diff options
Diffstat (limited to 'net/core/pktgen.c')
| -rw-r--r-- | net/core/pktgen.c | 3189 |
1 files changed, 1807 insertions, 1382 deletions
diff --git a/net/core/pktgen.c b/net/core/pktgen.c index 6a7320b39ed..fc17a9d309a 100644 --- a/net/core/pktgen.c +++ b/net/core/pktgen.c @@ -6,7 +6,7 @@ * * Alexey Kuznetsov <kuznet@ms2.inr.ac.ru> * Ben Greear <greearb@candelatech.com> - * Jens Låås <jens.laas@data.slu.se> + * Jens Låås <jens.laas@data.slu.se> * * This program is free software; you can redistribute it and/or * modify it under the terms of the GNU General Public License @@ -15,7 +15,7 @@ * * * A tool for loading the network with preconfigurated packets. - * The tool is implemented as a linux module. Parameters are output + * The tool is implemented as a linux module. Parameters are output * device, delay (to hard_xmit), number of packets, and whether * to use multiple SKBs or just the same one. * pktgen uses the installed interface's output routine. @@ -44,14 +44,14 @@ * * Add IOCTL interface to easily get counters & configuration. * --Ben Greear <greearb@candelatech.com> * - * Renamed multiskb to clone_skb and cleaned up sending core for two distinct - * skb modes. A clone_skb=0 mode for Ben "ranges" work and a clone_skb != 0 + * Renamed multiskb to clone_skb and cleaned up sending core for two distinct + * skb modes. A clone_skb=0 mode for Ben "ranges" work and a clone_skb != 0 * as a "fastpath" with a configurable number of clones after alloc's. - * clone_skb=0 means all packets are allocated this also means ranges time - * stamps etc can be used. clone_skb=100 means 1 malloc is followed by 100 + * clone_skb=0 means all packets are allocated this also means ranges time + * stamps etc can be used. clone_skb=100 means 1 malloc is followed by 100 * clones. * - * Also moved to /proc/net/pktgen/ + * Also moved to /proc/net/pktgen/ * --ro * * Sept 10: Fixed threading/locking. Lots of bone-headed and more clever @@ -60,28 +60,28 @@ * * Integrated to 2.5.x 021029 --Lucio Maciel (luciomaciel@zipmail.com.br) * - * + * * 021124 Finished major redesign and rewrite for new functionality. * See Documentation/networking/pktgen.txt for how to use this. * * The new operation: - * For each CPU one thread/process is created at start. This process checks - * for running devices in the if_list and sends packets until count is 0 it - * also the thread checks the thread->control which is used for inter-process - * communication. controlling process "posts" operations to the threads this + * For each CPU one thread/process is created at start. This process checks + * for running devices in the if_list and sends packets until count is 0 it + * also the thread checks the thread->control which is used for inter-process + * communication. controlling process "posts" operations to the threads this * way. The if_lock should be possible to remove when add/rem_device is merged * into this too. * - * By design there should only be *one* "controlling" process. In practice - * multiple write accesses gives unpredictable result. Understood by "write" + * By design there should only be *one* "controlling" process. In practice + * multiple write accesses gives unpredictable result. Understood by "write" * to /proc gives result code thats should be read be the "writer". * For practical use this should be no problem. * - * Note when adding devices to a specific CPU there good idea to also assign - * /proc/irq/XX/smp_affinity so TX-interrupts gets bound to the same CPU. + * Note when adding devices to a specific CPU there good idea to also assign + * /proc/irq/XX/smp_affinity so TX-interrupts gets bound to the same CPU. * --ro * - * Fix refcount off by one if first packet fails, potential null deref, + * Fix refcount off by one if first packet fails, potential null deref, * memleak 030710- KJP * * First "ranges" functionality for ipv6 030726 --ro @@ -89,33 +89,40 @@ * Included flow support. 030802 ANK. * * Fixed unaligned access on IA-64 Grant Grundler <grundler@parisc-linux.org> - * + * * Remove if fix from added Harald Welte <laforge@netfilter.org> 040419 * ia64 compilation fix from Aron Griffis <aron@hp.com> 040604 * - * New xmit() return, do_div and misc clean up by Stephen Hemminger + * New xmit() return, do_div and misc clean up by Stephen Hemminger * <shemminger@osdl.org> 040923 * - * Randy Dunlap fixed u64 printk compiler waring + * Randy Dunlap fixed u64 printk compiler waring * * Remove FCS from BW calculation. Lennert Buytenhek <buytenh@wantstofly.org> * New time handling. Lennert Buytenhek <buytenh@wantstofly.org> 041213 * - * Corrections from Nikolai Malykh (nmalykh@bilim.com) + * Corrections from Nikolai Malykh (nmalykh@bilim.com) * Removed unused flags F_SET_SRCMAC & F_SET_SRCIP 041230 * - * interruptible_sleep_on_timeout() replaced Nishanth Aravamudan <nacc@us.ibm.com> + * interruptible_sleep_on_timeout() replaced Nishanth Aravamudan <nacc@us.ibm.com> * 050103 * * MPLS support by Steven Whitehouse <steve@chygwyn.com> * + * 802.1Q/Q-in-Q support by Francesco Fondelli (FF) <francesco.fondelli@gmail.com> + * + * Fixed src_mac command to set source mac of packet to value specified in + * command by Adit Ranadive <adit.262@gmail.com> + * */ + +#define pr_fmt(fmt) KBUILD_MODNAME ": " fmt + #include <linux/sys.h> #include <linux/types.h> #include <linux/module.h> #include <linux/moduleparam.h> #include <linux/kernel.h> -#include <linux/smp_lock.h> #include <linux/mutex.h> #include <linux/sched.h> #include <linux/slab.h> @@ -127,6 +134,8 @@ #include <linux/ioport.h> #include <linux/interrupt.h> #include <linux/capability.h> +#include <linux/hrtimer.h> +#include <linux/freezer.h> #include <linux/delay.h> #include <linux/timer.h> #include <linux/list.h> @@ -137,6 +146,7 @@ #include <linux/inetdevice.h> #include <linux/rtnetlink.h> #include <linux/if_arp.h> +#include <linux/if_vlan.h> #include <linux/in.h> #include <linux/ip.h> #include <linux/ipv6.h> @@ -145,28 +155,33 @@ #include <linux/seq_file.h> #include <linux/wait.h> #include <linux/etherdevice.h> +#include <linux/kthread.h> +#include <linux/prefetch.h> +#include <net/net_namespace.h> #include <net/checksum.h> #include <net/ipv6.h> +#include <net/udp.h> +#include <net/ip6_checksum.h> #include <net/addrconf.h> +#ifdef CONFIG_XFRM +#include <net/xfrm.h> +#endif +#include <net/netns/generic.h> #include <asm/byteorder.h> #include <linux/rcupdate.h> -#include <asm/bitops.h> -#include <asm/io.h> +#include <linux/bitops.h> +#include <linux/io.h> +#include <linux/timex.h> +#include <linux/uaccess.h> #include <asm/dma.h> -#include <asm/uaccess.h> #include <asm/div64.h> /* do_div */ -#include <asm/timex.h> - -#define VERSION "pktgen v2.67: Packet Generator for packet performance testing.\n" -/* #define PG_DEBUG(a) a */ -#define PG_DEBUG(a) - -/* The buckets are exponential in 'width' */ -#define LAT_BUCKETS_MAX 32 +#define VERSION "2.74" #define IP_NAME_SZ 32 #define MAX_MPLS_LABELS 16 /* This is the max label stack depth */ -#define MPLS_STACK_BOTTOM __constant_htonl(0x00000100) +#define MPLS_STACK_BOTTOM htonl(0x00000100) + +#define func_enter() pr_debug("entering %s\n", __func__); /* Device flag bits */ #define F_IPSRC_RND (1<<0) /* IP-Src Random */ @@ -178,13 +193,20 @@ #define F_TXSIZE_RND (1<<6) /* Transmit size is random */ #define F_IPV6 (1<<7) /* Interface in IPV6 Mode */ #define F_MPLS_RND (1<<8) /* Random MPLS labels */ +#define F_VID_RND (1<<9) /* Random VLAN ID */ +#define F_SVID_RND (1<<10) /* Random SVLAN ID */ +#define F_FLOW_SEQ (1<<11) /* Sequential flows */ +#define F_IPSEC_ON (1<<12) /* ipsec on for flows */ +#define F_QUEUE_MAP_RND (1<<13) /* queue map Random */ +#define F_QUEUE_MAP_CPU (1<<14) /* queue map mirrors smp_processor_id() */ +#define F_NODE (1<<15) /* Node memory alloc*/ +#define F_UDPCSUM (1<<16) /* Include UDP checksum */ /* Thread control flag bits */ -#define T_TERMINATE (1<<0) -#define T_STOP (1<<1) /* Stop run */ -#define T_RUN (1<<2) /* Start run */ -#define T_REMDEVALL (1<<3) /* Remove all devs */ -#define T_REMDEV (1<<4) /* Remove one dev */ +#define T_STOP (1<<0) /* Stop run */ +#define T_RUN (1<<1) /* Start run */ +#define T_REMDEVALL (1<<2) /* Remove all devs */ +#define T_REMDEV (1<<3) /* Remove one dev */ /* If lock -- can be removed after some work */ #define if_lock(t) spin_lock(&(t->if_lock)); @@ -194,28 +216,33 @@ #define PKTGEN_MAGIC 0xbe9be955 #define PG_PROC_DIR "pktgen" #define PGCTRL "pgctrl" -static struct proc_dir_entry *pg_proc_dir = NULL; #define MAX_CFLOWS 65536 +#define VLAN_TAG_SIZE(x) ((x)->vlan_id == 0xffff ? 0 : 4) +#define SVLAN_TAG_SIZE(x) ((x)->svlan_id == 0xffff ? 0 : 4) + struct flow_state { - __u32 cur_daddr; + __be32 cur_daddr; int count; +#ifdef CONFIG_XFRM + struct xfrm_state *x; +#endif + __u32 flags; }; -struct pktgen_dev { +/* flow flag bits */ +#define F_INIT (1<<0) /* flow has been initialized */ +struct pktgen_dev { /* * Try to keep frequent/infrequent used vars. separated. */ + struct proc_dir_entry *entry; /* proc file */ + struct pktgen_thread *pg_thread;/* the owner */ + struct list_head list; /* chaining in the thread's run-queue */ - char ifname[IFNAMSIZ]; - char result[512]; - - struct pktgen_thread *pg_thread; /* the owner */ - struct list_head list; /* Used for chaining in the thread's run-queue */ - - int running; /* if this changes to false, the test will stop */ + int running; /* if false, the test will stop */ /* If min != max, then we will either do a linear iteration, or * we will do a random selection from within the range. @@ -224,36 +251,41 @@ struct pktgen_dev { int removal_mark; /* non-zero => the device is marked for * removal by worker thread */ - int min_pkt_size; /* = ETH_ZLEN; */ - int max_pkt_size; /* = ETH_ZLEN; */ + int min_pkt_size; + int max_pkt_size; + int pkt_overhead; /* overhead for MPLS, VLANs, IPSEC etc */ int nfrags; - __u32 delay_us; /* Default delay */ - __u32 delay_ns; + struct page *page; + u64 delay; /* nano-seconds */ + __u64 count; /* Default No packets to send */ __u64 sofar; /* How many pkts we've sent so far */ __u64 tx_bytes; /* How many bytes we've transmitted */ - __u64 errors; /* Errors when trying to transmit, pkts will be re-sent */ + __u64 errors; /* Errors when trying to transmit, */ /* runtime counters relating to clone_skb */ - __u64 next_tx_us; /* timestamp of when to tx next */ - __u32 next_tx_ns; __u64 allocated_skbs; __u32 clone_count; int last_ok; /* Was last skb sent? - * Or a failed transmit of some sort? This will keep - * sequence numbers in order, for example. + * Or a failed transmit of some sort? + * This will keep sequence numbers in order */ - __u64 started_at; /* micro-seconds */ - __u64 stopped_at; /* micro-seconds */ - __u64 idle_acc; /* micro-seconds */ + ktime_t next_tx; + ktime_t started_at; + ktime_t stopped_at; + u64 idle_acc; /* nano-seconds */ + __u32 seq_num; - int clone_skb; /* Use multiple SKBs during packet gen. If this number - * is greater than 1, then that many copies of the same - * packet will be sent before a new packet is allocated. - * For instance, if you want to send 1024 identical packets - * before creating a new packet, set clone_skb to 1024. + int clone_skb; /* + * Use multiple SKBs during packet gen. + * If this number is greater than 1, then + * that many copies of the same packet will be + * sent before a new packet is allocated. + * If you want to send 1024 identical packets + * before creating a new packet, + * set clone_skb to 1024. */ char dst_min[IP_NAME_SZ]; /* IP, ie 1.2.3.4 */ @@ -274,20 +306,35 @@ struct pktgen_dev { /* If we're doing ranges, random or incremental, then this * defines the min/max for those ranges. */ - __u32 saddr_min; /* inclusive, source IP address */ - __u32 saddr_max; /* exclusive, source IP address */ - __u32 daddr_min; /* inclusive, dest IP address */ - __u32 daddr_max; /* exclusive, dest IP address */ + __be32 saddr_min; /* inclusive, source IP address */ + __be32 saddr_max; /* exclusive, source IP address */ + __be32 daddr_min; /* inclusive, dest IP address */ + __be32 daddr_max; /* exclusive, dest IP address */ __u16 udp_src_min; /* inclusive, source UDP port */ __u16 udp_src_max; /* exclusive, source UDP port */ __u16 udp_dst_min; /* inclusive, dest UDP port */ __u16 udp_dst_max; /* exclusive, dest UDP port */ + /* DSCP + ECN */ + __u8 tos; /* six MSB of (former) IPv4 TOS + are for dscp codepoint */ + __u8 traffic_class; /* ditto for the (former) Traffic Class in IPv6 + (see RFC 3260, sec. 4) */ + /* MPLS */ - unsigned nr_labels; /* Depth of stack, 0 = no MPLS */ + unsigned int nr_labels; /* Depth of stack, 0 = no MPLS */ __be32 labels[MAX_MPLS_LABELS]; + /* VLAN/SVLAN (802.1Q/Q-in-Q) */ + __u8 vlan_p; + __u8 vlan_cfi; + __u16 vlan_id; /* 0xffff means no vlan tag */ + + __u8 svlan_p; + __u8 svlan_cfi; + __u16 svlan_id; /* 0xffff means no svlan tag */ + __u32 src_mac_count; /* How many MACs to iterate through */ __u32 dst_mac_count; /* How many MACs to iterate through */ @@ -296,11 +343,14 @@ struct pktgen_dev { __u32 cur_dst_mac_offset; __u32 cur_src_mac_offset; - __u32 cur_saddr; - __u32 cur_daddr; + __be32 cur_saddr; + __be32 cur_daddr; + __u16 ip_id; __u16 cur_udp_dst; __u16 cur_udp_src; + __u16 cur_queue_map; __u32 cur_pkt_size; + __u32 last_pkt_size; __u8 hh[14]; /* = { @@ -313,252 +363,157 @@ struct pktgen_dev { */ __u16 pad; /* pad out the hh struct to an even 16 bytes */ - struct sk_buff *skb; /* skb we are to transmit next, mainly used for when we + struct sk_buff *skb; /* skb we are to transmit next, used for when we * are transmitting the same one multiple times */ - struct net_device *odev; /* The out-going device. Note that the device should - * have it's pg_info pointer pointing back to this - * device. This will be set when the user specifies - * the out-going device name (not when the inject is - * started as it used to do.) - */ + struct net_device *odev; /* The out-going device. + * Note that the device should have it's + * pg_info pointer pointing back to this + * device. + * Set when the user specifies the out-going + * device name (not when the inject is + * started as it used to do.) + */ + char odevname[32]; struct flow_state *flows; - unsigned cflows; /* Concurrent flows (config) */ - unsigned lflow; /* Flow length (config) */ - unsigned nflows; /* accumulated flows (stats) */ + unsigned int cflows; /* Concurrent flows (config) */ + unsigned int lflow; /* Flow length (config) */ + unsigned int nflows; /* accumulated flows (stats) */ + unsigned int curfl; /* current sequenced flow (state)*/ + + u16 queue_map_min; + u16 queue_map_max; + __u32 skb_priority; /* skb priority field */ + int node; /* Memory node */ + +#ifdef CONFIG_XFRM + __u8 ipsmode; /* IPSEC mode (config) */ + __u8 ipsproto; /* IPSEC type (config) */ + __u32 spi; + struct dst_entry dst; + struct dst_ops dstops; +#endif + char result[512]; }; struct pktgen_hdr { - __u32 pgh_magic; - __u32 seq_num; - __u32 tv_sec; - __u32 tv_usec; + __be32 pgh_magic; + __be32 seq_num; + __be32 tv_sec; + __be32 tv_usec; +}; + + +static int pg_net_id __read_mostly; + +struct pktgen_net { + struct net *net; + struct proc_dir_entry *proc_dir; + struct list_head pktgen_threads; + bool pktgen_exiting; }; struct pktgen_thread { - spinlock_t if_lock; + spinlock_t if_lock; /* for list of devices */ struct list_head if_list; /* All device here */ struct list_head th_list; - int removed; - char name[32]; + struct task_struct *tsk; char result[512]; - u32 max_before_softirq; /* We'll call do_softirq to prevent starvation. */ - /* Field for thread to receive "posted" events terminate, stop ifs etc. */ + /* Field for thread to receive "posted" events terminate, + stop ifs etc. */ u32 control; - int pid; int cpu; wait_queue_head_t queue; + struct completion start_done; + struct pktgen_net *net; }; #define REMOVE 1 #define FIND 0 -/* This code works around the fact that do_div cannot handle two 64-bit - numbers, and regular 64-bit division doesn't work on x86 kernels. - --Ben -*/ - -#define PG_DIV 0 - -/* This was emailed to LMKL by: Chris Caputo <ccaputo@alt.net> - * Function copied/adapted/optimized from: - * - * nemesis.sourceforge.net/browse/lib/static/intmath/ix86/intmath.c.html - * - * Copyright 1994, University of Cambridge Computer Laboratory - * All Rights Reserved. - * - */ -static inline s64 divremdi3(s64 x, s64 y, int type) -{ - u64 a = (x < 0) ? -x : x; - u64 b = (y < 0) ? -y : y; - u64 res = 0, d = 1; - - if (b > 0) { - while (b < a) { - b <<= 1; - d <<= 1; - } - } - - do { - if (a >= b) { - a -= b; - res += d; - } - b >>= 1; - d >>= 1; - } - while (d); - - if (PG_DIV == type) { - return (((x ^ y) & (1ll << 63)) == 0) ? res : -(s64) res; - } else { - return ((x & (1ll << 63)) == 0) ? a : -(s64) a; - } -} - -/* End of hacks to deal with 64-bit math on x86 */ - -/** Convert to milliseconds */ -static inline __u64 tv_to_ms(const struct timeval *tv) -{ - __u64 ms = tv->tv_usec / 1000; - ms += (__u64) tv->tv_sec * (__u64) 1000; - return ms; -} - -/** Convert to micro-seconds */ -static inline __u64 tv_to_us(const struct timeval *tv) -{ - __u64 us = tv->tv_usec; - us += (__u64) tv->tv_sec * (__u64) 1000000; - return us; -} - -static inline __u64 pg_div(__u64 n, __u32 base) -{ - __u64 tmp = n; - do_div(tmp, base); - /* printk("pktgen: pg_div, n: %llu base: %d rv: %llu\n", - n, base, tmp); */ - return tmp; -} - -static inline __u64 pg_div64(__u64 n, __u64 base) -{ - __u64 tmp = n; -/* - * How do we know if the architecture we are running on - * supports division with 64 bit base? - * - */ -#if defined(__sparc_v9__) || defined(__powerpc64__) || defined(__alpha__) || defined(__x86_64__) || defined(__ia64__) - - do_div(tmp, base); -#else - tmp = divremdi3(n, base, PG_DIV); -#endif - return tmp; -} - -static inline u32 pktgen_random(void) -{ -#if 0 - __u32 n; - get_random_bytes(&n, 4); - return n; -#else - return net_random(); -#endif -} - -static inline __u64 getCurMs(void) -{ - struct timeval tv; - do_gettimeofday(&tv); - return tv_to_ms(&tv); -} - -static inline __u64 getCurUs(void) -{ - struct timeval tv; - do_gettimeofday(&tv); - return tv_to_us(&tv); -} - -static inline __u64 tv_diff(const struct timeval *a, const struct timeval *b) -{ - return tv_to_us(a) - tv_to_us(b); -} - -/* old include end */ - -static char version[] __initdata = VERSION; +static const char version[] = + "Packet Generator for packet performance testing. " + "Version: " VERSION "\n"; static int pktgen_remove_device(struct pktgen_thread *t, struct pktgen_dev *i); static int pktgen_add_device(struct pktgen_thread *t, const char *ifname); static struct pktgen_dev *pktgen_find_dev(struct pktgen_thread *t, - const char *ifname); + const char *ifname, bool exact); static int pktgen_device_event(struct notifier_block *, unsigned long, void *); -static void pktgen_run_all_threads(void); -static void pktgen_stop_all_threads_ifs(void); -static int pktgen_stop_device(struct pktgen_dev *pkt_dev); +static void pktgen_run_all_threads(struct pktgen_net *pn); +static void pktgen_reset_all_threads(struct pktgen_net *pn); +static void pktgen_stop_all_threads_ifs(struct pktgen_net *pn); + static void pktgen_stop(struct pktgen_thread *t); static void pktgen_clear_counters(struct pktgen_dev *pkt_dev); -static int pktgen_mark_device(const char *ifname); -static unsigned int scan_ip6(const char *s, char ip[16]); -static unsigned int fmt_ip6(char *s, const char ip[16]); /* Module parameters, defaults. */ -static int pg_count_d = 1000; /* 1000 pkts by default */ -static int pg_delay_d; -static int pg_clone_skb_d; -static int debug; +static int pg_count_d __read_mostly = 1000; +static int pg_delay_d __read_mostly; +static int pg_clone_skb_d __read_mostly; +static int debug __read_mostly; static DEFINE_MUTEX(pktgen_thread_lock); -static LIST_HEAD(pktgen_threads); static struct notifier_block pktgen_notifier_block = { .notifier_call = pktgen_device_event, }; /* - * /proc handling functions + * /proc handling functions * */ static int pgctrl_show(struct seq_file *seq, void *v) { - seq_puts(seq, VERSION); + seq_puts(seq, version); return 0; } -static ssize_t pgctrl_write(struct file *file, const char __user * buf, - size_t count, loff_t * ppos) +static ssize_t pgctrl_write(struct file *file, const char __user *buf, + size_t count, loff_t *ppos) { - int err = 0; char data[128]; + struct pktgen_net *pn = net_generic(current->nsproxy->net_ns, pg_net_id); - if (!capable(CAP_NET_ADMIN)) { - err = -EPERM; - goto out; - } + if (!capable(CAP_NET_ADMIN)) + return -EPERM; + + if (count == 0) + return -EINVAL; if (count > sizeof(data)) count = sizeof(data); - if (copy_from_user(data, buf, count)) { - err = -EFAULT; - goto out; - } - data[count - 1] = 0; /* Make string */ + if (copy_from_user(data, buf, count)) + return -EFAULT; + + data[count - 1] = 0; /* Strip trailing '\n' and terminate string */ if (!strcmp(data, "stop")) - pktgen_stop_all_threads_ifs(); + pktgen_stop_all_threads_ifs(pn); else if (!strcmp(data, "start")) - pktgen_run_all_threads(); + pktgen_run_all_threads(pn); - else - printk("pktgen: Unknown command: %s\n", data); + else if (!strcmp(data, "reset")) + pktgen_reset_all_threads(pn); - err = count; + else + pr_warning("Unknown command: %s\n", data); -out: - return err; + return count; } static int pgctrl_open(struct inode *inode, struct file *file) { - return single_open(file, pgctrl_show, PDE(inode)->data); + return single_open(file, pgctrl_show, PDE_DATA(inode)); } -static struct file_operations pktgen_fops = { +static const struct file_operations pktgen_fops = { .owner = THIS_MODULE, .open = pgctrl_open, .read = seq_read, @@ -569,11 +524,9 @@ static struct file_operations pktgen_fops = { static int pktgen_if_show(struct seq_file *seq, void *v) { - int i; - struct pktgen_dev *pkt_dev = seq->private; - __u64 sa; - __u64 stopped; - __u64 now = getCurUs(); + const struct pktgen_dev *pkt_dev = seq->private; + ktime_t stopped; + u64 idle; seq_printf(seq, "Params: count %llu min_pkt_size: %u max_pkt_size: %u\n", @@ -581,54 +534,51 @@ static int pktgen_if_show(struct seq_file *seq, void *v) pkt_dev->max_pkt_size); seq_printf(seq, - " frags: %d delay: %u clone_skb: %d ifname: %s\n", - pkt_dev->nfrags, - 1000 * pkt_dev->delay_us + pkt_dev->delay_ns, - pkt_dev->clone_skb, pkt_dev->ifname); + " frags: %d delay: %llu clone_skb: %d ifname: %s\n", + pkt_dev->nfrags, (unsigned long long) pkt_dev->delay, + pkt_dev->clone_skb, pkt_dev->odevname); seq_printf(seq, " flows: %u flowlen: %u\n", pkt_dev->cflows, pkt_dev->lflow); + seq_printf(seq, + " queue_map_min: %u queue_map_max: %u\n", + pkt_dev->queue_map_min, + pkt_dev->queue_map_max); + + if (pkt_dev->skb_priority) + seq_printf(seq, " skb_priority: %u\n", + pkt_dev->skb_priority); + if (pkt_dev->flags & F_IPV6) { - char b1[128], b2[128], b3[128]; - fmt_ip6(b1, pkt_dev->in6_saddr.s6_addr); - fmt_ip6(b2, pkt_dev->min_in6_saddr.s6_addr); - fmt_ip6(b3, pkt_dev->max_in6_saddr.s6_addr); seq_printf(seq, - " saddr: %s min_saddr: %s max_saddr: %s\n", b1, - b2, b3); - - fmt_ip6(b1, pkt_dev->in6_daddr.s6_addr); - fmt_ip6(b2, pkt_dev->min_in6_daddr.s6_addr); - fmt_ip6(b3, pkt_dev->max_in6_daddr.s6_addr); + " saddr: %pI6c min_saddr: %pI6c max_saddr: %pI6c\n" + " daddr: %pI6c min_daddr: %pI6c max_daddr: %pI6c\n", + &pkt_dev->in6_saddr, + &pkt_dev->min_in6_saddr, &pkt_dev->max_in6_saddr, + &pkt_dev->in6_daddr, + &pkt_dev->min_in6_daddr, &pkt_dev->max_in6_daddr); + } else { seq_printf(seq, - " daddr: %s min_daddr: %s max_daddr: %s\n", b1, - b2, b3); - - } else + " dst_min: %s dst_max: %s\n", + pkt_dev->dst_min, pkt_dev->dst_max); seq_printf(seq, - " dst_min: %s dst_max: %s\n src_min: %s src_max: %s\n", - pkt_dev->dst_min, pkt_dev->dst_max, pkt_dev->src_min, - pkt_dev->src_max); + " src_min: %s src_max: %s\n", + pkt_dev->src_min, pkt_dev->src_max); + } seq_puts(seq, " src_mac: "); - if (is_zero_ether_addr(pkt_dev->src_mac)) - for (i = 0; i < 6; i++) - seq_printf(seq, "%02X%s", pkt_dev->odev->dev_addr[i], - i == 5 ? " " : ":"); - else - for (i = 0; i < 6; i++) - seq_printf(seq, "%02X%s", pkt_dev->src_mac[i], - i == 5 ? " " : ":"); + seq_printf(seq, "%pM ", + is_zero_ether_addr(pkt_dev->src_mac) ? + pkt_dev->odev->dev_addr : pkt_dev->src_mac); - seq_printf(seq, "dst_mac: "); - for (i = 0; i < 6; i++) - seq_printf(seq, "%02X%s", pkt_dev->dst_mac[i], - i == 5 ? "\n" : ":"); + seq_puts(seq, "dst_mac: "); + seq_printf(seq, "%pM\n", pkt_dev->dst_mac); seq_printf(seq, - " udp_src_min: %d udp_src_max: %d udp_dst_min: %d udp_dst_max: %d\n", + " udp_src_min: %d udp_src_max: %d" + " udp_dst_min: %d udp_dst_max: %d\n", pkt_dev->udp_src_min, pkt_dev->udp_src_max, pkt_dev->udp_dst_min, pkt_dev->udp_dst_max); @@ -637,55 +587,111 @@ static int pktgen_if_show(struct seq_file *seq, void *v) pkt_dev->src_mac_count, pkt_dev->dst_mac_count); if (pkt_dev->nr_labels) { - unsigned i; - seq_printf(seq, " mpls: "); - for(i = 0; i < pkt_dev->nr_labels; i++) + unsigned int i; + seq_puts(seq, " mpls: "); + for (i = 0; i < pkt_dev->nr_labels; i++) seq_printf(seq, "%08x%s", ntohl(pkt_dev->labels[i]), i == pkt_dev->nr_labels-1 ? "\n" : ", "); } - seq_printf(seq, " Flags: "); + if (pkt_dev->vlan_id != 0xffff) + seq_printf(seq, " vlan_id: %u vlan_p: %u vlan_cfi: %u\n", + pkt_dev->vlan_id, pkt_dev->vlan_p, + pkt_dev->vlan_cfi); + + if (pkt_dev->svlan_id != 0xffff) + seq_printf(seq, " svlan_id: %u vlan_p: %u vlan_cfi: %u\n", + pkt_dev->svlan_id, pkt_dev->svlan_p, + pkt_dev->svlan_cfi); + + if (pkt_dev->tos) + seq_printf(seq, " tos: 0x%02x\n", pkt_dev->tos); + + if (pkt_dev->traffic_class) + seq_printf(seq, " traffic_class: 0x%02x\n", pkt_dev->traffic_class); + + if (pkt_dev->node >= 0) + seq_printf(seq, " node: %d\n", pkt_dev->node); + + seq_puts(seq, " Flags: "); if (pkt_dev->flags & F_IPV6) - seq_printf(seq, "IPV6 "); + seq_puts(seq, "IPV6 "); if (pkt_dev->flags & F_IPSRC_RND) - seq_printf(seq, "IPSRC_RND "); + seq_puts(seq, "IPSRC_RND "); if (pkt_dev->flags & F_IPDST_RND) - seq_printf(seq, "IPDST_RND "); + seq_puts(seq, "IPDST_RND "); if (pkt_dev->flags & F_TXSIZE_RND) - seq_printf(seq, "TXSIZE_RND "); + seq_puts(seq, "TXSIZE_RND "); if (pkt_dev->flags & F_UDPSRC_RND) - seq_printf(seq, "UDPSRC_RND "); + seq_puts(seq, "UDPSRC_RND "); if (pkt_dev->flags & F_UDPDST_RND) - seq_printf(seq, "UDPDST_RND "); + seq_puts(seq, "UDPDST_RND "); + + if (pkt_dev->flags & F_UDPCSUM) + seq_puts(seq, "UDPCSUM "); if (pkt_dev->flags & F_MPLS_RND) - seq_printf(seq, "MPLS_RND "); + seq_puts(seq, "MPLS_RND "); + + if (pkt_dev->flags & F_QUEUE_MAP_RND) + seq_puts(seq, "QUEUE_MAP_RND "); + + if (pkt_dev->flags & F_QUEUE_MAP_CPU) + seq_puts(seq, "QUEUE_MAP_CPU "); + + if (pkt_dev->cflows) { + if (pkt_dev->flags & F_FLOW_SEQ) + seq_puts(seq, "FLOW_SEQ "); /*in sequence flows*/ + else + seq_puts(seq, "FLOW_RND "); + } + +#ifdef CONFIG_XFRM + if (pkt_dev->flags & F_IPSEC_ON) { + seq_puts(seq, "IPSEC "); + if (pkt_dev->spi) + seq_printf(seq, "spi:%u", pkt_dev->spi); + } +#endif if (pkt_dev->flags & F_MACSRC_RND) - seq_printf(seq, "MACSRC_RND "); + seq_puts(seq, "MACSRC_RND "); if (pkt_dev->flags & F_MACDST_RND) - seq_printf(seq, "MACDST_RND "); + seq_puts(seq, "MACDST_RND "); + + if (pkt_dev->flags & F_VID_RND) + seq_puts(seq, "VID_RND "); + + if (pkt_dev->flags & F_SVID_RND) + seq_puts(seq, "SVID_RND "); + + if (pkt_dev->flags & F_NODE) + seq_puts(seq, "NODE_ALLOC "); seq_puts(seq, "\n"); - sa = pkt_dev->started_at; - stopped = pkt_dev->stopped_at; - if (pkt_dev->running) - stopped = now; /* not really stopped, more like last-running-at */ + /* not really stopped, more like last-running-at */ + stopped = pkt_dev->running ? ktime_get() : pkt_dev->stopped_at; + idle = pkt_dev->idle_acc; + do_div(idle, NSEC_PER_USEC); seq_printf(seq, - "Current:\n pkts-sofar: %llu errors: %llu\n started: %lluus stopped: %lluus idle: %lluus\n", + "Current:\n pkts-sofar: %llu errors: %llu\n", (unsigned long long)pkt_dev->sofar, - (unsigned long long)pkt_dev->errors, (unsigned long long)sa, - (unsigned long long)stopped, - (unsigned long long)pkt_dev->idle_acc); + (unsigned long long)pkt_dev->errors); + + seq_printf(seq, + " started: %lluus stopped: %lluus idle: %lluus\n", + (unsigned long long) ktime_to_us(pkt_dev->started_at), + (unsigned long long) ktime_to_us(stopped), + (unsigned long long) idle); seq_printf(seq, " seq_num: %d cur_dst_mac_offset: %d cur_src_mac_offset: %d\n", @@ -693,44 +699,44 @@ static int pktgen_if_show(struct seq_file *seq, void *v) pkt_dev->cur_src_mac_offset); if (pkt_dev->flags & F_IPV6) { - char b1[128], b2[128]; - fmt_ip6(b1, pkt_dev->cur_in6_daddr.s6_addr); - fmt_ip6(b2, pkt_dev->cur_in6_saddr.s6_addr); - seq_printf(seq, " cur_saddr: %s cur_daddr: %s\n", b2, b1); + seq_printf(seq, " cur_saddr: %pI6c cur_daddr: %pI6c\n", + &pkt_dev->cur_in6_saddr, + &pkt_dev->cur_in6_daddr); } else - seq_printf(seq, " cur_saddr: 0x%x cur_daddr: 0x%x\n", - pkt_dev->cur_saddr, pkt_dev->cur_daddr); + seq_printf(seq, " cur_saddr: %pI4 cur_daddr: %pI4\n", + &pkt_dev->cur_saddr, &pkt_dev->cur_daddr); seq_printf(seq, " cur_udp_dst: %d cur_udp_src: %d\n", pkt_dev->cur_udp_dst, pkt_dev->cur_udp_src); + seq_printf(seq, " cur_queue_map: %u\n", pkt_dev->cur_queue_map); + seq_printf(seq, " flows: %u\n", pkt_dev->nflows); if (pkt_dev->result[0]) seq_printf(seq, "Result: %s\n", pkt_dev->result); else - seq_printf(seq, "Result: Idle\n"); + seq_puts(seq, "Result: Idle\n"); return 0; } -static int hex32_arg(const char __user *user_buffer, __u32 *num) +static int hex32_arg(const char __user *user_buffer, unsigned long maxlen, + __u32 *num) { int i = 0; *num = 0; - for(; i < 8; i++) { + for (; i < maxlen; i++) { + int value; char c; *num <<= 4; if (get_user(c, &user_buffer[i])) return -EFAULT; - if ((c >= '0') && (c <= '9')) - *num |= c - '0'; - else if ((c >= 'a') && (c <= 'f')) - *num |= c - 'a' + 10; - else if ((c >= 'A') && (c <= 'F')) - *num |= c - 'A' + 10; + value = hex_to_bin(c); + if (value >= 0) + *num |= value; else break; } @@ -756,19 +762,19 @@ static int count_trail_chars(const char __user * user_buffer, break; default: goto done; - }; + } } done: return i; } -static unsigned long num_arg(const char __user * user_buffer, - unsigned long maxlen, unsigned long *num) +static long num_arg(const char __user *user_buffer, unsigned long maxlen, + unsigned long *num) { - int i = 0; + int i; *num = 0; - for (; i < maxlen; i++) { + for (i = 0; i < maxlen; i++) { char c; if (get_user(c, &user_buffer[i])) return -EFAULT; @@ -783,9 +789,9 @@ static unsigned long num_arg(const char __user * user_buffer, static int strn_len(const char __user * user_buffer, unsigned int maxlen) { - int i = 0; + int i; - for (; i < maxlen; i++) { + for (i = 0; i < maxlen; i++) { char c; if (get_user(c, &user_buffer[i])) return -EFAULT; @@ -799,7 +805,7 @@ static int strn_len(const char __user * user_buffer, unsigned int maxlen) break; default: break; - }; + } } done_str: return i; @@ -807,7 +813,7 @@ done_str: static ssize_t get_labels(const char __user *buffer, struct pktgen_dev *pkt_dev) { - unsigned n = 0; + unsigned int n = 0; char c; ssize_t i = 0; int len; @@ -815,7 +821,7 @@ static ssize_t get_labels(const char __user *buffer, struct pktgen_dev *pkt_dev) pkt_dev->nr_labels = 0; do { __u32 tmp; - len = hex32_arg(&buffer[i], &tmp); + len = hex32_arg(&buffer[i], 8, &tmp); if (len <= 0) return len; pkt_dev->labels[n] = htonl(tmp); @@ -828,7 +834,7 @@ static ssize_t get_labels(const char __user *buffer, struct pktgen_dev *pkt_dev) n++; if (n >= MAX_MPLS_LABELS) return -E2BIG; - } while(c == ','); + } while (c == ','); pkt_dev->nr_labels = n; return i; @@ -838,9 +844,9 @@ static ssize_t pktgen_if_write(struct file *file, const char __user * user_buffer, size_t count, loff_t * offset) { - struct seq_file *seq = (struct seq_file *)file->private_data; + struct seq_file *seq = file->private_data; struct pktgen_dev *pkt_dev = seq->private; - int i = 0, max, len; + int i, max, len; char name[16], valstr[32]; unsigned long value = 0; char *pg_result = NULL; @@ -850,24 +856,24 @@ static ssize_t pktgen_if_write(struct file *file, pg_result = &(pkt_dev->result[0]); if (count < 1) { - printk("pktgen: wrong command format\n"); + pr_warning("wrong command format\n"); return -EINVAL; } - max = count - i; - tmp = count_trail_chars(&user_buffer[i], max); + max = count; + tmp = count_trail_chars(user_buffer, max); if (tmp < 0) { - printk("pktgen: illegal format\n"); + pr_warning("illegal format\n"); return tmp; } - i += tmp; + i = tmp; /* Read variable name */ len = strn_len(&user_buffer[i], sizeof(name) - 1); - if (len < 0) { + if (len < 0) return len; - } + memset(name, 0, sizeof(name)); if (copy_from_user(name, &user_buffer[i], len)) return -EFAULT; @@ -881,19 +887,20 @@ static ssize_t pktgen_if_write(struct file *file, i += len; if (debug) { - char tb[count + 1]; - if (copy_from_user(tb, user_buffer, count)) + size_t copy = min_t(size_t, count, 1023); + char tb[copy + 1]; + if (copy_from_user(tb, user_buffer, copy)) return -EFAULT; - tb[count] = 0; - printk("pktgen: %s,%lu buffer -:%s:-\n", name, - (unsigned long)count, tb); + tb[copy] = 0; + pr_debug("%s,%lu buffer -:%s:-\n", + name, (unsigned long)count, tb); } if (!strcmp(name, "min_pkt_size")) { len = num_arg(&user_buffer[i], 10, &value); - if (len < 0) { + if (len < 0) return len; - } + i += len; if (value < 14 + 20 + 8) value = 14 + 20 + 8; @@ -908,9 +915,9 @@ static ssize_t pktgen_if_write(struct file *file, if (!strcmp(name, "max_pkt_size")) { len = num_arg(&user_buffer[i], 10, &value); - if (len < 0) { + if (len < 0) return len; - } + i += len; if (value < 14 + 20 + 8) value = 14 + 20 + 8; @@ -927,9 +934,9 @@ static ssize_t pktgen_if_write(struct file *file, if (!strcmp(name, "pkt_size")) { len = num_arg(&user_buffer[i], 10, &value); - if (len < 0) { + if (len < 0) return len; - } + i += len; if (value < 14 + 20 + 8) value = 14 + 20 + 8; @@ -944,9 +951,9 @@ static ssize_t pktgen_if_write(struct file *file, if (!strcmp(name, "debug")) { len = num_arg(&user_buffer[i], 10, &value); - if (len < 0) { + if (len < 0) return len; - } + i += len; debug = value; sprintf(pg_result, "OK: debug=%u", debug); @@ -955,9 +962,9 @@ static ssize_t pktgen_if_write(struct file *file, if (!strcmp(name, "frags")) { len = num_arg(&user_buffer[i], 10, &value); - if (len < 0) { + if (len < 0) return len; - } + i += len; pkt_dev->nfrags = value; sprintf(pg_result, "OK: frags=%u", pkt_dev->nfrags); @@ -965,26 +972,54 @@ static ssize_t pktgen_if_write(struct file *file, } if (!strcmp(name, "delay")) { len = num_arg(&user_buffer[i], 10, &value); - if (len < 0) { + if (len < 0) return len; - } + i += len; - if (value == 0x7FFFFFFF) { - pkt_dev->delay_us = 0x7FFFFFFF; - pkt_dev->delay_ns = 0; - } else { - pkt_dev->delay_us = value / 1000; - pkt_dev->delay_ns = value % 1000; - } - sprintf(pg_result, "OK: delay=%u", - 1000 * pkt_dev->delay_us + pkt_dev->delay_ns); + if (value == 0x7FFFFFFF) + pkt_dev->delay = ULLONG_MAX; + else + pkt_dev->delay = (u64)value; + + sprintf(pg_result, "OK: delay=%llu", + (unsigned long long) pkt_dev->delay); + return count; + } + if (!strcmp(name, "rate")) { + len = num_arg(&user_buffer[i], 10, &value); + if (len < 0) + return len; + + i += len; + if (!value) + return len; + pkt_dev->delay = pkt_dev->min_pkt_size*8*NSEC_PER_USEC/value; + if (debug) + pr_info("Delay set at: %llu ns\n", pkt_dev->delay); + + sprintf(pg_result, "OK: rate=%lu", value); + return count; + } + if (!strcmp(name, "ratep")) { + len = num_arg(&user_buffer[i], 10, &value); + if (len < 0) + return len; + + i += len; + if (!value) + return len; + pkt_dev->delay = NSEC_PER_SEC/value; + if (debug) + pr_info("Delay set at: %llu ns\n", pkt_dev->delay); + + sprintf(pg_result, "OK: rate=%lu", value); return count; } if (!strcmp(name, "udp_src_min")) { len = num_arg(&user_buffer[i], 10, &value); - if (len < 0) { + if (len < 0) return len; - } + i += len; if (value != pkt_dev->udp_src_min) { pkt_dev->udp_src_min = value; @@ -995,9 +1030,9 @@ static ssize_t pktgen_if_write(struct file *file, } if (!strcmp(name, "udp_dst_min")) { len = num_arg(&user_buffer[i], 10, &value); - if (len < 0) { + if (len < 0) return len; - } + i += len; if (value != pkt_dev->udp_dst_min) { pkt_dev->udp_dst_min = value; @@ -1008,9 +1043,9 @@ static ssize_t pktgen_if_write(struct file *file, } if (!strcmp(name, "udp_src_max")) { len = num_arg(&user_buffer[i], 10, &value); - if (len < 0) { + if (len < 0) return len; - } + i += len; if (value != pkt_dev->udp_src_max) { pkt_dev->udp_src_max = value; @@ -1021,9 +1056,9 @@ static ssize_t pktgen_if_write(struct file *file, } if (!strcmp(name, "udp_dst_max")) { len = num_arg(&user_buffer[i], 10, &value); - if (len < 0) { + if (len < 0) return len; - } + i += len; if (value != pkt_dev->udp_dst_max) { pkt_dev->udp_dst_max = value; @@ -1034,9 +1069,11 @@ static ssize_t pktgen_if_write(struct file *file, } if (!strcmp(name, "clone_skb")) { len = num_arg(&user_buffer[i], 10, &value); - if (len < 0) { + if (len < 0) return len; - } + if ((value > 0) && + (!(pkt_dev->odev->priv_flags & IFF_TX_SKB_SHARING))) + return -ENOTSUPP; i += len; pkt_dev->clone_skb = value; @@ -1045,9 +1082,9 @@ static ssize_t pktgen_if_write(struct file *file, } if (!strcmp(name, "count")) { len = num_arg(&user_buffer[i], 10, &value); - if (len < 0) { + if (len < 0) return len; - } + i += len; pkt_dev->count = value; sprintf(pg_result, "OK: count=%llu", @@ -1056,9 +1093,9 @@ static ssize_t pktgen_if_write(struct file *file, } if (!strcmp(name, "src_mac_count")) { len = num_arg(&user_buffer[i], 10, &value); - if (len < 0) { + if (len < 0) return len; - } + i += len; if (pkt_dev->src_mac_count != value) { pkt_dev->src_mac_count = value; @@ -1070,9 +1107,9 @@ static ssize_t pktgen_if_write(struct file *file, } if (!strcmp(name, "dst_mac_count")) { len = num_arg(&user_buffer[i], 10, &value); - if (len < 0) { + if (len < 0) return len; - } + i += len; if (pkt_dev->dst_mac_count != value) { pkt_dev->dst_mac_count = value; @@ -1082,13 +1119,32 @@ static ssize_t pktgen_if_write(struct file *file, pkt_dev->dst_mac_count); return count; } + if (!strcmp(name, "node")) { + len = num_arg(&user_buffer[i], 10, &value); + if (len < 0) + return len; + + i += len; + + if (node_possible(value)) { + pkt_dev->node = value; + sprintf(pg_result, "OK: node=%d", pkt_dev->node); + if (pkt_dev->page) { + put_page(pkt_dev->page); + pkt_dev->page = NULL; + } + } + else + sprintf(pg_result, "ERROR: node not possible"); + return count; + } if (!strcmp(name, "flag")) { char f[32]; memset(f, 0, 32); len = strn_len(&user_buffer[i], sizeof(f) - 1); - if (len < 0) { + if (len < 0) return len; - } + if (copy_from_user(f, &user_buffer[i], len)) return -EFAULT; i += len; @@ -1140,11 +1196,64 @@ static ssize_t pktgen_if_write(struct file *file, else if (strcmp(f, "!MPLS_RND") == 0) pkt_dev->flags &= ~F_MPLS_RND; + else if (strcmp(f, "VID_RND") == 0) + pkt_dev->flags |= F_VID_RND; + + else if (strcmp(f, "!VID_RND") == 0) + pkt_dev->flags &= ~F_VID_RND; + + else if (strcmp(f, "SVID_RND") == 0) + pkt_dev->flags |= F_SVID_RND; + + else if (strcmp(f, "!SVID_RND") == 0) + pkt_dev->flags &= ~F_SVID_RND; + + else if (strcmp(f, "FLOW_SEQ") == 0) + pkt_dev->flags |= F_FLOW_SEQ; + + else if (strcmp(f, "QUEUE_MAP_RND") == 0) + pkt_dev->flags |= F_QUEUE_MAP_RND; + + else if (strcmp(f, "!QUEUE_MAP_RND") == 0) + pkt_dev->flags &= ~F_QUEUE_MAP_RND; + + else if (strcmp(f, "QUEUE_MAP_CPU") == 0) + pkt_dev->flags |= F_QUEUE_MAP_CPU; + + else if (strcmp(f, "!QUEUE_MAP_CPU") == 0) + pkt_dev->flags &= ~F_QUEUE_MAP_CPU; +#ifdef CONFIG_XFRM + else if (strcmp(f, "IPSEC") == 0) + pkt_dev->flags |= F_IPSEC_ON; +#endif + + else if (strcmp(f, "!IPV6") == 0) + pkt_dev->flags &= ~F_IPV6; + + else if (strcmp(f, "NODE_ALLOC") == 0) + pkt_dev->flags |= F_NODE; + + else if (strcmp(f, "!NODE_ALLOC") == 0) + pkt_dev->flags &= ~F_NODE; + + else if (strcmp(f, "UDPCSUM") == 0) + pkt_dev->flags |= F_UDPCSUM; + + else if (strcmp(f, "!UDPCSUM") == 0) + pkt_dev->flags &= ~F_UDPCSUM; + else { sprintf(pg_result, "Flag -:%s:- unknown\nAvailable flags, (prepend ! to un-set flag):\n%s", f, - "IPSRC_RND, IPDST_RND, TXSIZE_RND, UDPSRC_RND, UDPDST_RND, MACSRC_RND, MACDST_RND\n"); + "IPSRC_RND, IPDST_RND, UDPSRC_RND, UDPDST_RND, " + "MACSRC_RND, MACDST_RND, TXSIZE_RND, IPV6, " + "MPLS_RND, VID_RND, SVID_RND, FLOW_SEQ, " + "QUEUE_MAP_RND, QUEUE_MAP_CPU, UDPCSUM, " +#ifdef CONFIG_XFRM + "IPSEC, " +#endif + "NODE_ALLOC\n"); return count; } sprintf(pg_result, "OK: flags=0x%x", pkt_dev->flags); @@ -1152,9 +1261,8 @@ static ssize_t pktgen_if_write(struct file *file, } if (!strcmp(name, "dst_min") || !strcmp(name, "dst")) { len = strn_len(&user_buffer[i], sizeof(pkt_dev->dst_min) - 1); - if (len < 0) { + if (len < 0) return len; - } if (copy_from_user(buf, &user_buffer[i], len)) return -EFAULT; @@ -1166,17 +1274,16 @@ static ssize_t pktgen_if_write(struct file *file, pkt_dev->cur_daddr = pkt_dev->daddr_min; } if (debug) - printk("pktgen: dst_min set to: %s\n", - pkt_dev->dst_min); + pr_debug("dst_min set to: %s\n", pkt_dev->dst_min); i += len; sprintf(pg_result, "OK: dst_min=%s", pkt_dev->dst_min); return count; } if (!strcmp(name, "dst_max")) { len = strn_len(&user_buffer[i], sizeof(pkt_dev->dst_max) - 1); - if (len < 0) { + if (len < 0) return len; - } + if (copy_from_user(buf, &user_buffer[i], len)) return -EFAULT; @@ -1189,8 +1296,7 @@ static ssize_t pktgen_if_write(struct file *file, pkt_dev->cur_daddr = pkt_dev->daddr_max; } if (debug) - printk("pktgen: dst_max set to: %s\n", - pkt_dev->dst_max); + pr_debug("dst_max set to: %s\n", pkt_dev->dst_max); i += len; sprintf(pg_result, "OK: dst_max=%s", pkt_dev->dst_max); return count; @@ -1206,13 +1312,13 @@ static ssize_t pktgen_if_write(struct file *file, return -EFAULT; buf[len] = 0; - scan_ip6(buf, pkt_dev->in6_daddr.s6_addr); - fmt_ip6(buf, pkt_dev->in6_daddr.s6_addr); + in6_pton(buf, -1, pkt_dev->in6_daddr.s6_addr, -1, NULL); + snprintf(buf, sizeof(buf), "%pI6c", &pkt_dev->in6_daddr); - ipv6_addr_copy(&pkt_dev->cur_in6_daddr, &pkt_dev->in6_daddr); + pkt_dev->cur_in6_daddr = pkt_dev->in6_daddr; if (debug) - printk("pktgen: dst6 set to: %s\n", buf); + pr_debug("dst6 set to: %s\n", buf); i += len; sprintf(pg_result, "OK: dst6=%s", buf); @@ -1229,13 +1335,12 @@ static ssize_t pktgen_if_write(struct file *file, return -EFAULT; buf[len] = 0; - scan_ip6(buf, pkt_dev->min_in6_daddr.s6_addr); - fmt_ip6(buf, pkt_dev->min_in6_daddr.s6_addr); + in6_pton(buf, -1, pkt_dev->min_in6_daddr.s6_addr, -1, NULL); + snprintf(buf, sizeof(buf), "%pI6c", &pkt_dev->min_in6_daddr); - ipv6_addr_copy(&pkt_dev->cur_in6_daddr, - &pkt_dev->min_in6_daddr); + pkt_dev->cur_in6_daddr = pkt_dev->min_in6_daddr; if (debug) - printk("pktgen: dst6_min set to: %s\n", buf); + pr_debug("dst6_min set to: %s\n", buf); i += len; sprintf(pg_result, "OK: dst6_min=%s", buf); @@ -1252,11 +1357,11 @@ static ssize_t pktgen_if_write(struct file *file, return -EFAULT; buf[len] = 0; - scan_ip6(buf, pkt_dev->max_in6_daddr.s6_addr); - fmt_ip6(buf, pkt_dev->max_in6_daddr.s6_addr); + in6_pton(buf, -1, pkt_dev->max_in6_daddr.s6_addr, -1, NULL); + snprintf(buf, sizeof(buf), "%pI6c", &pkt_dev->max_in6_daddr); if (debug) - printk("pktgen: dst6_max set to: %s\n", buf); + pr_debug("dst6_max set to: %s\n", buf); i += len; sprintf(pg_result, "OK: dst6_max=%s", buf); @@ -1273,13 +1378,13 @@ static ssize_t pktgen_if_write(struct file *file, return -EFAULT; buf[len] = 0; - scan_ip6(buf, pkt_dev->in6_saddr.s6_addr); - fmt_ip6(buf, pkt_dev->in6_saddr.s6_addr); + in6_pton(buf, -1, pkt_dev->in6_saddr.s6_addr, -1, NULL); + snprintf(buf, sizeof(buf), "%pI6c", &pkt_dev->in6_saddr); - ipv6_addr_copy(&pkt_dev->cur_in6_saddr, &pkt_dev->in6_saddr); + pkt_dev->cur_in6_saddr = pkt_dev->in6_saddr; if (debug) - printk("pktgen: src6 set to: %s\n", buf); + pr_debug("src6 set to: %s\n", buf); i += len; sprintf(pg_result, "OK: src6=%s", buf); @@ -1287,9 +1392,9 @@ static ssize_t pktgen_if_write(struct file *file, } if (!strcmp(name, "src_min")) { len = strn_len(&user_buffer[i], sizeof(pkt_dev->src_min) - 1); - if (len < 0) { + if (len < 0) return len; - } + if (copy_from_user(buf, &user_buffer[i], len)) return -EFAULT; buf[len] = 0; @@ -1300,17 +1405,16 @@ static ssize_t pktgen_if_write(struct file *file, pkt_dev->cur_saddr = pkt_dev->saddr_min; } if (debug) - printk("pktgen: src_min set to: %s\n", - pkt_dev->src_min); + pr_debug("src_min set to: %s\n", pkt_dev->src_min); i += len; sprintf(pg_result, "OK: src_min=%s", pkt_dev->src_min); return count; } if (!strcmp(name, "src_max")) { len = strn_len(&user_buffer[i], sizeof(pkt_dev->src_max) - 1); - if (len < 0) { + if (len < 0) return len; - } + if (copy_from_user(buf, &user_buffer[i], len)) return -EFAULT; buf[len] = 0; @@ -1321,86 +1425,43 @@ static ssize_t pktgen_if_write(struct file *file, pkt_dev->cur_saddr = pkt_dev->saddr_max; } if (debug) - printk("pktgen: src_max set to: %s\n", - pkt_dev->src_max); + pr_debug("src_max set to: %s\n", pkt_dev->src_max); i += len; sprintf(pg_result, "OK: src_max=%s", pkt_dev->src_max); return count; } if (!strcmp(name, "dst_mac")) { - char *v = valstr; - unsigned char old_dmac[ETH_ALEN]; - unsigned char *m = pkt_dev->dst_mac; - memcpy(old_dmac, pkt_dev->dst_mac, ETH_ALEN); - len = strn_len(&user_buffer[i], sizeof(valstr) - 1); - if (len < 0) { + if (len < 0) return len; - } + memset(valstr, 0, sizeof(valstr)); if (copy_from_user(valstr, &user_buffer[i], len)) return -EFAULT; - i += len; - - for (*m = 0; *v && m < pkt_dev->dst_mac + 6; v++) { - if (*v >= '0' && *v <= '9') { - *m *= 16; - *m += *v - '0'; - } - if (*v >= 'A' && *v <= 'F') { - *m *= 16; - *m += *v - 'A' + 10; - } - if (*v >= 'a' && *v <= 'f') { - *m *= 16; - *m += *v - 'a' + 10; - } - if (*v == ':') { - m++; - *m = 0; - } - } + if (!mac_pton(valstr, pkt_dev->dst_mac)) + return -EINVAL; /* Set up Dest MAC */ - if (compare_ether_addr(old_dmac, pkt_dev->dst_mac)) - memcpy(&(pkt_dev->hh[0]), pkt_dev->dst_mac, ETH_ALEN); + ether_addr_copy(&pkt_dev->hh[0], pkt_dev->dst_mac); - sprintf(pg_result, "OK: dstmac"); + sprintf(pg_result, "OK: dstmac %pM", pkt_dev->dst_mac); return count; } if (!strcmp(name, "src_mac")) { - char *v = valstr; - unsigned char *m = pkt_dev->src_mac; - len = strn_len(&user_buffer[i], sizeof(valstr) - 1); - if (len < 0) { + if (len < 0) return len; - } + memset(valstr, 0, sizeof(valstr)); if (copy_from_user(valstr, &user_buffer[i], len)) return -EFAULT; - i += len; - for (*m = 0; *v && m < pkt_dev->src_mac + 6; v++) { - if (*v >= '0' && *v <= '9') { - *m *= 16; - *m += *v - '0'; - } - if (*v >= 'A' && *v <= 'F') { - *m *= 16; - *m += *v - 'A' + 10; - } - if (*v >= 'a' && *v <= 'f') { - *m *= 16; - *m += *v - 'a' + 10; - } - if (*v == ':') { - m++; - *m = 0; - } - } + if (!mac_pton(valstr, pkt_dev->src_mac)) + return -EINVAL; + /* Set up Src MAC */ + ether_addr_copy(&pkt_dev->hh[6], pkt_dev->src_mac); - sprintf(pg_result, "OK: srcmac"); + sprintf(pg_result, "OK: srcmac %pM", pkt_dev->src_mac); return count; } @@ -1412,9 +1473,9 @@ static ssize_t pktgen_if_write(struct file *file, if (!strcmp(name, "flows")) { len = num_arg(&user_buffer[i], 10, &value); - if (len < 0) { + if (len < 0) return len; - } + i += len; if (value > MAX_CFLOWS) value = MAX_CFLOWS; @@ -1423,28 +1484,229 @@ static ssize_t pktgen_if_write(struct file *file, sprintf(pg_result, "OK: flows=%u", pkt_dev->cflows); return count; } +#ifdef CONFIG_XFRM + if (!strcmp(name, "spi")) { + len = num_arg(&user_buffer[i], 10, &value); + if (len < 0) + return len; + i += len; + pkt_dev->spi = value; + sprintf(pg_result, "OK: spi=%u", pkt_dev->spi); + return count; + } +#endif if (!strcmp(name, "flowlen")) { len = num_arg(&user_buffer[i], 10, &value); - if (len < 0) { + if (len < 0) return len; - } + i += len; pkt_dev->lflow = value; sprintf(pg_result, "OK: flowlen=%u", pkt_dev->lflow); return count; } + if (!strcmp(name, "queue_map_min")) { + len = num_arg(&user_buffer[i], 5, &value); + if (len < 0) + return len; + + i += len; + pkt_dev->queue_map_min = value; + sprintf(pg_result, "OK: queue_map_min=%u", pkt_dev->queue_map_min); + return count; + } + + if (!strcmp(name, "queue_map_max")) { + len = num_arg(&user_buffer[i], 5, &value); + if (len < 0) + return len; + + i += len; + pkt_dev->queue_map_max = value; + sprintf(pg_result, "OK: queue_map_max=%u", pkt_dev->queue_map_max); + return count; + } + if (!strcmp(name, "mpls")) { - unsigned n, offset; + unsigned int n, cnt; + len = get_labels(&user_buffer[i], pkt_dev); - if (len < 0) { return len; } + if (len < 0) + return len; i += len; - offset = sprintf(pg_result, "OK: mpls="); - for(n = 0; n < pkt_dev->nr_labels; n++) - offset += sprintf(pg_result + offset, - "%08x%s", ntohl(pkt_dev->labels[n]), - n == pkt_dev->nr_labels-1 ? "" : ","); + cnt = sprintf(pg_result, "OK: mpls="); + for (n = 0; n < pkt_dev->nr_labels; n++) + cnt += sprintf(pg_result + cnt, + "%08x%s", ntohl(pkt_dev->labels[n]), + n == pkt_dev->nr_labels-1 ? "" : ","); + + if (pkt_dev->nr_labels && pkt_dev->vlan_id != 0xffff) { + pkt_dev->vlan_id = 0xffff; /* turn off VLAN/SVLAN */ + pkt_dev->svlan_id = 0xffff; + + if (debug) + pr_debug("VLAN/SVLAN auto turned off\n"); + } + return count; + } + + if (!strcmp(name, "vlan_id")) { + len = num_arg(&user_buffer[i], 4, &value); + if (len < 0) + return len; + + i += len; + if (value <= 4095) { + pkt_dev->vlan_id = value; /* turn on VLAN */ + + if (debug) + pr_debug("VLAN turned on\n"); + + if (debug && pkt_dev->nr_labels) + pr_debug("MPLS auto turned off\n"); + + pkt_dev->nr_labels = 0; /* turn off MPLS */ + sprintf(pg_result, "OK: vlan_id=%u", pkt_dev->vlan_id); + } else { + pkt_dev->vlan_id = 0xffff; /* turn off VLAN/SVLAN */ + pkt_dev->svlan_id = 0xffff; + + if (debug) + pr_debug("VLAN/SVLAN turned off\n"); + } + return count; + } + + if (!strcmp(name, "vlan_p")) { + len = num_arg(&user_buffer[i], 1, &value); + if (len < 0) + return len; + + i += len; + if ((value <= 7) && (pkt_dev->vlan_id != 0xffff)) { + pkt_dev->vlan_p = value; + sprintf(pg_result, "OK: vlan_p=%u", pkt_dev->vlan_p); + } else { + sprintf(pg_result, "ERROR: vlan_p must be 0-7"); + } + return count; + } + + if (!strcmp(name, "vlan_cfi")) { + len = num_arg(&user_buffer[i], 1, &value); + if (len < 0) + return len; + + i += len; + if ((value <= 1) && (pkt_dev->vlan_id != 0xffff)) { + pkt_dev->vlan_cfi = value; + sprintf(pg_result, "OK: vlan_cfi=%u", pkt_dev->vlan_cfi); + } else { + sprintf(pg_result, "ERROR: vlan_cfi must be 0-1"); + } + return count; + } + + if (!strcmp(name, "svlan_id")) { + len = num_arg(&user_buffer[i], 4, &value); + if (len < 0) + return len; + + i += len; + if ((value <= 4095) && ((pkt_dev->vlan_id != 0xffff))) { + pkt_dev->svlan_id = value; /* turn on SVLAN */ + + if (debug) + pr_debug("SVLAN turned on\n"); + + if (debug && pkt_dev->nr_labels) + pr_debug("MPLS auto turned off\n"); + + pkt_dev->nr_labels = 0; /* turn off MPLS */ + sprintf(pg_result, "OK: svlan_id=%u", pkt_dev->svlan_id); + } else { + pkt_dev->vlan_id = 0xffff; /* turn off VLAN/SVLAN */ + pkt_dev->svlan_id = 0xffff; + + if (debug) + pr_debug("VLAN/SVLAN turned off\n"); + } + return count; + } + + if (!strcmp(name, "svlan_p")) { + len = num_arg(&user_buffer[i], 1, &value); + if (len < 0) + return len; + + i += len; + if ((value <= 7) && (pkt_dev->svlan_id != 0xffff)) { + pkt_dev->svlan_p = value; + sprintf(pg_result, "OK: svlan_p=%u", pkt_dev->svlan_p); + } else { + sprintf(pg_result, "ERROR: svlan_p must be 0-7"); + } + return count; + } + + if (!strcmp(name, "svlan_cfi")) { + len = num_arg(&user_buffer[i], 1, &value); + if (len < 0) + return len; + + i += len; + if ((value <= 1) && (pkt_dev->svlan_id != 0xffff)) { + pkt_dev->svlan_cfi = value; + sprintf(pg_result, "OK: svlan_cfi=%u", pkt_dev->svlan_cfi); + } else { + sprintf(pg_result, "ERROR: svlan_cfi must be 0-1"); + } + return count; + } + + if (!strcmp(name, "tos")) { + __u32 tmp_value = 0; + len = hex32_arg(&user_buffer[i], 2, &tmp_value); + if (len < 0) + return len; + + i += len; + if (len == 2) { + pkt_dev->tos = tmp_value; + sprintf(pg_result, "OK: tos=0x%02x", pkt_dev->tos); + } else { + sprintf(pg_result, "ERROR: tos must be 00-ff"); + } + return count; + } + + if (!strcmp(name, "traffic_class")) { + __u32 tmp_value = 0; + len = hex32_arg(&user_buffer[i], 2, &tmp_value); + if (len < 0) + return len; + + i += len; + if (len == 2) { + pkt_dev->traffic_class = tmp_value; + sprintf(pg_result, "OK: traffic_class=0x%02x", pkt_dev->traffic_class); + } else { + sprintf(pg_result, "ERROR: traffic_class must be 00-ff"); + } + return count; + } + + if (!strcmp(name, "skb_priority")) { + len = num_arg(&user_buffer[i], 9, &value); + if (len < 0) + return len; + + i += len; + pkt_dev->skb_priority = value; + sprintf(pg_result, "OK: skb_priority=%i", + pkt_dev->skb_priority); return count; } @@ -1454,10 +1716,10 @@ static ssize_t pktgen_if_write(struct file *file, static int pktgen_if_open(struct inode *inode, struct file *file) { - return single_open(file, pktgen_if_show, PDE(inode)->data); + return single_open(file, pktgen_if_show, PDE_DATA(inode)); } -static struct file_operations pktgen_if_fops = { +static const struct file_operations pktgen_if_fops = { .owner = THIS_MODULE, .open = pktgen_if_open, .read = seq_read, @@ -1469,30 +1731,27 @@ static struct file_operations pktgen_if_fops = { static int pktgen_thread_show(struct seq_file *seq, void *v) { struct pktgen_thread *t = seq->private; - struct pktgen_dev *pkt_dev; + const struct pktgen_dev *pkt_dev; BUG_ON(!t); - seq_printf(seq, "Name: %s max_before_softirq: %d\n", - t->name, t->max_before_softirq); - - seq_printf(seq, "Running: "); + seq_puts(seq, "Running: "); if_lock(t); list_for_each_entry(pkt_dev, &t->if_list, list) if (pkt_dev->running) - seq_printf(seq, "%s ", pkt_dev->ifname); + seq_printf(seq, "%s ", pkt_dev->odevname); - seq_printf(seq, "\nStopped: "); + seq_puts(seq, "\nStopped: "); list_for_each_entry(pkt_dev, &t->if_list, list) if (!pkt_dev->running) - seq_printf(seq, "%s ", pkt_dev->ifname); + seq_printf(seq, "%s ", pkt_dev->odevname); if (t->result[0]) seq_printf(seq, "\nResult: %s\n", t->result); else - seq_printf(seq, "\nResult: NA\n"); + seq_puts(seq, "\nResult: NA\n"); if_unlock(t); @@ -1503,24 +1762,23 @@ static ssize_t pktgen_thread_write(struct file *file, const char __user * user_buffer, size_t count, loff_t * offset) { - struct seq_file *seq = (struct seq_file *)file->private_data; + struct seq_file *seq = file->private_data; struct pktgen_thread *t = seq->private; - int i = 0, max, len, ret; + int i, max, len, ret; char name[40]; char *pg_result; - unsigned long value = 0; if (count < 1) { // sprintf(pg_result, "Wrong command format"); return -EINVAL; } - max = count - i; - len = count_trail_chars(&user_buffer[i], max); + max = count; + len = count_trail_chars(user_buffer, max); if (len < 0) return len; - i += len; + i = len; /* Read variable name */ @@ -1541,10 +1799,10 @@ static ssize_t pktgen_thread_write(struct file *file, i += len; if (debug) - printk("pktgen: t=%s, count=%lu\n", name, (unsigned long)count); + pr_debug("t=%s, count=%lu\n", name, (unsigned long)count); if (!t) { - printk("pktgen: ERROR: No thread\n"); + pr_err("ERROR: No thread\n"); ret = -EINVAL; goto out; } @@ -1563,10 +1821,13 @@ static ssize_t pktgen_thread_write(struct file *file, return -EFAULT; i += len; mutex_lock(&pktgen_thread_lock); - pktgen_add_device(t, f); + ret = pktgen_add_device(t, f); mutex_unlock(&pktgen_thread_lock); - ret = count; - sprintf(pg_result, "OK: add_device=%s", f); + if (!ret) { + ret = count; + sprintf(pg_result, "OK: add_device=%s", f); + } else + sprintf(pg_result, "ERROR: can not add device %s", f); goto out; } @@ -1581,12 +1842,8 @@ static ssize_t pktgen_thread_write(struct file *file, } if (!strcmp(name, "max_before_softirq")) { - len = num_arg(&user_buffer[i], 10, &value); - mutex_lock(&pktgen_thread_lock); - t->max_before_softirq = value; - mutex_unlock(&pktgen_thread_lock); + sprintf(pg_result, "OK: Note! max_before_softirq is obsoleted -- Do not use"); ret = count; - sprintf(pg_result, "OK: max_before_softirq=%lu", value); goto out; } @@ -1597,10 +1854,10 @@ out: static int pktgen_thread_open(struct inode *inode, struct file *file) { - return single_open(file, pktgen_thread_show, PDE(inode)->data); + return single_open(file, pktgen_thread_show, PDE_DATA(inode)); } -static struct file_operations pktgen_thread_fops = { +static const struct file_operations pktgen_thread_fops = { .owner = THIS_MODULE, .open = pktgen_thread_open, .read = seq_read, @@ -1610,13 +1867,15 @@ static struct file_operations pktgen_thread_fops = { }; /* Think find or remove for NN */ -static struct pktgen_dev *__pktgen_NN_threads(const char *ifname, int remove) +static struct pktgen_dev *__pktgen_NN_threads(const struct pktgen_net *pn, + const char *ifname, int remove) { struct pktgen_thread *t; struct pktgen_dev *pkt_dev = NULL; + bool exact = (remove == FIND); - list_for_each_entry(t, &pktgen_threads, th_list) { - pkt_dev = pktgen_find_dev(t, ifname); + list_for_each_entry(t, &pn->pktgen_threads, th_list) { + pkt_dev = pktgen_find_dev(t, ifname, exact); if (pkt_dev) { if (remove) { if_lock(t); @@ -1633,106 +1892,141 @@ static struct pktgen_dev *__pktgen_NN_threads(const char *ifname, int remove) /* * mark a device for removal */ -static int pktgen_mark_device(const char *ifname) +static void pktgen_mark_device(const struct pktgen_net *pn, const char *ifname) { struct pktgen_dev *pkt_dev = NULL; const int max_tries = 10, msec_per_try = 125; int i = 0; - int ret = 0; mutex_lock(&pktgen_thread_lock); - PG_DEBUG(printk("pktgen: pktgen_mark_device marking %s for removal\n", - ifname)); + pr_debug("%s: marking %s for removal\n", __func__, ifname); while (1) { - pkt_dev = __pktgen_NN_threads(ifname, REMOVE); + pkt_dev = __pktgen_NN_threads(pn, ifname, REMOVE); if (pkt_dev == NULL) break; /* success */ mutex_unlock(&pktgen_thread_lock); - PG_DEBUG(printk("pktgen: pktgen_mark_device waiting for %s " - "to disappear....\n", ifname)); + pr_debug("%s: waiting for %s to disappear....\n", + __func__, ifname); schedule_timeout_interruptible(msecs_to_jiffies(msec_per_try)); mutex_lock(&pktgen_thread_lock); if (++i >= max_tries) { - printk("pktgen_mark_device: timed out after waiting " - "%d msec for device %s to be removed\n", - msec_per_try * i, ifname); - ret = 1; + pr_err("%s: timed out after waiting %d msec for device %s to be removed\n", + __func__, msec_per_try * i, ifname); break; } } mutex_unlock(&pktgen_thread_lock); +} - return ret; +static void pktgen_change_name(const struct pktgen_net *pn, struct net_device *dev) +{ + struct pktgen_thread *t; + + list_for_each_entry(t, &pn->pktgen_threads, th_list) { + struct pktgen_dev *pkt_dev; + + list_for_each_entry(pkt_dev, &t->if_list, list) { + if (pkt_dev->odev != dev) + continue; + + proc_remove(pkt_dev->entry); + + pkt_dev->entry = proc_create_data(dev->name, 0600, + pn->proc_dir, + &pktgen_if_fops, + pkt_dev); + if (!pkt_dev->entry) + pr_err("can't move proc entry for '%s'\n", + dev->name); + break; + } + } } static int pktgen_device_event(struct notifier_block *unused, unsigned long event, void *ptr) { - struct net_device *dev = (struct net_device *)(ptr); + struct net_device *dev = netdev_notifier_info_to_dev(ptr); + struct pktgen_net *pn = net_generic(dev_net(dev), pg_net_id); + + if (pn->pktgen_exiting) + return NOTIFY_DONE; /* It is OK that we do not hold the group lock right now, * as we run under the RTNL lock. */ switch (event) { - case NETDEV_CHANGEADDR: - case NETDEV_GOING_DOWN: - case NETDEV_DOWN: - case NETDEV_UP: - /* Ignore for now */ + case NETDEV_CHANGENAME: + pktgen_change_name(pn, dev); break; case NETDEV_UNREGISTER: - pktgen_mark_device(dev->name); + pktgen_mark_device(pn, dev->name); break; - }; + } return NOTIFY_DONE; } +static struct net_device *pktgen_dev_get_by_name(const struct pktgen_net *pn, + struct pktgen_dev *pkt_dev, + const char *ifname) +{ + char b[IFNAMSIZ+5]; + int i; + + for (i = 0; ifname[i] != '@'; i++) { + if (i == IFNAMSIZ) + break; + + b[i] = ifname[i]; + } + b[i] = 0; + + return dev_get_by_name(pn->net, b); +} + + /* Associate pktgen_dev with a device. */ -static struct net_device *pktgen_setup_dev(struct pktgen_dev *pkt_dev) +static int pktgen_setup_dev(const struct pktgen_net *pn, + struct pktgen_dev *pkt_dev, const char *ifname) { struct net_device *odev; + int err; /* Clean old setups */ - if (pkt_dev->odev) { dev_put(pkt_dev->odev); pkt_dev->odev = NULL; } - odev = dev_get_by_name(pkt_dev->ifname); - + odev = pktgen_dev_get_by_name(pn, pkt_dev, ifname); if (!odev) { - printk("pktgen: no such netdevice: \"%s\"\n", pkt_dev->ifname); - goto out; + pr_err("no such netdevice: \"%s\"\n", ifname); + return -ENODEV; } + if (odev->type != ARPHRD_ETHER) { - printk("pktgen: not an ethernet device: \"%s\"\n", - pkt_dev->ifname); - goto out_put; - } - if (!netif_running(odev)) { - printk("pktgen: device is down: \"%s\"\n", pkt_dev->ifname); - goto out_put; + pr_err("not an ethernet device: \"%s\"\n", ifname); + err = -EINVAL; + } else if (!netif_running(odev)) { + pr_err("device is down: \"%s\"\n", ifname); + err = -ENETDOWN; + } else { + pkt_dev->odev = odev; + return 0; } - pkt_dev->odev = odev; - return pkt_dev->odev; - -out_put: dev_put(odev); -out: - return NULL; - + return err; } /* Read pkt_dev from the interface and set up internal pktgen_dev @@ -1740,38 +2034,50 @@ out: */ static void pktgen_setup_inject(struct pktgen_dev *pkt_dev) { - /* Try once more, just in case it works now. */ - if (!pkt_dev->odev) - pktgen_setup_dev(pkt_dev); + int ntxq; if (!pkt_dev->odev) { - printk("pktgen: ERROR: pkt_dev->odev == NULL in setup_inject.\n"); + pr_err("ERROR: pkt_dev->odev == NULL in setup_inject\n"); sprintf(pkt_dev->result, "ERROR: pkt_dev->odev == NULL in setup_inject.\n"); return; } + /* make sure that we don't pick a non-existing transmit queue */ + ntxq = pkt_dev->odev->real_num_tx_queues; + + if (ntxq <= pkt_dev->queue_map_min) { + pr_warning("WARNING: Requested queue_map_min (zero-based) (%d) exceeds valid range [0 - %d] for (%d) queues on %s, resetting\n", + pkt_dev->queue_map_min, (ntxq ?: 1) - 1, ntxq, + pkt_dev->odevname); + pkt_dev->queue_map_min = (ntxq ?: 1) - 1; + } + if (pkt_dev->queue_map_max >= ntxq) { + pr_warning("WARNING: Requested queue_map_max (zero-based) (%d) exceeds valid range [0 - %d] for (%d) queues on %s, resetting\n", + pkt_dev->queue_map_max, (ntxq ?: 1) - 1, ntxq, + pkt_dev->odevname); + pkt_dev->queue_map_max = (ntxq ?: 1) - 1; + } + /* Default to the interface's mac if not explicitly set. */ if (is_zero_ether_addr(pkt_dev->src_mac)) - memcpy(&(pkt_dev->hh[6]), pkt_dev->odev->dev_addr, ETH_ALEN); + ether_addr_copy(&(pkt_dev->hh[6]), pkt_dev->odev->dev_addr); /* Set up Dest MAC */ - memcpy(&(pkt_dev->hh[0]), pkt_dev->dst_mac, ETH_ALEN); - - /* Set up pkt size */ - pkt_dev->cur_pkt_size = pkt_dev->min_pkt_size; + ether_addr_copy(&(pkt_dev->hh[0]), pkt_dev->dst_mac); if (pkt_dev->flags & F_IPV6) { - /* - * Skip this automatic address setting until locks or functions - * gets exported - */ - -#ifdef NOTNOW int i, set = 0, err = 1; struct inet6_dev *idev; + if (pkt_dev->min_pkt_size == 0) { + pkt_dev->min_pkt_size = 14 + sizeof(struct ipv6hdr) + + sizeof(struct udphdr) + + sizeof(struct pktgen_hdr) + + pkt_dev->pkt_overhead; + } + for (i = 0; i < IN6_ADDR_HSIZE; i++) if (pkt_dev->cur_in6_saddr.s6_addr[i]) { set = 1; @@ -1786,31 +2092,34 @@ static void pktgen_setup_inject(struct pktgen_dev *pkt_dev) * use ipv6_get_lladdr if/when it's get exported */ - read_lock(&addrconf_lock); - if ((idev = __in6_dev_get(pkt_dev->odev)) != NULL) { + rcu_read_lock(); + idev = __in6_dev_get(pkt_dev->odev); + if (idev) { struct inet6_ifaddr *ifp; read_lock_bh(&idev->lock); - for (ifp = idev->addr_list; ifp; - ifp = ifp->if_next) { - if (ifp->scope == IFA_LINK - && !(ifp-> - flags & IFA_F_TENTATIVE)) { - ipv6_addr_copy(&pkt_dev-> - cur_in6_saddr, - &ifp->addr); + list_for_each_entry(ifp, &idev->addr_list, if_list) { + if ((ifp->scope & IFA_LINK) && + !(ifp->flags & IFA_F_TENTATIVE)) { + pkt_dev->cur_in6_saddr = ifp->addr; err = 0; break; } } read_unlock_bh(&idev->lock); } - read_unlock(&addrconf_lock); + rcu_read_unlock(); if (err) - printk("pktgen: ERROR: IPv6 link address not availble.\n"); + pr_err("ERROR: IPv6 link address not available\n"); } -#endif } else { + if (pkt_dev->min_pkt_size == 0) { + pkt_dev->min_pkt_size = 14 + sizeof(struct iphdr) + + sizeof(struct udphdr) + + sizeof(struct pktgen_hdr) + + pkt_dev->pkt_overhead; + } + pkt_dev->saddr_min = 0; pkt_dev->saddr_max = 0; if (strlen(pkt_dev->src_min) == 0) { @@ -1836,6 +2145,10 @@ static void pktgen_setup_inject(struct pktgen_dev *pkt_dev) pkt_dev->daddr_max = in_aton(pkt_dev->dst_max); } /* Initialize current values. */ + pkt_dev->cur_pkt_size = pkt_dev->min_pkt_size; + if (pkt_dev->min_pkt_size > pkt_dev->max_pkt_size) + pkt_dev->max_pkt_size = pkt_dev->min_pkt_size; + pkt_dev->cur_dst_mac_offset = 0; pkt_dev->cur_src_mac_offset = 0; pkt_dev->cur_saddr = pkt_dev->saddr_min; @@ -1845,29 +2158,145 @@ static void pktgen_setup_inject(struct pktgen_dev *pkt_dev) pkt_dev->nflows = 0; } -static void spin(struct pktgen_dev *pkt_dev, __u64 spin_until_us) + +static void spin(struct pktgen_dev *pkt_dev, ktime_t spin_until) { - __u64 start; - __u64 now; + ktime_t start_time, end_time; + s64 remaining; + struct hrtimer_sleeper t; - start = now = getCurUs(); - printk(KERN_INFO "sleeping for %d\n", (int)(spin_until_us - now)); - while (now < spin_until_us) { - /* TODO: optimize sleeping behavior */ - if (spin_until_us - now > jiffies_to_usecs(1) + 1) - schedule_timeout_interruptible(1); - else if (spin_until_us - now > 100) { - do_softirq(); - if (!pkt_dev->running) - return; - if (need_resched()) + hrtimer_init_on_stack(&t.timer, CLOCK_MONOTONIC, HRTIMER_MODE_ABS); + hrtimer_set_expires(&t.timer, spin_until); + + remaining = ktime_to_ns(hrtimer_expires_remaining(&t.timer)); + if (remaining <= 0) { + pkt_dev->next_tx = ktime_add_ns(spin_until, pkt_dev->delay); + return; + } + + start_time = ktime_get(); + if (remaining < 100000) { + /* for small delays (<100us), just loop until limit is reached */ + do { + end_time = ktime_get(); + } while (ktime_compare(end_time, spin_until) < 0); + } else { + /* see do_nanosleep */ + hrtimer_init_sleeper(&t, current); + do { + set_current_state(TASK_INTERRUPTIBLE); + hrtimer_start_expires(&t.timer, HRTIMER_MODE_ABS); + if (!hrtimer_active(&t.timer)) + t.task = NULL; + + if (likely(t.task)) schedule(); + + hrtimer_cancel(&t.timer); + } while (t.task && pkt_dev->running && !signal_pending(current)); + __set_current_state(TASK_RUNNING); + end_time = ktime_get(); + } + + pkt_dev->idle_acc += ktime_to_ns(ktime_sub(end_time, start_time)); + pkt_dev->next_tx = ktime_add_ns(spin_until, pkt_dev->delay); +} + +static inline void set_pkt_overhead(struct pktgen_dev *pkt_dev) +{ + pkt_dev->pkt_overhead = 0; + pkt_dev->pkt_overhead += pkt_dev->nr_labels*sizeof(u32); + pkt_dev->pkt_overhead += VLAN_TAG_SIZE(pkt_dev); + pkt_dev->pkt_overhead += SVLAN_TAG_SIZE(pkt_dev); +} + +static inline int f_seen(const struct pktgen_dev *pkt_dev, int flow) +{ + return !!(pkt_dev->flows[flow].flags & F_INIT); +} + +static inline int f_pick(struct pktgen_dev *pkt_dev) +{ + int flow = pkt_dev->curfl; + + if (pkt_dev->flags & F_FLOW_SEQ) { + if (pkt_dev->flows[flow].count >= pkt_dev->lflow) { + /* reset time */ + pkt_dev->flows[flow].count = 0; + pkt_dev->flows[flow].flags = 0; + pkt_dev->curfl += 1; + if (pkt_dev->curfl >= pkt_dev->cflows) + pkt_dev->curfl = 0; /*reset */ } + } else { + flow = prandom_u32() % pkt_dev->cflows; + pkt_dev->curfl = flow; - now = getCurUs(); + if (pkt_dev->flows[flow].count > pkt_dev->lflow) { + pkt_dev->flows[flow].count = 0; + pkt_dev->flows[flow].flags = 0; + } } - pkt_dev->idle_acc += now - start; + return pkt_dev->curfl; +} + + +#ifdef CONFIG_XFRM +/* If there was already an IPSEC SA, we keep it as is, else + * we go look for it ... +*/ +#define DUMMY_MARK 0 +static void get_ipsec_sa(struct pktgen_dev *pkt_dev, int flow) +{ + struct xfrm_state *x = pkt_dev->flows[flow].x; + struct pktgen_net *pn = net_generic(dev_net(pkt_dev->odev), pg_net_id); + if (!x) { + + if (pkt_dev->spi) { + /* We need as quick as possible to find the right SA + * Searching with minimum criteria to archieve this. + */ + x = xfrm_state_lookup_byspi(pn->net, htonl(pkt_dev->spi), AF_INET); + } else { + /* slow path: we dont already have xfrm_state */ + x = xfrm_stateonly_find(pn->net, DUMMY_MARK, + (xfrm_address_t *)&pkt_dev->cur_daddr, + (xfrm_address_t *)&pkt_dev->cur_saddr, + AF_INET, + pkt_dev->ipsmode, + pkt_dev->ipsproto, 0); + } + if (x) { + pkt_dev->flows[flow].x = x; + set_pkt_overhead(pkt_dev); + pkt_dev->pkt_overhead += x->props.header_len; + } + + } +} +#endif +static void set_cur_queue_map(struct pktgen_dev *pkt_dev) +{ + + if (pkt_dev->flags & F_QUEUE_MAP_CPU) + pkt_dev->cur_queue_map = smp_processor_id(); + + else if (pkt_dev->queue_map_min <= pkt_dev->queue_map_max) { + __u16 t; + if (pkt_dev->flags & F_QUEUE_MAP_RND) { + t = prandom_u32() % + (pkt_dev->queue_map_max - + pkt_dev->queue_map_min + 1) + + pkt_dev->queue_map_min; + } else { + t = pkt_dev->cur_queue_map + 1; + if (t > pkt_dev->queue_map_max) + t = pkt_dev->queue_map_min; + } + pkt_dev->cur_queue_map = t; + } + pkt_dev->cur_queue_map = pkt_dev->cur_queue_map % pkt_dev->odev->real_num_tx_queues; } /* Increment/randomize headers according to flags and current values @@ -1879,12 +2308,8 @@ static void mod_cur_headers(struct pktgen_dev *pkt_dev) __u32 imx; int flow = 0; - if (pkt_dev->cflows) { - flow = pktgen_random() % pkt_dev->cflows; - - if (pkt_dev->flows[flow].count > pkt_dev->lflow) - pkt_dev->flows[flow].count = 0; - } + if (pkt_dev->cflows) + flow = f_pick(pkt_dev); /* Deal with source MAC */ if (pkt_dev->src_mac_count > 1) { @@ -1892,10 +2317,10 @@ static void mod_cur_headers(struct pktgen_dev *pkt_dev) __u32 tmp; if (pkt_dev->flags & F_MACSRC_RND) - mc = pktgen_random() % (pkt_dev->src_mac_count); + mc = prandom_u32() % pkt_dev->src_mac_count; else { mc = pkt_dev->cur_src_mac_offset++; - if (pkt_dev->cur_src_mac_offset > + if (pkt_dev->cur_src_mac_offset >= pkt_dev->src_mac_count) pkt_dev->cur_src_mac_offset = 0; } @@ -1918,11 +2343,11 @@ static void mod_cur_headers(struct pktgen_dev *pkt_dev) __u32 tmp; if (pkt_dev->flags & F_MACDST_RND) - mc = pktgen_random() % (pkt_dev->dst_mac_count); + mc = prandom_u32() % pkt_dev->dst_mac_count; else { mc = pkt_dev->cur_dst_mac_offset++; - if (pkt_dev->cur_dst_mac_offset > + if (pkt_dev->cur_dst_mac_offset >= pkt_dev->dst_mac_count) { pkt_dev->cur_dst_mac_offset = 0; } @@ -1941,20 +2366,27 @@ static void mod_cur_headers(struct pktgen_dev *pkt_dev) } if (pkt_dev->flags & F_MPLS_RND) { - unsigned i; - for(i = 0; i < pkt_dev->nr_labels; i++) + unsigned int i; + for (i = 0; i < pkt_dev->nr_labels; i++) if (pkt_dev->labels[i] & MPLS_STACK_BOTTOM) pkt_dev->labels[i] = MPLS_STACK_BOTTOM | - (pktgen_random() & + ((__force __be32)prandom_u32() & htonl(0x000fffff)); } + if ((pkt_dev->flags & F_VID_RND) && (pkt_dev->vlan_id != 0xffff)) { + pkt_dev->vlan_id = prandom_u32() & (4096 - 1); + } + + if ((pkt_dev->flags & F_SVID_RND) && (pkt_dev->svlan_id != 0xffff)) { + pkt_dev->svlan_id = prandom_u32() & (4096 - 1); + } + if (pkt_dev->udp_src_min < pkt_dev->udp_src_max) { if (pkt_dev->flags & F_UDPSRC_RND) - pkt_dev->cur_udp_src = - ((pktgen_random() % - (pkt_dev->udp_src_max - pkt_dev->udp_src_min)) + - pkt_dev->udp_src_min); + pkt_dev->cur_udp_src = prandom_u32() % + (pkt_dev->udp_src_max - pkt_dev->udp_src_min) + + pkt_dev->udp_src_min; else { pkt_dev->cur_udp_src++; @@ -1965,10 +2397,9 @@ static void mod_cur_headers(struct pktgen_dev *pkt_dev) if (pkt_dev->udp_dst_min < pkt_dev->udp_dst_max) { if (pkt_dev->flags & F_UDPDST_RND) { - pkt_dev->cur_udp_dst = - ((pktgen_random() % - (pkt_dev->udp_dst_max - pkt_dev->udp_dst_min)) + - pkt_dev->udp_dst_min); + pkt_dev->cur_udp_dst = prandom_u32() % + (pkt_dev->udp_dst_max - pkt_dev->udp_dst_min) + + pkt_dev->udp_dst_min; } else { pkt_dev->cur_udp_dst++; if (pkt_dev->cur_udp_dst >= pkt_dev->udp_dst_max) @@ -1978,48 +2409,43 @@ static void mod_cur_headers(struct pktgen_dev *pkt_dev) if (!(pkt_dev->flags & F_IPV6)) { - if ((imn = ntohl(pkt_dev->saddr_min)) < (imx = - ntohl(pkt_dev-> - saddr_max))) { + imn = ntohl(pkt_dev->saddr_min); + imx = ntohl(pkt_dev->saddr_max); + if (imn < imx) { __u32 t; if (pkt_dev->flags & F_IPSRC_RND) - t = ((pktgen_random() % (imx - imn)) + imn); + t = prandom_u32() % (imx - imn) + imn; else { t = ntohl(pkt_dev->cur_saddr); t++; - if (t > imx) { + if (t > imx) t = imn; - } + } pkt_dev->cur_saddr = htonl(t); } - if (pkt_dev->cflows && pkt_dev->flows[flow].count != 0) { + if (pkt_dev->cflows && f_seen(pkt_dev, flow)) { pkt_dev->cur_daddr = pkt_dev->flows[flow].cur_daddr; } else { - - if ((imn = ntohl(pkt_dev->daddr_min)) < (imx = - ntohl(pkt_dev-> - daddr_max))) - { + imn = ntohl(pkt_dev->daddr_min); + imx = ntohl(pkt_dev->daddr_max); + if (imn < imx) { __u32 t; + __be32 s; if (pkt_dev->flags & F_IPDST_RND) { - t = ((pktgen_random() % (imx - imn)) + - imn); - t = htonl(t); - - while (LOOPBACK(t) || MULTICAST(t) - || BADCLASS(t) || ZERONET(t) - || LOCAL_MCAST(t)) { - t = ((pktgen_random() % - (imx - imn)) + imn); - t = htonl(t); - } - pkt_dev->cur_daddr = t; - } - - else { + do { + t = prandom_u32() % + (imx - imn) + imn; + s = htonl(t); + } while (ipv4_is_loopback(s) || + ipv4_is_multicast(s) || + ipv4_is_lbcast(s) || + ipv4_is_zeronet(s) || + ipv4_is_local_multicast(s)); + pkt_dev->cur_daddr = s; + } else { t = ntohl(pkt_dev->cur_daddr); t++; if (t > imx) { @@ -2029,25 +2455,26 @@ static void mod_cur_headers(struct pktgen_dev *pkt_dev) } } if (pkt_dev->cflows) { + pkt_dev->flows[flow].flags |= F_INIT; pkt_dev->flows[flow].cur_daddr = pkt_dev->cur_daddr; +#ifdef CONFIG_XFRM + if (pkt_dev->flags & F_IPSEC_ON) + get_ipsec_sa(pkt_dev, flow); +#endif pkt_dev->nflows++; } } } else { /* IPV6 * */ - if (pkt_dev->min_in6_daddr.s6_addr32[0] == 0 && - pkt_dev->min_in6_daddr.s6_addr32[1] == 0 && - pkt_dev->min_in6_daddr.s6_addr32[2] == 0 && - pkt_dev->min_in6_daddr.s6_addr32[3] == 0) ; - else { + if (!ipv6_addr_any(&pkt_dev->min_in6_daddr)) { int i; /* Only random destinations yet */ for (i = 0; i < 4; i++) { pkt_dev->cur_in6_daddr.s6_addr32[i] = - ((pktgen_random() | + (((__force __be32)prandom_u32() | pkt_dev->min_in6_daddr.s6_addr32[i]) & pkt_dev->max_in6_daddr.s6_addr32[i]); } @@ -2057,9 +2484,9 @@ static void mod_cur_headers(struct pktgen_dev *pkt_dev) if (pkt_dev->min_pkt_size < pkt_dev->max_pkt_size) { __u32 t; if (pkt_dev->flags & F_TXSIZE_RND) { - t = ((pktgen_random() % - (pkt_dev->max_pkt_size - pkt_dev->min_pkt_size)) - + pkt_dev->min_pkt_size); + t = prandom_u32() % + (pkt_dev->max_pkt_size - pkt_dev->min_pkt_size) + + pkt_dev->min_pkt_size; } else { t = pkt_dev->cur_pkt_size + 1; if (t > pkt_dev->max_pkt_size) @@ -2068,19 +2495,223 @@ static void mod_cur_headers(struct pktgen_dev *pkt_dev) pkt_dev->cur_pkt_size = t; } + set_cur_queue_map(pkt_dev); + pkt_dev->flows[flow].count++; } + +#ifdef CONFIG_XFRM +static u32 pktgen_dst_metrics[RTAX_MAX + 1] = { + + [RTAX_HOPLIMIT] = 0x5, /* Set a static hoplimit */ +}; + +static int pktgen_output_ipsec(struct sk_buff *skb, struct pktgen_dev *pkt_dev) +{ + struct xfrm_state *x = pkt_dev->flows[pkt_dev->curfl].x; + int err = 0; + struct net *net = dev_net(pkt_dev->odev); + + if (!x) + return 0; + /* XXX: we dont support tunnel mode for now until + * we resolve the dst issue */ + if ((x->props.mode != XFRM_MODE_TRANSPORT) && (pkt_dev->spi == 0)) + return 0; + + /* But when user specify an valid SPI, transformation + * supports both transport/tunnel mode + ESP/AH type. + */ + if ((x->props.mode == XFRM_MODE_TUNNEL) && (pkt_dev->spi != 0)) + skb->_skb_refdst = (unsigned long)&pkt_dev->dst | SKB_DST_NOREF; + + rcu_read_lock_bh(); + err = x->outer_mode->output(x, skb); + rcu_read_unlock_bh(); + if (err) { + XFRM_INC_STATS(net, LINUX_MIB_XFRMOUTSTATEMODEERROR); + goto error; + } + err = x->type->output(x, skb); + if (err) { + XFRM_INC_STATS(net, LINUX_MIB_XFRMOUTSTATEPROTOERROR); + goto error; + } + spin_lock_bh(&x->lock); + x->curlft.bytes += skb->len; + x->curlft.packets++; + spin_unlock_bh(&x->lock); +error: + return err; +} + +static void free_SAs(struct pktgen_dev *pkt_dev) +{ + if (pkt_dev->cflows) { + /* let go of the SAs if we have them */ + int i; + for (i = 0; i < pkt_dev->cflows; i++) { + struct xfrm_state *x = pkt_dev->flows[i].x; + if (x) { + xfrm_state_put(x); + pkt_dev->flows[i].x = NULL; + } + } + } +} + +static int process_ipsec(struct pktgen_dev *pkt_dev, + struct sk_buff *skb, __be16 protocol) +{ + if (pkt_dev->flags & F_IPSEC_ON) { + struct xfrm_state *x = pkt_dev->flows[pkt_dev->curfl].x; + int nhead = 0; + if (x) { + int ret; + __u8 *eth; + struct iphdr *iph; + + nhead = x->props.header_len - skb_headroom(skb); + if (nhead > 0) { + ret = pskb_expand_head(skb, nhead, 0, GFP_ATOMIC); + if (ret < 0) { + pr_err("Error expanding ipsec packet %d\n", + ret); + goto err; + } + } + + /* ipsec is not expecting ll header */ + skb_pull(skb, ETH_HLEN); + ret = pktgen_output_ipsec(skb, pkt_dev); + if (ret) { + pr_err("Error creating ipsec packet %d\n", ret); + goto err; + } + /* restore ll */ + eth = (__u8 *) skb_push(skb, ETH_HLEN); + memcpy(eth, pkt_dev->hh, 12); + *(u16 *) ð[12] = protocol; + + /* Update IPv4 header len as well as checksum value */ + iph = ip_hdr(skb); + iph->tot_len = htons(skb->len - ETH_HLEN); + ip_send_check(iph); + } + } + return 1; +err: + kfree_skb(skb); + return 0; +} +#endif + static void mpls_push(__be32 *mpls, struct pktgen_dev *pkt_dev) { - unsigned i; - for(i = 0; i < pkt_dev->nr_labels; i++) { + unsigned int i; + for (i = 0; i < pkt_dev->nr_labels; i++) *mpls++ = pkt_dev->labels[i] & ~MPLS_STACK_BOTTOM; - } + mpls--; *mpls |= MPLS_STACK_BOTTOM; } +static inline __be16 build_tci(unsigned int id, unsigned int cfi, + unsigned int prio) +{ + return htons(id | (cfi << 12) | (prio << 13)); +} + +static void pktgen_finalize_skb(struct pktgen_dev *pkt_dev, struct sk_buff *skb, + int datalen) +{ + struct timeval timestamp; + struct pktgen_hdr *pgh; + + pgh = (struct pktgen_hdr *)skb_put(skb, sizeof(*pgh)); + datalen -= sizeof(*pgh); + + if (pkt_dev->nfrags <= 0) { + memset(skb_put(skb, datalen), 0, datalen); + } else { + int frags = pkt_dev->nfrags; + int i, len; + int frag_len; + + + if (frags > MAX_SKB_FRAGS) + frags = MAX_SKB_FRAGS; + len = datalen - frags * PAGE_SIZE; + if (len > 0) { + memset(skb_put(skb, len), 0, len); + datalen = frags * PAGE_SIZE; + } + + i = 0; + frag_len = (datalen/frags) < PAGE_SIZE ? + (datalen/frags) : PAGE_SIZE; + while (datalen > 0) { + if (unlikely(!pkt_dev->page)) { + int node = numa_node_id(); + + if (pkt_dev->node >= 0 && (pkt_dev->flags & F_NODE)) + node = pkt_dev->node; + pkt_dev->page = alloc_pages_node(node, GFP_KERNEL | __GFP_ZERO, 0); + if (!pkt_dev->page) + break; + } + get_page(pkt_dev->page); + skb_frag_set_page(skb, i, pkt_dev->page); + skb_shinfo(skb)->frags[i].page_offset = 0; + /*last fragment, fill rest of data*/ + if (i == (frags - 1)) + skb_frag_size_set(&skb_shinfo(skb)->frags[i], + (datalen < PAGE_SIZE ? datalen : PAGE_SIZE)); + else + skb_frag_size_set(&skb_shinfo(skb)->frags[i], frag_len); + datalen -= skb_frag_size(&skb_shinfo(skb)->frags[i]); + skb->len += skb_frag_size(&skb_shinfo(skb)->frags[i]); + skb->data_len += skb_frag_size(&skb_shinfo(skb)->frags[i]); + i++; + skb_shinfo(skb)->nr_frags = i; + } + } + + /* Stamp the time, and sequence number, + * convert them to network byte order + */ + pgh->pgh_magic = htonl(PKTGEN_MAGIC); + pgh->seq_num = htonl(pkt_dev->seq_num); + + do_gettimeofday(×tamp); + pgh->tv_sec = htonl(timestamp.tv_sec); + pgh->tv_usec = htonl(timestamp.tv_usec); +} + +static struct sk_buff *pktgen_alloc_skb(struct net_device *dev, + struct pktgen_dev *pkt_dev, + unsigned int extralen) +{ + struct sk_buff *skb = NULL; + unsigned int size = pkt_dev->cur_pkt_size + 64 + extralen + + pkt_dev->pkt_overhead; + + if (pkt_dev->flags & F_NODE) { + int node = pkt_dev->node >= 0 ? pkt_dev->node : numa_node_id(); + + skb = __alloc_skb(NET_SKB_PAD + size, GFP_NOWAIT, 0, node); + if (likely(skb)) { + skb_reserve(skb, NET_SKB_PAD); + skb->dev = dev; + } + } else { + skb = __netdev_alloc_skb(dev, size, GFP_NOWAIT); + } + + return skb; +} + static struct sk_buff *fill_packet_ipv4(struct net_device *odev, struct pktgen_dev *pkt_dev) { @@ -2089,26 +2720,35 @@ static struct sk_buff *fill_packet_ipv4(struct net_device *odev, struct udphdr *udph; int datalen, iplen; struct iphdr *iph; - struct pktgen_hdr *pgh = NULL; - __be16 protocol = __constant_htons(ETH_P_IP); + __be16 protocol = htons(ETH_P_IP); __be32 *mpls; + __be16 *vlan_tci = NULL; /* Encapsulates priority and VLAN ID */ + __be16 *vlan_encapsulated_proto = NULL; /* packet type ID field (or len) for VLAN tag */ + __be16 *svlan_tci = NULL; /* Encapsulates priority and SVLAN ID */ + __be16 *svlan_encapsulated_proto = NULL; /* packet type ID field (or len) for SVLAN tag */ + u16 queue_map; if (pkt_dev->nr_labels) - protocol = __constant_htons(ETH_P_MPLS_UC); + protocol = htons(ETH_P_MPLS_UC); + + if (pkt_dev->vlan_id != 0xffff) + protocol = htons(ETH_P_8021Q); /* Update any of the values, used when we're incrementing various * fields. */ mod_cur_headers(pkt_dev); + queue_map = pkt_dev->cur_queue_map; datalen = (odev->hard_header_len + 16) & ~0xf; - skb = alloc_skb(pkt_dev->cur_pkt_size + 64 + datalen + - pkt_dev->nr_labels*sizeof(u32), GFP_ATOMIC); + + skb = pktgen_alloc_skb(odev, pkt_dev, datalen); if (!skb) { sprintf(pkt_dev->result, "No memory"); return NULL; } + prefetchw(skb->data); skb_reserve(skb, datalen); /* Reserve for ethernet and IP header */ @@ -2116,308 +2756,126 @@ static struct sk_buff *fill_packet_ipv4(struct net_device *odev, mpls = (__be32 *)skb_put(skb, pkt_dev->nr_labels*sizeof(__u32)); if (pkt_dev->nr_labels) mpls_push(mpls, pkt_dev); - iph = (struct iphdr *)skb_put(skb, sizeof(struct iphdr)); - udph = (struct udphdr *)skb_put(skb, sizeof(struct udphdr)); + + if (pkt_dev->vlan_id != 0xffff) { + if (pkt_dev->svlan_id != 0xffff) { + svlan_tci = (__be16 *)skb_put(skb, sizeof(__be16)); + *svlan_tci = build_tci(pkt_dev->svlan_id, + pkt_dev->svlan_cfi, + pkt_dev->svlan_p); + svlan_encapsulated_proto = (__be16 *)skb_put(skb, sizeof(__be16)); + *svlan_encapsulated_proto = htons(ETH_P_8021Q); + } + vlan_tci = (__be16 *)skb_put(skb, sizeof(__be16)); + *vlan_tci = build_tci(pkt_dev->vlan_id, + pkt_dev->vlan_cfi, + pkt_dev->vlan_p); + vlan_encapsulated_proto = (__be16 *)skb_put(skb, sizeof(__be16)); + *vlan_encapsulated_proto = htons(ETH_P_IP); + } + + skb_set_mac_header(skb, 0); + skb_set_network_header(skb, skb->len); + iph = (struct iphdr *) skb_put(skb, sizeof(struct iphdr)); + + skb_set_transport_header(skb, skb->len); + udph = (struct udphdr *) skb_put(skb, sizeof(struct udphdr)); + skb_set_queue_mapping(skb, queue_map); + skb->priority = pkt_dev->skb_priority; memcpy(eth, pkt_dev->hh, 12); - *(u16 *) & eth[12] = protocol; + *(__be16 *) & eth[12] = protocol; /* Eth + IPh + UDPh + mpls */ datalen = pkt_dev->cur_pkt_size - 14 - 20 - 8 - - pkt_dev->nr_labels*sizeof(u32); - if (datalen < sizeof(struct pktgen_hdr)) + pkt_dev->pkt_overhead; + if (datalen < 0 || datalen < sizeof(struct pktgen_hdr)) datalen = sizeof(struct pktgen_hdr); udph->source = htons(pkt_dev->cur_udp_src); udph->dest = htons(pkt_dev->cur_udp_dst); udph->len = htons(datalen + 8); /* DATA + udphdr */ - udph->check = 0; /* No checksum */ + udph->check = 0; iph->ihl = 5; iph->version = 4; iph->ttl = 32; - iph->tos = 0; + iph->tos = pkt_dev->tos; iph->protocol = IPPROTO_UDP; /* UDP */ iph->saddr = pkt_dev->cur_saddr; iph->daddr = pkt_dev->cur_daddr; + iph->id = htons(pkt_dev->ip_id); + pkt_dev->ip_id++; iph->frag_off = 0; iplen = 20 + 8 + datalen; iph->tot_len = htons(iplen); - iph->check = 0; - iph->check = ip_fast_csum((void *)iph, iph->ihl); + ip_send_check(iph); skb->protocol = protocol; - skb->mac.raw = ((u8 *) iph) - 14 - pkt_dev->nr_labels*sizeof(u32); skb->dev = odev; skb->pkt_type = PACKET_HOST; - skb->nh.iph = iph; - skb->h.uh = udph; - if (pkt_dev->nfrags <= 0) - pgh = (struct pktgen_hdr *)skb_put(skb, datalen); - else { - int frags = pkt_dev->nfrags; - int i; - - pgh = (struct pktgen_hdr *)(((char *)(udph)) + 8); - - if (frags > MAX_SKB_FRAGS) - frags = MAX_SKB_FRAGS; - if (datalen > frags * PAGE_SIZE) { - skb_put(skb, datalen - frags * PAGE_SIZE); - datalen = frags * PAGE_SIZE; - } - - i = 0; - while (datalen > 0) { - struct page *page = alloc_pages(GFP_KERNEL, 0); - skb_shinfo(skb)->frags[i].page = page; - skb_shinfo(skb)->frags[i].page_offset = 0; - skb_shinfo(skb)->frags[i].size = - (datalen < PAGE_SIZE ? datalen : PAGE_SIZE); - datalen -= skb_shinfo(skb)->frags[i].size; - skb->len += skb_shinfo(skb)->frags[i].size; - skb->data_len += skb_shinfo(skb)->frags[i].size; - i++; - skb_shinfo(skb)->nr_frags = i; - } - - while (i < frags) { - int rem; - - if (i == 0) - break; - - rem = skb_shinfo(skb)->frags[i - 1].size / 2; - if (rem == 0) - break; + if (!(pkt_dev->flags & F_UDPCSUM)) { + skb->ip_summed = CHECKSUM_NONE; + } else if (odev->features & NETIF_F_V4_CSUM) { + skb->ip_summed = CHECKSUM_PARTIAL; + skb->csum = 0; + udp4_hwcsum(skb, udph->source, udph->dest); + } else { + __wsum csum = udp_csum(skb); - skb_shinfo(skb)->frags[i - 1].size -= rem; + /* add protocol-dependent pseudo-header */ + udph->check = csum_tcpudp_magic(udph->source, udph->dest, + datalen + 8, IPPROTO_UDP, csum); - skb_shinfo(skb)->frags[i] = - skb_shinfo(skb)->frags[i - 1]; - get_page(skb_shinfo(skb)->frags[i].page); - skb_shinfo(skb)->frags[i].page = - skb_shinfo(skb)->frags[i - 1].page; - skb_shinfo(skb)->frags[i].page_offset += - skb_shinfo(skb)->frags[i - 1].size; - skb_shinfo(skb)->frags[i].size = rem; - i++; - skb_shinfo(skb)->nr_frags = i; - } + if (udph->check == 0) + udph->check = CSUM_MANGLED_0; } - /* Stamp the time, and sequence number, convert them to network byte order */ - - if (pgh) { - struct timeval timestamp; - - pgh->pgh_magic = htonl(PKTGEN_MAGIC); - pgh->seq_num = htonl(pkt_dev->seq_num); + pktgen_finalize_skb(pkt_dev, skb, datalen); - do_gettimeofday(×tamp); - pgh->tv_sec = htonl(timestamp.tv_sec); - pgh->tv_usec = htonl(timestamp.tv_usec); - } - pkt_dev->seq_num++; +#ifdef CONFIG_XFRM + if (!process_ipsec(pkt_dev, skb, protocol)) + return NULL; +#endif return skb; } -/* - * scan_ip6, fmt_ip taken from dietlibc-0.21 - * Author Felix von Leitner <felix-dietlibc@fefe.de> - * - * Slightly modified for kernel. - * Should be candidate for net/ipv4/utils.c - * --ro - */ - -static unsigned int scan_ip6(const char *s, char ip[16]) -{ - unsigned int i; - unsigned int len = 0; - unsigned long u; - char suffix[16]; - unsigned int prefixlen = 0; - unsigned int suffixlen = 0; - __u32 tmp; - - for (i = 0; i < 16; i++) - ip[i] = 0; - - for (;;) { - if (*s == ':') { - len++; - if (s[1] == ':') { /* Found "::", skip to part 2 */ - s += 2; - len++; - break; - } - s++; - } - { - char *tmp; - u = simple_strtoul(s, &tmp, 16); - i = tmp - s; - } - - if (!i) - return 0; - if (prefixlen == 12 && s[i] == '.') { - - /* the last 4 bytes may be written as IPv4 address */ - - tmp = in_aton(s); - memcpy((struct in_addr *)(ip + 12), &tmp, sizeof(tmp)); - return i + len; - } - ip[prefixlen++] = (u >> 8); - ip[prefixlen++] = (u & 255); - s += i; - len += i; - if (prefixlen == 16) - return len; - } - -/* part 2, after "::" */ - for (;;) { - if (*s == ':') { - if (suffixlen == 0) - break; - s++; - len++; - } else if (suffixlen != 0) - break; - { - char *tmp; - u = simple_strtol(s, &tmp, 16); - i = tmp - s; - } - if (!i) { - if (*s) - len--; - break; - } - if (suffixlen + prefixlen <= 12 && s[i] == '.') { - tmp = in_aton(s); - memcpy((struct in_addr *)(suffix + suffixlen), &tmp, - sizeof(tmp)); - suffixlen += 4; - len += strlen(s); - break; - } - suffix[suffixlen++] = (u >> 8); - suffix[suffixlen++] = (u & 255); - s += i; - len += i; - if (prefixlen + suffixlen == 16) - break; - } - for (i = 0; i < suffixlen; i++) - ip[16 - suffixlen + i] = suffix[i]; - return len; -} - -static char tohex(char hexdigit) -{ - return hexdigit > 9 ? hexdigit + 'a' - 10 : hexdigit + '0'; -} - -static int fmt_xlong(char *s, unsigned int i) -{ - char *bak = s; - *s = tohex((i >> 12) & 0xf); - if (s != bak || *s != '0') - ++s; - *s = tohex((i >> 8) & 0xf); - if (s != bak || *s != '0') - ++s; - *s = tohex((i >> 4) & 0xf); - if (s != bak || *s != '0') - ++s; - *s = tohex(i & 0xf); - return s - bak + 1; -} - -static unsigned int fmt_ip6(char *s, const char ip[16]) -{ - unsigned int len; - unsigned int i; - unsigned int temp; - unsigned int compressing; - int j; - - len = 0; - compressing = 0; - for (j = 0; j < 16; j += 2) { - -#ifdef V4MAPPEDPREFIX - if (j == 12 && !memcmp(ip, V4mappedprefix, 12)) { - inet_ntoa_r(*(struct in_addr *)(ip + 12), s); - temp = strlen(s); - return len + temp; - } -#endif - temp = ((unsigned long)(unsigned char)ip[j] << 8) + - (unsigned long)(unsigned char)ip[j + 1]; - if (temp == 0) { - if (!compressing) { - compressing = 1; - if (j == 0) { - *s++ = ':'; - ++len; - } - } - } else { - if (compressing) { - compressing = 0; - *s++ = ':'; - ++len; - } - i = fmt_xlong(s, temp); - len += i; - s += i; - if (j < 14) { - *s++ = ':'; - ++len; - } - } - } - if (compressing) { - *s++ = ':'; - ++len; - } - *s = 0; - return len; -} - static struct sk_buff *fill_packet_ipv6(struct net_device *odev, struct pktgen_dev *pkt_dev) { struct sk_buff *skb = NULL; __u8 *eth; struct udphdr *udph; - int datalen; + int datalen, udplen; struct ipv6hdr *iph; - struct pktgen_hdr *pgh = NULL; - __be16 protocol = __constant_htons(ETH_P_IPV6); + __be16 protocol = htons(ETH_P_IPV6); __be32 *mpls; + __be16 *vlan_tci = NULL; /* Encapsulates priority and VLAN ID */ + __be16 *vlan_encapsulated_proto = NULL; /* packet type ID field (or len) for VLAN tag */ + __be16 *svlan_tci = NULL; /* Encapsulates priority and SVLAN ID */ + __be16 *svlan_encapsulated_proto = NULL; /* packet type ID field (or len) for SVLAN tag */ + u16 queue_map; if (pkt_dev->nr_labels) - protocol = __constant_htons(ETH_P_MPLS_UC); + protocol = htons(ETH_P_MPLS_UC); + + if (pkt_dev->vlan_id != 0xffff) + protocol = htons(ETH_P_8021Q); /* Update any of the values, used when we're incrementing various * fields. */ mod_cur_headers(pkt_dev); + queue_map = pkt_dev->cur_queue_map; - skb = alloc_skb(pkt_dev->cur_pkt_size + 64 + 16 + - pkt_dev->nr_labels*sizeof(u32), GFP_ATOMIC); + skb = pktgen_alloc_skb(odev, pkt_dev, 16); if (!skb) { sprintf(pkt_dev->result, "No memory"); return NULL; } + prefetchw(skb->data); skb_reserve(skb, 16); /* Reserve for ethernet and IP header */ @@ -2425,119 +2883,95 @@ static struct sk_buff *fill_packet_ipv6(struct net_device *odev, mpls = (__be32 *)skb_put(skb, pkt_dev->nr_labels*sizeof(__u32)); if (pkt_dev->nr_labels) mpls_push(mpls, pkt_dev); - iph = (struct ipv6hdr *)skb_put(skb, sizeof(struct ipv6hdr)); - udph = (struct udphdr *)skb_put(skb, sizeof(struct udphdr)); + + if (pkt_dev->vlan_id != 0xffff) { + if (pkt_dev->svlan_id != 0xffff) { + svlan_tci = (__be16 *)skb_put(skb, sizeof(__be16)); + *svlan_tci = build_tci(pkt_dev->svlan_id, + pkt_dev->svlan_cfi, + pkt_dev->svlan_p); + svlan_encapsulated_proto = (__be16 *)skb_put(skb, sizeof(__be16)); + *svlan_encapsulated_proto = htons(ETH_P_8021Q); + } + vlan_tci = (__be16 *)skb_put(skb, sizeof(__be16)); + *vlan_tci = build_tci(pkt_dev->vlan_id, + pkt_dev->vlan_cfi, + pkt_dev->vlan_p); + vlan_encapsulated_proto = (__be16 *)skb_put(skb, sizeof(__be16)); + *vlan_encapsulated_proto = htons(ETH_P_IPV6); + } + + skb_set_mac_header(skb, 0); + skb_set_network_header(skb, skb->len); + iph = (struct ipv6hdr *) skb_put(skb, sizeof(struct ipv6hdr)); + + skb_set_transport_header(skb, skb->len); + udph = (struct udphdr *) skb_put(skb, sizeof(struct udphdr)); + skb_set_queue_mapping(skb, queue_map); + skb->priority = pkt_dev->skb_priority; memcpy(eth, pkt_dev->hh, 12); - *(u16 *) & eth[12] = __constant_htons(ETH_P_IPV6); + *(__be16 *) ð[12] = protocol; /* Eth + IPh + UDPh + mpls */ datalen = pkt_dev->cur_pkt_size - 14 - sizeof(struct ipv6hdr) - sizeof(struct udphdr) - - pkt_dev->nr_labels*sizeof(u32); + pkt_dev->pkt_overhead; - if (datalen < sizeof(struct pktgen_hdr)) { + if (datalen < 0 || datalen < sizeof(struct pktgen_hdr)) { datalen = sizeof(struct pktgen_hdr); - if (net_ratelimit()) - printk(KERN_INFO "pktgen: increased datalen to %d\n", - datalen); + net_info_ratelimited("increased datalen to %d\n", datalen); } + udplen = datalen + sizeof(struct udphdr); udph->source = htons(pkt_dev->cur_udp_src); udph->dest = htons(pkt_dev->cur_udp_dst); - udph->len = htons(datalen + sizeof(struct udphdr)); - udph->check = 0; /* No checksum */ + udph->len = htons(udplen); + udph->check = 0; + + *(__be32 *) iph = htonl(0x60000000); /* Version + flow */ - *(u32 *) iph = __constant_htonl(0x60000000); /* Version + flow */ + if (pkt_dev->traffic_class) { + /* Version + traffic class + flow (0) */ + *(__be32 *)iph |= htonl(0x60000000 | (pkt_dev->traffic_class << 20)); + } iph->hop_limit = 32; - iph->payload_len = htons(sizeof(struct udphdr) + datalen); + iph->payload_len = htons(udplen); iph->nexthdr = IPPROTO_UDP; - ipv6_addr_copy(&iph->daddr, &pkt_dev->cur_in6_daddr); - ipv6_addr_copy(&iph->saddr, &pkt_dev->cur_in6_saddr); + iph->daddr = pkt_dev->cur_in6_daddr; + iph->saddr = pkt_dev->cur_in6_saddr; - skb->mac.raw = ((u8 *) iph) - 14 - pkt_dev->nr_labels*sizeof(u32); skb->protocol = protocol; skb->dev = odev; skb->pkt_type = PACKET_HOST; - skb->nh.ipv6h = iph; - skb->h.uh = udph; - - if (pkt_dev->nfrags <= 0) - pgh = (struct pktgen_hdr *)skb_put(skb, datalen); - else { - int frags = pkt_dev->nfrags; - int i; - - pgh = (struct pktgen_hdr *)(((char *)(udph)) + 8); - - if (frags > MAX_SKB_FRAGS) - frags = MAX_SKB_FRAGS; - if (datalen > frags * PAGE_SIZE) { - skb_put(skb, datalen - frags * PAGE_SIZE); - datalen = frags * PAGE_SIZE; - } - - i = 0; - while (datalen > 0) { - struct page *page = alloc_pages(GFP_KERNEL, 0); - skb_shinfo(skb)->frags[i].page = page; - skb_shinfo(skb)->frags[i].page_offset = 0; - skb_shinfo(skb)->frags[i].size = - (datalen < PAGE_SIZE ? datalen : PAGE_SIZE); - datalen -= skb_shinfo(skb)->frags[i].size; - skb->len += skb_shinfo(skb)->frags[i].size; - skb->data_len += skb_shinfo(skb)->frags[i].size; - i++; - skb_shinfo(skb)->nr_frags = i; - } - while (i < frags) { - int rem; - - if (i == 0) - break; - - rem = skb_shinfo(skb)->frags[i - 1].size / 2; - if (rem == 0) - break; + if (!(pkt_dev->flags & F_UDPCSUM)) { + skb->ip_summed = CHECKSUM_NONE; + } else if (odev->features & NETIF_F_V6_CSUM) { + skb->ip_summed = CHECKSUM_PARTIAL; + skb->csum_start = skb_transport_header(skb) - skb->head; + skb->csum_offset = offsetof(struct udphdr, check); + udph->check = ~csum_ipv6_magic(&iph->saddr, &iph->daddr, udplen, IPPROTO_UDP, 0); + } else { + __wsum csum = udp_csum(skb); - skb_shinfo(skb)->frags[i - 1].size -= rem; + /* add protocol-dependent pseudo-header */ + udph->check = csum_ipv6_magic(&iph->saddr, &iph->daddr, udplen, IPPROTO_UDP, csum); - skb_shinfo(skb)->frags[i] = - skb_shinfo(skb)->frags[i - 1]; - get_page(skb_shinfo(skb)->frags[i].page); - skb_shinfo(skb)->frags[i].page = - skb_shinfo(skb)->frags[i - 1].page; - skb_shinfo(skb)->frags[i].page_offset += - skb_shinfo(skb)->frags[i - 1].size; - skb_shinfo(skb)->frags[i].size = rem; - i++; - skb_shinfo(skb)->nr_frags = i; - } + if (udph->check == 0) + udph->check = CSUM_MANGLED_0; } - /* Stamp the time, and sequence number, convert them to network byte order */ - /* should we update cloned packets too ? */ - if (pgh) { - struct timeval timestamp; - - pgh->pgh_magic = htonl(PKTGEN_MAGIC); - pgh->seq_num = htonl(pkt_dev->seq_num); - - do_gettimeofday(×tamp); - pgh->tv_sec = htonl(timestamp.tv_sec); - pgh->tv_usec = htonl(timestamp.tv_usec); - } - pkt_dev->seq_num++; + pktgen_finalize_skb(pkt_dev, skb, datalen); return skb; } -static inline struct sk_buff *fill_packet(struct net_device *odev, - struct pktgen_dev *pkt_dev) +static struct sk_buff *fill_packet(struct net_device *odev, + struct pktgen_dev *pkt_dev) { if (pkt_dev->flags & F_IPV6) return fill_packet_ipv6(odev, pkt_dev); @@ -2561,7 +2995,7 @@ static void pktgen_run(struct pktgen_thread *t) struct pktgen_dev *pkt_dev; int started = 0; - PG_DEBUG(printk("pktgen: entering pktgen_run. %p\n", t)); + func_enter(); if_lock(t); list_for_each_entry(pkt_dev, &t->if_list, list) { @@ -2575,9 +3009,9 @@ static void pktgen_run(struct pktgen_thread *t) pktgen_clear_counters(pkt_dev); pkt_dev->running = 1; /* Cranke yeself! */ pkt_dev->skb = NULL; - pkt_dev->started_at = getCurUs(); - pkt_dev->next_tx_us = getCurUs(); /* Transmit immediately */ - pkt_dev->next_tx_ns = 0; + pkt_dev->started_at = pkt_dev->next_tx = ktime_get(); + + set_pkt_overhead(pkt_dev); strcpy(pkt_dev->result, "Starting"); started++; @@ -2589,31 +3023,28 @@ static void pktgen_run(struct pktgen_thread *t) t->control &= ~(T_STOP); } -static void pktgen_stop_all_threads_ifs(void) +static void pktgen_stop_all_threads_ifs(struct pktgen_net *pn) { struct pktgen_thread *t; - PG_DEBUG(printk("pktgen: entering pktgen_stop_all_threads_ifs.\n")); + func_enter(); mutex_lock(&pktgen_thread_lock); - list_for_each_entry(t, &pktgen_threads, th_list) + list_for_each_entry(t, &pn->pktgen_threads, th_list) t->control |= T_STOP; mutex_unlock(&pktgen_thread_lock); } -static int thread_is_running(struct pktgen_thread *t) +static int thread_is_running(const struct pktgen_thread *t) { - struct pktgen_dev *pkt_dev; - int res = 0; + const struct pktgen_dev *pkt_dev; list_for_each_entry(pkt_dev, &t->if_list, list) - if (pkt_dev->running) { - res = 1; - break; - } - return res; + if (pkt_dev->running) + return 1; + return 0; } static int pktgen_wait_thread_run(struct pktgen_thread *t) @@ -2636,69 +3067,82 @@ signal: return 0; } -static int pktgen_wait_all_threads_run(void) +static int pktgen_wait_all_threads_run(struct pktgen_net *pn) { struct pktgen_thread *t; int sig = 1; mutex_lock(&pktgen_thread_lock); - list_for_each_entry(t, &pktgen_threads, th_list) { + list_for_each_entry(t, &pn->pktgen_threads, th_list) { sig = pktgen_wait_thread_run(t); if (sig == 0) break; } if (sig == 0) - list_for_each_entry(t, &pktgen_threads, th_list) + list_for_each_entry(t, &pn->pktgen_threads, th_list) t->control |= (T_STOP); mutex_unlock(&pktgen_thread_lock); return sig; } -static void pktgen_run_all_threads(void) +static void pktgen_run_all_threads(struct pktgen_net *pn) { struct pktgen_thread *t; - PG_DEBUG(printk("pktgen: entering pktgen_run_all_threads.\n")); + func_enter(); mutex_lock(&pktgen_thread_lock); - list_for_each_entry(t, &pktgen_threads, th_list) + list_for_each_entry(t, &pn->pktgen_threads, th_list) t->control |= (T_RUN); mutex_unlock(&pktgen_thread_lock); - schedule_timeout_interruptible(msecs_to_jiffies(125)); /* Propagate thread->control */ + /* Propagate thread->control */ + schedule_timeout_interruptible(msecs_to_jiffies(125)); - pktgen_wait_all_threads_run(); + pktgen_wait_all_threads_run(pn); } -static void show_results(struct pktgen_dev *pkt_dev, int nr_frags) +static void pktgen_reset_all_threads(struct pktgen_net *pn) { - __u64 total_us, bps, mbps, pps, idle; - char *p = pkt_dev->result; + struct pktgen_thread *t; - total_us = pkt_dev->stopped_at - pkt_dev->started_at; + func_enter(); - idle = pkt_dev->idle_acc; + mutex_lock(&pktgen_thread_lock); + + list_for_each_entry(t, &pn->pktgen_threads, th_list) + t->control |= (T_REMDEVALL); + + mutex_unlock(&pktgen_thread_lock); + + /* Propagate thread->control */ + schedule_timeout_interruptible(msecs_to_jiffies(125)); + + pktgen_wait_all_threads_run(pn); +} + +static void show_results(struct pktgen_dev *pkt_dev, int nr_frags) +{ + __u64 bps, mbps, pps; + char *p = pkt_dev->result; + ktime_t elapsed = ktime_sub(pkt_dev->stopped_at, + pkt_dev->started_at); + ktime_t idle = ns_to_ktime(pkt_dev->idle_acc); p += sprintf(p, "OK: %llu(c%llu+d%llu) usec, %llu (%dbyte,%dfrags)\n", - (unsigned long long)total_us, - (unsigned long long)(total_us - idle), - (unsigned long long)idle, + (unsigned long long)ktime_to_us(elapsed), + (unsigned long long)ktime_to_us(ktime_sub(elapsed, idle)), + (unsigned long long)ktime_to_us(idle), (unsigned long long)pkt_dev->sofar, pkt_dev->cur_pkt_size, nr_frags); - pps = pkt_dev->sofar * USEC_PER_SEC; - - while ((total_us >> 32) != 0) { - pps >>= 1; - total_us >>= 1; - } - - do_div(pps, total_us); + pps = div64_u64(pkt_dev->sofar * NSEC_PER_SEC, + ktime_to_ns(elapsed)); bps = pps * 8 * pkt_dev->cur_pkt_size; @@ -2712,18 +3156,19 @@ static void show_results(struct pktgen_dev *pkt_dev, int nr_frags) } /* Set stopped-at timer, remove from running list, do counters & statistics */ - static int pktgen_stop_device(struct pktgen_dev *pkt_dev) { int nr_frags = pkt_dev->skb ? skb_shinfo(pkt_dev->skb)->nr_frags : -1; if (!pkt_dev->running) { - printk("pktgen: interface: %s is already stopped\n", - pkt_dev->ifname); + pr_warning("interface: %s is already stopped\n", + pkt_dev->odevname); return -EINVAL; } - pkt_dev->stopped_at = getCurUs(); + kfree_skb(pkt_dev->skb); + pkt_dev->skb = NULL; + pkt_dev->stopped_at = ktime_get(); pkt_dev->running = 0; show_results(pkt_dev, nr_frags); @@ -2742,7 +3187,7 @@ static struct pktgen_dev *next_to_run(struct pktgen_thread *t) continue; if (best == NULL) best = pkt_dev; - else if (pkt_dev->next_tx_us < best->next_tx_us) + else if (ktime_compare(pkt_dev->next_tx, best->next_tx) < 0) best = pkt_dev; } if_unlock(t); @@ -2753,16 +3198,12 @@ static void pktgen_stop(struct pktgen_thread *t) { struct pktgen_dev *pkt_dev; - PG_DEBUG(printk("pktgen: entering pktgen_stop\n")); + func_enter(); if_lock(t); list_for_each_entry(pkt_dev, &t->if_list, list) { pktgen_stop_device(pkt_dev); - if (pkt_dev->skb) - kfree_skb(pkt_dev->skb); - - pkt_dev->skb = NULL; } if_unlock(t); @@ -2777,7 +3218,7 @@ static void pktgen_rem_one_if(struct pktgen_thread *t) struct list_head *q, *n; struct pktgen_dev *cur; - PG_DEBUG(printk("pktgen: entering pktgen_rem_one_if\n")); + func_enter(); if_lock(t); @@ -2787,8 +3228,7 @@ static void pktgen_rem_one_if(struct pktgen_thread *t) if (!cur->removal_mark) continue; - if (cur->skb) - kfree_skb(cur->skb); + kfree_skb(cur->skb); cur->skb = NULL; pktgen_remove_device(t, cur); @@ -2804,16 +3244,16 @@ static void pktgen_rem_all_ifs(struct pktgen_thread *t) struct list_head *q, *n; struct pktgen_dev *cur; + func_enter(); + /* Remove all devices, free mem */ - PG_DEBUG(printk("pktgen: entering pktgen_rem_all_ifs\n")); if_lock(t); list_for_each_safe(q, n, &t->if_list) { cur = list_entry(q, struct pktgen_dev, list); - if (cur->skb) - kfree_skb(cur->skb); + kfree_skb(cur->skb); cur->skb = NULL; pktgen_remove_device(t, cur); @@ -2825,239 +3265,176 @@ static void pktgen_rem_all_ifs(struct pktgen_thread *t) static void pktgen_rem_thread(struct pktgen_thread *t) { /* Remove from the thread list */ + remove_proc_entry(t->tsk->comm, t->net->proc_dir); +} - remove_proc_entry(t->name, pg_proc_dir); +static void pktgen_resched(struct pktgen_dev *pkt_dev) +{ + ktime_t idle_start = ktime_get(); + schedule(); + pkt_dev->idle_acc += ktime_to_ns(ktime_sub(ktime_get(), idle_start)); +} - mutex_lock(&pktgen_thread_lock); +static void pktgen_wait_for_skb(struct pktgen_dev *pkt_dev) +{ + ktime_t idle_start = ktime_get(); - list_del(&t->th_list); + while (atomic_read(&(pkt_dev->skb->users)) != 1) { + if (signal_pending(current)) + break; - mutex_unlock(&pktgen_thread_lock); + if (need_resched()) + pktgen_resched(pkt_dev); + else + cpu_relax(); + } + pkt_dev->idle_acc += ktime_to_ns(ktime_sub(ktime_get(), idle_start)); } -static __inline__ void pktgen_xmit(struct pktgen_dev *pkt_dev) +static void pktgen_xmit(struct pktgen_dev *pkt_dev) { - struct net_device *odev = NULL; - __u64 idle_start = 0; + struct net_device *odev = pkt_dev->odev; + netdev_tx_t (*xmit)(struct sk_buff *, struct net_device *) + = odev->netdev_ops->ndo_start_xmit; + struct netdev_queue *txq; + u16 queue_map; int ret; - odev = pkt_dev->odev; - - if (pkt_dev->delay_us || pkt_dev->delay_ns) { - u64 now; - - now = getCurUs(); - if (now < pkt_dev->next_tx_us) - spin(pkt_dev, pkt_dev->next_tx_us); - - /* This is max DELAY, this has special meaning of - * "never transmit" - */ - if (pkt_dev->delay_us == 0x7FFFFFFF) { - pkt_dev->next_tx_us = getCurUs() + pkt_dev->delay_us; - pkt_dev->next_tx_ns = pkt_dev->delay_ns; - goto out; - } + /* If device is offline, then don't send */ + if (unlikely(!netif_running(odev) || !netif_carrier_ok(odev))) { + pktgen_stop_device(pkt_dev); + return; } - if (netif_queue_stopped(odev) || need_resched()) { - idle_start = getCurUs(); - - if (!netif_running(odev)) { - pktgen_stop_device(pkt_dev); - if (pkt_dev->skb) - kfree_skb(pkt_dev->skb); - pkt_dev->skb = NULL; - goto out; - } - if (need_resched()) - schedule(); - - pkt_dev->idle_acc += getCurUs() - idle_start; - - if (netif_queue_stopped(odev)) { - pkt_dev->next_tx_us = getCurUs(); /* TODO */ - pkt_dev->next_tx_ns = 0; - goto out; /* Try the next interface */ - } + /* This is max DELAY, this has special meaning of + * "never transmit" + */ + if (unlikely(pkt_dev->delay == ULLONG_MAX)) { + pkt_dev->next_tx = ktime_add_ns(ktime_get(), ULONG_MAX); + return; } - if (pkt_dev->last_ok || !pkt_dev->skb) { - if ((++pkt_dev->clone_count >= pkt_dev->clone_skb) - || (!pkt_dev->skb)) { - /* build a new pkt */ - if (pkt_dev->skb) - kfree_skb(pkt_dev->skb); + /* If no skb or clone count exhausted then get new one */ + if (!pkt_dev->skb || (pkt_dev->last_ok && + ++pkt_dev->clone_count >= pkt_dev->clone_skb)) { + /* build a new pkt */ + kfree_skb(pkt_dev->skb); - pkt_dev->skb = fill_packet(odev, pkt_dev); - if (pkt_dev->skb == NULL) { - printk("pktgen: ERROR: couldn't allocate skb in fill_packet.\n"); - schedule(); - pkt_dev->clone_count--; /* back out increment, OOM */ - goto out; - } - pkt_dev->allocated_skbs++; - pkt_dev->clone_count = 0; /* reset counter */ + pkt_dev->skb = fill_packet(odev, pkt_dev); + if (pkt_dev->skb == NULL) { + pr_err("ERROR: couldn't allocate skb in fill_packet\n"); + schedule(); + pkt_dev->clone_count--; /* back out increment, OOM */ + return; } + pkt_dev->last_pkt_size = pkt_dev->skb->len; + pkt_dev->allocated_skbs++; + pkt_dev->clone_count = 0; /* reset counter */ } - netif_tx_lock_bh(odev); - if (!netif_queue_stopped(odev)) { + if (pkt_dev->delay && pkt_dev->last_ok) + spin(pkt_dev, pkt_dev->next_tx); - atomic_inc(&(pkt_dev->skb->users)); - retry_now: - ret = odev->hard_start_xmit(pkt_dev->skb, odev); - if (likely(ret == NETDEV_TX_OK)) { - pkt_dev->last_ok = 1; - pkt_dev->sofar++; - pkt_dev->seq_num++; - pkt_dev->tx_bytes += pkt_dev->cur_pkt_size; + queue_map = skb_get_queue_mapping(pkt_dev->skb); + txq = netdev_get_tx_queue(odev, queue_map); - } else if (ret == NETDEV_TX_LOCKED - && (odev->features & NETIF_F_LLTX)) { - cpu_relax(); - goto retry_now; - } else { /* Retry it next time */ - - atomic_dec(&(pkt_dev->skb->users)); + local_bh_disable(); - if (debug && net_ratelimit()) - printk(KERN_INFO "pktgen: Hard xmit error\n"); - - pkt_dev->errors++; - pkt_dev->last_ok = 0; - } + HARD_TX_LOCK(odev, txq, smp_processor_id()); - pkt_dev->next_tx_us = getCurUs(); - pkt_dev->next_tx_ns = 0; - - pkt_dev->next_tx_us += pkt_dev->delay_us; - pkt_dev->next_tx_ns += pkt_dev->delay_ns; - - if (pkt_dev->next_tx_ns > 1000) { - pkt_dev->next_tx_us++; - pkt_dev->next_tx_ns -= 1000; - } - } - - else { /* Retry it next time */ + if (unlikely(netif_xmit_frozen_or_drv_stopped(txq))) { + ret = NETDEV_TX_BUSY; + pkt_dev->last_ok = 0; + goto unlock; + } + atomic_inc(&(pkt_dev->skb->users)); + ret = (*xmit)(pkt_dev->skb, odev); + + switch (ret) { + case NETDEV_TX_OK: + txq_trans_update(txq); + pkt_dev->last_ok = 1; + pkt_dev->sofar++; + pkt_dev->seq_num++; + pkt_dev->tx_bytes += pkt_dev->last_pkt_size; + break; + case NET_XMIT_DROP: + case NET_XMIT_CN: + case NET_XMIT_POLICED: + /* skb has been consumed */ + pkt_dev->errors++; + break; + default: /* Drivers are not supposed to return other values! */ + net_info_ratelimited("%s xmit error: %d\n", + pkt_dev->odevname, ret); + pkt_dev->errors++; + /* fallthru */ + case NETDEV_TX_LOCKED: + case NETDEV_TX_BUSY: + /* Retry it next time */ + atomic_dec(&(pkt_dev->skb->users)); pkt_dev->last_ok = 0; - pkt_dev->next_tx_us = getCurUs(); /* TODO */ - pkt_dev->next_tx_ns = 0; } +unlock: + HARD_TX_UNLOCK(odev, txq); - netif_tx_unlock_bh(odev); + local_bh_enable(); /* If pkt_dev->count is zero, then run forever */ if ((pkt_dev->count != 0) && (pkt_dev->sofar >= pkt_dev->count)) { - if (atomic_read(&(pkt_dev->skb->users)) != 1) { - idle_start = getCurUs(); - while (atomic_read(&(pkt_dev->skb->users)) != 1) { - if (signal_pending(current)) { - break; - } - schedule(); - } - pkt_dev->idle_acc += getCurUs() - idle_start; - } + pktgen_wait_for_skb(pkt_dev); /* Done with this */ pktgen_stop_device(pkt_dev); - if (pkt_dev->skb) - kfree_skb(pkt_dev->skb); - pkt_dev->skb = NULL; } -out:; } -/* +/* * Main loop of the thread goes here */ -static void pktgen_thread_worker(struct pktgen_thread *t) +static int pktgen_thread_worker(void *arg) { DEFINE_WAIT(wait); + struct pktgen_thread *t = arg; struct pktgen_dev *pkt_dev = NULL; int cpu = t->cpu; - sigset_t tmpsig; - u32 max_before_softirq; - u32 tx_since_softirq = 0; - daemonize("pktgen/%d", cpu); - - /* Block all signals except SIGKILL, SIGSTOP and SIGTERM */ - - spin_lock_irq(¤t->sighand->siglock); - tmpsig = current->blocked; - siginitsetinv(¤t->blocked, - sigmask(SIGKILL) | sigmask(SIGSTOP) | sigmask(SIGTERM)); - - recalc_sigpending(); - spin_unlock_irq(¤t->sighand->siglock); - - /* Migrate to the right CPU */ - set_cpus_allowed(current, cpumask_of_cpu(cpu)); - if (smp_processor_id() != cpu) - BUG(); + BUG_ON(smp_processor_id() != cpu); init_waitqueue_head(&t->queue); + complete(&t->start_done); - t->control &= ~(T_TERMINATE); - t->control &= ~(T_RUN); - t->control &= ~(T_STOP); - t->control &= ~(T_REMDEVALL); - t->control &= ~(T_REMDEV); + pr_debug("starting pktgen/%d: pid=%d\n", cpu, task_pid_nr(current)); - t->pid = current->pid; + set_current_state(TASK_INTERRUPTIBLE); - PG_DEBUG(printk("pktgen: starting pktgen/%d: pid=%d\n", cpu, current->pid)); + set_freezable(); - max_before_softirq = t->max_before_softirq; - - __set_current_state(TASK_INTERRUPTIBLE); - mb(); + while (!kthread_should_stop()) { + pkt_dev = next_to_run(t); - while (1) { + if (unlikely(!pkt_dev && t->control == 0)) { + if (t->net->pktgen_exiting) + break; + wait_event_interruptible_timeout(t->queue, + t->control != 0, + HZ/10); + try_to_freeze(); + continue; + } __set_current_state(TASK_RUNNING); - /* - * Get next dev to xmit -- if any. - */ - - pkt_dev = next_to_run(t); - - if (pkt_dev) { - + if (likely(pkt_dev)) { pktgen_xmit(pkt_dev); - /* - * We like to stay RUNNING but must also give - * others fair share. - */ - - tx_since_softirq += pkt_dev->last_ok; - - if (tx_since_softirq > max_before_softirq) { - if (local_softirq_pending()) - do_softirq(); - tx_since_softirq = 0; - } - } else { - prepare_to_wait(&(t->queue), &wait, TASK_INTERRUPTIBLE); - schedule_timeout(HZ / 10); - finish_wait(&(t->queue), &wait); + if (need_resched()) + pktgen_resched(pkt_dev); + else + cpu_relax(); } - /* - * Back from sleep, either due to the timeout or signal. - * We check if we have any "posted" work for us. - */ - - if (t->control & T_TERMINATE || signal_pending(current)) - /* we received a request to terminate ourself */ - break; - if (t->control & T_STOP) { pktgen_stop(t); t->control &= ~(T_STOP); @@ -3078,41 +3455,54 @@ static void pktgen_thread_worker(struct pktgen_thread *t) t->control &= ~(T_REMDEV); } - if (need_resched()) - schedule(); + try_to_freeze(); + + set_current_state(TASK_INTERRUPTIBLE); } - PG_DEBUG(printk("pktgen: %s stopping all device\n", t->name)); + pr_debug("%s stopping all device\n", t->tsk->comm); pktgen_stop(t); - PG_DEBUG(printk("pktgen: %s removing all device\n", t->name)); + pr_debug("%s removing all device\n", t->tsk->comm); pktgen_rem_all_ifs(t); - PG_DEBUG(printk("pktgen: %s removing thread.\n", t->name)); + pr_debug("%s removing thread\n", t->tsk->comm); pktgen_rem_thread(t); - t->removed = 1; + /* Wait for kthread_stop */ + while (!kthread_should_stop()) { + set_current_state(TASK_INTERRUPTIBLE); + schedule(); + } + __set_current_state(TASK_RUNNING); + + return 0; } static struct pktgen_dev *pktgen_find_dev(struct pktgen_thread *t, - const char *ifname) + const char *ifname, bool exact) { struct pktgen_dev *p, *pkt_dev = NULL; - if_lock(t); + size_t len = strlen(ifname); + if_lock(t); list_for_each_entry(p, &t->if_list, list) - if (strncmp(p->ifname, ifname, IFNAMSIZ) == 0) { + if (strncmp(p->odevname, ifname, len) == 0) { + if (p->odevname[len]) { + if (exact || p->odevname[len] != '@') + continue; + } pkt_dev = p; break; } if_unlock(t); - PG_DEBUG(printk("pktgen: find_dev(%s) returning %p\n", ifname, pkt_dev)); + pr_debug("find_dev(%s) returning %p\n", ifname, pkt_dev); return pkt_dev; } -/* - * Adds a dev at front of if_list. +/* + * Adds a dev at front of if_list. */ static int add_dev_to_thread(struct pktgen_thread *t, @@ -3123,7 +3513,7 @@ static int add_dev_to_thread(struct pktgen_thread *t, if_lock(t); if (pkt_dev->pg_thread) { - printk("pktgen: ERROR: already assigned to a thread.\n"); + pr_err("ERROR: already assigned to a thread\n"); rv = -EBUSY; goto out; } @@ -3142,140 +3532,142 @@ out: static int pktgen_add_device(struct pktgen_thread *t, const char *ifname) { struct pktgen_dev *pkt_dev; - struct proc_dir_entry *pe; + int err; + int node = cpu_to_node(t->cpu); /* We don't allow a device to be on several threads */ - pkt_dev = __pktgen_NN_threads(ifname, FIND); + pkt_dev = __pktgen_NN_threads(t->net, ifname, FIND); if (pkt_dev) { - printk("pktgen: ERROR: interface already used.\n"); + pr_err("ERROR: interface already used\n"); return -EBUSY; } - pkt_dev = kzalloc(sizeof(struct pktgen_dev), GFP_KERNEL); + pkt_dev = kzalloc_node(sizeof(struct pktgen_dev), GFP_KERNEL, node); if (!pkt_dev) return -ENOMEM; - pkt_dev->flows = vmalloc(MAX_CFLOWS * sizeof(struct flow_state)); + strcpy(pkt_dev->odevname, ifname); + pkt_dev->flows = vzalloc_node(MAX_CFLOWS * sizeof(struct flow_state), + node); if (pkt_dev->flows == NULL) { kfree(pkt_dev); return -ENOMEM; } - memset(pkt_dev->flows, 0, MAX_CFLOWS * sizeof(struct flow_state)); pkt_dev->removal_mark = 0; - pkt_dev->min_pkt_size = ETH_ZLEN; - pkt_dev->max_pkt_size = ETH_ZLEN; pkt_dev->nfrags = 0; - pkt_dev->clone_skb = pg_clone_skb_d; - pkt_dev->delay_us = pg_delay_d / 1000; - pkt_dev->delay_ns = pg_delay_d % 1000; + pkt_dev->delay = pg_delay_d; pkt_dev->count = pg_count_d; pkt_dev->sofar = 0; pkt_dev->udp_src_min = 9; /* sink port */ pkt_dev->udp_src_max = 9; pkt_dev->udp_dst_min = 9; pkt_dev->udp_dst_max = 9; - - strncpy(pkt_dev->ifname, ifname, IFNAMSIZ); - - if (!pktgen_setup_dev(pkt_dev)) { - printk("pktgen: ERROR: pktgen_setup_dev failed.\n"); - if (pkt_dev->flows) - vfree(pkt_dev->flows); - kfree(pkt_dev); - return -ENODEV; - } - - pe = create_proc_entry(ifname, 0600, pg_proc_dir); - if (!pe) { - printk("pktgen: cannot create %s/%s procfs entry.\n", + pkt_dev->vlan_p = 0; + pkt_dev->vlan_cfi = 0; + pkt_dev->vlan_id = 0xffff; + pkt_dev->svlan_p = 0; + pkt_dev->svlan_cfi = 0; + pkt_dev->svlan_id = 0xffff; + pkt_dev->node = -1; + + err = pktgen_setup_dev(t->net, pkt_dev, ifname); + if (err) + goto out1; + if (pkt_dev->odev->priv_flags & IFF_TX_SKB_SHARING) + pkt_dev->clone_skb = pg_clone_skb_d; + + pkt_dev->entry = proc_create_data(ifname, 0600, t->net->proc_dir, + &pktgen_if_fops, pkt_dev); + if (!pkt_dev->entry) { + pr_err("cannot create %s/%s procfs entry\n", PG_PROC_DIR, ifname); - if (pkt_dev->flows) - vfree(pkt_dev->flows); - kfree(pkt_dev); - return -EINVAL; + err = -EINVAL; + goto out2; } - pe->proc_fops = &pktgen_if_fops; - pe->data = pkt_dev; +#ifdef CONFIG_XFRM + pkt_dev->ipsmode = XFRM_MODE_TRANSPORT; + pkt_dev->ipsproto = IPPROTO_ESP; + + /* xfrm tunnel mode needs additional dst to extract outter + * ip header protocol/ttl/id field, here creat a phony one. + * instead of looking for a valid rt, which definitely hurting + * performance under such circumstance. + */ + pkt_dev->dstops.family = AF_INET; + pkt_dev->dst.dev = pkt_dev->odev; + dst_init_metrics(&pkt_dev->dst, pktgen_dst_metrics, false); + pkt_dev->dst.child = &pkt_dev->dst; + pkt_dev->dst.ops = &pkt_dev->dstops; +#endif return add_dev_to_thread(t, pkt_dev); +out2: + dev_put(pkt_dev->odev); +out1: +#ifdef CONFIG_XFRM + free_SAs(pkt_dev); +#endif + vfree(pkt_dev->flows); + kfree(pkt_dev); + return err; } -static struct pktgen_thread *__init pktgen_find_thread(const char *name) +static int __net_init pktgen_create_thread(int cpu, struct pktgen_net *pn) { struct pktgen_thread *t; - - mutex_lock(&pktgen_thread_lock); - - list_for_each_entry(t, &pktgen_threads, th_list) - if (strcmp(t->name, name) == 0) { - mutex_unlock(&pktgen_thread_lock); - return t; - } - - mutex_unlock(&pktgen_thread_lock); - return NULL; -} - -static int __init pktgen_create_thread(const char *name, int cpu) -{ - int err; - struct pktgen_thread *t = NULL; struct proc_dir_entry *pe; + struct task_struct *p; - if (strlen(name) > 31) { - printk("pktgen: ERROR: Thread name cannot be more than 31 characters.\n"); - return -EINVAL; - } - - if (pktgen_find_thread(name)) { - printk("pktgen: ERROR: thread: %s already exists\n", name); - return -EINVAL; - } - - t = kzalloc(sizeof(struct pktgen_thread), GFP_KERNEL); + t = kzalloc_node(sizeof(struct pktgen_thread), GFP_KERNEL, + cpu_to_node(cpu)); if (!t) { - printk("pktgen: ERROR: out of memory, can't create new thread.\n"); + pr_err("ERROR: out of memory, can't create new thread\n"); return -ENOMEM; } - strcpy(t->name, name); spin_lock_init(&t->if_lock); t->cpu = cpu; - pe = create_proc_entry(t->name, 0600, pg_proc_dir); - if (!pe) { - printk("pktgen: cannot create %s/%s procfs entry.\n", - PG_PROC_DIR, t->name); - kfree(t); - return -EINVAL; - } - - pe->proc_fops = &pktgen_thread_fops; - pe->data = t; - INIT_LIST_HEAD(&t->if_list); - list_add_tail(&t->th_list, &pktgen_threads); + list_add_tail(&t->th_list, &pn->pktgen_threads); + init_completion(&t->start_done); - t->removed = 0; + p = kthread_create_on_node(pktgen_thread_worker, + t, + cpu_to_node(cpu), + "kpktgend_%d", cpu); + if (IS_ERR(p)) { + pr_err("kernel_thread() failed for cpu %d\n", t->cpu); + list_del(&t->th_list); + kfree(t); + return PTR_ERR(p); + } + kthread_bind(p, cpu); + t->tsk = p; - err = kernel_thread((void *)pktgen_thread_worker, (void *)t, - CLONE_FS | CLONE_FILES | CLONE_SIGHAND); - if (err < 0) { - printk("pktgen: kernel_thread() failed for cpu %d\n", t->cpu); - remove_proc_entry(t->name, pg_proc_dir); + pe = proc_create_data(t->tsk->comm, 0600, pn->proc_dir, + &pktgen_thread_fops, t); + if (!pe) { + pr_err("cannot create %s/%s procfs entry\n", + PG_PROC_DIR, t->tsk->comm); + kthread_stop(p); list_del(&t->th_list); kfree(t); - return err; + return -EINVAL; } + t->net = pn; + wake_up_process(p); + wait_for_completion(&t->start_done); + return 0; } -/* - * Removes a device from the thread if_list. +/* + * Removes a device from the thread if_list. */ static void _rem_dev_from_if_list(struct pktgen_thread *t, struct pktgen_dev *pkt_dev) @@ -3293,11 +3685,10 @@ static void _rem_dev_from_if_list(struct pktgen_thread *t, static int pktgen_remove_device(struct pktgen_thread *t, struct pktgen_dev *pkt_dev) { - - PG_DEBUG(printk("pktgen: remove_device pkt_dev=%p\n", pkt_dev)); + pr_debug("remove_device pkt_dev=%p\n", pkt_dev); if (pkt_dev->running) { - printk("pktgen:WARNING: trying to remove a running interface, stopping it now.\n"); + pr_warning("WARNING: trying to remove a running interface, stopping it now\n"); pktgen_stop_device(pkt_dev); } @@ -3312,95 +3703,129 @@ static int pktgen_remove_device(struct pktgen_thread *t, _rem_dev_from_if_list(t, pkt_dev); - /* Clean up proc file system */ - - remove_proc_entry(pkt_dev->ifname, pg_proc_dir); + if (pkt_dev->entry) + proc_remove(pkt_dev->entry); - if (pkt_dev->flows) - vfree(pkt_dev->flows); +#ifdef CONFIG_XFRM + free_SAs(pkt_dev); +#endif + vfree(pkt_dev->flows); + if (pkt_dev->page) + put_page(pkt_dev->page); kfree(pkt_dev); return 0; } -static int __init pg_init(void) +static int __net_init pg_net_init(struct net *net) { - int cpu; + struct pktgen_net *pn = net_generic(net, pg_net_id); struct proc_dir_entry *pe; - - printk(version); - - pg_proc_dir = proc_mkdir(PG_PROC_DIR, proc_net); - if (!pg_proc_dir) + int cpu, ret = 0; + + pn->net = net; + INIT_LIST_HEAD(&pn->pktgen_threads); + pn->pktgen_exiting = false; + pn->proc_dir = proc_mkdir(PG_PROC_DIR, pn->net->proc_net); + if (!pn->proc_dir) { + pr_warn("cannot create /proc/net/%s\n", PG_PROC_DIR); return -ENODEV; - pg_proc_dir->owner = THIS_MODULE; - - pe = create_proc_entry(PGCTRL, 0600, pg_proc_dir); + } + pe = proc_create(PGCTRL, 0600, pn->proc_dir, &pktgen_fops); if (pe == NULL) { - printk("pktgen: ERROR: cannot create %s procfs entry.\n", - PGCTRL); - proc_net_remove(PG_PROC_DIR); - return -EINVAL; + pr_err("cannot create %s procfs entry\n", PGCTRL); + ret = -EINVAL; + goto remove; } - pe->proc_fops = &pktgen_fops; - pe->data = NULL; - - /* Register us to receive netdevice events */ - register_netdevice_notifier(&pktgen_notifier_block); - for_each_online_cpu(cpu) { int err; - char buf[30]; - sprintf(buf, "kpktgend_%i", cpu); - err = pktgen_create_thread(buf, cpu); + err = pktgen_create_thread(cpu, pn); if (err) - printk("pktgen: WARNING: Cannot create thread for cpu %d (%d)\n", - cpu, err); + pr_warn("Cannot create thread for cpu %d (%d)\n", + cpu, err); } - if (list_empty(&pktgen_threads)) { - printk("pktgen: ERROR: Initialization failed for all threads\n"); - unregister_netdevice_notifier(&pktgen_notifier_block); - remove_proc_entry(PGCTRL, pg_proc_dir); - proc_net_remove(PG_PROC_DIR); - return -ENODEV; + if (list_empty(&pn->pktgen_threads)) { + pr_err("Initialization failed for all threads\n"); + ret = -ENODEV; + goto remove_entry; } return 0; + +remove_entry: + remove_proc_entry(PGCTRL, pn->proc_dir); +remove: + remove_proc_entry(PG_PROC_DIR, pn->net->proc_net); + return ret; } -static void __exit pg_cleanup(void) +static void __net_exit pg_net_exit(struct net *net) { + struct pktgen_net *pn = net_generic(net, pg_net_id); struct pktgen_thread *t; struct list_head *q, *n; - wait_queue_head_t queue; - init_waitqueue_head(&queue); + LIST_HEAD(list); /* Stop all interfaces & threads */ + pn->pktgen_exiting = true; - list_for_each_safe(q, n, &pktgen_threads) { - t = list_entry(q, struct pktgen_thread, th_list); - t->control |= (T_TERMINATE); + mutex_lock(&pktgen_thread_lock); + list_splice_init(&pn->pktgen_threads, &list); + mutex_unlock(&pktgen_thread_lock); - wait_event_interruptible_timeout(queue, (t->removed == 1), HZ); + list_for_each_safe(q, n, &list) { + t = list_entry(q, struct pktgen_thread, th_list); + list_del(&t->th_list); + kthread_stop(t->tsk); + kfree(t); } - /* Un-register us from receiving netdevice events */ - unregister_netdevice_notifier(&pktgen_notifier_block); + remove_proc_entry(PGCTRL, pn->proc_dir); + remove_proc_entry(PG_PROC_DIR, pn->net->proc_net); +} + +static struct pernet_operations pg_net_ops = { + .init = pg_net_init, + .exit = pg_net_exit, + .id = &pg_net_id, + .size = sizeof(struct pktgen_net), +}; + +static int __init pg_init(void) +{ + int ret = 0; - /* Clean up proc file system */ - remove_proc_entry(PGCTRL, pg_proc_dir); - proc_net_remove(PG_PROC_DIR); + pr_info("%s", version); + ret = register_pernet_subsys(&pg_net_ops); + if (ret) + return ret; + ret = register_netdevice_notifier(&pktgen_notifier_block); + if (ret) + unregister_pernet_subsys(&pg_net_ops); + + return ret; +} + +static void __exit pg_cleanup(void) +{ + unregister_netdevice_notifier(&pktgen_notifier_block); + unregister_pernet_subsys(&pg_net_ops); } module_init(pg_init); module_exit(pg_cleanup); -MODULE_AUTHOR("Robert Olsson <robert.olsson@its.uu.se"); +MODULE_AUTHOR("Robert Olsson <robert.olsson@its.uu.se>"); MODULE_DESCRIPTION("Packet Generator tool"); MODULE_LICENSE("GPL"); +MODULE_VERSION(VERSION); module_param(pg_count_d, int, 0); +MODULE_PARM_DESC(pg_count_d, "Default number of packets to inject"); module_param(pg_delay_d, int, 0); +MODULE_PARM_DESC(pg_delay_d, "Default delay between packets (nanoseconds)"); module_param(pg_clone_skb_d, int, 0); +MODULE_PARM_DESC(pg_clone_skb_d, "Default number of copies of the same packet"); module_param(debug, int, 0); +MODULE_PARM_DESC(debug, "Enable debugging of pktgen module"); |