_lock);
+ list_del_rcu(&pe->n_list);
+ mutex_unlock(&ip_vs_pe_mutex);
/* decrease the module use count */
ip_vs_use_count_dec();
diff --git a/net/netfilter/ipvs/ip_vs_pe_sip.c b/net/netfilter/ipvs/ip_vs_pe_sip.c
index 12475ef88da..bed5f704252 100644
--- a/net/netfilter/ipvs/ip_vs_pe_sip.c
+++ b/net/netfilter/ipvs/ip_vs_pe_sip.c
@@ -13,7 +13,8 @@ static const char *ip_vs_dbg_callid(char *buf, size_t buf_len,
const char *callid, size_t callid_len,
int *idx)
{
- size_t len = min(min(callid_len, (size_t)64), buf_len - *idx - 1);
+ size_t max_len = 64;
+ size_t len = min3(max_len, callid_len, buf_len - *idx - 1);
memcpy(buf + *idx, callid, len);
buf[*idx+len] = '\0';
*idx += len + 1;
@@ -37,14 +38,10 @@ static int get_callid(const char *dptr, unsigned int dataoff,
if (ret > 0)
break;
if (!ret)
- return 0;
+ return -EINVAL;
dataoff += *matchoff;
}
- /* Empty callid is useless */
- if (!*matchlen)
- return -EINVAL;
-
/* Too large is useless */
if (*matchlen > IP_VS_PEDATA_MAXLEN)
return -EINVAL;
@@ -68,7 +65,6 @@ static int get_callid(const char *dptr, unsigned int dataoff,
static int
ip_vs_sip_fill_param(struct ip_vs_conn_param *p, struct sk_buff *skb)
{
- struct sk_buff *reasm = skb_nfct_reasm(skb);
struct ip_vs_iphdr iph;
unsigned int dataoff, datalen, matchoff, matchlen;
const char *dptr;
@@ -82,15 +78,10 @@ ip_vs_sip_fill_param(struct ip_vs_conn_param *p, struct sk_buff *skb)
/* todo: IPv6 fragments:
* I think this only should be done for the first fragment. /HS
*/
- if (reasm) {
- skb = reasm;
- dataoff = iph.thoff_reasm + sizeof(struct udphdr);
- } else
- dataoff = iph.len + sizeof(struct udphdr);
+ dataoff = iph.len + sizeof(struct udphdr);
if (dataoff >= skb->len)
return -EINVAL;
- /* todo: Check if this will mess-up the reasm skb !!! /HS */
retc = skb_linearize(skb);
if (retc < 0)
return retc;
@@ -172,6 +163,7 @@ static int __init ip_vs_sip_init(void)
static void __exit ip_vs_sip_cleanup(void)
{
unregister_ip_vs_pe(&ip_vs_sip_pe);
+ synchronize_rcu();
}
module_init(ip_vs_sip_init);
diff --git a/net/netfilter/ipvs/ip_vs_proto_sctp.c b/net/netfilter/ipvs/ip_vs_proto_sctp.c
index 746048b13ef..2f7ea756404 100644
--- a/net/netfilter/ipvs/ip_vs_proto_sctp.c
+++ b/net/netfilter/ipvs/ip_vs_proto_sctp.c
@@ -15,29 +15,37 @@ sctp_conn_schedule(int af, struct sk_buff *skb, struct ip_vs_proto_data *pd,
{
struct net *net;
struct ip_vs_service *svc;
+ struct netns_ipvs *ipvs;
sctp_chunkhdr_t _schunkh, *sch;
sctp_sctphdr_t *sh, _sctph;
sh = skb_header_pointer(skb, iph->len, sizeof(_sctph), &_sctph);
- if (sh == NULL)
+ if (sh == NULL) {
+ *verdict = NF_DROP;
return 0;
+ }
sch = skb_header_pointer(skb, iph->len + sizeof(sctp_sctphdr_t),
sizeof(_schunkh), &_schunkh);
- if (sch == NULL)
+ if (sch == NULL) {
+ *verdict = NF_DROP;
return 0;
+ }
+
net = skb_net(skb);
- if ((sch->type == SCTP_CID_INIT) &&
- (svc = ip_vs_service_get(net, af, skb->mark, iph->protocol,
- &iph->daddr, sh->dest))) {
+ ipvs = net_ipvs(net);
+ rcu_read_lock();
+ if ((sch->type == SCTP_CID_INIT || sysctl_sloppy_sctp(ipvs)) &&
+ (svc = ip_vs_service_find(net, af, skb->mark, iph->protocol,
+ &iph->daddr, sh->dest))) {
int ignored;
- if (ip_vs_todrop(net_ipvs(net))) {
+ if (ip_vs_todrop(ipvs)) {
/*
* It seems that we are very loaded.
* We have to drop this packet :(
*/
- ip_vs_service_put(svc);
+ rcu_read_unlock();
*verdict = NF_DROP;
return 0;
}
@@ -49,26 +57,31 @@ sctp_conn_schedule(int af, struct sk_buff *skb, struct ip_vs_proto_data *pd,
if (!*cpp && ignored <= 0) {
if (!ignored)
*verdict = ip_vs_leave(svc, skb, pd, iph);
- else {
- ip_vs_service_put(svc);
+ else
*verdict = NF_DROP;
- }
+ rcu_read_unlock();
return 0;
}
- ip_vs_service_put(svc);
}
+ rcu_read_unlock();
/* NF_ACCEPT */
return 1;
}
+static void sctp_nat_csum(struct sk_buff *skb, sctp_sctphdr_t *sctph,
+ unsigned int sctphoff)
+{
+ sctph->checksum = sctp_compute_cksum(skb, sctphoff);
+ skb->ip_summed = CHECKSUM_UNNECESSARY;
+}
+
static int
sctp_snat_handler(struct sk_buff *skb, struct ip_vs_protocol *pp,
struct ip_vs_conn *cp, struct ip_vs_iphdr *iph)
{
sctp_sctphdr_t *sctph;
unsigned int sctphoff = iph->len;
- struct sk_buff *iter;
- __be32 crc32;
+ bool payload_csum = false;
#ifdef CONFIG_IP_VS_IPV6
if (cp->af == AF_INET6 && iph->fragoffs)
@@ -80,25 +93,31 @@ sctp_snat_handler(struct sk_buff *skb, struct ip_vs_protocol *pp,
return 0;
if (unlikely(cp->app != NULL)) {
+ int ret;
+
/* Some checks before mangling */
if (pp->csum_check && !pp->csum_check(cp->af, skb, pp))
return 0;
/* Call application helper if needed */
- if (!ip_vs_app_pkt_out(cp, skb))
+ ret = ip_vs_app_pkt_out(cp, skb);
+ if (ret == 0)
return 0;
+ /* ret=2: csum update is needed after payload mangling */
+ if (ret == 2)
+ payload_csum = true;
}
sctph = (void *) skb_network_header(skb) + sctphoff;
- sctph->source = cp->vport;
- /* Calculate the checksum */
- crc32 = sctp_start_cksum((u8 *) sctph, skb_headlen(skb) - sctphoff);
- skb_walk_frags(skb, iter)
- crc32 = sctp_update_cksum((u8 *) iter->data, skb_headlen(iter),
- crc32);
- crc32 = sctp_end_cksum(crc32);
- sctph->checksum = crc32;
+ /* Only update csum if we really have to */
+ if (sctph->source != cp->vport || payload_csum ||
+ skb->ip_summed == CHECKSUM_PARTIAL) {
+ sctph->source = cp->vport;
+ sctp_nat_csum(skb, sctph, sctphoff);
+ } else {
+ skb->ip_summed = CHECKSUM_UNNECESSARY;
+ }
return 1;
}
@@ -109,8 +128,7 @@ sctp_dnat_handler(struct sk_buff *skb, struct ip_vs_protocol *pp,
{
sctp_sctphdr_t *sctph;
unsigned int sctphoff = iph->len;
- struct sk_buff *iter;
- __be32 crc32;
+ bool payload_csum = false;
#ifdef CONFIG_IP_VS_IPV6
if (cp->af == AF_INET6 && iph->fragoffs)
@@ -122,25 +140,32 @@ sctp_dnat_handler(struct sk_buff *skb, struct ip_vs_protocol *pp,
return 0;
if (unlikely(cp->app != NULL)) {
+ int ret;
+
/* Some checks before mangling */
if (pp->csum_check && !pp->csum_check(cp->af, skb, pp))
return 0;
/* Call application helper if needed */
- if (!ip_vs_app_pkt_in(cp, skb))
+ ret = ip_vs_app_pkt_in(cp, skb);
+ if (ret == 0)
return 0;
+ /* ret=2: csum update is needed after payload mangling */
+ if (ret == 2)
+ payload_csum = true;
}
sctph = (void *) skb_network_header(skb) + sctphoff;
- sctph->dest = cp->dport;
- /* Calculate the checksum */
- crc32 = sctp_start_cksum((u8 *) sctph, skb_headlen(skb) - sctphoff);
- skb_walk_frags(skb, iter)
- crc32 = sctp_update_cksum((u8 *) iter->data, skb_headlen(iter),
- crc32);
- crc32 = sctp_end_cksum(crc32);
- sctph->checksum = crc32;
+ /* Only update csum if we really have to */
+ if (sctph->dest != cp->dport || payload_csum ||
+ (skb->ip_summed == CHECKSUM_PARTIAL &&
+ !(skb_dst(skb)->dev->features & NETIF_F_SCTP_CSUM))) {
+ sctph->dest = cp->dport;
+ sctp_nat_csum(skb, sctph, sctphoff);
+ } else if (skb->ip_summed != CHECKSUM_PARTIAL) {
+ skb->ip_summed = CHECKSUM_UNNECESSARY;
+ }
return 1;
}
@@ -150,10 +175,7 @@ sctp_csum_check(int af, struct sk_buff *skb, struct ip_vs_protocol *pp)
{
unsigned int sctphoff;
struct sctphdr *sh, _sctph;
- struct sk_buff *iter;
- __le32 cmp;
- __le32 val;
- __u32 tmp;
+ __le32 cmp, val;
#ifdef CONFIG_IP_VS_IPV6
if (af == AF_INET6)
@@ -167,13 +189,7 @@ sctp_csum_check(int af, struct sk_buff *skb, struct ip_vs_protocol *pp)
return 0;
cmp = sh->checksum;
-
- tmp = sctp_start_cksum((__u8 *) sh, skb_headlen(skb));
- skb_walk_frags(skb, iter)
- tmp = sctp_update_cksum((__u8 *) iter->data,
- skb_headlen(iter), tmp);
-
- val = sctp_end_cksum(tmp);
+ val = sctp_compute_cksum(skb, sctphoff);
if (val != cmp) {
/* CRC failure, dump it. */
@@ -184,710 +200,159 @@ sctp_csum_check(int af, struct sk_buff *skb, struct ip_vs_protocol *pp)
return 1;
}
-struct ipvs_sctp_nextstate {
- int next_state;
-};
enum ipvs_sctp_event_t {
- IP_VS_SCTP_EVE_DATA_CLI,
- IP_VS_SCTP_EVE_DATA_SER,
- IP_VS_SCTP_EVE_INIT_CLI,
- IP_VS_SCTP_EVE_INIT_SER,
- IP_VS_SCTP_EVE_INIT_ACK_CLI,
- IP_VS_SCTP_EVE_INIT_ACK_SER,
- IP_VS_SCTP_EVE_COOKIE_ECHO_CLI,
- IP_VS_SCTP_EVE_COOKIE_ECHO_SER,
- IP_VS_SCTP_EVE_COOKIE_ACK_CLI,
- IP_VS_SCTP_EVE_COOKIE_ACK_SER,
- IP_VS_SCTP_EVE_ABORT_CLI,
- IP_VS_SCTP_EVE__ABORT_SER,
- IP_VS_SCTP_EVE_SHUT_CLI,
- IP_VS_SCTP_EVE_SHUT_SER,
- IP_VS_SCTP_EVE_SHUT_ACK_CLI,
- IP_VS_SCTP_EVE_SHUT_ACK_SER,
- IP_VS_SCTP_EVE_SHUT_COM_CLI,
- IP_VS_SCTP_EVE_SHUT_COM_SER,
- IP_VS_SCTP_EVE_LAST
+ IP_VS_SCTP_DATA = 0, /* DATA, SACK, HEARTBEATs */
+ IP_VS_SCTP_INIT,
+ IP_VS_SCTP_INIT_ACK,
+ IP_VS_SCTP_COOKIE_ECHO,
+ IP_VS_SCTP_COOKIE_ACK,
+ IP_VS_SCTP_SHUTDOWN,
+ IP_VS_SCTP_SHUTDOWN_ACK,
+ IP_VS_SCTP_SHUTDOWN_COMPLETE,
+ IP_VS_SCTP_ERROR,
+ IP_VS_SCTP_ABORT,
+ IP_VS_SCTP_EVENT_LAST
};
-static enum ipvs_sctp_event_t sctp_events[255] = {
- IP_VS_SCTP_EVE_DATA_CLI,
- IP_VS_SCTP_EVE_INIT_CLI,
- IP_VS_SCTP_EVE_INIT_ACK_CLI,
- IP_VS_SCTP_EVE_DATA_CLI,
- IP_VS_SCTP_EVE_DATA_CLI,
- IP_VS_SCTP_EVE_DATA_CLI,
- IP_VS_SCTP_EVE_ABORT_CLI,
- IP_VS_SCTP_EVE_SHUT_CLI,
- IP_VS_SCTP_EVE_SHUT_ACK_CLI,
- IP_VS_SCTP_EVE_DATA_CLI,
- IP_VS_SCTP_EVE_COOKIE_ECHO_CLI,
- IP_VS_SCTP_EVE_COOKIE_ACK_CLI,
- IP_VS_SCTP_EVE_DATA_CLI,
- IP_VS_SCTP_EVE_DATA_CLI,
- IP_VS_SCTP_EVE_SHUT_COM_CLI,
+/* RFC 2960, 3.2 Chunk Field Descriptions */
+static __u8 sctp_events[] = {
+ [SCTP_CID_DATA] = IP_VS_SCTP_DATA,
+ [SCTP_CID_INIT] = IP_VS_SCTP_INIT,
+ [SCTP_CID_INIT_ACK] = IP_VS_SCTP_INIT_ACK,
+ [SCTP_CID_SACK] = IP_VS_SCTP_DATA,
+ [SCTP_CID_HEARTBEAT] = IP_VS_SCTP_DATA,
+ [SCTP_CID_HEARTBEAT_ACK] = IP_VS_SCTP_DATA,
+ [SCTP_CID_ABORT] = IP_VS_SCTP_ABORT,
+ [SCTP_CID_SHUTDOWN] = IP_VS_SCTP_SHUTDOWN,
+ [SCTP_CID_SHUTDOWN_ACK] = IP_VS_SCTP_SHUTDOWN_ACK,
+ [SCTP_CID_ERROR] = IP_VS_SCTP_ERROR,
+ [SCTP_CID_COOKIE_ECHO] = IP_VS_SCTP_COOKIE_ECHO,
+ [SCTP_CID_COOKIE_ACK] = IP_VS_SCTP_COOKIE_ACK,
+ [SCTP_CID_ECN_ECNE] = IP_VS_SCTP_DATA,
+ [SCTP_CID_ECN_CWR] = IP_VS_SCTP_DATA,
+ [SCTP_CID_SHUTDOWN_COMPLETE] = IP_VS_SCTP_SHUTDOWN_COMPLETE,
};
-static struct ipvs_sctp_nextstate
- sctp_states_table[IP_VS_SCTP_S_LAST][IP_VS_SCTP_EVE_LAST] = {
- /*
- * STATE : IP_VS_SCTP_S_NONE
- */
- /*next state *//*event */
- {{IP_VS_SCTP_S_CLOSED /* IP_VS_SCTP_EVE_DATA_CLI */ },
- {IP_VS_SCTP_S_CLOSED /* IP_VS_SCTP_EVE_DATA_SER */ },
- {IP_VS_SCTP_S_INIT_CLI /* IP_VS_SCTP_EVE_INIT_CLI */ },
- {IP_VS_SCTP_S_INIT_SER /* IP_VS_SCTP_EVE_INIT_SER */ },
- {IP_VS_SCTP_S_CLOSED /* IP_VS_SCTP_EVE_INIT_ACK_CLI */ },
- {IP_VS_SCTP_S_CLOSED /* IP_VS_SCTP_EVE_INIT_ACK_SER */ },
- {IP_VS_SCTP_S_CLOSED /* IP_VS_SCTP_EVE_COOKIE_ECHO_CLI */ },
- {IP_VS_SCTP_S_CLOSED /* IP_VS_SCTP_EVE_COOKIE_ECHO_SER */ },
- {IP_VS_SCTP_S_CLOSED /* IP_VS_SCTP_EVE_COOKIE_ACK_CLI */ },
- {IP_VS_SCTP_S_CLOSED /* IP_VS_SCTP_EVE_COOKIE_ACK_SER */ },
- {IP_VS_SCTP_S_CLOSED /* IP_VS_SCTP_EVE_ABORT_CLI */ },
- {IP_VS_SCTP_S_CLOSED /* IP_VS_SCTP_EVE_ABORT_SER */ },
- {IP_VS_SCTP_S_CLOSED /* IP_VS_SCTP_EVE_SHUT_CLI */ },
- {IP_VS_SCTP_S_CLOSED /* IP_VS_SCTP_EVE_SHUT_SER */ },
- {IP_VS_SCTP_S_CLOSED /* IP_VS_SCTP_EVE_SHUT_ACK_CLI */ },
- {IP_VS_SCTP_S_CLOSED /* IP_VS_SCTP_EVE_SHUT_ACK_SER */ },
- {IP_VS_SCTP_S_CLOSED /* IP_VS_SCTP_EVE_SHUT_COM_CLI */ },
- {IP_VS_SCTP_S_CLOSED /* IP_VS_SCTP_EVE_SHUT_COM_SER */ },
- },
- /*
- * STATE : IP_VS_SCTP_S_INIT_CLI
- * Cient sent INIT and is waiting for reply from server(In ECHO_WAIT)
- */
- {{IP_VS_SCTP_S_CLOSED /* IP_VS_SCTP_EVE_DATA_CLI */ },
- {IP_VS_SCTP_S_CLOSED /* IP_VS_SCTP_EVE_DATA_SER */ },
- {IP_VS_SCTP_S_INIT_CLI /* IP_VS_SCTP_EVE_INIT_CLI */ },
- {IP_VS_SCTP_S_INIT_SER /* IP_VS_SCTP_EVE_INIT_SER */ },
- {IP_VS_SCTP_S_CLOSED /* IP_VS_SCTP_EVE_INIT_ACK_CLI */ },
- {IP_VS_SCTP_S_INIT_ACK_SER /* IP_VS_SCTP_EVE_INIT_ACK_SER */ },
- {IP_VS_SCTP_S_CLOSED /* IP_VS_SCTP_EVE_ECHO_CLI */ },
- {IP_VS_SCTP_S_INIT_CLI /* IP_VS_SCTP_EVE_ECHO_SER */ },
- {IP_VS_SCTP_S_CLOSED /* IP_VS_SCTP_EVE_COOKIE_ACK_CLI */ },
- {IP_VS_SCTP_S_INIT_CLI /* IP_VS_SCTP_EVE_COOKIE_ACK_SER */ },
- {IP_VS_SCTP_S_CLOSED /* IP_VS_SCTP_EVE_ABORT_CLI */ },
- {IP_VS_SCTP_S_CLOSED /* IP_VS_SCTP_EVE_ABORT_SER */ },
- {IP_VS_SCTP_S_CLOSED /* IP_VS_SCTP_EVE_SHUT_CLI */ },
- {IP_VS_SCTP_S_CLOSED /* IP_VS_SCTP_EVE_SHUT_SER */ },
- {IP_VS_SCTP_S_CLOSED /* IP_VS_SCTP_EVE_SHUT_ACK_CLI */ },
- {IP_VS_SCTP_S_CLOSED /* IP_VS_SCTP_EVE_SHUT_ACK_SER */ },
- {IP_VS_SCTP_S_CLOSED /* IP_VS_SCTP_EVE_SHUT_COM_CLI */ },
- {IP_VS_SCTP_S_CLOSED /* IP_VS_SCTP_EVE_SHUT_COM_SER */ }
- },
- /*
- * State : IP_VS_SCTP_S_INIT_SER
- * Server sent INIT and waiting for INIT ACK from the client
- */
- {{IP_VS_SCTP_S_CLOSED /* IP_VS_SCTP_EVE_DATA_CLI */ },
- {IP_VS_SCTP_S_CLOSED /* IP_VS_SCTP_EVE_DATA_SER */ },
- {IP_VS_SCTP_S_INIT_CLI /* IP_VS_SCTP_EVE_INIT_CLI */ },
- {IP_VS_SCTP_S_INIT_SER /* IP_VS_SCTP_EVE_INIT_SER */ },
- {IP_VS_SCTP_S_INIT_ACK_CLI /* IP_VS_SCTP_EVE_INIT_ACK_CLI */ },
- {IP_VS_SCTP_S_CLOSED /* IP_VS_SCTP_EVE_INIT_ACK_SER */ },
- {IP_VS_SCTP_S_INIT_SER /* IP_VS_SCTP_EVE_COOKIE_ECHO_CLI */ },
- {IP_VS_SCTP_S_CLOSED /* IP_VS_SCTP_EVE_COOKIE_ECHO_SER */ },
- {IP_VS_SCTP_S_INIT_SER /* IP_VS_SCTP_EVE_COOKIE_ACK_CLI */ },
- {IP_VS_SCTP_S_CLOSED /* IP_VS_SCTP_EVE_COOKIE_ACK_SER */ },
- {IP_VS_SCTP_S_CLOSED /* IP_VS_SCTP_EVE_ABORT_CLI */ },
- {IP_VS_SCTP_S_CLOSED /* IP_VS_SCTP_EVE_ABORT_SER */ },
- {IP_VS_SCTP_S_CLOSED /* IP_VS_SCTP_EVE_SHUT_CLI */ },
- {IP_VS_SCTP_S_CLOSED /* IP_VS_SCTP_EVE_SHUT_SER */ },
- {IP_VS_SCTP_S_CLOSED /* IP_VS_SCTP_EVE_SHUT_ACK_CLI */ },
- {IP_VS_SCTP_S_CLOSED /* IP_VS_SCTP_EVE_SHUT_ACK_SER */ },
- {IP_VS_SCTP_S_CLOSED /* IP_VS_SCTP_EVE_SHUT_COM_CLI */ },
- {IP_VS_SCTP_S_CLOSED /* IP_VS_SCTP_EVE_SHUT_COM_SER */ }
- },
- /*
- * State : IP_VS_SCTP_S_INIT_ACK_CLI
- * Client sent INIT ACK and waiting for ECHO from the server
- */
- {{IP_VS_SCTP_S_CLOSED /* IP_VS_SCTP_EVE_DATA_CLI */ },
- {IP_VS_SCTP_S_CLOSED /* IP_VS_SCTP_EVE_DATA_SER */ },
- /*
- * We have got an INIT from client. From the spec.“Upon receipt of
- * an INIT in the COOKIE-WAIT state, an endpoint MUST respond with
- * an INIT ACK using the same parameters it sent in its original
- * INIT chunk (including its Initiate Tag, unchanged”).
- */
- {IP_VS_SCTP_S_INIT_CLI /* IP_VS_SCTP_EVE_INIT_CLI */ },
- {IP_VS_SCTP_S_INIT_SER /* IP_VS_SCTP_EVE_INIT_SER */ },
- /*
- * INIT_ACK has been resent by the client, let us stay is in
- * the same state
- */
- {IP_VS_SCTP_S_INIT_ACK_CLI /* IP_VS_SCTP_EVE_INIT_ACK_CLI */ },
- /*
- * INIT_ACK sent by the server, close the connection
- */
- {IP_VS_SCTP_S_CLOSED /* IP_VS_SCTP_EVE_INIT_ACK_SER */ },
- /*
- * ECHO by client, it should not happen, close the connection
- */
- {IP_VS_SCTP_S_CLOSED /* IP_VS_SCTP_EVE_COOKIE_ECHO_CLI */ },
- /*
- * ECHO by server, this is what we are expecting, move to ECHO_SER
- */
- {IP_VS_SCTP_S_ECHO_SER /* IP_VS_SCTP_EVE_COOKIE_ECHO_SER */ },
- /*
- * COOKIE ACK from client, it should not happen, close the connection
- */
- {IP_VS_SCTP_S_CLOSED /* IP_VS_SCTP_EVE_COOKIE_ACK_CLI */ },
- /*
- * Unexpected COOKIE ACK from server, staty in the same state
- */
- {IP_VS_SCTP_S_INIT_ACK_CLI /* IP_VS_SCTP_EVE_COOKIE_ACK_SER */ },
- {IP_VS_SCTP_S_CLOSED /* IP_VS_SCTP_EVE_ABORT_CLI */ },
- {IP_VS_SCTP_S_CLOSED /* IP_VS_SCTP_EVE_ABORT_SER */ },
- {IP_VS_SCTP_S_CLOSED /* IP_VS_SCTP_EVE_SHUT_CLI */ },
- {IP_VS_SCTP_S_CLOSED /* IP_VS_SCTP_EVE_SHUT_SER */ },
- {IP_VS_SCTP_S_CLOSED /* IP_VS_SCTP_EVE_SHUT_ACK_CLI */ },
- {IP_VS_SCTP_S_CLOSED /* IP_VS_SCTP_EVE_SHUT_ACK_SER */ },
- {IP_VS_SCTP_S_CLOSED /* IP_VS_SCTP_EVE_SHUT_COM_CLI */ },
- {IP_VS_SCTP_S_CLOSED /* IP_VS_SCTP_EVE_SHUT_COM_SER */ }
- },
- /*
- * State : IP_VS_SCTP_S_INIT_ACK_SER
- * Server sent INIT ACK and waiting for ECHO from the client
- */
- {{IP_VS_SCTP_S_CLOSED /* IP_VS_SCTP_EVE_DATA_CLI */ },
- {IP_VS_SCTP_S_CLOSED /* IP_VS_SCTP_EVE_DATA_SER */ },
- /*
- * We have got an INIT from client. From the spec.“Upon receipt of
- * an INIT in the COOKIE-WAIT state, an endpoint MUST respond with
- * an INIT ACK using the same parameters it sent in its original
- * INIT chunk (including its Initiate Tag, unchanged”).
- */
- {IP_VS_SCTP_S_INIT_CLI /* IP_VS_SCTP_EVE_INIT_CLI */ },
- {IP_VS_SCTP_S_INIT_SER /* IP_VS_SCTP_EVE_INIT_SER */ },
- /*
- * Unexpected INIT_ACK by the client, let us close the connection
- */
- {IP_VS_SCTP_S_CLOSED /* IP_VS_SCTP_EVE_INIT_ACK_CLI */ },
- /*
- * INIT_ACK resent by the server, let us move to same state
- */
- {IP_VS_SCTP_S_INIT_ACK_SER /* IP_VS_SCTP_EVE_INIT_ACK_SER */ },
- /*
- * Client send the ECHO, this is what we are expecting,
- * move to ECHO_CLI
- */
- {IP_VS_SCTP_S_ECHO_CLI /* IP_VS_SCTP_EVE_COOKIE_ECHO_CLI */ },
- /*
- * ECHO received from the server, Not sure what to do,
- * let us close it
- */
- {IP_VS_SCTP_S_CLOSED /* IP_VS_SCTP_EVE_COOKIE_ECHO_SER */ },
- /*
- * COOKIE ACK from client, let us stay in the same state
- */
- {IP_VS_SCTP_S_INIT_ACK_SER /* IP_VS_SCTP_EVE_COOKIE_ACK_CLI */ },
- /*
- * COOKIE ACK from server, hmm... this should not happen, lets close
- * the connection.
- */
- {IP_VS_SCTP_S_CLOSED /* IP_VS_SCTP_EVE_COOKIE_ACK_SER */ },
- {IP_VS_SCTP_S_CLOSED /* IP_VS_SCTP_EVE_ABORT_CLI */ },
- {IP_VS_SCTP_S_CLOSED /* IP_VS_SCTP_EVE_ABORT_SER */ },
- {IP_VS_SCTP_S_CLOSED /* IP_VS_SCTP_EVE_SHUT_CLI */ },
- {IP_VS_SCTP_S_CLOSED /* IP_VS_SCTP_EVE_SHUT_SER */ },
- {IP_VS_SCTP_S_CLOSED /* IP_VS_SCTP_EVE_SHUT_ACK_CLI */ },
- {IP_VS_SCTP_S_CLOSED /* IP_VS_SCTP_EVE_SHUT_ACK_SER */ },
- {IP_VS_SCTP_S_CLOSED /* IP_VS_SCTP_EVE_SHUT_COM_CLI */ },
- {IP_VS_SCTP_S_CLOSED /* IP_VS_SCTP_EVE_SHUT_COM_SER */ }
- },
- /*
- * State : IP_VS_SCTP_S_ECHO_CLI
- * Cient sent ECHO and waiting COOKEI ACK from the Server
- */
- {{IP_VS_SCTP_S_CLOSED /* IP_VS_SCTP_EVE_DATA_CLI */ },
- {IP_VS_SCTP_S_CLOSED /* IP_VS_SCTP_EVE_DATA_SER */ },
- /*
- * We have got an INIT from client. From the spec.“Upon receipt of
- * an INIT in the COOKIE-WAIT state, an endpoint MUST respond with
- * an INIT ACK using the same parameters it sent in its original
- * INIT chunk (including its Initiate Tag, unchanged”).
- */
- {IP_VS_SCTP_S_INIT_CLI /* IP_VS_SCTP_EVE_INIT_CLI */ },
- {IP_VS_SCTP_S_INIT_SER /* IP_VS_SCTP_EVE_INIT_SER */ },
- /*
- * INIT_ACK has been by the client, let us close the connection
- */
- {IP_VS_SCTP_S_CLOSED /* IP_VS_SCTP_EVE_INIT_ACK_CLI */ },
- /*
- * INIT_ACK sent by the server, Unexpected INIT ACK, spec says,
- * “If an INIT ACK is received by an endpoint in any state other
- * than the COOKIE-WAIT state, the endpoint should discard the
- * INIT ACK chunk”. Stay in the same state
- */
- {IP_VS_SCTP_S_ECHO_CLI /* IP_VS_SCTP_EVE_INIT_ACK_SER */ },
- /*
- * Client resent the ECHO, let us stay in the same state
- */
- {IP_VS_SCTP_S_ECHO_CLI /* IP_VS_SCTP_EVE_COOKIE_ECHO_CLI */ },
- /*
- * ECHO received from the server, Not sure what to do,
- * let us close it
- */
- {IP_VS_SCTP_S_CLOSED /* IP_VS_SCTP_EVE_COOKIE_ECHO_SER */ },
- /*
- * COOKIE ACK from client, this shoud not happen, let's close the
- * connection
- */
- {IP_VS_SCTP_S_CLOSED /* IP_VS_SCTP_EVE_COOKIE_ACK_CLI */ },
- /*
- * COOKIE ACK from server, this is what we are awaiting,lets move to
- * ESTABLISHED.
- */
- {IP_VS_SCTP_S_ESTABLISHED /* IP_VS_SCTP_EVE_COOKIE_ACK_SER */ },
- {IP_VS_SCTP_S_CLOSED /* IP_VS_SCTP_EVE_ABORT_CLI */ },
- {IP_VS_SCTP_S_CLOSED /* IP_VS_SCTP_EVE_ABORT_SER */ },
- {IP_VS_SCTP_S_CLOSED /* IP_VS_SCTP_EVE_SHUT_CLI */ },
- {IP_VS_SCTP_S_CLOSED /* IP_VS_SCTP_EVE_SHUT_SER */ },
- {IP_VS_SCTP_S_CLOSED /* IP_VS_SCTP_EVE_SHUT_ACK_CLI */ },
- {IP_VS_SCTP_S_CLOSED /* IP_VS_SCTP_EVE_SHUT_ACK_SER */ },
- {IP_VS_SCTP_S_CLOSED /* IP_VS_SCTP_EVE_SHUT_COM_CLI */ },
- {IP_VS_SCTP_S_CLOSED /* IP_VS_SCTP_EVE_SHUT_COM_SER */ }
- },
- /*
- * State : IP_VS_SCTP_S_ECHO_SER
- * Server sent ECHO and waiting COOKEI ACK from the client
- */
- {{IP_VS_SCTP_S_CLOSED /* IP_VS_SCTP_EVE_DATA_CLI */ },
- {IP_VS_SCTP_S_CLOSED /* IP_VS_SCTP_EVE_DATA_SER */ },
- /*
- * We have got an INIT from client. From the spec.“Upon receipt of
- * an INIT in the COOKIE-WAIT state, an endpoint MUST respond with
- * an INIT ACK using the same parameters it sent in its original
- * INIT chunk (including its Initiate Tag, unchanged”).
- */
- {IP_VS_SCTP_S_INIT_CLI /* IP_VS_SCTP_EVE_INIT_CLI */ },
- {IP_VS_SCTP_S_INIT_SER /* IP_VS_SCTP_EVE_INIT_SER */ },
- /*
- * INIT_ACK sent by the server, Unexpected INIT ACK, spec says,
- * “If an INIT ACK is received by an endpoint in any state other
- * than the COOKIE-WAIT state, the endpoint should discard the
- * INIT ACK chunk”. Stay in the same state
- */
- {IP_VS_SCTP_S_ECHO_SER /* IP_VS_SCTP_EVE_INIT_ACK_CLI */ },
- /*
- * INIT_ACK has been by the server, let us close the connection
- */
- {IP_VS_SCTP_S_CLOSED /* IP_VS_SCTP_EVE_INIT_ACK_SER */ },
- /*
- * Client sent the ECHO, not sure what to do, let's close the
- * connection.
- */
- {IP_VS_SCTP_S_CLOSED /* IP_VS_SCTP_EVE_COOKIE_ECHO_CLI */ },
- /*
- * ECHO resent by the server, stay in the same state
- */
- {IP_VS_SCTP_S_ECHO_SER /* IP_VS_SCTP_EVE_COOKIE_ECHO_SER */ },
- /*
- * COOKIE ACK from client, this is what we are expecting, let's move
- * to ESTABLISHED.
- */
- {IP_VS_SCTP_S_ESTABLISHED /* IP_VS_SCTP_EVE_COOKIE_ACK_CLI */ },
- /*
- * COOKIE ACK from server, this should not happen, lets close the
- * connection.
- */
- {IP_VS_SCTP_S_CLOSED /* IP_VS_SCTP_EVE_COOKIE_ACK_SER */ },
- {IP_VS_SCTP_S_CLOSED /* IP_VS_SCTP_EVE_ABORT_CLI */ },
- {IP_VS_SCTP_S_CLOSED /* IP_VS_SCTP_EVE_ABORT_SER */ },
- {IP_VS_SCTP_S_CLOSED /* IP_VS_SCTP_EVE_SHUT_CLI */ },
- {IP_VS_SCTP_S_CLOSED /* IP_VS_SCTP_EVE_SHUT_SER */ },
- {IP_VS_SCTP_S_CLOSED /* IP_VS_SCTP_EVE_SHUT_ACK_CLI */ },
- {IP_VS_SCTP_S_CLOSED /* IP_VS_SCTP_EVE_SHUT_ACK_SER */ },
- {IP_VS_SCTP_S_CLOSED /* IP_VS_SCTP_EVE_SHUT_COM_CLI */ },
- {IP_VS_SCTP_S_CLOSED /* IP_VS_SCTP_EVE_SHUT_COM_SER */ }
- },
- /*
- * State : IP_VS_SCTP_S_ESTABLISHED
- * Association established
- */
- {{IP_VS_SCTP_S_ESTABLISHED /* IP_VS_SCTP_EVE_DATA_CLI */ },
- {IP_VS_SCTP_S_ESTABLISHED /* IP_VS_SCTP_EVE_DATA_SER */ },
- /*
- * We have got an INIT from client. From the spec.“Upon receipt of
- * an INIT in the COOKIE-WAIT state, an endpoint MUST respond with
- * an INIT ACK using the same parameters it sent in its original
- * INIT chunk (including its Initiate Tag, unchanged”).
- */
- {IP_VS_SCTP_S_INIT_CLI /* IP_VS_SCTP_EVE_INIT_CLI */ },
- {IP_VS_SCTP_S_INIT_SER /* IP_VS_SCTP_EVE_INIT_SER */ },
- /*
- * INIT_ACK sent by the server, Unexpected INIT ACK, spec says,
- * “If an INIT ACK is received by an endpoint in any state other
- * than the COOKIE-WAIT state, the endpoint should discard the
- * INIT ACK chunk”. Stay in the same state
- */
- {IP_VS_SCTP_S_ESTABLISHED /* IP_VS_SCTP_EVE_INIT_ACK_CLI */ },
- {IP_VS_SCTP_S_ESTABLISHED /* IP_VS_SCTP_EVE_INIT_ACK_SER */ },
- /*
- * Client sent ECHO, Spec(sec 5.2.4) says it may be handled by the
- * peer and peer shall move to the ESTABISHED. if it doesn't handle
- * it will send ERROR chunk. So, stay in the same state
- */
- {IP_VS_SCTP_S_ESTABLISHED /* IP_VS_SCTP_EVE_COOKIE_ECHO_CLI */ },
- {IP_VS_SCTP_S_ESTABLISHED /* IP_VS_SCTP_EVE_COOKIE_ECHO_SER */ },
- /*
- * COOKIE ACK from client, not sure what to do stay in the same state
- */
- {IP_VS_SCTP_S_ESTABLISHED /* IP_VS_SCTP_EVE_COOKIE_ACK_CLI */ },
- {IP_VS_SCTP_S_ESTABLISHED /* IP_VS_SCTP_EVE_COOKIE_ACK_SER */ },
- {IP_VS_SCTP_S_CLOSED /* IP_VS_SCTP_EVE_ABORT_CLI */ },
- {IP_VS_SCTP_S_CLOSED /* IP_VS_SCTP_EVE_ABORT_SER */ },
- /*
- * SHUTDOWN from the client, move to SHUDDOWN_CLI
- */
- {IP_VS_SCTP_S_SHUT_CLI /* IP_VS_SCTP_EVE_SHUT_CLI */ },
- /*
- * SHUTDOWN from the server, move to SHUTDOWN_SER
- */
- {IP_VS_SCTP_S_SHUT_SER /* IP_VS_SCTP_EVE_SHUT_SER */ },
- /*
- * client sent SHUDTDOWN_ACK, this should not happen, let's close
- * the connection
- */
- {IP_VS_SCTP_S_CLOSED /* IP_VS_SCTP_EVE_SHUT_ACK_CLI */ },
- {IP_VS_SCTP_S_CLOSED /* IP_VS_SCTP_EVE_SHUT_ACK_SER */ },
- {IP_VS_SCTP_S_CLOSED /* IP_VS_SCTP_EVE_SHUT_COM_CLI */ },
- {IP_VS_SCTP_S_CLOSED /* IP_VS_SCTP_EVE_SHUT_COM_SER */ }
- },
- /*
- * State : IP_VS_SCTP_S_SHUT_CLI
- * SHUTDOWN sent from the client, waitinf for SHUT ACK from the server
- */
- /*
- * We received the data chuck, keep the state unchanged. I assume
- * that still data chuncks can be received by both the peers in
- * SHUDOWN state
- */
-
- {{IP_VS_SCTP_S_SHUT_CLI /* IP_VS_SCTP_EVE_DATA_CLI */ },
- {IP_VS_SCTP_S_SHUT_CLI /* IP_VS_SCTP_EVE_DATA_SER */ },
- /*
- * We have got an INIT from client. From the spec.“Upon receipt of
- * an INIT in the COOKIE-WAIT state, an endpoint MUST respond with
- * an INIT ACK using the same parameters it sent in its original
- * INIT chunk (including its Initiate Tag, unchanged”).
- */
- {IP_VS_SCTP_S_INIT_CLI /* IP_VS_SCTP_EVE_INIT_CLI */ },
- {IP_VS_SCTP_S_INIT_SER /* IP_VS_SCTP_EVE_INIT_SER */ },
- /*
- * INIT_ACK sent by the server, Unexpected INIT ACK, spec says,
- * “If an INIT ACK is received by an endpoint in any state other
- * than the COOKIE-WAIT state, the endpoint should discard the
- * INIT ACK chunk”. Stay in the same state
- */
- {IP_VS_SCTP_S_SHUT_CLI /* IP_VS_SCTP_EVE_INIT_ACK_CLI */ },
- {IP_VS_SCTP_S_SHUT_CLI /* IP_VS_SCTP_EVE_INIT_ACK_SER */ },
- /*
- * Client sent ECHO, Spec(sec 5.2.4) says it may be handled by the
- * peer and peer shall move to the ESTABISHED. if it doesn't handle
- * it will send ERROR chunk. So, stay in the same state
- */
- {IP_VS_SCTP_S_ESTABLISHED /* IP_VS_SCTP_EVE_COOKIE_ECHO_CLI */ },
- {IP_VS_SCTP_S_ESTABLISHED /* IP_VS_SCTP_EVE_COOKIE_ECHO_SER */ },
- /*
- * COOKIE ACK from client, not sure what to do stay in the same state
- */
- {IP_VS_SCTP_S_SHUT_CLI /* IP_VS_SCTP_EVE_COOKIE_ACK_CLI */ },
- {IP_VS_SCTP_S_SHUT_CLI /* IP_VS_SCTP_EVE_COOKIE_ACK_SER */ },
- {IP_VS_SCTP_S_CLOSED /* IP_VS_SCTP_EVE_ABORT_CLI */ },
- {IP_VS_SCTP_S_CLOSED /* IP_VS_SCTP_EVE_ABORT_SER */ },
- /*
- * SHUTDOWN resent from the client, move to SHUDDOWN_CLI
- */
- {IP_VS_SCTP_S_SHUT_CLI /* IP_VS_SCTP_EVE_SHUT_CLI */ },
- /*
- * SHUTDOWN from the server, move to SHUTDOWN_SER
- */
- {IP_VS_SCTP_S_SHUT_SER /* IP_VS_SCTP_EVE_SHUT_SER */ },
- /*
- * client sent SHUDTDOWN_ACK, this should not happen, let's close
- * the connection
- */
- {IP_VS_SCTP_S_CLOSED /* IP_VS_SCTP_EVE_SHUT_ACK_CLI */ },
- /*
- * Server sent SHUTDOWN ACK, this is what we are expecting, let's move
- * to SHUDOWN_ACK_SER
- */
- {IP_VS_SCTP_S_SHUT_ACK_SER /* IP_VS_SCTP_EVE_SHUT_ACK_SER */ },
- /*
- * SHUTDOWN COM from client, this should not happen, let's close the
- * connection
- */
- {IP_VS_SCTP_S_CLOSED /* IP_VS_SCTP_EVE_SHUT_COM_CLI */ },
- {IP_VS_SCTP_S_CLOSED /* IP_VS_SCTP_EVE_SHUT_COM_SER */ }
- },
- /*
- * State : IP_VS_SCTP_S_SHUT_SER
- * SHUTDOWN sent from the server, waitinf for SHUTDOWN ACK from client
- */
- /*
- * We received the data chuck, keep the state unchanged. I assume
- * that still data chuncks can be received by both the peers in
- * SHUDOWN state
- */
-
- {{IP_VS_SCTP_S_SHUT_SER /* IP_VS_SCTP_EVE_DATA_CLI */ },
- {IP_VS_SCTP_S_SHUT_SER /* IP_VS_SCTP_EVE_DATA_SER */ },
- /*
- * We have got an INIT from client. From the spec.“Upon receipt of
- * an INIT in the COOKIE-WAIT state, an endpoint MUST respond with
- * an INIT ACK using the same parameters it sent in its original
- * INIT chunk (including its Initiate Tag, unchanged”).
- */
- {IP_VS_SCTP_S_INIT_CLI /* IP_VS_SCTP_EVE_INIT_CLI */ },
- {IP_VS_SCTP_S_INIT_SER /* IP_VS_SCTP_EVE_INIT_SER */ },
- /*
- * INIT_ACK sent by the server, Unexpected INIT ACK, spec says,
- * “If an INIT ACK is received by an endpoint in any state other
- * than the COOKIE-WAIT state, the endpoint should discard the
- * INIT ACK chunk”. Stay in the same state
- */
- {IP_VS_SCTP_S_SHUT_SER /* IP_VS_SCTP_EVE_INIT_ACK_CLI */ },
- {IP_VS_SCTP_S_SHUT_SER /* IP_VS_SCTP_EVE_INIT_ACK_SER */ },
- /*
- * Client sent ECHO, Spec(sec 5.2.4) says it may be handled by the
- * peer and peer shall move to the ESTABISHED. if it doesn't handle
- * it will send ERROR chunk. So, stay in the same state
- */
- {IP_VS_SCTP_S_ESTABLISHED /* IP_VS_SCTP_EVE_COOKIE_ECHO_CLI */ },
- {IP_VS_SCTP_S_ESTABLISHED /* IP_VS_SCTP_EVE_COOKIE_ECHO_SER */ },
- /*
- * COOKIE ACK from client, not sure what to do stay in the same state
- */
- {IP_VS_SCTP_S_SHUT_SER /* IP_VS_SCTP_EVE_COOKIE_ACK_CLI */ },
- {IP_VS_SCTP_S_SHUT_SER /* IP_VS_SCTP_EVE_COOKIE_ACK_SER */ },
- {IP_VS_SCTP_S_CLOSED /* IP_VS_SCTP_EVE_ABORT_CLI */ },
- {IP_VS_SCTP_S_CLOSED /* IP_VS_SCTP_EVE_ABORT_SER */ },
- /*
- * SHUTDOWN resent from the client, move to SHUDDOWN_CLI
- */
- {IP_VS_SCTP_S_SHUT_CLI /* IP_VS_SCTP_EVE_SHUT_CLI */ },
- /*
- * SHUTDOWN resent from the server, move to SHUTDOWN_SER
- */
- {IP_VS_SCTP_S_SHUT_SER /* IP_VS_SCTP_EVE_SHUT_SER */ },
- /*
- * client sent SHUDTDOWN_ACK, this is what we are expecting, let's
- * move to SHUT_ACK_CLI
- */
- {IP_VS_SCTP_S_SHUT_ACK_CLI /* IP_VS_SCTP_EVE_SHUT_ACK_CLI */ },
- /*
- * Server sent SHUTDOWN ACK, this should not happen, let's close the
- * connection
- */
- {IP_VS_SCTP_S_CLOSED /* IP_VS_SCTP_EVE_SHUT_ACK_SER */ },
- /*
- * SHUTDOWN COM from client, this should not happen, let's close the
- * connection
- */
- {IP_VS_SCTP_S_CLOSED /* IP_VS_SCTP_EVE_SHUT_COM_CLI */ },
- {IP_VS_SCTP_S_CLOSED /* IP_VS_SCTP_EVE_SHUT_COM_SER */ }
- },
-
- /*
- * State : IP_VS_SCTP_S_SHUT_ACK_CLI
- * SHUTDOWN ACK from the client, awaiting for SHUTDOWN COM from server
- */
- /*
- * We received the data chuck, keep the state unchanged. I assume
- * that still data chuncks can be received by both the peers in
- * SHUDOWN state
- */
-
- {{IP_VS_SCTP_S_SHUT_ACK_CLI /* IP_VS_SCTP_EVE_DATA_CLI */ },
- {IP_VS_SCTP_S_SHUT_ACK_CLI /* IP_VS_SCTP_EVE_DATA_SER */ },
- /*
- * We have got an INIT from client. From the spec.“Upon receipt of
- * an INIT in the COOKIE-WAIT state, an endpoint MUST respond with
- * an INIT ACK using the same parameters it sent in its original
- * INIT chunk (including its Initiate Tag, unchanged”).
- */
- {IP_VS_SCTP_S_INIT_CLI /* IP_VS_SCTP_EVE_INIT_CLI */ },
- {IP_VS_SCTP_S_INIT_SER /* IP_VS_SCTP_EVE_INIT_SER */ },
- /*
- * INIT_ACK sent by the server, Unexpected INIT ACK, spec says,
- * “If an INIT ACK is received by an endpoint in any state other
- * than the COOKIE-WAIT state, the endpoint should discard the
- * INIT ACK chunk”. Stay in the same state
- */
- {IP_VS_SCTP_S_SHUT_ACK_CLI /* IP_VS_SCTP_EVE_INIT_ACK_CLI */ },
- {IP_VS_SCTP_S_SHUT_ACK_CLI /* IP_VS_SCTP_EVE_INIT_ACK_SER */ },
- /*
- * Client sent ECHO, Spec(sec 5.2.4) says it may be handled by the
- * peer and peer shall move to the ESTABISHED. if it doesn't handle
- * it will send ERROR chunk. So, stay in the same state
- */
- {IP_VS_SCTP_S_ESTABLISHED /* IP_VS_SCTP_EVE_COOKIE_ECHO_CLI */ },
- {IP_VS_SCTP_S_ESTABLISHED /* IP_VS_SCTP_EVE_COOKIE_ECHO_SER */ },
- /*
- * COOKIE ACK from client, not sure what to do stay in the same state
- */
- {IP_VS_SCTP_S_SHUT_ACK_CLI /* IP_VS_SCTP_EVE_COOKIE_ACK_CLI */ },
- {IP_VS_SCTP_S_SHUT_ACK_CLI /* IP_VS_SCTP_EVE_COOKIE_ACK_SER */ },
- {IP_VS_SCTP_S_CLOSED /* IP_VS_SCTP_EVE_ABORT_CLI */ },
- {IP_VS_SCTP_S_CLOSED /* IP_VS_SCTP_EVE_ABORT_SER */ },
- /*
- * SHUTDOWN sent from the client, move to SHUDDOWN_CLI
- */
- {IP_VS_SCTP_S_SHUT_CLI /* IP_VS_SCTP_EVE_SHUT_CLI */ },
- /*
- * SHUTDOWN sent from the server, move to SHUTDOWN_SER
- */
- {IP_VS_SCTP_S_SHUT_SER /* IP_VS_SCTP_EVE_SHUT_SER */ },
- /*
- * client resent SHUDTDOWN_ACK, let's stay in the same state
- */
- {IP_VS_SCTP_S_SHUT_ACK_CLI /* IP_VS_SCTP_EVE_SHUT_ACK_CLI */ },
- /*
- * Server sent SHUTDOWN ACK, this should not happen, let's close the
- * connection
- */
- {IP_VS_SCTP_S_CLOSED /* IP_VS_SCTP_EVE_SHUT_ACK_SER */ },
- /*
- * SHUTDOWN COM from client, this should not happen, let's close the
- * connection
- */
- {IP_VS_SCTP_S_CLOSED /* IP_VS_SCTP_EVE_SHUT_COM_CLI */ },
- /*
- * SHUTDOWN COMPLETE from server this is what we are expecting.
- */
- {IP_VS_SCTP_S_CLOSED /* IP_VS_SCTP_EVE_SHUT_COM_SER */ }
- },
-
- /*
- * State : IP_VS_SCTP_S_SHUT_ACK_SER
- * SHUTDOWN ACK from the server, awaiting for SHUTDOWN COM from client
- */
- /*
- * We received the data chuck, keep the state unchanged. I assume
- * that still data chuncks can be received by both the peers in
- * SHUDOWN state
- */
+/* SCTP States:
+ * See RFC 2960, 4. SCTP Association State Diagram
+ *
+ * New states (not in diagram):
+ * - INIT1 state: use shorter timeout for dropped INIT packets
+ * - REJECTED state: use shorter timeout if INIT is rejected with ABORT
+ * - INIT, COOKIE_SENT, COOKIE_REPLIED, COOKIE states: for better debugging
+ *
+ * The states are as seen in real server. In the diagram, INIT1, INIT,
+ * COOKIE_SENT and COOKIE_REPLIED processing happens in CLOSED state.
+ *
+ * States as per packets from client (C) and server (S):
+ *
+ * Setup of client connection:
+ * IP_VS_SCTP_S_INIT1: First C:INIT sent, wait for S:INIT-ACK
+ * IP_VS_SCTP_S_INIT: Next C:INIT sent, wait for S:INIT-ACK
+ * IP_VS_SCTP_S_COOKIE_SENT: S:INIT-ACK sent, wait for C:COOKIE-ECHO
+ * IP_VS_SCTP_S_COOKIE_REPLIED: C:COOKIE-ECHO sent, wait for S:COOKIE-ACK
+ *
+ * Setup of server connection:
+ * IP_VS_SCTP_S_COOKIE_WAIT: S:INIT sent, wait for C:INIT-ACK
+ * IP_VS_SCTP_S_COOKIE: C:INIT-ACK sent, wait for S:COOKIE-ECHO
+ * IP_VS_SCTP_S_COOKIE_ECHOED: S:COOKIE-ECHO sent, wait for C:COOKIE-ACK
+ */
- {{IP_VS_SCTP_S_SHUT_ACK_SER /* IP_VS_SCTP_EVE_DATA_CLI */ },
- {IP_VS_SCTP_S_SHUT_ACK_SER /* IP_VS_SCTP_EVE_DATA_SER */ },
- /*
- * We have got an INIT from client. From the spec.“Upon receipt of
- * an INIT in the COOKIE-WAIT state, an endpoint MUST respond with
- * an INIT ACK using the same parameters it sent in its original
- * INIT chunk (including its Initiate Tag, unchanged”).
- */
- {IP_VS_SCTP_S_INIT_CLI /* IP_VS_SCTP_EVE_INIT_CLI */ },
- {IP_VS_SCTP_S_INIT_SER /* IP_VS_SCTP_EVE_INIT_SER */ },
- /*
- * INIT_ACK sent by the server, Unexpected INIT ACK, spec says,
- * “If an INIT ACK is received by an endpoint in any state other
- * than the COOKIE-WAIT state, the endpoint should discard the
- * INIT ACK chunk”. Stay in the same state
- */
- {IP_VS_SCTP_S_SHUT_ACK_SER /* IP_VS_SCTP_EVE_INIT_ACK_CLI */ },
- {IP_VS_SCTP_S_SHUT_ACK_SER /* IP_VS_SCTP_EVE_INIT_ACK_SER */ },
- /*
- * Client sent ECHO, Spec(sec 5.2.4) says it may be handled by the
- * peer and peer shall move to the ESTABISHED. if it doesn't handle
- * it will send ERROR chunk. So, stay in the same state
- */
- {IP_VS_SCTP_S_ESTABLISHED /* IP_VS_SCTP_EVE_COOKIE_ECHO_CLI */ },
- {IP_VS_SCTP_S_ESTABLISHED /* IP_VS_SCTP_EVE_COOKIE_ECHO_SER */ },
- /*
- * COOKIE ACK from client, not sure what to do stay in the same state
- */
- {IP_VS_SCTP_S_SHUT_ACK_SER /* IP_VS_SCTP_EVE_COOKIE_ACK_CLI */ },
- {IP_VS_SCTP_S_SHUT_ACK_SER /* IP_VS_SCTP_EVE_COOKIE_ACK_SER */ },
- {IP_VS_SCTP_S_CLOSED /* IP_VS_SCTP_EVE_ABORT_CLI */ },
- {IP_VS_SCTP_S_CLOSED /* IP_VS_SCTP_EVE_ABORT_SER */ },
- /*
- * SHUTDOWN sent from the client, move to SHUDDOWN_CLI
- */
- {IP_VS_SCTP_S_SHUT_CLI /* IP_VS_SCTP_EVE_SHUT_CLI */ },
- /*
- * SHUTDOWN sent from the server, move to SHUTDOWN_SER
- */
- {IP_VS_SCTP_S_SHUT_SER /* IP_VS_SCTP_EVE_SHUT_SER */ },
- /*
- * client sent SHUDTDOWN_ACK, this should not happen let's close
- * the connection.
- */
- {IP_VS_SCTP_S_CLOSED /* IP_VS_SCTP_EVE_SHUT_ACK_CLI */ },
- /*
- * Server resent SHUTDOWN ACK, stay in the same state
- */
- {IP_VS_SCTP_S_SHUT_ACK_SER /* IP_VS_SCTP_EVE_SHUT_ACK_SER */ },
- /*
- * SHUTDOWN COM from client, this what we are expecting, let's close
- * the connection
- */
- {IP_VS_SCTP_S_CLOSED /* IP_VS_SCTP_EVE_SHUT_COM_CLI */ },
- /*
- * SHUTDOWN COMPLETE from server this should not happen.
- */
- {IP_VS_SCTP_S_CLOSED /* IP_VS_SCTP_EVE_SHUT_COM_SER */ }
- },
- /*
- * State : IP_VS_SCTP_S_CLOSED
- */
- {{IP_VS_SCTP_S_CLOSED /* IP_VS_SCTP_EVE_DATA_CLI */ },
- {IP_VS_SCTP_S_CLOSED /* IP_VS_SCTP_EVE_DATA_SER */ },
- {IP_VS_SCTP_S_INIT_CLI /* IP_VS_SCTP_EVE_INIT_CLI */ },
- {IP_VS_SCTP_S_INIT_SER /* IP_VS_SCTP_EVE_INIT_SER */ },
- {IP_VS_SCTP_S_CLOSED /* IP_VS_SCTP_EVE_INIT_ACK_CLI */ },
- {IP_VS_SCTP_S_CLOSED /* IP_VS_SCTP_EVE_INIT_ACK_SER */ },
- {IP_VS_SCTP_S_CLOSED /* IP_VS_SCTP_EVE_COOKIE_ECHO_CLI */ },
- {IP_VS_SCTP_S_CLOSED /* IP_VS_SCTP_EVE_COOKIE_ECHO_SER */ },
- {IP_VS_SCTP_S_CLOSED /* IP_VS_SCTP_EVE_COOKIE_ACK_CLI */ },
- {IP_VS_SCTP_S_CLOSED /* IP_VS_SCTP_EVE_COOKIE_ACK_SER */ },
- {IP_VS_SCTP_S_CLOSED /* IP_VS_SCTP_EVE_ABORT_CLI */ },
- {IP_VS_SCTP_S_CLOSED /* IP_VS_SCTP_EVE_ABORT_SER */ },
- {IP_VS_SCTP_S_CLOSED /* IP_VS_SCTP_EVE_SHUT_CLI */ },
- {IP_VS_SCTP_S_CLOSED /* IP_VS_SCTP_EVE_SHUT_SER */ },
- {IP_VS_SCTP_S_CLOSED /* IP_VS_SCTP_EVE_SHUT_ACK_CLI */ },
- {IP_VS_SCTP_S_CLOSED /* IP_VS_SCTP_EVE_SHUT_ACK_SER */ },
- {IP_VS_SCTP_S_CLOSED /* IP_VS_SCTP_EVE_SHUT_COM_CLI */ },
- {IP_VS_SCTP_S_CLOSED /* IP_VS_SCTP_EVE_SHUT_COM_SER */ }
- }
+#define sNO IP_VS_SCTP_S_NONE
+#define sI1 IP_VS_SCTP_S_INIT1
+#define sIN IP_VS_SCTP_S_INIT
+#define sCS IP_VS_SCTP_S_COOKIE_SENT
+#define sCR IP_VS_SCTP_S_COOKIE_REPLIED
+#define sCW IP_VS_SCTP_S_COOKIE_WAIT
+#define sCO IP_VS_SCTP_S_COOKIE
+#define sCE IP_VS_SCTP_S_COOKIE_ECHOED
+#define sES IP_VS_SCTP_S_ESTABLISHED
+#define sSS IP_VS_SCTP_S_SHUTDOWN_SENT
+#define sSR IP_VS_SCTP_S_SHUTDOWN_RECEIVED
+#define sSA IP_VS_SCTP_S_SHUTDOWN_ACK_SENT
+#define sRJ IP_VS_SCTP_S_REJECTED
+#define sCL IP_VS_SCTP_S_CLOSED
+
+static const __u8 sctp_states
+ [IP_VS_DIR_LAST][IP_VS_SCTP_EVENT_LAST][IP_VS_SCTP_S_LAST] = {
+ { /* INPUT */
+/* sNO, sI1, sIN, sCS, sCR, sCW, sCO, sCE, sES, sSS, sSR, sSA, sRJ, sCL*/
+/* d */{sES, sI1, sIN, sCS, sCR, sCW, sCO, sCE, sES, sSS, sSR, sSA, sRJ, sCL},
+/* i */{sI1, sIN, sIN, sCS, sCR, sCW, sCO, sCE, sES, sSS, sSR, sSA, sIN, sIN},
+/* i_a */{sCW, sCW, sCW, sCS, sCR, sCO, sCO, sCE, sES, sSS, sSR, sSA, sRJ, sCL},
+/* c_e */{sCR, sIN, sIN, sCR, sCR, sCW, sCO, sCE, sES, sSS, sSR, sSA, sRJ, sCL},
+/* c_a */{sES, sI1, sIN, sCS, sCR, sCW, sCO, sES, sES, sSS, sSR, sSA, sRJ, sCL},
+/* s */{sSR, sI1, sIN, sCS, sCR, sCW, sCO, sCE, sSR, sSS, sSR, sSA, sRJ, sCL},
+/* s_a */{sCL, sIN, sIN, sCS, sCR, sCW, sCO, sCE, sES, sCL, sSR, sCL, sRJ, sCL},
+/* s_c */{sCL, sCL, sCL, sCS, sCR, sCW, sCO, sCE, sES, sSS, sSR, sCL, sRJ, sCL},
+/* err */{sCL, sI1, sIN, sCS, sCR, sCW, sCO, sCL, sES, sSS, sSR, sSA, sRJ, sCL},
+/* ab */{sCL, sCL, sCL, sCL, sCL, sRJ, sCL, sCL, sCL, sCL, sCL, sCL, sCL, sCL},
+ },
+ { /* OUTPUT */
+/* sNO, sI1, sIN, sCS, sCR, sCW, sCO, sCE, sES, sSS, sSR, sSA, sRJ, sCL*/
+/* d */{sES, sI1, sIN, sCS, sCR, sCW, sCO, sCE, sES, sSS, sSR, sSA, sRJ, sCL},
+/* i */{sCW, sCW, sCW, sCW, sCW, sCW, sCW, sCW, sES, sCW, sCW, sCW, sCW, sCW},
+/* i_a */{sCS, sCS, sCS, sCS, sCR, sCW, sCO, sCE, sES, sSS, sSR, sSA, sRJ, sCL},
+/* c_e */{sCE, sCE, sCE, sCE, sCE, sCE, sCE, sCE, sES, sSS, sSR, sSA, sRJ, sCL},
+/* c_a */{sES, sES, sES, sES, sES, sES, sES, sES, sES, sSS, sSR, sSA, sRJ, sCL},
+/* s */{sSS, sSS, sSS, sSS, sSS, sSS, sSS, sSS, sSS, sSS, sSR, sSA, sRJ, sCL},
+/* s_a */{sSA, sSA, sSA, sSA, sSA, sCW, sCO, sCE, sES, sSA, sSA, sSA, sRJ, sCL},
+/* s_c */{sCL, sI1, sIN, sCS, sCR, sCW, sCO, sCE, sES, sSS, sSR, sSA, sRJ, sCL},
+/* err */{sCL, sCL, sCL, sCL, sCL, sCW, sCO, sCE, sES, sSS, sSR, sSA, sRJ, sCL},
+/* ab */{sCL, sRJ, sCL, sCL, sCL, sCL, sCL, sCL, sCL, sCL, sCL, sCL, sCL, sCL},
+ },
+ { /* INPUT-ONLY */
+/* sNO, sI1, sIN, sCS, sCR, sCW, sCO, sCE, sES, sSS, sSR, sSA, sRJ, sCL*/
+/* d */{sES, sI1, sIN, sCS, sCR, sES, sCO, sCE, sES, sSS, sSR, sSA, sRJ, sCL},
+/* i */{sI1, sIN, sIN, sIN, sIN, sIN, sCO, sCE, sES, sSS, sSR, sSA, sIN, sIN},
+/* i_a */{sCE, sCE, sCE, sCE, sCE, sCE, sCO, sCE, sES, sSS, sSR, sSA, sRJ, sCL},
+/* c_e */{sES, sES, sES, sES, sES, sES, sCO, sCE, sES, sSS, sSR, sSA, sRJ, sCL},
+/* c_a */{sES, sI1, sIN, sES, sES, sCW, sES, sES, sES, sSS, sSR, sSA, sRJ, sCL},
+/* s */{sSR, sI1, sIN, sCS, sCR, sCW, sCO, sCE, sSR, sSS, sSR, sSA, sRJ, sCL},
+/* s_a */{sCL, sIN, sIN, sCS, sCR, sCW, sCO, sCE, sCL, sCL, sSR, sCL, sRJ, sCL},
+/* s_c */{sCL, sCL, sCL, sCL, sCL, sCW, sCO, sCE, sES, sSS, sCL, sCL, sRJ, sCL},
+/* err */{sCL, sI1, sIN, sCS, sCR, sCW, sCO, sCE, sES, sSS, sSR, sSA, sRJ, sCL},
+/* ab */{sCL, sCL, sCL, sCL, sCL, sRJ, sCL, sCL, sCL, sCL, sCL, sCL, sCL, sCL},
+ },
};
-/*
- * Timeout table[state]
- */
+#define IP_VS_SCTP_MAX_RTO ((60 + 1) * HZ)
+
+/* Timeout table[state] */
static const int sctp_timeouts[IP_VS_SCTP_S_LAST + 1] = {
- [IP_VS_SCTP_S_NONE] = 2 * HZ,
- [IP_VS_SCTP_S_INIT_CLI] = 1 * 60 * HZ,
- [IP_VS_SCTP_S_INIT_SER] = 1 * 60 * HZ,
- [IP_VS_SCTP_S_INIT_ACK_CLI] = 1 * 60 * HZ,
- [IP_VS_SCTP_S_INIT_ACK_SER] = 1 * 60 * HZ,
- [IP_VS_SCTP_S_ECHO_CLI] = 1 * 60 * HZ,
- [IP_VS_SCTP_S_ECHO_SER] = 1 * 60 * HZ,
- [IP_VS_SCTP_S_ESTABLISHED] = 15 * 60 * HZ,
- [IP_VS_SCTP_S_SHUT_CLI] = 1 * 60 * HZ,
- [IP_VS_SCTP_S_SHUT_SER] = 1 * 60 * HZ,
- [IP_VS_SCTP_S_SHUT_ACK_CLI] = 1 * 60 * HZ,
- [IP_VS_SCTP_S_SHUT_ACK_SER] = 1 * 60 * HZ,
- [IP_VS_SCTP_S_CLOSED] = 10 * HZ,
- [IP_VS_SCTP_S_LAST] = 2 * HZ,
+ [IP_VS_SCTP_S_NONE] = 2 * HZ,
+ [IP_VS_SCTP_S_INIT1] = (0 + 3 + 1) * HZ,
+ [IP_VS_SCTP_S_INIT] = IP_VS_SCTP_MAX_RTO,
+ [IP_VS_SCTP_S_COOKIE_SENT] = IP_VS_SCTP_MAX_RTO,
+ [IP_VS_SCTP_S_COOKIE_REPLIED] = IP_VS_SCTP_MAX_RTO,
+ [IP_VS_SCTP_S_COOKIE_WAIT] = IP_VS_SCTP_MAX_RTO,
+ [IP_VS_SCTP_S_COOKIE] = IP_VS_SCTP_MAX_RTO,
+ [IP_VS_SCTP_S_COOKIE_ECHOED] = IP_VS_SCTP_MAX_RTO,
+ [IP_VS_SCTP_S_ESTABLISHED] = 15 * 60 * HZ,
+ [IP_VS_SCTP_S_SHUTDOWN_SENT] = IP_VS_SCTP_MAX_RTO,
+ [IP_VS_SCTP_S_SHUTDOWN_RECEIVED] = IP_VS_SCTP_MAX_RTO,
+ [IP_VS_SCTP_S_SHUTDOWN_ACK_SENT] = IP_VS_SCTP_MAX_RTO,
+ [IP_VS_SCTP_S_REJECTED] = (0 + 3 + 1) * HZ,
+ [IP_VS_SCTP_S_CLOSED] = IP_VS_SCTP_MAX_RTO,
+ [IP_VS_SCTP_S_LAST] = 2 * HZ,
};
static const char *sctp_state_name_table[IP_VS_SCTP_S_LAST + 1] = {
- [IP_VS_SCTP_S_NONE] = "NONE",
- [IP_VS_SCTP_S_INIT_CLI] = "INIT_CLI",
- [IP_VS_SCTP_S_INIT_SER] = "INIT_SER",
- [IP_VS_SCTP_S_INIT_ACK_CLI] = "INIT_ACK_CLI",
- [IP_VS_SCTP_S_INIT_ACK_SER] = "INIT_ACK_SER",
- [IP_VS_SCTP_S_ECHO_CLI] = "COOKIE_ECHO_CLI",
- [IP_VS_SCTP_S_ECHO_SER] = "COOKIE_ECHO_SER",
- [IP_VS_SCTP_S_ESTABLISHED] = "ESTABISHED",
- [IP_VS_SCTP_S_SHUT_CLI] = "SHUTDOWN_CLI",
- [IP_VS_SCTP_S_SHUT_SER] = "SHUTDOWN_SER",
- [IP_VS_SCTP_S_SHUT_ACK_CLI] = "SHUTDOWN_ACK_CLI",
- [IP_VS_SCTP_S_SHUT_ACK_SER] = "SHUTDOWN_ACK_SER",
- [IP_VS_SCTP_S_CLOSED] = "CLOSED",
- [IP_VS_SCTP_S_LAST] = "BUG!"
+ [IP_VS_SCTP_S_NONE] = "NONE",
+ [IP_VS_SCTP_S_INIT1] = "INIT1",
+ [IP_VS_SCTP_S_INIT] = "INIT",
+ [IP_VS_SCTP_S_COOKIE_SENT] = "C-SENT",
+ [IP_VS_SCTP_S_COOKIE_REPLIED] = "C-REPLIED",
+ [IP_VS_SCTP_S_COOKIE_WAIT] = "C-WAIT",
+ [IP_VS_SCTP_S_COOKIE] = "COOKIE",
+ [IP_VS_SCTP_S_COOKIE_ECHOED] = "C-ECHOED",
+ [IP_VS_SCTP_S_ESTABLISHED] = "ESTABLISHED",
+ [IP_VS_SCTP_S_SHUTDOWN_SENT] = "S-SENT",
+ [IP_VS_SCTP_S_SHUTDOWN_RECEIVED] = "S-RECEIVED",
+ [IP_VS_SCTP_S_SHUTDOWN_ACK_SENT] = "S-ACK-SENT",
+ [IP_VS_SCTP_S_REJECTED] = "REJECTED",
+ [IP_VS_SCTP_S_CLOSED] = "CLOSED",
+ [IP_VS_SCTP_S_LAST] = "BUG!",
};
@@ -907,7 +372,7 @@ set_sctp_state(struct ip_vs_proto_data *pd, struct ip_vs_conn *cp,
sctp_chunkhdr_t _sctpch, *sch;
unsigned char chunk_type;
int event, next_state;
- int ihl;
+ int ihl, cofs;
#ifdef CONFIG_IP_VS_IPV6
ihl = cp->af == AF_INET ? ip_hdrlen(skb) : sizeof(struct ipv6hdr);
@@ -915,8 +380,8 @@ set_sctp_state(struct ip_vs_proto_data *pd, struct ip_vs_conn *cp,
ihl = ip_hdrlen(skb);
#endif
- sch = skb_header_pointer(skb, ihl + sizeof(sctp_sctphdr_t),
- sizeof(_sctpch), &_sctpch);
+ cofs = ihl + sizeof(sctp_sctphdr_t);
+ sch = skb_header_pointer(skb, cofs, sizeof(_sctpch), &_sctpch);
if (sch == NULL)
return;
@@ -934,25 +399,30 @@ set_sctp_state(struct ip_vs_proto_data *pd, struct ip_vs_conn *cp,
*/
if ((sch->type == SCTP_CID_COOKIE_ECHO) ||
(sch->type == SCTP_CID_COOKIE_ACK)) {
- sch = skb_header_pointer(skb, (ihl + sizeof(sctp_sctphdr_t) +
- sch->length), sizeof(_sctpch), &_sctpch);
- if (sch) {
- if (sch->type == SCTP_CID_ABORT)
+ int clen = ntohs(sch->length);
+
+ if (clen >= sizeof(sctp_chunkhdr_t)) {
+ sch = skb_header_pointer(skb, cofs + ALIGN(clen, 4),
+ sizeof(_sctpch), &_sctpch);
+ if (sch && sch->type == SCTP_CID_ABORT)
chunk_type = sch->type;
}
}
- event = sctp_events[chunk_type];
+ event = (chunk_type < sizeof(sctp_events)) ?
+ sctp_events[chunk_type] : IP_VS_SCTP_DATA;
- /*
- * If the direction is IP_VS_DIR_OUTPUT, this event is from server
- */
- if (direction == IP_VS_DIR_OUTPUT)
- event++;
- /*
- * get next state
+ /* Update direction to INPUT_ONLY if necessary
+ * or delete NO_OUTPUT flag if output packet detected
*/
- next_state = sctp_states_table[cp->state][event].next_state;
+ if (cp->flags & IP_VS_CONN_F_NOOUTPUT) {
+ if (direction == IP_VS_DIR_OUTPUT)
+ cp->flags &= ~IP_VS_CONN_F_NOOUTPUT;
+ else
+ direction = IP_VS_DIR_INPUT_ONLY;
+ }
+
+ next_state = sctp_states[direction][event][cp->state];
if (next_state != cp->state) {
struct ip_vs_dest *dest = cp->dest;
@@ -993,9 +463,9 @@ static void
sctp_state_transition(struct ip_vs_conn *cp, int direction,
const struct sk_buff *skb, struct ip_vs_proto_data *pd)
{
- spin_lock(&cp->lock);
+ spin_lock_bh(&cp->lock);
set_sctp_state(pd, cp, direction, skb);
- spin_unlock(&cp->lock);
+ spin_unlock_bh(&cp->lock);
}
static inline __u16 sctp_app_hashkey(__be16 port)
@@ -1015,30 +485,25 @@ static int sctp_register_app(struct net *net, struct ip_vs_app *inc)
hash = sctp_app_hashkey(port);
- spin_lock_bh(&ipvs->sctp_app_lock);
list_for_each_entry(i, &ipvs->sctp_apps[hash], p_list) {
if (i->port == port) {
ret = -EEXIST;
goto out;
}
}
- list_add(&inc->p_list, &ipvs->sctp_apps[hash]);
+ list_add_rcu(&inc->p_list, &ipvs->sctp_apps[hash]);
atomic_inc(&pd->appcnt);
out:
- spin_unlock_bh(&ipvs->sctp_app_lock);
return ret;
}
static void sctp_unregister_app(struct net *net, struct ip_vs_app *inc)
{
- struct netns_ipvs *ipvs = net_ipvs(net);
struct ip_vs_proto_data *pd = ip_vs_proto_data_get(net, IPPROTO_SCTP);
- spin_lock_bh(&ipvs->sctp_app_lock);
atomic_dec(&pd->appcnt);
- list_del(&inc->p_list);
- spin_unlock_bh(&ipvs->sctp_app_lock);
+ list_del_rcu(&inc->p_list);
}
static int sctp_app_conn_bind(struct ip_vs_conn *cp)
@@ -1054,12 +519,12 @@ static int sctp_app_conn_bind(struct ip_vs_conn *cp)
/* Lookup application incarnations and bind the right one */
hash = sctp_app_hashkey(cp->vport);
- spin_lock(&ipvs->sctp_app_lock);
- list_for_each_entry(inc, &ipvs->sctp_apps[hash], p_list) {
+ rcu_read_lock();
+ list_for_each_entry_rcu(inc, &ipvs->sctp_apps[hash], p_list) {
if (inc->port == cp->vport) {
if (unlikely(!ip_vs_app_inc_get(inc)))
break;
- spin_unlock(&ipvs->sctp_app_lock);
+ rcu_read_unlock();
IP_VS_DBG_BUF(9, "%s: Binding conn %s:%u->"
"%s:%u to app %s on port %u\n",
@@ -1075,7 +540,7 @@ static int sctp_app_conn_bind(struct ip_vs_conn *cp)
goto out;
}
}
- spin_unlock(&ipvs->sctp_app_lock);
+ rcu_read_unlock();
out:
return result;
}
@@ -1089,7 +554,6 @@ static int __ip_vs_sctp_init(struct net *net, struct ip_vs_proto_data *pd)
struct netns_ipvs *ipvs = net_ipvs(net);
ip_vs_init_hash_table(ipvs->sctp_apps, SCTP_APP_TAB_SIZE);
- spin_lock_init(&ipvs->sctp_app_lock);
pd->timeout_table = ip_vs_create_timeout_table((int *)sctp_timeouts,
sizeof(sctp_timeouts));
if (!pd->timeout_table)
diff --git a/net/netfilter/ipvs/ip_vs_proto_tcp.c b/net/netfilter/ipvs/ip_vs_proto_tcp.c
index 9af653a7582..e3a697234a9 100644
--- a/net/netfilter/ipvs/ip_vs_proto_tcp.c
+++ b/net/netfilter/ipvs/ip_vs_proto_tcp.c
@@ -39,6 +39,7 @@ tcp_conn_schedule(int af, struct sk_buff *skb, struct ip_vs_proto_data *pd,
struct net *net;
struct ip_vs_service *svc;
struct tcphdr _tcph, *th;
+ struct netns_ipvs *ipvs;
th = skb_header_pointer(skb, iph->len, sizeof(_tcph), &_tcph);
if (th == NULL) {
@@ -46,18 +47,20 @@ tcp_conn_schedule(int af, struct sk_buff *skb, struct ip_vs_proto_data *pd,
return 0;
}
net = skb_net(skb);
+ ipvs = net_ipvs(net);
/* No !th->ack check to allow scheduling on SYN+ACK for Active FTP */
- if (th->syn &&
- (svc = ip_vs_service_get(net, af, skb->mark, iph->protocol,
- &iph->daddr, th->dest))) {
+ rcu_read_lock();
+ if ((th->syn || sysctl_sloppy_tcp(ipvs)) && !th->rst &&
+ (svc = ip_vs_service_find(net, af, skb->mark, iph->protocol,
+ &iph->daddr, th->dest))) {
int ignored;
- if (ip_vs_todrop(net_ipvs(net))) {
+ if (ip_vs_todrop(ipvs)) {
/*
* It seems that we are very loaded.
* We have to drop this packet :(
*/
- ip_vs_service_put(svc);
+ rcu_read_unlock();
*verdict = NF_DROP;
return 0;
}
@@ -70,14 +73,13 @@ tcp_conn_schedule(int af, struct sk_buff *skb, struct ip_vs_proto_data *pd,
if (!*cpp && ignored <= 0) {
if (!ignored)
*verdict = ip_vs_leave(svc, skb, pd, iph);
- else {
- ip_vs_service_put(svc);
+ else
*verdict = NF_DROP;
- }
+ rcu_read_unlock();
return 0;
}
- ip_vs_service_put(svc);
}
+ rcu_read_unlock();
/* NF_ACCEPT */
return 1;
}
@@ -401,7 +403,7 @@ static struct tcp_states_t tcp_states [] = {
/* sNO, sES, sSS, sSR, sFW, sTW, sCL, sCW, sLA, sLI, sSA */
/*syn*/ {{sSR, sES, sES, sSR, sSR, sSR, sSR, sSR, sSR, sSR, sSR }},
/*fin*/ {{sCL, sCW, sSS, sTW, sTW, sTW, sCL, sCW, sLA, sLI, sTW }},
-/*ack*/ {{sCL, sES, sSS, sES, sFW, sTW, sCL, sCW, sCL, sLI, sES }},
+/*ack*/ {{sES, sES, sSS, sES, sFW, sTW, sCL, sCW, sCL, sLI, sES }},
/*rst*/ {{sCL, sCL, sCL, sSR, sCL, sCL, sCL, sCL, sLA, sLI, sSR }},
/* OUTPUT */
@@ -415,7 +417,7 @@ static struct tcp_states_t tcp_states [] = {
/* sNO, sES, sSS, sSR, sFW, sTW, sCL, sCW, sLA, sLI, sSA */
/*syn*/ {{sSR, sES, sES, sSR, sSR, sSR, sSR, sSR, sSR, sSR, sSR }},
/*fin*/ {{sCL, sFW, sSS, sTW, sFW, sTW, sCL, sCW, sLA, sLI, sTW }},
-/*ack*/ {{sCL, sES, sSS, sES, sFW, sTW, sCL, sCW, sCL, sLI, sES }},
+/*ack*/ {{sES, sES, sSS, sES, sFW, sTW, sCL, sCW, sCL, sLI, sES }},
/*rst*/ {{sCL, sCL, sCL, sSR, sCL, sCL, sCL, sCL, sLA, sLI, sCL }},
};
@@ -424,7 +426,7 @@ static struct tcp_states_t tcp_states_dos [] = {
/* sNO, sES, sSS, sSR, sFW, sTW, sCL, sCW, sLA, sLI, sSA */
/*syn*/ {{sSR, sES, sES, sSR, sSR, sSR, sSR, sSR, sSR, sSR, sSA }},
/*fin*/ {{sCL, sCW, sSS, sTW, sTW, sTW, sCL, sCW, sLA, sLI, sSA }},
-/*ack*/ {{sCL, sES, sSS, sSR, sFW, sTW, sCL, sCW, sCL, sLI, sSA }},
+/*ack*/ {{sES, sES, sSS, sSR, sFW, sTW, sCL, sCW, sCL, sLI, sSA }},
/*rst*/ {{sCL, sCL, sCL, sSR, sCL, sCL, sCL, sCL, sLA, sLI, sCL }},
/* OUTPUT */
@@ -438,7 +440,7 @@ static struct tcp_states_t tcp_states_dos [] = {
/* sNO, sES, sSS, sSR, sFW, sTW, sCL, sCW, sLA, sLI, sSA */
/*syn*/ {{sSA, sES, sES, sSR, sSA, sSA, sSA, sSA, sSA, sSA, sSA }},
/*fin*/ {{sCL, sFW, sSS, sTW, sFW, sTW, sCL, sCW, sLA, sLI, sTW }},
-/*ack*/ {{sCL, sES, sSS, sES, sFW, sTW, sCL, sCW, sCL, sLI, sES }},
+/*ack*/ {{sES, sES, sSS, sES, sFW, sTW, sCL, sCW, sCL, sLI, sES }},
/*rst*/ {{sCL, sCL, sCL, sSR, sCL, sCL, sCL, sCL, sLA, sLI, sCL }},
};
@@ -557,9 +559,9 @@ tcp_state_transition(struct ip_vs_conn *cp, int direction,
if (th == NULL)
return;
- spin_lock(&cp->lock);
+ spin_lock_bh(&cp->lock);
set_tcp_state(pd, cp, direction, th);
- spin_unlock(&cp->lock);
+ spin_unlock_bh(&cp->lock);
}
static inline __u16 tcp_app_hashkey(__be16 port)
@@ -580,18 +582,16 @@ static int tcp_register_app(struct net *net, struct ip_vs_app *inc)
hash = tcp_app_hashkey(port);
- spin_lock_bh(&ipvs->tcp_app_lock);
list_for_each_entry(i, &ipvs->tcp_apps[hash], p_list) {
if (i->port == port) {
ret = -EEXIST;
goto out;
}
}
- list_add(&inc->p_list, &ipvs->tcp_apps[hash]);
+ list_add_rcu(&inc->p_list, &ipvs->tcp_apps[hash]);
atomic_inc(&pd->appcnt);
out:
- spin_unlock_bh(&ipvs->tcp_app_lock);
return ret;
}
@@ -599,13 +599,10 @@ static int tcp_register_app(struct net *net, struct ip_vs_app *inc)
static void
tcp_unregister_app(struct net *net, struct ip_vs_app *inc)
{
- struct netns_ipvs *ipvs = net_ipvs(net);
struct ip_vs_proto_data *pd = ip_vs_proto_data_get(net, IPPROTO_TCP);
- spin_lock_bh(&ipvs->tcp_app_lock);
atomic_dec(&pd->appcnt);
- list_del(&inc->p_list);
- spin_unlock_bh(&ipvs->tcp_app_lock);
+ list_del_rcu(&inc->p_list);
}
@@ -624,12 +621,12 @@ tcp_app_conn_bind(struct ip_vs_conn *cp)
/* Lookup application incarnations and bind the right one */
hash = tcp_app_hashkey(cp->vport);
- spin_lock(&ipvs->tcp_app_lock);
- list_for_each_entry(inc, &ipvs->tcp_apps[hash], p_list) {
+ rcu_read_lock();
+ list_for_each_entry_rcu(inc, &ipvs->tcp_apps[hash], p_list) {
if (inc->port == cp->vport) {
if (unlikely(!ip_vs_app_inc_get(inc)))
break;
- spin_unlock(&ipvs->tcp_app_lock);
+ rcu_read_unlock();
IP_VS_DBG_BUF(9, "%s(): Binding conn %s:%u->"
"%s:%u to app %s on port %u\n",
@@ -646,7 +643,7 @@ tcp_app_conn_bind(struct ip_vs_conn *cp)
goto out;
}
}
- spin_unlock(&ipvs->tcp_app_lock);
+ rcu_read_unlock();
out:
return result;
@@ -660,11 +657,11 @@ void ip_vs_tcp_conn_listen(struct net *net, struct ip_vs_conn *cp)
{
struct ip_vs_proto_data *pd = ip_vs_proto_data_get(net, IPPROTO_TCP);
- spin_lock(&cp->lock);
+ spin_lock_bh(&cp->lock);
cp->state = IP_VS_TCP_S_LISTEN;
cp->timeout = (pd ? pd->timeout_table[IP_VS_TCP_S_LISTEN]
: tcp_timeouts[IP_VS_TCP_S_LISTEN]);
- spin_unlock(&cp->lock);
+ spin_unlock_bh(&cp->lock);
}
/* ---------------------------------------------
@@ -676,7 +673,6 @@ static int __ip_vs_tcp_init(struct net *net, struct ip_vs_proto_data *pd)
struct netns_ipvs *ipvs = net_ipvs(net);
ip_vs_init_hash_table(ipvs->tcp_apps, TCP_APP_TAB_SIZE);
- spin_lock_init(&ipvs->tcp_app_lock);
pd->timeout_table = ip_vs_create_timeout_table((int *)tcp_timeouts,
sizeof(tcp_timeouts));
if (!pd->timeout_table)
diff --git a/net/netfilter/ipvs/ip_vs_proto_udp.c b/net/netfilter/ipvs/ip_vs_proto_udp.c
index 503a842c90d..b62a3c0ff9b 100644
--- a/net/netfilter/ipvs/ip_vs_proto_udp.c
+++ b/net/netfilter/ipvs/ip_vs_proto_udp.c
@@ -44,8 +44,9 @@ udp_conn_schedule(int af, struct sk_buff *skb, struct ip_vs_proto_data *pd,
return 0;
}
net = skb_net(skb);
- svc = ip_vs_service_get(net, af, skb->mark, iph->protocol,
- &iph->daddr, uh->dest);
+ rcu_read_lock();
+ svc = ip_vs_service_find(net, af, skb->mark, iph->protocol,
+ &iph->daddr, uh->dest);
if (svc) {
int ignored;
@@ -54,7 +55,7 @@ udp_conn_schedule(int af, struct sk_buff *skb, struct ip_vs_proto_data *pd,
* It seems that we are very loaded.
* We have to drop this packet :(
*/
- ip_vs_service_put(svc);
+ rcu_read_unlock();
*verdict = NF_DROP;
return 0;
}
@@ -67,14 +68,13 @@ udp_conn_schedule(int af, struct sk_buff *skb, struct ip_vs_proto_data *pd,
if (!*cpp && ignored <= 0) {
if (!ignored)
*verdict = ip_vs_leave(svc, skb, pd, iph);
- else {
- ip_vs_service_put(svc);
+ else
*verdict = NF_DROP;
- }
+ rcu_read_unlock();
return 0;
}
- ip_vs_service_put(svc);
}
+ rcu_read_unlock();
/* NF_ACCEPT */
return 1;
}
@@ -359,19 +359,16 @@ static int udp_register_app(struct net *net, struct ip_vs_app *inc)
hash = udp_app_hashkey(port);
-
- spin_lock_bh(&ipvs->udp_app_lock);
list_for_each_entry(i, &ipvs->udp_apps[hash], p_list) {
if (i->port == port) {
ret = -EEXIST;
goto out;
}
}
- list_add(&inc->p_list, &ipvs->udp_apps[hash]);
+ list_add_rcu(&inc->p_list, &ipvs->udp_apps[hash]);
atomic_inc(&pd->appcnt);
out:
- spin_unlock_bh(&ipvs->udp_app_lock);
return ret;
}
@@ -380,12 +377,9 @@ static void
udp_unregister_app(struct net *net, struct ip_vs_app *inc)
{
struct ip_vs_proto_data *pd = ip_vs_proto_data_get(net, IPPROTO_UDP);
- struct netns_ipvs *ipvs = net_ipvs(net);
- spin_lock_bh(&ipvs->udp_app_lock);
atomic_dec(&pd->appcnt);
- list_del(&inc->p_list);
- spin_unlock_bh(&ipvs->udp_app_lock);
+ list_del_rcu(&inc->p_list);
}
@@ -403,12 +397,12 @@ static int udp_app_conn_bind(struct ip_vs_conn *cp)
/* Lookup application incarnations and bind the right one */
hash = udp_app_hashkey(cp->vport);
- spin_lock(&ipvs->udp_app_lock);
- list_for_each_entry(inc, &ipvs->udp_apps[hash], p_list) {
+ rcu_read_lock();
+ list_for_each_entry_rcu(inc, &ipvs->udp_apps[hash], p_list) {
if (inc->port == cp->vport) {
if (unlikely(!ip_vs_app_inc_get(inc)))
break;
- spin_unlock(&ipvs->udp_app_lock);
+ rcu_read_unlock();
IP_VS_DBG_BUF(9, "%s(): Binding conn %s:%u->"
"%s:%u to app %s on port %u\n",
@@ -425,7 +419,7 @@ static int udp_app_conn_bind(struct ip_vs_conn *cp)
goto out;
}
}
- spin_unlock(&ipvs->udp_app_lock);
+ rcu_read_unlock();
out:
return result;
@@ -467,7 +461,6 @@ static int __udp_init(struct net *net, struct ip_vs_proto_data *pd)
struct netns_ipvs *ipvs = net_ipvs(net);
ip_vs_init_hash_table(ipvs->udp_apps, UDP_APP_TAB_SIZE);
- spin_lock_init(&ipvs->udp_app_lock);
pd->timeout_table = ip_vs_create_timeout_table((int *)udp_timeouts,
sizeof(udp_timeouts));
if (!pd->timeout_table)
diff --git a/net/netfilter/ipvs/ip_vs_rr.c b/net/netfilter/ipvs/ip_vs_rr.c
index c49b388d108..176b87c35e3 100644
--- a/net/netfilter/ipvs/ip_vs_rr.c
+++ b/net/netfilter/ipvs/ip_vs_rr.c
@@ -35,9 +35,18 @@ static int ip_vs_rr_init_svc(struct ip_vs_service *svc)
}
-static int ip_vs_rr_update_svc(struct ip_vs_service *svc)
+static int ip_vs_rr_del_dest(struct ip_vs_service *svc, struct ip_vs_dest *dest)
{
- svc->sched_data = &svc->destinations;
+ struct list_head *p;
+
+ spin_lock_bh(&svc->sched_lock);
+ p = (struct list_head *) svc->sched_data;
+ /* dest is already unlinked, so p->prev is not valid but
+ * p->next is valid, use it to reach previous entry.
+ */
+ if (p == &dest->n_list)
+ svc->sched_data = p->next->prev;
+ spin_unlock_bh(&svc->sched_lock);
return 0;
}
@@ -46,38 +55,44 @@ static int ip_vs_rr_update_svc(struct ip_vs_service *svc)
* Round-Robin Scheduling
*/
static struct ip_vs_dest *
-ip_vs_rr_schedule(struct ip_vs_service *svc, const struct sk_buff *skb)
+ip_vs_rr_schedule(struct ip_vs_service *svc, const struct sk_buff *skb,
+ struct ip_vs_iphdr *iph)
{
- struct list_head *p, *q;
- struct ip_vs_dest *dest;
+ struct list_head *p;
+ struct ip_vs_dest *dest, *last;
+ int pass = 0;
IP_VS_DBG(6, "%s(): Scheduling...\n", __func__);
- write_lock(&svc->sched_lock);
- p = (struct list_head *)svc->sched_data;
- p = p->next;
- q = p;
+ spin_lock_bh(&svc->sched_lock);
+ p = (struct list_head *) svc->sched_data;
+ last = dest = list_entry(p, struct ip_vs_dest, n_list);
+
do {
- /* skip list head */
- if (q == &svc->destinations) {
- q = q->next;
- continue;
+ list_for_each_entry_continue_rcu(dest,
+ &svc->destinations,
+ n_list) {
+ if (!(dest->flags & IP_VS_DEST_F_OVERLOAD) &&
+ atomic_read(&dest->weight) > 0)
+ /* HIT */
+ goto out;
+ if (dest == last)
+ goto stop;
}
-
- dest = list_entry(q, struct ip_vs_dest, n_list);
- if (!(dest->flags & IP_VS_DEST_F_OVERLOAD) &&
- atomic_read(&dest->weight) > 0)
- /* HIT */
- goto out;
- q = q->next;
- } while (q != p);
- write_unlock(&svc->sched_lock);
+ pass++;
+ /* Previous dest could be unlinked, do not loop forever.
+ * If we stay at head there is no need for 2nd pass.
+ */
+ } while (pass < 2 && p != &svc->destinations);
+
+stop:
+ spin_unlock_bh(&svc->sched_lock);
ip_vs_scheduler_err(svc, "no destination available");
return NULL;
out:
- svc->sched_data = q;
- write_unlock(&svc->sched_lock);
+ svc->sched_data = &dest->n_list;
+ spin_unlock_bh(&svc->sched_lock);
IP_VS_DBG_BUF(6, "RR: server %s:%u "
"activeconns %d refcnt %d weight %d\n",
IP_VS_DBG_ADDR(svc->af, &dest->addr), ntohs(dest->port),
@@ -94,7 +109,8 @@ static struct ip_vs_scheduler ip_vs_rr_scheduler = {
.module = THIS_MODULE,
.n_list = LIST_HEAD_INIT(ip_vs_rr_scheduler.n_list),
.init_service = ip_vs_rr_init_svc,
- .update_service = ip_vs_rr_update_svc,
+ .add_dest = NULL,
+ .del_dest = ip_vs_rr_del_dest,
.schedule = ip_vs_rr_schedule,
};
@@ -106,6 +122,7 @@ static int __init ip_vs_rr_init(void)
static void __exit ip_vs_rr_cleanup(void)
{
unregister_ip_vs_scheduler(&ip_vs_rr_scheduler);
+ synchronize_rcu();
}
module_init(ip_vs_rr_init);
diff --git a/net/netfilter/ipvs/ip_vs_sched.c b/net/netfilter/ipvs/ip_vs_sched.c
index d6bf20d6cdb..4dbcda6258b 100644
--- a/net/netfilter/ipvs/ip_vs_sched.c
+++ b/net/netfilter/ipvs/ip_vs_sched.c
@@ -35,8 +35,8 @@ EXPORT_SYMBOL(ip_vs_scheduler_err);
*/
static LIST_HEAD(ip_vs_schedulers);
-/* lock for service table */
-static DEFINE_SPINLOCK(ip_vs_sched_lock);
+/* semaphore for schedulers */
+static DEFINE_MUTEX(ip_vs_sched_mutex);
/*
@@ -47,8 +47,6 @@ int ip_vs_bind_scheduler(struct ip_vs_service *svc,
{
int ret;
- svc->scheduler = scheduler;
-
if (scheduler->init_service) {
ret = scheduler->init_service(svc);
if (ret) {
@@ -56,7 +54,7 @@ int ip_vs_bind_scheduler(struct ip_vs_service *svc,
return ret;
}
}
-
+ rcu_assign_pointer(svc->scheduler, scheduler);
return 0;
}
@@ -64,22 +62,19 @@ int ip_vs_bind_scheduler(struct ip_vs_service *svc,
/*
* Unbind a service with its scheduler
*/
-int ip_vs_unbind_scheduler(struct ip_vs_service *svc)
+void ip_vs_unbind_scheduler(struct ip_vs_service *svc,
+ struct ip_vs_scheduler *sched)
{
- struct ip_vs_scheduler *sched = svc->scheduler;
+ struct ip_vs_scheduler *cur_sched;
- if (!sched)
- return 0;
+ cur_sched = rcu_dereference_protected(svc->scheduler, 1);
+ /* This check proves that old 'sched' was installed */
+ if (!cur_sched)
+ return;
- if (sched->done_service) {
- if (sched->done_service(svc) != 0) {
- pr_err("%s(): done error\n", __func__);
- return -EINVAL;
- }
- }
-
- svc->scheduler = NULL;
- return 0;
+ if (sched->done_service)
+ sched->done_service(svc);
+ /* svc->scheduler can not be set to NULL */
}
@@ -92,7 +87,7 @@ static struct ip_vs_scheduler *ip_vs_sched_getbyname(const char *sched_name)
IP_VS_DBG(2, "%s(): sched_name \"%s\"\n", __func__, sched_name);
- spin_lock_bh(&ip_vs_sched_lock);
+ mutex_lock(&ip_vs_sched_mutex);
list_for_each_entry(sched, &ip_vs_schedulers, n_list) {
/*
@@ -106,14 +101,14 @@ static struct ip_vs_scheduler *ip_vs_sched_getbyname(const char *sched_name)
}
if (strcmp(sched_name, sched->name)==0) {
/* HIT */
- spin_unlock_bh(&ip_vs_sched_lock);
+ mutex_unlock(&ip_vs_sched_mutex);
return sched;
}
if (sched->module)
module_put(sched->module);
}
- spin_unlock_bh(&ip_vs_sched_lock);
+ mutex_unlock(&ip_vs_sched_mutex);
return NULL;
}
@@ -153,21 +148,21 @@ void ip_vs_scheduler_put(struct ip_vs_scheduler *scheduler)
void ip_vs_scheduler_err(struct ip_vs_service *svc, const char *msg)
{
+ struct ip_vs_scheduler *sched;
+
+ sched = rcu_dereference(svc->scheduler);
if (svc->fwmark) {
IP_VS_ERR_RL("%s: FWM %u 0x%08X - %s\n",
- svc->scheduler->name, svc->fwmark,
- svc->fwmark, msg);
+ sched->name, svc->fwmark, svc->fwmark, msg);
#ifdef CONFIG_IP_VS_IPV6
} else if (svc->af == AF_INET6) {
IP_VS_ERR_RL("%s: %s [%pI6c]:%d - %s\n",
- svc->scheduler->name,
- ip_vs_proto_name(svc->protocol),
+ sched->name, ip_vs_proto_name(svc->protocol),
&svc->addr.in6, ntohs(svc->port), msg);
#endif
} else {
IP_VS_ERR_RL("%s: %s %pI4:%d - %s\n",
- svc->scheduler->name,
- ip_vs_proto_name(svc->protocol),
+ sched->name, ip_vs_proto_name(svc->protocol),
&svc->addr.ip, ntohs(svc->port), msg);
}
}
@@ -192,10 +187,10 @@ int register_ip_vs_scheduler(struct ip_vs_scheduler *scheduler)
/* increase the module use count */
ip_vs_use_count_inc();
- spin_lock_bh(&ip_vs_sched_lock);
+ mutex_lock(&ip_vs_sched_mutex);
if (!list_empty(&scheduler->n_list)) {
- spin_unlock_bh(&ip_vs_sched_lock);
+ mutex_unlock(&ip_vs_sched_mutex);
ip_vs_use_count_dec();
pr_err("%s(): [%s] scheduler already linked\n",
__func__, scheduler->name);
@@ -208,7 +203,7 @@ int register_ip_vs_scheduler(struct ip_vs_scheduler *scheduler)
*/
list_for_each_entry(sched, &ip_vs_schedulers, n_list) {
if (strcmp(scheduler->name, sched->name) == 0) {
- spin_unlock_bh(&ip_vs_sched_lock);
+ mutex_unlock(&ip_vs_sched_mutex);
ip_vs_use_count_dec();
pr_err("%s(): [%s] scheduler already existed "
"in the system\n", __func__, scheduler->name);
@@ -219,7 +214,7 @@ int register_ip_vs_scheduler(struct ip_vs_scheduler *scheduler)
* Add it into the d-linked scheduler list
*/
list_add(&scheduler->n_list, &ip_vs_schedulers);
- spin_unlock_bh(&ip_vs_sched_lock);
+ mutex_unlock(&ip_vs_sched_mutex);
pr_info("[%s] scheduler registered.\n", scheduler->name);
@@ -237,9 +232,9 @@ int unregister_ip_vs_scheduler(struct ip_vs_scheduler *scheduler)
return -EINVAL;
}
- spin_lock_bh(&ip_vs_sched_lock);
+ mutex_lock(&ip_vs_sched_mutex);
if (list_empty(&scheduler->n_list)) {
- spin_unlock_bh(&ip_vs_sched_lock);
+ mutex_unlock(&ip_vs_sched_mutex);
pr_err("%s(): [%s] scheduler is not in the list. failed\n",
__func__, scheduler->name);
return -EINVAL;
@@ -249,7 +244,7 @@ int unregister_ip_vs_scheduler(struct ip_vs_scheduler *scheduler)
* Remove it from the d-linked scheduler list
*/
list_del(&scheduler->n_list);
- spin_unlock_bh(&ip_vs_sched_lock);
+ mutex_unlock(&ip_vs_sched_mutex);
/* decrease the module use count */
ip_vs_use_count_dec();
diff --git a/net/netfilter/ipvs/ip_vs_sed.c b/net/netfilter/ipvs/ip_vs_sed.c
index 89ead246ed3..e446b9fa742 100644
--- a/net/netfilter/ipvs/ip_vs_sed.c
+++ b/net/netfilter/ipvs/ip_vs_sed.c
@@ -44,7 +44,7 @@
#include <net/ip_vs.h>
-static inline unsigned int
+static inline int
ip_vs_sed_dest_overhead(struct ip_vs_dest *dest)
{
/*
@@ -59,10 +59,11 @@ ip_vs_sed_dest_overhead(struct ip_vs_dest *dest)
* Weighted Least Connection scheduling
*/
static struct ip_vs_dest *
-ip_vs_sed_schedule(struct ip_vs_service *svc, const struct sk_buff *skb)
+ip_vs_sed_schedule(struct ip_vs_service *svc, const struct sk_buff *skb,
+ struct ip_vs_iphdr *iph)
{
struct ip_vs_dest *dest, *least;
- unsigned int loh, doh;
+ int loh, doh;
IP_VS_DBG(6, "%s(): Scheduling...\n", __func__);
@@ -79,7 +80,7 @@ ip_vs_sed_schedule(struct ip_vs_service *svc, const struct sk_buff *skb)
* new connections.
*/
- list_for_each_entry(dest, &svc->destinations, n_list) {
+ list_for_each_entry_rcu(dest, &svc->destinations, n_list) {
if (!(dest->flags & IP_VS_DEST_F_OVERLOAD) &&
atomic_read(&dest->weight) > 0) {
least = dest;
@@ -94,12 +95,12 @@ ip_vs_sed_schedule(struct ip_vs_service *svc, const struct sk_buff *skb)
* Find the destination with the least load.
*/
nextstage:
- list_for_each_entry_continue(dest, &svc->destinations, n_list) {
+ list_for_each_entry_continue_rcu(dest, &svc->destinations, n_list) {
if (dest->flags & IP_VS_DEST_F_OVERLOAD)
continue;
doh = ip_vs_sed_dest_overhead(dest);
- if (loh * atomic_read(&dest->weight) >
- doh * atomic_read(&least->weight)) {
+ if ((__s64)loh * atomic_read(&dest->weight) >
+ (__s64)doh * atomic_read(&least->weight)) {
least = dest;
loh = doh;
}
@@ -134,6 +135,7 @@ static int __init ip_vs_sed_init(void)
static void __exit ip_vs_sed_cleanup(void)
{
unregister_ip_vs_scheduler(&ip_vs_sed_scheduler);
+ synchronize_rcu();
}
module_init(ip_vs_sed_init);
diff --git a/net/netfilter/ipvs/ip_vs_sh.c b/net/netfilter/ipvs/ip_vs_sh.c
index e3312699462..cc65b2f42cd 100644
--- a/net/netfilter/ipvs/ip_vs_sh.c
+++ b/net/netfilter/ipvs/ip_vs_sh.c
@@ -48,12 +48,16 @@
#include <net/ip_vs.h>
+#include <net/tcp.h>
+#include <linux/udp.h>
+#include <linux/sctp.h>
+
/*
* IPVS SH bucket
*/
struct ip_vs_sh_bucket {
- struct ip_vs_dest *dest; /* real server (cache) */
+ struct ip_vs_dest __rcu *dest; /* real server (cache) */
};
/*
@@ -66,11 +70,24 @@ struct ip_vs_sh_bucket {
#define IP_VS_SH_TAB_SIZE (1 << IP_VS_SH_TAB_BITS)
#define IP_VS_SH_TAB_MASK (IP_VS_SH_TAB_SIZE - 1)
+struct ip_vs_sh_state {
+ struct rcu_head rcu_head;
+ struct ip_vs_sh_bucket buckets[IP_VS_SH_TAB_SIZE];
+};
+
+/* Helper function to determine if server is unavailable */
+static inline bool is_unavailable(struct ip_vs_dest *dest)
+{
+ return atomic_read(&dest->weight) <= 0 ||
+ dest->flags & IP_VS_DEST_F_OVERLOAD;
+}
/*
* Returns hash value for IPVS SH entry
*/
-static inline unsigned int ip_vs_sh_hashkey(int af, const union nf_inet_addr *addr)
+static inline unsigned int
+ip_vs_sh_hashkey(int af, const union nf_inet_addr *addr,
+ __be16 port, unsigned int offset)
{
__be32 addr_fold = addr->ip;
@@ -79,7 +96,8 @@ static inline unsigned int ip_vs_sh_hashkey(int af, const union nf_inet_addr *ad
addr_fold = addr->ip6[0]^addr->ip6[1]^
addr->ip6[2]^addr->ip6[3];
#endif
- return (ntohl(addr_fold)*2654435761UL) & IP_VS_SH_TAB_MASK;
+ return (offset + (ntohs(port) + ntohl(addr_fold))*2654435761UL) &
+ IP_VS_SH_TAB_MASK;
}
@@ -87,38 +105,91 @@ static inline unsigned int ip_vs_sh_hashkey(int af, const union nf_inet_addr *ad
* Get ip_vs_dest associated with supplied parameters.
*/
static inline struct ip_vs_dest *
-ip_vs_sh_get(int af, struct ip_vs_sh_bucket *tbl,
- const union nf_inet_addr *addr)
+ip_vs_sh_get(struct ip_vs_service *svc, struct ip_vs_sh_state *s,
+ const union nf_inet_addr *addr, __be16 port)
{
- return (tbl[ip_vs_sh_hashkey(af, addr)]).dest;
+ unsigned int hash = ip_vs_sh_hashkey(svc->af, addr, port, 0);
+ struct ip_vs_dest *dest = rcu_dereference(s->buckets[hash].dest);
+
+ return (!dest || is_unavailable(dest)) ? NULL : dest;
}
+/* As ip_vs_sh_get, but with fallback if selected server is unavailable
+ *
+ * The fallback strategy loops around the table starting from a "random"
+ * point (in fact, it is chosen to be the original hash value to make the
+ * algorithm deterministic) to find a new server.
+ */
+static inline struct ip_vs_dest *
+ip_vs_sh_get_fallback(struct ip_vs_service *svc, struct ip_vs_sh_state *s,
+ const union nf_inet_addr *addr, __be16 port)
+{
+ unsigned int offset, roffset;
+ unsigned int hash, ihash;
+ struct ip_vs_dest *dest;
+
+ /* first try the dest it's supposed to go to */
+ ihash = ip_vs_sh_hashkey(svc->af, addr, port, 0);
+ dest = rcu_dereference(s->buckets[ihash].dest);
+ if (!dest)
+ return NULL;
+ if (!is_unavailable(dest))
+ return dest;
+
+ IP_VS_DBG_BUF(6, "SH: selected unavailable server %s:%d, reselecting",
+ IP_VS_DBG_ADDR(svc->af, &dest->addr), ntohs(dest->port));
+
+ /* if the original dest is unavailable, loop around the table
+ * starting from ihash to find a new dest
+ */
+ for (offset = 0; offset < IP_VS_SH_TAB_SIZE; offset++) {
+ roffset = (offset + ihash) % IP_VS_SH_TAB_SIZE;
+ hash = ip_vs_sh_hashkey(svc->af, addr, port, roffset);
+ dest = rcu_dereference(s->buckets[hash].dest);
+ if (!dest)
+ break;
+ if (!is_unavailable(dest))
+ return dest;
+ IP_VS_DBG_BUF(6, "SH: selected unavailable "
+ "server %s:%d (offset %d), reselecting",
+ IP_VS_DBG_ADDR(svc->af, &dest->addr),
+ ntohs(dest->port), roffset);
+ }
+
+ return NULL;
+}
+
/*
* Assign all the hash buckets of the specified table with the service.
*/
static int
-ip_vs_sh_assign(struct ip_vs_sh_bucket *tbl, struct ip_vs_service *svc)
+ip_vs_sh_reassign(struct ip_vs_sh_state *s, struct ip_vs_service *svc)
{
int i;
struct ip_vs_sh_bucket *b;
struct list_head *p;
struct ip_vs_dest *dest;
int d_count;
+ bool empty;
- b = tbl;
+ b = &s->buckets[0];
p = &svc->destinations;
+ empty = list_empty(p);
d_count = 0;
for (i=0; i<IP_VS_SH_TAB_SIZE; i++) {
- if (list_empty(p)) {
- b->dest = NULL;
- } else {
+ dest = rcu_dereference_protected(b->dest, 1);
+ if (dest)
+ ip_vs_dest_put(dest);
+ if (empty)
+ RCU_INIT_POINTER(b->dest, NULL);
+ else {
if (p == &svc->destinations)
p = p->next;
dest = list_entry(p, struct ip_vs_dest, n_list);
- atomic_inc(&dest->refcnt);
- b->dest = dest;
+ ip_vs_dest_hold(dest);
+ RCU_INIT_POINTER(b->dest, dest);
IP_VS_DBG_BUF(6, "assigned i: %d dest: %s weight: %d\n",
i, IP_VS_DBG_ADDR(svc->af, &dest->addr),
@@ -140,16 +211,18 @@ ip_vs_sh_assign(struct ip_vs_sh_bucket *tbl, struct ip_vs_service *svc)
/*
* Flush all the hash buckets of the specified table.
*/
-static void ip_vs_sh_flush(struct ip_vs_sh_bucket *tbl)
+static void ip_vs_sh_flush(struct ip_vs_sh_state *s)
{
int i;
struct ip_vs_sh_bucket *b;
+ struct ip_vs_dest *dest;
- b = tbl;
+ b = &s->buckets[0];
for (i=0; i<IP_VS_SH_TAB_SIZE; i++) {
- if (b->dest) {
- atomic_dec(&b->dest->refcnt);
- b->dest = NULL;
+ dest = rcu_dereference_protected(b->dest, 1);
+ if (dest) {
+ ip_vs_dest_put(dest);
+ RCU_INIT_POINTER(b->dest, NULL);
}
b++;
}
@@ -158,63 +231,84 @@ static void ip_vs_sh_flush(struct ip_vs_sh_bucket *tbl)
static int ip_vs_sh_init_svc(struct ip_vs_service *svc)
{
- struct ip_vs_sh_bucket *tbl;
+ struct ip_vs_sh_state *s;
/* allocate the SH table for this service */
- tbl = kmalloc(sizeof(struct ip_vs_sh_bucket)*IP_VS_SH_TAB_SIZE,
- GFP_KERNEL);
- if (tbl == NULL)
+ s = kzalloc(sizeof(struct ip_vs_sh_state), GFP_KERNEL);
+ if (s == NULL)
return -ENOMEM;
- svc->sched_data = tbl;
+ svc->sched_data = s;
IP_VS_DBG(6, "SH hash table (memory=%Zdbytes) allocated for "
"current service\n",
sizeof(struct ip_vs_sh_bucket)*IP_VS_SH_TAB_SIZE);
- /* assign the hash buckets with the updated service */
- ip_vs_sh_assign(tbl, svc);
+ /* assign the hash buckets with current dests */
+ ip_vs_sh_reassign(s, svc);
return 0;
}
-static int ip_vs_sh_done_svc(struct ip_vs_service *svc)
+static void ip_vs_sh_done_svc(struct ip_vs_service *svc)
{
- struct ip_vs_sh_bucket *tbl = svc->sched_data;
+ struct ip_vs_sh_state *s = svc->sched_data;
/* got to clean up hash buckets here */
- ip_vs_sh_flush(tbl);
+ ip_vs_sh_flush(s);
/* release the table itself */
- kfree(svc->sched_data);
+ kfree_rcu(s, rcu_head);
IP_VS_DBG(6, "SH hash table (memory=%Zdbytes) released\n",
sizeof(struct ip_vs_sh_bucket)*IP_VS_SH_TAB_SIZE);
-
- return 0;
}
-static int ip_vs_sh_update_svc(struct ip_vs_service *svc)
+static int ip_vs_sh_dest_changed(struct ip_vs_service *svc,
+ struct ip_vs_dest *dest)
{
- struct ip_vs_sh_bucket *tbl = svc->sched_data;
-
- /* got to clean up hash buckets here */
- ip_vs_sh_flush(tbl);
+ struct ip_vs_sh_state *s = svc->sched_data;
/* assign the hash buckets with the updated service */
- ip_vs_sh_assign(tbl, svc);
+ ip_vs_sh_reassign(s, svc);
return 0;
}
-/*
- * If the dest flags is set with IP_VS_DEST_F_OVERLOAD,
- * consider that the server is overloaded here.
- */
-static inline int is_overloaded(struct ip_vs_dest *dest)
+/* Helper function to get port number */
+static inline __be16
+ip_vs_sh_get_port(const struct sk_buff *skb, struct ip_vs_iphdr *iph)
{
- return dest->flags & IP_VS_DEST_F_OVERLOAD;
+ __be16 port;
+ struct tcphdr _tcph, *th;
+ struct udphdr _udph, *uh;
+ sctp_sctphdr_t _sctph, *sh;
+
+ switch (iph->protocol) {
+ case IPPROTO_TCP:
+ th = skb_header_pointer(skb, iph->len, sizeof(_tcph), &_tcph);
+ if (unlikely(th == NULL))
+ return 0;
+ port = th->source;
+ break;
+ case IPPROTO_UDP:
+ uh = skb_header_pointer(skb, iph->len, sizeof(_udph), &_udph);
+ if (unlikely(uh == NULL))
+ return 0;
+ port = uh->source;
+ break;
+ case IPPROTO_SCTP:
+ sh = skb_header_pointer(skb, iph->len, sizeof(_sctph), &_sctph);
+ if (unlikely(sh == NULL))
+ return 0;
+ port = sh->source;
+ break;
+ default:
+ port = 0;
+ }
+
+ return port;
}
@@ -222,28 +316,32 @@ static inline int is_overloaded(struct ip_vs_dest *dest)
* Source Hashing scheduling
*/
static struct ip_vs_dest *
-ip_vs_sh_schedule(struct ip_vs_service *svc, const struct sk_buff *skb)
+ip_vs_sh_schedule(struct ip_vs_service *svc, const struct sk_buff *skb,
+ struct ip_vs_iphdr *iph)
{
struct ip_vs_dest *dest;
- struct ip_vs_sh_bucket *tbl;
- struct ip_vs_iphdr iph;
-
- ip_vs_fill_iph_addr_only(svc->af, skb, &iph);
+ struct ip_vs_sh_state *s;
+ __be16 port = 0;
IP_VS_DBG(6, "ip_vs_sh_schedule(): Scheduling...\n");
- tbl = (struct ip_vs_sh_bucket *)svc->sched_data;
- dest = ip_vs_sh_get(svc->af, tbl, &iph.saddr);
- if (!dest
- || !(dest->flags & IP_VS_DEST_F_AVAILABLE)
- || atomic_read(&dest->weight) <= 0
- || is_overloaded(dest)) {
+ if (svc->flags & IP_VS_SVC_F_SCHED_SH_PORT)
+ port = ip_vs_sh_get_port(skb, iph);
+
+ s = (struct ip_vs_sh_state *) svc->sched_data;
+
+ if (svc->flags & IP_VS_SVC_F_SCHED_SH_FALLBACK)
+ dest = ip_vs_sh_get_fallback(svc, s, &iph->saddr, port);
+ else
+ dest = ip_vs_sh_get(svc, s, &iph->saddr, port);
+
+ if (!dest) {
ip_vs_scheduler_err(svc, "no destination available");
return NULL;
}
IP_VS_DBG_BUF(6, "SH: source IP address %s --> server %s:%d\n",
- IP_VS_DBG_ADDR(svc->af, &iph.saddr),
+ IP_VS_DBG_ADDR(svc->af, &iph->saddr),
IP_VS_DBG_ADDR(svc->af, &dest->addr),
ntohs(dest->port));
@@ -262,7 +360,9 @@ static struct ip_vs_scheduler ip_vs_sh_scheduler =
.n_list = LIST_HEAD_INIT(ip_vs_sh_scheduler.n_list),
.init_service = ip_vs_sh_init_svc,
.done_service = ip_vs_sh_done_svc,
- .update_service = ip_vs_sh_update_svc,
+ .add_dest = ip_vs_sh_dest_changed,
+ .del_dest = ip_vs_sh_dest_changed,
+ .upd_dest = ip_vs_sh_dest_changed,
.schedule = ip_vs_sh_schedule,
};
@@ -276,6 +376,7 @@ static int __init ip_vs_sh_init(void)
static void __exit ip_vs_sh_cleanup(void)
{
unregister_ip_vs_scheduler(&ip_vs_sh_scheduler);
+ synchronize_rcu();
}
diff --git a/net/netfilter/ipvs/ip_vs_sync.c b/net/netfilter/ipvs/ip_vs_sync.c
index effa10c9e4e..db801263ee9 100644
--- a/net/netfilter/ipvs/ip_vs_sync.c
+++ b/net/netfilter/ipvs/ip_vs_sync.c
@@ -246,7 +246,7 @@ struct ip_vs_sync_thread_data {
struct ip_vs_sync_mesg_v0 {
__u8 nr_conns;
__u8 syncid;
- __u16 size;
+ __be16 size;
/* ip_vs_sync_conn entries start here */
};
@@ -255,7 +255,7 @@ struct ip_vs_sync_mesg_v0 {
struct ip_vs_sync_mesg {
__u8 reserved; /* must be zero */
__u8 syncid;
- __u16 size;
+ __be16 size;
__u8 nr_conns;
__s8 version; /* SYNC_PROTO_VER */
__u16 spare;
@@ -335,7 +335,7 @@ ip_vs_sync_buff_create(struct netns_ipvs *ipvs)
sb->mesg->reserved = 0; /* old nr_conns i.e. must be zero now */
sb->mesg->version = SYNC_PROTO_VER;
sb->mesg->syncid = ipvs->master_syncid;
- sb->mesg->size = sizeof(struct ip_vs_sync_mesg);
+ sb->mesg->size = htons(sizeof(struct ip_vs_sync_mesg));
sb->mesg->nr_conns = 0;
sb->mesg->spare = 0;
sb->head = (unsigned char *)sb->mesg + sizeof(struct ip_vs_sync_mesg);
@@ -418,13 +418,23 @@ ip_vs_sync_buff_create_v0(struct netns_ipvs *ipvs)
mesg = (struct ip_vs_sync_mesg_v0 *)sb->mesg;
mesg->nr_conns = 0;
mesg->syncid = ipvs->master_syncid;
- mesg->size = sizeof(struct ip_vs_sync_mesg_v0);
+ mesg->size = htons(sizeof(struct ip_vs_sync_mesg_v0));
sb->head = (unsigned char *)mesg + sizeof(struct ip_vs_sync_mesg_v0);
sb->end = (unsigned char *)mesg + ipvs->send_mesg_maxlen;
sb->firstuse = jiffies;
return sb;
}
+/* Check if connection is controlled by persistence */
+static inline bool in_persistence(struct ip_vs_conn *cp)
+{
+ for (cp = cp->control; cp; cp = cp->control) {
+ if (cp->flags & IP_VS_CONN_F_TEMPLATE)
+ return true;
+ }
+ return false;
+}
+
/* Check if conn should be synced.
* pkts: conn packets, use sysctl_sync_threshold to avoid packet check
* - (1) sync_refresh_period: reduce sync rate. Additionally, retry
@@ -447,6 +457,8 @@ static int ip_vs_sync_conn_needed(struct netns_ipvs *ipvs,
/* Check if we sync in current state */
if (unlikely(cp->flags & IP_VS_CONN_F_TEMPLATE))
force = 0;
+ else if (unlikely(sysctl_sync_persist_mode(ipvs) && in_persistence(cp)))
+ return 0;
else if (likely(cp->protocol == IPPROTO_TCP)) {
if (!((1 << cp->state) &
((1 << IP_VS_TCP_S_ESTABLISHED) |
@@ -461,9 +473,10 @@ static int ip_vs_sync_conn_needed(struct netns_ipvs *ipvs,
} else if (unlikely(cp->protocol == IPPROTO_SCTP)) {
if (!((1 << cp->state) &
((1 << IP_VS_SCTP_S_ESTABLISHED) |
- (1 << IP_VS_SCTP_S_CLOSED) |
- (1 << IP_VS_SCTP_S_SHUT_ACK_CLI) |
- (1 << IP_VS_SCTP_S_SHUT_ACK_SER))))
+ (1 << IP_VS_SCTP_S_SHUTDOWN_SENT) |
+ (1 << IP_VS_SCTP_S_SHUTDOWN_RECEIVED) |
+ (1 << IP_VS_SCTP_S_SHUTDOWN_ACK_SENT) |
+ (1 << IP_VS_SCTP_S_CLOSED))))
return 0;
force = cp->state != cp->old_state;
if (force && cp->state != IP_VS_SCTP_S_ESTABLISHED)
@@ -531,9 +544,9 @@ static void ip_vs_sync_conn_v0(struct net *net, struct ip_vs_conn *cp,
if (!ip_vs_sync_conn_needed(ipvs, cp, pkts))
return;
- spin_lock(&ipvs->sync_buff_lock);
+ spin_lock_bh(&ipvs->sync_buff_lock);
if (!(ipvs->sync_state & IP_VS_STATE_MASTER)) {
- spin_unlock(&ipvs->sync_buff_lock);
+ spin_unlock_bh(&ipvs->sync_buff_lock);
return;
}
@@ -552,7 +565,7 @@ static void ip_vs_sync_conn_v0(struct net *net, struct ip_vs_conn *cp,
if (!buff) {
buff = ip_vs_sync_buff_create_v0(ipvs);
if (!buff) {
- spin_unlock(&ipvs->sync_buff_lock);
+ spin_unlock_bh(&ipvs->sync_buff_lock);
pr_err("ip_vs_sync_buff_create failed.\n");
return;
}
@@ -582,7 +595,7 @@ static void ip_vs_sync_conn_v0(struct net *net, struct ip_vs_conn *cp,
}
m->nr_conns++;
- m->size += len;
+ m->size = htons(ntohs(m->size) + len);
buff->head += len;
/* check if there is a space for next one */
@@ -590,7 +603,7 @@ static void ip_vs_sync_conn_v0(struct net *net, struct ip_vs_conn *cp,
sb_queue_tail(ipvs, ms);
ms->sync_buff = NULL;
}
- spin_unlock(&ipvs->sync_buff_lock);
+ spin_unlock_bh(&ipvs->sync_buff_lock);
/* synchronize its controller if it has */
cp = cp->control;
@@ -641,9 +654,9 @@ sloop:
pe_name_len = strnlen(cp->pe->name, IP_VS_PENAME_MAXLEN);
}
- spin_lock(&ipvs->sync_buff_lock);
+ spin_lock_bh(&ipvs->sync_buff_lock);
if (!(ipvs->sync_state & IP_VS_STATE_MASTER)) {
- spin_unlock(&ipvs->sync_buff_lock);
+ spin_unlock_bh(&ipvs->sync_buff_lock);
return;
}
@@ -683,7 +696,7 @@ sloop:
if (!buff) {
buff = ip_vs_sync_buff_create(ipvs);
if (!buff) {
- spin_unlock(&ipvs->sync_buff_lock);
+ spin_unlock_bh(&ipvs->sync_buff_lock);
pr_err("ip_vs_sync_buff_create failed.\n");
return;
}
@@ -693,7 +706,7 @@ sloop:
p = buff->head;
buff->head += pad + len;
- m->size += pad + len;
+ m->size = htons(ntohs(m->size) + pad + len);
/* Add ev. padding from prev. sync_conn */
while (pad--)
*(p++) = 0;
@@ -750,7 +763,7 @@ sloop:
}
}
- spin_unlock(&ipvs->sync_buff_lock);
+ spin_unlock_bh(&ipvs->sync_buff_lock);
control:
/* synchronize its controller if it has */
@@ -843,7 +856,7 @@ static void ip_vs_proc_conn(struct net *net, struct ip_vs_conn_param *param,
kfree(param->pe_data);
dest = cp->dest;
- spin_lock(&cp->lock);
+ spin_lock_bh(&cp->lock);
if ((cp->flags ^ flags) & IP_VS_CONN_F_INACTIVE &&
!(flags & IP_VS_CONN_F_TEMPLATE) && dest) {
if (flags & IP_VS_CONN_F_INACTIVE) {
@@ -857,24 +870,21 @@ static void ip_vs_proc_conn(struct net *net, struct ip_vs_conn_param *param,
flags &= IP_VS_CONN_F_BACKUP_UPD_MASK;
flags |= cp->flags & ~IP_VS_CONN_F_BACKUP_UPD_MASK;
cp->flags = flags;
- spin_unlock(&cp->lock);
- if (!dest) {
- dest = ip_vs_try_bind_dest(cp);
- if (dest)
- atomic_dec(&dest->refcnt);
- }
+ spin_unlock_bh(&cp->lock);
+ if (!dest)
+ ip_vs_try_bind_dest(cp);
} else {
/*
* Find the appropriate destination for the connection.
* If it is not found the connection will remain unbound
* but still handled.
*/
+ rcu_read_lock();
dest = ip_vs_find_dest(net, type, daddr, dport, param->vaddr,
param->vport, protocol, fwmark, flags);
cp = ip_vs_conn_new(param, daddr, dport, flags, dest, fwmark);
- if (dest)
- atomic_dec(&dest->refcnt);
+ rcu_read_unlock();
if (!cp) {
if (param->pe_data)
kfree(param->pe_data);
@@ -1178,10 +1188,8 @@ static void ip_vs_process_message(struct net *net, __u8 *buffer,
IP_VS_DBG(2, "BACKUP, message header too short\n");
return;
}
- /* Convert size back to host byte order */
- m2->size = ntohs(m2->size);
- if (buflen != m2->size) {
+ if (buflen != ntohs(m2->size)) {
IP_VS_DBG(2, "BACKUP, bogus message size\n");
return;
}
@@ -1547,10 +1555,7 @@ ip_vs_send_sync_msg(struct socket *sock, struct ip_vs_sync_mesg *msg)
int msize;
int ret;
- msize = msg->size;
-
- /* Put size in network byte order */
- msg->size = htons(msg->size);
+ msize = ntohs(msg->size);
ret = ip_vs_send_async(sock, (char *)msg, msize);
if (ret >= 0 || ret == -EAGAIN)
@@ -1632,12 +1637,12 @@ static int sync_thread_master(void *data)
continue;
}
while (ip_vs_send_sync_msg(tinfo->sock, sb->mesg) < 0) {
- int ret = 0;
-
+ /* (Ab)use interruptible sleep to avoid increasing
+ * the load avg.
+ */
__wait_event_interruptible(*sk_sleep(sk),
sock_writeable(sk) ||
- kthread_should_stop(),
- ret);
+ kthread_should_stop());
if (unlikely(kthread_should_stop()))
goto done;
}
@@ -1692,11 +1697,7 @@ static int sync_thread_backup(void *data)
break;
}
- /* disable bottom half, because it accesses the data
- shared by softirq while getting/creating conns */
- local_bh_disable();
ip_vs_process_message(tinfo->net, tinfo->buf, len);
- local_bh_enable();
}
}
@@ -1795,6 +1796,8 @@ int start_sync_thread(struct net *net, int state, char *mcast_ifn, __u8 syncid)
GFP_KERNEL);
if (!tinfo->buf)
goto outtinfo;
+ } else {
+ tinfo->buf = NULL;
}
tinfo->id = id;
diff --git a/net/netfilter/ipvs/ip_vs_wlc.c b/net/netfilter/ipvs/ip_vs_wlc.c
index bc1bfc48a17..b5b4650d50a 100644
--- a/net/netfilter/ipvs/ip_vs_wlc.c
+++ b/net/netfilter/ipvs/ip_vs_wlc.c
@@ -31,10 +31,11 @@
* Weighted Least Connection scheduling
*/
static struct ip_vs_dest *
-ip_vs_wlc_schedule(struct ip_vs_service *svc, const struct sk_buff *skb)
+ip_vs_wlc_schedule(struct ip_vs_service *svc, const struct sk_buff *skb,
+ struct ip_vs_iphdr *iph)
{
struct ip_vs_dest *dest, *least;
- unsigned int loh, doh;
+ int loh, doh;
IP_VS_DBG(6, "ip_vs_wlc_schedule(): Scheduling...\n");
@@ -51,7 +52,7 @@ ip_vs_wlc_schedule(struct ip_vs_service *svc, const struct sk_buff *skb)
* new connections.
*/
- list_for_each_entry(dest, &svc->destinations, n_list) {
+ list_for_each_entry_rcu(dest, &svc->destinations, n_list) {
if (!(dest->flags & IP_VS_DEST_F_OVERLOAD) &&
atomic_read(&dest->weight) > 0) {
least = dest;
@@ -66,12 +67,12 @@ ip_vs_wlc_schedule(struct ip_vs_service *svc, const struct sk_buff *skb)
* Find the destination with the least load.
*/
nextstage:
- list_for_each_entry_continue(dest, &svc->destinations, n_list) {
+ list_for_each_entry_continue_rcu(dest, &svc->destinations, n_list) {
if (dest->flags & IP_VS_DEST_F_OVERLOAD)
continue;
doh = ip_vs_dest_conn_overhead(dest);
- if (loh * atomic_read(&dest->weight) >
- doh * atomic_read(&least->weight)) {
+ if ((__s64)loh * atomic_read(&dest->weight) >
+ (__s64)doh * atomic_read(&least->weight)) {
least = dest;
loh = doh;
}
@@ -106,6 +107,7 @@ static int __init ip_vs_wlc_init(void)
static void __exit ip_vs_wlc_cleanup(void)
{
unregister_ip_vs_scheduler(&ip_vs_wlc_scheduler);
+ synchronize_rcu();
}
module_init(ip_vs_wlc_init);
diff --git a/net/netfilter/ipvs/ip_vs_wrr.c b/net/netfilter/ipvs/ip_vs_wrr.c
index 231be7dd547..0546cd572d6 100644
--- a/net/netfilter/ipvs/ip_vs_wrr.c
+++ b/net/netfilter/ipvs/ip_vs_wrr.c
@@ -29,14 +29,45 @@
#include <net/ip_vs.h>
+/* The WRR algorithm depends on some caclulations:
+ * - mw: maximum weight
+ * - di: weight step, greatest common divisor from all weights
+ * - cw: current required weight
+ * As result, all weights are in the [di..mw] range with a step=di.
+ *
+ * First, we start with cw = mw and select dests with weight >= cw.
+ * Then cw is reduced with di and all dests are checked again.
+ * Last pass should be with cw = di. We have mw/di passes in total:
+ *
+ * pass 1: cw = max weight
+ * pass 2: cw = max weight - di
+ * pass 3: cw = max weight - 2 * di
+ * ...
+ * last pass: cw = di
+ *
+ * Weights are supposed to be >= di but we run in parallel with
+ * weight changes, it is possible some dest weight to be reduced
+ * below di, bad if it is the only available dest.
+ *
+ * So, we modify how mw is calculated, now it is reduced with (di - 1),
+ * so that last cw is 1 to catch such dests with weight below di:
+ * pass 1: cw = max weight - (di - 1)
+ * pass 2: cw = max weight - di - (di - 1)
+ * pass 3: cw = max weight - 2 * di - (di - 1)
+ * ...
+ * last pass: cw = 1
+ *
+ */
+
/*
* current destination pointer for weighted round-robin scheduling
*/
struct ip_vs_wrr_mark {
- struct list_head *cl; /* current list head */
+ struct ip_vs_dest *cl; /* current dest or head */
int cw; /* current weight */
int mw; /* maximum weight */
int di; /* decreasing interval */
+ struct rcu_head rcu_head;
};
@@ -88,36 +119,41 @@ static int ip_vs_wrr_init_svc(struct ip_vs_service *svc)
if (mark == NULL)
return -ENOMEM;
- mark->cl = &svc->destinations;
- mark->cw = 0;
- mark->mw = ip_vs_wrr_max_weight(svc);
+ mark->cl = list_entry(&svc->destinations, struct ip_vs_dest, n_list);
mark->di = ip_vs_wrr_gcd_weight(svc);
+ mark->mw = ip_vs_wrr_max_weight(svc) - (mark->di - 1);
+ mark->cw = mark->mw;
svc->sched_data = mark;
return 0;
}
-static int ip_vs_wrr_done_svc(struct ip_vs_service *svc)
+static void ip_vs_wrr_done_svc(struct ip_vs_service *svc)
{
+ struct ip_vs_wrr_mark *mark = svc->sched_data;
+
/*
* Release the mark variable
*/
- kfree(svc->sched_data);
-
- return 0;
+ kfree_rcu(mark, rcu_head);
}
-static int ip_vs_wrr_update_svc(struct ip_vs_service *svc)
+static int ip_vs_wrr_dest_changed(struct ip_vs_service *svc,
+ struct ip_vs_dest *dest)
{
struct ip_vs_wrr_mark *mark = svc->sched_data;
- mark->cl = &svc->destinations;
- mark->mw = ip_vs_wrr_max_weight(svc);
+ spin_lock_bh(&svc->sched_lock);
+ mark->cl = list_entry(&svc->destinations, struct ip_vs_dest, n_list);
mark->di = ip_vs_wrr_gcd_weight(svc);
- if (mark->cw > mark->mw)
- mark->cw = 0;
+ mark->mw = ip_vs_wrr_max_weight(svc) - (mark->di - 1);
+ if (mark->cw > mark->mw || !mark->cw)
+ mark->cw = mark->mw;
+ else if (mark->di > 1)
+ mark->cw = (mark->cw / mark->di) * mark->di + 1;
+ spin_unlock_bh(&svc->sched_lock);
return 0;
}
@@ -126,82 +162,82 @@ static int ip_vs_wrr_update_svc(struct ip_vs_service *svc)
* Weighted Round-Robin Scheduling
*/
static struct ip_vs_dest *
-ip_vs_wrr_schedule(struct ip_vs_service *svc, const struct sk_buff *skb)
+ip_vs_wrr_schedule(struct ip_vs_service *svc, const struct sk_buff *skb,
+ struct ip_vs_iphdr *iph)
{
- struct ip_vs_dest *dest;
+ struct ip_vs_dest *dest, *last, *stop = NULL;
struct ip_vs_wrr_mark *mark = svc->sched_data;
- struct list_head *p;
+ bool last_pass = false, restarted = false;
IP_VS_DBG(6, "%s(): Scheduling...\n", __func__);
- /*
- * This loop will always terminate, because mark->cw in (0, max_weight]
- * and at least one server has its weight equal to max_weight.
- */
- write_lock(&svc->sched_lock);
- p = mark->cl;
+ spin_lock_bh(&svc->sched_lock);
+ dest = mark->cl;
+ /* No available dests? */
+ if (mark->mw == 0)
+ goto err_noavail;
+ last = dest;
+ /* Stop only after all dests were checked for weight >= 1 (last pass) */
while (1) {
- if (mark->cl == &svc->destinations) {
- /* it is at the head of the destination list */
-
- if (mark->cl == mark->cl->next) {
- /* no dest entry */
- ip_vs_scheduler_err(svc,
- "no destination available: "
- "no destinations present");
- dest = NULL;
- goto out;
- }
-
- mark->cl = svc->destinations.next;
- mark->cw -= mark->di;
- if (mark->cw <= 0) {
- mark->cw = mark->mw;
- /*
- * Still zero, which means no available servers.
- */
- if (mark->cw == 0) {
- mark->cl = &svc->destinations;
- ip_vs_scheduler_err(svc,
- "no destination available");
- dest = NULL;
- goto out;
- }
- }
- } else
- mark->cl = mark->cl->next;
-
- if (mark->cl != &svc->destinations) {
- /* not at the head of the list */
- dest = list_entry(mark->cl, struct ip_vs_dest, n_list);
+ list_for_each_entry_continue_rcu(dest,
+ &svc->destinations,
+ n_list) {
if (!(dest->flags & IP_VS_DEST_F_OVERLOAD) &&
- atomic_read(&dest->weight) >= mark->cw) {
- /* got it */
- break;
- }
+ atomic_read(&dest->weight) >= mark->cw)
+ goto found;
+ if (dest == stop)
+ goto err_over;
}
-
- if (mark->cl == p && mark->cw == mark->di) {
- /* back to the start, and no dest is found.
- It is only possible when all dests are OVERLOADED */
- dest = NULL;
- ip_vs_scheduler_err(svc,
- "no destination available: "
- "all destinations are overloaded");
- goto out;
+ mark->cw -= mark->di;
+ if (mark->cw <= 0) {
+ mark->cw = mark->mw;
+ /* Stop if we tried last pass from first dest:
+ * 1. last_pass: we started checks when cw > di but
+ * then all dests were checked for w >= 1
+ * 2. last was head: the first and only traversal
+ * was for weight >= 1, for all dests.
+ */
+ if (last_pass ||
+ &last->n_list == &svc->destinations)
+ goto err_over;
+ restarted = true;
+ }
+ last_pass = mark->cw <= mark->di;
+ if (last_pass && restarted &&
+ &last->n_list != &svc->destinations) {
+ /* First traversal was for w >= 1 but only
+ * for dests after 'last', now do the same
+ * for all dests up to 'last'.
+ */
+ stop = last;
}
}
+found:
IP_VS_DBG_BUF(6, "WRR: server %s:%u "
"activeconns %d refcnt %d weight %d\n",
IP_VS_DBG_ADDR(svc->af, &dest->addr), ntohs(dest->port),
atomic_read(&dest->activeconns),
atomic_read(&dest->refcnt),
atomic_read(&dest->weight));
+ mark->cl = dest;
out:
- write_unlock(&svc->sched_lock);
+ spin_unlock_bh(&svc->sched_lock);
return dest;
+
+err_noavail:
+ mark->cl = dest;
+ dest = NULL;
+ ip_vs_scheduler_err(svc, "no destination available");
+ goto out;
+
+err_over:
+ mark->cl = dest;
+ dest = NULL;
+ ip_vs_scheduler_err(svc, "no destination available: "
+ "all destinations are overloaded");
+ goto out;
}
@@ -212,7 +248,9 @@ static struct ip_vs_scheduler ip_vs_wrr_scheduler = {
.n_list = LIST_HEAD_INIT(ip_vs_wrr_scheduler.n_list),
.init_service = ip_vs_wrr_init_svc,
.done_service = ip_vs_wrr_done_svc,
- .update_service = ip_vs_wrr_update_svc,
+ .add_dest = ip_vs_wrr_dest_changed,
+ .del_dest = ip_vs_wrr_dest_changed,
+ .upd_dest = ip_vs_wrr_dest_changed,
.schedule = ip_vs_wrr_schedule,
};
@@ -224,6 +262,7 @@ static int __init ip_vs_wrr_init(void)
static void __exit ip_vs_wrr_cleanup(void)
{
unregister_ip_vs_scheduler(&ip_vs_wrr_scheduler);
+ synchronize_rcu();
}
module_init(ip_vs_wrr_init);
diff --git a/net/netfilter/ipvs/ip_vs_xmit.c b/net/netfilter/ipvs/ip_vs_xmit.c
index ee6b7a9f1ec..73ba1cc7a88 100644
--- a/net/netfilter/ipvs/ip_vs_xmit.c
+++ b/net/netfilter/ipvs/ip_vs_xmit.c
@@ -17,6 +17,8 @@
* - not all connections have destination server, for example,
* connections in backup server when fwmark is used
* - bypass connections use daddr from packet
+ * - we can use dst without ref while sending in RCU section, we use
+ * ref when returning NF_ACCEPT for NAT-ed packet via loopback
* LOCAL_OUT rules:
* - skb->dev is NULL, skb->protocol is not set (both are set in POST_ROUTING)
* - skb->pkt_type is not set yet
@@ -51,39 +53,54 @@ enum {
*/
IP_VS_RT_MODE_CONNECT = 8, /* Always bind route to saddr */
IP_VS_RT_MODE_KNOWN_NH = 16,/* Route via remote addr */
+ IP_VS_RT_MODE_TUNNEL = 32,/* Tunnel mode */
};
+static inline struct ip_vs_dest_dst *ip_vs_dest_dst_alloc(void)
+{
+ return kmalloc(sizeof(struct ip_vs_dest_dst), GFP_ATOMIC);
+}
+
+static inline void ip_vs_dest_dst_free(struct ip_vs_dest_dst *dest_dst)
+{
+ kfree(dest_dst);
+}
+
/*
* Destination cache to speed up outgoing route lookup
*/
static inline void
-__ip_vs_dst_set(struct ip_vs_dest *dest, u32 rtos, struct dst_entry *dst,
- u32 dst_cookie)
+__ip_vs_dst_set(struct ip_vs_dest *dest, struct ip_vs_dest_dst *dest_dst,
+ struct dst_entry *dst, u32 dst_cookie)
{
- struct dst_entry *old_dst;
+ struct ip_vs_dest_dst *old;
+
+ old = rcu_dereference_protected(dest->dest_dst,
+ lockdep_is_held(&dest->dst_lock));
- old_dst = dest->dst_cache;
- dest->dst_cache = dst;
- dest->dst_rtos = rtos;
- dest->dst_cookie = dst_cookie;
- dst_release(old_dst);
+ if (dest_dst) {
+ dest_dst->dst_cache = dst;
+ dest_dst->dst_cookie = dst_cookie;
+ }
+ rcu_assign_pointer(dest->dest_dst, dest_dst);
+
+ if (old)
+ call_rcu(&old->rcu_head, ip_vs_dest_dst_rcu_free);
}
-static inline struct dst_entry *
-__ip_vs_dst_check(struct ip_vs_dest *dest, u32 rtos)
+static inline struct ip_vs_dest_dst *
+__ip_vs_dst_check(struct ip_vs_dest *dest)
{
- struct dst_entry *dst = dest->dst_cache;
+ struct ip_vs_dest_dst *dest_dst = rcu_dereference(dest->dest_dst);
+ struct dst_entry *dst;
- if (!dst)
+ if (!dest_dst)
return NULL;
- if ((dst->obsolete || rtos != dest->dst_rtos) &&
- dst->ops->check(dst, dest->dst_cookie) == NULL) {
- dest->dst_cache = NULL;
- dst_release(dst);
+ dst = dest_dst->dst_cache;
+ if (dst->obsolete &&
+ dst->ops->check(dst, dest_dst->dst_cookie) == NULL)
return NULL;
- }
- dst_hold(dst);
- return dst;
+ return dest_dst;
}
static inline bool
@@ -104,7 +121,7 @@ __mtu_check_toobig_v6(const struct sk_buff *skb, u32 mtu)
/* Get route to daddr, update *saddr, optionally bind route to saddr */
static struct rtable *do_output_route4(struct net *net, __be32 daddr,
- u32 rtos, int rt_mode, __be32 *saddr)
+ int rt_mode, __be32 *saddr)
{
struct flowi4 fl4;
struct rtable *rt;
@@ -113,7 +130,6 @@ static struct rtable *do_output_route4(struct net *net, __be32 daddr,
memset(&fl4, 0, sizeof(fl4));
fl4.daddr = daddr;
fl4.saddr = (rt_mode & IP_VS_RT_MODE_CONNECT) ? *saddr : 0;
- fl4.flowi4_tos = rtos;
fl4.flowi4_flags = (rt_mode & IP_VS_RT_MODE_KNOWN_NH) ?
FLOWI_FLAG_KNOWN_NH : 0;
@@ -124,7 +140,7 @@ retry:
if (PTR_ERR(rt) == -EINVAL && *saddr &&
rt_mode & IP_VS_RT_MODE_CONNECT && !loop) {
*saddr = 0;
- flowi4_update_output(&fl4, 0, rtos, daddr, 0);
+ flowi4_update_output(&fl4, 0, 0, daddr, 0);
goto retry;
}
IP_VS_DBG_RL("ip_route_output error, dest: %pI4\n", &daddr);
@@ -132,7 +148,7 @@ retry:
} else if (!*saddr && rt_mode & IP_VS_RT_MODE_CONNECT && fl4.saddr) {
ip_rt_put(rt);
*saddr = fl4.saddr;
- flowi4_update_output(&fl4, 0, rtos, daddr, fl4.saddr);
+ flowi4_update_output(&fl4, 0, 0, daddr, fl4.saddr);
loop++;
goto retry;
}
@@ -141,113 +157,140 @@ retry:
}
/* Get route to destination or remote server */
-static struct rtable *
+static int
__ip_vs_get_out_rt(struct sk_buff *skb, struct ip_vs_dest *dest,
- __be32 daddr, u32 rtos, int rt_mode, __be32 *ret_saddr)
+ __be32 daddr, int rt_mode, __be32 *ret_saddr)
{
struct net *net = dev_net(skb_dst(skb)->dev);
+ struct netns_ipvs *ipvs = net_ipvs(net);
+ struct ip_vs_dest_dst *dest_dst;
struct rtable *rt; /* Route to the other host */
struct rtable *ort; /* Original route */
- int local;
+ struct iphdr *iph;
+ __be16 df;
+ int mtu;
+ int local, noref = 1;
if (dest) {
- spin_lock(&dest->dst_lock);
- if (!(rt = (struct rtable *)
- __ip_vs_dst_check(dest, rtos))) {
- rt = do_output_route4(net, dest->addr.ip, rtos,
- rt_mode, &dest->dst_saddr.ip);
+ dest_dst = __ip_vs_dst_check(dest);
+ if (likely(dest_dst))
+ rt = (struct rtable *) dest_dst->dst_cache;
+ else {
+ dest_dst = ip_vs_dest_dst_alloc();
+ spin_lock_bh(&dest->dst_lock);
+ if (!dest_dst) {
+ __ip_vs_dst_set(dest, NULL, NULL, 0);
+ spin_unlock_bh(&dest->dst_lock);
+ goto err_unreach;
+ }
+ rt = do_output_route4(net, dest->addr.ip, rt_mode,
+ &dest_dst->dst_saddr.ip);
if (!rt) {
- spin_unlock(&dest->dst_lock);
- return NULL;
+ __ip_vs_dst_set(dest, NULL, NULL, 0);
+ spin_unlock_bh(&dest->dst_lock);
+ ip_vs_dest_dst_free(dest_dst);
+ goto err_unreach;
}
- __ip_vs_dst_set(dest, rtos, dst_clone(&rt->dst), 0);
- IP_VS_DBG(10, "new dst %pI4, src %pI4, refcnt=%d, "
- "rtos=%X\n",
- &dest->addr.ip, &dest->dst_saddr.ip,
- atomic_read(&rt->dst.__refcnt), rtos);
+ __ip_vs_dst_set(dest, dest_dst, &rt->dst, 0);
+ spin_unlock_bh(&dest->dst_lock);
+ IP_VS_DBG(10, "new dst %pI4, src %pI4, refcnt=%d\n",
+ &dest->addr.ip, &dest_dst->dst_saddr.ip,
+ atomic_read(&rt->dst.__refcnt));
}
daddr = dest->addr.ip;
if (ret_saddr)
- *ret_saddr = dest->dst_saddr.ip;
- spin_unlock(&dest->dst_lock);
+ *ret_saddr = dest_dst->dst_saddr.ip;
} else {
__be32 saddr = htonl(INADDR_ANY);
+ noref = 0;
+
/* For such unconfigured boxes avoid many route lookups
* for performance reasons because we do not remember saddr
*/
rt_mode &= ~IP_VS_RT_MODE_CONNECT;
- rt = do_output_route4(net, daddr, rtos, rt_mode, &saddr);
+ rt = do_output_route4(net, daddr, rt_mode, &saddr);
if (!rt)
- return NULL;
+ goto err_unreach;
if (ret_saddr)
*ret_saddr = saddr;
}
- local = rt->rt_flags & RTCF_LOCAL;
+ local = (rt->rt_flags & RTCF_LOCAL) ? 1 : 0;
if (!((local ? IP_VS_RT_MODE_LOCAL : IP_VS_RT_MODE_NON_LOCAL) &
rt_mode)) {
IP_VS_DBG_RL("Stopping traffic to %s address, dest: %pI4\n",
(rt->rt_flags & RTCF_LOCAL) ?
"local":"non-local", &daddr);
- ip_rt_put(rt);
- return NULL;
- }
- if (local && !(rt_mode & IP_VS_RT_MODE_RDR) &&
- !((ort = skb_rtable(skb)) && ort->rt_flags & RTCF_LOCAL)) {
- IP_VS_DBG_RL("Redirect from non-local address %pI4 to local "
- "requires NAT method, dest: %pI4\n",
- &ip_hdr(skb)->daddr, &daddr);
- ip_rt_put(rt);
- return NULL;
+ goto err_put;
}
- if (unlikely(!local && ipv4_is_loopback(ip_hdr(skb)->saddr))) {
- IP_VS_DBG_RL("Stopping traffic from loopback address %pI4 "
- "to non-local address, dest: %pI4\n",
- &ip_hdr(skb)->saddr, &daddr);
- ip_rt_put(rt);
- return NULL;
+ iph = ip_hdr(skb);
+ if (likely(!local)) {
+ if (unlikely(ipv4_is_loopback(iph->saddr))) {
+ IP_VS_DBG_RL("Stopping traffic from loopback address "
+ "%pI4 to non-local address, dest: %pI4\n",
+ &iph->saddr, &daddr);
+ goto err_put;
+ }
+ } else {
+ ort = skb_rtable(skb);
+ if (!(rt_mode & IP_VS_RT_MODE_RDR) &&
+ !(ort->rt_flags & RTCF_LOCAL)) {
+ IP_VS_DBG_RL("Redirect from non-local address %pI4 to "
+ "local requires NAT method, dest: %pI4\n",
+ &iph->daddr, &daddr);
+ goto err_put;
+ }
+ /* skb to local stack, preserve old route */
+ if (!noref)
+ ip_rt_put(rt);
+ return local;
}
- return rt;
-}
-
-/* Reroute packet to local IPv4 stack after DNAT */
-static int
-__ip_vs_reroute_locally(struct sk_buff *skb)
-{
- struct rtable *rt = skb_rtable(skb);
- struct net_device *dev = rt->dst.dev;
- struct net *net = dev_net(dev);
- struct iphdr *iph = ip_hdr(skb);
-
- if (rt_is_input_route(rt)) {
- unsigned long orefdst = skb->_skb_refdst;
-
- if (ip_route_input(skb, iph->daddr, iph->saddr,
- iph->tos, skb->dev))
- return 0;
- refdst_drop(orefdst);
+ if (likely(!(rt_mode & IP_VS_RT_MODE_TUNNEL))) {
+ mtu = dst_mtu(&rt->dst);
+ df = iph->frag_off & htons(IP_DF);
} else {
- struct flowi4 fl4 = {
- .daddr = iph->daddr,
- .saddr = iph->saddr,
- .flowi4_tos = RT_TOS(iph->tos),
- .flowi4_mark = skb->mark,
- };
-
- rt = ip_route_output_key(net, &fl4);
- if (IS_ERR(rt))
- return 0;
- if (!(rt->rt_flags & RTCF_LOCAL)) {
- ip_rt_put(rt);
- return 0;
+ struct sock *sk = skb->sk;
+
+ mtu = dst_mtu(&rt->dst) - sizeof(struct iphdr);
+ if (mtu < 68) {
+ IP_VS_DBG_RL("%s(): mtu less than 68\n", __func__);
+ goto err_put;
}
- /* Drop old route. */
- skb_dst_drop(skb);
- skb_dst_set(skb, &rt->dst);
+ ort = skb_rtable(skb);
+ if (!skb->dev && sk && sk->sk_state != TCP_TIME_WAIT)
+ ort->dst.ops->update_pmtu(&ort->dst, sk, NULL, mtu);
+ /* MTU check allowed? */
+ df = sysctl_pmtu_disc(ipvs) ? iph->frag_off & htons(IP_DF) : 0;
}
- return 1;
+
+ /* MTU checking */
+ if (unlikely(df && skb->len > mtu && !skb_is_gso(skb))) {
+ icmp_send(skb, ICMP_DEST_UNREACH, ICMP_FRAG_NEEDED, htonl(mtu));
+ IP_VS_DBG(1, "frag needed for %pI4\n", &iph->saddr);
+ goto err_put;
+ }
+
+ skb_dst_drop(skb);
+ if (noref) {
+ if (!local)
+ skb_dst_set_noref_force(skb, &rt->dst);
+ else
+ skb_dst_set(skb, dst_clone(&rt->dst));
+ } else
+ skb_dst_set(skb, &rt->dst);
+
+ return local;
+
+err_put:
+ if (!noref)
+ ip_rt_put(rt);
+ return -1;
+
+err_unreach:
+ dst_link_failure(skb);
+ return -1;
}
#ifdef CONFIG_IP_VS_IPV6
@@ -294,44 +337,57 @@ out_err:
/*
* Get route to destination or remote server
*/
-static struct rt6_info *
+static int
__ip_vs_get_out_rt_v6(struct sk_buff *skb, struct ip_vs_dest *dest,
struct in6_addr *daddr, struct in6_addr *ret_saddr,
- int do_xfrm, int rt_mode)
+ struct ip_vs_iphdr *ipvsh, int do_xfrm, int rt_mode)
{
struct net *net = dev_net(skb_dst(skb)->dev);
+ struct ip_vs_dest_dst *dest_dst;
struct rt6_info *rt; /* Route to the other host */
struct rt6_info *ort; /* Original route */
struct dst_entry *dst;
- int local;
+ int mtu;
+ int local, noref = 1;
if (dest) {
- spin_lock(&dest->dst_lock);
- rt = (struct rt6_info *)__ip_vs_dst_check(dest, 0);
- if (!rt) {
+ dest_dst = __ip_vs_dst_check(dest);
+ if (likely(dest_dst))
+ rt = (struct rt6_info *) dest_dst->dst_cache;
+ else {
u32 cookie;
+ dest_dst = ip_vs_dest_dst_alloc();
+ spin_lock_bh(&dest->dst_lock);
+ if (!dest_dst) {
+ __ip_vs_dst_set(dest, NULL, NULL, 0);
+ spin_unlock_bh(&dest->dst_lock);
+ goto err_unreach;
+ }
dst = __ip_vs_route_output_v6(net, &dest->addr.in6,
- &dest->dst_saddr.in6,
+ &dest_dst->dst_saddr.in6,
do_xfrm);
if (!dst) {
- spin_unlock(&dest->dst_lock);
- return NULL;
+ __ip_vs_dst_set(dest, NULL, NULL, 0);
+ spin_unlock_bh(&dest->dst_lock);
+ ip_vs_dest_dst_free(dest_dst);
+ goto err_unreach;
}
rt = (struct rt6_info *) dst;
cookie = rt->rt6i_node ? rt->rt6i_node->fn_sernum : 0;
- __ip_vs_dst_set(dest, 0, dst_clone(&rt->dst), cookie);
+ __ip_vs_dst_set(dest, dest_dst, &rt->dst, cookie);
+ spin_unlock_bh(&dest->dst_lock);
IP_VS_DBG(10, "new dst %pI6, src %pI6, refcnt=%d\n",
- &dest->addr.in6, &dest->dst_saddr.in6,
+ &dest->addr.in6, &dest_dst->dst_saddr.in6,
atomic_read(&rt->dst.__refcnt));
}
if (ret_saddr)
- *ret_saddr = dest->dst_saddr.in6;
- spin_unlock(&dest->dst_lock);
+ *ret_saddr = dest_dst->dst_saddr.in6;
} else {
+ noref = 0;
dst = __ip_vs_route_output_v6(net, daddr, ret_saddr, do_xfrm);
if (!dst)
- return NULL;
+ goto err_unreach;
rt = (struct rt6_info *) dst;
}
@@ -340,86 +396,137 @@ __ip_vs_get_out_rt_v6(struct sk_buff *skb, struct ip_vs_dest *dest,
rt_mode)) {
IP_VS_DBG_RL("Stopping traffic to %s address, dest: %pI6c\n",
local ? "local":"non-local", daddr);
- dst_release(&rt->dst);
- return NULL;
+ goto err_put;
}
- if (local && !(rt_mode & IP_VS_RT_MODE_RDR) &&
- !((ort = (struct rt6_info *) skb_dst(skb)) &&
- __ip_vs_is_local_route6(ort))) {
- IP_VS_DBG_RL("Redirect from non-local address %pI6c to local "
- "requires NAT method, dest: %pI6c\n",
- &ipv6_hdr(skb)->daddr, daddr);
- dst_release(&rt->dst);
- return NULL;
+ if (likely(!local)) {
+ if (unlikely((!skb->dev || skb->dev->flags & IFF_LOOPBACK) &&
+ ipv6_addr_type(&ipv6_hdr(skb)->saddr) &
+ IPV6_ADDR_LOOPBACK)) {
+ IP_VS_DBG_RL("Stopping traffic from loopback address "
+ "%pI6c to non-local address, "
+ "dest: %pI6c\n",
+ &ipv6_hdr(skb)->saddr, daddr);
+ goto err_put;
+ }
+ } else {
+ ort = (struct rt6_info *) skb_dst(skb);
+ if (!(rt_mode & IP_VS_RT_MODE_RDR) &&
+ !__ip_vs_is_local_route6(ort)) {
+ IP_VS_DBG_RL("Redirect from non-local address %pI6c "
+ "to local requires NAT method, "
+ "dest: %pI6c\n",
+ &ipv6_hdr(skb)->daddr, daddr);
+ goto err_put;
+ }
+ /* skb to local stack, preserve old route */
+ if (!noref)
+ dst_release(&rt->dst);
+ return local;
}
- if (unlikely(!local && (!skb->dev || skb->dev->flags & IFF_LOOPBACK) &&
- ipv6_addr_type(&ipv6_hdr(skb)->saddr) &
- IPV6_ADDR_LOOPBACK)) {
- IP_VS_DBG_RL("Stopping traffic from loopback address %pI6c "
- "to non-local address, dest: %pI6c\n",
- &ipv6_hdr(skb)->saddr, daddr);
- dst_release(&rt->dst);
- return NULL;
+
+ /* MTU checking */
+ if (likely(!(rt_mode & IP_VS_RT_MODE_TUNNEL)))
+ mtu = dst_mtu(&rt->dst);
+ else {
+ struct sock *sk = skb->sk;
+
+ mtu = dst_mtu(&rt->dst) - sizeof(struct ipv6hdr);
+ if (mtu < IPV6_MIN_MTU) {
+ IP_VS_DBG_RL("%s(): mtu less than %d\n", __func__,
+ IPV6_MIN_MTU);
+ goto err_put;
+ }
+ ort = (struct rt6_info *) skb_dst(skb);
+ if (!skb->dev && sk && sk->sk_state != TCP_TIME_WAIT)
+ ort->dst.ops->update_pmtu(&ort->dst, sk, NULL, mtu);
}
- return rt;
+ if (unlikely(__mtu_check_toobig_v6(skb, mtu))) {
+ if (!skb->dev)
+ skb->dev = net->loopback_dev;
+ /* only send ICMP too big on first fragment */
+ if (!ipvsh->fragoffs)
+ icmpv6_send(skb, ICMPV6_PKT_TOOBIG, 0, mtu);
+ IP_VS_DBG(1, "frag needed for %pI6c\n", &ipv6_hdr(skb)->saddr);
+ goto err_put;
+ }
+
+ skb_dst_drop(skb);
+ if (noref) {
+ if (!local)
+ skb_dst_set_noref_force(skb, &rt->dst);
+ else
+ skb_dst_set(skb, dst_clone(&rt->dst));
+ } else
+ skb_dst_set(skb, &rt->dst);
+
+ return local;
+
+err_put:
+ if (!noref)
+ dst_release(&rt->dst);
+ return -1;
+
+err_unreach:
+ dst_link_failure(skb);
+ return -1;
}
#endif
-/*
- * Release dest->dst_cache before a dest is removed
- */
-void
-ip_vs_dst_reset(struct ip_vs_dest *dest)
+/* return NF_ACCEPT to allow forwarding or other NF_xxx on error */
+static inline int ip_vs_tunnel_xmit_prepare(struct sk_buff *skb,
+ struct ip_vs_conn *cp)
{
- struct dst_entry *old_dst;
+ int ret = NF_ACCEPT;
+
+ skb->ipvs_property = 1;
+ if (unlikely(cp->flags & IP_VS_CONN_F_NFCT))
+ ret = ip_vs_confirm_conntrack(skb);
+ if (ret == NF_ACCEPT) {
+ nf_reset(skb);
+ skb_forward_csum(skb);
+ }
+ return ret;
+}
+
+/* return NF_STOLEN (sent) or NF_ACCEPT if local=1 (not sent) */
+static inline int ip_vs_nat_send_or_cont(int pf, struct sk_buff *skb,
+ struct ip_vs_conn *cp, int local)
+{
+ int ret = NF_STOLEN;
- old_dst = dest->dst_cache;
- dest->dst_cache = NULL;
- dst_release(old_dst);
- dest->dst_saddr.ip = 0;
+ skb->ipvs_property = 1;
+ if (likely(!(cp->flags & IP_VS_CONN_F_NFCT)))
+ ip_vs_notrack(skb);
+ else
+ ip_vs_update_conntrack(skb, cp, 1);
+ if (!local) {
+ skb_forward_csum(skb);
+ NF_HOOK(pf, NF_INET_LOCAL_OUT, skb, NULL, skb_dst(skb)->dev,
+ dst_output);
+ } else
+ ret = NF_ACCEPT;
+ return ret;
}
-#define IP_VS_XMIT_TUNNEL(skb, cp) \
-({ \
- int __ret = NF_ACCEPT; \
- \
- (skb)->ipvs_property = 1; \
- if (unlikely((cp)->flags & IP_VS_CONN_F_NFCT)) \
- __ret = ip_vs_confirm_conntrack(skb); \
- if (__ret == NF_ACCEPT) { \
- nf_reset(skb); \
- skb_forward_csum(skb); \
- } \
- __ret; \
-})
-
-#define IP_VS_XMIT_NAT(pf, skb, cp, local) \
-do { \
- (skb)->ipvs_property = 1; \
- if (likely(!((cp)->flags & IP_VS_CONN_F_NFCT))) \
- ip_vs_notrack(skb); \
- else \
- ip_vs_update_conntrack(skb, cp, 1); \
- if (local) \
- return NF_ACCEPT; \
- skb_forward_csum(skb); \
- NF_HOOK(pf, NF_INET_LOCAL_OUT, (skb), NULL, \
- skb_dst(skb)->dev, dst_output); \
-} while (0)
-
-#define IP_VS_XMIT(pf, skb, cp, local) \
-do { \
- (skb)->ipvs_property = 1; \
- if (likely(!((cp)->flags & IP_VS_CONN_F_NFCT))) \
- ip_vs_notrack(skb); \
- if (local) \
- return NF_ACCEPT; \
- skb_forward_csum(skb); \
- NF_HOOK(pf, NF_INET_LOCAL_OUT, (skb), NULL, \
- skb_dst(skb)->dev, dst_output); \
-} while (0)
+/* return NF_STOLEN (sent) or NF_ACCEPT if local=1 (not sent) */
+static inline int ip_vs_send_or_cont(int pf, struct sk_buff *skb,
+ struct ip_vs_conn *cp, int local)
+{
+ int ret = NF_STOLEN;
+
+ skb->ipvs_property = 1;
+ if (likely(!(cp->flags & IP_VS_CONN_F_NFCT)))
+ ip_vs_notrack(skb);
+ if (!local) {
+ skb_forward_csum(skb);
+ NF_HOOK(pf, NF_INET_LOCAL_OUT, skb, NULL, skb_dst(skb)->dev,
+ dst_output);
+ } else
+ ret = NF_ACCEPT;
+ return ret;
+}
/*
@@ -430,7 +537,7 @@ ip_vs_null_xmit(struct sk_buff *skb, struct ip_vs_conn *cp,
struct ip_vs_protocol *pp, struct ip_vs_iphdr *ipvsh)
{
/* we do not touch skb and do not need pskb ptr */
- IP_VS_XMIT(NFPROTO_IPV4, skb, cp, 1);
+ return ip_vs_send_or_cont(NFPROTO_IPV4, skb, cp, 1);
}
@@ -443,52 +550,29 @@ int
ip_vs_bypass_xmit(struct sk_buff *skb, struct ip_vs_conn *cp,
struct ip_vs_protocol *pp, struct ip_vs_iphdr *ipvsh)
{
- struct rtable *rt; /* Route to the other host */
struct iphdr *iph = ip_hdr(skb);
- int mtu;
EnterFunction(10);
- if (!(rt = __ip_vs_get_out_rt(skb, NULL, iph->daddr, RT_TOS(iph->tos),
- IP_VS_RT_MODE_NON_LOCAL, NULL)))
- goto tx_error_icmp;
-
- /* MTU checking */
- mtu = dst_mtu(&rt->dst);
- if ((skb->len > mtu) && (iph->frag_off & htons(IP_DF)) &&
- !skb_is_gso(skb)) {
- ip_rt_put(rt);
- icmp_send(skb, ICMP_DEST_UNREACH,ICMP_FRAG_NEEDED, htonl(mtu));
- IP_VS_DBG_RL("%s(): frag needed\n", __func__);
+ rcu_read_lock();
+ if (__ip_vs_get_out_rt(skb, NULL, iph->daddr, IP_VS_RT_MODE_NON_LOCAL,
+ NULL) < 0)
goto tx_error;
- }
- /*
- * Call ip_send_check because we are not sure it is called
- * after ip_defrag. Is copy-on-write needed?
- */
- if (unlikely((skb = skb_share_check(skb, GFP_ATOMIC)) == NULL)) {
- ip_rt_put(rt);
- return NF_STOLEN;
- }
- ip_send_check(ip_hdr(skb));
-
- /* drop old route */
- skb_dst_drop(skb);
- skb_dst_set(skb, &rt->dst);
+ ip_send_check(iph);
/* Another hack: avoid icmp_send in ip_fragment */
- skb->local_df = 1;
+ skb->ignore_df = 1;
- IP_VS_XMIT(NFPROTO_IPV4, skb, cp, 0);
+ ip_vs_send_or_cont(NFPROTO_IPV4, skb, cp, 0);
+ rcu_read_unlock();
LeaveFunction(10);
return NF_STOLEN;
- tx_error_icmp:
- dst_link_failure(skb);
tx_error:
kfree_skb(skb);
+ rcu_read_unlock();
LeaveFunction(10);
return NF_STOLEN;
}
@@ -496,60 +580,27 @@ ip_vs_bypass_xmit(struct sk_buff *skb, struct ip_vs_conn *cp,
#ifdef CONFIG_IP_VS_IPV6
int
ip_vs_bypass_xmit_v6(struct sk_buff *skb, struct ip_vs_conn *cp,
- struct ip_vs_protocol *pp, struct ip_vs_iphdr *iph)
+ struct ip_vs_protocol *pp, struct ip_vs_iphdr *ipvsh)
{
- struct rt6_info *rt; /* Route to the other host */
- int mtu;
-
EnterFunction(10);
- rt = __ip_vs_get_out_rt_v6(skb, NULL, &iph->daddr.in6, NULL, 0,
- IP_VS_RT_MODE_NON_LOCAL);
- if (!rt)
- goto tx_error_icmp;
-
- /* MTU checking */
- mtu = dst_mtu(&rt->dst);
- if (__mtu_check_toobig_v6(skb, mtu)) {
- if (!skb->dev) {
- struct net *net = dev_net(skb_dst(skb)->dev);
-
- skb->dev = net->loopback_dev;
- }
- /* only send ICMP too big on first fragment */
- if (!iph->fragoffs)
- icmpv6_send(skb, ICMPV6_PKT_TOOBIG, 0, mtu);
- dst_release(&rt->dst);
- IP_VS_DBG_RL("%s(): frag needed\n", __func__);
+ rcu_read_lock();
+ if (__ip_vs_get_out_rt_v6(skb, NULL, &ipvsh->daddr.in6, NULL,
+ ipvsh, 0, IP_VS_RT_MODE_NON_LOCAL) < 0)
goto tx_error;
- }
-
- /*
- * Call ip_send_check because we are not sure it is called
- * after ip_defrag. Is copy-on-write needed?
- */
- skb = skb_share_check(skb, GFP_ATOMIC);
- if (unlikely(skb == NULL)) {
- dst_release(&rt->dst);
- return NF_STOLEN;
- }
-
- /* drop old route */
- skb_dst_drop(skb);
- skb_dst_set(skb, &rt->dst);
/* Another hack: avoid icmp_send in ip_fragment */
- skb->local_df = 1;
+ skb->ignore_df = 1;
- IP_VS_XMIT(NFPROTO_IPV6, skb, cp, 0);
+ ip_vs_send_or_cont(NFPROTO_IPV6, skb, cp, 0);
+ rcu_read_unlock();
LeaveFunction(10);
return NF_STOLEN;
- tx_error_icmp:
- dst_link_failure(skb);
tx_error:
kfree_skb(skb);
+ rcu_read_unlock();
LeaveFunction(10);
return NF_STOLEN;
}
@@ -564,29 +615,30 @@ ip_vs_nat_xmit(struct sk_buff *skb, struct ip_vs_conn *cp,
struct ip_vs_protocol *pp, struct ip_vs_iphdr *ipvsh)
{
struct rtable *rt; /* Route to the other host */
- int mtu;
- struct iphdr *iph = ip_hdr(skb);
- int local;
+ int local, rc, was_input;
EnterFunction(10);
+ rcu_read_lock();
/* check if it is a connection of no-client-port */
if (unlikely(cp->flags & IP_VS_CONN_F_NO_CPORT)) {
__be16 _pt, *p;
- p = skb_header_pointer(skb, iph->ihl*4, sizeof(_pt), &_pt);
+
+ p = skb_header_pointer(skb, ipvsh->len, sizeof(_pt), &_pt);
if (p == NULL)
goto tx_error;
ip_vs_conn_fill_cport(cp, *p);
IP_VS_DBG(10, "filled cport=%d\n", ntohs(*p));
}
- if (!(rt = __ip_vs_get_out_rt(skb, cp->dest, cp->daddr.ip,
- RT_TOS(iph->tos),
- IP_VS_RT_MODE_LOCAL |
- IP_VS_RT_MODE_NON_LOCAL |
- IP_VS_RT_MODE_RDR, NULL)))
- goto tx_error_icmp;
- local = rt->rt_flags & RTCF_LOCAL;
+ was_input = rt_is_input_route(skb_rtable(skb));
+ local = __ip_vs_get_out_rt(skb, cp->dest, cp->daddr.ip,
+ IP_VS_RT_MODE_LOCAL |
+ IP_VS_RT_MODE_NON_LOCAL |
+ IP_VS_RT_MODE_RDR, NULL);
+ if (local < 0)
+ goto tx_error;
+ rt = skb_rtable(skb);
/*
* Avoid duplicate tuple in reply direction for NAT traffic
* to local address when connection is sync-ed
@@ -600,57 +652,31 @@ ip_vs_nat_xmit(struct sk_buff *skb, struct ip_vs_conn *cp,
IP_VS_DBG_RL_PKT(10, AF_INET, pp, skb, 0,
"ip_vs_nat_xmit(): "
"stopping DNAT to local address");
- goto tx_error_put;
+ goto tx_error;
}
}
#endif
/* From world but DNAT to loopback address? */
- if (local && ipv4_is_loopback(cp->daddr.ip) &&
- rt_is_input_route(skb_rtable(skb))) {
+ if (local && ipv4_is_loopback(cp->daddr.ip) && was_input) {
IP_VS_DBG_RL_PKT(1, AF_INET, pp, skb, 0, "ip_vs_nat_xmit(): "
"stopping DNAT to loopback address");
- goto tx_error_put;
- }
-
- /* MTU checking */
- mtu = dst_mtu(&rt->dst);
- if ((skb->len > mtu) && (iph->frag_off & htons(IP_DF)) &&
- !skb_is_gso(skb)) {
- icmp_send(skb, ICMP_DEST_UNREACH,ICMP_FRAG_NEEDED, htonl(mtu));
- IP_VS_DBG_RL_PKT(0, AF_INET, pp, skb, 0,
- "ip_vs_nat_xmit(): frag needed for");
- goto tx_error_put;
+ goto tx_error;
}
/* copy-on-write the packet before mangling it */
if (!skb_make_writable(skb, sizeof(struct iphdr)))
- goto tx_error_put;
+ goto tx_error;
if (skb_cow(skb, rt->dst.dev->hard_header_len))
- goto tx_error_put;
+ goto tx_error;
/* mangle the packet */
if (pp->dnat_handler && !pp->dnat_handler(skb, pp, cp, ipvsh))
- goto tx_error_put;
+ goto tx_error;
ip_hdr(skb)->daddr = cp->daddr.ip;
ip_send_check(ip_hdr(skb));
- if (!local) {
- /* drop old route */
- skb_dst_drop(skb);
- skb_dst_set(skb, &rt->dst);
- } else {
- ip_rt_put(rt);
- /*
- * Some IPv4 replies get local address from routes,
- * not from iph, so while we DNAT after routing
- * we need this second input/output route.
- */
- if (!__ip_vs_reroute_locally(skb))
- goto tx_error;
- }
-
IP_VS_DBG_PKT(10, AF_INET, pp, skb, 0, "After DNAT");
/* FIXME: when application helper enlarges the packet and the length
@@ -658,51 +684,50 @@ ip_vs_nat_xmit(struct sk_buff *skb, struct ip_vs_conn *cp,
MTU problem. */
/* Another hack: avoid icmp_send in ip_fragment */
- skb->local_df = 1;
+ skb->ignore_df = 1;
- IP_VS_XMIT_NAT(NFPROTO_IPV4, skb, cp, local);
+ rc = ip_vs_nat_send_or_cont(NFPROTO_IPV4, skb, cp, local);
+ rcu_read_unlock();
LeaveFunction(10);
- return NF_STOLEN;
+ return rc;
- tx_error_icmp:
- dst_link_failure(skb);
tx_error:
kfree_skb(skb);
+ rcu_read_unlock();
LeaveFunction(10);
return NF_STOLEN;
- tx_error_put:
- ip_rt_put(rt);
- goto tx_error;
}
#ifdef CONFIG_IP_VS_IPV6
int
ip_vs_nat_xmit_v6(struct sk_buff *skb, struct ip_vs_conn *cp,
- struct ip_vs_protocol *pp, struct ip_vs_iphdr *iph)
+ struct ip_vs_protocol *pp, struct ip_vs_iphdr *ipvsh)
{
struct rt6_info *rt; /* Route to the other host */
- int mtu;
- int local;
+ int local, rc;
EnterFunction(10);
+ rcu_read_lock();
/* check if it is a connection of no-client-port */
- if (unlikely(cp->flags & IP_VS_CONN_F_NO_CPORT && !iph->fragoffs)) {
+ if (unlikely(cp->flags & IP_VS_CONN_F_NO_CPORT && !ipvsh->fragoffs)) {
__be16 _pt, *p;
- p = skb_header_pointer(skb, iph->len, sizeof(_pt), &_pt);
+ p = skb_header_pointer(skb, ipvsh->len, sizeof(_pt), &_pt);
if (p == NULL)
goto tx_error;
ip_vs_conn_fill_cport(cp, *p);
IP_VS_DBG(10, "filled cport=%d\n", ntohs(*p));
}
- if (!(rt = __ip_vs_get_out_rt_v6(skb, cp->dest, &cp->daddr.in6, NULL,
- 0, (IP_VS_RT_MODE_LOCAL |
- IP_VS_RT_MODE_NON_LOCAL |
- IP_VS_RT_MODE_RDR))))
- goto tx_error_icmp;
- local = __ip_vs_is_local_route6(rt);
+ local = __ip_vs_get_out_rt_v6(skb, cp->dest, &cp->daddr.in6, NULL,
+ ipvsh, 0,
+ IP_VS_RT_MODE_LOCAL |
+ IP_VS_RT_MODE_NON_LOCAL |
+ IP_VS_RT_MODE_RDR);
+ if (local < 0)
+ goto tx_error;
+ rt = (struct rt6_info *) skb_dst(skb);
/*
* Avoid duplicate tuple in reply direction for NAT traffic
* to local address when connection is sync-ed
@@ -716,7 +741,7 @@ ip_vs_nat_xmit_v6(struct sk_buff *skb, struct ip_vs_conn *cp,
IP_VS_DBG_RL_PKT(10, AF_INET6, pp, skb, 0,
"ip_vs_nat_xmit_v6(): "
"stopping DNAT to local address");
- goto tx_error_put;
+ goto tx_error;
}
}
#endif
@@ -727,46 +752,21 @@ ip_vs_nat_xmit_v6(struct sk_buff *skb, struct ip_vs_conn *cp,
IP_VS_DBG_RL_PKT(1, AF_INET6, pp, skb, 0,
"ip_vs_nat_xmit_v6(): "
"stopping DNAT to loopback address");
- goto tx_error_put;
- }
-
- /* MTU checking */
- mtu = dst_mtu(&rt->dst);
- if (__mtu_check_toobig_v6(skb, mtu)) {
- if (!skb->dev) {
- struct net *net = dev_net(skb_dst(skb)->dev);
-
- skb->dev = net->loopback_dev;
- }
- /* only send ICMP too big on first fragment */
- if (!iph->fragoffs)
- icmpv6_send(skb, ICMPV6_PKT_TOOBIG, 0, mtu);
- IP_VS_DBG_RL_PKT(0, AF_INET6, pp, skb, 0,
- "ip_vs_nat_xmit_v6(): frag needed for");
- goto tx_error_put;
+ goto tx_error;
}
/* copy-on-write the packet before mangling it */
if (!skb_make_writable(skb, sizeof(struct ipv6hdr)))
- goto tx_error_put;
+ goto tx_error;
if (skb_cow(skb, rt->dst.dev->hard_header_len))
- goto tx_error_put;
+ goto tx_error;
/* mangle the packet */
- if (pp->dnat_handler && !pp->dnat_handler(skb, pp, cp, iph))
+ if (pp->dnat_handler && !pp->dnat_handler(skb, pp, cp, ipvsh))
goto tx_error;
ipv6_hdr(skb)->daddr = cp->daddr.in6;
- if (!local || !skb->dev) {
- /* drop the old route when skb is not shared */
- skb_dst_drop(skb);
- skb_dst_set(skb, &rt->dst);
- } else {
- /* destined to loopback, do we need to change route? */
- dst_release(&rt->dst);
- }
-
IP_VS_DBG_PKT(10, AF_INET6, pp, skb, 0, "After DNAT");
/* FIXME: when application helper enlarges the packet and the length
@@ -774,22 +774,19 @@ ip_vs_nat_xmit_v6(struct sk_buff *skb, struct ip_vs_conn *cp,
MTU problem. */
/* Another hack: avoid icmp_send in ip_fragment */
- skb->local_df = 1;
+ skb->ignore_df = 1;
- IP_VS_XMIT_NAT(NFPROTO_IPV6, skb, cp, local);
+ rc = ip_vs_nat_send_or_cont(NFPROTO_IPV6, skb, cp, local);
+ rcu_read_unlock();
LeaveFunction(10);
- return NF_STOLEN;
+ return rc;
-tx_error_icmp:
- dst_link_failure(skb);
tx_error:
LeaveFunction(10);
kfree_skb(skb);
+ rcu_read_unlock();
return NF_STOLEN;
-tx_error_put:
- dst_release(&rt->dst);
- goto tx_error;
}
#endif
@@ -826,56 +823,40 @@ ip_vs_tunnel_xmit(struct sk_buff *skb, struct ip_vs_conn *cp,
__be16 df;
struct iphdr *iph; /* Our new IP header */
unsigned int max_headroom; /* The extra header space needed */
- int mtu;
- int ret;
+ int ret, local;
EnterFunction(10);
- if (!(rt = __ip_vs_get_out_rt(skb, cp->dest, cp->daddr.ip,
- RT_TOS(tos), IP_VS_RT_MODE_LOCAL |
- IP_VS_RT_MODE_NON_LOCAL |
- IP_VS_RT_MODE_CONNECT,
- &saddr)))
- goto tx_error_icmp;
- if (rt->rt_flags & RTCF_LOCAL) {
- ip_rt_put(rt);
- IP_VS_XMIT(NFPROTO_IPV4, skb, cp, 1);
+ rcu_read_lock();
+ local = __ip_vs_get_out_rt(skb, cp->dest, cp->daddr.ip,
+ IP_VS_RT_MODE_LOCAL |
+ IP_VS_RT_MODE_NON_LOCAL |
+ IP_VS_RT_MODE_CONNECT |
+ IP_VS_RT_MODE_TUNNEL, &saddr);
+ if (local < 0)
+ goto tx_error;
+ if (local) {
+ rcu_read_unlock();
+ return ip_vs_send_or_cont(NFPROTO_IPV4, skb, cp, 1);
}
+ rt = skb_rtable(skb);
tdev = rt->dst.dev;
- mtu = dst_mtu(&rt->dst) - sizeof(struct iphdr);
- if (mtu < 68) {
- IP_VS_DBG_RL("%s(): mtu less than 68\n", __func__);
- goto tx_error_put;
- }
- if (rt_is_output_route(skb_rtable(skb)))
- skb_dst(skb)->ops->update_pmtu(skb_dst(skb), NULL, skb, mtu);
-
/* Copy DF, reset fragment offset and MF */
df = sysctl_pmtu_disc(ipvs) ? old_iph->frag_off & htons(IP_DF) : 0;
- if (df && mtu < ntohs(old_iph->tot_len) && !skb_is_gso(skb)) {
- icmp_send(skb, ICMP_DEST_UNREACH,ICMP_FRAG_NEEDED, htonl(mtu));
- IP_VS_DBG_RL("%s(): frag needed\n", __func__);
- goto tx_error_put;
- }
-
/*
* Okay, now see if we can stuff it in the buffer as-is.
*/
max_headroom = LL_RESERVED_SPACE(tdev) + sizeof(struct iphdr);
- if (skb_headroom(skb) < max_headroom
- || skb_cloned(skb) || skb_shared(skb)) {
+ if (skb_headroom(skb) < max_headroom || skb_cloned(skb)) {
struct sk_buff *new_skb =
skb_realloc_headroom(skb, max_headroom);
- if (!new_skb) {
- ip_rt_put(rt);
- kfree_skb(skb);
- IP_VS_ERR_RL("%s(): no memory\n", __func__);
- return NF_STOLEN;
- }
+
+ if (!new_skb)
+ goto tx_error;
consume_skb(skb);
skb = new_skb;
old_iph = ip_hdr(skb);
@@ -890,10 +871,6 @@ ip_vs_tunnel_xmit(struct sk_buff *skb, struct ip_vs_conn *cp,
skb_reset_network_header(skb);
memset(&(IPCB(skb)->opt), 0, sizeof(IPCB(skb)->opt));
- /* drop old route */
- skb_dst_drop(skb);
- skb_dst_set(skb, &rt->dst);
-
/*
* Push down and install the IPIP header.
*/
@@ -906,30 +883,27 @@ ip_vs_tunnel_xmit(struct sk_buff *skb, struct ip_vs_conn *cp,
iph->daddr = cp->daddr.ip;
iph->saddr = saddr;
iph->ttl = old_iph->ttl;
- ip_select_ident(iph, &rt->dst, NULL);
+ ip_select_ident(skb, NULL);
/* Another hack: avoid icmp_send in ip_fragment */
- skb->local_df = 1;
+ skb->ignore_df = 1;
- ret = IP_VS_XMIT_TUNNEL(skb, cp);
+ ret = ip_vs_tunnel_xmit_prepare(skb, cp);
if (ret == NF_ACCEPT)
ip_local_out(skb);
else if (ret == NF_DROP)
kfree_skb(skb);
+ rcu_read_unlock();
LeaveFunction(10);
return NF_STOLEN;
- tx_error_icmp:
- dst_link_failure(skb);
tx_error:
kfree_skb(skb);
+ rcu_read_unlock();
LeaveFunction(10);
return NF_STOLEN;
-tx_error_put:
- ip_rt_put(rt);
- goto tx_error;
}
#ifdef CONFIG_IP_VS_IPV6
@@ -943,60 +917,37 @@ ip_vs_tunnel_xmit_v6(struct sk_buff *skb, struct ip_vs_conn *cp,
struct ipv6hdr *old_iph = ipv6_hdr(skb);
struct ipv6hdr *iph; /* Our new IP header */
unsigned int max_headroom; /* The extra header space needed */
- int mtu;
- int ret;
+ int ret, local;
EnterFunction(10);
- if (!(rt = __ip_vs_get_out_rt_v6(skb, cp->dest, &cp->daddr.in6,
- &saddr, 1, (IP_VS_RT_MODE_LOCAL |
- IP_VS_RT_MODE_NON_LOCAL))))
- goto tx_error_icmp;
- if (__ip_vs_is_local_route6(rt)) {
- dst_release(&rt->dst);
- IP_VS_XMIT(NFPROTO_IPV6, skb, cp, 1);
+ rcu_read_lock();
+ local = __ip_vs_get_out_rt_v6(skb, cp->dest, &cp->daddr.in6,
+ &saddr, ipvsh, 1,
+ IP_VS_RT_MODE_LOCAL |
+ IP_VS_RT_MODE_NON_LOCAL |
+ IP_VS_RT_MODE_TUNNEL);
+ if (local < 0)
+ goto tx_error;
+ if (local) {
+ rcu_read_unlock();
+ return ip_vs_send_or_cont(NFPROTO_IPV6, skb, cp, 1);
}
+ rt = (struct rt6_info *) skb_dst(skb);
tdev = rt->dst.dev;
- mtu = dst_mtu(&rt->dst) - sizeof(struct ipv6hdr);
- if (mtu < IPV6_MIN_MTU) {
- IP_VS_DBG_RL("%s(): mtu less than %d\n", __func__,
- IPV6_MIN_MTU);
- goto tx_error_put;
- }
- if (skb_dst(skb))
- skb_dst(skb)->ops->update_pmtu(skb_dst(skb), NULL, skb, mtu);
-
- /* MTU checking: Notice that 'mtu' have been adjusted before hand */
- if (__mtu_check_toobig_v6(skb, mtu)) {
- if (!skb->dev) {
- struct net *net = dev_net(skb_dst(skb)->dev);
-
- skb->dev = net->loopback_dev;
- }
- /* only send ICMP too big on first fragment */
- if (!ipvsh->fragoffs)
- icmpv6_send(skb, ICMPV6_PKT_TOOBIG, 0, mtu);
- IP_VS_DBG_RL("%s(): frag needed\n", __func__);
- goto tx_error_put;
- }
-
/*
* Okay, now see if we can stuff it in the buffer as-is.
*/
max_headroom = LL_RESERVED_SPACE(tdev) + sizeof(struct ipv6hdr);
- if (skb_headroom(skb) < max_headroom
- || skb_cloned(skb) || skb_shared(skb)) {
+ if (skb_headroom(skb) < max_headroom || skb_cloned(skb)) {
struct sk_buff *new_skb =
skb_realloc_headroom(skb, max_headroom);
- if (!new_skb) {
- dst_release(&rt->dst);
- kfree_skb(skb);
- IP_VS_ERR_RL("%s(): no memory\n", __func__);
- return NF_STOLEN;
- }
+
+ if (!new_skb)
+ goto tx_error;
consume_skb(skb);
skb = new_skb;
old_iph = ipv6_hdr(skb);
@@ -1008,10 +959,6 @@ ip_vs_tunnel_xmit_v6(struct sk_buff *skb, struct ip_vs_conn *cp,
skb_reset_network_header(skb);
memset(&(IPCB(skb)->opt), 0, sizeof(IPCB(skb)->opt));
- /* drop old route */
- skb_dst_drop(skb);
- skb_dst_set(skb, &rt->dst);
-
/*
* Push down and install the IPIP header.
*/
@@ -1027,27 +974,24 @@ ip_vs_tunnel_xmit_v6(struct sk_buff *skb, struct ip_vs_conn *cp,
iph->hop_limit = old_iph->hop_limit;
/* Another hack: avoid icmp_send in ip_fragment */
- skb->local_df = 1;
+ skb->ignore_df = 1;
- ret = IP_VS_XMIT_TUNNEL(skb, cp);
+ ret = ip_vs_tunnel_xmit_prepare(skb, cp);
if (ret == NF_ACCEPT)
ip6_local_out(skb);
else if (ret == NF_DROP)
kfree_skb(skb);
+ rcu_read_unlock();
LeaveFunction(10);
return NF_STOLEN;
-tx_error_icmp:
- dst_link_failure(skb);
tx_error:
kfree_skb(skb);
+ rcu_read_unlock();
LeaveFunction(10);
return NF_STOLEN;
-tx_error_put:
- dst_release(&rt->dst);
- goto tx_error;
}
#endif
@@ -1060,59 +1004,36 @@ int
ip_vs_dr_xmit(struct sk_buff *skb, struct ip_vs_conn *cp,
struct ip_vs_protocol *pp, struct ip_vs_iphdr *ipvsh)
{
- struct rtable *rt; /* Route to the other host */
- struct iphdr *iph = ip_hdr(skb);
- int mtu;
+ int local;
EnterFunction(10);
- if (!(rt = __ip_vs_get_out_rt(skb, cp->dest, cp->daddr.ip,
- RT_TOS(iph->tos),
- IP_VS_RT_MODE_LOCAL |
- IP_VS_RT_MODE_NON_LOCAL |
- IP_VS_RT_MODE_KNOWN_NH, NULL)))
- goto tx_error_icmp;
- if (rt->rt_flags & RTCF_LOCAL) {
- ip_rt_put(rt);
- IP_VS_XMIT(NFPROTO_IPV4, skb, cp, 1);
- }
-
- /* MTU checking */
- mtu = dst_mtu(&rt->dst);
- if ((iph->frag_off & htons(IP_DF)) && skb->len > mtu &&
- !skb_is_gso(skb)) {
- icmp_send(skb, ICMP_DEST_UNREACH,ICMP_FRAG_NEEDED, htonl(mtu));
- ip_rt_put(rt);
- IP_VS_DBG_RL("%s(): frag needed\n", __func__);
+ rcu_read_lock();
+ local = __ip_vs_get_out_rt(skb, cp->dest, cp->daddr.ip,
+ IP_VS_RT_MODE_LOCAL |
+ IP_VS_RT_MODE_NON_LOCAL |
+ IP_VS_RT_MODE_KNOWN_NH, NULL);
+ if (local < 0)
goto tx_error;
+ if (local) {
+ rcu_read_unlock();
+ return ip_vs_send_or_cont(NFPROTO_IPV4, skb, cp, 1);
}
- /*
- * Call ip_send_check because we are not sure it is called
- * after ip_defrag. Is copy-on-write needed?
- */
- if (unlikely((skb = skb_share_check(skb, GFP_ATOMIC)) == NULL)) {
- ip_rt_put(rt);
- return NF_STOLEN;
- }
ip_send_check(ip_hdr(skb));
- /* drop old route */
- skb_dst_drop(skb);
- skb_dst_set(skb, &rt->dst);
-
/* Another hack: avoid icmp_send in ip_fragment */
- skb->local_df = 1;
+ skb->ignore_df = 1;
- IP_VS_XMIT(NFPROTO_IPV4, skb, cp, 0);
+ ip_vs_send_or_cont(NFPROTO_IPV4, skb, cp, 0);
+ rcu_read_unlock();
LeaveFunction(10);
return NF_STOLEN;
- tx_error_icmp:
- dst_link_failure(skb);
tx_error:
kfree_skb(skb);
+ rcu_read_unlock();
LeaveFunction(10);
return NF_STOLEN;
}
@@ -1120,64 +1041,36 @@ ip_vs_dr_xmit(struct sk_buff *skb, struct ip_vs_conn *cp,
#ifdef CONFIG_IP_VS_IPV6
int
ip_vs_dr_xmit_v6(struct sk_buff *skb, struct ip_vs_conn *cp,
- struct ip_vs_protocol *pp, struct ip_vs_iphdr *iph)
+ struct ip_vs_protocol *pp, struct ip_vs_iphdr *ipvsh)
{
- struct rt6_info *rt; /* Route to the other host */
- int mtu;
+ int local;
EnterFunction(10);
- if (!(rt = __ip_vs_get_out_rt_v6(skb, cp->dest, &cp->daddr.in6, NULL,
- 0, (IP_VS_RT_MODE_LOCAL |
- IP_VS_RT_MODE_NON_LOCAL))))
- goto tx_error_icmp;
- if (__ip_vs_is_local_route6(rt)) {
- dst_release(&rt->dst);
- IP_VS_XMIT(NFPROTO_IPV6, skb, cp, 1);
- }
-
- /* MTU checking */
- mtu = dst_mtu(&rt->dst);
- if (__mtu_check_toobig_v6(skb, mtu)) {
- if (!skb->dev) {
- struct net *net = dev_net(skb_dst(skb)->dev);
-
- skb->dev = net->loopback_dev;
- }
- /* only send ICMP too big on first fragment */
- if (!iph->fragoffs)
- icmpv6_send(skb, ICMPV6_PKT_TOOBIG, 0, mtu);
- dst_release(&rt->dst);
- IP_VS_DBG_RL("%s(): frag needed\n", __func__);
+ rcu_read_lock();
+ local = __ip_vs_get_out_rt_v6(skb, cp->dest, &cp->daddr.in6, NULL,
+ ipvsh, 0,
+ IP_VS_RT_MODE_LOCAL |
+ IP_VS_RT_MODE_NON_LOCAL);
+ if (local < 0)
goto tx_error;
+ if (local) {
+ rcu_read_unlock();
+ return ip_vs_send_or_cont(NFPROTO_IPV6, skb, cp, 1);
}
- /*
- * Call ip_send_check because we are not sure it is called
- * after ip_defrag. Is copy-on-write needed?
- */
- skb = skb_share_check(skb, GFP_ATOMIC);
- if (unlikely(skb == NULL)) {
- dst_release(&rt->dst);
- return NF_STOLEN;
- }
-
- /* drop old route */
- skb_dst_drop(skb);
- skb_dst_set(skb, &rt->dst);
-
/* Another hack: avoid icmp_send in ip_fragment */
- skb->local_df = 1;
+ skb->ignore_df = 1;
- IP_VS_XMIT(NFPROTO_IPV6, skb, cp, 0);
+ ip_vs_send_or_cont(NFPROTO_IPV6, skb, cp, 0);
+ rcu_read_unlock();
LeaveFunction(10);
return NF_STOLEN;
-tx_error_icmp:
- dst_link_failure(skb);
tx_error:
kfree_skb(skb);
+ rcu_read_unlock();
LeaveFunction(10);
return NF_STOLEN;
}
@@ -1194,10 +1087,9 @@ ip_vs_icmp_xmit(struct sk_buff *skb, struct ip_vs_conn *cp,
struct ip_vs_iphdr *iph)
{
struct rtable *rt; /* Route to the other host */
- int mtu;
int rc;
int local;
- int rt_mode;
+ int rt_mode, was_input;
EnterFunction(10);
@@ -1217,16 +1109,17 @@ ip_vs_icmp_xmit(struct sk_buff *skb, struct ip_vs_conn *cp,
/*
* mangle and send the packet here (only for VS/NAT)
*/
+ was_input = rt_is_input_route(skb_rtable(skb));
/* LOCALNODE from FORWARD hook is not supported */
rt_mode = (hooknum != NF_INET_FORWARD) ?
IP_VS_RT_MODE_LOCAL | IP_VS_RT_MODE_NON_LOCAL |
IP_VS_RT_MODE_RDR : IP_VS_RT_MODE_NON_LOCAL;
- if (!(rt = __ip_vs_get_out_rt(skb, cp->dest, cp->daddr.ip,
- RT_TOS(ip_hdr(skb)->tos),
- rt_mode, NULL)))
- goto tx_error_icmp;
- local = rt->rt_flags & RTCF_LOCAL;
+ rcu_read_lock();
+ local = __ip_vs_get_out_rt(skb, cp->dest, cp->daddr.ip, rt_mode, NULL);
+ if (local < 0)
+ goto tx_error;
+ rt = skb_rtable(skb);
/*
* Avoid duplicate tuple in reply direction for NAT traffic
@@ -1241,82 +1134,51 @@ ip_vs_icmp_xmit(struct sk_buff *skb, struct ip_vs_conn *cp,
IP_VS_DBG(10, "%s(): "
"stopping DNAT to local address %pI4\n",
__func__, &cp->daddr.ip);
- goto tx_error_put;
+ goto tx_error;
}
}
#endif
/* From world but DNAT to loopback address? */
- if (local && ipv4_is_loopback(cp->daddr.ip) &&
- rt_is_input_route(skb_rtable(skb))) {
+ if (local && ipv4_is_loopback(cp->daddr.ip) && was_input) {
IP_VS_DBG(1, "%s(): "
"stopping DNAT to loopback %pI4\n",
__func__, &cp->daddr.ip);
- goto tx_error_put;
- }
-
- /* MTU checking */
- mtu = dst_mtu(&rt->dst);
- if ((skb->len > mtu) && (ip_hdr(skb)->frag_off & htons(IP_DF)) &&
- !skb_is_gso(skb)) {
- icmp_send(skb, ICMP_DEST_UNREACH, ICMP_FRAG_NEEDED, htonl(mtu));
- IP_VS_DBG_RL("%s(): frag needed\n", __func__);
- goto tx_error_put;
+ goto tx_error;
}
/* copy-on-write the packet before mangling it */
if (!skb_make_writable(skb, offset))
- goto tx_error_put;
+ goto tx_error;
if (skb_cow(skb, rt->dst.dev->hard_header_len))
- goto tx_error_put;
+ goto tx_error;
ip_vs_nat_icmp(skb, pp, cp, 0);
- if (!local) {
- /* drop the old route when skb is not shared */
- skb_dst_drop(skb);
- skb_dst_set(skb, &rt->dst);
- } else {
- ip_rt_put(rt);
- /*
- * Some IPv4 replies get local address from routes,
- * not from iph, so while we DNAT after routing
- * we need this second input/output route.
- */
- if (!__ip_vs_reroute_locally(skb))
- goto tx_error;
- }
-
/* Another hack: avoid icmp_send in ip_fragment */
- skb->local_df = 1;
-
- IP_VS_XMIT_NAT(NFPROTO_IPV4, skb, cp, local);
+ skb->ignore_df = 1;
- rc = NF_STOLEN;
+ rc = ip_vs_nat_send_or_cont(NFPROTO_IPV4, skb, cp, local);
+ rcu_read_unlock();
goto out;
- tx_error_icmp:
- dst_link_failure(skb);
tx_error:
- dev_kfree_skb(skb);
+ kfree_skb(skb);
+ rcu_read_unlock();
rc = NF_STOLEN;
out:
LeaveFunction(10);
return rc;
- tx_error_put:
- ip_rt_put(rt);
- goto tx_error;
}
#ifdef CONFIG_IP_VS_IPV6
int
ip_vs_icmp_xmit_v6(struct sk_buff *skb, struct ip_vs_conn *cp,
struct ip_vs_protocol *pp, int offset, unsigned int hooknum,
- struct ip_vs_iphdr *iph)
+ struct ip_vs_iphdr *ipvsh)
{
struct rt6_info *rt; /* Route to the other host */
- int mtu;
int rc;
int local;
int rt_mode;
@@ -1328,7 +1190,7 @@ ip_vs_icmp_xmit_v6(struct sk_buff *skb, struct ip_vs_conn *cp,
translate address/port back */
if (IP_VS_FWD_METHOD(cp) != IP_VS_CONN_F_MASQ) {
if (cp->packet_xmit)
- rc = cp->packet_xmit(skb, cp, pp, iph);
+ rc = cp->packet_xmit(skb, cp, pp, ipvsh);
else
rc = NF_ACCEPT;
/* do not touch skb anymore */
@@ -1344,11 +1206,12 @@ ip_vs_icmp_xmit_v6(struct sk_buff *skb, struct ip_vs_conn *cp,
rt_mode = (hooknum != NF_INET_FORWARD) ?
IP_VS_RT_MODE_LOCAL | IP_VS_RT_MODE_NON_LOCAL |
IP_VS_RT_MODE_RDR : IP_VS_RT_MODE_NON_LOCAL;
- if (!(rt = __ip_vs_get_out_rt_v6(skb, cp->dest, &cp->daddr.in6, NULL,
- 0, rt_mode)))
- goto tx_error_icmp;
-
- local = __ip_vs_is_local_route6(rt);
+ rcu_read_lock();
+ local = __ip_vs_get_out_rt_v6(skb, cp->dest, &cp->daddr.in6, NULL,
+ ipvsh, 0, rt_mode);
+ if (local < 0)
+ goto tx_error;
+ rt = (struct rt6_info *) skb_dst(skb);
/*
* Avoid duplicate tuple in reply direction for NAT traffic
* to local address when connection is sync-ed
@@ -1362,7 +1225,7 @@ ip_vs_icmp_xmit_v6(struct sk_buff *skb, struct ip_vs_conn *cp,
IP_VS_DBG(10, "%s(): "
"stopping DNAT to local address %pI6\n",
__func__, &cp->daddr.in6);
- goto tx_error_put;
+ goto tx_error;
}
}
#endif
@@ -1373,60 +1236,31 @@ ip_vs_icmp_xmit_v6(struct sk_buff *skb, struct ip_vs_conn *cp,
IP_VS_DBG(1, "%s(): "
"stopping DNAT to loopback %pI6\n",
__func__, &cp->daddr.in6);
- goto tx_error_put;
- }
-
- /* MTU checking */
- mtu = dst_mtu(&rt->dst);
- if (__mtu_check_toobig_v6(skb, mtu)) {
- if (!skb->dev) {
- struct net *net = dev_net(skb_dst(skb)->dev);
-
- skb->dev = net->loopback_dev;
- }
- /* only send ICMP too big on first fragment */
- if (!iph->fragoffs)
- icmpv6_send(skb, ICMPV6_PKT_TOOBIG, 0, mtu);
- IP_VS_DBG_RL("%s(): frag needed\n", __func__);
- goto tx_error_put;
+ goto tx_error;
}
/* copy-on-write the packet before mangling it */
if (!skb_make_writable(skb, offset))
- goto tx_error_put;
+ goto tx_error;
if (skb_cow(skb, rt->dst.dev->hard_header_len))
- goto tx_error_put;
+ goto tx_error;
ip_vs_nat_icmp_v6(skb, pp, cp, 0);
- if (!local || !skb->dev) {
- /* drop the old route when skb is not shared */
- skb_dst_drop(skb);
- skb_dst_set(skb, &rt->dst);
- } else {
- /* destined to loopback, do we need to change route? */
- dst_release(&rt->dst);
- }
-
/* Another hack: avoid icmp_send in ip_fragment */
- skb->local_df = 1;
+ skb->ignore_df = 1;
- IP_VS_XMIT_NAT(NFPROTO_IPV6, skb, cp, local);
-
- rc = NF_STOLEN;
+ rc = ip_vs_nat_send_or_cont(NFPROTO_IPV6, skb, cp, local);
+ rcu_read_unlock();
goto out;
-tx_error_icmp:
- dst_link_failure(skb);
tx_error:
- dev_kfree_skb(skb);
+ kfree_skb(skb);
+ rcu_read_unlock();
rc = NF_STOLEN;
out:
LeaveFunction(10);
return rc;
-tx_error_put:
- dst_release(&rt->dst);
- goto tx_error;
}
#endif
diff --git a/net/netfilter/nf_conntrack_acct.c b/net/netfilter/nf_conntrack_acct.c
index 7df424e2d10..a4b5e2a435a 100644
--- a/net/netfilter/nf_conntrack_acct.c
+++ b/net/netfilter/nf_conntrack_acct.c
@@ -39,21 +39,23 @@ static struct ctl_table acct_sysctl_table[] = {
unsigned int
seq_print_acct(struct seq_file *s, const struct nf_conn *ct, int dir)
{
- struct nf_conn_counter *acct;
+ struct nf_conn_acct *acct;
+ struct nf_conn_counter *counter;
acct = nf_conn_acct_find(ct);
if (!acct)
return 0;
+ counter = acct->counter;
return seq_printf(s, "packets=%llu bytes=%llu ",
- (unsigned long long)atomic64_read(&acct[dir].packets),
- (unsigned long long)atomic64_read(&acct[dir].bytes));
+ (unsigned long long)atomic64_read(&counter[dir].packets),
+ (unsigned long long)atomic64_read(&counter[dir].bytes));
};
EXPORT_SYMBOL_GPL(seq_print_acct);
static struct nf_ct_ext_type acct_extend __read_mostly = {
- .len = sizeof(struct nf_conn_counter[IP_CT_DIR_MAX]),
- .align = __alignof__(struct nf_conn_counter[IP_CT_DIR_MAX]),
+ .len = sizeof(struct nf_conn_acct),
+ .align = __alignof__(struct nf_conn_acct),
.id = NF_CT_EXT_ACCT,
};
@@ -106,36 +108,26 @@ static void nf_conntrack_acct_fini_sysctl(struct net *net)
}
#endif
-int nf_conntrack_acct_init(struct net *net)
+int nf_conntrack_acct_pernet_init(struct net *net)
{
- int ret;
-
net->ct.sysctl_acct = nf_ct_acct;
+ return nf_conntrack_acct_init_sysctl(net);
+}
- if (net_eq(net, &init_net)) {
- ret = nf_ct_extend_register(&acct_extend);
- if (ret < 0) {
- printk(KERN_ERR "nf_conntrack_acct: Unable to register extension\n");
- goto out_extend_register;
- }
- }
+void nf_conntrack_acct_pernet_fini(struct net *net)
+{
+ nf_conntrack_acct_fini_sysctl(net);
+}
- ret = nf_conntrack_acct_init_sysctl(net);
+int nf_conntrack_acct_init(void)
+{
+ int ret = nf_ct_extend_register(&acct_extend);
if (ret < 0)
- goto out_sysctl;
-
- return 0;
-
-out_sysctl:
- if (net_eq(net, &init_net))
- nf_ct_extend_unregister(&acct_extend);
-out_extend_register:
+ pr_err("nf_conntrack_acct: Unable to register extension\n");
return ret;
}
-void nf_conntrack_acct_fini(struct net *net)
+void nf_conntrack_acct_fini(void)
{
- nf_conntrack_acct_fini_sysctl(net);
- if (net_eq(net, &init_net))
- nf_ct_extend_unregister(&acct_extend);
+ nf_ct_extend_unregister(&acct_extend);
}
diff --git a/net/netfilter/nf_conntrack_amanda.c b/net/netfilter/nf_conntrack_amanda.c
index c514fe6033d..b8b95f4027c 100644
--- a/net/netfilter/nf_conntrack_amanda.c
+++ b/net/netfilter/nf_conntrack_amanda.c
@@ -2,6 +2,7 @@
*
* (C) 2002 by Brian J. Murrell <netfilter@interlinx.bc.ca>
* based on HW's ip_conntrack_irc.c as well as other modules
+ * (C) 2006 Patrick McHardy <kaber@trash.net>
*
* This program is free software; you can redistribute it and/or
* modify it under the terms of the GNU General Public License
@@ -145,6 +146,7 @@ static int amanda_help(struct sk_buff *skb,
exp = nf_ct_expect_alloc(ct);
if (exp == NULL) {
+ nf_ct_helper_log(skb, ct, "cannot alloc expectation");
ret = NF_DROP;
goto out;
}
@@ -158,8 +160,10 @@ static int amanda_help(struct sk_buff *skb,
if (nf_nat_amanda && ct->status & IPS_NAT_MASK)
ret = nf_nat_amanda(skb, ctinfo, protoff,
off - dataoff, len, exp);
- else if (nf_ct_expect_related(exp) != 0)
+ else if (nf_ct_expect_related(exp) != 0) {
+ nf_ct_helper_log(skb, ct, "cannot add expectation");
ret = NF_DROP;
+ }
nf_ct_expect_put(exp);
}
diff --git a/net/netfilter/nf_conntrack_core.c b/net/netfilter/nf_conntrack_core.c
index 016d95ead93..1f4f954c4b4 100644
--- a/net/netfilter/nf_conntrack_core.c
+++ b/net/netfilter/nf_conntrack_core.c
@@ -5,6 +5,7 @@
/* (C) 1999-2001 Paul `Rusty' Russell
* (C) 2002-2006 Netfilter Core Team <coreteam@netfilter.org>
* (C) 2003,2004 USAGI/WIDE Project <http://www.linux-ipv6.org>
+ * (C) 2005-2012 Patrick McHardy <kaber@trash.net>
*
* This program is free software; you can redistribute it and/or modify
* it under the terms of the GNU General Public License version 2 as
@@ -38,6 +39,7 @@
#include <net/netfilter/nf_conntrack_l4proto.h>
#include <net/netfilter/nf_conntrack_expect.h>
#include <net/netfilter/nf_conntrack_helper.h>
+#include <net/netfilter/nf_conntrack_seqadj.h>
#include <net/netfilter/nf_conntrack_core.h>
#include <net/netfilter/nf_conntrack_extend.h>
#include <net/netfilter/nf_conntrack_acct.h>
@@ -45,8 +47,11 @@
#include <net/netfilter/nf_conntrack_zones.h>
#include <net/netfilter/nf_conntrack_timestamp.h>
#include <net/netfilter/nf_conntrack_timeout.h>
+#include <net/netfilter/nf_conntrack_labels.h>
+#include <net/netfilter/nf_conntrack_synproxy.h>
#include <net/netfilter/nf_nat.h>
#include <net/netfilter/nf_nat_core.h>
+#include <net/netfilter/nf_nat_helper.h>
#define NF_CONNTRACK_VERSION "0.5.0"
@@ -55,14 +60,59 @@ int (*nfnetlink_parse_nat_setup_hook)(struct nf_conn *ct,
const struct nlattr *attr) __read_mostly;
EXPORT_SYMBOL_GPL(nfnetlink_parse_nat_setup_hook);
-int (*nf_nat_seq_adjust_hook)(struct sk_buff *skb,
- struct nf_conn *ct,
- enum ip_conntrack_info ctinfo,
- unsigned int protoff);
-EXPORT_SYMBOL_GPL(nf_nat_seq_adjust_hook);
+__cacheline_aligned_in_smp spinlock_t nf_conntrack_locks[CONNTRACK_LOCKS];
+EXPORT_SYMBOL_GPL(nf_conntrack_locks);
-DEFINE_SPINLOCK(nf_conntrack_lock);
-EXPORT_SYMBOL_GPL(nf_conntrack_lock);
+__cacheline_aligned_in_smp DEFINE_SPINLOCK(nf_conntrack_expect_lock);
+EXPORT_SYMBOL_GPL(nf_conntrack_expect_lock);
+
+static void nf_conntrack_double_unlock(unsigned int h1, unsigned int h2)
+{
+ h1 %= CONNTRACK_LOCKS;
+ h2 %= CONNTRACK_LOCKS;
+ spin_unlock(&nf_conntrack_locks[h1]);
+ if (h1 != h2)
+ spin_unlock(&nf_conntrack_locks[h2]);
+}
+
+/* return true if we need to recompute hashes (in case hash table was resized) */
+static bool nf_conntrack_double_lock(struct net *net, unsigned int h1,
+ unsigned int h2, unsigned int sequence)
+{
+ h1 %= CONNTRACK_LOCKS;
+ h2 %= CONNTRACK_LOCKS;
+ if (h1 <= h2) {
+ spin_lock(&nf_conntrack_locks[h1]);
+ if (h1 != h2)
+ spin_lock_nested(&nf_conntrack_locks[h2],
+ SINGLE_DEPTH_NESTING);
+ } else {
+ spin_lock(&nf_conntrack_locks[h2]);
+ spin_lock_nested(&nf_conntrack_locks[h1],
+ SINGLE_DEPTH_NESTING);
+ }
+ if (read_seqcount_retry(&net->ct.generation, sequence)) {
+ nf_conntrack_double_unlock(h1, h2);
+ return true;
+ }
+ return false;
+}
+
+static void nf_conntrack_all_lock(void)
+{
+ int i;
+
+ for (i = 0; i < CONNTRACK_LOCKS; i++)
+ spin_lock_nested(&nf_conntrack_locks[i], i);
+}
+
+static void nf_conntrack_all_unlock(void)
+{
+ int i;
+
+ for (i = 0; i < CONNTRACK_LOCKS; i++)
+ spin_unlock(&nf_conntrack_locks[i]);
+}
unsigned int nf_conntrack_htable_size __read_mostly;
EXPORT_SYMBOL_GPL(nf_conntrack_htable_size);
@@ -193,6 +243,50 @@ clean_from_lists(struct nf_conn *ct)
nf_ct_remove_expectations(ct);
}
+/* must be called with local_bh_disable */
+static void nf_ct_add_to_dying_list(struct nf_conn *ct)
+{
+ struct ct_pcpu *pcpu;
+
+ /* add this conntrack to the (per cpu) dying list */
+ ct->cpu = smp_processor_id();
+ pcpu = per_cpu_ptr(nf_ct_net(ct)->ct.pcpu_lists, ct->cpu);
+
+ spin_lock(&pcpu->lock);
+ hlist_nulls_add_head(&ct->tuplehash[IP_CT_DIR_ORIGINAL].hnnode,
+ &pcpu->dying);
+ spin_unlock(&pcpu->lock);
+}
+
+/* must be called with local_bh_disable */
+static void nf_ct_add_to_unconfirmed_list(struct nf_conn *ct)
+{
+ struct ct_pcpu *pcpu;
+
+ /* add this conntrack to the (per cpu) unconfirmed list */
+ ct->cpu = smp_processor_id();
+ pcpu = per_cpu_ptr(nf_ct_net(ct)->ct.pcpu_lists, ct->cpu);
+
+ spin_lock(&pcpu->lock);
+ hlist_nulls_add_head(&ct->tuplehash[IP_CT_DIR_ORIGINAL].hnnode,
+ &pcpu->unconfirmed);
+ spin_unlock(&pcpu->lock);
+}
+
+/* must be called with local_bh_disable */
+static void nf_ct_del_from_dying_or_unconfirmed_list(struct nf_conn *ct)
+{
+ struct ct_pcpu *pcpu;
+
+ /* We overload first tuple to link into unconfirmed or dying list.*/
+ pcpu = per_cpu_ptr(nf_ct_net(ct)->ct.pcpu_lists, ct->cpu);
+
+ spin_lock(&pcpu->lock);
+ BUG_ON(hlist_nulls_unhashed(&ct->tuplehash[IP_CT_DIR_ORIGINAL].hnnode));
+ hlist_nulls_del_rcu(&ct->tuplehash[IP_CT_DIR_ORIGINAL].hnnode);
+ spin_unlock(&pcpu->lock);
+}
+
static void
destroy_conntrack(struct nf_conntrack *nfct)
{
@@ -204,9 +298,6 @@ destroy_conntrack(struct nf_conntrack *nfct)
NF_CT_ASSERT(atomic_read(&nfct->use) == 0);
NF_CT_ASSERT(!timer_pending(&ct->timeout));
- /* To make sure we don't get any weird locking issues here:
- * destroy_conntrack() MUST NOT be called with a write lock
- * to nf_conntrack_lock!!! -HW */
rcu_read_lock();
l4proto = __nf_ct_l4proto_find(nf_ct_l3num(ct), nf_ct_protonum(ct));
if (l4proto && l4proto->destroy)
@@ -214,19 +305,18 @@ destroy_conntrack(struct nf_conntrack *nfct)
rcu_read_unlock();
- spin_lock_bh(&nf_conntrack_lock);
+ local_bh_disable();
/* Expectations will have been removed in clean_from_lists,
* except TFTP can create an expectation on the first packet,
* before connection is in the list, so we need to clean here,
- * too. */
+ * too.
+ */
nf_ct_remove_expectations(ct);
- /* We overload first tuple to link into unconfirmed or dying list.*/
- BUG_ON(hlist_nulls_unhashed(&ct->tuplehash[IP_CT_DIR_ORIGINAL].hnnode));
- hlist_nulls_del_rcu(&ct->tuplehash[IP_CT_DIR_ORIGINAL].hnnode);
+ nf_ct_del_from_dying_or_unconfirmed_list(ct);
NF_CT_STAT_INC(net, delete);
- spin_unlock_bh(&nf_conntrack_lock);
+ local_bh_enable();
if (ct->master)
nf_ct_put(ct->master);
@@ -235,22 +325,32 @@ destroy_conntrack(struct nf_conntrack *nfct)
nf_conntrack_free(ct);
}
-void nf_ct_delete_from_lists(struct nf_conn *ct)
+static void nf_ct_delete_from_lists(struct nf_conn *ct)
{
struct net *net = nf_ct_net(ct);
+ unsigned int hash, reply_hash;
+ u16 zone = nf_ct_zone(ct);
+ unsigned int sequence;
nf_ct_helper_destroy(ct);
- spin_lock_bh(&nf_conntrack_lock);
- /* Inside lock so preempt is disabled on module removal path.
- * Otherwise we can get spurious warnings. */
- NF_CT_STAT_INC(net, delete_list);
+
+ local_bh_disable();
+ do {
+ sequence = read_seqcount_begin(&net->ct.generation);
+ hash = hash_conntrack(net, zone,
+ &ct->tuplehash[IP_CT_DIR_ORIGINAL].tuple);
+ reply_hash = hash_conntrack(net, zone,
+ &ct->tuplehash[IP_CT_DIR_REPLY].tuple);
+ } while (nf_conntrack_double_lock(net, hash, reply_hash, sequence));
+
clean_from_lists(ct);
- /* add this conntrack to the dying list */
- hlist_nulls_add_head(&ct->tuplehash[IP_CT_DIR_ORIGINAL].hnnode,
- &net->ct.dying);
- spin_unlock_bh(&nf_conntrack_lock);
+ nf_conntrack_double_unlock(hash, reply_hash);
+
+ nf_ct_add_to_dying_list(ct);
+
+ NF_CT_STAT_INC(net, delete_list);
+ local_bh_enable();
}
-EXPORT_SYMBOL_GPL(nf_ct_delete_from_lists);
static void death_by_event(unsigned long ul_conntrack)
{
@@ -263,7 +363,7 @@ static void death_by_event(unsigned long ul_conntrack)
if (nf_conntrack_event(IPCT_DESTROY, ct) < 0) {
/* bad luck, let's retry again */
ecache->timeout.expires = jiffies +
- (random32() % net->ct.sysctl_events_retry_timeout);
+ (prandom_u32() % net->ct.sysctl_events_retry_timeout);
add_timer(&ecache->timeout);
return;
}
@@ -272,7 +372,7 @@ static void death_by_event(unsigned long ul_conntrack)
nf_ct_put(ct);
}
-void nf_ct_dying_timeout(struct nf_conn *ct)
+static void nf_ct_dying_timeout(struct nf_conn *ct)
{
struct net *net = nf_ct_net(ct);
struct nf_conntrack_ecache *ecache = nf_ct_ecache_find(ct);
@@ -282,38 +382,57 @@ void nf_ct_dying_timeout(struct nf_conn *ct)
/* set a new timer to retry event delivery */
setup_timer(&ecache->timeout, death_by_event, (unsigned long)ct);
ecache->timeout.expires = jiffies +
- (random32() % net->ct.sysctl_events_retry_timeout);
+ (prandom_u32() % net->ct.sysctl_events_retry_timeout);
add_timer(&ecache->timeout);
}
-EXPORT_SYMBOL_GPL(nf_ct_dying_timeout);
-static void death_by_timeout(unsigned long ul_conntrack)
+bool nf_ct_delete(struct nf_conn *ct, u32 portid, int report)
{
- struct nf_conn *ct = (void *)ul_conntrack;
struct nf_conn_tstamp *tstamp;
tstamp = nf_conn_tstamp_find(ct);
if (tstamp && tstamp->stop == 0)
tstamp->stop = ktime_to_ns(ktime_get_real());
- if (!test_bit(IPS_DYING_BIT, &ct->status) &&
- unlikely(nf_conntrack_event(IPCT_DESTROY, ct) < 0)) {
+ if (!nf_ct_is_dying(ct) &&
+ unlikely(nf_conntrack_event_report(IPCT_DESTROY, ct,
+ portid, report) < 0)) {
/* destroy event was not delivered */
nf_ct_delete_from_lists(ct);
nf_ct_dying_timeout(ct);
- return;
+ return false;
}
set_bit(IPS_DYING_BIT, &ct->status);
nf_ct_delete_from_lists(ct);
nf_ct_put(ct);
+ return true;
+}
+EXPORT_SYMBOL_GPL(nf_ct_delete);
+
+static void death_by_timeout(unsigned long ul_conntrack)
+{
+ nf_ct_delete((struct nf_conn *)ul_conntrack, 0, 0);
+}
+
+static inline bool
+nf_ct_key_equal(struct nf_conntrack_tuple_hash *h,
+ const struct nf_conntrack_tuple *tuple,
+ u16 zone)
+{
+ struct nf_conn *ct = nf_ct_tuplehash_to_ctrack(h);
+
+ /* A conntrack can be recreated with the equal tuple,
+ * so we need to check that the conntrack is confirmed
+ */
+ return nf_ct_tuple_equal(tuple, &h->tuple) &&
+ nf_ct_zone(ct) == zone &&
+ nf_ct_is_confirmed(ct);
}
/*
* Warning :
* - Caller must take a reference on returned object
* and recheck nf_ct_tuple_equal(tuple, &h->tuple)
- * OR
- * - Caller must lock nf_conntrack_lock before calling this function
*/
static struct nf_conntrack_tuple_hash *
____nf_conntrack_find(struct net *net, u16 zone,
@@ -329,8 +448,7 @@ ____nf_conntrack_find(struct net *net, u16 zone,
local_bh_disable();
begin:
hlist_nulls_for_each_entry_rcu(h, n, &net->ct.hash[bucket], hnnode) {
- if (nf_ct_tuple_equal(tuple, &h->tuple) &&
- nf_ct_zone(nf_ct_tuplehash_to_ctrack(h)) == zone) {
+ if (nf_ct_key_equal(h, tuple, zone)) {
NF_CT_STAT_INC(net, found);
local_bh_enable();
return h;
@@ -351,15 +469,6 @@ begin:
return NULL;
}
-struct nf_conntrack_tuple_hash *
-__nf_conntrack_find(struct net *net, u16 zone,
- const struct nf_conntrack_tuple *tuple)
-{
- return ____nf_conntrack_find(net, zone, tuple,
- hash_conntrack_raw(tuple, zone));
-}
-EXPORT_SYMBOL_GPL(__nf_conntrack_find);
-
/* Find a connection corresponding to a tuple. */
static struct nf_conntrack_tuple_hash *
__nf_conntrack_find_get(struct net *net, u16 zone,
@@ -377,8 +486,7 @@ begin:
!atomic_inc_not_zero(&ct->ct_general.use)))
h = NULL;
else {
- if (unlikely(!nf_ct_tuple_equal(tuple, &h->tuple) ||
- nf_ct_zone(ct) != zone)) {
+ if (unlikely(!nf_ct_key_equal(h, tuple, zone))) {
nf_ct_put(ct);
goto begin;
}
@@ -400,32 +508,36 @@ EXPORT_SYMBOL_GPL(nf_conntrack_find_get);
static void __nf_conntrack_hash_insert(struct nf_conn *ct,
unsigned int hash,
- unsigned int repl_hash)
+ unsigned int reply_hash)
{
struct net *net = nf_ct_net(ct);
hlist_nulls_add_head_rcu(&ct->tuplehash[IP_CT_DIR_ORIGINAL].hnnode,
&net->ct.hash[hash]);
hlist_nulls_add_head_rcu(&ct->tuplehash[IP_CT_DIR_REPLY].hnnode,
- &net->ct.hash[repl_hash]);
+ &net->ct.hash[reply_hash]);
}
int
nf_conntrack_hash_check_insert(struct nf_conn *ct)
{
struct net *net = nf_ct_net(ct);
- unsigned int hash, repl_hash;
+ unsigned int hash, reply_hash;
struct nf_conntrack_tuple_hash *h;
struct hlist_nulls_node *n;
u16 zone;
+ unsigned int sequence;
zone = nf_ct_zone(ct);
- hash = hash_conntrack(net, zone,
- &ct->tuplehash[IP_CT_DIR_ORIGINAL].tuple);
- repl_hash = hash_conntrack(net, zone,
- &ct->tuplehash[IP_CT_DIR_REPLY].tuple);
- spin_lock_bh(&nf_conntrack_lock);
+ local_bh_disable();
+ do {
+ sequence = read_seqcount_begin(&net->ct.generation);
+ hash = hash_conntrack(net, zone,
+ &ct->tuplehash[IP_CT_DIR_ORIGINAL].tuple);
+ reply_hash = hash_conntrack(net, zone,
+ &ct->tuplehash[IP_CT_DIR_REPLY].tuple);
+ } while (nf_conntrack_double_lock(net, hash, reply_hash, sequence));
/* See if there's one in the list already, including reverse */
hlist_nulls_for_each_entry(h, n, &net->ct.hash[hash], hnnode)
@@ -433,32 +545,57 @@ nf_conntrack_hash_check_insert(struct nf_conn *ct)
&h->tuple) &&
zone == nf_ct_zone(nf_ct_tuplehash_to_ctrack(h)))
goto out;
- hlist_nulls_for_each_entry(h, n, &net->ct.hash[repl_hash], hnnode)
+ hlist_nulls_for_each_entry(h, n, &net->ct.hash[reply_hash], hnnode)
if (nf_ct_tuple_equal(&ct->tuplehash[IP_CT_DIR_REPLY].tuple,
&h->tuple) &&
zone == nf_ct_zone(nf_ct_tuplehash_to_ctrack(h)))
goto out;
add_timer(&ct->timeout);
- nf_conntrack_get(&ct->ct_general);
- __nf_conntrack_hash_insert(ct, hash, repl_hash);
+ smp_wmb();
+ /* The caller holds a reference to this object */
+ atomic_set(&ct->ct_general.use, 2);
+ __nf_conntrack_hash_insert(ct, hash, reply_hash);
+ nf_conntrack_double_unlock(hash, reply_hash);
NF_CT_STAT_INC(net, insert);
- spin_unlock_bh(&nf_conntrack_lock);
-
+ local_bh_enable();
return 0;
out:
+ nf_conntrack_double_unlock(hash, reply_hash);
NF_CT_STAT_INC(net, insert_failed);
- spin_unlock_bh(&nf_conntrack_lock);
+ local_bh_enable();
return -EEXIST;
}
EXPORT_SYMBOL_GPL(nf_conntrack_hash_check_insert);
+/* deletion from this larval template list happens via nf_ct_put() */
+void nf_conntrack_tmpl_insert(struct net *net, struct nf_conn *tmpl)
+{
+ struct ct_pcpu *pcpu;
+
+ __set_bit(IPS_TEMPLATE_BIT, &tmpl->status);
+ __set_bit(IPS_CONFIRMED_BIT, &tmpl->status);
+ nf_conntrack_get(&tmpl->ct_general);
+
+ /* add this conntrack to the (per cpu) tmpl list */
+ local_bh_disable();
+ tmpl->cpu = smp_processor_id();
+ pcpu = per_cpu_ptr(nf_ct_net(tmpl)->ct.pcpu_lists, tmpl->cpu);
+
+ spin_lock(&pcpu->lock);
+ /* Overload tuple linked list to put us in template list. */
+ hlist_nulls_add_head_rcu(&tmpl->tuplehash[IP_CT_DIR_ORIGINAL].hnnode,
+ &pcpu->tmpl);
+ spin_unlock_bh(&pcpu->lock);
+}
+EXPORT_SYMBOL_GPL(nf_conntrack_tmpl_insert);
+
/* Confirm a connection given skb; places it in hash table */
int
__nf_conntrack_confirm(struct sk_buff *skb)
{
- unsigned int hash, repl_hash;
+ unsigned int hash, reply_hash;
struct nf_conntrack_tuple_hash *h;
struct nf_conn *ct;
struct nf_conn_help *help;
@@ -467,6 +604,7 @@ __nf_conntrack_confirm(struct sk_buff *skb)
enum ip_conntrack_info ctinfo;
struct net *net;
u16 zone;
+ unsigned int sequence;
ct = nf_ct_get(skb, &ctinfo);
net = nf_ct_net(ct);
@@ -479,31 +617,37 @@ __nf_conntrack_confirm(struct sk_buff *skb)
return NF_ACCEPT;
zone = nf_ct_zone(ct);
- /* reuse the hash saved before */
- hash = *(unsigned long *)&ct->tuplehash[IP_CT_DIR_REPLY].hnnode.pprev;
- hash = hash_bucket(hash, net);
- repl_hash = hash_conntrack(net, zone,
- &ct->tuplehash[IP_CT_DIR_REPLY].tuple);
+ local_bh_disable();
+
+ do {
+ sequence = read_seqcount_begin(&net->ct.generation);
+ /* reuse the hash saved before */
+ hash = *(unsigned long *)&ct->tuplehash[IP_CT_DIR_REPLY].hnnode.pprev;
+ hash = hash_bucket(hash, net);
+ reply_hash = hash_conntrack(net, zone,
+ &ct->tuplehash[IP_CT_DIR_REPLY].tuple);
+
+ } while (nf_conntrack_double_lock(net, hash, reply_hash, sequence));
/* We're not in hash table, and we refuse to set up related
- connections for unconfirmed conns. But packet copies and
- REJECT will give spurious warnings here. */
+ * connections for unconfirmed conns. But packet copies and
+ * REJECT will give spurious warnings here.
+ */
/* NF_CT_ASSERT(atomic_read(&ct->ct_general.use) == 1); */
/* No external references means no one else could have
- confirmed us. */
+ * confirmed us.
+ */
NF_CT_ASSERT(!nf_ct_is_confirmed(ct));
pr_debug("Confirming conntrack %p\n", ct);
-
- spin_lock_bh(&nf_conntrack_lock);
-
/* We have to check the DYING flag inside the lock to prevent
a race against nf_ct_get_next_corpse() possibly called from
user context, else we insert an already 'dead' hash, blocking
further use of that particular connection -JM */
if (unlikely(nf_ct_is_dying(ct))) {
- spin_unlock_bh(&nf_conntrack_lock);
+ nf_conntrack_double_unlock(hash, reply_hash);
+ local_bh_enable();
return NF_ACCEPT;
}
@@ -515,14 +659,13 @@ __nf_conntrack_confirm(struct sk_buff *skb)
&h->tuple) &&
zone == nf_ct_zone(nf_ct_tuplehash_to_ctrack(h)))
goto out;
- hlist_nulls_for_each_entry(h, n, &net->ct.hash[repl_hash], hnnode)
+ hlist_nulls_for_each_entry(h, n, &net->ct.hash[reply_hash], hnnode)
if (nf_ct_tuple_equal(&ct->tuplehash[IP_CT_DIR_REPLY].tuple,
&h->tuple) &&
zone == nf_ct_zone(nf_ct_tuplehash_to_ctrack(h)))
goto out;
- /* Remove from unconfirmed list */
- hlist_nulls_del_rcu(&ct->tuplehash[IP_CT_DIR_ORIGINAL].hnnode);
+ nf_ct_del_from_dying_or_unconfirmed_list(ct);
/* Timer relative to confirmation time, not original
setting time, otherwise we'd get timer wrap in
@@ -545,9 +688,10 @@ __nf_conntrack_confirm(struct sk_buff *skb)
* guarantee that no other CPU can find the conntrack before the above
* stores are visible.
*/
- __nf_conntrack_hash_insert(ct, hash, repl_hash);
+ __nf_conntrack_hash_insert(ct, hash, reply_hash);
+ nf_conntrack_double_unlock(hash, reply_hash);
NF_CT_STAT_INC(net, insert);
- spin_unlock_bh(&nf_conntrack_lock);
+ local_bh_enable();
help = nfct_help(ct);
if (help && help->helper)
@@ -558,8 +702,9 @@ __nf_conntrack_confirm(struct sk_buff *skb)
return NF_ACCEPT;
out:
+ nf_conntrack_double_unlock(hash, reply_hash);
NF_CT_STAT_INC(net, insert_failed);
- spin_unlock_bh(&nf_conntrack_lock);
+ local_bh_enable();
return NF_DROP;
}
EXPORT_SYMBOL_GPL(__nf_conntrack_confirm);
@@ -602,48 +747,54 @@ EXPORT_SYMBOL_GPL(nf_conntrack_tuple_taken);
/* There's a small race here where we may free a just-assured
connection. Too bad: we're in trouble anyway. */
-static noinline int early_drop(struct net *net, unsigned int hash)
+static noinline int early_drop(struct net *net, unsigned int _hash)
{
/* Use oldest entry, which is roughly LRU */
struct nf_conntrack_tuple_hash *h;
struct nf_conn *ct = NULL, *tmp;
struct hlist_nulls_node *n;
- unsigned int i, cnt = 0;
+ unsigned int i = 0, cnt = 0;
int dropped = 0;
+ unsigned int hash, sequence;
+ spinlock_t *lockp;
- rcu_read_lock();
- for (i = 0; i < net->ct.htable_size; i++) {
+ local_bh_disable();
+restart:
+ sequence = read_seqcount_begin(&net->ct.generation);
+ hash = hash_bucket(_hash, net);
+ for (; i < net->ct.htable_size; i++) {
+ lockp = &nf_conntrack_locks[hash % CONNTRACK_LOCKS];
+ spin_lock(lockp);
+ if (read_seqcount_retry(&net->ct.generation, sequence)) {
+ spin_unlock(lockp);
+ goto restart;
+ }
hlist_nulls_for_each_entry_rcu(h, n, &net->ct.hash[hash],
hnnode) {
tmp = nf_ct_tuplehash_to_ctrack(h);
- if (!test_bit(IPS_ASSURED_BIT, &tmp->status))
+ if (!test_bit(IPS_ASSURED_BIT, &tmp->status) &&
+ !nf_ct_is_dying(tmp) &&
+ atomic_inc_not_zero(&tmp->ct_general.use)) {
ct = tmp;
+ break;
+ }
cnt++;
}
- if (ct != NULL) {
- if (likely(!nf_ct_is_dying(ct) &&
- atomic_inc_not_zero(&ct->ct_general.use)))
- break;
- else
- ct = NULL;
- }
+ hash = (hash + 1) % net->ct.htable_size;
+ spin_unlock(lockp);
- if (cnt >= NF_CT_EVICTION_RANGE)
+ if (ct || cnt >= NF_CT_EVICTION_RANGE)
break;
- hash = (hash + 1) % net->ct.htable_size;
}
- rcu_read_unlock();
+ local_bh_enable();
if (!ct)
return dropped;
if (del_timer(&ct->timeout)) {
- death_by_timeout((unsigned long)ct);
- /* Check if we indeed killed this entry. Reliable event
- delivery may have inserted it into the dying list. */
- if (test_bit(IPS_DYING_BIT, &ct->status)) {
+ if (nf_ct_delete(ct, 0, 0)) {
dropped = 1;
NF_CT_STAT_INC_ATOMIC(net, early_drop);
}
@@ -686,7 +837,7 @@ __nf_conntrack_alloc(struct net *net, u16 zone,
if (nf_conntrack_max &&
unlikely(atomic_read(&net->ct.count) > nf_conntrack_max)) {
- if (!early_drop(net, hash_bucket(hash, net))) {
+ if (!early_drop(net, hash)) {
atomic_dec(&net->ct.count);
net_warn_ratelimited("nf_conntrack: table full, dropping packet\n");
return ERR_PTR(-ENOMEM);
@@ -728,11 +879,10 @@ __nf_conntrack_alloc(struct net *net, u16 zone,
nf_ct_zone->id = zone;
}
#endif
- /*
- * changes to lookup keys must be done before setting refcnt to 1
+ /* Because we use RCU lookups, we set ct_general.use to zero before
+ * this is inserted in any list.
*/
- smp_wmb();
- atomic_set(&ct->ct_general.use, 1);
+ atomic_set(&ct->ct_general.use, 0);
return ct;
#ifdef CONFIG_NF_CONNTRACK_ZONES
@@ -756,13 +906,20 @@ void nf_conntrack_free(struct nf_conn *ct)
{
struct net *net = nf_ct_net(ct);
+ /* A freed object has refcnt == 0, that's
+ * the golden rule for SLAB_DESTROY_BY_RCU
+ */
+ NF_CT_ASSERT(atomic_read(&ct->ct_general.use) == 0);
+
nf_ct_ext_destroy(ct);
- atomic_dec(&net->ct.count);
nf_ct_ext_free(ct);
kmem_cache_free(net->ct.nf_conntrack_cachep, ct);
+ smp_mb__before_atomic();
+ atomic_dec(&net->ct.count);
}
EXPORT_SYMBOL_GPL(nf_conntrack_free);
+
/* Allocate a new conntrack: we return -ENOMEM if classification
failed due to stress. Otherwise it really is unclassifiable. */
static struct nf_conntrack_tuple_hash *
@@ -777,7 +934,7 @@ init_conntrack(struct net *net, struct nf_conn *tmpl,
struct nf_conn_help *help;
struct nf_conntrack_tuple repl_tuple;
struct nf_conntrack_ecache *ecache;
- struct nf_conntrack_expect *exp;
+ struct nf_conntrack_expect *exp = NULL;
u16 zone = tmpl ? nf_ct_zone(tmpl) : NF_CT_DEFAULT_ZONE;
struct nf_conn_timeout *timeout_ext;
unsigned int *timeouts;
@@ -792,6 +949,11 @@ init_conntrack(struct net *net, struct nf_conn *tmpl,
if (IS_ERR(ct))
return (struct nf_conntrack_tuple_hash *)ct;
+ if (tmpl && nfct_synproxy(tmpl)) {
+ nfct_seqadj_ext_add(ct);
+ nfct_synproxy_ext_add(ct);
+ }
+
timeout_ext = tmpl ? nf_ct_timeout_find(tmpl) : NULL;
if (timeout_ext)
timeouts = NF_CT_TIMEOUT_EXT_DATA(timeout_ext);
@@ -809,45 +971,51 @@ init_conntrack(struct net *net, struct nf_conn *tmpl,
nf_ct_acct_ext_add(ct, GFP_ATOMIC);
nf_ct_tstamp_ext_add(ct, GFP_ATOMIC);
+ nf_ct_labels_ext_add(ct);
ecache = tmpl ? nf_ct_ecache_find(tmpl) : NULL;
nf_ct_ecache_ext_add(ct, ecache ? ecache->ctmask : 0,
ecache ? ecache->expmask : 0,
GFP_ATOMIC);
- spin_lock_bh(&nf_conntrack_lock);
- exp = nf_ct_find_expectation(net, zone, tuple);
- if (exp) {
- pr_debug("conntrack: expectation arrives ct=%p exp=%p\n",
- ct, exp);
- /* Welcome, Mr. Bond. We've been expecting you... */
- __set_bit(IPS_EXPECTED_BIT, &ct->status);
- ct->master = exp->master;
- if (exp->helper) {
- help = nf_ct_helper_ext_add(ct, exp->helper,
- GFP_ATOMIC);
- if (help)
- rcu_assign_pointer(help->helper, exp->helper);
- }
+ local_bh_disable();
+ if (net->ct.expect_count) {
+ spin_lock(&nf_conntrack_expect_lock);
+ exp = nf_ct_find_expectation(net, zone, tuple);
+ if (exp) {
+ pr_debug("conntrack: expectation arrives ct=%p exp=%p\n",
+ ct, exp);
+ /* Welcome, Mr. Bond. We've been expecting you... */
+ __set_bit(IPS_EXPECTED_BIT, &ct->status);
+ /* exp->master safe, refcnt bumped in nf_ct_find_expectation */
+ ct->master = exp->master;
+ if (exp->helper) {
+ help = nf_ct_helper_ext_add(ct, exp->helper,
+ GFP_ATOMIC);
+ if (help)
+ rcu_assign_pointer(help->helper, exp->helper);
+ }
#ifdef CONFIG_NF_CONNTRACK_MARK
- ct->mark = exp->master->mark;
+ ct->mark = exp->master->mark;
#endif
#ifdef CONFIG_NF_CONNTRACK_SECMARK
- ct->secmark = exp->master->secmark;
+ ct->secmark = exp->master->secmark;
#endif
- nf_conntrack_get(&ct->master->ct_general);
- NF_CT_STAT_INC(net, expect_new);
- } else {
+ NF_CT_STAT_INC(net, expect_new);
+ }
+ spin_unlock(&nf_conntrack_expect_lock);
+ }
+ if (!exp) {
__nf_ct_try_assign_helper(ct, tmpl, GFP_ATOMIC);
NF_CT_STAT_INC(net, new);
}
- /* Overload tuple linked list to put us in unconfirmed list. */
- hlist_nulls_add_head_rcu(&ct->tuplehash[IP_CT_DIR_ORIGINAL].hnnode,
- &net->ct.unconfirmed);
+ /* Now it is inserted into the unconfirmed list, bump refcount */
+ nf_conntrack_get(&ct->ct_general);
+ nf_ct_add_to_unconfirmed_list(ct);
- spin_unlock_bh(&nf_conntrack_lock);
+ local_bh_enable();
if (exp) {
if (exp->expectfn)
@@ -1095,12 +1263,14 @@ void __nf_ct_refresh_acct(struct nf_conn *ct,
acct:
if (do_acct) {
- struct nf_conn_counter *acct;
+ struct nf_conn_acct *acct;
acct = nf_conn_acct_find(ct);
if (acct) {
- atomic64_inc(&acct[CTINFO2DIR(ctinfo)].packets);
- atomic64_add(skb->len, &acct[CTINFO2DIR(ctinfo)].bytes);
+ struct nf_conn_counter *counter = acct->counter;
+
+ atomic64_inc(&counter[CTINFO2DIR(ctinfo)].packets);
+ atomic64_add(skb->len, &counter[CTINFO2DIR(ctinfo)].bytes);
}
}
}
@@ -1112,13 +1282,15 @@ bool __nf_ct_kill_acct(struct nf_conn *ct,
int do_acct)
{
if (do_acct) {
- struct nf_conn_counter *acct;
+ struct nf_conn_acct *acct;
acct = nf_conn_acct_find(ct);
if (acct) {
- atomic64_inc(&acct[CTINFO2DIR(ctinfo)].packets);
+ struct nf_conn_counter *counter = acct->counter;
+
+ atomic64_inc(&counter[CTINFO2DIR(ctinfo)].packets);
atomic64_add(skb->len - skb_network_offset(skb),
- &acct[CTINFO2DIR(ctinfo)].bytes);
+ &counter[CTINFO2DIR(ctinfo)].bytes);
}
}
@@ -1187,7 +1359,7 @@ EXPORT_SYMBOL_GPL(nf_ct_port_nlattr_tuple_size);
#endif
/* Used by ipt_REJECT and ip6t_REJECT. */
-static void nf_conntrack_attach(struct sk_buff *nskb, struct sk_buff *skb)
+static void nf_conntrack_attach(struct sk_buff *nskb, const struct sk_buff *skb)
{
struct nf_conn *ct;
enum ip_conntrack_info ctinfo;
@@ -1213,33 +1385,48 @@ get_next_corpse(struct net *net, int (*iter)(struct nf_conn *i, void *data),
struct nf_conntrack_tuple_hash *h;
struct nf_conn *ct;
struct hlist_nulls_node *n;
+ int cpu;
+ spinlock_t *lockp;
- spin_lock_bh(&nf_conntrack_lock);
for (; *bucket < net->ct.htable_size; (*bucket)++) {
- hlist_nulls_for_each_entry(h, n, &net->ct.hash[*bucket], hnnode) {
- if (NF_CT_DIRECTION(h) != IP_CT_DIR_ORIGINAL)
- continue;
+ lockp = &nf_conntrack_locks[*bucket % CONNTRACK_LOCKS];
+ local_bh_disable();
+ spin_lock(lockp);
+ if (*bucket < net->ct.htable_size) {
+ hlist_nulls_for_each_entry(h, n, &net->ct.hash[*bucket], hnnode) {
+ if (NF_CT_DIRECTION(h) != IP_CT_DIR_ORIGINAL)
+ continue;
+ ct = nf_ct_tuplehash_to_ctrack(h);
+ if (iter(ct, data))
+ goto found;
+ }
+ }
+ spin_unlock(lockp);
+ local_bh_enable();
+ }
+
+ for_each_possible_cpu(cpu) {
+ struct ct_pcpu *pcpu = per_cpu_ptr(net->ct.pcpu_lists, cpu);
+
+ spin_lock_bh(&pcpu->lock);
+ hlist_nulls_for_each_entry(h, n, &pcpu->unconfirmed, hnnode) {
ct = nf_ct_tuplehash_to_ctrack(h);
if (iter(ct, data))
- goto found;
+ set_bit(IPS_DYING_BIT, &ct->status);
}
+ spin_unlock_bh(&pcpu->lock);
}
- hlist_nulls_for_each_entry(h, n, &net->ct.unconfirmed, hnnode) {
- ct = nf_ct_tuplehash_to_ctrack(h);
- if (iter(ct, data))
- set_bit(IPS_DYING_BIT, &ct->status);
- }
- spin_unlock_bh(&nf_conntrack_lock);
return NULL;
found:
atomic_inc(&ct->ct_general.use);
- spin_unlock_bh(&nf_conntrack_lock);
+ spin_unlock(lockp);
+ local_bh_enable();
return ct;
}
void nf_ct_iterate_cleanup(struct net *net,
int (*iter)(struct nf_conn *i, void *data),
- void *data)
+ void *data, u32 portid, int report)
{
struct nf_conn *ct;
unsigned int bucket = 0;
@@ -1247,7 +1434,8 @@ void nf_ct_iterate_cleanup(struct net *net,
while ((ct = get_next_corpse(net, iter, data, &bucket)) != NULL) {
/* Time to push up daises... */
if (del_timer(&ct->timeout))
- death_by_timeout((unsigned long)ct);
+ nf_ct_delete(ct, portid, report);
+
/* ... else the timer will get him soon. */
nf_ct_put(ct);
@@ -1255,30 +1443,6 @@ void nf_ct_iterate_cleanup(struct net *net,
}
EXPORT_SYMBOL_GPL(nf_ct_iterate_cleanup);
-struct __nf_ct_flush_report {
- u32 pid;
- int report;
-};
-
-static int kill_report(struct nf_conn *i, void *data)
-{
- struct __nf_ct_flush_report *fr = (struct __nf_ct_flush_report *)data;
- struct nf_conn_tstamp *tstamp;
-
- tstamp = nf_conn_tstamp_find(i);
- if (tstamp && tstamp->stop == 0)
- tstamp->stop = ktime_to_ns(ktime_get_real());
-
- /* If we fail to deliver the event, death_by_timeout() will retry */
- if (nf_conntrack_event_report(IPCT_DESTROY, i,
- fr->pid, fr->report) < 0)
- return 1;
-
- /* Avoid the delivery of the destroy event in death_by_timeout(). */
- set_bit(IPS_DYING_BIT, &i->status);
- return 1;
-}
-
static int kill_all(struct nf_conn *i, void *data)
{
return 1;
@@ -1294,13 +1458,9 @@ void nf_ct_free_hashtable(void *hash, unsigned int size)
}
EXPORT_SYMBOL_GPL(nf_ct_free_hashtable);
-void nf_conntrack_flush_report(struct net *net, u32 pid, int report)
+void nf_conntrack_flush_report(struct net *net, u32 portid, int report)
{
- struct __nf_ct_flush_report fr = {
- .pid = pid,
- .report = report,
- };
- nf_ct_iterate_cleanup(net, kill_report, &fr);
+ nf_ct_iterate_cleanup(net, kill_all, NULL, portid, report);
}
EXPORT_SYMBOL_GPL(nf_conntrack_flush_report);
@@ -1309,14 +1469,19 @@ static void nf_ct_release_dying_list(struct net *net)
struct nf_conntrack_tuple_hash *h;
struct nf_conn *ct;
struct hlist_nulls_node *n;
+ int cpu;
- spin_lock_bh(&nf_conntrack_lock);
- hlist_nulls_for_each_entry(h, n, &net->ct.dying, hnnode) {
- ct = nf_ct_tuplehash_to_ctrack(h);
- /* never fails to remove them, no listeners at this point */
- nf_ct_kill(ct);
+ for_each_possible_cpu(cpu) {
+ struct ct_pcpu *pcpu = per_cpu_ptr(net->ct.pcpu_lists, cpu);
+
+ spin_lock_bh(&pcpu->lock);
+ hlist_nulls_for_each_entry(h, n, &pcpu->dying, hnnode) {
+ ct = nf_ct_tuplehash_to_ctrack(h);
+ /* never fails to remove them, no listeners at this point */
+ nf_ct_kill(ct);
+ }
+ spin_unlock_bh(&pcpu->lock);
}
- spin_unlock_bh(&nf_conntrack_lock);
}
static int untrack_refs(void)
@@ -1331,55 +1496,79 @@ static int untrack_refs(void)
return cnt;
}
-static void nf_conntrack_cleanup_init_net(void)
+void nf_conntrack_cleanup_start(void)
+{
+ RCU_INIT_POINTER(ip_ct_attach, NULL);
+}
+
+void nf_conntrack_cleanup_end(void)
{
+ RCU_INIT_POINTER(nf_ct_destroy, NULL);
while (untrack_refs() > 0)
schedule();
#ifdef CONFIG_NF_CONNTRACK_ZONES
nf_ct_extend_unregister(&nf_ct_zone_extend);
#endif
+ nf_conntrack_proto_fini();
+ nf_conntrack_seqadj_fini();
+ nf_conntrack_labels_fini();
+ nf_conntrack_helper_fini();
+ nf_conntrack_timeout_fini();
+ nf_conntrack_ecache_fini();
+ nf_conntrack_tstamp_fini();
+ nf_conntrack_acct_fini();
+ nf_conntrack_expect_fini();
}
-static void nf_conntrack_cleanup_net(struct net *net)
+/*
+ * Mishearing the voices in his head, our hero wonders how he's
+ * supposed to kill the mall.
+ */
+void nf_conntrack_cleanup_net(struct net *net)
{
- i_see_dead_people:
- nf_ct_iterate_cleanup(net, kill_all, NULL);
- nf_ct_release_dying_list(net);
- if (atomic_read(&net->ct.count) != 0) {
- schedule();
- goto i_see_dead_people;
- }
+ LIST_HEAD(single);
- nf_ct_free_hashtable(net->ct.hash, net->ct.htable_size);
- nf_conntrack_helper_fini(net);
- nf_conntrack_timeout_fini(net);
- nf_conntrack_ecache_fini(net);
- nf_conntrack_tstamp_fini(net);
- nf_conntrack_acct_fini(net);
- nf_conntrack_expect_fini(net);
- kmem_cache_destroy(net->ct.nf_conntrack_cachep);
- kfree(net->ct.slabname);
- free_percpu(net->ct.stat);
+ list_add(&net->exit_list, &single);
+ nf_conntrack_cleanup_net_list(&single);
}
-/* Mishearing the voices in his head, our hero wonders how he's
- supposed to kill the mall. */
-void nf_conntrack_cleanup(struct net *net)
+void nf_conntrack_cleanup_net_list(struct list_head *net_exit_list)
{
- if (net_eq(net, &init_net))
- RCU_INIT_POINTER(ip_ct_attach, NULL);
+ int busy;
+ struct net *net;
- /* This makes sure all current packets have passed through
- netfilter framework. Roll on, two-stage module
- delete... */
+ /*
+ * This makes sure all current packets have passed through
+ * netfilter framework. Roll on, two-stage module
+ * delete...
+ */
synchronize_net();
- nf_conntrack_proto_fini(net);
- nf_conntrack_cleanup_net(net);
+i_see_dead_people:
+ busy = 0;
+ list_for_each_entry(net, net_exit_list, exit_list) {
+ nf_ct_iterate_cleanup(net, kill_all, NULL, 0, 0);
+ nf_ct_release_dying_list(net);
+ if (atomic_read(&net->ct.count) != 0)
+ busy = 1;
+ }
+ if (busy) {
+ schedule();
+ goto i_see_dead_people;
+ }
- if (net_eq(net, &init_net)) {
- RCU_INIT_POINTER(nf_ct_destroy, NULL);
- nf_conntrack_cleanup_init_net();
+ list_for_each_entry(net, net_exit_list, exit_list) {
+ nf_ct_free_hashtable(net->ct.hash, net->ct.htable_size);
+ nf_conntrack_proto_pernet_fini(net);
+ nf_conntrack_helper_pernet_fini(net);
+ nf_conntrack_ecache_pernet_fini(net);
+ nf_conntrack_tstamp_pernet_fini(net);
+ nf_conntrack_acct_pernet_fini(net);
+ nf_conntrack_expect_pernet_fini(net);
+ kmem_cache_destroy(net->ct.nf_conntrack_cachep);
+ kfree(net->ct.slabname);
+ free_percpu(net->ct.stat);
+ free_percpu(net->ct.pcpu_lists);
}
}
@@ -1432,12 +1621,16 @@ int nf_conntrack_set_hashsize(const char *val, struct kernel_param *kp)
if (!hash)
return -ENOMEM;
+ local_bh_disable();
+ nf_conntrack_all_lock();
+ write_seqcount_begin(&init_net.ct.generation);
+
/* Lookups in the old hash might happen in parallel, which means we
* might get false negatives during connection lookup. New connections
* created because of a false negative won't make it into the hash
- * though since that required taking the lock.
+ * though since that required taking the locks.
*/
- spin_lock_bh(&nf_conntrack_lock);
+
for (i = 0; i < init_net.ct.htable_size; i++) {
while (!hlist_nulls_empty(&init_net.ct.hash[i])) {
h = hlist_nulls_entry(init_net.ct.hash[i].first,
@@ -1454,7 +1647,10 @@ int nf_conntrack_set_hashsize(const char *val, struct kernel_param *kp)
init_net.ct.htable_size = nf_conntrack_htable_size = hashsize;
init_net.ct.hash = hash;
- spin_unlock_bh(&nf_conntrack_lock);
+
+ write_seqcount_end(&init_net.ct.generation);
+ nf_conntrack_all_unlock();
+ local_bh_enable();
nf_ct_free_hashtable(old_hash, old_size);
return 0;
@@ -1473,10 +1669,13 @@ void nf_ct_untracked_status_or(unsigned long bits)
}
EXPORT_SYMBOL_GPL(nf_ct_untracked_status_or);
-static int nf_conntrack_init_init_net(void)
+int nf_conntrack_init_start(void)
{
int max_factor = 8;
- int ret, cpu;
+ int i, ret, cpu;
+
+ for (i = 0; i < CONNTRACK_LOCKS; i++)
+ spin_lock_init(&nf_conntrack_locks[i]);
/* Idea from tcp.c: use 1/16384 of memory. On i386: 32MB
* machine has 512 buckets. >= 1GB machines have 16384 buckets. */
@@ -1500,11 +1699,48 @@ static int nf_conntrack_init_init_net(void)
printk(KERN_INFO "nf_conntrack version %s (%u buckets, %d max)\n",
NF_CONNTRACK_VERSION, nf_conntrack_htable_size,
nf_conntrack_max);
+
+ ret = nf_conntrack_expect_init();
+ if (ret < 0)
+ goto err_expect;
+
+ ret = nf_conntrack_acct_init();
+ if (ret < 0)
+ goto err_acct;
+
+ ret = nf_conntrack_tstamp_init();
+ if (ret < 0)
+ goto err_tstamp;
+
+ ret = nf_conntrack_ecache_init();
+ if (ret < 0)
+ goto err_ecache;
+
+ ret = nf_conntrack_timeout_init();
+ if (ret < 0)
+ goto err_timeout;
+
+ ret = nf_conntrack_helper_init();
+ if (ret < 0)
+ goto err_helper;
+
+ ret = nf_conntrack_labels_init();
+ if (ret < 0)
+ goto err_labels;
+
+ ret = nf_conntrack_seqadj_init();
+ if (ret < 0)
+ goto err_seqadj;
+
#ifdef CONFIG_NF_CONNTRACK_ZONES
ret = nf_ct_extend_register(&nf_ct_zone_extend);
if (ret < 0)
goto err_extend;
#endif
+ ret = nf_conntrack_proto_init();
+ if (ret < 0)
+ goto err_proto;
+
/* Set up fake conntrack: to never be deleted, not in any hashes */
for_each_possible_cpu(cpu) {
struct nf_conn *ct = &per_cpu(nf_conntrack_untracked, cpu);
@@ -1515,12 +1751,37 @@ static int nf_conntrack_init_init_net(void)
nf_ct_untracked_status_or(IPS_CONFIRMED | IPS_UNTRACKED);
return 0;
+err_proto:
#ifdef CONFIG_NF_CONNTRACK_ZONES
+ nf_ct_extend_unregister(&nf_ct_zone_extend);
err_extend:
#endif
+ nf_conntrack_seqadj_fini();
+err_seqadj:
+ nf_conntrack_labels_fini();
+err_labels:
+ nf_conntrack_helper_fini();
+err_helper:
+ nf_conntrack_timeout_fini();
+err_timeout:
+ nf_conntrack_ecache_fini();
+err_ecache:
+ nf_conntrack_tstamp_fini();
+err_tstamp:
+ nf_conntrack_acct_fini();
+err_acct:
+ nf_conntrack_expect_fini();
+err_expect:
return ret;
}
+void nf_conntrack_init_end(void)
+{
+ /* For use by REJECT target */
+ RCU_INIT_POINTER(ip_ct_attach, nf_conntrack_attach);
+ RCU_INIT_POINTER(nf_ct_destroy, destroy_conntrack);
+}
+
/*
* We need to use special "null" values, not used in hash table
*/
@@ -1528,71 +1789,79 @@ err_extend:
#define DYING_NULLS_VAL ((1<<30)+1)
#define TEMPLATE_NULLS_VAL ((1<<30)+2)
-static int nf_conntrack_init_net(struct net *net)
+int nf_conntrack_init_net(struct net *net)
{
- int ret;
+ int ret = -ENOMEM;
+ int cpu;
atomic_set(&net->ct.count, 0);
- INIT_HLIST_NULLS_HEAD(&net->ct.unconfirmed, UNCONFIRMED_NULLS_VAL);
- INIT_HLIST_NULLS_HEAD(&net->ct.dying, DYING_NULLS_VAL);
- INIT_HLIST_NULLS_HEAD(&net->ct.tmpl, TEMPLATE_NULLS_VAL);
- net->ct.stat = alloc_percpu(struct ip_conntrack_stat);
- if (!net->ct.stat) {
- ret = -ENOMEM;
+ seqcount_init(&net->ct.generation);
+
+ net->ct.pcpu_lists = alloc_percpu(struct ct_pcpu);
+ if (!net->ct.pcpu_lists)
goto err_stat;
+
+ for_each_possible_cpu(cpu) {
+ struct ct_pcpu *pcpu = per_cpu_ptr(net->ct.pcpu_lists, cpu);
+
+ spin_lock_init(&pcpu->lock);
+ INIT_HLIST_NULLS_HEAD(&pcpu->unconfirmed, UNCONFIRMED_NULLS_VAL);
+ INIT_HLIST_NULLS_HEAD(&pcpu->dying, DYING_NULLS_VAL);
+ INIT_HLIST_NULLS_HEAD(&pcpu->tmpl, TEMPLATE_NULLS_VAL);
}
+ net->ct.stat = alloc_percpu(struct ip_conntrack_stat);
+ if (!net->ct.stat)
+ goto err_pcpu_lists;
+
net->ct.slabname = kasprintf(GFP_KERNEL, "nf_conntrack_%p", net);
- if (!net->ct.slabname) {
- ret = -ENOMEM;
+ if (!net->ct.slabname)
goto err_slabname;
- }
net->ct.nf_conntrack_cachep = kmem_cache_create(net->ct.slabname,
sizeof(struct nf_conn), 0,
SLAB_DESTROY_BY_RCU, NULL);
if (!net->ct.nf_conntrack_cachep) {
printk(KERN_ERR "Unable to create nf_conn slab cache\n");
- ret = -ENOMEM;
goto err_cache;
}
net->ct.htable_size = nf_conntrack_htable_size;
net->ct.hash = nf_ct_alloc_hashtable(&net->ct.htable_size, 1);
if (!net->ct.hash) {
- ret = -ENOMEM;
printk(KERN_ERR "Unable to create nf_conntrack_hash\n");
goto err_hash;
}
- ret = nf_conntrack_expect_init(net);
+ ret = nf_conntrack_expect_pernet_init(net);
if (ret < 0)
goto err_expect;
- ret = nf_conntrack_acct_init(net);
+ ret = nf_conntrack_acct_pernet_init(net);
if (ret < 0)
goto err_acct;
- ret = nf_conntrack_tstamp_init(net);
+ ret = nf_conntrack_tstamp_pernet_init(net);
if (ret < 0)
goto err_tstamp;
- ret = nf_conntrack_ecache_init(net);
+ ret = nf_conntrack_ecache_pernet_init(net);
if (ret < 0)
goto err_ecache;
- ret = nf_conntrack_timeout_init(net);
- if (ret < 0)
- goto err_timeout;
- ret = nf_conntrack_helper_init(net);
+ ret = nf_conntrack_helper_pernet_init(net);
if (ret < 0)
goto err_helper;
+ ret = nf_conntrack_proto_pernet_init(net);
+ if (ret < 0)
+ goto err_proto;
return 0;
+
+err_proto:
+ nf_conntrack_helper_pernet_fini(net);
err_helper:
- nf_conntrack_timeout_fini(net);
-err_timeout:
- nf_conntrack_ecache_fini(net);
+ nf_conntrack_ecache_pernet_fini(net);
err_ecache:
- nf_conntrack_tstamp_fini(net);
+ nf_conntrack_tstamp_pernet_fini(net);
err_tstamp:
- nf_conntrack_acct_fini(net);
+ nf_conntrack_acct_pernet_fini(net);
err_acct:
- nf_conntrack_expect_fini(net);
+ nf_conntrack_expect_pernet_fini(net);
err_expect:
nf_ct_free_hashtable(net->ct.hash, net->ct.htable_size);
err_hash:
@@ -1601,46 +1870,8 @@ err_cache:
kfree(net->ct.slabname);
err_slabname:
free_percpu(net->ct.stat);
+err_pcpu_lists:
+ free_percpu(net->ct.pcpu_lists);
err_stat:
return ret;
}
-
-s16 (*nf_ct_nat_offset)(const struct nf_conn *ct,
- enum ip_conntrack_dir dir,
- u32 seq);
-EXPORT_SYMBOL_GPL(nf_ct_nat_offset);
-
-int nf_conntrack_init(struct net *net)
-{
- int ret;
-
- if (net_eq(net, &init_net)) {
- ret = nf_conntrack_init_init_net();
- if (ret < 0)
- goto out_init_net;
- }
- ret = nf_conntrack_proto_init(net);
- if (ret < 0)
- goto out_proto;
- ret = nf_conntrack_init_net(net);
- if (ret < 0)
- goto out_net;
-
- if (net_eq(net, &init_net)) {
- /* For use by REJECT target */
- RCU_INIT_POINTER(ip_ct_attach, nf_conntrack_attach);
- RCU_INIT_POINTER(nf_ct_destroy, destroy_conntrack);
-
- /* Howto get NAT offsets */
- RCU_INIT_POINTER(nf_ct_nat_offset, NULL);
- }
- return 0;
-
-out_net:
- nf_conntrack_proto_fini(net);
-out_proto:
- if (net_eq(net, &init_net))
- nf_conntrack_cleanup_init_net();
-out_init_net:
- return ret;
-}
diff --git a/net/netfilter/nf_conntrack_ecache.c b/net/netfilter/nf_conntrack_ecache.c
index faa978f1714..1df17614656 100644
--- a/net/netfilter/nf_conntrack_ecache.c
+++ b/net/netfilter/nf_conntrack_ecache.c
@@ -1,8 +1,10 @@
/* Event cache for netfilter. */
-/* (C) 1999-2001 Paul `Rusty' Russell
- * (C) 2002-2006 Netfilter Core Team <coreteam@netfilter.org>
- * (C) 2003,2004 USAGI/WIDE Project <http://www.linux-ipv6.org>
+/*
+ * (C) 2005 Harald Welte <laforge@gnumonks.org>
+ * (C) 2005 Patrick McHardy <kaber@trash.net>
+ * (C) 2005-2006 Netfilter Core Team <coreteam@netfilter.org>
+ * (C) 2005 USAGI/WIDE Project <http://www.linux-ipv6.org>
*
* This program is free software; you can redistribute it and/or modify
* it under the terms of the GNU General Public License version 2 as
@@ -233,38 +235,27 @@ static void nf_conntrack_event_fini_sysctl(struct net *net)
}
#endif /* CONFIG_SYSCTL */
-int nf_conntrack_ecache_init(struct net *net)
+int nf_conntrack_ecache_pernet_init(struct net *net)
{
- int ret;
-
net->ct.sysctl_events = nf_ct_events;
net->ct.sysctl_events_retry_timeout = nf_ct_events_retry_timeout;
+ return nf_conntrack_event_init_sysctl(net);
+}
- if (net_eq(net, &init_net)) {
- ret = nf_ct_extend_register(&event_extend);
- if (ret < 0) {
- printk(KERN_ERR "nf_ct_event: Unable to register "
- "event extension.\n");
- goto out_extend_register;
- }
- }
+void nf_conntrack_ecache_pernet_fini(struct net *net)
+{
+ nf_conntrack_event_fini_sysctl(net);
+}
- ret = nf_conntrack_event_init_sysctl(net);
+int nf_conntrack_ecache_init(void)
+{
+ int ret = nf_ct_extend_register(&event_extend);
if (ret < 0)
- goto out_sysctl;
-
- return 0;
-
-out_sysctl:
- if (net_eq(net, &init_net))
- nf_ct_extend_unregister(&event_extend);
-out_extend_register:
+ pr_err("nf_ct_event: Unable to register event extension.\n");
return ret;
}
-void nf_conntrack_ecache_fini(struct net *net)
+void nf_conntrack_ecache_fini(void)
{
- nf_conntrack_event_fini_sysctl(net);
- if (net_eq(net, &init_net))
- nf_ct_extend_unregister(&event_extend);
+ nf_ct_extend_unregister(&event_extend);
}
diff --git a/net/netfilter/nf_conntrack_expect.c b/net/netfilter/nf_conntrack_expect.c
index 527651a53a4..f87e8f68ad4 100644
--- a/net/netfilter/nf_conntrack_expect.c
+++ b/net/netfilter/nf_conntrack_expect.c
@@ -3,6 +3,7 @@
/* (C) 1999-2001 Paul `Rusty' Russell
* (C) 2002-2006 Netfilter Core Team <coreteam@netfilter.org>
* (C) 2003,2004 USAGI/WIDE Project <http://www.linux-ipv6.org>
+ * (c) 2005-2012 Patrick McHardy <kaber@trash.net>
*
* This program is free software; you can redistribute it and/or modify
* it under the terms of the GNU General Public License version 2 as
@@ -40,7 +41,7 @@ static struct kmem_cache *nf_ct_expect_cachep __read_mostly;
/* nf_conntrack_expect helper functions */
void nf_ct_unlink_expect_report(struct nf_conntrack_expect *exp,
- u32 pid, int report)
+ u32 portid, int report)
{
struct nf_conn_help *master_help = nfct_help(exp->master);
struct net *net = nf_ct_exp_net(exp);
@@ -54,7 +55,7 @@ void nf_ct_unlink_expect_report(struct nf_conntrack_expect *exp,
hlist_del(&exp->lnode);
master_help->expecting[exp->class]--;
- nf_ct_expect_event_report(IPEXP_DESTROY, exp, pid, report);
+ nf_ct_expect_event_report(IPEXP_DESTROY, exp, portid, report);
nf_ct_expect_put(exp);
NF_CT_STAT_INC(net, expect_delete);
@@ -65,9 +66,9 @@ static void nf_ct_expectation_timed_out(unsigned long ul_expect)
{
struct nf_conntrack_expect *exp = (void *)ul_expect;
- spin_lock_bh(&nf_conntrack_lock);
+ spin_lock_bh(&nf_conntrack_expect_lock);
nf_ct_unlink_expect(exp);
- spin_unlock_bh(&nf_conntrack_lock);
+ spin_unlock_bh(&nf_conntrack_expect_lock);
nf_ct_expect_put(exp);
}
@@ -90,14 +91,13 @@ __nf_ct_expect_find(struct net *net, u16 zone,
const struct nf_conntrack_tuple *tuple)
{
struct nf_conntrack_expect *i;
- struct hlist_node *n;
unsigned int h;
if (!net->ct.expect_count)
return NULL;
h = nf_ct_expect_dst_hash(tuple);
- hlist_for_each_entry_rcu(i, n, &net->ct.expect_hash[h], hnode) {
+ hlist_for_each_entry_rcu(i, &net->ct.expect_hash[h], hnode) {
if (nf_ct_tuple_mask_cmp(tuple, &i->tuple, &i->mask) &&
nf_ct_zone(i->master) == zone)
return i;
@@ -130,14 +130,13 @@ nf_ct_find_expectation(struct net *net, u16 zone,
const struct nf_conntrack_tuple *tuple)
{
struct nf_conntrack_expect *i, *exp = NULL;
- struct hlist_node *n;
unsigned int h;
if (!net->ct.expect_count)
return NULL;
h = nf_ct_expect_dst_hash(tuple);
- hlist_for_each_entry(i, n, &net->ct.expect_hash[h], hnode) {
+ hlist_for_each_entry(i, &net->ct.expect_hash[h], hnode) {
if (!(i->flags & NF_CT_EXPECT_INACTIVE) &&
nf_ct_tuple_mask_cmp(tuple, &i->tuple, &i->mask) &&
nf_ct_zone(i->master) == zone) {
@@ -156,6 +155,18 @@ nf_ct_find_expectation(struct net *net, u16 zone,
if (!nf_ct_is_confirmed(exp->master))
return NULL;
+ /* Avoid race with other CPUs, that for exp->master ct, is
+ * about to invoke ->destroy(), or nf_ct_delete() via timeout
+ * or early_drop().
+ *
+ * The atomic_inc_not_zero() check tells: If that fails, we
+ * know that the ct is being destroyed. If it succeeds, we
+ * can be sure the ct cannot disappear underneath.
+ */
+ if (unlikely(nf_ct_is_dying(exp->master) ||
+ !atomic_inc_not_zero(&exp->master->ct_general.use)))
+ return NULL;
+
if (exp->flags & NF_CT_EXPECT_PERMANENT) {
atomic_inc(&exp->use);
return exp;
@@ -163,6 +174,8 @@ nf_ct_find_expectation(struct net *net, u16 zone,
nf_ct_unlink_expect(exp);
return exp;
}
+ /* Undo exp->master refcnt increase, if del_timer() failed */
+ nf_ct_put(exp->master);
return NULL;
}
@@ -172,18 +185,20 @@ void nf_ct_remove_expectations(struct nf_conn *ct)
{
struct nf_conn_help *help = nfct_help(ct);
struct nf_conntrack_expect *exp;
- struct hlist_node *n, *next;
+ struct hlist_node *next;
/* Optimization: most connection never expect any others. */
if (!help)
return;
- hlist_for_each_entry_safe(exp, n, next, &help->expectations, lnode) {
+ spin_lock_bh(&nf_conntrack_expect_lock);
+ hlist_for_each_entry_safe(exp, next, &help->expectations, lnode) {
if (del_timer(&exp->timeout)) {
nf_ct_unlink_expect(exp);
nf_ct_expect_put(exp);
}
}
+ spin_unlock_bh(&nf_conntrack_expect_lock);
}
EXPORT_SYMBOL_GPL(nf_ct_remove_expectations);
@@ -218,12 +233,12 @@ static inline int expect_matches(const struct nf_conntrack_expect *a,
/* Generally a bad idea to call this: could have matched already. */
void nf_ct_unexpect_related(struct nf_conntrack_expect *exp)
{
- spin_lock_bh(&nf_conntrack_lock);
+ spin_lock_bh(&nf_conntrack_expect_lock);
if (del_timer(&exp->timeout)) {
nf_ct_unlink_expect(exp);
nf_ct_expect_put(exp);
}
- spin_unlock_bh(&nf_conntrack_lock);
+ spin_unlock_bh(&nf_conntrack_expect_lock);
}
EXPORT_SYMBOL_GPL(nf_ct_unexpect_related);
@@ -294,6 +309,11 @@ void nf_ct_expect_init(struct nf_conntrack_expect *exp, unsigned int class,
sizeof(exp->tuple.dst.u3) - len);
exp->tuple.dst.u.all = *dst;
+
+#ifdef CONFIG_NF_NAT_NEEDED
+ memset(&exp->saved_addr, 0, sizeof(exp->saved_addr));
+ memset(&exp->saved_proto, 0, sizeof(exp->saved_proto));
+#endif
}
EXPORT_SYMBOL_GPL(nf_ct_expect_init);
@@ -331,7 +351,7 @@ static int nf_ct_expect_insert(struct nf_conntrack_expect *exp)
setup_timer(&exp->timeout, nf_ct_expectation_timed_out,
(unsigned long)exp);
helper = rcu_dereference_protected(master_help->helper,
- lockdep_is_held(&nf_conntrack_lock));
+ lockdep_is_held(&nf_conntrack_expect_lock));
if (helper) {
exp->timeout.expires = jiffies +
helper->expect_policy[exp->class].timeout * HZ;
@@ -348,9 +368,8 @@ static void evict_oldest_expect(struct nf_conn *master,
{
struct nf_conn_help *master_help = nfct_help(master);
struct nf_conntrack_expect *exp, *last = NULL;
- struct hlist_node *n;
- hlist_for_each_entry(exp, n, &master_help->expectations, lnode) {
+ hlist_for_each_entry(exp, &master_help->expectations, lnode) {
if (exp->class == new->class)
last = exp;
}
@@ -369,7 +388,7 @@ static inline int __nf_ct_expect_check(struct nf_conntrack_expect *expect)
struct nf_conn_help *master_help = nfct_help(master);
struct nf_conntrack_helper *helper;
struct net *net = nf_ct_exp_net(expect);
- struct hlist_node *n, *next;
+ struct hlist_node *next;
unsigned int h;
int ret = 1;
@@ -378,7 +397,7 @@ static inline int __nf_ct_expect_check(struct nf_conntrack_expect *expect)
goto out;
}
h = nf_ct_expect_dst_hash(&expect->tuple);
- hlist_for_each_entry_safe(i, n, next, &net->ct.expect_hash[h], hnode) {
+ hlist_for_each_entry_safe(i, next, &net->ct.expect_hash[h], hnode) {
if (expect_matches(i, expect)) {
if (del_timer(&i->timeout)) {
nf_ct_unlink_expect(i);
@@ -392,7 +411,7 @@ static inline int __nf_ct_expect_check(struct nf_conntrack_expect *expect)
}
/* Will be over limit? */
helper = rcu_dereference_protected(master_help->helper,
- lockdep_is_held(&nf_conntrack_lock));
+ lockdep_is_held(&nf_conntrack_expect_lock));
if (helper) {
p = &helper->expect_policy[expect->class];
if (p->max_expected &&
@@ -414,12 +433,12 @@ out:
return ret;
}
-int nf_ct_expect_related_report(struct nf_conntrack_expect *expect,
- u32 pid, int report)
+int nf_ct_expect_related_report(struct nf_conntrack_expect *expect,
+ u32 portid, int report)
{
int ret;
- spin_lock_bh(&nf_conntrack_lock);
+ spin_lock_bh(&nf_conntrack_expect_lock);
ret = __nf_ct_expect_check(expect);
if (ret <= 0)
goto out;
@@ -427,11 +446,11 @@ int nf_ct_expect_related_report(struct nf_conntrack_expect *expect,
ret = nf_ct_expect_insert(expect);
if (ret < 0)
goto out;
- spin_unlock_bh(&nf_conntrack_lock);
- nf_ct_expect_event_report(IPEXP_NEW, expect, pid, report);
+ spin_unlock_bh(&nf_conntrack_expect_lock);
+ nf_ct_expect_event_report(IPEXP_NEW, expect, portid, report);
return ret;
out:
- spin_unlock_bh(&nf_conntrack_lock);
+ spin_unlock_bh(&nf_conntrack_expect_lock);
return ret;
}
EXPORT_SYMBOL_GPL(nf_ct_expect_related_report);
@@ -571,7 +590,8 @@ static int exp_proc_init(struct net *net)
#ifdef CONFIG_NF_CONNTRACK_PROCFS
struct proc_dir_entry *proc;
- proc = proc_net_fops_create(net, "nf_conntrack_expect", 0440, &exp_file_ops);
+ proc = proc_create("nf_conntrack_expect", 0440, net->proc_net,
+ &exp_file_ops);
if (!proc)
return -ENOMEM;
#endif /* CONFIG_NF_CONNTRACK_PROCFS */
@@ -581,59 +601,56 @@ static int exp_proc_init(struct net *net)
static void exp_proc_remove(struct net *net)
{
#ifdef CONFIG_NF_CONNTRACK_PROCFS
- proc_net_remove(net, "nf_conntrack_expect");
+ remove_proc_entry("nf_conntrack_expect", net->proc_net);
#endif /* CONFIG_NF_CONNTRACK_PROCFS */
}
module_param_named(expect_hashsize, nf_ct_expect_hsize, uint, 0400);
-int nf_conntrack_expect_init(struct net *net)
+int nf_conntrack_expect_pernet_init(struct net *net)
{
int err = -ENOMEM;
- if (net_eq(net, &init_net)) {
- if (!nf_ct_expect_hsize) {
- nf_ct_expect_hsize = net->ct.htable_size / 256;
- if (!nf_ct_expect_hsize)
- nf_ct_expect_hsize = 1;
- }
- nf_ct_expect_max = nf_ct_expect_hsize * 4;
- }
-
net->ct.expect_count = 0;
net->ct.expect_hash = nf_ct_alloc_hashtable(&nf_ct_expect_hsize, 0);
if (net->ct.expect_hash == NULL)
goto err1;
- if (net_eq(net, &init_net)) {
- nf_ct_expect_cachep = kmem_cache_create("nf_conntrack_expect",
- sizeof(struct nf_conntrack_expect),
- 0, 0, NULL);
- if (!nf_ct_expect_cachep)
- goto err2;
- }
-
err = exp_proc_init(net);
if (err < 0)
- goto err3;
+ goto err2;
return 0;
-
-err3:
- if (net_eq(net, &init_net))
- kmem_cache_destroy(nf_ct_expect_cachep);
err2:
nf_ct_free_hashtable(net->ct.expect_hash, nf_ct_expect_hsize);
err1:
return err;
}
-void nf_conntrack_expect_fini(struct net *net)
+void nf_conntrack_expect_pernet_fini(struct net *net)
{
exp_proc_remove(net);
- if (net_eq(net, &init_net)) {
- rcu_barrier(); /* Wait for call_rcu() before destroy */
- kmem_cache_destroy(nf_ct_expect_cachep);
- }
nf_ct_free_hashtable(net->ct.expect_hash, nf_ct_expect_hsize);
}
+
+int nf_conntrack_expect_init(void)
+{
+ if (!nf_ct_expect_hsize) {
+ nf_ct_expect_hsize = nf_conntrack_htable_size / 256;
+ if (!nf_ct_expect_hsize)
+ nf_ct_expect_hsize = 1;
+ }
+ nf_ct_expect_max = nf_ct_expect_hsize * 4;
+ nf_ct_expect_cachep = kmem_cache_create("nf_conntrack_expect",
+ sizeof(struct nf_conntrack_expect),
+ 0, 0, NULL);
+ if (!nf_ct_expect_cachep)
+ return -ENOMEM;
+ return 0;
+}
+
+void nf_conntrack_expect_fini(void)
+{
+ rcu_barrier(); /* Wait for call_rcu() before destroy */
+ kmem_cache_destroy(nf_ct_expect_cachep);
+}
diff --git a/net/netfilter/nf_conntrack_ftp.c b/net/netfilter/nf_conntrack_ftp.c
index 1ce3befb7c8..b8a0924064e 100644
--- a/net/netfilter/nf_conntrack_ftp.c
+++ b/net/netfilter/nf_conntrack_ftp.c
@@ -3,6 +3,7 @@
/* (C) 1999-2001 Paul `Rusty' Russell
* (C) 2002-2004 Netfilter Core Team <coreteam@netfilter.org>
* (C) 2003,2004 USAGI/WIDE Project <http://www.linux-ipv6.org>
+ * (C) 2006-2012 Patrick McHardy <kaber@trash.net>
*
* This program is free software; you can redistribute it and/or modify
* it under the terms of the GNU General Public License version 2 as
@@ -54,10 +55,14 @@ unsigned int (*nf_nat_ftp_hook)(struct sk_buff *skb,
struct nf_conntrack_expect *exp);
EXPORT_SYMBOL_GPL(nf_nat_ftp_hook);
-static int try_rfc959(const char *, size_t, struct nf_conntrack_man *, char);
-static int try_eprt(const char *, size_t, struct nf_conntrack_man *, char);
+static int try_rfc959(const char *, size_t, struct nf_conntrack_man *,
+ char, unsigned int *);
+static int try_rfc1123(const char *, size_t, struct nf_conntrack_man *,
+ char, unsigned int *);
+static int try_eprt(const char *, size_t, struct nf_conntrack_man *,
+ char, unsigned int *);
static int try_epsv_response(const char *, size_t, struct nf_conntrack_man *,
- char);
+ char, unsigned int *);
static struct ftp_search {
const char *pattern;
@@ -65,7 +70,7 @@ static struct ftp_search {
char skip;
char term;
enum nf_ct_ftp_type ftptype;
- int (*getnum)(const char *, size_t, struct nf_conntrack_man *, char);
+ int (*getnum)(const char *, size_t, struct nf_conntrack_man *, char, unsigned int *);
} search[IP_CT_DIR_MAX][2] = {
[IP_CT_DIR_ORIGINAL] = {
{
@@ -89,10 +94,8 @@ static struct ftp_search {
{
.pattern = "227 ",
.plen = sizeof("227 ") - 1,
- .skip = '(',
- .term = ')',
.ftptype = NF_CT_FTP_PASV,
- .getnum = try_rfc959,
+ .getnum = try_rfc1123,
},
{
.pattern = "229 ",
@@ -131,8 +134,9 @@ static int try_number(const char *data, size_t dlen, u_int32_t array[],
i++;
else {
/* Unexpected character; true if it's the
- terminator and we're finished. */
- if (*data == term && i == array_size - 1)
+ terminator (or we don't care about one)
+ and we're finished. */
+ if ((*data == term || !term) && i == array_size - 1)
return len;
pr_debug("Char %u (got %u nums) `%u' unexpected\n",
@@ -147,7 +151,8 @@ static int try_number(const char *data, size_t dlen, u_int32_t array[],
/* Returns 0, or length of numbers: 192,168,1,1,5,6 */
static int try_rfc959(const char *data, size_t dlen,
- struct nf_conntrack_man *cmd, char term)
+ struct nf_conntrack_man *cmd, char term,
+ unsigned int *offset)
{
int length;
u_int32_t array[6];
@@ -162,6 +167,33 @@ static int try_rfc959(const char *data, size_t dlen,
return length;
}
+/*
+ * From RFC 1123:
+ * The format of the 227 reply to a PASV command is not
+ * well standardized. In particular, an FTP client cannot
+ * assume that the parentheses shown on page 40 of RFC-959
+ * will be present (and in fact, Figure 3 on page 43 omits
+ * them). Therefore, a User-FTP program that interprets
+ * the PASV reply must scan the reply for the first digit
+ * of the host and port numbers.
+ */
+static int try_rfc1123(const char *data, size_t dlen,
+ struct nf_conntrack_man *cmd, char term,
+ unsigned int *offset)
+{
+ int i;
+ for (i = 0; i < dlen; i++)
+ if (isdigit(data[i]))
+ break;
+
+ if (i == dlen)
+ return 0;
+
+ *offset += i;
+
+ return try_rfc959(data + i, dlen - i, cmd, 0, offset);
+}
+
/* Grab port: number up to delimiter */
static int get_port(const char *data, int start, size_t dlen, char delim,
__be16 *port)
@@ -190,7 +222,7 @@ static int get_port(const char *data, int start, size_t dlen, char delim,
/* Returns 0, or length of numbers: |1|132.235.1.2|6275| or |2|3ffe::1|6275| */
static int try_eprt(const char *data, size_t dlen, struct nf_conntrack_man *cmd,
- char term)
+ char term, unsigned int *offset)
{
char delim;
int length;
@@ -238,7 +270,8 @@ static int try_eprt(const char *data, size_t dlen, struct nf_conntrack_man *cmd,
/* Returns 0, or length of numbers: |||6446| */
static int try_epsv_response(const char *data, size_t dlen,
- struct nf_conntrack_man *cmd, char term)
+ struct nf_conntrack_man *cmd, char term,
+ unsigned int *offset)
{
char delim;
@@ -260,9 +293,10 @@ static int find_pattern(const char *data, size_t dlen,
unsigned int *numlen,
struct nf_conntrack_man *cmd,
int (*getnum)(const char *, size_t,
- struct nf_conntrack_man *, char))
+ struct nf_conntrack_man *, char,
+ unsigned int *))
{
- size_t i;
+ size_t i = plen;
pr_debug("find_pattern `%s': dlen = %Zu\n", pattern, dlen);
if (dlen == 0)
@@ -292,16 +326,18 @@ static int find_pattern(const char *data, size_t dlen,
pr_debug("Pattern matches!\n");
/* Now we've found the constant string, try to skip
to the 'skip' character */
- for (i = plen; data[i] != skip; i++)
- if (i == dlen - 1) return -1;
+ if (skip) {
+ for (i = plen; data[i] != skip; i++)
+ if (i == dlen - 1) return -1;
- /* Skip over the last character */
- i++;
+ /* Skip over the last character */
+ i++;
+ }
pr_debug("Skipped up to `%c'!\n", skip);
*numoff = i;
- *numlen = getnum(data + i, dlen - i, cmd, term);
+ *numlen = getnum(data + i, dlen - i, cmd, term, numoff);
if (!*numlen)
return -1;
@@ -435,8 +471,8 @@ skip_nl_seq:
connection tracking, not packet filtering.
However, it is necessary for accurate tracking in
this case. */
- pr_debug("conntrack_ftp: partial %s %u+%u\n",
- search[dir][i].pattern, ntohl(th->seq), datalen);
+ nf_ct_helper_log(skb, ct, "partial matching of `%s'",
+ search[dir][i].pattern);
ret = NF_DROP;
goto out;
} else if (found == 0) { /* No match */
@@ -450,6 +486,7 @@ skip_nl_seq:
exp = nf_ct_expect_alloc(ct);
if (exp == NULL) {
+ nf_ct_helper_log(skb, ct, "cannot alloc expectation");
ret = NF_DROP;
goto out;
}
@@ -500,9 +537,10 @@ skip_nl_seq:
protoff, matchoff, matchlen, exp);
else {
/* Can't expect this? Best to drop packet now. */
- if (nf_ct_expect_related(exp) != 0)
+ if (nf_ct_expect_related(exp) != 0) {
+ nf_ct_helper_log(skb, ct, "cannot add expectation");
ret = NF_DROP;
- else
+ } else
ret = NF_ACCEPT;
}
diff --git a/net/netfilter/nf_conntrack_h323_main.c b/net/netfilter/nf_conntrack_h323_main.c
index 962795e839a..3a3a60b126e 100644
--- a/net/netfilter/nf_conntrack_h323_main.c
+++ b/net/netfilter/nf_conntrack_h323_main.c
@@ -2,6 +2,7 @@
* H.323 connection tracking helper
*
* Copyright (c) 2006 Jing Min Zhao <zhaojingmin@users.sourceforge.net>
+ * Copyright (c) 2006-2012 Patrick McHardy <kaber@trash.net>
*
* This source code is licensed under General Public License version 2.
*
@@ -623,7 +624,7 @@ static int h245_help(struct sk_buff *skb, unsigned int protoff,
drop:
spin_unlock_bh(&nf_h323_lock);
- net_info_ratelimited("nf_ct_h245: packet dropped\n");
+ nf_ct_helper_log(skb, ct, "cannot process H.245 message");
return NF_DROP;
}
@@ -777,8 +778,8 @@ static int callforward_do_filter(const union nf_inet_addr *src,
flowi6_to_flowi(&fl1), false)) {
if (!afinfo->route(&init_net, (struct dst_entry **)&rt2,
flowi6_to_flowi(&fl2), false)) {
- if (!memcmp(&rt1->rt6i_gateway, &rt2->rt6i_gateway,
- sizeof(rt1->rt6i_gateway)) &&
+ if (ipv6_addr_equal(rt6_nexthop(rt1),
+ rt6_nexthop(rt2)) &&
rt1->dst.dev == rt2->dst.dev)
ret = 1;
dst_release(&rt2->dst);
@@ -1197,7 +1198,7 @@ static int q931_help(struct sk_buff *skb, unsigned int protoff,
drop:
spin_unlock_bh(&nf_h323_lock);
- net_info_ratelimited("nf_ct_q931: packet dropped\n");
+ nf_ct_helper_log(skb, ct, "cannot process Q.931 message");
return NF_DROP;
}
@@ -1475,7 +1476,7 @@ static int process_rcf(struct sk_buff *skb, struct nf_conn *ct,
nf_ct_refresh(ct, skb, info->timeout * HZ);
/* Set expect timeout */
- spin_lock_bh(&nf_conntrack_lock);
+ spin_lock_bh(&nf_conntrack_expect_lock);
exp = find_expect(ct, &ct->tuplehash[dir].tuple.dst.u3,
info->sig_port[!dir]);
if (exp) {
@@ -1485,7 +1486,7 @@ static int process_rcf(struct sk_buff *skb, struct nf_conn *ct,
nf_ct_dump_tuple(&exp->tuple);
set_expect_timeout(exp, info->timeout);
}
- spin_unlock_bh(&nf_conntrack_lock);
+ spin_unlock_bh(&nf_conntrack_expect_lock);
}
return 0;
@@ -1795,7 +1796,7 @@ static int ras_help(struct sk_buff *skb, unsigned int protoff,
drop:
spin_unlock_bh(&nf_h323_lock);
- net_info_ratelimited("nf_ct_ras: packet dropped\n");
+ nf_ct_helper_log(skb, ct, "cannot process RAS message");
return NF_DROP;
}
diff --git a/net/netfilter/nf_conntrack_helper.c b/net/netfilter/nf_conntrack_helper.c