diff options
386 files changed, 28243 insertions, 5906 deletions
diff --git a/Documentation/SubmittingDrivers b/Documentation/SubmittingDrivers index dd311cff1cc..6bd30fdd078 100644 --- a/Documentation/SubmittingDrivers +++ b/Documentation/SubmittingDrivers @@ -143,7 +143,7 @@ KernelNewbies: http://kernelnewbies.org/ Linux USB project: - http://linux-usb.sourceforge.net/ + http://www.linux-usb.org/ How to NOT write kernel driver by arjanv@redhat.com http://people.redhat.com/arjanv/olspaper.pdf diff --git a/Documentation/SubmittingPatches b/Documentation/SubmittingPatches index 6198e5ebcf6..c2c85bcb3d4 100644 --- a/Documentation/SubmittingPatches +++ b/Documentation/SubmittingPatches @@ -478,10 +478,11 @@ Andrew Morton, "The perfect patch" (tpp). Jeff Garzik, "Linux kernel patch submission format." <http://linux.yyz.us/patch-format.html> -Greg Kroah, "How to piss off a kernel subsystem maintainer". +Greg Kroah-Hartman "How to piss off a kernel subsystem maintainer". <http://www.kroah.com/log/2005/03/31/> <http://www.kroah.com/log/2005/07/08/> <http://www.kroah.com/log/2005/10/19/> + <http://www.kroah.com/log/2006/01/11/> NO!!!! No more huge patch bombs to linux-kernel@vger.kernel.org people!. <http://marc.theaimsgroup.com/?l=linux-kernel&m=112112749912944&w=2> diff --git a/MAINTAINERS b/MAINTAINERS index 0db72a36e24..71693c5c313 100644 --- a/MAINTAINERS +++ b/MAINTAINERS @@ -2519,6 +2519,19 @@ P: Romain Lievin M: roms@lpg.ticalc.org S: Maintained +TIPC NETWORK LAYER +P: Per Liden +M: per.liden@nospam.ericsson.com +P: Jon Maloy +M: jon.maloy@nospam.ericsson.com +P: Allan Stephens +M: allan.stephens@nospam.windriver.com +L: tipc-discussion@lists.sourceforge.net +W: http://tipc.sourceforge.net/ +W: http://tipc.cslab.ericsson.net/ +T: git tipc.cslab.ericsson.net:/pub/git/tipc.git +S: Maintained + TLAN NETWORK DRIVER P: Samuel Chessman M: chessman@tux.org diff --git a/arch/ia64/hp/sim/simserial.c b/arch/ia64/hp/sim/simserial.c index a346e1833bf..626cdc83668 100644 --- a/arch/ia64/hp/sim/simserial.c +++ b/arch/ia64/hp/sim/simserial.c @@ -108,7 +108,6 @@ static struct async_struct *IRQ_ports[NR_IRQS]; static struct console *console; static unsigned char *tmp_buf; -static DECLARE_MUTEX(tmp_buf_sem); extern struct console *console_drivers; /* from kernel/printk.c */ @@ -167,15 +166,9 @@ static void receive_chars(struct tty_struct *tty, struct pt_regs *regs) } } seen_esc = 0; - if (tty->flip.count >= TTY_FLIPBUF_SIZE) break; - *tty->flip.char_buf_ptr = ch; - - *tty->flip.flag_buf_ptr = 0; - - tty->flip.flag_buf_ptr++; - tty->flip.char_buf_ptr++; - tty->flip.count++; + if (tty_insert_flip_char(tty, ch, TTY_NORMAL) == 0) + break; } tty_flip_buffer_push(tty); } diff --git a/arch/ia64/kernel/fsys.S b/arch/ia64/kernel/fsys.S index 2ddbac6f499..ce423910ca9 100644 --- a/arch/ia64/kernel/fsys.S +++ b/arch/ia64/kernel/fsys.S @@ -903,5 +903,6 @@ fsyscall_table: data8 0 data8 0 data8 0 + data8 0 // 1280 .org fsyscall_table + 8*NR_syscalls // guard against failures to increase NR_syscalls diff --git a/arch/ia64/kernel/jprobes.S b/arch/ia64/kernel/jprobes.S index 2323377e369..5cd6226f44f 100644 --- a/arch/ia64/kernel/jprobes.S +++ b/arch/ia64/kernel/jprobes.S @@ -60,3 +60,30 @@ END(jprobe_break) GLOBAL_ENTRY(jprobe_inst_return) br.call.sptk.many b0=jprobe_break END(jprobe_inst_return) + +GLOBAL_ENTRY(invalidate_stacked_regs) + movl r16=invalidate_restore_cfm + ;; + mov b6=r16 + ;; + br.ret.sptk.many b6 + ;; +invalidate_restore_cfm: + mov r16=ar.rsc + ;; + mov ar.rsc=r0 + ;; + loadrs + ;; + mov ar.rsc=r16 + ;; + br.cond.sptk.many rp +END(invalidate_stacked_regs) + +GLOBAL_ENTRY(flush_register_stack) + // flush dirty regs to backing store (must be first in insn group) + flushrs + ;; + br.ret.sptk.many rp +END(flush_register_stack) + diff --git a/arch/ia64/kernel/kprobes.c b/arch/ia64/kernel/kprobes.c index 346fedf9ea4..50ae8c7d453 100644 --- a/arch/ia64/kernel/kprobes.c +++ b/arch/ia64/kernel/kprobes.c @@ -766,11 +766,56 @@ int __kprobes kprobe_exceptions_notify(struct notifier_block *self, return ret; } +struct param_bsp_cfm { + unsigned long ip; + unsigned long *bsp; + unsigned long cfm; +}; + +static void ia64_get_bsp_cfm(struct unw_frame_info *info, void *arg) +{ + unsigned long ip; + struct param_bsp_cfm *lp = arg; + + do { + unw_get_ip(info, &ip); + if (ip == 0) + break; + if (ip == lp->ip) { + unw_get_bsp(info, (unsigned long*)&lp->bsp); + unw_get_cfm(info, (unsigned long*)&lp->cfm); + return; + } + } while (unw_unwind(info) >= 0); + lp->bsp = 0; + lp->cfm = 0; + return; +} + int __kprobes setjmp_pre_handler(struct kprobe *p, struct pt_regs *regs) { struct jprobe *jp = container_of(p, struct jprobe, kp); unsigned long addr = ((struct fnptr *)(jp->entry))->ip; struct kprobe_ctlblk *kcb = get_kprobe_ctlblk(); + struct param_bsp_cfm pa; + int bytes; + + /* + * Callee owns the argument space and could overwrite it, eg + * tail call optimization. So to be absolutely safe + * we save the argument space before transfering the control + * to instrumented jprobe function which runs in + * the process context + */ + pa.ip = regs->cr_iip; + unw_init_running(ia64_get_bsp_cfm, &pa); + bytes = (char *)ia64_rse_skip_regs(pa.bsp, pa.cfm & 0x3f) + - (char *)pa.bsp; + memcpy( kcb->jprobes_saved_stacked_regs, + pa.bsp, + bytes ); + kcb->bsp = pa.bsp; + kcb->cfm = pa.cfm; /* save architectural state */ kcb->jprobe_saved_regs = *regs; @@ -792,8 +837,20 @@ int __kprobes setjmp_pre_handler(struct kprobe *p, struct pt_regs *regs) int __kprobes longjmp_break_handler(struct kprobe *p, struct pt_regs *regs) { struct kprobe_ctlblk *kcb = get_kprobe_ctlblk(); + int bytes; + /* restoring architectural state */ *regs = kcb->jprobe_saved_regs; + + /* restoring the original argument space */ + flush_register_stack(); + bytes = (char *)ia64_rse_skip_regs(kcb->bsp, kcb->cfm & 0x3f) + - (char *)kcb->bsp; + memcpy( kcb->bsp, + kcb->jprobes_saved_stacked_regs, + bytes ); + invalidate_stacked_regs(); + preempt_enable_no_resched(); return 1; } diff --git a/arch/ia64/kernel/mca_asm.S b/arch/ia64/kernel/mca_asm.S index db32fc1d393..403a80a58c1 100644 --- a/arch/ia64/kernel/mca_asm.S +++ b/arch/ia64/kernel/mca_asm.S @@ -847,7 +847,7 @@ ia64_state_restore: ;; mov cr.iim=temp3 mov cr.iha=temp4 - dep r22=0,r22,62,2 // pal_min_state, physical, uncached + dep r22=0,r22,62,1 // pal_min_state, physical, uncached mov IA64_KR(CURRENT)=r21 ld8 r8=[temp1] // os_status ld8 r10=[temp2] // context diff --git a/arch/ia64/kernel/salinfo.c b/arch/ia64/kernel/salinfo.c index a87a162a308..9d5a823479a 100644 --- a/arch/ia64/kernel/salinfo.c +++ b/arch/ia64/kernel/salinfo.c @@ -3,7 +3,7 @@ * * Creates entries in /proc/sal for various system features. * - * Copyright (c) 2003 Silicon Graphics, Inc. All rights reserved. + * Copyright (c) 2003, 2006 Silicon Graphics, Inc. All rights reserved. * Copyright (c) 2003 Hewlett-Packard Co * Bjorn Helgaas <bjorn.helgaas@hp.com> * @@ -27,9 +27,17 @@ * mca.c may not pass a buffer, a NULL buffer just indicates that a new * record is available in SAL. * Replace some NR_CPUS by cpus_online, for hotplug cpu. + * + * Jan 5 2006 kaos@sgi.com + * Handle hotplug cpus coming online. + * Handle hotplug cpus going offline while they still have outstanding records. + * Use the cpu_* macros consistently. + * Replace the counting semaphore with a mutex and a test if the cpumask is non-empty. + * Modify the locking to make the test for "work to do" an atomic operation. */ #include <linux/capability.h> +#include <linux/cpu.h> #include <linux/types.h> #include <linux/proc_fs.h> #include <linux/module.h> @@ -132,8 +140,8 @@ enum salinfo_state { }; struct salinfo_data { - volatile cpumask_t cpu_event; /* which cpus have outstanding events */ - struct semaphore sem; /* count of cpus with outstanding events (bits set in cpu_event) */ + cpumask_t cpu_event; /* which cpus have outstanding events */ + struct semaphore mutex; u8 *log_buffer; u64 log_size; u8 *oemdata; /* decoded oem data */ @@ -174,6 +182,21 @@ struct salinfo_platform_oemdata_parms { int ret; }; +/* Kick the mutex that tells user space that there is work to do. Instead of + * trying to track the state of the mutex across multiple cpus, in user + * context, interrupt context, non-maskable interrupt context and hotplug cpu, + * it is far easier just to grab the mutex if it is free then release it. + * + * This routine must be called with data_saved_lock held, to make the down/up + * operation atomic. + */ +static void +salinfo_work_to_do(struct salinfo_data *data) +{ + down_trylock(&data->mutex); + up(&data->mutex); +} + static void salinfo_platform_oemdata_cpu(void *context) { @@ -212,9 +235,9 @@ salinfo_log_wakeup(int type, u8 *buffer, u64 size, int irqsafe) BUG_ON(type >= ARRAY_SIZE(salinfo_log_name)); + if (irqsafe) + spin_lock_irqsave(&data_saved_lock, flags); if (buffer) { - if (irqsafe) - spin_lock_irqsave(&data_saved_lock, flags); for (i = 0, data_saved = data->data_saved; i < saved_size; ++i, ++data_saved) { if (!data_saved->buffer) break; @@ -232,13 +255,11 @@ salinfo_log_wakeup(int type, u8 *buffer, u64 size, int irqsafe) data_saved->size = size; data_saved->buffer = buffer; } - if (irqsafe) - spin_unlock_irqrestore(&data_saved_lock, flags); } - - if (!test_and_set_bit(smp_processor_id(), &data->cpu_event)) { - if (irqsafe) - up(&data->sem); + cpu_set(smp_processor_id(), data->cpu_event); + if (irqsafe) { + salinfo_work_to_do(data); + spin_unlock_irqrestore(&data_saved_lock, flags); } } @@ -249,20 +270,17 @@ static struct timer_list salinfo_timer; static void salinfo_timeout_check(struct salinfo_data *data) { - int i; + unsigned long flags; if (!data->open) return; - for_each_online_cpu(i) { - if (test_bit(i, &data->cpu_event)) { - /* double up() is not a problem, user space will see no - * records for the additional "events". - */ - up(&data->sem); - } + if (!cpus_empty(data->cpu_event)) { + spin_lock_irqsave(&data_saved_lock, flags); + salinfo_work_to_do(data); + spin_unlock_irqrestore(&data_saved_lock, flags); } } -static void +static void salinfo_timeout (unsigned long arg) { salinfo_timeout_check(salinfo_data + SAL_INFO_TYPE_MCA); @@ -290,16 +308,20 @@ salinfo_event_read(struct file *file, char __user *buffer, size_t count, loff_t int i, n, cpu = -1; retry: - if (down_trylock(&data->sem)) { + if (cpus_empty(data->cpu_event) && down_trylock(&data->mutex)) { if (file->f_flags & O_NONBLOCK) return -EAGAIN; - if (down_interruptible(&data->sem)) + if (down_interruptible(&data->mutex)) return -EINTR; } n = data->cpu_check; for (i = 0; i < NR_CPUS; i++) { - if (test_bit(n, &data->cpu_event) && cpu_online(n)) { + if (cpu_isset(n, data->cpu_event)) { + if (!cpu_online(n)) { + cpu_clear(n, data->cpu_event); + continue; + } cpu = n; break; } @@ -310,9 +332,6 @@ retry: if (cpu == -1) goto retry; - /* events are sticky until the user says "clear" */ - up(&data->sem); - /* for next read, start checking at next CPU */ data->cpu_check = cpu; if (++data->cpu_check == NR_CPUS) @@ -381,10 +400,8 @@ salinfo_log_release(struct inode *inode, struct file *file) static void call_on_cpu(int cpu, void (*fn)(void *), void *arg) { - cpumask_t save_cpus_allowed, new_cpus_allowed; - memcpy(&save_cpus_allowed, ¤t->cpus_allowed, sizeof(save_cpus_allowed)); - memset(&new_cpus_allowed, 0, sizeof(new_cpus_allowed)); - set_bit(cpu, &new_cpus_allowed); + cpumask_t save_cpus_allowed = current->cpus_allowed; + cpumask_t new_cpus_allowed = cpumask_of_cpu(cpu); set_cpus_allowed(current, new_cpus_allowed); (*fn)(arg); set_cpus_allowed(current, save_cpus_allowed); @@ -433,10 +450,10 @@ retry: if (!data->saved_num) call_on_cpu(cpu, salinfo_log_read_cpu, data); if (!data->log_size) { - data->state = STATE_NO_DATA; - clear_bit(cpu, &data->cpu_event); + data->state = STATE_NO_DATA; + cpu_clear(cpu, data->cpu_event); } else { - data->state = STATE_LOG_RECORD; + data->state = STATE_LOG_RECORD; } } @@ -473,27 +490,31 @@ static int salinfo_log_clear(struct salinfo_data *data, int cpu) { sal_log_record_header_t *rh; + unsigned long flags; + spin_lock_irqsave(&data_saved_lock, flags); data->state = STATE_NO_DATA; - if (!test_bit(cpu, &data->cpu_event)) + if (!cpu_isset(cpu, data->cpu_event)) { + spin_unlock_irqrestore(&data_saved_lock, flags); return 0; - down(&data->sem); - clear_bit(cpu, &data->cpu_event); + } + cpu_clear(cpu, data->cpu_event); if (data->saved_num) { - unsigned long flags; - spin_lock_irqsave(&data_saved_lock, flags); - shift1_data_saved(data, data->saved_num - 1 ); + shift1_data_saved(data, data->saved_num - 1); data->saved_num = 0; - spin_unlock_irqrestore(&data_saved_lock, flags); } + spin_unlock_irqrestore(&data_saved_lock, flags); rh = (sal_log_record_header_t *)(data->log_buffer); /* Corrected errors have already been cleared from SAL */ if (rh->severity != sal_log_severity_corrected) call_on_cpu(cpu, salinfo_log_clear_cpu, data); /* clearing a record may make a new record visible */ salinfo_log_new_read(cpu, data); - if (data->state == STATE_LOG_RECORD && - !test_and_set_bit(cpu, &data->cpu_event)) - up(&data->sem); + if (data->state == STATE_LOG_RECORD) { + spin_lock_irqsave(&data_saved_lock, flags); + cpu_set(cpu, data->cpu_event); + salinfo_work_to_do(data); + spin_unlock_irqrestore(&data_saved_lock, flags); + } return 0; } @@ -550,6 +571,53 @@ static struct file_operations salinfo_data_fops = { .write = salinfo_log_write, }; +#ifdef CONFIG_HOTPLUG_CPU +static int __devinit +salinfo_cpu_callback(struct notifier_block *nb, unsigned long action, void *hcpu) +{ + unsigned int i, cpu = (unsigned long)hcpu; + unsigned long flags; + struct salinfo_data *data; + switch (action) { + case CPU_ONLINE: + spin_lock_irqsave(&data_saved_lock, flags); + for (i = 0, data = salinfo_data; + i < ARRAY_SIZE(salinfo_data); + ++i, ++data) { + cpu_set(cpu, data->cpu_event); + salinfo_work_to_do(data); + } + spin_unlock_irqrestore(&data_saved_lock, flags); + break; + case CPU_DEAD: + spin_lock_irqsave(&data_saved_lock, flags); + for (i = 0, data = salinfo_data; + i < ARRAY_SIZE(salinfo_data); + ++i, ++data) { + struct salinfo_data_saved *data_saved; + int j; + for (j = ARRAY_SIZE(data->data_saved) - 1, data_saved = data->data_saved + j; + j >= 0; + --j, --data_saved) { + if (data_saved->buffer && data_saved->cpu == cpu) { + shift1_data_saved(data, j); + } + } + cpu_clear(cpu, data->cpu_event); + } + spin_unlock_irqrestore(&data_saved_lock, flags); + break; + } + return NOTIFY_OK; +} + +static struct notifier_block salinfo_cpu_notifier = +{ + .notifier_call = salinfo_cpu_callback, + .priority = 0, +}; +#endif /* CONFIG_HOTPLUG_CPU */ + static int __init salinfo_init(void) { @@ -557,7 +625,7 @@ salinfo_init(void) struct proc_dir_entry **sdir = salinfo_proc_entries; /* keeps track of every entry */ struct proc_dir_entry *dir, *entry; struct salinfo_data *data; - int i, j, online; + int i, j; salinfo_dir = proc_mkdir("sal", NULL); if (!salinfo_dir) @@ -572,7 +640,7 @@ salinfo_init(void) for (i = 0; i < ARRAY_SIZE(salinfo_log_name); i++) { data = salinfo_data + i; data->type = i; - sema_init(&data->sem, 0); + init_MUTEX(&data->mutex); dir = proc_mkdir(salinfo_log_name[i], salinfo_dir); if (!dir) continue; @@ -592,12 +660,8 @@ salinfo_init(void) *sdir++ = entry; /* we missed any events before now */ - online = 0; - for_each_online_cpu(j) { - set_bit(j, &data->cpu_event); - ++online; - } - sema_init(&data->sem, online); + for_each_online_cpu(j) + cpu_set(j, data->cpu_event); *sdir++ = dir; } @@ -609,6 +673,10 @@ salinfo_init(void) salinfo_timer.function = &salinfo_timeout; add_timer(&salinfo_timer); +#ifdef CONFIG_HOTPLUG_CPU + register_cpu_notifier(&salinfo_cpu_notifier); +#endif + return 0; } diff --git a/arch/ia64/kernel/traps.c b/arch/ia64/kernel/traps.c index d3e0ecb56d6..55391901b01 100644 --- a/arch/ia64/kernel/traps.c +++ b/arch/ia64/kernel/traps.c @@ -530,12 +530,15 @@ ia64_fault (unsigned long vector, unsigned long isr, unsigned long ifa, if (fsys_mode(current, ®s)) { extern char __kernel_syscall_via_break[]; /* - * Got a trap in fsys-mode: Taken Branch Trap and Single Step trap - * need special handling; Debug trap is not supposed to happen. + * Got a trap in fsys-mode: Taken Branch Trap + * and Single Step trap need special handling; + * Debug trap is ignored (we disable it here + * and re-enable it in the lower-privilege trap). */ if (unlikely(vector == 29)) { - die("Got debug trap in fsys-mode---not supposed to happen!", - ®s, 0); + set_thread_flag(TIF_DB_DISABLED); + ia64_psr(®s)->db = 0; + ia64_psr(®s)->lp = 1; return; } /* re-do the system call via break 0x100000: */ @@ -589,10 +592,19 @@ ia64_fault (unsigned long vector, unsigned long isr, unsigned long ifa, case 34: if (isr & 0x2) { /* Lower-Privilege Transfer Trap */ + + /* If we disabled debug traps during an fsyscall, + * re-enable them here. + */ + if (test_thread_flag(TIF_DB_DISABLED)) { + clear_thread_flag(TIF_DB_DISABLED); + ia64_psr(®s)->db = 1; + } + /* - * Just clear PSR.lp and then return immediately: all the - * interesting work (e.g., signal delivery is done in the kernel - * exit path). + * Just clear PSR.lp and then return immediately: + * all the interesting work (e.g., signal delivery) + * is done in the kernel exit path. */ ia64_psr(®s)->lp = 0; return; diff --git a/arch/ia64/mm/tlb.c b/arch/ia64/mm/tlb.c index 41105d45442..6a4eec9113e 100644 --- a/arch/ia64/mm/tlb.c +++ b/arch/ia64/mm/tlb.c @@ -90,7 +90,7 @@ ia64_global_tlb_purge (struct mm_struct *mm, unsigned long start, { static DEFINE_SPINLOCK(ptcg_lock); - if (mm != current->active_mm) { + if (mm != current->active_mm || !current->mm) { flush_tlb_all(); return; } diff --git a/arch/ia64/sn/include/xtalk/hubdev.h b/arch/ia64/sn/include/xtalk/hubdev.h index 71c2b271b4c..4d417c30120 100644 --- a/arch/ia64/sn/include/xtalk/hubdev.h +++ b/arch/ia64/sn/include/xtalk/hubdev.h @@ -26,11 +26,14 @@ #define IIO_NUM_ITTES 7 #define HUB_NUM_BIG_WINDOW (IIO_NUM_ITTES - 1) -struct sn_flush_device_list { +/* This struct is shared between the PROM and the kernel. + * Changes to this struct will require corresponding changes to the kernel. + */ +struct sn_flush_device_common { int sfdl_bus; int sfdl_slot; int sfdl_pin; - struct bar_list { + struct common_bar_list { unsigned long start; unsigned long end; } sfdl_bar_list[6]; @@ -40,14 +43,19 @@ struct sn_flush_device_list { uint32_t sfdl_persistent_busnum; uint32_t sfdl_persistent_segment; struct pcibus_info *sfdl_pcibus_info; +}; + +/* This struct is kernel only and is not used by the PROM */ +struct sn_flush_device_kernel { spinlock_t sfdl_flush_lock; + struct sn_flush_device_common *common; }; /* - * **widget_p - Used as an array[wid_num][device] of sn_flush_device_list. + * **widget_p - Used as an array[wid_num][device] of sn_flush_device_kernel. */ struct sn_flush_nasid_entry { - struct sn_flush_device_list **widget_p; /* Used as a array of wid_num */ + struct sn_flush_device_kernel **widget_p; // Used as an array of wid_num uint64_t iio_itte[8]; }; diff --git a/arch/ia64/sn/kernel/bte_error.c b/arch/ia64/sn/kernel/bte_error.c index fcbc748ae43..f1ec1370b3e 100644 --- a/arch/ia64/sn/kernel/bte_error.c +++ b/arch/ia64/sn/kernel/bte_error.c @@ -33,7 +33,7 @@ void bte_error_handler(unsigned long); * Wait until all BTE related CRBs are completed * and then reset the interfaces. */ -void shub1_bte_error_handler(unsigned long _nodepda) +int shub1_bte_error_handler(unsigned long _nodepda) { struct nodepda_s *err_nodepda = (struct nodepda_s *)_nodepda; struct timer_list *recovery_timer = &err_nodepda->bte_recovery_timer; @@ -53,7 +53,7 @@ void shub1_bte_error_handler(unsigned long _nodepda) (err_nodepda->bte_if[1].bh_error == BTE_SUCCESS)) { BTE_PRINTK(("eh:%p:%d Nothing to do.\n", err_nodepda, smp_processor_id())); - return; + return 1; } /* Determine information about our hub */ @@ -81,7 +81,7 @@ void shub1_bte_error_handler(unsigned long _nodepda) mod_timer(recovery_timer, HZ * 5); BTE_PRINTK(("eh:%p:%d Marked Giving up\n", err_nodepda, smp_processor_id())); - return; + return 1; } if (icmr.ii_icmr_fld_s.i_crb_vld != 0) { @@ -99,7 +99,7 @@ void shub1_bte_error_handler(unsigned long _nodepda) BTE_PRINTK(("eh:%p:%d Valid %d, Giving up\n", err_nodepda, smp_processor_id(), i)); - return; + return 1; } } } @@ -124,6 +124,42 @@ void shub1_bte_error_handler(unsigned long _nodepda) REMOTE_HUB_S(nasid, IIO_IBCR, ibcr.ii_ibcr_regval); del_timer(recovery_timer); + return 0; +} + +/* + * Wait until all BTE related CRBs are completed + * and then reset the interfaces. + */ +int shub2_bte_error_handler(unsigned long _nodepda) +{ + struct nodepda_s *err_nodepda = (struct nodepda_s *)_nodepda; + struct timer_list *recovery_timer = &err_nodepda->bte_recovery_timer; + struct bteinfo_s *bte; + nasid_t nasid; + u64 status; + int i; + + nasid = cnodeid_to_nasid(err_nodepda->bte_if[0].bte_cnode); + + /* + * Verify that all the BTEs are complete + */ + for (i = 0; i < BTES_PER_NODE; i++) { + bte = &err_nodepda->bte_if[i]; + status = BTE_LNSTAT_LOAD(bte); + if ((status & IBLS_ERROR) || !(status & IBLS_BUSY)) + continue; + mod_timer(recovery_timer, HZ * 5); + BTE_PRINTK(("eh:%p:%d Marked Giving up\n", err_nodepda, + smp_processor_id())); + return 1; + } + if (ia64_sn_bte_recovery(nasid)) + panic("bte_error_handler(): Fatal BTE Error"); + + del_timer(recovery_timer); + return 0; } /* @@ -135,7 +171,6 @@ void bte_error_handler(unsigned long _nodepda) struct nodepda_s *err_nodepda = (struct nodepda_s *)_nodepda; spinlock_t *recovery_lock = &err_nodepda->bte_recovery_lock; int i; - nasid_t nasid; unsigned long irq_flags; volatile u64 *notify; bte_result_t bh_error; @@ -160,12 +195,15 @@ void bte_error_handler(unsigned long _nodepda) } if (is_shub1()) { - shub1_bte_error_handler(_nodepda); + if (shub1_bte_error_handler(_nodepda)) { + spin_unlock_irqrestore(recovery_lock, irq_flags); + return; + } } else { - nasid = cnodeid_to_nasid(err_nodepda->bte_if[0].bte_cnode); - - if (ia64_sn_bte_recovery(nasid)) - panic("bte_error_handler(): Fatal BTE Error"); + if (shub2_bte_error_handler(_nodepda)) { + spin_unlock_irqrestore(recovery_lock, irq_flags); + return; + } } for (i = 0; i < BTES_PER_NODE; i++) { diff --git a/arch/ia64/sn/kernel/huberror.c b/arch/ia64/sn/kernel/huberror.c index 5c5eb01c50f..56ab6bae00e 100644 --- a/arch/ia64/sn/kernel/huberror.c +++ b/arch/ia64/sn/kernel/huberror.c @@ -32,13 +32,14 @@ static irqreturn_t hub_eint_handler(int irq, void *arg, struct pt_regs *ep) ret_stuff.v0 = 0; hubdev_info = (struct hubdev_info *)arg; nasid = hubdev_info->hdi_nasid; - SAL_CALL_NOLOCK(ret_stuff, SN_SAL_HUB_ERROR_INTERRUPT, + + if (is_shub1()) { + SAL_CALL_NOLOCK(ret_stuff, SN_SAL_HUB_ERROR_INTERRUPT, (u64) nasid, 0, 0, 0, 0, 0, 0); - if ((int)ret_stuff.v0) - panic("hubii_eint_handler(): Fatal TIO Error"); + if ((int)ret_stuff.v0) + panic("hubii_eint_handler(): Fatal TIO Error"); - if (is_shub1()) { if (!(nasid & 1)) /* Not a TIO, handle CRB errors */ (void)hubiio_crb_error_handler(hubdev_info); } else diff --git a/arch/ia64/sn/kernel/io_init.c b/arch/ia64/sn/kernel/io_init.c index 318087e35b6..258d9d7aff9 100644 --- a/arch/ia64/sn/kernel/io_init.c +++ b/arch/ia64/sn/kernel/io_init.c @@ -76,11 +76,12 @@ static struct sn_pcibus_provider sn_pci_default_provider = { }; /* - * Retrieve the DMA Flush List given nasid. This list is needed - * to implement the WAR - Flush DMA data on PIO Reads. + * Retrieve the DMA Flush List given nasid, widget, and device. + * This list is needed to implement the WAR - Flush DMA data on PIO Reads. */ -static inline uint64_t -sal_get_widget_dmaflush_list(u64 nasid, u64 widget_num, u64 address) +static inline u64 +sal_get_device_dmaflush_list(u64 nasid, u64 widget_num, u64 device_num, + u64 address) { struct ia64_sal_retval ret_stuff; @@ -88,17 +89,17 @@ sal_get_widget_dmaflush_list(u64 nasid, u64 widget_num, u64 address) ret_stuff.v0 = 0; SAL_CALL_NOLOCK(ret_stuff, - (u64) SN_SAL_IOIF_GET_WIDGET_DMAFLUSH_LIST, - (u64) nasid, (u64) widget_num, (u64) address, 0, 0, 0, - 0); - return ret_stuff.v0; + (u64) SN_SAL_IOIF_GET_DEVICE_DMAFLUSH_LIST, + (u64) nasid, (u64) widget_num, + (u64) device_num, (u64) address, 0, 0, 0); + return ret_stuff.status; } /* * Retrieve the hub device info structure for the given nasid. */ -static inline uint64_t sal_get_hubdev_info(u64 handle, u64 address) +static inline u64 sal_get_hubdev_info(u64 handle, u64 address) { struct ia64_sal_retval ret_stuff; @@ -114,7 +115,7 @@ static inline uint64_t sal_get_hubdev_info(u64 handle, u64 address) /* * Retrieve the pci bus information given the bus number. */ -static inline uint64_t sal_get_pcibus_info(u64 segment, u64 busnum, u64 address) +static inline u64 sal_get_pcibus_info(u64 segment, u64 busnum, u64 address) { struct ia64_sal_retval ret_stuff; @@ -130,7 +131,7 @@ static inline uint64_t sal_get_pcibus_info(u64 segment, u64 busnum, u64 address) /* * Retrieve the pci device information given the bus and device|function number. */ -static inline uint64_t +static inline u64 sal_get_pcidev_info(u64 segment, u64 bus_number, u64 devfn, u64 pci_dev, u64 sn_irq_info) { @@ -170,12 +171,12 @@ sn_pcidev_info_get(struct pci_dev *dev) */ static void sn_fixup_ionodes(void) { - - struct sn_flush_device_list *sn_flush_device_list; + struct sn_flush_device_kernel *sn_flush_device_kernel; + struct sn_flush_device_kernel *dev_entry; struct hubdev_info *hubdev; - uint64_t status; - uint64_t nasid; - int i, widget; + u64 status; + u64 nasid; + int i, widget, device; /* * Get SGI Specific HUB chipset information. @@ -186,7 +187,7 @@ static void sn_fixup_ionodes(void) nasid = cnodeid_to_nasid(i); hubdev->max_segment_number = 0xffffffff; hubdev->max_pcibus_number = 0xff; - status = sal_get_hubdev_info(nasid, (uint64_t) __pa(hubdev)); + status = sal_get_hubdev_info(nasid, (u64) __pa(hubdev)); if (status) continue; @@ -213,38 +214,49 @@ static void sn_fixup_ionodes(void) hubdev->hdi_flush_nasid_list.widget_p = kmalloc((HUB_WIDGET_ID_MAX + 1) * - sizeof(struct sn_flush_device_list *), GFP_KERNEL); - + sizeof(struct sn_flush_device_kernel *), + GFP_KERNEL); memset(hubdev->hdi_flush_nasid_list.widget_p, 0x0, (HUB_WIDGET_ID_MAX + 1) * - sizeof(struct sn_flush_device_list *)); + sizeof(struct sn_flush_device_kernel *)); for (widget = 0; widget <= HUB_WIDGET_ID_MAX; widget++) { - sn_flush_device_list = kmalloc(DEV_PER_WIDGET * - sizeof(struct - sn_flush_device_list), - GFP_KERNEL); - memset(sn_flush_device_list, 0x0, + sn_flush_device_kernel = kmalloc(DEV_PER_WIDGET * + sizeof(struct + sn_flush_device_kernel), + GFP_KERNEL); + if (!sn_flush_device_kernel) + BUG(); + memset(sn_flush_device_kernel, 0x0, DEV_PER_WIDGET * - sizeof(struct sn_flush_device_list)); - - status = - sal_get_widget_dmaflush_list(nasid, widget, - (uint64_t) - __pa - (sn_flush_device_list)); - if (status) { - kfree(sn_flush_device_list); - continue; + sizeof(struct sn_flush_device_kernel)); + + dev_entry = sn_flush_device_kernel; + for (device = 0; device < DEV_PER_WIDGET; + device++,dev_entry++) { + dev_entry->common = kmalloc(sizeof(struct + sn_flush_device_common), + GFP_KERNEL); + if (!dev_entry->common) + BUG(); + memset(dev_entry->common, 0x0, sizeof(struct + sn_flush_device_common)); + + status = sal_get_device_dmaflush_list(nasid, + widget, + device, + (u64)(dev_entry->common)); + if (status) + BUG(); + + spin_lock_init(&dev_entry->sfdl_flush_lock); } - spin_lock_init(&sn_flush_device_list->sfdl_flush_lock); - hubdev->hdi_flush_nasid_list.widget_p[widget] = - sn_flush_device_list; - } - + if (sn_flush_device_kernel) + hubdev->hdi_flush_nasid_list.widget_p[widget] = + sn_flush_device_kernel; + } } - } /* diff --git a/arch/ia64/sn/kernel/xpc_channel.c b/arch/ia64/sn/kernel/xpc_channel.c index abf4fc2a87b..0c0a6890240 100644 --- a/arch/ia64/sn/kernel/xpc_channel.c +++ b/arch/ia64/sn/kernel/xpc_channel.c @@ -3,7 +3,7 @@ * License. See the file "COPYING" in the main directory of this archive * for more details. * - * Copyright (c) 2004-2005 Silicon Graphics, Inc. All Rights Reserved. + * Copyright (c) 2004-2006 Silicon Graphics, Inc. All Rights Reserved. */ @@ -24,7 +24,7 @@ #include <linux/slab.h> #include <asm/sn/bte.h> #include <asm/sn/sn_sal.h> -#include "xpc.h" +#include <asm/sn/xpc.h> /* @@ -779,6 +779,12 @@ xpc_process_disconnect(struct xpc_channel *ch, unsigned long *irq_flags) /* both sides are disconnected now */ + if (ch->flags & XPC_C_CONNECTCALLOUT) { + spin_unlock_irqrestore(&ch->lock, *irq_flags); + xpc_disconnect_callout(ch, xpcDisconnected); + spin_lock_irqsave(&ch->lock, *irq_flags); + } + /* it's now safe to free the channel's message queues */ xpc_free_msgqueues(ch); @@ -1645,7 +1651,7 @@ xpc_disconnect_channel(const int line, struct xpc_channel *ch, void -xpc_disconnecting_callout(struct xpc_channel *ch) +xpc_disconnect_callout(struct xpc_channel *ch, enum xpc_retval reason) { /* * Let the channel's registerer know that the channel is being @@ -1654,15 +1660,13 @@ xpc_disconnecting_callout(struct xpc_channel *ch) */ if (ch->func != NULL) { - dev_dbg(xpc_chan, "ch->func() called, reason=xpcDisconnecting," - " partid=%d, channel=%d\n", ch->partid, ch->number); + dev_dbg(xpc_chan, "ch->func() called, reason=%d, partid=%d, " + "channel=%d\n", reason, ch->partid, ch->number); - ch->func(xpcDisconnecting, ch->partid, ch->number, NULL, - ch->key); + ch->func(reason, ch->partid, ch->number, NULL, ch->key); - dev_dbg(xpc_chan, "ch->func() returned, reason=" - "xpcDisconnecting, partid=%d, channel=%d\n", - ch->partid, ch->number); + dev_dbg(xpc_chan, "ch->func() returned, reason=%d, partid=%d, " + "channel=%d\n", reason, ch->partid, ch->number); } } diff --git a/arch/ia64/sn/kernel/xpc_main.c b/arch/ia64/sn/kernel/xpc_main.c index b617236524c..8930586e0eb 100644 --- a/arch/ia64/sn/kernel/xpc_main.c +++ b/arch/ia64/sn/kernel/xpc_main.c @@ -3,7 +3,7 @@ * License. See the file "COPYING" in the main directory of this archive * for more details. * - * Copyright (c) 2004-2005 Silicon Graphics, Inc. All Rights Reserved. + * Copyright (c) 2004-2006 Silicon Graphics, Inc. All Rights Reserved. */ @@ -59,7 +59,7 @@ #include <asm/sn/sn_sal.h> #include <asm/kdebug.h> #include <asm/uaccess.h> -#include "xpc.h" +#include <asm/sn/xpc.h> /* define two XPC debug device structures to be used with dev_dbg() et al */ @@ -82,6 +82,9 @@ struct device *xpc_part = &xpc_part_dbg_subname; struct device *xpc_chan = &xpc_chan_dbg_subname; +static int xpc_kdebug_ignore; + + /* systune related variables for /proc/sys directories */ static int xpc_hb_interval = XPC_HB_DEFAULT_INTERVAL; @@ -162,6 +165,8 @@ static ctl_table xpc_sys_dir[] = { }; static struct ctl_table_header *xpc_sysctl; +/* non-zero if any remote partition disengage request was timed out */ +int xpc_disengage_request_timedout; /* #of IRQs received */ static atomic_t xpc_act_IRQ_rcvd; @@ -773,7 +778,7 @@ xpc_daemonize_kthread(void *args) ch->flags |= XPC_C_DISCONNECTCALLOUT; spin_unlock_irqrestore(&ch->lock, irq_flags); - xpc_disconnecting_callout(ch); + xpc_disconnect_callout(ch, xpcDisconnecting); } else { spin_unlock_irqrestore(&ch->lock, irq_flags); } @@ -921,9 +926,9 @@ static void xpc_do_exit(enum xpc_retval reason) { partid_t partid; - int active_part_count; + int active_part_count, printed_waiting_msg = 0; struct xpc_partition *part; - unsigned long printmsg_time; + unsigned long printmsg_time, disengage_request_timeout = 0; /* a 'rmmod XPC' and a 'reboot' cannot both end up here together */ @@ -953,7 +958,8 @@ xpc_do_exit(enum xpc_retval reason) /* wait for all partitions to become inactive */ - printmsg_time = jiffies; + printmsg_time = jiffies + (XPC_DISENGAGE_PRINTMSG_INTERVAL * HZ); + xpc_disengage_request_timedout = 0; do { active_part_count = 0; @@ -969,20 +975,39 @@ xpc_do_exit(enum xpc_retval reason) active_part_count++; XPC_DEACTIVATE_PARTITION(part, reason); - } - if (active_part_count == 0) { - break; + if (part->disengage_request_timeout > + disengage_request_timeout) { + disengage_request_timeout = + part->disengage_request_timeout; + } } - if (jiffies >= printmsg_time) { - dev_info(xpc_part, "waiting for partitions to " - "deactivate/disengage, active count=%d, remote " - "engaged=0x%lx\n", active_part_count, - xpc_partition_engaged(1UL << partid)); - - printmsg_time = jiffies + + if (xpc_partition_engaged(-1UL)) { + if (time_after(jiffies, printmsg_time)) { + dev_info(xpc_part, "waiting for remote " + "partitions to disengage, timeout in " + "%ld seconds\n", + (disengage_request_timeout - jiffies) + / HZ); + printmsg_time = jiffies + (XPC_DISENGAGE_PRINTMSG_INTERVAL * HZ); + printed_waiting_msg = 1; + } + + } else if (active_part_count > 0) { + if (printed_waiting_msg) { + dev_info(xpc_part, "waiting for local partition" + " to disengage\n"); + printed_waiting_msg = 0; + } + + } else { + if (!xpc_disengage_request_timedout) { + dev_info(xpc_part, "all partitions have " + "disengaged\n"); + } + break; } /* sleep for a 1/3 of a second or so */ @@ -1000,11 +1025,13 @@ xpc_do_exit(enum xpc_retval reason) del_timer_sync(&xpc_hb_timer); DBUG_ON(xpc_vars->heartbeating_to_mask != 0); - /* take ourselves off of the reboot_notifier_list */ - (void) unregister_reboot_notifier(&xpc_reboot_notifier); + if (reason == xpcUnloading) { + /* take ourselves off of the reboot_notifier_list */ + (void) unregister_reboot_notifier(&xpc_reboot_notifier); - /* take ourselves off of the die_notifier list */ - (void) unregister_die_notifier(&xpc_die_notifier); + /* take ourselves off of the die_notifier list */ + (void) unregister_die_notifier(&xpc_die_notifier); + } /* close down protections for IPI operations */ xpc_restrict_IPI_ops(); @@ -1020,7 +1047,35 @@ xpc_do_exit(enum xpc_retval reason) /* - * Called when the system is about to be either restarted or halted. + * This function is called when the system is being rebooted. + */ +static int +xpc_system_reboot(struct notifier_block *nb, unsigned long event, void *unused) +{ + enum xpc_retval reason; + + + switch (event) { + case SYS_RESTART: + reason = xpcSystemReboot; + break; + case SYS_HALT: + reason = xpcSystemHalt; + break; + case SYS_POWER_OFF: + reason = xpcSystemPoweroff; + break; + default: + reason = xpcSystemGoingDown; + } + + xpc_do_exit(reason); + return NOTIFY_DONE; +} + + +/* + * Notify other partitions to disengage from all references to our memory. */ static void xpc_die_disengage(void) @@ -1028,7 +1083,7 @@ xpc_die_disengage(void) struct xpc_partition *part; partid_t partid; unsigned long engaged; - long time, print_time, disengage_request_timeout; + long time, printmsg_time, disengage_request_timeout; /* keep xpc_hb_checker thread from doing anything (just in case) */ @@ -1055,57 +1110,53 @@ xpc_die_disengage(void) } } - print_time = rtc_time(); - disengage_request_timeout = print_time + + time = rtc_time(); + printmsg_time = time + + (XPC_DISENGAGE_PRINTMSG_INTERVAL * sn_rtc_cycles_per_second); + disengage_request_timeout = time + (xpc_disengage_request_timelimit * sn_rtc_cycles_per_second); /* wait for all other partitions to disengage from us */ - while ((engaged = xpc_partition_engaged(-1UL)) && - (time = rtc_time()) < disengage_request_timeout) { + while (1) { + engaged = xpc_partition_engaged(-1UL); + if (!engaged) { + dev_info(xpc_part, "all partitions have disengaged\n"); + break; + } - if (time >= print_time) { + time = rtc_time(); + if (time >= disengage_request_timeout) { + for (partid = 1; partid < XP_MAX_PARTITIONS; partid++) { + if (engaged & (1UL << partid)) { + dev_info(xpc_part, "disengage from " + "remote partition %d timed " + "out\n", partid); + } + } + break; + } + + if (time >= printmsg_time) { dev_info(xpc_part, "waiting for remote partitions to " - "disengage, engaged=0x%lx\n", engaged); - print_time = time + (XPC_DISENGAGE_PRINTMSG_INTERVAL * + "disengage, timeout in %ld seconds\n", + (disengage_request_timeout - time) / + sn_rtc_cycles_per_second); + printmsg_time = time + + (XPC_DISENGAGE_PRINTMSG_INTERVAL * sn_rtc_cycles_per_second); } } - dev_info(xpc_part, "finished waiting for remote partitions to " - "disengage, engaged=0x%lx\n", engaged); -} - - -/* - * This function is called when the system is being rebooted. - */ -static int -xpc_system_reboot(struct notifier_block *nb, unsigned long event, void *unused) -{ - enum xpc_retval reason; - - - switch (event) { - case SYS_RESTART: - reason = xpcSystemReboot; - break; - case SYS_HALT: - reason = xpcSystemHalt; - break; - case SYS_POWER_OFF: - reason = xpcSystemPoweroff; - break; - default: - reason = xpcSystemGoingDown; - } - - xpc_do_exit(reason); - return NOTIFY_DONE; } /* - * This function is called when the system is being rebooted. + * This function is called when the system is being restarted or halted due + * to some sort of system failure. If this is the case we need to notify the + * other partitions to disengage from all references to our memory. + * This function can also be called when our heartbeater could be offlined + * for a time. In this case we need to notify other partitions to not worry + * about the lack of a heartbeat. */ static int xpc_system_die(struct notifier_block *nb, unsigned long event, void *unused) @@ -1115,11 +1166,25 @@ xpc_system_die(struct notifier_block *nb, unsigned long event, void *unused) case DIE_MACHINE_HALT: xpc_die_disengage(); break; + + case DIE_KDEBUG_ENTER: + /* Should lack of heartbeat be ignored by other partitions? */ + if (!xpc_kdebug_ignore) { + break; + } + /* fall through */ case DIE_MCA_MONARCH_ENTER: case DIE_INIT_MONARCH_ENTER: xpc_vars->heartbeat++; xpc_vars->heartbeat_offline = 1; break; + + case DIE_KDEBUG_LEAVE: + /* Is lack of heartbeat being ignored by other partitions? */ + if (!xpc_kdebug_ignore) { + break; + } + /* fall through */ case DIE_MCA_MONARCH_LEAVE: case DIE_INIT_MONARCH_LEAVE: xpc_vars->heartbeat++; @@ -1344,3 +1409,7 @@ module_param(xpc_disengage_request_timelimit, int, 0); MODULE_PARM_DESC(xpc_disengage_request_timelimit, "Number of seconds to wait " "for disengage request to complete."); +module_param(xpc_kdebug_ignore, int, 0); +MODULE_PARM_DESC(xpc_kdebug_ignore, "Should lack of heartbeat be ignored by " + "other partitions when dropping into kdebug."); + diff --git a/arch/ia64/sn/kernel/xpc_partition.c b/arch/ia64/sn/kernel/xpc_partition.c index cdd6431853a..88a730e6cfd 100644 --- a/arch/ia64/sn/kernel/xpc_partition.c +++ b/arch/ia64/sn/kernel/xpc_partition.c @@ -3,7 +3,7 @@ * License. See the file "COPYING" in the main directory of this archive * for more details. * - * Copyright (c) 2004-2005 Silicon Graphics, Inc. All Rights Reserved. + * Copyright (c) 2004-2006 Silicon Graphics, Inc. All Rights Reserved. */ @@ -28,7 +28,7 @@ #include <asm/sn/sn_sal.h> #include <asm/sn/nodepda.h> #include <asm/sn/addrs.h> -#include "xpc.h" +#include <asm/sn/xpc.h> /* XPC is exiting flag */ @@ -771,7 +771,8 @@ xpc_identify_act_IRQ_req(int nasid) } } - if (!xpc_partition_disengaged(part)) { + if (part->disengage_request_timeout > 0 && + !xpc_partition_disengaged(part)) { /* still waiting on other side to disengage from us */ return; } @@ -873,6 +874,9 @@ xpc_partition_disengaged(struct xpc_partition *part) * request in a timely fashion, so assume it's dead. */ + dev_info(xpc_part, "disengage from remote partition %d " + "timed out\n", partid); + xpc_disengage_request_timedout = 1; xpc_clear_partition_engaged(1UL << partid); disengaged = 1; } diff --git a/arch/ia64/sn/pci/pcibr/pcibr_dma.c b/arch/ia64/sn/pci/pcibr/pcibr_dma.c index 34093476e96..e68332d9317 100644 --- a/arch/ia64/sn/pci/pcibr/pcibr_dma.c +++ b/arch/ia64/sn/pci/pcibr/pcibr_dma.c @@ -218,7 +218,9 @@ void sn_dma_flush(uint64_t addr) uint64_t flags; uint64_t itte; struct hubdev_info *hubinfo; - volatile struct sn_flush_device_list *p; + volatile struct sn_flush_device_kernel *p; + volatile struct sn_flush_device_common *common; + struct sn_flush_nasid_entry *flush_nasid_list; if (!sn_ioif_inited) @@ -268,17 +270,17 @@ void sn_dma_flush(uint64_t addr) p = &flush_nasid_list->widget_p[wid_num][0]; /* find a matching BAR */ - for (i = 0; i < DEV_PER_WIDGET; i++) { + for (i = 0; i < DEV_PER_WIDGET; i++,p++) { + common = p->common; for (j = 0; j < PCI_ROM_RESOURCE; j++) { - if (p->sfdl_bar_list[j].start == 0) + if (common->sfdl_bar_list[j].start == 0) break; - if (addr >= p->sfdl_bar_list[j].start - && addr <= p->sfdl_bar_list[j].end) + if (addr >= common->sfdl_bar_list[j].start + && addr <= common->sfdl_bar_list[j].end) break; } - if (j < PCI_ROM_RESOURCE && p->sfdl_bar_list[j].start != 0) + if (j < PCI_ROM_RESOURCE && common->sfdl_bar_list[j].start != 0) break; - p++; } /* if no matching BAR, return without doing anything. */ @@ -304,24 +306,24 @@ void sn_dma_flush(uint64_t addr) if ((1 << XWIDGET_PART_REV_NUM_REV(revnum)) & PV907516) { return; } else { - pcireg_wrb_flush_get(p->sfdl_pcibus_info, - (p->sfdl_slot - 1)); + pcireg_wrb_flush_get(common->sfdl_pcibus_info, + (common->sfdl_slot - 1)); } } else { - spin_lock_irqsave(&((struct sn_flush_device_list *)p)-> - sfdl_flush_lock, flags); - - *p->sfdl_flush_addr = 0; + spin_lock_irqsave((spinlock_t *)&p->sfdl_flush_lock, + flags); + *common->sfdl_flush_addr = 0; /* force an interrupt. */ - *(volatile uint32_t *)(p->sfdl_force_int_addr) = 1; + *(volatile uint32_t *)(common->sfdl_force_int_addr) = 1; /* wait for the interrupt to come back. */ - while (*(p->sfdl_flush_addr) != 0x10f) + while (*(common->sfdl_flush_addr) != 0x10f) cpu_relax(); /* okay, everything is synched up. */ - spin_unlock_irqrestore((spinlock_t *)&p->sfdl_flush_lock, flags); + spin_unlock_irqrestore((spinlock_t *)&p->sfdl_flush_lock, + flags); } return; } diff --git a/arch/ia64/sn/pci/pcibr/pcibr_provider.c b/arch/ia64/sn/pci/pcibr/pcibr_provider.c index 1f500c81002..e328e948175 100644 --- a/arch/ia64/sn/pci/pcibr/pcibr_provider.c +++ b/arch/ia64/sn/pci/pcibr/pcibr_provider.c @@ -92,7 +92,8 @@ pcibr_bus_fixup(struct pcibus_bussoft *prom_bussoft, struct pci_controller *cont cnodeid_t near_cnode; struct hubdev_info *hubdev_info; struct pcibus_info *soft; - struct sn_flush_device_list *sn_flush_device_list; + struct sn_flush_device_kernel *sn_flush_device_kernel; + struct sn_flush_device_common *common; if (! IS_PCI_BRIDGE_ASIC(prom_bussoft->bs_asic_type)) { return NULL; @@ -137,20 +138,19 @@ pcibr_bus_fixup(struct pcibus_bussoft *prom_bussoft, struct pci_controller *cont hubdev_info = (struct hubdev_info *)(NODEPDA(cnode)->pdinfo); if (hubdev_info->hdi_flush_nasid_list.widget_p) { - sn_flush_device_list = hubdev_info->hdi_flush_nasid_list. + sn_flush_device_kernel = hubdev_info->hdi_flush_nasid_list. widget_p[(int)soft->pbi_buscommon.bs_xid]; - if (sn_flush_device_list) { + if (sn_flush_device_kernel) { for (j = 0; j < DEV_PER_WIDGET; - j++, sn_flush_device_list++) { - if (sn_flush_device_list->sfdl_slot == -1) + j++, sn_flush_device_kernel++) { + common = sn_flush_device_kernel->common; + if (common->sfdl_slot == -1) continue; - if ((sn_flush_device_list-> - sfdl_persistent_segment == + if ((common->sfdl_persistent_segment == soft->pbi_buscommon.bs_persist_segment) && - (sn_flush_device_list-> - sfdl_persistent_busnum == + (common->sfdl_persistent_busnum == soft->pbi_buscommon.bs_persist_busnum)) - sn_flush_device_list->sfdl_pcibus_info = + common->sfdl_pcibus_info = soft; } } diff --git a/arch/powerpc/Makefile b/arch/powerpc/Makefile index d3654a264ef..44dd82b791d 100644 --- a/arch/powerpc/Makefile +++ b/arch/powerpc/Makefile @@ -139,17 +139,14 @@ drivers-$(CONFIG_CPM2) += arch/ppc/8260_io/ drivers-$(CONFIG_OPROFILE) += arch/powerpc/oprofile/ -defaultimage-$(CONFIG_PPC32) := zImage +# Default to zImage, override when needed +defaultimage-y := zImage defaultimage-$(CONFIG_PPC_ISERIES) := vmlinux -defaultimage-$(CONFIG_PPC_PSERIES) := zImage KBUILD_IMAGE := $(defaultimage-y) all: $(KBUILD_IMAGE) CPPFLAGS_vmlinux.lds := -Upowerpc -# All the instructions talk about "make bzImage". -bzImage: zImage - BOOT_TARGETS = zImage zImage.initrd znetboot znetboot.initrd vmlinux.sm uImage .PHONY: $(BOOT_TARGETS) diff --git a/arch/powerpc/boot/Makefile b/arch/powerpc/boot/Makefile index b53d677f674..788dec4c7ef 100644 --- a/arch/powerpc/boot/Makefile +++ b/arch/powerpc/boot/Makefile @@ -25,8 +25,8 @@ HOSTCC := gcc BOOTCFLAGS := $(HOSTCFLAGS) -fno-builtin -nostdinc -isystem \ $(shell $(CROSS32CC) -print-file-name=include) -fPIC BOOTAFLAGS := -D__ASSEMBLY__ $(BOOTCFLAGS) -traditional -nostdinc -BOOTLFLAGS := -T $(srctree)/$(src)/zImage.lds OBJCOPYFLAGS := contents,alloc,load,readonly,data +OBJCOPY_COFF_ARGS := -O aixcoff-rs6000 --set-start 0x500000 zlib := infblock.c infcodes.c inffast.c inflate.c inftrees.c infutil.c zlibheader := infblock.h infcodes.h inffast.h inftrees.h infutil.h @@ -35,7 +35,7 @@ zliblinuxheader := zlib.h zconf.h zutil.h $(addprefix $(obj)/,$(zlib) main.o): $(addprefix $(obj)/,$(zliblinuxheader)) $(addprefix $(obj)/,$(zlibheader)) #$(addprefix $(obj)/,main.o): $(addprefix $(obj)/,zlib.h) -src-boot := string.S prom.c main.c div64.S crt0.S +src-boot := crt0.S string.S prom.c stdio.c main.c div64.S src-boot += $(zlib) src-boot := $(addprefix $(obj)/, $(src-boot)) obj-boot := $(addsuffix .o, $(basename $(src-boot))) @@ -70,7 +70,7 @@ quiet_cmd_bootas = BOOTAS $@ cmd_bootas = $(CROSS32CC) -Wp,-MD,$(depfile) $(BOOTAFLAGS) -c -o $@ $< quiet_cmd_bootld = BOOTLD $@ - cmd_bootld = $(CROSS32LD) $(BOOTLFLAGS) -o $@ $(2) + cmd_bootld = $(CROSS32LD) -T $(srctree)/$(src)/$(3) -o $@ $(2) $(patsubst %.c,%.o, $(filter %.c, $(src-boot))): %.o: %.c $(call if_changed_dep,bootcc) @@ -87,12 +87,14 @@ obj-sec = $(foreach section, $(1), $(patsubst %,$(obj)/kernel-%.o, $(section))) src-sec = $(foreach section, $(1), $(patsubst %,$(obj)/kernel-%.c, $(section))) gz-sec = $(foreach section, $(1), $(patsubst %,$(obj)/kernel-%.gz, $(section))) -hostprogs-y := addnote addRamDisk -targets += zImage.vmode zImage.initrd.vmode zImage zImage.initrd \ - $(patsubst $(obj)/%,%, $(call obj-sec, $(required) $(initrd))) \ - $(patsubst $(obj)/%,%, $(call src-sec, $(required) $(initrd))) \ - $(patsubst $(obj)/%,%, $(call gz-sec, $(required) $(initrd))) \ - vmlinux.initrd +hostprogs-y := addnote addRamDisk hack-coff + +targets += zImage.vmode zImage.initrd.vmode zImage zImage.initrd \ + zImage.coff zImage.initrd.coff \ + $(patsubst $(obj)/%,%, $(call obj-sec, $(required) $(initrd))) \ + $(patsubst $(obj)/%,%, $(call src-sec, $(required) $(initrd))) \ + $(patsubst $(obj)/%,%, $(call gz-sec, $(required) $(initrd))) \ + vmlinux.initrd extra-y := initrd.o quiet_cmd_ramdisk = RAMDISK $@ @@ -114,6 +116,10 @@ quiet_cmd_addsection = ADDSEC $@ quiet_cmd_addnote = ADDNOTE $@ cmd_addnote = $(obj)/addnote $@ +quiet_cmd_gencoff = COFF $@ + cmd_gencoff = $(OBJCOPY) $(OBJCOPY_COFF_ARGS) $@ && \ + $(obj)/hack-coff $@ + $(call gz-sec, $(required)): $(obj)/kernel-%.gz: % $(call if_changed,gzip) @@ -127,22 +133,35 @@ $(call obj-sec, $(required) $(initrd)): $(obj)/kernel-%.o: $(obj)/kernel-%.c $(call if_changed_dep,bootcc) $(call cmd,addsection) -$(obj)/zImage.vmode: obj-boot += $(call obj-sec, $(required)) +$(obj)/zImage.vmode $(obj)/zImage.coff: obj-boot += $(call obj-sec, $(required)) $(obj)/zImage.vmode: $(call obj-sec, $(required)) $(obj-boot) $(srctree)/$(src)/zImage.lds - $(call cmd,bootld,$(obj-boot)) + $(call cmd,bootld,$(obj-boot),zImage.lds) -$(obj)/zImage.initrd.vmode: obj-boot += $(call obj-sec, $(required) $(initrd)) +$(obj)/zImage.initrd.vmode $(obj)/zImage.initrd.coff: obj-boot += $(call obj-sec, $(required) $(initrd)) $(obj)/zImage.initrd.vmode: $(call obj-sec, $(required) $(initrd)) $(obj-boot) $(srctree)/$(src)/zImage.lds - $(call cmd,bootld,$(obj-boot)) + $(call cmd,bootld,$(obj-boot),zImage.lds) + +# For 32-bit powermacs, build the COFF images as well as the ELF images. +coffimage-$(CONFIG_PPC_PMAC)-$(CONFIG_PPC32) := $(obj)/zImage.coff +coffrdimg-$(CONFIG_PPC_PMAC)-$(CONFIG_PPC32) := $(obj)/zImage.initrd.coff -$(obj)/zImage: $(obj)/zImage.vmode $(obj)/addnote +$(obj)/zImage: $(obj)/zImage.vmode $(obj)/addnote $(coffimage-y-y) @cp -f $< $@ $(call if_changed,addnote) -$(obj)/zImage.initrd: $(obj)/zImage.initrd.vmode $(obj)/addnote +$(obj)/zImage.initrd: $(obj)/zImage.initrd.vmode $(obj)/addnote $(coffrdimg-y-y) @cp -f $< $@ $(call if_changed,addnote) +$(obj)/zImage.coff: $(call obj-sec, $(required)) $(obj-boot) $(srctree)/$(src)/zImage.coff.lds $(obj)/hack-coff + $(call cmd,bootld,$(obj-boot),zImage.coff.lds) + $(call cmd,gencoff) + +$(obj)/zImage.initrd.coff: $(call obj-sec, $(required) $(initrd)) $(obj-boot) \ + $(srctree)/$(src)/zImage.coff.lds $(obj)/hack-coff + $(call cmd,bootld,$(obj-boot),zImage.coff.lds) + $(call cmd,gencoff) + #----------------------------------------------------------- # build u-boot images #----------------------------------------------------------- diff --git a/arch/powerpc/boot/crt0.S b/arch/powerpc/boot/crt0.S index d2f2ace56cd..e0192c26037 100644 --- a/arch/powerpc/boot/crt0.S +++ b/arch/powerpc/boot/crt0.S @@ -12,17 +12,23 @@ #include "ppc_asm.h" .text + /* a procedure descriptor used when booting this as a COFF file */ +_zimage_start_opd: + .long _zimage_start, 0, 0, 0 + .globl _zimage_start _zimage_start: + /* Work out the offset between the address we were linked at + and the address where we're running. */ bl 1f - -1: - mflr r0 +1: mflr r0 lis r9,1b@ha addi r9,r9,1b@l subf. r0,r9,r0 - beq 3f + beq 3f /* if running at same address as linked */ + /* The .got2 section contains a list of addresses, so add + the address offset onto each entry. */ lis r9,__got2_start@ha addi r9,r9,__got2_start@l lis r8,__got2_end@ha @@ -32,15 +38,14 @@ _zimage_start: srwi. r8,r8,2 mtctr r8 add r9,r0,r9 -2: - lwz r8,0(r9) +2: lwz r8,0(r9) add r8,r8,r0 stw r8,0(r9) addi r9,r9,4 bdnz 2b -3: - lis r9,_start@h + /* Do a cache flush for our text, in case OF didn't */ +3: lis r9,_start@h add r9,r0,r9 lis r8,_etext@ha addi r8,r8,_etext@l diff --git a/arch/powerpc/boot/hack-coff.c b/arch/powerpc/boot/hack-coff.c new file mode 100644 index 00000000000..5e5a6573a1e --- /dev/null +++ b/arch/powerpc/boot/hack-coff.c @@ -0,0 +1,84 @@ +/* + * hack-coff.c - hack the header of an xcoff file to fill in + * a few fields needed by the Open Firmware xcoff loader on + * Power Macs but not initialized by objcopy. + * + * Copyright (C) Paul Mackerras 1997. + * + * This program is free software; you can redistribute it and/or + * modify it under the terms of the GNU General Public License + * as published by the Free Software Foundation; either version + * 2 of the License, or (at your option) any later version. + */ +#include <stdio.h> +#include <stdlib.h> +#include <unistd.h> +#include <fcntl.h> +#include <string.h> +#include "rs6000.h" + +#define AOUT_MAGIC 0x010b + +#define get_16be(x) ((((unsigned char *)(x))[0] << 8) \ + + ((unsigned char *)(x))[1]) +#define put_16be(x, v) (((unsigned char *)(x))[0] = (v) >> 8, \ + ((unsigned char *)(x))[1] = (v) & 0xff) +#define get_32be(x) ((((unsigned char *)(x))[0] << 24) \ + + (((unsigned char *)(x))[1] << 16) \ + + (((unsigned char *)(x))[2] << 8) \ + + ((unsigned char *)(x))[3]) + +int +main(int ac, char **av) +{ + int fd; + int i, nsect; + int aoutsz; + struct external_filehdr fhdr; + AOUTHDR aout; + struct external_scnhdr shdr; + + if (ac != 2) { + fprintf(stderr, "Usage: hack-coff coff-file\n"); + exit(1); + } + if ((fd = open(av[1], 2)) == -1) { + perror(av[2]); + exit(1); + } + if (read(fd, &fhdr, sizeof(fhdr)) != sizeof(fhdr)) + goto readerr; + i = get_16be(fhdr.f_magic); + if (i != U802TOCMAGIC && i != U802WRMAGIC && i != U802ROMAGIC) { + fprintf(stderr, "%s: not an xcoff file\n", av[1]); + exit(1); + } + aoutsz = get_16be(fhdr.f_opthdr); + if (read(fd, &aout, aoutsz) != aoutsz) + goto readerr; + nsect = get_16be(fhdr.f_nscns); + for (i = 0; i < nsect; ++i) { + if (read(fd, &shdr, sizeof(shdr)) != sizeof(shdr)) + goto readerr; + if (strcmp(shdr.s_name, ".text") == 0) { + put_16be(aout.o_snentry, i+1); + put_16be(aout.o_sntext, i+1); + } else if (strcmp(shdr.s_name, ".data") == 0) { + put_16be(aout.o_sndata, i+1); + } else if (strcmp(shdr.s_name, ".bss") == 0) { + put_16be(aout.o_snbss, i+1); + } + } + put_16be(aout.magic, AOUT_MAGIC); + if (lseek(fd, (long) sizeof(struct external_filehdr), 0) == -1 + || write(fd, &aout, aoutsz) != aoutsz) { + fprintf(stderr, "%s: write error\n", av[1]); + exit(1); + } + close(fd); + exit(0); + +readerr: + fprintf(stderr, "%s: read error or file too short\n", av[1]); + exit(1); +} diff --git a/arch/powerpc/boot/main.c b/arch/powerpc/boot/main.c index 64ec93116fa..55ec5986725 100644 --- a/arch/powerpc/boot/main.c +++ b/arch/powerpc/boot/main.c @@ -21,8 +21,8 @@ extern void flush_cache(void *, unsigned long); /* Value picked to match that used by yaboot */ -#define PROG_START 0x01400000 -#define RAM_END (512<<20) // Fixme: use OF */ +#define PROG_START 0x01400000 /* only used on 64-bit systems */ +#define RAM_END (512<<20) /* Fixme: use OF */ #define ONE_MB 0x100000 extern char _start[]; @@ -160,6 +160,17 @@ static int is_elf64(void *hdr) elfoffset = (unsigned long)elf64ph->p_offset; vmlinux.size = (unsigned long)elf64ph->p_filesz + elfoffset; vmlinux.memsize = (unsigned long)elf64ph->p_memsz + elfoffset; + +#if defined(PROG_START) + /* + * Maintain a "magic" minimum address. This keeps some older + * firmware platforms running. + */ + + if (claim_base < PROG_START) + claim_base = PROG_START; +#endif + return 1; } @@ -206,12 +217,18 @@ void start(unsigned long a1, unsigned long a2, void *promptr, void *sp) exit(); if (getprop(chosen_handle, "stdout", &stdout, sizeof(stdout)) != 4) exit(); - stderr = stdout; - if (getprop(chosen_handle, "stdin", &stdin, sizeof(stdin)) != 4) - exit(); printf("\n\rzImage starting: loaded at 0x%p (sp: 0x%p)\n\r", _start, sp); + /* + * The first available claim_base must be above the end of the + * the loaded kernel wrapper file (_start to _end includes the + * initrd image if it is present) and rounded up to a nice + * 1 MB boundary for good measure. + */ + + claim_base = _ALIGN_UP((unsigned long)_end, ONE_MB); + vmlinuz.addr = (unsigned long)_vmlinux_start; vmlinuz.size = (unsigned long)(_vmlinux_end - _vmlinux_start); @@ -228,25 +245,6 @@ void start(unsigned long a1, unsigned long a2, void *promptr, void *sp) exit(); } - /* - * The first available claim_base must be above the end of the - * the loaded kernel wrapper file (_start to _end includes the - * initrd image if it is present) and rounded up to a nice - * 1 MB boundary for good measure. - */ - - claim_base = _ALIGN_UP((unsigned long)_end, ONE_MB); - -#if defined(PROG_START) - /* - * Maintain a "magic" minimum address. This keeps some older - * firmware platforms running. - */ - - if (claim_base < PROG_START) - claim_base = PROG_START; -#endif - /* We need to claim the memsize plus the file offset since gzip * will expand the header (file offset), then the kernel, then * possible rubbish we don't care about. But the kernel bss must diff --git a/arch/powerpc/boot/prom.c b/arch/powerpc/boot/prom.c index 4bea2f4dcb0..fa0057736f6 100644 --- a/arch/powerpc/boot/prom.c +++ b/arch/powerpc/boot/prom.c @@ -13,487 +13,153 @@ #include "prom.h" int (*prom)(void *); +phandle chosen_handle; +ihandle stdout; -void *chosen_handle; - -void *stdin; -void *stdout; -void *stderr; - - -int -write(void *handle, void *ptr, int nb) -{ - struct prom_args { - char *service; - int nargs; - int nret; - void *ihandle; - void *addr; - int len; - int actual; - } args; - - args.service = "write"; - args.nargs = 3; - args.nret = 1; - args.ihandle = handle; - args.addr = ptr; - args.len = nb; - args.actual = -1; - (*prom)(&args); - return args.actual; -} - -int -read(void *handle, void *ptr, int nb) +int call_prom(const char *service, int nargs, int nret, ...) { + int i; struct prom_args { - char *service; + const char *service; int nargs; int nret; - void *ihandle; - void *addr; - int len; - int actual; - } args; - - args.service = "read"; - args.nargs = 3; - args.nret = 1; - args.ihandle = handle; - args.addr = ptr; - args.len = nb; - args.actual = -1; - (*prom)(&args); - return args.actual; -} - -void -exit() -{ - struct prom_args { - char *service; - } args; - - for (;;) { - args.service = "exit"; - (*prom)(&args); - } -} - -void -pause(void) -{ - struct prom_args { - char *service; + unsigned int args[12]; } args; + va_list list; - args.service = "enter"; - (*prom)(&args); -} + args.service = service; + args.nargs = nargs; + args.nret = nret; -void * -finddevice(const char *name) -{ - struct prom_args { - char *service; - int nargs; - int nret; - const char *devspec; - void *phandle; - } args; + va_start(list, nret); + for (i = 0; i < nargs; i++) + args.args[i] = va_arg(list, unsigned int); + va_end(list); - args.service = "finddevice"; - args.nargs = 1; - args.nret = 1; - args.devspec = name; - args.phandle = (void *) -1; - (*prom)(&args); - return args.phandle; -} + for (i = 0; i < nret; i++) + args.args[nargs+i] = 0; -void * -claim(unsigned long virt, unsigned long size, unsigned long align) -{ - struct prom_args { - char *service; - int nargs; - int nret; - unsigned int virt; - unsigned int size; - unsigned int align; - void *ret; - } args; + if (prom(&args) < 0) + return -1; - args.service = "claim"; - args.nargs = 3; - args.nret = 1; - args.virt = virt; - args.size = size; - args.align = align; - (*prom)(&args); - return args.ret; + return (nret > 0)? args.args[nargs]: 0; } -int -getprop(void *phandle, const char *name, void *buf, int buflen) +int call_prom_ret(const char *service, int nargs, int nret, + unsigned int *rets, ...) { + int i; struct prom_args { - char *service; + const char *service; int nargs; int nret; - void *phandle; - const char *name; - void *buf; - int buflen; - int size; + unsigned int args[12]; } args; + va_list list; - args.service = "getprop"; - args.nargs = 4; - args.nret = 1; - args.phandle = phandle; - args.name = name; - args.buf = buf; - args.buflen = buflen; - args.size = -1; - (*prom)(&args); - return args.size; -} + args.service = service; + args.nargs = nargs; + args.nret = nret; -int -putc(int c, void *f) -{ - char ch = c; + va_start(list, rets); + for (i = 0; i < nargs; i++) + args.args[i] = va_arg(list, unsigned int); + va_end(list); - if (c == '\n') - putc('\r', f); - return write(f, &ch, 1) == 1? c: -1; -} + for (i = 0; i < nret; i++) + args.args[nargs+i] = 0; -int -putchar(int c) -{ - return putc(c, stdout); -} + if (prom(&args) < 0) + return -1; -int -fputs(char *str, void *f) -{ - int n = strlen(str); + if (rets != (void *) 0) + for (i = 1; i < nret; ++i) + rets[i-1] = args.args[nargs+i]; - return write(f, str, n) == n? 0: -1; + return (nret > 0)? args.args[nargs]: 0; } -size_t strnlen(const char * s, size_t count) +int write(void *handle, void *ptr, int nb) { - const char *sc; - - for (sc = s; count-- && *sc != '\0'; ++sc) - /* nothing */; - return sc - s; + return call_prom("write", 3, 1, handle, ptr, nb); } -extern unsigned int __div64_32(unsigned long long *dividend, - unsigned int divisor); - -/* The unnecessary pointer compare is there - * to check for type safety (n must be 64bit) +/* + * Older OF's require that when claiming a specific range of addresses, + * we claim the physical space in the /memory node and the virtual + * space in the chosen mmu node, and then do a map operation to + * map virtual to physical. */ -# define do_div(n,base) ({ \ - unsigned int __base = (base); \ - unsigned int __rem; \ - (void)(((typeof((n)) *)0) == ((unsigned long long *)0)); \ - if (((n) >> 32) == 0) { \ - __rem = (unsigned int)(n) % __base; \ - (n) = (unsigned int)(n) / __base; \ - } else \ - __rem = __div64_32(&(n), __base); \ - __rem; \ - }) +static int need_map = -1; +static ihandle chosen_mmu; +static phandle memory; -static int skip_atoi(const char **s) +/* returns true if s2 is a prefix of s1 */ +static int string_match(const char *s1, const char *s2) { - int i, c; - - for (i = 0; '0' <= (c = **s) && c <= '9'; ++*s) - i = i*10 + c - '0'; - return i; + for (; *s2; ++s2) + if (*s1++ != *s2) + return 0; + return 1; } -#define ZEROPAD 1 /* pad with zero */ -#define SIGN 2 /* unsigned/signed long */ -#define PLUS 4 /* show plus */ -#define SPACE 8 /* space if plus */ -#define LEFT 16 /* left justified */ -#define SPECIAL 32 /* 0x */ -#define LARGE 64 /* use 'ABCDEF' instead of 'abcdef' */ - -static char * number(char * str, unsigned long long num, int base, int size, int precision, int type) +static int check_of_version(void) { - char c,sign,tmp[66]; - const char *digits="0123456789abcdefghijklmnopqrstuvwxyz"; - int i; + phandle oprom, chosen; + char version[64]; - if (type & LARGE) - digits = "0123456789ABCDEFGHIJKLMNOPQRSTUVWXYZ"; - if (type & LEFT) - type &= ~ZEROPAD; - if (base < 2 || base > 36) + oprom = finddevice("/openprom"); + if (oprom == (phandle) -1) return 0; - c = (type & ZEROPAD) ? '0' : ' '; - sign = 0; - if (type & SIGN) { - if ((signed long long)num < 0) { - sign = '-'; - num = - (signed long long)num; - size--; - } else if (type & PLUS) { - sign = '+'; - size--; - } else if (type & SPACE) { - sign = ' '; - size--; + if (getprop(oprom, "model", version, sizeof(version)) <= 0) + return 0; + version[sizeof(version)-1] = 0; + printf("OF version = '%s'\r\n", version); + if (!string_match(version, "Open Firmware, 1.") + && !string_match(version, "FirmWorks,3.")) + return 0; + chosen = finddevice("/chosen"); + if (chosen == (phandle) -1) { + chosen = finddevice("/chosen@0"); + if (chosen == (phandle) -1) { + printf("no chosen\n"); + return 0; } } - if (type & SPECIAL) { - if (base == 16) - size -= 2; - else if (base == 8) - size--; - } - i = 0; - if (num == 0) - tmp[i++]='0'; - else while (num != 0) { - tmp[i++] = digits[do_div(num, base)]; + if (getprop(chosen, "mmu", &chosen_mmu, sizeof(chosen_mmu)) <= 0) { + printf("no mmu\n"); + return 0; } - if (i > precision) - precision = i; - size -= precision; - if (!(type&(ZEROPAD+LEFT))) - while(size-->0) - *str++ = ' '; - if (sign) - *str++ = sign; - if (type & SPECIAL) { - if (base==8) - *str++ = '0'; - else if (base==16) { - *str++ = '0'; - *str++ = digits[33]; + memory = (ihandle) call_prom("open", 1, 1, "/memory"); + if (memory == (ihandle) -1) { + memory = (ihandle) call_prom("open", 1, 1, "/memory@0"); + if (memory == (ihandle) -1) { + printf("no memory node\n"); + return 0; } } - if (!(type & LEFT)) - while (size-- > 0) - *str++ = c; - while (i < precision--) - *str++ = '0'; - while (i-- > 0) - *str++ = tmp[i]; - while (size-- > 0) - *str++ = ' '; - return str; + printf("old OF detected\r\n"); + return 1; } -int vsprintf(char *buf, const char *fmt, va_list args) +void *claim(unsigned long virt, unsigned long size, unsigned long align) { - int len; - unsigned long long num; - int i, base; - char * str; - const char *s; - - int flags; /* flags to number() */ - - int field_width; /* width of output field */ - int precision; /* min. # of digits for integers; max - number of chars for from string */ - int qualifier; /* 'h', 'l', or 'L' for integer fields */ - /* 'z' support added 23/7/1999 S.H. */ - /* 'z' changed to 'Z' --davidm 1/25/99 */ + int ret; + unsigned int result; + if (need_map < 0) + need_map = check_of_version(); + if (align || !need_map) + return (void *) call_prom("claim", 3, 1, virt, size, align); - for (str=buf ; *fmt ; ++fmt) { - if (*fmt != '%') { - *str++ = *fmt; - continue; - } - - /* process flags */ - flags = 0; - repeat: - ++fmt; /* this also skips first '%' */ - switch (*fmt) { - case '-': flags |= LEFT; goto repeat; - case '+': flags |= PLUS; goto repeat; - case ' ': flags |= SPACE; goto repeat; - case '#': flags |= SPECIAL; goto repeat; - case '0': flags |= ZEROPAD; goto repeat; - } - - /* get field width */ - field_width = -1; - if ('0' <= *fmt && *fmt <= '9') - field_width = skip_atoi(&fmt); - else if (*fmt == '*') { - ++fmt; - /* it's the next argument */ - field_width = va_arg(args, int); - if (field_width < 0) { - field_width = -field_width; - flags |= LEFT; - } - } - - /* get the precision */ - precision = -1; - if (*fmt == '.') { - ++fmt; - if ('0' <= *fmt && *fmt <= '9') - precision = skip_atoi(&fmt); - else if (*fmt == '*') { - ++fmt; - /* it's the next argument */ - precision = va_arg(args, int); - } - if (precision < 0) - precision = 0; - } - - /* get the conversion qualifier */ - qualifier = -1; - if (*fmt == 'h' || *fmt == 'l' || *fmt == 'L' || *fmt =='Z') { - qualifier = *fmt; - ++fmt; - } - - /* default base */ - base = 10; - - switch (*fmt) { - case 'c': - if (!(flags & LEFT)) - while (--field_width > 0) - *str++ = ' '; - *str++ = (unsigned char) va_arg(args, int); - while (--field_width > 0) - *str++ = ' '; - continue; - - case 's': - s = va_arg(args, char *); - if (!s) - s = "<NULL>"; - - len = strnlen(s, precision); - - if (!(flags & LEFT)) - while (len < field_width--) - *str++ = ' '; - for (i = 0; i < len; ++i) - *str++ = *s++; - while (len < field_width--) - *str++ = ' '; - continue; - - case 'p': - if (field_width == -1) { - field_width = 2*sizeof(void *); - flags |= ZEROPAD; - } - str = number(str, - (unsigned long) va_arg(args, void *), 16, - field_width, precision, flags); - continue; - - - case 'n': - if (qualifier == 'l') { - long * ip = va_arg(args, long *); - *ip = (str - buf); - } else if (qualifier == 'Z') { - size_t * ip = va_arg(args, size_t *); - *ip = (str - buf); - } else { - int * ip = va_arg(args, int *); - *ip = (str - buf); - } - continue; - - case '%': - *str++ = '%'; - continue; - - /* integer number formats - set up the flags and "break" */ - case 'o': - base = 8; - break; - - case 'X': - flags |= LARGE; - case 'x': - base = 16; - break; - - case 'd': - case 'i': - flags |= SIGN; - case 'u': - break; - - default: - *str++ = '%'; - if (*fmt) - *str++ = *fmt; - else - --fmt; - continue; - } - if (qualifier == 'l') { - num = va_arg(args, unsigned long); - if (flags & SIGN) - num = (signed long) num; - } else if (qualifier == 'Z') { - num = va_arg(args, size_t); - } else if (qualifier == 'h') { - num = (unsigned short) va_arg(args, int); - if (flags & SIGN) - num = (signed short) num; - } else { - num = va_arg(args, unsigned int); - if (flags & SIGN) - num = (signed int) num; - } - str = number(str, num, base, field_width, precision, flags); - } - *str = '\0'; - return str-buf; -} - -int sprintf(char * buf, const char *fmt, ...) -{ - va_list args; - int i; - - va_start(args, fmt); - i=vsprintf(buf,fmt,args); - va_end(args); - return i; -} - -static char sprint_buf[1024]; - -int -printf(const char *fmt, ...) -{ - va_list args; - int n; - - va_start(args, fmt); - n = vsprintf(sprint_buf, fmt, args); - va_end(args); - write(stdout, sprint_buf, n); - return n; + ret = call_prom_ret("call-method", 5, 2, &result, "claim", memory, + align, size, virt); + if (ret != 0 || result == -1) + return (void *) -1; + ret = call_prom_ret("call-method", 5, 2, &result, "claim", chosen_mmu, + align, size, virt); + /* 0x12 == coherent + read/write */ + ret = call_prom("call-method", 6, 1, "map", chosen_mmu, + 0x12, size, virt, virt); + return (void *) virt; } diff --git a/arch/powerpc/boot/prom.h b/arch/powerpc/boot/prom.h index 96ab5aec740..3e2ddd4a5a8 100644 --- a/arch/powerpc/boot/prom.h +++ b/arch/powerpc/boot/prom.h @@ -1,18 +1,34 @@ #ifndef _PPC_BOOT_PROM_H_ #define _PPC_BOOT_PROM_H_ +typedef void *phandle; +typedef void *ihandle; + extern int (*prom) (void *); -extern void *chosen_handle; +extern phandle chosen_handle; +extern ihandle stdout; -extern void *stdin; -extern void *stdout; -extern void *stderr; +int call_prom(const char *service, int nargs, int nret, ...); +int call_prom_ret(const char *service, int nargs, int nret, + unsigned int *rets, ...); extern int write(void *handle, void *ptr, int nb); -extern int read(void *handle, void *ptr, int nb); -extern void exit(void); -extern void pause(void); -extern void *finddevice(const char *); -extern void *claim(unsigned long virt, unsigned long size, unsigned long align); -extern int getprop(void *phandle, const char *name, void *buf, int buflen); +extern void *claim(unsigned long virt, unsigned long size, unsigned long aln); + +static inline void exit(void) +{ + call_prom("exit", 0, 0); +} + +static inline phandle finddevice(const char *name) +{ + return (phandle) call_prom("finddevice", 1, 1, name); +} + +static inline int getprop(void *phandle, const char *name, + void *buf, int buflen) +{ + return call_prom("getprop", 4, 1, phandle, name, buf, buflen); +} + #endif /* _PPC_BOOT_PROM_H_ */ diff --git a/arch/powerpc/boot/rs6000.h b/arch/powerpc/boot/rs6000.h new file mode 100644 index 00000000000..433f45084e4 --- /dev/null +++ b/arch/powerpc/boot/rs6000.h @@ -0,0 +1,243 @@ +/* IBM RS/6000 "XCOFF" file definitions for BFD. + Copyright (C) 1990, 1991 Free Software Foundation, Inc. + FIXME: Can someone provide a transliteration of this name into ASCII? + Using the following chars caused a compiler warning on HIUX (so I replaced + them with octal escapes), and isn't useful without an understanding of what + character set it is. + Written by Mimi Ph\373\364ng-Th\345o V\365 of IBM + and John Gilmore of Cygnus Support. */ + +/********************** FILE HEADER **********************/ + +struct external_filehdr { + char f_magic[2]; /* magic number */ + char f_nscns[2]; /* number of sections */ + char f_timdat[4]; /* time & date stamp */ + char f_symptr[4]; /* file pointer to symtab */ + char f_nsyms[4]; /* number of symtab entries */ + char f_opthdr[2]; /* sizeof(optional hdr) */ + char f_flags[2]; /* flags */ +}; + + /* IBM RS/6000 */ +#define U802WRMAGIC 0730 /* writeable text segments **chh** */ +#define U802ROMAGIC 0735 /* readonly sharable text segments */ +#define U802TOCMAGIC 0737 /* readonly text segments and TOC */ + +#define BADMAG(x) \ + ((x).f_magic != U802ROMAGIC && (x).f_magic != U802WRMAGIC && \ + (x).f_magic != U802TOCMAGIC) + +#define FILHDR struct external_filehdr +#define FILHSZ 20 + + +/********************** AOUT "OPTIONAL HEADER" **********************/ + + +typedef struct +{ + unsigned char magic[2]; /* type of file */ + unsigned char vstamp[2]; /* version stamp */ + unsigned char tsize[4]; /* text size in bytes, padded to FW bdry */ + unsigned char dsize[4]; /* initialized data " " */ + unsigned char bsize[4]; /* uninitialized data " " */ + unsigned char entry[4]; /* entry pt. */ + unsigned char text_start[4]; /* base of text used for this file */ + unsigned char data_start[4]; /* base of data used for this file */ + unsigned char o_toc[4]; /* address of TOC */ + unsigned char o_snentry[2]; /* section number of entry point */ + unsigned char o_sntext[2]; /* section number of .text section */ + unsigned char o_sndata[2]; /* section number of .data section */ + unsigned char o_sntoc[2]; /* section number of TOC */ + unsigned char o_snloader[2]; /* section number of .loader section */ + unsigned char o_snbss[2]; /* section number of .bss section */ + unsigned char o_algntext[2]; /* .text alignment */ + unsigned char o_algndata[2]; /* .data alignment */ + unsigned char o_modtype[2]; /* module type (??) */ + unsigned char o_cputype[2]; /* cpu type */ + unsigned char o_maxstack[4]; /* max stack size (??) */ + unsigned char o_maxdata[4]; /* max data size (??) */ + unsigned char o_resv2[12]; /* reserved */ +} +AOUTHDR; + +#define AOUTSZ 72 +#define SMALL_AOUTSZ (28) +#define AOUTHDRSZ 72 + +#define RS6K_AOUTHDR_OMAGIC 0x0107 /* old: text & data writeable */ +#define RS6K_AOUTHDR_NMAGIC 0x0108 /* new: text r/o, data r/w */ +#define RS6K_AOUTHDR_ZMAGIC 0x010B /* paged: text r/o, both page-aligned */ + + +/********************** SECTION HEADER **********************/ + + +struct external_scnhdr { + char s_name[8]; /* section name */ + char s_paddr[4]; /* physical address, aliased s_nlib */ + char s_vaddr[4]; /* virtual address */ + char s_size[4]; /* section size */ + char s_scnptr[4]; /* file ptr to raw data for section */ + char s_relptr[4]; /* file ptr to relocation */ + char s_lnnoptr[4]; /* file ptr to line numbers */ + char s_nreloc[2]; /* number of relocation entries */ + char s_nlnno[2]; /* number of line number entries*/ + char s_flags[4]; /* flags */ +}; + +/* + * names of "special" sections + */ +#define _TEXT ".text" +#define _DATA ".data" +#define _BSS ".bss" +#define _PAD ".pad" +#define _LOADER ".loader" + +#define SCNHDR struct external_scnhdr +#define SCNHSZ 40 + +/* XCOFF uses a special .loader section with type STYP_LOADER. */ +#define STYP_LOADER 0x1000 + +/* XCOFF uses a special .debug section with type STYP_DEBUG. */ +#define STYP_DEBUG 0x2000 + +/* XCOFF handles line number or relocation overflow by creating + another section header with STYP_OVRFLO set. */ +#define STYP_OVRFLO 0x8000 + +/********************** LINE NUMBERS **********************/ + +/* 1 line number entry for every "breakpointable" source line in a section. + * Line numbers are grouped on a per function basis; first entry in a function + * grouping will have l_lnno = 0 and in place of physical address will be the + * symbol table index of the function name. + */ +struct external_lineno { + union { + char l_symndx[4]; /* function name symbol index, iff l_lnno == 0*/ + char l_paddr[4]; /* (physical) address of line number */ + } l_addr; + char l_lnno[2]; /* line number */ +}; + + +#define LINENO struct external_lineno +#define LINESZ 6 + + +/********************** SYMBOLS **********************/ + +#define E_SYMNMLEN 8 /* # characters in a symbol name */ +#define E_FILNMLEN 14 /* # characters in a file name */ +#define E_DIMNUM 4 /* # array dimensions in auxiliary entry */ + +struct external_syment +{ + union { + char e_name[E_SYMNMLEN]; + struct { + char e_zeroes[4]; + char e_offset[4]; + } e; + } e; + char e_value[4]; + char e_scnum[2]; + char e_type[2]; + char e_sclass[1]; + char e_numaux[1]; +}; + + + +#define N_BTMASK (017) +#define N_TMASK (060) +#define N_BTSHFT (4) +#define N_TSHIFT (2) + + +union external_auxent { + struct { + char x_tagndx[4]; /* str, un, or enum tag indx */ + union { + struct { + char x_lnno[2]; /* declaration line number */ + char x_size[2]; /* str/union/array size */ + } x_lnsz; + char x_fsize[4]; /* size of function */ + } x_misc; + union { + struct { /* if ISFCN, tag, or .bb */ + char x_lnnoptr[4]; /* ptr to fcn line # */ + char x_endndx[4]; /* entry ndx past block end */ + } x_fcn; + struct { /* if ISARY, up to 4 dimen. */ + char x_dimen[E_DIMNUM][2]; + } x_ary; + } x_fcnary; + char x_tvndx[2]; /* tv index */ + } x_sym; + + union { + char x_fname[E_FILNMLEN]; + struct { + char x_zeroes[4]; + char x_offset[4]; + } x_n; + } x_file; + + struct { + char x_scnlen[4]; /* section length */ + char x_nreloc[2]; /* # relocation entries */ + char x_nlinno[2]; /* # line numbers */ + } x_scn; + + struct { + char x_tvfill[4]; /* tv fill value */ + char x_tvlen[2]; /* length of .tv */ + char x_tvran[2][2]; /* tv range */ + } x_tv; /* info about .tv section (in auxent of symbol .tv)) */ + + struct { + unsigned char x_scnlen[4]; + unsigned char x_parmhash[4]; + unsigned char x_snhash[2]; + unsigned char x_smtyp[1]; + unsigned char x_smclas[1]; + unsigned char x_stab[4]; + unsigned char x_snstab[2]; + } x_csect; + +}; + +#define SYMENT struct external_syment +#define SYMESZ 18 +#define AUXENT union external_auxent +#define AUXESZ 18 +#define DBXMASK 0x80 /* for dbx storage mask */ +#define SYMNAME_IN_DEBUG(symptr) ((symptr)->n_sclass & DBXMASK) + + + +/********************** RELOCATION DIRECTIVES **********************/ + + +struct external_reloc { + char r_vaddr[4]; + char r_symndx[4]; + char r_size[1]; + char r_type[1]; +}; + + +#define RELOC struct external_reloc +#define RELSZ 10 + +#define DEFAULT_DATA_SECTION_ALIGNMENT 4 +#define DEFAULT_BSS_SECTION_ALIGNMENT 4 +#define DEFAULT_TEXT_SECTION_ALIGNMENT 4 +/* For new sections we havn't heard of before */ +#define DEFAULT_SECTION_ALIGNMENT 4 diff --git a/arch/powerpc/boot/stdio.c b/arch/powerpc/boot/stdio.c new file mode 100644 index 00000000000..b5aa522f8b7 --- /dev/null +++ b/arch/powerpc/boot/stdio.c @@ -0,0 +1,325 @@ +/* + * Copyright (C) Paul Mackerras 1997. + * + * This program is free software; you can redistribute it and/or + * modify it under the terms of the GNU General Public License + * as published by the Free Software Foundation; either version + * 2 of the License, or (at your option) any later version. + */ +#include <stdarg.h> +#include <stddef.h> +#include "string.h" +#include "stdio.h" +#include "prom.h" + +size_t strnlen(const char * s, size_t count) +{ + const char *sc; + + for (sc = s; count-- && *sc != '\0'; ++sc) + /* nothing */; + return sc - s; +} + +extern unsigned int __div64_32(unsigned long long *dividend, + unsigned int divisor); + +/* The unnecessary pointer compare is there + * to check for type safety (n must be 64bit) + */ +# define do_div(n,base) ({ \ + unsigned int __base = (base); \ + unsigned int __rem; \ + (void)(((typeof((n)) *)0) == ((unsigned long long *)0)); \ + if (((n) >> 32) == 0) { \ + __rem = (unsigned int)(n) % __base; \ + (n) = (unsigned int)(n) / __base; \ + } else \ + __rem = __div64_32(&(n), __base); \ + __rem; \ + }) + +static int skip_atoi(const char **s) +{ + int i, c; + + for (i = 0; '0' <= (c = **s) && c <= '9'; ++*s) + i = i*10 + c - '0'; + return i; +} + +#define ZEROPAD 1 /* pad with zero */ +#define SIGN 2 /* unsigned/signed long */ +#define PLUS 4 /* show plus */ +#define SPACE 8 /* space if plus */ +#define LEFT 16 /* left justified */ +#define SPECIAL 32 /* 0x */ +#define LARGE 64 /* use 'ABCDEF' instead of 'abcdef' */ + +static char * number(char * str, unsigned long long num, int base, int size, int precision, int type) +{ + char c,sign,tmp[66]; + const char *digits="0123456789abcdefghijklmnopqrstuvwxyz"; + int i; + + if (type & LARGE) + digits = "0123456789ABCDEFGHIJKLMNOPQRSTUVWXYZ"; + if (type & LEFT) + type &= ~ZEROPAD; + if (base < 2 || base > 36) + return 0; + c = (type & ZEROPAD) ? '0' : ' '; + sign = 0; + if (type & SIGN) { + if ((signed long long)num < 0) { + sign = '-'; + num = - (signed long long)num; + size--; + } else if (type & PLUS) { + sign = '+'; + size--; + } else if (type & SPACE) { + sign = ' '; + size--; + } + } + if (type & SPECIAL) { + if (base == 16) + size -= 2; + else if (base == 8) + size--; + } + i = 0; + if (num == 0) + tmp[i++]='0'; + else while (num != 0) { + tmp[i++] = digits[do_div(num, base)]; + } + if (i > precision) + precision = i; + size -= precision; + if (!(type&(ZEROPAD+LEFT))) + while(size-->0) + *str++ = ' '; + if (sign) + *str++ = sign; + if (type & SPECIAL) { + if (base==8) + *str++ = '0'; + else if (base==16) { + *str++ = '0'; + *str++ = digits[33]; + } + } + if (!(type & LEFT)) + while (size-- > 0) + *str++ = c; + while (i < precision--) + *str++ = '0'; + while (i-- > 0) + *str++ = tmp[i]; + while (size-- > 0) + *str++ = ' '; + return str; +} + +int vsprintf(char *buf, const char *fmt, va_list args) +{ + int len; + unsigned long long num; + int i, base; + char * str; + const char *s; + + int flags; /* flags to number() */ + + int field_width; /* width of output field */ + int precision; /* min. # of digits for integers; max + number of chars for from string */ + int qualifier; /* 'h', 'l', or 'L' for integer fields */ + /* 'z' support added 23/7/1999 S.H. */ + /* 'z' changed to 'Z' --davidm 1/25/99 */ + + + for (str=buf ; *fmt ; ++fmt) { + if (*fmt != '%') { + *str++ = *fmt; + continue; + } + + /* process flags */ + flags = 0; + repeat: + ++fmt; /* this also skips first '%' */ + switch (*fmt) { + case '-': flags |= LEFT; goto repeat; + case '+': flags |= PLUS; goto repeat; + case ' ': flags |= SPACE; goto repeat; + case '#': flags |= SPECIAL; goto repeat; + case '0': flags |= ZEROPAD; goto repeat; + } + + /* get field width */ + field_width = -1; + if ('0' <= *fmt && *fmt <= '9') + field_width = skip_atoi(&fmt); + else if (*fmt == '*') { + ++fmt; + /* it's the next argument */ + field_width = va_arg(args, int); + if (field_width < 0) { + field_width = -field_width; + flags |= LEFT; + } + } + + /* get the precision */ + precision = -1; + if (*fmt == '.') { + ++fmt; + if ('0' <= *fmt && *fmt <= '9') + precision = skip_atoi(&fmt); + else if (*fmt == '*') { + ++fmt; + /* it's the next argument */ + precision = va_arg(args, int); + } + if (precision < 0) + precision = 0; + } + + /* get the conversion qualifier */ + qualifier = -1; + if (*fmt == 'h' || *fmt == 'l' || *fmt == 'L' || *fmt =='Z') { + qualifier = *fmt; + ++fmt; + } + + /* default base */ + base = 10; + + switch (*fmt) { + case 'c': + if (!(flags & LEFT)) + while (--field_width > 0) + *str++ = ' '; + *str++ = (unsigned char) va_arg(args, int); + while (--field_width > 0) + *str++ = ' '; + continue; + + case 's': + s = va_arg(args, char *); + if (!s) + s = "<NULL>"; + + len = strnlen(s, precision); + + if (!(flags & LEFT)) + while (len < field_width--) + *str++ = ' '; + for (i = 0; i < len; ++i) + *str++ = *s++; + while (len < field_width--) + *str++ = ' '; + continue; + + case 'p': + if (field_width == -1) { + field_width = 2*sizeof(void *); + flags |= ZEROPAD; + } + str = number(str, + (unsigned long) va_arg(args, void *), 16, + field_width, precision, flags); + continue; + + + case 'n': + if (qualifier == 'l') { + long * ip = va_arg(args, long *); + *ip = (str - buf); + } else if (qualifier == 'Z') { + size_t * ip = va_arg(args, size_t *); + *ip = (str - buf); + } else { + int * ip = va_arg(args, int *); + *ip = (str - buf); + } + continue; + + case '%': + *str++ = '%'; + continue; + + /* integer number formats - set up the flags and "break" */ + case 'o': + base = 8; + break; + + case 'X': + flags |= LARGE; + case 'x': + base = 16; + break; + + case 'd': + case 'i': + flags |= SIGN; + case 'u': + break; + + default: + *str++ = '%'; + if (*fmt) + *str++ = *fmt; + else + --fmt; + continue; + } + if (qualifier == 'l') { + num = va_arg(args, unsigned long); + if (flags & SIGN) + num = (signed long) num; + } else if (qualifier == 'Z') { + num = va_arg(args, size_t); + } else if (qualifier == 'h') { + num = (unsigned short) va_arg(args, int); + if (flags & SIGN) + num = (signed short) num; + } else { + num = va_arg(args, unsigned int); + if (flags & SIGN) + num = (signed int) num; + } + str = number(str, num, base, field_width, precision, flags); + } + *str = '\0'; + return str-buf; +} + +int sprintf(char * buf, const char *fmt, ...) +{ + va_list args; + int i; + + va_start(args, fmt); + i=vsprintf(buf,fmt,args); + va_end(args); + return i; +} + +static char sprint_buf[1024]; + +int +printf(const char *fmt, ...) +{ + va_list args; + int n; + + va_start(args, fmt); + n = vsprintf(sprint_buf, fmt, args); + va_end(args); + write(stdout, sprint_buf, n); + return n; +} diff --git a/arch/powerpc/boot/stdio.h b/arch/powerpc/boot/stdio.h index 24bd3a8dee9..eb9e16c87ae 100644 --- a/arch/powerpc/boot/stdio.h +++ b/arch/powerpc/boot/stdio.h @@ -7,10 +7,4 @@ extern int sprintf(char *buf, const char *fmt, ...); extern int vsprintf(char *buf, const char *fmt, va_list args); -extern int putc(int c, void *f); -extern int putchar(int c); -extern int getchar(void); - -extern int fputs(char *str, void *f); - #endif /* _PPC_BOOT_STDIO_H_ */ diff --git a/arch/powerpc/boot/string.S b/arch/powerpc/boot/string.S index b1eeaed7db1..ac3d43b6a32 100644 --- a/arch/powerpc/boot/string.S +++ b/arch/powerpc/boot/string.S @@ -107,10 +107,12 @@ memcpy: rlwinm. r7,r5,32-3,3,31 /* r7 = r5 >> 3 */ addi r6,r3,-4 addi r4,r4,-4 - beq 2f /* if less than 8 bytes to do */ + beq 3f /* if less than 8 bytes to do */ andi. r0,r6,3 /* get dest word aligned */ mtctr r7 bne 5f + andi. r0,r4,3 /* check src word aligned too */ + bne 3f 1: lwz r7,4(r4) lwzu r8,8(r4) stw r7,4(r6) @@ -132,6 +134,11 @@ memcpy: bdnz 4b blr 5: subfic r0,r0,4 + cmpw cr1,r0,r5 + add r7,r0,r4 + andi. r7,r7,3 /* will source be word-aligned too? */ + ble cr1,3b + bne 3b /* do byte-by-byte if not */ mtctr r0 6: lbz r7,4(r4) addi r4,r4,1 @@ -149,10 +156,12 @@ backwards_memcpy: rlwinm. r7,r5,32-3,3,31 /* r7 = r5 >> 3 */ add r6,r3,r5 add r4,r4,r5 - beq 2f + beq 3f andi. r0,r6,3 mtctr r7 bne 5f + andi. r0,r4,3 + bne 3f 1: lwz r7,-4(r4) lwzu r8,-8(r4) stw r7,-4(r6) @@ -171,7 +180,12 @@ backwards_memcpy: stbu r0,-1(r6) bdnz 4b blr -5: mtctr r0 +5: cmpw cr1,r0,r5 + subf r7,r0,r4 + andi. r7,r7,3 + ble cr1,3b + bne 3b + mtctr r0 6: lbzu r7,-1(r4) stbu r7,-1(r6) bdnz 6b diff --git a/arch/powerpc/boot/zImage.coff.lds b/arch/powerpc/boot/zImage.coff.lds new file mode 100644 index 00000000000..6016251a1a2 --- /dev/null +++ b/arch/powerpc/boot/zImage.coff.lds @@ -0,0 +1,46 @@ +OUTPUT_ARCH(powerpc:common) +ENTRY(_start) +SECTIONS +{ + . = (5*1024*1024); + _start = .; + .text : + { + *(.text) + *(.fixup) + } + _etext = .; + . = ALIGN(4096); + .data : + { + *(.rodata*) + *(.data*) + *(.sdata*) + __got2_start = .; + *(.got2) + __got2_end = .; + + _vmlinux_start = .; + *(.kernel:vmlinux.strip) + _vmlinux_end = .; + + _initrd_start = .; + *(.kernel:initrd) + _initrd_end = .; + } + + . = ALIGN(4096); + _edata = .; + __bss_start = .; + .bss : + { + *(.sbss) + *(.bss) + } + _end = . ; + + /DISCARD/ : + { + *(.comment) + } +} diff --git a/arch/powerpc/configs/mpc834x_sys_defconfig b/arch/powerpc/configs/mpc834x_sys_defconfig new file mode 100644 index 00000000000..3bff761965c --- /dev/null +++ b/arch/powerpc/configs/mpc834x_sys_defconfig @@ -0,0 +1,911 @@ +# +# Automatically generated make config: don't edit +# Linux kernel version: 2.6.15-g461d4edf-dirty +# Fri Jan 13 11:01:47 2006 +# +# CONFIG_PPC64 is not set +CONFIG_PPC32=y +CONFIG_PPC_MERGE=y +CONFIG_MMU=y +CONFIG_GENERIC_HARDIRQS=y +CONFIG_RWSEM_XCHGADD_ALGORITHM=y +CONFIG_GENERIC_CALIBRATE_DELAY=y +CONFIG_PPC=y +CONFIG_EARLY_PRINTK=y +CONFIG_GENERIC_NVRAM=y +CONFIG_SCHED_NO_NO_OMIT_FRAME_POINTER=y +CONFIG_ARCH_MAY_HAVE_PC_FDC=y +CONFIG_PPC_OF=y +CONFIG_PPC_UDBG_16550=y +# CONFIG_GENERIC_TBSYNC is not set +CONFIG_DEFAULT_UIMAGE=y + +# +# Processor support +# +# CONFIG_CLASSIC32 is not set +# CONFIG_PPC_52xx is not set +# CONFIG_PPC_82xx is not set +CONFIG_PPC_83xx=y +# CONFIG_40x is not set +# CONFIG_44x is not set +# CONFIG_8xx is not set +# CONFIG_E200 is not set +# CONFIG_E500 is not set +CONFIG_6xx=y +CONFIG_83xx=y +CONFIG_PPC_FPU=y +CONFIG_PPC_STD_MMU=y +CONFIG_PPC_STD_MMU_32=y +# CONFIG_SMP is not set + +# +# Code maturity level options +# +CONFIG_EXPERIMENTAL=y +CONFIG_CLEAN_COMPILE=y +CONFIG_BROKEN_ON_SMP=y +CONFIG_INIT_ENV_ARG_LIMIT=32 + +# +# General setup +# +CONFIG_LOCALVERSION="" +CONFIG_LOCALVERSION_AUTO=y +CONFIG_SWAP=y +CONFIG_SYSVIPC=y +# CONFIG_POSIX_MQUEUE is not set +# CONFIG_BSD_PROCESS_ACCT is not set +CONFIG_SYSCTL=y +# CONFIG_AUDIT is not set +# CONFIG_IKCONFIG is not set +CONFIG_INITRAMFS_SOURCE="" +# CONFIG_CC_OPTIMIZE_FOR_SIZE is not set +CONFIG_EMBEDDED=y +# CONFIG_KALLSYMS is not set +CONFIG_HOTPLUG=y +CONFIG_PRINTK=y +CONFIG_BUG=y +CONFIG_ELF_CORE=y +CONFIG_BASE_FULL=y +CONFIG_FUTEX=y +# CONFIG_EPOLL is not set +CONFIG_SHMEM=y +CONFIG_CC_ALIGN_FUNCTIONS=0 +CONFIG_CC_ALIGN_LABELS=0 +CONFIG_CC_ALIGN_LOOPS=0 +CONFIG_CC_ALIGN_JUMPS=0 +CONFIG_SLAB=y +# CONFIG_TINY_SHMEM is not set +CONFIG_BASE_SMALL=0 +# CONFIG_SLOB is not set + +# +# Loadable module support +# +CONFIG_MODULES=y +CONFIG_MODULE_UNLOAD=y +# CONFIG_MODULE_FORCE_UNLOAD is not set +CONFIG_OBSOLETE_MODPARM=y +# CONFIG_MODVERSIONS is not set +# CONFIG_MODULE_SRCVERSION_ALL is not set +# CONFIG_KMOD is not set + +# +# Block layer +# +# CONFIG_LBD is not set + +# +# IO Schedulers +# +CONFIG_IOSCHED_NOOP=y +CONFIG_IOSCHED_AS=y +CONFIG_IOSCHED_DEADLINE=y +CONFIG_IOSCHED_CFQ=y +CONFIG_DEFAULT_AS=y +# CONFIG_DEFAULT_DEADLINE is not set +# CONFIG_DEFAULT_CFQ is not set +# CONFIG_DEFAULT_NOOP is not set +CONFIG_DEFAULT_IOSCHED="anticipatory" +CONFIG_PPC_GEN550=y +# CONFIG_WANT_EARLY_SERIAL is not set + +# +# Platform support +# +CONFIG_MPC834x_SYS=y +CONFIG_MPC834x=y + +# +# Kernel options +# +# CONFIG_HIGHMEM is not set +# CONFIG_HZ_100 is not set +CONFIG_HZ_250=y +# CONFIG_HZ_1000 is not set +CONFIG_HZ=250 +CONFIG_PREEMPT_NONE=y +# CONFIG_PREEMPT_VOLUNTARY is not set +# CONFIG_PREEMPT is not set +CONFIG_BINFMT_ELF=y +# CONFIG_BINFMT_MISC is not set +CONFIG_ARCH_FLATMEM_ENABLE=y +CONFIG_SELECT_MEMORY_MODEL=y +CONFIG_FLATMEM_MANUAL=y +# CONFIG_DISCONTIGMEM_MANUAL is not set +# CONFIG_SPARSEMEM_MANUAL is not set +CONFIG_FLATMEM=y +CONFIG_FLAT_NODE_MEM_MAP=y +# CONFIG_SPARSEMEM_STATIC is not set +CONFIG_SPLIT_PTLOCK_CPUS=4 +CONFIG_PROC_DEVICETREE=y +# CONFIG_CMDLINE_BOOL is not set +# CONFIG_PM is not set +# CONFIG_SOFTWARE_SUSPEND is not set +CONFIG_SECCOMP=y +CONFIG_ISA_DMA_API=y + +# +# Bus options +# +CONFIG_GENERIC_ISA_DMA=y +# CONFIG_PPC_I8259 is not set +CONFIG_PPC_INDIRECT_PCI=y +CONFIG_FSL_SOC=y +CONFIG_PCI=y +CONFIG_PCI_DOMAINS=y +# CONFIG_PCI_LEGACY_PROC is not set + +# +# PCCARD (PCMCIA/CardBus) support +# +# CONFIG_PCCARD is not set + +# +# PCI Hotplug Support +# +# CONFIG_HOTPLUG_PCI is not set + +# +# Advanced setup +# +# CONFIG_ADVANCED_OPTIONS is not set + +# +# Default settings for advanced configuration options are used +# +CONFIG_HIGHMEM_START=0xfe000000 +CONFIG_LOWMEM_SIZE=0x30000000 +CONFIG_KERNEL_START=0xc0000000 +CONFIG_TASK_SIZE=0x80000000 +CONFIG_BOOT_LOAD=0x00800000 + +# +# Networking +# +CONFIG_NET=y + +# +# Networking options +# +CONFIG_PACKET=y +# CONFIG_PACKET_MMAP is not set +CONFIG_UNIX=y +# CONFIG_NET_KEY is not set +CONFIG_INET=y +CONFIG_IP_MULTICAST=y +# CONFIG_IP_ADVANCED_ROUTER is not set +CONFIG_IP_FIB_HASH=y +CONFIG_IP_PNP=y +CONFIG_IP_PNP_DHCP=y +CONFIG_IP_PNP_BOOTP=y +# CONFIG_IP_PNP_RARP is not set +# CONFIG_NET_IPIP is not set +# CONFIG_NET_IPGRE is not set +# CONFIG_IP_MROUTE is not set +# CONFIG_ARPD is not set +CONFIG_SYN_COOKIES=y +# CONFIG_INET_AH is not set +# CONFIG_INET_ESP is not set +# CONFIG_INET_IPCOMP is not set +# CONFIG_INET_TUNNEL is not set +CONFIG_INET_DIAG=y +CONFIG_INET_TCP_DIAG=y +# CONFIG_TCP_CONG_ADVANCED is not set +CONFIG_TCP_CONG_BIC=y +# CONFIG_IPV6 is not set +# CONFIG_NETFILTER is not set + +# +# DCCP Configuration (EXPERIMENTAL) +# +# CONFIG_IP_DCCP is not set + +# +# SCTP Configuration (EXPERIMENTAL) +# +# CONFIG_IP_SCTP is not set +# CONFIG_ATM is not set +# CONFIG_BRIDGE is not set +# CONFIG_VLAN_8021Q is not set +# CONFIG_DECNET is not set +# CONFIG_LLC2 is not set +# CONFIG_IPX is not set +# CONFIG_ATALK is not set +# CONFIG_X25 is not set +# CONFIG_LAPB is not set +# CONFIG_NET_DIVERT is not set +# CONFIG_ECONET is not set +# CONFIG_WAN_ROUTER is not set + +# +# QoS and/or fair queueing +# +# CONFIG_NET_SCHED is not set + +# +# Network testing +# +# CONFIG_NET_PKTGEN is not set +# CONFIG_HAMRADIO is not set +# CONFIG_IRDA is not set +# CONFIG_BT is not set +# CONFIG_IEEE80211 is not set + +# +# Device Drivers +# + +# +# Generic Driver Options +# +CONFIG_STANDALONE=y +CONFIG_PREVENT_FIRMWARE_BUILD=y +# CONFIG_FW_LOADER is not set + +# +# Connector - unified userspace <-> kernelspace linker +# +# CONFIG_CONNECTOR is not set + +# +# Memory Technology Devices (MTD) +# +# CONFIG_MTD is not set + +# +# Parallel port support +# +# CONFIG_PARPORT is not set + +# +# Plug and Play support +# + +# +# Block devices +# +# CONFIG_BLK_DEV_FD is not set +# CONFIG_BLK_CPQ_DA is not set +# CONFIG_BLK_CPQ_CISS_DA is not set +# CONFIG_BLK_DEV_DAC960 is not set +# CONFIG_BLK_DEV_UMEM is not set +# CONFIG_BLK_DEV_COW_COMMON is not set +CONFIG_BLK_DEV_LOOP=y +# CONFIG_BLK_DEV_CRYPTOLOOP is not set +# CONFIG_BLK_DEV_NBD is not set +# CONFIG_BLK_DEV_SX8 is not set +CONFIG_BLK_DEV_RAM=y +CONFIG_BLK_DEV_RAM_COUNT=16 +CONFIG_BLK_DEV_RAM_SIZE=32768 +CONFIG_BLK_DEV_INITRD=y +# CONFIG_CDROM_PKTCDVD is not set +# CONFIG_ATA_OVER_ETH is not set + +# +# ATA/ATAPI/MFM/RLL support +# +# CONFIG_IDE is not set + +# +# SCSI device support +# +# CONFIG_RAID_ATTRS is not set +# CONFIG_SCSI is not set + +# +# Multi-device support (RAID and LVM) +# +# CONFIG_MD is not set + +# +# Fusion MPT device support +# +# CONFIG_FUSION is not set + +# +# IEEE 1394 (FireWire) support +# +# CONFIG_IEEE1394 is not set + +# +# I2O device support +# +# CONFIG_I2O is not set + +# +# Macintosh device drivers +# +# CONFIG_WINDFARM is not set + +# +# Network device support +# +CONFIG_NETDEVICES=y +# CONFIG_DUMMY is not set +# CONFIG_BONDING is not set +# CONFIG_EQUALIZER is not set +# CONFIG_TUN is not set + +# +# ARCnet devices +# +# CONFIG_ARCNET is not set + +# +# PHY device support +# +CONFIG_PHYLIB=y + +# +# MII PHY device drivers +# +CONFIG_MARVELL_PHY=y +# CONFIG_DAVICOM_PHY is not set +# CONFIG_QSEMI_PHY is not set +# CONFIG_LXT_PHY is not set +# CONFIG_CICADA_PHY is not set + +# +# Ethernet (10 or 100Mbit) +# +CONFIG_NET_ETHERNET=y +CONFIG_MII=y +# CONFIG_HAPPYMEAL is not set +# CONFIG_SUNGEM is not set +# CONFIG_CASSINI is not set +# CONFIG_NET_VENDOR_3COM is not set + +# +# Tulip family network device support +# +# CONFIG_NET_TULIP is not set +# CONFIG_HP100 is not set +CONFIG_NET_PCI=y +# CONFIG_PCNET32 is not set +# CONFIG_AMD8111_ETH is not set +# CONFIG_ADAPTEC_STARFIRE is not set +# CONFIG_B44 is not set +# CONFIG_FORCEDETH is not set +# CONFIG_DGRS is not set +# CONFIG_EEPRO100 is not set +CONFIG_E100=y +# CONFIG_FEALNX is not set +# CONFIG_NATSEMI is not set +# CONFIG_NE2K_PCI is not set +# CONFIG_8139CP is not set +# CONFIG_8139TOO is not set +# CONFIG_SIS900 is not set +# CONFIG_EPIC100 is not set +# CONFIG_SUNDANCE is not set +# CONFIG_TLAN is not set +# CONFIG_VIA_RHINE is not set + +# +# Ethernet (1000 Mbit) +# +# CONFIG_ACENIC is not set +# CONFIG_DL2K is not set +# CONFIG_E1000 is not set +# CONFIG_NS83820 is not set +# CONFIG_HAMACHI is not set +# CONFIG_YELLOWFIN is not set +# CONFIG_R8169 is not set +# CONFIG_SIS190 is not set +# CONFIG_SKGE is not set +# CONFIG_SKY2 is not set +# CONFIG_SK98LIN is not set +# CONFIG_VIA_VELOCITY is not set +# CONFIG_TIGON3 is not set +# CONFIG_BNX2 is not set +CONFIG_GIANFAR=y +# CONFIG_GFAR_NAPI is not set + +# +# Ethernet (10000 Mbit) +# +# CONFIG_CHELSIO_T1 is not set +# CONFIG_IXGB is not set +# CONFIG_S2IO is not set + +# +# Token Ring devices +# +# CONFIG_TR is not set + +# +# Wireless LAN (non-hamradio) +# +# CONFIG_NET_RADIO is not set + +# +# Wan interfaces +# +# CONFIG_WAN is not set +# CONFIG_FDDI is not set +# CONFIG_HIPPI is not set +# CONFIG_PPP is not set +# CONFIG_SLIP is not set +# CONFIG_SHAPER is not set +# CONFIG_NETCONSOLE is not set +# CONFIG_NETPOLL is not set +# CONFIG_NET_POLL_CONTROLLER is not set + +# +# ISDN subsystem +# +# CONFIG_ISDN is not set + +# +# Telephony Support +# +# CONFIG_PHONE is not set + +# +# Input device support +# +CONFIG_INPUT=y + +# +# Userland interfaces +# +# CONFIG_INPUT_MOUSEDEV is not set +# CONFIG_INPUT_JOYDEV is not set +# CONFIG_INPUT_TSDEV is not set +# CONFIG_INPUT_EVDEV is not set +# CONFIG_INPUT_EVBUG is not set + +# +# Input Device Drivers +# +# CONFIG_INPUT_KEYBOARD is not set +# CONFIG_INPUT_MOUSE is not set +# CONFIG_INPUT_JOYSTICK is not set +# CONFIG_INPUT_TOUCHSCREEN is not set +# CONFIG_INPUT_MISC is not set + +# +# Hardware I/O ports +# +# CONFIG_SERIO is not set +# CONFIG_GAMEPORT is not set + +# +# Character devices +# +# CONFIG_VT is not set +# CONFIG_SERIAL_NONSTANDARD is not set + +# +# Serial drivers +# +CONFIG_SERIAL_8250=y +CONFIG_SERIAL_8250_CONSOLE=y +CONFIG_SERIAL_8250_NR_UARTS=4 +CONFIG_SERIAL_8250_RUNTIME_UARTS=4 +# CONFIG_SERIAL_8250_EXTENDED is not set + +# +# Non-8250 serial port support +# +CONFIG_SERIAL_CORE=y +CONFIG_SERIAL_CORE_CONSOLE=y +CONFIG_UNIX98_PTYS=y +CONFIG_LEGACY_PTYS=y +CONFIG_LEGACY_PTY_COUNT=256 + +# +# IPMI +# +# CONFIG_IPMI_HANDLER is not set + +# +# Watchdog Cards +# +CONFIG_WATCHDOG=y +# CONFIG_WATCHDOG_NOWAYOUT is not set + +# +# Watchdog Device Drivers +# +# CONFIG_SOFT_WATCHDOG is not set +CONFIG_83xx_WDT=y + +# +# PCI-based Watchdog Cards +# +# CONFIG_PCIPCWATCHDOG is not set +# CONFIG_WDTPCI is not set +# CONFIG_NVRAM is not set +CONFIG_GEN_RTC=y +# CONFIG_GEN_RTC_X is not set +# CONFIG_DTLK is not set +# CONFIG_R3964 is not set +# CONFIG_APPLICOM is not set + +# +# Ftape, the floppy tape device driver +# +# CONFIG_AGP is not set +# CONFIG_DRM is not set +# CONFIG_RAW_DRIVER is not set + +# +# TPM devices +# +# CONFIG_TCG_TPM is not set +# CONFIG_TELCLOCK is not set + +# +# I2C support +# +CONFIG_I2C=y +CONFIG_I2C_CHARDEV=y + +# +# I2C Algorithms +# +# CONFIG_I2C_ALGOBIT is not set +# CONFIG_I2C_ALGOPCF is not set +# CONFIG_I2C_ALGOPCA is not set + +# +# I2C Hardware Bus support +# +# CONFIG_I2C_ALI1535 is not set +# CONFIG_I2C_ALI1563 is not set +# CONFIG_I2C_ALI15X3 is not set +# CONFIG_I2C_AMD756 is not set +# CONFIG_I2C_AMD8111 is not set +# CONFIG_I2C_I801 is not set +# CONFIG_I2C_I810 is not set +# CONFIG_I2C_PIIX4 is not set +CONFIG_I2C_MPC=y +# CONFIG_I2C_NFORCE2 is not set +# CONFIG_I2C_PARPORT_LIGHT is not set +# CONFIG_I2C_PROSAVAGE is not set +# CONFIG_I2C_SAVAGE4 is not set +# CONFIG_SCx200_ACB is not set +# CONFIG_I2C_SIS5595 is not set +# CONFIG_I2C_SIS630 is not set +# CONFIG_I2C_SIS96X is not set +# CONFIG_I2C_STUB is not set +# CONFIG_I2C_VIA is not set +# CONFIG_I2C_VIAPRO is not set +# CONFIG_I2C_VOODOO3 is not set +# CONFIG_I2C_PCA_ISA is not set + +# +# Miscellaneous I2C Chip support +# +# CONFIG_SENSORS_DS1337 is not set +# CONFIG_SENSORS_DS1374 is not set +# CONFIG_SENSORS_EEPROM is not set +# CONFIG_SENSORS_PCF8574 is not set +# CONFIG_SENSORS_PCA9539 is not set +# CONFIG_SENSORS_PCF8591 is not set +# CONFIG_SENSORS_RTC8564 is not set +# CONFIG_SENSORS_M41T00 is not set +# CONFIG_SENSORS_MAX6875 is not set +# CONFIG_RTC_X1205_I2C is not set +# CONFIG_I2C_DEBUG_CORE is not set +# CONFIG_I2C_DEBUG_ALGO is not set +# CONFIG_I2C_DEBUG_BUS is not set +# CONFIG_I2C_DEBUG_CHIP is not set + +# +# Dallas's 1-wire bus +# +# CONFIG_W1 is not set + +# +# Hardware Monitoring support +# +CONFIG_HWMON=y +# CONFIG_HWMON_VID is not set +# CONFIG_SENSORS_ADM1021 is not set +# CONFIG_SENSORS_ADM1025 is not set +# CONFIG_SENSORS_ADM1026 is not set +# CONFIG_SENSORS_ADM1031 is not set +# CONFIG_SENSORS_ADM9240 is not set +# CONFIG_SENSORS_ASB100 is not set +# CONFIG_SENSORS_ATXP1 is not set +# CONFIG_SENSORS_DS1621 is not set +# CONFIG_SENSORS_FSCHER is not set +# CONFIG_SENSORS_FSCPOS is not set +# CONFIG_SENSORS_GL518SM is not set +# CONFIG_SENSORS_GL520SM is not set +# CONFIG_SENSORS_IT87 is not set +# CONFIG_SENSORS_LM63 is not set +# CONFIG_SENSORS_LM75 is not set +# CONFIG_SENSORS_LM77 is not set +# CONFIG_SENSORS_LM78 is not set +# CONFIG_SENSORS_LM80 is not set +# CONFIG_SENSORS_LM83 is not set +# CONFIG_SENSORS_LM85 is not set +# CONFIG_SENSORS_LM87 is not set +# CONFIG_SENSORS_LM90 is not set +# CONFIG_SENSORS_LM92 is not set +# CONFIG_SENSORS_MAX1619 is not set +# CONFIG_SENSORS_PC87360 is not set +# CONFIG_SENSORS_SIS5595 is not set +# CONFIG_SENSORS_SMSC47M1 is not set +# CONFIG_SENSORS_SMSC47B397 is not set +# CONFIG_SENSORS_VIA686A is not set +# CONFIG_SENSORS_VT8231 is not set +# CONFIG_SENSORS_W83781D is not set +# CONFIG_SENSORS_W83792D is not set +# CONFIG_SENSORS_W83L785TS is not set +# CONFIG_SENSORS_W83627HF is not set +# CONFIG_SENSORS_W83627EHF is not set +# CONFIG_HWMON_DEBUG_CHIP is not set + +# +# Misc devices +# + +# +# Multimedia Capabilities Port drivers +# + +# +# Multimedia devices +# +# CONFIG_VIDEO_DEV is not set + +# +# Digital Video Broadcasting Devices +# +# CONFIG_DVB is not set + +# +# Graphics support +# +# CONFIG_FB is not set + +# +# Sound +# +# CONFIG_SOUND is not set + +# +# USB support +# +CONFIG_USB_ARCH_HAS_HCD=y +CONFIG_USB_ARCH_HAS_OHCI=y +# CONFIG_USB is not set + +# +# NOTE: USB_STORAGE enables SCSI, and 'SCSI disk support' +# + +# +# USB Gadget Support +# +# CONFIG_USB_GADGET is not set + +# +# MMC/SD Card support +# +# CONFIG_MMC is not set + +# +# InfiniBand support +# +# CONFIG_INFINIBAND is not set + +# +# SN Devices +# + +# +# File systems +# +CONFIG_EXT2_FS=y +# CONFIG_EXT2_FS_XATTR is not set +# CONFIG_EXT2_FS_XIP is not set +CONFIG_EXT3_FS=y +CONFIG_EXT3_FS_XATTR=y +# CONFIG_EXT3_FS_POSIX_ACL is not set +# CONFIG_EXT3_FS_SECURITY is not set +CONFIG_JBD=y +# CONFIG_JBD_DEBUG is not set +CONFIG_FS_MBCACHE=y +# CONFIG_REISERFS_FS is not set +# CONFIG_JFS_FS is not set +# CONFIG_FS_POSIX_ACL is not set +# CONFIG_XFS_FS is not set +# CONFIG_OCFS2_FS is not set +# CONFIG_MINIX_FS is not set +# CONFIG_ROMFS_FS is not set +CONFIG_INOTIFY=y +# CONFIG_QUOTA is not set +CONFIG_DNOTIFY=y +# CONFIG_AUTOFS_FS is not set +# CONFIG_AUTOFS4_FS is not set +# CONFIG_FUSE_FS is not set + +# +# CD-ROM/DVD Filesystems +# +# CONFIG_ISO9660_FS is not set +# CONFIG_UDF_FS is not set + +# +# DOS/FAT/NT Filesystems +# +# CONFIG_MSDOS_FS is not set +# CONFIG_VFAT_FS is not set +# CONFIG_NTFS_FS is not set + +# +# Pseudo filesystems +# +CONFIG_PROC_FS=y +CONFIG_PROC_KCORE=y +CONFIG_SYSFS=y +CONFIG_TMPFS=y +# CONFIG_HUGETLB_PAGE is not set +CONFIG_RAMFS=y +# CONFIG_RELAYFS_FS is not set +# CONFIG_CONFIGFS_FS is not set + +# +# Miscellaneous filesystems +# +# CONFIG_ADFS_FS is not set +# CONFIG_AFFS_FS is not set +# CONFIG_HFS_FS is not set +# CONFIG_HFSPLUS_FS is not set +# CONFIG_BEFS_FS is not set +# CONFIG_BFS_FS is not set +# CONFIG_EFS_FS is not set +# CONFIG_CRAMFS is not set +# CONFIG_VXFS_FS is not set +# CONFIG_HPFS_FS is not set +# CONFIG_QNX4FS_FS is not set +# CONFIG_SYSV_FS is not set +# CONFIG_UFS_FS is not set + +# +# Network File Systems +# +CONFIG_NFS_FS=y +CONFIG_NFS_V3=y +# CONFIG_NFS_V3_ACL is not set +CONFIG_NFS_V4=y +# CONFIG_NFS_DIRECTIO is not set +# CONFIG_NFSD is not set +CONFIG_ROOT_NFS=y +CONFIG_LOCKD=y +CONFIG_LOCKD_V4=y +CONFIG_NFS_COMMON=y +CONFIG_SUNRPC=y +CONFIG_SUNRPC_GSS=y +CONFIG_RPCSEC_GSS_KRB5=y +# CONFIG_RPCSEC_GSS_SPKM3 is not set +# CONFIG_SMB_FS is not set +# CONFIG_CIFS is not set +# CONFIG_NCP_FS is not set +# CONFIG_CODA_FS is not set +# CONFIG_AFS_FS is not set +# CONFIG_9P_FS is not set + +# +# Partition Types +# +CONFIG_PARTITION_ADVANCED=y +# CONFIG_ACORN_PARTITION is not set +# CONFIG_OSF_PARTITION is not set +# CONFIG_AMIGA_PARTITION is not set +# CONFIG_ATARI_PARTITION is not set +# CONFIG_MAC_PARTITION is not set +# CONFIG_MSDOS_PARTITION is not set +# CONFIG_LDM_PARTITION is not set +# CONFIG_SGI_PARTITION is not set +# CONFIG_ULTRIX_PARTITION is not set +# CONFIG_SUN_PARTITION is not set +# CONFIG_EFI_PARTITION is not set + +# +# Native Language Support +# +# CONFIG_NLS is not set + +# +# Library routines +# +# CONFIG_CRC_CCITT is not set +# CONFIG_CRC16 is not set +CONFIG_CRC32=y +# CONFIG_LIBCRC32C is not set + +# +# Instrumentation Support +# +# CONFIG_PROFILING is not set + +# +# Kernel hacking +# +# CONFIG_PRINTK_TIME is not set +# CONFIG_MAGIC_SYSRQ is not set +# CONFIG_DEBUG_KERNEL is not set +CONFIG_LOG_BUF_SHIFT=14 +# CONFIG_BOOTX_TEXT is not set +# CONFIG_SERIAL_TEXT_DEBUG is not set +# CONFIG_PPC_EARLY_DEBUG_LPAR is not set +# CONFIG_PPC_EARLY_DEBUG_G5 is not set +# CONFIG_PPC_EARLY_DEBUG_RTAS is not set +# CONFIG_PPC_EARLY_DEBUG_MAPLE is not set +# CONFIG_PPC_EARLY_DEBUG_ISERIES is not set + +# +# Security options +# +# CONFIG_KEYS is not set +# CONFIG_SECURITY is not set + +# +# Cryptographic options +# +CONFIG_CRYPTO=y +# CONFIG_CRYPTO_HMAC is not set +# CONFIG_CRYPTO_NULL is not set +# CONFIG_CRYPTO_MD4 is not set +CONFIG_CRYPTO_MD5=y +# CONFIG_CRYPTO_SHA1 is not set +# CONFIG_CRYPTO_SHA256 is not set +# CONFIG_CRYPTO_SHA512 is not set +# CONFIG_CRYPTO_WP512 is not set +# CONFIG_CRYPTO_TGR192 is not set +CONFIG_CRYPTO_DES=y +# CONFIG_CRYPTO_BLOWFISH is not set +# CONFIG_CRYPTO_TWOFISH is not set +# CONFIG_CRYPTO_SERPENT is not set +# CONFIG_CRYPTO_AES is not set +# CONFIG_CRYPTO_CAST5 is not set +# CONFIG_CRYPTO_CAST6 is not set +# CONFIG_CRYPTO_TEA is not set +# CONFIG_CRYPTO_ARC4 is not set +# CONFIG_CRYPTO_KHAZAD is not set +# CONFIG_CRYPTO_ANUBIS is not set +# CONFIG_CRYPTO_DEFLATE is not set +# CONFIG_CRYPTO_MICHAEL_MIC is not set +# CONFIG_CRYPTO_CRC32C is not set +# CONFIG_CRYPTO_TEST is not set + +# +# Hardware crypto devices +# + +# +# SEC2.x Options +# +CONFIG_MPC8349E_SEC2x=y + +# +# SEC2.x Test Options +# +CONFIG_MPC8349E_SEC2xTEST=y diff --git a/arch/powerpc/kernel/asm-offsets.c b/arch/powerpc/kernel/asm-offsets.c index 56399c5c931..840aad43a98 100644 --- a/arch/powerpc/kernel/asm-offsets.c +++ b/arch/powerpc/kernel/asm-offsets.c @@ -135,7 +135,7 @@ int main(void) DEFINE(PACA_EXMC, offsetof(struct paca_struct, exmc)); DEFINE(PACA_EXSLB, offsetof(struct paca_struct, exslb)); DEFINE(PACAEMERGSP, offsetof(struct paca_struct, emergency_sp)); - DEFINE(PACALPPACA, offsetof(struct paca_struct, lppaca)); + DEFINE(PACALPPACAPTR, offsetof(struct paca_struct, lppaca_ptr)); DEFINE(PACAHWCPUID, offsetof(struct paca_struct, hw_cpu_id)); DEFINE(LPPACASRR0, offsetof(struct lppaca, saved_srr0)); diff --git a/arch/powerpc/kernel/cpu_setup_power4.S b/arch/powerpc/kernel/cpu_setup_power4.S index cca942fe611..b61d86e7ceb 100644 --- a/arch/powerpc/kernel/cpu_setup_power4.S +++ b/arch/powerpc/kernel/cpu_setup_power4.S @@ -130,7 +130,7 @@ _GLOBAL(__save_cpu_setup) mfcr r7 /* Get storage ptr */ - LOADADDR(r5,cpu_state_storage) + LOAD_REG_IMMEDIATE(r5,cpu_state_storage) /* We only deal with 970 for now */ mfspr r0,SPRN_PVR @@ -164,7 +164,7 @@ _GLOBAL(__restore_cpu_setup) /* Get storage ptr (FIXME when using anton reloc as we * are running with translation disabled here */ - LOADADDR(r5,cpu_state_storage) + LOAD_REG_IMMEDIATE(r5,cpu_state_storage) /* We only deal with 970 for now */ mfspr r0,SPRN_PVR diff --git a/arch/powerpc/kernel/cputable.c b/arch/powerpc/kernel/cputable.c index 43c74a6b07b..10696456a4c 100644 --- a/arch/powerpc/kernel/cputable.c +++ b/arch/powerpc/kernel/cputable.c @@ -55,7 +55,8 @@ extern void __setup_cpu_ppc970(unsigned long offset, struct cpu_spec* spec); #define COMMON_USER_POWER4 (COMMON_USER_PPC64 | PPC_FEATURE_POWER4) #define COMMON_USER_POWER5 (COMMON_USER_PPC64 | PPC_FEATURE_POWER5) #define COMMON_USER_POWER5_PLUS (COMMON_USER_PPC64 | PPC_FEATURE_POWER5_PLUS) - +#define COMMON_USER_BOOKE (PPC_FEATURE_32 | PPC_FEATURE_HAS_MMU | \ + PPC_FEATURE_BOOKE) /* We only set the spe features if the kernel was compiled with * spe support @@ -79,7 +80,8 @@ struct cpu_spec cpu_specs[] = { .num_pmcs = 8, .cpu_setup = __setup_cpu_power3, .oprofile_cpu_type = "ppc64/power3", - .oprofile_type = RS64, + .oprofile_type = PPC_OPROFILE_RS64, + .platform = "power3", }, { /* Power3+ */ .pvr_mask = 0xffff0000, @@ -92,7 +94,8 @@ struct cpu_spec cpu_specs[] = { .num_pmcs = 8, .cpu_setup = __setup_cpu_power3, .oprofile_cpu_type = "ppc64/power3", - .oprofile_type = RS64, + .oprofile_type = PPC_OPROFILE_RS64, + .platform = "power3", }, { /* Northstar */ .pvr_mask = 0xffff0000, @@ -105,7 +108,8 @@ struct cpu_spec cpu_specs[] = { .num_pmcs = 8, .cpu_setup = __setup_cpu_power3, .oprofile_cpu_type = "ppc64/rs64", - .oprofile_type = RS64, + .oprofile_type = PPC_OPROFILE_RS64, + .platform = "rs64", }, { /* Pulsar */ .pvr_mask = 0xffff0000, @@ -118,7 +122,8 @@ struct cpu_spec cpu_specs[] = { .num_pmcs = 8, .cpu_setup = __setup_cpu_power3, .oprofile_cpu_type = "ppc64/rs64", - .oprofile_type = RS64, + .oprofile_type = PPC_OPROFILE_RS64, + .platform = "rs64", }, { /* I-star */ .pvr_mask = 0xffff0000, @@ -131,7 +136,8 @@ struct cpu_spec cpu_specs[] = { .num_pmcs = 8, .cpu_setup = __setup_cpu_power3, .oprofile_cpu_type = "ppc64/rs64", - .oprofile_type = RS64, + .oprofile_type = PPC_OPROFILE_RS64, + .platform = "rs64", }, { /* S-star */ .pvr_mask = 0xffff0000, @@ -144,7 +150,8 @@ struct cpu_spec cpu_specs[] = { .num_pmcs = 8, .cpu_setup = __setup_cpu_power3, .oprofile_cpu_type = "ppc64/rs64", - .oprofile_type = RS64, + .oprofile_type = PPC_OPROFILE_RS64, + .platform = "rs64", }, { /* Power4 */ .pvr_mask = 0xffff0000, @@ -157,7 +164,8 @@ struct cpu_spec cpu_specs[] = { .num_pmcs = 8, .cpu_setup = __setup_cpu_power4, .oprofile_cpu_type = "ppc64/power4", - .oprofile_type = POWER4, + .oprofile_type = PPC_OPROFILE_POWER4, + .platform = "power4", }, { /* Power4+ */ .pvr_mask = 0xffff0000, @@ -170,7 +178,8 @@ struct cpu_spec cpu_specs[] = { .num_pmcs = 8, .cpu_setup = __setup_cpu_power4, .oprofile_cpu_type = "ppc64/power4", - .oprofile_type = POWER4, + .oprofile_type = PPC_OPROFILE_POWER4, + .platform = "power4", }, { /* PPC970 */ .pvr_mask = 0xffff0000, @@ -184,7 +193,8 @@ struct cpu_spec cpu_specs[] = { .num_pmcs = 8, .cpu_setup = __setup_cpu_ppc970, .oprofile_cpu_type = "ppc64/970", - .oprofile_type = POWER4, + .oprofile_type = PPC_OPROFILE_POWER4, + .platform = "ppc970", }, #endif /* CONFIG_PPC64 */ #if defined(CONFIG_PPC64) || defined(CONFIG_POWER4) @@ -204,7 +214,8 @@ struct cpu_spec cpu_specs[] = { .num_pmcs = 8, .cpu_setup = __setup_cpu_ppc970, .oprofile_cpu_type = "ppc64/970", - .oprofile_type = POWER4, + .oprofile_type = PPC_OPROFILE_POWER4, + .platform = "ppc970", }, #endif /* defined(CONFIG_PPC64) || defined(CONFIG_POWER4) */ #ifdef CONFIG_PPC64 @@ -219,7 +230,8 @@ struct cpu_spec cpu_specs[] = { .dcache_bsize = 128, .cpu_setup = __setup_cpu_ppc970, .oprofile_cpu_type = "ppc64/970", - .oprofile_type = POWER4, + .oprofile_type = PPC_OPROFILE_POWER4, + .platform = "ppc970", }, { /* Power5 GR */ .pvr_mask = 0xffff0000, @@ -232,7 +244,8 @@ struct cpu_spec cpu_specs[] = { .num_pmcs = 6, .cpu_setup = __setup_cpu_power4, .oprofile_cpu_type = "ppc64/power5", - .oprofile_type = POWER4, + .oprofile_type = PPC_OPROFILE_POWER4, + .platform = "power5", }, { /* Power5 GS */ .pvr_mask = 0xffff0000, @@ -245,7 +258,8 @@ struct cpu_spec cpu_specs[] = { .num_pmcs = 6, .cpu_setup = __setup_cpu_power4, .oprofile_cpu_type = "ppc64/power5+", - .oprofile_type = POWER4, + .oprofile_type = PPC_OPROFILE_POWER4, + .platform = "power5+", }, { /* Cell Broadband Engine */ .pvr_mask = 0xffff0000, @@ -257,6 +271,7 @@ struct cpu_spec cpu_specs[] = { .icache_bsize = 128, .dcache_bsize = 128, .cpu_setup = __setup_cpu_be, + .platform = "ppc-cell-be", }, { /* default match */ .pvr_mask = 0x00000000, @@ -268,6 +283,7 @@ struct cpu_spec cpu_specs[] = { .dcache_bsize = 128, .num_pmcs = 6, .cpu_setup = __setup_cpu_power4, + .platform = "power4", } #endif /* CONFIG_PPC64 */ #ifdef CONFIG_PPC32 @@ -281,6 +297,7 @@ struct cpu_spec cpu_specs[] = { PPC_FEATURE_UNIFIED_CACHE | PPC_FEATURE_NO_TB, .icache_bsize = 32, .dcache_bsize = 32, + .platform = "ppc601", }, { /* 603 */ .pvr_mask = 0xffff0000, @@ -290,7 +307,8 @@ struct cpu_spec cpu_specs[] = { .cpu_user_features = COMMON_USER, .icache_bsize = 32, .dcache_bsize = 32, - .cpu_setup = __setup_cpu_603 + .cpu_setup = __setup_cpu_603, + .platform = "ppc603", }, { /* 603e */ .pvr_mask = 0xffff0000, @@ -300,7 +318,8 @@ struct cpu_spec cpu_specs[] = { .cpu_user_features = COMMON_USER, .icache_bsize = 32, .dcache_bsize = 32, - .cpu_setup = __setup_cpu_603 + .cpu_setup = __setup_cpu_603, + .platform = "ppc603", }, { /* 603ev */ .pvr_mask = 0xffff0000, @@ -310,7 +329,8 @@ struct cpu_spec cpu_specs[] = { .cpu_user_features = COMMON_USER, .icache_bsize = 32, .dcache_bsize = 32, - .cpu_setup = __setup_cpu_603 + .cpu_setup = __setup_cpu_603, + .platform = "ppc603", }, { /* 604 */ .pvr_mask = 0xffff0000, @@ -321,7 +341,8 @@ struct cpu_spec cpu_specs[] = { .icache_bsize = 32, .dcache_bsize = 32, .num_pmcs = 2, - .cpu_setup = __setup_cpu_604 + .cpu_setup = __setup_cpu_604, + .platform = "ppc604", }, { /* 604e */ .pvr_mask = 0xfffff000, @@ -332,7 +353,8 @@ struct cpu_spec cpu_specs[] = { .icache_bsize = 32, .dcache_bsize = 32, .num_pmcs = 4, - .cpu_setup = __setup_cpu_604 + .cpu_setup = __setup_cpu_604, + .platform = "ppc604", }, { /* 604r */ .pvr_mask = 0xffff0000, @@ -343,7 +365,8 @@ struct cpu_spec cpu_specs[] = { .icache_bsize = 32, .dcache_bsize = 32, .num_pmcs = 4, - .cpu_setup = __setup_cpu_604 + .cpu_setup = __setup_cpu_604, + .platform = "ppc604", }, { /* 604ev */ .pvr_mask = 0xffff0000, @@ -354,7 +377,8 @@ struct cpu_spec cpu_specs[] = { .icache_bsize = 32, .dcache_bsize = 32, .num_pmcs = 4, - .cpu_setup = __setup_cpu_604 + .cpu_setup = __setup_cpu_604, + .platform = "ppc604", }, { /* 740/750 (0x4202, don't support TAU ?) */ .pvr_mask = 0xffffffff, @@ -365,7 +389,8 @@ struct cpu_spec cpu_specs[] = { .icache_bsize = 32, .dcache_bsize = 32, .num_pmcs = 4, - .cpu_setup = __setup_cpu_750 + .cpu_setup = __setup_cpu_750, + .platform = "ppc750", }, { /* 750CX (80100 and 8010x?) */ .pvr_mask = 0xfffffff0, @@ -376,7 +401,8 @@ struct cpu_spec cpu_specs[] = { .icache_bsize = 32, .dcache_bsize = 32, .num_pmcs = 4, - .cpu_setup = __setup_cpu_750cx + .cpu_setup = __setup_cpu_750cx, + .platform = "ppc750", }, { /* 750CX (82201 and 82202) */ .pvr_mask = 0xfffffff0, @@ -387,7 +413,8 @@ struct cpu_spec cpu_specs[] = { .icache_bsize = 32, .dcache_bsize = 32, .num_pmcs = 4, - .cpu_setup = __setup_cpu_750cx + .cpu_setup = __setup_cpu_750cx, + .platform = "ppc750", }, { /* 750CXe (82214) */ .pvr_mask = 0xfffffff0, @@ -398,7 +425,8 @@ struct cpu_spec cpu_specs[] = { .icache_bsize = 32, .dcache_bsize = 32, .num_pmcs = 4, - .cpu_setup = __setup_cpu_750cx + .cpu_setup = __setup_cpu_750cx, + .platform = "ppc750", }, { /* 750CXe "Gekko" (83214) */ .pvr_mask = 0xffffffff, @@ -409,7 +437,8 @@ struct cpu_spec cpu_specs[] = { .icache_bsize = 32, .dcache_bsize = 32, .num_pmcs = 4, - .cpu_setup = __setup_cpu_750cx + .cpu_setup = __setup_cpu_750cx, + .platform = "ppc750", }, { /* 745/755 */ .pvr_mask = 0xfffff000, @@ -420,7 +449,8 @@ struct cpu_spec cpu_specs[] = { .icache_bsize = 32, .dcache_bsize = 32, .num_pmcs = 4, - .cpu_setup = __setup_cpu_750 + .cpu_setup = __setup_cpu_750, + .platform = "ppc750", }, { /* 750FX rev 1.x */ .pvr_mask = 0xffffff00, @@ -431,7 +461,8 @@ struct cpu_spec cpu_specs[] = { .icache_bsize = 32, .dcache_bsize = 32, .num_pmcs = 4, - .cpu_setup = __setup_cpu_750 + .cpu_setup = __setup_cpu_750, + .platform = "ppc750", }, { /* 750FX rev 2.0 must disable HID0[DPM] */ .pvr_mask = 0xffffffff, @@ -442,7 +473,8 @@ struct cpu_spec cpu_specs[] = { .icache_bsize = 32, .dcache_bsize = 32, .num_pmcs = 4, - .cpu_setup = __setup_cpu_750 + .cpu_setup = __setup_cpu_750, + .platform = "ppc750", }, { /* 750FX (All revs except 2.0) */ .pvr_mask = 0xffff0000, @@ -453,7 +485,8 @@ struct cpu_spec cpu_specs[] = { .icache_bsize = 32, .dcache_bsize = 32, .num_pmcs = 4, - .cpu_setup = __setup_cpu_750fx + .cpu_setup = __setup_cpu_750fx, + .platform = "ppc750", }, { /* 750GX */ .pvr_mask = 0xffff0000, @@ -464,7 +497,8 @@ struct cpu_spec cpu_specs[] = { .icache_bsize = 32, .dcache_bsize = 32, .num_pmcs = 4, - .cpu_setup = __setup_cpu_750fx + .cpu_setup = __setup_cpu_750fx, + .platform = "ppc750", }, { /* 740/750 (L2CR bit need fixup for 740) */ .pvr_mask = 0xffff0000, @@ -475,7 +509,8 @@ struct cpu_spec cpu_specs[] = { .icache_bsize = 32, .dcache_bsize = 32, .num_pmcs = 4, - .cpu_setup = __setup_cpu_750 + .cpu_setup = __setup_cpu_750, + .platform = "ppc750", }, { /* 7400 rev 1.1 ? (no TAU) */ .pvr_mask = 0xffffffff, @@ -486,7 +521,8 @@ struct cpu_spec cpu_specs[] = { .icache_bsize = 32, .dcache_bsize = 32, .num_pmcs = 4, - .cpu_setup = __setup_cpu_7400 + .cpu_setup = __setup_cpu_7400, + .platform = "ppc7400", }, { /* 7400 */ .pvr_mask = 0xffff0000, @@ -497,7 +533,8 @@ struct cpu_spec cpu_specs[] = { .icache_bsize = 32, .dcache_bsize = 32, .num_pmcs = 4, - .cpu_setup = __setup_cpu_7400 + .cpu_setup = __setup_cpu_7400, + .platform = "ppc7400", }, { /* 7410 */ .pvr_mask = 0xffff0000, @@ -508,7 +545,8 @@ struct cpu_spec cpu_specs[] = { .icache_bsize = 32, .dcache_bsize = 32, .num_pmcs = 4, - .cpu_setup = __setup_cpu_7410 + .cpu_setup = __setup_cpu_7410, + .platform = "ppc7400", }, { /* 7450 2.0 - no doze/nap */ .pvr_mask = 0xffffffff, @@ -521,7 +559,8 @@ struct cpu_spec cpu_specs[] = { .num_pmcs = 6, .cpu_setup = __setup_cpu_745x, .oprofile_cpu_type = "ppc/7450", - .oprofile_type = G4, + .oprofile_type = PPC_OPROFILE_G4, + .platform = "ppc7450", }, { /* 7450 2.1 */ .pvr_mask = 0xffffffff, @@ -534,7 +573,8 @@ struct cpu_spec cpu_specs[] = { .num_pmcs = 6, .cpu_setup = __setup_cpu_745x, .oprofile_cpu_type = "ppc/7450", - .oprofile_type = G4, + .oprofile_type = PPC_OPROFILE_G4, + .platform = "ppc7450", }, { /* 7450 2.3 and newer */ .pvr_mask = 0xffff0000, @@ -547,7 +587,8 @@ struct cpu_spec cpu_specs[] = { .num_pmcs = 6, .cpu_setup = __setup_cpu_745x, .oprofile_cpu_type = "ppc/7450", - .oprofile_type = G4, + .oprofile_type = PPC_OPROFILE_G4, + .platform = "ppc7450", }, { /* 7455 rev 1.x */ .pvr_mask = 0xffffff00, @@ -560,7 +601,8 @@ struct cpu_spec cpu_specs[] = { .num_pmcs = 6, .cpu_setup = __setup_cpu_745x, .oprofile_cpu_type = "ppc/7450", - .oprofile_type = G4, + .oprofile_type = PPC_OPROFILE_G4, + .platform = "ppc7450", }, { /* 7455 rev 2.0 */ .pvr_mask = 0xffffffff, @@ -573,7 +615,8 @@ struct cpu_spec cpu_specs[] = { .num_pmcs = 6, .cpu_setup = __setup_cpu_745x, .oprofile_cpu_type = "ppc/7450", - .oprofile_type = G4, + .oprofile_type = PPC_OPROFILE_G4, + .platform = "ppc7450", }, { /* 7455 others */ .pvr_mask = 0xffff0000, @@ -586,7 +629,8 @@ struct cpu_spec cpu_specs[] = { .num_pmcs = 6, .cpu_setup = __setup_cpu_745x, .oprofile_cpu_type = "ppc/7450", - .oprofile_type = G4, + .oprofile_type = PPC_OPROFILE_G4, + .platform = "ppc7450", }, { /* 7447/7457 Rev 1.0 */ .pvr_mask = 0xffffffff, @@ -599,7 +643,8 @@ struct cpu_spec cpu_specs[] = { .num_pmcs = 6, .cpu_setup = __setup_cpu_745x, .oprofile_cpu_type = "ppc/7450", - .oprofile_type = G4, + .oprofile_type = PPC_OPROFILE_G4, + .platform = "ppc7450", }, { /* 7447/7457 Rev 1.1 */ .pvr_mask = 0xffffffff, @@ -612,7 +657,8 @@ struct cpu_spec cpu_specs[] = { .num_pmcs = 6, .cpu_setup = __setup_cpu_745x, .oprofile_cpu_type = "ppc/7450", - .oprofile_type = G4, + .oprofile_type = PPC_OPROFILE_G4, + .platform = "ppc7450", }, { /* 7447/7457 Rev 1.2 and later */ .pvr_mask = 0xffff0000, @@ -625,7 +671,8 @@ struct cpu_spec cpu_specs[] = { .num_pmcs = 6, .cpu_setup = __setup_cpu_745x, .oprofile_cpu_type = "ppc/7450", - .oprofile_type = G4, + .oprofile_type = PPC_OPROFILE_G4, + .platform = "ppc7450", }, { /* 7447A */ .pvr_mask = 0xffff0000, @@ -638,7 +685,8 @@ struct cpu_spec cpu_specs[] = { .num_pmcs = 6, .cpu_setup = __setup_cpu_745x, .oprofile_cpu_type = "ppc/7450", - .oprofile_type = G4, + .oprofile_type = PPC_OPROFILE_G4, + .platform = "ppc7450", }, { /* 7448 */ .pvr_mask = 0xffff0000, @@ -651,7 +699,8 @@ struct cpu_spec cpu_specs[] = { .num_pmcs = 6, .cpu_setup = __setup_cpu_745x, .oprofile_cpu_type = "ppc/7450", - .oprofile_type = G4, + .oprofile_type = PPC_OPROFILE_G4, + .platform = "ppc7450", }, { /* 82xx (8240, 8245, 8260 are all 603e cores) */ .pvr_mask = 0x7fff0000, @@ -661,7 +710,8 @@ struct cpu_spec cpu_specs[] = { .cpu_user_features = COMMON_USER, .icache_bsize = 32, .dcache_bsize = 32, - .cpu_setup = __setup_cpu_603 + .cpu_setup = __setup_cpu_603, + .platform = "ppc603", }, { /* All G2_LE (603e core, plus some) have the same pvr */ .pvr_mask = 0x7fff0000, @@ -671,7 +721,8 @@ struct cpu_spec cpu_specs[] = { .cpu_user_features = COMMON_USER, .icache_bsize = 32, .dcache_bsize = 32, - .cpu_setup = __setup_cpu_603 + .cpu_setup = __setup_cpu_603, + .platform = "ppc603", }, { /* e300 (a 603e core, plus some) on 83xx */ .pvr_mask = 0x7fff0000, @@ -681,7 +732,8 @@ struct cpu_spec cpu_specs[] = { .cpu_user_features = COMMON_USER, .icache_bsize = 32, .dcache_bsize = 32, - .cpu_setup = __setup_cpu_603 + .cpu_setup = __setup_cpu_603, + .platform = "ppc603", }, { /* default match, we assume split I/D cache & TB (non-601)... */ .pvr_mask = 0x00000000, @@ -691,6 +743,7 @@ struct cpu_spec cpu_specs[] = { .cpu_user_features = COMMON_USER, .icache_bsize = 32, .dcache_bsize = 32, + .platform = "ppc603", }, #endif /* CLASSIC_PPC */ #ifdef CONFIG_8xx @@ -704,6 +757,7 @@ struct cpu_spec cpu_specs[] = { .cpu_user_features = PPC_FEATURE_32 | PPC_FEATURE_HAS_MMU, .icache_bsize = 16, .dcache_bsize = 16, + .platform = "ppc823", }, #endif /* CONFIG_8xx */ #ifdef CONFIG_40x @@ -715,6 +769,7 @@ struct cpu_spec cpu_specs[] = { .cpu_user_features = PPC_FEATURE_32 | PPC_FEATURE_HAS_MMU, .icache_bsize = 16, .dcache_bsize = 16, + .platform = "ppc403", }, { /* 403GCX */ .pvr_mask = 0xffffff00, @@ -725,6 +780,7 @@ struct cpu_spec cpu_specs[] = { PPC_FEATURE_HAS_MMU | PPC_FEATURE_NO_TB, .icache_bsize = 16, .dcache_bsize = 16, + .platform = "ppc403", }, { /* 403G ?? */ .pvr_mask = 0xffff0000, @@ -734,6 +790,7 @@ struct cpu_spec cpu_specs[] = { .cpu_user_features = PPC_FEATURE_32 | PPC_FEATURE_HAS_MMU, .icache_bsize = 16, .dcache_bsize = 16, + .platform = "ppc403", }, { /* 405GP */ .pvr_mask = 0xffff0000, @@ -744,6 +801,7 @@ struct cpu_spec cpu_specs[] = { PPC_FEATURE_HAS_MMU | PPC_FEATURE_HAS_4xxMAC, .icache_bsize = 32, .dcache_bsize = 32, + .platform = "ppc405", }, { /* STB 03xxx */ .pvr_mask = 0xffff0000, @@ -754,6 +812,7 @@ struct cpu_spec cpu_specs[] = { PPC_FEATURE_HAS_MMU | PPC_FEATURE_HAS_4xxMAC, .icache_bsize = 32, .dcache_bsize = 32, + .platform = "ppc405", }, { /* STB 04xxx */ .pvr_mask = 0xffff0000, @@ -764,6 +823,7 @@ struct cpu_spec cpu_specs[] = { PPC_FEATURE_HAS_MMU | PPC_FEATURE_HAS_4xxMAC, .icache_bsize = 32, .dcache_bsize = 32, + .platform = "ppc405", }, { /* NP405L */ .pvr_mask = 0xffff0000, @@ -774,6 +834,7 @@ struct cpu_spec cpu_specs[] = { PPC_FEATURE_HAS_MMU | PPC_FEATURE_HAS_4xxMAC, .icache_bsize = 32, .dcache_bsize = 32, + .platform = "ppc405", }, { /* NP4GS3 */ .pvr_mask = 0xffff0000, @@ -784,6 +845,7 @@ struct cpu_spec cpu_specs[] = { PPC_FEATURE_HAS_MMU | PPC_FEATURE_HAS_4xxMAC, .icache_bsize = 32, .dcache_bsize = 32, + .platform = "ppc405", }, { /* NP405H */ .pvr_mask = 0xffff0000, @@ -794,6 +856,7 @@ struct cpu_spec cpu_specs[] = { PPC_FEATURE_HAS_MMU | PPC_FEATURE_HAS_4xxMAC, .icache_bsize = 32, .dcache_bsize = 32, + .platform = "ppc405", }, { /* 405GPr */ .pvr_mask = 0xffff0000, @@ -804,6 +867,7 @@ struct cpu_spec cpu_specs[] = { PPC_FEATURE_HAS_MMU | PPC_FEATURE_HAS_4xxMAC, .icache_bsize = 32, .dcache_bsize = 32, + .platform = "ppc405", }, { /* STBx25xx */ .pvr_mask = 0xffff0000, @@ -814,6 +878,7 @@ struct cpu_spec cpu_specs[] = { PPC_FEATURE_HAS_MMU | PPC_FEATURE_HAS_4xxMAC, .icache_bsize = 32, .dcache_bsize = 32, + .platform = "ppc405", }, { /* 405LP */ .pvr_mask = 0xffff0000, @@ -823,6 +888,7 @@ struct cpu_spec cpu_specs[] = { .cpu_user_features = PPC_FEATURE_32 | PPC_FEATURE_HAS_MMU, .icache_bsize = 32, .dcache_bsize = 32, + .platform = "ppc405", }, { /* Xilinx Virtex-II Pro */ .pvr_mask = 0xffff0000, @@ -833,6 +899,7 @@ struct cpu_spec cpu_specs[] = { PPC_FEATURE_HAS_MMU | PPC_FEATURE_HAS_4xxMAC, .icache_bsize = 32, .dcache_bsize = 32, + .platform = "ppc405", }, { /* 405EP */ .pvr_mask = 0xffff0000, @@ -843,6 +910,7 @@ struct cpu_spec cpu_specs[] = { PPC_FEATURE_HAS_MMU | PPC_FEATURE_HAS_4xxMAC, .icache_bsize = 32, .dcache_bsize = 32, + .platform = "ppc405", }, #endif /* CONFIG_40x */ @@ -852,81 +920,90 @@ struct cpu_spec cpu_specs[] = { .pvr_value = 0x40000850, .cpu_name = "440EP Rev. A", .cpu_features = CPU_FTRS_44X, - .cpu_user_features = COMMON_USER, /* 440EP has an FPU */ + .cpu_user_features = COMMON_USER_BOOKE | PPC_FEATURE_HAS_FPU, .icache_bsize = 32, .dcache_bsize = 32, + .platform = "ppc440", }, { .pvr_mask = 0xf0000fff, .pvr_value = 0x400008d3, .cpu_name = "440EP Rev. B", .cpu_features = CPU_FTRS_44X, - .cpu_user_features = COMMON_USER, /* 440EP has an FPU */ + .cpu_user_features = COMMON_USER_BOOKE | PPC_FEATURE_HAS_FPU, .icache_bsize = 32, .dcache_bsize = 32, + .platform = "ppc440", }, { /* 440GP Rev. B */ .pvr_mask = 0xf0000fff, .pvr_value = 0x40000440, .cpu_name = "440GP Rev. B", .cpu_features = CPU_FTRS_44X, - .cpu_user_features = PPC_FEATURE_32 | PPC_FEATURE_HAS_MMU, + .cpu_user_features = COMMON_USER_BOOKE, .icache_bsize = 32, .dcache_bsize = 32, + .platform = "ppc440gp", }, { /* 440GP Rev. C */ .pvr_mask = 0xf0000fff, .pvr_value = 0x40000481, .cpu_name = "440GP Rev. C", .cpu_features = CPU_FTRS_44X, - .cpu_user_features = PPC_FEATURE_32 | PPC_FEATURE_HAS_MMU, + .cpu_user_features = COMMON_USER_BOOKE, .icache_bsize = 32, .dcache_bsize = 32, + .platform = "ppc440gp", }, { /* 440GX Rev. A */ .pvr_mask = 0xf0000fff, .pvr_value = 0x50000850, .cpu_name = "440GX Rev. A", .cpu_features = CPU_FTRS_44X, - .cpu_user_features = PPC_FEATURE_32 | PPC_FEATURE_HAS_MMU, + .cpu_user_features = COMMON_USER_BOOKE, .icache_bsize = 32, .dcache_bsize = 32, + .platform = "ppc440", }, { /* 440GX Rev. B */ .pvr_mask = 0xf0000fff, .pvr_value = 0x50000851, .cpu_name = "440GX Rev. B", .cpu_features = CPU_FTRS_44X, - .cpu_user_features = PPC_FEATURE_32 | PPC_FEATURE_HAS_MMU, + .cpu_user_features = COMMON_USER_BOOKE, .icache_bsize = 32, .dcache_bsize = 32, + .platform = "ppc440", }, { /* 440GX Rev. C */ .pvr_mask = 0xf0000fff, .pvr_value = 0x50000892, .cpu_name = "440GX Rev. C", .cpu_features = CPU_FTRS_44X, - .cpu_user_features = PPC_FEATURE_32 | PPC_FEATURE_HAS_MMU, + .cpu_user_features = COMMON_USER_BOOKE, .icache_bsize = 32, .dcache_bsize = 32, + .platform = "ppc440", }, { /* 440GX Rev. F */ .pvr_mask = 0xf0000fff, .pvr_value = 0x50000894, .cpu_name = "440GX Rev. F", .cpu_features = CPU_FTRS_44X, - .cpu_user_features = PPC_FEATURE_32 | PPC_FEATURE_HAS_MMU, + .cpu_user_features = COMMON_USER_BOOKE, .icache_bsize = 32, .dcache_bsize = 32, + .platform = "ppc440", }, { /* 440SP Rev. A */ .pvr_mask = 0xff000fff, .pvr_value = 0x53000891, .cpu_name = "440SP Rev. A", .cpu_features = CPU_FTRS_44X, - .cpu_user_features = PPC_FEATURE_32 | PPC_FEATURE_HAS_MMU, + .cpu_user_features = COMMON_USER_BOOKE, .icache_bsize = 32, .dcache_bsize = 32, + .platform = "ppc440", }, { /* 440SPe Rev. A */ .pvr_mask = 0xff000fff, @@ -934,9 +1011,10 @@ struct cpu_spec cpu_specs[] = { .cpu_name = "440SPe Rev. A", .cpu_features = CPU_FTR_SPLIT_ID_CACHE | CPU_FTR_USE_TB, - .cpu_user_features = PPC_FEATURE_32 | PPC_FEATURE_HAS_MMU, + .cpu_user_features = COMMON_USER_BOOKE, .icache_bsize = 32, .dcache_bsize = 32, + .platform = "ppc440", }, #endif /* CONFIG_44x */ #ifdef CONFIG_FSL_BOOKE @@ -946,10 +1024,11 @@ struct cpu_spec cpu_specs[] = { .cpu_name = "e200z5", /* xxx - galak: add CPU_FTR_MAYBE_CAN_DOZE */ .cpu_features = CPU_FTRS_E200, - .cpu_user_features = PPC_FEATURE_32 | - PPC_FEATURE_HAS_MMU | PPC_FEATURE_HAS_EFP_SINGLE | + .cpu_user_features = COMMON_USER_BOOKE | + PPC_FEATURE_HAS_EFP_SINGLE | PPC_FEATURE_UNIFIED_CACHE, .dcache_bsize = 32, + .platform = "ppc5554", }, { /* e200z6 */ .pvr_mask = 0xfff00000, @@ -957,11 +1036,12 @@ struct cpu_spec cpu_specs[] = { .cpu_name = "e200z6", /* xxx - galak: add CPU_FTR_MAYBE_CAN_DOZE */ .cpu_features = CPU_FTRS_E200, - .cpu_user_features = PPC_FEATURE_32 | - PPC_FEATURE_HAS_MMU | PPC_FEATURE_SPE_COMP | + .cpu_user_features = COMMON_USER_BOOKE | + PPC_FEATURE_SPE_COMP | PPC_FEATURE_HAS_EFP_SINGLE | PPC_FEATURE_UNIFIED_CACHE, .dcache_bsize = 32, + .platform = "ppc5554", }, { /* e500 */ .pvr_mask = 0xffff0000, @@ -969,14 +1049,15 @@ struct cpu_spec cpu_specs[] = { .cpu_name = "e500", /* xxx - galak: add CPU_FTR_MAYBE_CAN_DOZE */ .cpu_features = CPU_FTRS_E500, - .cpu_user_features = PPC_FEATURE_32 | - PPC_FEATURE_HAS_MMU | PPC_FEATURE_SPE_COMP | + .cpu_user_features = COMMON_USER_BOOKE | + PPC_FEATURE_SPE_COMP | PPC_FEATURE_HAS_EFP_SINGLE, .icache_bsize = 32, .dcache_bsize = 32, .num_pmcs = 4, .oprofile_cpu_type = "ppc/e500", - .oprofile_type = BOOKE, + .oprofile_type = PPC_OPROFILE_BOOKE, + .platform = "ppc8540", }, { /* e500v2 */ .pvr_mask = 0xffff0000, @@ -984,14 +1065,16 @@ struct cpu_spec cpu_specs[] = { .cpu_name = "e500v2", /* xxx - galak: add CPU_FTR_MAYBE_CAN_DOZE */ .cpu_features = CPU_FTRS_E500_2, - .cpu_user_features = PPC_FEATURE_32 | - PPC_FEATURE_HAS_MMU | PPC_FEATURE_SPE_COMP | - PPC_FEATURE_HAS_EFP_SINGLE | PPC_FEATURE_HAS_EFP_DOUBLE, + .cpu_user_features = COMMON_USER_BOOKE | + PPC_FEATURE_SPE_COMP | + PPC_FEATURE_HAS_EFP_SINGLE | + PPC_FEATURE_HAS_EFP_DOUBLE, .icache_bsize = 32, .dcache_bsize = 32, .num_pmcs = 4, .oprofile_cpu_type = "ppc/e500", - .oprofile_type = BOOKE, + .oprofile_type = PPC_OPROFILE_BOOKE, + .platform = "ppc8548", }, #endif #if !CLASSIC_PPC @@ -1003,6 +1086,7 @@ struct cpu_spec cpu_specs[] = { .cpu_user_features = PPC_FEATURE_32, .icache_bsize = 32, .dcache_bsize = 32, + .platform = "powerpc", } #endif /* !CLASSIC_PPC */ #endif /* CONFIG_PPC32 */ diff --git a/arch/powerpc/kernel/entry_32.S b/arch/powerpc/kernel/entry_32.S index 036b71d2adf..d8da2a35c0a 100644 --- a/arch/powerpc/kernel/entry_32.S +++ b/arch/powerpc/kernel/entry_32.S @@ -988,7 +988,7 @@ _GLOBAL(enter_rtas) stwu r1,-INT_FRAME_SIZE(r1) mflr r0 stw r0,INT_FRAME_SIZE+4(r1) - LOADADDR(r4, rtas) + LOAD_REG_ADDR(r4, rtas) lis r6,1f@ha /* physical return address for rtas */ addi r6,r6,1f@l tophys(r6,r6) diff --git a/arch/powerpc/kernel/entry_64.S b/arch/powerpc/kernel/entry_64.S index aacebb33e98..54203631886 100644 --- a/arch/powerpc/kernel/entry_64.S +++ b/arch/powerpc/kernel/entry_64.S @@ -511,7 +511,8 @@ restore: cmpdi 0,r5,0 beq 4f /* Check for pending interrupts (iSeries) */ - ld r3,PACALPPACA+LPPACAANYINT(r13) + ld r3,PACALPPACAPTR(r13) + ld r3,LPPACAANYINT(r3) cmpdi r3,0 beq+ 4f /* skip do_IRQ if no interrupts */ @@ -689,9 +690,8 @@ _GLOBAL(enter_rtas) std r6,PACASAVEDMSR(r13) /* Setup our real return addr */ - SET_REG_TO_LABEL(r4,.rtas_return_loc) - SET_REG_TO_CONST(r9,PAGE_OFFSET) - sub r4,r4,r9 + LOAD_REG_ADDR(r4,.rtas_return_loc) + clrldi r4,r4,2 /* convert to realmode address */ mtlr r4 li r0,0 @@ -706,7 +706,7 @@ _GLOBAL(enter_rtas) sync /* disable interrupts so SRR0/1 */ mtmsrd r0 /* don't get trashed */ - SET_REG_TO_LABEL(r4,rtas) + LOAD_REG_ADDR(r4, rtas) ld r5,RTASENTRY(r4) /* get the rtas->entry value */ ld r4,RTASBASE(r4) /* get the rtas->base value */ @@ -718,8 +718,7 @@ _GLOBAL(enter_rtas) _STATIC(rtas_return_loc) /* relocation is off at this point */ mfspr r4,SPRN_SPRG3 /* Get PACA */ - SET_REG_TO_CONST(r5, PAGE_OFFSET) - sub r4,r4,r5 /* RELOC the PACA base pointer */ + clrldi r4,r4,2 /* convert to realmode address */ mfmsr r6 li r0,MSR_RI @@ -728,7 +727,7 @@ _STATIC(rtas_return_loc) mtmsrd r6 ld r1,PACAR1(r4) /* Restore our SP */ - LOADADDR(r3,.rtas_restore_regs) + LOAD_REG_IMMEDIATE(r3,.rtas_restore_regs) ld r4,PACASAVEDMSR(r4) /* Restore our MSR */ mtspr SPRN_SRR0,r3 diff --git a/arch/powerpc/kernel/fpu.S b/arch/powerpc/kernel/fpu.S index b780b42c95f..e4362dfa37f 100644 --- a/arch/powerpc/kernel/fpu.S +++ b/arch/powerpc/kernel/fpu.S @@ -39,9 +39,9 @@ _GLOBAL(load_up_fpu) * to another. Instead we call giveup_fpu in switch_to. */ #ifndef CONFIG_SMP - LOADBASE(r3, last_task_used_math) + LOAD_REG_ADDRBASE(r3, last_task_used_math) toreal(r3) - PPC_LL r4,OFF(last_task_used_math)(r3) + PPC_LL r4,ADDROFF(last_task_used_math)(r3) PPC_LCMPI 0,r4,0 beq 1f toreal(r4) @@ -77,7 +77,7 @@ _GLOBAL(load_up_fpu) #ifndef CONFIG_SMP subi r4,r5,THREAD fromreal(r4) - PPC_STL r4,OFF(last_task_used_math)(r3) + PPC_STL r4,ADDROFF(last_task_used_math)(r3) #endif /* CONFIG_SMP */ /* restore registers and return */ /* we haven't used ctr or xer or lr */ @@ -113,8 +113,8 @@ _GLOBAL(giveup_fpu) 1: #ifndef CONFIG_SMP li r5,0 - LOADBASE(r4,last_task_used_math) - PPC_STL r5,OFF(last_task_used_math)(r4) + LOAD_REG_ADDRBASE(r4,last_task_used_math) + PPC_STL r5,ADDROFF(last_task_used_math)(r4) #endif /* CONFIG_SMP */ blr diff --git a/arch/powerpc/kernel/head_64.S b/arch/powerpc/kernel/head_64.S index 1c066d12537..30826846634 100644 --- a/arch/powerpc/kernel/head_64.S +++ b/arch/powerpc/kernel/head_64.S @@ -154,12 +154,12 @@ _GLOBAL(__secondary_hold) bne 100b #ifdef CONFIG_HMT - LOADADDR(r4, .hmt_init) + SET_REG_IMMEDIATE(r4, .hmt_init) mtctr r4 bctr #else #ifdef CONFIG_SMP - LOADADDR(r4, .pSeries_secondary_smp_init) + LOAD_REG_IMMEDIATE(r4, .pSeries_secondary_smp_init) mtctr r4 mr r3,r24 bctr @@ -205,9 +205,10 @@ exception_marker: #define EX_LR 72 /* - * We're short on space and time in the exception prolog, so we can't use - * the normal LOADADDR macro. Normally we just need the low halfword of the - * address, but for Kdump we need the whole low word. + * We're short on space and time in the exception prolog, so we can't + * use the normal SET_REG_IMMEDIATE macro. Normally we just need the + * low halfword of the address, but for Kdump we need the whole low + * word. */ #ifdef CONFIG_CRASH_DUMP #define LOAD_HANDLER(reg, label) \ @@ -254,8 +255,9 @@ exception_marker: #define EXCEPTION_PROLOG_ISERIES_2 \ mfmsr r10; \ - ld r11,PACALPPACA+LPPACASRR0(r13); \ - ld r12,PACALPPACA+LPPACASRR1(r13); \ + ld r12,PACALPPACAPTR(r13); \ + ld r11,LPPACASRR0(r12); \ + ld r12,LPPACASRR1(r12); \ ori r10,r10,MSR_RI; \ mtmsrd r10,1 @@ -634,7 +636,8 @@ data_access_slb_iSeries: std r12,PACA_EXSLB+EX_R12(r13) mfspr r10,SPRN_SPRG1 std r10,PACA_EXSLB+EX_R13(r13) - ld r12,PACALPPACA+LPPACASRR1(r13); + ld r12,PACALPPACAPTR(r13) + ld r12,LPPACASRR1(r12) b .slb_miss_realmode STD_EXCEPTION_ISERIES(0x400, instruction_access, PACA_EXGEN) @@ -644,7 +647,8 @@ instruction_access_slb_iSeries: mtspr SPRN_SPRG1,r13 /* save r13 */ mfspr r13,SPRN_SPRG3 /* get paca address into r13 */ std r3,PACA_EXSLB+EX_R3(r13) - ld r3,PACALPPACA+LPPACASRR0(r13) /* get SRR0 value */ + ld r3,PACALPPACAPTR(r13) + ld r3,LPPACASRR0(r3) /* get SRR0 value */ std r9,PACA_EXSLB+EX_R9(r13) mfcr r9 #ifdef __DISABLED__ @@ -656,7 +660,8 @@ instruction_access_slb_iSeries: std r12,PACA_EXSLB+EX_R12(r13) mfspr r10,SPRN_SPRG1 std r10,PACA_EXSLB+EX_R13(r13) - ld r12,PACALPPACA+LPPACASRR1(r13); + ld r12,PACALPPACAPTR(r13) + ld r12,LPPACASRR1(r12) b .slb_miss_realmode #ifdef __DISABLED__ @@ -713,7 +718,7 @@ system_reset_iSeries: lbz r23,PACAPROCSTART(r13) /* Test if this processor * should start */ sync - LOADADDR(r3,current_set) + LOAD_REG_IMMEDIATE(r3,current_set) sldi r28,r24,3 /* get current_set[cpu#] */ ldx r3,r3,r28 addi r1,r3,THREAD_SIZE @@ -745,17 +750,19 @@ iSeries_secondary_smp_loop: .globl decrementer_iSeries_masked decrementer_iSeries_masked: li r11,1 - stb r11,PACALPPACA+LPPACADECRINT(r13) - LOADBASE(r12,tb_ticks_per_jiffy) - lwz r12,OFF(tb_ticks_per_jiffy)(r12) + ld r12,PACALPPACAPTR(r13) + stb r11,LPPACADECRINT(r12) + LOAD_REG_ADDRBASE(r12,tb_ticks_per_jiffy) + lwz r12,ADDROFF(tb_ticks_per_jiffy)(r12) mtspr SPRN_DEC,r12 /* fall through */ .globl hardware_interrupt_iSeries_masked hardware_interrupt_iSeries_masked: mtcrf 0x80,r9 /* Restore regs */ - ld r11,PACALPPACA+LPPACASRR0(r13) - ld r12,PACALPPACA+LPPACASRR1(r13) + ld r12,PACALPPACAPTR(r13) + ld r11,LPPACASRR0(r12) + ld r12,LPPACASRR1(r12) mtspr SPRN_SRR0,r11 mtspr SPRN_SRR1,r12 ld r9,PACA_EXGEN+EX_R9(r13) @@ -994,7 +1001,8 @@ _GLOBAL(slb_miss_realmode) ld r3,PACA_EXSLB+EX_R3(r13) lwz r9,PACA_EXSLB+EX_CCR(r13) /* get saved CR */ #ifdef CONFIG_PPC_ISERIES - ld r11,PACALPPACA+LPPACASRR0(r13) /* get SRR0 value */ + ld r11,PACALPPACAPTR(r13) + ld r11,LPPACASRR0(r11) /* get SRR0 value */ #endif /* CONFIG_PPC_ISERIES */ mtlr r10 @@ -1412,7 +1420,7 @@ _GLOBAL(pSeries_secondary_smp_init) * physical cpu id in r24, we need to search the pacas to find * which logical id maps to our physical one. */ - LOADADDR(r13, paca) /* Get base vaddr of paca array */ + LOAD_REG_IMMEDIATE(r13, paca) /* Get base vaddr of paca array */ li r5,0 /* logical cpu id */ 1: lhz r6,PACAHWCPUID(r13) /* Load HW procid from paca */ cmpw r6,r24 /* Compare to our id */ @@ -1446,8 +1454,8 @@ _GLOBAL(pSeries_secondary_smp_init) #ifdef CONFIG_PPC_ISERIES _STATIC(__start_initialization_iSeries) /* Clear out the BSS */ - LOADADDR(r11,__bss_stop) - LOADADDR(r8,__bss_start) + LOAD_REG_IMMEDIATE(r11,__bss_stop) + LOAD_REG_IMMEDIATE(r8,__bss_start) sub r11,r11,r8 /* bss size */ addi r11,r11,7 /* round up to an even double word */ rldicl. r11,r11,61,3 /* shift right by 3 */ @@ -1458,17 +1466,17 @@ _STATIC(__start_initialization_iSeries) 3: stdu r0,8(r8) bdnz 3b 4: - LOADADDR(r1,init_thread_union) + LOAD_REG_IMMEDIATE(r1,init_thread_union) addi r1,r1,THREAD_SIZE li r0,0 stdu r0,-STACK_FRAME_OVERHEAD(r1) - LOADADDR(r3,cpu_specs) - LOADADDR(r4,cur_cpu_spec) + LOAD_REG_IMMEDIATE(r3,cpu_specs) + LOAD_REG_IMMEDIATE(r4,cur_cpu_spec) li r5,0 bl .identify_cpu - LOADADDR(r2,__toc_start) + LOAD_REG_IMMEDIATE(r2,__toc_start) addi r2,r2,0x4000 addi r2,r2,0x4000 @@ -1528,7 +1536,7 @@ _GLOBAL(__start_initialization_multiplatform) li r24,0 /* Switch off MMU if not already */ - LOADADDR(r4, .__after_prom_start - KERNELBASE) + LOAD_REG_IMMEDIATE(r4, .__after_prom_start - KERNELBASE) add r4,r4,r30 bl .__mmu_off b .__after_prom_start @@ -1548,7 +1556,7 @@ _STATIC(__boot_from_prom) /* put a relocation offset into r3 */ bl .reloc_offset - LOADADDR(r2,__toc_start) + LOAD_REG_IMMEDIATE(r2,__toc_start) addi r2,r2,0x4000 addi r2,r2,0x4000 @@ -1588,9 +1596,9 @@ _STATIC(__after_prom_start) */ bl .reloc_offset mr r26,r3 - SET_REG_TO_CONST(r27,KERNELBASE) + LOAD_REG_IMMEDIATE(r27, KERNELBASE) - LOADADDR(r3, PHYSICAL_START) /* target addr */ + LOAD_REG_IMMEDIATE(r3, PHYSICAL_START) /* target addr */ // XXX FIXME: Use phys returned by OF (r30) add r4,r27,r26 /* source addr */ @@ -1598,7 +1606,7 @@ _STATIC(__after_prom_start) /* i.e. where we are running */ /* the source addr */ - LOADADDR(r5,copy_to_here) /* # bytes of memory to copy */ + LOAD_REG_IMMEDIATE(r5,copy_to_here) /* # bytes of memory to copy */ sub r5,r5,r27 li r6,0x100 /* Start offset, the first 0x100 */ @@ -1608,11 +1616,11 @@ _STATIC(__after_prom_start) /* this includes the code being */ /* executed here. */ - LOADADDR(r0, 4f) /* Jump to the copy of this code */ + LOAD_REG_IMMEDIATE(r0, 4f) /* Jump to the copy of this code */ mtctr r0 /* that we just made/relocated */ bctr -4: LOADADDR(r5,klimit) +4: LOAD_REG_IMMEDIATE(r5,klimit) add r5,r5,r26 ld r5,0(r5) /* get the value of klimit */ sub r5,r5,r27 @@ -1694,7 +1702,7 @@ _GLOBAL(pmac_secondary_start) mtmsrd r3 /* RI on */ /* Set up a paca value for this processor. */ - LOADADDR(r4, paca) /* Get base vaddr of paca array */ + LOAD_REG_IMMEDIATE(r4, paca) /* Get base vaddr of paca array */ mulli r13,r24,PACA_SIZE /* Calculate vaddr of right paca */ add r13,r13,r4 /* for this processor. */ mtspr SPRN_SPRG3,r13 /* Save vaddr of paca in SPRG3 */ @@ -1731,7 +1739,7 @@ _GLOBAL(__secondary_start) bl .early_setup_secondary /* Initialize the kernel stack. Just a repeat for iSeries. */ - LOADADDR(r3,current_set) + LOAD_REG_ADDR(r3, current_set) sldi r28,r24,3 /* get current_set[cpu#] */ ldx r1,r3,r28 addi r1,r1,THREAD_SIZE-STACK_FRAME_OVERHEAD @@ -1742,8 +1750,8 @@ _GLOBAL(__secondary_start) mtlr r7 /* enable MMU and jump to start_secondary */ - LOADADDR(r3,.start_secondary_prolog) - SET_REG_TO_CONST(r4, MSR_KERNEL) + LOAD_REG_ADDR(r3, .start_secondary_prolog) + LOAD_REG_IMMEDIATE(r4, MSR_KERNEL) #ifdef DO_SOFT_DISABLE ori r4,r4,MSR_EE #endif @@ -1792,8 +1800,8 @@ _STATIC(start_here_multiplatform) * be detached from the kernel completely. Besides, we need * to clear it now for kexec-style entry. */ - LOADADDR(r11,__bss_stop) - LOADADDR(r8,__bss_start) + LOAD_REG_IMMEDIATE(r11,__bss_stop) + LOAD_REG_IMMEDIATE(r8,__bss_start) sub r11,r11,r8 /* bss size */ addi r11,r11,7 /* round up to an even double word */ rldicl. r11,r11,61,3 /* shift right by 3 */ @@ -1831,7 +1839,7 @@ _STATIC(start_here_multiplatform) /* up the htab. This is done because we have relocated the */ /* kernel but are still running in real mode. */ - LOADADDR(r3,init_thread_union) + LOAD_REG_IMMEDIATE(r3,init_thread_union) add r3,r3,r26 /* set up a stack pointer (physical address) */ @@ -1840,14 +1848,14 @@ _STATIC(start_here_multiplatform) stdu r0,-STACK_FRAME_OVERHEAD(r1) /* set up the TOC (physical address) */ - LOADADDR(r2,__toc_start) + LOAD_REG_IMMEDIATE(r2,__toc_start) addi r2,r2,0x4000 addi r2,r2,0x4000 add r2,r2,r26 - LOADADDR(r3,cpu_specs) + LOAD_REG_IMMEDIATE(r3, cpu_specs) add r3,r3,r26 - LOADADDR(r4,cur_cpu_spec) + LOAD_REG_IMMEDIATE(r4,cur_cpu_spec) add r4,r4,r26 mr r5,r26 bl .identify_cpu @@ -1863,11 +1871,11 @@ _STATIC(start_here_multiplatform) * nowhere it can be initialized differently before we reach this * code */ - LOADADDR(r27, boot_cpuid) + LOAD_REG_IMMEDIATE(r27, boot_cpuid) add r27,r27,r26 lwz r27,0(r27) - LOADADDR(r24, paca) /* Get base vaddr of paca array */ + LOAD_REG_IMMEDIATE(r24, paca) /* Get base vaddr of paca array */ mulli r13,r27,PACA_SIZE /* Calculate vaddr of right paca */ add r13,r13,r24 /* for this processor. */ add r13,r13,r26 /* convert to physical addr */ @@ -1880,8 +1888,8 @@ _STATIC(start_here_multiplatform) mr r3,r31 bl .early_setup - LOADADDR(r3,.start_here_common) - SET_REG_TO_CONST(r4, MSR_KERNEL) + LOAD_REG_IMMEDIATE(r3, .start_here_common) + LOAD_REG_IMMEDIATE(r4, MSR_KERNEL) mtspr SPRN_SRR0,r3 mtspr SPRN_SRR1,r4 rfid @@ -1895,7 +1903,7 @@ _STATIC(start_here_common) /* The following code sets up the SP and TOC now that we are */ /* running with translation enabled. */ - LOADADDR(r3,init_thread_union) + LOAD_REG_IMMEDIATE(r3,init_thread_union) /* set up the stack */ addi r1,r3,THREAD_SIZE @@ -1908,16 +1916,16 @@ _STATIC(start_here_common) li r3,0 bl .do_cpu_ftr_fixups - LOADADDR(r26, boot_cpuid) + LOAD_REG_IMMEDIATE(r26, boot_cpuid) lwz r26,0(r26) - LOADADDR(r24, paca) /* Get base vaddr of paca array */ + LOAD_REG_IMMEDIATE(r24, paca) /* Get base vaddr of paca array */ mulli r13,r26,PACA_SIZE /* Calculate vaddr of right paca */ add r13,r13,r24 /* for this processor. */ mtspr SPRN_SPRG3,r13 /* ptr to current */ - LOADADDR(r4,init_task) + LOAD_REG_IMMEDIATE(r4, init_task) std r4,PACACURRENT(r13) /* Load the TOC */ @@ -1940,7 +1948,7 @@ _STATIC(start_here_common) _GLOBAL(hmt_init) #ifdef CONFIG_HMT - LOADADDR(r5, hmt_thread_data) + LOAD_REG_IMMEDIATE(r5, hmt_thread_data) mfspr r7,SPRN_PVR srwi r7,r7,16 cmpwi r7,0x34 /* Pulsar */ @@ -1961,7 +1969,7 @@ _GLOBAL(hmt_init) b 101f __hmt_secondary_hold: - LOADADDR(r5, hmt_thread_data) + LOAD_REG_IMMEDIATE(r5, hmt_thread_data) clrldi r5,r5,4 li r7,0 mfspr r6,SPRN_PIR @@ -1989,7 +1997,7 @@ __hmt_secondary_hold: #ifdef CONFIG_HMT _GLOBAL(hmt_start_secondary) - LOADADDR(r4,__hmt_secondary_hold) + LOAD_REG_IMMEDIATE(r4,__hmt_secondary_hold) clrldi r4,r4,4 mtspr SPRN_NIADORM, r4 mfspr r4, SPRN_MSRDORM diff --git a/arch/powerpc/kernel/idle_power4.S b/arch/powerpc/kernel/idle_power4.S index 1494e2f177f..c16b4afab58 100644 --- a/arch/powerpc/kernel/idle_power4.S +++ b/arch/powerpc/kernel/idle_power4.S @@ -38,14 +38,14 @@ END_FTR_SECTION_IFCLR(CPU_FTR_CAN_NAP) /* We must dynamically check for the NAP feature as it * can be cleared by CPU init after the fixups are done */ - LOADBASE(r3,cur_cpu_spec) - ld r4,OFF(cur_cpu_spec)(r3) + LOAD_REG_ADDRBASE(r3,cur_cpu_spec) + ld r4,ADDROFF(cur_cpu_spec)(r3) ld r4,CPU_SPEC_FEATURES(r4) andi. r0,r4,CPU_FTR_CAN_NAP beqlr /* Now check if user or arch enabled NAP mode */ - LOADBASE(r3,powersave_nap) - lwz r4,OFF(powersave_nap)(r3) + LOAD_REG_ADDRBASE(r3,powersave_nap) + lwz r4,ADDROFF(powersave_nap)(r3) cmpwi 0,r4,0 beqlr diff --git a/arch/powerpc/kernel/irq.c b/arch/powerpc/kernel/irq.c index 5651032d870..d1fffce86df 100644 --- a/arch/powerpc/kernel/irq.c +++ b/arch/powerpc/kernel/irq.c @@ -238,14 +238,10 @@ void do_IRQ(struct pt_regs *regs) irq_exit(); #ifdef CONFIG_PPC_ISERIES - { - struct paca_struct *lpaca = get_paca(); - - if (lpaca->lppaca.int_dword.fields.decr_int) { - lpaca->lppaca.int_dword.fields.decr_int = 0; - /* Signal a fake decrementer interrupt */ - timer_interrupt(regs); - } + if (get_lppaca()->int_dword.fields.decr_int) { + get_lppaca()->int_dword.fields.decr_int = 0; + /* Signal a fake decrementer interrupt */ + timer_interrupt(regs); } #endif } diff --git a/arch/powerpc/kernel/lparcfg.c b/arch/powerpc/kernel/lparcfg.c index 9dda16ccde7..1ae96a8ed7e 100644 --- a/arch/powerpc/kernel/lparcfg.c +++ b/arch/powerpc/kernel/lparcfg.c @@ -55,15 +55,13 @@ static unsigned long get_purr(void) { unsigned long sum_purr = 0; int cpu; - struct paca_struct *lpaca; for_each_cpu(cpu) { - lpaca = paca + cpu; - sum_purr += lpaca->lppaca.emulated_time_base; + sum_purr += lppaca[cpu].emulated_time_base; #ifdef PURR_DEBUG printk(KERN_INFO "get_purr for cpu (%d) has value (%ld) \n", - cpu, lpaca->lppaca.emulated_time_base); + cpu, lppaca[cpu].emulated_time_base); #endif } return sum_purr; @@ -79,12 +77,11 @@ static int lparcfg_data(struct seq_file *m, void *v) unsigned long pool_id, lp_index; int shared, entitled_capacity, max_entitled_capacity; int processors, max_processors; - struct paca_struct *lpaca = get_paca(); unsigned long purr = get_purr(); seq_printf(m, "%s %s \n", MODULE_NAME, MODULE_VERS); - shared = (int)(lpaca->lppaca_ptr->shared_proc); + shared = (int)(get_lppaca()->shared_proc); seq_printf(m, "serial_number=%c%c%c%c%c%c%c\n", e2a(xItExtVpdPanel.mfgID[2]), e2a(xItExtVpdPanel.mfgID[3]), @@ -402,7 +399,7 @@ static int lparcfg_data(struct seq_file *m, void *v) (h_resource >> 0 * 8) & 0xffff); /* pool related entries are apropriate for shared configs */ - if (paca[0].lppaca.shared_proc) { + if (lppaca[0].shared_proc) { h_pic(&pool_idle_time, &pool_procs); @@ -451,7 +448,7 @@ static int lparcfg_data(struct seq_file *m, void *v) seq_printf(m, "partition_potential_processors=%d\n", partition_potential_processors); - seq_printf(m, "shared_processor_mode=%d\n", paca[0].lppaca.shared_proc); + seq_printf(m, "shared_processor_mode=%d\n", lppaca[0].shared_proc); return 0; } diff --git a/arch/powerpc/kernel/misc_32.S b/arch/powerpc/kernel/misc_32.S index 01d0d97a16e..be982023409 100644 --- a/arch/powerpc/kernel/misc_32.S +++ b/arch/powerpc/kernel/misc_32.S @@ -68,7 +68,7 @@ _GLOBAL(reloc_offset) mflr r0 bl 1f 1: mflr r3 - LOADADDR(r4,1b) + LOAD_REG_IMMEDIATE(r4,1b) subf r3,r4,r3 mtlr r0 blr @@ -80,7 +80,7 @@ _GLOBAL(add_reloc_offset) mflr r0 bl 1f 1: mflr r5 - LOADADDR(r4,1b) + LOAD_REG_IMMEDIATE(r4,1b) subf r5,r4,r5 add r3,r3,r5 mtlr r0 diff --git a/arch/powerpc/kernel/misc_64.S b/arch/powerpc/kernel/misc_64.S index ae48a002f81..2778cce058e 100644 --- a/arch/powerpc/kernel/misc_64.S +++ b/arch/powerpc/kernel/misc_64.S @@ -39,7 +39,7 @@ _GLOBAL(reloc_offset) mflr r0 bl 1f 1: mflr r3 - LOADADDR(r4,1b) + LOAD_REG_IMMEDIATE(r4,1b) subf r3,r4,r3 mtlr r0 blr @@ -51,7 +51,7 @@ _GLOBAL(add_reloc_offset) mflr r0 bl 1f 1: mflr r5 - LOADADDR(r4,1b) + LOAD_REG_IMMEDIATE(r4,1b) subf r5,r4,r5 add r3,r3,r5 mtlr r0 @@ -498,15 +498,15 @@ _GLOBAL(identify_cpu) */ _GLOBAL(do_cpu_ftr_fixups) /* Get CPU 0 features */ - LOADADDR(r6,cur_cpu_spec) + LOAD_REG_IMMEDIATE(r6,cur_cpu_spec) sub r6,r6,r3 ld r4,0(r6) sub r4,r4,r3 ld r4,CPU_SPEC_FEATURES(r4) /* Get the fixup table */ - LOADADDR(r6,__start___ftr_fixup) + LOAD_REG_IMMEDIATE(r6,__start___ftr_fixup) sub r6,r6,r3 - LOADADDR(r7,__stop___ftr_fixup) + LOAD_REG_IMMEDIATE(r7,__stop___ftr_fixup) sub r7,r7,r3 /* Do the fixup */ 1: cmpld r6,r7 diff --git a/arch/powerpc/kernel/paca.c b/arch/powerpc/kernel/paca.c index 999bdd81676..5d1b708086b 100644 --- a/arch/powerpc/kernel/paca.c +++ b/arch/powerpc/kernel/paca.c @@ -25,6 +25,28 @@ * field correctly */ extern unsigned long __toc_start; +/* + * iSeries structure which the hypervisor knows about - this structure + * should not cross a page boundary. The vpa_init/register_vpa call + * is now known to fail if the lppaca structure crosses a page + * boundary. The lppaca is also used on POWER5 pSeries boxes. The + * lppaca is 640 bytes long, and cannot readily change since the + * hypervisor knows its layout, so a 1kB alignment will suffice to + * ensure that it doesn't cross a page boundary. + */ +struct lppaca lppaca[] = { + [0 ... (NR_CPUS-1)] = { + .desc = 0xd397d781, /* "LpPa" */ + .size = sizeof(struct lppaca), + .dyn_proc_status = 2, + .decr_val = 0x00ff0000, + .fpregs_in_use = 1, + .end_of_quantum = 0xfffffffffffffffful, + .slb_count = 64, + .vmxregs_in_use = 0, + }, +}; + /* The Paca is an array with one entry per processor. Each contains an * lppaca, which contains the information shared between the * hypervisor and Linux. @@ -35,27 +57,17 @@ extern unsigned long __toc_start; * processor (not thread). */ #define PACA_INIT_COMMON(number, start, asrr, asrv) \ + .lppaca_ptr = &lppaca[number], \ .lock_token = 0x8000, \ .paca_index = (number), /* Paca Index */ \ .kernel_toc = (unsigned long)(&__toc_start) + 0x8000UL, \ .stab_real = (asrr), /* Real pointer to segment table */ \ .stab_addr = (asrv), /* Virt pointer to segment table */ \ .cpu_start = (start), /* Processor start */ \ - .hw_cpu_id = 0xffff, \ - .lppaca = { \ - .desc = 0xd397d781, /* "LpPa" */ \ - .size = sizeof(struct lppaca), \ - .dyn_proc_status = 2, \ - .decr_val = 0x00ff0000, \ - .fpregs_in_use = 1, \ - .end_of_quantum = 0xfffffffffffffffful, \ - .slb_count = 64, \ - .vmxregs_in_use = 0, \ - }, \ + .hw_cpu_id = 0xffff, #ifdef CONFIG_PPC_ISERIES #define PACA_INIT_ISERIES(number) \ - .lppaca_ptr = &paca[number].lppaca, \ .reg_save_ptr = &iseries_reg_save[number], #define PACA_INIT(number) \ diff --git a/arch/powerpc/kernel/ppc_ksyms.c b/arch/powerpc/kernel/ppc_ksyms.c index 16d9a904f3c..d9a459c144d 100644 --- a/arch/powerpc/kernel/ppc_ksyms.c +++ b/arch/powerpc/kernel/ppc_ksyms.c @@ -230,8 +230,7 @@ EXPORT_SYMBOL(__down_interruptible); EXPORT_SYMBOL(cpm_install_handler); EXPORT_SYMBOL(cpm_free_handler); #endif /* CONFIG_8xx */ -#if defined(CONFIG_8xx) || defined(CONFIG_40x) || defined(CONFIG_85xx) ||\ - defined(CONFIG_83xx) +#if defined(CONFIG_8xx) || defined(CONFIG_40x) EXPORT_SYMBOL(__res); #endif diff --git a/arch/powerpc/kernel/prom.c b/arch/powerpc/kernel/prom.c index 02e2115323e..d50c8df0183 100644 --- a/arch/powerpc/kernel/prom.c +++ b/arch/powerpc/kernel/prom.c @@ -1627,6 +1627,11 @@ static void of_node_release(struct kref *kref) kfree(prop->value); kfree(prop); prop = next; + + if (!prop) { + prop = node->deadprops; + node->deadprops = NULL; + } } kfree(node->intrs); kfree(node->full_name); @@ -1774,22 +1779,32 @@ static int __init prom_reconfig_setup(void) __initcall(prom_reconfig_setup); #endif -/* - * Find a property with a given name for a given node - * and return the value. - */ -unsigned char *get_property(struct device_node *np, const char *name, - int *lenp) +struct property *of_find_property(struct device_node *np, const char *name, + int *lenp) { struct property *pp; + read_lock(&devtree_lock); for (pp = np->properties; pp != 0; pp = pp->next) if (strcmp(pp->name, name) == 0) { if (lenp != 0) *lenp = pp->length; - return pp->value; + break; } - return NULL; + read_unlock(&devtree_lock); + + return pp; +} + +/* + * Find a property with a given name for a given node + * and return the value. + */ +unsigned char *get_property(struct device_node *np, const char *name, + int *lenp) +{ + struct property *pp = of_find_property(np,name,lenp); + return pp ? pp->value : NULL; } EXPORT_SYMBOL(get_property); @@ -1823,4 +1838,82 @@ int prom_add_property(struct device_node* np, struct property* prop) return 0; } +/* + * Remove a property from a node. Note that we don't actually + * remove it, since we have given out who-knows-how-many pointers + * to the data using get-property. Instead we just move the property + * to the "dead properties" list, so it won't be found any more. + */ +int prom_remove_property(struct device_node *np, struct property *prop) +{ + struct property **next; + int found = 0; + write_lock(&devtree_lock); + next = &np->properties; + while (*next) { + if (*next == prop) { + /* found the node */ + *next = prop->next; + prop->next = np->deadprops; + np->deadprops = prop; + found = 1; + break; + } + next = &(*next)->next; + } + write_unlock(&devtree_lock); + + if (!found) + return -ENODEV; + +#ifdef CONFIG_PROC_DEVICETREE + /* try to remove the proc node as well */ + if (np->pde) + proc_device_tree_remove_prop(np->pde, prop); +#endif /* CONFIG_PROC_DEVICETREE */ + + return 0; +} + +/* + * Update a property in a node. Note that we don't actually + * remove it, since we have given out who-knows-how-many pointers + * to the data using get-property. Instead we just move the property + * to the "dead properties" list, and add the new property to the + * property list + */ +int prom_update_property(struct device_node *np, + struct property *newprop, + struct property *oldprop) +{ + struct property **next; + int found = 0; + + write_lock(&devtree_lock); + next = &np->properties; + while (*next) { + if (*next == oldprop) { + /* found the node */ + newprop->next = oldprop->next; + *next = newprop; + oldprop->next = np->deadprops; + np->deadprops = oldprop; + found = 1; + break; + } + next = &(*next)->next; + } + write_unlock(&devtree_lock); + + if (!found) + return -ENODEV; + +#ifdef CONFIG_PROC_DEVICETREE + /* try to add to proc as well if it was initialized */ + if (np->pde) + proc_device_tree_update_prop(np->pde, newprop, oldprop); +#endif /* CONFIG_PROC_DEVICETREE */ + + return 0; +} diff --git a/arch/powerpc/kernel/prom_parse.c b/arch/powerpc/kernel/prom_parse.c index 309ae1d5fa7..a8099c80615 100644 --- a/arch/powerpc/kernel/prom_parse.c +++ b/arch/powerpc/kernel/prom_parse.c @@ -113,7 +113,8 @@ static unsigned int of_bus_default_get_flags(u32 *addr) static int of_bus_pci_match(struct device_node *np) { - return !strcmp(np->type, "pci"); + /* "vci" is for the /chaos bridge on 1st-gen PCI powermacs */ + return !strcmp(np->type, "pci") || !strcmp(np->type, "vci"); } static void of_bus_pci_count_cells(struct device_node *np, diff --git a/arch/powerpc/kernel/rtas.c b/arch/powerpc/kernel/rtas.c index 4b9cfe4637b..7fe4a5c944c 100644 --- a/arch/powerpc/kernel/rtas.c +++ b/arch/powerpc/kernel/rtas.c @@ -36,6 +36,11 @@ struct rtas_t rtas = { .lock = SPIN_LOCK_UNLOCKED }; +struct rtas_suspend_me_data { + long waiting; + struct rtas_args *args; +}; + EXPORT_SYMBOL(rtas); DEFINE_SPINLOCK(rtas_data_buf_lock); @@ -556,6 +561,80 @@ void rtas_os_term(char *str) } while (status == RTAS_BUSY); } +static int ibm_suspend_me_token = RTAS_UNKNOWN_SERVICE; +#ifdef CONFIG_PPC_PSERIES +static void rtas_percpu_suspend_me(void *info) +{ + long rc; + long flags; + struct rtas_suspend_me_data *data = + (struct rtas_suspend_me_data *)info; + + /* + * We use "waiting" to indicate our state. As long + * as it is >0, we are still trying to all join up. + * If it goes to 0, we have successfully joined up and + * one thread got H_Continue. If any error happens, + * we set it to <0. + */ + local_irq_save(flags); + do { + rc = plpar_hcall_norets(H_JOIN); + smp_rmb(); + } while (rc == H_Success && data->waiting > 0); + if (rc == H_Success) + goto out; + + if (rc == H_Continue) { + data->waiting = 0; + rtas_call(ibm_suspend_me_token, 0, 1, + data->args->args); + } else { + data->waiting = -EBUSY; + printk(KERN_ERR "Error on H_Join hypervisor call\n"); + } + +out: + /* before we restore interrupts, make sure we don't + * generate a spurious soft lockup errors + */ + touch_softlockup_watchdog(); + local_irq_restore(flags); + return; +} + +static int rtas_ibm_suspend_me(struct rtas_args *args) +{ + int i; + + struct rtas_suspend_me_data data; + + data.waiting = 1; + data.args = args; + + /* Call function on all CPUs. One of us will make the + * rtas call + */ + if (on_each_cpu(rtas_percpu_suspend_me, &data, 1, 0)) + data.waiting = -EINVAL; + + if (data.waiting != 0) + printk(KERN_ERR "Error doing global join\n"); + + /* Prod each CPU. This won't hurt, and will wake + * anyone we successfully put to sleep with H_Join + */ + for_each_cpu(i) + plpar_hcall_norets(H_PROD, i); + + return data.waiting; +} +#else /* CONFIG_PPC_PSERIES */ +static int rtas_ibm_suspend_me(struct rtas_args *args) +{ + return -ENOSYS; +} +#endif asmlinkage int ppc_rtas(struct rtas_args __user *uargs) { @@ -563,6 +642,7 @@ asmlinkage int ppc_rtas(struct rtas_args __user *uargs) unsigned long flags; char *buff_copy, *errbuf = NULL; int nargs; + int rc; if (!capable(CAP_SYS_ADMIN)) return -EPERM; @@ -581,6 +661,17 @@ asmlinkage int ppc_rtas(struct rtas_args __user *uargs) nargs * sizeof(rtas_arg_t)) != 0) return -EFAULT; + if (args.token == RTAS_UNKNOWN_SERVICE) + return -EINVAL; + + /* Need to handle ibm,suspend_me call specially */ + if (args.token == ibm_suspend_me_token) { + rc = rtas_ibm_suspend_me(&args); + if (rc) + return rc; + goto copy_return; + } + buff_copy = get_errorlog_buffer(); spin_lock_irqsave(&rtas.lock, flags); @@ -604,6 +695,7 @@ asmlinkage int ppc_rtas(struct rtas_args __user *uargs) kfree(buff_copy); } + copy_return: /* Copy out args. */ if (copy_to_user(uargs->args + nargs, args.args + nargs, @@ -675,8 +767,10 @@ void __init rtas_initialize(void) * the stop-self token if any */ #ifdef CONFIG_PPC64 - if (_machine == PLATFORM_PSERIES_LPAR) + if (_machine == PLATFORM_PSERIES_LPAR) { rtas_region = min(lmb.rmo_size, RTAS_INSTANTIATE_MAX); + ibm_suspend_me_token = rtas_token("ibm,suspend-me"); + } #endif rtas_rmo_buf = lmb_alloc_base(RTAS_RMOBUF_MAX, PAGE_SIZE, rtas_region); diff --git a/arch/powerpc/kernel/setup-common.c b/arch/powerpc/kernel/setup-common.c index d5c52fae023..be12041c0fc 100644 --- a/arch/powerpc/kernel/setup-common.c +++ b/arch/powerpc/kernel/setup-common.c @@ -100,7 +100,8 @@ void machine_shutdown(void) void machine_restart(char *cmd) { machine_shutdown(); - ppc_md.restart(cmd); + if (ppc_md.restart) + ppc_md.restart(cmd); #ifdef CONFIG_SMP smp_send_stop(); #endif @@ -112,7 +113,8 @@ void machine_restart(char *cmd) void machine_power_off(void) { machine_shutdown(); - ppc_md.power_off(); + if (ppc_md.power_off) + ppc_md.power_off(); #ifdef CONFIG_SMP smp_send_stop(); #endif @@ -129,7 +131,8 @@ EXPORT_SYMBOL_GPL(pm_power_off); void machine_halt(void) { machine_shutdown(); - ppc_md.halt(); + if (ppc_md.halt) + ppc_md.halt(); #ifdef CONFIG_SMP smp_send_stop(); #endif diff --git a/arch/powerpc/kernel/time.c b/arch/powerpc/kernel/time.c index 56f50e91bdd..c4a294d657b 100644 --- a/arch/powerpc/kernel/time.c +++ b/arch/powerpc/kernel/time.c @@ -431,7 +431,7 @@ void timer_interrupt(struct pt_regs * regs) profile_tick(CPU_PROFILING, regs); #ifdef CONFIG_PPC_ISERIES - get_paca()->lppaca.int_dword.fields.decr_int = 0; + get_lppaca()->int_dword.fields.decr_int = 0; #endif while ((ticks = tb_ticks_since(per_cpu(last_jiffy, cpu))) diff --git a/arch/powerpc/lib/locks.c b/arch/powerpc/lib/locks.c index 35bd03c41dd..8362fa272ca 100644 --- a/arch/powerpc/lib/locks.c +++ b/arch/powerpc/lib/locks.c @@ -28,15 +28,13 @@ void __spin_yield(raw_spinlock_t *lock) { unsigned int lock_value, holder_cpu, yield_count; - struct paca_struct *holder_paca; lock_value = lock->slock; if (lock_value == 0) return; holder_cpu = lock_value & 0xffff; BUG_ON(holder_cpu >= NR_CPUS); - holder_paca = &paca[holder_cpu]; - yield_count = holder_paca->lppaca.yield_count; + yield_count = lppaca[holder_cpu].yield_count; if ((yield_count & 1) == 0) return; /* virtual cpu is currently running */ rmb(); @@ -60,15 +58,13 @@ void __rw_yield(raw_rwlock_t *rw) { int lock_value; unsigned int holder_cpu, yield_count; - struct paca_struct *holder_paca; lock_value = rw->lock; if (lock_value >= 0) return; /* no write lock at present */ holder_cpu = lock_value & 0xffff; BUG_ON(holder_cpu >= NR_CPUS); - holder_paca = &paca[holder_cpu]; - yield_count = holder_paca->lppaca.yield_count; + yield_count = lppaca[holder_cpu].yield_count; if ((yield_count & 1) == 0) return; /* virtual cpu is currently running */ rmb(); diff --git a/arch/powerpc/oprofile/common.c b/arch/powerpc/oprofile/common.c index 71615eb70b2..cc2535be3a7 100644 --- a/arch/powerpc/oprofile/common.c +++ b/arch/powerpc/oprofile/common.c @@ -140,19 +140,19 @@ int __init oprofile_arch_init(struct oprofile_operations *ops) switch (cur_cpu_spec->oprofile_type) { #ifdef CONFIG_PPC64 - case RS64: + case PPC_OPROFILE_RS64: model = &op_model_rs64; break; - case POWER4: + case PPC_OPROFILE_POWER4: model = &op_model_power4; break; #else - case G4: + case PPC_OPROFILE_G4: model = &op_model_7450; break; #endif #ifdef CONFIG_FSL_BOOKE - case BOOKE: + case PPC_OPROFILE_BOOKE: model = &op_model_fsl_booke; break; #endif diff --git a/arch/powerpc/platforms/83xx/Kconfig b/arch/powerpc/platforms/83xx/Kconfig index b20812d460e..7675e675dce 100644 --- a/arch/powerpc/platforms/83xx/Kconfig +++ b/arch/powerpc/platforms/83xx/Kconfig @@ -7,6 +7,7 @@ choice config MPC834x_SYS bool "Freescale MPC834x SYS" + select DEFAULT_UIMAGE help This option enables support for the MPC 834x SYS evaluation board. diff --git a/arch/powerpc/platforms/83xx/mpc834x_sys.c b/arch/powerpc/platforms/83xx/mpc834x_sys.c new file mode 100644 index 00000000000..2098dd05a77 --- /dev/null +++ b/arch/powerpc/platforms/83xx/mpc834x_sys.c @@ -0,0 +1,243 @@ +/* + * arch/powerpc/platforms/83xx/mpc834x_sys.c + * + * MPC834x SYS board specific routines + * + * Maintainer: Kumar Gala <galak@kernel.crashing.org> + * + * This program is free software; you can redistribute it and/or modify it + * under the terms of the GNU General Public License as published by the + * Free Software Foundation; either version 2 of the License, or (at your + * option) any later version. + */ + +#include <linux/config.h> +#include <linux/stddef.h> +#include <linux/kernel.h> +#include <linux/init.h> +#include <linux/errno.h> +#include <linux/reboot.h> +#include <linux/pci.h> +#include <linux/kdev_t.h> +#include <linux/major.h> +#include <linux/console.h> +#include <linux/delay.h> +#include <linux/seq_file.h> +#include <linux/root_dev.h> +#include <linux/module.h> +#include <linux/fsl_devices.h> + +#include <asm/system.h> +#include <asm/pgtable.h> +#include <asm/page.h> +#include <asm/atomic.h> +#include <asm/time.h> +#include <asm/io.h> +#include <asm/machdep.h> +#include <asm/ipic.h> +#include <asm/bootinfo.h> +#include <asm/pci-bridge.h> +#include <asm/mpc83xx.h> +#include <asm/irq.h> +#include <mm/mmu_decl.h> +#include <asm/prom.h> +#include <asm/udbg.h> +#include <sysdev/fsl_soc.h> + +#include "mpc83xx.h" + +#ifndef CONFIG_PCI +unsigned long isa_io_base = 0; +unsigned long isa_mem_base = 0; +#endif + +#ifdef CONFIG_PCI +extern int mpc83xx_pci2_busno; + +static int +mpc83xx_map_irq(struct pci_dev *dev, unsigned char idsel, unsigned char pin) +{ + static char pci_irq_table[][4] = + /* + * PCI IDSEL/INTPIN->INTLINE + * A B C D + */ + { + {PIRQA, PIRQB, PIRQC, PIRQD}, /* idsel 0x11 */ + {PIRQC, PIRQD, PIRQA, PIRQB}, /* idsel 0x12 */ + {PIRQD, PIRQA, PIRQB, PIRQC}, /* idsel 0x13 */ + {0, 0, 0, 0}, + {PIRQA, PIRQB, PIRQC, PIRQD}, /* idsel 0x15 */ + {PIRQD, PIRQA, PIRQB, PIRQC}, /* idsel 0x16 */ + {PIRQC, PIRQD, PIRQA, PIRQB}, /* idsel 0x17 */ + {PIRQB, PIRQC, PIRQD, PIRQA}, /* idsel 0x18 */ + {0, 0, 0, 0}, /* idsel 0x19 */ + {0, 0, 0, 0}, /* idsel 0x20 */ + }; + + const long min_idsel = 0x11, max_idsel = 0x20, irqs_per_slot = 4; + return PCI_IRQ_TABLE_LOOKUP; +} + +static int +mpc83xx_exclude_device(u_char bus, u_char devfn) +{ + if (bus == 0 && PCI_SLOT(devfn) == 0) + return PCIBIOS_DEVICE_NOT_FOUND; + if (mpc83xx_pci2_busno) + if (bus == (mpc83xx_pci2_busno) && PCI_SLOT(devfn) == 0) + return PCIBIOS_DEVICE_NOT_FOUND; + return PCIBIOS_SUCCESSFUL; +} +#endif /* CONFIG_PCI */ + +/* ************************************************************************ + * + * Setup the architecture + * + */ +static void __init +mpc834x_sys_setup_arch(void) +{ + struct device_node *np; + + if (ppc_md.progress) + ppc_md.progress("mpc834x_sys_setup_arch()", 0); + + np = of_find_node_by_type(NULL, "cpu"); + if (np != 0) { + unsigned int *fp = (int *) get_property(np, "clock-frequency", NULL); + if (fp != 0) + loops_per_jiffy = *fp / HZ; + else + loops_per_jiffy = 50000000 / HZ; + of_node_put(np); + } + +#ifdef CONFIG_PCI + for (np = NULL; (np = of_find_node_by_type(np, "pci")) != NULL;) + add_bridge(np); + + ppc_md.pci_swizzle = common_swizzle; + ppc_md.pci_map_irq = mpc83xx_map_irq; + ppc_md.pci_exclude_device = mpc83xx_exclude_device; +#endif + +#ifdef CONFIG_ROOT_NFS + ROOT_DEV = Root_NFS; +#else + ROOT_DEV = Root_HDA1; +#endif +} + +void __init +mpc834x_sys_init_IRQ(void) +{ + u8 senses[8] = { + 0, /* EXT 0 */ + IRQ_SENSE_LEVEL, /* EXT 1 */ + IRQ_SENSE_LEVEL, /* EXT 2 */ + 0, /* EXT 3 */ +#ifdef CONFIG_PCI + IRQ_SENSE_LEVEL, /* EXT 4 */ + IRQ_SENSE_LEVEL, /* EXT 5 */ + IRQ_SENSE_LEVEL, /* EXT 6 */ + IRQ_SENSE_LEVEL, /* EXT 7 */ +#else + 0, /* EXT 4 */ + 0, /* EXT 5 */ + 0, /* EXT 6 */ + 0, /* EXT 7 */ +#endif + }; + + ipic_init(get_immrbase() + 0x00700, 0, 0, senses, 8); + + /* Initialize the default interrupt mapping priorities, + * in case the boot rom changed something on us. + */ + ipic_set_default_priority(); +} + +#if defined(CONFIG_I2C_MPC) && defined(CONFIG_SENSORS_DS1374) +extern ulong ds1374_get_rtc_time(void); +extern int ds1374_set_rtc_time(ulong); + +static int __init +mpc834x_rtc_hookup(void) +{ + struct timespec tv; + + ppc_md.get_rtc_time = ds1374_get_rtc_time; + ppc_md.set_rtc_time = ds1374_set_rtc_time; + + tv.tv_nsec = 0; + tv.tv_sec = (ppc_md.get_rtc_time)(); + do_settimeofday(&tv); + + return 0; +} +late_initcall(mpc834x_rtc_hookup); +#endif + +static void +mpc83xx_restart(char *cmd) +{ +#define RST_OFFSET 0x00000900 +#define RST_PROT_REG 0x00000018 +#define RST_CTRL_REG 0x0000001c + __be32 __iomem *reg; + + // map reset register space + reg = ioremap(get_immrbase() + 0x900, 0xff); + + local_irq_disable(); + + /* enable software reset "RSTE" */ + out_be32(reg + (RST_PROT_REG >> 2), 0x52535445); + + /* set software hard reset */ + out_be32(reg + (RST_CTRL_REG >> 2), 0x52535445); + for(;;); +} + +static long __init +mpc83xx_time_init(void) +{ +#define SPCR_OFFSET 0x00000110 +#define SPCR_TBEN 0x00400000 + __be32 __iomem *spcr = ioremap(get_immrbase() + SPCR_OFFSET, 4); + __be32 tmp; + + tmp = in_be32(spcr); + out_be32(spcr, tmp|SPCR_TBEN); + + iounmap(spcr); + + return 0; +} +void __init +platform_init(void) +{ + /* setup the PowerPC module struct */ + ppc_md.setup_arch = mpc834x_sys_setup_arch; + + ppc_md.init_IRQ = mpc834x_sys_init_IRQ; + ppc_md.get_irq = ipic_get_irq; + + ppc_md.restart = mpc83xx_restart; + + ppc_md.time_init = mpc83xx_time_init; + ppc_md.set_rtc_time = NULL; + ppc_md.get_rtc_time = NULL; + ppc_md.calibrate_decr = generic_calibrate_decr; + + ppc_md.progress = udbg_progress; + + if (ppc_md.progress) + ppc_md.progress("mpc834x_sys_init(): exit", 0); + + return; +} + + diff --git a/arch/powerpc/platforms/83xx/mpc834x_sys.h b/arch/powerpc/platforms/83xx/mpc834x_sys.h new file mode 100644 index 00000000000..e4ca39f6a86 --- /dev/null +++ b/arch/powerpc/platforms/83xx/mpc834x_sys.h @@ -0,0 +1,23 @@ +/* + * arch/powerppc/platforms/83xx/mpc834x_sys.h + * + * MPC834X SYS common board definitions + * + * Maintainer: Kumar Gala <galak@kernel.crashing.org> + * + * This program is free software; you can redistribute it and/or modify it + * under the terms of the GNU General Public License as published by the + * Free Software Foundation; either version 2 of the License, or (at your + * option) any later version. + * + */ + +#ifndef __MACH_MPC83XX_SYS_H__ +#define __MACH_MPC83XX_SYS_H__ + +#define PIRQA MPC83xx_IRQ_EXT4 +#define PIRQB MPC83xx_IRQ_EXT5 +#define PIRQC MPC83xx_IRQ_EXT6 +#define PIRQD MPC83xx_IRQ_EXT7 + +#endif /* __MACH_MPC83XX_SYS_H__ */ diff --git a/arch/powerpc/platforms/83xx/mpc83xx.h b/arch/powerpc/platforms/83xx/mpc83xx.h new file mode 100644 index 00000000000..ce9e66abef2 --- /dev/null +++ b/arch/powerpc/platforms/83xx/mpc83xx.h @@ -0,0 +1,14 @@ +#ifndef __MPC83XX_H__ +#define __MPC83XX_H__ + +#include <linux/init.h> +#include <linux/device.h> + +/* + * Declaration for the various functions exported by the + * mpc83xx_* files. Mostly for use by mpc83xx_setup + */ + +extern int add_bridge(struct device_node *dev); + +#endif /* __MPC83XX_H__ */ diff --git a/arch/powerpc/platforms/83xx/pci.c b/arch/powerpc/platforms/83xx/pci.c new file mode 100644 index 00000000000..469cdacc5bd --- /dev/null +++ b/arch/powerpc/platforms/83xx/pci.c @@ -0,0 +1,99 @@ +/* + * FSL SoC setup code + * + * Maintained by Kumar Gala (see MAINTAINERS for contact information) + * + * This program is free software; you can redistribute it and/or modify it + * under the terms of the GNU General Public License as published by the + * Free Software Foundation; either version 2 of the License, or (at your + * option) any later version. + */ + +#include <linux/config.h> +#include <linux/stddef.h> +#include <linux/kernel.h> +#include <linux/init.h> +#include <linux/errno.h> +#include <linux/pci.h> +#include <linux/delay.h> +#include <linux/irq.h> +#include <linux/module.h> + +#include <asm/system.h> +#include <asm/atomic.h> +#include <asm/io.h> +#include <asm/pci-bridge.h> +#include <asm/prom.h> +#include <sysdev/fsl_soc.h> + +#undef DEBUG + +#ifdef DEBUG +#define DBG(x...) printk(x) +#else +#define DBG(x...) +#endif + +int mpc83xx_pci2_busno; + +#ifdef CONFIG_PCI +int __init add_bridge(struct device_node *dev) +{ + int len; + struct pci_controller *hose; + struct resource rsrc; + int *bus_range; + int primary = 1, has_address = 0; + phys_addr_t immr = get_immrbase(); + + DBG("Adding PCI host bridge %s\n", dev->full_name); + + /* Fetch host bridge registers address */ + has_address = (of_address_to_resource(dev, 0, &rsrc) == 0); + + /* Get bus range if any */ + bus_range = (int *) get_property(dev, "bus-range", &len); + if (bus_range == NULL || len < 2 * sizeof(int)) { + printk(KERN_WARNING "Can't get bus-range for %s, assume" + " bus 0\n", dev->full_name); + } + + hose = pcibios_alloc_controller(); + if (!hose) + return -ENOMEM; + hose->arch_data = dev; + hose->set_cfg_type = 1; + + hose->first_busno = bus_range ? bus_range[0] : 0; + hose->last_busno = bus_range ? bus_range[1] : 0xff; + + /* MPC83xx supports up to two host controllers one at 0x8500 from immrbar + * the other at 0x8600, we consider the 0x8500 the primary controller + */ + /* PCI 1 */ + if ((rsrc.start & 0xfffff) == 0x8500) { + setup_indirect_pci(hose, immr + 0x8300, immr + 0x8304); + } + /* PCI 2*/ + if ((rsrc.start & 0xfffff) == 0x8600) { + setup_indirect_pci(hose, immr + 0x8380, immr + 0x8384); + primary = 0; + hose->bus_offset = hose->first_busno; + mpc83xx_pci2_busno = hose->first_busno; + } + + printk(KERN_INFO "Found MPC83xx PCI host bridge at 0x%08lx. " + "Firmware bus number: %d->%d\n", + rsrc.start, hose->first_busno, hose->last_busno); + + DBG(" ->Hose at 0x%p, cfg_addr=0x%p,cfg_data=0x%p\n", + hose, hose->cfg_addr, hose->cfg_data); + + /* Interpret the "ranges" property */ + /* This also maps the I/O region and sets isa_io/mem_base */ + pci_process_bridge_OF_ranges(hose, dev, primary); + + return 0; +} + +#endif diff --git a/arch/powerpc/platforms/chrp/pci.c b/arch/powerpc/platforms/chrp/pci.c index 82c429d487f..00c52f27ef4 100644 --- a/arch/powerpc/platforms/chrp/pci.c +++ b/arch/powerpc/platforms/chrp/pci.c @@ -135,12 +135,13 @@ int __init hydra_init(void) { struct device_node *np; + struct resource r; np = find_devices("mac-io"); - if (np == NULL || np->n_addrs == 0) + if (np == NULL || of_address_to_resource(np, 0, &r)) return 0; - Hydra = ioremap(np->addrs[0].address, np->addrs[0].size); - printk("Hydra Mac I/O at %lx\n", np->addrs[0].address); + Hydra = ioremap(r.start, r.end-r.start); + printk("Hydra Mac I/O at %lx\n", r.start); printk("Hydra Feature_Control was %x", in_le32(&Hydra->Feature_Control)); out_le32(&Hydra->Feature_Control, (HYDRA_FC_SCC_CELL_EN | @@ -177,18 +178,24 @@ setup_python(struct pci_controller *hose, struct device_node *dev) { u32 __iomem *reg; u32 val; - unsigned long addr = dev->addrs[0].address; + struct resource r; - setup_indirect_pci(hose, addr + 0xf8000, addr + 0xf8010); + if (of_address_to_resource(dev, 0, &r)) { + printk(KERN_ERR "No address for Python PCI controller\n"); + return; + } /* Clear the magic go-slow bit */ - reg = ioremap(dev->addrs[0].address + 0xf6000, 0x40); + reg = ioremap(r.start + 0xf6000, 0x40); + BUG_ON(!reg); val = in_be32(®[12]); if (val & PRG_CL_RESET_VALID) { out_be32(®[12], val & ~PRG_CL_RESET_VALID); in_be32(®[12]); } iounmap(reg); + + setup_indirect_pci(hose, r.start + 0xf8000, r.start + 0xf8010); } /* Marvell Discovery II based Pegasos 2 */ @@ -218,7 +225,7 @@ chrp_find_bridges(void) char *model, *machine; int is_longtrail = 0, is_mot = 0, is_pegasos = 0; struct device_node *root = find_path_device("/"); - + struct resource r; /* * The PCI host bridge nodes on some machines don't have * properties to adequately identify them, so we have to @@ -238,7 +245,7 @@ chrp_find_bridges(void) continue; ++index; /* The GG2 bridge on the LongTrail doesn't have an address */ - if (dev->n_addrs < 1 && !is_longtrail) { + if (of_address_to_resource(dev, 0, &r) && !is_longtrail) { printk(KERN_WARNING "Can't use %s: no address\n", dev->full_name); continue; @@ -255,8 +262,8 @@ chrp_find_bridges(void) printk(KERN_INFO "PCI buses %d..%d", bus_range[0], bus_range[1]); printk(" controlled by %s", dev->type); - if (dev->n_addrs > 0) - printk(" at %lx", dev->addrs[0].address); + if (!is_longtrail) + printk(" at %lx", r.start); printk("\n"); hose = pcibios_alloc_controller(); diff --git a/arch/powerpc/platforms/chrp/setup.c b/arch/powerpc/platforms/chrp/setup.c index 4ec8ba737e7..2dc87aa5962 100644 --- a/arch/powerpc/platforms/chrp/setup.c +++ b/arch/powerpc/platforms/chrp/setup.c @@ -352,9 +352,10 @@ static void __init chrp_find_openpic(void) opaddr = opprop[na-1]; /* assume 32-bit */ oplen /= na * sizeof(unsigned int); } else { - if (np->n_addrs == 0) + struct resource r; + if (of_address_to_resource(np, 0, &r)) return; - opaddr = np->addrs[0].address; + opaddr = r.start; oplen = 0; } @@ -377,7 +378,7 @@ static void __init chrp_find_openpic(void) */ if (oplen < len) { printk(KERN_ERR "Insufficient addresses for distributed" - " OpenPIC (%d < %d)\n", np->n_addrs, len); + " OpenPIC (%d < %d)\n", oplen, len); len = oplen; } diff --git a/arch/powerpc/platforms/chrp/time.c b/arch/powerpc/platforms/chrp/time.c index 737ee5d9f0a..36a0f97bb7b 100644 --- a/arch/powerpc/platforms/chrp/time.c +++ b/arch/powerpc/platforms/chrp/time.c @@ -21,6 +21,7 @@ #include <linux/mc146818rtc.h> #include <linux/init.h> #include <linux/bcd.h> +#include <linux/ioport.h> #include <asm/io.h> #include <asm/nvram.h> @@ -37,14 +38,16 @@ static int nvram_data = NVRAM_DATA; long __init chrp_time_init(void) { struct device_node *rtcs; + struct resource r; int base; rtcs = find_compatible_devices("rtc", "pnpPNP,b00"); if (rtcs == NULL) rtcs = find_compatible_devices("rtc", "ds1385-rtc"); - if (rtcs == NULL || rtcs->addrs == NULL) + if (rtcs == NULL || of_address_to_resource(rtcs, 0, &r)) return 0; - base = rtcs->addrs[0].address; + + base = r.start; nvram_as1 = 0; nvram_as0 = base; nvram_data = base + 1; diff --git a/arch/powerpc/platforms/iseries/irq.c b/arch/powerpc/platforms/iseries/irq.c index 83442ea7747..be3fbfc24e6 100644 --- a/arch/powerpc/platforms/iseries/irq.c +++ b/arch/powerpc/platforms/iseries/irq.c @@ -334,14 +334,12 @@ int __init iSeries_allocate_IRQ(HvBusNumber bus, */ int iSeries_get_irq(struct pt_regs *regs) { - struct paca_struct *lpaca; /* -2 means ignore this interrupt */ int irq = -2; - lpaca = get_paca(); #ifdef CONFIG_SMP - if (lpaca->lppaca.int_dword.fields.ipi_cnt) { - lpaca->lppaca.int_dword.fields.ipi_cnt = 0; + if (get_lppaca()->int_dword.fields.ipi_cnt) { + get_lppaca()->int_dword.fields.ipi_cnt = 0; iSeries_smp_message_recv(regs); } #endif /* CONFIG_SMP */ diff --git a/arch/powerpc/platforms/iseries/misc.S b/arch/powerpc/platforms/iseries/misc.S index dfe7aa1ba09..7641fc7e550 100644 --- a/arch/powerpc/platforms/iseries/misc.S +++ b/arch/powerpc/platforms/iseries/misc.S @@ -44,7 +44,8 @@ _GLOBAL(local_irq_restore) /* Check pending interrupts */ /* A decrementer, IPI or PMC interrupt may have occurred * while we were in the hypervisor (which enables) */ - ld r4,PACALPPACA+LPPACAANYINT(r13) + ld r4,PACALPPACAPTR(r13) + ld r4,LPPACAANYINT(r4) cmpdi r4,0 beqlr diff --git a/arch/powerpc/platforms/iseries/setup.c b/arch/powerpc/platforms/iseries/setup.c index c6bbe5c2510..3f8790146b0 100644 --- a/arch/powerpc/platforms/iseries/setup.c +++ b/arch/powerpc/platforms/iseries/setup.c @@ -538,7 +538,7 @@ static unsigned long __init build_iSeries_Memory_Map(void) */ static void __init iSeries_setup_arch(void) { - if (get_paca()->lppaca.shared_proc) { + if (get_lppaca()->shared_proc) { ppc_md.idle_loop = iseries_shared_idle; printk(KERN_INFO "Using shared processor idle loop\n"); } else { @@ -647,7 +647,7 @@ static void yield_shared_processor(void) * The decrementer stops during the yield. Force a fake decrementer * here and let the timer_interrupt code sort out the actual time. */ - get_paca()->lppaca.int_dword.fields.decr_int = 1; + get_lppaca()->int_dword.fields.decr_int = 1; process_iSeries_events(); } @@ -883,7 +883,7 @@ void dt_cpus(struct iseries_flat_dt *dt) pft_size[1] = __ilog2(HvCallHpt_getHptPages() * HW_PAGE_SIZE); for (i = 0; i < NR_CPUS; i++) { - if (paca[i].lppaca.dyn_proc_status >= 2) + if (lppaca[i].dyn_proc_status >= 2) continue; snprintf(p, 32 - (p - buf), "@%d", i); @@ -891,7 +891,7 @@ void dt_cpus(struct iseries_flat_dt *dt) dt_prop_str(dt, "device_type", "cpu"); - index = paca[i].lppaca.dyn_hv_phys_proc_index; + index = lppaca[i].dyn_hv_phys_proc_index; d = &xIoHriProcessorVpd[index]; dt_prop_u32(dt, "i-cache-size", d->xInstCacheSize * 1024); diff --git a/arch/powerpc/platforms/iseries/smp.c b/arch/powerpc/platforms/iseries/smp.c index fcb094ec6ae..6f9d407a709 100644 --- a/arch/powerpc/platforms/iseries/smp.c +++ b/arch/powerpc/platforms/iseries/smp.c @@ -91,7 +91,7 @@ static void smp_iSeries_kick_cpu(int nr) BUG_ON((nr < 0) || (nr >= NR_CPUS)); /* Verify that our partition has a processor nr */ - if (paca[nr].lppaca.dyn_proc_status >= 2) + if (lppaca[nr].dyn_proc_status >= 2) return; /* The processor is currently spinning, waiting diff --git a/arch/powerpc/platforms/pseries/lpar.c b/arch/powerpc/platforms/pseries/lpar.c index 1fe445ab78a..8952528d31a 100644 --- a/arch/powerpc/platforms/pseries/lpar.c +++ b/arch/powerpc/platforms/pseries/lpar.c @@ -254,11 +254,11 @@ out: void vpa_init(int cpu) { int hwcpu = get_hard_smp_processor_id(cpu); - unsigned long vpa = __pa(&paca[cpu].lppaca); + unsigned long vpa = __pa(&lppaca[cpu]); long ret; if (cpu_has_feature(CPU_FTR_ALTIVEC)) - paca[cpu].lppaca.vmxregs_in_use = 1; + lppaca[cpu].vmxregs_in_use = 1; ret = register_vpa(hwcpu, vpa); diff --git a/arch/powerpc/platforms/pseries/reconfig.c b/arch/powerpc/platforms/pseries/reconfig.c index d8864164dbe..86cfa6ecdcf 100644 --- a/arch/powerpc/platforms/pseries/reconfig.c +++ b/arch/powerpc/platforms/pseries/reconfig.c @@ -350,6 +350,100 @@ static int do_remove_node(char *buf) return rv; } +static char *parse_node(char *buf, size_t bufsize, struct device_node **npp) +{ + char *handle_str; + phandle handle; + *npp = NULL; + + handle_str = buf; + + buf = strchr(buf, ' '); + if (!buf) + return NULL; + *buf = '\0'; + buf++; + + handle = simple_strtoul(handle_str, NULL, 10); + + *npp = of_find_node_by_phandle(handle); + return buf; +} + +static int do_add_property(char *buf, size_t bufsize) +{ + struct property *prop = NULL; + struct device_node *np; + unsigned char *value; + char *name, *end; + int length; + end = buf + bufsize; + buf = parse_node(buf, bufsize, &np); + + if (!np) + return -ENODEV; + + if (parse_next_property(buf, end, &name, &length, &value) == NULL) + return -EINVAL; + + prop = new_property(name, length, value, NULL); + if (!prop) + return -ENOMEM; + + prom_add_property(np, prop); + + return 0; +} + +static int do_remove_property(char *buf, size_t bufsize) +{ + struct device_node *np; + char *tmp; + struct property *prop; + buf = parse_node(buf, bufsize, &np); + + if (!np) + return -ENODEV; + + tmp = strchr(buf,' '); + if (tmp) + *tmp = '\0'; + + if (strlen(buf) == 0) + return -EINVAL; + + prop = of_find_property(np, buf, NULL); + + return prom_remove_property(np, prop); +} + +static int do_update_property(char *buf, size_t bufsize) +{ + struct device_node *np; + unsigned char *value; + char *name, *end; + int length; + struct property *newprop, *oldprop; + buf = parse_node(buf, bufsize, &np); + end = buf + bufsize; + + if (!np) + return -ENODEV; + + if (parse_next_property(buf, end, &name, &length, &value) == NULL) + return -EINVAL; + + newprop = new_property(name, length, value, NULL); + if (!newprop) + return -ENOMEM; + + oldprop = of_find_property(np, name,NULL); + if (!oldprop) + return -ENODEV; + + return prom_update_property(np, newprop, oldprop); +} + /** * ofdt_write - perform operations on the Open Firmware device tree * @@ -392,6 +486,12 @@ static ssize_t ofdt_write(struct file *file, const char __user *buf, size_t coun rv = do_add_node(tmp, count - (tmp - kbuf)); else if (!strcmp(kbuf, "remove_node")) rv = do_remove_node(tmp); + else if (!strcmp(kbuf, "add_property")) + rv = do_add_property(tmp, count - (tmp - kbuf)); + else if (!strcmp(kbuf, "remove_property")) + rv = do_remove_property(tmp, count - (tmp - kbuf)); + else if (!strcmp(kbuf, "update_property")) + rv = do_update_property(tmp, count - (tmp - kbuf)); else rv = -EINVAL; out: diff --git a/arch/powerpc/platforms/pseries/setup.c b/arch/powerpc/platforms/pseries/setup.c index 68b7f086d63..da6cebaf72c 100644 --- a/arch/powerpc/platforms/pseries/setup.c +++ b/arch/powerpc/platforms/pseries/setup.c @@ -190,7 +190,7 @@ static void pseries_lpar_enable_pmcs(void) /* instruct hypervisor to maintain PMCs */ if (firmware_has_feature(FW_FEATURE_SPLPAR)) - get_paca()->lppaca.pmcregs_in_use = 1; + get_lppaca()->pmcregs_in_use = 1; } static void __init pSeries_setup_arch(void) @@ -234,7 +234,7 @@ static void __init pSeries_setup_arch(void) /* Choose an idle loop */ if (firmware_has_feature(FW_FEATURE_SPLPAR)) { vpa_init(boot_cpuid); - if (get_paca()->lppaca.shared_proc) { + if (get_lppaca()->shared_proc) { printk(KERN_INFO "Using shared processor idle loop\n"); ppc_md.idle_loop = pseries_shared_idle; } else { @@ -444,10 +444,10 @@ DECLARE_PER_CPU(unsigned long, smt_snooze_delay); static inline void dedicated_idle_sleep(unsigned int cpu) { - struct paca_struct *ppaca = &paca[cpu ^ 1]; + struct lppaca *plppaca = &lppaca[cpu ^ 1]; /* Only sleep if the other thread is not idle */ - if (!(ppaca->lppaca.idle)) { + if (!(plppaca->idle)) { local_irq_disable(); /* @@ -480,7 +480,6 @@ static inline void dedicated_idle_sleep(unsigned int cpu) static void pseries_dedicated_idle(void) { - struct paca_struct *lpaca = get_paca(); unsigned int cpu = smp_processor_id(); unsigned long start_snooze; unsigned long *smt_snooze_delay = &__get_cpu_var(smt_snooze_delay); @@ -491,7 +490,7 @@ static void pseries_dedicated_idle(void) * Indicate to the HV that we are idle. Now would be * a good time to find other work to dispatch. */ - lpaca->lppaca.idle = 1; + get_lppaca()->idle = 1; if (!need_resched()) { start_snooze = get_tb() + @@ -518,7 +517,7 @@ static void pseries_dedicated_idle(void) HMT_medium(); } - lpaca->lppaca.idle = 0; + get_lppaca()->idle = 0; ppc64_runlatch_on(); preempt_enable_no_resched(); @@ -532,7 +531,6 @@ static void pseries_dedicated_idle(void) static void pseries_shared_idle(void) { - struct paca_struct *lpaca = get_paca(); unsigned int cpu = smp_processor_id(); while (1) { @@ -540,7 +538,7 @@ static void pseries_shared_idle(void) * Indicate to the HV that we are idle. Now would be * a good time to find other work to dispatch. */ - lpaca->lppaca.idle = 1; + get_lppaca()->idle = 1; while (!need_resched() && !cpu_is_offline(cpu)) { local_irq_disable(); @@ -564,7 +562,7 @@ static void pseries_shared_idle(void) HMT_medium(); } - lpaca->lppaca.idle = 0; + get_lppaca()->idle = 0; ppc64_runlatch_on(); preempt_enable_no_resched(); @@ -588,7 +586,7 @@ static void pseries_kexec_cpu_down(int crash_shutdown, int secondary) { /* Don't risk a hypervisor call if we're crashing */ if (!crash_shutdown) { - unsigned long vpa = __pa(&get_paca()->lppaca); + unsigned long vpa = __pa(get_lppaca()); if (unregister_vpa(hard_smp_processor_id(), vpa)) { printk("VPA deregistration of cpu %u (hw_cpu_id %d) " diff --git a/arch/powerpc/sysdev/Makefile b/arch/powerpc/sysdev/Makefile index 0ae841347a0..4c2b356774e 100644 --- a/arch/powerpc/sysdev/Makefile +++ b/arch/powerpc/sysdev/Makefile @@ -7,3 +7,4 @@ obj-$(CONFIG_40x) += dcr.o obj-$(CONFIG_U3_DART) += dart_iommu.o obj-$(CONFIG_MMIO_NVRAM) += mmio_nvram.o obj-$(CONFIG_PPC_83xx) += ipic.o +obj-$(CONFIG_FSL_SOC) += fsl_soc.o diff --git a/arch/powerpc/sysdev/fsl_soc.c b/arch/powerpc/sysdev/fsl_soc.c new file mode 100644 index 00000000000..064c9de4773 --- /dev/null +++ b/arch/powerpc/sysdev/fsl_soc.c @@ -0,0 +1,317 @@ +/* + * FSL SoC setup code + * + * Maintained by Kumar Gala (see MAINTAINERS for contact information) + * + * This program is free software; you can redistribute it and/or modify it + * under the terms of the GNU General Public License as published by the + * Free Software Foundation; either version 2 of the License, or (at your + * option) any later version. + */ + +#include <linux/config.h> +#include <linux/stddef.h> +#include <linux/kernel.h> +#include <linux/init.h> +#include <linux/errno.h> +#include <linux/major.h> +#include <linux/delay.h> +#include <linux/irq.h> +#include <linux/module.h> +#include <linux/device.h> +#include <linux/platform_device.h> +#include <linux/fsl_devices.h> + +#include <asm/system.h> +#include <asm/atomic.h> +#include <asm/io.h> +#include <asm/irq.h> +#include <asm/prom.h> +#include <sysdev/fsl_soc.h> +#include <mm/mmu_decl.h> + +static phys_addr_t immrbase = -1; + +phys_addr_t get_immrbase(void) +{ + struct device_node *soc; + + if (immrbase != -1) + return immrbase; + + soc = of_find_node_by_type(NULL, "soc"); + if (soc != 0) { + unsigned int size; + void *prop = get_property(soc, "reg", &size); + immrbase = of_translate_address(soc, prop); + of_node_put(soc); + }; + + return immrbase; +} +EXPORT_SYMBOL(get_immrbase); + +static const char * gfar_tx_intr = "tx"; +static const char * gfar_rx_intr = "rx"; +static const char * gfar_err_intr = "error"; + +static int __init gfar_of_init(void) +{ + struct device_node *np; + unsigned int i; + struct platform_device *mdio_dev, *gfar_dev; + struct resource res; + int ret; + + for (np = NULL, i = 0; (np = of_find_compatible_node(np, "mdio", "gianfar")) != NULL; i++) { + int k; + struct device_node *child = NULL; + struct gianfar_mdio_data mdio_data; + + memset(&res, 0, sizeof(res)); + memset(&mdio_data, 0, sizeof(mdio_data)); + + ret = of_address_to_resource(np, 0, &res); + if (ret) + goto mdio_err; + + mdio_dev = platform_device_register_simple("fsl-gianfar_mdio", res.start, &res, 1); + if (IS_ERR(mdio_dev)) { + ret = PTR_ERR(mdio_dev); + goto mdio_err; + } + + for (k = 0; k < 32; k++) + mdio_data.irq[k] = -1; + + while ((child = of_get_next_child(np, child)) != NULL) { + if (child->n_intrs) { + u32 *id = (u32 *) get_property(child, "reg", NULL); + mdio_data.irq[*id] = child->intrs[0].line; + } + } + + ret = platform_device_add_data(mdio_dev, &mdio_data, sizeof(struct gianfar_mdio_data)); + if (ret) + goto mdio_unreg; + } + + for (np = NULL, i = 0; (np = of_find_compatible_node(np, "network", "gianfar")) != NULL; i++) { + struct resource r[4]; + struct device_node *phy, *mdio; + struct gianfar_platform_data gfar_data; + unsigned int *id; + char *model; + void *mac_addr; + phandle *ph; + + memset(r, 0, sizeof(r)); + memset(&gfar_data, 0, sizeof(gfar_data)); + + ret = of_address_to_resource(np, 0, &r[0]); + if (ret) + goto gfar_err; + + r[1].start = np->intrs[0].line; + r[1].end = np->intrs[0].line; + r[1].flags = IORESOURCE_IRQ; + + model = get_property(np, "model", NULL); + + /* If we aren't the FEC we have multiple interrupts */ + if (model && strcasecmp(model, "FEC")) { + r[1].name = gfar_tx_intr; + + r[2].name = gfar_rx_intr; + r[2].start = np->intrs[1].line; + r[2].end = np->intrs[1].line; + r[2].flags = IORESOURCE_IRQ; + + r[3].name = gfar_err_intr; + r[3].start = np->intrs[2].line; + r[3].end = np->intrs[2].line; + r[3].flags = IORESOURCE_IRQ; + } + + gfar_dev = platform_device_register_simple("fsl-gianfar", i, &r[0], np->n_intrs + 1); + + if (IS_ERR(gfar_dev)) { + ret = PTR_ERR(gfar_dev); + goto gfar_err; + } + + mac_addr = get_property(np, "address", NULL); + memcpy(gfar_data.mac_addr, mac_addr, 6); + + if (model && !strcasecmp(model, "TSEC")) + gfar_data.device_flags = + FSL_GIANFAR_DEV_HAS_GIGABIT | + FSL_GIANFAR_DEV_HAS_COALESCE | + FSL_GIANFAR_DEV_HAS_RMON | + FSL_GIANFAR_DEV_HAS_MULTI_INTR; + if (model && !strcasecmp(model, "eTSEC")) + gfar_data.device_flags = + FSL_GIANFAR_DEV_HAS_GIGABIT | + FSL_GIANFAR_DEV_HAS_COALESCE | + FSL_GIANFAR_DEV_HAS_RMON | + FSL_GIANFAR_DEV_HAS_MULTI_INTR | + FSL_GIANFAR_DEV_HAS_CSUM | + FSL_GIANFAR_DEV_HAS_VLAN | + FSL_GIANFAR_DEV_HAS_EXTENDED_HASH; + + ph = (phandle *) get_property(np, "phy-handle", NULL); + phy = of_find_node_by_phandle(*ph); + + if (phy == NULL) { + ret = -ENODEV; + goto gfar_unreg; + } + + mdio = of_get_parent(phy); + + id = (u32 *) get_property(phy, "reg", NULL); + ret = of_address_to_resource(mdio, 0, &res); + if (ret) { + of_node_put(phy); + of_node_put(mdio); + goto gfar_unreg; + } + + gfar_data.phy_id = *id; + gfar_data.bus_id = res.start; + + of_node_put(phy); + of_node_put(mdio); + + ret = platform_device_add_data(gfar_dev, &gfar_data, sizeof(struct gianfar_platform_data)); + if (ret) + goto gfar_unreg; + } + + return 0; + +mdio_unreg: + platform_device_unregister(mdio_dev); +mdio_err: + return ret; + +gfar_unreg: + platform_device_unregister(gfar_dev); +gfar_err: + return ret; +} +arch_initcall(gfar_of_init); + +static int __init fsl_i2c_of_init(void) +{ + struct device_node *np; + unsigned int i; + struct platform_device *i2c_dev; + int ret; + + for (np = NULL, i = 0; (np = of_find_compatible_node(np, "i2c", "fsl-i2c")) != NULL; i++) { + struct resource r[2]; + struct fsl_i2c_platform_data i2c_data; + unsigned char * flags = NULL; + + memset(&r, 0, sizeof(r)); + memset(&i2c_data, 0, sizeof(i2c_data)); + + ret = of_address_to_resource(np, 0, &r[0]); + if (ret) + goto i2c_err; + + r[1].start = np->intrs[0].line; + r[1].end = np->intrs[0].line; + r[1].flags = IORESOURCE_IRQ; + + i2c_dev = platform_device_register_simple("fsl-i2c", i, r, 2); + if (IS_ERR(i2c_dev)) { + ret = PTR_ERR(i2c_dev); + goto i2c_err; + } + + i2c_data.device_flags = 0; + flags = get_property(np, "dfsrr", NULL); + if (flags) + i2c_data.device_flags |= FSL_I2C_DEV_SEPARATE_DFSRR; + + flags = get_property(np, "fsl5200-clocking", NULL); + if (flags) + i2c_data.device_flags |= FSL_I2C_DEV_CLOCK_5200; + + ret = platform_device_add_data(i2c_dev, &i2c_data, sizeof(struct fsl_i2c_platform_data)); + if (ret) + goto i2c_unreg; + } + + return 0; + +i2c_unreg: + platform_device_unregister(i2c_dev); +i2c_err: + return ret; +} +arch_initcall(fsl_i2c_of_init); + +#ifdef CONFIG_PPC_83xx +static int __init mpc83xx_wdt_init(void) +{ + struct resource r; + struct device_node *soc, *np; + struct platform_device *dev; + unsigned int *freq; + int ret; + + np = of_find_compatible_node(NULL, "watchdog", "mpc83xx_wdt"); + + if (!np) { + ret = -ENODEV; + goto mpc83xx_wdt_nodev; + } + + soc = of_find_node_by_type(NULL, "soc"); + + if (!soc) { + ret = -ENODEV; + goto mpc83xx_wdt_nosoc; + } + + freq = (unsigned int *)get_property(soc, "bus-frequency", NULL); + if (!freq) { + ret = -ENODEV; + goto mpc83xx_wdt_err; + } + + memset(&r, 0, sizeof(r)); + + ret = of_address_to_resource(np, 0, &r); + if (ret) + goto mpc83xx_wdt_err; + + dev = platform_device_register_simple("mpc83xx_wdt", 0, &r, 1); + if (IS_ERR(dev)) { + ret = PTR_ERR(dev); + goto mpc83xx_wdt_err; + } + + ret = platform_device_add_data(dev, freq, sizeof(int)); + if (ret) + goto mpc83xx_wdt_unreg; + + of_node_put(soc); + of_node_put(np); + + return 0; + +mpc83xx_wdt_unreg: + platform_device_unregister(dev); +mpc83xx_wdt_err: + of_node_put(soc); +mpc83xx_wdt_nosoc: + of_node_put(np); +mpc83xx_wdt_nodev: + return ret; +} +arch_initcall(mpc83xx_wdt_init); +#endif diff --git a/arch/powerpc/sysdev/fsl_soc.h b/arch/powerpc/sysdev/fsl_soc.h new file mode 100644 index 00000000000..c433d3f39ed --- /dev/null +++ b/arch/powerpc/sysdev/fsl_soc.h @@ -0,0 +1,8 @@ +#ifndef __PPC_FSL_SOC_H +#define __PPC_FSL_SOC_H +#ifdef __KERNEL__ + +extern phys_addr_t get_immrbase(void); + +#endif +#endif diff --git a/arch/ppc/4xx_io/serial_sicc.c b/arch/ppc/4xx_io/serial_sicc.c index ebc4db8fcc6..8ace2a1f3b4 100644 --- a/arch/ppc/4xx_io/serial_sicc.c +++ b/arch/ppc/4xx_io/serial_sicc.c @@ -215,7 +215,6 @@ static struct tty_driver *siccnormal_driver; * memory if large numbers of serial ports are open. */ static u_char *tmp_buf; -static DECLARE_MUTEX(tmp_buf_sem); #define HIGH_BITS_OFFSET ((sizeof(long)-sizeof(int))*8) diff --git a/arch/ppc/kernel/head_8xx.S b/arch/ppc/kernel/head_8xx.S index de097874222..3e6ca7f5843 100644 --- a/arch/ppc/kernel/head_8xx.S +++ b/arch/ppc/kernel/head_8xx.S @@ -375,6 +375,8 @@ DataStoreTLBMiss: lis r11, swapper_pg_dir@h ori r11, r11, swapper_pg_dir@l rlwimi r10, r11, 0, 2, 19 + stw r12, 16(r0) + b LoadLargeDTLB 3: lwz r11, 0(r10) /* Get the level 1 entry */ rlwinm. r10, r11,0,0,19 /* Extract page descriptor page address */ @@ -430,6 +432,81 @@ DataStoreTLBMiss: InstructionTLBError: b InstructionAccess +LoadLargeDTLB: + li r12, 0 + lwz r11, 0(r10) /* Get the level 1 entry */ + rlwinm. r10, r11,0,0,19 /* Extract page descriptor page address */ + beq 3f /* If zero, don't try to find a pte */ + + /* We have a pte table, so load fetch the pte from the table. + */ + ori r11, r11, 1 /* Set valid bit in physical L2 page */ + DO_8xx_CPU6(0x3b80, r3) + mtspr SPRN_MD_TWC, r11 /* Load pte table base address */ + mfspr r10, SPRN_MD_TWC /* ....and get the pte address */ + lwz r10, 0(r10) /* Get the pte */ + + /* Insert the Guarded flag into the TWC from the Linux PTE. + * It is bit 27 of both the Linux PTE and the TWC (at least + * I got that right :-). It will be better when we can put + * this into the Linux pgd/pmd and load it in the operation + * above. + */ + rlwimi r11, r10, 0, 27, 27 + + rlwimi r12, r10, 0, 0, 9 /* extract phys. addr */ + mfspr r3, SPRN_MD_EPN + rlwinm r3, r3, 0, 0, 9 /* extract virtual address */ + tophys(r3, r3) + cmpw r3, r12 /* only use 8M page if it is a direct + kernel mapping */ + bne 1f + ori r11, r11, MD_PS8MEG + li r12, 1 + b 2f +1: + li r12, 0 /* can't use 8MB TLB, so zero r12. */ +2: + DO_8xx_CPU6(0x3b80, r3) + mtspr SPRN_MD_TWC, r11 + + /* The Linux PTE won't go exactly into the MMU TLB. + * Software indicator bits 21, 22 and 28 must be clear. + * Software indicator bits 24, 25, 26, and 27 must be + * set. All other Linux PTE bits control the behavior + * of the MMU. + */ +3: li r11, 0x00f0 + rlwimi r10, r11, 0, 24, 28 /* Set 24-27, clear 28 */ + cmpwi r12, 1 + bne 4f + ori r10, r10, 0x8 + + mfspr r12, SPRN_MD_EPN + lis r3, 0xff80 /* 10-19 must be clear for 8MB TLB */ + ori r3, r3, 0x0fff + and r12, r3, r12 + DO_8xx_CPU6(0x3780, r3) + mtspr SPRN_MD_EPN, r12 + + lis r3, 0xff80 /* 10-19 must be clear for 8MB TLB */ + ori r3, r3, 0x0fff + and r10, r3, r10 +4: + DO_8xx_CPU6(0x3d80, r3) + mtspr SPRN_MD_RPN, r10 /* Update TLB entry */ + + mfspr r10, SPRN_M_TW /* Restore registers */ + lwz r11, 0(r0) + mtcr r11 + lwz r11, 4(r0) + + lwz r12, 16(r0) +#ifdef CONFIG_8xx_CPU6 + lwz r3, 8(r0) +#endif + rfi + /* This is the data TLB error on the MPC8xx. This could be due to * many reasons, including a dirty update to a pte. We can catch that * one here, but anything else is an error. First, we track down the diff --git a/arch/ppc/kernel/ppc_ksyms.c b/arch/ppc/kernel/ppc_ksyms.c index 95075f99a6d..fb0da7c209d 100644 --- a/arch/ppc/kernel/ppc_ksyms.c +++ b/arch/ppc/kernel/ppc_ksyms.c @@ -270,7 +270,6 @@ EXPORT_SYMBOL(__delay); EXPORT_SYMBOL(timer_interrupt); EXPORT_SYMBOL(irq_desc); EXPORT_SYMBOL(tb_ticks_per_jiffy); -EXPORT_SYMBOL(get_wchan); EXPORT_SYMBOL(console_drivers); #ifdef CONFIG_XMON EXPORT_SYMBOL(xmon); diff --git a/arch/ppc/platforms/83xx/mpc834x_sys.c b/arch/ppc/platforms/83xx/mpc834x_sys.c index 04bdc39bf47..012e1e652c0 100644 --- a/arch/ppc/platforms/83xx/mpc834x_sys.c +++ b/arch/ppc/platforms/83xx/mpc834x_sys.c @@ -51,9 +51,6 @@ #include <syslib/ppc83xx_setup.h> -static const char *GFAR_PHY_0 = "phy0:0"; -static const char *GFAR_PHY_1 = "phy0:1"; - #ifndef CONFIG_PCI unsigned long isa_io_base = 0; unsigned long isa_mem_base = 0; @@ -129,20 +126,21 @@ mpc834x_sys_setup_arch(void) mdata->irq[1] = MPC83xx_IRQ_EXT2; mdata->irq[2] = -1; mdata->irq[31] = -1; - mdata->paddr += binfo->bi_immr_base; /* setup the board related information for the enet controllers */ pdata = (struct gianfar_platform_data *) ppc_sys_get_pdata(MPC83xx_TSEC1); if (pdata) { pdata->board_flags = FSL_GIANFAR_BRD_HAS_PHY_INTR; - pdata->bus_id = GFAR_PHY_0; + pdata->bus_id = 0; + pdata->phy_id = 0; memcpy(pdata->mac_addr, binfo->bi_enetaddr, 6); } pdata = (struct gianfar_platform_data *) ppc_sys_get_pdata(MPC83xx_TSEC2); if (pdata) { pdata->board_flags = FSL_GIANFAR_BRD_HAS_PHY_INTR; - pdata->bus_id = GFAR_PHY_1; + pdata->bus_id = 0; + pdata->phy_id = 1; memcpy(pdata->mac_addr, binfo->bi_enet1addr, 6); } diff --git a/arch/ppc/platforms/85xx/mpc8540_ads.c b/arch/ppc/platforms/85xx/mpc8540_ads.c index c5cde97c6ef..2eceb1e6f4e 100644 --- a/arch/ppc/platforms/85xx/mpc8540_ads.c +++ b/arch/ppc/platforms/85xx/mpc8540_ads.c @@ -52,10 +52,6 @@ #include <syslib/ppc85xx_setup.h> -static const char *GFAR_PHY_0 = "phy0:0"; -static const char *GFAR_PHY_1 = "phy0:1"; -static const char *GFAR_PHY_3 = "phy0:3"; - /* ************************************************************************ * * Setup the architecture @@ -102,27 +98,29 @@ mpc8540ads_setup_arch(void) mdata->irq[2] = -1; mdata->irq[3] = MPC85xx_IRQ_EXT5; mdata->irq[31] = -1; - mdata->paddr += binfo->bi_immr_base; /* setup the board related information for the enet controllers */ pdata = (struct gianfar_platform_data *) ppc_sys_get_pdata(MPC85xx_TSEC1); if (pdata) { pdata->board_flags = FSL_GIANFAR_BRD_HAS_PHY_INTR; - pdata->bus_id = GFAR_PHY_0; + pdata->bus_id = 0; + pdata->phy_id = 0; memcpy(pdata->mac_addr, binfo->bi_enetaddr, 6); } pdata = (struct gianfar_platform_data *) ppc_sys_get_pdata(MPC85xx_TSEC2); if (pdata) { pdata->board_flags = FSL_GIANFAR_BRD_HAS_PHY_INTR; - pdata->bus_id = GFAR_PHY_1; + pdata->bus_id = 0; + pdata->phy_id = 1; memcpy(pdata->mac_addr, binfo->bi_enet1addr, 6); } pdata = (struct gianfar_platform_data *) ppc_sys_get_pdata(MPC85xx_FEC); if (pdata) { pdata->board_flags = 0; - pdata->bus_id = GFAR_PHY_3; + pdata->bus_id = 0; + pdata->phy_id = 3; memcpy(pdata->mac_addr, binfo->bi_enet2addr, 6); } diff --git a/arch/ppc/platforms/85xx/mpc8560_ads.c b/arch/ppc/platforms/85xx/mpc8560_ads.c index 8e39a551709..442c7ff195d 100644 --- a/arch/ppc/platforms/85xx/mpc8560_ads.c +++ b/arch/ppc/platforms/85xx/mpc8560_ads.c @@ -56,10 +56,6 @@ #include <syslib/ppc85xx_setup.h> -static const char *GFAR_PHY_0 = "phy0:0"; -static const char *GFAR_PHY_1 = "phy0:1"; -static const char *GFAR_PHY_3 = "phy0:3"; - /* ************************************************************************ * * Setup the architecture @@ -99,20 +95,21 @@ mpc8560ads_setup_arch(void) mdata->irq[2] = -1; mdata->irq[3] = MPC85xx_IRQ_EXT5; mdata->irq[31] = -1; - mdata->paddr += binfo->bi_immr_base; /* setup the board related information for the enet controllers */ pdata = (struct gianfar_platform_data *) ppc_sys_get_pdata(MPC85xx_TSEC1); if (pdata) { pdata->board_flags = FSL_GIANFAR_BRD_HAS_PHY_INTR; - pdata->bus_id = GFAR_PHY_0; + pdata->bus_id = 0; + pdata->phy_id = 0; memcpy(pdata->mac_addr, binfo->bi_enetaddr, 6); } pdata = (struct gianfar_platform_data *) ppc_sys_get_pdata(MPC85xx_TSEC2); if (pdata) { pdata->board_flags = FSL_GIANFAR_BRD_HAS_PHY_INTR; - pdata->bus_id = GFAR_PHY_1; + pdata->bus_id = 0; + pdata->phy_id = 1; memcpy(pdata->mac_addr, binfo->bi_enet1addr, 6); } diff --git a/arch/ppc/platforms/85xx/mpc85xx_cds_common.c b/arch/ppc/platforms/85xx/mpc85xx_cds_common.c index 2959e3c4083..b332ebae6bd 100644 --- a/arch/ppc/platforms/85xx/mpc85xx_cds_common.c +++ b/arch/ppc/platforms/85xx/mpc85xx_cds_common.c @@ -395,9 +395,6 @@ mpc85xx_cds_pcibios_fixup(void) TODC_ALLOC(); -static const char *GFAR_PHY_0 = "phy0:0"; -static const char *GFAR_PHY_1 = "phy0:1"; - /* ************************************************************************ * * Setup the architecture @@ -461,34 +458,37 @@ mpc85xx_cds_setup_arch(void) mdata->irq[2] = -1; mdata->irq[3] = -1; mdata->irq[31] = -1; - mdata->paddr += binfo->bi_immr_base; /* setup the board related information for the enet controllers */ pdata = (struct gianfar_platform_data *) ppc_sys_get_pdata(MPC85xx_TSEC1); if (pdata) { pdata->board_flags = FSL_GIANFAR_BRD_HAS_PHY_INTR; - pdata->bus_id = GFAR_PHY_0; + pdata->bus_id = 0; + pdata->phy_id = 0; memcpy(pdata->mac_addr, binfo->bi_enetaddr, 6); } pdata = (struct gianfar_platform_data *) ppc_sys_get_pdata(MPC85xx_TSEC2); if (pdata) { pdata->board_flags = FSL_GIANFAR_BRD_HAS_PHY_INTR; - pdata->bus_id = GFAR_PHY_1; + pdata->bus_id = 0; + pdata->phy_id = 1; memcpy(pdata->mac_addr, binfo->bi_enet1addr, 6); } pdata = (struct gianfar_platform_data *) ppc_sys_get_pdata(MPC85xx_eTSEC1); if (pdata) { pdata->board_flags = FSL_GIANFAR_BRD_HAS_PHY_INTR; - pdata->bus_id = GFAR_PHY_0; + pdata->bus_id = 0; + pdata->phy_id = 0; memcpy(pdata->mac_addr, binfo->bi_enetaddr, 6); } pdata = (struct gianfar_platform_data *) ppc_sys_get_pdata(MPC85xx_eTSEC2); if (pdata) { pdata->board_flags = FSL_GIANFAR_BRD_HAS_PHY_INTR; - pdata->bus_id = GFAR_PHY_1; + pdata->bus_id = 0; + pdata->phy_id = 1; memcpy(pdata->mac_addr, binfo->bi_enet1addr, 6); } diff --git a/arch/ppc/platforms/85xx/sbc8560.c b/arch/ppc/platforms/85xx/sbc8560.c index 45a5b81b4ed..e777ba824aa 100644 --- a/arch/ppc/platforms/85xx/sbc8560.c +++ b/arch/ppc/platforms/85xx/sbc8560.c @@ -91,9 +91,6 @@ sbc8560_early_serial_map(void) } #endif -static const char *GFAR_PHY_25 = "phy0:25"; -static const char *GFAR_PHY_26 = "phy0:26"; - /* ************************************************************************ * * Setup the architecture @@ -136,20 +133,21 @@ sbc8560_setup_arch(void) mdata->irq[25] = MPC85xx_IRQ_EXT6; mdata->irq[26] = MPC85xx_IRQ_EXT7; mdata->irq[31] = -1; - mdata->paddr += binfo->bi_immr_base; /* setup the board related information for the enet controllers */ pdata = (struct gianfar_platform_data *) ppc_sys_get_pdata(MPC85xx_TSEC1); if (pdata) { pdata->board_flags = FSL_GIANFAR_BRD_HAS_PHY_INTR; - pdata->bus_id = GFAR_PHY_25; + pdata->bus_id = 0; + pdata->phy_id = 25; memcpy(pdata->mac_addr, binfo->bi_enetaddr, 6); } pdata = (struct gianfar_platform_data *) ppc_sys_get_pdata(MPC85xx_TSEC2); if (pdata) { pdata->board_flags = FSL_GIANFAR_BRD_HAS_PHY_INTR; - pdata->bus_id = GFAR_PHY_26; + pdata->bus_id = 0; + pdata->phy_id = 26; memcpy(pdata->mac_addr, binfo->bi_enet1addr, 6); } diff --git a/arch/ppc/platforms/85xx/stx_gp3.c b/arch/ppc/platforms/85xx/stx_gp3.c index 15ce9d07063..061bb7cf2d9 100644 --- a/arch/ppc/platforms/85xx/stx_gp3.c +++ b/arch/ppc/platforms/85xx/stx_gp3.c @@ -93,9 +93,6 @@ static u8 gp3_openpic_initsenses[] __initdata = { 0x0, /* External 11: */ }; -static const char *GFAR_PHY_2 = "phy0:2"; -static const char *GFAR_PHY_4 = "phy0:4"; - /* * Setup the architecture */ @@ -130,20 +127,21 @@ gp3_setup_arch(void) mdata->irq[2] = MPC85xx_IRQ_EXT5; mdata->irq[4] = MPC85xx_IRQ_EXT5; mdata->irq[31] = -1; - mdata->paddr += binfo->bi_immr_base; /* setup the board related information for the enet controllers */ pdata = (struct gianfar_platform_data *) ppc_sys_get_pdata(MPC85xx_TSEC1); if (pdata) { /* pdata->board_flags = FSL_GIANFAR_BRD_HAS_PHY_INTR; */ - pdata->bus_id = GFAR_PHY_2; + pdata->bus_id = 0; + pdata->phy_id = 2; memcpy(pdata->mac_addr, binfo->bi_enetaddr, 6); } pdata = (struct gianfar_platform_data *) ppc_sys_get_pdata(MPC85xx_TSEC2); if (pdata) { /* pdata->board_flags = FSL_GIANFAR_BRD_HAS_PHY_INTR; */ - pdata->bus_id = GFAR_PHY_4; + pdata->bus_id = 0; + pdata->phy_id = 4; memcpy(pdata->mac_addr, binfo->bi_enet1addr, 6); } diff --git a/arch/ppc/platforms/85xx/tqm85xx.c b/arch/ppc/platforms/85xx/tqm85xx.c index c6dfd8f0f9d..b436f4d0a3f 100644 --- a/arch/ppc/platforms/85xx/tqm85xx.c +++ b/arch/ppc/platforms/85xx/tqm85xx.c @@ -91,12 +91,6 @@ static u_char tqm85xx_openpic_initsenses[] __initdata = { 0x0, /* External 11: */ }; -static const char *GFAR_PHY_0 = "phy0:2"; -static const char *GFAR_PHY_1 = "phy0:1"; -#ifdef CONFIG_MPC8540 -static const char *GFAR_PHY_3 = "phy0:3"; -#endif - /* ************************************************************************ * * Setup the architecture @@ -149,20 +143,21 @@ tqm85xx_setup_arch(void) mdata->irq[2] = -1; mdata->irq[3] = MPC85xx_IRQ_EXT8; mdata->irq[31] = -1; - mdata->paddr += binfo->bi_immr_base; /* setup the board related information for the enet controllers */ pdata = (struct gianfar_platform_data *) ppc_sys_get_pdata(MPC85xx_TSEC1); if (pdata) { pdata->board_flags = FSL_GIANFAR_BRD_HAS_PHY_INTR; - pdata->bus_id = GFAR_PHY_0; + pdata->bus_id = 0; + pdata->phy_id = 2; memcpy(pdata->mac_addr, binfo->bi_enetaddr, 6); } pdata = (struct gianfar_platform_data *) ppc_sys_get_pdata(MPC85xx_TSEC2); if (pdata) { pdata->board_flags = FSL_GIANFAR_BRD_HAS_PHY_INTR; - pdata->bus_id = GFAR_PHY_1; + pdata->bus_id = 0; + pdata->phy_id = 1; memcpy(pdata->mac_addr, binfo->bi_enet1addr, 6); } @@ -170,7 +165,8 @@ tqm85xx_setup_arch(void) pdata = (struct gianfar_platform_data *) ppc_sys_get_pdata(MPC85xx_FEC); if (pdata) { pdata->board_flags = 0; - pdata->bus_id = GFAR_PHY_3; + pdata->bus_id = 0; + pdata->phy_id = 3; memcpy(pdata->mac_addr, binfo->bi_enet2addr, 6); } #endif diff --git a/arch/ppc/syslib/mpc83xx_devices.c b/arch/ppc/syslib/mpc83xx_devices.c index 847df440998..f9b95de70e2 100644 --- a/arch/ppc/syslib/mpc83xx_devices.c +++ b/arch/ppc/syslib/mpc83xx_devices.c @@ -28,7 +28,6 @@ */ struct gianfar_mdio_data mpc83xx_mdio_pdata = { - .paddr = 0x24520, }; static struct gianfar_platform_data mpc83xx_tsec1_pdata = { @@ -226,7 +225,14 @@ struct platform_device ppc_sys_platform_devices[] = { .name = "fsl-gianfar_mdio", .id = 0, .dev.platform_data = &mpc83xx_mdio_pdata, - .num_resources = 0, + .num_resources = 1, + .resource = (struct resource[]) { + { + .start = 0x24520, + .end = 0x2453f, + .flags = IORESOURCE_MEM, + }, + }, }, }; diff --git a/arch/ppc/syslib/mpc85xx_devices.c b/arch/ppc/syslib/mpc85xx_devices.c index 69949d25565..00e9b6ff2f6 100644 --- a/arch/ppc/syslib/mpc85xx_devices.c +++ b/arch/ppc/syslib/mpc85xx_devices.c @@ -26,7 +26,6 @@ * what CCSRBAR is, will get fixed up by mach_mpc85xx_fixup */ struct gianfar_mdio_data mpc85xx_mdio_pdata = { - .paddr = MPC85xx_MIIM_OFFSET, }; static struct gianfar_platform_data mpc85xx_tsec1_pdata = { @@ -720,7 +719,14 @@ struct platform_device ppc_sys_platform_devices[] = { .name = "fsl-gianfar_mdio", .id = 0, .dev.platform_data = &mpc85xx_mdio_pdata, - .num_resources = 0, + .num_resources = 1, + .resource = (struct resource[]) { + { + .start = 0x24520, + .end = 0x2453f, + .flags = IORESOURCE_MEM, + }, + }, }, }; diff --git a/drivers/char/amiserial.c b/drivers/char/amiserial.c index 667a21c72ed..7ac365b5d9e 100644 --- a/drivers/char/amiserial.c +++ b/drivers/char/amiserial.c @@ -129,7 +129,6 @@ static struct serial_state rs_table[1]; * memory if large numbers of serial ports are open. */ static unsigned char *tmp_buf; -static DECLARE_MUTEX(tmp_buf_sem); #include <asm/uaccess.h> diff --git a/drivers/char/esp.c b/drivers/char/esp.c index e469f641c72..dd5dc8fa490 100644 --- a/drivers/char/esp.c +++ b/drivers/char/esp.c @@ -160,7 +160,6 @@ static void rs_wait_until_sent(struct tty_struct *, int); * memory if large numbers of serial ports are open. */ static unsigned char *tmp_buf; -static DECLARE_MUTEX(tmp_buf_sem); static inline int serial_paranoia_check(struct esp_struct *info, char *name, const char *routine) diff --git a/drivers/char/generic_serial.c b/drivers/char/generic_serial.c index 204a7302a4a..e38a5f0e07b 100644 --- a/drivers/char/generic_serial.c +++ b/drivers/char/generic_serial.c @@ -34,7 +34,6 @@ #define DEBUG static char * tmp_buf; -static DECLARE_MUTEX(tmp_buf_sem); static int gs_debug; diff --git a/drivers/char/riscom8.c b/drivers/char/riscom8.c index 050e70ee592..119e629656b 100644 --- a/drivers/char/riscom8.c +++ b/drivers/char/riscom8.c @@ -82,7 +82,6 @@ static struct riscom_board * IRQ_to_board[16]; static struct tty_driver *riscom_driver; static unsigned char * tmp_buf; -static DECLARE_MUTEX(tmp_buf_sem); static unsigned long baud_table[] = { 0, 50, 75, 110, 134, 150, 200, 300, 600, 1200, 1800, 2400, 4800, diff --git a/drivers/char/serial167.c b/drivers/char/serial167.c index f36342ae8e7..037c940ac71 100644 --- a/drivers/char/serial167.c +++ b/drivers/char/serial167.c @@ -129,7 +129,6 @@ struct cyclades_port cy_port[] = { * memory if large numbers of serial ports are open. */ static unsigned char *tmp_buf = 0; -DECLARE_MUTEX(tmp_buf_sem); /* * This is used to look up the divisor speeds and the timeouts diff --git a/drivers/char/specialix.c b/drivers/char/specialix.c index 0a574bdbce3..5343e9fc6ab 100644 --- a/drivers/char/specialix.c +++ b/drivers/char/specialix.c @@ -184,7 +184,6 @@ static int sx_poll = HZ; static struct tty_driver *specialix_driver; static unsigned char * tmp_buf; -static DECLARE_MUTEX(tmp_buf_sem); static unsigned long baud_table[] = { 0, 50, 75, 110, 134, 150, 200, 300, 600, 1200, 1800, 2400, 4800, @@ -2556,8 +2555,6 @@ static int __init specialix_init_module(void) func_enter(); - init_MUTEX(&tmp_buf_sem); /* Init de the semaphore - pvdl */ - if (iobase[0] || iobase[1] || iobase[2] || iobase[3]) { for(i = 0; i < SX_NBOARD; i++) { sx_board[i].base = iobase[i]; diff --git a/drivers/char/synclink.c b/drivers/char/synclink.c index 9f1b466c4f8..ede688a4e14 100644 --- a/drivers/char/synclink.c +++ b/drivers/char/synclink.c @@ -951,7 +951,6 @@ static void* mgsl_get_text_ptr(void) * memory if large numbers of serial ports are open. */ static unsigned char *tmp_buf; -static DECLARE_MUTEX(tmp_buf_sem); static inline int mgsl_paranoia_check(struct mgsl_struct *info, char *name, const char *routine) diff --git a/drivers/infiniband/core/cm.c b/drivers/infiniband/core/cm.c index 3a611fe5497..c06b18102b6 100644 --- a/drivers/infiniband/core/cm.c +++ b/drivers/infiniband/core/cm.c @@ -3163,22 +3163,6 @@ int ib_cm_init_qp_attr(struct ib_cm_id *cm_id, } EXPORT_SYMBOL(ib_cm_init_qp_attr); -static __be64 cm_get_ca_guid(struct ib_device *device) -{ - struct ib_device_attr *device_attr; - __be64 guid; - int ret; - - device_attr = kmalloc(sizeof *device_attr, GFP_KERNEL); - if (!device_attr) - return 0; - - ret = ib_query_device(device, device_attr); - guid = ret ? 0 : device_attr->node_guid; - kfree(device_attr); - return guid; -} - static void cm_add_one(struct ib_device *device) { struct cm_device *cm_dev; @@ -3200,9 +3184,7 @@ static void cm_add_one(struct ib_device *device) return; cm_dev->device = device; - cm_dev->ca_guid = cm_get_ca_guid(device); - if (!cm_dev->ca_guid) - goto error1; + cm_dev->ca_guid = device->node_guid; set_bit(IB_MGMT_METHOD_SEND, reg_req.method_mask); for (i = 1; i <= device->phys_port_cnt; i++) { @@ -3217,11 +3199,11 @@ static void cm_add_one(struct ib_device *device) cm_recv_handler, port); if (IS_ERR(port->mad_agent)) - goto error2; + goto error1; ret = ib_modify_port(device, i, 0, &port_modify); if (ret) - goto error3; + goto error2; } ib_set_client_data(device, &cm_client, cm_dev); @@ -3230,9 +3212,9 @@ static void cm_add_one(struct ib_device *device) write_unlock_irqrestore(&cm.device_lock, flags); return; -error3: - ib_unregister_mad_agent(port->mad_agent); error2: + ib_unregister_mad_agent(port->mad_agent); +error1: port_modify.set_port_cap_mask = 0; port_modify.clr_port_cap_mask = IB_PORT_CM_SUP; while (--i) { @@ -3240,7 +3222,6 @@ error2: ib_modify_port(device, port->port_num, 0, &port_modify); ib_unregister_mad_agent(port->mad_agent); } -error1: kfree(cm_dev); } diff --git a/drivers/infiniband/core/device.c b/drivers/infiniband/core/device.c index e169e798354..b2f3cb91d9b 100644 --- a/drivers/infiniband/core/device.c +++ b/drivers/infiniband/core/device.c @@ -38,8 +38,7 @@ #include <linux/errno.h> #include <linux/slab.h> #include <linux/init.h> - -#include <asm/semaphore.h> +#include <linux/mutex.h> #include "core_priv.h" @@ -57,13 +56,13 @@ static LIST_HEAD(device_list); static LIST_HEAD(client_list); /* - * device_sem protects access to both device_list and client_list. + * device_mutex protects access to both device_list and client_list. * There's no real point to using multiple locks or something fancier * like an rwsem: we always access both lists, and we're always * modifying one list or the other list. In any case this is not a * hot path so there's no point in trying to optimize. */ -static DECLARE_MUTEX(device_sem); +static DEFINE_MUTEX(device_mutex); static int ib_device_check_mandatory(struct ib_device *device) { @@ -221,7 +220,7 @@ int ib_register_device(struct ib_device *device) { int ret; - down(&device_sem); + mutex_lock(&device_mutex); if (strchr(device->name, '%')) { ret = alloc_name(device->name); @@ -259,7 +258,7 @@ int ib_register_device(struct ib_device *device) } out: - up(&device_sem); + mutex_unlock(&device_mutex); return ret; } EXPORT_SYMBOL(ib_register_device); @@ -276,7 +275,7 @@ void ib_unregister_device(struct ib_device *device) struct ib_client_data *context, *tmp; unsigned long flags; - down(&device_sem); + mutex_lock(&device_mutex); list_for_each_entry_reverse(client, &client_list, list) if (client->remove) @@ -284,7 +283,7 @@ void ib_unregister_device(struct ib_device *device) list_del(&device->core_list); - up(&device_sem); + mutex_unlock(&device_mutex); spin_lock_irqsave(&device->client_data_lock, flags); list_for_each_entry_safe(context, tmp, &device->client_data_list, list) @@ -312,14 +311,14 @@ int ib_register_client(struct ib_client *client) { struct ib_device *device; - down(&device_sem); + mutex_lock(&device_mutex); list_add_tail(&client->list, &client_list); list_for_each_entry(device, &device_list, core_list) if (client->add && !add_client_context(device, client)) client->add(device); - up(&device_sem); + mutex_unlock(&device_mutex); return 0; } @@ -339,7 +338,7 @@ void ib_unregister_client(struct ib_client *client) struct ib_device *device; unsigned long flags; - down(&device_sem); + mutex_lock(&device_mutex); list_for_each_entry(device, &device_list, core_list) { if (client->remove) @@ -355,7 +354,7 @@ void ib_unregister_client(struct ib_client *client) } list_del(&client->list); - up(&device_sem); + mutex_unlock(&device_mutex); } EXPORT_SYMBOL(ib_unregister_client); diff --git a/drivers/infiniband/core/sysfs.c b/drivers/infiniband/core/sysfs.c index 1f1743c5c9a..5982d687a00 100644 --- a/drivers/infiniband/core/sysfs.c +++ b/drivers/infiniband/core/sysfs.c @@ -445,13 +445,7 @@ static int ib_device_uevent(struct class_device *cdev, char **envp, return -ENOMEM; /* - * It might be nice to pass the node GUID with the event, but - * right now the only way to get it is to query the device - * provider, and this can crash during device removal because - * we are will be running after driver removal has started. - * We could add a node_guid field to struct ib_device, or we - * could just let userspace read the node GUID from sysfs when - * devices are added. + * It would be nice to pass the node GUID with the event... */ envp[i] = NULL; @@ -623,21 +617,15 @@ static ssize_t show_sys_image_guid(struct class_device *cdev, char *buf) static ssize_t show_node_guid(struct class_device *cdev, char *buf) { struct ib_device *dev = container_of(cdev, struct ib_device, class_dev); - struct ib_device_attr attr; - ssize_t ret; if (!ibdev_is_alive(dev)) return -ENODEV; - ret = ib_query_device(dev, &attr); - if (ret) - return ret; - return sprintf(buf, "%04x:%04x:%04x:%04x\n", - be16_to_cpu(((__be16 *) &attr.node_guid)[0]), - be16_to_cpu(((__be16 *) &attr.node_guid)[1]), - be16_to_cpu(((__be16 *) &attr.node_guid)[2]), - be16_to_cpu(((__be16 *) &attr.node_guid)[3])); + be16_to_cpu(((__be16 *) &dev->node_guid)[0]), + be16_to_cpu(((__be16 *) &dev->node_guid)[1]), + be16_to_cpu(((__be16 *) &dev->node_guid)[2]), + be16_to_cpu(((__be16 *) &dev->node_guid)[3])); } static CLASS_DEVICE_ATTR(node_type, S_IRUGO, show_node_type, NULL); diff --git a/drivers/infiniband/core/ucm.c b/drivers/infiniband/core/ucm.c index 6e15787d1de..e95c4293a49 100644 --- a/drivers/infiniband/core/ucm.c +++ b/drivers/infiniband/core/ucm.c @@ -42,6 +42,7 @@ #include <linux/mount.h> #include <linux/cdev.h> #include <linux/idr.h> +#include <linux/mutex.h> #include <asm/uaccess.h> @@ -113,7 +114,7 @@ static struct ib_client ucm_client = { .remove = ib_ucm_remove_one }; -static DECLARE_MUTEX(ctx_id_mutex); +static DEFINE_MUTEX(ctx_id_mutex); static DEFINE_IDR(ctx_id_table); static DECLARE_BITMAP(dev_map, IB_UCM_MAX_DEVICES); @@ -121,7 +122,7 @@ static struct ib_ucm_context *ib_ucm_ctx_get(struct ib_ucm_file *file, int id) { struct ib_ucm_context *ctx; - down(&ctx_id_mutex); + mutex_lock(&ctx_id_mutex); ctx = idr_find(&ctx_id_table, id); if (!ctx) ctx = ERR_PTR(-ENOENT); @@ -129,7 +130,7 @@ static struct ib_ucm_context *ib_ucm_ctx_get(struct ib_ucm_file *file, int id) ctx = ERR_PTR(-EINVAL); else atomic_inc(&ctx->ref); - up(&ctx_id_mutex); + mutex_unlock(&ctx_id_mutex); return ctx; } @@ -186,9 +187,9 @@ static struct ib_ucm_context *ib_ucm_ctx_alloc(struct ib_ucm_file *file) if (!result) goto error; - down(&ctx_id_mutex); + mutex_lock(&ctx_id_mutex); result = idr_get_new(&ctx_id_table, ctx, &ctx->id); - up(&ctx_id_mutex); + mutex_unlock(&ctx_id_mutex); } while (result == -EAGAIN); if (result) @@ -550,9 +551,9 @@ static ssize_t ib_ucm_create_id(struct ib_ucm_file *file, err2: ib_destroy_cm_id(ctx->cm_id); err1: - down(&ctx_id_mutex); + mutex_lock(&ctx_id_mutex); idr_remove(&ctx_id_table, ctx->id); - up(&ctx_id_mutex); + mutex_unlock(&ctx_id_mutex); kfree(ctx); return result; } @@ -572,7 +573,7 @@ static ssize_t ib_ucm_destroy_id(struct ib_ucm_file *file, if (copy_from_user(&cmd, inbuf, sizeof(cmd))) return -EFAULT; - down(&ctx_id_mutex); + mutex_lock(&ctx_id_mutex); ctx = idr_find(&ctx_id_table, cmd.id); if (!ctx) ctx = ERR_PTR(-ENOENT); @@ -580,7 +581,7 @@ static ssize_t ib_ucm_destroy_id(struct ib_ucm_file *file, ctx = ERR_PTR(-EINVAL); else idr_remove(&ctx_id_table, ctx->id); - up(&ctx_id_mutex); + mutex_unlock(&ctx_id_mutex); if (IS_ERR(ctx)) return PTR_ERR(ctx); @@ -1280,9 +1281,9 @@ static int ib_ucm_close(struct inode *inode, struct file *filp) struct ib_ucm_context, file_list); up(&file->mutex); - down(&ctx_id_mutex); + mutex_lock(&ctx_id_mutex); idr_remove(&ctx_id_table, ctx->id); - up(&ctx_id_mutex); + mutex_unlock(&ctx_id_mutex); ib_destroy_cm_id(ctx->cm_id); ib_ucm_cleanup_events(ctx); diff --git a/drivers/infiniband/core/uverbs.h b/drivers/infiniband/core/uverbs.h index 7114e3fbab0..f7eecbc6af6 100644 --- a/drivers/infiniband/core/uverbs.h +++ b/drivers/infiniband/core/uverbs.h @@ -41,6 +41,7 @@ #include <linux/kref.h> #include <linux/idr.h> +#include <linux/mutex.h> #include <rdma/ib_verbs.h> #include <rdma/ib_user_verbs.h> @@ -88,7 +89,7 @@ struct ib_uverbs_event_file { struct ib_uverbs_file { struct kref ref; - struct semaphore mutex; + struct mutex mutex; struct ib_uverbs_device *device; struct ib_ucontext *ucontext; struct ib_event_handler event_handler; @@ -131,7 +132,7 @@ struct ib_ucq_object { u32 async_events_reported; }; -extern struct semaphore ib_uverbs_idr_mutex; +extern struct mutex ib_uverbs_idr_mutex; extern struct idr ib_uverbs_pd_idr; extern struct idr ib_uverbs_mr_idr; extern struct idr ib_uverbs_mw_idr; diff --git a/drivers/infiniband/core/uverbs_cmd.c b/drivers/infiniband/core/uverbs_cmd.c index a02c5a05c98..407b6284d7d 100644 --- a/drivers/infiniband/core/uverbs_cmd.c +++ b/drivers/infiniband/core/uverbs_cmd.c @@ -67,7 +67,7 @@ ssize_t ib_uverbs_get_context(struct ib_uverbs_file *file, if (copy_from_user(&cmd, buf, sizeof cmd)) return -EFAULT; - down(&file->mutex); + mutex_lock(&file->mutex); if (file->ucontext) { ret = -EINVAL; @@ -119,7 +119,7 @@ ssize_t ib_uverbs_get_context(struct ib_uverbs_file *file, fd_install(resp.async_fd, filp); - up(&file->mutex); + mutex_unlock(&file->mutex); return in_len; @@ -131,7 +131,7 @@ err_free: ibdev->dealloc_ucontext(ucontext); err: - up(&file->mutex); + mutex_unlock(&file->mutex); return ret; } @@ -157,7 +157,7 @@ ssize_t ib_uverbs_query_device(struct ib_uverbs_file *file, memset(&resp, 0, sizeof resp); resp.fw_ver = attr.fw_ver; - resp.node_guid = attr.node_guid; + resp.node_guid = file->device->ib_dev->node_guid; resp.sys_image_guid = attr.sys_image_guid; resp.max_mr_size = attr.max_mr_size; resp.page_size_cap = attr.page_size_cap; @@ -290,7 +290,7 @@ ssize_t ib_uverbs_alloc_pd(struct ib_uverbs_file *file, pd->uobject = uobj; atomic_set(&pd->usecnt, 0); - down(&ib_uverbs_idr_mutex); + mutex_lock(&ib_uverbs_idr_mutex); retry: if (!idr_pre_get(&ib_uverbs_pd_idr, GFP_KERNEL)) { @@ -314,11 +314,11 @@ retry: goto err_idr; } - down(&file->mutex); + mutex_lock(&file->mutex); list_add_tail(&uobj->list, &file->ucontext->pd_list); - up(&file->mutex); + mutex_unlock(&file->mutex); - up(&ib_uverbs_idr_mutex); + mutex_unlock(&ib_uverbs_idr_mutex); return in_len; @@ -326,7 +326,7 @@ err_idr: idr_remove(&ib_uverbs_pd_idr, uobj->id); err_up: - up(&ib_uverbs_idr_mutex); + mutex_unlock(&ib_uverbs_idr_mutex); ib_dealloc_pd(pd); err: @@ -346,7 +346,7 @@ ssize_t ib_uverbs_dealloc_pd(struct ib_uverbs_file *file, if (copy_from_user(&cmd, buf, sizeof cmd)) return -EFAULT; - down(&ib_uverbs_idr_mutex); + mutex_lock(&ib_uverbs_idr_mutex); pd = idr_find(&ib_uverbs_pd_idr, cmd.pd_handle); if (!pd || pd->uobject->context != file->ucontext) @@ -360,14 +360,14 @@ ssize_t ib_uverbs_dealloc_pd(struct ib_uverbs_file *file, idr_remove(&ib_uverbs_pd_idr, cmd.pd_handle); - down(&file->mutex); + mutex_lock(&file->mutex); list_del(&uobj->list); - up(&file->mutex); + mutex_unlock(&file->mutex); kfree(uobj); out: - up(&ib_uverbs_idr_mutex); + mutex_unlock(&ib_uverbs_idr_mutex); return ret ? ret : in_len; } @@ -426,7 +426,7 @@ ssize_t ib_uverbs_reg_mr(struct ib_uverbs_file *file, obj->umem.virt_base = cmd.hca_va; - down(&ib_uverbs_idr_mutex); + mutex_lock(&ib_uverbs_idr_mutex); pd = idr_find(&ib_uverbs_pd_idr, cmd.pd_handle); if (!pd || pd->uobject->context != file->ucontext) { @@ -476,11 +476,11 @@ retry: goto err_idr; } - down(&file->mutex); + mutex_lock(&file->mutex); list_add_tail(&obj->uobject.list, &file->ucontext->mr_list); - up(&file->mutex); + mutex_unlock(&file->mutex); - up(&ib_uverbs_idr_mutex); + mutex_unlock(&ib_uverbs_idr_mutex); return in_len; @@ -492,7 +492,7 @@ err_unreg: atomic_dec(&pd->usecnt); err_up: - up(&ib_uverbs_idr_mutex); + mutex_unlock(&ib_uverbs_idr_mutex); ib_umem_release(file->device->ib_dev, &obj->umem); @@ -513,7 +513,7 @@ ssize_t ib_uverbs_dereg_mr(struct ib_uverbs_file *file, if (copy_from_user(&cmd, buf, sizeof cmd)) return -EFAULT; - down(&ib_uverbs_idr_mutex); + mutex_lock(&ib_uverbs_idr_mutex); mr = idr_find(&ib_uverbs_mr_idr, cmd.mr_handle); if (!mr || mr->uobject->context != file->ucontext) @@ -527,15 +527,15 @@ ssize_t ib_uverbs_dereg_mr(struct ib_uverbs_file *file, idr_remove(&ib_uverbs_mr_idr, cmd.mr_handle); - down(&file->mutex); + mutex_lock(&file->mutex); list_del(&memobj->uobject.list); - up(&file->mutex); + mutex_unlock(&file->mutex); ib_umem_release(file->device->ib_dev, &memobj->umem); kfree(memobj); out: - up(&ib_uverbs_idr_mutex); + mutex_unlock(&ib_uverbs_idr_mutex); return ret ? ret : in_len; } @@ -628,7 +628,7 @@ ssize_t ib_uverbs_create_cq(struct ib_uverbs_file *file, cq->cq_context = ev_file; atomic_set(&cq->usecnt, 0); - down(&ib_uverbs_idr_mutex); + mutex_lock(&ib_uverbs_idr_mutex); retry: if (!idr_pre_get(&ib_uverbs_cq_idr, GFP_KERNEL)) { @@ -653,11 +653,11 @@ retry: goto err_idr; } - down(&file->mutex); + mutex_lock(&file->mutex); list_add_tail(&uobj->uobject.list, &file->ucontext->cq_list); - up(&file->mutex); + mutex_unlock(&file->mutex); - up(&ib_uverbs_idr_mutex); + mutex_unlock(&ib_uverbs_idr_mutex); return in_len; @@ -665,7 +665,7 @@ err_idr: idr_remove(&ib_uverbs_cq_idr, uobj->uobject.id); err_up: - up(&ib_uverbs_idr_mutex); + mutex_unlock(&ib_uverbs_idr_mutex); ib_destroy_cq(cq); err: @@ -701,7 +701,7 @@ ssize_t ib_uverbs_poll_cq(struct ib_uverbs_file *file, goto out_wc; } - down(&ib_uverbs_idr_mutex); + mutex_lock(&ib_uverbs_idr_mutex); cq = idr_find(&ib_uverbs_cq_idr, cmd.cq_handle); if (!cq || cq->uobject->context != file->ucontext) { ret = -EINVAL; @@ -731,7 +731,7 @@ ssize_t ib_uverbs_poll_cq(struct ib_uverbs_file *file, ret = -EFAULT; out: - up(&ib_uverbs_idr_mutex); + mutex_unlock(&ib_uverbs_idr_mutex); kfree(resp); out_wc: @@ -750,14 +750,14 @@ ssize_t ib_uverbs_req_notify_cq(struct ib_uverbs_file *file, if (copy_from_user(&cmd, buf, sizeof cmd)) return -EFAULT; - down(&ib_uverbs_idr_mutex); + mutex_lock(&ib_uverbs_idr_mutex); cq = idr_find(&ib_uverbs_cq_idr, cmd.cq_handle); if (cq && cq->uobject->context == file->ucontext) { ib_req_notify_cq(cq, cmd.solicited_only ? IB_CQ_SOLICITED : IB_CQ_NEXT_COMP); ret = in_len; } - up(&ib_uverbs_idr_mutex); + mutex_unlock(&ib_uverbs_idr_mutex); return ret; } @@ -779,7 +779,7 @@ ssize_t ib_uverbs_destroy_cq(struct ib_uverbs_file *file, memset(&resp, 0, sizeof resp); - down(&ib_uverbs_idr_mutex); + mutex_lock(&ib_uverbs_idr_mutex); cq = idr_find(&ib_uverbs_cq_idr, cmd.cq_handle); if (!cq || cq->uobject->context != file->ucontext) @@ -795,9 +795,9 @@ ssize_t ib_uverbs_destroy_cq(struct ib_uverbs_file *file, idr_remove(&ib_uverbs_cq_idr, cmd.cq_handle); - down(&file->mutex); + mutex_lock(&file->mutex); list_del(&uobj->uobject.list); - up(&file->mutex); + mutex_unlock(&file->mutex); ib_uverbs_release_ucq(file, ev_file, uobj); @@ -811,7 +811,7 @@ ssize_t ib_uverbs_destroy_cq(struct ib_uverbs_file *file, ret = -EFAULT; out: - up(&ib_uverbs_idr_mutex); + mutex_unlock(&ib_uverbs_idr_mutex); return ret ? ret : in_len; } @@ -845,7 +845,7 @@ ssize_t ib_uverbs_create_qp(struct ib_uverbs_file *file, if (!uobj) return -ENOMEM; - down(&ib_uverbs_idr_mutex); + mutex_lock(&ib_uverbs_idr_mutex); pd = idr_find(&ib_uverbs_pd_idr, cmd.pd_handle); scq = idr_find(&ib_uverbs_cq_idr, cmd.send_cq_handle); @@ -930,11 +930,11 @@ retry: goto err_idr; } - down(&file->mutex); + mutex_lock(&file->mutex); list_add_tail(&uobj->uevent.uobject.list, &file->ucontext->qp_list); - up(&file->mutex); + mutex_unlock(&file->mutex); - up(&ib_uverbs_idr_mutex); + mutex_unlock(&ib_uverbs_idr_mutex); return in_len; @@ -950,7 +950,7 @@ err_destroy: atomic_dec(&attr.srq->usecnt); err_up: - up(&ib_uverbs_idr_mutex); + mutex_unlock(&ib_uverbs_idr_mutex); kfree(uobj); return ret; @@ -972,7 +972,7 @@ ssize_t ib_uverbs_modify_qp(struct ib_uverbs_file *file, if (!attr) return -ENOMEM; - down(&ib_uverbs_idr_mutex); + mutex_lock(&ib_uverbs_idr_mutex); qp = idr_find(&ib_uverbs_qp_idr, cmd.qp_handle); if (!qp || qp->uobject->context != file->ucontext) { @@ -1033,7 +1033,7 @@ ssize_t ib_uverbs_modify_qp(struct ib_uverbs_file *file, ret = in_len; out: - up(&ib_uverbs_idr_mutex); + mutex_unlock(&ib_uverbs_idr_mutex); kfree(attr); return ret; @@ -1054,7 +1054,7 @@ ssize_t ib_uverbs_destroy_qp(struct ib_uverbs_file *file, memset(&resp, 0, sizeof resp); - down(&ib_uverbs_idr_mutex); + mutex_lock(&ib_uverbs_idr_mutex); qp = idr_find(&ib_uverbs_qp_idr, cmd.qp_handle); if (!qp || qp->uobject->context != file->ucontext) @@ -1073,9 +1073,9 @@ ssize_t ib_uverbs_destroy_qp(struct ib_uverbs_file *file, idr_remove(&ib_uverbs_qp_idr, cmd.qp_handle); - down(&file->mutex); + mutex_lock(&file->mutex); list_del(&uobj->uevent.uobject.list); - up(&file->mutex); + mutex_unlock(&file->mutex); ib_uverbs_release_uevent(file, &uobj->uevent); @@ -1088,7 +1088,7 @@ ssize_t ib_uverbs_destroy_qp(struct ib_uverbs_file *file, ret = -EFAULT; out: - up(&ib_uverbs_idr_mutex); + mutex_unlock(&ib_uverbs_idr_mutex); return ret ? ret : in_len; } @@ -1119,7 +1119,7 @@ ssize_t ib_uverbs_post_send(struct ib_uverbs_file *file, if (!user_wr) return -ENOMEM; - down(&ib_uverbs_idr_mutex); + mutex_lock(&ib_uverbs_idr_mutex); qp = idr_find(&ib_uverbs_qp_idr, cmd.qp_handle); if (!qp || qp->uobject->context != file->ucontext) @@ -1224,7 +1224,7 @@ ssize_t ib_uverbs_post_send(struct ib_uverbs_file *file, ret = -EFAULT; out: - up(&ib_uverbs_idr_mutex); + mutex_unlock(&ib_uverbs_idr_mutex); while (wr) { next = wr->next; @@ -1341,7 +1341,7 @@ ssize_t ib_uverbs_post_recv(struct ib_uverbs_file *file, if (IS_ERR(wr)) return PTR_ERR(wr); - down(&ib_uverbs_idr_mutex); + mutex_lock(&ib_uverbs_idr_mutex); qp = idr_find(&ib_uverbs_qp_idr, cmd.qp_handle); if (!qp || qp->uobject->context != file->ucontext) @@ -1362,7 +1362,7 @@ ssize_t ib_uverbs_post_recv(struct ib_uverbs_file *file, ret = -EFAULT; out: - up(&ib_uverbs_idr_mutex); + mutex_unlock(&ib_uverbs_idr_mutex); while (wr) { next = wr->next; @@ -1392,7 +1392,7 @@ ssize_t ib_uverbs_post_srq_recv(struct ib_uverbs_file *file, if (IS_ERR(wr)) return PTR_ERR(wr); - down(&ib_uverbs_idr_mutex); + mutex_lock(&ib_uverbs_idr_mutex); srq = idr_find(&ib_uverbs_srq_idr, cmd.srq_handle); if (!srq || srq->uobject->context != file->ucontext) @@ -1413,7 +1413,7 @@ ssize_t ib_uverbs_post_srq_recv(struct ib_uverbs_file *file, ret = -EFAULT; out: - up(&ib_uverbs_idr_mutex); + mutex_unlock(&ib_uverbs_idr_mutex); while (wr) { next = wr->next; @@ -1446,7 +1446,7 @@ ssize_t ib_uverbs_create_ah(struct ib_uverbs_file *file, if (!uobj) return -ENOMEM; - down(&ib_uverbs_idr_mutex); + mutex_lock(&ib_uverbs_idr_mutex); pd = idr_find(&ib_uverbs_pd_idr, cmd.pd_handle); if (!pd || pd->uobject->context != file->ucontext) { @@ -1498,11 +1498,11 @@ retry: goto err_idr; } - down(&file->mutex); + mutex_lock(&file->mutex); list_add_tail(&uobj->list, &file->ucontext->ah_list); - up(&file->mutex); + mutex_unlock(&file->mutex); - up(&ib_uverbs_idr_mutex); + mutex_unlock(&ib_uverbs_idr_mutex); return in_len; @@ -1513,7 +1513,7 @@ err_destroy: ib_destroy_ah(ah); err_up: - up(&ib_uverbs_idr_mutex); + mutex_unlock(&ib_uverbs_idr_mutex); kfree(uobj); return ret; @@ -1530,7 +1530,7 @@ ssize_t ib_uverbs_destroy_ah(struct ib_uverbs_file *file, if (copy_from_user(&cmd, buf, sizeof cmd)) return -EFAULT; - down(&ib_uverbs_idr_mutex); + mutex_lock(&ib_uverbs_idr_mutex); ah = idr_find(&ib_uverbs_ah_idr, cmd.ah_handle); if (!ah || ah->uobject->context != file->ucontext) @@ -1544,14 +1544,14 @@ ssize_t ib_uverbs_destroy_ah(struct ib_uverbs_file *file, idr_remove(&ib_uverbs_ah_idr, cmd.ah_handle); - down(&file->mutex); + mutex_lock(&file->mutex); list_del(&uobj->list); - up(&file->mutex); + mutex_unlock(&file->mutex); kfree(uobj); out: - up(&ib_uverbs_idr_mutex); + mutex_unlock(&ib_uverbs_idr_mutex); return ret ? ret : in_len; } @@ -1569,7 +1569,7 @@ ssize_t ib_uverbs_attach_mcast(struct ib_uverbs_file *file, if (copy_from_user(&cmd, buf, sizeof cmd)) return -EFAULT; - down(&ib_uverbs_idr_mutex); + mutex_lock(&ib_uverbs_idr_mutex); qp = idr_find(&ib_uverbs_qp_idr, cmd.qp_handle); if (!qp || qp->uobject->context != file->ucontext) @@ -1602,7 +1602,7 @@ ssize_t ib_uverbs_attach_mcast(struct ib_uverbs_file *file, kfree(mcast); out: - up(&ib_uverbs_idr_mutex); + mutex_unlock(&ib_uverbs_idr_mutex); return ret ? ret : in_len; } @@ -1620,7 +1620,7 @@ ssize_t ib_uverbs_detach_mcast(struct ib_uverbs_file *file, if (copy_from_user(&cmd, buf, sizeof cmd)) return -EFAULT; - down(&ib_uverbs_idr_mutex); + mutex_lock(&ib_uverbs_idr_mutex); qp = idr_find(&ib_uverbs_qp_idr, cmd.qp_handle); if (!qp || qp->uobject->context != file->ucontext) @@ -1641,7 +1641,7 @@ ssize_t ib_uverbs_detach_mcast(struct ib_uverbs_file *file, } out: - up(&ib_uverbs_idr_mutex); + mutex_unlock(&ib_uverbs_idr_mutex); return ret ? ret : in_len; } @@ -1673,7 +1673,7 @@ ssize_t ib_uverbs_create_srq(struct ib_uverbs_file *file, if (!uobj) return -ENOMEM; - down(&ib_uverbs_idr_mutex); + mutex_lock(&ib_uverbs_idr_mutex); pd = idr_find(&ib_uverbs_pd_idr, cmd.pd_handle); @@ -1730,11 +1730,11 @@ retry: goto err_idr; } - down(&file->mutex); + mutex_lock(&file->mutex); list_add_tail(&uobj->uobject.list, &file->ucontext->srq_list); - up(&file->mutex); + mutex_unlock(&file->mutex); - up(&ib_uverbs_idr_mutex); + mutex_unlock(&ib_uverbs_idr_mutex); return in_len; @@ -1746,7 +1746,7 @@ err_destroy: atomic_dec(&pd->usecnt); err_up: - up(&ib_uverbs_idr_mutex); + mutex_unlock(&ib_uverbs_idr_mutex); kfree(uobj); return ret; @@ -1764,7 +1764,7 @@ ssize_t ib_uverbs_modify_srq(struct ib_uverbs_file *file, if (copy_from_user(&cmd, buf, sizeof cmd)) return -EFAULT; - down(&ib_uverbs_idr_mutex); + mutex_lock(&ib_uverbs_idr_mutex); srq = idr_find(&ib_uverbs_srq_idr, cmd.srq_handle); if (!srq || srq->uobject->context != file->ucontext) { @@ -1778,7 +1778,7 @@ ssize_t ib_uverbs_modify_srq(struct ib_uverbs_file *file, ret = ib_modify_srq(srq, &attr, cmd.attr_mask); out: - up(&ib_uverbs_idr_mutex); + mutex_unlock(&ib_uverbs_idr_mutex); return ret ? ret : in_len; } @@ -1796,7 +1796,7 @@ ssize_t ib_uverbs_destroy_srq(struct ib_uverbs_file *file, if (copy_from_user(&cmd, buf, sizeof cmd)) return -EFAULT; - down(&ib_uverbs_idr_mutex); + mutex_lock(&ib_uverbs_idr_mutex); memset(&resp, 0, sizeof resp); @@ -1812,9 +1812,9 @@ ssize_t ib_uverbs_destroy_srq(struct ib_uverbs_file *file, idr_remove(&ib_uverbs_srq_idr, cmd.srq_handle); - down(&file->mutex); + mutex_lock(&file->mutex); list_del(&uobj->uobject.list); - up(&file->mutex); + mutex_unlock(&file->mutex); ib_uverbs_release_uevent(file, uobj); @@ -1827,7 +1827,7 @@ ssize_t ib_uverbs_destroy_srq(struct ib_uverbs_file *file, ret = -EFAULT; out: - up(&ib_uverbs_idr_mutex); + mutex_unlock(&ib_uverbs_idr_mutex); return ret ? ret : in_len; } diff --git a/drivers/infiniband/core/uverbs_main.c b/drivers/infiniband/core/uverbs_main.c index 81737bd6fae..96ea79b63df 100644 --- a/drivers/infiniband/core/uverbs_main.c +++ b/drivers/infiniband/core/uverbs_main.c @@ -66,7 +66,7 @@ enum { static struct class *uverbs_class; -DECLARE_MUTEX(ib_uverbs_idr_mutex); +DEFINE_MUTEX(ib_uverbs_idr_mutex); DEFINE_IDR(ib_uverbs_pd_idr); DEFINE_IDR(ib_uverbs_mr_idr); DEFINE_IDR(ib_uverbs_mw_idr); @@ -180,7 +180,7 @@ static int ib_uverbs_cleanup_ucontext(struct ib_uverbs_file *file, if (!context) return 0; - down(&ib_uverbs_idr_mutex); + mutex_lock(&ib_uverbs_idr_mutex); list_for_each_entry_safe(uobj, tmp, &context->ah_list, list) { struct ib_ah *ah = idr_find(&ib_uverbs_ah_idr, uobj->id); @@ -250,7 +250,7 @@ static int ib_uverbs_cleanup_ucontext(struct ib_uverbs_file *file, kfree(uobj); } - up(&ib_uverbs_idr_mutex); + mutex_unlock(&ib_uverbs_idr_mutex); return context->device->dealloc_ucontext(context); } @@ -653,7 +653,7 @@ static int ib_uverbs_open(struct inode *inode, struct file *filp) file->ucontext = NULL; file->async_file = NULL; kref_init(&file->ref); - init_MUTEX(&file->mutex); + mutex_init(&file->mutex); filp->private_data = file; diff --git a/drivers/infiniband/hw/mthca/mthca_av.c b/drivers/infiniband/hw/mthca/mthca_av.c index 22fdc446f25..a14eed08a0f 100644 --- a/drivers/infiniband/hw/mthca/mthca_av.c +++ b/drivers/infiniband/hw/mthca/mthca_av.c @@ -163,6 +163,11 @@ int mthca_destroy_ah(struct mthca_dev *dev, struct mthca_ah *ah) return 0; } +int mthca_ah_grh_present(struct mthca_ah *ah) +{ + return !!(ah->av->g_slid & 0x80); +} + int mthca_read_ah(struct mthca_dev *dev, struct mthca_ah *ah, struct ib_ud_header *header) { @@ -172,8 +177,7 @@ int mthca_read_ah(struct mthca_dev *dev, struct mthca_ah *ah, header->lrh.service_level = be32_to_cpu(ah->av->sl_tclass_flowlabel) >> 28; header->lrh.destination_lid = ah->av->dlid; header->lrh.source_lid = cpu_to_be16(ah->av->g_slid & 0x7f); - if (ah->av->g_slid & 0x80) { - header->grh_present = 1; + if (mthca_ah_grh_present(ah)) { header->grh.traffic_class = (be32_to_cpu(ah->av->sl_tclass_flowlabel) >> 20) & 0xff; header->grh.flow_label = @@ -184,8 +188,6 @@ int mthca_read_ah(struct mthca_dev *dev, struct mthca_ah *ah, &header->grh.source_gid); memcpy(header->grh.destination_gid.raw, ah->av->dgid, 16); - } else { - header->grh_present = 0; } return 0; diff --git a/drivers/infiniband/hw/mthca/mthca_cmd.c b/drivers/infiniband/hw/mthca/mthca_cmd.c index 22ac72bc20c..be1791be627 100644 --- a/drivers/infiniband/hw/mthca/mthca_cmd.c +++ b/drivers/infiniband/hw/mthca/mthca_cmd.c @@ -606,7 +606,7 @@ static int mthca_map_cmd(struct mthca_dev *dev, u16 op, struct mthca_icm *icm, err = -EINVAL; goto out; } - for (i = 0; i < mthca_icm_size(&iter) / (1 << lg); ++i) { + for (i = 0; i < mthca_icm_size(&iter) >> lg; ++i) { if (virt != -1) { pages[nent * 2] = cpu_to_be64(virt); virt += 1 << lg; @@ -727,8 +727,8 @@ int mthca_QUERY_FW(struct mthca_dev *dev, u8 *status) * system pages needed. */ dev->fw.arbel.fw_pages = - (dev->fw.arbel.fw_pages + (1 << (PAGE_SHIFT - 12)) - 1) >> - (PAGE_SHIFT - 12); + ALIGN(dev->fw.arbel.fw_pages, PAGE_SIZE >> 12) >> + (PAGE_SHIFT - 12); mthca_dbg(dev, "Clear int @ %llx, EQ arm @ %llx, EQ set CI @ %llx\n", (unsigned long long) dev->fw.arbel.clr_int_base, @@ -1445,6 +1445,7 @@ int mthca_SET_ICM_SIZE(struct mthca_dev *dev, u64 icm_size, u64 *aux_pages, * pages needed. */ *aux_pages = (*aux_pages + (1 << (PAGE_SHIFT - 12)) - 1) >> (PAGE_SHIFT - 12); + *aux_pages = ALIGN(*aux_pages, PAGE_SIZE >> 12) >> (PAGE_SHIFT - 12); return 0; } diff --git a/drivers/infiniband/hw/mthca/mthca_dev.h b/drivers/infiniband/hw/mthca/mthca_dev.h index 795b379260b..a104ab041ea 100644 --- a/drivers/infiniband/hw/mthca/mthca_dev.h +++ b/drivers/infiniband/hw/mthca/mthca_dev.h @@ -520,6 +520,7 @@ int mthca_create_ah(struct mthca_dev *dev, int mthca_destroy_ah(struct mthca_dev *dev, struct mthca_ah *ah); int mthca_read_ah(struct mthca_dev *dev, struct mthca_ah *ah, struct ib_ud_header *header); +int mthca_ah_grh_present(struct mthca_ah *ah); int mthca_multicast_attach(struct ib_qp *ibqp, union ib_gid *gid, u16 lid); int mthca_multicast_detach(struct ib_qp *ibqp, union ib_gid *gid, u16 lid); diff --git a/drivers/infiniband/hw/mthca/mthca_eq.c b/drivers/infiniband/hw/mthca/mthca_eq.c index e8a948f087c..2eabb27804c 100644 --- a/drivers/infiniband/hw/mthca/mthca_eq.c +++ b/drivers/infiniband/hw/mthca/mthca_eq.c @@ -45,6 +45,7 @@ enum { MTHCA_NUM_ASYNC_EQE = 0x80, MTHCA_NUM_CMD_EQE = 0x80, + MTHCA_NUM_SPARE_EQE = 0x80, MTHCA_EQ_ENTRY_SIZE = 0x20 }; @@ -277,11 +278,10 @@ static int mthca_eq_int(struct mthca_dev *dev, struct mthca_eq *eq) { struct mthca_eqe *eqe; int disarm_cqn; - int eqes_found = 0; + int eqes_found = 0; + int set_ci = 0; while ((eqe = next_eqe_sw(eq))) { - int set_ci = 0; - /* * Make sure we read EQ entry contents after we've * checked the ownership bit. @@ -345,12 +345,6 @@ static int mthca_eq_int(struct mthca_dev *dev, struct mthca_eq *eq) be16_to_cpu(eqe->event.cmd.token), eqe->event.cmd.status, be64_to_cpu(eqe->event.cmd.out_param)); - /* - * cmd_event() may add more commands. - * The card will think the queue has overflowed if - * we don't tell it we've been processing events. - */ - set_ci = 1; break; case MTHCA_EVENT_TYPE_PORT_CHANGE: @@ -385,8 +379,16 @@ static int mthca_eq_int(struct mthca_dev *dev, struct mthca_eq *eq) set_eqe_hw(eqe); ++eq->cons_index; eqes_found = 1; + ++set_ci; - if (unlikely(set_ci)) { + /* + * The HCA will think the queue has overflowed if we + * don't tell it we've been processing events. We + * create our EQs with MTHCA_NUM_SPARE_EQE extra + * entries, so we must update our consumer index at + * least that often. + */ + if (unlikely(set_ci >= MTHCA_NUM_SPARE_EQE)) { /* * Conditional on hca_type is OK here because * this is a rare case, not the fast path. @@ -862,19 +864,19 @@ int __devinit mthca_init_eq_table(struct mthca_dev *dev) intr = (dev->mthca_flags & MTHCA_FLAG_MSI) ? 128 : dev->eq_table.inta_pin; - err = mthca_create_eq(dev, dev->limits.num_cqs, + err = mthca_create_eq(dev, dev->limits.num_cqs + MTHCA_NUM_SPARE_EQE, (dev->mthca_flags & MTHCA_FLAG_MSI_X) ? 128 : intr, &dev->eq_table.eq[MTHCA_EQ_COMP]); if (err) goto err_out_unmap; - err = mthca_create_eq(dev, MTHCA_NUM_ASYNC_EQE, + err = mthca_create_eq(dev, MTHCA_NUM_ASYNC_EQE + MTHCA_NUM_SPARE_EQE, (dev->mthca_flags & MTHCA_FLAG_MSI_X) ? 129 : intr, &dev->eq_table.eq[MTHCA_EQ_ASYNC]); if (err) goto err_out_comp; - err = mthca_create_eq(dev, MTHCA_NUM_CMD_EQE, + err = mthca_create_eq(dev, MTHCA_NUM_CMD_EQE + MTHCA_NUM_SPARE_EQE, (dev->mthca_flags & MTHCA_FLAG_MSI_X) ? 130 : intr, &dev->eq_table.eq[MTHCA_EQ_CMD]); if (err) diff --git a/drivers/infiniband/hw/mthca/mthca_provider.c b/drivers/infiniband/hw/mthca/mthca_provider.c index 4cc7e2846df..484a7e6b7f8 100644 --- a/drivers/infiniband/hw/mthca/mthca_provider.c +++ b/drivers/infiniband/hw/mthca/mthca_provider.c @@ -33,7 +33,7 @@ * CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN THE * SOFTWARE. * - * $Id: mthca_provider.c 1397 2004-12-28 05:09:00Z roland $ + * $Id: mthca_provider.c 4859 2006-01-09 21:55:10Z roland $ */ #include <rdma/ib_smi.h> @@ -45,6 +45,14 @@ #include "mthca_user.h" #include "mthca_memfree.h" +static void init_query_mad(struct ib_smp *mad) +{ + mad->base_version = 1; + mad->mgmt_class = IB_MGMT_CLASS_SUBN_LID_ROUTED; + mad->class_version = 1; + mad->method = IB_MGMT_METHOD_GET; +} + static int mthca_query_device(struct ib_device *ibdev, struct ib_device_attr *props) { @@ -55,7 +63,7 @@ static int mthca_query_device(struct ib_device *ibdev, u8 status; - in_mad = kmalloc(sizeof *in_mad, GFP_KERNEL); + in_mad = kzalloc(sizeof *in_mad, GFP_KERNEL); out_mad = kmalloc(sizeof *out_mad, GFP_KERNEL); if (!in_mad || !out_mad) goto out; @@ -64,12 +72,8 @@ static int mthca_query_device(struct ib_device *ibdev, props->fw_ver = mdev->fw_ver; - memset(in_mad, 0, sizeof *in_mad); - in_mad->base_version = 1; - in_mad->mgmt_class = IB_MGMT_CLASS_SUBN_LID_ROUTED; - in_mad->class_version = 1; - in_mad->method = IB_MGMT_METHOD_GET; - in_mad->attr_id = IB_SMP_ATTR_NODE_INFO; + init_query_mad(in_mad); + in_mad->attr_id = IB_SMP_ATTR_NODE_INFO; err = mthca_MAD_IFC(mdev, 1, 1, 1, NULL, NULL, in_mad, out_mad, @@ -87,7 +91,6 @@ static int mthca_query_device(struct ib_device *ibdev, props->vendor_part_id = be16_to_cpup((__be16 *) (out_mad->data + 30)); props->hw_ver = be32_to_cpup((__be32 *) (out_mad->data + 32)); memcpy(&props->sys_image_guid, out_mad->data + 4, 8); - memcpy(&props->node_guid, out_mad->data + 12, 8); props->max_mr_size = ~0ull; props->page_size_cap = mdev->limits.page_size_cap; @@ -128,20 +131,16 @@ static int mthca_query_port(struct ib_device *ibdev, int err = -ENOMEM; u8 status; - in_mad = kmalloc(sizeof *in_mad, GFP_KERNEL); + in_mad = kzalloc(sizeof *in_mad, GFP_KERNEL); out_mad = kmalloc(sizeof *out_mad, GFP_KERNEL); if (!in_mad || !out_mad) goto out; memset(props, 0, sizeof *props); - memset(in_mad, 0, sizeof *in_mad); - in_mad->base_version = 1; - in_mad->mgmt_class = IB_MGMT_CLASS_SUBN_LID_ROUTED; - in_mad->class_version = 1; - in_mad->method = IB_MGMT_METHOD_GET; - in_mad->attr_id = IB_SMP_ATTR_PORT_INFO; - in_mad->attr_mod = cpu_to_be32(port); + init_query_mad(in_mad); + in_mad->attr_id = IB_SMP_ATTR_PORT_INFO; + in_mad->attr_mod = cpu_to_be32(port); err = mthca_MAD_IFC(to_mdev(ibdev), 1, 1, port, NULL, NULL, in_mad, out_mad, @@ -220,18 +219,14 @@ static int mthca_query_pkey(struct ib_device *ibdev, int err = -ENOMEM; u8 status; - in_mad = kmalloc(sizeof *in_mad, GFP_KERNEL); + in_mad = kzalloc(sizeof *in_mad, GFP_KERNEL); out_mad = kmalloc(sizeof *out_mad, GFP_KERNEL); if (!in_mad || !out_mad) goto out; - memset(in_mad, 0, sizeof *in_mad); - in_mad->base_version = 1; - in_mad->mgmt_class = IB_MGMT_CLASS_SUBN_LID_ROUTED; - in_mad->class_version = 1; - in_mad->method = IB_MGMT_METHOD_GET; - in_mad->attr_id = IB_SMP_ATTR_PKEY_TABLE; - in_mad->attr_mod = cpu_to_be32(index / 32); + init_query_mad(in_mad); + in_mad->attr_id = IB_SMP_ATTR_PKEY_TABLE; + in_mad->attr_mod = cpu_to_be32(index / 32); err = mthca_MAD_IFC(to_mdev(ibdev), 1, 1, port, NULL, NULL, in_mad, out_mad, @@ -259,18 +254,14 @@ static int mthca_query_gid(struct ib_device *ibdev, u8 port, int err = -ENOMEM; u8 status; - in_mad = kmalloc(sizeof *in_mad, GFP_KERNEL); + in_mad = kzalloc(sizeof *in_mad, GFP_KERNEL); out_mad = kmalloc(sizeof *out_mad, GFP_KERNEL); if (!in_mad || !out_mad) goto out; - memset(in_mad, 0, sizeof *in_mad); - in_mad->base_version = 1; - in_mad->mgmt_class = IB_MGMT_CLASS_SUBN_LID_ROUTED; - in_mad->class_version = 1; - in_mad->method = IB_MGMT_METHOD_GET; - in_mad->attr_id = IB_SMP_ATTR_PORT_INFO; - in_mad->attr_mod = cpu_to_be32(port); + init_query_mad(in_mad); + in_mad->attr_id = IB_SMP_ATTR_PORT_INFO; + in_mad->attr_mod = cpu_to_be32(port); err = mthca_MAD_IFC(to_mdev(ibdev), 1, 1, port, NULL, NULL, in_mad, out_mad, @@ -284,13 +275,9 @@ static int mthca_query_gid(struct ib_device *ibdev, u8 port, memcpy(gid->raw, out_mad->data + 8, 8); - memset(in_mad, 0, sizeof *in_mad); - in_mad->base_version = 1; - in_mad->mgmt_class = IB_MGMT_CLASS_SUBN_LID_ROUTED; - in_mad->class_version = 1; - in_mad->method = IB_MGMT_METHOD_GET; - in_mad->attr_id = IB_SMP_ATTR_GUID_INFO; - in_mad->attr_mod = cpu_to_be32(index / 8); + init_query_mad(in_mad); + in_mad->attr_id = IB_SMP_ATTR_GUID_INFO; + in_mad->attr_mod = cpu_to_be32(index / 8); err = mthca_MAD_IFC(to_mdev(ibdev), 1, 1, port, NULL, NULL, in_mad, out_mad, @@ -458,8 +445,10 @@ static struct ib_srq *mthca_create_srq(struct ib_pd *pd, if (pd->uobject) { context = to_mucontext(pd->uobject->context); - if (ib_copy_from_udata(&ucmd, udata, sizeof ucmd)) - return ERR_PTR(-EFAULT); + if (ib_copy_from_udata(&ucmd, udata, sizeof ucmd)) { + err = -EFAULT; + goto err_free; + } err = mthca_map_user_db(to_mdev(pd->device), &context->uar, context->db_tab, ucmd.db_index, @@ -535,8 +524,10 @@ static struct ib_qp *mthca_create_qp(struct ib_pd *pd, if (pd->uobject) { context = to_mucontext(pd->uobject->context); - if (ib_copy_from_udata(&ucmd, udata, sizeof ucmd)) + if (ib_copy_from_udata(&ucmd, udata, sizeof ucmd)) { + kfree(qp); return ERR_PTR(-EFAULT); + } err = mthca_map_user_db(to_mdev(pd->device), &context->uar, context->db_tab, @@ -783,24 +774,20 @@ static struct ib_mr *mthca_reg_phys_mr(struct ib_pd *pd, if ((*iova_start & ~PAGE_MASK) != (buffer_list[0].addr & ~PAGE_MASK)) return ERR_PTR(-EINVAL); - if (num_phys_buf > 1 && - ((buffer_list[0].addr + buffer_list[0].size) & ~PAGE_MASK)) - return ERR_PTR(-EINVAL); - mask = 0; total_size = 0; for (i = 0; i < num_phys_buf; ++i) { - if (i != 0 && buffer_list[i].addr & ~PAGE_MASK) - return ERR_PTR(-EINVAL); - if (i != 0 && i != num_phys_buf - 1 && - (buffer_list[i].size & ~PAGE_MASK)) - return ERR_PTR(-EINVAL); + if (i != 0) + mask |= buffer_list[i].addr; + if (i != num_phys_buf - 1) + mask |= buffer_list[i].addr + buffer_list[i].size; total_size += buffer_list[i].size; - if (i > 0) - mask |= buffer_list[i].addr; } + if (mask & ~PAGE_MASK) + return ERR_PTR(-EINVAL); + /* Find largest page shift we can use to cover buffers */ for (shift = PAGE_SHIFT; shift < 31; ++shift) if (num_phys_buf > 1) { @@ -1070,11 +1057,48 @@ static struct class_device_attribute *mthca_class_attributes[] = { &class_device_attr_board_id }; +static int mthca_init_node_data(struct mthca_dev *dev) +{ + struct ib_smp *in_mad = NULL; + struct ib_smp *out_mad = NULL; + int err = -ENOMEM; + u8 status; + + in_mad = kzalloc(sizeof *in_mad, GFP_KERNEL); + out_mad = kmalloc(sizeof *out_mad, GFP_KERNEL); + if (!in_mad || !out_mad) + goto out; + + init_query_mad(in_mad); + in_mad->attr_id = IB_SMP_ATTR_NODE_INFO; + + err = mthca_MAD_IFC(dev, 1, 1, + 1, NULL, NULL, in_mad, out_mad, + &status); + if (err) + goto out; + if (status) { + err = -EINVAL; + goto out; + } + + memcpy(&dev->ib_dev.node_guid, out_mad->data + 12, 8); + +out: + kfree(in_mad); + kfree(out_mad); + return err; +} + int mthca_register_device(struct mthca_dev *dev) { int ret; int i; + ret = mthca_init_node_data(dev); + if (ret) + return ret; + strlcpy(dev->ib_dev.name, "mthca%d", IB_DEVICE_NAME_MAX); dev->ib_dev.owner = THIS_MODULE; diff --git a/drivers/infiniband/hw/mthca/mthca_qp.c b/drivers/infiniband/hw/mthca/mthca_qp.c index 564b6d51c39..fba608ed7df 100644 --- a/drivers/infiniband/hw/mthca/mthca_qp.c +++ b/drivers/infiniband/hw/mthca/mthca_qp.c @@ -1434,7 +1434,7 @@ static int build_mlx_header(struct mthca_dev *dev, struct mthca_sqp *sqp, u16 pkey; ib_ud_header_init(256, /* assume a MAD */ - sqp->ud_header.grh_present, + mthca_ah_grh_present(to_mah(wr->wr.ud.ah)), &sqp->ud_header); err = mthca_read_ah(dev, to_mah(wr->wr.ud.ah), &sqp->ud_header); diff --git a/drivers/infiniband/ulp/ipoib/ipoib.h b/drivers/infiniband/ulp/ipoib/ipoib.h index 9923a15a999..e0a5412b7e6 100644 --- a/drivers/infiniband/ulp/ipoib/ipoib.h +++ b/drivers/infiniband/ulp/ipoib/ipoib.h @@ -45,11 +45,11 @@ #include <linux/config.h> #include <linux/kref.h> #include <linux/if_infiniband.h> +#include <linux/mutex.h> #include <net/neighbour.h> #include <asm/atomic.h> -#include <asm/semaphore.h> #include <rdma/ib_verbs.h> #include <rdma/ib_pack.h> @@ -123,8 +123,8 @@ struct ipoib_dev_priv { unsigned long flags; - struct semaphore mcast_mutex; - struct semaphore vlan_mutex; + struct mutex mcast_mutex; + struct mutex vlan_mutex; struct rb_root path_tree; struct list_head path_list; diff --git a/drivers/infiniband/ulp/ipoib/ipoib_ib.c b/drivers/infiniband/ulp/ipoib/ipoib_ib.c index 23885801b6d..86bcdd72a10 100644 --- a/drivers/infiniband/ulp/ipoib/ipoib_ib.c +++ b/drivers/infiniband/ulp/ipoib/ipoib_ib.c @@ -52,7 +52,7 @@ MODULE_PARM_DESC(data_debug_level, #define IPOIB_OP_RECV (1ul << 31) -static DECLARE_MUTEX(pkey_sem); +static DEFINE_MUTEX(pkey_mutex); struct ipoib_ah *ipoib_create_ah(struct net_device *dev, struct ib_pd *pd, struct ib_ah_attr *attr) @@ -445,25 +445,16 @@ int ipoib_ib_dev_down(struct net_device *dev) /* Shutdown the P_Key thread if still active */ if (!test_bit(IPOIB_PKEY_ASSIGNED, &priv->flags)) { - down(&pkey_sem); + mutex_lock(&pkey_mutex); set_bit(IPOIB_PKEY_STOP, &priv->flags); cancel_delayed_work(&priv->pkey_task); - up(&pkey_sem); + mutex_unlock(&pkey_mutex); flush_workqueue(ipoib_workqueue); } ipoib_mcast_stop_thread(dev, 1); - - /* - * Flush the multicast groups first so we stop any multicast joins. The - * completion thread may have already died and we may deadlock waiting - * for the completion thread to finish some multicast joins. - */ ipoib_mcast_dev_flush(dev); - /* Delete broadcast and local addresses since they will be recreated */ - ipoib_mcast_dev_down(dev); - ipoib_flush_paths(dev); return 0; @@ -608,13 +599,13 @@ void ipoib_ib_dev_flush(void *_dev) if (test_bit(IPOIB_FLAG_ADMIN_UP, &priv->flags)) ipoib_ib_dev_up(dev); - down(&priv->vlan_mutex); + mutex_lock(&priv->vlan_mutex); /* Flush any child interfaces too */ list_for_each_entry(cpriv, &priv->child_intfs, list) ipoib_ib_dev_flush(&cpriv->dev); - up(&priv->vlan_mutex); + mutex_unlock(&priv->vlan_mutex); } void ipoib_ib_dev_cleanup(struct net_device *dev) @@ -624,9 +615,7 @@ void ipoib_ib_dev_cleanup(struct net_device *dev) ipoib_dbg(priv, "cleaning up ib_dev\n"); ipoib_mcast_stop_thread(dev, 1); - - /* Delete the broadcast address and the local address */ - ipoib_mcast_dev_down(dev); + ipoib_mcast_dev_flush(dev); ipoib_transport_dev_cleanup(dev); } @@ -662,12 +651,12 @@ void ipoib_pkey_poll(void *dev_ptr) if (test_bit(IPOIB_PKEY_ASSIGNED, &priv->flags)) ipoib_open(dev); else { - down(&pkey_sem); + mutex_lock(&pkey_mutex); if (!test_bit(IPOIB_PKEY_STOP, &priv->flags)) queue_delayed_work(ipoib_workqueue, &priv->pkey_task, HZ); - up(&pkey_sem); + mutex_unlock(&pkey_mutex); } } @@ -681,12 +670,12 @@ int ipoib_pkey_dev_delay_open(struct net_device *dev) /* P_Key value not assigned yet - start polling */ if (!test_bit(IPOIB_PKEY_ASSIGNED, &priv->flags)) { - down(&pkey_sem); + mutex_lock(&pkey_mutex); clear_bit(IPOIB_PKEY_STOP, &priv->flags); queue_delayed_work(ipoib_workqueue, &priv->pkey_task, HZ); - up(&pkey_sem); + mutex_unlock(&pkey_mutex); return 1; } diff --git a/drivers/infiniband/ulp/ipoib/ipoib_main.c b/drivers/infiniband/ulp/ipoib/ipoib_main.c index 780009c7eaa..fd3f5c862a5 100644 --- a/drivers/infiniband/ulp/ipoib/ipoib_main.c +++ b/drivers/infiniband/ulp/ipoib/ipoib_main.c @@ -105,7 +105,7 @@ int ipoib_open(struct net_device *dev) struct ipoib_dev_priv *cpriv; /* Bring up any child interfaces too */ - down(&priv->vlan_mutex); + mutex_lock(&priv->vlan_mutex); list_for_each_entry(cpriv, &priv->child_intfs, list) { int flags; @@ -115,7 +115,7 @@ int ipoib_open(struct net_device *dev) dev_change_flags(cpriv->dev, flags | IFF_UP); } - up(&priv->vlan_mutex); + mutex_unlock(&priv->vlan_mutex); } netif_start_queue(dev); @@ -140,7 +140,7 @@ static int ipoib_stop(struct net_device *dev) struct ipoib_dev_priv *cpriv; /* Bring down any child interfaces too */ - down(&priv->vlan_mutex); + mutex_lock(&priv->vlan_mutex); list_for_each_entry(cpriv, &priv->child_intfs, list) { int flags; @@ -150,7 +150,7 @@ static int ipoib_stop(struct net_device *dev) dev_change_flags(cpriv->dev, flags & ~IFF_UP); } - up(&priv->vlan_mutex); + mutex_unlock(&priv->vlan_mutex); } return 0; @@ -892,8 +892,8 @@ static void ipoib_setup(struct net_device *dev) spin_lock_init(&priv->lock); spin_lock_init(&priv->tx_lock); - init_MUTEX(&priv->mcast_mutex); - init_MUTEX(&priv->vlan_mutex); + mutex_init(&priv->mcast_mutex); + mutex_init(&priv->vlan_mutex); INIT_LIST_HEAD(&priv->path_list); INIT_LIST_HEAD(&priv->child_intfs); diff --git a/drivers/infiniband/ulp/ipoib/ipoib_multicast.c b/drivers/infiniband/ulp/ipoib/ipoib_multicast.c index ed0c2ead8bc..98039da0caf 100644 --- a/drivers/infiniband/ulp/ipoib/ipoib_multicast.c +++ b/drivers/infiniband/ulp/ipoib/ipoib_multicast.c @@ -55,7 +55,7 @@ MODULE_PARM_DESC(mcast_debug_level, "Enable multicast debug tracing if > 0"); #endif -static DECLARE_MUTEX(mcast_mutex); +static DEFINE_MUTEX(mcast_mutex); /* Used for all multicast joins (broadcast, IPv4 mcast and IPv6 mcast) */ struct ipoib_mcast { @@ -97,8 +97,6 @@ static void ipoib_mcast_free(struct ipoib_mcast *mcast) struct ipoib_dev_priv *priv = netdev_priv(dev); struct ipoib_neigh *neigh, *tmp; unsigned long flags; - LIST_HEAD(ah_list); - struct ipoib_ah *ah, *tah; ipoib_dbg_mcast(netdev_priv(dev), "deleting multicast group " IPOIB_GID_FMT "\n", @@ -107,8 +105,14 @@ static void ipoib_mcast_free(struct ipoib_mcast *mcast) spin_lock_irqsave(&priv->lock, flags); list_for_each_entry_safe(neigh, tmp, &mcast->neigh_list, list) { + /* + * It's safe to call ipoib_put_ah() inside priv->lock + * here, because we know that mcast->ah will always + * hold one more reference, so ipoib_put_ah() will + * never do more than decrement the ref count. + */ if (neigh->ah) - list_add_tail(&neigh->ah->list, &ah_list); + ipoib_put_ah(neigh->ah); *to_ipoib_neigh(neigh->neighbour) = NULL; neigh->neighbour->ops->destructor = NULL; kfree(neigh); @@ -116,9 +120,6 @@ static void ipoib_mcast_free(struct ipoib_mcast *mcast) spin_unlock_irqrestore(&priv->lock, flags); - list_for_each_entry_safe(ah, tah, &ah_list, list) - ipoib_put_ah(ah); - if (mcast->ah) ipoib_put_ah(mcast->ah); @@ -384,10 +385,10 @@ static void ipoib_mcast_join_complete(int status, if (!status && !ipoib_mcast_join_finish(mcast, mcmember)) { mcast->backoff = 1; - down(&mcast_mutex); + mutex_lock(&mcast_mutex); if (test_bit(IPOIB_MCAST_RUN, &priv->flags)) queue_work(ipoib_workqueue, &priv->mcast_task); - up(&mcast_mutex); + mutex_unlock(&mcast_mutex); complete(&mcast->done); return; } @@ -417,7 +418,7 @@ static void ipoib_mcast_join_complete(int status, mcast->query = NULL; - down(&mcast_mutex); + mutex_lock(&mcast_mutex); if (test_bit(IPOIB_MCAST_RUN, &priv->flags)) { if (status == -ETIMEDOUT) queue_work(ipoib_workqueue, &priv->mcast_task); @@ -426,7 +427,7 @@ static void ipoib_mcast_join_complete(int status, mcast->backoff * HZ); } else complete(&mcast->done); - up(&mcast_mutex); + mutex_unlock(&mcast_mutex); return; } @@ -481,12 +482,12 @@ static void ipoib_mcast_join(struct net_device *dev, struct ipoib_mcast *mcast, if (mcast->backoff > IPOIB_MAX_BACKOFF_SECONDS) mcast->backoff = IPOIB_MAX_BACKOFF_SECONDS; - down(&mcast_mutex); + mutex_lock(&mcast_mutex); if (test_bit(IPOIB_MCAST_RUN, &priv->flags)) queue_delayed_work(ipoib_workqueue, &priv->mcast_task, mcast->backoff * HZ); - up(&mcast_mutex); + mutex_unlock(&mcast_mutex); } else mcast->query_id = ret; } @@ -519,11 +520,11 @@ void ipoib_mcast_join_task(void *dev_ptr) priv->broadcast = ipoib_mcast_alloc(dev, 1); if (!priv->broadcast) { ipoib_warn(priv, "failed to allocate broadcast group\n"); - down(&mcast_mutex); + mutex_lock(&mcast_mutex); if (test_bit(IPOIB_MCAST_RUN, &priv->flags)) queue_delayed_work(ipoib_workqueue, &priv->mcast_task, HZ); - up(&mcast_mutex); + mutex_unlock(&mcast_mutex); return; } @@ -579,10 +580,10 @@ int ipoib_mcast_start_thread(struct net_device *dev) ipoib_dbg_mcast(priv, "starting multicast thread\n"); - down(&mcast_mutex); + mutex_lock(&mcast_mutex); if (!test_and_set_bit(IPOIB_MCAST_RUN, &priv->flags)) queue_work(ipoib_workqueue, &priv->mcast_task); - up(&mcast_mutex); + mutex_unlock(&mcast_mutex); return 0; } @@ -594,10 +595,10 @@ int ipoib_mcast_stop_thread(struct net_device *dev, int flush) ipoib_dbg_mcast(priv, "stopping multicast thread\n"); - down(&mcast_mutex); + mutex_lock(&mcast_mutex); clear_bit(IPOIB_MCAST_RUN, &priv->flags); cancel_delayed_work(&priv->mcast_task); - up(&mcast_mutex); + mutex_unlock(&mcast_mutex); if (flush) flush_workqueue(ipoib_workqueue); @@ -741,48 +742,23 @@ void ipoib_mcast_dev_flush(struct net_device *dev) { struct ipoib_dev_priv *priv = netdev_priv(dev); LIST_HEAD(remove_list); - struct ipoib_mcast *mcast, *tmcast, *nmcast; + struct ipoib_mcast *mcast, *tmcast; unsigned long flags; ipoib_dbg_mcast(priv, "flushing multicast list\n"); spin_lock_irqsave(&priv->lock, flags); - list_for_each_entry_safe(mcast, tmcast, &priv->multicast_list, list) { - nmcast = ipoib_mcast_alloc(dev, 0); - if (nmcast) { - nmcast->flags = - mcast->flags & (1 << IPOIB_MCAST_FLAG_SENDONLY); - nmcast->mcmember.mgid = mcast->mcmember.mgid; - - /* Add the new group in before the to-be-destroyed group */ - list_add_tail(&nmcast->list, &mcast->list); - list_del_init(&mcast->list); - - rb_replace_node(&mcast->rb_node, &nmcast->rb_node, - &priv->multicast_tree); - - list_add_tail(&mcast->list, &remove_list); - } else { - ipoib_warn(priv, "could not reallocate multicast group " - IPOIB_GID_FMT "\n", - IPOIB_GID_ARG(mcast->mcmember.mgid)); - } + list_for_each_entry_safe(mcast, tmcast, &priv->multicast_list, list) { + list_del(&mcast->list); + rb_erase(&mcast->rb_node, &priv->multicast_tree); + list_add_tail(&mcast->list, &remove_list); } if (priv->broadcast) { - nmcast = ipoib_mcast_alloc(dev, 0); - if (nmcast) { - nmcast->mcmember.mgid = priv->broadcast->mcmember.mgid; - - rb_replace_node(&priv->broadcast->rb_node, - &nmcast->rb_node, - &priv->multicast_tree); - - list_add_tail(&priv->broadcast->list, &remove_list); - } - - priv->broadcast = nmcast; + rb_erase(&priv->broadcast->rb_node, &priv->multicast_tree); + list_add_tail(&priv->broadcast->list, &remove_list); + priv->broadcast = NULL; } spin_unlock_irqrestore(&priv->lock, flags); @@ -793,24 +769,6 @@ void ipoib_mcast_dev_flush(struct net_device *dev) } } -void ipoib_mcast_dev_down(struct net_device *dev) -{ - struct ipoib_dev_priv *priv = netdev_priv(dev); - unsigned long flags; - - /* Delete broadcast since it will be recreated */ - if (priv->broadcast) { - ipoib_dbg_mcast(priv, "deleting broadcast group\n"); - - spin_lock_irqsave(&priv->lock, flags); - rb_erase(&priv->broadcast->rb_node, &priv->multicast_tree); - spin_unlock_irqrestore(&priv->lock, flags); - ipoib_mcast_leave(dev, priv->broadcast); - ipoib_mcast_free(priv->broadcast); - priv->broadcast = NULL; - } -} - void ipoib_mcast_restart_task(void *dev_ptr) { struct net_device *dev = dev_ptr; @@ -824,7 +782,8 @@ void ipoib_mcast_restart_task(void *dev_ptr) ipoib_mcast_stop_thread(dev, 0); - spin_lock_irqsave(&priv->lock, flags); + spin_lock_irqsave(&dev->xmit_lock, flags); + spin_lock(&priv->lock); /* * Unfortunately, the networking core only gives us a list of all of @@ -896,7 +855,9 @@ void ipoib_mcast_restart_task(void *dev_ptr) list_add_tail(&mcast->list, &remove_list); } } - spin_unlock_irqrestore(&priv->lock, flags); + + spin_unlock(&priv->lock); + spin_unlock_irqrestore(&dev->xmit_lock, flags); /* We have to cancel outside of the spinlock */ list_for_each_entry_safe(mcast, tmcast, &remove_list, list) { diff --git a/drivers/infiniband/ulp/ipoib/ipoib_verbs.c b/drivers/infiniband/ulp/ipoib/ipoib_verbs.c index e829e10400e..faaf10e5fc7 100644 --- a/drivers/infiniband/ulp/ipoib/ipoib_verbs.c +++ b/drivers/infiniband/ulp/ipoib/ipoib_verbs.c @@ -65,9 +65,9 @@ int ipoib_mcast_attach(struct net_device *dev, u16 mlid, union ib_gid *mgid) } /* attach QP to multicast group */ - down(&priv->mcast_mutex); + mutex_lock(&priv->mcast_mutex); ret = ib_attach_mcast(priv->qp, mgid, mlid); - up(&priv->mcast_mutex); + mutex_unlock(&priv->mcast_mutex); if (ret) ipoib_warn(priv, "failed to attach to multicast group, ret = %d\n", ret); @@ -81,9 +81,9 @@ int ipoib_mcast_detach(struct net_device *dev, u16 mlid, union ib_gid *mgid) struct ipoib_dev_priv *priv = netdev_priv(dev); int ret; - down(&priv->mcast_mutex); + mutex_lock(&priv->mcast_mutex); ret = ib_detach_mcast(priv->qp, mgid, mlid); - up(&priv->mcast_mutex); + mutex_unlock(&priv->mcast_mutex); if (ret) ipoib_warn(priv, "ib_detach_mcast failed (result = %d)\n", ret); diff --git a/drivers/infiniband/ulp/ipoib/ipoib_vlan.c b/drivers/infiniband/ulp/ipoib/ipoib_vlan.c index d280b341a37..4ca175553f9 100644 --- a/drivers/infiniband/ulp/ipoib/ipoib_vlan.c +++ b/drivers/infiniband/ulp/ipoib/ipoib_vlan.c @@ -63,7 +63,7 @@ int ipoib_vlan_add(struct net_device *pdev, unsigned short pkey) ppriv = netdev_priv(pdev); - down(&ppriv->vlan_mutex); + mutex_lock(&ppriv->vlan_mutex); /* * First ensure this isn't a duplicate. We check the parent device and @@ -124,7 +124,7 @@ int ipoib_vlan_add(struct net_device *pdev, unsigned short pkey) list_add_tail(&priv->list, &ppriv->child_intfs); - up(&ppriv->vlan_mutex); + mutex_unlock(&ppriv->vlan_mutex); return 0; @@ -139,7 +139,7 @@ device_init_failed: free_netdev(priv->dev); err: - up(&ppriv->vlan_mutex); + mutex_unlock(&ppriv->vlan_mutex); return result; } @@ -153,7 +153,7 @@ int ipoib_vlan_delete(struct net_device *pdev, unsigned short pkey) ppriv = netdev_priv(pdev); - down(&ppriv->vlan_mutex); + mutex_lock(&ppriv->vlan_mutex); list_for_each_entry_safe(priv, tpriv, &ppriv->child_intfs, list) { if (priv->pkey == pkey) { unregister_netdev(priv->dev); @@ -167,7 +167,7 @@ int ipoib_vlan_delete(struct net_device *pdev, unsigned short pkey) break; } } - up(&ppriv->vlan_mutex); + mutex_unlock(&ppriv->vlan_mutex); return ret; } diff --git a/drivers/infiniband/ulp/srp/ib_srp.c b/drivers/infiniband/ulp/srp/ib_srp.c index dd488d3cffa..31207e66414 100644 --- a/drivers/infiniband/ulp/srp/ib_srp.c +++ b/drivers/infiniband/ulp/srp/ib_srp.c @@ -1516,8 +1516,7 @@ static ssize_t show_port(struct class_device *class_dev, char *buf) static CLASS_DEVICE_ATTR(port, S_IRUGO, show_port, NULL); -static struct srp_host *srp_add_port(struct ib_device *device, - __be64 node_guid, u8 port) +static struct srp_host *srp_add_port(struct ib_device *device, u8 port) { struct srp_host *host; @@ -1532,7 +1531,7 @@ static struct srp_host *srp_add_port(struct ib_device *device, host->port = port; host->initiator_port_id[7] = port; - memcpy(host->initiator_port_id + 8, &node_guid, 8); + memcpy(host->initiator_port_id + 8, &device->node_guid, 8); host->pd = ib_alloc_pd(device); if (IS_ERR(host->pd)) @@ -1580,22 +1579,11 @@ static void srp_add_one(struct ib_device *device) { struct list_head *dev_list; struct srp_host *host; - struct ib_device_attr *dev_attr; int s, e, p; - dev_attr = kmalloc(sizeof *dev_attr, GFP_KERNEL); - if (!dev_attr) - return; - - if (ib_query_device(device, dev_attr)) { - printk(KERN_WARNING PFX "Couldn't query node GUID for %s.\n", - device->name); - goto out; - } - dev_list = kmalloc(sizeof *dev_list, GFP_KERNEL); if (!dev_list) - goto out; + return; INIT_LIST_HEAD(dev_list); @@ -1608,15 +1596,12 @@ static void srp_add_one(struct ib_device *device) } for (p = s; p <= e; ++p) { - host = srp_add_port(device, dev_attr->node_guid, p); + host = srp_add_port(device, p); if (host) list_add_tail(&host->list, dev_list); } ib_set_client_data(device, &srp_client, dev_list); - -out: - kfree(dev_attr); } static void srp_remove_one(struct ib_device *device) diff --git a/drivers/input/mouse/alps.c b/drivers/input/mouse/alps.c index 24474335dfd..2141501e9f2 100644 --- a/drivers/input/mouse/alps.c +++ b/drivers/input/mouse/alps.c @@ -348,6 +348,40 @@ static int alps_tap_mode(struct psmouse *psmouse, int enable) return 0; } +/* + * alps_poll() - poll the touchpad for current motion packet. + * Used in resync. + */ +static int alps_poll(struct psmouse *psmouse) +{ + struct alps_data *priv = psmouse->private; + unsigned char buf[6]; + int poll_failed; + + if (priv->i->flags & ALPS_PASS) + alps_passthrough_mode(psmouse, 1); + + poll_failed = ps2_command(&psmouse->ps2dev, buf, + PSMOUSE_CMD_POLL | (psmouse->pktsize << 8)) < 0; + + if (priv->i->flags & ALPS_PASS) + alps_passthrough_mode(psmouse, 0); + + if (poll_failed || (buf[0] & priv->i->mask0) != priv->i->byte0) + return -1; + + if ((psmouse->badbyte & 0xc8) == 0x08) { +/* + * Poll the track stick ... + */ + if (ps2_command(&psmouse->ps2dev, buf, PSMOUSE_CMD_POLL | (3 << 8))) + return -1; + } + + memcpy(psmouse->packet, buf, sizeof(buf)); + return 0; +} + static int alps_reconnect(struct psmouse *psmouse) { struct alps_data *priv = psmouse->private; @@ -451,10 +485,14 @@ int alps_init(struct psmouse *psmouse) input_register_device(priv->dev2); psmouse->protocol_handler = alps_process_byte; + psmouse->poll = alps_poll; psmouse->disconnect = alps_disconnect; psmouse->reconnect = alps_reconnect; psmouse->pktsize = 6; + /* We are having trouble resyncing ALPS touchpads so disable it for now */ + psmouse->resync_time = 0; + return 0; init_fail: diff --git a/drivers/input/mouse/logips2pp.c b/drivers/input/mouse/logips2pp.c index 025a71de540..c88520d3d13 100644 --- a/drivers/input/mouse/logips2pp.c +++ b/drivers/input/mouse/logips2pp.c @@ -117,7 +117,7 @@ static int ps2pp_cmd(struct psmouse *psmouse, unsigned char *param, unsigned cha if (psmouse_sliced_command(psmouse, command)) return -1; - if (ps2_command(&psmouse->ps2dev, param, PSMOUSE_CMD_POLL)) + if (ps2_command(&psmouse->ps2dev, param, PSMOUSE_CMD_POLL | 0x0300)) return -1; return 0; diff --git a/drivers/input/mouse/psmouse-base.c b/drivers/input/mouse/psmouse-base.c index 4d5ecc04c5b..7665fd9ce55 100644 --- a/drivers/input/mouse/psmouse-base.c +++ b/drivers/input/mouse/psmouse-base.c @@ -54,10 +54,14 @@ static unsigned int psmouse_smartscroll = 1; module_param_named(smartscroll, psmouse_smartscroll, bool, 0644); MODULE_PARM_DESC(smartscroll, "Logitech Smartscroll autorepeat, 1 = enabled (default), 0 = disabled."); -static unsigned int psmouse_resetafter; +static unsigned int psmouse_resetafter = 5; module_param_named(resetafter, psmouse_resetafter, uint, 0644); MODULE_PARM_DESC(resetafter, "Reset device after so many bad packets (0 = never)."); +static unsigned int psmouse_resync_time = 5; +module_param_named(resync_time, psmouse_resync_time, uint, 0644); +MODULE_PARM_DESC(resync_time, "How long can mouse stay idle before forcing resync (in seconds, 0 = never)."); + PSMOUSE_DEFINE_ATTR(protocol, S_IWUSR | S_IRUGO, NULL, psmouse_attr_show_protocol, psmouse_attr_set_protocol); @@ -70,12 +74,16 @@ PSMOUSE_DEFINE_ATTR(resolution, S_IWUSR | S_IRUGO, PSMOUSE_DEFINE_ATTR(resetafter, S_IWUSR | S_IRUGO, (void *) offsetof(struct psmouse, resetafter), psmouse_show_int_attr, psmouse_set_int_attr); +PSMOUSE_DEFINE_ATTR(resync_time, S_IWUSR | S_IRUGO, + (void *) offsetof(struct psmouse, resync_time), + psmouse_show_int_attr, psmouse_set_int_attr); static struct attribute *psmouse_attributes[] = { &psmouse_attr_protocol.dattr.attr, &psmouse_attr_rate.dattr.attr, &psmouse_attr_resolution.dattr.attr, &psmouse_attr_resetafter.dattr.attr, + &psmouse_attr_resync_time.dattr.attr, NULL }; @@ -98,6 +106,8 @@ __obsolete_setup("psmouse_rate="); */ static DECLARE_MUTEX(psmouse_sem); +static struct workqueue_struct *kpsmoused_wq; + struct psmouse_protocol { enum psmouse_type type; char *name; @@ -178,15 +188,79 @@ static psmouse_ret_t psmouse_process_byte(struct psmouse *psmouse, struct pt_reg } /* - * psmouse_interrupt() handles incoming characters, either gathering them into - * packets or passing them to the command routine as command output. + * __psmouse_set_state() sets new psmouse state and resets all flags. + */ + +static inline void __psmouse_set_state(struct psmouse *psmouse, enum psmouse_state new_state) +{ + psmouse->state = new_state; + psmouse->pktcnt = psmouse->out_of_sync = 0; + psmouse->ps2dev.flags = 0; + psmouse->last = jiffies; +} + + +/* + * psmouse_set_state() sets new psmouse state and resets all flags and + * counters while holding serio lock so fighting with interrupt handler + * is not a concern. + */ + +static void psmouse_set_state(struct psmouse *psmouse, enum psmouse_state new_state) +{ + serio_pause_rx(psmouse->ps2dev.serio); + __psmouse_set_state(psmouse, new_state); + serio_continue_rx(psmouse->ps2dev.serio); +} + +/* + * psmouse_handle_byte() processes one byte of the input data stream + * by calling corresponding protocol handler. + */ + +static int psmouse_handle_byte(struct psmouse *psmouse, struct pt_regs *regs) +{ + psmouse_ret_t rc = psmouse->protocol_handler(psmouse, regs); + + switch (rc) { + case PSMOUSE_BAD_DATA: + if (psmouse->state == PSMOUSE_ACTIVATED) { + printk(KERN_WARNING "psmouse.c: %s at %s lost sync at byte %d\n", + psmouse->name, psmouse->phys, psmouse->pktcnt); + if (++psmouse->out_of_sync == psmouse->resetafter) { + __psmouse_set_state(psmouse, PSMOUSE_IGNORE); + printk(KERN_NOTICE "psmouse.c: issuing reconnect request\n"); + serio_reconnect(psmouse->ps2dev.serio); + return -1; + } + } + psmouse->pktcnt = 0; + break; + + case PSMOUSE_FULL_PACKET: + psmouse->pktcnt = 0; + if (psmouse->out_of_sync) { + psmouse->out_of_sync = 0; + printk(KERN_NOTICE "psmouse.c: %s at %s - driver resynched.\n", + psmouse->name, psmouse->phys); + } + break; + + case PSMOUSE_GOOD_DATA: + break; + } + return 0; +} + +/* + * psmouse_interrupt() handles incoming characters, either passing them + * for normal processing or gathering them as command response. */ static irqreturn_t psmouse_interrupt(struct serio *serio, unsigned char data, unsigned int flags, struct pt_regs *regs) { struct psmouse *psmouse = serio_get_drvdata(serio); - psmouse_ret_t rc; if (psmouse->state == PSMOUSE_IGNORE) goto out; @@ -208,67 +282,58 @@ static irqreturn_t psmouse_interrupt(struct serio *serio, if (ps2_handle_response(&psmouse->ps2dev, data)) goto out; - if (psmouse->state == PSMOUSE_INITIALIZING) + if (psmouse->state <= PSMOUSE_RESYNCING) goto out; if (psmouse->state == PSMOUSE_ACTIVATED && psmouse->pktcnt && time_after(jiffies, psmouse->last + HZ/2)) { - printk(KERN_WARNING "psmouse.c: %s at %s lost synchronization, throwing %d bytes away.\n", + printk(KERN_INFO "psmouse.c: %s at %s lost synchronization, throwing %d bytes away.\n", psmouse->name, psmouse->phys, psmouse->pktcnt); - psmouse->pktcnt = 0; + psmouse->badbyte = psmouse->packet[0]; + __psmouse_set_state(psmouse, PSMOUSE_RESYNCING); + queue_work(kpsmoused_wq, &psmouse->resync_work); + goto out; } - psmouse->last = jiffies; psmouse->packet[psmouse->pktcnt++] = data; - - if (psmouse->packet[0] == PSMOUSE_RET_BAT) { +/* + * Check if this is a new device announcement (0xAA 0x00) + */ + if (unlikely(psmouse->packet[0] == PSMOUSE_RET_BAT && psmouse->pktcnt <= 2)) { if (psmouse->pktcnt == 1) goto out; - if (psmouse->pktcnt == 2) { - if (psmouse->packet[1] == PSMOUSE_RET_ID) { - psmouse->state = PSMOUSE_IGNORE; - serio_reconnect(serio); - goto out; - } - if (psmouse->type == PSMOUSE_SYNAPTICS) { - /* neither 0xAA nor 0x00 are valid first bytes - * for a packet in absolute mode - */ - psmouse->pktcnt = 0; - goto out; - } + if (psmouse->packet[1] == PSMOUSE_RET_ID) { + __psmouse_set_state(psmouse, PSMOUSE_IGNORE); + serio_reconnect(serio); + goto out; } - } - - rc = psmouse->protocol_handler(psmouse, regs); +/* + * Not a new device, try processing first byte normally + */ + psmouse->pktcnt = 1; + if (psmouse_handle_byte(psmouse, regs)) + goto out; - switch (rc) { - case PSMOUSE_BAD_DATA: - printk(KERN_WARNING "psmouse.c: %s at %s lost sync at byte %d\n", - psmouse->name, psmouse->phys, psmouse->pktcnt); - psmouse->pktcnt = 0; + psmouse->packet[psmouse->pktcnt++] = data; + } - if (++psmouse->out_of_sync == psmouse->resetafter) { - psmouse->state = PSMOUSE_IGNORE; - printk(KERN_NOTICE "psmouse.c: issuing reconnect request\n"); - serio_reconnect(psmouse->ps2dev.serio); - } - break; +/* + * See if we need to force resync because mouse was idle for too long + */ + if (psmouse->state == PSMOUSE_ACTIVATED && + psmouse->pktcnt == 1 && psmouse->resync_time && + time_after(jiffies, psmouse->last + psmouse->resync_time * HZ)) { + psmouse->badbyte = psmouse->packet[0]; + __psmouse_set_state(psmouse, PSMOUSE_RESYNCING); + queue_work(kpsmoused_wq, &psmouse->resync_work); + goto out; + } - case PSMOUSE_FULL_PACKET: - psmouse->pktcnt = 0; - if (psmouse->out_of_sync) { - psmouse->out_of_sync = 0; - printk(KERN_NOTICE "psmouse.c: %s at %s - driver resynched.\n", - psmouse->name, psmouse->phys); - } - break; + psmouse->last = jiffies; + psmouse_handle_byte(psmouse, regs); - case PSMOUSE_GOOD_DATA: - break; - } -out: + out: return IRQ_HANDLED; } @@ -752,21 +817,6 @@ static void psmouse_initialize(struct psmouse *psmouse) } /* - * psmouse_set_state() sets new psmouse state and resets all flags and - * counters while holding serio lock so fighting with interrupt handler - * is not a concern. - */ - -static void psmouse_set_state(struct psmouse *psmouse, enum psmouse_state new_state) -{ - serio_pause_rx(psmouse->ps2dev.serio); - psmouse->state = new_state; - psmouse->pktcnt = psmouse->out_of_sync = 0; - psmouse->ps2dev.flags = 0; - serio_continue_rx(psmouse->ps2dev.serio); -} - -/* * psmouse_activate() enables the mouse so that we get motion reports from it. */ @@ -794,6 +844,111 @@ static void psmouse_deactivate(struct psmouse *psmouse) psmouse_set_state(psmouse, PSMOUSE_CMD_MODE); } +/* + * psmouse_poll() - default poll hanlder. Everyone except for ALPS uses it. + */ + +static int psmouse_poll(struct psmouse *psmouse) +{ + return ps2_command(&psmouse->ps2dev, psmouse->packet, + PSMOUSE_CMD_POLL | (psmouse->pktsize << 8)); +} + + +/* + * psmouse_resync() attempts to re-validate current protocol. + */ + +static void psmouse_resync(void *p) +{ + struct psmouse *psmouse = p, *parent = NULL; + struct serio *serio = psmouse->ps2dev.serio; + psmouse_ret_t rc = PSMOUSE_GOOD_DATA; + int failed = 0, enabled = 0; + int i; + + down(&psmouse_sem); + + if (psmouse->state != PSMOUSE_RESYNCING) + goto out; + + if (serio->parent && serio->id.type == SERIO_PS_PSTHRU) { + parent = serio_get_drvdata(serio->parent); + psmouse_deactivate(parent); + } + +/* + * Some mice don't ACK commands sent while they are in the middle of + * transmitting motion packet. To avoid delay we use ps2_sendbyte() + * instead of ps2_command() which would wait for 200ms for an ACK + * that may never come. + * As an additional quirk ALPS touchpads may not only forget to ACK + * disable command but will stop reporting taps, so if we see that + * mouse at least once ACKs disable we will do full reconnect if ACK + * is missing. + */ + psmouse->num_resyncs++; + + if (ps2_sendbyte(&psmouse->ps2dev, PSMOUSE_CMD_DISABLE, 20)) { + if (psmouse->num_resyncs < 3 || psmouse->acks_disable_command) + failed = 1; + } else + psmouse->acks_disable_command = 1; + +/* + * Poll the mouse. If it was reset the packet will be shorter than + * psmouse->pktsize and ps2_command will fail. We do not expect and + * do not handle scenario when mouse "upgrades" its protocol while + * disconnected since it would require additional delay. If we ever + * see a mouse that does it we'll adjust the code. + */ + if (!failed) { + if (psmouse->poll(psmouse)) + failed = 1; + else { + psmouse_set_state(psmouse, PSMOUSE_CMD_MODE); + for (i = 0; i < psmouse->pktsize; i++) { + psmouse->pktcnt++; + rc = psmouse->protocol_handler(psmouse, NULL); + if (rc != PSMOUSE_GOOD_DATA) + break; + } + if (rc != PSMOUSE_FULL_PACKET) + failed = 1; + psmouse_set_state(psmouse, PSMOUSE_RESYNCING); + } + } +/* + * Now try to enable mouse. We try to do that even if poll failed and also + * repeat our attempts 5 times, otherwise we may be left out with disabled + * mouse. + */ + for (i = 0; i < 5; i++) { + if (!ps2_command(&psmouse->ps2dev, NULL, PSMOUSE_CMD_ENABLE)) { + enabled = 1; + break; + } + msleep(200); + } + + if (!enabled) { + printk(KERN_WARNING "psmouse.c: failed to re-enable mouse on %s\n", + psmouse->ps2dev.serio->phys); + failed = 1; + } + + if (failed) { + psmouse_set_state(psmouse, PSMOUSE_IGNORE); + printk(KERN_INFO "psmouse.c: resync failed, issuing reconnect request\n"); + serio_reconnect(serio); + } else + psmouse_set_state(psmouse, PSMOUSE_ACTIVATED); + + if (parent) + psmouse_activate(parent); + out: + up(&psmouse_sem); +} /* * psmouse_cleanup() resets the mouse into power-on state. @@ -822,6 +977,11 @@ static void psmouse_disconnect(struct serio *serio) psmouse_set_state(psmouse, PSMOUSE_CMD_MODE); + /* make sure we don't have a resync in progress */ + up(&psmouse_sem); + flush_workqueue(kpsmoused_wq); + down(&psmouse_sem); + if (serio->parent && serio->id.type == SERIO_PS_PSTHRU) { parent = serio_get_drvdata(serio->parent); psmouse_deactivate(parent); @@ -859,6 +1019,7 @@ static int psmouse_switch_protocol(struct psmouse *psmouse, struct psmouse_proto psmouse->set_rate = psmouse_set_rate; psmouse->set_resolution = psmouse_set_resolution; + psmouse->poll = psmouse_poll; psmouse->protocol_handler = psmouse_process_byte; psmouse->pktsize = 3; @@ -874,6 +1035,23 @@ static int psmouse_switch_protocol(struct psmouse *psmouse, struct psmouse_proto else psmouse->type = psmouse_extensions(psmouse, psmouse_max_proto, 1); + /* + * If mouse's packet size is 3 there is no point in polling the + * device in hopes to detect protocol reset - we won't get less + * than 3 bytes response anyhow. + */ + if (psmouse->pktsize == 3) + psmouse->resync_time = 0; + + /* + * Some smart KVMs fake response to POLL command returning just + * 3 bytes and messing up our resync logic, so if initial poll + * fails we won't try polling the device anymore. Hopefully + * such KVM will maintain initially selected protocol. + */ + if (psmouse->resync_time && psmouse->poll(psmouse)) + psmouse->resync_time = 0; + sprintf(psmouse->devname, "%s %s %s", psmouse_protocol_by_type(psmouse->type)->name, psmouse->vendor, psmouse->name); @@ -914,6 +1092,7 @@ static int psmouse_connect(struct serio *serio, struct serio_driver *drv) goto out; ps2_init(&psmouse->ps2dev, serio); + INIT_WORK(&psmouse->resync_work, psmouse_resync, psmouse); psmouse->dev = input_dev; sprintf(psmouse->phys, "%s/input0", serio->phys); @@ -934,6 +1113,7 @@ static int psmouse_connect(struct serio *serio, struct serio_driver *drv) psmouse->rate = psmouse_rate; psmouse->resolution = psmouse_resolution; psmouse->resetafter = psmouse_resetafter; + psmouse->resync_time = parent ? 0 : psmouse_resync_time; psmouse->smartscroll = psmouse_smartscroll; psmouse_switch_protocol(psmouse, NULL); @@ -1278,13 +1458,21 @@ static int psmouse_get_maxproto(char *buffer, struct kernel_param *kp) static int __init psmouse_init(void) { + kpsmoused_wq = create_singlethread_workqueue("kpsmoused"); + if (!kpsmoused_wq) { + printk(KERN_ERR "psmouse: failed to create kpsmoused workqueue\n"); + return -ENOMEM; + } + serio_register_driver(&psmouse_drv); + return 0; } static void __exit psmouse_exit(void) { serio_unregister_driver(&psmouse_drv); + destroy_workqueue(kpsmoused_wq); } module_init(psmouse_init); diff --git a/drivers/input/mouse/psmouse.h b/drivers/input/mouse/psmouse.h index 7c4192bd127..4d9107fba6a 100644 --- a/drivers/input/mouse/psmouse.h +++ b/drivers/input/mouse/psmouse.h @@ -7,7 +7,7 @@ #define PSMOUSE_CMD_GETINFO 0x03e9 #define PSMOUSE_CMD_SETSTREAM 0x00ea #define PSMOUSE_CMD_SETPOLL 0x00f0 -#define PSMOUSE_CMD_POLL 0x03eb +#define PSMOUSE_CMD_POLL 0x00eb /* caller sets number of bytes to receive */ #define PSMOUSE_CMD_GETID 0x02f2 #define PSMOUSE_CMD_SETRATE 0x10f3 #define PSMOUSE_CMD_ENABLE 0x00f4 @@ -23,6 +23,7 @@ enum psmouse_state { PSMOUSE_IGNORE, PSMOUSE_INITIALIZING, + PSMOUSE_RESYNCING, PSMOUSE_CMD_MODE, PSMOUSE_ACTIVATED, }; @@ -38,15 +39,19 @@ struct psmouse { void *private; struct input_dev *dev; struct ps2dev ps2dev; + struct work_struct resync_work; char *vendor; char *name; unsigned char packet[8]; + unsigned char badbyte; unsigned char pktcnt; unsigned char pktsize; unsigned char type; + unsigned char acks_disable_command; unsigned int model; unsigned long last; unsigned long out_of_sync; + unsigned long num_resyncs; enum psmouse_state state; char devname[64]; char phys[32]; @@ -54,6 +59,7 @@ struct psmouse { unsigned int rate; unsigned int resolution; unsigned int resetafter; + unsigned int resync_time; unsigned int smartscroll; /* Logitech only */ psmouse_ret_t (*protocol_handler)(struct psmouse *psmouse, struct pt_regs *regs); @@ -62,6 +68,7 @@ struct psmouse { int (*reconnect)(struct psmouse *psmouse); void (*disconnect)(struct psmouse *psmouse); + int (*poll)(struct psmouse *psmouse); void (*pt_activate)(struct psmouse *psmouse); void (*pt_deactivate)(struct psmouse *psmouse); diff --git a/drivers/input/mouse/synaptics.c b/drivers/input/mouse/synaptics.c index 97cdfd6acac..2051bec2c39 100644 --- a/drivers/input/mouse/synaptics.c +++ b/drivers/input/mouse/synaptics.c @@ -652,6 +652,8 @@ int synaptics_init(struct psmouse *psmouse) psmouse->disconnect = synaptics_disconnect; psmouse->reconnect = synaptics_reconnect; psmouse->pktsize = 6; + /* Synaptics can usually stay in sync without extra help */ + psmouse->resync_time = 0; if (SYN_CAP_PASS_THROUGH(priv->capabilities)) synaptics_pt_create(psmouse); diff --git a/drivers/input/serio/i8042-x86ia64io.h b/drivers/input/serio/i8042-x86ia64io.h index 2d2f9fb3ade..a4c6f352272 100644 --- a/drivers/input/serio/i8042-x86ia64io.h +++ b/drivers/input/serio/i8042-x86ia64io.h @@ -173,6 +173,13 @@ static struct dmi_system_id __initdata i8042_dmi_nomux_table[] = { DMI_MATCH(DMI_PRODUCT_NAME, "PC-MM20 Series"), }, }, + { + .ident = "Sony Vaio FS-115b", + .matches = { + DMI_MATCH(DMI_SYS_VENDOR, "Sony Corporation"), + DMI_MATCH(DMI_PRODUCT_NAME, "VGN-FS115B"), + }, + }, { } }; diff --git a/drivers/macintosh/macio-adb.c b/drivers/macintosh/macio-adb.c index cf6a6f2248a..314fc0830d9 100644 --- a/drivers/macintosh/macio-adb.c +++ b/drivers/macintosh/macio-adb.c @@ -17,6 +17,7 @@ #include <asm/irq.h> #include <asm/system.h> #include <linux/init.h> +#include <linux/ioport.h> struct preg { unsigned char r; @@ -88,24 +89,26 @@ int macio_probe(void) int macio_init(void) { struct device_node *adbs; + struct resource r; adbs = find_compatible_devices("adb", "chrp,adb0"); if (adbs == 0) return -ENXIO; #if 0 - { int i; + { int i = 0; printk("macio_adb_init: node = %p, addrs =", adbs->node); - for (i = 0; i < adbs->n_addrs; ++i) - printk(" %x(%x)", adbs->addrs[i].address, adbs->addrs[i].size); + while(!of_address_to_resource(adbs, i, &r)) + printk(" %x(%x)", r.start, r.end - r.start); printk(", intrs ="); for (i = 0; i < adbs->n_intrs; ++i) printk(" %x", adbs->intrs[i].line); printk("\n"); } #endif - - adb = ioremap(adbs->addrs->address, sizeof(struct adb_regs)); + if (of_address_to_resource(adbs, 0, &r)) + return -ENXIO; + adb = ioremap(r.start, sizeof(struct adb_regs)); out_8(&adb->ctrl.r, 0); out_8(&adb->intr.r, 0); diff --git a/drivers/sbus/char/aurora.c b/drivers/sbus/char/aurora.c index 92e6c5639dd..015db40ad8a 100644 --- a/drivers/sbus/char/aurora.c +++ b/drivers/sbus/char/aurora.c @@ -92,7 +92,6 @@ static struct Aurora_port aurora_port[AURORA_TNPORTS] = { /* no longer used. static struct Aurora_board * IRQ_to_board[16] = { NULL, } ;*/ static unsigned char * tmp_buf = NULL; -static DECLARE_MUTEX(tmp_buf_sem); DECLARE_TASK_QUEUE(tq_aurora); diff --git a/drivers/serial/68328serial.c b/drivers/serial/68328serial.c index 4dd5c3f9816..8cbf0fc5a22 100644 --- a/drivers/serial/68328serial.c +++ b/drivers/serial/68328serial.c @@ -143,7 +143,6 @@ static int m68328_console_cbaud = DEFAULT_CBAUD; * memory if large numbers of serial ports are open. */ static unsigned char tmp_buf[SERIAL_XMIT_SIZE]; /* This is cheating */ -DECLARE_MUTEX(tmp_buf_sem); static inline int serial_paranoia_check(struct m68k_serial *info, char *name, const char *routine) diff --git a/drivers/usb/input/Kconfig b/drivers/usb/input/Kconfig index 509dd0a04c5..5246b35301d 100644 --- a/drivers/usb/input/Kconfig +++ b/drivers/usb/input/Kconfig @@ -37,6 +37,16 @@ config USB_HIDINPUT If unsure, say Y. +config USB_HIDINPUT_POWERBOOK + bool "Enable support for iBook/PowerBook special keys" + default n + depends on USB_HIDINPUT + help + Say Y here if you want support for the special keys (Fn, Numlock) on + Apple iBooks and PowerBooks. + + If unsure, say N. + config HID_FF bool "Force feedback support (EXPERIMENTAL)" depends on USB_HIDINPUT && EXPERIMENTAL diff --git a/drivers/usb/input/hid-core.c b/drivers/usb/input/hid-core.c index 5f52979af1c..a91e72c4141 100644 --- a/drivers/usb/input/hid-core.c +++ b/drivers/usb/input/hid-core.c @@ -1450,6 +1450,9 @@ void hid_init_reports(struct hid_device *hid) #define USB_VENDOR_ID_APPLE 0x05ac #define USB_DEVICE_ID_APPLE_POWERMOUSE 0x0304 +#define USB_VENDOR_ID_CHERRY 0x046a +#define USB_DEVICE_ID_CHERRY_CYMOTION 0x0023 + /* * Alphabetically sorted blacklist by quirk type. */ @@ -1580,6 +1583,16 @@ static const struct hid_blacklist { { USB_VENDOR_ID_SAITEK, USB_DEVICE_ID_SAITEK_RUMBLEPAD, HID_QUIRK_BADPAD }, { USB_VENDOR_ID_TOPMAX, USB_DEVICE_ID_TOPMAX_COBRAPAD, HID_QUIRK_BADPAD }, + { USB_VENDOR_ID_CHERRY, USB_DEVICE_ID_CHERRY_CYMOTION, HID_QUIRK_CYMOTION }, + + { USB_VENDOR_ID_APPLE, 0x020E, HID_QUIRK_POWERBOOK_HAS_FN }, + { USB_VENDOR_ID_APPLE, 0x020F, HID_QUIRK_POWERBOOK_HAS_FN }, + { USB_VENDOR_ID_APPLE, 0x0214, HID_QUIRK_POWERBOOK_HAS_FN }, + { USB_VENDOR_ID_APPLE, 0x0215, HID_QUIRK_POWERBOOK_HAS_FN }, + { USB_VENDOR_ID_APPLE, 0x0216, HID_QUIRK_POWERBOOK_HAS_FN }, + { USB_VENDOR_ID_APPLE, 0x030A, HID_QUIRK_POWERBOOK_HAS_FN }, + { USB_VENDOR_ID_APPLE, 0x030B, HID_QUIRK_POWERBOOK_HAS_FN }, + { 0, 0 } }; @@ -1626,6 +1639,20 @@ static void hid_free_buffers(struct usb_device *dev, struct hid_device *hid) usb_buffer_free(dev, hid->bufsize, hid->ctrlbuf, hid->ctrlbuf_dma); } +/* + * Cherry Cymotion keyboard have an invalid HID report descriptor, + * that needs fixing before we can parse it. + */ + +static void hid_fixup_cymotion_descriptor(char *rdesc, int rsize) +{ + if (rsize >= 17 && rdesc[11] == 0x3c && rdesc[12] == 0x02) { + info("Fixing up Cherry Cymotion report descriptor"); + rdesc[11] = rdesc[16] = 0xff; + rdesc[12] = rdesc[17] = 0x03; + } +} + static struct hid_device *usb_hid_configure(struct usb_interface *intf) { struct usb_host_interface *interface = intf->cur_altsetting; @@ -1673,6 +1700,9 @@ static struct hid_device *usb_hid_configure(struct usb_interface *intf) return NULL; } + if ((quirks & HID_QUIRK_CYMOTION)) + hid_fixup_cymotion_descriptor(rdesc, rsize); + #ifdef DEBUG_DATA printk(KERN_DEBUG __FILE__ ": report descriptor (size %u, read %d) = ", rsize, n); for (n = 0; n < rsize; n++) diff --git a/drivers/usb/input/hid-input.c b/drivers/usb/input/hid-input.c index 192a03b2897..cb0d80f4925 100644 --- a/drivers/usb/input/hid-input.c +++ b/drivers/usb/input/hid-input.c @@ -73,6 +73,160 @@ static const struct { #define map_key_clear(c) do { map_key(c); clear_bit(c, bit); } while (0) #define map_ff_effect(c) do { set_bit(c, input->ffbit); } while (0) +#ifdef CONFIG_USB_HIDINPUT_POWERBOOK + +struct hidinput_key_translation { + u16 from; + u16 to; + u8 flags; +}; + +#define POWERBOOK_FLAG_FKEY 0x01 + +static struct hidinput_key_translation powerbook_fn_keys[] = { + { KEY_BACKSPACE, KEY_DELETE }, + { KEY_F1, KEY_BRIGHTNESSDOWN, POWERBOOK_FLAG_FKEY }, + { KEY_F2, KEY_BRIGHTNESSUP, POWERBOOK_FLAG_FKEY }, + { KEY_F3, KEY_MUTE, POWERBOOK_FLAG_FKEY }, + { KEY_F4, KEY_VOLUMEDOWN, POWERBOOK_FLAG_FKEY }, + { KEY_F5, KEY_VOLUMEUP, POWERBOOK_FLAG_FKEY }, + { KEY_F6, KEY_NUMLOCK, POWERBOOK_FLAG_FKEY }, + { KEY_F7, KEY_SWITCHVIDEOMODE, POWERBOOK_FLAG_FKEY }, + { KEY_F8, KEY_KBDILLUMTOGGLE, POWERBOOK_FLAG_FKEY }, + { KEY_F9, KEY_KBDILLUMDOWN, POWERBOOK_FLAG_FKEY }, + { KEY_F10, KEY_KBDILLUMUP, POWERBOOK_FLAG_FKEY }, + { KEY_UP, KEY_PAGEUP }, + { KEY_DOWN, KEY_PAGEDOWN }, + { KEY_LEFT, KEY_HOME }, + { KEY_RIGHT, KEY_END }, + { } +}; + +static struct hidinput_key_translation powerbook_numlock_keys[] = { + { KEY_J, KEY_KP1 }, + { KEY_K, KEY_KP2 }, + { KEY_L, KEY_KP3 }, + { KEY_U, KEY_KP4 }, + { KEY_I, KEY_KP5 }, + { KEY_O, KEY_KP6 }, + { KEY_7, KEY_KP7 }, + { KEY_8, KEY_KP8 }, + { KEY_9, KEY_KP9 }, + { KEY_M, KEY_KP0 }, + { KEY_DOT, KEY_KPDOT }, + { KEY_SLASH, KEY_KPPLUS }, + { KEY_SEMICOLON, KEY_KPMINUS }, + { KEY_P, KEY_KPASTERISK }, + { KEY_MINUS, KEY_KPEQUAL }, + { KEY_0, KEY_KPSLASH }, + { KEY_F6, KEY_NUMLOCK }, + { KEY_KPENTER, KEY_KPENTER }, + { KEY_BACKSPACE, KEY_BACKSPACE }, + { } +}; + +static int usbhid_pb_fnmode = 1; +module_param_named(pb_fnmode, usbhid_pb_fnmode, int, 0644); +MODULE_PARM_DESC(pb_fnmode, + "Mode of fn key on PowerBooks (0 = disabled, 1 = fkeyslast, 2 = fkeysfirst)"); + +static struct hidinput_key_translation *find_translation(struct hidinput_key_translation *table, u16 from) +{ + struct hidinput_key_translation *trans; + + /* Look for the translation */ + for (trans = table; trans->from; trans++) + if (trans->from == from) + return trans; + + return NULL; +} + +static int hidinput_pb_event(struct hid_device *hid, struct input_dev *input, + struct hid_usage *usage, __s32 value) +{ + struct hidinput_key_translation *trans; + + if (usage->code == KEY_FN) { + if (value) hid->quirks |= HID_QUIRK_POWERBOOK_FN_ON; + else hid->quirks &= ~HID_QUIRK_POWERBOOK_FN_ON; + + input_event(input, usage->type, usage->code, value); + + return 1; + } + + if (usbhid_pb_fnmode) { + int do_translate; + + trans = find_translation(powerbook_fn_keys, usage->code); + if (trans) { + if (test_bit(usage->code, hid->pb_pressed_fn)) + do_translate = 1; + else if (trans->flags & POWERBOOK_FLAG_FKEY) + do_translate = + (usbhid_pb_fnmode == 2 && (hid->quirks & HID_QUIRK_POWERBOOK_FN_ON)) || + (usbhid_pb_fnmode == 1 && !(hid->quirks & HID_QUIRK_POWERBOOK_FN_ON)); + else + do_translate = (hid->quirks & HID_QUIRK_POWERBOOK_FN_ON); + + if (do_translate) { + if (value) + set_bit(usage->code, hid->pb_pressed_fn); + else + clear_bit(usage->code, hid->pb_pressed_fn); + + input_event(input, usage->type, trans->to, value); + + return 1; + } + } + + if (test_bit(usage->code, hid->pb_pressed_numlock) || + test_bit(LED_NUML, input->led)) { + trans = find_translation(powerbook_numlock_keys, usage->code); + + if (trans) { + if (value) + set_bit(usage->code, hid->pb_pressed_numlock); + else + clear_bit(usage->code, hid->pb_pressed_numlock); + + input_event(input, usage->type, trans->to, value); + } + + return 1; + } + } + + return 0; +} + +static void hidinput_pb_setup(struct input_dev *input) +{ + struct hidinput_key_translation *trans; + + set_bit(KEY_NUMLOCK, input->keybit); + + /* Enable all needed keys */ + for (trans = powerbook_fn_keys; trans->from; trans++) + set_bit(trans->to, input->keybit); + + for (trans = powerbook_numlock_keys; trans->from; trans++) + set_bit(trans->to, input->keybit); +} +#else +static inline int hidinput_pb_event(struct hid_device *hid, struct input_dev *input, + struct hid_usage *usage, __s32 value) +{ + return 0; +} + +static inline void hidinput_pb_setup(struct input_dev *input) +{ +} +#endif + static void hidinput_configure_usage(struct hid_input *hidinput, struct hid_field *field, struct hid_usage *usage) { @@ -135,8 +289,11 @@ static void hidinput_configure_usage(struct hid_input *hidinput, struct hid_fiel case HID_UP_SIMULATION: switch (usage->hid & 0xffff) { - case 0xba: map_abs(ABS_RUDDER); break; + case 0xba: map_abs(ABS_RUDDER); break; case 0xbb: map_abs(ABS_THROTTLE); break; + case 0xc4: map_abs(ABS_GAS); break; + case 0xc5: map_abs(ABS_BRAKE); break; + case 0xc8: map_abs(ABS_WHEEL); break; default: goto ignore; } break; @@ -289,11 +446,19 @@ static void hidinput_configure_usage(struct hid_input *hidinput, struct hid_fiel case 0x226: map_key_clear(KEY_STOP); break; case 0x227: map_key_clear(KEY_REFRESH); break; case 0x22a: map_key_clear(KEY_BOOKMARKS); break; + case 0x233: map_key_clear(KEY_SCROLLUP); break; + case 0x234: map_key_clear(KEY_SCROLLDOWN); break; case 0x238: map_rel(REL_HWHEEL); break; case 0x279: map_key_clear(KEY_REDO); break; case 0x289: map_key_clear(KEY_REPLY); break; case 0x28b: map_key_clear(KEY_FORWARDMAIL); break; case 0x28c: map_key_clear(KEY_SEND); break; + + /* Reported on a Cherry Cymotion keyboard */ + case 0x301: map_key_clear(KEY_PROG1); break; + case 0x302: map_key_clear(KEY_PROG2); break; + case 0x303: map_key_clear(KEY_PROG3); break; + default: goto ignore; } break; @@ -325,7 +490,12 @@ static void hidinput_configure_usage(struct hid_input *hidinput, struct hid_fiel set_bit(EV_REP, input->evbit); switch(usage->hid & HID_USAGE) { - case 0x003: map_key_clear(KEY_FN); break; + case 0x003: + /* The fn key on Apple PowerBooks */ + map_key_clear(KEY_FN); + hidinput_pb_setup(input); + break; + default: goto ignore; } break; @@ -482,6 +652,9 @@ void hidinput_hid_event(struct hid_device *hid, struct hid_field *field, struct return; } + if ((hid->quirks & HID_QUIRK_POWERBOOK_HAS_FN) && hidinput_pb_event(hid, input, usage, value)) + return; + if (usage->hat_min < usage->hat_max || usage->hat_dir) { int hat_dir = usage->hat_dir; if (!hat_dir) @@ -524,7 +697,7 @@ void hidinput_hid_event(struct hid_device *hid, struct hid_field *field, struct return; } - if((usage->type == EV_KEY) && (usage->code == 0)) /* Key 0 is "unassigned", not KEY_UNKNOWN */ + if ((usage->type == EV_KEY) && (usage->code == 0)) /* Key 0 is "unassigned", not KEY_UNKNOWN */ return; input_event(input, usage->type, usage->code, value); diff --git a/drivers/usb/input/hid.h b/drivers/usb/input/hid.h index ee48a227610..8b0d4346ce9 100644 --- a/drivers/usb/input/hid.h +++ b/drivers/usb/input/hid.h @@ -235,17 +235,20 @@ struct hid_item { * HID device quirks. */ -#define HID_QUIRK_INVERT 0x001 -#define HID_QUIRK_NOTOUCH 0x002 -#define HID_QUIRK_IGNORE 0x004 -#define HID_QUIRK_NOGET 0x008 -#define HID_QUIRK_HIDDEV 0x010 -#define HID_QUIRK_BADPAD 0x020 -#define HID_QUIRK_MULTI_INPUT 0x040 -#define HID_QUIRK_2WHEEL_MOUSE_HACK_7 0x080 -#define HID_QUIRK_2WHEEL_MOUSE_HACK_5 0x100 -#define HID_QUIRK_2WHEEL_MOUSE_HACK_ON 0x200 -#define HID_QUIRK_2WHEEL_POWERMOUSE 0x400 +#define HID_QUIRK_INVERT 0x00000001 +#define HID_QUIRK_NOTOUCH 0x00000002 +#define HID_QUIRK_IGNORE 0x00000004 +#define HID_QUIRK_NOGET 0x00000008 +#define HID_QUIRK_HIDDEV 0x00000010 +#define HID_QUIRK_BADPAD 0x00000020 +#define HID_QUIRK_MULTI_INPUT 0x00000040 +#define HID_QUIRK_2WHEEL_MOUSE_HACK_7 0x00000080 +#define HID_QUIRK_2WHEEL_MOUSE_HACK_5 0x00000100 +#define HID_QUIRK_2WHEEL_MOUSE_HACK_ON 0x00000200 +#define HID_QUIRK_2WHEEL_POWERMOUSE 0x00000400 +#define HID_QUIRK_CYMOTION 0x00000800 +#define HID_QUIRK_POWERBOOK_HAS_FN 0x00001000 +#define HID_QUIRK_POWERBOOK_FN_ON 0x00002000 /* * This is the global environment of the parser. This information is @@ -431,6 +434,11 @@ struct hid_device { /* device report descriptor */ void (*ff_exit)(struct hid_device*); /* Called by hid_exit_ff(hid) */ int (*ff_event)(struct hid_device *hid, struct input_dev *input, unsigned int type, unsigned int code, int value); + +#ifdef CONFIG_USB_HIDINPUT_POWERBOOK + unsigned long pb_pressed_fn[NBITS(KEY_MAX)]; + unsigned long pb_pressed_numlock[NBITS(KEY_MAX)]; +#endif }; #define HID_GLOBAL_STACK_SIZE 4 diff --git a/drivers/usb/input/pid.c b/drivers/usb/input/pid.c index 19e015d171a..d9d9f656b8c 100644 --- a/drivers/usb/input/pid.c +++ b/drivers/usb/input/pid.c @@ -259,7 +259,7 @@ static int hid_pid_upload_effect(struct input_dev *dev, int hid_pid_init(struct hid_device *hid) { struct hid_ff_pid *private; - struct hid_input *hidinput = list_entry(&hid->inputs, struct hid_input, list); + struct hid_input *hidinput = list_entry(hid->inputs.next, struct hid_input, list); struct input_dev *input_dev = hidinput->input; private = hid->ff_private = kzalloc(sizeof(struct hid_ff_pid), GFP_KERNEL); diff --git a/drivers/usb/input/wacom.c b/drivers/usb/input/wacom.c index 48df4cfd5a4..d3e15df9e81 100644 --- a/drivers/usb/input/wacom.c +++ b/drivers/usb/input/wacom.c @@ -95,7 +95,7 @@ MODULE_LICENSE(DRIVER_LICENSE); enum { PENPARTNER = 0, GRAPHIRE, - G4, + WACOM_G4, PL, INTUOS, INTUOS3, @@ -373,7 +373,7 @@ static void wacom_graphire_irq(struct urb *urb, struct pt_regs *regs) case 2: /* Mouse with wheel */ input_report_key(dev, BTN_MIDDLE, data[1] & 0x04); - if (wacom->features->type == G4) { + if (wacom->features->type == WACOM_G4) { rw = data[7] & 0x04 ? -(data[7] & 0x03) : (data[7] & 0x03); input_report_rel(dev, REL_WHEEL, rw); } else @@ -385,7 +385,7 @@ static void wacom_graphire_irq(struct urb *urb, struct pt_regs *regs) id = CURSOR_DEVICE_ID; input_report_key(dev, BTN_LEFT, data[1] & 0x01); input_report_key(dev, BTN_RIGHT, data[1] & 0x02); - if (wacom->features->type == G4) + if (wacom->features->type == WACOM_G4) input_report_abs(dev, ABS_DISTANCE, data[6]); else input_report_abs(dev, ABS_DISTANCE, data[7]); @@ -410,7 +410,7 @@ static void wacom_graphire_irq(struct urb *urb, struct pt_regs *regs) input_sync(dev); /* send pad data */ - if (wacom->features->type == G4) { + if (wacom->features->type == WACOM_G4) { /* fist time sending pad data */ if (wacom->tool[1] != BTN_TOOL_FINGER) { wacom->id[1] = 0; @@ -713,8 +713,8 @@ static struct wacom_features wacom_features[] = { { "Wacom Graphire2 5x7", 8, 13918, 10206, 511, 32, GRAPHIRE, wacom_graphire_irq }, { "Wacom Graphire3", 8, 10208, 7424, 511, 32, GRAPHIRE, wacom_graphire_irq }, { "Wacom Graphire3 6x8", 8, 16704, 12064, 511, 32, GRAPHIRE, wacom_graphire_irq }, - { "Wacom Graphire4 4x5", 8, 10208, 7424, 511, 32, G4, wacom_graphire_irq }, - { "Wacom Graphire4 6x8", 8, 16704, 12064, 511, 32, G4, wacom_graphire_irq }, + { "Wacom Graphire4 4x5", 8, 10208, 7424, 511, 32, WACOM_G4, wacom_graphire_irq }, + { "Wacom Graphire4 6x8", 8, 16704, 12064, 511, 32, WACOM_G4, wacom_graphire_irq }, { "Wacom Volito", 8, 5104, 3712, 511, 32, GRAPHIRE, wacom_graphire_irq }, { "Wacom PenStation2", 8, 3250, 2320, 255, 32, GRAPHIRE, wacom_graphire_irq }, { "Wacom Volito2 4x5", 8, 5104, 3712, 511, 32, GRAPHIRE, wacom_graphire_irq }, @@ -859,7 +859,7 @@ static int wacom_probe(struct usb_interface *intf, const struct usb_device_id *i input_set_abs_params(input_dev, ABS_PRESSURE, 0, wacom->features->pressure_max, 0, 0); switch (wacom->features->type) { - case G4: + case WACOM_G4: input_dev->evbit[0] |= BIT(EV_MSC); input_dev->mscbit[0] |= BIT(MSC_SERIAL); input_dev->keybit[LONG(BTN_DIGI)] |= BIT(BTN_TOOL_FINGER); diff --git a/drivers/usb/serial/pl2303.c b/drivers/usb/serial/pl2303.c index 9ffff193823..0eb883f44ad 100644 --- a/drivers/usb/serial/pl2303.c +++ b/drivers/usb/serial/pl2303.c @@ -43,8 +43,6 @@ static int debug; #define PL2303_BUF_SIZE 1024 #define PL2303_TMP_BUF_SIZE 1024 -static DECLARE_MUTEX(pl2303_tmp_buf_sem); - struct pl2303_buf { unsigned int buf_size; char *buf_buf; diff --git a/fs/proc/proc_devtree.c b/fs/proc/proc_devtree.c index fb117b74809..9bdd077d6f5 100644 --- a/fs/proc/proc_devtree.c +++ b/fs/proc/proc_devtree.c @@ -81,6 +81,30 @@ void proc_device_tree_add_prop(struct proc_dir_entry *pde, struct property *prop __proc_device_tree_add_prop(pde, prop); } +void proc_device_tree_remove_prop(struct proc_dir_entry *pde, + struct property *prop) +{ + remove_proc_entry(prop->name, pde); +} + +void proc_device_tree_update_prop(struct proc_dir_entry *pde, + struct property *newprop, + struct property *oldprop) +{ + struct proc_dir_entry *ent; + + for (ent = pde->subdir; ent != NULL; ent = ent->next) + if (ent->data == oldprop) + break; + if (ent == NULL) { + printk(KERN_WARNING "device-tree: property \"%s\" " + " does not exist\n", oldprop->name); + } else { + ent->data = newprop; + ent->size = newprop->length; + } +} + /* * Process a node, adding entries for its children and its properties. */ diff --git a/fs/ufs/balloc.c b/fs/ufs/balloc.c index a9f4421ddb6..3ada9dcf55b 100644 --- a/fs/ufs/balloc.c +++ b/fs/ufs/balloc.c @@ -49,7 +49,7 @@ void ufs_free_fragments (struct inode * inode, unsigned fragment, unsigned count sb = inode->i_sb; uspi = UFS_SB(sb)->s_uspi; - usb1 = ubh_get_usb_first(USPI_UBH); + usb1 = ubh_get_usb_first(uspi); UFSD(("ENTER, fragment %u, count %u\n", fragment, count)) @@ -81,8 +81,9 @@ void ufs_free_fragments (struct inode * inode, unsigned fragment, unsigned count for (i = bit; i < end_bit; i++) { if (ubh_isclr (UCPI_UBH, ucpi->c_freeoff, i)) ubh_setbit (UCPI_UBH, ucpi->c_freeoff, i); - else ufs_error (sb, "ufs_free_fragments", - "bit already cleared for fragment %u", i); + else + ufs_error (sb, "ufs_free_fragments", + "bit already cleared for fragment %u", i); } DQUOT_FREE_BLOCK (inode, count); @@ -143,7 +144,7 @@ void ufs_free_blocks (struct inode * inode, unsigned fragment, unsigned count) { sb = inode->i_sb; uspi = UFS_SB(sb)->s_uspi; - usb1 = ubh_get_usb_first(USPI_UBH); + usb1 = ubh_get_usb_first(uspi); UFSD(("ENTER, fragment %u, count %u\n", fragment, count)) @@ -247,7 +248,7 @@ unsigned ufs_new_fragments (struct inode * inode, __fs32 * p, unsigned fragment, sb = inode->i_sb; uspi = UFS_SB(sb)->s_uspi; - usb1 = ubh_get_usb_first(USPI_UBH); + usb1 = ubh_get_usb_first(uspi); *err = -ENOSPC; lock_super (sb); @@ -407,7 +408,7 @@ ufs_add_fragments (struct inode * inode, unsigned fragment, sb = inode->i_sb; uspi = UFS_SB(sb)->s_uspi; - usb1 = ubh_get_usb_first (USPI_UBH); + usb1 = ubh_get_usb_first (uspi); count = newcount - oldcount; cgno = ufs_dtog(fragment); @@ -490,7 +491,7 @@ static unsigned ufs_alloc_fragments (struct inode * inode, unsigned cgno, sb = inode->i_sb; uspi = UFS_SB(sb)->s_uspi; - usb1 = ubh_get_usb_first(USPI_UBH); + usb1 = ubh_get_usb_first(uspi); oldcg = cgno; /* @@ -606,7 +607,7 @@ static unsigned ufs_alloccg_block (struct inode * inode, sb = inode->i_sb; uspi = UFS_SB(sb)->s_uspi; - usb1 = ubh_get_usb_first(USPI_UBH); + usb1 = ubh_get_usb_first(uspi); ucg = ubh_get_ucg(UCPI_UBH); if (goal == 0) { @@ -663,7 +664,7 @@ static unsigned ufs_bitmap_search (struct super_block * sb, UFSD(("ENTER, cg %u, goal %u, count %u\n", ucpi->c_cgx, goal, count)) uspi = UFS_SB(sb)->s_uspi; - usb1 = ubh_get_usb_first (USPI_UBH); + usb1 = ubh_get_usb_first (uspi); ucg = ubh_get_ucg(UCPI_UBH); if (goal) diff --git a/fs/ufs/ialloc.c b/fs/ufs/ialloc.c index 0938945b9cb..c7a47ed4f43 100644 --- a/fs/ufs/ialloc.c +++ b/fs/ufs/ialloc.c @@ -72,7 +72,7 @@ void ufs_free_inode (struct inode * inode) sb = inode->i_sb; uspi = UFS_SB(sb)->s_uspi; - usb1 = ubh_get_usb_first(USPI_UBH); + usb1 = ubh_get_usb_first(uspi); ino = inode->i_ino; @@ -167,7 +167,7 @@ struct inode * ufs_new_inode(struct inode * dir, int mode) ufsi = UFS_I(inode); sbi = UFS_SB(sb); uspi = sbi->s_uspi; - usb1 = ubh_get_usb_first(USPI_UBH); + usb1 = ubh_get_usb_first(uspi); lock_super (sb); diff --git a/fs/ufs/inode.c b/fs/ufs/inode.c index 55f4aa16e3f..e0c04e36a05 100644 --- a/fs/ufs/inode.c +++ b/fs/ufs/inode.c @@ -61,7 +61,7 @@ static int ufs_block_to_path(struct inode *inode, sector_t i_block, sector_t off int n = 0; - UFSD(("ptrs=uspi->s_apb = %d,double_blocks=%d \n",ptrs,double_blocks)); + UFSD(("ptrs=uspi->s_apb = %d,double_blocks=%ld \n",ptrs,double_blocks)); if (i_block < 0) { ufs_warning(inode->i_sb, "ufs_block_to_path", "block < 0"); } else if (i_block < direct_blocks) { @@ -104,7 +104,7 @@ u64 ufs_frag_map(struct inode *inode, sector_t frag) unsigned flags = UFS_SB(sb)->s_flags; u64 temp = 0L; - UFSD((": frag = %lu depth = %d\n",frag,depth)); + UFSD((": frag = %llu depth = %d\n", (unsigned long long)frag, depth)); UFSD((": uspi->s_fpbshift = %d ,uspi->s_apbmask = %x, mask=%llx\n",uspi->s_fpbshift,uspi->s_apbmask,mask)); if (depth == 0) @@ -365,9 +365,10 @@ repeat: sync_dirty_buffer(bh); inode->i_ctime = CURRENT_TIME_SEC; mark_inode_dirty(inode); + UFSD(("result %u\n", tmp + blockoff)); out: brelse (bh); - UFSD(("EXIT, result %u\n", tmp + blockoff)) + UFSD(("EXIT\n")); return result; } @@ -386,7 +387,7 @@ static int ufs_getfrag_block (struct inode *inode, sector_t fragment, struct buf if (!create) { phys64 = ufs_frag_map(inode, fragment); - UFSD(("phys64 = %lu \n",phys64)); + UFSD(("phys64 = %llu \n",phys64)); if (phys64) map_bh(bh_result, sb, phys64); return 0; @@ -401,7 +402,7 @@ static int ufs_getfrag_block (struct inode *inode, sector_t fragment, struct buf lock_kernel(); - UFSD(("ENTER, ino %lu, fragment %u\n", inode->i_ino, fragment)) + UFSD(("ENTER, ino %lu, fragment %llu\n", inode->i_ino, (unsigned long long)fragment)) if (fragment < 0) goto abort_negative; if (fragment > diff --git a/fs/ufs/super.c b/fs/ufs/super.c index e9a42c711a9..d4aacee593f 100644 --- a/fs/ufs/super.c +++ b/fs/ufs/super.c @@ -221,7 +221,7 @@ void ufs_error (struct super_block * sb, const char * function, va_list args; uspi = UFS_SB(sb)->s_uspi; - usb1 = ubh_get_usb_first(USPI_UBH); + usb1 = ubh_get_usb_first(uspi); if (!(sb->s_flags & MS_RDONLY)) { usb1->fs_clean = UFS_FSBAD; @@ -253,7 +253,7 @@ void ufs_panic (struct super_block * sb, const char * function, va_list args; uspi = UFS_SB(sb)->s_uspi; - usb1 = ubh_get_usb_first(USPI_UBH); + usb1 = ubh_get_usb_first(uspi); if (!(sb->s_flags & MS_RDONLY)) { usb1->fs_clean = UFS_FSBAD; @@ -420,21 +420,18 @@ static int ufs_read_cylinder_structures (struct super_block *sb) { if (i + uspi->s_fpb > blks) size = (blks - i) * uspi->s_fsize; - if ((flags & UFS_TYPE_MASK) == UFS_TYPE_UFS2) { + if ((flags & UFS_TYPE_MASK) == UFS_TYPE_UFS2) ubh = ubh_bread(sb, fs64_to_cpu(sb, usb->fs_u11.fs_u2.fs_csaddr) + i, size); - if (!ubh) - goto failed; - ubh_ubhcpymem (space, ubh, size); - sbi->s_csp[ufs_fragstoblks(i)]=(struct ufs_csum *)space; - } - else { + else ubh = ubh_bread(sb, uspi->s_csaddr + i, size); - if (!ubh) - goto failed; - ubh_ubhcpymem(space, ubh, size); - sbi->s_csp[ufs_fragstoblks(i)]=(struct ufs_csum *)space; - } + + if (!ubh) + goto failed; + + ubh_ubhcpymem (space, ubh, size); + sbi->s_csp[ufs_fragstoblks(i)]=(struct ufs_csum *)space; + space += size; ubh_brelse (ubh); ubh = NULL; @@ -539,6 +536,7 @@ static int ufs_fill_super(struct super_block *sb, void *data, int silent) struct inode *inode; unsigned block_size, super_block_size; unsigned flags; + unsigned super_block_offset; uspi = NULL; ubh = NULL; @@ -586,10 +584,11 @@ static int ufs_fill_super(struct super_block *sb, void *data, int silent) if (!uspi) goto failed; + super_block_offset=UFS_SBLOCK; + /* Keep 2Gig file limit. Some UFS variants need to override this but as I don't know which I'll let those in the know loosen the rules */ - switch (sbi->s_mount_opt & UFS_MOUNT_UFSTYPE) { case UFS_MOUNT_UFSTYPE_44BSD: UFSD(("ufstype=44bsd\n")) @@ -601,7 +600,8 @@ static int ufs_fill_super(struct super_block *sb, void *data, int silent) flags |= UFS_DE_44BSD | UFS_UID_44BSD | UFS_ST_44BSD | UFS_CG_44BSD; break; case UFS_MOUNT_UFSTYPE_UFS2: - UFSD(("ufstype=ufs2\n")) + UFSD(("ufstype=ufs2\n")); + super_block_offset=SBLOCK_UFS2; uspi->s_fsize = block_size = 512; uspi->s_fmask = ~(512 - 1); uspi->s_fshift = 9; @@ -725,19 +725,16 @@ again: /* * read ufs super block from device */ - if ( (flags & UFS_TYPE_MASK) == UFS_TYPE_UFS2) { - ubh = ubh_bread_uspi(uspi, sb, uspi->s_sbbase + SBLOCK_UFS2/block_size, super_block_size); - } - else { - ubh = ubh_bread_uspi(uspi, sb, uspi->s_sbbase + UFS_SBLOCK/block_size, super_block_size); - } + + ubh = ubh_bread_uspi(uspi, sb, uspi->s_sbbase + super_block_offset/block_size, super_block_size); + if (!ubh) goto failed; - usb1 = ubh_get_usb_first(USPI_UBH); - usb2 = ubh_get_usb_second(USPI_UBH); - usb3 = ubh_get_usb_third(USPI_UBH); + usb1 = ubh_get_usb_first(uspi); + usb2 = ubh_get_usb_second(uspi); + usb3 = ubh_get_usb_third(uspi); usb = (struct ufs_super_block *) ((struct ufs_buffer_head *)uspi)->bh[0]->b_data ; @@ -1006,8 +1003,8 @@ static void ufs_write_super (struct super_block *sb) { UFSD(("ENTER\n")) flags = UFS_SB(sb)->s_flags; uspi = UFS_SB(sb)->s_uspi; - usb1 = ubh_get_usb_first(USPI_UBH); - usb3 = ubh_get_usb_third(USPI_UBH); + usb1 = ubh_get_usb_first(uspi); + usb3 = ubh_get_usb_third(uspi); if (!(sb->s_flags & MS_RDONLY)) { usb1->fs_time = cpu_to_fs32(sb, get_seconds()); @@ -1049,8 +1046,8 @@ static int ufs_remount (struct super_block *sb, int *mount_flags, char *data) uspi = UFS_SB(sb)->s_uspi; flags = UFS_SB(sb)->s_flags; - usb1 = ubh_get_usb_first(USPI_UBH); - usb3 = ubh_get_usb_third(USPI_UBH); + usb1 = ubh_get_usb_first(uspi); + usb3 = ubh_get_usb_third(uspi); /* * Allow the "check" option to be passed as a remount option. @@ -1124,7 +1121,7 @@ static int ufs_statfs (struct super_block *sb, struct kstatfs *buf) lock_kernel(); uspi = UFS_SB(sb)->s_uspi; - usb1 = ubh_get_usb_first (USPI_UBH); + usb1 = ubh_get_usb_first (uspi); usb = (struct ufs_super_block *) ((struct ufs_buffer_head *)uspi)->bh[0]->b_data ; diff --git a/fs/ufs/util.h b/fs/ufs/util.h index e45ad537987..48d6d9bcc15 100644 --- a/fs/ufs/util.h +++ b/fs/ufs/util.h @@ -249,18 +249,28 @@ extern void _ubh_memcpyubh_(struct ufs_sb_private_info *, struct ufs_buffer_head /* - * macros to get important structures from ufs_buffer_head + * macros and inline function to get important structures from ufs_sb_private_info */ -#define ubh_get_usb_first(ubh) \ - ((struct ufs_super_block_first *)((ubh)->bh[0]->b_data)) -#define ubh_get_usb_second(ubh) \ - ((struct ufs_super_block_second *)((ubh)->\ - bh[UFS_SECTOR_SIZE >> uspi->s_fshift]->b_data + (UFS_SECTOR_SIZE & ~uspi->s_fmask))) +static inline void *get_usb_offset(struct ufs_sb_private_info *uspi, + unsigned int offset) +{ + unsigned int index; + + index = offset >> uspi->s_fshift; + offset &= ~uspi->s_fmask; + return uspi->s_ubh.bh[index]->b_data + offset; +} + +#define ubh_get_usb_first(uspi) \ + ((struct ufs_super_block_first *)get_usb_offset((uspi), 0)) + +#define ubh_get_usb_second(uspi) \ + ((struct ufs_super_block_second *)get_usb_offset((uspi), UFS_SECTOR_SIZE)) + +#define ubh_get_usb_third(uspi) \ + ((struct ufs_super_block_third *)get_usb_offset((uspi), 2*UFS_SECTOR_SIZE)) -#define ubh_get_usb_third(ubh) \ - ((struct ufs_super_block_third *)((ubh)-> \ - bh[UFS_SECTOR_SIZE*2 >> uspi->s_fshift]->b_data + (UFS_SECTOR_SIZE*2 & ~uspi->s_fmask))) #define ubh_get_ucg(ubh) \ ((struct ufs_cylinder_group *)((ubh)->bh[0]->b_data)) diff --git a/include/asm-ia64/kprobes.h b/include/asm-ia64/kprobes.h index a74b6810455..8c0fc227f0f 100644 --- a/include/asm-ia64/kprobes.h +++ b/include/asm-ia64/kprobes.h @@ -68,10 +68,14 @@ struct prev_kprobe { unsigned long status; }; +#define MAX_PARAM_RSE_SIZE (0x60+0x60/0x3f) /* per-cpu kprobe control block */ struct kprobe_ctlblk { unsigned long kprobe_status; struct pt_regs jprobe_saved_regs; + unsigned long jprobes_saved_stacked_regs[MAX_PARAM_RSE_SIZE]; + unsigned long *bsp; + unsigned long cfm; struct prev_kprobe prev_kprobe; }; @@ -118,5 +122,7 @@ extern int kprobe_exceptions_notify(struct notifier_block *self, static inline void jprobe_return(void) { } +extern void invalidate_stacked_regs(void); +extern void flush_register_stack(void); #endif /* _ASM_KPROBES_H */ diff --git a/include/asm-ia64/sn/sn_sal.h b/include/asm-ia64/sn/sn_sal.h index 2a8b0d92a5d..8b9e10e7cdb 100644 --- a/include/asm-ia64/sn/sn_sal.h +++ b/include/asm-ia64/sn/sn_sal.h @@ -75,7 +75,8 @@ #define SN_SAL_IOIF_GET_HUBDEV_INFO 0x02000055 #define SN_SAL_IOIF_GET_PCIBUS_INFO 0x02000056 #define SN_SAL_IOIF_GET_PCIDEV_INFO 0x02000057 -#define SN_SAL_IOIF_GET_WIDGET_DMAFLUSH_LIST 0x02000058 +#define SN_SAL_IOIF_GET_WIDGET_DMAFLUSH_LIST 0x02000058 // deprecated +#define SN_SAL_IOIF_GET_DEVICE_DMAFLUSH_LIST 0x0200005a #define SN_SAL_HUB_ERROR_INTERRUPT 0x02000060 #define SN_SAL_BTE_RECOVER 0x02000061 @@ -1100,7 +1101,7 @@ ia64_sn_bte_recovery(nasid_t nasid) struct ia64_sal_retval rv; rv.status = 0; - SAL_CALL_NOLOCK(rv, SN_SAL_BTE_RECOVER, 0, 0, 0, 0, 0, 0, 0); + SAL_CALL_NOLOCK(rv, SN_SAL_BTE_RECOVER, (u64)nasid, 0, 0, 0, 0, 0, 0); if (rv.status == SALRET_NOT_IMPLEMENTED) return 0; return (int) rv.status; diff --git a/include/asm-ia64/sn/xp.h b/include/asm-ia64/sn/xp.h index 49faf8f2643..203945ae034 100644 --- a/include/asm-ia64/sn/xp.h +++ b/include/asm-ia64/sn/xp.h @@ -227,7 +227,9 @@ enum xpc_retval { xpcOpenCloseError, /* 50: channel open/close protocol error */ - xpcUnknownReason /* 51: unknown reason -- must be last in list */ + xpcDisconnected, /* 51: channel disconnected (closed) */ + + xpcUnknownReason /* 52: unknown reason -- must be last in list */ }; diff --git a/arch/ia64/sn/kernel/xpc.h b/include/asm-ia64/sn/xpc.h index 5483a9f227d..87e9cd58851 100644 --- a/arch/ia64/sn/kernel/xpc.h +++ b/include/asm-ia64/sn/xpc.h @@ -3,7 +3,7 @@ * License. See the file "COPYING" in the main directory of this archive * for more details. * - * Copyright (c) 2004-2005 Silicon Graphics, Inc. All Rights Reserved. + * Copyright (c) 2004-2006 Silicon Graphics, Inc. All Rights Reserved. */ @@ -11,8 +11,8 @@ * Cross Partition Communication (XPC) structures and macros. */ -#ifndef _IA64_SN_KERNEL_XPC_H -#define _IA64_SN_KERNEL_XPC_H +#ifndef _ASM_IA64_SN_XPC_H +#define _ASM_IA64_SN_XPC_H #include <linux/config.h> @@ -663,6 +663,7 @@ extern struct xpc_registration xpc_registrations[]; extern struct device *xpc_part; extern struct device *xpc_chan; extern int xpc_disengage_request_timelimit; +extern int xpc_disengage_request_timedout; extern irqreturn_t xpc_notify_IRQ_handler(int, void *, struct pt_regs *); extern void xpc_dropped_IPI_check(struct xpc_partition *); extern void xpc_activate_partition(struct xpc_partition *); @@ -707,7 +708,7 @@ extern void xpc_connected_callout(struct xpc_channel *); extern void xpc_deliver_msg(struct xpc_channel *); extern void xpc_disconnect_channel(const int, struct xpc_channel *, enum xpc_retval, unsigned long *); -extern void xpc_disconnecting_callout(struct xpc_channel *); +extern void xpc_disconnect_callout(struct xpc_channel *, enum xpc_retval); extern void xpc_partition_going_down(struct xpc_partition *, enum xpc_retval); extern void xpc_teardown_infrastructure(struct xpc_partition *); @@ -1269,5 +1270,5 @@ xpc_check_for_channel_activity(struct xpc_partition *part) } -#endif /* _IA64_SN_KERNEL_XPC_H */ +#endif /* _ASM_IA64_SN_XPC_H */ diff --git a/include/asm-ia64/thread_info.h b/include/asm-ia64/thread_info.h index 653bb7f9a75..1d6518fe1f0 100644 --- a/include/asm-ia64/thread_info.h +++ b/include/asm-ia64/thread_info.h @@ -93,6 +93,7 @@ struct thread_info { #define TIF_POLLING_NRFLAG 16 /* true if poll_idle() is polling TIF_NEED_RESCHED */ #define TIF_MEMDIE 17 #define TIF_MCA_INIT 18 /* this task is processing MCA or INIT */ +#define TIF_DB_DISABLED 19 /* debug trap disabled for fsyscall */ #define _TIF_SYSCALL_TRACE (1 << TIF_SYSCALL_TRACE) #define _TIF_SYSCALL_AUDIT (1 << TIF_SYSCALL_AUDIT) @@ -100,9 +101,10 @@ struct thread_info { #define _TIF_NOTIFY_RESUME (1 << TIF_NOTIFY_RESUME) #define _TIF_SIGPENDING (1 << TIF_SIGPENDING) #define _TIF_NEED_RESCHED (1 << TIF_NEED_RESCHED) -#define _TIF_SIGDELAYED (1 << TIF_SIGDELAYED) +#define _TIF_SIGDELAYED (1 << TIF_SIGDELAYED) #define _TIF_POLLING_NRFLAG (1 << TIF_POLLING_NRFLAG) #define _TIF_MCA_INIT (1 << TIF_MCA_INIT) +#define _TIF_DB_DISABLED (1 << TIF_DB_DISABLED) /* "work to do on user-return" bits */ #define TIF_ALLWORK_MASK (_TIF_NOTIFY_RESUME|_TIF_SIGPENDING|_TIF_NEED_RESCHED|_TIF_SYSCALL_TRACE|_TIF_SYSCALL_AUDIT|_TIF_SIGDELAYED) diff --git a/include/asm-powerpc/atomic.h b/include/asm-powerpc/atomic.h index 248f9aec959..147a38dcc76 100644 --- a/include/asm-powerpc/atomic.h +++ b/include/asm-powerpc/atomic.h @@ -36,7 +36,7 @@ static __inline__ int atomic_add_return(int a, atomic_t *v) int t; __asm__ __volatile__( - EIEIO_ON_SMP + LWSYNC_ON_SMP "1: lwarx %0,0,%2 # atomic_add_return\n\ add %0,%1,%0\n" PPC405_ERR77(0,%2) @@ -72,7 +72,7 @@ static __inline__ int atomic_sub_return(int a, atomic_t *v) int t; __asm__ __volatile__( - EIEIO_ON_SMP + LWSYNC_ON_SMP "1: lwarx %0,0,%2 # atomic_sub_return\n\ subf %0,%1,%0\n" PPC405_ERR77(0,%2) @@ -106,7 +106,7 @@ static __inline__ int atomic_inc_return(atomic_t *v) int t; __asm__ __volatile__( - EIEIO_ON_SMP + LWSYNC_ON_SMP "1: lwarx %0,0,%1 # atomic_inc_return\n\ addic %0,%0,1\n" PPC405_ERR77(0,%1) @@ -150,7 +150,7 @@ static __inline__ int atomic_dec_return(atomic_t *v) int t; __asm__ __volatile__( - EIEIO_ON_SMP + LWSYNC_ON_SMP "1: lwarx %0,0,%1 # atomic_dec_return\n\ addic %0,%0,-1\n" PPC405_ERR77(0,%1) @@ -176,19 +176,19 @@ static __inline__ int atomic_dec_return(atomic_t *v) * Atomically adds @a to @v, so long as it was not @u. * Returns non-zero if @v was not @u, and zero otherwise. */ -#define atomic_add_unless(v, a, u) \ -({ \ - int c, old; \ - c = atomic_read(v); \ - for (;;) { \ - if (unlikely(c == (u))) \ - break; \ - old = atomic_cmpxchg((v), c, c + (a)); \ - if (likely(old == c)) \ - break; \ - c = old; \ - } \ - c != (u); \ +#define atomic_add_unless(v, a, u) \ +({ \ + int c, old; \ + c = atomic_read(v); \ + for (;;) { \ + if (unlikely(c == (u))) \ + break; \ + old = atomic_cmpxchg((v), c, c + (a)); \ + if (likely(old == c)) \ + break; \ + c = old; \ + } \ + c != (u); \ }) #define atomic_inc_not_zero(v) atomic_add_unless((v), 1, 0) @@ -204,7 +204,7 @@ static __inline__ int atomic_dec_if_positive(atomic_t *v) int t; __asm__ __volatile__( - EIEIO_ON_SMP + LWSYNC_ON_SMP "1: lwarx %0,0,%1 # atomic_dec_if_positive\n\ addic. %0,%0,-1\n\ blt- 2f\n" @@ -253,7 +253,7 @@ static __inline__ long atomic64_add_return(long a, atomic64_t *v) long t; __asm__ __volatile__( - EIEIO_ON_SMP + LWSYNC_ON_SMP "1: ldarx %0,0,%2 # atomic64_add_return\n\ add %0,%1,%0\n\ stdcx. %0,0,%2 \n\ @@ -287,7 +287,7 @@ static __inline__ long atomic64_sub_return(long a, atomic64_t *v) long t; __asm__ __volatile__( - EIEIO_ON_SMP + LWSYNC_ON_SMP "1: ldarx %0,0,%2 # atomic64_sub_return\n\ subf %0,%1,%0\n\ stdcx. %0,0,%2 \n\ @@ -319,7 +319,7 @@ static __inline__ long atomic64_inc_return(atomic64_t *v) long t; __asm__ __volatile__( - EIEIO_ON_SMP + LWSYNC_ON_SMP "1: ldarx %0,0,%1 # atomic64_inc_return\n\ addic %0,%0,1\n\ stdcx. %0,0,%1 \n\ @@ -361,7 +361,7 @@ static __inline__ long atomic64_dec_return(atomic64_t *v) long t; __asm__ __volatile__( - EIEIO_ON_SMP + LWSYNC_ON_SMP "1: ldarx %0,0,%1 # atomic64_dec_return\n\ addic %0,%0,-1\n\ stdcx. %0,0,%1\n\ @@ -386,7 +386,7 @@ static __inline__ long atomic64_dec_if_positive(atomic64_t *v) long t; __asm__ __volatile__( - EIEIO_ON_SMP + LWSYNC_ON_SMP "1: ldarx %0,0,%1 # atomic64_dec_if_positive\n\ addic. %0,%0,-1\n\ blt- 2f\n\ diff --git a/include/asm-powerpc/bitops.h b/include/asm-powerpc/bitops.h index 1996eaa8aea..bf6941a810b 100644 --- a/include/asm-powerpc/bitops.h +++ b/include/asm-powerpc/bitops.h @@ -112,7 +112,7 @@ static __inline__ int test_and_set_bit(unsigned long nr, unsigned long *p = ((unsigned long *)addr) + BITOP_WORD(nr); __asm__ __volatile__( - EIEIO_ON_SMP + LWSYNC_ON_SMP "1:" PPC_LLARX "%0,0,%3 # test_and_set_bit\n" "or %1,%0,%2 \n" PPC405_ERR77(0,%3) @@ -134,7 +134,7 @@ static __inline__ int test_and_clear_bit(unsigned long nr, unsigned long *p = ((unsigned long *)addr) + BITOP_WORD(nr); __asm__ __volatile__( - EIEIO_ON_SMP + LWSYNC_ON_SMP "1:" PPC_LLARX "%0,0,%3 # test_and_clear_bit\n" "andc %1,%0,%2 \n" PPC405_ERR77(0,%3) @@ -156,7 +156,7 @@ static __inline__ int test_and_change_bit(unsigned long nr, unsigned long *p = ((unsigned long *)addr) + BITOP_WORD(nr); __asm__ __volatile__( - EIEIO_ON_SMP + LWSYNC_ON_SMP "1:" PPC_LLARX "%0,0,%3 # test_and_change_bit\n" "xor %1,%0,%2 \n" PPC405_ERR77(0,%3) diff --git a/include/asm-powerpc/cputable.h b/include/asm-powerpc/cputable.h index ef6ead34a77..64210549f56 100644 --- a/include/asm-powerpc/cputable.h +++ b/include/asm-powerpc/cputable.h @@ -19,6 +19,7 @@ #define PPC_FEATURE_POWER5 0x00040000 #define PPC_FEATURE_POWER5_PLUS 0x00020000 #define PPC_FEATURE_CELL 0x00010000 +#define PPC_FEATURE_BOOKE 0x00008000 #ifdef __KERNEL__ #ifndef __ASSEMBLY__ @@ -31,11 +32,11 @@ struct cpu_spec; typedef void (*cpu_setup_t)(unsigned long offset, struct cpu_spec* spec); enum powerpc_oprofile_type { - INVALID = 0, - RS64 = 1, - POWER4 = 2, - G4 = 3, - BOOKE = 4, + PPC_OPROFILE_INVALID = 0, + PPC_OPROFILE_RS64 = 1, + PPC_OPROFILE_POWER4 = 2, + PPC_OPROFILE_G4 = 3, + PPC_OPROFILE_BOOKE = 4, }; struct cpu_spec { @@ -64,6 +65,9 @@ struct cpu_spec { /* Processor specific oprofile operations */ enum powerpc_oprofile_type oprofile_type; + + /* Name of processor class, for the ELF AT_PLATFORM entry */ + char *platform; }; extern struct cpu_spec *cur_cpu_spec; diff --git a/include/asm-powerpc/elf.h b/include/asm-powerpc/elf.h index 45f2af6f89c..94d228f9c6a 100644 --- a/include/asm-powerpc/elf.h +++ b/include/asm-powerpc/elf.h @@ -221,20 +221,18 @@ extern int dump_task_fpu(struct task_struct *, elf_fpregset_t *); instruction set this cpu supports. This could be done in userspace, but it's not easy, and we've already done it here. */ # define ELF_HWCAP (cur_cpu_spec->cpu_user_features) -#ifdef __powerpc64__ -# define ELF_PLAT_INIT(_r, load_addr) do { \ - _r->gpr[2] = load_addr; \ -} while (0) -#endif /* __powerpc64__ */ /* This yields a string that ld.so will use to load implementation specific libraries for optimization. This is more specific in - intent than poking at uname or /proc/cpuinfo. + intent than poking at uname or /proc/cpuinfo. */ - For the moment, we have only optimizations for the Intel generations, - but that could change... */ +#define ELF_PLATFORM (cur_cpu_spec->platform) -#define ELF_PLATFORM (NULL) +#ifdef __powerpc64__ +# define ELF_PLAT_INIT(_r, load_addr) do { \ + _r->gpr[2] = load_addr; \ +} while (0) +#endif /* __powerpc64__ */ #ifdef __KERNEL__ diff --git a/include/asm-powerpc/futex.h b/include/asm-powerpc/futex.h index f0319d50b12..39e85f320a7 100644 --- a/include/asm-powerpc/futex.h +++ b/include/asm-powerpc/futex.h @@ -11,7 +11,7 @@ #define __futex_atomic_op(insn, ret, oldval, uaddr, oparg) \ __asm__ __volatile ( \ - SYNC_ON_SMP \ + LWSYNC_ON_SMP \ "1: lwarx %0,0,%2\n" \ insn \ PPC405_ERR77(0, %2) \ diff --git a/include/asm-powerpc/hvcall.h b/include/asm-powerpc/hvcall.h index da7af5a720e..38ca9ad6110 100644 --- a/include/asm-powerpc/hvcall.h +++ b/include/asm-powerpc/hvcall.h @@ -6,7 +6,10 @@ #define H_Success 0 #define H_Busy 1 /* Hardware busy -- retry later */ +#define H_Closed 2 /* Resource closed */ #define H_Constrained 4 /* Resource request constrained to max allowed */ +#define H_InProgress 14 /* Kind of like busy */ +#define H_Continue 18 /* Returned from H_Join on success */ #define H_LongBusyStartRange 9900 /* Start of long busy range */ #define H_LongBusyOrder1msec 9900 /* Long busy, hint that 1msec is a good time to retry */ #define H_LongBusyOrder10msec 9901 /* Long busy, hint that 10msec is a good time to retry */ @@ -114,6 +117,8 @@ #define H_REGISTER_VTERM 0x154 #define H_FREE_VTERM 0x158 #define H_POLL_PENDING 0x1D8 +#define H_JOIN 0x298 +#define H_ENABLE_CRQ 0x2B0 #ifndef __ASSEMBLY__ diff --git a/include/asm-powerpc/lppaca.h b/include/asm-powerpc/lppaca.h index ff82ea7c482..cd9f11f1ef1 100644 --- a/include/asm-powerpc/lppaca.h +++ b/include/asm-powerpc/lppaca.h @@ -29,7 +29,9 @@ //---------------------------------------------------------------------------- #include <asm/types.h> -struct lppaca { +/* The Hypervisor barfs if the lppaca crosses a page boundary. A 1k + * alignment is sufficient to prevent this */ +struct __attribute__((__aligned__(0x400))) lppaca { //============================================================================= // CACHE_LINE_1 0x0000 - 0x007F Contains read-only data // NOTE: The xDynXyz fields are fields that will be dynamically changed by @@ -129,5 +131,7 @@ struct lppaca { u8 pmc_save_area[256]; // PMC interrupt Area x00-xFF }; +extern struct lppaca lppaca[]; + #endif /* __KERNEL__ */ #endif /* _ASM_POWERPC_LPPACA_H */ diff --git a/include/asm-powerpc/paca.h b/include/asm-powerpc/paca.h index a64b4d425da..c9add8f1ad9 100644 --- a/include/asm-powerpc/paca.h +++ b/include/asm-powerpc/paca.h @@ -23,6 +23,7 @@ register struct paca_struct *local_paca asm("r13"); #define get_paca() local_paca +#define get_lppaca() (get_paca()->lppaca_ptr) struct task_struct; @@ -95,19 +96,6 @@ struct paca_struct { u64 saved_r1; /* r1 save for RTAS calls */ u64 saved_msr; /* MSR saved here by enter_rtas */ u8 proc_enabled; /* irq soft-enable flag */ - - /* - * iSeries structure which the hypervisor knows about - - * this structure should not cross a page boundary. - * The vpa_init/register_vpa call is now known to fail if the - * lppaca structure crosses a page boundary. - * The lppaca is also used on POWER5 pSeries boxes. - * The lppaca is 640 bytes long, and cannot readily change - * since the hypervisor knows its layout, so a 1kB - * alignment will suffice to ensure that it doesn't - * cross a page boundary. - */ - struct lppaca lppaca __attribute__((__aligned__(0x400))); }; extern struct paca_struct paca[]; diff --git a/include/asm-powerpc/ppc_asm.h b/include/asm-powerpc/ppc_asm.h index 0dc798d46ea..ab8688d3902 100644 --- a/include/asm-powerpc/ppc_asm.h +++ b/include/asm-powerpc/ppc_asm.h @@ -156,52 +156,56 @@ n: #endif /* - * LOADADDR( rn, name ) - * loads the address of 'name' into 'rn' + * LOAD_REG_IMMEDIATE(rn, expr) + * Loads the value of the constant expression 'expr' into register 'rn' + * using immediate instructions only. Use this when it's important not + * to reference other data (i.e. on ppc64 when the TOC pointer is not + * valid). * - * LOADBASE( rn, name ) - * loads the address (possibly without the low 16 bits) of 'name' into 'rn' - * suitable for base+disp addressing + * LOAD_REG_ADDR(rn, name) + * Loads the address of label 'name' into register 'rn'. Use this when + * you don't particularly need immediate instructions only, but you need + * the whole address in one register (e.g. it's a structure address and + * you want to access various offsets within it). On ppc32 this is + * identical to LOAD_REG_IMMEDIATE. + * + * LOAD_REG_ADDRBASE(rn, name) + * ADDROFF(name) + * LOAD_REG_ADDRBASE loads part of the address of label 'name' into + * register 'rn'. ADDROFF(name) returns the remainder of the address as + * a constant expression. ADDROFF(name) is a signed expression < 16 bits + * in size, so is suitable for use directly as an offset in load and store + * instructions. Use this when loading/storing a single word or less as: + * LOAD_REG_ADDRBASE(rX, name) + * ld rY,ADDROFF(name)(rX) */ #ifdef __powerpc64__ -#define LOADADDR(rn,name) \ - lis rn,name##@highest; \ - ori rn,rn,name##@higher; \ - rldicr rn,rn,32,31; \ - oris rn,rn,name##@h; \ - ori rn,rn,name##@l - -#define LOADBASE(rn,name) \ - ld rn,name@got(r2) - -#define OFF(name) 0 - -#define SET_REG_TO_CONST(reg, value) \ - lis reg,(((value)>>48)&0xFFFF); \ - ori reg,reg,(((value)>>32)&0xFFFF); \ - rldicr reg,reg,32,31; \ - oris reg,reg,(((value)>>16)&0xFFFF); \ - ori reg,reg,((value)&0xFFFF); - -#define SET_REG_TO_LABEL(reg, label) \ - lis reg,(label)@highest; \ - ori reg,reg,(label)@higher; \ - rldicr reg,reg,32,31; \ - oris reg,reg,(label)@h; \ - ori reg,reg,(label)@l; +#define LOAD_REG_IMMEDIATE(reg,expr) \ + lis (reg),(expr)@highest; \ + ori (reg),(reg),(expr)@higher; \ + rldicr (reg),(reg),32,31; \ + oris (reg),(reg),(expr)@h; \ + ori (reg),(reg),(expr)@l; + +#define LOAD_REG_ADDR(reg,name) \ + ld (reg),name@got(r2) + +#define LOAD_REG_ADDRBASE(reg,name) LOAD_REG_ADDR(reg,name) +#define ADDROFF(name) 0 /* offsets for stack frame layout */ #define LRSAVE 16 #else /* 32-bit */ -#define LOADADDR(rn,name) \ - lis rn,name@ha; \ - addi rn,rn,name@l -#define LOADBASE(rn,name) \ - lis rn,name@ha +#define LOAD_REG_IMMEDIATE(reg,expr) \ + lis (reg),(expr)@ha; \ + addi (reg),(reg),(expr)@l; + +#define LOAD_REG_ADDR(reg,name) LOAD_REG_IMMEDIATE(reg, name) -#define OFF(name) name@l +#define LOAD_REG_ADDRBASE(reg, name) lis (reg),name@ha +#define ADDROFF(name) name@l /* offsets for stack frame layout */ #define LRSAVE 4 diff --git a/include/asm-powerpc/prom.h b/include/asm-powerpc/prom.h index 329e9bf6226..5b2bd4eefb0 100644 --- a/include/asm-powerpc/prom.h +++ b/include/asm-powerpc/prom.h @@ -87,6 +87,7 @@ struct device_node { char *full_name; struct property *properties; + struct property *deadprops; /* removed properties */ struct device_node *parent; struct device_node *child; struct device_node *sibling; @@ -135,6 +136,9 @@ extern struct device_node *of_find_all_nodes(struct device_node *prev); extern struct device_node *of_get_parent(const struct device_node *node); extern struct device_node *of_get_next_child(const struct device_node *node, struct device_node *prev); +extern struct property *of_find_property(struct device_node *np, + const char *name, + int *lenp); extern struct device_node *of_node_get(struct device_node *node); extern void of_node_put(struct device_node *node); @@ -164,6 +168,10 @@ extern int prom_n_size_cells(struct device_node* np); extern int prom_n_intr_cells(struct device_node* np); extern void prom_get_irq_senses(unsigned char *senses, int off, int max); extern int prom_add_property(struct device_node* np, struct property* prop); +extern int prom_remove_property(struct device_node *np, struct property *prop); +extern int prom_update_property(struct device_node *np, + struct property *newprop, + struct property *oldprop); #ifdef CONFIG_PPC32 /* diff --git a/include/asm-powerpc/spinlock.h b/include/asm-powerpc/spinlock.h index 754900901cd..895cb6d3a42 100644 --- a/include/asm-powerpc/spinlock.h +++ b/include/asm-powerpc/spinlock.h @@ -46,7 +46,7 @@ static __inline__ unsigned long __spin_trylock(raw_spinlock_t *lock) token = LOCK_TOKEN; __asm__ __volatile__( -"1: lwarx %0,0,%2 # __spin_trylock\n\ +"1: lwarx %0,0,%2\n\ cmpwi 0,%0,0\n\ bne- 2f\n\ stwcx. %1,0,%2\n\ @@ -80,7 +80,7 @@ static int __inline__ __raw_spin_trylock(raw_spinlock_t *lock) #if defined(CONFIG_PPC_SPLPAR) || defined(CONFIG_PPC_ISERIES) /* We only yield to the hypervisor if we are in shared processor mode */ -#define SHARED_PROCESSOR (get_paca()->lppaca.shared_proc) +#define SHARED_PROCESSOR (get_lppaca()->shared_proc) extern void __spin_yield(raw_spinlock_t *lock); extern void __rw_yield(raw_rwlock_t *lock); #else /* SPLPAR || ISERIES */ @@ -124,8 +124,8 @@ static void __inline__ __raw_spin_lock_flags(raw_spinlock_t *lock, unsigned long static __inline__ void __raw_spin_unlock(raw_spinlock_t *lock) { - __asm__ __volatile__(SYNC_ON_SMP" # __raw_spin_unlock" - : : :"memory"); + __asm__ __volatile__("# __raw_spin_unlock\n\t" + LWSYNC_ON_SMP: : :"memory"); lock->slock = 0; } @@ -167,7 +167,7 @@ static long __inline__ __read_trylock(raw_rwlock_t *rw) long tmp; __asm__ __volatile__( -"1: lwarx %0,0,%1 # read_trylock\n" +"1: lwarx %0,0,%1\n" __DO_SIGN_EXTEND " addic. %0,%0,1\n\ ble- 2f\n" @@ -192,7 +192,7 @@ static __inline__ long __write_trylock(raw_rwlock_t *rw) token = WRLOCK_TOKEN; __asm__ __volatile__( -"1: lwarx %0,0,%2 # write_trylock\n\ +"1: lwarx %0,0,%2\n\ cmpwi 0,%0,0\n\ bne- 2f\n" PPC405_ERR77(0,%1) @@ -249,8 +249,9 @@ static void __inline__ __raw_read_unlock(raw_rwlock_t *rw) long tmp; __asm__ __volatile__( - "eieio # read_unlock\n\ -1: lwarx %0,0,%1\n\ + "# read_unlock\n\t" + LWSYNC_ON_SMP +"1: lwarx %0,0,%1\n\ addic %0,%0,-1\n" PPC405_ERR77(0,%1) " stwcx. %0,0,%1\n\ @@ -262,8 +263,8 @@ static void __inline__ __raw_read_unlock(raw_rwlock_t *rw) static __inline__ void __raw_write_unlock(raw_rwlock_t *rw) { - __asm__ __volatile__(SYNC_ON_SMP" # write_unlock" - : : :"memory"); + __asm__ __volatile__("# write_unlock\n\t" + LWSYNC_ON_SMP: : :"memory"); rw->lock = 0; } diff --git a/include/asm-powerpc/synch.h b/include/asm-powerpc/synch.h index 794870ab8fd..c90d9d9aae7 100644 --- a/include/asm-powerpc/synch.h +++ b/include/asm-powerpc/synch.h @@ -2,6 +2,8 @@ #define _ASM_POWERPC_SYNCH_H #ifdef __KERNEL__ +#include <linux/stringify.h> + #ifdef __powerpc64__ #define __SUBARCH_HAS_LWSYNC #endif @@ -12,20 +14,12 @@ # define LWSYNC sync #endif - -/* - * Arguably the bitops and *xchg operations don't imply any memory barrier - * or SMP ordering, but in fact a lot of drivers expect them to imply - * both, since they do on x86 cpus. - */ #ifdef CONFIG_SMP -#define EIEIO_ON_SMP "eieio\n" #define ISYNC_ON_SMP "\n\tisync" -#define SYNC_ON_SMP __stringify(LWSYNC) "\n" +#define LWSYNC_ON_SMP __stringify(LWSYNC) "\n" #else -#define EIEIO_ON_SMP #define ISYNC_ON_SMP -#define SYNC_ON_SMP +#define LWSYNC_ON_SMP #endif static inline void eieio(void) @@ -38,14 +32,5 @@ static inline void isync(void) __asm__ __volatile__ ("isync" : : : "memory"); } -#ifdef CONFIG_SMP -#define eieio_on_smp() eieio() -#define isync_on_smp() isync() -#else -#define eieio_on_smp() __asm__ __volatile__("": : :"memory") -#define isync_on_smp() __asm__ __volatile__("": : :"memory") -#endif - #endif /* __KERNEL__ */ #endif /* _ASM_POWERPC_SYNCH_H */ - diff --git a/include/asm-powerpc/system.h b/include/asm-powerpc/system.h index 9b822afa7d0..d9bf53653b1 100644 --- a/include/asm-powerpc/system.h +++ b/include/asm-powerpc/system.h @@ -212,7 +212,7 @@ __xchg_u32(volatile void *p, unsigned long val) unsigned long prev; __asm__ __volatile__( - EIEIO_ON_SMP + LWSYNC_ON_SMP "1: lwarx %0,0,%2 \n" PPC405_ERR77(0,%2) " stwcx. %3,0,%2 \n\ @@ -232,7 +232,7 @@ __xchg_u64(volatile void *p, unsigned long val) unsigned long prev; __asm__ __volatile__( - EIEIO_ON_SMP + LWSYNC_ON_SMP "1: ldarx %0,0,%2 \n" PPC405_ERR77(0,%2) " stdcx. %3,0,%2 \n\ @@ -287,7 +287,7 @@ __cmpxchg_u32(volatile unsigned int *p, unsigned long old, unsigned long new) unsigned int prev; __asm__ __volatile__ ( - EIEIO_ON_SMP + LWSYNC_ON_SMP "1: lwarx %0,0,%2 # __cmpxchg_u32\n\ cmpw 0,%0,%3\n\ bne- 2f\n" @@ -311,7 +311,7 @@ __cmpxchg_u64(volatile unsigned long *p, unsigned long old, unsigned long new) unsigned long prev; __asm__ __volatile__ ( - EIEIO_ON_SMP + LWSYNC_ON_SMP "1: ldarx %0,0,%2 # __cmpxchg_u64\n\ cmpd 0,%0,%3\n\ bne- 2f\n\ diff --git a/include/asm-powerpc/time.h b/include/asm-powerpc/time.h index d9b86a17271..baddc9ab57a 100644 --- a/include/asm-powerpc/time.h +++ b/include/asm-powerpc/time.h @@ -175,11 +175,10 @@ static inline void set_dec(int val) set_dec_cpu6(val); #else #ifdef CONFIG_PPC_ISERIES - struct paca_struct *lpaca = get_paca(); int cur_dec; - if (lpaca->lppaca.shared_proc) { - lpaca->lppaca.virtual_decr = val; + if (get_lppaca()->shared_proc) { + get_lppaca()->virtual_decr = val; cur_dec = get_dec(); if (cur_dec > val) HvCall_setVirtualDecr(); diff --git a/include/linux/kernel.h b/include/linux/kernel.h index e6ee2d95da7..323924edb26 100644 --- a/include/linux/kernel.h +++ b/include/linux/kernel.h @@ -216,6 +216,7 @@ extern void dump_stack(void); ((unsigned char *)&addr)[1], \ ((unsigned char *)&addr)[2], \ ((unsigned char *)&addr)[3] +#define NIPQUAD_FMT "%u.%u.%u.%u" #define NIP6(addr) \ ntohs((addr).s6_addr16[0]), \ @@ -226,6 +227,7 @@ extern void dump_stack(void); ntohs((addr).s6_addr16[5]), \ ntohs((addr).s6_addr16[6]), \ ntohs((addr).s6_addr16[7]) +#define NIP6_FMT "%04x:%04x:%04x:%04x:%04x:%04x:%04x:%04x" #if defined(__LITTLE_ENDIAN) #define HIPQUAD(addr) \ diff --git a/include/linux/netfilter/nf_conntrack_common.h b/include/linux/netfilter/nf_conntrack_common.h index 6d39b518486..3ff88c87830 100644 --- a/include/linux/netfilter/nf_conntrack_common.h +++ b/include/linux/netfilter/nf_conntrack_common.h @@ -154,6 +154,9 @@ struct ip_conntrack_stat unsigned int expect_delete; }; +/* call to create an explicit dependency on nf_conntrack. */ +extern void need_conntrack(void); + #endif /* __KERNEL__ */ #endif /* _NF_CONNTRACK_COMMON_H */ diff --git a/include/linux/netfilter/x_tables.h b/include/linux/netfilter/x_tables.h new file mode 100644 index 00000000000..472f0483480 --- /dev/null +++ b/include/linux/netfilter/x_tables.h @@ -0,0 +1,224 @@ +#ifndef _X_TABLES_H +#define _X_TABLES_H + +#define XT_FUNCTION_MAXNAMELEN 30 +#define XT_TABLE_MAXNAMELEN 32 + +/* The argument to IPT_SO_GET_REVISION_*. Returns highest revision + * kernel supports, if >= revision. */ +struct xt_get_revision +{ + char name[XT_FUNCTION_MAXNAMELEN-1]; + + u_int8_t revision; +}; + +/* CONTINUE verdict for targets */ +#define XT_CONTINUE 0xFFFFFFFF + +/* For standard target */ +#define XT_RETURN (-NF_REPEAT - 1) + +#define XT_ALIGN(s) (((s) + (__alignof__(void *)-1)) & ~(__alignof__(void *)-1)) + +/* Standard return verdict, or do jump. */ +#define XT_STANDARD_TARGET "" +/* Error verdict. */ +#define XT_ERROR_TARGET "ERROR" + +/* + * New IP firewall options for [gs]etsockopt at the RAW IP level. + * Unlike BSD Linux inherits IP options so you don't have to use a raw + * socket for this. Instead we check rights in the calls. */ +#define XT_BASE_CTL 64 /* base for firewall socket options */ + +#define XT_SO_SET_REPLACE (XT_BASE_CTL) +#define XT_SO_SET_ADD_COUNTERS (XT_BASE_CTL + 1) +#define XT_SO_SET_MAX XT_SO_SET_ADD_COUNTERS + +#define XT_SO_GET_INFO (XT_BASE_CTL) +#define XT_SO_GET_ENTRIES (XT_BASE_CTL + 1) +#define XT_SO_GET_REVISION_MATCH (XT_BASE_CTL + 2) +#define XT_SO_GET_REVISION_TARGET (XT_BASE_CTL + 3) +#define XT_SO_GET_MAX XT_SO_GET_REVISION_TARGET + +#define SET_COUNTER(c,b,p) do { (c).bcnt = (b); (c).pcnt = (p); } while(0) +#define ADD_COUNTER(c,b,p) do { (c).bcnt += (b); (c).pcnt += (p); } while(0) + +struct xt_counters +{ + u_int64_t pcnt, bcnt; /* Packet and byte counters */ +}; + +/* The argument to IPT_SO_ADD_COUNTERS. */ +struct xt_counters_info +{ + /* Which table. */ + char name[XT_TABLE_MAXNAMELEN]; + + unsigned int num_counters; + + /* The counters (actually `number' of these). */ + struct xt_counters counters[0]; +}; + +#define XT_INV_PROTO 0x40 /* Invert the sense of PROTO. */ + +#ifdef __KERNEL__ + +#include <linux/netdevice.h> + +#define ASSERT_READ_LOCK(x) +#define ASSERT_WRITE_LOCK(x) +#include <linux/netfilter_ipv4/listhelp.h> + +struct xt_match +{ + struct list_head list; + + const char name[XT_FUNCTION_MAXNAMELEN-1]; + + u_int8_t revision; + + /* Return true or false: return FALSE and set *hotdrop = 1 to + force immediate packet drop. */ + /* Arguments changed since 2.6.9, as this must now handle + non-linear skb, using skb_header_pointer and + skb_ip_make_writable. */ + int (*match)(const struct sk_buff *skb, + const struct net_device *in, + const struct net_device *out, + const void *matchinfo, + int offset, + unsigned int protoff, + int *hotdrop); + + /* Called when user tries to insert an entry of this type. */ + /* Should return true or false. */ + int (*checkentry)(const char *tablename, + const void *ip, + void *matchinfo, + unsigned int matchinfosize, + unsigned int hook_mask); + + /* Called when entry of this type deleted. */ + void (*destroy)(void *matchinfo, unsigned int matchinfosize); + + /* Set this to THIS_MODULE if you are a module, otherwise NULL */ + struct module *me; +}; + +/* Registration hooks for targets. */ +struct xt_target +{ + struct list_head list; + + const char name[XT_FUNCTION_MAXNAMELEN-1]; + + u_int8_t revision; + + /* Returns verdict. Argument order changed since 2.6.9, as this + must now handle non-linear skbs, using skb_copy_bits and + skb_ip_make_writable. */ + unsigned int (*target)(struct sk_buff **pskb, + const struct net_device *in, + const struct net_device *out, + unsigned int hooknum, + const void *targinfo, + void *userdata); + + /* Called when user tries to insert an entry of this type: + hook_mask is a bitmask of hooks from which it can be + called. */ + /* Should return true or false. */ + int (*checkentry)(const char *tablename, + const void *entry, + void *targinfo, + unsigned int targinfosize, + unsigned int hook_mask); + + /* Called when entry of this type deleted. */ + void (*destroy)(void *targinfo, unsigned int targinfosize); + + /* Set this to THIS_MODULE if you are a module, otherwise NULL */ + struct module *me; +}; + +/* Furniture shopping... */ +struct xt_table +{ + struct list_head list; + + /* A unique name... */ + char name[XT_TABLE_MAXNAMELEN]; + + /* What hooks you will enter on */ + unsigned int valid_hooks; + + /* Lock for the curtain */ + rwlock_t lock; + + /* Man behind the curtain... */ + //struct ip6t_table_info *private; + void *private; + + /* Set this to THIS_MODULE if you are a module, otherwise NULL */ + struct module *me; + + int af; /* address/protocol family */ +}; + +#include <linux/netfilter_ipv4.h> + +/* The table itself */ +struct xt_table_info +{ + /* Size per table */ + unsigned int size; + /* Number of entries: FIXME. --RR */ + unsigned int number; + /* Initial number of entries. Needed for module usage count */ + unsigned int initial_entries; + + /* Entry points and underflows */ + unsigned int hook_entry[NF_IP_NUMHOOKS]; + unsigned int underflow[NF_IP_NUMHOOKS]; + + /* ipt_entry tables: one per CPU */ + char *entries[NR_CPUS]; +}; + +extern int xt_register_target(int af, struct xt_target *target); +extern void xt_unregister_target(int af, struct xt_target *target); +extern int xt_register_match(int af, struct xt_match *target); +extern void xt_unregister_match(int af, struct xt_match *target); + +extern int xt_register_table(struct xt_table *table, + struct xt_table_info *bootstrap, + struct xt_table_info *newinfo); +extern void *xt_unregister_table(struct xt_table *table); + +extern struct xt_table_info *xt_replace_table(struct xt_table *table, + unsigned int num_counters, + struct xt_table_info *newinfo, + int *error); + +extern struct xt_match *xt_find_match(int af, const char *name, u8 revision); +extern struct xt_target *xt_find_target(int af, const char *name, u8 revision); +extern struct xt_target *xt_request_find_target(int af, const char *name, + u8 revision); +extern int xt_find_revision(int af, const char *name, u8 revision, int target, + int *err); + +extern struct xt_table *xt_find_table_lock(int af, const char *name); +extern void xt_table_unlock(struct xt_table *t); + +extern int xt_proto_init(int af); +extern void xt_proto_fini(int af); + +extern struct xt_table_info *xt_alloc_table_info(unsigned int size); +extern void xt_free_table_info(struct xt_table_info *info); + +#endif /* __KERNEL__ */ + +#endif /* _X_TABLES_H */ diff --git a/include/linux/netfilter/xt_CLASSIFY.h b/include/linux/netfilter/xt_CLASSIFY.h new file mode 100644 index 00000000000..58111355255 --- /dev/null +++ b/include/linux/netfilter/xt_CLASSIFY.h @@ -0,0 +1,8 @@ +#ifndef _XT_CLASSIFY_H +#define _XT_CLASSIFY_H + +struct xt_classify_target_info { + u_int32_t priority; +}; + +#endif /*_XT_CLASSIFY_H */ diff --git a/include/linux/netfilter/xt_CONNMARK.h b/include/linux/netfilter/xt_CONNMARK.h new file mode 100644 index 00000000000..9f744689fff --- /dev/null +++ b/include/linux/netfilter/xt_CONNMARK.h @@ -0,0 +1,25 @@ +#ifndef _XT_CONNMARK_H_target +#define _XT_CONNMARK_H_target + +/* Copyright (C) 2002,2004 MARA Systems AB <http://www.marasystems.com> + * by Henrik Nordstrom <hno@marasystems.com> + * + * This program is free software; you can redistribute it and/or modify + * it under the terms of the GNU General Public License as published by + * the Free Software Foundation; either version 2 of the License, or + * (at your option) any later version. + */ + +enum { + XT_CONNMARK_SET = 0, + XT_CONNMARK_SAVE, + XT_CONNMARK_RESTORE +}; + +struct xt_connmark_target_info { + unsigned long mark; + unsigned long mask; + u_int8_t mode; +}; + +#endif /*_XT_CONNMARK_H_target*/ diff --git a/include/linux/netfilter/xt_MARK.h b/include/linux/netfilter/xt_MARK.h new file mode 100644 index 00000000000..b021e93ee5d --- /dev/null +++ b/include/linux/netfilter/xt_MARK.h @@ -0,0 +1,21 @@ +#ifndef _XT_MARK_H_target +#define _XT_MARK_H_target + +/* Version 0 */ +struct xt_mark_target_info { + unsigned long mark; +}; + +/* Version 1 */ +enum { + XT_MARK_SET=0, + XT_MARK_AND, + XT_MARK_OR, +}; + +struct xt_mark_target_info_v1 { + unsigned long mark; + u_int8_t mode; +}; + +#endif /*_XT_MARK_H_target */ diff --git a/include/linux/netfilter/xt_NFQUEUE.h b/include/linux/netfilter/xt_NFQUEUE.h new file mode 100644 index 00000000000..9a9af79f74d --- /dev/null +++ b/include/linux/netfilter/xt_NFQUEUE.h @@ -0,0 +1,16 @@ +/* iptables module for using NFQUEUE mechanism + * + * (C) 2005 Harald Welte <laforge@netfilter.org> + * + * This software is distributed under GNU GPL v2, 1991 + * +*/ +#ifndef _XT_NFQ_TARGET_H +#define _XT_NFQ_TARGET_H + +/* target info */ +struct xt_NFQ_info { + u_int16_t queuenum; +}; + +#endif /* _XT_NFQ_TARGET_H */ diff --git a/include/linux/netfilter/xt_comment.h b/include/linux/netfilter/xt_comment.h new file mode 100644 index 00000000000..eacfedc6b5d --- /dev/null +++ b/include/linux/netfilter/xt_comment.h @@ -0,0 +1,10 @@ +#ifndef _XT_COMMENT_H +#define _XT_COMMENT_H + +#define XT_MAX_COMMENT_LEN 256 + +struct xt_comment_info { + unsigned char comment[XT_MAX_COMMENT_LEN]; +}; + +#endif /* XT_COMMENT_H */ diff --git a/include/linux/netfilter/xt_connbytes.h b/include/linux/netfilter/xt_connbytes.h new file mode 100644 index 00000000000..c022c989754 --- /dev/null +++ b/include/linux/netfilter/xt_connbytes.h @@ -0,0 +1,25 @@ +#ifndef _XT_CONNBYTES_H +#define _XT_CONNBYTES_H + +enum xt_connbytes_what { + XT_CONNBYTES_PKTS, + XT_CONNBYTES_BYTES, + XT_CONNBYTES_AVGPKT, +}; + +enum xt_connbytes_direction { + XT_CONNBYTES_DIR_ORIGINAL, + XT_CONNBYTES_DIR_REPLY, + XT_CONNBYTES_DIR_BOTH, +}; + +struct xt_connbytes_info +{ + struct { + aligned_u64 from; /* count to be matched */ + aligned_u64 to; /* count to be matched */ + } count; + u_int8_t what; /* ipt_connbytes_what */ + u_int8_t direction; /* ipt_connbytes_direction */ +}; +#endif diff --git a/include/linux/netfilter/xt_connmark.h b/include/linux/netfilter/xt_connmark.h new file mode 100644 index 00000000000..c592f6ae088 --- /dev/null +++ b/include/linux/netfilter/xt_connmark.h @@ -0,0 +1,18 @@ +#ifndef _XT_CONNMARK_H +#define _XT_CONNMARK_H + +/* Copyright (C) 2002,2004 MARA Systems AB <http://www.marasystems.com> + * by Henrik Nordstrom <hno@marasystems.com> + * + * This program is free software; you can redistribute it and/or modify + * it under the terms of the GNU General Public License as published by + * the Free Software Foundation; either version 2 of the License, or + * (at your option) any later version. + */ + +struct xt_connmark_info { + unsigned long mark, mask; + u_int8_t invert; +}; + +#endif /*_XT_CONNMARK_H*/ diff --git a/include/linux/netfilter/xt_conntrack.h b/include/linux/netfilter/xt_conntrack.h new file mode 100644 index 00000000000..34f63cf2e29 --- /dev/null +++ b/include/linux/netfilter/xt_conntrack.h @@ -0,0 +1,63 @@ +/* Header file for kernel module to match connection tracking information. + * GPL (C) 2001 Marc Boucher (marc@mbsi.ca). + */ + +#ifndef _XT_CONNTRACK_H +#define _XT_CONNTRACK_H + +#include <linux/netfilter/nf_conntrack_tuple_common.h> +#include <linux/in.h> + +#define XT_CONNTRACK_STATE_BIT(ctinfo) (1 << ((ctinfo)%IP_CT_IS_REPLY+1)) +#define XT_CONNTRACK_STATE_INVALID (1 << 0) + +#define XT_CONNTRACK_STATE_SNAT (1 << (IP_CT_NUMBER + 1)) +#define XT_CONNTRACK_STATE_DNAT (1 << (IP_CT_NUMBER + 2)) +#define XT_CONNTRACK_STATE_UNTRACKED (1 << (IP_CT_NUMBER + 3)) + +/* flags, invflags: */ +#define XT_CONNTRACK_STATE 0x01 +#define XT_CONNTRACK_PROTO 0x02 +#define XT_CONNTRACK_ORIGSRC 0x04 +#define XT_CONNTRACK_ORIGDST 0x08 +#define XT_CONNTRACK_REPLSRC 0x10 +#define XT_CONNTRACK_REPLDST 0x20 +#define XT_CONNTRACK_STATUS 0x40 +#define XT_CONNTRACK_EXPIRES 0x80 + +/* This is exposed to userspace, so remains frozen in time. */ +struct ip_conntrack_old_tuple +{ + struct { + __u32 ip; + union { + __u16 all; + } u; + } src; + + struct { + __u32 ip; + union { + __u16 all; + } u; + + /* The protocol. */ + u16 protonum; + } dst; +}; + +struct xt_conntrack_info +{ + unsigned int statemask, statusmask; + + struct ip_conntrack_old_tuple tuple[IP_CT_DIR_MAX]; + struct in_addr sipmsk[IP_CT_DIR_MAX], dipmsk[IP_CT_DIR_MAX]; + + unsigned long expires_min, expires_max; + + /* Flags word */ + u_int8_t flags; + /* Inverse flags */ + u_int8_t invflags; +}; +#endif /*_XT_CONNTRACK_H*/ diff --git a/include/linux/netfilter/xt_dccp.h b/include/linux/netfilter/xt_dccp.h new file mode 100644 index 00000000000..e0221b9d32c --- /dev/null +++ b/include/linux/netfilter/xt_dccp.h @@ -0,0 +1,23 @@ +#ifndef _XT_DCCP_H_ +#define _XT_DCCP_H_ + +#define XT_DCCP_SRC_PORTS 0x01 +#define XT_DCCP_DEST_PORTS 0x02 +#define XT_DCCP_TYPE 0x04 +#define XT_DCCP_OPTION 0x08 + +#define XT_DCCP_VALID_FLAGS 0x0f + +struct xt_dccp_info { + u_int16_t dpts[2]; /* Min, Max */ + u_int16_t spts[2]; /* Min, Max */ + + u_int16_t flags; + u_int16_t invflags; + + u_int16_t typemask; + u_int8_t option; +}; + +#endif /* _XT_DCCP_H_ */ + diff --git a/include/linux/netfilter/xt_helper.h b/include/linux/netfilter/xt_helper.h new file mode 100644 index 00000000000..6b42763f999 --- /dev/null +++ b/include/linux/netfilter/xt_helper.h @@ -0,0 +1,8 @@ +#ifndef _XT_HELPER_H +#define _XT_HELPER_H + +struct xt_helper_info { + int invert; + char name[30]; +}; +#endif /* _XT_HELPER_H */ diff --git a/include/linux/netfilter/xt_length.h b/include/linux/netfilter/xt_length.h new file mode 100644 index 00000000000..7c2b439f73f --- /dev/null +++ b/include/linux/netfilter/xt_length.h @@ -0,0 +1,9 @@ +#ifndef _XT_LENGTH_H +#define _XT_LENGTH_H + +struct xt_length_info { + u_int16_t min, max; + u_int8_t invert; +}; + +#endif /*_XT_LENGTH_H*/ diff --git a/include/linux/netfilter/xt_limit.h b/include/linux/netfilter/xt_limit.h new file mode 100644 index 00000000000..b3ce65375ec --- /dev/null +++ b/include/linux/netfilter/xt_limit.h @@ -0,0 +1,21 @@ +#ifndef _XT_RATE_H +#define _XT_RATE_H + +/* timings are in milliseconds. */ +#define XT_LIMIT_SCALE 10000 + +/* 1/10,000 sec period => max of 10,000/sec. Min rate is then 429490 + seconds, or one every 59 hours. */ +struct xt_rateinfo { + u_int32_t avg; /* Average secs between packets * scale */ + u_int32_t burst; /* Period multiplier for upper limit. */ + + /* Used internally by the kernel */ + unsigned long prev; + u_int32_t credit; + u_int32_t credit_cap, cost; + + /* Ugly, ugly fucker. */ + struct xt_rateinfo *master; +}; +#endif /*_XT_RATE_H*/ diff --git a/include/linux/netfilter/xt_mac.h b/include/linux/netfilter/xt_mac.h new file mode 100644 index 00000000000..b892cdc67e0 --- /dev/null +++ b/include/linux/netfilter/xt_mac.h @@ -0,0 +1,8 @@ +#ifndef _XT_MAC_H +#define _XT_MAC_H + +struct xt_mac_info { + unsigned char srcaddr[ETH_ALEN]; + int invert; +}; +#endif /*_XT_MAC_H*/ diff --git a/include/linux/netfilter/xt_mark.h b/include/linux/netfilter/xt_mark.h new file mode 100644 index 00000000000..802dd4842ca --- /dev/null +++ b/include/linux/netfilter/xt_mark.h @@ -0,0 +1,9 @@ +#ifndef _XT_MARK_H +#define _XT_MARK_H + +struct xt_mark_info { + unsigned long mark, mask; + u_int8_t invert; +}; + +#endif /*_XT_MARK_H*/ diff --git a/include/linux/netfilter/xt_physdev.h b/include/linux/netfilter/xt_physdev.h new file mode 100644 index 00000000000..25a7a1815b5 --- /dev/null +++ b/include/linux/netfilter/xt_physdev.h @@ -0,0 +1,24 @@ +#ifndef _XT_PHYSDEV_H +#define _XT_PHYSDEV_H + +#ifdef __KERNEL__ +#include <linux/if.h> +#endif + +#define XT_PHYSDEV_OP_IN 0x01 +#define XT_PHYSDEV_OP_OUT 0x02 +#define XT_PHYSDEV_OP_BRIDGED 0x04 +#define XT_PHYSDEV_OP_ISIN 0x08 +#define XT_PHYSDEV_OP_ISOUT 0x10 +#define XT_PHYSDEV_OP_MASK (0x20 - 1) + +struct xt_physdev_info { + char physindev[IFNAMSIZ]; + char in_mask[IFNAMSIZ]; + char physoutdev[IFNAMSIZ]; + char out_mask[IFNAMSIZ]; + u_int8_t invert; + u_int8_t bitmask; +}; + +#endif /*_XT_PHYSDEV_H*/ diff --git a/include/linux/netfilter/xt_pkttype.h b/include/linux/netfilter/xt_pkttype.h new file mode 100644 index 00000000000..f265cf52fae --- /dev/null +++ b/include/linux/netfilter/xt_pkttype.h @@ -0,0 +1,8 @@ +#ifndef _XT_PKTTYPE_H +#define _XT_PKTTYPE_H + +struct xt_pkttype_info { + int pkttype; + int invert; +}; +#endif /*_XT_PKTTYPE_H*/ diff --git a/include/linux/netfilter/xt_realm.h b/include/linux/netfilter/xt_realm.h new file mode 100644 index 00000000000..220e8724571 --- /dev/null +++ b/include/linux/netfilter/xt_realm.h @@ -0,0 +1,10 @@ +#ifndef _XT_REALM_H +#define _XT_REALM_H + +struct xt_realm_info { + u_int32_t id; + u_int32_t mask; + u_int8_t invert; +}; + +#endif /* _XT_REALM_H */ diff --git a/include/linux/netfilter/xt_sctp.h b/include/linux/netfilter/xt_sctp.h new file mode 100644 index 00000000000..b157897e779 --- /dev/null +++ b/include/linux/netfilter/xt_sctp.h @@ -0,0 +1,107 @@ +#ifndef _XT_SCTP_H_ +#define _XT_SCTP_H_ + +#define XT_SCTP_SRC_PORTS 0x01 +#define XT_SCTP_DEST_PORTS 0x02 +#define XT_SCTP_CHUNK_TYPES 0x04 + +#define XT_SCTP_VALID_FLAGS 0x07 + +#define ELEMCOUNT(x) (sizeof(x)/sizeof(x[0])) + + +struct xt_sctp_flag_info { + u_int8_t chunktype; + u_int8_t flag; + u_int8_t flag_mask; +}; + +#define XT_NUM_SCTP_FLAGS 4 + +struct xt_sctp_info { + u_int16_t dpts[2]; /* Min, Max */ + u_int16_t spts[2]; /* Min, Max */ + + u_int32_t chunkmap[256 / sizeof (u_int32_t)]; /* Bit mask of chunks to be matched according to RFC 2960 */ + +#define SCTP_CHUNK_MATCH_ANY 0x01 /* Match if any of the chunk types are present */ +#define SCTP_CHUNK_MATCH_ALL 0x02 /* Match if all of the chunk types are present */ +#define SCTP_CHUNK_MATCH_ONLY 0x04 /* Match if these are the only chunk types present */ + + u_int32_t chunk_match_type; + struct xt_sctp_flag_info flag_info[XT_NUM_SCTP_FLAGS]; + int flag_count; + + u_int32_t flags; + u_int32_t invflags; +}; + +#define bytes(type) (sizeof(type) * 8) + +#define SCTP_CHUNKMAP_SET(chunkmap, type) \ + do { \ + chunkmap[type / bytes(u_int32_t)] |= \ + 1 << (type % bytes(u_int32_t)); \ + } while (0) + +#define SCTP_CHUNKMAP_CLEAR(chunkmap, type) \ + do { \ + chunkmap[type / bytes(u_int32_t)] &= \ + ~(1 << (type % bytes(u_int32_t))); \ + } while (0) + +#define SCTP_CHUNKMAP_IS_SET(chunkmap, type) \ +({ \ + (chunkmap[type / bytes (u_int32_t)] & \ + (1 << (type % bytes (u_int32_t)))) ? 1: 0; \ +}) + +#define SCTP_CHUNKMAP_RESET(chunkmap) \ + do { \ + int i; \ + for (i = 0; i < ELEMCOUNT(chunkmap); i++) \ + chunkmap[i] = 0; \ + } while (0) + +#define SCTP_CHUNKMAP_SET_ALL(chunkmap) \ + do { \ + int i; \ + for (i = 0; i < ELEMCOUNT(chunkmap); i++) \ + chunkmap[i] = ~0; \ + } while (0) + +#define SCTP_CHUNKMAP_COPY(destmap, srcmap) \ + do { \ + int i; \ + for (i = 0; i < ELEMCOUNT(chunkmap); i++) \ + destmap[i] = srcmap[i]; \ + } while (0) + +#define SCTP_CHUNKMAP_IS_CLEAR(chunkmap) \ +({ \ + int i; \ + int flag = 1; \ + for (i = 0; i < ELEMCOUNT(chunkmap); i++) { \ + if (chunkmap[i]) { \ + flag = 0; \ + break; \ + } \ + } \ + flag; \ +}) + +#define SCTP_CHUNKMAP_IS_ALL_SET(chunkmap) \ +({ \ + int i; \ + int flag = 1; \ + for (i = 0; i < ELEMCOUNT(chunkmap); i++) { \ + if (chunkmap[i] != ~0) { \ + flag = 0; \ + break; \ + } \ + } \ + flag; \ +}) + +#endif /* _XT_SCTP_H_ */ + diff --git a/include/linux/netfilter/xt_state.h b/include/linux/netfilter/xt_state.h new file mode 100644 index 00000000000..c06f32edee0 --- /dev/null +++ b/include/linux/netfilter/xt_state.h @@ -0,0 +1,13 @@ +#ifndef _XT_STATE_H +#define _XT_STATE_H + +#define XT_STATE_BIT(ctinfo) (1 << ((ctinfo)%IP_CT_IS_REPLY+1)) +#define XT_STATE_INVALID (1 << 0) + +#define XT_STATE_UNTRACKED (1 << (IP_CT_NUMBER + 1)) + +struct xt_state_info +{ + unsigned int statemask; +}; +#endif /*_XT_STATE_H*/ diff --git a/include/linux/netfilter/xt_string.h b/include/linux/netfilter/xt_string.h new file mode 100644 index 00000000000..3b3419f2637 --- /dev/null +++ b/include/linux/netfilter/xt_string.h @@ -0,0 +1,18 @@ +#ifndef _XT_STRING_H +#define _XT_STRING_H + +#define XT_STRING_MAX_PATTERN_SIZE 128 +#define XT_STRING_MAX_ALGO_NAME_SIZE 16 + +struct xt_string_info +{ + u_int16_t from_offset; + u_int16_t to_offset; + char algo[XT_STRING_MAX_ALGO_NAME_SIZE]; + char pattern[XT_STRING_MAX_PATTERN_SIZE]; + u_int8_t patlen; + u_int8_t invert; + struct ts_config __attribute__((aligned(8))) *config; +}; + +#endif /*_XT_STRING_H*/ diff --git a/include/linux/netfilter/xt_tcpmss.h b/include/linux/netfilter/xt_tcpmss.h new file mode 100644 index 00000000000..e03274c4c79 --- /dev/null +++ b/include/linux/netfilter/xt_tcpmss.h @@ -0,0 +1,9 @@ +#ifndef _XT_TCPMSS_MATCH_H +#define _XT_TCPMSS_MATCH_H + +struct xt_tcpmss_match_info { + u_int16_t mss_min, mss_max; + u_int8_t invert; +}; + +#endif /*_XT_TCPMSS_MATCH_H*/ diff --git a/include/linux/netfilter/xt_tcpudp.h b/include/linux/netfilter/xt_tcpudp.h new file mode 100644 index 00000000000..78bc65f11ad --- /dev/null +++ b/include/linux/netfilter/xt_tcpudp.h @@ -0,0 +1,36 @@ +#ifndef _XT_TCPUDP_H +#define _XT_TCPUDP_H + +/* TCP matching stuff */ +struct xt_tcp +{ + u_int16_t spts[2]; /* Source port range. */ + u_int16_t dpts[2]; /* Destination port range. */ + u_int8_t option; /* TCP Option iff non-zero*/ + u_int8_t flg_mask; /* TCP flags mask byte */ + u_int8_t flg_cmp; /* TCP flags compare byte */ + u_int8_t invflags; /* Inverse flags */ +}; + +/* Values for "inv" field in struct ipt_tcp. */ +#define XT_TCP_INV_SRCPT 0x01 /* Invert the sense of source ports. */ +#define XT_TCP_INV_DSTPT 0x02 /* Invert the sense of dest ports. */ +#define XT_TCP_INV_FLAGS 0x04 /* Invert the sense of TCP flags. */ +#define XT_TCP_INV_OPTION 0x08 /* Invert the sense of option test. */ +#define XT_TCP_INV_MASK 0x0F /* All possible flags. */ + +/* UDP matching stuff */ +struct xt_udp +{ + u_int16_t spts[2]; /* Source port range. */ + u_int16_t dpts[2]; /* Destination port range. */ + u_int8_t invflags; /* Inverse flags */ +}; + +/* Values for "invflags" field in struct ipt_udp. */ +#define XT_UDP_INV_SRCPT 0x01 /* Invert the sense of source ports. */ +#define XT_UDP_INV_DSTPT 0x02 /* Invert the sense of dest ports. */ +#define XT_UDP_INV_MASK 0x03 /* All possible flags. */ + + +#endif diff --git a/include/linux/netfilter_arp/arp_tables.h b/include/linux/netfilter_arp/arp_tables.h index e98a870a20b..fd21796e513 100644 --- a/include/linux/netfilter_arp/arp_tables.h +++ b/include/linux/netfilter_arp/arp_tables.h @@ -19,8 +19,12 @@ #include <linux/compiler.h> #include <linux/netfilter_arp.h> -#define ARPT_FUNCTION_MAXNAMELEN 30 -#define ARPT_TABLE_MAXNAMELEN 32 +#include <linux/netfilter/x_tables.h> + +#define ARPT_FUNCTION_MAXNAMELEN XT_FUNCTION_MAXNAMELEN +#define ARPT_TABLE_MAXNAMELEN XT_TABLE_MAXNAMELEN +#define arpt_target xt_target +#define arpt_table xt_table #define ARPT_DEV_ADDR_LEN_MAX 16 @@ -91,11 +95,6 @@ struct arpt_standard_target int verdict; }; -struct arpt_counters -{ - u_int64_t pcnt, bcnt; /* Packet and byte counters */ -}; - /* Values for "flag" field in struct arpt_ip (general arp structure). * No flags defined yet. */ @@ -130,7 +129,7 @@ struct arpt_entry unsigned int comefrom; /* Packet and byte counters. */ - struct arpt_counters counters; + struct xt_counters counters; /* The matches (if any), then the target. */ unsigned char elems[0]; @@ -141,23 +140,24 @@ struct arpt_entry * Unlike BSD Linux inherits IP options so you don't have to use a raw * socket for this. Instead we check rights in the calls. */ -#define ARPT_BASE_CTL 96 /* base for firewall socket options */ +#define ARPT_CTL_OFFSET 32 +#define ARPT_BASE_CTL (XT_BASE_CTL+ARPT_CTL_OFFSET) -#define ARPT_SO_SET_REPLACE (ARPT_BASE_CTL) -#define ARPT_SO_SET_ADD_COUNTERS (ARPT_BASE_CTL + 1) -#define ARPT_SO_SET_MAX ARPT_SO_SET_ADD_COUNTERS +#define ARPT_SO_SET_REPLACE (XT_SO_SET_REPLACE+ARPT_CTL_OFFSET) +#define ARPT_SO_SET_ADD_COUNTERS (XT_SO_SET_ADD_COUNTERS+ARPT_CTL_OFFSET) +#define ARPT_SO_SET_MAX (XT_SO_SET_MAX+ARPT_CTL_OFFSET) -#define ARPT_SO_GET_INFO (ARPT_BASE_CTL) -#define ARPT_SO_GET_ENTRIES (ARPT_BASE_CTL + 1) -/* #define ARPT_SO_GET_REVISION_MATCH (ARPT_BASE_CTL + 2)*/ -#define ARPT_SO_GET_REVISION_TARGET (ARPT_BASE_CTL + 3) -#define ARPT_SO_GET_MAX ARPT_SO_GET_REVISION_TARGET +#define ARPT_SO_GET_INFO (XT_SO_GET_INFO+ARPT_CTL_OFFSET) +#define ARPT_SO_GET_ENTRIES (XT_SO_GET_ENTRIES+ARPT_CTL_OFFSET) +/* #define ARPT_SO_GET_REVISION_MATCH XT_SO_GET_REVISION_MATCH */ +#define ARPT_SO_GET_REVISION_TARGET (XT_SO_GET_REVISION_TARGET+ARPT_CTL_OFFSET) +#define ARPT_SO_GET_MAX (XT_SO_GET_REVISION_TARGET+ARPT_CTL_OFFSET) /* CONTINUE verdict for targets */ -#define ARPT_CONTINUE 0xFFFFFFFF +#define ARPT_CONTINUE XT_CONTINUE /* For standard target */ -#define ARPT_RETURN (-NF_REPEAT - 1) +#define ARPT_RETURN XT_RETURN /* The argument to ARPT_SO_GET_INFO */ struct arpt_getinfo @@ -208,23 +208,14 @@ struct arpt_replace /* Number of counters (must be equal to current number of entries). */ unsigned int num_counters; /* The old entries' counters. */ - struct arpt_counters __user *counters; + struct xt_counters __user *counters; /* The entries (hang off end: not really an array). */ struct arpt_entry entries[0]; }; /* The argument to ARPT_SO_ADD_COUNTERS. */ -struct arpt_counters_info -{ - /* Which table. */ - char name[ARPT_TABLE_MAXNAMELEN]; - - unsigned int num_counters; - - /* The counters (actually `number' of these). */ - struct arpt_counters counters[0]; -}; +#define arpt_counters_info xt_counters_info /* The argument to ARPT_SO_GET_ENTRIES. */ struct arpt_get_entries @@ -239,19 +230,10 @@ struct arpt_get_entries struct arpt_entry entrytable[0]; }; -/* The argument to ARPT_SO_GET_REVISION_*. Returns highest revision - * kernel supports, if >= revision. */ -struct arpt_get_revision -{ - char name[ARPT_FUNCTION_MAXNAMELEN-1]; - - u_int8_t revision; -}; - /* Standard return verdict, or do jump. */ -#define ARPT_STANDARD_TARGET "" +#define ARPT_STANDARD_TARGET XT_STANDARD_TARGET /* Error verdict. */ -#define ARPT_ERROR_TARGET "ERROR" +#define ARPT_ERROR_TARGET XT_ERROR_TARGET /* Helper functions */ static __inline__ struct arpt_entry_target *arpt_get_target(struct arpt_entry *e) @@ -281,63 +263,8 @@ static __inline__ struct arpt_entry_target *arpt_get_target(struct arpt_entry *e */ #ifdef __KERNEL__ -/* Registration hooks for targets. */ -struct arpt_target -{ - struct list_head list; - - const char name[ARPT_FUNCTION_MAXNAMELEN-1]; - - u_int8_t revision; - - /* Returns verdict. */ - unsigned int (*target)(struct sk_buff **pskb, - unsigned int hooknum, - const struct net_device *in, - const struct net_device *out, - const void *targinfo, - void *userdata); - - /* Called when user tries to insert an entry of this type: - hook_mask is a bitmask of hooks from which it can be - called. */ - /* Should return true or false. */ - int (*checkentry)(const char *tablename, - const struct arpt_entry *e, - void *targinfo, - unsigned int targinfosize, - unsigned int hook_mask); - - /* Called when entry of this type deleted. */ - void (*destroy)(void *targinfo, unsigned int targinfosize); - - /* Set this to THIS_MODULE if you are a module, otherwise NULL */ - struct module *me; -}; - -extern int arpt_register_target(struct arpt_target *target); -extern void arpt_unregister_target(struct arpt_target *target); - -/* Furniture shopping... */ -struct arpt_table -{ - struct list_head list; - - /* A unique name... */ - char name[ARPT_TABLE_MAXNAMELEN]; - - /* What hooks you will enter on */ - unsigned int valid_hooks; - - /* Lock for the curtain */ - rwlock_t lock; - - /* Man behind the curtain... */ - struct arpt_table_info *private; - - /* Set this to THIS_MODULE if you are a module, otherwise NULL */ - struct module *me; -}; +#define arpt_register_target(tgt) xt_register_target(NF_ARP, tgt) +#define arpt_unregister_target(tgt) xt_unregister_target(NF_ARP, tgt) extern int arpt_register_table(struct arpt_table *table, const struct arpt_replace *repl); diff --git a/include/linux/netfilter_ipv4/ip_conntrack.h b/include/linux/netfilter_ipv4/ip_conntrack.h index b3432ab59a1..215765f043e 100644 --- a/include/linux/netfilter_ipv4/ip_conntrack.h +++ b/include/linux/netfilter_ipv4/ip_conntrack.h @@ -199,9 +199,6 @@ ip_conntrack_put(struct ip_conntrack *ct) nf_conntrack_put(&ct->ct_general); } -/* call to create an explicit dependency on ip_conntrack. */ -extern void need_ip_conntrack(void); - extern int invert_tuplepr(struct ip_conntrack_tuple *inverse, const struct ip_conntrack_tuple *orig); diff --git a/include/linux/netfilter_ipv4/ip_tables.h b/include/linux/netfilter_ipv4/ip_tables.h index d19d65cf453..76ba24b6851 100644 --- a/include/linux/netfilter_ipv4/ip_tables.h +++ b/include/linux/netfilter_ipv4/ip_tables.h @@ -25,8 +25,14 @@ #include <linux/compiler.h> #include <linux/netfilter_ipv4.h> -#define IPT_FUNCTION_MAXNAMELEN 30 -#define IPT_TABLE_MAXNAMELEN 32 +#include <linux/netfilter/x_tables.h> + +#define IPT_FUNCTION_MAXNAMELEN XT_FUNCTION_MAXNAMELEN +#define IPT_TABLE_MAXNAMELEN XT_FUNCTION_MAXNAMELEN +#define ipt_match xt_match +#define ipt_target xt_target +#define ipt_table xt_table +#define ipt_get_revision xt_get_revision /* Yes, Virginia, you have to zero the padding. */ struct ipt_ip { @@ -102,10 +108,7 @@ struct ipt_standard_target int verdict; }; -struct ipt_counters -{ - u_int64_t pcnt, bcnt; /* Packet and byte counters */ -}; +#define ipt_counters xt_counters /* Values for "flag" field in struct ipt_ip (general ip structure). */ #define IPT_F_FRAG 0x01 /* Set if rule is a fragment rule */ @@ -119,7 +122,7 @@ struct ipt_counters #define IPT_INV_SRCIP 0x08 /* Invert the sense of SRC IP. */ #define IPT_INV_DSTIP 0x10 /* Invert the sense of DST OP. */ #define IPT_INV_FRAG 0x20 /* Invert the sense of FRAG. */ -#define IPT_INV_PROTO 0x40 /* Invert the sense of PROTO. */ +#define IPT_INV_PROTO XT_INV_PROTO #define IPT_INV_MASK 0x7F /* All possible flag bits mask. */ /* This structure defines each of the firewall rules. Consists of 3 @@ -141,7 +144,7 @@ struct ipt_entry unsigned int comefrom; /* Packet and byte counters. */ - struct ipt_counters counters; + struct xt_counters counters; /* The matches (if any), then the target. */ unsigned char elems[0]; @@ -151,54 +154,34 @@ struct ipt_entry * New IP firewall options for [gs]etsockopt at the RAW IP level. * Unlike BSD Linux inherits IP options so you don't have to use a raw * socket for this. Instead we check rights in the calls. */ -#define IPT_BASE_CTL 64 /* base for firewall socket options */ +#define IPT_BASE_CTL XT_BASE_CTL -#define IPT_SO_SET_REPLACE (IPT_BASE_CTL) -#define IPT_SO_SET_ADD_COUNTERS (IPT_BASE_CTL + 1) -#define IPT_SO_SET_MAX IPT_SO_SET_ADD_COUNTERS +#define IPT_SO_SET_REPLACE XT_SO_SET_REPLACE +#define IPT_SO_SET_ADD_COUNTERS XT_SO_SET_ADD_COUNTERS +#define IPT_SO_SET_MAX XT_SO_SET_MAX -#define IPT_SO_GET_INFO (IPT_BASE_CTL) -#define IPT_SO_GET_ENTRIES (IPT_BASE_CTL + 1) -#define IPT_SO_GET_REVISION_MATCH (IPT_BASE_CTL + 2) -#define IPT_SO_GET_REVISION_TARGET (IPT_BASE_CTL + 3) -#define IPT_SO_GET_MAX IPT_SO_GET_REVISION_TARGET +#define IPT_SO_GET_INFO XT_SO_GET_INFO +#define IPT_SO_GET_ENTRIES XT_SO_GET_ENTRIES +#define IPT_SO_GET_REVISION_MATCH XT_SO_GET_REVISION_MATCH +#define IPT_SO_GET_REVISION_TARGET XT_SO_GET_REVISION_TARGET +#define IPT_SO_GET_MAX XT_SO_GET_REVISION_TARGET -/* CONTINUE verdict for targets */ -#define IPT_CONTINUE 0xFFFFFFFF +#define IPT_CONTINUE XT_CONTINUE +#define IPT_RETURN XT_RETURN -/* For standard target */ -#define IPT_RETURN (-NF_REPEAT - 1) +#include <linux/netfilter/xt_tcpudp.h> +#define ipt_udp xt_udp +#define ipt_tcp xt_tcp -/* TCP matching stuff */ -struct ipt_tcp -{ - u_int16_t spts[2]; /* Source port range. */ - u_int16_t dpts[2]; /* Destination port range. */ - u_int8_t option; /* TCP Option iff non-zero*/ - u_int8_t flg_mask; /* TCP flags mask byte */ - u_int8_t flg_cmp; /* TCP flags compare byte */ - u_int8_t invflags; /* Inverse flags */ -}; - -/* Values for "inv" field in struct ipt_tcp. */ -#define IPT_TCP_INV_SRCPT 0x01 /* Invert the sense of source ports. */ -#define IPT_TCP_INV_DSTPT 0x02 /* Invert the sense of dest ports. */ -#define IPT_TCP_INV_FLAGS 0x04 /* Invert the sense of TCP flags. */ -#define IPT_TCP_INV_OPTION 0x08 /* Invert the sense of option test. */ -#define IPT_TCP_INV_MASK 0x0F /* All possible flags. */ - -/* UDP matching stuff */ -struct ipt_udp -{ - u_int16_t spts[2]; /* Source port range. */ - u_int16_t dpts[2]; /* Destination port range. */ - u_int8_t invflags; /* Inverse flags */ -}; +#define IPT_TCP_INV_SRCPT XT_TCP_INV_SRCPT +#define IPT_TCP_INV_DSTPT XT_TCP_INV_DSTPT +#define IPT_TCP_INV_FLAGS XT_TCP_INV_FLAGS +#define IPT_TCP_INV_OPTION XT_TCP_INV_OPTION +#define IPT_TCP_INV_MASK XT_TCP_INV_MASK -/* Values for "invflags" field in struct ipt_udp. */ -#define IPT_UDP_INV_SRCPT 0x01 /* Invert the sense of source ports. */ -#define IPT_UDP_INV_DSTPT 0x02 /* Invert the sense of dest ports. */ -#define IPT_UDP_INV_MASK 0x03 /* All possible flags. */ +#define IPT_UDP_INV_SRCPT XT_UDP_INV_SRCPT +#define IPT_UDP_INV_DSTPT XT_UDP_INV_DSTPT +#define IPT_UDP_INV_MASK XT_UDP_INV_MASK /* ICMP matching stuff */ struct ipt_icmp @@ -260,23 +243,14 @@ struct ipt_replace /* Number of counters (must be equal to current number of entries). */ unsigned int num_counters; /* The old entries' counters. */ - struct ipt_counters __user *counters; + struct xt_counters __user *counters; /* The entries (hang off end: not really an array). */ struct ipt_entry entries[0]; }; /* The argument to IPT_SO_ADD_COUNTERS. */ -struct ipt_counters_info -{ - /* Which table. */ - char name[IPT_TABLE_MAXNAMELEN]; - - unsigned int num_counters; - - /* The counters (actually `number' of these). */ - struct ipt_counters counters[0]; -}; +#define ipt_counters_info xt_counters_info /* The argument to IPT_SO_GET_ENTRIES. */ struct ipt_get_entries @@ -291,19 +265,10 @@ struct ipt_get_entries struct ipt_entry entrytable[0]; }; -/* The argument to IPT_SO_GET_REVISION_*. Returns highest revision - * kernel supports, if >= revision. */ -struct ipt_get_revision -{ - char name[IPT_FUNCTION_MAXNAMELEN-1]; - - u_int8_t revision; -}; - /* Standard return verdict, or do jump. */ -#define IPT_STANDARD_TARGET "" +#define IPT_STANDARD_TARGET XT_STANDARD_TARGET /* Error verdict. */ -#define IPT_ERROR_TARGET "ERROR" +#define IPT_ERROR_TARGET XT_ERROR_TARGET /* Helper functions */ static __inline__ struct ipt_entry_target * @@ -356,103 +321,18 @@ ipt_get_target(struct ipt_entry *e) #include <linux/init.h> extern void ipt_init(void) __init; -struct ipt_match -{ - struct list_head list; - - const char name[IPT_FUNCTION_MAXNAMELEN-1]; - - u_int8_t revision; - - /* Return true or false: return FALSE and set *hotdrop = 1 to - force immediate packet drop. */ - /* Arguments changed since 2.4, as this must now handle - non-linear skbs, using skb_copy_bits and - skb_ip_make_writable. */ - int (*match)(const struct sk_buff *skb, - const struct net_device *in, - const struct net_device *out, - const void *matchinfo, - int offset, - int *hotdrop); - - /* Called when user tries to insert an entry of this type. */ - /* Should return true or false. */ - int (*checkentry)(const char *tablename, - const struct ipt_ip *ip, - void *matchinfo, - unsigned int matchinfosize, - unsigned int hook_mask); - - /* Called when entry of this type deleted. */ - void (*destroy)(void *matchinfo, unsigned int matchinfosize); - - /* Set this to THIS_MODULE. */ - struct module *me; -}; - -/* Registration hooks for targets. */ -struct ipt_target -{ - struct list_head list; - - const char name[IPT_FUNCTION_MAXNAMELEN-1]; - - u_int8_t revision; - - /* Called when user tries to insert an entry of this type: - hook_mask is a bitmask of hooks from which it can be - called. */ - /* Should return true or false. */ - int (*checkentry)(const char *tablename, - const struct ipt_entry *e, - void *targinfo, - unsigned int targinfosize, - unsigned int hook_mask); - - /* Called when entry of this type deleted. */ - void (*destroy)(void *targinfo, unsigned int targinfosize); - - /* Returns verdict. Argument order changed since 2.4, as this - must now handle non-linear skbs, using skb_copy_bits and - skb_ip_make_writable. */ - unsigned int (*target)(struct sk_buff **pskb, - const struct net_device *in, - const struct net_device *out, - unsigned int hooknum, - const void *targinfo, - void *userdata); - - /* Set this to THIS_MODULE. */ - struct module *me; -}; +#define ipt_register_target(tgt) xt_register_target(AF_INET, tgt) +#define ipt_unregister_target(tgt) xt_unregister_target(AF_INET, tgt) -extern int ipt_register_target(struct ipt_target *target); -extern void ipt_unregister_target(struct ipt_target *target); +#define ipt_register_match(mtch) xt_register_match(AF_INET, mtch) +#define ipt_unregister_match(mtch) xt_unregister_match(AF_INET, mtch) -extern int ipt_register_match(struct ipt_match *match); -extern void ipt_unregister_match(struct ipt_match *match); +//#define ipt_register_table(tbl, repl) xt_register_table(AF_INET, tbl, repl) +//#define ipt_unregister_table(tbl) xt_unregister_table(AF_INET, tbl) -/* Furniture shopping... */ -struct ipt_table -{ - struct list_head list; - - /* A unique name... */ - char name[IPT_TABLE_MAXNAMELEN]; - - /* What hooks you will enter on */ - unsigned int valid_hooks; - - /* Lock for the curtain */ - rwlock_t lock; - - /* Man behind the curtain... */ - struct ipt_table_info *private; - - /* Set to THIS_MODULE. */ - struct module *me; -}; +extern int ipt_register_table(struct ipt_table *table, + const struct ipt_replace *repl); +extern void ipt_unregister_table(struct ipt_table *table); /* net/sched/ipt.c: Gimme access to your targets! Gets target->me. */ extern struct ipt_target *ipt_find_target(const char *name, u8 revision); @@ -476,9 +356,6 @@ struct ipt_error struct ipt_error_target target; }; -extern int ipt_register_table(struct ipt_table *table, - const struct ipt_replace *repl); -extern void ipt_unregister_table(struct ipt_table *table); extern unsigned int ipt_do_table(struct sk_buff **pskb, unsigned int hook, const struct net_device *in, @@ -486,6 +363,6 @@ extern unsigned int ipt_do_table(struct sk_buff **pskb, struct ipt_table *table, void *userdata); -#define IPT_ALIGN(s) (((s) + (__alignof__(struct ipt_entry)-1)) & ~(__alignof__(struct ipt_entry)-1)) +#define IPT_ALIGN(s) XT_ALIGN(s) #endif /*__KERNEL__*/ #endif /* _IPTABLES_H */ diff --git a/include/linux/netfilter_ipv4/ipt_CLASSIFY.h b/include/linux/netfilter_ipv4/ipt_CLASSIFY.h index 7596e3dd00c..a46d511b5c3 100644 --- a/include/linux/netfilter_ipv4/ipt_CLASSIFY.h +++ b/include/linux/netfilter_ipv4/ipt_CLASSIFY.h @@ -1,8 +1,7 @@ #ifndef _IPT_CLASSIFY_H #define _IPT_CLASSIFY_H -struct ipt_classify_target_info { - u_int32_t priority; -}; +#include <linux/netfilter/xt_CLASSIFY.h> +#define ipt_classify_target_info xt_classify_target_info #endif /*_IPT_CLASSIFY_H */ diff --git a/include/linux/netfilter_ipv4/ipt_CONNMARK.h b/include/linux/netfilter_ipv4/ipt_CONNMARK.h index d3c02536fc4..9ecfee0a9e3 100644 --- a/include/linux/netfilter_ipv4/ipt_CONNMARK.h +++ b/include/linux/netfilter_ipv4/ipt_CONNMARK.h @@ -9,17 +9,11 @@ * the Free Software Foundation; either version 2 of the License, or * (at your option) any later version. */ +#include <linux/netfilter/xt_CONNMARK.h> +#define IPT_CONNMARK_SET XT_CONNMARK_SET +#define IPT_CONNMARK_SAVE XT_CONNMARK_SAVE +#define IPT_CONNMARK_RESTORE XT_CONNMARK_RESTORE -enum { - IPT_CONNMARK_SET = 0, - IPT_CONNMARK_SAVE, - IPT_CONNMARK_RESTORE -}; - -struct ipt_connmark_target_info { - unsigned long mark; - unsigned long mask; - u_int8_t mode; -}; +#define ipt_connmark_target_info xt_connmark_target_info #endif /*_IPT_CONNMARK_H_target*/ diff --git a/include/linux/netfilter_ipv4/ipt_MARK.h b/include/linux/netfilter_ipv4/ipt_MARK.h index f47485790ed..697a486a96d 100644 --- a/include/linux/netfilter_ipv4/ipt_MARK.h +++ b/include/linux/netfilter_ipv4/ipt_MARK.h @@ -1,20 +1,18 @@ #ifndef _IPT_MARK_H_target #define _IPT_MARK_H_target +/* Backwards compatibility for old userspace */ + +#include <linux/netfilter/xt_MARK.h> + /* Version 0 */ -struct ipt_mark_target_info { - unsigned long mark; -}; +#define ipt_mark_target_info xt_mark_target_info /* Version 1 */ -enum { - IPT_MARK_SET=0, - IPT_MARK_AND, - IPT_MARK_OR -}; +#define IPT_MARK_SET XT_MARK_SET +#define IPT_MARK_AND XT_MARK_AND +#define IPT_MARK_OR XT_MARK_OR + +#define ipt_mark_target_info_v1 xt_mark_target_info_v1 -struct ipt_mark_target_info_v1 { - unsigned long mark; - u_int8_t mode; -}; #endif /*_IPT_MARK_H_target*/ diff --git a/include/linux/netfilter_ipv4/ipt_NFQUEUE.h b/include/linux/netfilter_ipv4/ipt_NFQUEUE.h index b5b2943b0c6..97a2a7557cb 100644 --- a/include/linux/netfilter_ipv4/ipt_NFQUEUE.h +++ b/include/linux/netfilter_ipv4/ipt_NFQUEUE.h @@ -8,9 +8,9 @@ #ifndef _IPT_NFQ_TARGET_H #define _IPT_NFQ_TARGET_H -/* target info */ -struct ipt_NFQ_info { - u_int16_t queuenum; -}; +/* Backwards compatibility for old userspace */ +#include <linux/netfilter/xt_NFQUEUE.h> + +#define ipt_NFQ_info xt_NFQ_info #endif /* _IPT_DSCP_TARGET_H */ diff --git a/include/linux/netfilter_ipv4/ipt_comment.h b/include/linux/netfilter_ipv4/ipt_comment.h index 85c1123c29c..ae2afc2f748 100644 --- a/include/linux/netfilter_ipv4/ipt_comment.h +++ b/include/linux/netfilter_ipv4/ipt_comment.h @@ -1,10 +1,10 @@ #ifndef _IPT_COMMENT_H #define _IPT_COMMENT_H -#define IPT_MAX_COMMENT_LEN 256 +#include <linux/netfilter/xt_comment.h> -struct ipt_comment_info { - unsigned char comment[IPT_MAX_COMMENT_LEN]; -}; +#define IPT_MAX_COMMENT_LEN XT_MAX_COMMENT_LEN + +#define ipt_comment_info xt_comment_info #endif /* _IPT_COMMENT_H */ diff --git a/include/linux/netfilter_ipv4/ipt_connbytes.h b/include/linux/netfilter_ipv4/ipt_connbytes.h index 9e5532f8d8a..b04dfa3083c 100644 --- a/include/linux/netfilter_ipv4/ipt_connbytes.h +++ b/include/linux/netfilter_ipv4/ipt_connbytes.h @@ -1,25 +1,18 @@ #ifndef _IPT_CONNBYTES_H #define _IPT_CONNBYTES_H -enum ipt_connbytes_what { - IPT_CONNBYTES_PKTS, - IPT_CONNBYTES_BYTES, - IPT_CONNBYTES_AVGPKT, -}; +#include <net/netfilter/xt_connbytes.h> +#define ipt_connbytes_what xt_connbytes_what -enum ipt_connbytes_direction { - IPT_CONNBYTES_DIR_ORIGINAL, - IPT_CONNBYTES_DIR_REPLY, - IPT_CONNBYTES_DIR_BOTH, -}; +#define IPT_CONNBYTES_PKTS XT_CONNBYTES_PACKETS +#define IPT_CONNBYTES_BYTES XT_CONNBYTES_BYTES +#define IPT_CONNBYTES_AVGPKT XT_CONNBYTES_AVGPKT + +#define ipt_connbytes_direction xt_connbytes_direction +#define IPT_CONNBYTES_DIR_ORIGINAL XT_CONNBYTES_DIR_ORIGINAL +#define IPT_CONNBYTES_DIR_REPLY XT_CONNBYTES_DIR_REPLY +#define IPT_CONNBYTES_DIR_BOTH XT_CONNBYTES_DIR_BOTH + +#define ipt_connbytes_info xt_connbytes_info -struct ipt_connbytes_info -{ - struct { - aligned_u64 from; /* count to be matched */ - aligned_u64 to; /* count to be matched */ - } count; - u_int8_t what; /* ipt_connbytes_what */ - u_int8_t direction; /* ipt_connbytes_direction */ -}; #endif diff --git a/include/linux/netfilter_ipv4/ipt_connmark.h b/include/linux/netfilter_ipv4/ipt_connmark.h index 46573270d9a..c7ba6560d44 100644 --- a/include/linux/netfilter_ipv4/ipt_connmark.h +++ b/include/linux/netfilter_ipv4/ipt_connmark.h @@ -1,18 +1,7 @@ #ifndef _IPT_CONNMARK_H #define _IPT_CONNMARK_H -/* Copyright (C) 2002,2004 MARA Systems AB <http://www.marasystems.com> - * by Henrik Nordstrom <hno@marasystems.com> - * - * This program is free software; you can redistribute it and/or modify - * it under the terms of the GNU General Public License as published by - * the Free Software Foundation; either version 2 of the License, or - * (at your option) any later version. - */ - -struct ipt_connmark_info { - unsigned long mark, mask; - u_int8_t invert; -}; +#include <linux/netfilter/xt_connmark.h> +#define ipt_connmark_info xt_connmark_info #endif /*_IPT_CONNMARK_H*/ diff --git a/include/linux/netfilter_ipv4/ipt_conntrack.h b/include/linux/netfilter_ipv4/ipt_conntrack.h index 413c5658bd3..cde6762949c 100644 --- a/include/linux/netfilter_ipv4/ipt_conntrack.h +++ b/include/linux/netfilter_ipv4/ipt_conntrack.h @@ -5,56 +5,24 @@ #ifndef _IPT_CONNTRACK_H #define _IPT_CONNTRACK_H -#define IPT_CONNTRACK_STATE_BIT(ctinfo) (1 << ((ctinfo)%IP_CT_IS_REPLY+1)) -#define IPT_CONNTRACK_STATE_INVALID (1 << 0) +#include <linux/netfilter/xt_conntrack.h> -#define IPT_CONNTRACK_STATE_SNAT (1 << (IP_CT_NUMBER + 1)) -#define IPT_CONNTRACK_STATE_DNAT (1 << (IP_CT_NUMBER + 2)) -#define IPT_CONNTRACK_STATE_UNTRACKED (1 << (IP_CT_NUMBER + 3)) +#define IPT_CONNTRACK_STATE_BIT(ctinfo) XT_CONNTRACK_STATE_BIT(ctinfo) +#define IPT_CONNTRACK_STATE_INVALID XT_CONNTRACK_STATE_INVALID -/* flags, invflags: */ -#define IPT_CONNTRACK_STATE 0x01 -#define IPT_CONNTRACK_PROTO 0x02 -#define IPT_CONNTRACK_ORIGSRC 0x04 -#define IPT_CONNTRACK_ORIGDST 0x08 -#define IPT_CONNTRACK_REPLSRC 0x10 -#define IPT_CONNTRACK_REPLDST 0x20 -#define IPT_CONNTRACK_STATUS 0x40 -#define IPT_CONNTRACK_EXPIRES 0x80 - -/* This is exposed to userspace, so remains frozen in time. */ -struct ip_conntrack_old_tuple -{ - struct { - __u32 ip; - union { - __u16 all; - } u; - } src; - - struct { - __u32 ip; - union { - __u16 all; - } u; - - /* The protocol. */ - u16 protonum; - } dst; -}; +#define IPT_CONNTRACK_STATE_SNAT XT_CONNTRACK_STATE_SNAT +#define IPT_CONNTRACK_STATE_DNAT XT_CONNTRACK_STATE_DNAT +#define IPT_CONNTRACK_STATE_UNTRACKED XT_CONNTRACK_STATE_UNTRACKED -struct ipt_conntrack_info -{ - unsigned int statemask, statusmask; - - struct ip_conntrack_old_tuple tuple[IP_CT_DIR_MAX]; - struct in_addr sipmsk[IP_CT_DIR_MAX], dipmsk[IP_CT_DIR_MAX]; - - unsigned long expires_min, expires_max; - - /* Flags word */ - u_int8_t flags; - /* Inverse flags */ - u_int8_t invflags; -}; +/* flags, invflags: */ +#define IPT_CONNTRACK_STATE XT_CONNTRACK_STATE +#define IPT_CONNTRACK_PROTO XT_CONNTRACK_PROTO +#define IPT_CONNTRACK_ORIGSRC XT_CONNTRACK_ORIGSRC +#define IPT_CONNTRACK_ORIGDST XT_CONNTRACK_ORIGDST +#define IPT_CONNTRACK_REPLSRC XT_CONNTRACK_REPLSRC +#define IPT_CONNTRACK_REPLDST XT_CONNTRACK_REPLDST +#define IPT_CONNTRACK_STATUS XT_CONNTRACK_STATUS +#define IPT_CONNTRACK_EXPIRES XT_CONNTRACK_EXPIRES + +#define ipt_conntrack_info xt_conntrack_info #endif /*_IPT_CONNTRACK_H*/ diff --git a/include/linux/netfilter_ipv4/ipt_dccp.h b/include/linux/netfilter_ipv4/ipt_dccp.h index 3cb3a522e62..e70d11e1f53 100644 --- a/include/linux/netfilter_ipv4/ipt_dccp.h +++ b/include/linux/netfilter_ipv4/ipt_dccp.h @@ -1,23 +1,15 @@ #ifndef _IPT_DCCP_H_ #define _IPT_DCCP_H_ -#define IPT_DCCP_SRC_PORTS 0x01 -#define IPT_DCCP_DEST_PORTS 0x02 -#define IPT_DCCP_TYPE 0x04 -#define IPT_DCCP_OPTION 0x08 +#include <linux/netfilter/xt_dccp.h> +#define IPT_DCCP_SRC_PORTS XT_DCCP_SRC_PORTS +#define IPT_DCCP_DEST_PORTS XT_DCCP_DEST_PORTS +#define IPT_DCCP_TYPE XT_DCCP_TYPE +#define IPT_DCCP_OPTION XT_DCCP_OPTION -#define IPT_DCCP_VALID_FLAGS 0x0f +#define IPT_DCCP_VALID_FLAGS XT_DCCP_VALID_FLAGS -struct ipt_dccp_info { - u_int16_t dpts[2]; /* Min, Max */ - u_int16_t spts[2]; /* Min, Max */ - - u_int16_t flags; - u_int16_t invflags; - - u_int16_t typemask; - u_int8_t option; -}; +#define ipt_dccp_info xt_dccp_info #endif /* _IPT_DCCP_H_ */ diff --git a/include/linux/netfilter_ipv4/ipt_helper.h b/include/linux/netfilter_ipv4/ipt_helper.h index 6f12ecb8c93..80452c21855 100644 --- a/include/linux/netfilter_ipv4/ipt_helper.h +++ b/include/linux/netfilter_ipv4/ipt_helper.h @@ -1,8 +1,7 @@ #ifndef _IPT_HELPER_H #define _IPT_HELPER_H -struct ipt_helper_info { - int invert; - char name[30]; -}; +#include <linux/netfilter/xt_helper.h> +#define ipt_helper_info xt_helper_info + #endif /* _IPT_HELPER_H */ diff --git a/include/linux/netfilter_ipv4/ipt_length.h b/include/linux/netfilter_ipv4/ipt_length.h index 6e088522961..9b45206ffce 100644 --- a/include/linux/netfilter_ipv4/ipt_length.h +++ b/include/linux/netfilter_ipv4/ipt_length.h @@ -1,9 +1,7 @@ #ifndef _IPT_LENGTH_H #define _IPT_LENGTH_H -struct ipt_length_info { - u_int16_t min, max; - u_int8_t invert; -}; +#include <linux/netfilter/xt_length.h> +#define ipt_length_info xt_length_info #endif /*_IPT_LENGTH_H*/ diff --git a/include/linux/netfilter_ipv4/ipt_limit.h b/include/linux/netfilter_ipv4/ipt_limit.h index 256453409e2..92f5cd07bbc 100644 --- a/include/linux/netfilter_ipv4/ipt_limit.h +++ b/include/linux/netfilter_ipv4/ipt_limit.h @@ -1,21 +1,8 @@ #ifndef _IPT_RATE_H #define _IPT_RATE_H -/* timings are in milliseconds. */ -#define IPT_LIMIT_SCALE 10000 +#include <linux/netfilter/xt_limit.h> +#define IPT_LIMIT_SCALE XT_LIMIT_SCALE +#define ipt_rateinfo xt_rateinfo -/* 1/10,000 sec period => max of 10,000/sec. Min rate is then 429490 - seconds, or one every 59 hours. */ -struct ipt_rateinfo { - u_int32_t avg; /* Average secs between packets * scale */ - u_int32_t burst; /* Period multiplier for upper limit. */ - - /* Used internally by the kernel */ - unsigned long prev; - u_int32_t credit; - u_int32_t credit_cap, cost; - - /* Ugly, ugly fucker. */ - struct ipt_rateinfo *master; -}; #endif /*_IPT_RATE_H*/ diff --git a/include/linux/netfilter_ipv4/ipt_mac.h b/include/linux/netfilter_ipv4/ipt_mac.h index f8d5b8e7ccd..b186008a3c4 100644 --- a/include/linux/netfilter_ipv4/ipt_mac.h +++ b/include/linux/netfilter_ipv4/ipt_mac.h @@ -1,8 +1,7 @@ #ifndef _IPT_MAC_H #define _IPT_MAC_H -struct ipt_mac_info { - unsigned char srcaddr[ETH_ALEN]; - int invert; -}; +#include <linux/netfilter/xt_mac.h> +#define ipt_mac_info xt_mac_info + #endif /*_IPT_MAC_H*/ diff --git a/include/linux/netfilter_ipv4/ipt_mark.h b/include/linux/netfilter_ipv4/ipt_mark.h index f3952b563d4..bfde67c6122 100644 --- a/include/linux/netfilter_ipv4/ipt_mark.h +++ b/include/linux/netfilter_ipv4/ipt_mark.h @@ -1,9 +1,9 @@ #ifndef _IPT_MARK_H #define _IPT_MARK_H -struct ipt_mark_info { - unsigned long mark, mask; - u_int8_t invert; -}; +/* Backwards compatibility for old userspace */ +#include <linux/netfilter/xt_mark.h> + +#define ipt_mark_info xt_mark_info #endif /*_IPT_MARK_H*/ diff --git a/include/linux/netfilter_ipv4/ipt_physdev.h b/include/linux/netfilter_ipv4/ipt_physdev.h index 7538c8655ec..2400e7140f2 100644 --- a/include/linux/netfilter_ipv4/ipt_physdev.h +++ b/include/linux/netfilter_ipv4/ipt_physdev.h @@ -1,24 +1,17 @@ #ifndef _IPT_PHYSDEV_H #define _IPT_PHYSDEV_H -#ifdef __KERNEL__ -#include <linux/if.h> -#endif +/* Backwards compatibility for old userspace */ -#define IPT_PHYSDEV_OP_IN 0x01 -#define IPT_PHYSDEV_OP_OUT 0x02 -#define IPT_PHYSDEV_OP_BRIDGED 0x04 -#define IPT_PHYSDEV_OP_ISIN 0x08 -#define IPT_PHYSDEV_OP_ISOUT 0x10 -#define IPT_PHYSDEV_OP_MASK (0x20 - 1) +#include <linux/netfilter/xt_physdev.h> -struct ipt_physdev_info { - char physindev[IFNAMSIZ]; - char in_mask[IFNAMSIZ]; - char physoutdev[IFNAMSIZ]; - char out_mask[IFNAMSIZ]; - u_int8_t invert; - u_int8_t bitmask; -}; +#define IPT_PHYSDEV_OP_IN XT_PHYSDEV_OP_IN +#define IPT_PHYSDEV_OP_OUT XT_PHYSDEV_OP_OUT +#define IPT_PHYSDEV_OP_BRIDGED XT_PHYSDEV_OP_BRIDGED +#define IPT_PHYSDEV_OP_ISIN XT_PHYSDEV_OP_ISIN +#define IPT_PHYSDEV_OP_ISOUT XT_PHYSDEV_OP_ISOUT +#define IPT_PHYSDEV_OP_MASK XT_PHYSDEV_OP_MASK + +#define ipt_physdev_info xt_physdev_info #endif /*_IPT_PHYSDEV_H*/ diff --git a/include/linux/netfilter_ipv4/ipt_pkttype.h b/include/linux/netfilter_ipv4/ipt_pkttype.h index d53a6584868..ff1fbc949a0 100644 --- a/include/linux/netfilter_ipv4/ipt_pkttype.h +++ b/include/linux/netfilter_ipv4/ipt_pkttype.h @@ -1,8 +1,7 @@ #ifndef _IPT_PKTTYPE_H #define _IPT_PKTTYPE_H -struct ipt_pkttype_info { - int pkttype; - int invert; -}; +#include <linux/netfilter/xt_pkttype.h> +#define ipt_pkttype_info xt_pkttype_info + #endif /*_IPT_PKTTYPE_H*/ diff --git a/include/linux/netfilter_ipv4/ipt_realm.h b/include/linux/netfilter_ipv4/ipt_realm.h index a4d6698723a..b3996eaa018 100644 --- a/include/linux/netfilter_ipv4/ipt_realm.h +++ b/include/linux/netfilter_ipv4/ipt_realm.h @@ -1,10 +1,7 @@ #ifndef _IPT_REALM_H #define _IPT_REALM_H -struct ipt_realm_info { - u_int32_t id; - u_int32_t mask; - u_int8_t invert; -}; +#include <linux/netfilter/xt_realm.h> +#define ipt_realm_info xt_realm_info #endif /* _IPT_REALM_H */ diff --git a/include/linux/netfilter_ipv4/ipt_state.h b/include/linux/netfilter_ipv4/ipt_state.h index 5df37868933..a44a99cc28c 100644 --- a/include/linux/netfilter_ipv4/ipt_state.h +++ b/include/linux/netfilter_ipv4/ipt_state.h @@ -1,13 +1,15 @@ #ifndef _IPT_STATE_H #define _IPT_STATE_H -#define IPT_STATE_BIT(ctinfo) (1 << ((ctinfo)%IP_CT_IS_REPLY+1)) -#define IPT_STATE_INVALID (1 << 0) +/* Backwards compatibility for old userspace */ -#define IPT_STATE_UNTRACKED (1 << (IP_CT_NUMBER + 1)) +#include <linux/netfilter/xt_state.h> + +#define IPT_STATE_BIT XT_STATE_BIT +#define IPT_STATE_INVALID XT_STATE_INVALID + +#define IPT_STATE_UNTRACKED XT_STATE_UNTRACKED + +#define ipt_state_info xt_state_info -struct ipt_state_info -{ - unsigned int statemask; -}; #endif /*_IPT_STATE_H*/ diff --git a/include/linux/netfilter_ipv4/ipt_string.h b/include/linux/netfilter_ipv4/ipt_string.h index a265f6e44ea..c26de305990 100644 --- a/include/linux/netfilter_ipv4/ipt_string.h +++ b/include/linux/netfilter_ipv4/ipt_string.h @@ -1,18 +1,10 @@ #ifndef _IPT_STRING_H #define _IPT_STRING_H -#define IPT_STRING_MAX_PATTERN_SIZE 128 -#define IPT_STRING_MAX_ALGO_NAME_SIZE 16 +#include <linux/netfilter/xt_string.h> -struct ipt_string_info -{ - u_int16_t from_offset; - u_int16_t to_offset; - char algo[IPT_STRING_MAX_ALGO_NAME_SIZE]; - char pattern[IPT_STRING_MAX_PATTERN_SIZE]; - u_int8_t patlen; - u_int8_t invert; - struct ts_config __attribute__((aligned(8))) *config; -}; +#define IPT_STRING_MAX_PATTERN_SIZE XT_STRING_MAX_PATTERN_SIZE +#define IPT_STRING_MAX_ALGO_NAME_SIZE XT_STRING_MAX_ALGO_NAME_SIZE +#define ipt_string_info xt_string_info #endif /*_IPT_STRING_H*/ diff --git a/include/linux/netfilter_ipv4/ipt_tcpmss.h b/include/linux/netfilter_ipv4/ipt_tcpmss.h index e2b14397f70..18bbc8e8e00 100644 --- a/include/linux/netfilter_ipv4/ipt_tcpmss.h +++ b/include/linux/netfilter_ipv4/ipt_tcpmss.h @@ -1,9 +1,7 @@ #ifndef _IPT_TCPMSS_MATCH_H #define _IPT_TCPMSS_MATCH_H -struct ipt_tcpmss_match_info { - u_int16_t mss_min, mss_max; - u_int8_t invert; -}; +#include <linux/netfilter/xt_tcpmss.h> +#define ipt_tcpmss_match_info xt_tcpmss_match_info #endif /*_IPT_TCPMSS_MATCH_H*/ diff --git a/include/linux/netfilter_ipv6/ip6_tables.h b/include/linux/netfilter_ipv6/ip6_tables.h index c163ba31aab..f249b574f0f 100644 --- a/include/linux/netfilter_ipv6/ip6_tables.h +++ b/include/linux/netfilter_ipv6/ip6_tables.h @@ -25,8 +25,15 @@ #include <linux/compiler.h> #include <linux/netfilter_ipv6.h> -#define IP6T_FUNCTION_MAXNAMELEN 30 -#define IP6T_TABLE_MAXNAMELEN 32 +#include <linux/netfilter/x_tables.h> + +#define IP6T_FUNCTION_MAXNAMELEN XT_FUNCTION_MAXNAMELEN +#define IP6T_TABLE_MAXNAMELEN XT_TABLE_MAXNAMELEN + +#define ip6t_match xt_match +#define ip6t_target xt_target +#define ip6t_table xt_table +#define ip6t_get_revision xt_get_revision /* Yes, Virginia, you have to zero the padding. */ struct ip6t_ip6 { @@ -104,10 +111,7 @@ struct ip6t_standard_target int verdict; }; -struct ip6t_counters -{ - u_int64_t pcnt, bcnt; /* Packet and byte counters */ -}; +#define ip6t_counters xt_counters /* Values for "flag" field in struct ip6t_ip6 (general ip6 structure). */ #define IP6T_F_PROTO 0x01 /* Set if rule cares about upper @@ -123,7 +127,7 @@ struct ip6t_counters #define IP6T_INV_SRCIP 0x08 /* Invert the sense of SRC IP. */ #define IP6T_INV_DSTIP 0x10 /* Invert the sense of DST OP. */ #define IP6T_INV_FRAG 0x20 /* Invert the sense of FRAG. */ -#define IP6T_INV_PROTO 0x40 /* Invert the sense of PROTO. */ +#define IP6T_INV_PROTO XT_INV_PROTO #define IP6T_INV_MASK 0x7F /* All possible flag bits mask. */ /* This structure defines each of the firewall rules. Consists of 3 @@ -145,7 +149,7 @@ struct ip6t_entry unsigned int comefrom; /* Packet and byte counters. */ - struct ip6t_counters counters; + struct xt_counters counters; /* The matches (if any), then the target. */ unsigned char elems[0]; @@ -155,54 +159,41 @@ struct ip6t_entry * New IP firewall options for [gs]etsockopt at the RAW IP level. * Unlike BSD Linux inherits IP options so you don't have to use * a raw socket for this. Instead we check rights in the calls. */ -#define IP6T_BASE_CTL 64 /* base for firewall socket options */ +#define IP6T_BASE_CTL XT_BASE_CTL -#define IP6T_SO_SET_REPLACE (IP6T_BASE_CTL) -#define IP6T_SO_SET_ADD_COUNTERS (IP6T_BASE_CTL + 1) -#define IP6T_SO_SET_MAX IP6T_SO_SET_ADD_COUNTERS +#define IP6T_SO_SET_REPLACE XT_SO_SET_REPLACE +#define IP6T_SO_SET_ADD_COUNTERS XT_SO_SET_ADD_COUNTERS +#define IP6T_SO_SET_MAX XT_SO_SET_MAX -#define IP6T_SO_GET_INFO (IP6T_BASE_CTL) -#define IP6T_SO_GET_ENTRIES (IP6T_BASE_CTL + 1) -#define IP6T_SO_GET_REVISION_MATCH (IP6T_BASE_CTL + 2) -#define IP6T_SO_GET_REVISION_TARGET (IP6T_BASE_CTL + 3) -#define IP6T_SO_GET_MAX IP6T_SO_GET_REVISION_TARGET +#define IP6T_SO_GET_INFO XT_SO_GET_INFO +#define IP6T_SO_GET_ENTRIES XT_SO_GET_ENTRIES +#define IP6T_SO_GET_REVISION_MATCH XT_SO_GET_REVISION_MATCH +#define IP6T_SO_GET_REVISION_TARGET XT_SO_GET_REVISION_TARGET +#define IP6T_SO_GET_MAX XT_SO_GET_REVISION_TARGET /* CONTINUE verdict for targets */ -#define IP6T_CONTINUE 0xFFFFFFFF +#define IP6T_CONTINUE XT_CONTINUE /* For standard target */ -#define IP6T_RETURN (-NF_REPEAT - 1) +#define IP6T_RETURN XT_RETURN -/* TCP matching stuff */ -struct ip6t_tcp -{ - u_int16_t spts[2]; /* Source port range. */ - u_int16_t dpts[2]; /* Destination port range. */ - u_int8_t option; /* TCP Option iff non-zero*/ - u_int8_t flg_mask; /* TCP flags mask byte */ - u_int8_t flg_cmp; /* TCP flags compare byte */ - u_int8_t invflags; /* Inverse flags */ -}; +/* TCP/UDP matching stuff */ +#include <linux/netfilter/xt_tcpudp.h> + +#define ip6t_tcp xt_tcp +#define ip6t_udp xt_udp /* Values for "inv" field in struct ipt_tcp. */ -#define IP6T_TCP_INV_SRCPT 0x01 /* Invert the sense of source ports. */ -#define IP6T_TCP_INV_DSTPT 0x02 /* Invert the sense of dest ports. */ -#define IP6T_TCP_INV_FLAGS 0x04 /* Invert the sense of TCP flags. */ -#define IP6T_TCP_INV_OPTION 0x08 /* Invert the sense of option test. */ -#define IP6T_TCP_INV_MASK 0x0F /* All possible flags. */ - -/* UDP matching stuff */ -struct ip6t_udp -{ - u_int16_t spts[2]; /* Source port range. */ - u_int16_t dpts[2]; /* Destination port range. */ - u_int8_t invflags; /* Inverse flags */ -}; +#define IP6T_TCP_INV_SRCPT XT_TCP_INV_SRCPT +#define IP6T_TCP_INV_DSTPT XT_TCP_INV_DSTPT +#define IP6T_TCP_INV_FLAGS XT_TCP_INV_FLAGS +#define IP6T_TCP_INV_OPTION XT_TCP_INV_OPTION +#define IP6T_TCP_INV_MASK XT_TCP_INV_MASK /* Values for "invflags" field in struct ipt_udp. */ -#define IP6T_UDP_INV_SRCPT 0x01 /* Invert the sense of source ports. */ -#define IP6T_UDP_INV_DSTPT 0x02 /* Invert the sense of dest ports. */ -#define IP6T_UDP_INV_MASK 0x03 /* All possible flags. */ +#define IP6T_UDP_INV_SRCPT XT_UDP_INV_SRCPT +#define IP6T_UDP_INV_DSTPT XT_UDP_INV_DSTPT +#define IP6T_UDP_INV_MASK XT_UDP_INV_MASK /* ICMP matching stuff */ struct ip6t_icmp @@ -264,23 +255,14 @@ struct ip6t_replace /* Number of counters (must be equal to current number of entries). */ unsigned int num_counters; /* The old entries' counters. */ - struct ip6t_counters __user *counters; + struct xt_counters __user *counters; /* The entries (hang off end: not really an array). */ struct ip6t_entry entries[0]; }; /* The argument to IP6T_SO_ADD_COUNTERS. */ -struct ip6t_counters_info -{ - /* Which table. */ - char name[IP6T_TABLE_MAXNAMELEN]; - - unsigned int num_counters; - - /* The counters (actually `number' of these). */ - struct ip6t_counters counters[0]; -}; +#define ip6t_counters_info xt_counters_info /* The argument to IP6T_SO_GET_ENTRIES. */ struct ip6t_get_entries @@ -295,19 +277,10 @@ struct ip6t_get_entries struct ip6t_entry entrytable[0]; }; -/* The argument to IP6T_SO_GET_REVISION_*. Returns highest revision - * kernel supports, if >= revision. */ -struct ip6t_get_revision -{ - char name[IP6T_FUNCTION_MAXNAMELEN-1]; - - u_int8_t revision; -}; - /* Standard return verdict, or do jump. */ -#define IP6T_STANDARD_TARGET "" +#define IP6T_STANDARD_TARGET XT_STANDARD_TARGET /* Error verdict. */ -#define IP6T_ERROR_TARGET "ERROR" +#define IP6T_ERROR_TARGET XT_ERROR_TARGET /* Helper functions */ static __inline__ struct ip6t_entry_target * @@ -361,104 +334,11 @@ ip6t_get_target(struct ip6t_entry *e) #include <linux/init.h> extern void ip6t_init(void) __init; -struct ip6t_match -{ - struct list_head list; - - const char name[IP6T_FUNCTION_MAXNAMELEN-1]; - - u_int8_t revision; - - /* Return true or false: return FALSE and set *hotdrop = 1 to - force immediate packet drop. */ - /* Arguments changed since 2.6.9, as this must now handle - non-linear skb, using skb_header_pointer and - skb_ip_make_writable. */ - int (*match)(const struct sk_buff *skb, - const struct net_device *in, - const struct net_device *out, - const void *matchinfo, - int offset, - unsigned int protoff, - int *hotdrop); - - /* Called when user tries to insert an entry of this type. */ - /* Should return true or false. */ - int (*checkentry)(const char *tablename, - const struct ip6t_ip6 *ip, - void *matchinfo, - unsigned int matchinfosize, - unsigned int hook_mask); - - /* Called when entry of this type deleted. */ - void (*destroy)(void *matchinfo, unsigned int matchinfosize); - - /* Set this to THIS_MODULE if you are a module, otherwise NULL */ - struct module *me; -}; - -/* Registration hooks for targets. */ -struct ip6t_target -{ - struct list_head list; - - const char name[IP6T_FUNCTION_MAXNAMELEN-1]; - - u_int8_t revision; - - /* Returns verdict. Argument order changed since 2.6.9, as this - must now handle non-linear skbs, using skb_copy_bits and - skb_ip_make_writable. */ - unsigned int (*target)(struct sk_buff **pskb, - const struct net_device *in, - const struct net_device *out, - unsigned int hooknum, - const void *targinfo, - void *userdata); - - /* Called when user tries to insert an entry of this type: - hook_mask is a bitmask of hooks from which it can be - called. */ - /* Should return true or false. */ - int (*checkentry)(const char *tablename, - const struct ip6t_entry *e, - void *targinfo, - unsigned int targinfosize, - unsigned int hook_mask); - - /* Called when entry of this type deleted. */ - void (*destroy)(void *targinfo, unsigned int targinfosize); - - /* Set this to THIS_MODULE if you are a module, otherwise NULL */ - struct module *me; -}; - -extern int ip6t_register_target(struct ip6t_target *target); -extern void ip6t_unregister_target(struct ip6t_target *target); - -extern int ip6t_register_match(struct ip6t_match *match); -extern void ip6t_unregister_match(struct ip6t_match *match); +#define ip6t_register_target(tgt) xt_register_target(AF_INET6, tgt) +#define ip6t_unregister_target(tgt) xt_unregister_target(AF_INET6, tgt) -/* Furniture shopping... */ -struct ip6t_table -{ - struct list_head list; - - /* A unique name... */ - char name[IP6T_TABLE_MAXNAMELEN]; - - /* What hooks you will enter on */ - unsigned int valid_hooks; - - /* Lock for the curtain */ - rwlock_t lock; - - /* Man behind the curtain... */ - struct ip6t_table_info *private; - - /* Set this to THIS_MODULE if you are a module, otherwise NULL */ - struct module *me; -}; +#define ip6t_register_match(match) xt_register_match(AF_INET6, match) +#define ip6t_unregister_match(match) xt_unregister_match(AF_INET6, match) extern int ip6t_register_table(struct ip6t_table *table, const struct ip6t_replace *repl); diff --git a/include/linux/netfilter_ipv6/ip6t_MARK.h b/include/linux/netfilter_ipv6/ip6t_MARK.h index 7ade8d8f524..7cf629a8ab9 100644 --- a/include/linux/netfilter_ipv6/ip6t_MARK.h +++ b/include/linux/netfilter_ipv6/ip6t_MARK.h @@ -1,8 +1,9 @@ #ifndef _IP6T_MARK_H_target #define _IP6T_MARK_H_target -struct ip6t_mark_target_info { - unsigned long mark; -}; +/* Backwards compatibility for old userspace */ +#include <linux/netfilter/xt_MARK.h> -#endif /*_IPT_MARK_H_target*/ +#define ip6t_mark_target_info xt_mark_target_info + +#endif /*_IP6T_MARK_H_target*/ diff --git a/include/linux/netfilter_ipv6/ip6t_length.h b/include/linux/netfilter_ipv6/ip6t_length.h index 7fc09f9f9d6..9e9689d03ed 100644 --- a/include/linux/netfilter_ipv6/ip6t_length.h +++ b/include/linux/netfilter_ipv6/ip6t_length.h @@ -1,10 +1,8 @@ #ifndef _IP6T_LENGTH_H #define _IP6T_LENGTH_H -struct ip6t_length_info { - u_int16_t min, max; - u_int8_t invert; -}; +#include <linux/netfilter/xt_length.h> +#define ip6t_length_info xt_length_info #endif /*_IP6T_LENGTH_H*/ diff --git a/include/linux/netfilter_ipv6/ip6t_limit.h b/include/linux/netfilter_ipv6/ip6t_limit.h index f2866e50f3b..487e5ea342c 100644 --- a/include/linux/netfilter_ipv6/ip6t_limit.h +++ b/include/linux/netfilter_ipv6/ip6t_limit.h @@ -1,21 +1,8 @@ #ifndef _IP6T_RATE_H #define _IP6T_RATE_H -/* timings are in milliseconds. */ -#define IP6T_LIMIT_SCALE 10000 +#include <linux/netfilter/xt_limit.h> +#define IP6T_LIMIT_SCALE XT_LIMIT_SCALE +#define ip6t_rateinfo xt_rateinfo -/* 1/10,000 sec period => max of 10,000/sec. Min rate is then 429490 - seconds, or one every 59 hours. */ -struct ip6t_rateinfo { - u_int32_t avg; /* Average secs between packets * scale */ - u_int32_t burst; /* Period multiplier for upper limit. */ - - /* Used internally by the kernel */ - unsigned long prev; - u_int32_t credit; - u_int32_t credit_cap, cost; - - /* Ugly, ugly fucker. */ - struct ip6t_rateinfo *master; -}; -#endif /*_IPT_RATE_H*/ +#endif /*_IP6T_RATE_H*/ diff --git a/include/linux/netfilter_ipv6/ip6t_mac.h b/include/linux/netfilter_ipv6/ip6t_mac.h index 87c088c2184..ac58e83e942 100644 --- a/include/linux/netfilter_ipv6/ip6t_mac.h +++ b/include/linux/netfilter_ipv6/ip6t_mac.h @@ -1,8 +1,7 @@ #ifndef _IP6T_MAC_H #define _IP6T_MAC_H -struct ip6t_mac_info { - unsigned char srcaddr[ETH_ALEN]; - int invert; -}; -#endif /*_IPT_MAC_H*/ +#include <linux/netfilter/xt_mac.h> +#define ip6t_mac_info xt_mac_info + +#endif /*_IP6T_MAC_H*/ diff --git a/include/linux/netfilter_ipv6/ip6t_mark.h b/include/linux/netfilter_ipv6/ip6t_mark.h index a734441e1c1..ff204951ddc 100644 --- a/include/linux/netfilter_ipv6/ip6t_mark.h +++ b/include/linux/netfilter_ipv6/ip6t_mark.h @@ -1,9 +1,9 @@ #ifndef _IP6T_MARK_H #define _IP6T_MARK_H -struct ip6t_mark_info { - unsigned long mark, mask; - u_int8_t invert; -}; +/* Backwards compatibility for old userspace */ +#include <linux/netfilter/xt_mark.h> + +#define ip6t_mark_info xt_mark_info #endif /*_IPT_MARK_H*/ diff --git a/include/linux/netfilter_ipv6/ip6t_physdev.h b/include/linux/netfilter_ipv6/ip6t_physdev.h index c234731cd66..c161c0a81b5 100644 --- a/include/linux/netfilter_ipv6/ip6t_physdev.h +++ b/include/linux/netfilter_ipv6/ip6t_physdev.h @@ -1,24 +1,17 @@ #ifndef _IP6T_PHYSDEV_H #define _IP6T_PHYSDEV_H -#ifdef __KERNEL__ -#include <linux/if.h> -#endif +/* Backwards compatibility for old userspace */ -#define IP6T_PHYSDEV_OP_IN 0x01 -#define IP6T_PHYSDEV_OP_OUT 0x02 -#define IP6T_PHYSDEV_OP_BRIDGED 0x04 -#define IP6T_PHYSDEV_OP_ISIN 0x08 -#define IP6T_PHYSDEV_OP_ISOUT 0x10 -#define IP6T_PHYSDEV_OP_MASK (0x20 - 1) +#include <linux/netfilter/xt_physdev.h> -struct ip6t_physdev_info { - char physindev[IFNAMSIZ]; - char in_mask[IFNAMSIZ]; - char physoutdev[IFNAMSIZ]; - char out_mask[IFNAMSIZ]; - u_int8_t invert; - u_int8_t bitmask; -}; +#define IP6T_PHYSDEV_OP_IN XT_PHYSDEV_OP_IN +#define IP6T_PHYSDEV_OP_OUT XT_PHYSDEV_OP_OUT +#define IP6T_PHYSDEV_OP_BRIDGED XT_PHYSDEV_OP_BRIDGED +#define IP6T_PHYSDEV_OP_ISIN XT_PHYSDEV_OP_ISIN +#define IP6T_PHYSDEV_OP_ISOUT XT_PHYSDEV_OP_ISOUT +#define IP6T_PHYSDEV_OP_MASK XT_PHYSDEV_OP_MASK + +#define ip6t_physdev_info xt_physdev_info #endif /*_IP6T_PHYSDEV_H*/ diff --git a/include/linux/proc_fs.h b/include/linux/proc_fs.h index 74488e49166..aa6322d4519 100644 --- a/include/linux/proc_fs.h +++ b/include/linux/proc_fs.h @@ -146,6 +146,11 @@ struct property; extern void proc_device_tree_init(void); extern void proc_device_tree_add_node(struct device_node *, struct proc_dir_entry *); extern void proc_device_tree_add_prop(struct proc_dir_entry *pde, struct property *prop); +extern void proc_device_tree_remove_prop(struct proc_dir_entry *pde, + struct property *prop); +extern void proc_device_tree_update_prop(struct proc_dir_entry *pde, + struct property *newprop, + struct property *oldprop); #endif /* CONFIG_PROC_DEVICETREE */ extern struct proc_dir_entry *proc_symlink(const char *, diff --git a/include/linux/socket.h b/include/linux/socket.h index 9f4019156fd..b02dda4ee83 100644 --- a/include/linux/socket.h +++ b/include/linux/socket.h @@ -186,6 +186,7 @@ struct ucred { #define AF_PPPOX 24 /* PPPoX sockets */ #define AF_WANPIPE 25 /* Wanpipe API Sockets */ #define AF_LLC 26 /* Linux LLC */ +#define AF_TIPC 30 /* TIPC sockets */ #define AF_BLUETOOTH 31 /* Bluetooth sockets */ #define AF_MAX 32 /* For now.. */ @@ -218,6 +219,7 @@ struct ucred { #define PF_PPPOX AF_PPPOX #define PF_WANPIPE AF_WANPIPE #define PF_LLC AF_LLC +#define PF_TIPC AF_TIPC #define PF_BLUETOOTH AF_BLUETOOTH #define PF_MAX AF_MAX @@ -279,6 +281,7 @@ struct ucred { #define SOL_LLC 268 #define SOL_DCCP 269 #define SOL_NETLINK 270 +#define SOL_TIPC 271 /* IPX options */ #define IPX_TYPE 1 diff --git a/include/linux/tipc.h b/include/linux/tipc.h new file mode 100644 index 00000000000..243a15f5400 --- /dev/null +++ b/include/linux/tipc.h @@ -0,0 +1,212 @@ +/* + * include/linux/tipc.h: Include file for TIPC socket interface + * + * Copyright (c) 2003-2006, Ericsson AB + * Copyright (c) 2005, Wind River Systems + * All rights reserved. + * + * Redistribution and use in source and binary forms, with or without + * modification, are permitted provided that the following conditions are met: + * + * 1. Redistributions of source code must retain the above copyright + * notice, this list of conditions and the following disclaimer. + * 2. Redistributions in binary form must reproduce the above copyright + * notice, this list of conditions and the following disclaimer in the + * documentation and/or other materials provided with the distribution. + * 3. Neither the names of the copyright holders nor the names of its + * contributors may be used to endorse or promote products derived from + * this software without specific prior written permission. + * + * Alternatively, this software may be distributed under the terms of the + * GNU General Public License ("GPL") version 2 as published by the Free + * Software Foundation. + * + * THIS SOFTWARE IS PROVIDED BY THE COPYRIGHT HOLDERS AND CONTRIBUTORS "AS IS" + * AND ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT LIMITED TO, THE + * IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR A PARTICULAR PURPOSE + * ARE DISCLAIMED. IN NO EVENT SHALL THE COPYRIGHT OWNER OR CONTRIBUTORS BE + * LIABLE FOR ANY DIRECT, INDIRECT, INCIDENTAL, SPECIAL, EXEMPLARY, OR + * CONSEQUENTIAL DAMAGES (INCLUDING, BUT NOT LIMITED TO, PROCUREMENT OF + * SUBSTITUTE GOODS OR SERVICES; LOSS OF USE, DATA, OR PROFITS; OR BUSINESS + * INTERRUPTION) HOWEVER CAUSED AND ON ANY THEORY OF LIABILITY, WHETHER IN + * CONTRACT, STRICT LIABILITY, OR TORT (INCLUDING NEGLIGENCE OR OTHERWISE) + * ARISING IN ANY WAY OUT OF THE USE OF THIS SOFTWARE, EVEN IF ADVISED OF THE + * POSSIBILITY OF SUCH DAMAGE. + */ + +#ifndef _LINUX_TIPC_H_ +#define _LINUX_TIPC_H_ + +#include <linux/types.h> + +/* + * TIPC addressing primitives + */ + +struct tipc_portid { + __u32 ref; + __u32 node; +}; + +struct tipc_name { + __u32 type; + __u32 instance; +}; + +struct tipc_name_seq { + __u32 type; + __u32 lower; + __u32 upper; +}; + +static inline __u32 tipc_addr(unsigned int zone, + unsigned int cluster, + unsigned int node) +{ + return (zone << 24) | (cluster << 12) | node; +} + +static inline unsigned int tipc_zone(__u32 addr) +{ + return addr >> 24; +} + +static inline unsigned int tipc_cluster(__u32 addr) +{ + return (addr >> 12) & 0xfff; +} + +static inline unsigned int tipc_node(__u32 addr) +{ + return addr & 0xfff; +} + +/* + * Application-accessible port name types + */ + +#define TIPC_CFG_SRV 0 /* configuration service name type */ +#define TIPC_TOP_SRV 1 /* topology service name type */ +#define TIPC_RESERVED_TYPES 64 /* lowest user-publishable name type */ + +/* + * Publication scopes when binding port names and port name sequences + */ + +#define TIPC_ZONE_SCOPE 1 +#define TIPC_CLUSTER_SCOPE 2 +#define TIPC_NODE_SCOPE 3 + +/* + * Limiting values for messages + */ + +#define TIPC_MAX_USER_MSG_SIZE 66000 + +/* + * Message importance levels + */ + +#define TIPC_LOW_IMPORTANCE 0 /* default */ +#define TIPC_MEDIUM_IMPORTANCE 1 +#define TIPC_HIGH_IMPORTANCE 2 +#define TIPC_CRITICAL_IMPORTANCE 3 + +/* + * Msg rejection/connection shutdown reasons + */ + +#define TIPC_OK 0 +#define TIPC_ERR_NO_NAME 1 +#define TIPC_ERR_NO_PORT 2 +#define TIPC_ERR_NO_NODE 3 +#define TIPC_ERR_OVERLOAD 4 +#define TIPC_CONN_SHUTDOWN 5 + +/* + * TIPC topology subscription service definitions + */ + +#define TIPC_SUB_PORTS 0x01 /* filter for port availability */ +#define TIPC_SUB_SERVICE 0x02 /* filter for service availability */ +#if 0 +/* The following filter options are not currently implemented */ +#define TIPC_SUB_NO_BIND_EVTS 0x04 /* filter out "publish" events */ +#define TIPC_SUB_NO_UNBIND_EVTS 0x08 /* filter out "withdraw" events */ +#define TIPC_SUB_SINGLE_EVT 0x10 /* expire after first event */ +#endif + +#define TIPC_WAIT_FOREVER ~0 /* timeout for permanent subscription */ + +struct tipc_subscr { + struct tipc_name_seq seq; /* name sequence of interest */ + __u32 timeout; /* subscription duration (in ms) */ + __u32 filter; /* bitmask of filter options */ + char usr_handle[8]; /* available for subscriber use */ +}; + +#define TIPC_PUBLISHED 1 /* publication event */ +#define TIPC_WITHDRAWN 2 /* withdraw event */ +#define TIPC_SUBSCR_TIMEOUT 3 /* subscription timeout event */ + +struct tipc_event { + __u32 event; /* event type */ + __u32 found_lower; /* matching name seq instances */ + __u32 found_upper; /* " " " " */ + struct tipc_portid port; /* associated port */ + struct tipc_subscr s; /* associated subscription */ +}; + +/* + * Socket API + */ + +#ifndef AF_TIPC +#define AF_TIPC 30 +#endif + +#ifndef PF_TIPC +#define PF_TIPC AF_TIPC +#endif + +#ifndef SOL_TIPC +#define SOL_TIPC 271 +#endif + +#define TIPC_ADDR_NAMESEQ 1 +#define TIPC_ADDR_MCAST 1 +#define TIPC_ADDR_NAME 2 +#define TIPC_ADDR_ID 3 + +struct sockaddr_tipc { + unsigned short family; + unsigned char addrtype; + signed char scope; + union { + struct tipc_portid id; + struct tipc_name_seq nameseq; + struct { + struct tipc_name name; + __u32 domain; /* 0: own zone */ + } name; + } addr; +}; + +/* + * Ancillary data objects supported by recvmsg() + */ + +#define TIPC_ERRINFO 1 /* error info */ +#define TIPC_RETDATA 2 /* returned data */ +#define TIPC_DESTNAME 3 /* destination name */ + +/* + * TIPC-specific socket option values + */ + +#define TIPC_IMPORTANCE 127 /* Default: TIPC_LOW_IMPORTANCE */ +#define TIPC_SRC_DROPPABLE 128 /* Default: 0 (resend congested msg) */ +#define TIPC_DEST_DROPPABLE 129 /* Default: based on socket type */ +#define TIPC_CONN_TIMEOUT 130 /* Default: 8000 (ms) */ + +#endif diff --git a/include/linux/tipc_config.h b/include/linux/tipc_config.h new file mode 100644 index 00000000000..a52c8c64a5a --- /dev/null +++ b/include/linux/tipc_config.h @@ -0,0 +1,407 @@ +/* + * include/linux/tipc_config.h: Include file for TIPC configuration interface + * + * Copyright (c) 2003-2006, Ericsson AB + * Copyright (c) 2005, Wind River Systems + * All rights reserved. + * + * Redistribution and use in source and binary forms, with or without + * modification, are permitted provided that the following conditions are met: + * + * 1. Redistributions of source code must retain the above copyright + * notice, this list of conditions and the following disclaimer. + * 2. Redistributions in binary form must reproduce the above copyright + * notice, this list of conditions and the following disclaimer in the + * documentation and/or other materials provided with the distribution. + * 3. Neither the names of the copyright holders nor the names of its + * contributors may be used to endorse or promote products derived from + * this software without specific prior written permission. + * + * Alternatively, this software may be distributed under the terms of the + * GNU General Public License ("GPL") version 2 as published by the Free + * Software Foundation. + * + * THIS SOFTWARE IS PROVIDED BY THE COPYRIGHT HOLDERS AND CONTRIBUTORS "AS IS" + * AND ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT LIMITED TO, THE + * IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR A PARTICULAR PURPOSE + * ARE DISCLAIMED. IN NO EVENT SHALL THE COPYRIGHT OWNER OR CONTRIBUTORS BE + * LIABLE FOR ANY DIRECT, INDIRECT, INCIDENTAL, SPECIAL, EXEMPLARY, OR + * CONSEQUENTIAL DAMAGES (INCLUDING, BUT NOT LIMITED TO, PROCUREMENT OF + * SUBSTITUTE GOODS OR SERVICES; LOSS OF USE, DATA, OR PROFITS; OR BUSINESS + * INTERRUPTION) HOWEVER CAUSED AND ON ANY THEORY OF LIABILITY, WHETHER IN + * CONTRACT, STRICT LIABILITY, OR TORT (INCLUDING NEGLIGENCE OR OTHERWISE) + * ARISING IN ANY WAY OUT OF THE USE OF THIS SOFTWARE, EVEN IF ADVISED OF THE + * POSSIBILITY OF SUCH DAMAGE. + */ + +#ifndef _LINUX_TIPC_CONFIG_H_ +#define _LINUX_TIPC_CONFIG_H_ + +#include <linux/types.h> +#include <linux/string.h> +#include <asm/byteorder.h> + +/* + * Configuration + * + * All configuration management messaging involves sending a request message + * to the TIPC configuration service on a node, which sends a reply message + * back. (In the future multi-message replies may be supported.) + * + * Both request and reply messages consist of a transport header and payload. + * The transport header contains info about the desired operation; + * the payload consists of zero or more type/length/value (TLV) items + * which specify parameters or results for the operation. + * + * For many operations, the request and reply messages have a fixed number + * of TLVs (usually zero or one); however, some reply messages may return + * a variable number of TLVs. A failed request is denoted by the presence + * of an "error string" TLV in the reply message instead of the TLV(s) the + * reply should contain if the request succeeds. + */ + +/* + * Public commands: + * May be issued by any process. + * Accepted by own node, or by remote node only if remote management enabled. + */ + +#define TIPC_CMD_NOOP 0x0000 /* tx none, rx none */ +#define TIPC_CMD_GET_NODES 0x0001 /* tx net_addr, rx node_info(s) */ +#define TIPC_CMD_GET_MEDIA_NAMES 0x0002 /* tx none, rx media_name(s) */ +#define TIPC_CMD_GET_BEARER_NAMES 0x0003 /* tx none, rx bearer_name(s) */ +#define TIPC_CMD_GET_LINKS 0x0004 /* tx net_addr, rx link_info(s) */ +#define TIPC_CMD_SHOW_NAME_TABLE 0x0005 /* tx name_tbl_query, rx ultra_string */ +#define TIPC_CMD_SHOW_PORTS 0x0006 /* tx none, rx ultra_string */ +#define TIPC_CMD_SHOW_LINK_STATS 0x000B /* tx link_name, rx ultra_string */ + +#if 0 +#define TIPC_CMD_SHOW_PORT_STATS 0x0008 /* tx port_ref, rx ultra_string */ +#define TIPC_CMD_RESET_PORT_STATS 0x0009 /* tx port_ref, rx none */ +#define TIPC_CMD_GET_ROUTES 0x000A /* tx ?, rx ? */ +#define TIPC_CMD_GET_LINK_PEER 0x000D /* tx link_name, rx ? */ +#endif + +/* + * Protected commands: + * May only be issued by "network administration capable" process. + * Accepted by own node, or by remote node only if remote management enabled + * and this node is zone manager. + */ + +#define TIPC_CMD_GET_REMOTE_MNG 0x4003 /* tx none, rx unsigned */ +#define TIPC_CMD_GET_MAX_PORTS 0x4004 /* tx none, rx unsigned */ +#define TIPC_CMD_GET_MAX_PUBL 0x4005 /* tx none, rx unsigned */ +#define TIPC_CMD_GET_MAX_SUBSCR 0x4006 /* tx none, rx unsigned */ +#define TIPC_CMD_GET_MAX_ZONES 0x4007 /* tx none, rx unsigned */ +#define TIPC_CMD_GET_MAX_CLUSTERS 0x4008 /* tx none, rx unsigned */ +#define TIPC_CMD_GET_MAX_NODES 0x4009 /* tx none, rx unsigned */ +#define TIPC_CMD_GET_MAX_SLAVES 0x400A /* tx none, rx unsigned */ +#define TIPC_CMD_GET_NETID 0x400B /* tx none, rx unsigned */ + +#define TIPC_CMD_ENABLE_BEARER 0x4101 /* tx bearer_config, rx none */ +#define TIPC_CMD_DISABLE_BEARER 0x4102 /* tx bearer_name, rx none */ +#define TIPC_CMD_SET_LINK_TOL 0x4107 /* tx link_config, rx none */ +#define TIPC_CMD_SET_LINK_PRI 0x4108 /* tx link_config, rx none */ +#define TIPC_CMD_SET_LINK_WINDOW 0x4109 /* tx link_config, rx none */ +#define TIPC_CMD_SET_LOG_SIZE 0x410A /* tx unsigned, rx none */ +#define TIPC_CMD_DUMP_LOG 0x410B /* tx none, rx ultra_string */ +#define TIPC_CMD_RESET_LINK_STATS 0x410C /* tx link_name, rx none */ + +#if 0 +#define TIPC_CMD_CREATE_LINK 0x4103 /* tx link_create, rx none */ +#define TIPC_CMD_REMOVE_LINK 0x4104 /* tx link_name, rx none */ +#define TIPC_CMD_BLOCK_LINK 0x4105 /* tx link_name, rx none */ +#define TIPC_CMD_UNBLOCK_LINK 0x4106 /* tx link_name, rx none */ +#endif + +/* + * Private commands: + * May only be issued by "network administration capable" process. + * Accepted by own node only; cannot be used on a remote node. + */ + +#define TIPC_CMD_SET_NODE_ADDR 0x8001 /* tx net_addr, rx none */ +#if 0 +#define TIPC_CMD_SET_ZONE_MASTER 0x8002 /* tx none, rx none */ +#endif +#define TIPC_CMD_SET_REMOTE_MNG 0x8003 /* tx unsigned, rx none */ +#define TIPC_CMD_SET_MAX_PORTS 0x8004 /* tx unsigned, rx none */ +#define TIPC_CMD_SET_MAX_PUBL 0x8005 /* tx unsigned, rx none */ +#define TIPC_CMD_SET_MAX_SUBSCR 0x8006 /* tx unsigned, rx none */ +#define TIPC_CMD_SET_MAX_ZONES 0x8007 /* tx unsigned, rx none */ +#define TIPC_CMD_SET_MAX_CLUSTERS 0x8008 /* tx unsigned, rx none */ +#define TIPC_CMD_SET_MAX_NODES 0x8009 /* tx unsigned, rx none */ +#define TIPC_CMD_SET_MAX_SLAVES 0x800A /* tx unsigned, rx none */ +#define TIPC_CMD_SET_NETID 0x800B /* tx unsigned, rx none */ + +/* + * TLV types defined for TIPC + */ + +#define TIPC_TLV_NONE 0 /* no TLV present */ +#define TIPC_TLV_VOID 1 /* empty TLV (0 data bytes)*/ +#define TIPC_TLV_UNSIGNED 2 /* 32-bit integer */ +#define TIPC_TLV_STRING 3 /* char[128] (max) */ +#define TIPC_TLV_LARGE_STRING 4 /* char[2048] (max) */ +#define TIPC_TLV_ULTRA_STRING 5 /* char[32768] (max) */ + +#define TIPC_TLV_ERROR_STRING 16 /* char[128] containing "error code" */ +#define TIPC_TLV_NET_ADDR 17 /* 32-bit integer denoting <Z.C.N> */ +#define TIPC_TLV_MEDIA_NAME 18 /* char[TIPC_MAX_MEDIA_NAME] */ +#define TIPC_TLV_BEARER_NAME 19 /* char[TIPC_MAX_BEARER_NAME] */ +#define TIPC_TLV_LINK_NAME 20 /* char[TIPC_MAX_LINK_NAME] */ +#define TIPC_TLV_NODE_INFO 21 /* struct tipc_node_info */ +#define TIPC_TLV_LINK_INFO 22 /* struct tipc_link_info */ +#define TIPC_TLV_BEARER_CONFIG 23 /* struct tipc_bearer_config */ +#define TIPC_TLV_LINK_CONFIG 24 /* struct tipc_link_config */ +#define TIPC_TLV_NAME_TBL_QUERY 25 /* struct tipc_name_table_query */ +#define TIPC_TLV_PORT_REF 26 /* 32-bit port reference */ + +/* + * Maximum sizes of TIPC bearer-related names (including terminating NUL) + */ + +#define TIPC_MAX_MEDIA_NAME 16 /* format = media */ +#define TIPC_MAX_IF_NAME 16 /* format = interface */ +#define TIPC_MAX_BEARER_NAME 32 /* format = media:interface */ +#define TIPC_MAX_LINK_NAME 60 /* format = Z.C.N:interface-Z.C.N:interface */ + +/* + * Link priority limits (range from 0 to # priorities - 1) + */ + +#define TIPC_NUM_LINK_PRI 32 + +/* + * Link tolerance limits (min, default, max), in ms + */ + +#define TIPC_MIN_LINK_TOL 50 +#define TIPC_DEF_LINK_TOL 1500 +#define TIPC_MAX_LINK_TOL 30000 + +/* + * Link window limits (min, default, max), in packets + */ + +#define TIPC_MIN_LINK_WIN 16 +#define TIPC_DEF_LINK_WIN 50 +#define TIPC_MAX_LINK_WIN 150 + + +struct tipc_node_info { + __u32 addr; /* network address of node */ + __u32 up; /* 0=down, 1= up */ +}; + +struct tipc_link_info { + __u32 dest; /* network address of peer node */ + __u32 up; /* 0=down, 1=up */ + char str[TIPC_MAX_LINK_NAME]; /* link name */ +}; + +struct tipc_bearer_config { + __u32 priority; /* Range [1,31]. Override per link */ + __u32 detect_scope; + char name[TIPC_MAX_BEARER_NAME]; +}; + +struct tipc_link_config { + __u32 value; + char name[TIPC_MAX_LINK_NAME]; +}; + +#define TIPC_NTQ_ALLTYPES 0x80000000 + +struct tipc_name_table_query { + __u32 depth; /* 1:type, 2:+name info, 3:+port info, 4+:+debug info */ + __u32 type; /* {t,l,u} info ignored if high bit of "depth" is set */ + __u32 lowbound; /* (i.e. displays all entries of name table) */ + __u32 upbound; +}; + +/* + * The error string TLV is a null-terminated string describing the cause + * of the request failure. To simplify error processing (and to save space) + * the first character of the string can be a special error code character + * (lying by the range 0x80 to 0xFF) which represents a pre-defined reason. + */ + +#define TIPC_CFG_TLV_ERROR "\x80" /* request contains incorrect TLV(s) */ +#define TIPC_CFG_NOT_NET_ADMIN "\x81" /* must be network administrator */ +#define TIPC_CFG_NOT_ZONE_MSTR "\x82" /* must be zone master */ +#define TIPC_CFG_NO_REMOTE "\x83" /* remote management not enabled */ +#define TIPC_CFG_NOT_SUPPORTED "\x84" /* request is not supported by TIPC */ +#define TIPC_CFG_INVALID_VALUE "\x85" /* request has invalid argument value */ + +#if 0 +/* prototypes TLV structures for proposed commands */ +struct tipc_link_create { + __u32 domain; + struct tipc_media_addr peer_addr; + char bearer_name[TIPC_MAX_BEARER_NAME]; +}; + +struct tipc_route_info { + __u32 dest; + __u32 router; +}; +#endif + +/* + * A TLV consists of a descriptor, followed by the TLV value. + * TLV descriptor fields are stored in network byte order; + * TLV values must also be stored in network byte order (where applicable). + * TLV descriptors must be aligned to addresses which are multiple of 4, + * so up to 3 bytes of padding may exist at the end of the TLV value area. + * There must not be any padding between the TLV descriptor and its value. + */ + +struct tlv_desc { + __u16 tlv_len; /* TLV length (descriptor + value) */ + __u16 tlv_type; /* TLV identifier */ +}; + +#define TLV_ALIGNTO 4 + +#define TLV_ALIGN(datalen) (((datalen)+(TLV_ALIGNTO-1)) & ~(TLV_ALIGNTO-1)) +#define TLV_LENGTH(datalen) (sizeof(struct tlv_desc) + (datalen)) +#define TLV_SPACE(datalen) (TLV_ALIGN(TLV_LENGTH(datalen))) +#define TLV_DATA(tlv) ((void *)((char *)(tlv) + TLV_LENGTH(0))) + +static inline int TLV_OK(const void *tlv, __u16 space) +{ + /* + * Would also like to check that "tlv" is a multiple of 4, + * but don't know how to do this in a portable way. + * - Tried doing (!(tlv & (TLV_ALIGNTO-1))), but GCC compiler + * won't allow binary "&" with a pointer. + * - Tried casting "tlv" to integer type, but causes warning about size + * mismatch when pointer is bigger than chosen type (int, long, ...). + */ + + return (space >= TLV_SPACE(0)) && + (ntohs(((struct tlv_desc *)tlv)->tlv_len) <= space); +} + +static inline int TLV_CHECK(const void *tlv, __u16 space, __u16 exp_type) +{ + return TLV_OK(tlv, space) && + (ntohs(((struct tlv_desc *)tlv)->tlv_type) == exp_type); +} + +static inline int TLV_SET(void *tlv, __u16 type, void *data, __u16 len) +{ + struct tlv_desc *tlv_ptr; + int tlv_len; + + tlv_len = TLV_LENGTH(len); + tlv_ptr = (struct tlv_desc *)tlv; + tlv_ptr->tlv_type = htons(type); + tlv_ptr->tlv_len = htons(tlv_len); + if (len && data) + memcpy(TLV_DATA(tlv_ptr), data, tlv_len); + return TLV_SPACE(len); +} + +/* + * A TLV list descriptor simplifies processing of messages + * containing multiple TLVs. + */ + +struct tlv_list_desc { + struct tlv_desc *tlv_ptr; /* ptr to current TLV */ + __u32 tlv_space; /* # bytes from curr TLV to list end */ +}; + +static inline void TLV_LIST_INIT(struct tlv_list_desc *list, + void *data, __u32 space) +{ + list->tlv_ptr = (struct tlv_desc *)data; + list->tlv_space = space; +} + +static inline int TLV_LIST_EMPTY(struct tlv_list_desc *list) +{ + return (list->tlv_space == 0); +} + +static inline int TLV_LIST_CHECK(struct tlv_list_desc *list, __u16 exp_type) +{ + return TLV_CHECK(list->tlv_ptr, list->tlv_space, exp_type); +} + +static inline void *TLV_LIST_DATA(struct tlv_list_desc *list) +{ + return TLV_DATA(list->tlv_ptr); +} + +static inline void TLV_LIST_STEP(struct tlv_list_desc *list) +{ + __u16 tlv_space = TLV_ALIGN(ntohs(list->tlv_ptr->tlv_len)); + + list->tlv_ptr = (struct tlv_desc *)((char *)list->tlv_ptr + tlv_space); + list->tlv_space -= tlv_space; +} + +/* + * Configuration messages exchanged via NETLINK_GENERIC use the following + * family id, name, version and command. + */ +#define TIPC_GENL_NAME "TIPC" +#define TIPC_GENL_VERSION 0x1 +#define TIPC_GENL_CMD 0x1 + +/* + * TIPC specific header used in NETLINK_GENERIC requests. + */ +struct tipc_genlmsghdr { + __u32 dest; /* Destination address */ + __u16 cmd; /* Command */ + __u16 reserved; /* Unused */ +}; + +#define TIPC_GENL_HDRLEN NLMSG_ALIGN(sizeof(struct tipc_genlmsghdr)) + +/* + * Configuration messages exchanged via TIPC sockets use the TIPC configuration + * message header, which is defined below. This structure is analogous + * to the Netlink message header, but fields are stored in network byte order + * and no padding is permitted between the header and the message data + * that follows. + */ + +struct tipc_cfg_msg_hdr +{ + __u32 tcm_len; /* Message length (including header) */ + __u16 tcm_type; /* Command type */ + __u16 tcm_flags; /* Additional flags */ + char tcm_reserved[8]; /* Unused */ +}; + +#define TCM_F_REQUEST 0x1 /* Flag: Request message */ +#define TCM_F_MORE 0x2 /* Flag: Message to be continued */ + +#define TCM_ALIGN(datalen) (((datalen)+3) & ~3) +#define TCM_LENGTH(datalen) (sizeof(struct tipc_cfg_msg_hdr) + datalen) +#define TCM_SPACE(datalen) (TCM_ALIGN(TCM_LENGTH(datalen))) +#define TCM_DATA(tcm_hdr) ((void *)((char *)(tcm_hdr) + TCM_LENGTH(0))) + +static inline int TCM_SET(void *msg, __u16 cmd, __u16 flags, + void *data, __u16 data_len) +{ + struct tipc_cfg_msg_hdr *tcm_hdr; + int msg_len; + + msg_len = TCM_LENGTH(data_len); + tcm_hdr = (struct tipc_cfg_msg_hdr *)msg; + tcm_hdr->tcm_len = htonl(msg_len); + tcm_hdr->tcm_type = htons(cmd); + tcm_hdr->tcm_flags = htons(flags); + if (data_len && data) + memcpy(TCM_DATA(msg), data, data_len); + return TCM_SPACE(data_len); +} + +#endif diff --git a/include/net/genetlink.h b/include/net/genetlink.h index c5b96b2b815..805de50df00 100644 --- a/include/net/genetlink.h +++ b/include/net/genetlink.h @@ -22,7 +22,6 @@ struct genl_family char name[GENL_NAMSIZ]; unsigned int version; unsigned int maxattr; - struct module * owner; struct nlattr ** attrbuf; /* private */ struct list_head ops_list; /* private */ struct list_head family_list; /* private */ diff --git a/include/net/netfilter/ipv4/nf_conntrack_ipv4.h b/include/net/netfilter/ipv4/nf_conntrack_ipv4.h index 25b081a730e..91684436af8 100644 --- a/include/net/netfilter/ipv4/nf_conntrack_ipv4.h +++ b/include/net/netfilter/ipv4/nf_conntrack_ipv4.h @@ -37,7 +37,4 @@ struct nf_conntrack_ipv4 { struct sk_buff * nf_ct_ipv4_ct_gather_frags(struct sk_buff *skb); -/* call to create an explicit dependency on nf_conntrack_l3proto_ipv4. */ -extern void need_ip_conntrack(void); - #endif /*_NF_CONNTRACK_IPV4_H*/ diff --git a/include/net/netfilter/nf_conntrack.h b/include/net/netfilter/nf_conntrack.h index 64b82b74a65..6d075ca16e6 100644 --- a/include/net/netfilter/nf_conntrack.h +++ b/include/net/netfilter/nf_conntrack.h @@ -221,9 +221,6 @@ extern void nf_ct_helper_put(struct nf_conntrack_helper *helper); extern struct nf_conntrack_helper * __nf_conntrack_helper_find_byname(const char *name); -/* call to create an explicit dependency on nf_conntrack. */ -extern void need_nf_conntrack(void); - extern int nf_ct_invert_tuplepr(struct nf_conntrack_tuple *inverse, const struct nf_conntrack_tuple *orig); diff --git a/include/net/netfilter/nf_conntrack_tuple.h b/include/net/netfilter/nf_conntrack_tuple.h index 14ce790e5c6..530ef1f7528 100644 --- a/include/net/netfilter/nf_conntrack_tuple.h +++ b/include/net/netfilter/nf_conntrack_tuple.h @@ -111,7 +111,7 @@ struct nf_conntrack_tuple #ifdef __KERNEL__ #define NF_CT_DUMP_TUPLE(tp) \ -DEBUGP("tuple %p: %u %u %04x:%04x:%04x:%04x:%04x:%04x:%04x:%04x %hu -> %04x:%04x:%04x:%04x:%04x:%04x:%04x:%04x %hu\n", \ +DEBUGP("tuple %p: %u %u " NIP6_FMT " %hu -> " NIP6_FMT " %hu\n", \ (tp), (tp)->src.l3num, (tp)->dst.protonum, \ NIP6(*(struct in6_addr *)(tp)->src.u3.all), ntohs((tp)->src.u.all), \ NIP6(*(struct in6_addr *)(tp)->dst.u3.all), ntohs((tp)->dst.u.all)) diff --git a/include/net/sctp/sctp.h b/include/net/sctp/sctp.h index 8f241216f46..a553f39f6ae 100644 --- a/include/net/sctp/sctp.h +++ b/include/net/sctp/sctp.h @@ -225,13 +225,13 @@ extern int sctp_debug_flag; if (sctp_debug_flag) { \ if (saddr->sa.sa_family == AF_INET6) { \ printk(KERN_DEBUG \ - lead "%04x:%04x:%04x:%04x:%04x:%04x:%04x:%04x" trail, \ + lead NIP6_FMT trail, \ leadparm, \ NIP6(saddr->v6.sin6_addr), \ otherparms); \ } else { \ printk(KERN_DEBUG \ - lead "%u.%u.%u.%u" trail, \ + lead NIPQUAD_FMT trail, \ leadparm, \ NIPQUAD(saddr->v4.sin_addr.s_addr), \ otherparms); \ diff --git a/include/net/tipc/tipc.h b/include/net/tipc/tipc.h new file mode 100644 index 00000000000..9566608c88c --- /dev/null +++ b/include/net/tipc/tipc.h @@ -0,0 +1,257 @@ +/* + * include/net/tipc/tipc.h: Main include file for TIPC users + * + * Copyright (c) 2003-2006, Ericsson AB + * Copyright (c) 2005, Wind River Systems + * All rights reserved. + * + * Redistribution and use in source and binary forms, with or without + * modification, are permitted provided that the following conditions are met: + * + * 1. Redistributions of source code must retain the above copyright + * notice, this list of conditions and the following disclaimer. + * 2. Redistributions in binary form must reproduce the above copyright + * notice, this list of conditions and the following disclaimer in the + * documentation and/or other materials provided with the distribution. + * 3. Neither the names of the copyright holders nor the names of its + * contributors may be used to endorse or promote products derived from + * this software without specific prior written permission. + * + * Alternatively, this software may be distributed under the terms of the + * GNU General Public License ("GPL") version 2 as published by the Free + * Software Foundation. + * + * THIS SOFTWARE IS PROVIDED BY THE COPYRIGHT HOLDERS AND CONTRIBUTORS "AS IS" + * AND ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT LIMITED TO, THE + * IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR A PARTICULAR PURPOSE + * ARE DISCLAIMED. IN NO EVENT SHALL THE COPYRIGHT OWNER OR CONTRIBUTORS BE + * LIABLE FOR ANY DIRECT, INDIRECT, INCIDENTAL, SPECIAL, EXEMPLARY, OR + * CONSEQUENTIAL DAMAGES (INCLUDING, BUT NOT LIMITED TO, PROCUREMENT OF + * SUBSTITUTE GOODS OR SERVICES; LOSS OF USE, DATA, OR PROFITS; OR BUSINESS + * INTERRUPTION) HOWEVER CAUSED AND ON ANY THEORY OF LIABILITY, WHETHER IN + * CONTRACT, STRICT LIABILITY, OR TORT (INCLUDING NEGLIGENCE OR OTHERWISE) + * ARISING IN ANY WAY OUT OF THE USE OF THIS SOFTWARE, EVEN IF ADVISED OF THE + * POSSIBILITY OF SUCH DAMAGE. + */ + +#ifndef _NET_TIPC_H_ +#define _NET_TIPC_H_ + +#ifdef __KERNEL__ + +#include <linux/tipc.h> +#include <linux/skbuff.h> + +/* + * Native API + */ + +/* + * TIPC operating mode routines + */ + +u32 tipc_get_addr(void); + +#define TIPC_NOT_RUNNING 0 +#define TIPC_NODE_MODE 1 +#define TIPC_NET_MODE 2 + +typedef void (*tipc_mode_event)(void *usr_handle, int mode, u32 addr); + +int tipc_attach(unsigned int *userref, tipc_mode_event, void *usr_handle); + +void tipc_detach(unsigned int userref); + +int tipc_get_mode(void); + +/* + * TIPC port manipulation routines + */ + +typedef void (*tipc_msg_err_event) (void *usr_handle, + u32 portref, + struct sk_buff **buf, + unsigned char const *data, + unsigned int size, + int reason, + struct tipc_portid const *attmpt_destid); + +typedef void (*tipc_named_msg_err_event) (void *usr_handle, + u32 portref, + struct sk_buff **buf, + unsigned char const *data, + unsigned int size, + int reason, + struct tipc_name_seq const *attmpt_dest); + +typedef void (*tipc_conn_shutdown_event) (void *usr_handle, + u32 portref, + struct sk_buff **buf, + unsigned char const *data, + unsigned int size, + int reason); + +typedef void (*tipc_msg_event) (void *usr_handle, + u32 portref, + struct sk_buff **buf, + unsigned char const *data, + unsigned int size, + unsigned int importance, + struct tipc_portid const *origin); + +typedef void (*tipc_named_msg_event) (void *usr_handle, + u32 portref, + struct sk_buff **buf, + unsigned char const *data, + unsigned int size, + unsigned int importance, + struct tipc_portid const *orig, + struct tipc_name_seq const *dest); + +typedef void (*tipc_conn_msg_event) (void *usr_handle, + u32 portref, + struct sk_buff **buf, + unsigned char const *data, + unsigned int size); + +typedef void (*tipc_continue_event) (void *usr_handle, + u32 portref); + +int tipc_createport(unsigned int tipc_user, + void *usr_handle, + unsigned int importance, + tipc_msg_err_event error_cb, + tipc_named_msg_err_event named_error_cb, + tipc_conn_shutdown_event conn_error_cb, + tipc_msg_event message_cb, + tipc_named_msg_event named_message_cb, + tipc_conn_msg_event conn_message_cb, + tipc_continue_event continue_event_cb,/* May be zero */ + u32 *portref); + +int tipc_deleteport(u32 portref); + +int tipc_ownidentity(u32 portref, struct tipc_portid *port); + +int tipc_portimportance(u32 portref, unsigned int *importance); +int tipc_set_portimportance(u32 portref, unsigned int importance); + +int tipc_portunreliable(u32 portref, unsigned int *isunreliable); +int tipc_set_portunreliable(u32 portref, unsigned int isunreliable); + +int tipc_portunreturnable(u32 portref, unsigned int *isunreturnable); +int tipc_set_portunreturnable(u32 portref, unsigned int isunreturnable); + +int tipc_publish(u32 portref, unsigned int scope, + struct tipc_name_seq const *name_seq); +int tipc_withdraw(u32 portref, unsigned int scope, + struct tipc_name_seq const *name_seq); /* 0: all */ + +int tipc_connect2port(u32 portref, struct tipc_portid const *port); + +int tipc_disconnect(u32 portref); + +int tipc_shutdown(u32 ref); /* Sends SHUTDOWN msg */ + +int tipc_isconnected(u32 portref, int *isconnected); + +int tipc_peer(u32 portref, struct tipc_portid *peer); + +int tipc_ref_valid(u32 portref); + +/* + * TIPC messaging routines + */ + +#define TIPC_PORT_IMPORTANCE 100 /* send using current port setting */ + + +int tipc_send(u32 portref, + unsigned int num_sect, + struct iovec const *msg_sect); + +int tipc_send_buf(u32 portref, + struct sk_buff *buf, + unsigned int dsz); + +int tipc_send2name(u32 portref, + struct tipc_name const *name, + u32 domain, /* 0:own zone */ + unsigned int num_sect, + struct iovec const *msg_sect); + +int tipc_send_buf2name(u32 portref, + struct tipc_name const *name, + u32 domain, + struct sk_buff *buf, + unsigned int dsz); + +int tipc_forward2name(u32 portref, + struct tipc_name const *name, + u32 domain, /*0: own zone */ + unsigned int section_count, + struct iovec const *msg_sect, + struct tipc_portid const *origin, + unsigned int importance); + +int tipc_forward_buf2name(u32 portref, + struct tipc_name const *name, + u32 domain, + struct sk_buff *buf, + unsigned int dsz, + struct tipc_portid const *orig, + unsigned int importance); + +int tipc_send2port(u32 portref, + struct tipc_portid const *dest, + unsigned int num_sect, + struct iovec const *msg_sect); + +int tipc_send_buf2port(u32 portref, + struct tipc_portid const *dest, + struct sk_buff *buf, + unsigned int dsz); + +int tipc_forward2port(u32 portref, + struct tipc_portid const *dest, + unsigned int num_sect, + struct iovec const *msg_sect, + struct tipc_portid const *origin, + unsigned int importance); + +int tipc_forward_buf2port(u32 portref, + struct tipc_portid const *dest, + struct sk_buff *buf, + unsigned int dsz, + struct tipc_portid const *orig, + unsigned int importance); + +int tipc_multicast(u32 portref, + struct tipc_name_seq const *seq, + u32 domain, /* 0:own zone */ + unsigned int section_count, + struct iovec const *msg); + +#if 0 +int tipc_multicast_buf(u32 portref, + struct tipc_name_seq const *seq, + u32 domain, /* 0:own zone */ + void *buf, + unsigned int size); +#endif + +/* + * TIPC subscription routines + */ + +int tipc_ispublished(struct tipc_name const *name); + +/* + * Get number of available nodes within specified domain (excluding own node) + */ + +unsigned int tipc_available_nodes(const u32 domain); + +#endif + +#endif diff --git a/include/net/tipc/tipc_bearer.h b/include/net/tipc/tipc_bearer.h new file mode 100644 index 00000000000..098607cd4b7 --- /dev/null +++ b/include/net/tipc/tipc_bearer.h @@ -0,0 +1,121 @@ +/* + * include/net/tipc/tipc_bearer.h: Include file for privileged access to TIPC bearers + * + * Copyright (c) 2003-2006, Ericsson AB + * Copyright (c) 2005, Wind River Systems + * All rights reserved. + * + * Redistribution and use in source and binary forms, with or without + * modification, are permitted provided that the following conditions are met: + * + * 1. Redistributions of source code must retain the above copyright + * notice, this list of conditions and the following disclaimer. + * 2. Redistributions in binary form must reproduce the above copyright + * notice, this list of conditions and the following disclaimer in the + * documentation and/or other materials provided with the distribution. + * 3. Neither the names of the copyright holders nor the names of its + * contributors may be used to endorse or promote products derived from + * this software without specific prior written permission. + * + * Alternatively, this software may be distributed under the terms of the + * GNU General Public License ("GPL") version 2 as published by the Free + * Software Foundation. + * + * THIS SOFTWARE IS PROVIDED BY THE COPYRIGHT HOLDERS AND CONTRIBUTORS "AS IS" + * AND ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT LIMITED TO, THE + * IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR A PARTICULAR PURPOSE + * ARE DISCLAIMED. IN NO EVENT SHALL THE COPYRIGHT OWNER OR CONTRIBUTORS BE + * LIABLE FOR ANY DIRECT, INDIRECT, INCIDENTAL, SPECIAL, EXEMPLARY, OR + * CONSEQUENTIAL DAMAGES (INCLUDING, BUT NOT LIMITED TO, PROCUREMENT OF + * SUBSTITUTE GOODS OR SERVICES; LOSS OF USE, DATA, OR PROFITS; OR BUSINESS + * INTERRUPTION) HOWEVER CAUSED AND ON ANY THEORY OF LIABILITY, WHETHER IN + * CONTRACT, STRICT LIABILITY, OR TORT (INCLUDING NEGLIGENCE OR OTHERWISE) + * ARISING IN ANY WAY OUT OF THE USE OF THIS SOFTWARE, EVEN IF ADVISED OF THE + * POSSIBILITY OF SUCH DAMAGE. + */ + +#ifndef _NET_TIPC_BEARER_H_ +#define _NET_TIPC_BEARER_H_ + +#ifdef __KERNEL__ + +#include <linux/tipc_config.h> +#include <linux/skbuff.h> +#include <linux/spinlock.h> + +/* + * Identifiers of supported TIPC media types + */ + +#define TIPC_MEDIA_TYPE_ETH 1 + +struct tipc_media_addr { + __u32 type; + union { + __u8 eth_addr[6]; /* Ethernet bearer */ +#if 0 + /* Prototypes for other possible bearer types */ + + struct { + __u16 sin_family; + __u16 sin_port; + struct { + __u32 s_addr; + } sin_addr; + char pad[4]; + } addr_in; /* IP-based bearer */ + __u16 sock_descr; /* generic socket bearer */ +#endif + } dev_addr; +}; + +/** + * struct tipc_bearer - TIPC bearer info available to privileged users + * @usr_handle: pointer to additional user-defined information about bearer + * @mtu: max packet size bearer can support + * @blocked: non-zero if bearer is blocked + * @lock: spinlock for controlling access to bearer + * @addr: media-specific address associated with bearer + * @name: bearer name (format = media:interface) + * + * Note: TIPC initializes "name" and "lock" fields; user is responsible for + * initialization all other fields when a bearer is enabled. + */ + +struct tipc_bearer { + void *usr_handle; + u32 mtu; + int blocked; + spinlock_t lock; + struct tipc_media_addr addr; + char name[TIPC_MAX_BEARER_NAME]; +}; + + +int tipc_register_media(u32 media_type, + char *media_name, + int (*enable)(struct tipc_bearer *), + void (*disable)(struct tipc_bearer *), + int (*send_msg)(struct sk_buff *, + struct tipc_bearer *, + struct tipc_media_addr *), + char *(*addr2str)(struct tipc_media_addr *a, + char *str_buf, + int str_size), + struct tipc_media_addr *bcast_addr, + const u32 bearer_priority, + const u32 link_tolerance, /* [ms] */ + const u32 send_window_limit); + +void tipc_recv_msg(struct sk_buff *buf, struct tipc_bearer *tb_ptr); + +int tipc_block_bearer(const char *name); +void tipc_continue(struct tipc_bearer *tb_ptr); + +int tipc_enable_bearer(const char *bearer_name, u32 bcast_scope, u32 priority); +int tipc_disable_bearer(const char *name); + + +#endif + +#endif diff --git a/include/net/tipc/tipc_msg.h b/include/net/tipc/tipc_msg.h new file mode 100644 index 00000000000..4d096eebc93 --- /dev/null +++ b/include/net/tipc/tipc_msg.h @@ -0,0 +1,223 @@ +/* + * include/net/tipc/tipc_msg.h: Include file for privileged access to TIPC message headers + * + * Copyright (c) 2003-2006, Ericsson AB + * Copyright (c) 2005, Wind River Systems + * All rights reserved. + * + * Redistribution and use in source and binary forms, with or without + * modification, are permitted provided that the following conditions are met: + * + * 1. Redistributions of source code must retain the above copyright + * notice, this list of conditions and the following disclaimer. + * 2. Redistributions in binary form must reproduce the above copyright + * notice, this list of conditions and the following disclaimer in the + * documentation and/or other materials provided with the distribution. + * 3. Neither the names of the copyright holders nor the names of its + * contributors may be used to endorse or promote products derived from + * this software without specific prior written permission. + * + * Alternatively, this software may be distributed under the terms of the + * GNU General Public License ("GPL") version 2 as published by the Free + * Software Foundation. + * + * THIS SOFTWARE IS PROVIDED BY THE COPYRIGHT HOLDERS AND CONTRIBUTORS "AS IS" + * AND ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT LIMITED TO, THE + * IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR A PARTICULAR PURPOSE + * ARE DISCLAIMED. IN NO EVENT SHALL THE COPYRIGHT OWNER OR CONTRIBUTORS BE + * LIABLE FOR ANY DIRECT, INDIRECT, INCIDENTAL, SPECIAL, EXEMPLARY, OR + * CONSEQUENTIAL DAMAGES (INCLUDING, BUT NOT LIMITED TO, PROCUREMENT OF + * SUBSTITUTE GOODS OR SERVICES; LOSS OF USE, DATA, OR PROFITS; OR BUSINESS + * INTERRUPTION) HOWEVER CAUSED AND ON ANY THEORY OF LIABILITY, WHETHER IN + * CONTRACT, STRICT LIABILITY, OR TORT (INCLUDING NEGLIGENCE OR OTHERWISE) + * ARISING IN ANY WAY OUT OF THE USE OF THIS SOFTWARE, EVEN IF ADVISED OF THE + * POSSIBILITY OF SUCH DAMAGE. + */ + +#ifndef _NET_TIPC_MSG_H_ +#define _NET_TIPC_MSG_H_ + +#ifdef __KERNEL__ + +struct tipc_msg { + u32 hdr[15]; +}; + + +/* + TIPC user data message header format, version 2: + + + 1 0 9 8 7 6 5 4|3 2 1 0 9 8 7 6|5 4 3 2 1 0 9 8|7 6 5 4 3 2 1 0 + +-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+ + w0:|vers | user |hdr sz |n|d|s|-| message size | + +-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+ + w1:|mstyp| error |rer cnt|lsc|opt p| broadcast ack no | + +-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+ + w2:| link level ack no | broadcast/link level seq no | + +-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+ + w3:| previous node | + +-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+ + w4:| originating port | + +-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+ + w5:| destination port | + +-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+ + w6:| originating node | + +-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+ + w7:| destination node | + +-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+ + w8:| name type / transport sequence number | + +-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+ + w9:| name instance/multicast lower bound | + +-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+ + wA:| multicast upper bound | + +-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+ + / / + \ options \ + / / + +-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+ + +*/ + +#define TIPC_CONN_MSG 0 +#define TIPC_MCAST_MSG 1 +#define TIPC_NAMED_MSG 2 +#define TIPC_DIRECT_MSG 3 + + +static inline u32 msg_word(struct tipc_msg *m, u32 pos) +{ + return ntohl(m->hdr[pos]); +} + +static inline u32 msg_bits(struct tipc_msg *m, u32 w, u32 pos, u32 mask) +{ + return (msg_word(m, w) >> pos) & mask; +} + +static inline u32 msg_importance(struct tipc_msg *m) +{ + return msg_bits(m, 0, 25, 0xf); +} + +static inline u32 msg_hdr_sz(struct tipc_msg *m) +{ + return msg_bits(m, 0, 21, 0xf) << 2; +} + +static inline int msg_short(struct tipc_msg *m) +{ + return (msg_hdr_sz(m) == 24); +} + +static inline u32 msg_size(struct tipc_msg *m) +{ + return msg_bits(m, 0, 0, 0x1ffff); +} + +static inline u32 msg_data_sz(struct tipc_msg *m) +{ + return (msg_size(m) - msg_hdr_sz(m)); +} + +static inline unchar *msg_data(struct tipc_msg *m) +{ + return ((unchar *)m) + msg_hdr_sz(m); +} + +static inline u32 msg_type(struct tipc_msg *m) +{ + return msg_bits(m, 1, 29, 0x7); +} + +static inline u32 msg_direct(struct tipc_msg *m) +{ + return (msg_type(m) == TIPC_DIRECT_MSG); +} + +static inline u32 msg_named(struct tipc_msg *m) +{ + return (msg_type(m) == TIPC_NAMED_MSG); +} + +static inline u32 msg_mcast(struct tipc_msg *m) +{ + return (msg_type(m) == TIPC_MCAST_MSG); +} + +static inline u32 msg_connected(struct tipc_msg *m) +{ + return (msg_type(m) == TIPC_CONN_MSG); +} + +static inline u32 msg_errcode(struct tipc_msg *m) +{ + return msg_bits(m, 1, 25, 0xf); +} + +static inline u32 msg_prevnode(struct tipc_msg *m) +{ + return msg_word(m, 3); +} + +static inline u32 msg_origport(struct tipc_msg *m) +{ + return msg_word(m, 4); +} + +static inline u32 msg_destport(struct tipc_msg *m) +{ + return msg_word(m, 5); +} + +static inline u32 msg_mc_netid(struct tipc_msg *m) +{ + return msg_word(m, 5); +} + +static inline u32 msg_orignode(struct tipc_msg *m) +{ + if (likely(msg_short(m))) + return msg_prevnode(m); + return msg_word(m, 6); +} + +static inline u32 msg_destnode(struct tipc_msg *m) +{ + return msg_word(m, 7); +} + +static inline u32 msg_nametype(struct tipc_msg *m) +{ + return msg_word(m, 8); +} + +static inline u32 msg_nameinst(struct tipc_msg *m) +{ + return msg_word(m, 9); +} + +static inline u32 msg_namelower(struct tipc_msg *m) +{ + return msg_nameinst(m); +} + +static inline u32 msg_nameupper(struct tipc_msg *m) +{ + return msg_word(m, 10); +} + +static inline char *msg_options(struct tipc_msg *m, u32 *len) +{ + u32 pos = msg_bits(m, 1, 16, 0x7); + + if (!pos) + return 0; + pos = (pos * 4) + 28; + *len = msg_hdr_sz(m) - pos; + return (char *)&m->hdr[pos/4]; +} + +#endif + +#endif diff --git a/include/net/tipc/tipc_port.h b/include/net/tipc/tipc_port.h new file mode 100644 index 00000000000..333bba6dc52 --- /dev/null +++ b/include/net/tipc/tipc_port.h @@ -0,0 +1,108 @@ +/* + * include/net/tipc/tipc_port.h: Include file for privileged access to TIPC ports + * + * Copyright (c) 1994-2006, Ericsson AB + * Copyright (c) 2005, Wind River Systems + * All rights reserved. + * + * Redistribution and use in source and binary forms, with or without + * modification, are permitted provided that the following conditions are met: + * + * 1. Redistributions of source code must retain the above copyright + * notice, this list of conditions and the following disclaimer. + * 2. Redistributions in binary form must reproduce the above copyright + * notice, this list of conditions and the following disclaimer in the + * documentation and/or other materials provided with the distribution. + * 3. Neither the names of the copyright holders nor the names of its + * contributors may be used to endorse or promote products derived from + * this software without specific prior written permission. + * + * Alternatively, this software may be distributed under the terms of the + * GNU General Public License ("GPL") version 2 as published by the Free + * Software Foundation. + * + * THIS SOFTWARE IS PROVIDED BY THE COPYRIGHT HOLDERS AND CONTRIBUTORS "AS IS" + * AND ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT LIMITED TO, THE + * IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR A PARTICULAR PURPOSE + * ARE DISCLAIMED. IN NO EVENT SHALL THE COPYRIGHT OWNER OR CONTRIBUTORS BE + * LIABLE FOR ANY DIRECT, INDIRECT, INCIDENTAL, SPECIAL, EXEMPLARY, OR + * CONSEQUENTIAL DAMAGES (INCLUDING, BUT NOT LIMITED TO, PROCUREMENT OF + * SUBSTITUTE GOODS OR SERVICES; LOSS OF USE, DATA, OR PROFITS; OR BUSINESS + * INTERRUPTION) HOWEVER CAUSED AND ON ANY THEORY OF LIABILITY, WHETHER IN + * CONTRACT, STRICT LIABILITY, OR TORT (INCLUDING NEGLIGENCE OR OTHERWISE) + * ARISING IN ANY WAY OUT OF THE USE OF THIS SOFTWARE, EVEN IF ADVISED OF THE + * POSSIBILITY OF SUCH DAMAGE. + */ + +#ifndef _NET_TIPC_PORT_H_ +#define _NET_TIPC_PORT_H_ + +#ifdef __KERNEL__ + +#include <linux/tipc.h> +#include <linux/skbuff.h> +#include <net/tipc/tipc_msg.h> + +#define TIPC_FLOW_CONTROL_WIN 512 + +/** + * struct tipc_port - native TIPC port info available to privileged users + * @usr_handle: pointer to additional user-defined information about port + * @lock: pointer to spinlock for controlling access to port + * @connected: non-zero if port is currently connected to a peer port + * @conn_type: TIPC type used when connection was established + * @conn_instance: TIPC instance used when connection was established + * @conn_unacked: number of unacknowledged messages received from peer port + * @published: non-zero if port has one or more associated names + * @congested: non-zero if cannot send because of link or port congestion + * @ref: unique reference to port in TIPC object registry + * @phdr: preformatted message header used when sending messages + */ + +struct tipc_port { + void *usr_handle; + spinlock_t *lock; + int connected; + u32 conn_type; + u32 conn_instance; + u32 conn_unacked; + int published; + u32 congested; + u32 ref; + struct tipc_msg phdr; +}; + + +/** + * tipc_createport_raw - create a native TIPC port and return it's reference + * + * Note: 'dispatcher' and 'wakeup' deliver a locked port. + */ + +u32 tipc_createport_raw(void *usr_handle, + u32 (*dispatcher)(struct tipc_port *, struct sk_buff *), + void (*wakeup)(struct tipc_port *), + const u32 importance); + +/* + * tipc_set_msg_option(): port must be locked. + */ +int tipc_set_msg_option(struct tipc_port *tp_ptr, + const char *opt, + const u32 len); + +int tipc_reject_msg(struct sk_buff *buf, u32 err); + +int tipc_send_buf_fast(struct sk_buff *buf, u32 destnode); + +void tipc_acknowledge(u32 port_ref,u32 ack); + +struct tipc_port *tipc_get_port(const u32 ref); + +void *tipc_get_handle(const u32 ref); + + +#endif + +#endif + diff --git a/include/rdma/ib_verbs.h b/include/rdma/ib_verbs.h index a7f4c355a91..22fc886b969 100644 --- a/include/rdma/ib_verbs.h +++ b/include/rdma/ib_verbs.h @@ -88,7 +88,6 @@ enum ib_atomic_cap { struct ib_device_attr { u64 fw_ver; - __be64 node_guid; __be64 sys_image_guid; u64 max_mr_size; u64 page_size_cap; @@ -951,6 +950,7 @@ struct ib_device { u64 uverbs_cmd_mask; int uverbs_abi_ver; + __be64 node_guid; u8 node_type; u8 phys_port_cnt; }; diff --git a/net/Kconfig b/net/Kconfig index 60f6f321bd7..9296b269d67 100644 --- a/net/Kconfig +++ b/net/Kconfig @@ -159,6 +159,7 @@ source "net/ipx/Kconfig" source "drivers/net/appletalk/Kconfig" source "net/x25/Kconfig" source "net/lapb/Kconfig" +source "net/tipc/Kconfig" config NET_DIVERT bool "Frame Diverter (EXPERIMENTAL)" diff --git a/net/Makefile b/net/Makefile index f5141b9d4f3..065796f5fb1 100644 --- a/net/Makefile +++ b/net/Makefile @@ -45,6 +45,7 @@ obj-$(CONFIG_VLAN_8021Q) += 8021q/ obj-$(CONFIG_IP_DCCP) += dccp/ obj-$(CONFIG_IP_SCTP) += sctp/ obj-$(CONFIG_IEEE80211) += ieee80211/ +obj-$(CONFIG_TIPC) += tipc/ ifeq ($(CONFIG_NET),y) obj-$(CONFIG_SYSCTL) += sysctl_net.o diff --git a/net/bridge/netfilter/ebt_log.c b/net/bridge/netfilter/ebt_log.c index 9f6e0193ae1..a29c1232c42 100644 --- a/net/bridge/netfilter/ebt_log.c +++ b/net/bridge/netfilter/ebt_log.c @@ -15,6 +15,7 @@ #include <linux/netfilter.h> #include <linux/module.h> #include <linux/ip.h> +#include <linux/in.h> #include <linux/if_arp.h> #include <linux/spinlock.h> diff --git a/net/core/filter.c b/net/core/filter.c index 9eb9d0017a0..a52665f7522 100644 --- a/net/core/filter.c +++ b/net/core/filter.c @@ -287,7 +287,9 @@ load_b: * no references or jumps that are out of range, no illegal * instructions, and must end with a RET instruction. * - * Returns 0 if the rule set is legal or a negative errno code if not. + * All jumps are forward as they are not signed. + * + * Returns 0 if the rule set is legal or -EINVAL if not. */ int sk_chk_filter(struct sock_filter *filter, int flen) { @@ -299,7 +301,6 @@ int sk_chk_filter(struct sock_filter *filter, int flen) /* check the filter code now */ for (pc = 0; pc < flen; pc++) { - /* all jumps are forward as they are not signed */ ftest = &filter[pc]; /* Only allow valid instructions */ @@ -383,11 +384,6 @@ int sk_chk_filter(struct sock_filter *filter, int flen) } } - /* - * The program must end with a return. We don't care where they - * jumped within the script (its always forwards) but in the end - * they _will_ hit this. - */ return (BPF_CLASS(filter[flen - 1].code) == BPF_RET) ? 0 : -EINVAL; } diff --git a/net/ipv4/netfilter/Kconfig b/net/ipv4/netfilter/Kconfig index a9893ec03e0..db783036e4d 100644 --- a/net/ipv4/netfilter/Kconfig +++ b/net/ipv4/netfilter/Kconfig @@ -182,6 +182,7 @@ config IP_NF_QUEUE config IP_NF_IPTABLES tristate "IP tables support (required for filtering/masq/NAT)" + depends on NETFILTER_XTABLES help iptables is a general, extensible packet identification framework. The packet filtering and full NAT (masquerading, port forwarding, @@ -191,16 +192,6 @@ config IP_NF_IPTABLES To compile it as a module, choose M here. If unsure, say N. # The matches. -config IP_NF_MATCH_LIMIT - tristate "limit match support" - depends on IP_NF_IPTABLES - help - limit matching allows you to control the rate at which a rule can be - matched: mainly useful in combination with the LOG target ("LOG - target support", below) and to avoid some Denial of Service attacks. - - To compile it as a module, choose M here. If unsure, say N. - config IP_NF_MATCH_IPRANGE tristate "IP range match support" depends on IP_NF_IPTABLES @@ -210,37 +201,6 @@ config IP_NF_MATCH_IPRANGE To compile it as a module, choose M here. If unsure, say N. -config IP_NF_MATCH_MAC - tristate "MAC address match support" - depends on IP_NF_IPTABLES - help - MAC matching allows you to match packets based on the source - Ethernet address of the packet. - - To compile it as a module, choose M here. If unsure, say N. - -config IP_NF_MATCH_PKTTYPE - tristate "Packet type match support" - depends on IP_NF_IPTABLES - help - Packet type matching allows you to match a packet by - its "class", eg. BROADCAST, MULTICAST, ... - - Typical usage: - iptables -A INPUT -m pkttype --pkt-type broadcast -j LOG - - To compile it as a module, choose M here. If unsure, say N. - -config IP_NF_MATCH_MARK - tristate "netfilter MARK match support" - depends on IP_NF_IPTABLES - help - Netfilter mark matching allows you to match packets based on the - `nfmark' value in the packet. This can be set by the MARK target - (see below). - - To compile it as a module, choose M here. If unsure, say N. - config IP_NF_MATCH_MULTIPORT tristate "Multiple port match support" depends on IP_NF_IPTABLES @@ -301,15 +261,6 @@ config IP_NF_MATCH_AH_ESP To compile it as a module, choose M here. If unsure, say N. -config IP_NF_MATCH_LENGTH - tristate "LENGTH match support" - depends on IP_NF_IPTABLES - help - This option allows you to match the length of a packet against a - specific value or range of values. - - To compile it as a module, choose M here. If unsure, say N. - config IP_NF_MATCH_TTL tristate "TTL match support" depends on IP_NF_IPTABLES @@ -319,50 +270,6 @@ config IP_NF_MATCH_TTL To compile it as a module, choose M here. If unsure, say N. -config IP_NF_MATCH_TCPMSS - tristate "tcpmss match support" - depends on IP_NF_IPTABLES - help - This option adds a `tcpmss' match, which allows you to examine the - MSS value of TCP SYN packets, which control the maximum packet size - for that connection. - - To compile it as a module, choose M here. If unsure, say N. - -config IP_NF_MATCH_HELPER - tristate "Helper match support" - depends on IP_NF_IPTABLES - depends on IP_NF_CONNTRACK || NF_CONNTRACK_IPV4 - help - Helper matching allows you to match packets in dynamic connections - tracked by a conntrack-helper, ie. ip_conntrack_ftp - - To compile it as a module, choose M here. If unsure, say Y. - -config IP_NF_MATCH_STATE - tristate "Connection state match support" - depends on IP_NF_IPTABLES - depends on IP_NF_CONNTRACK || NF_CONNTRACK_IPV4 - help - Connection state matching allows you to match packets based on their - relationship to a tracked connection (ie. previous packets). This - is a powerful tool for packet classification. - - To compile it as a module, choose M here. If unsure, say N. - -config IP_NF_MATCH_CONNTRACK - tristate "Connection tracking match support" - depends on IP_NF_IPTABLES - depends on IP_NF_CONNTRACK || NF_CONNTRACK_IPV4 - help - This is a general conntrack match module, a superset of the state match. - - It allows matching on additional conntrack information, which is - useful in complex configurations, such as NAT gateways with multiple - internet links or tunnels. - - To compile it as a module, choose M here. If unsure, say N. - config IP_NF_MATCH_OWNER tristate "Owner match support" depends on IP_NF_IPTABLES @@ -372,15 +279,6 @@ config IP_NF_MATCH_OWNER To compile it as a module, choose M here. If unsure, say N. -config IP_NF_MATCH_PHYSDEV - tristate "Physdev match support" - depends on IP_NF_IPTABLES && BRIDGE_NETFILTER - help - Physdev packet matching matches against the physical bridge ports - the IP packet arrived on or will leave by. - - To compile it as a module, choose M here. If unsure, say N. - config IP_NF_MATCH_ADDRTYPE tristate 'address type match support' depends on IP_NF_IPTABLES @@ -391,75 +289,6 @@ config IP_NF_MATCH_ADDRTYPE If you want to compile it as a module, say M here and read <file:Documentation/modules.txt>. If unsure, say `N'. -config IP_NF_MATCH_REALM - tristate 'realm match support' - depends on IP_NF_IPTABLES - select NET_CLS_ROUTE - help - This option adds a `realm' match, which allows you to use the realm - key from the routing subsystem inside iptables. - - This match pretty much resembles the CONFIG_NET_CLS_ROUTE4 option - in tc world. - - If you want to compile it as a module, say M here and read - <file:Documentation/modules.txt>. If unsure, say `N'. - -config IP_NF_MATCH_SCTP - tristate 'SCTP protocol match support' - depends on IP_NF_IPTABLES - help - With this option enabled, you will be able to use the iptables - `sctp' match in order to match on SCTP source/destination ports - and SCTP chunk types. - - If you want to compile it as a module, say M here and read - <file:Documentation/modules.txt>. If unsure, say `N'. - -config IP_NF_MATCH_DCCP - tristate 'DCCP protocol match support' - depends on IP_NF_IPTABLES - help - With this option enabled, you will be able to use the iptables - `dccp' match in order to match on DCCP source/destination ports - and DCCP flags. - - If you want to compile it as a module, say M here and read - <file:Documentation/modules.txt>. If unsure, say `N'. - -config IP_NF_MATCH_COMMENT - tristate 'comment match support' - depends on IP_NF_IPTABLES - help - This option adds a `comment' dummy-match, which allows you to put - comments in your iptables ruleset. - - If you want to compile it as a module, say M here and read - <file:Documentation/modules.txt>. If unsure, say `N'. - -config IP_NF_MATCH_CONNMARK - tristate 'Connection mark match support' - depends on IP_NF_IPTABLES - depends on (IP_NF_CONNTRACK && IP_NF_CONNTRACK_MARK) || (NF_CONNTRACK_MARK && NF_CONNTRACK_IPV4) - help - This option adds a `connmark' match, which allows you to match the - connection mark value previously set for the session by `CONNMARK'. - - If you want to compile it as a module, say M here and read - <file:Documentation/modules.txt>. The module will be called - ipt_connmark.o. If unsure, say `N'. - -config IP_NF_MATCH_CONNBYTES - tristate 'Connection byte/packet counter match support' - depends on IP_NF_IPTABLES - depends on (IP_NF_CONNTRACK && IP_NF_CT_ACCT) || (NF_CT_ACCT && NF_CONNTRACK_IPV4) - help - This option adds a `connbytes' match, which allows you to match the - number of bytes and/or packets for each direction within a connection. - - If you want to compile it as a module, say M here and read - <file:Documentation/modules.txt>. If unsure, say `N'. - config IP_NF_MATCH_HASHLIMIT tristate 'hashlimit match support' depends on IP_NF_IPTABLES @@ -474,19 +303,6 @@ config IP_NF_MATCH_HASHLIMIT destination IP' or `500pps from any given source IP' with a single IPtables rule. -config IP_NF_MATCH_STRING - tristate 'string match support' - depends on IP_NF_IPTABLES - select TEXTSEARCH - select TEXTSEARCH_KMP - select TEXTSEARCH_BM - select TEXTSEARCH_FSM - help - This option adds a `string' match, which allows you to look for - pattern matchings in packets. - - To compile it as a module, choose M here. If unsure, say N. - config IP_NF_MATCH_POLICY tristate "IPsec policy match support" depends on IP_NF_IPTABLES && XFRM @@ -572,17 +388,6 @@ config IP_NF_TARGET_TCPMSS To compile it as a module, choose M here. If unsure, say N. -config IP_NF_TARGET_NFQUEUE - tristate "NFQUEUE Target Support" - depends on IP_NF_IPTABLES - help - This Target replaced the old obsolete QUEUE target. - - As opposed to QUEUE, it supports 65535 different queues, - not just one. - - To compile it as a module, choose M here. If unsure, say N. - # NAT + specific targets config IP_NF_NAT tristate "Full NAT" @@ -735,31 +540,6 @@ config IP_NF_TARGET_DSCP To compile it as a module, choose M here. If unsure, say N. -config IP_NF_TARGET_MARK - tristate "MARK target support" - depends on IP_NF_MANGLE - help - This option adds a `MARK' target, which allows you to create rules - in the `mangle' table which alter the netfilter mark (nfmark) field - associated with the packet prior to routing. This can change - the routing method (see `Use netfilter MARK value as routing - key') and can also be used by other subsystems to change their - behavior. - - To compile it as a module, choose M here. If unsure, say N. - -config IP_NF_TARGET_CLASSIFY - tristate "CLASSIFY target support" - depends on IP_NF_MANGLE - help - This option adds a `CLASSIFY' target, which enables the user to set - the priority of a packet. Some qdiscs can use this value for - classification, among these are: - - atm, cbq, dsmark, pfifo_fast, htb, prio - - To compile it as a module, choose M here. If unsure, say N. - config IP_NF_TARGET_TTL tristate 'TTL target support' depends on IP_NF_MANGLE @@ -774,19 +554,6 @@ config IP_NF_TARGET_TTL To compile it as a module, choose M here. If unsure, say N. -config IP_NF_TARGET_CONNMARK - tristate 'CONNMARK target support' - depends on IP_NF_MANGLE - depends on (IP_NF_CONNTRACK && IP_NF_CONNTRACK_MARK) || (NF_CONNTRACK_MARK && NF_CONNTRACK_IPV4) - help - This option adds a `CONNMARK' target, which allows one to manipulate - the connection mark value. Similar to the MARK target, but - affects the connection mark value rather than the packet mark value. - - If you want to compile it as a module, say M here and read - <file:Documentation/modules.txt>. The module will be called - ipt_CONNMARK.o. If unsure, say `N'. - config IP_NF_TARGET_CLUSTERIP tristate "CLUSTERIP target support (EXPERIMENTAL)" depends on IP_NF_MANGLE && EXPERIMENTAL @@ -810,23 +577,10 @@ config IP_NF_RAW If you want to compile it as a module, say M here and read <file:Documentation/modules.txt>. If unsure, say `N'. -config IP_NF_TARGET_NOTRACK - tristate 'NOTRACK target support' - depends on IP_NF_RAW - depends on IP_NF_CONNTRACK || NF_CONNTRACK_IPV4 - help - The NOTRACK target allows a select rule to specify - which packets *not* to enter the conntrack/NAT - subsystem with all the consequences (no ICMP error tracking, - no protocol helpers for the selected packets). - - If you want to compile it as a module, say M here and read - <file:Documentation/modules.txt>. If unsure, say `N'. - - # ARP tables config IP_NF_ARPTABLES tristate "ARP tables support" + depends on NETFILTER_XTABLES help arptables is a general, extensible packet identification framework. The ARP packet filtering and mangling (manipulation)subsystems diff --git a/net/ipv4/netfilter/Makefile b/net/ipv4/netfilter/Makefile index 549b01a648b..bcefe64b931 100644 --- a/net/ipv4/netfilter/Makefile +++ b/net/ipv4/netfilter/Makefile @@ -47,14 +47,8 @@ obj-$(CONFIG_IP_NF_RAW) += iptable_raw.o # matches obj-$(CONFIG_IP_NF_MATCH_HELPER) += ipt_helper.o -obj-$(CONFIG_IP_NF_MATCH_LIMIT) += ipt_limit.o obj-$(CONFIG_IP_NF_MATCH_HASHLIMIT) += ipt_hashlimit.o -obj-$(CONFIG_IP_NF_MATCH_SCTP) += ipt_sctp.o -obj-$(CONFIG_IP_NF_MATCH_DCCP) += ipt_dccp.o -obj-$(CONFIG_IP_NF_MATCH_MARK) += ipt_mark.o -obj-$(CONFIG_IP_NF_MATCH_MAC) += ipt_mac.o obj-$(CONFIG_IP_NF_MATCH_IPRANGE) += ipt_iprange.o -obj-$(CONFIG_IP_NF_MATCH_PKTTYPE) += ipt_pkttype.o obj-$(CONFIG_IP_NF_MATCH_MULTIPORT) += ipt_multiport.o obj-$(CONFIG_IP_NF_MATCH_OWNER) += ipt_owner.o obj-$(CONFIG_IP_NF_MATCH_TOS) += ipt_tos.o @@ -62,40 +56,25 @@ obj-$(CONFIG_IP_NF_MATCH_RECENT) += ipt_recent.o obj-$(CONFIG_IP_NF_MATCH_ECN) += ipt_ecn.o obj-$(CONFIG_IP_NF_MATCH_DSCP) += ipt_dscp.o obj-$(CONFIG_IP_NF_MATCH_AH_ESP) += ipt_ah.o ipt_esp.o -obj-$(CONFIG_IP_NF_MATCH_LENGTH) += ipt_length.o obj-$(CONFIG_IP_NF_MATCH_TTL) += ipt_ttl.o -obj-$(CONFIG_IP_NF_MATCH_STATE) += ipt_state.o -obj-$(CONFIG_IP_NF_MATCH_CONNMARK) += ipt_connmark.o -obj-$(CONFIG_IP_NF_MATCH_CONNTRACK) += ipt_conntrack.o -obj-$(CONFIG_IP_NF_MATCH_CONNBYTES) += ipt_connbytes.o -obj-$(CONFIG_IP_NF_MATCH_TCPMSS) += ipt_tcpmss.o -obj-$(CONFIG_IP_NF_MATCH_REALM) += ipt_realm.o obj-$(CONFIG_IP_NF_MATCH_ADDRTYPE) += ipt_addrtype.o -obj-$(CONFIG_IP_NF_MATCH_PHYSDEV) += ipt_physdev.o obj-$(CONFIG_IP_NF_MATCH_POLICY) += ipt_policy.o -obj-$(CONFIG_IP_NF_MATCH_COMMENT) += ipt_comment.o -obj-$(CONFIG_IP_NF_MATCH_STRING) += ipt_string.o # targets obj-$(CONFIG_IP_NF_TARGET_REJECT) += ipt_REJECT.o obj-$(CONFIG_IP_NF_TARGET_TOS) += ipt_TOS.o obj-$(CONFIG_IP_NF_TARGET_ECN) += ipt_ECN.o obj-$(CONFIG_IP_NF_TARGET_DSCP) += ipt_DSCP.o -obj-$(CONFIG_IP_NF_TARGET_MARK) += ipt_MARK.o obj-$(CONFIG_IP_NF_TARGET_MASQUERADE) += ipt_MASQUERADE.o obj-$(CONFIG_IP_NF_TARGET_REDIRECT) += ipt_REDIRECT.o obj-$(CONFIG_IP_NF_TARGET_NETMAP) += ipt_NETMAP.o obj-$(CONFIG_IP_NF_TARGET_SAME) += ipt_SAME.o -obj-$(CONFIG_IP_NF_TARGET_CLASSIFY) += ipt_CLASSIFY.o obj-$(CONFIG_IP_NF_NAT_SNMP_BASIC) += ip_nat_snmp_basic.o obj-$(CONFIG_IP_NF_TARGET_LOG) += ipt_LOG.o -obj-$(CONFIG_IP_NF_TARGET_CONNMARK) += ipt_CONNMARK.o obj-$(CONFIG_IP_NF_TARGET_ULOG) += ipt_ULOG.o obj-$(CONFIG_IP_NF_TARGET_TCPMSS) += ipt_TCPMSS.o -obj-$(CONFIG_IP_NF_TARGET_NOTRACK) += ipt_NOTRACK.o obj-$(CONFIG_IP_NF_TARGET_CLUSTERIP) += ipt_CLUSTERIP.o obj-$(CONFIG_IP_NF_TARGET_TTL) += ipt_TTL.o -obj-$(CONFIG_IP_NF_TARGET_NFQUEUE) += ipt_NFQUEUE.o # generic ARP tables obj-$(CONFIG_IP_NF_ARPTABLES) += arp_tables.o diff --git a/net/ipv4/netfilter/arp_tables.c b/net/ipv4/netfilter/arp_tables.c index b6d5284c802..afe3d8f8177 100644 --- a/net/ipv4/netfilter/arp_tables.c +++ b/net/ipv4/netfilter/arp_tables.c @@ -24,6 +24,7 @@ #include <asm/uaccess.h> #include <asm/semaphore.h> +#include <linux/netfilter/x_tables.h> #include <linux/netfilter_arp/arp_tables.h> MODULE_LICENSE("GPL"); @@ -55,28 +56,9 @@ do { \ #else #define ARP_NF_ASSERT(x) #endif -#define SMP_ALIGN(x) (((x) + SMP_CACHE_BYTES-1) & ~(SMP_CACHE_BYTES-1)) -static DECLARE_MUTEX(arpt_mutex); - -#define ASSERT_READ_LOCK(x) ARP_NF_ASSERT(down_trylock(&arpt_mutex) != 0) -#define ASSERT_WRITE_LOCK(x) ARP_NF_ASSERT(down_trylock(&arpt_mutex) != 0) #include <linux/netfilter_ipv4/listhelp.h> -struct arpt_table_info { - unsigned int size; - unsigned int number; - unsigned int initial_entries; - unsigned int hook_entry[NF_ARP_NUMHOOKS]; - unsigned int underflow[NF_ARP_NUMHOOKS]; - void *entries[NR_CPUS]; -}; - -static LIST_HEAD(arpt_target); -static LIST_HEAD(arpt_tables); -#define SET_COUNTER(c,b,p) do { (c).bcnt = (b); (c).pcnt = (p); } while(0) -#define ADD_COUNTER(c,b,p) do { (c).bcnt += (b); (c).pcnt += (p); } while(0) - static inline int arp_devaddr_compare(const struct arpt_devaddr_info *ap, char *hdr_addr, int len) { @@ -223,9 +205,9 @@ static inline int arp_checkentry(const struct arpt_arp *arp) } static unsigned int arpt_error(struct sk_buff **pskb, - unsigned int hooknum, const struct net_device *in, const struct net_device *out, + unsigned int hooknum, const void *targinfo, void *userinfo) { @@ -254,6 +236,7 @@ unsigned int arpt_do_table(struct sk_buff **pskb, struct arpt_entry *e, *back; const char *indev, *outdev; void *table_base; + struct xt_table_info *private = table->private; /* ARP header, plus 2 device addresses, plus 2 IP addresses. */ if (!pskb_may_pull((*pskb), (sizeof(struct arphdr) + @@ -265,9 +248,9 @@ unsigned int arpt_do_table(struct sk_buff **pskb, outdev = out ? out->name : nulldevname; read_lock_bh(&table->lock); - table_base = (void *)table->private->entries[smp_processor_id()]; - e = get_entry(table_base, table->private->hook_entry[hook]); - back = get_entry(table_base, table->private->underflow[hook]); + table_base = (void *)private->entries[smp_processor_id()]; + e = get_entry(table_base, private->hook_entry[hook]); + back = get_entry(table_base, private->underflow[hook]); arp = (*pskb)->nh.arph; do { @@ -315,8 +298,8 @@ unsigned int arpt_do_table(struct sk_buff **pskb, * abs. verdicts */ verdict = t->u.kernel.target->target(pskb, - hook, in, out, + hook, t->data, userdata); @@ -341,106 +324,6 @@ unsigned int arpt_do_table(struct sk_buff **pskb, return verdict; } -/* - * These are weird, but module loading must not be done with mutex - * held (since they will register), and we have to have a single - * function to use try_then_request_module(). - */ - -/* Find table by name, grabs mutex & ref. Returns ERR_PTR() on error. */ -static inline struct arpt_table *find_table_lock(const char *name) -{ - struct arpt_table *t; - - if (down_interruptible(&arpt_mutex) != 0) - return ERR_PTR(-EINTR); - - list_for_each_entry(t, &arpt_tables, list) - if (strcmp(t->name, name) == 0 && try_module_get(t->me)) - return t; - up(&arpt_mutex); - return NULL; -} - - -/* Find target, grabs ref. Returns ERR_PTR() on error. */ -static inline struct arpt_target *find_target(const char *name, u8 revision) -{ - struct arpt_target *t; - int err = 0; - - if (down_interruptible(&arpt_mutex) != 0) - return ERR_PTR(-EINTR); - - list_for_each_entry(t, &arpt_target, list) { - if (strcmp(t->name, name) == 0) { - if (t->revision == revision) { - if (try_module_get(t->me)) { - up(&arpt_mutex); - return t; - } - } else - err = -EPROTOTYPE; /* Found something. */ - } - } - up(&arpt_mutex); - return ERR_PTR(err); -} - -struct arpt_target *arpt_find_target(const char *name, u8 revision) -{ - struct arpt_target *target; - - target = try_then_request_module(find_target(name, revision), - "arpt_%s", name); - if (IS_ERR(target) || !target) - return NULL; - return target; -} - -static int target_revfn(const char *name, u8 revision, int *bestp) -{ - struct arpt_target *t; - int have_rev = 0; - - list_for_each_entry(t, &arpt_target, list) { - if (strcmp(t->name, name) == 0) { - if (t->revision > *bestp) - *bestp = t->revision; - if (t->revision == revision) - have_rev =1; - } - } - return have_rev; -} - -/* Returns true or false (if no such extension at all) */ -static inline int find_revision(const char *name, u8 revision, - int (*revfn)(const char *, u8, int *), - int *err) -{ - int have_rev, best = -1; - - if (down_interruptible(&arpt_mutex) != 0) { - *err = -EINTR; - return 1; - } - have_rev = revfn(name, revision, &best); - up(&arpt_mutex); - - /* Nothing at all? Return 0 to try loading module. */ - if (best == -1) { - *err = -ENOENT; - return 0; - } - - *err = best; - if (!have_rev) - *err = -EPROTONOSUPPORT; - return 1; -} - - /* All zeroes == unconditional rule. */ static inline int unconditional(const struct arpt_arp *arp) { @@ -456,7 +339,7 @@ static inline int unconditional(const struct arpt_arp *arp) /* Figures out from what hook each rule can be called: returns 0 if * there are loops. Puts hook bitmask in comefrom. */ -static int mark_source_chains(struct arpt_table_info *newinfo, +static int mark_source_chains(struct xt_table_info *newinfo, unsigned int valid_hooks, void *entry0) { unsigned int hook; @@ -587,8 +470,8 @@ static inline int check_entry(struct arpt_entry *e, const char *name, unsigned i } t = arpt_get_target(e); - target = try_then_request_module(find_target(t->u.user.name, - t->u.user.revision), + target = try_then_request_module(xt_find_target(NF_ARP, t->u.user.name, + t->u.user.revision), "arpt_%s", t->u.user.name); if (IS_ERR(target) || !target) { duprintf("check_entry: `%s' not found\n", t->u.user.name); @@ -622,7 +505,7 @@ out: } static inline int check_entry_size_and_hooks(struct arpt_entry *e, - struct arpt_table_info *newinfo, + struct xt_table_info *newinfo, unsigned char *base, unsigned char *limit, const unsigned int *hook_entries, @@ -656,7 +539,7 @@ static inline int check_entry_size_and_hooks(struct arpt_entry *e, < 0 (not ARPT_RETURN). --RR */ /* Clear counters and comefrom */ - e->counters = ((struct arpt_counters) { 0, 0 }); + e->counters = ((struct xt_counters) { 0, 0 }); e->comefrom = 0; (*i)++; @@ -683,7 +566,7 @@ static inline int cleanup_entry(struct arpt_entry *e, unsigned int *i) */ static int translate_table(const char *name, unsigned int valid_hooks, - struct arpt_table_info *newinfo, + struct xt_table_info *newinfo, void *entry0, unsigned int size, unsigned int number, @@ -764,34 +647,9 @@ static int translate_table(const char *name, return ret; } -static struct arpt_table_info *replace_table(struct arpt_table *table, - unsigned int num_counters, - struct arpt_table_info *newinfo, - int *error) -{ - struct arpt_table_info *oldinfo; - - /* Do the substitution. */ - write_lock_bh(&table->lock); - /* Check inside lock: is the old number correct? */ - if (num_counters != table->private->number) { - duprintf("num_counters != table->private->number (%u/%u)\n", - num_counters, table->private->number); - write_unlock_bh(&table->lock); - *error = -EAGAIN; - return NULL; - } - oldinfo = table->private; - table->private = newinfo; - newinfo->initial_entries = oldinfo->initial_entries; - write_unlock_bh(&table->lock); - - return oldinfo; -} - /* Gets counters. */ static inline int add_entry_to_counter(const struct arpt_entry *e, - struct arpt_counters total[], + struct xt_counters total[], unsigned int *i) { ADD_COUNTER(total[*i], e->counters.bcnt, e->counters.pcnt); @@ -801,7 +659,7 @@ static inline int add_entry_to_counter(const struct arpt_entry *e, } static inline int set_entry_to_counter(const struct arpt_entry *e, - struct arpt_counters total[], + struct xt_counters total[], unsigned int *i) { SET_COUNTER(total[*i], e->counters.bcnt, e->counters.pcnt); @@ -810,8 +668,8 @@ static inline int set_entry_to_counter(const struct arpt_entry *e, return 0; } -static void get_counters(const struct arpt_table_info *t, - struct arpt_counters counters[]) +static void get_counters(const struct xt_table_info *t, + struct xt_counters counters[]) { unsigned int cpu; unsigned int i; @@ -849,7 +707,8 @@ static int copy_entries_to_user(unsigned int total_size, { unsigned int off, num, countersize; struct arpt_entry *e; - struct arpt_counters *counters; + struct xt_counters *counters; + struct xt_table_info *private = table->private; int ret = 0; void *loc_cpu_entry; @@ -857,18 +716,18 @@ static int copy_entries_to_user(unsigned int total_size, * (other than comefrom, which userspace doesn't care * about). */ - countersize = sizeof(struct arpt_counters) * table->private->number; - counters = vmalloc(countersize); + countersize = sizeof(struct xt_counters) * private->number; + counters = vmalloc_node(countersize, numa_node_id()); if (counters == NULL) return -ENOMEM; /* First, sum counters... */ write_lock_bh(&table->lock); - get_counters(table->private, counters); + get_counters(private, counters); write_unlock_bh(&table->lock); - loc_cpu_entry = table->private->entries[raw_smp_processor_id()]; + loc_cpu_entry = private->entries[raw_smp_processor_id()]; /* ... then copy entire thing ... */ if (copy_to_user(userptr, loc_cpu_entry, total_size) != 0) { ret = -EFAULT; @@ -911,75 +770,34 @@ static int get_entries(const struct arpt_get_entries *entries, int ret; struct arpt_table *t; - t = find_table_lock(entries->name); + t = xt_find_table_lock(NF_ARP, entries->name); if (t || !IS_ERR(t)) { + struct xt_table_info *private = t->private; duprintf("t->private->number = %u\n", - t->private->number); - if (entries->size == t->private->size) - ret = copy_entries_to_user(t->private->size, + private->number); + if (entries->size == private->size) + ret = copy_entries_to_user(private->size, t, uptr->entrytable); else { duprintf("get_entries: I've got %u not %u!\n", - t->private->size, - entries->size); + private->size, entries->size); ret = -EINVAL; } module_put(t->me); - up(&arpt_mutex); + xt_table_unlock(t); } else ret = t ? PTR_ERR(t) : -ENOENT; return ret; } -static void free_table_info(struct arpt_table_info *info) -{ - int cpu; - for_each_cpu(cpu) { - if (info->size <= PAGE_SIZE) - kfree(info->entries[cpu]); - else - vfree(info->entries[cpu]); - } - kfree(info); -} - -static struct arpt_table_info *alloc_table_info(unsigned int size) -{ - struct arpt_table_info *newinfo; - int cpu; - - newinfo = kzalloc(sizeof(struct arpt_table_info), GFP_KERNEL); - if (!newinfo) - return NULL; - - newinfo->size = size; - - for_each_cpu(cpu) { - if (size <= PAGE_SIZE) - newinfo->entries[cpu] = kmalloc_node(size, - GFP_KERNEL, - cpu_to_node(cpu)); - else - newinfo->entries[cpu] = vmalloc_node(size, - cpu_to_node(cpu)); - - if (newinfo->entries[cpu] == NULL) { - free_table_info(newinfo); - return NULL; - } - } - - return newinfo; -} - static int do_replace(void __user *user, unsigned int len) { int ret; struct arpt_replace tmp; struct arpt_table *t; - struct arpt_table_info *newinfo, *oldinfo; - struct arpt_counters *counters; + struct xt_table_info *newinfo, *oldinfo; + struct xt_counters *counters; void *loc_cpu_entry, *loc_cpu_old_entry; if (copy_from_user(&tmp, user, sizeof(tmp)) != 0) @@ -989,11 +807,7 @@ static int do_replace(void __user *user, unsigned int len) if (len != sizeof(tmp) + tmp.size) return -ENOPROTOOPT; - /* Pedantry: prevent them from hitting BUG() in vmalloc.c --RR */ - if ((SMP_ALIGN(tmp.size) >> PAGE_SHIFT) + 2 > num_physpages) - return -ENOMEM; - - newinfo = alloc_table_info(tmp.size); + newinfo = xt_alloc_table_info(tmp.size); if (!newinfo) return -ENOMEM; @@ -1005,7 +819,7 @@ static int do_replace(void __user *user, unsigned int len) goto free_newinfo; } - counters = vmalloc(tmp.num_counters * sizeof(struct arpt_counters)); + counters = vmalloc(tmp.num_counters * sizeof(struct xt_counters)); if (!counters) { ret = -ENOMEM; goto free_newinfo; @@ -1019,7 +833,7 @@ static int do_replace(void __user *user, unsigned int len) duprintf("arp_tables: Translated table\n"); - t = try_then_request_module(find_table_lock(tmp.name), + t = try_then_request_module(xt_find_table_lock(NF_ARP, tmp.name), "arptable_%s", tmp.name); if (!t || IS_ERR(t)) { ret = t ? PTR_ERR(t) : -ENOENT; @@ -1034,7 +848,7 @@ static int do_replace(void __user *user, unsigned int len) goto put_module; } - oldinfo = replace_table(t, tmp.num_counters, newinfo, &ret); + oldinfo = xt_replace_table(t, tmp.num_counters, newinfo, &ret); if (!oldinfo) goto put_module; @@ -1054,23 +868,23 @@ static int do_replace(void __user *user, unsigned int len) loc_cpu_old_entry = oldinfo->entries[raw_smp_processor_id()]; ARPT_ENTRY_ITERATE(loc_cpu_old_entry, oldinfo->size, cleanup_entry,NULL); - free_table_info(oldinfo); + xt_free_table_info(oldinfo); if (copy_to_user(tmp.counters, counters, - sizeof(struct arpt_counters) * tmp.num_counters) != 0) + sizeof(struct xt_counters) * tmp.num_counters) != 0) ret = -EFAULT; vfree(counters); - up(&arpt_mutex); + xt_table_unlock(t); return ret; put_module: module_put(t->me); - up(&arpt_mutex); + xt_table_unlock(t); free_newinfo_counters_untrans: ARPT_ENTRY_ITERATE(loc_cpu_entry, newinfo->size, cleanup_entry, NULL); free_newinfo_counters: vfree(counters); free_newinfo: - free_table_info(newinfo); + xt_free_table_info(newinfo); return ret; } @@ -1078,7 +892,7 @@ static int do_replace(void __user *user, unsigned int len) * and everything is OK. */ static inline int add_counter_to_entry(struct arpt_entry *e, - const struct arpt_counters addme[], + const struct xt_counters addme[], unsigned int *i) { @@ -1091,15 +905,16 @@ static inline int add_counter_to_entry(struct arpt_entry *e, static int do_add_counters(void __user *user, unsigned int len) { unsigned int i; - struct arpt_counters_info tmp, *paddc; + struct xt_counters_info tmp, *paddc; struct arpt_table *t; + struct xt_table_info *private; int ret = 0; void *loc_cpu_entry; if (copy_from_user(&tmp, user, sizeof(tmp)) != 0) return -EFAULT; - if (len != sizeof(tmp) + tmp.num_counters*sizeof(struct arpt_counters)) + if (len != sizeof(tmp) + tmp.num_counters*sizeof(struct xt_counters)) return -EINVAL; paddc = vmalloc(len); @@ -1111,29 +926,30 @@ static int do_add_counters(void __user *user, unsigned int len) goto free; } - t = find_table_lock(tmp.name); + t = xt_find_table_lock(NF_ARP, tmp.name); if (!t || IS_ERR(t)) { ret = t ? PTR_ERR(t) : -ENOENT; goto free; } write_lock_bh(&t->lock); - if (t->private->number != paddc->num_counters) { + private = t->private; + if (private->number != paddc->num_counters) { ret = -EINVAL; goto unlock_up_free; } i = 0; /* Choose the copy that is on our node */ - loc_cpu_entry = t->private->entries[smp_processor_id()]; + loc_cpu_entry = private->entries[smp_processor_id()]; ARPT_ENTRY_ITERATE(loc_cpu_entry, - t->private->size, + private->size, add_counter_to_entry, paddc->counters, &i); unlock_up_free: write_unlock_bh(&t->lock); - up(&arpt_mutex); + xt_table_unlock(t); module_put(t->me); free: vfree(paddc); @@ -1190,25 +1006,26 @@ static int do_arpt_get_ctl(struct sock *sk, int cmd, void __user *user, int *len } name[ARPT_TABLE_MAXNAMELEN-1] = '\0'; - t = try_then_request_module(find_table_lock(name), + t = try_then_request_module(xt_find_table_lock(NF_ARP, name), "arptable_%s", name); if (t && !IS_ERR(t)) { struct arpt_getinfo info; + struct xt_table_info *private = t->private; info.valid_hooks = t->valid_hooks; - memcpy(info.hook_entry, t->private->hook_entry, + memcpy(info.hook_entry, private->hook_entry, sizeof(info.hook_entry)); - memcpy(info.underflow, t->private->underflow, + memcpy(info.underflow, private->underflow, sizeof(info.underflow)); - info.num_entries = t->private->number; - info.size = t->private->size; + info.num_entries = private->number; + info.size = private->size; strcpy(info.name, name); if (copy_to_user(user, &info, *len) != 0) ret = -EFAULT; else ret = 0; - up(&arpt_mutex); + xt_table_unlock(t); module_put(t->me); } else ret = t ? PTR_ERR(t) : -ENOENT; @@ -1233,7 +1050,7 @@ static int do_arpt_get_ctl(struct sock *sk, int cmd, void __user *user, int *len } case ARPT_SO_GET_REVISION_TARGET: { - struct arpt_get_revision rev; + struct xt_get_revision rev; if (*len != sizeof(rev)) { ret = -EINVAL; @@ -1244,8 +1061,8 @@ static int do_arpt_get_ctl(struct sock *sk, int cmd, void __user *user, int *len break; } - try_then_request_module(find_revision(rev.name, rev.revision, - target_revfn, &ret), + try_then_request_module(xt_find_revision(NF_ARP, rev.name, + rev.revision, 1, &ret), "arpt_%s", rev.name); break; } @@ -1258,38 +1075,16 @@ static int do_arpt_get_ctl(struct sock *sk, int cmd, void __user *user, int *len return ret; } -/* Registration hooks for targets. */ -int arpt_register_target(struct arpt_target *target) -{ - int ret; - - ret = down_interruptible(&arpt_mutex); - if (ret != 0) - return ret; - - list_add(&target->list, &arpt_target); - up(&arpt_mutex); - - return ret; -} - -void arpt_unregister_target(struct arpt_target *target) -{ - down(&arpt_mutex); - LIST_DELETE(&arpt_target, target); - up(&arpt_mutex); -} - int arpt_register_table(struct arpt_table *table, const struct arpt_replace *repl) { int ret; - struct arpt_table_info *newinfo; - static struct arpt_table_info bootstrap + struct xt_table_info *newinfo; + static struct xt_table_info bootstrap = { 0, 0, 0, { 0 }, { 0 }, { } }; void *loc_cpu_entry; - newinfo = alloc_table_info(repl->size); + newinfo = xt_alloc_table_info(repl->size); if (!newinfo) { ret = -ENOMEM; return ret; @@ -1304,60 +1099,33 @@ int arpt_register_table(struct arpt_table *table, repl->num_entries, repl->hook_entry, repl->underflow); + duprintf("arpt_register_table: translate table gives %d\n", ret); if (ret != 0) { - free_table_info(newinfo); + xt_free_table_info(newinfo); return ret; } - ret = down_interruptible(&arpt_mutex); - if (ret != 0) { - free_table_info(newinfo); + if (xt_register_table(table, &bootstrap, newinfo) != 0) { + xt_free_table_info(newinfo); return ret; } - /* Don't autoload: we'd eat our tail... */ - if (list_named_find(&arpt_tables, table->name)) { - ret = -EEXIST; - goto free_unlock; - } - - /* Simplifies replace_table code. */ - table->private = &bootstrap; - if (!replace_table(table, 0, newinfo, &ret)) - goto free_unlock; - - duprintf("table->private->number = %u\n", - table->private->number); - - /* save number of initial entries */ - table->private->initial_entries = table->private->number; - - rwlock_init(&table->lock); - list_prepend(&arpt_tables, table); - - unlock: - up(&arpt_mutex); - return ret; - - free_unlock: - free_table_info(newinfo); - goto unlock; + return 0; } void arpt_unregister_table(struct arpt_table *table) { + struct xt_table_info *private; void *loc_cpu_entry; - down(&arpt_mutex); - LIST_DELETE(&arpt_tables, table); - up(&arpt_mutex); + private = xt_unregister_table(table); /* Decrease module usage counts and free resources */ - loc_cpu_entry = table->private->entries[raw_smp_processor_id()]; - ARPT_ENTRY_ITERATE(loc_cpu_entry, table->private->size, + loc_cpu_entry = private->entries[raw_smp_processor_id()]; + ARPT_ENTRY_ITERATE(loc_cpu_entry, private->size, cleanup_entry, NULL); - free_table_info(table->private); + xt_free_table_info(private); } /* The built-in targets: standard (NULL) and error. */ @@ -1380,52 +1148,15 @@ static struct nf_sockopt_ops arpt_sockopts = { .get = do_arpt_get_ctl, }; -#ifdef CONFIG_PROC_FS -static inline int print_name(const struct arpt_table *t, - off_t start_offset, char *buffer, int length, - off_t *pos, unsigned int *count) -{ - if ((*count)++ >= start_offset) { - unsigned int namelen; - - namelen = sprintf(buffer + *pos, "%s\n", t->name); - if (*pos + namelen > length) { - /* Stop iterating */ - return 1; - } - *pos += namelen; - } - return 0; -} - -static int arpt_get_tables(char *buffer, char **start, off_t offset, int length) -{ - off_t pos = 0; - unsigned int count = 0; - - if (down_interruptible(&arpt_mutex) != 0) - return 0; - - LIST_FIND(&arpt_tables, print_name, struct arpt_table *, - offset, buffer, length, &pos, &count); - - up(&arpt_mutex); - - /* `start' hack - see fs/proc/generic.c line ~105 */ - *start=(char *)((unsigned long)count-offset); - return pos; -} -#endif /*CONFIG_PROC_FS*/ - static int __init init(void) { int ret; + xt_proto_init(NF_ARP); + /* Noone else will be downing sem now, so we won't sleep */ - down(&arpt_mutex); - list_append(&arpt_target, &arpt_standard_target); - list_append(&arpt_target, &arpt_error_target); - up(&arpt_mutex); + xt_register_target(NF_ARP, &arpt_standard_target); + xt_register_target(NF_ARP, &arpt_error_target); /* Register setsockopt */ ret = nf_register_sockopt(&arpt_sockopts); @@ -1434,19 +1165,6 @@ static int __init init(void) return ret; } -#ifdef CONFIG_PROC_FS - { - struct proc_dir_entry *proc; - - proc = proc_net_create("arp_tables_names", 0, arpt_get_tables); - if (!proc) { - nf_unregister_sockopt(&arpt_sockopts); - return -ENOMEM; - } - proc->owner = THIS_MODULE; - } -#endif - printk("arp_tables: (C) 2002 David S. Miller\n"); return 0; } @@ -1454,16 +1172,12 @@ static int __init init(void) static void __exit fini(void) { nf_unregister_sockopt(&arpt_sockopts); -#ifdef CONFIG_PROC_FS - proc_net_remove("arp_tables_names"); -#endif + xt_proto_fini(NF_ARP); } EXPORT_SYMBOL(arpt_register_table); EXPORT_SYMBOL(arpt_unregister_table); EXPORT_SYMBOL(arpt_do_table); -EXPORT_SYMBOL(arpt_register_target); -EXPORT_SYMBOL(arpt_unregister_target); module_init(init); module_exit(fini); diff --git a/net/ipv4/netfilter/arpt_mangle.c b/net/ipv4/netfilter/arpt_mangle.c index 3e592ec8648..c97650a16a5 100644 --- a/net/ipv4/netfilter/arpt_mangle.c +++ b/net/ipv4/netfilter/arpt_mangle.c @@ -8,8 +8,9 @@ MODULE_AUTHOR("Bart De Schuymer <bdschuym@pandora.be>"); MODULE_DESCRIPTION("arptables arp payload mangle target"); static unsigned int -target(struct sk_buff **pskb, unsigned int hooknum, const struct net_device *in, - const struct net_device *out, const void *targinfo, void *userinfo) +target(struct sk_buff **pskb, const struct net_device *in, + const struct net_device *out, unsigned int hooknum, const void *targinfo, + void *userinfo) { const struct arpt_mangle *mangle = targinfo; struct arphdr *arp; @@ -64,7 +65,7 @@ target(struct sk_buff **pskb, unsigned int hooknum, const struct net_device *in, } static int -checkentry(const char *tablename, const struct arpt_entry *e, void *targinfo, +checkentry(const char *tablename, const void *e, void *targinfo, unsigned int targinfosize, unsigned int hook_mask) { const struct arpt_mangle *mangle = targinfo; diff --git a/net/ipv4/netfilter/arptable_filter.c b/net/ipv4/netfilter/arptable_filter.c index 0d759f5a4ef..f6ab45f4868 100644 --- a/net/ipv4/netfilter/arptable_filter.c +++ b/net/ipv4/netfilter/arptable_filter.c @@ -145,6 +145,7 @@ static struct arpt_table packet_filter = { .lock = RW_LOCK_UNLOCKED, .private = NULL, .me = THIS_MODULE, + .af = NF_ARP, }; /* The work comes in here from netfilter.c */ diff --git a/net/ipv4/netfilter/ip_conntrack_standalone.c b/net/ipv4/netfilter/ip_conntrack_standalone.c index 9dec1293f67..833fcb4be5e 100644 --- a/net/ipv4/netfilter/ip_conntrack_standalone.c +++ b/net/ipv4/netfilter/ip_conntrack_standalone.c @@ -944,7 +944,7 @@ module_exit(fini); /* Some modules need us, but don't depend directly on any symbol. They should call this. */ -void need_ip_conntrack(void) +void need_conntrack(void) { } @@ -962,7 +962,7 @@ EXPORT_SYMBOL(ip_ct_get_tuple); EXPORT_SYMBOL(invert_tuplepr); EXPORT_SYMBOL(ip_conntrack_alter_reply); EXPORT_SYMBOL(ip_conntrack_destroyed); -EXPORT_SYMBOL(need_ip_conntrack); +EXPORT_SYMBOL(need_conntrack); EXPORT_SYMBOL(ip_conntrack_helper_register); EXPORT_SYMBOL(ip_conntrack_helper_unregister); EXPORT_SYMBOL(ip_ct_iterate_cleanup); diff --git a/net/ipv4/netfilter/ip_nat_rule.c b/net/ipv4/netfilter/ip_nat_rule.c index cb66b8bddeb..1de86282d23 100644 --- a/net/ipv4/netfilter/ip_nat_rule.c +++ b/net/ipv4/netfilter/ip_nat_rule.c @@ -95,6 +95,7 @@ static struct ipt_table nat_table = { .valid_hooks = NAT_VALID_HOOKS, .lock = RW_LOCK_UNLOCKED, .me = THIS_MODULE, + .af = AF_INET, }; /* Source NAT */ @@ -168,7 +169,7 @@ static unsigned int ipt_dnat_target(struct sk_buff **pskb, } static int ipt_snat_checkentry(const char *tablename, - const struct ipt_entry *e, + const void *entry, void *targinfo, unsigned int targinfosize, unsigned int hook_mask) @@ -201,7 +202,7 @@ static int ipt_snat_checkentry(const char *tablename, } static int ipt_dnat_checkentry(const char *tablename, - const struct ipt_entry *e, + const void *entry, void *targinfo, unsigned int targinfosize, unsigned int hook_mask) diff --git a/net/ipv4/netfilter/ip_nat_standalone.c b/net/ipv4/netfilter/ip_nat_standalone.c index 8b8a1f00bbf..ad438fb185b 100644 --- a/net/ipv4/netfilter/ip_nat_standalone.c +++ b/net/ipv4/netfilter/ip_nat_standalone.c @@ -364,7 +364,7 @@ static int init_or_cleanup(int init) { int ret = 0; - need_ip_conntrack(); + need_conntrack(); if (!init) goto cleanup; diff --git a/net/ipv4/netfilter/ip_tables.c b/net/ipv4/netfilter/ip_tables.c index 877bc96d333..2371b2062c2 100644 --- a/net/ipv4/netfilter/ip_tables.c +++ b/net/ipv4/netfilter/ip_tables.c @@ -2,7 +2,7 @@ * Packet matching code. * * Copyright (C) 1999 Paul `Rusty' Russell & Michael J. Neuling - * Copyright (C) 2000-2004 Netfilter Core Team <coreteam@netfilter.org> + * Copyright (C) 2000-2005 Netfilter Core Team <coreteam@netfilter.org> * * This program is free software; you can redistribute it and/or modify * it under the terms of the GNU General Public License version 2 as @@ -11,6 +11,8 @@ * 19 Jan 2002 Harald Welte <laforge@gnumonks.org> * - increase module usage count as soon as we have rules inside * a table + * 08 Oct 2005 Harald Welte <lafore@netfilter.org> + * - Generalize into "x_tables" layer and "{ip,ip6,arp}_tables" */ #include <linux/config.h> #include <linux/cache.h> @@ -20,8 +22,6 @@ #include <linux/vmalloc.h> #include <linux/netdevice.h> #include <linux/module.h> -#include <linux/tcp.h> -#include <linux/udp.h> #include <linux/icmp.h> #include <net/ip.h> #include <asm/uaccess.h> @@ -30,6 +30,7 @@ #include <linux/err.h> #include <linux/cpumask.h> +#include <linux/netfilter/x_tables.h> #include <linux/netfilter_ipv4/ip_tables.h> MODULE_LICENSE("GPL"); @@ -62,14 +63,6 @@ do { \ #else #define IP_NF_ASSERT(x) #endif -#define SMP_ALIGN(x) (((x) + SMP_CACHE_BYTES-1) & ~(SMP_CACHE_BYTES-1)) - -static DECLARE_MUTEX(ipt_mutex); - -/* Must have mutex */ -#define ASSERT_READ_LOCK(x) IP_NF_ASSERT(down_trylock(&ipt_mutex) != 0) -#define ASSERT_WRITE_LOCK(x) IP_NF_ASSERT(down_trylock(&ipt_mutex) != 0) -#include <linux/netfilter_ipv4/listhelp.h> #if 0 /* All the better to debug you with... */ @@ -86,36 +79,6 @@ static DECLARE_MUTEX(ipt_mutex); Hence the start of any table is given by get_table() below. */ -/* The table itself */ -struct ipt_table_info -{ - /* Size per table */ - unsigned int size; - /* Number of entries: FIXME. --RR */ - unsigned int number; - /* Initial number of entries. Needed for module usage count */ - unsigned int initial_entries; - - /* Entry points and underflows */ - unsigned int hook_entry[NF_IP_NUMHOOKS]; - unsigned int underflow[NF_IP_NUMHOOKS]; - - /* ipt_entry tables: one per CPU */ - void *entries[NR_CPUS]; -}; - -static LIST_HEAD(ipt_target); -static LIST_HEAD(ipt_match); -static LIST_HEAD(ipt_tables); -#define SET_COUNTER(c,b,p) do { (c).bcnt = (b); (c).pcnt = (p); } while(0) -#define ADD_COUNTER(c,b,p) do { (c).bcnt += (b); (c).pcnt += (p); } while(0) - -#if 0 -#define down(x) do { printk("DOWN:%u:" #x "\n", __LINE__); down(x); } while(0) -#define down_interruptible(x) ({ int __r; printk("DOWNi:%u:" #x "\n", __LINE__); __r = down_interruptible(x); if (__r != 0) printk("ABORT-DOWNi:%u\n", __LINE__); __r; }) -#define up(x) do { printk("UP:%u:" #x "\n", __LINE__); up(x); } while(0) -#endif - /* Returns whether matches rule or not. */ static inline int ip_packet_match(const struct iphdr *ip, @@ -234,7 +197,8 @@ int do_match(struct ipt_entry_match *m, int *hotdrop) { /* Stop iteration if it doesn't match */ - if (!m->u.kernel.match->match(skb, in, out, m->data, offset, hotdrop)) + if (!m->u.kernel.match->match(skb, in, out, m->data, offset, + skb->nh.iph->ihl*4, hotdrop)) return 1; else return 0; @@ -265,6 +229,7 @@ ipt_do_table(struct sk_buff **pskb, const char *indev, *outdev; void *table_base; struct ipt_entry *e, *back; + struct xt_table_info *private = table->private; /* Initialization */ ip = (*pskb)->nh.iph; @@ -281,24 +246,11 @@ ipt_do_table(struct sk_buff **pskb, read_lock_bh(&table->lock); IP_NF_ASSERT(table->valid_hooks & (1 << hook)); - table_base = (void *)table->private->entries[smp_processor_id()]; - e = get_entry(table_base, table->private->hook_entry[hook]); - -#ifdef CONFIG_NETFILTER_DEBUG - /* Check noone else using our table */ - if (((struct ipt_entry *)table_base)->comefrom != 0xdead57ac - && ((struct ipt_entry *)table_base)->comefrom != 0xeeeeeeec) { - printk("ASSERT: CPU #%u, %s comefrom(%p) = %X\n", - smp_processor_id(), - table->name, - &((struct ipt_entry *)table_base)->comefrom, - ((struct ipt_entry *)table_base)->comefrom); - } - ((struct ipt_entry *)table_base)->comefrom = 0x57acc001; -#endif + table_base = (void *)private->entries[smp_processor_id()]; + e = get_entry(table_base, private->hook_entry[hook]); /* For return from builtin chain */ - back = get_entry(table_base, table->private->underflow[hook]); + back = get_entry(table_base, private->underflow[hook]); do { IP_NF_ASSERT(e); @@ -384,9 +336,6 @@ ipt_do_table(struct sk_buff **pskb, } } while (!hotdrop); -#ifdef CONFIG_NETFILTER_DEBUG - ((struct ipt_entry *)table_base)->comefrom = 0xdead57ac; -#endif read_unlock_bh(&table->lock); #ifdef DEBUG_ALLOW_ALL @@ -398,145 +347,6 @@ ipt_do_table(struct sk_buff **pskb, #endif } -/* - * These are weird, but module loading must not be done with mutex - * held (since they will register), and we have to have a single - * function to use try_then_request_module(). - */ - -/* Find table by name, grabs mutex & ref. Returns ERR_PTR() on error. */ -static inline struct ipt_table *find_table_lock(const char *name) -{ - struct ipt_table *t; - - if (down_interruptible(&ipt_mutex) != 0) - return ERR_PTR(-EINTR); - - list_for_each_entry(t, &ipt_tables, list) - if (strcmp(t->name, name) == 0 && try_module_get(t->me)) - return t; - up(&ipt_mutex); - return NULL; -} - -/* Find match, grabs ref. Returns ERR_PTR() on error. */ -static inline struct ipt_match *find_match(const char *name, u8 revision) -{ - struct ipt_match *m; - int err = 0; - - if (down_interruptible(&ipt_mutex) != 0) - return ERR_PTR(-EINTR); - - list_for_each_entry(m, &ipt_match, list) { - if (strcmp(m->name, name) == 0) { - if (m->revision == revision) { - if (try_module_get(m->me)) { - up(&ipt_mutex); - return m; - } - } else - err = -EPROTOTYPE; /* Found something. */ - } - } - up(&ipt_mutex); - return ERR_PTR(err); -} - -/* Find target, grabs ref. Returns ERR_PTR() on error. */ -static inline struct ipt_target *find_target(const char *name, u8 revision) -{ - struct ipt_target *t; - int err = 0; - - if (down_interruptible(&ipt_mutex) != 0) - return ERR_PTR(-EINTR); - - list_for_each_entry(t, &ipt_target, list) { - if (strcmp(t->name, name) == 0) { - if (t->revision == revision) { - if (try_module_get(t->me)) { - up(&ipt_mutex); - return t; - } - } else - err = -EPROTOTYPE; /* Found something. */ - } - } - up(&ipt_mutex); - return ERR_PTR(err); -} - -struct ipt_target *ipt_find_target(const char *name, u8 revision) -{ - struct ipt_target *target; - - target = try_then_request_module(find_target(name, revision), - "ipt_%s", name); - if (IS_ERR(target) || !target) - return NULL; - return target; -} - -static int match_revfn(const char *name, u8 revision, int *bestp) -{ - struct ipt_match *m; - int have_rev = 0; - - list_for_each_entry(m, &ipt_match, list) { - if (strcmp(m->name, name) == 0) { - if (m->revision > *bestp) - *bestp = m->revision; - if (m->revision == revision) - have_rev = 1; - } - } - return have_rev; -} - -static int target_revfn(const char *name, u8 revision, int *bestp) -{ - struct ipt_target *t; - int have_rev = 0; - - list_for_each_entry(t, &ipt_target, list) { - if (strcmp(t->name, name) == 0) { - if (t->revision > *bestp) - *bestp = t->revision; - if (t->revision == revision) - have_rev = 1; - } - } - return have_rev; -} - -/* Returns true or false (if no such extension at all) */ -static inline int find_revision(const char *name, u8 revision, - int (*revfn)(const char *, u8, int *), - int *err) -{ - int have_rev, best = -1; - - if (down_interruptible(&ipt_mutex) != 0) { - *err = -EINTR; - return 1; - } - have_rev = revfn(name, revision, &best); - up(&ipt_mutex); - - /* Nothing at all? Return 0 to try loading module. */ - if (best == -1) { - *err = -ENOENT; - return 0; - } - - *err = best; - if (!have_rev) - *err = -EPROTONOSUPPORT; - return 1; -} - - /* All zeroes == unconditional rule. */ static inline int unconditional(const struct ipt_ip *ip) @@ -553,7 +363,7 @@ unconditional(const struct ipt_ip *ip) /* Figures out from what hook each rule can be called: returns 0 if there are loops. Puts hook bitmask in comefrom. */ static int -mark_source_chains(struct ipt_table_info *newinfo, +mark_source_chains(struct xt_table_info *newinfo, unsigned int valid_hooks, void *entry0) { unsigned int hook; @@ -699,7 +509,7 @@ check_match(struct ipt_entry_match *m, { struct ipt_match *match; - match = try_then_request_module(find_match(m->u.user.name, + match = try_then_request_module(xt_find_match(AF_INET, m->u.user.name, m->u.user.revision), "ipt_%s", m->u.user.name); if (IS_ERR(match) || !match) { @@ -744,7 +554,8 @@ check_entry(struct ipt_entry *e, const char *name, unsigned int size, goto cleanup_matches; t = ipt_get_target(e); - target = try_then_request_module(find_target(t->u.user.name, + target = try_then_request_module(xt_find_target(AF_INET, + t->u.user.name, t->u.user.revision), "ipt_%s", t->u.user.name); if (IS_ERR(target) || !target) { @@ -781,7 +592,7 @@ check_entry(struct ipt_entry *e, const char *name, unsigned int size, static inline int check_entry_size_and_hooks(struct ipt_entry *e, - struct ipt_table_info *newinfo, + struct xt_table_info *newinfo, unsigned char *base, unsigned char *limit, const unsigned int *hook_entries, @@ -815,7 +626,7 @@ check_entry_size_and_hooks(struct ipt_entry *e, < 0 (not IPT_RETURN). --RR */ /* Clear counters and comefrom */ - e->counters = ((struct ipt_counters) { 0, 0 }); + e->counters = ((struct xt_counters) { 0, 0 }); e->comefrom = 0; (*i)++; @@ -845,7 +656,7 @@ cleanup_entry(struct ipt_entry *e, unsigned int *i) static int translate_table(const char *name, unsigned int valid_hooks, - struct ipt_table_info *newinfo, + struct xt_table_info *newinfo, void *entry0, unsigned int size, unsigned int number, @@ -922,48 +733,10 @@ translate_table(const char *name, return ret; } -static struct ipt_table_info * -replace_table(struct ipt_table *table, - unsigned int num_counters, - struct ipt_table_info *newinfo, - int *error) -{ - struct ipt_table_info *oldinfo; - -#ifdef CONFIG_NETFILTER_DEBUG - { - int cpu; - - for_each_cpu(cpu) { - struct ipt_entry *table_base = newinfo->entries[cpu]; - if (table_base) - table_base->comefrom = 0xdead57ac; - } - } -#endif - - /* Do the substitution. */ - write_lock_bh(&table->lock); - /* Check inside lock: is the old number correct? */ - if (num_counters != table->private->number) { - duprintf("num_counters != table->private->number (%u/%u)\n", - num_counters, table->private->number); - write_unlock_bh(&table->lock); - *error = -EAGAIN; - return NULL; - } - oldinfo = table->private; - table->private = newinfo; - newinfo->initial_entries = oldinfo->initial_entries; - write_unlock_bh(&table->lock); - - return oldinfo; -} - /* Gets counters. */ static inline int add_entry_to_counter(const struct ipt_entry *e, - struct ipt_counters total[], + struct xt_counters total[], unsigned int *i) { ADD_COUNTER(total[*i], e->counters.bcnt, e->counters.pcnt); @@ -984,8 +757,8 @@ set_entry_to_counter(const struct ipt_entry *e, } static void -get_counters(const struct ipt_table_info *t, - struct ipt_counters counters[]) +get_counters(const struct xt_table_info *t, + struct xt_counters counters[]) { unsigned int cpu; unsigned int i; @@ -1024,14 +797,15 @@ copy_entries_to_user(unsigned int total_size, { unsigned int off, num, countersize; struct ipt_entry *e; - struct ipt_counters *counters; + struct xt_counters *counters; + struct xt_table_info *private = table->private; int ret = 0; void *loc_cpu_entry; /* We need atomic snapshot of counters: rest doesn't change (other than comefrom, which userspace doesn't care about). */ - countersize = sizeof(struct ipt_counters) * table->private->number; + countersize = sizeof(struct xt_counters) * private->number; counters = vmalloc_node(countersize, numa_node_id()); if (counters == NULL) @@ -1039,14 +813,14 @@ copy_entries_to_user(unsigned int total_size, /* First, sum counters... */ write_lock_bh(&table->lock); - get_counters(table->private, counters); + get_counters(private, counters); write_unlock_bh(&table->lock); /* choose the copy that is on our node/cpu, ... * This choice is lazy (because current thread is * allowed to migrate to another cpu) */ - loc_cpu_entry = table->private->entries[raw_smp_processor_id()]; + loc_cpu_entry = private->entries[raw_smp_processor_id()]; /* ... then copy entire thing ... */ if (copy_to_user(userptr, loc_cpu_entry, total_size) != 0) { ret = -EFAULT; @@ -1108,74 +882,36 @@ get_entries(const struct ipt_get_entries *entries, int ret; struct ipt_table *t; - t = find_table_lock(entries->name); + t = xt_find_table_lock(AF_INET, entries->name); if (t && !IS_ERR(t)) { + struct xt_table_info *private = t->private; duprintf("t->private->number = %u\n", - t->private->number); - if (entries->size == t->private->size) - ret = copy_entries_to_user(t->private->size, + private->number); + if (entries->size == private->size) + ret = copy_entries_to_user(private->size, t, uptr->entrytable); else { duprintf("get_entries: I've got %u not %u!\n", - t->private->size, + private->size, entries->size); ret = -EINVAL; } module_put(t->me); - up(&ipt_mutex); + xt_table_unlock(t); } else ret = t ? PTR_ERR(t) : -ENOENT; return ret; } -static void free_table_info(struct ipt_table_info *info) -{ - int cpu; - for_each_cpu(cpu) { - if (info->size <= PAGE_SIZE) - kfree(info->entries[cpu]); - else - vfree(info->entries[cpu]); - } - kfree(info); -} - -static struct ipt_table_info *alloc_table_info(unsigned int size) -{ - struct ipt_table_info *newinfo; - int cpu; - - newinfo = kzalloc(sizeof(struct ipt_table_info), GFP_KERNEL); - if (!newinfo) - return NULL; - - newinfo->size = size; - - for_each_cpu(cpu) { - if (size <= PAGE_SIZE) - newinfo->entries[cpu] = kmalloc_node(size, - GFP_KERNEL, - cpu_to_node(cpu)); - else - newinfo->entries[cpu] = vmalloc_node(size, cpu_to_node(cpu)); - if (newinfo->entries[cpu] == 0) { - free_table_info(newinfo); - return NULL; - } - } - - return newinfo; -} - static int do_replace(void __user *user, unsigned int len) { int ret; struct ipt_replace tmp; struct ipt_table *t; - struct ipt_table_info *newinfo, *oldinfo; - struct ipt_counters *counters; + struct xt_table_info *newinfo, *oldinfo; + struct xt_counters *counters; void *loc_cpu_entry, *loc_cpu_old_entry; if (copy_from_user(&tmp, user, sizeof(tmp)) != 0) @@ -1185,11 +921,7 @@ do_replace(void __user *user, unsigned int len) if (len != sizeof(tmp) + tmp.size) return -ENOPROTOOPT; - /* Pedantry: prevent them from hitting BUG() in vmalloc.c --RR */ - if ((SMP_ALIGN(tmp.size) >> PAGE_SHIFT) + 2 > num_physpages) - return -ENOMEM; - - newinfo = alloc_table_info(tmp.size); + newinfo = xt_alloc_table_info(tmp.size); if (!newinfo) return -ENOMEM; @@ -1201,7 +933,7 @@ do_replace(void __user *user, unsigned int len) goto free_newinfo; } - counters = vmalloc(tmp.num_counters * sizeof(struct ipt_counters)); + counters = vmalloc(tmp.num_counters * sizeof(struct xt_counters)); if (!counters) { ret = -ENOMEM; goto free_newinfo; @@ -1215,7 +947,7 @@ do_replace(void __user *user, unsigned int len) duprintf("ip_tables: Translated table\n"); - t = try_then_request_module(find_table_lock(tmp.name), + t = try_then_request_module(xt_find_table_lock(AF_INET, tmp.name), "iptable_%s", tmp.name); if (!t || IS_ERR(t)) { ret = t ? PTR_ERR(t) : -ENOENT; @@ -1230,7 +962,7 @@ do_replace(void __user *user, unsigned int len) goto put_module; } - oldinfo = replace_table(t, tmp.num_counters, newinfo, &ret); + oldinfo = xt_replace_table(t, tmp.num_counters, newinfo, &ret); if (!oldinfo) goto put_module; @@ -1249,23 +981,23 @@ do_replace(void __user *user, unsigned int len) /* Decrease module usage counts and free resource */ loc_cpu_old_entry = oldinfo->entries[raw_smp_processor_id()]; IPT_ENTRY_ITERATE(loc_cpu_old_entry, oldinfo->size, cleanup_entry,NULL); - free_table_info(oldinfo); + xt_free_table_info(oldinfo); if (copy_to_user(tmp.counters, counters, - sizeof(struct ipt_counters) * tmp.num_counters) != 0) + sizeof(struct xt_counters) * tmp.num_counters) != 0) ret = -EFAULT; vfree(counters); - up(&ipt_mutex); + xt_table_unlock(t); return ret; put_module: module_put(t->me); - up(&ipt_mutex); + xt_table_unlock(t); free_newinfo_counters_untrans: IPT_ENTRY_ITERATE(loc_cpu_entry, newinfo->size, cleanup_entry,NULL); free_newinfo_counters: vfree(counters); free_newinfo: - free_table_info(newinfo); + xt_free_table_info(newinfo); return ret; } @@ -1273,7 +1005,7 @@ do_replace(void __user *user, unsigned int len) * and everything is OK. */ static inline int add_counter_to_entry(struct ipt_entry *e, - const struct ipt_counters addme[], + const struct xt_counters addme[], unsigned int *i) { #if 0 @@ -1295,15 +1027,16 @@ static int do_add_counters(void __user *user, unsigned int len) { unsigned int i; - struct ipt_counters_info tmp, *paddc; + struct xt_counters_info tmp, *paddc; struct ipt_table *t; + struct xt_table_info *private; int ret = 0; void *loc_cpu_entry; if (copy_from_user(&tmp, user, sizeof(tmp)) != 0) return -EFAULT; - if (len != sizeof(tmp) + tmp.num_counters*sizeof(struct ipt_counters)) + if (len != sizeof(tmp) + tmp.num_counters*sizeof(struct xt_counters)) return -EINVAL; paddc = vmalloc_node(len, numa_node_id()); @@ -1315,29 +1048,30 @@ do_add_counters(void __user *user, unsigned int len) goto free; } - t = find_table_lock(tmp.name); + t = xt_find_table_lock(AF_INET, tmp.name); if (!t || IS_ERR(t)) { ret = t ? PTR_ERR(t) : -ENOENT; goto free; } write_lock_bh(&t->lock); - if (t->private->number != paddc->num_counters) { + private = t->private; + if (private->number != paddc->num_counters) { ret = -EINVAL; goto unlock_up_free; } i = 0; /* Choose the copy that is on our node */ - loc_cpu_entry = t->private->entries[raw_smp_processor_id()]; + loc_cpu_entry = private->entries[raw_smp_processor_id()]; IPT_ENTRY_ITERATE(loc_cpu_entry, - t->private->size, + private->size, add_counter_to_entry, paddc->counters, &i); unlock_up_free: write_unlock_bh(&t->lock); - up(&ipt_mutex); + xt_table_unlock(t); module_put(t->me); free: vfree(paddc); @@ -1396,25 +1130,26 @@ do_ipt_get_ctl(struct sock *sk, int cmd, void __user *user, int *len) } name[IPT_TABLE_MAXNAMELEN-1] = '\0'; - t = try_then_request_module(find_table_lock(name), + t = try_then_request_module(xt_find_table_lock(AF_INET, name), "iptable_%s", name); if (t && !IS_ERR(t)) { struct ipt_getinfo info; + struct xt_table_info *private = t->private; info.valid_hooks = t->valid_hooks; - memcpy(info.hook_entry, t->private->hook_entry, + memcpy(info.hook_entry, private->hook_entry, sizeof(info.hook_entry)); - memcpy(info.underflow, t->private->underflow, + memcpy(info.underflow, private->underflow, sizeof(info.underflow)); - info.num_entries = t->private->number; - info.size = t->private->size; + info.num_entries = private->number; + info.size = private->size; memcpy(info.name, name, sizeof(info.name)); if (copy_to_user(user, &info, *len) != 0) ret = -EFAULT; else ret = 0; - up(&ipt_mutex); + xt_table_unlock(t); module_put(t->me); } else ret = t ? PTR_ERR(t) : -ENOENT; @@ -1441,7 +1176,7 @@ do_ipt_get_ctl(struct sock *sk, int cmd, void __user *user, int *len) case IPT_SO_GET_REVISION_MATCH: case IPT_SO_GET_REVISION_TARGET: { struct ipt_get_revision rev; - int (*revfn)(const char *, u8, int *); + int target; if (*len != sizeof(rev)) { ret = -EINVAL; @@ -1453,12 +1188,13 @@ do_ipt_get_ctl(struct sock *sk, int cmd, void __user *user, int *len) } if (cmd == IPT_SO_GET_REVISION_TARGET) - revfn = target_revfn; + target = 1; else - revfn = match_revfn; + target = 0; - try_then_request_module(find_revision(rev.name, rev.revision, - revfn, &ret), + try_then_request_module(xt_find_revision(AF_INET, rev.name, + rev.revision, + target, &ret), "ipt_%s", rev.name); break; } @@ -1471,60 +1207,15 @@ do_ipt_get_ctl(struct sock *sk, int cmd, void __user *user, int *len) return ret; } -/* Registration hooks for targets. */ -int -ipt_register_target(struct ipt_target *target) +int ipt_register_table(struct xt_table *table, const struct ipt_replace *repl) { int ret; - - ret = down_interruptible(&ipt_mutex); - if (ret != 0) - return ret; - list_add(&target->list, &ipt_target); - up(&ipt_mutex); - return ret; -} - -void -ipt_unregister_target(struct ipt_target *target) -{ - down(&ipt_mutex); - LIST_DELETE(&ipt_target, target); - up(&ipt_mutex); -} - -int -ipt_register_match(struct ipt_match *match) -{ - int ret; - - ret = down_interruptible(&ipt_mutex); - if (ret != 0) - return ret; - - list_add(&match->list, &ipt_match); - up(&ipt_mutex); - - return ret; -} - -void -ipt_unregister_match(struct ipt_match *match) -{ - down(&ipt_mutex); - LIST_DELETE(&ipt_match, match); - up(&ipt_mutex); -} - -int ipt_register_table(struct ipt_table *table, const struct ipt_replace *repl) -{ - int ret; - struct ipt_table_info *newinfo; - static struct ipt_table_info bootstrap + struct xt_table_info *newinfo; + static struct xt_table_info bootstrap = { 0, 0, 0, { 0 }, { 0 }, { } }; void *loc_cpu_entry; - newinfo = alloc_table_info(repl->size); + newinfo = xt_alloc_table_info(repl->size); if (!newinfo) return -ENOMEM; @@ -1540,246 +1231,29 @@ int ipt_register_table(struct ipt_table *table, const struct ipt_replace *repl) repl->hook_entry, repl->underflow); if (ret != 0) { - free_table_info(newinfo); + xt_free_table_info(newinfo); return ret; } - ret = down_interruptible(&ipt_mutex); - if (ret != 0) { - free_table_info(newinfo); + if (xt_register_table(table, &bootstrap, newinfo) != 0) { + xt_free_table_info(newinfo); return ret; } - /* Don't autoload: we'd eat our tail... */ - if (list_named_find(&ipt_tables, table->name)) { - ret = -EEXIST; - goto free_unlock; - } - - /* Simplifies replace_table code. */ - table->private = &bootstrap; - if (!replace_table(table, 0, newinfo, &ret)) - goto free_unlock; - - duprintf("table->private->number = %u\n", - table->private->number); - - /* save number of initial entries */ - table->private->initial_entries = table->private->number; - - rwlock_init(&table->lock); - list_prepend(&ipt_tables, table); - - unlock: - up(&ipt_mutex); - return ret; - - free_unlock: - free_table_info(newinfo); - goto unlock; + return 0; } void ipt_unregister_table(struct ipt_table *table) { + struct xt_table_info *private; void *loc_cpu_entry; - down(&ipt_mutex); - LIST_DELETE(&ipt_tables, table); - up(&ipt_mutex); + private = xt_unregister_table(table); /* Decrease module usage counts and free resources */ - loc_cpu_entry = table->private->entries[raw_smp_processor_id()]; - IPT_ENTRY_ITERATE(loc_cpu_entry, table->private->size, - cleanup_entry, NULL); - free_table_info(table->private); -} - -/* Returns 1 if the port is matched by the range, 0 otherwise */ -static inline int -port_match(u_int16_t min, u_int16_t max, u_int16_t port, int invert) -{ - int ret; - - ret = (port >= min && port <= max) ^ invert; - return ret; -} - -static int -tcp_find_option(u_int8_t option, - const struct sk_buff *skb, - unsigned int optlen, - int invert, - int *hotdrop) -{ - /* tcp.doff is only 4 bits, ie. max 15 * 4 bytes */ - u_int8_t _opt[60 - sizeof(struct tcphdr)], *op; - unsigned int i; - - duprintf("tcp_match: finding option\n"); - - if (!optlen) - return invert; - - /* If we don't have the whole header, drop packet. */ - op = skb_header_pointer(skb, - skb->nh.iph->ihl*4 + sizeof(struct tcphdr), - optlen, _opt); - if (op == NULL) { - *hotdrop = 1; - return 0; - } - - for (i = 0; i < optlen; ) { - if (op[i] == option) return !invert; - if (op[i] < 2) i++; - else i += op[i+1]?:1; - } - - return invert; -} - -static int -tcp_match(const struct sk_buff *skb, - const struct net_device *in, - const struct net_device *out, - const void *matchinfo, - int offset, - int *hotdrop) -{ - struct tcphdr _tcph, *th; - const struct ipt_tcp *tcpinfo = matchinfo; - - if (offset) { - /* To quote Alan: - - Don't allow a fragment of TCP 8 bytes in. Nobody normal - causes this. Its a cracker trying to break in by doing a - flag overwrite to pass the direction checks. - */ - if (offset == 1) { - duprintf("Dropping evil TCP offset=1 frag.\n"); - *hotdrop = 1; - } - /* Must not be a fragment. */ - return 0; - } - -#define FWINVTCP(bool,invflg) ((bool) ^ !!(tcpinfo->invflags & invflg)) - - th = skb_header_pointer(skb, skb->nh.iph->ihl*4, - sizeof(_tcph), &_tcph); - if (th == NULL) { - /* We've been asked to examine this packet, and we - can't. Hence, no choice but to drop. */ - duprintf("Dropping evil TCP offset=0 tinygram.\n"); - *hotdrop = 1; - return 0; - } - - if (!port_match(tcpinfo->spts[0], tcpinfo->spts[1], - ntohs(th->source), - !!(tcpinfo->invflags & IPT_TCP_INV_SRCPT))) - return 0; - if (!port_match(tcpinfo->dpts[0], tcpinfo->dpts[1], - ntohs(th->dest), - !!(tcpinfo->invflags & IPT_TCP_INV_DSTPT))) - return 0; - if (!FWINVTCP((((unsigned char *)th)[13] & tcpinfo->flg_mask) - == tcpinfo->flg_cmp, - IPT_TCP_INV_FLAGS)) - return 0; - if (tcpinfo->option) { - if (th->doff * 4 < sizeof(_tcph)) { - *hotdrop = 1; - return 0; - } - if (!tcp_find_option(tcpinfo->option, skb, - th->doff*4 - sizeof(_tcph), - tcpinfo->invflags & IPT_TCP_INV_OPTION, - hotdrop)) - return 0; - } - return 1; -} - -/* Called when user tries to insert an entry of this type. */ -static int -tcp_checkentry(const char *tablename, - const struct ipt_ip *ip, - void *matchinfo, - unsigned int matchsize, - unsigned int hook_mask) -{ - const struct ipt_tcp *tcpinfo = matchinfo; - - /* Must specify proto == TCP, and no unknown invflags */ - return ip->proto == IPPROTO_TCP - && !(ip->invflags & IPT_INV_PROTO) - && matchsize == IPT_ALIGN(sizeof(struct ipt_tcp)) - && !(tcpinfo->invflags & ~IPT_TCP_INV_MASK); -} - -static int -udp_match(const struct sk_buff *skb, - const struct net_device *in, - const struct net_device *out, - const void *matchinfo, - int offset, - int *hotdrop) -{ - struct udphdr _udph, *uh; - const struct ipt_udp *udpinfo = matchinfo; - - /* Must not be a fragment. */ - if (offset) - return 0; - - uh = skb_header_pointer(skb, skb->nh.iph->ihl*4, - sizeof(_udph), &_udph); - if (uh == NULL) { - /* We've been asked to examine this packet, and we - can't. Hence, no choice but to drop. */ - duprintf("Dropping evil UDP tinygram.\n"); - *hotdrop = 1; - return 0; - } - - return port_match(udpinfo->spts[0], udpinfo->spts[1], - ntohs(uh->source), - !!(udpinfo->invflags & IPT_UDP_INV_SRCPT)) - && port_match(udpinfo->dpts[0], udpinfo->dpts[1], - ntohs(uh->dest), - !!(udpinfo->invflags & IPT_UDP_INV_DSTPT)); -} - -/* Called when user tries to insert an entry of this type. */ -static int -udp_checkentry(const char *tablename, - const struct ipt_ip *ip, - void *matchinfo, - unsigned int matchinfosize, - unsigned int hook_mask) -{ - const struct ipt_udp *udpinfo = matchinfo; - - /* Must specify proto == UDP, and no unknown invflags */ - if (ip->proto != IPPROTO_UDP || (ip->invflags & IPT_INV_PROTO)) { - duprintf("ipt_udp: Protocol %u != %u\n", ip->proto, - IPPROTO_UDP); - return 0; - } - if (matchinfosize != IPT_ALIGN(sizeof(struct ipt_udp))) { - duprintf("ipt_udp: matchsize %u != %u\n", - matchinfosize, IPT_ALIGN(sizeof(struct ipt_udp))); - return 0; - } - if (udpinfo->invflags & ~IPT_UDP_INV_MASK) { - duprintf("ipt_udp: unknown flags %X\n", - udpinfo->invflags); - return 0; - } - - return 1; + loc_cpu_entry = private->entries[raw_smp_processor_id()]; + IPT_ENTRY_ITERATE(loc_cpu_entry, private->size, cleanup_entry, NULL); + xt_free_table_info(private); } /* Returns 1 if the type and code is matched by the range, 0 otherwise */ @@ -1798,6 +1272,7 @@ icmp_match(const struct sk_buff *skb, const struct net_device *out, const void *matchinfo, int offset, + unsigned int protoff, int *hotdrop) { struct icmphdr _icmph, *ic; @@ -1807,8 +1282,7 @@ icmp_match(const struct sk_buff *skb, if (offset) return 0; - ic = skb_header_pointer(skb, skb->nh.iph->ihl*4, - sizeof(_icmph), &_icmph); + ic = skb_header_pointer(skb, protoff, sizeof(_icmph), &_icmph); if (ic == NULL) { /* We've been asked to examine this packet, and we * can't. Hence, no choice but to drop. @@ -1828,11 +1302,12 @@ icmp_match(const struct sk_buff *skb, /* Called when user tries to insert an entry of this type. */ static int icmp_checkentry(const char *tablename, - const struct ipt_ip *ip, + const void *info, void *matchinfo, unsigned int matchsize, unsigned int hook_mask) { + const struct ipt_ip *ip = info; const struct ipt_icmp *icmpinfo = matchinfo; /* Must specify proto == ICMP, and no unknown invflags */ @@ -1862,123 +1337,22 @@ static struct nf_sockopt_ops ipt_sockopts = { .get = do_ipt_get_ctl, }; -static struct ipt_match tcp_matchstruct = { - .name = "tcp", - .match = &tcp_match, - .checkentry = &tcp_checkentry, -}; - -static struct ipt_match udp_matchstruct = { - .name = "udp", - .match = &udp_match, - .checkentry = &udp_checkentry, -}; - static struct ipt_match icmp_matchstruct = { .name = "icmp", .match = &icmp_match, .checkentry = &icmp_checkentry, }; -#ifdef CONFIG_PROC_FS -static inline int print_name(const char *i, - off_t start_offset, char *buffer, int length, - off_t *pos, unsigned int *count) -{ - if ((*count)++ >= start_offset) { - unsigned int namelen; - - namelen = sprintf(buffer + *pos, "%s\n", - i + sizeof(struct list_head)); - if (*pos + namelen > length) { - /* Stop iterating */ - return 1; - } - *pos += namelen; - } - return 0; -} - -static inline int print_target(const struct ipt_target *t, - off_t start_offset, char *buffer, int length, - off_t *pos, unsigned int *count) -{ - if (t == &ipt_standard_target || t == &ipt_error_target) - return 0; - return print_name((char *)t, start_offset, buffer, length, pos, count); -} - -static int ipt_get_tables(char *buffer, char **start, off_t offset, int length) -{ - off_t pos = 0; - unsigned int count = 0; - - if (down_interruptible(&ipt_mutex) != 0) - return 0; - - LIST_FIND(&ipt_tables, print_name, void *, - offset, buffer, length, &pos, &count); - - up(&ipt_mutex); - - /* `start' hack - see fs/proc/generic.c line ~105 */ - *start=(char *)((unsigned long)count-offset); - return pos; -} - -static int ipt_get_targets(char *buffer, char **start, off_t offset, int length) -{ - off_t pos = 0; - unsigned int count = 0; - - if (down_interruptible(&ipt_mutex) != 0) - return 0; - - LIST_FIND(&ipt_target, print_target, struct ipt_target *, - offset, buffer, length, &pos, &count); - - up(&ipt_mutex); - - *start = (char *)((unsigned long)count - offset); - return pos; -} - -static int ipt_get_matches(char *buffer, char **start, off_t offset, int length) -{ - off_t pos = 0; - unsigned int count = 0; - - if (down_interruptible(&ipt_mutex) != 0) - return 0; - - LIST_FIND(&ipt_match, print_name, void *, - offset, buffer, length, &pos, &count); - - up(&ipt_mutex); - - *start = (char *)((unsigned long)count - offset); - return pos; -} - -static const struct { char *name; get_info_t *get_info; } ipt_proc_entry[] = -{ { "ip_tables_names", ipt_get_tables }, - { "ip_tables_targets", ipt_get_targets }, - { "ip_tables_matches", ipt_get_matches }, - { NULL, NULL} }; -#endif /*CONFIG_PROC_FS*/ - static int __init init(void) { int ret; + xt_proto_init(AF_INET); + /* Noone else will be downing sem now, so we won't sleep */ - down(&ipt_mutex); - list_append(&ipt_target, &ipt_standard_target); - list_append(&ipt_target, &ipt_error_target); - list_append(&ipt_match, &tcp_matchstruct); - list_append(&ipt_match, &udp_matchstruct); - list_append(&ipt_match, &icmp_matchstruct); - up(&ipt_mutex); + xt_register_target(AF_INET, &ipt_standard_target); + xt_register_target(AF_INET, &ipt_error_target); + xt_register_match(AF_INET, &icmp_matchstruct); /* Register setsockopt */ ret = nf_register_sockopt(&ipt_sockopts); @@ -1987,49 +1361,23 @@ static int __init init(void) return ret; } -#ifdef CONFIG_PROC_FS - { - struct proc_dir_entry *proc; - int i; - - for (i = 0; ipt_proc_entry[i].name; i++) { - proc = proc_net_create(ipt_proc_entry[i].name, 0, - ipt_proc_entry[i].get_info); - if (!proc) { - while (--i >= 0) - proc_net_remove(ipt_proc_entry[i].name); - nf_unregister_sockopt(&ipt_sockopts); - return -ENOMEM; - } - proc->owner = THIS_MODULE; - } - } -#endif - - printk("ip_tables: (C) 2000-2002 Netfilter core team\n"); + printk("ip_tables: (C) 2000-2006 Netfilter Core Team\n"); return 0; } static void __exit fini(void) { nf_unregister_sockopt(&ipt_sockopts); -#ifdef CONFIG_PROC_FS - { - int i; - for (i = 0; ipt_proc_entry[i].name; i++) - proc_net_remove(ipt_proc_entry[i].name); - } -#endif + + xt_unregister_match(AF_INET, &icmp_matchstruct); + xt_unregister_target(AF_INET, &ipt_error_target); + xt_unregister_target(AF_INET, &ipt_standard_target); + + xt_proto_fini(AF_INET); } EXPORT_SYMBOL(ipt_register_table); EXPORT_SYMBOL(ipt_unregister_table); -EXPORT_SYMBOL(ipt_register_match); -EXPORT_SYMBOL(ipt_unregister_match); EXPORT_SYMBOL(ipt_do_table); -EXPORT_SYMBOL(ipt_register_target); -EXPORT_SYMBOL(ipt_unregister_target); -EXPORT_SYMBOL(ipt_find_target); - module_init(init); module_exit(fini); diff --git a/net/ipv4/netfilter/ipt_CLUSTERIP.c b/net/ipv4/netfilter/ipt_CLUSTERIP.c index 45c52d8f4d9..d9bc971f03a 100644 --- a/net/ipv4/netfilter/ipt_CLUSTERIP.c +++ b/net/ipv4/netfilter/ipt_CLUSTERIP.c @@ -379,12 +379,13 @@ target(struct sk_buff **pskb, static int checkentry(const char *tablename, - const struct ipt_entry *e, + const void *e_void, void *targinfo, unsigned int targinfosize, unsigned int hook_mask) { struct ipt_clusterip_tgt_info *cipinfo = targinfo; + const struct ipt_entry *e = e_void; struct clusterip_config *config; diff --git a/net/ipv4/netfilter/ipt_DSCP.c b/net/ipv4/netfilter/ipt_DSCP.c index 6e319570a28..898cdf79ce1 100644 --- a/net/ipv4/netfilter/ipt_DSCP.c +++ b/net/ipv4/netfilter/ipt_DSCP.c @@ -57,7 +57,7 @@ target(struct sk_buff **pskb, static int checkentry(const char *tablename, - const struct ipt_entry *e, + const void *e_void, void *targinfo, unsigned int targinfosize, unsigned int hook_mask) diff --git a/net/ipv4/netfilter/ipt_ECN.c b/net/ipv4/netfilter/ipt_ECN.c index a1319693f64..706445426a6 100644 --- a/net/ipv4/netfilter/ipt_ECN.c +++ b/net/ipv4/netfilter/ipt_ECN.c @@ -113,12 +113,13 @@ target(struct sk_buff **pskb, static int checkentry(const char *tablename, - const struct ipt_entry *e, + const void *e_void, void *targinfo, unsigned int targinfosize, unsigned int hook_mask) { const struct ipt_ECN_info *einfo = (struct ipt_ECN_info *)targinfo; + const struct ipt_entry *e = e_void; if (targinfosize != IPT_ALIGN(sizeof(struct ipt_ECN_info))) { printk(KERN_WARNING "ECN: targinfosize %u != %Zu\n", diff --git a/net/ipv4/netfilter/ipt_LOG.c b/net/ipv4/netfilter/ipt_LOG.c index 30be0f1dae3..6606ddb66a2 100644 --- a/net/ipv4/netfilter/ipt_LOG.c +++ b/net/ipv4/netfilter/ipt_LOG.c @@ -431,7 +431,7 @@ ipt_log_target(struct sk_buff **pskb, } static int ipt_log_checkentry(const char *tablename, - const struct ipt_entry *e, + const void *e, void *targinfo, unsigned int targinfosize, unsigned int hook_mask) diff --git a/net/ipv4/netfilter/ipt_MASQUERADE.c b/net/ipv4/netfilter/ipt_MASQUERADE.c index 27860510ca6..12c56d3343c 100644 --- a/net/ipv4/netfilter/ipt_MASQUERADE.c +++ b/net/ipv4/netfilter/ipt_MASQUERADE.c @@ -40,7 +40,7 @@ static DEFINE_RWLOCK(masq_lock); /* FIXME: Multiple targets. --RR */ static int masquerade_check(const char *tablename, - const struct ipt_entry *e, + const void *e, void *targinfo, unsigned int targinfosize, unsigned int hook_mask) diff --git a/net/ipv4/netfilter/ipt_NETMAP.c b/net/ipv4/netfilter/ipt_NETMAP.c index e6e7b609536..b074467fe67 100644 --- a/net/ipv4/netfilter/ipt_NETMAP.c +++ b/net/ipv4/netfilter/ipt_NETMAP.c @@ -31,7 +31,7 @@ MODULE_DESCRIPTION("iptables 1:1 NAT mapping of IP networks target"); static int check(const char *tablename, - const struct ipt_entry *e, + const void *e, void *targinfo, unsigned int targinfosize, unsigned int hook_mask) diff --git a/net/ipv4/netfilter/ipt_NFQUEUE.c b/net/ipv4/netfilter/ipt_NFQUEUE.c deleted file mode 100644 index 3cedc9be880..00000000000 --- a/net/ipv4/netfilter/ipt_NFQUEUE.c +++ /dev/null @@ -1,70 +0,0 @@ -/* iptables module for using new netfilter netlink queue - * - * (C) 2005 by Harald Welte <laforge@netfilter.org> - * - * This program is free software; you can redistribute it and/or modify - * it under the terms of the GNU General Public License version 2 as - * published by the Free Software Foundation. - * - */ - -#include <linux/module.h> -#include <linux/skbuff.h> - -#include <linux/netfilter.h> -#include <linux/netfilter_ipv4/ip_tables.h> -#include <linux/netfilter_ipv4/ipt_NFQUEUE.h> - -MODULE_AUTHOR("Harald Welte <laforge@netfilter.org>"); -MODULE_DESCRIPTION("iptables NFQUEUE target"); -MODULE_LICENSE("GPL"); - -static unsigned int -target(struct sk_buff **pskb, - const struct net_device *in, - const struct net_device *out, - unsigned int hooknum, - const void *targinfo, - void *userinfo) -{ - const struct ipt_NFQ_info *tinfo = targinfo; - - return NF_QUEUE_NR(tinfo->queuenum); -} - -static int -checkentry(const char *tablename, - const struct ipt_entry *e, - void *targinfo, - unsigned int targinfosize, - unsigned int hook_mask) -{ - if (targinfosize != IPT_ALIGN(sizeof(struct ipt_NFQ_info))) { - printk(KERN_WARNING "NFQUEUE: targinfosize %u != %Zu\n", - targinfosize, - IPT_ALIGN(sizeof(struct ipt_NFQ_info))); - return 0; - } - - return 1; -} - -static struct ipt_target ipt_NFQ_reg = { - .name = "NFQUEUE", - .target = target, - .checkentry = checkentry, - .me = THIS_MODULE, -}; - -static int __init init(void) -{ - return ipt_register_target(&ipt_NFQ_reg); -} - -static void __exit fini(void) -{ - ipt_unregister_target(&ipt_NFQ_reg); -} - -module_init(init); -module_exit(fini); diff --git a/net/ipv4/netfilter/ipt_REDIRECT.c b/net/ipv4/netfilter/ipt_REDIRECT.c index 5245bfd33d5..140be51f2f0 100644 --- a/net/ipv4/netfilter/ipt_REDIRECT.c +++ b/net/ipv4/netfilter/ipt_REDIRECT.c @@ -33,7 +33,7 @@ MODULE_DESCRIPTION("iptables REDIRECT target module"); /* FIXME: Take multiple ranges --RR */ static int redirect_check(const char *tablename, - const struct ipt_entry *e, + const void *e, void *targinfo, unsigned int targinfosize, unsigned int hook_mask) diff --git a/net/ipv4/netfilter/ipt_REJECT.c b/net/ipv4/netfilter/ipt_REJECT.c index 6693526ae12..3eb47aae78c 100644 --- a/net/ipv4/netfilter/ipt_REJECT.c +++ b/net/ipv4/netfilter/ipt_REJECT.c @@ -282,12 +282,13 @@ static unsigned int reject(struct sk_buff **pskb, } static int check(const char *tablename, - const struct ipt_entry *e, + const void *e_void, void *targinfo, unsigned int targinfosize, unsigned int hook_mask) { const struct ipt_reject_info *rejinfo = targinfo; + const struct ipt_entry *e = e_void; if (targinfosize != IPT_ALIGN(sizeof(struct ipt_reject_info))) { DEBUGP("REJECT: targinfosize %u != 0\n", targinfosize); diff --git a/net/ipv4/netfilter/ipt_SAME.c b/net/ipv4/netfilter/ipt_SAME.c index 7a0536d864a..a22de59bba0 100644 --- a/net/ipv4/netfilter/ipt_SAME.c +++ b/net/ipv4/netfilter/ipt_SAME.c @@ -49,7 +49,7 @@ MODULE_DESCRIPTION("iptables special SNAT module for consistent sourceip"); static int same_check(const char *tablename, - const struct ipt_entry *e, + const void *e, void *targinfo, unsigned int targinfosize, unsigned int hook_mask) diff --git a/net/ipv4/netfilter/ipt_TCPMSS.c b/net/ipv4/netfilter/ipt_TCPMSS.c index 8db70d6908c..c122841e182 100644 --- a/net/ipv4/netfilter/ipt_TCPMSS.c +++ b/net/ipv4/netfilter/ipt_TCPMSS.c @@ -210,12 +210,13 @@ static inline int find_syn_match(const struct ipt_entry_match *m) /* Must specify -p tcp --syn/--tcp-flags SYN */ static int ipt_tcpmss_checkentry(const char *tablename, - const struct ipt_entry *e, + const void *e_void, void *targinfo, unsigned int targinfosize, unsigned int hook_mask) { const struct ipt_tcpmss_info *tcpmssinfo = targinfo; + const struct ipt_entry *e = e_void; if (targinfosize != IPT_ALIGN(sizeof(struct ipt_tcpmss_info))) { DEBUGP("ipt_tcpmss_checkentry: targinfosize %u != %u\n", diff --git a/net/ipv4/netfilter/ipt_TOS.c b/net/ipv4/netfilter/ipt_TOS.c index deadb36d442..3a44a56db23 100644 --- a/net/ipv4/netfilter/ipt_TOS.c +++ b/net/ipv4/netfilter/ipt_TOS.c @@ -52,7 +52,7 @@ target(struct sk_buff **pskb, static int checkentry(const char *tablename, - const struct ipt_entry *e, + const void *e_void, void *targinfo, unsigned int targinfosize, unsigned int hook_mask) diff --git a/net/ipv4/netfilter/ipt_TTL.c b/net/ipv4/netfilter/ipt_TTL.c index b9ae6a9382f..b769eb23197 100644 --- a/net/ipv4/netfilter/ipt_TTL.c +++ b/net/ipv4/netfilter/ipt_TTL.c @@ -66,7 +66,7 @@ ipt_ttl_target(struct sk_buff **pskb, const struct net_device *in, } static int ipt_ttl_checkentry(const char *tablename, - const struct ipt_entry *e, + const void *e, void *targinfo, unsigned int targinfosize, unsigned int hook_mask) diff --git a/net/ipv4/netfilter/ipt_ULOG.c b/net/ipv4/netfilter/ipt_ULOG.c index 38641cd0612..641dbc47765 100644 --- a/net/ipv4/netfilter/ipt_ULOG.c +++ b/net/ipv4/netfilter/ipt_ULOG.c @@ -330,7 +330,7 @@ static void ipt_logfn(unsigned int pf, } static int ipt_ulog_checkentry(const char *tablename, - const struct ipt_entry *e, + const void *e, void *targinfo, unsigned int targinfosize, unsigned int hookmask) diff --git a/net/ipv4/netfilter/ipt_addrtype.c b/net/ipv4/netfilter/ipt_addrtype.c index e19c2a52d00..d6b83a97651 100644 --- a/net/ipv4/netfilter/ipt_addrtype.c +++ b/net/ipv4/netfilter/ipt_addrtype.c @@ -29,7 +29,7 @@ static inline int match_type(u_int32_t addr, u_int16_t mask) static int match(const struct sk_buff *skb, const struct net_device *in, const struct net_device *out, const void *matchinfo, - int offset, int *hotdrop) + int offset, unsigned int protoff, int *hotdrop) { const struct ipt_addrtype_info *info = matchinfo; const struct iphdr *iph = skb->nh.iph; @@ -43,7 +43,7 @@ static int match(const struct sk_buff *skb, const struct net_device *in, return ret; } -static int checkentry(const char *tablename, const struct ipt_ip *ip, +static int checkentry(const char *tablename, const void *ip, void *matchinfo, unsigned int matchsize, unsigned int hook_mask) { diff --git a/net/ipv4/netfilter/ipt_ah.c b/net/ipv4/netfilter/ipt_ah.c index a0fea847cb7..144adfec13c 100644 --- a/net/ipv4/netfilter/ipt_ah.c +++ b/net/ipv4/netfilter/ipt_ah.c @@ -41,6 +41,7 @@ match(const struct sk_buff *skb, const struct net_device *out, const void *matchinfo, int offset, + unsigned int protoff, int *hotdrop) { struct ip_auth_hdr _ahdr, *ah; @@ -50,7 +51,7 @@ match(const struct sk_buff *skb, if (offset) return 0; - ah = skb_header_pointer(skb, skb->nh.iph->ihl * 4, + ah = skb_header_pointer(skb, protoff, sizeof(_ahdr), &_ahdr); if (ah == NULL) { /* We've been asked to examine this packet, and we @@ -69,12 +70,13 @@ match(const struct sk_buff *skb, /* Called when user tries to insert an entry of this type. */ static int checkentry(const char *tablename, - const struct ipt_ip *ip, + const void *ip_void, void *matchinfo, unsigned int matchinfosize, unsigned int hook_mask) { const struct ipt_ah *ahinfo = matchinfo; + const struct ipt_ip *ip = ip_void; /* Must specify proto == AH, and no unknown invflags */ if (ip->proto != IPPROTO_AH || (ip->invflags & IPT_INV_PROTO)) { diff --git a/net/ipv4/netfilter/ipt_dscp.c b/net/ipv4/netfilter/ipt_dscp.c index 5df52a64a5d..92063b4f860 100644 --- a/net/ipv4/netfilter/ipt_dscp.c +++ b/net/ipv4/netfilter/ipt_dscp.c @@ -21,7 +21,7 @@ MODULE_LICENSE("GPL"); static int match(const struct sk_buff *skb, const struct net_device *in, const struct net_device *out, const void *matchinfo, - int offset, int *hotdrop) + int offset, unsigned int protoff, int *hotdrop) { const struct ipt_dscp_info *info = matchinfo; const struct iphdr *iph = skb->nh.iph; @@ -31,7 +31,7 @@ static int match(const struct sk_buff *skb, const struct net_device *in, return ((iph->tos&IPT_DSCP_MASK) == sh_dscp) ^ info->invert; } -static int checkentry(const char *tablename, const struct ipt_ip *ip, +static int checkentry(const char *tablename, const void *ip, void *matchinfo, unsigned int matchsize, unsigned int hook_mask) { diff --git a/net/ipv4/netfilter/ipt_ecn.c b/net/ipv4/netfilter/ipt_ecn.c index b6f7181e89c..e68b0c7981f 100644 --- a/net/ipv4/netfilter/ipt_ecn.c +++ b/net/ipv4/netfilter/ipt_ecn.c @@ -67,7 +67,7 @@ static inline int match_tcp(const struct sk_buff *skb, static int match(const struct sk_buff *skb, const struct net_device *in, const struct net_device *out, const void *matchinfo, - int offset, int *hotdrop) + int offset, unsigned int protoff, int *hotdrop) { const struct ipt_ecn_info *info = matchinfo; @@ -85,11 +85,12 @@ static int match(const struct sk_buff *skb, const struct net_device *in, return 1; } -static int checkentry(const char *tablename, const struct ipt_ip *ip, +static int checkentry(const char *tablename, const void *ip_void, void *matchinfo, unsigned int matchsize, unsigned int hook_mask) { const struct ipt_ecn_info *info = matchinfo; + const struct ipt_ip *ip = ip_void; if (matchsize != IPT_ALIGN(sizeof(struct ipt_ecn_info))) return 0; diff --git a/net/ipv4/netfilter/ipt_esp.c b/net/ipv4/netfilter/ipt_esp.c index e1d0dd31e11..9de191a8162 100644 --- a/net/ipv4/netfilter/ipt_esp.c +++ b/net/ipv4/netfilter/ipt_esp.c @@ -42,6 +42,7 @@ match(const struct sk_buff *skb, const struct net_device *out, const void *matchinfo, int offset, + unsigned int protoff, int *hotdrop) { struct ip_esp_hdr _esp, *eh; @@ -51,7 +52,7 @@ match(const struct sk_buff *skb, if (offset) return 0; - eh = skb_header_pointer(skb, skb->nh.iph->ihl * 4, + eh = skb_header_pointer(skb, protoff, sizeof(_esp), &_esp); if (eh == NULL) { /* We've been asked to examine this packet, and we @@ -70,12 +71,13 @@ match(const struct sk_buff *skb, /* Called when user tries to insert an entry of this type. */ static int checkentry(const char *tablename, - const struct ipt_ip *ip, + const void *ip_void, void *matchinfo, unsigned int matchinfosize, unsigned int hook_mask) { const struct ipt_esp *espinfo = matchinfo; + const struct ipt_ip *ip = ip_void; /* Must specify proto == ESP, and no unknown invflags */ if (ip->proto != IPPROTO_ESP || (ip->invflags & IPT_INV_PROTO)) { diff --git a/net/ipv4/netfilter/ipt_hashlimit.c b/net/ipv4/netfilter/ipt_hashlimit.c index 2dd1cccbdab..4fe48c1bd5f 100644 --- a/net/ipv4/netfilter/ipt_hashlimit.c +++ b/net/ipv4/netfilter/ipt_hashlimit.c @@ -429,6 +429,7 @@ hashlimit_match(const struct sk_buff *skb, const struct net_device *out, const void *matchinfo, int offset, + unsigned int protoff, int *hotdrop) { struct ipt_hashlimit_info *r = @@ -504,7 +505,7 @@ hashlimit_match(const struct sk_buff *skb, static int hashlimit_checkentry(const char *tablename, - const struct ipt_ip *ip, + const void *inf, void *matchinfo, unsigned int matchsize, unsigned int hook_mask) diff --git a/net/ipv4/netfilter/ipt_iprange.c b/net/ipv4/netfilter/ipt_iprange.c index b835b7b2e56..13fb16fb789 100644 --- a/net/ipv4/netfilter/ipt_iprange.c +++ b/net/ipv4/netfilter/ipt_iprange.c @@ -28,7 +28,7 @@ match(const struct sk_buff *skb, const struct net_device *in, const struct net_device *out, const void *matchinfo, - int offset, int *hotdrop) + int offset, unsigned int protoff, int *hotdrop) { const struct ipt_iprange_info *info = matchinfo; const struct iphdr *iph = skb->nh.iph; @@ -63,7 +63,7 @@ match(const struct sk_buff *skb, } static int check(const char *tablename, - const struct ipt_ip *ip, + const void *inf, void *matchinfo, unsigned int matchsize, unsigned int hook_mask) diff --git a/net/ipv4/netfilter/ipt_length.c b/net/ipv4/netfilter/ipt_length.c deleted file mode 100644 index 4eabcfbda9d..00000000000 --- a/net/ipv4/netfilter/ipt_length.c +++ /dev/null @@ -1,64 +0,0 @@ -/* Kernel module to match packet length. */ -/* (C) 1999-2001 James Morris <jmorros@intercode.com.au> - * - * This program is free software; you can redistribute it and/or modify - * it under the terms of the GNU General Public License version 2 as - * published by the Free Software Foundation. - */ - -#include <linux/module.h> -#include <linux/skbuff.h> - -#include <linux/netfilter_ipv4/ipt_length.h> -#include <linux/netfilter_ipv4/ip_tables.h> - -MODULE_AUTHOR("James Morris <jmorris@intercode.com.au>"); -MODULE_DESCRIPTION("IP tables packet length matching module"); -MODULE_LICENSE("GPL"); - -static int -match(const struct sk_buff *skb, - const struct net_device *in, - const struct net_device *out, - const void *matchinfo, - int offset, - int *hotdrop) -{ - const struct ipt_length_info *info = matchinfo; - u_int16_t pktlen = ntohs(skb->nh.iph->tot_len); - - return (pktlen >= info->min && pktlen <= info->max) ^ info->invert; -} - -static int -checkentry(const char *tablename, - const struct ipt_ip *ip, - void *matchinfo, - unsigned int matchsize, - unsigned int hook_mask) -{ - if (matchsize != IPT_ALIGN(sizeof(struct ipt_length_info))) - return 0; - - return 1; -} - -static struct ipt_match length_match = { - .name = "length", - .match = &match, - .checkentry = &checkentry, - .me = THIS_MODULE, -}; - -static int __init init(void) -{ - return ipt_register_match(&length_match); -} - -static void __exit fini(void) -{ - ipt_unregister_match(&length_match); -} - -module_init(init); -module_exit(fini); diff --git a/net/ipv4/netfilter/ipt_multiport.c b/net/ipv4/netfilter/ipt_multiport.c index 99e8188162e..2d52326553f 100644 --- a/net/ipv4/netfilter/ipt_multiport.c +++ b/net/ipv4/netfilter/ipt_multiport.c @@ -97,6 +97,7 @@ match(const struct sk_buff *skb, const struct net_device *out, const void *matchinfo, int offset, + unsigned int protoff, int *hotdrop) { u16 _ports[2], *pptr; @@ -105,7 +106,7 @@ match(const struct sk_buff *skb, if (offset) return 0; - pptr = skb_header_pointer(skb, skb->nh.iph->ihl * 4, + pptr = skb_header_pointer(skb, protoff, sizeof(_ports), _ports); if (pptr == NULL) { /* We've been asked to examine this packet, and we @@ -128,6 +129,7 @@ match_v1(const struct sk_buff *skb, const struct net_device *out, const void *matchinfo, int offset, + unsigned int protoff, int *hotdrop) { u16 _ports[2], *pptr; @@ -136,7 +138,7 @@ match_v1(const struct sk_buff *skb, if (offset) return 0; - pptr = skb_header_pointer(skb, skb->nh.iph->ihl * 4, + pptr = skb_header_pointer(skb, protoff, sizeof(_ports), _ports); if (pptr == NULL) { /* We've been asked to examine this packet, and we @@ -154,7 +156,7 @@ match_v1(const struct sk_buff *skb, /* Called when user tries to insert an entry of this type. */ static int checkentry(const char *tablename, - const struct ipt_ip *ip, + const void *ip, void *matchinfo, unsigned int matchsize, unsigned int hook_mask) @@ -164,7 +166,7 @@ checkentry(const char *tablename, static int checkentry_v1(const char *tablename, - const struct ipt_ip *ip, + const void *ip, void *matchinfo, unsigned int matchsize, unsigned int hook_mask) diff --git a/net/ipv4/netfilter/ipt_owner.c b/net/ipv4/netfilter/ipt_owner.c index 0cee2862ed8..4843d0c9734 100644 --- a/net/ipv4/netfilter/ipt_owner.c +++ b/net/ipv4/netfilter/ipt_owner.c @@ -27,6 +27,7 @@ match(const struct sk_buff *skb, const struct net_device *out, const void *matchinfo, int offset, + unsigned int protoff, int *hotdrop) { const struct ipt_owner_info *info = matchinfo; @@ -51,7 +52,7 @@ match(const struct sk_buff *skb, static int checkentry(const char *tablename, - const struct ipt_ip *ip, + const void *ip, void *matchinfo, unsigned int matchsize, unsigned int hook_mask) diff --git a/net/ipv4/netfilter/ipt_physdev.c b/net/ipv4/netfilter/ipt_physdev.c deleted file mode 100644 index 03f554857a4..00000000000 --- a/net/ipv4/netfilter/ipt_physdev.c +++ /dev/null @@ -1,135 +0,0 @@ -/* Kernel module to match the bridge port in and - * out device for IP packets coming into contact with a bridge. */ - -/* (C) 2001-2003 Bart De Schuymer <bdschuym@pandora.be> - * - * This program is free software; you can redistribute it and/or modify - * it under the terms of the GNU General Public License version 2 as - * published by the Free Software Foundation. - */ - -#include <linux/module.h> -#include <linux/netdevice.h> -#include <linux/skbuff.h> -#include <linux/netfilter_ipv4/ipt_physdev.h> -#include <linux/netfilter_ipv4/ip_tables.h> -#include <linux/netfilter_bridge.h> -#define MATCH 1 -#define NOMATCH 0 - -MODULE_LICENSE("GPL"); -MODULE_AUTHOR("Bart De Schuymer <bdschuym@pandora.be>"); -MODULE_DESCRIPTION("iptables bridge physical device match module"); - -static int -match(const struct sk_buff *skb, - const struct net_device *in, - const struct net_device *out, - const void *matchinfo, - int offset, - int *hotdrop) -{ - int i; - static const char nulldevname[IFNAMSIZ]; - const struct ipt_physdev_info *info = matchinfo; - unsigned int ret; - const char *indev, *outdev; - struct nf_bridge_info *nf_bridge; - - /* Not a bridged IP packet or no info available yet: - * LOCAL_OUT/mangle and LOCAL_OUT/nat don't know if - * the destination device will be a bridge. */ - if (!(nf_bridge = skb->nf_bridge)) { - /* Return MATCH if the invert flags of the used options are on */ - if ((info->bitmask & IPT_PHYSDEV_OP_BRIDGED) && - !(info->invert & IPT_PHYSDEV_OP_BRIDGED)) - return NOMATCH; - if ((info->bitmask & IPT_PHYSDEV_OP_ISIN) && - !(info->invert & IPT_PHYSDEV_OP_ISIN)) - return NOMATCH; - if ((info->bitmask & IPT_PHYSDEV_OP_ISOUT) && - !(info->invert & IPT_PHYSDEV_OP_ISOUT)) - return NOMATCH; - if ((info->bitmask & IPT_PHYSDEV_OP_IN) && - !(info->invert & IPT_PHYSDEV_OP_IN)) - return NOMATCH; - if ((info->bitmask & IPT_PHYSDEV_OP_OUT) && - !(info->invert & IPT_PHYSDEV_OP_OUT)) - return NOMATCH; - return MATCH; - } - - /* This only makes sense in the FORWARD and POSTROUTING chains */ - if ((info->bitmask & IPT_PHYSDEV_OP_BRIDGED) && - (!!(nf_bridge->mask & BRNF_BRIDGED) ^ - !(info->invert & IPT_PHYSDEV_OP_BRIDGED))) - return NOMATCH; - - if ((info->bitmask & IPT_PHYSDEV_OP_ISIN && - (!nf_bridge->physindev ^ !!(info->invert & IPT_PHYSDEV_OP_ISIN))) || - (info->bitmask & IPT_PHYSDEV_OP_ISOUT && - (!nf_bridge->physoutdev ^ !!(info->invert & IPT_PHYSDEV_OP_ISOUT)))) - return NOMATCH; - - if (!(info->bitmask & IPT_PHYSDEV_OP_IN)) - goto match_outdev; - indev = nf_bridge->physindev ? nf_bridge->physindev->name : nulldevname; - for (i = 0, ret = 0; i < IFNAMSIZ/sizeof(unsigned int); i++) { - ret |= (((const unsigned int *)indev)[i] - ^ ((const unsigned int *)info->physindev)[i]) - & ((const unsigned int *)info->in_mask)[i]; - } - - if ((ret == 0) ^ !(info->invert & IPT_PHYSDEV_OP_IN)) - return NOMATCH; - -match_outdev: - if (!(info->bitmask & IPT_PHYSDEV_OP_OUT)) - return MATCH; - outdev = nf_bridge->physoutdev ? - nf_bridge->physoutdev->name : nulldevname; - for (i = 0, ret = 0; i < IFNAMSIZ/sizeof(unsigned int); i++) { - ret |= (((const unsigned int *)outdev)[i] - ^ ((const unsigned int *)info->physoutdev)[i]) - & ((const unsigned int *)info->out_mask)[i]; - } - - return (ret != 0) ^ !(info->invert & IPT_PHYSDEV_OP_OUT); -} - -static int -checkentry(const char *tablename, - const struct ipt_ip *ip, - void *matchinfo, - unsigned int matchsize, - unsigned int hook_mask) -{ - const struct ipt_physdev_info *info = matchinfo; - - if (matchsize != IPT_ALIGN(sizeof(struct ipt_physdev_info))) - return 0; - if (!(info->bitmask & IPT_PHYSDEV_OP_MASK) || - info->bitmask & ~IPT_PHYSDEV_OP_MASK) - return 0; - return 1; -} - -static struct ipt_match physdev_match = { - .name = "physdev", - .match = &match, - .checkentry = &checkentry, - .me = THIS_MODULE, -}; - -static int __init init(void) -{ - return ipt_register_match(&physdev_match); -} - -static void __exit fini(void) -{ - ipt_unregister_match(&physdev_match); -} - -module_init(init); -module_exit(fini); diff --git a/net/ipv4/netfilter/ipt_recent.c b/net/ipv4/netfilter/ipt_recent.c index 5ddccb18c65..44611d6d14f 100644 --- a/net/ipv4/netfilter/ipt_recent.c +++ b/net/ipv4/netfilter/ipt_recent.c @@ -104,6 +104,7 @@ match(const struct sk_buff *skb, const struct net_device *out, const void *matchinfo, int offset, + unsigned int protoff, int *hotdrop); /* Function to hash a given address into the hash table of table_size size */ @@ -317,7 +318,7 @@ static int ip_recent_ctrl(struct file *file, const char __user *input, unsigned skb->nh.iph->daddr = 0; /* Clear ttl since we have no way of knowing it */ skb->nh.iph->ttl = 0; - match(skb,NULL,NULL,info,0,NULL); + match(skb,NULL,NULL,info,0,0,NULL); kfree(skb->nh.iph); out_free_skb: @@ -357,6 +358,7 @@ match(const struct sk_buff *skb, const struct net_device *out, const void *matchinfo, int offset, + unsigned int protoff, int *hotdrop) { int pkt_count, hits_found, ans; @@ -654,7 +656,7 @@ match(const struct sk_buff *skb, */ static int checkentry(const char *tablename, - const struct ipt_ip *ip, + const void *ip, void *matchinfo, unsigned int matchsize, unsigned int hook_mask) diff --git a/net/ipv4/netfilter/ipt_tos.c b/net/ipv4/netfilter/ipt_tos.c index 086a1bb61e3..9ab765e126f 100644 --- a/net/ipv4/netfilter/ipt_tos.c +++ b/net/ipv4/netfilter/ipt_tos.c @@ -23,6 +23,7 @@ match(const struct sk_buff *skb, const struct net_device *out, const void *matchinfo, int offset, + unsigned int protoff, int *hotdrop) { const struct ipt_tos_info *info = matchinfo; @@ -32,7 +33,7 @@ match(const struct sk_buff *skb, static int checkentry(const char *tablename, - const struct ipt_ip *ip, + const void *ip, void *matchinfo, unsigned int matchsize, unsigned int hook_mask) diff --git a/net/ipv4/netfilter/ipt_ttl.c b/net/ipv4/netfilter/ipt_ttl.c index 219aa9de88c..82da53f430a 100644 --- a/net/ipv4/netfilter/ipt_ttl.c +++ b/net/ipv4/netfilter/ipt_ttl.c @@ -21,7 +21,7 @@ MODULE_LICENSE("GPL"); static int match(const struct sk_buff *skb, const struct net_device *in, const struct net_device *out, const void *matchinfo, - int offset, int *hotdrop) + int offset, unsigned int protoff, int *hotdrop) { const struct ipt_ttl_info *info = matchinfo; @@ -47,7 +47,7 @@ static int match(const struct sk_buff *skb, const struct net_device *in, return 0; } -static int checkentry(const char *tablename, const struct ipt_ip *ip, +static int checkentry(const char *tablename, const void *ip, void *matchinfo, unsigned int matchsize, unsigned int hook_mask) { diff --git a/net/ipv4/netfilter/iptable_filter.c b/net/ipv4/netfilter/iptable_filter.c index 260a4f0a2a9..212a3079085 100644 --- a/net/ipv4/netfilter/iptable_filter.c +++ b/net/ipv4/netfilter/iptable_filter.c @@ -78,7 +78,8 @@ static struct ipt_table packet_filter = { .name = "filter", .valid_hooks = FILTER_VALID_HOOKS, .lock = RW_LOCK_UNLOCKED, - .me = THIS_MODULE + .me = THIS_MODULE, + .af = AF_INET, }; /* The work comes in here from netfilter.c. */ diff --git a/net/ipv4/netfilter/iptable_mangle.c b/net/ipv4/netfilter/iptable_mangle.c index 160eb11b6e2..3212a5cc4b6 100644 --- a/net/ipv4/netfilter/iptable_mangle.c +++ b/net/ipv4/netfilter/iptable_mangle.c @@ -109,6 +109,7 @@ static struct ipt_table packet_mangler = { .valid_hooks = MANGLE_VALID_HOOKS, .lock = RW_LOCK_UNLOCKED, .me = THIS_MODULE, + .af = AF_INET, }; /* The work comes in here from netfilter.c. */ diff --git a/net/ipv4/netfilter/iptable_raw.c b/net/ipv4/netfilter/iptable_raw.c index 47449ba83eb..fdb9e9c81e8 100644 --- a/net/ipv4/netfilter/iptable_raw.c +++ b/net/ipv4/netfilter/iptable_raw.c @@ -83,7 +83,8 @@ static struct ipt_table packet_raw = { .name = "raw", .valid_hooks = RAW_VALID_HOOKS, .lock = RW_LOCK_UNLOCKED, - .me = THIS_MODULE + .me = THIS_MODULE, + .af = AF_INET, }; /* The work comes in here from netfilter.c. */ diff --git a/net/ipv4/netfilter/nf_conntrack_l3proto_ipv4.c b/net/ipv4/netfilter/nf_conntrack_l3proto_ipv4.c index 0c56c52a383..167619f638c 100644 --- a/net/ipv4/netfilter/nf_conntrack_l3proto_ipv4.c +++ b/net/ipv4/netfilter/nf_conntrack_l3proto_ipv4.c @@ -575,7 +575,7 @@ MODULE_LICENSE("GPL"); static int __init init(void) { - need_nf_conntrack(); + need_conntrack(); return init_or_cleanup(1); } @@ -587,9 +587,4 @@ static void __exit fini(void) module_init(init); module_exit(fini); -void need_ip_conntrack(void) -{ -} - -EXPORT_SYMBOL(need_ip_conntrack); EXPORT_SYMBOL(nf_ct_ipv4_gather_frags); diff --git a/net/ipv4/xfrm4_state.c b/net/ipv4/xfrm4_state.c index d23e07fc81f..dbabf81a9b7 100644 --- a/net/ipv4/xfrm4_state.c +++ b/net/ipv4/xfrm4_state.c @@ -42,6 +42,21 @@ __xfrm4_init_tempsel(struct xfrm_state *x, struct flowi *fl, x->props.saddr = tmpl->saddr; if (x->props.saddr.a4 == 0) x->props.saddr.a4 = saddr->a4; + if (tmpl->mode && x->props.saddr.a4 == 0) { + struct rtable *rt; + struct flowi fl_tunnel = { + .nl_u = { + .ip4_u = { + .daddr = x->id.daddr.a4, + } + } + }; + if (!xfrm_dst_lookup((struct xfrm_dst **)&rt, + &fl_tunnel, AF_INET)) { + x->props.saddr.a4 = rt->rt_src; + dst_release(&rt->u.dst); + } + } x->props.mode = tmpl->mode; x->props.reqid = tmpl->reqid; x->props.family = AF_INET; diff --git a/net/ipv6/addrconf.c b/net/ipv6/addrconf.c index 7129d423975..dfb4f145a13 100644 --- a/net/ipv6/addrconf.c +++ b/net/ipv6/addrconf.c @@ -2644,7 +2644,7 @@ static int if6_seq_show(struct seq_file *seq, void *v) { struct inet6_ifaddr *ifp = (struct inet6_ifaddr *)v; seq_printf(seq, - "%04x%04x%04x%04x%04x%04x%04x%04x %02x %02x %02x %02x %8s\n", + NIP6_FMT " %02x %02x %02x %02x %8s\n", NIP6(ifp->addr), ifp->idev->dev->ifindex, ifp->prefix_len, diff --git a/net/ipv6/ah6.c b/net/ipv6/ah6.c index 13cc7f89558..c7932cb420a 100644 --- a/net/ipv6/ah6.c +++ b/net/ipv6/ah6.c @@ -332,8 +332,7 @@ static void ah6_err(struct sk_buff *skb, struct inet6_skb_parm *opt, if (!x) return; - NETDEBUG(KERN_DEBUG "pmtu discovery on SA AH/%08x/" - "%04x:%04x:%04x:%04x:%04x:%04x:%04x:%04x\n", + NETDEBUG(KERN_DEBUG "pmtu discovery on SA AH/%08x/" NIP6_FMT "\n", ntohl(ah->spi), NIP6(iph->daddr)); xfrm_state_put(x); diff --git a/net/ipv6/anycast.c b/net/ipv6/anycast.c index 65e73ac0d6d..72bd08af2df 100644 --- a/net/ipv6/anycast.c +++ b/net/ipv6/anycast.c @@ -532,9 +532,7 @@ static int ac6_seq_show(struct seq_file *seq, void *v) struct ac6_iter_state *state = ac6_seq_private(seq); seq_printf(seq, - "%-4d %-15s " - "%04x%04x%04x%04x%04x%04x%04x%04x " - "%5d\n", + "%-4d %-15s " NIP6_FMT " %5d\n", state->dev->ifindex, state->dev->name, NIP6(im->aca_addr), im->aca_users); diff --git a/net/ipv6/esp6.c b/net/ipv6/esp6.c index 6de8ee1a5ad..7b5b94f1390 100644 --- a/net/ipv6/esp6.c +++ b/net/ipv6/esp6.c @@ -266,8 +266,7 @@ static void esp6_err(struct sk_buff *skb, struct inet6_skb_parm *opt, x = xfrm_state_lookup((xfrm_address_t *)&iph->daddr, esph->spi, IPPROTO_ESP, AF_INET6); if (!x) return; - printk(KERN_DEBUG "pmtu discovery on SA ESP/%08x/" - "%04x:%04x:%04x:%04x:%04x:%04x:%04x:%04x\n", + printk(KERN_DEBUG "pmtu discovery on SA ESP/%08x/" NIP6_FMT "\n", ntohl(esph->spi), NIP6(iph->daddr)); xfrm_state_put(x); } diff --git a/net/ipv6/icmp.c b/net/ipv6/icmp.c index 53c81fcd20b..fcf883183ce 100644 --- a/net/ipv6/icmp.c +++ b/net/ipv6/icmp.c @@ -607,7 +607,7 @@ static int icmpv6_rcv(struct sk_buff **pskb) skb->csum = ~csum_ipv6_magic(saddr, daddr, skb->len, IPPROTO_ICMPV6, 0); if (__skb_checksum_complete(skb)) { - LIMIT_NETDEBUG(KERN_DEBUG "ICMPv6 checksum failed [%04x:%04x:%04x:%04x:%04x:%04x:%04x:%04x > %04x:%04x:%04x:%04x:%04x:%04x:%04x:%04x]\n", + LIMIT_NETDEBUG(KERN_DEBUG "ICMPv6 checksum failed [" NIP6_FMT " > " NIP6_FMT "]\n", NIP6(*saddr), NIP6(*daddr)); goto discard_it; } diff --git a/net/ipv6/ip6_flowlabel.c b/net/ipv6/ip6_flowlabel.c index 964ad9d1276..4183c8dac7f 100644 --- a/net/ipv6/ip6_flowlabel.c +++ b/net/ipv6/ip6_flowlabel.c @@ -629,9 +629,7 @@ static void ip6fl_fl_seq_show(struct seq_file *seq, struct ip6_flowlabel *fl) { while(fl) { seq_printf(seq, - "%05X %-1d %-6d %-6d %-6ld %-8ld " - "%02x%02x%02x%02x%02x%02x%02x%02x " - "%-4d\n", + "%05X %-1d %-6d %-6d %-6ld %-8ld " NIP6_FMT " %-4d\n", (unsigned)ntohl(fl->label), fl->share, (unsigned)fl->owner, @@ -647,8 +645,8 @@ static void ip6fl_fl_seq_show(struct seq_file *seq, struct ip6_flowlabel *fl) static int ip6fl_seq_show(struct seq_file *seq, void *v) { if (v == SEQ_START_TOKEN) - seq_puts(seq, "Label S Owner Users Linger Expires " - "Dst Opt\n"); + seq_printf(seq, "%-5s %-1s %-6s %-6s %-6s %-8s %-39s %s\n", + "Label", "S", "Owner", "Users", "Linger", "Expires", "Dst", "Opt"); else ip6fl_fl_seq_show(seq, v); return 0; diff --git a/net/ipv6/ipcomp6.c b/net/ipv6/ipcomp6.c index 626dd39685f..d511a884dad 100644 --- a/net/ipv6/ipcomp6.c +++ b/net/ipv6/ipcomp6.c @@ -212,8 +212,7 @@ static void ipcomp6_err(struct sk_buff *skb, struct inet6_skb_parm *opt, if (!x) return; - printk(KERN_DEBUG "pmtu discovery on SA IPCOMP/%08x/" - "%04x:%04x:%04x:%04x:%04x:%04x:%04x:%04x\n", + printk(KERN_DEBUG "pmtu discovery on SA IPCOMP/%08x/" NIP6_FMT "\n", spi, NIP6(iph->daddr)); xfrm_state_put(x); } diff --git a/net/ipv6/mcast.c b/net/ipv6/mcast.c index cc3e9f56086..0e03eabfb9d 100644 --- a/net/ipv6/mcast.c +++ b/net/ipv6/mcast.c @@ -2373,7 +2373,7 @@ static int igmp6_mc_seq_show(struct seq_file *seq, void *v) struct igmp6_mc_iter_state *state = igmp6_mc_seq_private(seq); seq_printf(seq, - "%-4d %-15s %04x%04x%04x%04x%04x%04x%04x%04x %5d %08X %ld\n", + "%-4d %-15s " NIP6_FMT " %5d %08X %ld\n", state->dev->ifindex, state->dev->name, NIP6(im->mca_addr), im->mca_users, im->mca_flags, @@ -2542,15 +2542,12 @@ static int igmp6_mcf_seq_show(struct seq_file *seq, void *v) if (v == SEQ_START_TOKEN) { seq_printf(seq, "%3s %6s " - "%32s %32s %6s %6s\n", "Idx", + "%39s %39s %6s %6s\n", "Idx", "Device", "Multicast Address", "Source Address", "INC", "EXC"); } else { seq_printf(seq, - "%3d %6.6s " - "%04x%04x%04x%04x%04x%04x%04x%04x " - "%04x%04x%04x%04x%04x%04x%04x%04x " - "%6lu %6lu\n", + "%3d %6.6s " NIP6_FMT " " NIP6_FMT " %6lu %6lu\n", state->dev->ifindex, state->dev->name, NIP6(state->im->mca_addr), NIP6(psf->sf_addr), diff --git a/net/ipv6/ndisc.c b/net/ipv6/ndisc.c index 305d9ee6d7d..cb8856b1d95 100644 --- a/net/ipv6/ndisc.c +++ b/net/ipv6/ndisc.c @@ -692,7 +692,7 @@ static void ndisc_solicit(struct neighbour *neigh, struct sk_buff *skb) if (!(neigh->nud_state & NUD_VALID)) { ND_PRINTK1(KERN_DEBUG "%s(): trying to ucast probe in NUD_INVALID: " - "%04x:%04x:%04x:%04x:%04x:%04x:%04x:%04x\n", + NIP6_FMT "\n", __FUNCTION__, NIP6(*target)); } diff --git a/net/ipv6/netfilter/Kconfig b/net/ipv6/netfilter/Kconfig index 105dd69ee9f..2d6f8ecbc27 100644 --- a/net/ipv6/netfilter/Kconfig +++ b/net/ipv6/netfilter/Kconfig @@ -41,6 +41,7 @@ config IP6_NF_QUEUE config IP6_NF_IPTABLES tristate "IP6 tables support (required for filtering/masq/NAT)" + depends on NETFILTER_XTABLES help ip6tables is a general, extensible packet identification framework. Currently only the packet filtering and packet mangling subsystem @@ -50,25 +51,6 @@ config IP6_NF_IPTABLES To compile it as a module, choose M here. If unsure, say N. # The simple matches. -config IP6_NF_MATCH_LIMIT - tristate "limit match support" - depends on IP6_NF_IPTABLES - help - limit matching allows you to control the rate at which a rule can be - matched: mainly useful in combination with the LOG target ("LOG - target support", below) and to avoid some Denial of Service attacks. - - To compile it as a module, choose M here. If unsure, say N. - -config IP6_NF_MATCH_MAC - tristate "MAC address match support" - depends on IP6_NF_IPTABLES - help - mac matching allows you to match packets based on the source - Ethernet address of the packet. - - To compile it as a module, choose M here. If unsure, say N. - config IP6_NF_MATCH_RT tristate "Routing header match support" depends on IP6_NF_IPTABLES @@ -124,16 +106,6 @@ config IP6_NF_MATCH_OWNER To compile it as a module, choose M here. If unsure, say N. -config IP6_NF_MATCH_MARK - tristate "netfilter MARK match support" - depends on IP6_NF_IPTABLES - help - Netfilter mark matching allows you to match packets based on the - `nfmark' value in the packet. This can be set by the MARK target - (see below). - - To compile it as a module, choose M here. If unsure, say N. - config IP6_NF_MATCH_IPV6HEADER tristate "IPv6 Extension Headers Match" depends on IP6_NF_IPTABLES @@ -151,15 +123,6 @@ config IP6_NF_MATCH_AHESP To compile it as a module, choose M here. If unsure, say N. -config IP6_NF_MATCH_LENGTH - tristate "Packet Length match support" - depends on IP6_NF_IPTABLES - help - This option allows you to match the length of a packet against a - specific value or range of values. - - To compile it as a module, choose M here. If unsure, say N. - config IP6_NF_MATCH_EUI64 tristate "EUI64 address check" depends on IP6_NF_IPTABLES @@ -170,15 +133,6 @@ config IP6_NF_MATCH_EUI64 To compile it as a module, choose M here. If unsure, say N. -config IP6_NF_MATCH_PHYSDEV - tristate "Physdev match support" - depends on IP6_NF_IPTABLES && BRIDGE_NETFILTER - help - Physdev packet matching matches against the physical bridge ports - the IP packet arrived on or will leave by. - - To compile it as a module, choose M here. If unsure, say N. - config IP6_NF_MATCH_POLICY tristate "IPsec policy match support" depends on IP6_NF_IPTABLES && XFRM @@ -219,17 +173,6 @@ config IP6_NF_TARGET_REJECT To compile it as a module, choose M here. If unsure, say N. -config IP6_NF_TARGET_NFQUEUE - tristate "NFQUEUE Target Support" - depends on IP6_NF_IPTABLES - help - This Target replaced the old obsolete QUEUE target. - - As opposed to QUEUE, it supports 65535 different queues, - not just one. - - To compile it as a module, choose M here. If unsure, say N. - config IP6_NF_MANGLE tristate "Packet mangling" depends on IP6_NF_IPTABLES @@ -240,19 +183,6 @@ config IP6_NF_MANGLE To compile it as a module, choose M here. If unsure, say N. -config IP6_NF_TARGET_MARK - tristate "MARK target support" - depends on IP6_NF_MANGLE - help - This option adds a `MARK' target, which allows you to create rules - in the `mangle' table which alter the netfilter mark (nfmark) field - associated with the packet packet prior to routing. This can change - the routing method (see `Use netfilter MARK value as routing - key') and can also be used by other subsystems to change their - behavior. - - To compile it as a module, choose M here. If unsure, say N. - config IP6_NF_TARGET_HL tristate 'HL (hoplimit) target support' depends on IP6_NF_MANGLE diff --git a/net/ipv6/netfilter/Makefile b/net/ipv6/netfilter/Makefile index c0c809b426e..663b4749820 100644 --- a/net/ipv6/netfilter/Makefile +++ b/net/ipv6/netfilter/Makefile @@ -4,10 +4,7 @@ # Link order matters here. obj-$(CONFIG_IP6_NF_IPTABLES) += ip6_tables.o -obj-$(CONFIG_IP6_NF_MATCH_LIMIT) += ip6t_limit.o -obj-$(CONFIG_IP6_NF_MATCH_MARK) += ip6t_mark.o obj-$(CONFIG_IP6_NF_MATCH_LENGTH) += ip6t_length.o -obj-$(CONFIG_IP6_NF_MATCH_MAC) += ip6t_mac.o obj-$(CONFIG_IP6_NF_MATCH_RT) += ip6t_rt.o obj-$(CONFIG_IP6_NF_MATCH_OPTS) += ip6t_hbh.o ip6t_dst.o obj-$(CONFIG_IP6_NF_MATCH_IPV6HEADER) += ip6t_ipv6header.o @@ -17,12 +14,9 @@ obj-$(CONFIG_IP6_NF_MATCH_POLICY) += ip6t_policy.o obj-$(CONFIG_IP6_NF_MATCH_EUI64) += ip6t_eui64.o obj-$(CONFIG_IP6_NF_MATCH_MULTIPORT) += ip6t_multiport.o obj-$(CONFIG_IP6_NF_MATCH_OWNER) += ip6t_owner.o -obj-$(CONFIG_IP6_NF_MATCH_PHYSDEV) += ip6t_physdev.o obj-$(CONFIG_IP6_NF_FILTER) += ip6table_filter.o obj-$(CONFIG_IP6_NF_MANGLE) += ip6table_mangle.o -obj-$(CONFIG_IP6_NF_TARGET_MARK) += ip6t_MARK.o obj-$(CONFIG_IP6_NF_TARGET_HL) += ip6t_HL.o -obj-$(CONFIG_IP6_NF_TARGET_NFQUEUE) += ip6t_NFQUEUE.o obj-$(CONFIG_IP6_NF_QUEUE) += ip6_queue.o obj-$(CONFIG_IP6_NF_TARGET_LOG) += ip6t_LOG.o obj-$(CONFIG_IP6_NF_RAW) += ip6table_raw.o diff --git a/net/ipv6/netfilter/ip6_tables.c b/net/ipv6/netfilter/ip6_tables.c index 1390370186d..847068fd336 100644 --- a/net/ipv6/netfilter/ip6_tables.c +++ b/net/ipv6/netfilter/ip6_tables.c @@ -13,6 +13,9 @@ * a table * 06 Jun 2002 Andras Kis-Szabo <kisza@sch.bme.hu> * - new extension header parser code + * 15 Oct 2005 Harald Welte <laforge@netfilter.org> + * - Unification of {ip,ip6}_tables into x_tables + * - Removed tcp and udp code, since it's not ipv6 specific */ #include <linux/capability.h> @@ -23,8 +26,6 @@ #include <linux/vmalloc.h> #include <linux/netdevice.h> #include <linux/module.h> -#include <linux/tcp.h> -#include <linux/udp.h> #include <linux/icmpv6.h> #include <net/ipv6.h> #include <asm/uaccess.h> @@ -33,6 +34,7 @@ #include <linux/cpumask.h> #include <linux/netfilter_ipv6/ip6_tables.h> +#include <linux/netfilter/x_tables.h> MODULE_LICENSE("GPL"); MODULE_AUTHOR("Netfilter Core Team <coreteam@netfilter.org>"); @@ -67,13 +69,8 @@ do { \ #else #define IP_NF_ASSERT(x) #endif -#define SMP_ALIGN(x) (((x) + SMP_CACHE_BYTES-1) & ~(SMP_CACHE_BYTES-1)) -static DECLARE_MUTEX(ip6t_mutex); -/* Must have mutex */ -#define ASSERT_READ_LOCK(x) IP_NF_ASSERT(down_trylock(&ip6t_mutex) != 0) -#define ASSERT_WRITE_LOCK(x) IP_NF_ASSERT(down_trylock(&ip6t_mutex) != 0) #include <linux/netfilter_ipv4/listhelp.h> #if 0 @@ -91,30 +88,6 @@ static DECLARE_MUTEX(ip6t_mutex); Hence the start of any table is given by get_table() below. */ -/* The table itself */ -struct ip6t_table_info -{ - /* Size per table */ - unsigned int size; - /* Number of entries: FIXME. --RR */ - unsigned int number; - /* Initial number of entries. Needed for module usage count */ - unsigned int initial_entries; - - /* Entry points and underflows */ - unsigned int hook_entry[NF_IP6_NUMHOOKS]; - unsigned int underflow[NF_IP6_NUMHOOKS]; - - /* ip6t_entry tables: one per CPU */ - void *entries[NR_CPUS]; -}; - -static LIST_HEAD(ip6t_target); -static LIST_HEAD(ip6t_match); -static LIST_HEAD(ip6t_tables); -#define SET_COUNTER(c,b,p) do { (c).bcnt = (b); (c).pcnt = (p); } while(0) -#define ADD_COUNTER(c,b,p) do { (c).bcnt += (b); (c).pcnt += (p); } while(0) - #if 0 #define down(x) do { printk("DOWN:%u:" #x "\n", __LINE__); down(x); } while(0) #define down_interruptible(x) ({ int __r; printk("DOWNi:%u:" #x "\n", __LINE__); __r = down_interruptible(x); if (__r != 0) printk("ABORT-DOWNi:%u\n", __LINE__); __r; }) @@ -297,7 +270,7 @@ ip6t_do_table(struct sk_buff **pskb, unsigned int hook, const struct net_device *in, const struct net_device *out, - struct ip6t_table *table, + struct xt_table *table, void *userdata) { static const char nulldevname[IFNAMSIZ] __attribute__((aligned(sizeof(long)))); @@ -309,6 +282,7 @@ ip6t_do_table(struct sk_buff **pskb, const char *indev, *outdev; void *table_base; struct ip6t_entry *e, *back; + struct xt_table_info *private; /* Initialization */ indev = in ? in->name : nulldevname; @@ -321,9 +295,10 @@ ip6t_do_table(struct sk_buff **pskb, * match it. */ read_lock_bh(&table->lock); + private = table->private; IP_NF_ASSERT(table->valid_hooks & (1 << hook)); - table_base = (void *)table->private->entries[smp_processor_id()]; - e = get_entry(table_base, table->private->hook_entry[hook]); + table_base = (void *)private->entries[smp_processor_id()]; + e = get_entry(table_base, private->hook_entry[hook]); #ifdef CONFIG_NETFILTER_DEBUG /* Check noone else using our table */ @@ -339,7 +314,7 @@ ip6t_do_table(struct sk_buff **pskb, #endif /* For return from builtin chain */ - back = get_entry(table_base, table->private->underflow[hook]); + back = get_entry(table_base, private->underflow[hook]); do { IP_NF_ASSERT(e); @@ -439,145 +414,6 @@ ip6t_do_table(struct sk_buff **pskb, #endif } -/* - * These are weird, but module loading must not be done with mutex - * held (since they will register), and we have to have a single - * function to use try_then_request_module(). - */ - -/* Find table by name, grabs mutex & ref. Returns ERR_PTR() on error. */ -static inline struct ip6t_table *find_table_lock(const char *name) -{ - struct ip6t_table *t; - - if (down_interruptible(&ip6t_mutex) != 0) - return ERR_PTR(-EINTR); - - list_for_each_entry(t, &ip6t_tables, list) - if (strcmp(t->name, name) == 0 && try_module_get(t->me)) - return t; - up(&ip6t_mutex); - return NULL; -} - -/* Find match, grabs ref. Returns ERR_PTR() on error. */ -static inline struct ip6t_match *find_match(const char *name, u8 revision) -{ - struct ip6t_match *m; - int err = 0; - - if (down_interruptible(&ip6t_mutex) != 0) - return ERR_PTR(-EINTR); - - list_for_each_entry(m, &ip6t_match, list) { - if (strcmp(m->name, name) == 0) { - if (m->revision == revision) { - if (try_module_get(m->me)) { - up(&ip6t_mutex); - return m; - } - } else - err = -EPROTOTYPE; /* Found something. */ - } - } - up(&ip6t_mutex); - return ERR_PTR(err); -} - -/* Find target, grabs ref. Returns ERR_PTR() on error. */ -static inline struct ip6t_target *find_target(const char *name, u8 revision) -{ - struct ip6t_target *t; - int err = 0; - - if (down_interruptible(&ip6t_mutex) != 0) - return ERR_PTR(-EINTR); - - list_for_each_entry(t, &ip6t_target, list) { - if (strcmp(t->name, name) == 0) { - if (t->revision == revision) { - if (try_module_get(t->me)) { - up(&ip6t_mutex); - return t; - } - } else - err = -EPROTOTYPE; /* Found something. */ - } - } - up(&ip6t_mutex); - return ERR_PTR(err); -} - -struct ip6t_target *ip6t_find_target(const char *name, u8 revision) -{ - struct ip6t_target *target; - - target = try_then_request_module(find_target(name, revision), - "ip6t_%s", name); - if (IS_ERR(target) || !target) - return NULL; - return target; -} - -static int match_revfn(const char *name, u8 revision, int *bestp) -{ - struct ip6t_match *m; - int have_rev = 0; - - list_for_each_entry(m, &ip6t_match, list) { - if (strcmp(m->name, name) == 0) { - if (m->revision > *bestp) - *bestp = m->revision; - if (m->revision == revision) - have_rev = 1; - } - } - return have_rev; -} - -static int target_revfn(const char *name, u8 revision, int *bestp) -{ - struct ip6t_target *t; - int have_rev = 0; - - list_for_each_entry(t, &ip6t_target, list) { - if (strcmp(t->name, name) == 0) { - if (t->revision > *bestp) - *bestp = t->revision; - if (t->revision == revision) - have_rev = 1; - } - } - return have_rev; -} - -/* Returns true or fals (if no such extension at all) */ -static inline int find_revision(const char *name, u8 revision, - int (*revfn)(const char *, u8, int *), - int *err) -{ - int have_rev, best = -1; - - if (down_interruptible(&ip6t_mutex) != 0) { - *err = -EINTR; - return 1; - } - have_rev = revfn(name, revision, &best); - up(&ip6t_mutex); - - /* Nothing at all? Return 0 to try loading module. */ - if (best == -1) { - *err = -ENOENT; - return 0; - } - - *err = best; - if (!have_rev) - *err = -EPROTONOSUPPORT; - return 1; -} - - /* All zeroes == unconditional rule. */ static inline int unconditional(const struct ip6t_ip6 *ipv6) @@ -594,7 +430,7 @@ unconditional(const struct ip6t_ip6 *ipv6) /* Figures out from what hook each rule can be called: returns 0 if there are loops. Puts hook bitmask in comefrom. */ static int -mark_source_chains(struct ip6t_table_info *newinfo, +mark_source_chains(struct xt_table_info *newinfo, unsigned int valid_hooks, void *entry0) { unsigned int hook; @@ -740,11 +576,11 @@ check_match(struct ip6t_entry_match *m, { struct ip6t_match *match; - match = try_then_request_module(find_match(m->u.user.name, - m->u.user.revision), + match = try_then_request_module(xt_find_match(AF_INET6, m->u.user.name, + m->u.user.revision), "ip6t_%s", m->u.user.name); if (IS_ERR(match) || !match) { - duprintf("check_match: `%s' not found\n", m->u.user.name); + duprintf("check_match: `%s' not found\n", m->u.user.name); return match ? PTR_ERR(match) : -ENOENT; } m->u.kernel.match = match; @@ -785,8 +621,9 @@ check_entry(struct ip6t_entry *e, const char *name, unsigned int size, goto cleanup_matches; t = ip6t_get_target(e); - target = try_then_request_module(find_target(t->u.user.name, - t->u.user.revision), + target = try_then_request_module(xt_find_target(AF_INET6, + t->u.user.name, + t->u.user.revision), "ip6t_%s", t->u.user.name); if (IS_ERR(target) || !target) { duprintf("check_entry: `%s' not found\n", t->u.user.name); @@ -822,7 +659,7 @@ check_entry(struct ip6t_entry *e, const char *name, unsigned int size, static inline int check_entry_size_and_hooks(struct ip6t_entry *e, - struct ip6t_table_info *newinfo, + struct xt_table_info *newinfo, unsigned char *base, unsigned char *limit, const unsigned int *hook_entries, @@ -856,7 +693,7 @@ check_entry_size_and_hooks(struct ip6t_entry *e, < 0 (not IP6T_RETURN). --RR */ /* Clear counters and comefrom */ - e->counters = ((struct ip6t_counters) { 0, 0 }); + e->counters = ((struct xt_counters) { 0, 0 }); e->comefrom = 0; (*i)++; @@ -886,7 +723,7 @@ cleanup_entry(struct ip6t_entry *e, unsigned int *i) static int translate_table(const char *name, unsigned int valid_hooks, - struct ip6t_table_info *newinfo, + struct xt_table_info *newinfo, void *entry0, unsigned int size, unsigned int number, @@ -963,48 +800,10 @@ translate_table(const char *name, return ret; } -static struct ip6t_table_info * -replace_table(struct ip6t_table *table, - unsigned int num_counters, - struct ip6t_table_info *newinfo, - int *error) -{ - struct ip6t_table_info *oldinfo; - -#ifdef CONFIG_NETFILTER_DEBUG - { - int cpu; - - for_each_cpu(cpu) { - struct ip6t_entry *table_base = newinfo->entries[cpu]; - if (table_base) - table_base->comefrom = 0xdead57ac; - } - } -#endif - - /* Do the substitution. */ - write_lock_bh(&table->lock); - /* Check inside lock: is the old number correct? */ - if (num_counters != table->private->number) { - duprintf("num_counters != table->private->number (%u/%u)\n", - num_counters, table->private->number); - write_unlock_bh(&table->lock); - *error = -EAGAIN; - return NULL; - } - oldinfo = table->private; - table->private = newinfo; - newinfo->initial_entries = oldinfo->initial_entries; - write_unlock_bh(&table->lock); - - return oldinfo; -} - /* Gets counters. */ static inline int add_entry_to_counter(const struct ip6t_entry *e, - struct ip6t_counters total[], + struct xt_counters total[], unsigned int *i) { ADD_COUNTER(total[*i], e->counters.bcnt, e->counters.pcnt); @@ -1025,8 +824,8 @@ set_entry_to_counter(const struct ip6t_entry *e, } static void -get_counters(const struct ip6t_table_info *t, - struct ip6t_counters counters[]) +get_counters(const struct xt_table_info *t, + struct xt_counters counters[]) { unsigned int cpu; unsigned int i; @@ -1060,19 +859,20 @@ get_counters(const struct ip6t_table_info *t, static int copy_entries_to_user(unsigned int total_size, - struct ip6t_table *table, + struct xt_table *table, void __user *userptr) { unsigned int off, num, countersize; struct ip6t_entry *e; - struct ip6t_counters *counters; + struct xt_counters *counters; + struct xt_table_info *private = table->private; int ret = 0; void *loc_cpu_entry; /* We need atomic snapshot of counters: rest doesn't change (other than comefrom, which userspace doesn't care about). */ - countersize = sizeof(struct ip6t_counters) * table->private->number; + countersize = sizeof(struct xt_counters) * private->number; counters = vmalloc(countersize); if (counters == NULL) @@ -1080,11 +880,11 @@ copy_entries_to_user(unsigned int total_size, /* First, sum counters... */ write_lock_bh(&table->lock); - get_counters(table->private, counters); + get_counters(private, counters); write_unlock_bh(&table->lock); /* choose the copy that is on ourc node/cpu */ - loc_cpu_entry = table->private->entries[raw_smp_processor_id()]; + loc_cpu_entry = private->entries[raw_smp_processor_id()]; if (copy_to_user(userptr, loc_cpu_entry, total_size) != 0) { ret = -EFAULT; goto free_counters; @@ -1143,87 +943,42 @@ get_entries(const struct ip6t_get_entries *entries, struct ip6t_get_entries __user *uptr) { int ret; - struct ip6t_table *t; + struct xt_table *t; - t = find_table_lock(entries->name); + t = xt_find_table_lock(AF_INET6, entries->name); if (t && !IS_ERR(t)) { - duprintf("t->private->number = %u\n", - t->private->number); - if (entries->size == t->private->size) - ret = copy_entries_to_user(t->private->size, + struct xt_table_info *private = t->private; + duprintf("t->private->number = %u\n", private->number); + if (entries->size == private->size) + ret = copy_entries_to_user(private->size, t, uptr->entrytable); else { duprintf("get_entries: I've got %u not %u!\n", - t->private->size, - entries->size); + private->size, entries->size); ret = -EINVAL; } module_put(t->me); - up(&ip6t_mutex); + xt_table_unlock(t); } else ret = t ? PTR_ERR(t) : -ENOENT; return ret; } -static void free_table_info(struct ip6t_table_info *info) -{ - int cpu; - for_each_cpu(cpu) { - if (info->size <= PAGE_SIZE) - kfree(info->entries[cpu]); - else - vfree(info->entries[cpu]); - } - kfree(info); -} - -static struct ip6t_table_info *alloc_table_info(unsigned int size) -{ - struct ip6t_table_info *newinfo; - int cpu; - - newinfo = kzalloc(sizeof(struct ip6t_table_info), GFP_KERNEL); - if (!newinfo) - return NULL; - - newinfo->size = size; - - for_each_cpu(cpu) { - if (size <= PAGE_SIZE) - newinfo->entries[cpu] = kmalloc_node(size, - GFP_KERNEL, - cpu_to_node(cpu)); - else - newinfo->entries[cpu] = vmalloc_node(size, - cpu_to_node(cpu)); - if (newinfo->entries[cpu] == NULL) { - free_table_info(newinfo); - return NULL; - } - } - - return newinfo; -} - static int do_replace(void __user *user, unsigned int len) { int ret; struct ip6t_replace tmp; - struct ip6t_table *t; - struct ip6t_table_info *newinfo, *oldinfo; - struct ip6t_counters *counters; + struct xt_table *t; + struct xt_table_info *newinfo, *oldinfo; + struct xt_counters *counters; void *loc_cpu_entry, *loc_cpu_old_entry; if (copy_from_user(&tmp, user, sizeof(tmp)) != 0) return -EFAULT; - /* Pedantry: prevent them from hitting BUG() in vmalloc.c --RR */ - if ((SMP_ALIGN(tmp.size) >> PAGE_SHIFT) + 2 > num_physpages) - return -ENOMEM; - - newinfo = alloc_table_info(tmp.size); + newinfo = xt_alloc_table_info(tmp.size); if (!newinfo) return -ENOMEM; @@ -1235,7 +990,7 @@ do_replace(void __user *user, unsigned int len) goto free_newinfo; } - counters = vmalloc(tmp.num_counters * sizeof(struct ip6t_counters)); + counters = vmalloc(tmp.num_counters * sizeof(struct xt_counters)); if (!counters) { ret = -ENOMEM; goto free_newinfo; @@ -1249,7 +1004,7 @@ do_replace(void __user *user, unsigned int len) duprintf("ip_tables: Translated table\n"); - t = try_then_request_module(find_table_lock(tmp.name), + t = try_then_request_module(xt_find_table_lock(AF_INET6, tmp.name), "ip6table_%s", tmp.name); if (!t || IS_ERR(t)) { ret = t ? PTR_ERR(t) : -ENOENT; @@ -1264,7 +1019,7 @@ do_replace(void __user *user, unsigned int len) goto put_module; } - oldinfo = replace_table(t, tmp.num_counters, newinfo, &ret); + oldinfo = xt_replace_table(t, tmp.num_counters, newinfo, &ret); if (!oldinfo) goto put_module; @@ -1283,23 +1038,23 @@ do_replace(void __user *user, unsigned int len) /* Decrease module usage counts and free resource */ loc_cpu_old_entry = oldinfo->entries[raw_smp_processor_id()]; IP6T_ENTRY_ITERATE(loc_cpu_old_entry, oldinfo->size, cleanup_entry,NULL); - free_table_info(oldinfo); + xt_free_table_info(oldinfo); if (copy_to_user(tmp.counters, counters, - sizeof(struct ip6t_counters) * tmp.num_counters) != 0) + sizeof(struct xt_counters) * tmp.num_counters) != 0) ret = -EFAULT; vfree(counters); - up(&ip6t_mutex); + xt_table_unlock(t); return ret; put_module: module_put(t->me); - up(&ip6t_mutex); + xt_table_unlock(t); free_newinfo_counters_untrans: IP6T_ENTRY_ITERATE(loc_cpu_entry, newinfo->size, cleanup_entry,NULL); free_newinfo_counters: vfree(counters); free_newinfo: - free_table_info(newinfo); + xt_free_table_info(newinfo); return ret; } @@ -1307,7 +1062,7 @@ do_replace(void __user *user, unsigned int len) * and everything is OK. */ static inline int add_counter_to_entry(struct ip6t_entry *e, - const struct ip6t_counters addme[], + const struct xt_counters addme[], unsigned int *i) { #if 0 @@ -1329,15 +1084,16 @@ static int do_add_counters(void __user *user, unsigned int len) { unsigned int i; - struct ip6t_counters_info tmp, *paddc; - struct ip6t_table *t; + struct xt_counters_info tmp, *paddc; + struct xt_table_info *private; + struct xt_table *t; int ret = 0; void *loc_cpu_entry; if (copy_from_user(&tmp, user, sizeof(tmp)) != 0) return -EFAULT; - if (len != sizeof(tmp) + tmp.num_counters*sizeof(struct ip6t_counters)) + if (len != sizeof(tmp) + tmp.num_counters*sizeof(struct xt_counters)) return -EINVAL; paddc = vmalloc(len); @@ -1349,29 +1105,30 @@ do_add_counters(void __user *user, unsigned int len) goto free; } - t = find_table_lock(tmp.name); + t = xt_find_table_lock(AF_INET6, tmp.name); if (!t || IS_ERR(t)) { ret = t ? PTR_ERR(t) : -ENOENT; goto free; } write_lock_bh(&t->lock); - if (t->private->number != paddc->num_counters) { + private = t->private; + if (private->number != paddc->num_counters) { ret = -EINVAL; goto unlock_up_free; } i = 0; /* Choose the copy that is on our node */ - loc_cpu_entry = t->private->entries[smp_processor_id()]; + loc_cpu_entry = private->entries[smp_processor_id()]; IP6T_ENTRY_ITERATE(loc_cpu_entry, - t->private->size, + private->size, add_counter_to_entry, paddc->counters, &i); unlock_up_free: write_unlock_bh(&t->lock); - up(&ip6t_mutex); + xt_table_unlock(t); module_put(t->me); free: vfree(paddc); @@ -1415,7 +1172,7 @@ do_ip6t_get_ctl(struct sock *sk, int cmd, void __user *user, int *len) switch (cmd) { case IP6T_SO_GET_INFO: { char name[IP6T_TABLE_MAXNAMELEN]; - struct ip6t_table *t; + struct xt_table *t; if (*len != sizeof(struct ip6t_getinfo)) { duprintf("length %u != %u\n", *len, @@ -1430,25 +1187,26 @@ do_ip6t_get_ctl(struct sock *sk, int cmd, void __user *user, int *len) } name[IP6T_TABLE_MAXNAMELEN-1] = '\0'; - t = try_then_request_module(find_table_lock(name), + t = try_then_request_module(xt_find_table_lock(AF_INET6, name), "ip6table_%s", name); if (t && !IS_ERR(t)) { struct ip6t_getinfo info; + struct xt_table_info *private = t->private; info.valid_hooks = t->valid_hooks; - memcpy(info.hook_entry, t->private->hook_entry, + memcpy(info.hook_entry, private->hook_entry, sizeof(info.hook_entry)); - memcpy(info.underflow, t->private->underflow, + memcpy(info.underflow, private->underflow, sizeof(info.underflow)); - info.num_entries = t->private->number; - info.size = t->private->size; + info.num_entries = private->number; + info.size = private->size; memcpy(info.name, name, sizeof(info.name)); if (copy_to_user(user, &info, *len) != 0) ret = -EFAULT; else ret = 0; - up(&ip6t_mutex); + xt_table_unlock(t); module_put(t->me); } else ret = t ? PTR_ERR(t) : -ENOENT; @@ -1475,7 +1233,7 @@ do_ip6t_get_ctl(struct sock *sk, int cmd, void __user *user, int *len) case IP6T_SO_GET_REVISION_MATCH: case IP6T_SO_GET_REVISION_TARGET: { struct ip6t_get_revision rev; - int (*revfn)(const char *, u8, int *); + int target; if (*len != sizeof(rev)) { ret = -EINVAL; @@ -1487,12 +1245,13 @@ do_ip6t_get_ctl(struct sock *sk, int cmd, void __user *user, int *len) } if (cmd == IP6T_SO_GET_REVISION_TARGET) - revfn = target_revfn; + target = 1; else - revfn = match_revfn; + target = 0; - try_then_request_module(find_revision(rev.name, rev.revision, - revfn, &ret), + try_then_request_module(xt_find_revision(AF_INET6, rev.name, + rev.revision, + target, &ret), "ip6t_%s", rev.name); break; } @@ -1505,61 +1264,16 @@ do_ip6t_get_ctl(struct sock *sk, int cmd, void __user *user, int *len) return ret; } -/* Registration hooks for targets. */ -int -ip6t_register_target(struct ip6t_target *target) -{ - int ret; - - ret = down_interruptible(&ip6t_mutex); - if (ret != 0) - return ret; - list_add(&target->list, &ip6t_target); - up(&ip6t_mutex); - return ret; -} - -void -ip6t_unregister_target(struct ip6t_target *target) -{ - down(&ip6t_mutex); - LIST_DELETE(&ip6t_target, target); - up(&ip6t_mutex); -} - -int -ip6t_register_match(struct ip6t_match *match) -{ - int ret; - - ret = down_interruptible(&ip6t_mutex); - if (ret != 0) - return ret; - - list_add(&match->list, &ip6t_match); - up(&ip6t_mutex); - - return ret; -} - -void -ip6t_unregister_match(struct ip6t_match *match) -{ - down(&ip6t_mutex); - LIST_DELETE(&ip6t_match, match); - up(&ip6t_mutex); -} - -int ip6t_register_table(struct ip6t_table *table, +int ip6t_register_table(struct xt_table *table, const struct ip6t_replace *repl) { int ret; - struct ip6t_table_info *newinfo; - static struct ip6t_table_info bootstrap + struct xt_table_info *newinfo; + static struct xt_table_info bootstrap = { 0, 0, 0, { 0 }, { 0 }, { } }; void *loc_cpu_entry; - newinfo = alloc_table_info(repl->size); + newinfo = xt_alloc_table_info(repl->size); if (!newinfo) return -ENOMEM; @@ -1573,244 +1287,29 @@ int ip6t_register_table(struct ip6t_table *table, repl->hook_entry, repl->underflow); if (ret != 0) { - free_table_info(newinfo); + xt_free_table_info(newinfo); return ret; } - ret = down_interruptible(&ip6t_mutex); - if (ret != 0) { - free_table_info(newinfo); + if (xt_register_table(table, &bootstrap, newinfo) != 0) { + xt_free_table_info(newinfo); return ret; } - /* Don't autoload: we'd eat our tail... */ - if (list_named_find(&ip6t_tables, table->name)) { - ret = -EEXIST; - goto free_unlock; - } - - /* Simplifies replace_table code. */ - table->private = &bootstrap; - if (!replace_table(table, 0, newinfo, &ret)) - goto free_unlock; - - duprintf("table->private->number = %u\n", - table->private->number); - - /* save number of initial entries */ - table->private->initial_entries = table->private->number; - - rwlock_init(&table->lock); - list_prepend(&ip6t_tables, table); - - unlock: - up(&ip6t_mutex); - return ret; - - free_unlock: - free_table_info(newinfo); - goto unlock; + return 0; } -void ip6t_unregister_table(struct ip6t_table *table) +void ip6t_unregister_table(struct xt_table *table) { + struct xt_table_info *private; void *loc_cpu_entry; - down(&ip6t_mutex); - LIST_DELETE(&ip6t_tables, table); - up(&ip6t_mutex); + private = xt_unregister_table(table); /* Decrease module usage counts and free resources */ - loc_cpu_entry = table->private->entries[raw_smp_processor_id()]; - IP6T_ENTRY_ITERATE(loc_cpu_entry, table->private->size, - cleanup_entry, NULL); - free_table_info(table->private); -} - -/* Returns 1 if the port is matched by the range, 0 otherwise */ -static inline int -port_match(u_int16_t min, u_int16_t max, u_int16_t port, int invert) -{ - int ret; - - ret = (port >= min && port <= max) ^ invert; - return ret; -} - -static int -tcp_find_option(u_int8_t option, - const struct sk_buff *skb, - unsigned int tcpoff, - unsigned int optlen, - int invert, - int *hotdrop) -{ - /* tcp.doff is only 4 bits, ie. max 15 * 4 bytes */ - u_int8_t _opt[60 - sizeof(struct tcphdr)], *op; - unsigned int i; - - duprintf("tcp_match: finding option\n"); - if (!optlen) - return invert; - /* If we don't have the whole header, drop packet. */ - op = skb_header_pointer(skb, tcpoff + sizeof(struct tcphdr), optlen, - _opt); - if (op == NULL) { - *hotdrop = 1; - return 0; - } - - for (i = 0; i < optlen; ) { - if (op[i] == option) return !invert; - if (op[i] < 2) i++; - else i += op[i+1]?:1; - } - - return invert; -} - -static int -tcp_match(const struct sk_buff *skb, - const struct net_device *in, - const struct net_device *out, - const void *matchinfo, - int offset, - unsigned int protoff, - int *hotdrop) -{ - struct tcphdr _tcph, *th; - const struct ip6t_tcp *tcpinfo = matchinfo; - - if (offset) { - /* To quote Alan: - - Don't allow a fragment of TCP 8 bytes in. Nobody normal - causes this. Its a cracker trying to break in by doing a - flag overwrite to pass the direction checks. - */ - if (offset == 1) { - duprintf("Dropping evil TCP offset=1 frag.\n"); - *hotdrop = 1; - } - /* Must not be a fragment. */ - return 0; - } - -#define FWINVTCP(bool,invflg) ((bool) ^ !!(tcpinfo->invflags & invflg)) - - th = skb_header_pointer(skb, protoff, sizeof(_tcph), &_tcph); - if (th == NULL) { - /* We've been asked to examine this packet, and we - can't. Hence, no choice but to drop. */ - duprintf("Dropping evil TCP offset=0 tinygram.\n"); - *hotdrop = 1; - return 0; - } - - if (!port_match(tcpinfo->spts[0], tcpinfo->spts[1], - ntohs(th->source), - !!(tcpinfo->invflags & IP6T_TCP_INV_SRCPT))) - return 0; - if (!port_match(tcpinfo->dpts[0], tcpinfo->dpts[1], - ntohs(th->dest), - !!(tcpinfo->invflags & IP6T_TCP_INV_DSTPT))) - return 0; - if (!FWINVTCP((((unsigned char *)th)[13] & tcpinfo->flg_mask) - == tcpinfo->flg_cmp, - IP6T_TCP_INV_FLAGS)) - return 0; - if (tcpinfo->option) { - if (th->doff * 4 < sizeof(_tcph)) { - *hotdrop = 1; - return 0; - } - if (!tcp_find_option(tcpinfo->option, skb, protoff, - th->doff*4 - sizeof(*th), - tcpinfo->invflags & IP6T_TCP_INV_OPTION, - hotdrop)) - return 0; - } - return 1; -} - -/* Called when user tries to insert an entry of this type. */ -static int -tcp_checkentry(const char *tablename, - const struct ip6t_ip6 *ipv6, - void *matchinfo, - unsigned int matchsize, - unsigned int hook_mask) -{ - const struct ip6t_tcp *tcpinfo = matchinfo; - - /* Must specify proto == TCP, and no unknown invflags */ - return ipv6->proto == IPPROTO_TCP - && !(ipv6->invflags & IP6T_INV_PROTO) - && matchsize == IP6T_ALIGN(sizeof(struct ip6t_tcp)) - && !(tcpinfo->invflags & ~IP6T_TCP_INV_MASK); -} - -static int -udp_match(const struct sk_buff *skb, - const struct net_device *in, - const struct net_device *out, - const void *matchinfo, - int offset, - unsigned int protoff, - int *hotdrop) -{ - struct udphdr _udph, *uh; - const struct ip6t_udp *udpinfo = matchinfo; - - /* Must not be a fragment. */ - if (offset) - return 0; - - uh = skb_header_pointer(skb, protoff, sizeof(_udph), &_udph); - if (uh == NULL) { - /* We've been asked to examine this packet, and we - can't. Hence, no choice but to drop. */ - duprintf("Dropping evil UDP tinygram.\n"); - *hotdrop = 1; - return 0; - } - - return port_match(udpinfo->spts[0], udpinfo->spts[1], - ntohs(uh->source), - !!(udpinfo->invflags & IP6T_UDP_INV_SRCPT)) - && port_match(udpinfo->dpts[0], udpinfo->dpts[1], - ntohs(uh->dest), - !!(udpinfo->invflags & IP6T_UDP_INV_DSTPT)); -} - -/* Called when user tries to insert an entry of this type. */ -static int -udp_checkentry(const char *tablename, - const struct ip6t_ip6 *ipv6, - void *matchinfo, - unsigned int matchinfosize, - unsigned int hook_mask) -{ - const struct ip6t_udp *udpinfo = matchinfo; - - /* Must specify proto == UDP, and no unknown invflags */ - if (ipv6->proto != IPPROTO_UDP || (ipv6->invflags & IP6T_INV_PROTO)) { - duprintf("ip6t_udp: Protocol %u != %u\n", ipv6->proto, - IPPROTO_UDP); - return 0; - } - if (matchinfosize != IP6T_ALIGN(sizeof(struct ip6t_udp))) { - duprintf("ip6t_udp: matchsize %u != %u\n", - matchinfosize, IP6T_ALIGN(sizeof(struct ip6t_udp))); - return 0; - } - if (udpinfo->invflags & ~IP6T_UDP_INV_MASK) { - duprintf("ip6t_udp: unknown flags %X\n", - udpinfo->invflags); - return 0; - } - - return 1; + loc_cpu_entry = private->entries[raw_smp_processor_id()]; + IP6T_ENTRY_ITERATE(loc_cpu_entry, private->size, cleanup_entry, NULL); + xt_free_table_info(private); } /* Returns 1 if the type and code is matched by the range, 0 otherwise */ @@ -1858,11 +1357,12 @@ icmp6_match(const struct sk_buff *skb, /* Called when user tries to insert an entry of this type. */ static int icmp6_checkentry(const char *tablename, - const struct ip6t_ip6 *ipv6, + const void *entry, void *matchinfo, unsigned int matchsize, unsigned int hook_mask) { + const struct ip6t_ip6 *ipv6 = entry; const struct ip6t_icmp *icmpinfo = matchinfo; /* Must specify proto == ICMP, and no unknown invflags */ @@ -1892,164 +1392,42 @@ static struct nf_sockopt_ops ip6t_sockopts = { .get = do_ip6t_get_ctl, }; -static struct ip6t_match tcp_matchstruct = { - .name = "tcp", - .match = &tcp_match, - .checkentry = &tcp_checkentry, -}; - -static struct ip6t_match udp_matchstruct = { - .name = "udp", - .match = &udp_match, - .checkentry = &udp_checkentry, -}; - static struct ip6t_match icmp6_matchstruct = { .name = "icmp6", .match = &icmp6_match, .checkentry = &icmp6_checkentry, }; -#ifdef CONFIG_PROC_FS -static inline int print_name(const char *i, - off_t start_offset, char *buffer, int length, - off_t *pos, unsigned int *count) -{ - if ((*count)++ >= start_offset) { - unsigned int namelen; - - namelen = sprintf(buffer + *pos, "%s\n", - i + sizeof(struct list_head)); - if (*pos + namelen > length) { - /* Stop iterating */ - return 1; - } - *pos += namelen; - } - return 0; -} - -static inline int print_target(const struct ip6t_target *t, - off_t start_offset, char *buffer, int length, - off_t *pos, unsigned int *count) -{ - if (t == &ip6t_standard_target || t == &ip6t_error_target) - return 0; - return print_name((char *)t, start_offset, buffer, length, pos, count); -} - -static int ip6t_get_tables(char *buffer, char **start, off_t offset, int length) -{ - off_t pos = 0; - unsigned int count = 0; - - if (down_interruptible(&ip6t_mutex) != 0) - return 0; - - LIST_FIND(&ip6t_tables, print_name, char *, - offset, buffer, length, &pos, &count); - - up(&ip6t_mutex); - - /* `start' hack - see fs/proc/generic.c line ~105 */ - *start=(char *)((unsigned long)count-offset); - return pos; -} - -static int ip6t_get_targets(char *buffer, char **start, off_t offset, int length) -{ - off_t pos = 0; - unsigned int count = 0; - - if (down_interruptible(&ip6t_mutex) != 0) - return 0; - - LIST_FIND(&ip6t_target, print_target, struct ip6t_target *, - offset, buffer, length, &pos, &count); - - up(&ip6t_mutex); - - *start = (char *)((unsigned long)count - offset); - return pos; -} - -static int ip6t_get_matches(char *buffer, char **start, off_t offset, int length) -{ - off_t pos = 0; - unsigned int count = 0; - - if (down_interruptible(&ip6t_mutex) != 0) - return 0; - - LIST_FIND(&ip6t_match, print_name, char *, - offset, buffer, length, &pos, &count); - - up(&ip6t_mutex); - - *start = (char *)((unsigned long)count - offset); - return pos; -} - -static const struct { char *name; get_info_t *get_info; } ip6t_proc_entry[] = -{ { "ip6_tables_names", ip6t_get_tables }, - { "ip6_tables_targets", ip6t_get_targets }, - { "ip6_tables_matches", ip6t_get_matches }, - { NULL, NULL} }; -#endif /*CONFIG_PROC_FS*/ - static int __init init(void) { int ret; + xt_proto_init(AF_INET6); + /* Noone else will be downing sem now, so we won't sleep */ - down(&ip6t_mutex); - list_append(&ip6t_target, &ip6t_standard_target); - list_append(&ip6t_target, &ip6t_error_target); - list_append(&ip6t_match, &tcp_matchstruct); - list_append(&ip6t_match, &udp_matchstruct); - list_append(&ip6t_match, &icmp6_matchstruct); - up(&ip6t_mutex); + xt_register_target(AF_INET6, &ip6t_standard_target); + xt_register_target(AF_INET6, &ip6t_error_target); + xt_register_match(AF_INET6, &icmp6_matchstruct); /* Register setsockopt */ ret = nf_register_sockopt(&ip6t_sockopts); if (ret < 0) { duprintf("Unable to register sockopts.\n"); + xt_proto_fini(AF_INET6); return ret; } -#ifdef CONFIG_PROC_FS - { - struct proc_dir_entry *proc; - int i; - - for (i = 0; ip6t_proc_entry[i].name; i++) { - proc = proc_net_create(ip6t_proc_entry[i].name, 0, - ip6t_proc_entry[i].get_info); - if (!proc) { - while (--i >= 0) - proc_net_remove(ip6t_proc_entry[i].name); - nf_unregister_sockopt(&ip6t_sockopts); - return -ENOMEM; - } - proc->owner = THIS_MODULE; - } - } -#endif - - printk("ip6_tables: (C) 2000-2002 Netfilter core team\n"); + printk("ip6_tables: (C) 2000-2006 Netfilter Core Team\n"); return 0; } static void __exit fini(void) { nf_unregister_sockopt(&ip6t_sockopts); -#ifdef CONFIG_PROC_FS - { - int i; - for (i = 0; ip6t_proc_entry[i].name; i++) - proc_net_remove(ip6t_proc_entry[i].name); - } -#endif + xt_unregister_match(AF_INET6, &icmp6_matchstruct); + xt_unregister_target(AF_INET6, &ip6t_error_target); + xt_unregister_target(AF_INET6, &ip6t_standard_target); + xt_proto_fini(AF_INET6); } /* @@ -2128,10 +1506,6 @@ int ipv6_find_hdr(const struct sk_buff *skb, unsigned int *offset, EXPORT_SYMBOL(ip6t_register_table); EXPORT_SYMBOL(ip6t_unregister_table); EXPORT_SYMBOL(ip6t_do_table); -EXPORT_SYMBOL(ip6t_register_match); -EXPORT_SYMBOL(ip6t_unregister_match); -EXPORT_SYMBOL(ip6t_register_target); -EXPORT_SYMBOL(ip6t_unregister_target); EXPORT_SYMBOL(ip6t_ext_hdr); EXPORT_SYMBOL(ipv6_find_hdr); EXPORT_SYMBOL(ip6_masked_addrcmp); diff --git a/net/ipv6/netfilter/ip6t_HL.c b/net/ipv6/netfilter/ip6t_HL.c index 8f5549b7272..306200c3505 100644 --- a/net/ipv6/netfilter/ip6t_HL.c +++ b/net/ipv6/netfilter/ip6t_HL.c @@ -62,7 +62,7 @@ static unsigned int ip6t_hl_target(struct sk_buff **pskb, } static int ip6t_hl_checkentry(const char *tablename, - const struct ip6t_entry *e, + const void *entry, void *targinfo, unsigned int targinfosize, unsigned int hook_mask) diff --git a/net/ipv6/netfilter/ip6t_LOG.c b/net/ipv6/netfilter/ip6t_LOG.c index ae4653bfd65..77c725832de 100644 --- a/net/ipv6/netfilter/ip6t_LOG.c +++ b/net/ipv6/netfilter/ip6t_LOG.c @@ -63,9 +63,8 @@ static void dump_packet(const struct nf_loginfo *info, return; } - /* Max length: 88 "SRC=0000.0000.0000.0000.0000.0000.0000.0000 DST=0000.0000.0000.0000.0000.0000.0000.0000" */ - printk("SRC=%04x:%04x:%04x:%04x:%04x:%04x:%04x:%04x ", NIP6(ih->saddr)); - printk("DST=%04x:%04x:%04x:%04x:%04x:%04x:%04x:%04x ", NIP6(ih->daddr)); + /* Max length: 88 "SRC=0000.0000.0000.0000.0000.0000.0000.0000 DST=0000.0000.0000.0000.0000.0000.0000.0000 " */ + printk("SRC=" NIP6_FMT " DST=" NIP6_FMT " ", NIP6(ih->saddr), NIP6(ih->daddr)); /* Max length: 44 "LEN=65535 TC=255 HOPLIMIT=255 FLOWLBL=FFFFF " */ printk("LEN=%Zu TC=%u HOPLIMIT=%u FLOWLBL=%u ", @@ -444,7 +443,7 @@ ip6t_log_target(struct sk_buff **pskb, static int ip6t_log_checkentry(const char *tablename, - const struct ip6t_entry *e, + const void *entry, void *targinfo, unsigned int targinfosize, unsigned int hook_mask) diff --git a/net/ipv6/netfilter/ip6t_MARK.c b/net/ipv6/netfilter/ip6t_MARK.c deleted file mode 100644 index eab8fb864ee..00000000000 --- a/net/ipv6/netfilter/ip6t_MARK.c +++ /dev/null @@ -1,81 +0,0 @@ -/* This is a module which is used for setting the NFMARK field of an skb. */ - -/* (C) 1999-2001 Marc Boucher <marc@mbsi.ca> - * - * This program is free software; you can redistribute it and/or modify - * it under the terms of the GNU General Public License version 2 as - * published by the Free Software Foundation. - */ - -#include <linux/module.h> -#include <linux/skbuff.h> -#include <linux/ip.h> -#include <net/checksum.h> - -#include <linux/netfilter_ipv6/ip6_tables.h> -#include <linux/netfilter_ipv6/ip6t_MARK.h> - -MODULE_LICENSE("GPL"); -MODULE_AUTHOR("Netfilter Core Team <coreteam@netfilter.org>"); - -static unsigned int -target(struct sk_buff **pskb, - const struct net_device *in, - const struct net_device *out, - unsigned int hooknum, - const void *targinfo, - void *userinfo) -{ - const struct ip6t_mark_target_info *markinfo = targinfo; - - if((*pskb)->nfmark != markinfo->mark) - (*pskb)->nfmark = markinfo->mark; - - return IP6T_CONTINUE; -} - -static int -checkentry(const char *tablename, - const struct ip6t_entry *e, - void *targinfo, - unsigned int targinfosize, - unsigned int hook_mask) -{ - if (targinfosize != IP6T_ALIGN(sizeof(struct ip6t_mark_target_info))) { - printk(KERN_WARNING "MARK: targinfosize %u != %Zu\n", - targinfosize, - IP6T_ALIGN(sizeof(struct ip6t_mark_target_info))); - return 0; - } - - if (strcmp(tablename, "mangle") != 0) { - printk(KERN_WARNING "MARK: can only be called from \"mangle\" table, not \"%s\"\n", tablename); - return 0; - } - - return 1; -} - -static struct ip6t_target ip6t_mark_reg = { - .name = "MARK", - .target = target, - .checkentry = checkentry, - .me = THIS_MODULE -}; - -static int __init init(void) -{ - printk(KERN_DEBUG "registering ipv6 mark target\n"); - if (ip6t_register_target(&ip6t_mark_reg)) - return -EINVAL; - - return 0; -} - -static void __exit fini(void) -{ - ip6t_unregister_target(&ip6t_mark_reg); -} - -module_init(init); -module_exit(fini); diff --git a/net/ipv6/netfilter/ip6t_NFQUEUE.c b/net/ipv6/netfilter/ip6t_NFQUEUE.c deleted file mode 100644 index c6e3730e740..00000000000 --- a/net/ipv6/netfilter/ip6t_NFQUEUE.c +++ /dev/null @@ -1,70 +0,0 @@ -/* ip6tables module for using new netfilter netlink queue - * - * (C) 2005 by Harald Welte <laforge@netfilter.org> - * - * This program is free software; you can redistribute it and/or modify - * it under the terms of the GNU General Public License version 2 as - * published by the Free Software Foundation. - * - */ - -#include <linux/module.h> -#include <linux/skbuff.h> - -#include <linux/netfilter.h> -#include <linux/netfilter_ipv6/ip6_tables.h> -#include <linux/netfilter_ipv4/ipt_NFQUEUE.h> - -MODULE_AUTHOR("Harald Welte <laforge@netfilter.org>"); -MODULE_DESCRIPTION("ip6tables NFQUEUE target"); -MODULE_LICENSE("GPL"); - -static unsigned int -target(struct sk_buff **pskb, - const struct net_device *in, - const struct net_device *out, - unsigned int hooknum, - const void *targinfo, - void *userinfo) -{ - const struct ipt_NFQ_info *tinfo = targinfo; - - return NF_QUEUE_NR(tinfo->queuenum); -} - -static int -checkentry(const char *tablename, - const struct ip6t_entry *e, - void *targinfo, - unsigned int targinfosize, - unsigned int hook_mask) -{ - if (targinfosize != IP6T_ALIGN(sizeof(struct ipt_NFQ_info))) { - printk(KERN_WARNING "NFQUEUE: targinfosize %u != %Zu\n", - targinfosize, - IP6T_ALIGN(sizeof(struct ipt_NFQ_info))); - return 0; - } - - return 1; -} - -static struct ip6t_target ipt_NFQ_reg = { - .name = "NFQUEUE", - .target = target, - .checkentry = checkentry, - .me = THIS_MODULE, -}; - -static int __init init(void) -{ - return ip6t_register_target(&ipt_NFQ_reg); -} - -static void __exit fini(void) -{ - ip6t_unregister_target(&ipt_NFQ_reg); -} - -module_init(init); -module_exit(fini); diff --git a/net/ipv6/netfilter/ip6t_REJECT.c b/net/ipv6/netfilter/ip6t_REJECT.c index b03e87adca9..c745717b4ce 100644 --- a/net/ipv6/netfilter/ip6t_REJECT.c +++ b/net/ipv6/netfilter/ip6t_REJECT.c @@ -218,12 +218,13 @@ static unsigned int reject6_target(struct sk_buff **pskb, } static int check(const char *tablename, - const struct ip6t_entry *e, + const void *entry, void *targinfo, unsigned int targinfosize, unsigned int hook_mask) { const struct ip6t_reject_info *rejinfo = targinfo; + const struct ip6t_entry *e = entry; if (targinfosize != IP6T_ALIGN(sizeof(struct ip6t_reject_info))) { DEBUGP("ip6t_REJECT: targinfosize %u != 0\n", targinfosize); diff --git a/net/ipv6/netfilter/ip6t_ah.c b/net/ipv6/netfilter/ip6t_ah.c index f5c1a7ff4a1..219a30365df 100644 --- a/net/ipv6/netfilter/ip6t_ah.c +++ b/net/ipv6/netfilter/ip6t_ah.c @@ -98,7 +98,7 @@ match(const struct sk_buff *skb, /* Called when user tries to insert an entry of this type. */ static int checkentry(const char *tablename, - const struct ip6t_ip6 *ip, + const void *entry, void *matchinfo, unsigned int matchinfosize, unsigned int hook_mask) diff --git a/net/ipv6/netfilter/ip6t_dst.c b/net/ipv6/netfilter/ip6t_dst.c index 48cf5f9efc9..80fe82669ce 100644 --- a/net/ipv6/netfilter/ip6t_dst.c +++ b/net/ipv6/netfilter/ip6t_dst.c @@ -178,7 +178,7 @@ match(const struct sk_buff *skb, /* Called when user tries to insert an entry of this type. */ static int checkentry(const char *tablename, - const struct ip6t_ip6 *ip, + const void *info, void *matchinfo, unsigned int matchinfosize, unsigned int hook_mask) diff --git a/net/ipv6/netfilter/ip6t_esp.c b/net/ipv6/netfilter/ip6t_esp.c index e1828f6d0a4..724285df871 100644 --- a/net/ipv6/netfilter/ip6t_esp.c +++ b/net/ipv6/netfilter/ip6t_esp.c @@ -76,7 +76,7 @@ match(const struct sk_buff *skb, /* Called when user tries to insert an entry of this type. */ static int checkentry(const char *tablename, - const struct ip6t_ip6 *ip, + const void *ip, void *matchinfo, unsigned int matchinfosize, unsigned int hook_mask) diff --git a/net/ipv6/netfilter/ip6t_eui64.c b/net/ipv6/netfilter/ip6t_eui64.c index 616c2cbcd54..ddf5f571909 100644 --- a/net/ipv6/netfilter/ip6t_eui64.c +++ b/net/ipv6/netfilter/ip6t_eui64.c @@ -62,7 +62,7 @@ match(const struct sk_buff *skb, static int ip6t_eui64_checkentry(const char *tablename, - const struct ip6t_ip6 *ip, + const void *ip, void *matchinfo, unsigned int matchsize, unsigned int hook_mask) diff --git a/net/ipv6/netfilter/ip6t_frag.c b/net/ipv6/netfilter/ip6t_frag.c index d1549b26866..a9964b946ed 100644 --- a/net/ipv6/netfilter/ip6t_frag.c +++ b/net/ipv6/netfilter/ip6t_frag.c @@ -115,7 +115,7 @@ match(const struct sk_buff *skb, /* Called when user tries to insert an entry of this type. */ static int checkentry(const char *tablename, - const struct ip6t_ip6 *ip, + const void *ip, void *matchinfo, unsigned int matchinfosize, unsigned int hook_mask) diff --git a/net/ipv6/netfilter/ip6t_hbh.c b/net/ipv6/netfilter/ip6t_hbh.c index e3bc8e2700e..ed8ded18bbd 100644 --- a/net/ipv6/netfilter/ip6t_hbh.c +++ b/net/ipv6/netfilter/ip6t_hbh.c @@ -178,7 +178,7 @@ match(const struct sk_buff *skb, /* Called when user tries to insert an entry of this type. */ static int checkentry(const char *tablename, - const struct ip6t_ip6 *ip, + const void *entry, void *matchinfo, unsigned int matchinfosize, unsigned int hook_mask) diff --git a/net/ipv6/netfilter/ip6t_hl.c b/net/ipv6/netfilter/ip6t_hl.c index 0beaff5471d..c5d9079f2d9 100644 --- a/net/ipv6/netfilter/ip6t_hl.c +++ b/net/ipv6/netfilter/ip6t_hl.c @@ -48,7 +48,7 @@ static int match(const struct sk_buff *skb, const struct net_device *in, return 0; } -static int checkentry(const char *tablename, const struct ip6t_ip6 *ip, +static int checkentry(const char *tablename, const void *entry, void *matchinfo, unsigned int matchsize, unsigned int hook_mask) { diff --git a/net/ipv6/netfilter/ip6t_ipv6header.c b/net/ipv6/netfilter/ip6t_ipv6header.c index 32e67f05845..fda1ceaf5a2 100644 --- a/net/ipv6/netfilter/ip6t_ipv6header.c +++ b/net/ipv6/netfilter/ip6t_ipv6header.c @@ -124,7 +124,7 @@ ipv6header_match(const struct sk_buff *skb, static int ipv6header_checkentry(const char *tablename, - const struct ip6t_ip6 *ip, + const void *ip, void *matchinfo, unsigned int matchsize, unsigned int hook_mask) diff --git a/net/ipv6/netfilter/ip6t_length.c b/net/ipv6/netfilter/ip6t_length.c deleted file mode 100644 index e0537d3811d..00000000000 --- a/net/ipv6/netfilter/ip6t_length.c +++ /dev/null @@ -1,66 +0,0 @@ -/* Length Match - IPv6 Port */ - -/* (C) 1999-2001 James Morris <jmorros@intercode.com.au> - * - * This program is free software; you can redistribute it and/or modify - * it under the terms of the GNU General Public License version 2 as - * published by the Free Software Foundation. - */ - - -#include <linux/module.h> -#include <linux/skbuff.h> -#include <linux/netfilter_ipv6/ip6t_length.h> -#include <linux/netfilter_ipv6/ip6_tables.h> - -MODULE_LICENSE("GPL"); -MODULE_AUTHOR("James Morris <jmorris@intercode.com.au>"); -MODULE_DESCRIPTION("IPv6 packet length match"); - -static int -match(const struct sk_buff *skb, - const struct net_device *in, - const struct net_device *out, - const void *matchinfo, - int offset, - unsigned int protoff, - int *hotdrop) -{ - const struct ip6t_length_info *info = matchinfo; - u_int16_t pktlen = ntohs(skb->nh.ipv6h->payload_len) + sizeof(struct ipv6hdr); - - return (pktlen >= info->min && pktlen <= info->max) ^ info->invert; -} - -static int -checkentry(const char *tablename, - const struct ip6t_ip6 *ip, - void *matchinfo, - unsigned int matchsize, - unsigned int hook_mask) -{ - if (matchsize != IP6T_ALIGN(sizeof(struct ip6t_length_info))) - return 0; - - return 1; -} - -static struct ip6t_match length_match = { - .name = "length", - .match = &match, - .checkentry = &checkentry, - .me = THIS_MODULE, -}; - -static int __init init(void) -{ - return ip6t_register_match(&length_match); -} - -static void __exit fini(void) -{ - ip6t_unregister_match(&length_match); -} - -module_init(init); -module_exit(fini); diff --git a/net/ipv6/netfilter/ip6t_limit.c b/net/ipv6/netfilter/ip6t_limit.c deleted file mode 100644 index fb782f610be..00000000000 --- a/net/ipv6/netfilter/ip6t_limit.c +++ /dev/null @@ -1,147 +0,0 @@ -/* Kernel module to control the rate - * - * 2 September 1999: Changed from the target RATE to the match - * `limit', removed logging. Did I mention that - * Alexey is a fucking genius? - * Rusty Russell (rusty@rustcorp.com.au). */ - -/* (C) 1999 Jérôme de Vivie <devivie@info.enserb.u-bordeaux.fr> - * (C) 1999 Hervé Eychenne <eychenne@info.enserb.u-bordeaux.fr> - * - * This program is free software; you can redistribute it and/or modify - * it under the terms of the GNU General Public License version 2 as - * published by the Free Software Foundation. - */ - -#include <linux/module.h> -#include <linux/skbuff.h> -#include <linux/spinlock.h> -#include <linux/interrupt.h> - -#include <linux/netfilter_ipv6/ip6_tables.h> -#include <linux/netfilter_ipv6/ip6t_limit.h> - -MODULE_LICENSE("GPL"); -MODULE_AUTHOR("Herve Eychenne <rv@wallfire.org>"); -MODULE_DESCRIPTION("rate limiting within ip6tables"); - -/* The algorithm used is the Simple Token Bucket Filter (TBF) - * see net/sched/sch_tbf.c in the linux source tree - */ - -static DEFINE_SPINLOCK(limit_lock); - -/* Rusty: This is my (non-mathematically-inclined) understanding of - this algorithm. The `average rate' in jiffies becomes your initial - amount of credit `credit' and the most credit you can ever have - `credit_cap'. The `peak rate' becomes the cost of passing the - test, `cost'. - - `prev' tracks the last packet hit: you gain one credit per jiffy. - If you get credit balance more than this, the extra credit is - discarded. Every time the match passes, you lose `cost' credits; - if you don't have that many, the test fails. - - See Alexey's formal explanation in net/sched/sch_tbf.c. - - To avoid underflow, we multiply by 128 (ie. you get 128 credits per - jiffy). Hence a cost of 2^32-1, means one pass per 32768 seconds - at 1024HZ (or one every 9 hours). A cost of 1 means 12800 passes - per second at 100HZ. */ - -#define CREDITS_PER_JIFFY 128 - -static int -ip6t_limit_match(const struct sk_buff *skb, - const struct net_device *in, - const struct net_device *out, - const void *matchinfo, - int offset, - unsigned int protoff, - int *hotdrop) -{ - struct ip6t_rateinfo *r = ((struct ip6t_rateinfo *)matchinfo)->master; - unsigned long now = jiffies; - - spin_lock_bh(&limit_lock); - r->credit += (now - xchg(&r->prev, now)) * CREDITS_PER_JIFFY; - if (r->credit > r->credit_cap) - r->credit = r->credit_cap; - - if (r->credit >= r->cost) { - /* We're not limited. */ - r->credit -= r->cost; - spin_unlock_bh(&limit_lock); - return 1; - } - - spin_unlock_bh(&limit_lock); - return 0; -} - -/* Precision saver. */ -static u_int32_t -user2credits(u_int32_t user) -{ - /* If multiplying would overflow... */ - if (user > 0xFFFFFFFF / (HZ*CREDITS_PER_JIFFY)) - /* Divide first. */ - return (user / IP6T_LIMIT_SCALE) * HZ * CREDITS_PER_JIFFY; - - return (user * HZ * CREDITS_PER_JIFFY) / IP6T_LIMIT_SCALE; -} - -static int -ip6t_limit_checkentry(const char *tablename, - const struct ip6t_ip6 *ip, - void *matchinfo, - unsigned int matchsize, - unsigned int hook_mask) -{ - struct ip6t_rateinfo *r = matchinfo; - - if (matchsize != IP6T_ALIGN(sizeof(struct ip6t_rateinfo))) - return 0; - - /* Check for overflow. */ - if (r->burst == 0 - || user2credits(r->avg * r->burst) < user2credits(r->avg)) { - printk("Call rusty: overflow in ip6t_limit: %u/%u\n", - r->avg, r->burst); - return 0; - } - - /* User avg in seconds * IP6T_LIMIT_SCALE: convert to jiffies * - 128. */ - r->prev = jiffies; - r->credit = user2credits(r->avg * r->burst); /* Credits full. */ - r->credit_cap = user2credits(r->avg * r->burst); /* Credits full. */ - r->cost = user2credits(r->avg); - - /* For SMP, we only want to use one set of counters. */ - r->master = r; - - return 1; -} - -static struct ip6t_match ip6t_limit_reg = { - .name = "limit", - .match = ip6t_limit_match, - .checkentry = ip6t_limit_checkentry, - .me = THIS_MODULE, -}; - -static int __init init(void) -{ - if (ip6t_register_match(&ip6t_limit_reg)) - return -EINVAL; - return 0; -} - -static void __exit fini(void) -{ - ip6t_unregister_match(&ip6t_limit_reg); -} - -module_init(init); -module_exit(fini); diff --git a/net/ipv6/netfilter/ip6t_mac.c b/net/ipv6/netfilter/ip6t_mac.c deleted file mode 100644 index c848152315b..00000000000 --- a/net/ipv6/netfilter/ip6t_mac.c +++ /dev/null @@ -1,81 +0,0 @@ -/* Kernel module to match MAC address parameters. */ - -/* (C) 1999-2001 Paul `Rusty' Russell - * (C) 2002-2004 Netfilter Core Team <coreteam@netfilter.org> - * - * This program is free software; you can redistribute it and/or modify - * it under the terms of the GNU General Public License version 2 as - * published by the Free Software Foundation. - */ - -#include <linux/module.h> -#include <linux/skbuff.h> -#include <linux/if_ether.h> -#include <linux/etherdevice.h> - -#include <linux/netfilter_ipv6/ip6t_mac.h> -#include <linux/netfilter_ipv6/ip6_tables.h> - -MODULE_LICENSE("GPL"); -MODULE_DESCRIPTION("MAC address matching module for IPv6"); -MODULE_AUTHOR("Netfilter Core Teaam <coreteam@netfilter.org>"); - -static int -match(const struct sk_buff *skb, - const struct net_device *in, - const struct net_device *out, - const void *matchinfo, - int offset, - unsigned int protoff, - int *hotdrop) -{ - const struct ip6t_mac_info *info = matchinfo; - - /* Is mac pointer valid? */ - return (skb->mac.raw >= skb->head - && (skb->mac.raw + ETH_HLEN) <= skb->data - /* If so, compare... */ - && ((!compare_ether_addr(eth_hdr(skb)->h_source, info->srcaddr)) - ^ info->invert)); -} - -static int -ip6t_mac_checkentry(const char *tablename, - const struct ip6t_ip6 *ip, - void *matchinfo, - unsigned int matchsize, - unsigned int hook_mask) -{ - if (hook_mask - & ~((1 << NF_IP6_PRE_ROUTING) | (1 << NF_IP6_LOCAL_IN) - | (1 << NF_IP6_FORWARD))) { - printk("ip6t_mac: only valid for PRE_ROUTING, LOCAL_IN or" - " FORWARD\n"); - return 0; - } - - if (matchsize != IP6T_ALIGN(sizeof(struct ip6t_mac_info))) - return 0; - - return 1; -} - -static struct ip6t_match mac_match = { - .name = "mac", - .match = &match, - .checkentry = &ip6t_mac_checkentry, - .me = THIS_MODULE, -}; - -static int __init init(void) -{ - return ip6t_register_match(&mac_match); -} - -static void __exit fini(void) -{ - ip6t_unregister_match(&mac_match); -} - -module_init(init); -module_exit(fini); diff --git a/net/ipv6/netfilter/ip6t_mark.c b/net/ipv6/netfilter/ip6t_mark.c deleted file mode 100644 index affc3de364f..00000000000 --- a/net/ipv6/netfilter/ip6t_mark.c +++ /dev/null @@ -1,66 +0,0 @@ -/* Kernel module to match NFMARK values. */ - -/* (C) 1999-2001 Marc Boucher <marc@mbsi.ca> - * - * This program is free software; you can redistribute it and/or modify - * it under the terms of the GNU General Public License version 2 as - * published by the Free Software Foundation. - */ - - -#include <linux/module.h> -#include <linux/skbuff.h> - -#include <linux/netfilter_ipv6/ip6t_mark.h> -#include <linux/netfilter_ipv6/ip6_tables.h> - -MODULE_LICENSE("GPL"); -MODULE_AUTHOR("Netfilter Core Team <coreteam@netfilter.org>"); -MODULE_DESCRIPTION("ip6tables mark match"); - -static int -match(const struct sk_buff *skb, - const struct net_device *in, - const struct net_device *out, - const void *matchinfo, - int offset, - unsigned int protoff, - int *hotdrop) -{ - const struct ip6t_mark_info *info = matchinfo; - - return ((skb->nfmark & info->mask) == info->mark) ^ info->invert; -} - -static int -checkentry(const char *tablename, - const struct ip6t_ip6 *ip, - void *matchinfo, - unsigned int matchsize, - unsigned int hook_mask) -{ - if (matchsize != IP6T_ALIGN(sizeof(struct ip6t_mark_info))) - return 0; - - return 1; -} - -static struct ip6t_match mark_match = { - .name = "mark", - .match = &match, - .checkentry = &checkentry, - .me = THIS_MODULE, -}; - -static int __init init(void) -{ - return ip6t_register_match(&mark_match); -} - -static void __exit fini(void) -{ - ip6t_unregister_match(&mark_match); -} - -module_init(init); -module_exit(fini); diff --git a/net/ipv6/netfilter/ip6t_multiport.c b/net/ipv6/netfilter/ip6t_multiport.c index 6e3246153fa..49f7829dfbc 100644 --- a/net/ipv6/netfilter/ip6t_multiport.c +++ b/net/ipv6/netfilter/ip6t_multiport.c @@ -84,11 +84,12 @@ match(const struct sk_buff *skb, /* Called when user tries to insert an entry of this type. */ static int checkentry(const char *tablename, - const struct ip6t_ip6 *ip, + const void *info, void *matchinfo, unsigned int matchsize, unsigned int hook_mask) { + const struct ip6t_ip6 *ip = info; const struct ip6t_multiport *multiinfo = matchinfo; if (matchsize != IP6T_ALIGN(sizeof(struct ip6t_multiport))) diff --git a/net/ipv6/netfilter/ip6t_owner.c b/net/ipv6/netfilter/ip6t_owner.c index 4de4cdad4b7..5409b375b51 100644 --- a/net/ipv6/netfilter/ip6t_owner.c +++ b/net/ipv6/netfilter/ip6t_owner.c @@ -53,7 +53,7 @@ match(const struct sk_buff *skb, static int checkentry(const char *tablename, - const struct ip6t_ip6 *ip, + const void *ip, void *matchinfo, unsigned int matchsize, unsigned int hook_mask) diff --git a/net/ipv6/netfilter/ip6t_rt.c b/net/ipv6/netfilter/ip6t_rt.c index c1e770e4554..8465b437585 100644 --- a/net/ipv6/netfilter/ip6t_rt.c +++ b/net/ipv6/netfilter/ip6t_rt.c @@ -183,7 +183,7 @@ match(const struct sk_buff *skb, /* Called when user tries to insert an entry of this type. */ static int checkentry(const char *tablename, - const struct ip6t_ip6 *ip, + const void *entry, void *matchinfo, unsigned int matchinfosize, unsigned int hook_mask) diff --git a/net/ipv6/netfilter/ip6table_filter.c b/net/ipv6/netfilter/ip6table_filter.c index 4c0028671c2..ce4a968e1f7 100644 --- a/net/ipv6/netfilter/ip6table_filter.c +++ b/net/ipv6/netfilter/ip6table_filter.c @@ -97,6 +97,7 @@ static struct ip6t_table packet_filter = { .valid_hooks = FILTER_VALID_HOOKS, .lock = RW_LOCK_UNLOCKED, .me = THIS_MODULE, + .af = AF_INET6, }; /* The work comes in here from netfilter.c. */ diff --git a/net/ipv6/netfilter/ip6table_mangle.c b/net/ipv6/netfilter/ip6table_mangle.c index 85c1e6eada1..30a4627e000 100644 --- a/net/ipv6/netfilter/ip6table_mangle.c +++ b/net/ipv6/netfilter/ip6table_mangle.c @@ -127,6 +127,7 @@ static struct ip6t_table packet_mangler = { .valid_hooks = MANGLE_VALID_HOOKS, .lock = RW_LOCK_UNLOCKED, .me = THIS_MODULE, + .af = AF_INET6, }; /* The work comes in here from netfilter.c. */ diff --git a/net/ipv6/netfilter/ip6table_raw.c b/net/ipv6/netfilter/ip6table_raw.c index c2982efd14a..db28ba3855e 100644 --- a/net/ipv6/netfilter/ip6table_raw.c +++ b/net/ipv6/netfilter/ip6table_raw.c @@ -106,11 +106,12 @@ static struct } }; -static struct ip6t_table packet_raw = { +static struct xt_table packet_raw = { .name = "raw", .valid_hooks = RAW_VALID_HOOKS, .lock = RW_LOCK_UNLOCKED, - .me = THIS_MODULE + .me = THIS_MODULE, + .af = AF_INET6, }; /* The work comes in here from netfilter.c. */ diff --git a/net/ipv6/netfilter/nf_conntrack_l3proto_ipv6.c b/net/ipv6/netfilter/nf_conntrack_l3proto_ipv6.c index e57d6fc9957..ac702a29dd1 100644 --- a/net/ipv6/netfilter/nf_conntrack_l3proto_ipv6.c +++ b/net/ipv6/netfilter/nf_conntrack_l3proto_ipv6.c @@ -74,7 +74,7 @@ static int ipv6_invert_tuple(struct nf_conntrack_tuple *tuple, static int ipv6_print_tuple(struct seq_file *s, const struct nf_conntrack_tuple *tuple) { - return seq_printf(s, "src=%x:%x:%x:%x:%x:%x:%x:%x dst=%x:%x:%x:%x:%x:%x:%x:%x ", + return seq_printf(s, "src=" NIP6_FMT " dst=" NIP6_FMT " ", NIP6(*((struct in6_addr *)tuple->src.u3.ip6)), NIP6(*((struct in6_addr *)tuple->dst.u3.ip6))); } @@ -584,7 +584,7 @@ MODULE_AUTHOR("Yasuyuki KOZAKAI @USAGI <yasuyuki.kozakai@toshiba.co.jp>"); static int __init init(void) { - need_nf_conntrack(); + need_conntrack(); return init_or_cleanup(1); } @@ -595,9 +595,3 @@ static void __exit fini(void) module_init(init); module_exit(fini); - -void need_ip6_conntrack(void) -{ -} - -EXPORT_SYMBOL(need_ip6_conntrack); diff --git a/net/ipv6/netfilter/nf_conntrack_reasm.c b/net/ipv6/netfilter/nf_conntrack_reasm.c index f3e5ffbd592..84ef9a13108 100644 --- a/net/ipv6/netfilter/nf_conntrack_reasm.c +++ b/net/ipv6/netfilter/nf_conntrack_reasm.c @@ -70,8 +70,8 @@ struct nf_ct_frag6_skb_cb struct nf_ct_frag6_queue { - struct nf_ct_frag6_queue *next; - struct list_head lru_list; /* lru list member */ + struct hlist_node list; + struct list_head lru_list; /* lru list member */ __u32 id; /* fragment id */ struct in6_addr saddr; @@ -90,14 +90,13 @@ struct nf_ct_frag6_queue #define FIRST_IN 2 #define LAST_IN 1 __u16 nhoffset; - struct nf_ct_frag6_queue **pprev; }; /* Hash table. */ #define FRAG6Q_HASHSZ 64 -static struct nf_ct_frag6_queue *nf_ct_frag6_hash[FRAG6Q_HASHSZ]; +static struct hlist_head nf_ct_frag6_hash[FRAG6Q_HASHSZ]; static DEFINE_RWLOCK(nf_ct_frag6_lock); static u32 nf_ct_frag6_hash_rnd; static LIST_HEAD(nf_ct_frag6_lru_list); @@ -105,9 +104,7 @@ int nf_ct_frag6_nqueues = 0; static __inline__ void __fq_unlink(struct nf_ct_frag6_queue *fq) { - if (fq->next) - fq->next->pprev = fq->pprev; - *fq->pprev = fq->next; + hlist_del(&fq->list); list_del(&fq->lru_list); nf_ct_frag6_nqueues--; } @@ -158,28 +155,18 @@ static void nf_ct_frag6_secret_rebuild(unsigned long dummy) get_random_bytes(&nf_ct_frag6_hash_rnd, sizeof(u32)); for (i = 0; i < FRAG6Q_HASHSZ; i++) { struct nf_ct_frag6_queue *q; + struct hlist_node *p, *n; - q = nf_ct_frag6_hash[i]; - while (q) { - struct nf_ct_frag6_queue *next = q->next; + hlist_for_each_entry_safe(q, p, n, &nf_ct_frag6_hash[i], list) { unsigned int hval = ip6qhashfn(q->id, &q->saddr, &q->daddr); - if (hval != i) { - /* Unlink. */ - if (q->next) - q->next->pprev = q->pprev; - *q->pprev = q->next; - + hlist_del(&q->list); /* Relink to new hash chain. */ - if ((q->next = nf_ct_frag6_hash[hval]) != NULL) - q->next->pprev = &q->next; - nf_ct_frag6_hash[hval] = q; - q->pprev = &nf_ct_frag6_hash[hval]; + hlist_add_head(&q->list, + &nf_ct_frag6_hash[hval]); } - - q = next; } } write_unlock(&nf_ct_frag6_lock); @@ -314,15 +301,17 @@ out: /* Creation primitives. */ - static struct nf_ct_frag6_queue *nf_ct_frag6_intern(unsigned int hash, struct nf_ct_frag6_queue *fq_in) { struct nf_ct_frag6_queue *fq; +#ifdef CONFIG_SMP + struct hlist_node *n; +#endif write_lock(&nf_ct_frag6_lock); #ifdef CONFIG_SMP - for (fq = nf_ct_frag6_hash[hash]; fq; fq = fq->next) { + hlist_for_each_entry(fq, n, &nf_ct_frag6_hash[hash], list) { if (fq->id == fq_in->id && !ipv6_addr_cmp(&fq_in->saddr, &fq->saddr) && !ipv6_addr_cmp(&fq_in->daddr, &fq->daddr)) { @@ -340,10 +329,7 @@ static struct nf_ct_frag6_queue *nf_ct_frag6_intern(unsigned int hash, atomic_inc(&fq->refcnt); atomic_inc(&fq->refcnt); - if ((fq->next = nf_ct_frag6_hash[hash]) != NULL) - fq->next->pprev = &fq->next; - nf_ct_frag6_hash[hash] = fq; - fq->pprev = &nf_ct_frag6_hash[hash]; + hlist_add_head(&fq->list, &nf_ct_frag6_hash[hash]); INIT_LIST_HEAD(&fq->lru_list); list_add_tail(&fq->lru_list, &nf_ct_frag6_lru_list); nf_ct_frag6_nqueues++; @@ -384,10 +370,11 @@ static __inline__ struct nf_ct_frag6_queue * fq_find(u32 id, struct in6_addr *src, struct in6_addr *dst) { struct nf_ct_frag6_queue *fq; + struct hlist_node *n; unsigned int hash = ip6qhashfn(id, src, dst); read_lock(&nf_ct_frag6_lock); - for (fq = nf_ct_frag6_hash[hash]; fq; fq = fq->next) { + hlist_for_each_entry(fq, n, &nf_ct_frag6_hash[hash], list) { if (fq->id == id && !ipv6_addr_cmp(src, &fq->saddr) && !ipv6_addr_cmp(dst, &fq->daddr)) { diff --git a/net/ipv6/xfrm6_state.c b/net/ipv6/xfrm6_state.c index bf0d0abc387..a5723024d3b 100644 --- a/net/ipv6/xfrm6_state.c +++ b/net/ipv6/xfrm6_state.c @@ -15,6 +15,7 @@ #include <linux/pfkeyv2.h> #include <linux/ipsec.h> #include <net/ipv6.h> +#include <net/addrconf.h> static struct xfrm_state_afinfo xfrm6_state_afinfo; @@ -41,6 +42,22 @@ __xfrm6_init_tempsel(struct xfrm_state *x, struct flowi *fl, memcpy(&x->props.saddr, &tmpl->saddr, sizeof(x->props.saddr)); if (ipv6_addr_any((struct in6_addr*)&x->props.saddr)) memcpy(&x->props.saddr, saddr, sizeof(x->props.saddr)); + if (tmpl->mode && ipv6_addr_any((struct in6_addr*)&x->props.saddr)) { + struct rt6_info *rt; + struct flowi fl_tunnel = { + .nl_u = { + .ip6_u = { + .daddr = *(struct in6_addr *)daddr, + } + } + }; + if (!xfrm_dst_lookup((struct xfrm_dst **)&rt, + &fl_tunnel, AF_INET6)) { + ipv6_get_saddr(&rt->u.dst, (struct in6_addr *)daddr, + (struct in6_addr *)&x->props.saddr); + dst_release(&rt->u.dst); + } + } x->props.mode = tmpl->mode; x->props.reqid = tmpl->reqid; x->props.family = AF_INET6; diff --git a/net/ipv6/xfrm6_tunnel.c b/net/ipv6/xfrm6_tunnel.c index da09ff25864..8cfc58b96fc 100644 --- a/net/ipv6/xfrm6_tunnel.c +++ b/net/ipv6/xfrm6_tunnel.c @@ -259,8 +259,7 @@ try_next_2:; spi = 0; goto out; alloc_spi: - X6TPRINTK3(KERN_DEBUG "%s(): allocate new spi for " - "%04x:%04x:%04x:%04x:%04x:%04x:%04x:%04x\n", + X6TPRINTK3(KERN_DEBUG "%s(): allocate new spi for " NIP6_FMT "\n", __FUNCTION__, NIP6(*(struct in6_addr *)saddr)); x6spi = kmem_cache_alloc(xfrm6_tunnel_spi_kmem, SLAB_ATOMIC); @@ -323,9 +322,8 @@ void xfrm6_tunnel_free_spi(xfrm_address_t *saddr) list_byaddr) { if (memcmp(&x6spi->addr, saddr, sizeof(x6spi->addr)) == 0) { - X6TPRINTK3(KERN_DEBUG "%s(): x6spi object " - "for %04x:%04x:%04x:%04x:%04x:%04x:%04x:%04x " - "found at %p\n", + X6TPRINTK3(KERN_DEBUG "%s(): x6spi object for " NIP6_FMT + " found at %p\n", __FUNCTION__, NIP6(*(struct in6_addr *)saddr), x6spi); diff --git a/net/netfilter/Kconfig b/net/netfilter/Kconfig index 7d55f9cbd85..99c0a0fa4a9 100644 --- a/net/netfilter/Kconfig +++ b/net/netfilter/Kconfig @@ -103,3 +103,261 @@ config NF_CT_NETLINK This option enables support for a netlink-based userspace interface endmenu + +config NETFILTER_XTABLES + tristate "Netfilter Xtables support (required for ip_tables)" + help + This is required if you intend to use any of ip_tables, + ip6_tables or arp_tables. + +# alphabetically ordered list of targets + +config NETFILTER_XT_TARGET_CLASSIFY + tristate '"CLASSIFY" target support' + depends on NETFILTER_XTABLES + help + This option adds a `CLASSIFY' target, which enables the user to set + the priority of a packet. Some qdiscs can use this value for + classification, among these are: + + atm, cbq, dsmark, pfifo_fast, htb, prio + + To compile it as a module, choose M here. If unsure, say N. + +config NETFILTER_XT_TARGET_CONNMARK + tristate '"CONNMARK" target support' + depends on NETFILTER_XTABLES + depends on IP_NF_MANGLE || IP6_NF_MANGLE + depends on (IP_NF_CONNTRACK && IP_NF_CONNTRACK_MARK) || (NF_CONNTRACK_MARK && NF_CONNTRACK_IPV4) + help + This option adds a `CONNMARK' target, which allows one to manipulate + the connection mark value. Similar to the MARK target, but + affects the connection mark value rather than the packet mark value. + + If you want to compile it as a module, say M here and read + <file:Documentation/modules.txt>. The module will be called + ipt_CONNMARK.o. If unsure, say `N'. + +config NETFILTER_XT_TARGET_MARK + tristate '"MARK" target support' + depends on NETFILTER_XTABLES + help + This option adds a `MARK' target, which allows you to create rules + in the `mangle' table which alter the netfilter mark (nfmark) field + associated with the packet prior to routing. This can change + the routing method (see `Use netfilter MARK value as routing + key') and can also be used by other subsystems to change their + behavior. + + To compile it as a module, choose M here. If unsure, say N. + +config NETFILTER_XT_TARGET_NFQUEUE + tristate '"NFQUEUE" target Support' + depends on NETFILTER_XTABLES + help + This Target replaced the old obsolete QUEUE target. + + As opposed to QUEUE, it supports 65535 different queues, + not just one. + + To compile it as a module, choose M here. If unsure, say N. + +config NETFILTER_XT_TARGET_NOTRACK + tristate '"NOTRACK" target support' + depends on NETFILTER_XTABLES + depends on IP_NF_RAW || IP6_NF_RAW + depends on IP_NF_CONNTRACK || NF_CONNTRACK + help + The NOTRACK target allows a select rule to specify + which packets *not* to enter the conntrack/NAT + subsystem with all the consequences (no ICMP error tracking, + no protocol helpers for the selected packets). + + If you want to compile it as a module, say M here and read + <file:Documentation/modules.txt>. If unsure, say `N'. + +config NETFILTER_XT_MATCH_COMMENT + tristate '"comment" match support' + depends on NETFILTER_XTABLES + help + This option adds a `comment' dummy-match, which allows you to put + comments in your iptables ruleset. + + If you want to compile it as a module, say M here and read + <file:Documentation/modules.txt>. If unsure, say `N'. + +config NETFILTER_XT_MATCH_CONNBYTES + tristate '"connbytes" per-connection counter match support' + depends on NETFILTER_XTABLES + depends on (IP_NF_CONNTRACK && IP_NF_CT_ACCT) || NF_CT_ACCT + help + This option adds a `connbytes' match, which allows you to match the + number of bytes and/or packets for each direction within a connection. + + If you want to compile it as a module, say M here and read + <file:Documentation/modules.txt>. If unsure, say `N'. + +config NETFILTER_XT_MATCH_CONNMARK + tristate '"connmark" connection mark match support' + depends on NETFILTER_XTABLES + depends on (IP_NF_CONNTRACK && IP_NF_CONNTRACK_MARK) || NF_CONNTRACK_MARK + help + This option adds a `connmark' match, which allows you to match the + connection mark value previously set for the session by `CONNMARK'. + + If you want to compile it as a module, say M here and read + <file:Documentation/modules.txt>. The module will be called + ipt_connmark.o. If unsure, say `N'. + +config NETFILTER_XT_MATCH_CONNTRACK + tristate '"conntrack" connection tracking match support' + depends on NETFILTER_XTABLES + depends on IP_NF_CONNTRACK || NF_CONNTRACK + help + This is a general conntrack match module, a superset of the state match. + + It allows matching on additional conntrack information, which is + useful in complex configurations, such as NAT gateways with multiple + internet links or tunnels. + + To compile it as a module, choose M here. If unsure, say N. + +config NETFILTER_XT_MATCH_DCCP + tristate '"DCCP" protocol match support' + depends on NETFILTER_XTABLES + help + With this option enabled, you will be able to use the iptables + `dccp' match in order to match on DCCP source/destination ports + and DCCP flags. + + If you want to compile it as a module, say M here and read + <file:Documentation/modules.txt>. If unsure, say `N'. + +config NETFILTER_XT_MATCH_HELPER + tristate '"helper" match support' + depends on NETFILTER_XTABLES + depends on IP_NF_CONNTRACK || NF_CONNTRACK + help + Helper matching allows you to match packets in dynamic connections + tracked by a conntrack-helper, ie. ip_conntrack_ftp + + To compile it as a module, choose M here. If unsure, say Y. + +config NETFILTER_XT_MATCH_LENGTH + tristate '"length" match support' + depends on NETFILTER_XTABLES + help + This option allows you to match the length of a packet against a + specific value or range of values. + + To compile it as a module, choose M here. If unsure, say N. + +config NETFILTER_XT_MATCH_LIMIT + tristate '"limit" match support' + depends on NETFILTER_XTABLES + help + limit matching allows you to control the rate at which a rule can be + matched: mainly useful in combination with the LOG target ("LOG + target support", below) and to avoid some Denial of Service attacks. + + To compile it as a module, choose M here. If unsure, say N. + +config NETFILTER_XT_MATCH_MAC + tristate '"mac" address match support' + depends on NETFILTER_XTABLES + help + MAC matching allows you to match packets based on the source + Ethernet address of the packet. + + To compile it as a module, choose M here. If unsure, say N. + +config NETFILTER_XT_MATCH_MARK + tristate '"mark" match support' + depends on NETFILTER_XTABLES + help + Netfilter mark matching allows you to match packets based on the + `nfmark' value in the packet. This can be set by the MARK target + (see below). + + To compile it as a module, choose M here. If unsure, say N. + +config NETFILTER_XT_MATCH_PHYSDEV + tristate '"physdev" match support' + depends on NETFILTER_XTABLES && BRIDGE_NETFILTER + help + Physdev packet matching matches against the physical bridge ports + the IP packet arrived on or will leave by. + + To compile it as a module, choose M here. If unsure, say N. + +config NETFILTER_XT_MATCH_PKTTYPE + tristate '"pkttype" packet type match support' + depends on NETFILTER_XTABLES + help + Packet type matching allows you to match a packet by + its "class", eg. BROADCAST, MULTICAST, ... + + Typical usage: + iptables -A INPUT -m pkttype --pkt-type broadcast -j LOG + + To compile it as a module, choose M here. If unsure, say N. + +config NETFILTER_XT_MATCH_REALM + tristate '"realm" match support' + depends on NETFILTER_XTABLES + select NET_CLS_ROUTE + help + This option adds a `realm' match, which allows you to use the realm + key from the routing subsystem inside iptables. + + This match pretty much resembles the CONFIG_NET_CLS_ROUTE4 option + in tc world. + + If you want to compile it as a module, say M here and read + <file:Documentation/modules.txt>. If unsure, say `N'. + +config NETFILTER_XT_MATCH_SCTP + tristate '"sctp" protocol match support' + depends on NETFILTER_XTABLES + help + With this option enabled, you will be able to use the + `sctp' match in order to match on SCTP source/destination ports + and SCTP chunk types. + + If you want to compile it as a module, say M here and read + <file:Documentation/modules.txt>. If unsure, say `N'. + +config NETFILTER_XT_MATCH_STATE + tristate '"state" match support' + depends on NETFILTER_XTABLES + depends on IP_NF_CONNTRACK || NF_CONNTRACK + help + Connection state matching allows you to match packets based on their + relationship to a tracked connection (ie. previous packets). This + is a powerful tool for packet classification. + + To compile it as a module, choose M here. If unsure, say N. + +config NETFILTER_XT_MATCH_STRING + tristate '"string" match support' + depends on NETFILTER_XTABLES + select TEXTSEARCH + select TEXTSEARCH_KMP + select TEXTSEARCH_BM + select TEXTSEARCH_FSM + help + This option adds a `string' match, which allows you to look for + pattern matchings in packets. + + To compile it as a module, choose M here. If unsure, say N. + +config NETFILTER_XT_MATCH_TCPMSS + tristate '"tcpmss" match support' + depends on NETFILTER_XTABLES + help + This option adds a `tcpmss' match, which allows you to examine the + MSS value of TCP SYN packets, which control the maximum packet size + for that connection. + + To compile it as a module, choose M here. If unsure, say N. + diff --git a/net/netfilter/Makefile b/net/netfilter/Makefile index cb2183145c3..746172ebc91 100644 --- a/net/netfilter/Makefile +++ b/net/netfilter/Makefile @@ -1,4 +1,5 @@ netfilter-objs := core.o nf_log.o nf_queue.o nf_sockopt.o +nf_conntrack-objs := nf_conntrack_core.o nf_conntrack_standalone.o nf_conntrack_l3proto_generic.o nf_conntrack_proto_generic.o nf_conntrack_proto_tcp.o nf_conntrack_proto_udp.o obj-$(CONFIG_NETFILTER) = netfilter.o @@ -6,13 +7,43 @@ obj-$(CONFIG_NETFILTER_NETLINK) += nfnetlink.o obj-$(CONFIG_NETFILTER_NETLINK_QUEUE) += nfnetlink_queue.o obj-$(CONFIG_NETFILTER_NETLINK_LOG) += nfnetlink_log.o -nf_conntrack-objs := nf_conntrack_core.o nf_conntrack_standalone.o nf_conntrack_l3proto_generic.o nf_conntrack_proto_generic.o nf_conntrack_proto_tcp.o nf_conntrack_proto_udp.o - +# connection tracking obj-$(CONFIG_NF_CONNTRACK) += nf_conntrack.o -obj-$(CONFIG_NF_CONNTRACK_FTP) += nf_conntrack_ftp.o # SCTP protocol connection tracking obj-$(CONFIG_NF_CT_PROTO_SCTP) += nf_conntrack_proto_sctp.o # netlink interface for nf_conntrack obj-$(CONFIG_NF_CT_NETLINK) += nf_conntrack_netlink.o + +# connection tracking helpers +obj-$(CONFIG_NF_CONNTRACK_FTP) += nf_conntrack_ftp.o + +# generic X tables +obj-$(CONFIG_NETFILTER_XTABLES) += x_tables.o xt_tcpudp.o + +# targets +obj-$(CONFIG_NETFILTER_XT_TARGET_CLASSIFY) += xt_CLASSIFY.o +obj-$(CONFIG_NETFILTER_XT_TARGET_CONNMARK) += xt_CONNMARK.o +obj-$(CONFIG_NETFILTER_XT_TARGET_MARK) += xt_MARK.o +obj-$(CONFIG_NETFILTER_XT_TARGET_NFQUEUE) += xt_NFQUEUE.o +obj-$(CONFIG_NETFILTER_XT_TARGET_NOTRACK) += xt_NOTRACK.o + +# matches +obj-$(CONFIG_NETFILTER_XT_MATCH_COMMENT) += xt_comment.o +obj-$(CONFIG_NETFILTER_XT_MATCH_CONNBYTES) += xt_connbytes.o +obj-$(CONFIG_NETFILTER_XT_MATCH_CONNMARK) += xt_connmark.o +obj-$(CONFIG_NETFILTER_XT_MATCH_CONNTRACK) += xt_conntrack.o +obj-$(CONFIG_NETFILTER_XT_MATCH_DCCP) += xt_dccp.o +obj-$(CONFIG_NETFILTER_XT_MATCH_HELPER) += xt_helper.o +obj-$(CONFIG_NETFILTER_XT_MATCH_LENGTH) += xt_length.o +obj-$(CONFIG_NETFILTER_XT_MATCH_LIMIT) += xt_limit.o +obj-$(CONFIG_NETFILTER_XT_MATCH_MAC) += xt_mac.o +obj-$(CONFIG_NETFILTER_XT_MATCH_MARK) += xt_mark.o +obj-$(CONFIG_NETFILTER_XT_MATCH_PKTTYPE) += xt_pkttype.o +obj-$(CONFIG_NETFILTER_XT_MATCH_REALM) += xt_realm.o +obj-$(CONFIG_NETFILTER_XT_MATCH_SCTP) += xt_sctp.o +obj-$(CONFIG_NETFILTER_XT_MATCH_STATE) += xt_state.o +obj-$(CONFIG_NETFILTER_XT_MATCH_STRING) += xt_string.o +obj-$(CONFIG_NETFILTER_XT_MATCH_TCPMSS) += xt_tcpmss.o +obj-$(CONFIG_NETFILTER_XT_MATCH_PHYSDEV) += xt_physdev.o diff --git a/net/netfilter/nf_conntrack_ftp.c b/net/netfilter/nf_conntrack_ftp.c index d5a6eaf4a1d..ab0c920f0d3 100644 --- a/net/netfilter/nf_conntrack_ftp.c +++ b/net/netfilter/nf_conntrack_ftp.c @@ -545,11 +545,11 @@ static int help(struct sk_buff **pskb, different IP address. Simply don't record it for NAT. */ if (cmd.l3num == PF_INET) { - DEBUGP("conntrack_ftp: NOT RECORDING: %u,%u,%u,%u != %u.%u.%u.%u\n", + DEBUGP("conntrack_ftp: NOT RECORDING: " NIPQUAD_FMT " != " NIPQUAD_FMT "\n", NIPQUAD(cmd.u3.ip), NIPQUAD(ct->tuplehash[dir].tuple.src.u3.ip)); } else { - DEBUGP("conntrack_ftp: NOT RECORDING: %x:%x:%x:%x:%x:%x:%x:%x != %x:%x:%x:%x:%x:%x:%x:%x\n", + DEBUGP("conntrack_ftp: NOT RECORDING: " NIP6_FMT " != " NIP6_FMT "\n", NIP6(*((struct in6_addr *)cmd.u3.ip6)), NIP6(*((struct in6_addr *)ct->tuplehash[dir] .tuple.src.u3.ip6))); diff --git a/net/netfilter/nf_conntrack_standalone.c b/net/netfilter/nf_conntrack_standalone.c index 3531d142f69..617599aeeea 100644 --- a/net/netfilter/nf_conntrack_standalone.c +++ b/net/netfilter/nf_conntrack_standalone.c @@ -821,7 +821,7 @@ module_exit(fini); /* Some modules need us, but don't depend directly on any symbol. They should call this. */ -void need_nf_conntrack(void) +void need_conntrack(void) { } @@ -841,7 +841,7 @@ EXPORT_SYMBOL(nf_conntrack_protocol_unregister); EXPORT_SYMBOL(nf_ct_invert_tuplepr); EXPORT_SYMBOL(nf_conntrack_alter_reply); EXPORT_SYMBOL(nf_conntrack_destroyed); -EXPORT_SYMBOL(need_nf_conntrack); +EXPORT_SYMBOL(need_conntrack); EXPORT_SYMBOL(nf_conntrack_helper_register); EXPORT_SYMBOL(nf_conntrack_helper_unregister); EXPORT_SYMBOL(nf_ct_iterate_cleanup); diff --git a/net/netfilter/x_tables.c b/net/netfilter/x_tables.c new file mode 100644 index 00000000000..d7817afc6b9 --- /dev/null +++ b/net/netfilter/x_tables.c @@ -0,0 +1,624 @@ +/* + * x_tables core - Backend for {ip,ip6,arp}_tables + * + * Copyright (C) 2006-2006 Harald Welte <laforge@netfilter.org> + * + * Based on existing ip_tables code which is + * Copyright (C) 1999 Paul `Rusty' Russell & Michael J. Neuling + * Copyright (C) 2000-2005 Netfilter Core Team <coreteam@netfilter.org> + * + * This program is free software; you can redistribute it and/or modify + * it under the terms of the GNU General Public License version 2 as + * published by the Free Software Foundation. + * + */ + +#include <linux/config.h> +#include <linux/kernel.h> +#include <linux/socket.h> +#include <linux/net.h> +#include <linux/proc_fs.h> +#include <linux/seq_file.h> +#include <linux/string.h> +#include <linux/vmalloc.h> + +#include <linux/netfilter/x_tables.h> +#include <linux/netfilter_arp.h> + +MODULE_LICENSE("GPL"); +MODULE_AUTHOR("Harald Welte <laforge@netfilter.org>"); +MODULE_DESCRIPTION("[ip,ip6,arp]_tables backend module"); + +#define SMP_ALIGN(x) (((x) + SMP_CACHE_BYTES-1) & ~(SMP_CACHE_BYTES-1)) + +struct xt_af { + struct semaphore mutex; + struct list_head match; + struct list_head target; + struct list_head tables; +}; + +static struct xt_af *xt; + +#ifdef DEBUG_IP_FIREWALL_USER +#define duprintf(format, args...) printk(format , ## args) +#else +#define duprintf(format, args...) +#endif + +enum { + TABLE, + TARGET, + MATCH, +}; + +/* Registration hooks for targets. */ +int +xt_register_target(int af, struct xt_target *target) +{ + int ret; + + ret = down_interruptible(&xt[af].mutex); + if (ret != 0) + return ret; + list_add(&target->list, &xt[af].target); + up(&xt[af].mutex); + return ret; +} +EXPORT_SYMBOL(xt_register_target); + +void +xt_unregister_target(int af, struct xt_target *target) +{ + down(&xt[af].mutex); + LIST_DELETE(&xt[af].target, target); + up(&xt[af].mutex); +} +EXPORT_SYMBOL(xt_unregister_target); + +int +xt_register_match(int af, struct xt_match *match) +{ + int ret; + + ret = down_interruptible(&xt[af].mutex); + if (ret != 0) + return ret; + + list_add(&match->list, &xt[af].match); + up(&xt[af].mutex); + + return ret; +} +EXPORT_SYMBOL(xt_register_match); + +void +xt_unregister_match(int af, struct xt_match *match) +{ + down(&xt[af].mutex); + LIST_DELETE(&xt[af].match, match); + up(&xt[af].mutex); +} +EXPORT_SYMBOL(xt_unregister_match); + + +/* + * These are weird, but module loading must not be done with mutex + * held (since they will register), and we have to have a single + * function to use try_then_request_module(). + */ + +/* Find match, grabs ref. Returns ERR_PTR() on error. */ +struct xt_match *xt_find_match(int af, const char *name, u8 revision) +{ + struct xt_match *m; + int err = 0; + + if (down_interruptible(&xt[af].mutex) != 0) + return ERR_PTR(-EINTR); + + list_for_each_entry(m, &xt[af].match, list) { + if (strcmp(m->name, name) == 0) { + if (m->revision == revision) { + if (try_module_get(m->me)) { + up(&xt[af].mutex); + return m; + } + } else + err = -EPROTOTYPE; /* Found something. */ + } + } + up(&xt[af].mutex); + return ERR_PTR(err); +} +EXPORT_SYMBOL(xt_find_match); + +/* Find target, grabs ref. Returns ERR_PTR() on error. */ +struct xt_target *xt_find_target(int af, const char *name, u8 revision) +{ + struct xt_target *t; + int err = 0; + + if (down_interruptible(&xt[af].mutex) != 0) + return ERR_PTR(-EINTR); + + list_for_each_entry(t, &xt[af].target, list) { + if (strcmp(t->name, name) == 0) { + if (t->revision == revision) { + if (try_module_get(t->me)) { + up(&xt[af].mutex); + return t; + } + } else + err = -EPROTOTYPE; /* Found something. */ + } + } + up(&xt[af].mutex); + return ERR_PTR(err); +} +EXPORT_SYMBOL(xt_find_target); + +static const char *xt_prefix[NPROTO] = { + [AF_INET] = "ipt_%s", + [AF_INET6] = "ip6t_%s", + [NF_ARP] = "arpt_%s", +}; + +struct xt_target *xt_request_find_target(int af, const char *name, u8 revision) +{ + struct xt_target *target; + + target = try_then_request_module(xt_find_target(af, name, revision), + xt_prefix[af], name); + if (IS_ERR(target) || !target) + return NULL; + return target; +} +EXPORT_SYMBOL_GPL(xt_request_find_target); + +static int match_revfn(int af, const char *name, u8 revision, int *bestp) +{ + struct xt_match *m; + int have_rev = 0; + + list_for_each_entry(m, &xt[af].match, list) { + if (strcmp(m->name, name) == 0) { + if (m->revision > *bestp) + *bestp = m->revision; + if (m->revision == revision) + have_rev = 1; + } + } + return have_rev; +} + +static int target_revfn(int af, const char *name, u8 revision, int *bestp) +{ + struct xt_target *t; + int have_rev = 0; + + list_for_each_entry(t, &xt[af].target, list) { + if (strcmp(t->name, name) == 0) { + if (t->revision > *bestp) + *bestp = t->revision; + if (t->revision == revision) + have_rev = 1; + } + } + return have_rev; +} + +/* Returns true or false (if no such extension at all) */ +int xt_find_revision(int af, const char *name, u8 revision, int target, + int *err) +{ + int have_rev, best = -1; + + if (down_interruptible(&xt[af].mutex) != 0) { + *err = -EINTR; + return 1; + } + if (target == 1) + have_rev = target_revfn(af, name, revision, &best); + else + have_rev = match_revfn(af, name, revision, &best); + up(&xt[af].mutex); + + /* Nothing at all? Return 0 to try loading module. */ + if (best == -1) { + *err = -ENOENT; + return 0; + } + + *err = best; + if (!have_rev) + *err = -EPROTONOSUPPORT; + return 1; +} +EXPORT_SYMBOL_GPL(xt_find_revision); + +struct xt_table_info *xt_alloc_table_info(unsigned int size) +{ + struct xt_table_info *newinfo; + int cpu; + + /* Pedantry: prevent them from hitting BUG() in vmalloc.c --RR */ + if ((SMP_ALIGN(size) >> PAGE_SHIFT) + 2 > num_physpages) + return NULL; + + newinfo = kzalloc(sizeof(struct xt_table_info), GFP_KERNEL); + if (!newinfo) + return NULL; + + newinfo->size = size; + + for_each_cpu(cpu) { + if (size <= PAGE_SIZE) + newinfo->entries[cpu] = kmalloc_node(size, + GFP_KERNEL, + cpu_to_node(cpu)); + else + newinfo->entries[cpu] = vmalloc_node(size, + cpu_to_node(cpu)); + + if (newinfo->entries[cpu] == NULL) { + xt_free_table_info(newinfo); + return NULL; + } + } + + return newinfo; +} +EXPORT_SYMBOL(xt_alloc_table_info); + +void xt_free_table_info(struct xt_table_info *info) +{ + int cpu; + + for_each_cpu(cpu) { + if (info->size <= PAGE_SIZE) + kfree(info->entries[cpu]); + else + vfree(info->entries[cpu]); + } + kfree(info); +} +EXPORT_SYMBOL(xt_free_table_info); + +/* Find table by name, grabs mutex & ref. Returns ERR_PTR() on error. */ +struct xt_table *xt_find_table_lock(int af, const char *name) +{ + struct xt_table *t; + + if (down_interruptible(&xt[af].mutex) != 0) + return ERR_PTR(-EINTR); + + list_for_each_entry(t, &xt[af].tables, list) + if (strcmp(t->name, name) == 0 && try_module_get(t->me)) + return t; + up(&xt[af].mutex); + return NULL; +} +EXPORT_SYMBOL_GPL(xt_find_table_lock); + +void xt_table_unlock(struct xt_table *table) +{ + up(&xt[table->af].mutex); +} +EXPORT_SYMBOL_GPL(xt_table_unlock); + + +struct xt_table_info * +xt_replace_table(struct xt_table *table, + unsigned int num_counters, + struct xt_table_info *newinfo, + int *error) +{ + struct xt_table_info *oldinfo, *private; + + /* Do the substitution. */ + write_lock_bh(&table->lock); + private = table->private; + /* Check inside lock: is the old number correct? */ + if (num_counters != private->number) { + duprintf("num_counters != table->private->number (%u/%u)\n", + num_counters, private->number); + write_unlock_bh(&table->lock); + *error = -EAGAIN; + return NULL; + } + oldinfo = private; + table->private = newinfo; + newinfo->initial_entries = oldinfo->initial_entries; + write_unlock_bh(&table->lock); + + return oldinfo; +} +EXPORT_SYMBOL_GPL(xt_replace_table); + +int xt_register_table(struct xt_table *table, + struct xt_table_info *bootstrap, + struct xt_table_info *newinfo) +{ + int ret; + struct xt_table_info *private; + + ret = down_interruptible(&xt[table->af].mutex); + if (ret != 0) + return ret; + + /* Don't autoload: we'd eat our tail... */ + if (list_named_find(&xt[table->af].tables, table->name)) { + ret = -EEXIST; + goto unlock; + } + + /* Simplifies replace_table code. */ + table->private = bootstrap; + if (!xt_replace_table(table, 0, newinfo, &ret)) + goto unlock; + + private = table->private; + duprintf("table->private->number = %u\n", private->number); + + /* save number of initial entries */ + private->initial_entries = private->number; + + rwlock_init(&table->lock); + list_prepend(&xt[table->af].tables, table); + + ret = 0; + unlock: + up(&xt[table->af].mutex); + return ret; +} +EXPORT_SYMBOL_GPL(xt_register_table); + +void *xt_unregister_table(struct xt_table *table) +{ + struct xt_table_info *private; + + down(&xt[table->af].mutex); + private = table->private; + LIST_DELETE(&xt[table->af].tables, table); + up(&xt[table->af].mutex); + + return private; +} +EXPORT_SYMBOL_GPL(xt_unregister_table); + +#ifdef CONFIG_PROC_FS +static char *xt_proto_prefix[NPROTO] = { + [AF_INET] = "ip", + [AF_INET6] = "ip6", + [NF_ARP] = "arp", +}; + +static struct list_head *xt_get_idx(struct list_head *list, struct seq_file *seq, loff_t pos) +{ + struct list_head *head = list->next; + + if (!head || list_empty(list)) + return NULL; + + while (pos && (head = head->next)) { + if (head == list) + return NULL; + pos--; + } + return pos ? NULL : head; +} + +static struct list_head *type2list(u_int16_t af, u_int16_t type) +{ + struct list_head *list; + + switch (type) { + case TARGET: + list = &xt[af].target; + break; + case MATCH: + list = &xt[af].match; + break; + case TABLE: + list = &xt[af].tables; + break; + default: + list = NULL; + break; + } + + return list; +} + +static void *xt_tgt_seq_start(struct seq_file *seq, loff_t *pos) +{ + struct proc_dir_entry *pde = (struct proc_dir_entry *) seq->private; + u_int16_t af = (unsigned long)pde->data & 0xffff; + u_int16_t type = (unsigned long)pde->data >> 16; + struct list_head *list; + + if (af >= NPROTO) + return NULL; + + list = type2list(af, type); + if (!list) + return NULL; + + if (down_interruptible(&xt[af].mutex) != 0) + return NULL; + + return xt_get_idx(list, seq, *pos); +} + +static void *xt_tgt_seq_next(struct seq_file *seq, void *v, loff_t *pos) +{ + struct proc_dir_entry *pde = seq->private; + u_int16_t af = (unsigned long)pde->data & 0xffff; + u_int16_t type = (unsigned long)pde->data >> 16; + struct list_head *list; + + if (af >= NPROTO) + return NULL; + + list = type2list(af, type); + if (!list) + return NULL; + + (*pos)++; + return xt_get_idx(list, seq, *pos); +} + +static void xt_tgt_seq_stop(struct seq_file *seq, void *v) +{ + struct proc_dir_entry *pde = seq->private; + u_int16_t af = (unsigned long)pde->data & 0xffff; + + up(&xt[af].mutex); +} + +static int xt_name_seq_show(struct seq_file *seq, void *v) +{ + char *name = (char *)v + sizeof(struct list_head); + + if (strlen(name)) + return seq_printf(seq, "%s\n", name); + else + return 0; +} + +static struct seq_operations xt_tgt_seq_ops = { + .start = xt_tgt_seq_start, + .next = xt_tgt_seq_next, + .stop = xt_tgt_seq_stop, + .show = xt_name_seq_show, +}; + +static int xt_tgt_open(struct inode *inode, struct file *file) +{ + int ret; + + ret = seq_open(file, &xt_tgt_seq_ops); + if (!ret) { + struct seq_file *seq = file->private_data; + struct proc_dir_entry *pde = PDE(inode); + + seq->private = pde; + } + + return ret; +} + +static struct file_operations xt_file_ops = { + .owner = THIS_MODULE, + .open = xt_tgt_open, + .read = seq_read, + .llseek = seq_lseek, + .release = seq_release, +}; + +#define FORMAT_TABLES "_tables_names" +#define FORMAT_MATCHES "_tables_matches" +#define FORMAT_TARGETS "_tables_targets" + +#endif /* CONFIG_PROC_FS */ + +int xt_proto_init(int af) +{ +#ifdef CONFIG_PROC_FS + char buf[XT_FUNCTION_MAXNAMELEN]; + struct proc_dir_entry *proc; +#endif + + if (af >= NPROTO) + return -EINVAL; + + +#ifdef CONFIG_PROC_FS + strlcpy(buf, xt_proto_prefix[af], sizeof(buf)); + strlcat(buf, FORMAT_TABLES, sizeof(buf)); + proc = proc_net_fops_create(buf, 0440, &xt_file_ops); + if (!proc) + goto out; + proc->data = (void *) ((unsigned long) af | (TABLE << 16)); + + + strlcpy(buf, xt_proto_prefix[af], sizeof(buf)); + strlcat(buf, FORMAT_MATCHES, sizeof(buf)); + proc = proc_net_fops_create(buf, 0440, &xt_file_ops); + if (!proc) + goto out_remove_tables; + proc->data = (void *) ((unsigned long) af | (MATCH << 16)); + + strlcpy(buf, xt_proto_prefix[af], sizeof(buf)); + strlcat(buf, FORMAT_TARGETS, sizeof(buf)); + proc = proc_net_fops_create(buf, 0440, &xt_file_ops); + if (!proc) + goto out_remove_matches; + proc->data = (void *) ((unsigned long) af | (TARGET << 16)); +#endif + + return 0; + +#ifdef CONFIG_PROC_FS +out_remove_matches: + strlcpy(buf, xt_proto_prefix[af], sizeof(buf)); + strlcat(buf, FORMAT_MATCHES, sizeof(buf)); + proc_net_remove(buf); + +out_remove_tables: + strlcpy(buf, xt_proto_prefix[af], sizeof(buf)); + strlcat(buf, FORMAT_TABLES, sizeof(buf)); + proc_net_remove(buf); +out: + return -1; +#endif +} +EXPORT_SYMBOL_GPL(xt_proto_init); + +void xt_proto_fini(int af) +{ +#ifdef CONFIG_PROC_FS + char buf[XT_FUNCTION_MAXNAMELEN]; + + strlcpy(buf, xt_proto_prefix[af], sizeof(buf)); + strlcat(buf, FORMAT_TABLES, sizeof(buf)); + proc_net_remove(buf); + + strlcpy(buf, xt_proto_prefix[af], sizeof(buf)); + strlcat(buf, FORMAT_TARGETS, sizeof(buf)); + proc_net_remove(buf); + + strlcpy(buf, xt_proto_prefix[af], sizeof(buf)); + strlcat(buf, FORMAT_MATCHES, sizeof(buf)); + proc_net_remove(buf); +#endif /*CONFIG_PROC_FS*/ +} +EXPORT_SYMBOL_GPL(xt_proto_fini); + + +static int __init xt_init(void) +{ + int i; + + xt = kmalloc(sizeof(struct xt_af) * NPROTO, GFP_KERNEL); + if (!xt) + return -ENOMEM; + + for (i = 0; i < NPROTO; i++) { + init_MUTEX(&xt[i].mutex); + INIT_LIST_HEAD(&xt[i].target); + INIT_LIST_HEAD(&xt[i].match); + INIT_LIST_HEAD(&xt[i].tables); + } + return 0; +} + +static void __exit xt_fini(void) +{ + kfree(xt); +} + +module_init(xt_init); +module_exit(xt_fini); + diff --git a/net/ipv4/netfilter/ipt_CLASSIFY.c b/net/netfilter/xt_CLASSIFY.c index dab78d8bd49..78ee266a12e 100644 --- a/net/ipv4/netfilter/ipt_CLASSIFY.c +++ b/net/netfilter/xt_CLASSIFY.c @@ -15,12 +15,13 @@ #include <linux/ip.h> #include <net/checksum.h> -#include <linux/netfilter_ipv4/ip_tables.h> -#include <linux/netfilter_ipv4/ipt_CLASSIFY.h> +#include <linux/netfilter/x_tables.h> +#include <linux/netfilter/xt_CLASSIFY.h> MODULE_AUTHOR("Patrick McHardy <kaber@trash.net>"); MODULE_LICENSE("GPL"); MODULE_DESCRIPTION("iptables qdisc classification target module"); +MODULE_ALIAS("ipt_CLASSIFY"); static unsigned int target(struct sk_buff **pskb, @@ -30,25 +31,25 @@ target(struct sk_buff **pskb, const void *targinfo, void *userinfo) { - const struct ipt_classify_target_info *clinfo = targinfo; + const struct xt_classify_target_info *clinfo = targinfo; - if((*pskb)->priority != clinfo->priority) + if ((*pskb)->priority != clinfo->priority) (*pskb)->priority = clinfo->priority; - return IPT_CONTINUE; + return XT_CONTINUE; } static int checkentry(const char *tablename, - const struct ipt_entry *e, + const void *e, void *targinfo, unsigned int targinfosize, unsigned int hook_mask) { - if (targinfosize != IPT_ALIGN(sizeof(struct ipt_classify_target_info))){ + if (targinfosize != XT_ALIGN(sizeof(struct xt_classify_target_info))){ printk(KERN_ERR "CLASSIFY: invalid size (%u != %Zu).\n", targinfosize, - IPT_ALIGN(sizeof(struct ipt_classify_target_info))); + XT_ALIGN(sizeof(struct xt_classify_target_info))); return 0; } @@ -69,21 +70,39 @@ checkentry(const char *tablename, return 1; } -static struct ipt_target ipt_classify_reg = { +static struct xt_target classify_reg = { + .name = "CLASSIFY", + .target = target, + .checkentry = checkentry, + .me = THIS_MODULE, +}; +static struct xt_target classify6_reg = { .name = "CLASSIFY", .target = target, .checkentry = checkentry, .me = THIS_MODULE, }; + static int __init init(void) { - return ipt_register_target(&ipt_classify_reg); + int ret; + + ret = xt_register_target(AF_INET, &classify_reg); + if (ret) + return ret; + + ret = xt_register_target(AF_INET6, &classify6_reg); + if (ret) + xt_unregister_target(AF_INET, &classify_reg); + + return ret; } static void __exit fini(void) { - ipt_unregister_target(&ipt_classify_reg); + xt_unregister_target(AF_INET, &classify_reg); + xt_unregister_target(AF_INET6, &classify6_reg); } module_init(init); diff --git a/net/ipv4/netfilter/ipt_CONNMARK.c b/net/netfilter/xt_CONNMARK.c index 8acac5a40a9..22506e376be 100644 --- a/net/ipv4/netfilter/ipt_CONNMARK.c +++ b/net/netfilter/xt_CONNMARK.c @@ -26,9 +26,10 @@ MODULE_AUTHOR("Henrik Nordstrom <hno@marasytems.com>"); MODULE_DESCRIPTION("IP tables CONNMARK matching module"); MODULE_LICENSE("GPL"); +MODULE_ALIAS("ipt_CONNMARK"); -#include <linux/netfilter_ipv4/ip_tables.h> -#include <linux/netfilter_ipv4/ipt_CONNMARK.h> +#include <linux/netfilter/x_tables.h> +#include <linux/netfilter/xt_CONNMARK.h> #include <net/netfilter/nf_conntrack_compat.h> static unsigned int @@ -39,7 +40,7 @@ target(struct sk_buff **pskb, const void *targinfo, void *userinfo) { - const struct ipt_connmark_target_info *markinfo = targinfo; + const struct xt_connmark_target_info *markinfo = targinfo; u_int32_t diff; u_int32_t nfmark; u_int32_t newmark; @@ -48,17 +49,17 @@ target(struct sk_buff **pskb, if (ctmark) { switch(markinfo->mode) { - case IPT_CONNMARK_SET: + case XT_CONNMARK_SET: newmark = (*ctmark & ~markinfo->mask) | markinfo->mark; if (newmark != *ctmark) *ctmark = newmark; break; - case IPT_CONNMARK_SAVE: + case XT_CONNMARK_SAVE: newmark = (*ctmark & ~markinfo->mask) | ((*pskb)->nfmark & markinfo->mask); if (*ctmark != newmark) *ctmark = newmark; break; - case IPT_CONNMARK_RESTORE: + case XT_CONNMARK_RESTORE: nfmark = (*pskb)->nfmark; diff = (*ctmark ^ nfmark) & markinfo->mask; if (diff != 0) @@ -67,25 +68,25 @@ target(struct sk_buff **pskb, } } - return IPT_CONTINUE; + return XT_CONTINUE; } static int checkentry(const char *tablename, - const struct ipt_entry *e, + const void *entry, void *targinfo, unsigned int targinfosize, unsigned int hook_mask) { - struct ipt_connmark_target_info *matchinfo = targinfo; - if (targinfosize != IPT_ALIGN(sizeof(struct ipt_connmark_target_info))) { + struct xt_connmark_target_info *matchinfo = targinfo; + if (targinfosize != XT_ALIGN(sizeof(struct xt_connmark_target_info))) { printk(KERN_WARNING "CONNMARK: targinfosize %u != %Zu\n", targinfosize, - IPT_ALIGN(sizeof(struct ipt_connmark_target_info))); + XT_ALIGN(sizeof(struct xt_connmark_target_info))); return 0; } - if (matchinfo->mode == IPT_CONNMARK_RESTORE) { + if (matchinfo->mode == XT_CONNMARK_RESTORE) { if (strcmp(tablename, "mangle") != 0) { printk(KERN_WARNING "CONNMARK: restore can only be called from \"mangle\" table, not \"%s\"\n", tablename); return 0; @@ -100,7 +101,13 @@ checkentry(const char *tablename, return 1; } -static struct ipt_target ipt_connmark_reg = { +static struct xt_target connmark_reg = { + .name = "CONNMARK", + .target = &target, + .checkentry = &checkentry, + .me = THIS_MODULE +}; +static struct xt_target connmark6_reg = { .name = "CONNMARK", .target = &target, .checkentry = &checkentry, @@ -109,13 +116,25 @@ static struct ipt_target ipt_connmark_reg = { static int __init init(void) { - need_ip_conntrack(); - return ipt_register_target(&ipt_connmark_reg); + int ret; + + need_conntrack(); + + ret = xt_register_target(AF_INET, &connmark_reg); + if (ret) + return ret; + + ret = xt_register_target(AF_INET6, &connmark6_reg); + if (ret) + xt_unregister_target(AF_INET, &connmark_reg); + + return ret; } static void __exit fini(void) { - ipt_unregister_target(&ipt_connmark_reg); + xt_unregister_target(AF_INET, &connmark_reg); + xt_unregister_target(AF_INET6, &connmark6_reg); } module_init(init); diff --git a/net/ipv4/netfilter/ipt_MARK.c b/net/netfilter/xt_MARK.c index 52b4f2c296b..0c11ee9550f 100644 --- a/net/ipv4/netfilter/ipt_MARK.c +++ b/net/netfilter/xt_MARK.c @@ -12,12 +12,14 @@ #include <linux/ip.h> #include <net/checksum.h> -#include <linux/netfilter_ipv4/ip_tables.h> -#include <linux/netfilter_ipv4/ipt_MARK.h> +#include <linux/netfilter/x_tables.h> +#include <linux/netfilter/xt_MARK.h> MODULE_LICENSE("GPL"); MODULE_AUTHOR("Marc Boucher <marc@mbsi.ca>"); -MODULE_DESCRIPTION("iptables MARK modification module"); +MODULE_DESCRIPTION("ip[6]tables MARK modification module"); +MODULE_ALIAS("ipt_MARK"); +MODULE_ALIAS("ip6t_MARK"); static unsigned int target_v0(struct sk_buff **pskb, @@ -27,12 +29,12 @@ target_v0(struct sk_buff **pskb, const void *targinfo, void *userinfo) { - const struct ipt_mark_target_info *markinfo = targinfo; + const struct xt_mark_target_info *markinfo = targinfo; if((*pskb)->nfmark != markinfo->mark) (*pskb)->nfmark = markinfo->mark; - return IPT_CONTINUE; + return XT_CONTINUE; } static unsigned int @@ -43,19 +45,19 @@ target_v1(struct sk_buff **pskb, const void *targinfo, void *userinfo) { - const struct ipt_mark_target_info_v1 *markinfo = targinfo; + const struct xt_mark_target_info_v1 *markinfo = targinfo; int mark = 0; switch (markinfo->mode) { - case IPT_MARK_SET: + case XT_MARK_SET: mark = markinfo->mark; break; - case IPT_MARK_AND: + case XT_MARK_AND: mark = (*pskb)->nfmark & markinfo->mark; break; - case IPT_MARK_OR: + case XT_MARK_OR: mark = (*pskb)->nfmark | markinfo->mark; break; } @@ -63,23 +65,23 @@ target_v1(struct sk_buff **pskb, if((*pskb)->nfmark != mark) (*pskb)->nfmark = mark; - return IPT_CONTINUE; + return XT_CONTINUE; } static int checkentry_v0(const char *tablename, - const struct ipt_entry *e, + const void *entry, void *targinfo, unsigned int targinfosize, unsigned int hook_mask) { - struct ipt_mark_target_info *markinfo = targinfo; + struct xt_mark_target_info *markinfo = targinfo; - if (targinfosize != IPT_ALIGN(sizeof(struct ipt_mark_target_info))) { + if (targinfosize != XT_ALIGN(sizeof(struct xt_mark_target_info))) { printk(KERN_WARNING "MARK: targinfosize %u != %Zu\n", targinfosize, - IPT_ALIGN(sizeof(struct ipt_mark_target_info))); + XT_ALIGN(sizeof(struct xt_mark_target_info))); return 0; } @@ -98,17 +100,17 @@ checkentry_v0(const char *tablename, static int checkentry_v1(const char *tablename, - const struct ipt_entry *e, + const void *entry, void *targinfo, unsigned int targinfosize, unsigned int hook_mask) { - struct ipt_mark_target_info_v1 *markinfo = targinfo; + struct xt_mark_target_info_v1 *markinfo = targinfo; - if (targinfosize != IPT_ALIGN(sizeof(struct ipt_mark_target_info_v1))){ + if (targinfosize != XT_ALIGN(sizeof(struct xt_mark_target_info_v1))){ printk(KERN_WARNING "MARK: targinfosize %u != %Zu\n", targinfosize, - IPT_ALIGN(sizeof(struct ipt_mark_target_info_v1))); + XT_ALIGN(sizeof(struct xt_mark_target_info_v1))); return 0; } @@ -117,9 +119,9 @@ checkentry_v1(const char *tablename, return 0; } - if (markinfo->mode != IPT_MARK_SET - && markinfo->mode != IPT_MARK_AND - && markinfo->mode != IPT_MARK_OR) { + if (markinfo->mode != XT_MARK_SET + && markinfo->mode != XT_MARK_AND + && markinfo->mode != XT_MARK_OR) { printk(KERN_WARNING "MARK: unknown mode %u\n", markinfo->mode); return 0; @@ -133,7 +135,7 @@ checkentry_v1(const char *tablename, return 1; } -static struct ipt_target ipt_mark_reg_v0 = { +static struct xt_target ipt_mark_reg_v0 = { .name = "MARK", .target = target_v0, .checkentry = checkentry_v0, @@ -141,7 +143,7 @@ static struct ipt_target ipt_mark_reg_v0 = { .revision = 0, }; -static struct ipt_target ipt_mark_reg_v1 = { +static struct xt_target ipt_mark_reg_v1 = { .name = "MARK", .target = target_v1, .checkentry = checkentry_v1, @@ -149,23 +151,40 @@ static struct ipt_target ipt_mark_reg_v1 = { .revision = 1, }; +static struct xt_target ip6t_mark_reg_v0 = { + .name = "MARK", + .target = target_v0, + .checkentry = checkentry_v0, + .me = THIS_MODULE, + .revision = 0, +}; + static int __init init(void) { int err; - err = ipt_register_target(&ipt_mark_reg_v0); - if (!err) { - err = ipt_register_target(&ipt_mark_reg_v1); - if (err) - ipt_unregister_target(&ipt_mark_reg_v0); + err = xt_register_target(AF_INET, &ipt_mark_reg_v0); + if (err) + return err; + + err = xt_register_target(AF_INET, &ipt_mark_reg_v1); + if (err) + xt_unregister_target(AF_INET, &ipt_mark_reg_v0); + + err = xt_register_target(AF_INET6, &ip6t_mark_reg_v0); + if (err) { + xt_unregister_target(AF_INET, &ipt_mark_reg_v0); + xt_unregister_target(AF_INET, &ipt_mark_reg_v1); } + return err; } static void __exit fini(void) { - ipt_unregister_target(&ipt_mark_reg_v0); - ipt_unregister_target(&ipt_mark_reg_v1); + xt_unregister_target(AF_INET, &ipt_mark_reg_v0); + xt_unregister_target(AF_INET, &ipt_mark_reg_v1); + xt_unregister_target(AF_INET6, &ip6t_mark_reg_v0); } module_init(init); diff --git a/net/netfilter/xt_NFQUEUE.c b/net/netfilter/xt_NFQUEUE.c new file mode 100644 index 00000000000..8b76b6f8d1e --- /dev/null +++ b/net/netfilter/xt_NFQUEUE.c @@ -0,0 +1,107 @@ +/* iptables module for using new netfilter netlink queue + * + * (C) 2005 by Harald Welte <laforge@netfilter.org> + * + * This program is free software; you can redistribute it and/or modify + * it under the terms of the GNU General Public License version 2 as + * published by the Free Software Foundation. + * + */ + +#include <linux/module.h> +#include <linux/skbuff.h> + +#include <linux/netfilter.h> +#include <linux/netfilter_arp.h> +#include <linux/netfilter/x_tables.h> +#include <linux/netfilter/xt_NFQUEUE.h> + +MODULE_AUTHOR("Harald Welte <laforge@netfilter.org>"); +MODULE_DESCRIPTION("[ip,ip6,arp]_tables NFQUEUE target"); +MODULE_LICENSE("GPL"); +MODULE_ALIAS("ipt_NFQUEUE"); +MODULE_ALIAS("ip6t_NFQUEUE"); +MODULE_ALIAS("arpt_NFQUEUE"); + +static unsigned int +target(struct sk_buff **pskb, + const struct net_device *in, + const struct net_device *out, + unsigned int hooknum, + const void *targinfo, + void *userinfo) +{ + const struct xt_NFQ_info *tinfo = targinfo; + + return NF_QUEUE_NR(tinfo->queuenum); +} + +static int +checkentry(const char *tablename, + const void *entry, + void *targinfo, + unsigned int targinfosize, + unsigned int hook_mask) +{ + if (targinfosize != XT_ALIGN(sizeof(struct xt_NFQ_info))) { + printk(KERN_WARNING "NFQUEUE: targinfosize %u != %Zu\n", + targinfosize, + XT_ALIGN(sizeof(struct xt_NFQ_info))); + return 0; + } + + return 1; +} + +static struct xt_target ipt_NFQ_reg = { + .name = "NFQUEUE", + .target = target, + .checkentry = checkentry, + .me = THIS_MODULE, +}; + +static struct xt_target ip6t_NFQ_reg = { + .name = "NFQUEUE", + .target = target, + .checkentry = checkentry, + .me = THIS_MODULE, +}; + +static struct xt_target arpt_NFQ_reg = { + .name = "NFQUEUE", + .target = target, + .checkentry = checkentry, + .me = THIS_MODULE, +}; + +static int __init init(void) +{ + int ret; + ret = xt_register_target(AF_INET, &ipt_NFQ_reg); + if (ret) + return ret; + ret = xt_register_target(AF_INET6, &ip6t_NFQ_reg); + if (ret) + goto out_ip; + ret = xt_register_target(NF_ARP, &arpt_NFQ_reg); + if (ret) + goto out_ip6; + + return ret; +out_ip6: + xt_unregister_target(AF_INET6, &ip6t_NFQ_reg); +out_ip: + xt_unregister_target(AF_INET, &ipt_NFQ_reg); + + return ret; +} + +static void __exit fini(void) +{ + xt_unregister_target(NF_ARP, &arpt_NFQ_reg); + xt_unregister_target(AF_INET6, &ip6t_NFQ_reg); + xt_unregister_target(AF_INET, &ipt_NFQ_reg); +} + +module_init(init); +module_exit(fini); diff --git a/net/ipv4/netfilter/ipt_NOTRACK.c b/net/netfilter/xt_NOTRACK.c index e3c69d072c6..24d477afa93 100644 --- a/net/ipv4/netfilter/ipt_NOTRACK.c +++ b/net/netfilter/xt_NOTRACK.c @@ -4,9 +4,12 @@ #include <linux/module.h> #include <linux/skbuff.h> -#include <linux/netfilter_ipv4/ip_tables.h> +#include <linux/netfilter/x_tables.h> #include <net/netfilter/nf_conntrack_compat.h> +MODULE_LICENSE("GPL"); +MODULE_ALIAS("ipt_NOTRACK"); + static unsigned int target(struct sk_buff **pskb, const struct net_device *in, @@ -17,7 +20,7 @@ target(struct sk_buff **pskb, { /* Previously seen (loopback)? Ignore. */ if ((*pskb)->nfct != NULL) - return IPT_CONTINUE; + return XT_CONTINUE; /* Attach fake conntrack entry. If there is a real ct entry correspondig to this packet, @@ -27,12 +30,12 @@ target(struct sk_buff **pskb, (*pskb)->nfctinfo = IP_CT_NEW; nf_conntrack_get((*pskb)->nfct); - return IPT_CONTINUE; + return XT_CONTINUE; } static int checkentry(const char *tablename, - const struct ipt_entry *e, + const void *entry, void *targinfo, unsigned int targinfosize, unsigned int hook_mask) @@ -51,26 +54,39 @@ checkentry(const char *tablename, return 1; } -static struct ipt_target ipt_notrack_reg = { +static struct xt_target notrack_reg = { .name = "NOTRACK", .target = target, .checkentry = checkentry, - .me = THIS_MODULE + .me = THIS_MODULE, +}; +static struct xt_target notrack6_reg = { + .name = "NOTRACK", + .target = target, + .checkentry = checkentry, + .me = THIS_MODULE, }; static int __init init(void) { - if (ipt_register_target(&ipt_notrack_reg)) - return -EINVAL; + int ret; + + ret = xt_register_target(AF_INET, ¬rack_reg); + if (ret) + return ret; - return 0; + ret = xt_register_target(AF_INET6, ¬rack6_reg); + if (ret) + xt_unregister_target(AF_INET, ¬rack_reg); + + return ret; } static void __exit fini(void) { - ipt_unregister_target(&ipt_notrack_reg); + xt_unregister_target(AF_INET6, ¬rack6_reg); + xt_unregister_target(AF_INET, ¬rack_reg); } module_init(init); module_exit(fini); -MODULE_LICENSE("GPL"); diff --git a/net/ipv4/netfilter/ipt_comment.c b/net/netfilter/xt_comment.c index 6b76a1ea524..4ba6fd65c6e 100644 --- a/net/ipv4/netfilter/ipt_comment.c +++ b/net/netfilter/xt_comment.c @@ -6,12 +6,14 @@ #include <linux/module.h> #include <linux/skbuff.h> -#include <linux/netfilter_ipv4/ip_tables.h> -#include <linux/netfilter_ipv4/ipt_comment.h> +#include <linux/netfilter/x_tables.h> +#include <linux/netfilter/xt_comment.h> MODULE_AUTHOR("Brad Fisher <brad@info-link.net>"); MODULE_DESCRIPTION("iptables comment match module"); MODULE_LICENSE("GPL"); +MODULE_ALIAS("ipt_comment"); +MODULE_ALIAS("ip6t_comment"); static int match(const struct sk_buff *skb, @@ -19,6 +21,7 @@ match(const struct sk_buff *skb, const struct net_device *out, const void *matchinfo, int offset, + unsigned int protooff, int *hotdrop) { /* We always match */ @@ -27,18 +30,25 @@ match(const struct sk_buff *skb, static int checkentry(const char *tablename, - const struct ipt_ip *ip, + const void *ip, void *matchinfo, unsigned int matchsize, unsigned int hook_mask) { /* Check the size */ - if (matchsize != IPT_ALIGN(sizeof(struct ipt_comment_info))) + if (matchsize != XT_ALIGN(sizeof(struct xt_comment_info))) return 0; return 1; } -static struct ipt_match comment_match = { +static struct xt_match comment_match = { + .name = "comment", + .match = match, + .checkentry = checkentry, + .me = THIS_MODULE +}; + +static struct xt_match comment6_match = { .name = "comment", .match = match, .checkentry = checkentry, @@ -47,12 +57,23 @@ static struct ipt_match comment_match = { static int __init init(void) { - return ipt_register_match(&comment_match); + int ret; + + ret = xt_register_match(AF_INET, &comment_match); + if (ret) + return ret; + + ret = xt_register_match(AF_INET6, &comment6_match); + if (ret) + xt_unregister_match(AF_INET, &comment_match); + + return ret; } static void __exit fini(void) { - ipt_unregister_match(&comment_match); + xt_unregister_match(AF_INET, &comment_match); + xt_unregister_match(AF_INET6, &comment6_match); } module_init(init); diff --git a/net/ipv4/netfilter/ipt_connbytes.c b/net/netfilter/xt_connbytes.c index d68a048b717..150d2a4b0f7 100644 --- a/net/ipv4/netfilter/ipt_connbytes.c +++ b/net/netfilter/xt_connbytes.c @@ -6,13 +6,15 @@ * - add functionality to match number of packets * - add functionality to match average packet size * - add support to match directions seperately + * 2005-10-16 Harald Welte <laforge@netfilter.org> + * - Port to x_tables * */ #include <linux/module.h> #include <linux/skbuff.h> #include <net/netfilter/nf_conntrack_compat.h> -#include <linux/netfilter_ipv4/ip_tables.h> -#include <linux/netfilter_ipv4/ipt_connbytes.h> +#include <linux/netfilter/x_tables.h> +#include <linux/netfilter/xt_connbytes.h> #include <asm/div64.h> #include <asm/bitops.h> @@ -20,6 +22,7 @@ MODULE_LICENSE("GPL"); MODULE_AUTHOR("Harald Welte <laforge@netfilter.org>"); MODULE_DESCRIPTION("iptables match for matching number of pkts/bytes per connection"); +MODULE_ALIAS("ipt_connbytes"); /* 64bit divisor, dividend and result. dynamic precision */ static u_int64_t div64_64(u_int64_t dividend, u_int64_t divisor) @@ -43,9 +46,10 @@ match(const struct sk_buff *skb, const struct net_device *out, const void *matchinfo, int offset, + unsigned int protoff, int *hotdrop) { - const struct ipt_connbytes_info *sinfo = matchinfo; + const struct xt_connbytes_info *sinfo = matchinfo; u_int64_t what = 0; /* initialize to make gcc happy */ const struct ip_conntrack_counter *counters; @@ -53,45 +57,45 @@ match(const struct sk_buff *skb, return 0; /* no match */ switch (sinfo->what) { - case IPT_CONNBYTES_PKTS: + case XT_CONNBYTES_PKTS: switch (sinfo->direction) { - case IPT_CONNBYTES_DIR_ORIGINAL: + case XT_CONNBYTES_DIR_ORIGINAL: what = counters[IP_CT_DIR_ORIGINAL].packets; break; - case IPT_CONNBYTES_DIR_REPLY: + case XT_CONNBYTES_DIR_REPLY: what = counters[IP_CT_DIR_REPLY].packets; break; - case IPT_CONNBYTES_DIR_BOTH: + case XT_CONNBYTES_DIR_BOTH: what = counters[IP_CT_DIR_ORIGINAL].packets; what += counters[IP_CT_DIR_REPLY].packets; break; } break; - case IPT_CONNBYTES_BYTES: + case XT_CONNBYTES_BYTES: switch (sinfo->direction) { - case IPT_CONNBYTES_DIR_ORIGINAL: + case XT_CONNBYTES_DIR_ORIGINAL: what = counters[IP_CT_DIR_ORIGINAL].bytes; break; - case IPT_CONNBYTES_DIR_REPLY: + case XT_CONNBYTES_DIR_REPLY: what = counters[IP_CT_DIR_REPLY].bytes; break; - case IPT_CONNBYTES_DIR_BOTH: + case XT_CONNBYTES_DIR_BOTH: what = counters[IP_CT_DIR_ORIGINAL].bytes; what += counters[IP_CT_DIR_REPLY].bytes; break; } break; - case IPT_CONNBYTES_AVGPKT: + case XT_CONNBYTES_AVGPKT: switch (sinfo->direction) { - case IPT_CONNBYTES_DIR_ORIGINAL: + case XT_CONNBYTES_DIR_ORIGINAL: what = div64_64(counters[IP_CT_DIR_ORIGINAL].bytes, counters[IP_CT_DIR_ORIGINAL].packets); break; - case IPT_CONNBYTES_DIR_REPLY: + case XT_CONNBYTES_DIR_REPLY: what = div64_64(counters[IP_CT_DIR_REPLY].bytes, counters[IP_CT_DIR_REPLY].packets); break; - case IPT_CONNBYTES_DIR_BOTH: + case XT_CONNBYTES_DIR_BOTH: { u_int64_t bytes; u_int64_t pkts; @@ -117,30 +121,36 @@ match(const struct sk_buff *skb, } static int check(const char *tablename, - const struct ipt_ip *ip, + const void *ip, void *matchinfo, unsigned int matchsize, unsigned int hook_mask) { - const struct ipt_connbytes_info *sinfo = matchinfo; + const struct xt_connbytes_info *sinfo = matchinfo; - if (matchsize != IPT_ALIGN(sizeof(struct ipt_connbytes_info))) + if (matchsize != XT_ALIGN(sizeof(struct xt_connbytes_info))) return 0; - if (sinfo->what != IPT_CONNBYTES_PKTS && - sinfo->what != IPT_CONNBYTES_BYTES && - sinfo->what != IPT_CONNBYTES_AVGPKT) + if (sinfo->what != XT_CONNBYTES_PKTS && + sinfo->what != XT_CONNBYTES_BYTES && + sinfo->what != XT_CONNBYTES_AVGPKT) return 0; - if (sinfo->direction != IPT_CONNBYTES_DIR_ORIGINAL && - sinfo->direction != IPT_CONNBYTES_DIR_REPLY && - sinfo->direction != IPT_CONNBYTES_DIR_BOTH) + if (sinfo->direction != XT_CONNBYTES_DIR_ORIGINAL && + sinfo->direction != XT_CONNBYTES_DIR_REPLY && + sinfo->direction != XT_CONNBYTES_DIR_BOTH) return 0; return 1; } -static struct ipt_match state_match = { +static struct xt_match connbytes_match = { + .name = "connbytes", + .match = &match, + .checkentry = &check, + .me = THIS_MODULE +}; +static struct xt_match connbytes6_match = { .name = "connbytes", .match = &match, .checkentry = &check, @@ -149,12 +159,21 @@ static struct ipt_match state_match = { static int __init init(void) { - return ipt_register_match(&state_match); + int ret; + ret = xt_register_match(AF_INET, &connbytes_match); + if (ret) + return ret; + + ret = xt_register_match(AF_INET6, &connbytes6_match); + if (ret) + xt_unregister_match(AF_INET, &connbytes_match); + return ret; } static void __exit fini(void) { - ipt_unregister_match(&state_match); + xt_unregister_match(AF_INET, &connbytes_match); + xt_unregister_match(AF_INET6, &connbytes6_match); } module_init(init); diff --git a/net/ipv4/netfilter/ipt_connmark.c b/net/netfilter/xt_connmark.c index 5306ef293b9..d06e925032d 100644 --- a/net/ipv4/netfilter/ipt_connmark.c +++ b/net/netfilter/xt_connmark.c @@ -25,9 +25,10 @@ MODULE_AUTHOR("Henrik Nordstrom <hno@marasytems.com>"); MODULE_DESCRIPTION("IP tables connmark match module"); MODULE_LICENSE("GPL"); +MODULE_ALIAS("ipt_connmark"); -#include <linux/netfilter_ipv4/ip_tables.h> -#include <linux/netfilter_ipv4/ipt_connmark.h> +#include <linux/netfilter/x_tables.h> +#include <linux/netfilter/xt_connmark.h> #include <net/netfilter/nf_conntrack_compat.h> static int @@ -36,9 +37,10 @@ match(const struct sk_buff *skb, const struct net_device *out, const void *matchinfo, int offset, + unsigned int protoff, int *hotdrop) { - const struct ipt_connmark_info *info = matchinfo; + const struct xt_connmark_info *info = matchinfo; u_int32_t ctinfo; const u_int32_t *ctmark = nf_ct_get_mark(skb, &ctinfo); if (!ctmark) @@ -49,14 +51,14 @@ match(const struct sk_buff *skb, static int checkentry(const char *tablename, - const struct ipt_ip *ip, + const void *ip, void *matchinfo, unsigned int matchsize, unsigned int hook_mask) { - struct ipt_connmark_info *cm = - (struct ipt_connmark_info *)matchinfo; - if (matchsize != IPT_ALIGN(sizeof(struct ipt_connmark_info))) + struct xt_connmark_info *cm = + (struct xt_connmark_info *)matchinfo; + if (matchsize != XT_ALIGN(sizeof(struct xt_connmark_info))) return 0; if (cm->mark > 0xffffffff || cm->mask > 0xffffffff) { @@ -67,21 +69,40 @@ checkentry(const char *tablename, return 1; } -static struct ipt_match connmark_match = { +static struct xt_match connmark_match = { + .name = "connmark", + .match = &match, + .checkentry = &checkentry, + .me = THIS_MODULE +}; +static struct xt_match connmark6_match = { .name = "connmark", .match = &match, .checkentry = &checkentry, .me = THIS_MODULE }; + static int __init init(void) { - return ipt_register_match(&connmark_match); + int ret; + + need_conntrack(); + + ret = xt_register_match(AF_INET, &connmark_match); + if (ret) + return ret; + + ret = xt_register_match(AF_INET6, &connmark6_match); + if (ret) + xt_unregister_match(AF_INET, &connmark_match); + return ret; } static void __exit fini(void) { - ipt_unregister_match(&connmark_match); + xt_unregister_match(AF_INET6, &connmark6_match); + xt_unregister_match(AF_INET, &connmark_match); } module_init(init); diff --git a/net/ipv4/netfilter/ipt_conntrack.c b/net/netfilter/xt_conntrack.c index c8d18705469..ffdebc95eb9 100644 --- a/net/ipv4/netfilter/ipt_conntrack.c +++ b/net/netfilter/xt_conntrack.c @@ -18,12 +18,13 @@ #include <net/netfilter/nf_conntrack.h> #endif -#include <linux/netfilter_ipv4/ip_tables.h> -#include <linux/netfilter_ipv4/ipt_conntrack.h> +#include <linux/netfilter/x_tables.h> +#include <linux/netfilter/xt_conntrack.h> MODULE_LICENSE("GPL"); MODULE_AUTHOR("Marc Boucher <marc@mbsi.ca>"); MODULE_DESCRIPTION("iptables connection tracking match module"); +MODULE_ALIAS("ipt_conntrack"); #if defined(CONFIG_IP_NF_CONNTRACK) || defined(CONFIG_IP_NF_CONNTRACK_MODULE) @@ -33,9 +34,10 @@ match(const struct sk_buff *skb, const struct net_device *out, const void *matchinfo, int offset, + unsigned int protoff, int *hotdrop) { - const struct ipt_conntrack_info *sinfo = matchinfo; + const struct xt_conntrack_info *sinfo = matchinfo; struct ip_conntrack *ct; enum ip_conntrack_info ctinfo; unsigned int statebit; @@ -45,58 +47,58 @@ match(const struct sk_buff *skb, #define FWINV(bool,invflg) ((bool) ^ !!(sinfo->invflags & invflg)) if (ct == &ip_conntrack_untracked) - statebit = IPT_CONNTRACK_STATE_UNTRACKED; + statebit = XT_CONNTRACK_STATE_UNTRACKED; else if (ct) - statebit = IPT_CONNTRACK_STATE_BIT(ctinfo); + statebit = XT_CONNTRACK_STATE_BIT(ctinfo); else - statebit = IPT_CONNTRACK_STATE_INVALID; + statebit = XT_CONNTRACK_STATE_INVALID; - if(sinfo->flags & IPT_CONNTRACK_STATE) { + if(sinfo->flags & XT_CONNTRACK_STATE) { if (ct) { if(ct->tuplehash[IP_CT_DIR_ORIGINAL].tuple.src.ip != ct->tuplehash[IP_CT_DIR_REPLY].tuple.dst.ip) - statebit |= IPT_CONNTRACK_STATE_SNAT; + statebit |= XT_CONNTRACK_STATE_SNAT; if(ct->tuplehash[IP_CT_DIR_ORIGINAL].tuple.dst.ip != ct->tuplehash[IP_CT_DIR_REPLY].tuple.src.ip) - statebit |= IPT_CONNTRACK_STATE_DNAT; + statebit |= XT_CONNTRACK_STATE_DNAT; } - if (FWINV((statebit & sinfo->statemask) == 0, IPT_CONNTRACK_STATE)) + if (FWINV((statebit & sinfo->statemask) == 0, XT_CONNTRACK_STATE)) return 0; } - if(sinfo->flags & IPT_CONNTRACK_PROTO) { - if (!ct || FWINV(ct->tuplehash[IP_CT_DIR_ORIGINAL].tuple.dst.protonum != sinfo->tuple[IP_CT_DIR_ORIGINAL].dst.protonum, IPT_CONNTRACK_PROTO)) + if(sinfo->flags & XT_CONNTRACK_PROTO) { + if (!ct || FWINV(ct->tuplehash[IP_CT_DIR_ORIGINAL].tuple.dst.protonum != sinfo->tuple[IP_CT_DIR_ORIGINAL].dst.protonum, XT_CONNTRACK_PROTO)) return 0; } - if(sinfo->flags & IPT_CONNTRACK_ORIGSRC) { - if (!ct || FWINV((ct->tuplehash[IP_CT_DIR_ORIGINAL].tuple.src.ip&sinfo->sipmsk[IP_CT_DIR_ORIGINAL].s_addr) != sinfo->tuple[IP_CT_DIR_ORIGINAL].src.ip, IPT_CONNTRACK_ORIGSRC)) + if(sinfo->flags & XT_CONNTRACK_ORIGSRC) { + if (!ct || FWINV((ct->tuplehash[IP_CT_DIR_ORIGINAL].tuple.src.ip&sinfo->sipmsk[IP_CT_DIR_ORIGINAL].s_addr) != sinfo->tuple[IP_CT_DIR_ORIGINAL].src.ip, XT_CONNTRACK_ORIGSRC)) return 0; } - if(sinfo->flags & IPT_CONNTRACK_ORIGDST) { - if (!ct || FWINV((ct->tuplehash[IP_CT_DIR_ORIGINAL].tuple.dst.ip&sinfo->dipmsk[IP_CT_DIR_ORIGINAL].s_addr) != sinfo->tuple[IP_CT_DIR_ORIGINAL].dst.ip, IPT_CONNTRACK_ORIGDST)) + if(sinfo->flags & XT_CONNTRACK_ORIGDST) { + if (!ct || FWINV((ct->tuplehash[IP_CT_DIR_ORIGINAL].tuple.dst.ip&sinfo->dipmsk[IP_CT_DIR_ORIGINAL].s_addr) != sinfo->tuple[IP_CT_DIR_ORIGINAL].dst.ip, XT_CONNTRACK_ORIGDST)) return 0; } - if(sinfo->flags & IPT_CONNTRACK_REPLSRC) { - if (!ct || FWINV((ct->tuplehash[IP_CT_DIR_REPLY].tuple.src.ip&sinfo->sipmsk[IP_CT_DIR_REPLY].s_addr) != sinfo->tuple[IP_CT_DIR_REPLY].src.ip, IPT_CONNTRACK_REPLSRC)) + if(sinfo->flags & XT_CONNTRACK_REPLSRC) { + if (!ct || FWINV((ct->tuplehash[IP_CT_DIR_REPLY].tuple.src.ip&sinfo->sipmsk[IP_CT_DIR_REPLY].s_addr) != sinfo->tuple[IP_CT_DIR_REPLY].src.ip, XT_CONNTRACK_REPLSRC)) return 0; } - if(sinfo->flags & IPT_CONNTRACK_REPLDST) { - if (!ct || FWINV((ct->tuplehash[IP_CT_DIR_REPLY].tuple.dst.ip&sinfo->dipmsk[IP_CT_DIR_REPLY].s_addr) != sinfo->tuple[IP_CT_DIR_REPLY].dst.ip, IPT_CONNTRACK_REPLDST)) + if(sinfo->flags & XT_CONNTRACK_REPLDST) { + if (!ct || FWINV((ct->tuplehash[IP_CT_DIR_REPLY].tuple.dst.ip&sinfo->dipmsk[IP_CT_DIR_REPLY].s_addr) != sinfo->tuple[IP_CT_DIR_REPLY].dst.ip, XT_CONNTRACK_REPLDST)) return 0; } - if(sinfo->flags & IPT_CONNTRACK_STATUS) { - if (!ct || FWINV((ct->status & sinfo->statusmask) == 0, IPT_CONNTRACK_STATUS)) + if(sinfo->flags & XT_CONNTRACK_STATUS) { + if (!ct || FWINV((ct->status & sinfo->statusmask) == 0, XT_CONNTRACK_STATUS)) return 0; } - if(sinfo->flags & IPT_CONNTRACK_EXPIRES) { + if(sinfo->flags & XT_CONNTRACK_EXPIRES) { unsigned long expires; if(!ct) @@ -104,7 +106,7 @@ match(const struct sk_buff *skb, expires = timer_pending(&ct->timeout) ? (ct->timeout.expires - jiffies)/HZ : 0; - if (FWINV(!(expires >= sinfo->expires_min && expires <= sinfo->expires_max), IPT_CONNTRACK_EXPIRES)) + if (FWINV(!(expires >= sinfo->expires_min && expires <= sinfo->expires_max), XT_CONNTRACK_EXPIRES)) return 0; } @@ -118,9 +120,10 @@ match(const struct sk_buff *skb, const struct net_device *out, const void *matchinfo, int offset, + unsigned int protoff, int *hotdrop) { - const struct ipt_conntrack_info *sinfo = matchinfo; + const struct xt_conntrack_info *sinfo = matchinfo; struct nf_conn *ct; enum ip_conntrack_info ctinfo; unsigned int statebit; @@ -130,58 +133,58 @@ match(const struct sk_buff *skb, #define FWINV(bool,invflg) ((bool) ^ !!(sinfo->invflags & invflg)) if (ct == &nf_conntrack_untracked) - statebit = IPT_CONNTRACK_STATE_UNTRACKED; + statebit = XT_CONNTRACK_STATE_UNTRACKED; else if (ct) - statebit = IPT_CONNTRACK_STATE_BIT(ctinfo); + statebit = XT_CONNTRACK_STATE_BIT(ctinfo); else - statebit = IPT_CONNTRACK_STATE_INVALID; + statebit = XT_CONNTRACK_STATE_INVALID; - if(sinfo->flags & IPT_CONNTRACK_STATE) { + if(sinfo->flags & XT_CONNTRACK_STATE) { if (ct) { if(ct->tuplehash[IP_CT_DIR_ORIGINAL].tuple.src.u3.ip != ct->tuplehash[IP_CT_DIR_REPLY].tuple.dst.u3.ip) - statebit |= IPT_CONNTRACK_STATE_SNAT; + statebit |= XT_CONNTRACK_STATE_SNAT; if(ct->tuplehash[IP_CT_DIR_ORIGINAL].tuple.dst.u3.ip != ct->tuplehash[IP_CT_DIR_REPLY].tuple.src.u3.ip) - statebit |= IPT_CONNTRACK_STATE_DNAT; + statebit |= XT_CONNTRACK_STATE_DNAT; } - if (FWINV((statebit & sinfo->statemask) == 0, IPT_CONNTRACK_STATE)) + if (FWINV((statebit & sinfo->statemask) == 0, XT_CONNTRACK_STATE)) return 0; } - if(sinfo->flags & IPT_CONNTRACK_PROTO) { - if (!ct || FWINV(ct->tuplehash[IP_CT_DIR_ORIGINAL].tuple.dst.protonum != sinfo->tuple[IP_CT_DIR_ORIGINAL].dst.protonum, IPT_CONNTRACK_PROTO)) + if(sinfo->flags & XT_CONNTRACK_PROTO) { + if (!ct || FWINV(ct->tuplehash[IP_CT_DIR_ORIGINAL].tuple.dst.protonum != sinfo->tuple[IP_CT_DIR_ORIGINAL].dst.protonum, XT_CONNTRACK_PROTO)) return 0; } - if(sinfo->flags & IPT_CONNTRACK_ORIGSRC) { - if (!ct || FWINV((ct->tuplehash[IP_CT_DIR_ORIGINAL].tuple.src.u3.ip&sinfo->sipmsk[IP_CT_DIR_ORIGINAL].s_addr) != sinfo->tuple[IP_CT_DIR_ORIGINAL].src.ip, IPT_CONNTRACK_ORIGSRC)) + if(sinfo->flags & XT_CONNTRACK_ORIGSRC) { + if (!ct || FWINV((ct->tuplehash[IP_CT_DIR_ORIGINAL].tuple.src.u3.ip&sinfo->sipmsk[IP_CT_DIR_ORIGINAL].s_addr) != sinfo->tuple[IP_CT_DIR_ORIGINAL].src.ip, XT_CONNTRACK_ORIGSRC)) return 0; } - if(sinfo->flags & IPT_CONNTRACK_ORIGDST) { - if (!ct || FWINV((ct->tuplehash[IP_CT_DIR_ORIGINAL].tuple.dst.u3.ip&sinfo->dipmsk[IP_CT_DIR_ORIGINAL].s_addr) != sinfo->tuple[IP_CT_DIR_ORIGINAL].dst.ip, IPT_CONNTRACK_ORIGDST)) + if(sinfo->flags & XT_CONNTRACK_ORIGDST) { + if (!ct || FWINV((ct->tuplehash[IP_CT_DIR_ORIGINAL].tuple.dst.u3.ip&sinfo->dipmsk[IP_CT_DIR_ORIGINAL].s_addr) != sinfo->tuple[IP_CT_DIR_ORIGINAL].dst.ip, XT_CONNTRACK_ORIGDST)) return 0; } - if(sinfo->flags & IPT_CONNTRACK_REPLSRC) { - if (!ct || FWINV((ct->tuplehash[IP_CT_DIR_REPLY].tuple.src.u3.ip&sinfo->sipmsk[IP_CT_DIR_REPLY].s_addr) != sinfo->tuple[IP_CT_DIR_REPLY].src.ip, IPT_CONNTRACK_REPLSRC)) + if(sinfo->flags & XT_CONNTRACK_REPLSRC) { + if (!ct || FWINV((ct->tuplehash[IP_CT_DIR_REPLY].tuple.src.u3.ip&sinfo->sipmsk[IP_CT_DIR_REPLY].s_addr) != sinfo->tuple[IP_CT_DIR_REPLY].src.ip, XT_CONNTRACK_REPLSRC)) return 0; } - if(sinfo->flags & IPT_CONNTRACK_REPLDST) { - if (!ct || FWINV((ct->tuplehash[IP_CT_DIR_REPLY].tuple.dst.u3.ip&sinfo->dipmsk[IP_CT_DIR_REPLY].s_addr) != sinfo->tuple[IP_CT_DIR_REPLY].dst.ip, IPT_CONNTRACK_REPLDST)) + if(sinfo->flags & XT_CONNTRACK_REPLDST) { + if (!ct || FWINV((ct->tuplehash[IP_CT_DIR_REPLY].tuple.dst.u3.ip&sinfo->dipmsk[IP_CT_DIR_REPLY].s_addr) != sinfo->tuple[IP_CT_DIR_REPLY].dst.ip, XT_CONNTRACK_REPLDST)) return 0; } - if(sinfo->flags & IPT_CONNTRACK_STATUS) { - if (!ct || FWINV((ct->status & sinfo->statusmask) == 0, IPT_CONNTRACK_STATUS)) + if(sinfo->flags & XT_CONNTRACK_STATUS) { + if (!ct || FWINV((ct->status & sinfo->statusmask) == 0, XT_CONNTRACK_STATUS)) return 0; } - if(sinfo->flags & IPT_CONNTRACK_EXPIRES) { + if(sinfo->flags & XT_CONNTRACK_EXPIRES) { unsigned long expires; if(!ct) @@ -189,7 +192,7 @@ match(const struct sk_buff *skb, expires = timer_pending(&ct->timeout) ? (ct->timeout.expires - jiffies)/HZ : 0; - if (FWINV(!(expires >= sinfo->expires_min && expires <= sinfo->expires_max), IPT_CONNTRACK_EXPIRES)) + if (FWINV(!(expires >= sinfo->expires_min && expires <= sinfo->expires_max), XT_CONNTRACK_EXPIRES)) return 0; } @@ -199,18 +202,18 @@ match(const struct sk_buff *skb, #endif /* CONFIG_NF_IP_CONNTRACK */ static int check(const char *tablename, - const struct ipt_ip *ip, + const void *ip, void *matchinfo, unsigned int matchsize, unsigned int hook_mask) { - if (matchsize != IPT_ALIGN(sizeof(struct ipt_conntrack_info))) + if (matchsize != XT_ALIGN(sizeof(struct xt_conntrack_info))) return 0; return 1; } -static struct ipt_match conntrack_match = { +static struct xt_match conntrack_match = { .name = "conntrack", .match = &match, .checkentry = &check, @@ -219,13 +222,16 @@ static struct ipt_match conntrack_match = { static int __init init(void) { - need_ip_conntrack(); - return ipt_register_match(&conntrack_match); + int ret; + need_conntrack(); + ret = xt_register_match(AF_INET, &conntrack_match); + + return ret; } static void __exit fini(void) { - ipt_unregister_match(&conntrack_match); + xt_unregister_match(AF_INET, &conntrack_match); } module_init(init); diff --git a/net/ipv4/netfilter/ipt_dccp.c b/net/netfilter/xt_dccp.c index ad3278bba6c..779f42fc952 100644 --- a/net/ipv4/netfilter/ipt_dccp.c +++ b/net/netfilter/xt_dccp.c @@ -14,8 +14,16 @@ #include <net/ip.h> #include <linux/dccp.h> +#include <linux/netfilter/x_tables.h> +#include <linux/netfilter/xt_dccp.h> + #include <linux/netfilter_ipv4/ip_tables.h> -#include <linux/netfilter_ipv4/ipt_dccp.h> +#include <linux/netfilter_ipv6/ip6_tables.h> + +MODULE_LICENSE("GPL"); +MODULE_AUTHOR("Harald Welte <laforge@netfilter.org>"); +MODULE_DESCRIPTION("Match for DCCP protocol packets"); +MODULE_ALIAS("ipt_dccp"); #define DCCHECK(cond, option, flag, invflag) (!((flag) & (option)) \ || (!!((invflag) & (option)) ^ (cond))) @@ -26,6 +34,7 @@ static DEFINE_SPINLOCK(dccp_buflock); static inline int dccp_find_option(u_int8_t option, const struct sk_buff *skb, + unsigned int protoff, const struct dccp_hdr *dh, int *hotdrop) { @@ -44,9 +53,7 @@ dccp_find_option(u_int8_t option, return 0; spin_lock_bh(&dccp_buflock); - op = skb_header_pointer(skb, - skb->nh.iph->ihl*4 + optoff, - optlen, dccp_optbuf); + op = skb_header_pointer(skb, protoff + optoff, optlen, dccp_optbuf); if (op == NULL) { /* If we don't have the whole header, drop packet. */ spin_unlock_bh(&dccp_buflock); @@ -78,10 +85,10 @@ match_types(const struct dccp_hdr *dh, u_int16_t typemask) } static inline int -match_option(u_int8_t option, const struct sk_buff *skb, +match_option(u_int8_t option, const struct sk_buff *skb, unsigned int protoff, const struct dccp_hdr *dh, int *hotdrop) { - return dccp_find_option(option, skb, dh, hotdrop); + return dccp_find_option(option, skb, protoff, dh, hotdrop); } static int @@ -90,16 +97,17 @@ match(const struct sk_buff *skb, const struct net_device *out, const void *matchinfo, int offset, + unsigned int protoff, int *hotdrop) { - const struct ipt_dccp_info *info = - (const struct ipt_dccp_info *)matchinfo; + const struct xt_dccp_info *info = + (const struct xt_dccp_info *)matchinfo; struct dccp_hdr _dh, *dh; if (offset) return 0; - dh = skb_header_pointer(skb, skb->nh.iph->ihl*4, sizeof(_dh), &_dh); + dh = skb_header_pointer(skb, protoff, sizeof(_dh), &_dh); if (dh == NULL) { *hotdrop = 1; return 0; @@ -107,42 +115,73 @@ match(const struct sk_buff *skb, return DCCHECK(((ntohs(dh->dccph_sport) >= info->spts[0]) && (ntohs(dh->dccph_sport) <= info->spts[1])), - IPT_DCCP_SRC_PORTS, info->flags, info->invflags) + XT_DCCP_SRC_PORTS, info->flags, info->invflags) && DCCHECK(((ntohs(dh->dccph_dport) >= info->dpts[0]) && (ntohs(dh->dccph_dport) <= info->dpts[1])), - IPT_DCCP_DEST_PORTS, info->flags, info->invflags) + XT_DCCP_DEST_PORTS, info->flags, info->invflags) && DCCHECK(match_types(dh, info->typemask), - IPT_DCCP_TYPE, info->flags, info->invflags) - && DCCHECK(match_option(info->option, skb, dh, hotdrop), - IPT_DCCP_OPTION, info->flags, info->invflags); + XT_DCCP_TYPE, info->flags, info->invflags) + && DCCHECK(match_option(info->option, skb, protoff, dh, + hotdrop), + XT_DCCP_OPTION, info->flags, info->invflags); } static int checkentry(const char *tablename, - const struct ipt_ip *ip, + const void *inf, void *matchinfo, unsigned int matchsize, unsigned int hook_mask) { - const struct ipt_dccp_info *info; + const struct ipt_ip *ip = inf; + const struct xt_dccp_info *info; - info = (const struct ipt_dccp_info *)matchinfo; + info = (const struct xt_dccp_info *)matchinfo; return ip->proto == IPPROTO_DCCP - && !(ip->invflags & IPT_INV_PROTO) - && matchsize == IPT_ALIGN(sizeof(struct ipt_dccp_info)) - && !(info->flags & ~IPT_DCCP_VALID_FLAGS) - && !(info->invflags & ~IPT_DCCP_VALID_FLAGS) + && !(ip->invflags & XT_INV_PROTO) + && matchsize == XT_ALIGN(sizeof(struct xt_dccp_info)) + && !(info->flags & ~XT_DCCP_VALID_FLAGS) + && !(info->invflags & ~XT_DCCP_VALID_FLAGS) && !(info->invflags & ~info->flags); } -static struct ipt_match dccp_match = +static int +checkentry6(const char *tablename, + const void *inf, + void *matchinfo, + unsigned int matchsize, + unsigned int hook_mask) +{ + const struct ip6t_ip6 *ip = inf; + const struct xt_dccp_info *info; + + info = (const struct xt_dccp_info *)matchinfo; + + return ip->proto == IPPROTO_DCCP + && !(ip->invflags & XT_INV_PROTO) + && matchsize == XT_ALIGN(sizeof(struct xt_dccp_info)) + && !(info->flags & ~XT_DCCP_VALID_FLAGS) + && !(info->invflags & ~XT_DCCP_VALID_FLAGS) + && !(info->invflags & ~info->flags); +} + + +static struct xt_match dccp_match = { .name = "dccp", .match = &match, .checkentry = &checkentry, .me = THIS_MODULE, }; +static struct xt_match dccp6_match = +{ + .name = "dccp", + .match = &match, + .checkentry = &checkentry6, + .me = THIS_MODULE, +}; + static int __init init(void) { @@ -154,23 +193,29 @@ static int __init init(void) dccp_optbuf = kmalloc(256 * 4, GFP_KERNEL); if (!dccp_optbuf) return -ENOMEM; - ret = ipt_register_match(&dccp_match); + ret = xt_register_match(AF_INET, &dccp_match); if (ret) - kfree(dccp_optbuf); + goto out_kfree; + ret = xt_register_match(AF_INET6, &dccp6_match); + if (ret) + goto out_unreg; + + return ret; + +out_unreg: + xt_unregister_match(AF_INET, &dccp_match); +out_kfree: + kfree(dccp_optbuf); return ret; } static void __exit fini(void) { - ipt_unregister_match(&dccp_match); + xt_unregister_match(AF_INET6, &dccp6_match); + xt_unregister_match(AF_INET, &dccp_match); kfree(dccp_optbuf); } module_init(init); module_exit(fini); - -MODULE_LICENSE("GPL"); -MODULE_AUTHOR("Harald Welte <laforge@netfilter.org>"); -MODULE_DESCRIPTION("Match for DCCP protocol packets"); - diff --git a/net/ipv4/netfilter/ipt_helper.c b/net/netfilter/xt_helper.c index aef649e393a..38b6715e1db 100644 --- a/net/ipv4/netfilter/ipt_helper.c +++ b/net/netfilter/xt_helper.c @@ -13,7 +13,6 @@ #include <linux/module.h> #include <linux/skbuff.h> #include <linux/netfilter.h> -#include <linux/interrupt.h> #if defined(CONFIG_IP_NF_CONNTRACK) || defined(CONFIG_IP_NF_CONNTRACK_MODULE) #include <linux/netfilter_ipv4/ip_conntrack.h> #include <linux/netfilter_ipv4/ip_conntrack_core.h> @@ -23,12 +22,14 @@ #include <net/netfilter/nf_conntrack_core.h> #include <net/netfilter/nf_conntrack_helper.h> #endif -#include <linux/netfilter_ipv4/ip_tables.h> -#include <linux/netfilter_ipv4/ipt_helper.h> +#include <linux/netfilter/x_tables.h> +#include <linux/netfilter/xt_helper.h> MODULE_LICENSE("GPL"); MODULE_AUTHOR("Martin Josefsson <gandalf@netfilter.org>"); MODULE_DESCRIPTION("iptables helper match module"); +MODULE_ALIAS("ipt_helper"); +MODULE_ALIAS("ip6t_helper"); #if 0 #define DEBUGP printk @@ -43,27 +44,28 @@ match(const struct sk_buff *skb, const struct net_device *out, const void *matchinfo, int offset, + unsigned int protoff, int *hotdrop) { - const struct ipt_helper_info *info = matchinfo; + const struct xt_helper_info *info = matchinfo; struct ip_conntrack *ct; enum ip_conntrack_info ctinfo; int ret = info->invert; ct = ip_conntrack_get((struct sk_buff *)skb, &ctinfo); if (!ct) { - DEBUGP("ipt_helper: Eek! invalid conntrack?\n"); + DEBUGP("xt_helper: Eek! invalid conntrack?\n"); return ret; } if (!ct->master) { - DEBUGP("ipt_helper: conntrack %p has no master\n", ct); + DEBUGP("xt_helper: conntrack %p has no master\n", ct); return ret; } read_lock_bh(&ip_conntrack_lock); if (!ct->master->helper) { - DEBUGP("ipt_helper: master ct %p has no helper\n", + DEBUGP("xt_helper: master ct %p has no helper\n", exp->expectant); goto out_unlock; } @@ -89,27 +91,28 @@ match(const struct sk_buff *skb, const struct net_device *out, const void *matchinfo, int offset, + unsigned int protoff, int *hotdrop) { - const struct ipt_helper_info *info = matchinfo; + const struct xt_helper_info *info = matchinfo; struct nf_conn *ct; enum ip_conntrack_info ctinfo; int ret = info->invert; ct = nf_ct_get((struct sk_buff *)skb, &ctinfo); if (!ct) { - DEBUGP("ipt_helper: Eek! invalid conntrack?\n"); + DEBUGP("xt_helper: Eek! invalid conntrack?\n"); return ret; } if (!ct->master) { - DEBUGP("ipt_helper: conntrack %p has no master\n", ct); + DEBUGP("xt_helper: conntrack %p has no master\n", ct); return ret; } read_lock_bh(&nf_conntrack_lock); if (!ct->master->helper) { - DEBUGP("ipt_helper: master ct %p has no helper\n", + DEBUGP("xt_helper: master ct %p has no helper\n", exp->expectant); goto out_unlock; } @@ -129,23 +132,29 @@ out_unlock: #endif static int check(const char *tablename, - const struct ipt_ip *ip, + const void *inf, void *matchinfo, unsigned int matchsize, unsigned int hook_mask) { - struct ipt_helper_info *info = matchinfo; + struct xt_helper_info *info = matchinfo; info->name[29] = '\0'; /* verify size */ - if (matchsize != IPT_ALIGN(sizeof(struct ipt_helper_info))) + if (matchsize != XT_ALIGN(sizeof(struct xt_helper_info))) return 0; return 1; } -static struct ipt_match helper_match = { +static struct xt_match helper_match = { + .name = "helper", + .match = &match, + .checkentry = &check, + .me = THIS_MODULE, +}; +static struct xt_match helper6_match = { .name = "helper", .match = &match, .checkentry = &check, @@ -154,13 +163,24 @@ static struct ipt_match helper_match = { static int __init init(void) { - need_ip_conntrack(); - return ipt_register_match(&helper_match); + int ret; + need_conntrack(); + + ret = xt_register_match(AF_INET, &helper_match); + if (ret < 0) + return ret; + + ret = xt_register_match(AF_INET6, &helper6_match); + if (ret < 0) + xt_unregister_match(AF_INET, &helper_match); + + return ret; } static void __exit fini(void) { - ipt_unregister_match(&helper_match); + xt_unregister_match(AF_INET, &helper_match); + xt_unregister_match(AF_INET6, &helper6_match); } module_init(init); diff --git a/net/netfilter/xt_length.c b/net/netfilter/xt_length.c new file mode 100644 index 00000000000..39c8faea63d --- /dev/null +++ b/net/netfilter/xt_length.c @@ -0,0 +1,99 @@ +/* Kernel module to match packet length. */ +/* (C) 1999-2001 James Morris <jmorros@intercode.com.au> + * + * This program is free software; you can redistribute it and/or modify + * it under the terms of the GNU General Public License version 2 as + * published by the Free Software Foundation. + */ + +#include <linux/module.h> +#include <linux/skbuff.h> +#include <linux/ipv6.h> +#include <net/ip.h> + +#include <linux/netfilter/xt_length.h> +#include <linux/netfilter/x_tables.h> + +MODULE_AUTHOR("James Morris <jmorris@intercode.com.au>"); +MODULE_DESCRIPTION("IP tables packet length matching module"); +MODULE_LICENSE("GPL"); +MODULE_ALIAS("ipt_length"); +MODULE_ALIAS("ip6t_length"); + +static int +match(const struct sk_buff *skb, + const struct net_device *in, + const struct net_device *out, + const void *matchinfo, + int offset, + unsigned int protoff, + int *hotdrop) +{ + const struct xt_length_info *info = matchinfo; + u_int16_t pktlen = ntohs(skb->nh.iph->tot_len); + + return (pktlen >= info->min && pktlen <= info->max) ^ info->invert; +} + +static int +match6(const struct sk_buff *skb, + const struct net_device *in, + const struct net_device *out, + const void *matchinfo, + int offset, + unsigned int protoff, + int *hotdrop) +{ + const struct xt_length_info *info = matchinfo; + u_int16_t pktlen = ntohs(skb->nh.ipv6h->payload_len) + sizeof(struct ipv6hdr); + + return (pktlen >= info->min && pktlen <= info->max) ^ info->invert; +} + +static int +checkentry(const char *tablename, + const void *ip, + void *matchinfo, + unsigned int matchsize, + unsigned int hook_mask) +{ + if (matchsize != XT_ALIGN(sizeof(struct xt_length_info))) + return 0; + + return 1; +} + +static struct xt_match length_match = { + .name = "length", + .match = &match, + .checkentry = &checkentry, + .me = THIS_MODULE, +}; +static struct xt_match length6_match = { + .name = "length", + .match = &match6, + .checkentry = &checkentry, + .me = THIS_MODULE, +}; + +static int __init init(void) +{ + int ret; + ret = xt_register_match(AF_INET, &length_match); + if (ret) + return ret; + ret = xt_register_match(AF_INET6, &length6_match); + if (ret) + xt_unregister_match(AF_INET, &length_match); + + return ret; +} + +static void __exit fini(void) +{ + xt_unregister_match(AF_INET, &length_match); + xt_unregister_match(AF_INET6, &length6_match); +} + +module_init(init); +module_exit(fini); diff --git a/net/ipv4/netfilter/ipt_limit.c b/net/netfilter/xt_limit.c index 0c24dcc703a..15e40506bc3 100644 --- a/net/ipv4/netfilter/ipt_limit.c +++ b/net/netfilter/xt_limit.c @@ -18,12 +18,14 @@ #include <linux/spinlock.h> #include <linux/interrupt.h> -#include <linux/netfilter_ipv4/ip_tables.h> -#include <linux/netfilter_ipv4/ipt_limit.h> +#include <linux/netfilter/x_tables.h> +#include <linux/netfilter/xt_limit.h> MODULE_LICENSE("GPL"); MODULE_AUTHOR("Herve Eychenne <rv@wallfire.org>"); MODULE_DESCRIPTION("iptables rate limit match"); +MODULE_ALIAS("ipt_limit"); +MODULE_ALIAS("ip6t_limit"); /* The algorithm used is the Simple Token Bucket Filter (TBF) * see net/sched/sch_tbf.c in the linux source tree @@ -68,9 +70,10 @@ ipt_limit_match(const struct sk_buff *skb, const struct net_device *out, const void *matchinfo, int offset, + unsigned int protoff, int *hotdrop) { - struct ipt_rateinfo *r = ((struct ipt_rateinfo *)matchinfo)->master; + struct xt_rateinfo *r = ((struct xt_rateinfo *)matchinfo)->master; unsigned long now = jiffies; spin_lock_bh(&limit_lock); @@ -96,32 +99,32 @@ user2credits(u_int32_t user) /* If multiplying would overflow... */ if (user > 0xFFFFFFFF / (HZ*CREDITS_PER_JIFFY)) /* Divide first. */ - return (user / IPT_LIMIT_SCALE) * HZ * CREDITS_PER_JIFFY; + return (user / XT_LIMIT_SCALE) * HZ * CREDITS_PER_JIFFY; - return (user * HZ * CREDITS_PER_JIFFY) / IPT_LIMIT_SCALE; + return (user * HZ * CREDITS_PER_JIFFY) / XT_LIMIT_SCALE; } static int ipt_limit_checkentry(const char *tablename, - const struct ipt_ip *ip, + const void *inf, void *matchinfo, unsigned int matchsize, unsigned int hook_mask) { - struct ipt_rateinfo *r = matchinfo; + struct xt_rateinfo *r = matchinfo; - if (matchsize != IPT_ALIGN(sizeof(struct ipt_rateinfo))) + if (matchsize != XT_ALIGN(sizeof(struct xt_rateinfo))) return 0; /* Check for overflow. */ if (r->burst == 0 || user2credits(r->avg * r->burst) < user2credits(r->avg)) { - printk("Overflow in ipt_limit, try lower: %u/%u\n", + printk("Overflow in xt_limit, try lower: %u/%u\n", r->avg, r->burst); return 0; } - /* User avg in seconds * IPT_LIMIT_SCALE: convert to jiffies * + /* User avg in seconds * XT_LIMIT_SCALE: convert to jiffies * 128. */ r->prev = jiffies; r->credit = user2credits(r->avg * r->burst); /* Credits full. */ @@ -134,7 +137,13 @@ ipt_limit_checkentry(const char *tablename, return 1; } -static struct ipt_match ipt_limit_reg = { +static struct xt_match ipt_limit_reg = { + .name = "limit", + .match = ipt_limit_match, + .checkentry = ipt_limit_checkentry, + .me = THIS_MODULE, +}; +static struct xt_match limit6_reg = { .name = "limit", .match = ipt_limit_match, .checkentry = ipt_limit_checkentry, @@ -143,14 +152,23 @@ static struct ipt_match ipt_limit_reg = { static int __init init(void) { - if (ipt_register_match(&ipt_limit_reg)) - return -EINVAL; - return 0; + int ret; + + ret = xt_register_match(AF_INET, &ipt_limit_reg); + if (ret) + return ret; + + ret = xt_register_match(AF_INET6, &limit6_reg); + if (ret) + xt_unregister_match(AF_INET, &ipt_limit_reg); + + return ret; } static void __exit fini(void) { - ipt_unregister_match(&ipt_limit_reg); + xt_unregister_match(AF_INET, &ipt_limit_reg); + xt_unregister_match(AF_INET6, &limit6_reg); } module_init(init); diff --git a/net/ipv4/netfilter/ipt_mac.c b/net/netfilter/xt_mac.c index 1b9bb4559f8..0461dcb5fc7 100644 --- a/net/ipv4/netfilter/ipt_mac.c +++ b/net/netfilter/xt_mac.c @@ -13,12 +13,15 @@ #include <linux/if_ether.h> #include <linux/etherdevice.h> -#include <linux/netfilter_ipv4/ipt_mac.h> -#include <linux/netfilter_ipv4/ip_tables.h> +#include <linux/netfilter_ipv4.h> +#include <linux/netfilter/xt_mac.h> +#include <linux/netfilter/x_tables.h> MODULE_LICENSE("GPL"); MODULE_AUTHOR("Netfilter Core Team <coreteam@netfilter.org>"); MODULE_DESCRIPTION("iptables mac matching module"); +MODULE_ALIAS("ipt_mac"); +MODULE_ALIAS("ip6t_mac"); static int match(const struct sk_buff *skb, @@ -26,9 +29,10 @@ match(const struct sk_buff *skb, const struct net_device *out, const void *matchinfo, int offset, + unsigned int protoff, int *hotdrop) { - const struct ipt_mac_info *info = matchinfo; + const struct xt_mac_info *info = matchinfo; /* Is mac pointer valid? */ return (skb->mac.raw >= skb->head @@ -40,7 +44,7 @@ match(const struct sk_buff *skb, static int ipt_mac_checkentry(const char *tablename, - const struct ipt_ip *ip, + const void *inf, void *matchinfo, unsigned int matchsize, unsigned int hook_mask) @@ -49,17 +53,23 @@ ipt_mac_checkentry(const char *tablename, if (hook_mask & ~((1 << NF_IP_PRE_ROUTING) | (1 << NF_IP_LOCAL_IN) | (1 << NF_IP_FORWARD))) { - printk("ipt_mac: only valid for PRE_ROUTING, LOCAL_IN or FORWARD.\n"); + printk("xt_mac: only valid for PRE_ROUTING, LOCAL_IN or FORWARD.\n"); return 0; } - if (matchsize != IPT_ALIGN(sizeof(struct ipt_mac_info))) + if (matchsize != XT_ALIGN(sizeof(struct xt_mac_info))) return 0; return 1; } -static struct ipt_match mac_match = { +static struct xt_match mac_match = { + .name = "mac", + .match = &match, + .checkentry = &ipt_mac_checkentry, + .me = THIS_MODULE, +}; +static struct xt_match mac6_match = { .name = "mac", .match = &match, .checkentry = &ipt_mac_checkentry, @@ -68,12 +78,22 @@ static struct ipt_match mac_match = { static int __init init(void) { - return ipt_register_match(&mac_match); + int ret; + ret = xt_register_match(AF_INET, &mac_match); + if (ret) + return ret; + + ret = xt_register_match(AF_INET6, &mac6_match); + if (ret) + xt_unregister_match(AF_INET, &mac_match); + + return ret; } static void __exit fini(void) { - ipt_unregister_match(&mac_match); + xt_unregister_match(AF_INET, &mac_match); + xt_unregister_match(AF_INET6, &mac6_match); } module_init(init); diff --git a/net/ipv4/netfilter/ipt_mark.c b/net/netfilter/xt_mark.c index 00bef6cdd3f..2a0ac62b72c 100644 --- a/net/ipv4/netfilter/ipt_mark.c +++ b/net/netfilter/xt_mark.c @@ -10,12 +10,14 @@ #include <linux/module.h> #include <linux/skbuff.h> -#include <linux/netfilter_ipv4/ipt_mark.h> -#include <linux/netfilter_ipv4/ip_tables.h> +#include <linux/netfilter/xt_mark.h> +#include <linux/netfilter/x_tables.h> MODULE_LICENSE("GPL"); MODULE_AUTHOR("Marc Boucher <marc@mbsi.ca>"); MODULE_DESCRIPTION("iptables mark matching module"); +MODULE_ALIAS("ipt_mark"); +MODULE_ALIAS("ip6t_mark"); static int match(const struct sk_buff *skb, @@ -23,23 +25,24 @@ match(const struct sk_buff *skb, const struct net_device *out, const void *matchinfo, int offset, + unsigned int protoff, int *hotdrop) { - const struct ipt_mark_info *info = matchinfo; + const struct xt_mark_info *info = matchinfo; return ((skb->nfmark & info->mask) == info->mark) ^ info->invert; } static int checkentry(const char *tablename, - const struct ipt_ip *ip, + const void *entry, void *matchinfo, unsigned int matchsize, unsigned int hook_mask) { - struct ipt_mark_info *minfo = (struct ipt_mark_info *) matchinfo; + struct xt_mark_info *minfo = (struct xt_mark_info *) matchinfo; - if (matchsize != IPT_ALIGN(sizeof(struct ipt_mark_info))) + if (matchsize != XT_ALIGN(sizeof(struct xt_mark_info))) return 0; if (minfo->mark > 0xffffffff || minfo->mask > 0xffffffff) { @@ -50,7 +53,14 @@ checkentry(const char *tablename, return 1; } -static struct ipt_match mark_match = { +static struct xt_match mark_match = { + .name = "mark", + .match = &match, + .checkentry = &checkentry, + .me = THIS_MODULE, +}; + +static struct xt_match mark6_match = { .name = "mark", .match = &match, .checkentry = &checkentry, @@ -59,12 +69,22 @@ static struct ipt_match mark_match = { static int __init init(void) { - return ipt_register_match(&mark_match); + int ret; + ret = xt_register_match(AF_INET, &mark_match); + if (ret) + return ret; + + ret = xt_register_match(AF_INET6, &mark6_match); + if (ret) + xt_unregister_match(AF_INET, &mark_match); + + return ret; } static void __exit fini(void) { - ipt_unregister_match(&mark_match); + xt_unregister_match(AF_INET, &mark_match); + xt_unregister_match(AF_INET6, &mark6_match); } module_init(init); diff --git a/net/ipv6/netfilter/ip6t_physdev.c b/net/netfilter/xt_physdev.c index 71515c86ece..19bb57c14df 100644 --- a/net/ipv6/netfilter/ip6t_physdev.c +++ b/net/netfilter/xt_physdev.c @@ -10,8 +10,8 @@ #include <linux/module.h> #include <linux/skbuff.h> -#include <linux/netfilter_ipv6/ip6t_physdev.h> -#include <linux/netfilter_ipv6/ip6_tables.h> +#include <linux/netfilter/xt_physdev.h> +#include <linux/netfilter/x_tables.h> #include <linux/netfilter_bridge.h> #define MATCH 1 #define NOMATCH 0 @@ -19,6 +19,8 @@ MODULE_LICENSE("GPL"); MODULE_AUTHOR("Bart De Schuymer <bdschuym@pandora.be>"); MODULE_DESCRIPTION("iptables bridge physical device match module"); +MODULE_ALIAS("ipt_physdev"); +MODULE_ALIAS("ip6t_physdev"); static int match(const struct sk_buff *skb, @@ -31,7 +33,7 @@ match(const struct sk_buff *skb, { int i; static const char nulldevname[IFNAMSIZ]; - const struct ip6t_physdev_info *info = matchinfo; + const struct xt_physdev_info *info = matchinfo; unsigned int ret; const char *indev, *outdev; struct nf_bridge_info *nf_bridge; @@ -41,37 +43,37 @@ match(const struct sk_buff *skb, * the destination device will be a bridge. */ if (!(nf_bridge = skb->nf_bridge)) { /* Return MATCH if the invert flags of the used options are on */ - if ((info->bitmask & IP6T_PHYSDEV_OP_BRIDGED) && - !(info->invert & IP6T_PHYSDEV_OP_BRIDGED)) + if ((info->bitmask & XT_PHYSDEV_OP_BRIDGED) && + !(info->invert & XT_PHYSDEV_OP_BRIDGED)) return NOMATCH; - if ((info->bitmask & IP6T_PHYSDEV_OP_ISIN) && - !(info->invert & IP6T_PHYSDEV_OP_ISIN)) + if ((info->bitmask & XT_PHYSDEV_OP_ISIN) && + !(info->invert & XT_PHYSDEV_OP_ISIN)) return NOMATCH; - if ((info->bitmask & IP6T_PHYSDEV_OP_ISOUT) && - !(info->invert & IP6T_PHYSDEV_OP_ISOUT)) + if ((info->bitmask & XT_PHYSDEV_OP_ISOUT) && + !(info->invert & XT_PHYSDEV_OP_ISOUT)) return NOMATCH; - if ((info->bitmask & IP6T_PHYSDEV_OP_IN) && - !(info->invert & IP6T_PHYSDEV_OP_IN)) + if ((info->bitmask & XT_PHYSDEV_OP_IN) && + !(info->invert & XT_PHYSDEV_OP_IN)) return NOMATCH; - if ((info->bitmask & IP6T_PHYSDEV_OP_OUT) && - !(info->invert & IP6T_PHYSDEV_OP_OUT)) + if ((info->bitmask & XT_PHYSDEV_OP_OUT) && + !(info->invert & XT_PHYSDEV_OP_OUT)) return NOMATCH; return MATCH; } /* This only makes sense in the FORWARD and POSTROUTING chains */ - if ((info->bitmask & IP6T_PHYSDEV_OP_BRIDGED) && + if ((info->bitmask & XT_PHYSDEV_OP_BRIDGED) && (!!(nf_bridge->mask & BRNF_BRIDGED) ^ - !(info->invert & IP6T_PHYSDEV_OP_BRIDGED))) + !(info->invert & XT_PHYSDEV_OP_BRIDGED))) return NOMATCH; - if ((info->bitmask & IP6T_PHYSDEV_OP_ISIN && - (!nf_bridge->physindev ^ !!(info->invert & IP6T_PHYSDEV_OP_ISIN))) || - (info->bitmask & IP6T_PHYSDEV_OP_ISOUT && - (!nf_bridge->physoutdev ^ !!(info->invert & IP6T_PHYSDEV_OP_ISOUT)))) + if ((info->bitmask & XT_PHYSDEV_OP_ISIN && + (!nf_bridge->physindev ^ !!(info->invert & XT_PHYSDEV_OP_ISIN))) || + (info->bitmask & XT_PHYSDEV_OP_ISOUT && + (!nf_bridge->physoutdev ^ !!(info->invert & XT_PHYSDEV_OP_ISOUT)))) return NOMATCH; - if (!(info->bitmask & IP6T_PHYSDEV_OP_IN)) + if (!(info->bitmask & XT_PHYSDEV_OP_IN)) goto match_outdev; indev = nf_bridge->physindev ? nf_bridge->physindev->name : nulldevname; for (i = 0, ret = 0; i < IFNAMSIZ/sizeof(unsigned int); i++) { @@ -80,11 +82,11 @@ match(const struct sk_buff *skb, & ((const unsigned int *)info->in_mask)[i]; } - if ((ret == 0) ^ !(info->invert & IP6T_PHYSDEV_OP_IN)) + if ((ret == 0) ^ !(info->invert & XT_PHYSDEV_OP_IN)) return NOMATCH; match_outdev: - if (!(info->bitmask & IP6T_PHYSDEV_OP_OUT)) + if (!(info->bitmask & XT_PHYSDEV_OP_OUT)) return MATCH; outdev = nf_bridge->physoutdev ? nf_bridge->physoutdev->name : nulldevname; @@ -94,27 +96,34 @@ match_outdev: & ((const unsigned int *)info->out_mask)[i]; } - return (ret != 0) ^ !(info->invert & IP6T_PHYSDEV_OP_OUT); + return (ret != 0) ^ !(info->invert & XT_PHYSDEV_OP_OUT); } static int checkentry(const char *tablename, - const struct ip6t_ip6 *ip, + const void *ip, void *matchinfo, unsigned int matchsize, unsigned int hook_mask) { - const struct ip6t_physdev_info *info = matchinfo; + const struct xt_physdev_info *info = matchinfo; - if (matchsize != IP6T_ALIGN(sizeof(struct ip6t_physdev_info))) + if (matchsize != XT_ALIGN(sizeof(struct xt_physdev_info))) return 0; - if (!(info->bitmask & IP6T_PHYSDEV_OP_MASK) || - info->bitmask & ~IP6T_PHYSDEV_OP_MASK) + if (!(info->bitmask & XT_PHYSDEV_OP_MASK) || + info->bitmask & ~XT_PHYSDEV_OP_MASK) return 0; return 1; } -static struct ip6t_match physdev_match = { +static struct xt_match physdev_match = { + .name = "physdev", + .match = &match, + .checkentry = &checkentry, + .me = THIS_MODULE, +}; + +static struct xt_match physdev6_match = { .name = "physdev", .match = &match, .checkentry = &checkentry, @@ -123,12 +132,23 @@ static struct ip6t_match physdev_match = { static int __init init(void) { - return ip6t_register_match(&physdev_match); + int ret; + + ret = xt_register_match(AF_INET, &physdev_match); + if (ret < 0) + return ret; + + ret = xt_register_match(AF_INET6, &physdev6_match); + if (ret < 0) + xt_unregister_match(AF_INET, &physdev_match); + + return ret; } static void __exit fini(void) { - ip6t_unregister_match(&physdev_match); + xt_unregister_match(AF_INET, &physdev_match); + xt_unregister_match(AF_INET6, &physdev6_match); } module_init(init); diff --git a/net/ipv4/netfilter/ipt_pkttype.c b/net/netfilter/xt_pkttype.c index 8ddb1dc5e5a..ab1b2630f97 100644 --- a/net/ipv4/netfilter/ipt_pkttype.c +++ b/net/netfilter/xt_pkttype.c @@ -10,60 +10,72 @@ #include <linux/if_ether.h> #include <linux/if_packet.h> -#include <linux/netfilter_ipv4/ipt_pkttype.h> -#include <linux/netfilter_ipv4/ip_tables.h> +#include <linux/netfilter/xt_pkttype.h> +#include <linux/netfilter/x_tables.h> MODULE_LICENSE("GPL"); MODULE_AUTHOR("Michal Ludvig <michal@logix.cz>"); MODULE_DESCRIPTION("IP tables match to match on linklayer packet type"); +MODULE_ALIAS("ipt_pkttype"); +MODULE_ALIAS("ip6t_pkttype"); static int match(const struct sk_buff *skb, const struct net_device *in, const struct net_device *out, const void *matchinfo, int offset, + unsigned int protoff, int *hotdrop) { - const struct ipt_pkttype_info *info = matchinfo; + const struct xt_pkttype_info *info = matchinfo; - return (skb->pkt_type == info->pkttype) ^ info->invert; + return (skb->pkt_type == info->pkttype) ^ info->invert; } static int checkentry(const char *tablename, - const struct ipt_ip *ip, + const void *ip, void *matchinfo, unsigned int matchsize, unsigned int hook_mask) { -/* - if (hook_mask - & ~((1 << NF_IP_PRE_ROUTING) | (1 << NF_IP_LOCAL_IN) - | (1 << NF_IP_FORWARD))) { - printk("ipt_pkttype: only valid for PRE_ROUTING, LOCAL_IN or FORWARD.\n"); - return 0; - } -*/ - if (matchsize != IPT_ALIGN(sizeof(struct ipt_pkttype_info))) + if (matchsize != XT_ALIGN(sizeof(struct xt_pkttype_info))) return 0; return 1; } -static struct ipt_match pkttype_match = { +static struct xt_match pkttype_match = { .name = "pkttype", .match = &match, .checkentry = &checkentry, .me = THIS_MODULE, }; +static struct xt_match pkttype6_match = { + .name = "pkttype", + .match = &match, + .checkentry = &checkentry, + .me = THIS_MODULE, +}; + static int __init init(void) { - return ipt_register_match(&pkttype_match); + int ret; + ret = xt_register_match(AF_INET, &pkttype_match); + if (ret) + return ret; + + ret = xt_register_match(AF_INET6, &pkttype6_match); + if (ret) + xt_unregister_match(AF_INET, &pkttype_match); + + return ret; } static void __exit fini(void) { - ipt_unregister_match(&pkttype_match); + xt_unregister_match(AF_INET, &pkttype_match); + xt_unregister_match(AF_INET6, &pkttype6_match); } module_init(init); diff --git a/net/ipv4/netfilter/ipt_realm.c b/net/netfilter/xt_realm.c index 54a6897ebaa..2b7e1781d34 100644 --- a/net/ipv4/netfilter/ipt_realm.c +++ b/net/netfilter/xt_realm.c @@ -14,12 +14,14 @@ #include <linux/netdevice.h> #include <net/route.h> -#include <linux/netfilter_ipv4/ipt_realm.h> -#include <linux/netfilter_ipv4/ip_tables.h> +#include <linux/netfilter_ipv4.h> +#include <linux/netfilter/xt_realm.h> +#include <linux/netfilter/x_tables.h> MODULE_AUTHOR("Sampsa Ranta <sampsa@netsonic.fi>"); MODULE_LICENSE("GPL"); -MODULE_DESCRIPTION("iptables realm match"); +MODULE_DESCRIPTION("X_tables realm match"); +MODULE_ALIAS("ipt_realm"); static int match(const struct sk_buff *skb, @@ -27,16 +29,17 @@ match(const struct sk_buff *skb, const struct net_device *out, const void *matchinfo, int offset, + unsigned int protoff, int *hotdrop) { - const struct ipt_realm_info *info = matchinfo; + const struct xt_realm_info *info = matchinfo; struct dst_entry *dst = skb->dst; return (info->id == (dst->tclassid & info->mask)) ^ info->invert; } static int check(const char *tablename, - const struct ipt_ip *ip, + const void *ip, void *matchinfo, unsigned int matchsize, unsigned int hook_mask) @@ -44,18 +47,18 @@ static int check(const char *tablename, if (hook_mask & ~((1 << NF_IP_POST_ROUTING) | (1 << NF_IP_FORWARD) | (1 << NF_IP_LOCAL_OUT) | (1 << NF_IP_LOCAL_IN))) { - printk("ipt_realm: only valid for POST_ROUTING, LOCAL_OUT, " + printk("xt_realm: only valid for POST_ROUTING, LOCAL_OUT, " "LOCAL_IN or FORWARD.\n"); return 0; } - if (matchsize != IPT_ALIGN(sizeof(struct ipt_realm_info))) { - printk("ipt_realm: invalid matchsize.\n"); + if (matchsize != XT_ALIGN(sizeof(struct xt_realm_info))) { + printk("xt_realm: invalid matchsize.\n"); return 0; } return 1; } -static struct ipt_match realm_match = { +static struct xt_match realm_match = { .name = "realm", .match = match, .checkentry = check, @@ -64,12 +67,12 @@ static struct ipt_match realm_match = { static int __init init(void) { - return ipt_register_match(&realm_match); + return xt_register_match(AF_INET, &realm_match); } static void __exit fini(void) { - ipt_unregister_match(&realm_match); + xt_unregister_match(AF_INET, &realm_match); } module_init(init); diff --git a/net/ipv4/netfilter/ipt_sctp.c b/net/netfilter/xt_sctp.c index fe2b327bcaa..10fbfc5ba75 100644 --- a/net/ipv4/netfilter/ipt_sctp.c +++ b/net/netfilter/xt_sctp.c @@ -1,10 +1,18 @@ #include <linux/module.h> #include <linux/skbuff.h> #include <net/ip.h> +#include <net/ipv6.h> #include <linux/sctp.h> +#include <linux/netfilter/x_tables.h> +#include <linux/netfilter/xt_sctp.h> #include <linux/netfilter_ipv4/ip_tables.h> -#include <linux/netfilter_ipv4/ipt_sctp.h> +#include <linux/netfilter_ipv6/ip6_tables.h> + +MODULE_LICENSE("GPL"); +MODULE_AUTHOR("Kiran Kumar Immidi"); +MODULE_DESCRIPTION("Match for SCTP protocol packets"); +MODULE_ALIAS("ipt_sctp"); #ifdef DEBUG_SCTP #define duprintf(format, args...) printk(format , ## args) @@ -16,7 +24,7 @@ || (!!((invflag) & (option)) ^ (cond))) static int -match_flags(const struct ipt_sctp_flag_info *flag_info, +match_flags(const struct xt_sctp_flag_info *flag_info, const int flag_count, u_int8_t chunktype, u_int8_t chunkflags) @@ -32,15 +40,15 @@ match_flags(const struct ipt_sctp_flag_info *flag_info, return 1; } -static int +static inline int match_packet(const struct sk_buff *skb, + unsigned int offset, const u_int32_t *chunkmap, int chunk_match_type, - const struct ipt_sctp_flag_info *flag_info, + const struct xt_sctp_flag_info *flag_info, const int flag_count, int *hotdrop) { - int offset; u_int32_t chunkmapcopy[256 / sizeof (u_int32_t)]; sctp_chunkhdr_t _sch, *sch; @@ -52,7 +60,6 @@ match_packet(const struct sk_buff *skb, SCTP_CHUNKMAP_COPY(chunkmapcopy, chunkmap); } - offset = skb->nh.iph->ihl * 4 + sizeof (sctp_sctphdr_t); do { sch = skb_header_pointer(skb, offset, sizeof(_sch), &_sch); if (sch == NULL) { @@ -118,19 +125,20 @@ match(const struct sk_buff *skb, const struct net_device *out, const void *matchinfo, int offset, + unsigned int protoff, int *hotdrop) { - const struct ipt_sctp_info *info; + const struct xt_sctp_info *info; sctp_sctphdr_t _sh, *sh; - info = (const struct ipt_sctp_info *)matchinfo; + info = (const struct xt_sctp_info *)matchinfo; if (offset) { duprintf("Dropping non-first fragment.. FIXME\n"); return 0; } - sh = skb_header_pointer(skb, skb->nh.iph->ihl*4, sizeof(_sh), &_sh); + sh = skb_header_pointer(skb, protoff, sizeof(_sh), &_sh); if (sh == NULL) { duprintf("Dropping evil TCP offset=0 tinygram.\n"); *hotdrop = 1; @@ -140,64 +148,103 @@ match(const struct sk_buff *skb, return SCCHECK(((ntohs(sh->source) >= info->spts[0]) && (ntohs(sh->source) <= info->spts[1])), - IPT_SCTP_SRC_PORTS, info->flags, info->invflags) + XT_SCTP_SRC_PORTS, info->flags, info->invflags) && SCCHECK(((ntohs(sh->dest) >= info->dpts[0]) && (ntohs(sh->dest) <= info->dpts[1])), - IPT_SCTP_DEST_PORTS, info->flags, info->invflags) - && SCCHECK(match_packet(skb, info->chunkmap, info->chunk_match_type, + XT_SCTP_DEST_PORTS, info->flags, info->invflags) + && SCCHECK(match_packet(skb, protoff, + info->chunkmap, info->chunk_match_type, info->flag_info, info->flag_count, hotdrop), - IPT_SCTP_CHUNK_TYPES, info->flags, info->invflags); + XT_SCTP_CHUNK_TYPES, info->flags, info->invflags); } static int checkentry(const char *tablename, - const struct ipt_ip *ip, + const void *inf, + void *matchinfo, + unsigned int matchsize, + unsigned int hook_mask) +{ + const struct xt_sctp_info *info; + const struct ipt_ip *ip = inf; + + info = (const struct xt_sctp_info *)matchinfo; + + return ip->proto == IPPROTO_SCTP + && !(ip->invflags & XT_INV_PROTO) + && matchsize == XT_ALIGN(sizeof(struct xt_sctp_info)) + && !(info->flags & ~XT_SCTP_VALID_FLAGS) + && !(info->invflags & ~XT_SCTP_VALID_FLAGS) + && !(info->invflags & ~info->flags) + && ((!(info->flags & XT_SCTP_CHUNK_TYPES)) || + (info->chunk_match_type & + (SCTP_CHUNK_MATCH_ALL + | SCTP_CHUNK_MATCH_ANY + | SCTP_CHUNK_MATCH_ONLY))); +} + +static int +checkentry6(const char *tablename, + const void *inf, void *matchinfo, unsigned int matchsize, unsigned int hook_mask) { - const struct ipt_sctp_info *info; + const struct xt_sctp_info *info; + const struct ip6t_ip6 *ip = inf; - info = (const struct ipt_sctp_info *)matchinfo; + info = (const struct xt_sctp_info *)matchinfo; return ip->proto == IPPROTO_SCTP - && !(ip->invflags & IPT_INV_PROTO) - && matchsize == IPT_ALIGN(sizeof(struct ipt_sctp_info)) - && !(info->flags & ~IPT_SCTP_VALID_FLAGS) - && !(info->invflags & ~IPT_SCTP_VALID_FLAGS) + && !(ip->invflags & XT_INV_PROTO) + && matchsize == XT_ALIGN(sizeof(struct xt_sctp_info)) + && !(info->flags & ~XT_SCTP_VALID_FLAGS) + && !(info->invflags & ~XT_SCTP_VALID_FLAGS) && !(info->invflags & ~info->flags) - && ((!(info->flags & IPT_SCTP_CHUNK_TYPES)) || + && ((!(info->flags & XT_SCTP_CHUNK_TYPES)) || (info->chunk_match_type & (SCTP_CHUNK_MATCH_ALL | SCTP_CHUNK_MATCH_ANY | SCTP_CHUNK_MATCH_ONLY))); } -static struct ipt_match sctp_match = + +static struct xt_match sctp_match = { - .list = { NULL, NULL}, .name = "sctp", .match = &match, .checkentry = &checkentry, - .destroy = NULL, + .me = THIS_MODULE +}; +static struct xt_match sctp6_match = +{ + .name = "sctp", + .match = &match, + .checkentry = &checkentry6, .me = THIS_MODULE }; + static int __init init(void) { - return ipt_register_match(&sctp_match); + int ret; + ret = xt_register_match(AF_INET, &sctp_match); + if (ret) + return ret; + + ret = xt_register_match(AF_INET6, &sctp6_match); + if (ret) + xt_unregister_match(AF_INET, &sctp_match); + + return ret; } static void __exit fini(void) { - ipt_unregister_match(&sctp_match); + xt_unregister_match(AF_INET6, &sctp6_match); + xt_unregister_match(AF_INET, &sctp_match); } module_init(init); module_exit(fini); - -MODULE_LICENSE("GPL"); -MODULE_AUTHOR("Kiran Kumar Immidi"); -MODULE_DESCRIPTION("Match for SCTP protocol packets"); - diff --git a/net/ipv4/netfilter/ipt_state.c b/net/netfilter/xt_state.c index 4d7f16b70ce..39ce808d40e 100644 --- a/net/ipv4/netfilter/ipt_state.c +++ b/net/netfilter/xt_state.c @@ -1,7 +1,7 @@ /* Kernel module to match connection tracking information. */ /* (C) 1999-2001 Paul `Rusty' Russell - * (C) 2002-2004 Netfilter Core Team <coreteam@netfilter.org> + * (C) 2002-2005 Netfilter Core Team <coreteam@netfilter.org> * * This program is free software; you can redistribute it and/or modify * it under the terms of the GNU General Public License version 2 as @@ -11,12 +11,14 @@ #include <linux/module.h> #include <linux/skbuff.h> #include <net/netfilter/nf_conntrack_compat.h> -#include <linux/netfilter_ipv4/ip_tables.h> -#include <linux/netfilter_ipv4/ipt_state.h> +#include <linux/netfilter/x_tables.h> +#include <linux/netfilter/xt_state.h> MODULE_LICENSE("GPL"); MODULE_AUTHOR("Rusty Russell <rusty@rustcorp.com.au>"); -MODULE_DESCRIPTION("iptables connection tracking state match module"); +MODULE_DESCRIPTION("ip[6]_tables connection tracking state match module"); +MODULE_ALIAS("ipt_state"); +MODULE_ALIAS("ip6t_state"); static int match(const struct sk_buff *skb, @@ -24,35 +26,43 @@ match(const struct sk_buff *skb, const struct net_device *out, const void *matchinfo, int offset, + unsigned int protoff, int *hotdrop) { - const struct ipt_state_info *sinfo = matchinfo; + const struct xt_state_info *sinfo = matchinfo; enum ip_conntrack_info ctinfo; unsigned int statebit; if (nf_ct_is_untracked(skb)) - statebit = IPT_STATE_UNTRACKED; + statebit = XT_STATE_UNTRACKED; else if (!nf_ct_get_ctinfo(skb, &ctinfo)) - statebit = IPT_STATE_INVALID; + statebit = XT_STATE_INVALID; else - statebit = IPT_STATE_BIT(ctinfo); + statebit = XT_STATE_BIT(ctinfo); return (sinfo->statemask & statebit); } static int check(const char *tablename, - const struct ipt_ip *ip, + const void *ip, void *matchinfo, unsigned int matchsize, unsigned int hook_mask) { - if (matchsize != IPT_ALIGN(sizeof(struct ipt_state_info))) + if (matchsize != XT_ALIGN(sizeof(struct xt_state_info))) return 0; return 1; } -static struct ipt_match state_match = { +static struct xt_match state_match = { + .name = "state", + .match = &match, + .checkentry = &check, + .me = THIS_MODULE, +}; + +static struct xt_match state6_match = { .name = "state", .match = &match, .checkentry = &check, @@ -61,13 +71,25 @@ static struct ipt_match state_match = { static int __init init(void) { - need_ip_conntrack(); - return ipt_register_match(&state_match); + int ret; + + need_conntrack(); + + ret = xt_register_match(AF_INET, &state_match); + if (ret < 0) + return ret; + + ret = xt_register_match(AF_INET6, &state6_match); + if (ret < 0) + xt_unregister_match(AF_INET,&state_match); + + return ret; } static void __exit fini(void) { - ipt_unregister_match(&state_match); + xt_unregister_match(AF_INET, &state_match); + xt_unregister_match(AF_INET6, &state6_match); } module_init(init); diff --git a/net/ipv4/netfilter/ipt_string.c b/net/netfilter/xt_string.c index b5def204d79..7c7d5c8807d 100644 --- a/net/ipv4/netfilter/ipt_string.c +++ b/net/netfilter/xt_string.c @@ -11,23 +11,26 @@ #include <linux/module.h> #include <linux/kernel.h> #include <linux/skbuff.h> -#include <linux/netfilter_ipv4/ip_tables.h> -#include <linux/netfilter_ipv4/ipt_string.h> +#include <linux/netfilter/x_tables.h> +#include <linux/netfilter/xt_string.h> #include <linux/textsearch.h> MODULE_AUTHOR("Pablo Neira Ayuso <pablo@eurodev.net>"); MODULE_DESCRIPTION("IP tables string match module"); MODULE_LICENSE("GPL"); +MODULE_ALIAS("ipt_string"); +MODULE_ALIAS("ip6t_string"); static int match(const struct sk_buff *skb, const struct net_device *in, const struct net_device *out, const void *matchinfo, int offset, + unsigned int protoff, int *hotdrop) { struct ts_state state; - struct ipt_string_info *conf = (struct ipt_string_info *) matchinfo; + struct xt_string_info *conf = (struct xt_string_info *) matchinfo; memset(&state, 0, sizeof(struct ts_state)); @@ -36,18 +39,18 @@ static int match(const struct sk_buff *skb, != UINT_MAX) && !conf->invert; } -#define STRING_TEXT_PRIV(m) ((struct ipt_string_info *) m) +#define STRING_TEXT_PRIV(m) ((struct xt_string_info *) m) static int checkentry(const char *tablename, - const struct ipt_ip *ip, + const void *ip, void *matchinfo, unsigned int matchsize, unsigned int hook_mask) { - struct ipt_string_info *conf = matchinfo; + struct xt_string_info *conf = matchinfo; struct ts_config *ts_conf; - if (matchsize != IPT_ALIGN(sizeof(struct ipt_string_info))) + if (matchsize != XT_ALIGN(sizeof(struct xt_string_info))) return 0; /* Damn, can't handle this case properly with iptables... */ @@ -69,7 +72,14 @@ static void destroy(void *matchinfo, unsigned int matchsize) textsearch_destroy(STRING_TEXT_PRIV(matchinfo)->config); } -static struct ipt_match string_match = { +static struct xt_match string_match = { + .name = "string", + .match = match, + .checkentry = checkentry, + .destroy = destroy, + .me = THIS_MODULE +}; +static struct xt_match string6_match = { .name = "string", .match = match, .checkentry = checkentry, @@ -79,12 +89,22 @@ static struct ipt_match string_match = { static int __init init(void) { - return ipt_register_match(&string_match); + int ret; + + ret = xt_register_match(AF_INET, &string_match); + if (ret) + return ret; + ret = xt_register_match(AF_INET6, &string6_match); + if (ret) + xt_unregister_match(AF_INET, &string_match); + + return ret; } static void __exit fini(void) { - ipt_unregister_match(&string_match); + xt_unregister_match(AF_INET, &string_match); + xt_unregister_match(AF_INET6, &string6_match); } module_init(init); diff --git a/net/ipv4/netfilter/ipt_tcpmss.c b/net/netfilter/xt_tcpmss.c index 4dc9b16ab4a..acf7f533e9f 100644 --- a/net/ipv4/netfilter/ipt_tcpmss.c +++ b/net/netfilter/xt_tcpmss.c @@ -1,6 +1,7 @@ /* Kernel module to match TCP MSS values. */ /* Copyright (C) 2000 Marc Boucher <marc@mbsi.ca> + * Portions (C) 2005 by Harald Welte <laforge@netfilter.org> * * This program is free software; you can redistribute it and/or modify * it under the terms of the GNU General Public License version 2 as @@ -11,19 +12,24 @@ #include <linux/skbuff.h> #include <net/tcp.h> -#include <linux/netfilter_ipv4/ipt_tcpmss.h> +#include <linux/netfilter/xt_tcpmss.h> +#include <linux/netfilter/x_tables.h> + #include <linux/netfilter_ipv4/ip_tables.h> +#include <linux/netfilter_ipv6/ip6_tables.h> #define TH_SYN 0x02 MODULE_LICENSE("GPL"); MODULE_AUTHOR("Marc Boucher <marc@mbsi.ca>"); MODULE_DESCRIPTION("iptables TCP MSS match module"); +MODULE_ALIAS("ipt_tcpmss"); /* Returns 1 if the mss option is set and matched by the range, 0 otherwise */ static inline int mssoption_match(u_int16_t min, u_int16_t max, const struct sk_buff *skb, + unsigned int protoff, int invert, int *hotdrop) { @@ -33,8 +39,7 @@ mssoption_match(u_int16_t min, u_int16_t max, unsigned int i, optlen; /* If we don't have the whole header, drop packet. */ - th = skb_header_pointer(skb, skb->nh.iph->ihl * 4, - sizeof(_tcph), &_tcph); + th = skb_header_pointer(skb, protoff, sizeof(_tcph), &_tcph); if (th == NULL) goto dropit; @@ -47,8 +52,7 @@ mssoption_match(u_int16_t min, u_int16_t max, goto out; /* Truncated options. */ - op = skb_header_pointer(skb, skb->nh.iph->ihl * 4 + sizeof(*th), - optlen, _opt); + op = skb_header_pointer(skb, protoff + sizeof(*th), optlen, _opt); if (op == NULL) goto dropit; @@ -79,22 +83,24 @@ match(const struct sk_buff *skb, const struct net_device *out, const void *matchinfo, int offset, + unsigned int protoff, int *hotdrop) { - const struct ipt_tcpmss_match_info *info = matchinfo; + const struct xt_tcpmss_match_info *info = matchinfo; - return mssoption_match(info->mss_min, info->mss_max, skb, + return mssoption_match(info->mss_min, info->mss_max, skb, protoff, info->invert, hotdrop); } static int checkentry(const char *tablename, - const struct ipt_ip *ip, + const void *ipinfo, void *matchinfo, unsigned int matchsize, unsigned int hook_mask) { - if (matchsize != IPT_ALIGN(sizeof(struct ipt_tcpmss_match_info))) + const struct ipt_ip *ip = ipinfo; + if (matchsize != XT_ALIGN(sizeof(struct xt_tcpmss_match_info))) return 0; /* Must specify -p tcp */ @@ -106,21 +112,60 @@ checkentry(const char *tablename, return 1; } -static struct ipt_match tcpmss_match = { +static int +checkentry6(const char *tablename, + const void *ipinfo, + void *matchinfo, + unsigned int matchsize, + unsigned int hook_mask) +{ + const struct ip6t_ip6 *ip = ipinfo; + + if (matchsize != XT_ALIGN(sizeof(struct xt_tcpmss_match_info))) + return 0; + + /* Must specify -p tcp */ + if (ip->proto != IPPROTO_TCP || (ip->invflags & XT_INV_PROTO)) { + printk("tcpmss: Only works on TCP packets\n"); + return 0; + } + + return 1; +} + +static struct xt_match tcpmss_match = { .name = "tcpmss", .match = &match, .checkentry = &checkentry, .me = THIS_MODULE, }; +static struct xt_match tcpmss6_match = { + .name = "tcpmss", + .match = &match, + .checkentry = &checkentry6, + .me = THIS_MODULE, +}; + + static int __init init(void) { - return ipt_register_match(&tcpmss_match); + int ret; + ret = xt_register_match(AF_INET, &tcpmss_match); + if (ret) + return ret; + + ret = xt_register_match(AF_INET6, &tcpmss6_match); + if (ret) + xt_unregister_match(AF_INET, &tcpmss_match); + + return ret; } static void __exit fini(void) { - ipt_unregister_match(&tcpmss_match); + xt_unregister_match(AF_INET6, &tcpmss6_match); + xt_unregister_match(AF_INET, &tcpmss_match); } module_init(init); diff --git a/net/netfilter/xt_tcpudp.c b/net/netfilter/xt_tcpudp.c new file mode 100644 index 00000000000..669c8113cc6 --- /dev/null +++ b/net/netfilter/xt_tcpudp.c @@ -0,0 +1,334 @@ +#include <linux/types.h> +#include <linux/module.h> +#include <net/ip.h> +#include <linux/ipv6.h> +#include <net/ipv6.h> +#include <net/tcp.h> +#include <net/udp.h> +#include <linux/netfilter/x_tables.h> +#include <linux/netfilter/xt_tcpudp.h> +#include <linux/netfilter_ipv4/ip_tables.h> +#include <linux/netfilter_ipv6/ip6_tables.h> + +MODULE_DESCRIPTION("x_tables match for TCP and UDP, supports IPv4 and IPv6"); +MODULE_LICENSE("GPL"); +MODULE_ALIAS("xt_tcp"); +MODULE_ALIAS("xt_udp"); +MODULE_ALIAS("ipt_udp"); +MODULE_ALIAS("ipt_tcp"); +MODULE_ALIAS("ip6t_udp"); +MODULE_ALIAS("ip6t_tcp"); + +#ifdef DEBUG_IP_FIREWALL_USER +#define duprintf(format, args...) printk(format , ## args) +#else +#define duprintf(format, args...) +#endif + + +/* Returns 1 if the port is matched by the range, 0 otherwise */ +static inline int +port_match(u_int16_t min, u_int16_t max, u_int16_t port, int invert) +{ + int ret; + + ret = (port >= min && port <= max) ^ invert; + return ret; +} + +static int +tcp_find_option(u_int8_t option, + const struct sk_buff *skb, + unsigned int protoff, + unsigned int optlen, + int invert, + int *hotdrop) +{ + /* tcp.doff is only 4 bits, ie. max 15 * 4 bytes */ + u_int8_t _opt[60 - sizeof(struct tcphdr)], *op; + unsigned int i; + + duprintf("tcp_match: finding option\n"); + + if (!optlen) + return invert; + + /* If we don't have the whole header, drop packet. */ + op = skb_header_pointer(skb, protoff + sizeof(struct tcphdr), + optlen, _opt); + if (op == NULL) { + *hotdrop = 1; + return 0; + } + + for (i = 0; i < optlen; ) { + if (op[i] == option) return !invert; + if (op[i] < 2) i++; + else i += op[i+1]?:1; + } + + return invert; +} + +static int +tcp_match(const struct sk_buff *skb, + const struct net_device *in, + const struct net_device *out, + const void *matchinfo, + int offset, + unsigned int protoff, + int *hotdrop) +{ + struct tcphdr _tcph, *th; + const struct xt_tcp *tcpinfo = matchinfo; + + if (offset) { + /* To quote Alan: + + Don't allow a fragment of TCP 8 bytes in. Nobody normal + causes this. Its a cracker trying to break in by doing a + flag overwrite to pass the direction checks. + */ + if (offset == 1) { + duprintf("Dropping evil TCP offset=1 frag.\n"); + *hotdrop = 1; + } + /* Must not be a fragment. */ + return 0; + } + +#define FWINVTCP(bool,invflg) ((bool) ^ !!(tcpinfo->invflags & invflg)) + + th = skb_header_pointer(skb, protoff, sizeof(_tcph), &_tcph); + if (th == NULL) { + /* We've been asked to examine this packet, and we + can't. Hence, no choice but to drop. */ + duprintf("Dropping evil TCP offset=0 tinygram.\n"); + *hotdrop = 1; + return 0; + } + + if (!port_match(tcpinfo->spts[0], tcpinfo->spts[1], + ntohs(th->source), + !!(tcpinfo->invflags & XT_TCP_INV_SRCPT))) + return 0; + if (!port_match(tcpinfo->dpts[0], tcpinfo->dpts[1], + ntohs(th->dest), + !!(tcpinfo->invflags & XT_TCP_INV_DSTPT))) + return 0; + if (!FWINVTCP((((unsigned char *)th)[13] & tcpinfo->flg_mask) + == tcpinfo->flg_cmp, + XT_TCP_INV_FLAGS)) + return 0; + if (tcpinfo->option) { + if (th->doff * 4 < sizeof(_tcph)) { + *hotdrop = 1; + return 0; + } + if (!tcp_find_option(tcpinfo->option, skb, protoff, + th->doff*4 - sizeof(_tcph), + tcpinfo->invflags & XT_TCP_INV_OPTION, + hotdrop)) + return 0; + } + return 1; +} + +/* Called when user tries to insert an entry of this type. */ +static int +tcp_checkentry(const char *tablename, + const void *info, + void *matchinfo, + unsigned int matchsize, + unsigned int hook_mask) +{ + const struct ipt_ip *ip = info; + const struct xt_tcp *tcpinfo = matchinfo; + + /* Must specify proto == TCP, and no unknown invflags */ + return ip->proto == IPPROTO_TCP + && !(ip->invflags & XT_INV_PROTO) + && matchsize == XT_ALIGN(sizeof(struct xt_tcp)) + && !(tcpinfo->invflags & ~XT_TCP_INV_MASK); +} + +/* Called when user tries to insert an entry of this type. */ +static int +tcp6_checkentry(const char *tablename, + const void *entry, + void *matchinfo, + unsigned int matchsize, + unsigned int hook_mask) +{ + const struct ip6t_ip6 *ipv6 = entry; + const struct xt_tcp *tcpinfo = matchinfo; + + /* Must specify proto == TCP, and no unknown invflags */ + return ipv6->proto == IPPROTO_TCP + && !(ipv6->invflags & XT_INV_PROTO) + && matchsize == XT_ALIGN(sizeof(struct xt_tcp)) + && !(tcpinfo->invflags & ~XT_TCP_INV_MASK); +} + + +static int +udp_match(const struct sk_buff *skb, + const struct net_device *in, + const struct net_device *out, + const void *matchinfo, + int offset, + unsigned int protoff, + int *hotdrop) +{ + struct udphdr _udph, *uh; + const struct xt_udp *udpinfo = matchinfo; + + /* Must not be a fragment. */ + if (offset) + return 0; + + uh = skb_header_pointer(skb, protoff, sizeof(_udph), &_udph); + if (uh == NULL) { + /* We've been asked to examine this packet, and we + can't. Hence, no choice but to drop. */ + duprintf("Dropping evil UDP tinygram.\n"); + *hotdrop = 1; + return 0; + } + + return port_match(udpinfo->spts[0], udpinfo->spts[1], + ntohs(uh->source), + !!(udpinfo->invflags & XT_UDP_INV_SRCPT)) + && port_match(udpinfo->dpts[0], udpinfo->dpts[1], + ntohs(uh->dest), + !!(udpinfo->invflags & XT_UDP_INV_DSTPT)); +} + +/* Called when user tries to insert an entry of this type. */ +static int +udp_checkentry(const char *tablename, + const void *info, + void *matchinfo, + unsigned int matchinfosize, + unsigned int hook_mask) +{ + const struct ipt_ip *ip = info; + const struct xt_udp *udpinfo = matchinfo; + + /* Must specify proto == UDP, and no unknown invflags */ + if (ip->proto != IPPROTO_UDP || (ip->invflags & XT_INV_PROTO)) { + duprintf("ipt_udp: Protocol %u != %u\n", ip->proto, + IPPROTO_UDP); + return 0; + } + if (matchinfosize != XT_ALIGN(sizeof(struct xt_udp))) { + duprintf("ipt_udp: matchsize %u != %u\n", + matchinfosize, XT_ALIGN(sizeof(struct xt_udp))); + return 0; + } + if (udpinfo->invflags & ~XT_UDP_INV_MASK) { + duprintf("ipt_udp: unknown flags %X\n", + udpinfo->invflags); + return 0; + } + + return 1; +} + +/* Called when user tries to insert an entry of this type. */ +static int +udp6_checkentry(const char *tablename, + const void *entry, + void *matchinfo, + unsigned int matchinfosize, + unsigned int hook_mask) +{ + const struct ip6t_ip6 *ipv6 = entry; + const struct xt_udp *udpinfo = matchinfo; + + /* Must specify proto == UDP, and no unknown invflags */ + if (ipv6->proto != IPPROTO_UDP || (ipv6->invflags & XT_INV_PROTO)) { + duprintf("ip6t_udp: Protocol %u != %u\n", ipv6->proto, + IPPROTO_UDP); + return 0; + } + if (matchinfosize != XT_ALIGN(sizeof(struct xt_udp))) { + duprintf("ip6t_udp: matchsize %u != %u\n", + matchinfosize, XT_ALIGN(sizeof(struct xt_udp))); + return 0; + } + if (udpinfo->invflags & ~XT_UDP_INV_MASK) { + duprintf("ip6t_udp: unknown flags %X\n", + udpinfo->invflags); + return 0; + } + + return 1; +} + +static struct xt_match tcp_matchstruct = { + .name = "tcp", + .match = &tcp_match, + .checkentry = &tcp_checkentry, + .me = THIS_MODULE, +}; +static struct xt_match tcp6_matchstruct = { + .name = "tcp", + .match = &tcp_match, + .checkentry = &tcp6_checkentry, + .me = THIS_MODULE, +}; + +static struct xt_match udp_matchstruct = { + .name = "udp", + .match = &udp_match, + .checkentry = &udp_checkentry, + .me = THIS_MODULE, +}; +static struct xt_match udp6_matchstruct = { + .name = "udp", + .match = &udp_match, + .checkentry = &udp6_checkentry, + .me = THIS_MODULE, +}; + +static int __init init(void) +{ + int ret; + ret = xt_register_match(AF_INET, &tcp_matchstruct); + if (ret) + return ret; + + ret = xt_register_match(AF_INET6, &tcp6_matchstruct); + if (ret) + goto out_unreg_tcp; + + ret = xt_register_match(AF_INET, &udp_matchstruct); + if (ret) + goto out_unreg_tcp6; + + ret = xt_register_match(AF_INET6, &udp6_matchstruct); + if (ret) + goto out_unreg_udp; + + return ret; + +out_unreg_udp: + xt_unregister_match(AF_INET, &tcp_matchstruct); +out_unreg_tcp6: + xt_unregister_match(AF_INET6, &tcp6_matchstruct); +out_unreg_tcp: + xt_unregister_match(AF_INET, &tcp_matchstruct); + return ret; +} + +static void __exit fini(void) +{ + xt_unregister_match(AF_INET6, &udp6_matchstruct); + xt_unregister_match(AF_INET, &udp_matchstruct); + xt_unregister_match(AF_INET6, &tcp6_matchstruct); + xt_unregister_match(AF_INET, &tcp_matchstruct); +} + +module_init(init); +module_exit(fini); diff --git a/net/netlink/genetlink.c b/net/netlink/genetlink.c index 3b1378498d5..4ae1538c54a 100644 --- a/net/netlink/genetlink.c +++ b/net/netlink/genetlink.c @@ -222,11 +222,6 @@ int genl_register_family(struct genl_family *family) goto errout_locked; } - if (!try_module_get(family->owner)) { - err = -EBUSY; - goto errout_locked; - } - if (family->id == GENL_ID_GENERATE) { u16 newid = genl_generate_id(); @@ -283,7 +278,6 @@ int genl_unregister_family(struct genl_family *family) INIT_LIST_HEAD(&family->ops_list); genl_unlock(); - module_put(family->owner); kfree(family->attrbuf); genl_ctrl_event(CTRL_CMD_DELFAMILY, family); return 0; @@ -535,7 +529,6 @@ static struct genl_family genl_ctrl = { .name = "nlctrl", .version = 0x1, .maxattr = CTRL_ATTR_MAX, - .owner = THIS_MODULE, }; static int __init genl_init(void) diff --git a/net/sched/Kconfig b/net/sched/Kconfig index 8a260d43cee..778b1e5a4b5 100644 --- a/net/sched/Kconfig +++ b/net/sched/Kconfig @@ -44,7 +44,7 @@ if NET_SCHED choice prompt "Packet scheduler clock source" - default NET_SCH_CLK_JIFFIES + default NET_SCH_CLK_GETTIMEOFDAY ---help--- Packet schedulers need a monotonic clock that increments at a static rate. The kernel provides several suitable interfaces, each with diff --git a/net/sched/act_ipt.c b/net/sched/act_ipt.c index b5001939b74..39a22a3ffe7 100644 --- a/net/sched/act_ipt.c +++ b/net/sched/act_ipt.c @@ -62,7 +62,7 @@ ipt_init_target(struct ipt_entry_target *t, char *table, unsigned int hook) struct ipt_target *target; int ret = 0; - target = ipt_find_target(t->u.user.name, t->u.user.revision); + target = xt_find_target(AF_INET, t->u.user.name, t->u.user.revision); if (!target) return -ENOENT; diff --git a/net/sctp/ipv6.c b/net/sctp/ipv6.c index 04c7fab4edc..2e266129a76 100644 --- a/net/sctp/ipv6.c +++ b/net/sctp/ipv6.c @@ -180,8 +180,7 @@ static int sctp_v6_xmit(struct sk_buff *skb, struct sctp_transport *transport, } SCTP_DEBUG_PRINTK("%s: skb:%p, len:%d, " - "src:%04x:%04x:%04x:%04x:%04x:%04x:%04x:%04x " - "dst:%04x:%04x:%04x:%04x:%04x:%04x:%04x:%04x\n", + "src:" NIP6_FMT " dst:" NIP6_FMT "\n", __FUNCTION__, skb, skb->len, NIP6(fl.fl6_src), NIP6(fl.fl6_dst)); @@ -206,13 +205,13 @@ static struct dst_entry *sctp_v6_get_dst(struct sctp_association *asoc, fl.oif = daddr->v6.sin6_scope_id; - SCTP_DEBUG_PRINTK("%s: DST=%04x:%04x:%04x:%04x:%04x:%04x:%04x:%04x ", + SCTP_DEBUG_PRINTK("%s: DST=" NIP6_FMT " ", __FUNCTION__, NIP6(fl.fl6_dst)); if (saddr) { ipv6_addr_copy(&fl.fl6_src, &saddr->v6.sin6_addr); SCTP_DEBUG_PRINTK( - "SRC=%04x:%04x:%04x:%04x:%04x:%04x:%04x:%04x - ", + "SRC=" NIP6_FMT " - ", NIP6(fl.fl6_src)); } @@ -221,8 +220,7 @@ static struct dst_entry *sctp_v6_get_dst(struct sctp_association *asoc, struct rt6_info *rt; rt = (struct rt6_info *)dst; SCTP_DEBUG_PRINTK( - "rt6_dst:%04x:%04x:%04x:%04x:%04x:%04x:%04x:%04x " - "rt6_src:%04x:%04x:%04x:%04x:%04x:%04x:%04x:%04x\n", + "rt6_dst:" NIP6_FMT " rt6_src:" NIP6_FMT "\n", NIP6(rt->rt6i_dst.addr), NIP6(rt->rt6i_src.addr)); } else { SCTP_DEBUG_PRINTK("NO ROUTE\n"); @@ -271,13 +269,12 @@ static void sctp_v6_get_saddr(struct sctp_association *asoc, __u8 bmatchlen; SCTP_DEBUG_PRINTK("%s: asoc:%p dst:%p " - "daddr:%04x:%04x:%04x:%04x:%04x:%04x:%04x:%04x ", + "daddr:" NIP6_FMT " ", __FUNCTION__, asoc, dst, NIP6(daddr->v6.sin6_addr)); if (!asoc) { ipv6_get_saddr(dst, &daddr->v6.sin6_addr,&saddr->v6.sin6_addr); - SCTP_DEBUG_PRINTK("saddr from ipv6_get_saddr: " - "%04x:%04x:%04x:%04x:%04x:%04x:%04x:%04x\n", + SCTP_DEBUG_PRINTK("saddr from ipv6_get_saddr: " NIP6_FMT "\n", NIP6(saddr->v6.sin6_addr)); return; } @@ -305,13 +302,11 @@ static void sctp_v6_get_saddr(struct sctp_association *asoc, if (baddr) { memcpy(saddr, baddr, sizeof(union sctp_addr)); - SCTP_DEBUG_PRINTK("saddr: " - "%04x:%04x:%04x:%04x:%04x:%04x:%04x:%04x\n", + SCTP_DEBUG_PRINTK("saddr: " NIP6_FMT "\n", NIP6(saddr->v6.sin6_addr)); } else { printk(KERN_ERR "%s: asoc:%p Could not find a valid source " - "address for the " - "dest:%04x:%04x:%04x:%04x:%04x:%04x:%04x:%04x\n", + "address for the dest:" NIP6_FMT "\n", __FUNCTION__, asoc, NIP6(daddr->v6.sin6_addr)); } @@ -675,8 +670,7 @@ static int sctp_v6_is_ce(const struct sk_buff *skb) /* Dump the v6 addr to the seq file. */ static void sctp_v6_seq_dump_addr(struct seq_file *seq, union sctp_addr *addr) { - seq_printf(seq, "%04x:%04x:%04x:%04x:%04x:%04x:%04x:%04x ", - NIP6(addr->v6.sin6_addr)); + seq_printf(seq, NIP6_FMT " ", NIP6(addr->v6.sin6_addr)); } /* Initialize a PF_INET6 socket msg_name. */ diff --git a/net/sctp/sm_statefuns.c b/net/sctp/sm_statefuns.c index 557a7d90b92..477d7f80dba 100644 --- a/net/sctp/sm_statefuns.c +++ b/net/sctp/sm_statefuns.c @@ -1036,14 +1036,14 @@ sctp_disposition_t sctp_sf_backbeat_8_3(const struct sctp_endpoint *ep, if (from_addr.sa.sa_family == AF_INET6) { printk(KERN_WARNING "%s association %p could not find address " - "%04x:%04x:%04x:%04x:%04x:%04x:%04x:%04x\n", + NIP6_FMT "\n", __FUNCTION__, asoc, NIP6(from_addr.v6.sin6_addr)); } else { printk(KERN_WARNING "%s association %p could not find address " - "%u.%u.%u.%u\n", + NIPQUAD_FMT "\n", __FUNCTION__, asoc, NIPQUAD(from_addr.v4.sin_addr.s_addr)); diff --git a/net/tipc/Kconfig b/net/tipc/Kconfig new file mode 100644 index 00000000000..05ab18e62de --- /dev/null +++ b/net/tipc/Kconfig @@ -0,0 +1,112 @@ +# +# TIPC configuration +# + +menu "TIPC Configuration (EXPERIMENTAL)" + depends on INET && EXPERIMENTAL + +config TIPC + tristate "The TIPC Protocol (EXPERIMENTAL)" + ---help--- + TBD. + + This protocol support is also available as a module ( = code which + can be inserted in and removed from the running kernel whenever you + want). The module will be called tipc. If you want to compile it + as a module, say M here and read <file:Documentation/modules.txt>. + + If in doubt, say N. + +config TIPC_ADVANCED + bool "TIPC: Advanced configuration" + depends on TIPC + default n + help + Saying Y here will open some advanced configuration + for TIPC. Most users do not need to bother, so if + unsure, just say N. + +config TIPC_ZONES + int "Maximum number of zones in network" + depends on TIPC && TIPC_ADVANCED + default "3" + help + Max number of zones inside TIPC network. Max supported value + is 255 zones, minimum is 1 + + Default is 3 zones in a network; setting this to higher + allows more zones but might use more memory. + +config TIPC_CLUSTERS + int "Maximum number of clusters in a zone" + depends on TIPC && TIPC_ADVANCED + default "1" + help + ***Only 1 (one cluster in a zone) is supported by current code. + Any value set here will be overridden.*** + + (Max number of clusters inside TIPC zone. Max supported + value is 4095 clusters, minimum is 1. + + Default is 1; setting this to smaller value might save + some memory, setting it to higher + allows more clusters and might consume more memory.) + +config TIPC_NODES + int "Maximum number of nodes in cluster" + depends on TIPC && TIPC_ADVANCED + default "255" + help + Maximum number of nodes inside a TIPC cluster. Maximum + supported value is 2047 nodes, minimum is 8. + + Setting this to a smaller value saves some memory, + setting it to higher allows more nodes. + +config TIPC_SLAVE_NODES + int "Maximum number of slave nodes in cluster" + depends on TIPC && TIPC_ADVANCED + default "0" + help + ***This capability is not supported by current code.*** + + Maximum number of slave nodes inside a TIPC cluster. Maximum + supported value is 2047 nodes, minimum is 0. + + Setting this to a smaller value saves some memory, + setting it to higher allows more nodes. + +config TIPC_PORTS + int "Maximum number of ports in a node" + depends on TIPC && TIPC_ADVANCED + default "8191" + help + Maximum number of ports within a node. Maximum + supported value is 64535 nodes, minimum is 127. + + Setting this to a smaller value saves some memory, + setting it to higher allows more ports. + +config TIPC_LOG + int "Size of log buffer" + depends on TIPC && TIPC_ADVANCED + default 0 + help + Size (in bytes) of TIPC's internal log buffer, which records the + occurrence of significant events. Maximum supported value + is 32768 bytes, minimum is 0. + + There is no need to enable the log buffer unless the node will be + managed remotely via TIPC. + +config TIPC_DEBUG + bool "Enable debugging support" + depends on TIPC + default n + help + This will enable debugging of TIPC. + + Only say Y here if you are having trouble with TIPC. It will + enable the display of detailed information about what is going on. + +endmenu diff --git a/net/tipc/Makefile b/net/tipc/Makefile new file mode 100644 index 00000000000..dceb7027946 --- /dev/null +++ b/net/tipc/Makefile @@ -0,0 +1,13 @@ +# +# Makefile for the Linux TIPC layer +# + +obj-$(CONFIG_TIPC) := tipc.o + +tipc-y += addr.o bcast.o bearer.o config.o cluster.o \ + core.o handler.o link.o discover.o msg.o \ + name_distr.o subscr.o name_table.o net.o \ + netlink.o node.o node_subscr.o port.o ref.o \ + socket.o user_reg.o zone.o dbg.o eth_media.o + +# End of file diff --git a/net/tipc/addr.c b/net/tipc/addr.c new file mode 100644 index 00000000000..eca22260c98 --- /dev/null +++ b/net/tipc/addr.c @@ -0,0 +1,94 @@ +/* + * net/tipc/addr.c: TIPC address utility routines + * + * Copyright (c) 2000-2006, Ericsson AB + * Copyright (c) 2004-2005, Wind River Systems + * All rights reserved. + * + * Redistribution and use in source and binary forms, with or without + * modification, are permitted provided that the following conditions are met: + * + * 1. Redistributions of source code must retain the above copyright + * notice, this list of conditions and the following disclaimer. + * 2. Redistributions in binary form must reproduce the above copyright + * notice, this list of conditions and the following disclaimer in the + * documentation and/or other materials provided with the distribution. + * 3. Neither the names of the copyright holders nor the names of its + * contributors may be used to endorse or promote products derived from + * this software without specific prior written permission. + * + * Alternatively, this software may be distributed under the terms of the + * GNU General Public License ("GPL") version 2 as published by the Free + * Software Foundation. + * + * THIS SOFTWARE IS PROVIDED BY THE COPYRIGHT HOLDERS AND CONTRIBUTORS "AS IS" + * AND ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT LIMITED TO, THE + * IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR A PARTICULAR PURPOSE + * ARE DISCLAIMED. IN NO EVENT SHALL THE COPYRIGHT OWNER OR CONTRIBUTORS BE + * LIABLE FOR ANY DIRECT, INDIRECT, INCIDENTAL, SPECIAL, EXEMPLARY, OR + * CONSEQUENTIAL DAMAGES (INCLUDING, BUT NOT LIMITED TO, PROCUREMENT OF + * SUBSTITUTE GOODS OR SERVICES; LOSS OF USE, DATA, OR PROFITS; OR BUSINESS + * INTERRUPTION) HOWEVER CAUSED AND ON ANY THEORY OF LIABILITY, WHETHER IN + * CONTRACT, STRICT LIABILITY, OR TORT (INCLUDING NEGLIGENCE OR OTHERWISE) + * ARISING IN ANY WAY OUT OF THE USE OF THIS SOFTWARE, EVEN IF ADVISED OF THE + * POSSIBILITY OF SUCH DAMAGE. + */ + +#include "core.h" +#include "dbg.h" +#include "addr.h" +#include "zone.h" +#include "cluster.h" +#include "net.h" + +u32 tipc_get_addr(void) +{ + return tipc_own_addr; +} + +/** + * addr_domain_valid - validates a network domain address + * + * Accepts <Z.C.N>, <Z.C.0>, <Z.0.0>, and <0.0.0>, + * where Z, C, and N are non-zero and do not exceed the configured limits. + * + * Returns 1 if domain address is valid, otherwise 0 + */ + +int addr_domain_valid(u32 addr) +{ + u32 n = tipc_node(addr); + u32 c = tipc_cluster(addr); + u32 z = tipc_zone(addr); + u32 max_nodes = tipc_max_nodes; + + if (is_slave(addr)) + max_nodes = LOWEST_SLAVE + tipc_max_slaves; + if (n > max_nodes) + return 0; + if (c > tipc_max_clusters) + return 0; + if (z > tipc_max_zones) + return 0; + + if (n && (!z || !c)) + return 0; + if (c && !z) + return 0; + return 1; +} + +/** + * addr_node_valid - validates a proposed network address for this node + * + * Accepts <Z.C.N>, where Z, C, and N are non-zero and do not exceed + * the configured limits. + * + * Returns 1 if address can be used, otherwise 0 + */ + +int addr_node_valid(u32 addr) +{ + return (addr_domain_valid(addr) && tipc_node(addr)); +} + diff --git a/net/tipc/addr.h b/net/tipc/addr.h new file mode 100644 index 00000000000..02ca71783e2 --- /dev/null +++ b/net/tipc/addr.h @@ -0,0 +1,128 @@ +/* + * net/tipc/addr.h: Include file for TIPC address utility routines + * + * Copyright (c) 2000-2006, Ericsson AB + * Copyright (c) 2004-2005, Wind River Systems + * All rights reserved. + * + * Redistribution and use in source and binary forms, with or without + * modification, are permitted provided that the following conditions are met: + * + * 1. Redistributions of source code must retain the above copyright + * notice, this list of conditions and the following disclaimer. + * 2. Redistributions in binary form must reproduce the above copyright + * notice, this list of conditions and the following disclaimer in the + * documentation and/or other materials provided with the distribution. + * 3. Neither the names of the copyright holders nor the names of its + * contributors may be used to endorse or promote products derived from + * this software without specific prior written permission. + * + * Alternatively, this software may be distributed under the terms of the + * GNU General Public License ("GPL") version 2 as published by the Free + * Software Foundation. + * + * THIS SOFTWARE IS PROVIDED BY THE COPYRIGHT HOLDERS AND CONTRIBUTORS "AS IS" + * AND ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT LIMITED TO, THE + * IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR A PARTICULAR PURPOSE + * ARE DISCLAIMED. IN NO EVENT SHALL THE COPYRIGHT OWNER OR CONTRIBUTORS BE + * LIABLE FOR ANY DIRECT, INDIRECT, INCIDENTAL, SPECIAL, EXEMPLARY, OR + * CONSEQUENTIAL DAMAGES (INCLUDING, BUT NOT LIMITED TO, PROCUREMENT OF + * SUBSTITUTE GOODS OR SERVICES; LOSS OF USE, DATA, OR PROFITS; OR BUSINESS + * INTERRUPTION) HOWEVER CAUSED AND ON ANY THEORY OF LIABILITY, WHETHER IN + * CONTRACT, STRICT LIABILITY, OR TORT (INCLUDING NEGLIGENCE OR OTHERWISE) + * ARISING IN ANY WAY OUT OF THE USE OF THIS SOFTWARE, EVEN IF ADVISED OF THE + * POSSIBILITY OF SUCH DAMAGE. + */ + +#ifndef _TIPC_ADDR_H +#define _TIPC_ADDR_H + +static inline u32 own_node(void) +{ + return tipc_node(tipc_own_addr); +} + +static inline u32 own_cluster(void) +{ + return tipc_cluster(tipc_own_addr); +} + +static inline u32 own_zone(void) +{ + return tipc_zone(tipc_own_addr); +} + +static inline int in_own_cluster(u32 addr) +{ + return !((addr ^ tipc_own_addr) >> 12); +} + +static inline int in_own_zone(u32 addr) +{ + return !((addr ^ tipc_own_addr) >> 24); +} + +static inline int is_slave(u32 addr) +{ + return addr & 0x800; +} + +static inline int may_route(u32 addr) +{ + return(addr ^ tipc_own_addr) >> 11; +} + +static inline int in_scope(u32 domain, u32 addr) +{ + if (!domain || (domain == addr)) + return 1; + if (domain == (addr & 0xfffff000u)) /* domain <Z.C.0> */ + return 1; + if (domain == (addr & 0xff000000u)) /* domain <Z.0.0> */ + return 1; + return 0; +} + +/** + * addr_scope - convert message lookup domain to equivalent 2-bit scope value + */ + +static inline int addr_scope(u32 domain) +{ + if (likely(!domain)) + return TIPC_ZONE_SCOPE; + if (tipc_node(domain)) + return TIPC_NODE_SCOPE; + if (tipc_cluster(domain)) + return TIPC_CLUSTER_SCOPE; + return TIPC_ZONE_SCOPE; +} + +/** + * addr_domain - convert 2-bit scope value to equivalent message lookup domain + * + * Needed when address of a named message must be looked up a second time + * after a network hop. + */ + +static inline int addr_domain(int sc) +{ + if (likely(sc == TIPC_NODE_SCOPE)) + return tipc_own_addr; + if (sc == TIPC_CLUSTER_SCOPE) + return tipc_addr(tipc_zone(tipc_own_addr), + tipc_cluster(tipc_own_addr), 0); + return tipc_addr(tipc_zone(tipc_own_addr), 0, 0); +} + +static inline char *addr_string_fill(char *string, u32 addr) +{ + snprintf(string, 16, "<%u.%u.%u>", + tipc_zone(addr), tipc_cluster(addr), tipc_node(addr)); + return string; +} + +int addr_domain_valid(u32); +int addr_node_valid(u32 addr); + +#endif diff --git a/net/tipc/bcast.c b/net/tipc/bcast.c new file mode 100644 index 00000000000..9713d622efb --- /dev/null +++ b/net/tipc/bcast.c @@ -0,0 +1,806 @@ +/* + * net/tipc/bcast.c: TIPC broadcast code + * + * Copyright (c) 2004-2006, Ericsson AB + * Copyright (c) 2004, Intel Corporation. + * Copyright (c) 2005, Wind River Systems + * All rights reserved. + * + * Redistribution and use in source and binary forms, with or without + * modification, are permitted provided that the following conditions are met: + * + * 1. Redistributions of source code must retain the above copyright + * notice, this list of conditions and the following disclaimer. + * 2. Redistributions in binary form must reproduce the above copyright + * notice, this list of conditions and the following disclaimer in the + * documentation and/or other materials provided with the distribution. + * 3. Neither the names of the copyright holders nor the names of its + * contributors may be used to endorse or promote products derived from + * this software without specific prior written permission. + * + * Alternatively, this software may be distributed under the terms of the + * GNU General Public License ("GPL") version 2 as published by the Free + * Software Foundation. + * + * THIS SOFTWARE IS PROVIDED BY THE COPYRIGHT HOLDERS AND CONTRIBUTORS "AS IS" + * AND ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT LIMITED TO, THE + * IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR A PARTICULAR PURPOSE + * ARE DISCLAIMED. IN NO EVENT SHALL THE COPYRIGHT OWNER OR CONTRIBUTORS BE + * LIABLE FOR ANY DIRECT, INDIRECT, INCIDENTAL, SPECIAL, EXEMPLARY, OR + * CONSEQUENTIAL DAMAGES (INCLUDING, BUT NOT LIMITED TO, PROCUREMENT OF + * SUBSTITUTE GOODS OR SERVICES; LOSS OF USE, DATA, OR PROFITS; OR BUSINESS + * INTERRUPTION) HOWEVER CAUSED AND ON ANY THEORY OF LIABILITY, WHETHER IN + * CONTRACT, STRICT LIABILITY, OR TORT (INCLUDING NEGLIGENCE OR OTHERWISE) + * ARISING IN ANY WAY OUT OF THE USE OF THIS SOFTWARE, EVEN IF ADVISED OF THE + * POSSIBILITY OF SUCH DAMAGE. + */ + +#include "core.h" +#include "msg.h" +#include "dbg.h" +#include "link.h" +#include "net.h" +#include "node.h" +#include "port.h" +#include "addr.h" +#include "node_subscr.h" +#include "name_distr.h" +#include "bearer.h" +#include "name_table.h" +#include "bcast.h" + + +#define MAX_PKT_DEFAULT_MCAST 1500 /* bcast link max packet size (fixed) */ + +#define BCLINK_WIN_DEFAULT 20 /* bcast link window size (default) */ + +#define BCLINK_LOG_BUF_SIZE 0 + +/** + * struct bcbearer_pair - a pair of bearers used by broadcast link + * @primary: pointer to primary bearer + * @secondary: pointer to secondary bearer + * + * Bearers must have same priority and same set of reachable destinations + * to be paired. + */ + +struct bcbearer_pair { + struct bearer *primary; + struct bearer *secondary; +}; + +/** + * struct bcbearer - bearer used by broadcast link + * @bearer: (non-standard) broadcast bearer structure + * @media: (non-standard) broadcast media structure + * @bpairs: array of bearer pairs + * @bpairs_temp: array of bearer pairs used during creation of "bpairs" + */ + +struct bcbearer { + struct bearer bearer; + struct media media; + struct bcbearer_pair bpairs[MAX_BEARERS]; + struct bcbearer_pair bpairs_temp[TIPC_NUM_LINK_PRI]; +}; + +/** + * struct bclink - link used for broadcast messages + * @link: (non-standard) broadcast link structure + * @node: (non-standard) node structure representing b'cast link's peer node + * + * Handles sequence numbering, fragmentation, bundling, etc. + */ + +struct bclink { + struct link link; + struct node node; +}; + + +static struct bcbearer *bcbearer = NULL; +static struct bclink *bclink = NULL; +static struct link *bcl = NULL; +static spinlock_t bc_lock = SPIN_LOCK_UNLOCKED; + +char bc_link_name[] = "multicast-link"; + + +static inline u32 buf_seqno(struct sk_buff *buf) +{ + return msg_seqno(buf_msg(buf)); +} + +static inline u32 bcbuf_acks(struct sk_buff *buf) +{ + return (u32)(unsigned long)TIPC_SKB_CB(buf)->handle; +} + +static inline void bcbuf_set_acks(struct sk_buff *buf, u32 acks) +{ + TIPC_SKB_CB(buf)->handle = (void *)(unsigned long)acks; +} + +static inline void bcbuf_decr_acks(struct sk_buff *buf) +{ + bcbuf_set_acks(buf, bcbuf_acks(buf) - 1); +} + + +/** + * bclink_set_gap - set gap according to contents of current deferred pkt queue + * + * Called with 'node' locked, bc_lock unlocked + */ + +static inline void bclink_set_gap(struct node *n_ptr) +{ + struct sk_buff *buf = n_ptr->bclink.deferred_head; + + n_ptr->bclink.gap_after = n_ptr->bclink.gap_to = + mod(n_ptr->bclink.last_in); + if (unlikely(buf != NULL)) + n_ptr->bclink.gap_to = mod(buf_seqno(buf) - 1); +} + +/** + * bclink_ack_allowed - test if ACK or NACK message can be sent at this moment + * + * This mechanism endeavours to prevent all nodes in network from trying + * to ACK or NACK at the same time. + * + * Note: TIPC uses a different trigger to distribute ACKs than it does to + * distribute NACKs, but tries to use the same spacing (divide by 16). + */ + +static inline int bclink_ack_allowed(u32 n) +{ + return((n % TIPC_MIN_LINK_WIN) == tipc_own_tag); +} + + +/** + * bclink_retransmit_pkt - retransmit broadcast packets + * @after: sequence number of last packet to *not* retransmit + * @to: sequence number of last packet to retransmit + * + * Called with 'node' locked, bc_lock unlocked + */ + +static void bclink_retransmit_pkt(u32 after, u32 to) +{ + struct sk_buff *buf; + + spin_lock_bh(&bc_lock); + buf = bcl->first_out; + while (buf && less_eq(buf_seqno(buf), after)) { + buf = buf->next; + } + if (buf != NULL) + link_retransmit(bcl, buf, mod(to - after)); + spin_unlock_bh(&bc_lock); +} + +/** + * bclink_acknowledge - handle acknowledgement of broadcast packets + * @n_ptr: node that sent acknowledgement info + * @acked: broadcast sequence # that has been acknowledged + * + * Node is locked, bc_lock unlocked. + */ + +void bclink_acknowledge(struct node *n_ptr, u32 acked) +{ + struct sk_buff *crs; + struct sk_buff *next; + unsigned int released = 0; + + if (less_eq(acked, n_ptr->bclink.acked)) + return; + + spin_lock_bh(&bc_lock); + + /* Skip over packets that node has previously acknowledged */ + + crs = bcl->first_out; + while (crs && less_eq(buf_seqno(crs), n_ptr->bclink.acked)) { + crs = crs->next; + } + + /* Update packets that node is now acknowledging */ + + while (crs && less_eq(buf_seqno(crs), acked)) { + next = crs->next; + bcbuf_decr_acks(crs); + if (bcbuf_acks(crs) == 0) { + bcl->first_out = next; + bcl->out_queue_size--; + buf_discard(crs); + released = 1; + } + crs = next; + } + n_ptr->bclink.acked = acked; + + /* Try resolving broadcast link congestion, if necessary */ + + if (unlikely(bcl->next_out)) + link_push_queue(bcl); + if (unlikely(released && !list_empty(&bcl->waiting_ports))) + link_wakeup_ports(bcl, 0); + spin_unlock_bh(&bc_lock); +} + +/** + * bclink_send_ack - unicast an ACK msg + * + * net_lock and node lock set + */ + +static void bclink_send_ack(struct node *n_ptr) +{ + struct link *l_ptr = n_ptr->active_links[n_ptr->addr & 1]; + + if (l_ptr != NULL) + link_send_proto_msg(l_ptr, STATE_MSG, 0, 0, 0, 0, 0); +} + +/** + * bclink_send_nack- broadcast a NACK msg + * + * net_lock and node lock set + */ + +static void bclink_send_nack(struct node *n_ptr) +{ + struct sk_buff *buf; + struct tipc_msg *msg; + + if (!less(n_ptr->bclink.gap_after, n_ptr->bclink.gap_to)) + return; + + buf = buf_acquire(INT_H_SIZE); + if (buf) { + msg = buf_msg(buf); + msg_init(msg, BCAST_PROTOCOL, STATE_MSG, + TIPC_OK, INT_H_SIZE, n_ptr->addr); + msg_set_mc_netid(msg, tipc_net_id); + msg_set_bcast_ack(msg, mod(n_ptr->bclink.last_in)); + msg_set_bcgap_after(msg, n_ptr->bclink.gap_after); + msg_set_bcgap_to(msg, n_ptr->bclink.gap_to); + msg_set_bcast_tag(msg, tipc_own_tag); + + if (bearer_send(&bcbearer->bearer, buf, 0)) { + bcl->stats.sent_nacks++; + buf_discard(buf); + } else { + bearer_schedule(bcl->b_ptr, bcl); + bcl->proto_msg_queue = buf; + bcl->stats.bearer_congs++; + } + + /* + * Ensure we doesn't send another NACK msg to the node + * until 16 more deferred messages arrive from it + * (i.e. helps prevent all nodes from NACK'ing at same time) + */ + + n_ptr->bclink.nack_sync = tipc_own_tag; + } +} + +/** + * bclink_check_gap - send a NACK if a sequence gap exists + * + * net_lock and node lock set + */ + +void bclink_check_gap(struct node *n_ptr, u32 last_sent) +{ + if (!n_ptr->bclink.supported || + less_eq(last_sent, mod(n_ptr->bclink.last_in))) + return; + + bclink_set_gap(n_ptr); + if (n_ptr->bclink.gap_after == n_ptr->bclink.gap_to) + n_ptr->bclink.gap_to = last_sent; + bclink_send_nack(n_ptr); +} + +/** + * bclink_peek_nack - process a NACK msg meant for another node + * + * Only net_lock set. + */ + +void bclink_peek_nack(u32 dest, u32 sender_tag, u32 gap_after, u32 gap_to) +{ + struct node *n_ptr = node_find(dest); + u32 my_after, my_to; + + if (unlikely(!n_ptr || !node_is_up(n_ptr))) + return; + node_lock(n_ptr); + /* + * Modify gap to suppress unnecessary NACKs from this node + */ + my_after = n_ptr->bclink.gap_after; + my_to = n_ptr->bclink.gap_to; + + if (less_eq(gap_after, my_after)) { + if (less(my_after, gap_to) && less(gap_to, my_to)) + n_ptr->bclink.gap_after = gap_to; + else if (less_eq(my_to, gap_to)) + n_ptr->bclink.gap_to = n_ptr->bclink.gap_after; + } else if (less_eq(gap_after, my_to)) { + if (less_eq(my_to, gap_to)) + n_ptr->bclink.gap_to = gap_after; + } else { + /* + * Expand gap if missing bufs not in deferred queue: + */ + struct sk_buff *buf = n_ptr->bclink.deferred_head; + u32 prev = n_ptr->bclink.gap_to; + + for (; buf; buf = buf->next) { + u32 seqno = buf_seqno(buf); + + if (mod(seqno - prev) != 1) + buf = NULL; + if (seqno == gap_after) + break; + prev = seqno; + } + if (buf == NULL) + n_ptr->bclink.gap_to = gap_after; + } + /* + * Some nodes may send a complementary NACK now: + */ + if (bclink_ack_allowed(sender_tag + 1)) { + if (n_ptr->bclink.gap_to != n_ptr->bclink.gap_after) { + bclink_send_nack(n_ptr); + bclink_set_gap(n_ptr); + } + } + node_unlock(n_ptr); +} + +/** + * bclink_send_msg - broadcast a packet to all nodes in cluster + */ + +int bclink_send_msg(struct sk_buff *buf) +{ + int res; + + spin_lock_bh(&bc_lock); + + res = link_send_buf(bcl, buf); + if (unlikely(res == -ELINKCONG)) + buf_discard(buf); + else + bcl->stats.sent_info++; + + if (bcl->out_queue_size > bcl->stats.max_queue_sz) + bcl->stats.max_queue_sz = bcl->out_queue_size; + bcl->stats.queue_sz_counts++; + bcl->stats.accu_queue_sz += bcl->out_queue_size; + + spin_unlock_bh(&bc_lock); + return res; +} + +/** + * bclink_recv_pkt - receive a broadcast packet, and deliver upwards + * + * net_lock is read_locked, no other locks set + */ + +void bclink_recv_pkt(struct sk_buff *buf) +{ + struct tipc_msg *msg = buf_msg(buf); + struct node* node = node_find(msg_prevnode(msg)); + u32 next_in; + u32 seqno; + struct sk_buff *deferred; + + msg_dbg(msg, "<BC<<<"); + + if (unlikely(!node || !node_is_up(node) || !node->bclink.supported || + (msg_mc_netid(msg) != tipc_net_id))) { + buf_discard(buf); + return; + } + + if (unlikely(msg_user(msg) == BCAST_PROTOCOL)) { + msg_dbg(msg, "<BCNACK<<<"); + if (msg_destnode(msg) == tipc_own_addr) { + node_lock(node); + bclink_acknowledge(node, msg_bcast_ack(msg)); + node_unlock(node); + bcl->stats.recv_nacks++; + bclink_retransmit_pkt(msg_bcgap_after(msg), + msg_bcgap_to(msg)); + } else { + bclink_peek_nack(msg_destnode(msg), + msg_bcast_tag(msg), + msg_bcgap_after(msg), + msg_bcgap_to(msg)); + } + buf_discard(buf); + return; + } + + node_lock(node); +receive: + deferred = node->bclink.deferred_head; + next_in = mod(node->bclink.last_in + 1); + seqno = msg_seqno(msg); + + if (likely(seqno == next_in)) { + bcl->stats.recv_info++; + node->bclink.last_in++; + bclink_set_gap(node); + if (unlikely(bclink_ack_allowed(seqno))) { + bclink_send_ack(node); + bcl->stats.sent_acks++; + } + if (likely(msg_isdata(msg))) { + node_unlock(node); + port_recv_mcast(buf, NULL); + } else if (msg_user(msg) == MSG_BUNDLER) { + bcl->stats.recv_bundles++; + bcl->stats.recv_bundled += msg_msgcnt(msg); + node_unlock(node); + link_recv_bundle(buf); + } else if (msg_user(msg) == MSG_FRAGMENTER) { + bcl->stats.recv_fragments++; + if (link_recv_fragment(&node->bclink.defragm, + &buf, &msg)) + bcl->stats.recv_fragmented++; + node_unlock(node); + net_route_msg(buf); + } else { + node_unlock(node); + net_route_msg(buf); + } + if (deferred && (buf_seqno(deferred) == mod(next_in + 1))) { + node_lock(node); + buf = deferred; + msg = buf_msg(buf); + node->bclink.deferred_head = deferred->next; + goto receive; + } + return; + } else if (less(next_in, seqno)) { + u32 gap_after = node->bclink.gap_after; + u32 gap_to = node->bclink.gap_to; + + if (link_defer_pkt(&node->bclink.deferred_head, + &node->bclink.deferred_tail, + buf)) { + node->bclink.nack_sync++; + bcl->stats.deferred_recv++; + if (seqno == mod(gap_after + 1)) + node->bclink.gap_after = seqno; + else if (less(gap_after, seqno) && less(seqno, gap_to)) + node->bclink.gap_to = seqno; + } + if (bclink_ack_allowed(node->bclink.nack_sync)) { + if (gap_to != gap_after) + bclink_send_nack(node); + bclink_set_gap(node); + } + } else { + bcl->stats.duplicates++; + buf_discard(buf); + } + node_unlock(node); +} + +u32 bclink_get_last_sent(void) +{ + u32 last_sent = mod(bcl->next_out_no - 1); + + if (bcl->next_out) + last_sent = mod(buf_seqno(bcl->next_out) - 1); + return last_sent; +} + +u32 bclink_acks_missing(struct node *n_ptr) +{ + return (n_ptr->bclink.supported && + (bclink_get_last_sent() != n_ptr->bclink.acked)); +} + + +/** + * bcbearer_send - send a packet through the broadcast pseudo-bearer + * + * Send through as many bearers as necessary to reach all nodes + * that support TIPC multicasting. + * + * Returns 0 if packet sent successfully, non-zero if not + */ + +int bcbearer_send(struct sk_buff *buf, + struct tipc_bearer *unused1, + struct tipc_media_addr *unused2) +{ + static int send_count = 0; + + struct node_map remains; + struct node_map remains_new; + int bp_index; + int swap_time; + + /* Prepare buffer for broadcasting (if first time trying to send it) */ + + if (likely(!msg_non_seq(buf_msg(buf)))) { + struct tipc_msg *msg; + + assert(cluster_bcast_nodes.count != 0); + bcbuf_set_acks(buf, cluster_bcast_nodes.count); + msg = buf_msg(buf); + msg_set_non_seq(msg); + msg_set_mc_netid(msg, tipc_net_id); + } + + /* Determine if bearer pairs should be swapped following this attempt */ + + if ((swap_time = (++send_count >= 10))) + send_count = 0; + + /* Send buffer over bearers until all targets reached */ + + remains = cluster_bcast_nodes; + + for (bp_index = 0; bp_index < MAX_BEARERS; bp_index++) { + struct bearer *p = bcbearer->bpairs[bp_index].primary; + struct bearer *s = bcbearer->bpairs[bp_index].secondary; + + if (!p) + break; /* no more bearers to try */ + + nmap_diff(&remains, &p->nodes, &remains_new); + if (remains_new.count == remains.count) + continue; /* bearer pair doesn't add anything */ + + if (!p->publ.blocked && + !p->media->send_msg(buf, &p->publ, &p->media->bcast_addr)) { + if (swap_time && s && !s->publ.blocked) + goto swap; + else + goto update; + } + + if (!s || s->publ.blocked || + s->media->send_msg(buf, &s->publ, &s->media->bcast_addr)) + continue; /* unable to send using bearer pair */ +swap: + bcbearer->bpairs[bp_index].primary = s; + bcbearer->bpairs[bp_index].secondary = p; +update: + if (remains_new.count == 0) + return TIPC_OK; + + remains = remains_new; + } + + /* Unable to reach all targets */ + + bcbearer->bearer.publ.blocked = 1; + bcl->stats.bearer_congs++; + return ~TIPC_OK; +} + +/** + * bcbearer_sort - create sets of bearer pairs used by broadcast bearer + */ + +void bcbearer_sort(void) +{ + struct bcbearer_pair *bp_temp = bcbearer->bpairs_temp; + struct bcbearer_pair *bp_curr; + int b_index; + int pri; + + spin_lock_bh(&bc_lock); + + /* Group bearers by priority (can assume max of two per priority) */ + + memset(bp_temp, 0, sizeof(bcbearer->bpairs_temp)); + + for (b_index = 0; b_index < MAX_BEARERS; b_index++) { + struct bearer *b = &bearers[b_index]; + + if (!b->active || !b->nodes.count) + continue; + + if (!bp_temp[b->priority].primary) + bp_temp[b->priority].primary = b; + else + bp_temp[b->priority].secondary = b; + } + + /* Create array of bearer pairs for broadcasting */ + + bp_curr = bcbearer->bpairs; + memset(bcbearer->bpairs, 0, sizeof(bcbearer->bpairs)); + + for (pri = (TIPC_NUM_LINK_PRI - 1); pri >= 0; pri--) { + + if (!bp_temp[pri].primary) + continue; + + bp_curr->primary = bp_temp[pri].primary; + + if (bp_temp[pri].secondary) { + if (nmap_equal(&bp_temp[pri].primary->nodes, + &bp_temp[pri].secondary->nodes)) { + bp_curr->secondary = bp_temp[pri].secondary; + } else { + bp_curr++; + bp_curr->primary = bp_temp[pri].secondary; + } + } + + bp_curr++; + } + + spin_unlock_bh(&bc_lock); +} + +/** + * bcbearer_push - resolve bearer congestion + * + * Forces bclink to push out any unsent packets, until all packets are gone + * or congestion reoccurs. + * No locks set when function called + */ + +void bcbearer_push(void) +{ + struct bearer *b_ptr; + + spin_lock_bh(&bc_lock); + b_ptr = &bcbearer->bearer; + if (b_ptr->publ.blocked) { + b_ptr->publ.blocked = 0; + bearer_lock_push(b_ptr); + } + spin_unlock_bh(&bc_lock); +} + + +int bclink_stats(char *buf, const u32 buf_size) +{ + struct print_buf pb; + + if (!bcl) + return 0; + + printbuf_init(&pb, buf, buf_size); + + spin_lock_bh(&bc_lock); + + tipc_printf(&pb, "Link <%s>\n" + " Window:%u packets\n", + bcl->name, bcl->queue_limit[0]); + tipc_printf(&pb, " RX packets:%u fragments:%u/%u bundles:%u/%u\n", + bcl->stats.recv_info, + bcl->stats.recv_fragments, + bcl->stats.recv_fragmented, + bcl->stats.recv_bundles, + bcl->stats.recv_bundled); + tipc_printf(&pb, " TX packets:%u fragments:%u/%u bundles:%u/%u\n", + bcl->stats.sent_info, + bcl->stats.sent_fragments, + bcl->stats.sent_fragmented, + bcl->stats.sent_bundles, + bcl->stats.sent_bundled); + tipc_printf(&pb, " RX naks:%u defs:%u dups:%u\n", + bcl->stats.recv_nacks, + bcl->stats.deferred_recv, + bcl->stats.duplicates); + tipc_printf(&pb, " TX naks:%u acks:%u dups:%u\n", + bcl->stats.sent_nacks, + bcl->stats.sent_acks, + bcl->stats.retransmitted); + tipc_printf(&pb, " Congestion bearer:%u link:%u Send queue max:%u avg:%u\n", + bcl->stats.bearer_congs, + bcl->stats.link_congs, + bcl->stats.max_queue_sz, + bcl->stats.queue_sz_counts + ? (bcl->stats.accu_queue_sz / bcl->stats.queue_sz_counts) + : 0); + + spin_unlock_bh(&bc_lock); + return printbuf_validate(&pb); +} + +int bclink_reset_stats(void) +{ + if (!bcl) + return -ENOPROTOOPT; + + spin_lock_bh(&bc_lock); + memset(&bcl->stats, 0, sizeof(bcl->stats)); + spin_unlock_bh(&bc_lock); + return TIPC_OK; +} + +int bclink_set_queue_limits(u32 limit) +{ + if (!bcl) + return -ENOPROTOOPT; + if ((limit < TIPC_MIN_LINK_WIN) || (limit > TIPC_MAX_LINK_WIN)) + return -EINVAL; + + spin_lock_bh(&bc_lock); + link_set_queue_limits(bcl, limit); + spin_unlock_bh(&bc_lock); + return TIPC_OK; +} + +int bclink_init(void) +{ + bcbearer = kmalloc(sizeof(*bcbearer), GFP_ATOMIC); + bclink = kmalloc(sizeof(*bclink), GFP_ATOMIC); + if (!bcbearer || !bclink) { + nomem: + warn("Memory squeeze; Failed to create multicast link\n"); + kfree(bcbearer); + bcbearer = NULL; + kfree(bclink); + bclink = NULL; + return -ENOMEM; + } + + memset(bcbearer, 0, sizeof(struct bcbearer)); + INIT_LIST_HEAD(&bcbearer->bearer.cong_links); + bcbearer->bearer.media = &bcbearer->media; + bcbearer->media.send_msg = bcbearer_send; + sprintf(bcbearer->media.name, "tipc-multicast"); + + bcl = &bclink->link; + memset(bclink, 0, sizeof(struct bclink)); + INIT_LIST_HEAD(&bcl->waiting_ports); + bcl->next_out_no = 1; + bclink->node.lock = SPIN_LOCK_UNLOCKED; + bcl->owner = &bclink->node; + bcl->max_pkt = MAX_PKT_DEFAULT_MCAST; + link_set_queue_limits(bcl, BCLINK_WIN_DEFAULT); + bcl->b_ptr = &bcbearer->bearer; + bcl->state = WORKING_WORKING; + sprintf(bcl->name, bc_link_name); + + if (BCLINK_LOG_BUF_SIZE) { + char *pb = kmalloc(BCLINK_LOG_BUF_SIZE, GFP_ATOMIC); + + if (!pb) + goto nomem; + printbuf_init(&bcl->print_buf, pb, BCLINK_LOG_BUF_SIZE); + } + + return TIPC_OK; +} + +void bclink_stop(void) +{ + spin_lock_bh(&bc_lock); + if (bcbearer) { + link_stop(bcl); + if (BCLINK_LOG_BUF_SIZE) + kfree(bcl->print_buf.buf); + bcl = NULL; + kfree(bclink); + bclink = NULL; + kfree(bcbearer); + bcbearer = NULL; + } + spin_unlock_bh(&bc_lock); +} + diff --git a/net/tipc/bcast.h b/net/tipc/bcast.h new file mode 100644 index 00000000000..5430e524b4f --- /dev/null +++ b/net/tipc/bcast.h @@ -0,0 +1,223 @@ +/* + * net/tipc/bcast.h: Include file for TIPC broadcast code + * + * Copyright (c) 2003-2006, Ericsson AB + * Copyright (c) 2005, Wind River Systems + * All rights reserved. + * + * Redistribution and use in source and binary forms, with or without + * modification, are permitted provided that the following conditions are met: + * + * 1. Redistributions of source code must retain the above copyright + * notice, this list of conditions and the following disclaimer. + * 2. Redistributions in binary form must reproduce the above copyright + * notice, this list of conditions and the following disclaimer in the + * documentation and/or other materials provided with the distribution. + * 3. Neither the names of the copyright holders nor the names of its + * contributors may be used to endorse or promote products derived from + * this software without specific prior written permission. + * + * Alternatively, this software may be distributed under the terms of the + * GNU General Public License ("GPL") version 2 as published by the Free + * Software Foundation. + * + * THIS SOFTWARE IS PROVIDED BY THE COPYRIGHT HOLDERS AND CONTRIBUTORS "AS IS" + * AND ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT LIMITED TO, THE + * IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR A PARTICULAR PURPOSE + * ARE DISCLAIMED. IN NO EVENT SHALL THE COPYRIGHT OWNER OR CONTRIBUTORS BE + * LIABLE FOR ANY DIRECT, INDIRECT, INCIDENTAL, SPECIAL, EXEMPLARY, OR + * CONSEQUENTIAL DAMAGES (INCLUDING, BUT NOT LIMITED TO, PROCUREMENT OF + * SUBSTITUTE GOODS OR SERVICES; LOSS OF USE, DATA, OR PROFITS; OR BUSINESS + * INTERRUPTION) HOWEVER CAUSED AND ON ANY THEORY OF LIABILITY, WHETHER IN + * CONTRACT, STRICT LIABILITY, OR TORT (INCLUDING NEGLIGENCE OR OTHERWISE) + * ARISING IN ANY WAY OUT OF THE USE OF THIS SOFTWARE, EVEN IF ADVISED OF THE + * POSSIBILITY OF SUCH DAMAGE. + */ + +#ifndef _TIPC_BCAST_H +#define _TIPC_BCAST_H + +#define MAX_NODES 4096 +#define WSIZE 32 + +/** + * struct node_map - set of node identifiers + * @count: # of nodes in set + * @map: bitmap of node identifiers that are in the set + */ + +struct node_map { + u32 count; + u32 map[MAX_NODES / WSIZE]; +}; + + +#define PLSIZE 32 + +/** + * struct port_list - set of node local destination ports + * @count: # of ports in set (only valid for first entry in list) + * @next: pointer to next entry in list + * @ports: array of port references + */ + +struct port_list { + int count; + struct port_list *next; + u32 ports[PLSIZE]; +}; + + +struct node; + +extern char bc_link_name[]; + + +/** + * nmap_get - determine if node exists in a node map + */ + +static inline int nmap_get(struct node_map *nm_ptr, u32 node) +{ + int n = tipc_node(node); + int w = n / WSIZE; + int b = n % WSIZE; + + return nm_ptr->map[w] & (1 << b); +} + +/** + * nmap_add - add a node to a node map + */ + +static inline void nmap_add(struct node_map *nm_ptr, u32 node) +{ + int n = tipc_node(node); + int w = n / WSIZE; + u32 mask = (1 << (n % WSIZE)); + + if ((nm_ptr->map[w] & mask) == 0) { + nm_ptr->count++; + nm_ptr->map[w] |= mask; + } +} + +/** + * nmap_remove - remove a node from a node map + */ + +static inline void nmap_remove(struct node_map *nm_ptr, u32 node) +{ + int n = tipc_node(node); + int w = n / WSIZE; + u32 mask = (1 << (n % WSIZE)); + + if ((nm_ptr->map[w] & mask) != 0) { + nm_ptr->map[w] &= ~mask; + nm_ptr->count--; + } +} + +/** + * nmap_equal - test for equality of node maps + */ + +static inline int nmap_equal(struct node_map *nm_a, struct node_map *nm_b) +{ + return !memcmp(nm_a, nm_b, sizeof(*nm_a)); +} + +/** + * nmap_diff - find differences between node maps + * @nm_a: input node map A + * @nm_b: input node map B + * @nm_diff: output node map A-B (i.e. nodes of A that are not in B) + */ + +static inline void nmap_diff(struct node_map *nm_a, struct node_map *nm_b, + struct node_map *nm_diff) +{ + int stop = sizeof(nm_a->map) / sizeof(u32); + int w; + int b; + u32 map; + + memset(nm_diff, 0, sizeof(*nm_diff)); + for (w = 0; w < stop; w++) { + map = nm_a->map[w] ^ (nm_a->map[w] & nm_b->map[w]); + nm_diff->map[w] = map; + if (map != 0) { + for (b = 0 ; b < WSIZE; b++) { + if (map & (1 << b)) + nm_diff->count++; + } + } + } +} + +/** + * port_list_add - add a port to a port list, ensuring no duplicates + */ + +static inline void port_list_add(struct port_list *pl_ptr, u32 port) +{ + struct port_list *item = pl_ptr; + int i; + int item_sz = PLSIZE; + int cnt = pl_ptr->count; + + for (; ; cnt -= item_sz, item = item->next) { + if (cnt < PLSIZE) + item_sz = cnt; + for (i = 0; i < item_sz; i++) + if (item->ports[i] == port) + return; + if (i < PLSIZE) { + item->ports[i] = port; + pl_ptr->count++; + return; + } + if (!item->next) { + item->next = kmalloc(sizeof(*item), GFP_ATOMIC); + if (!item->next) { + warn("Memory squeeze: multicast destination port list is incomplete\n"); + return; + } + item->next->next = NULL; + } + } +} + +/** + * port_list_free - free dynamically created entries in port_list chain + * + * Note: First item is on stack, so it doesn't need to be released + */ + +static inline void port_list_free(struct port_list *pl_ptr) +{ + struct port_list *item; + struct port_list *next; + + for (item = pl_ptr->next; item; item = next) { + next = item->next; + kfree(item); + } +} + + +int bclink_init(void); +void bclink_stop(void); +void bclink_acknowledge(struct node *n_ptr, u32 acked); +int bclink_send_msg(struct sk_buff *buf); +void bclink_recv_pkt(struct sk_buff *buf); +u32 bclink_get_last_sent(void); +u32 bclink_acks_missing(struct node *n_ptr); +void bclink_check_gap(struct node *n_ptr, u32 seqno); +int bclink_stats(char *stats_buf, const u32 buf_size); +int bclink_reset_stats(void); +int bclink_set_queue_limits(u32 limit); +void bcbearer_sort(void); +void bcbearer_push(void); + +#endif diff --git a/net/tipc/bearer.c b/net/tipc/bearer.c new file mode 100644 index 00000000000..3dd19fdc5a2 --- /dev/null +++ b/net/tipc/bearer.c @@ -0,0 +1,692 @@ +/* + * net/tipc/bearer.c: TIPC bearer code + * + * Copyright (c) 1996-2006, Ericsson AB + * Copyright (c) 2004-2005, Wind River Systems + * All rights reserved. + * + * Redistribution and use in source and binary forms, with or without + * modification, are permitted provided that the following conditions are met: + * + * 1. Redistributions of source code must retain the above copyright + * notice, this list of conditions and the following disclaimer. + * 2. Redistributions in binary form must reproduce the above copyright + * notice, this list of conditions and the following disclaimer in the + * documentation and/or other materials provided with the distribution. + * 3. Neither the names of the copyright holders nor the names of its + * contributors may be used to endorse or promote products derived from + * this software without specific prior written permission. + * + * Alternatively, this software may be distributed under the terms of the + * GNU General Public License ("GPL") version 2 as published by the Free + * Software Foundation. + * + * THIS SOFTWARE IS PROVIDED BY THE COPYRIGHT HOLDERS AND CONTRIBUTORS "AS IS" + * AND ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT LIMITED TO, THE + * IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR A PARTICULAR PURPOSE + * ARE DISCLAIMED. IN NO EVENT SHALL THE COPYRIGHT OWNER OR CONTRIBUTORS BE + * LIABLE FOR ANY DIRECT, INDIRECT, INCIDENTAL, SPECIAL, EXEMPLARY, OR + * CONSEQUENTIAL DAMAGES (INCLUDING, BUT NOT LIMITED TO, PROCUREMENT OF + * SUBSTITUTE GOODS OR SERVICES; LOSS OF USE, DATA, OR PROFITS; OR BUSINESS + * INTERRUPTION) HOWEVER CAUSED AND ON ANY THEORY OF LIABILITY, WHETHER IN + * CONTRACT, STRICT LIABILITY, OR TORT (INCLUDING NEGLIGENCE OR OTHERWISE) + * ARISING IN ANY WAY OUT OF THE USE OF THIS SOFTWARE, EVEN IF ADVISED OF THE + * POSSIBILITY OF SUCH DAMAGE. + */ + +#include "core.h" +#include "config.h" +#include "dbg.h" +#include "bearer.h" +#include "link.h" +#include "port.h" +#include "discover.h" +#include "bcast.h" + +#define MAX_ADDR_STR 32 + +static struct media *media_list = 0; +static u32 media_count = 0; + +struct bearer *bearers = 0; + +/** + * media_name_valid - validate media name + * + * Returns 1 if media name is valid, otherwise 0. + */ + +static int media_name_valid(const char *name) +{ + u32 len; + + len = strlen(name); + if ((len + 1) > TIPC_MAX_MEDIA_NAME) + return 0; + return (strspn(name, tipc_alphabet) == len); +} + +/** + * media_find - locates specified media object by name + */ + +static struct media *media_find(const char *name) +{ + struct media *m_ptr; + u32 i; + + for (i = 0, m_ptr = media_list; i < media_count; i++, m_ptr++) { + if (!strcmp(m_ptr->name, name)) + return m_ptr; + } + return 0; +} + +/** + * tipc_register_media - register a media type + * + * Bearers for this media type must be activated separately at a later stage. + */ + +int tipc_register_media(u32 media_type, + char *name, + int (*enable)(struct tipc_bearer *), + void (*disable)(struct tipc_bearer *), + int (*send_msg)(struct sk_buff *, + struct tipc_bearer *, + struct tipc_media_addr *), + char *(*addr2str)(struct tipc_media_addr *a, + char *str_buf, int str_size), + struct tipc_media_addr *bcast_addr, + const u32 bearer_priority, + const u32 link_tolerance, /* [ms] */ + const u32 send_window_limit) +{ + struct media *m_ptr; + u32 media_id; + u32 i; + int res = -EINVAL; + + write_lock_bh(&net_lock); + if (!media_list) + goto exit; + + if (!media_name_valid(name)) { + warn("Media registration error: illegal name <%s>\n", name); + goto exit; + } + if (!bcast_addr) { + warn("Media registration error: no broadcast address supplied\n"); + goto exit; + } + if (bearer_priority >= TIPC_NUM_LINK_PRI) { + warn("Media registration error: priority %u\n", bearer_priority); + goto exit; + } + if ((link_tolerance < TIPC_MIN_LINK_TOL) || + (link_tolerance > TIPC_MAX_LINK_TOL)) { + warn("Media registration error: tolerance %u\n", link_tolerance); + goto exit; + } + + media_id = media_count++; + if (media_id >= MAX_MEDIA) { + warn("Attempt to register more than %u media\n", MAX_MEDIA); + media_count--; + goto exit; + } + for (i = 0; i < media_id; i++) { + if (media_list[i].type_id == media_type) { + warn("Attempt to register second media with type %u\n", + media_type); + media_count--; + goto exit; + } + if (!strcmp(name, media_list[i].name)) { + warn("Attempt to re-register media name <%s>\n", name); + media_count--; + goto exit; + } + } + + m_ptr = &media_list[media_id]; + m_ptr->type_id = media_type; + m_ptr->send_msg = send_msg; + m_ptr->enable_bearer = enable; + m_ptr->disable_bearer = disable; + m_ptr->addr2str = addr2str; + memcpy(&m_ptr->bcast_addr, bcast_addr, sizeof(*bcast_addr)); + m_ptr->bcast = 1; + strcpy(m_ptr->name, name); + m_ptr->priority = bearer_priority; + m_ptr->tolerance = link_tolerance; + m_ptr->window = send_window_limit; + dbg("Media <%s> registered\n", name); + res = 0; +exit: + write_unlock_bh(&net_lock); + return res; +} + +/** + * media_addr_printf - record media address in print buffer + */ + +void media_addr_printf(struct print_buf *pb, struct tipc_media_addr *a) +{ + struct media *m_ptr; + u32 media_type; + u32 i; + + media_type = ntohl(a->type); + for (i = 0, m_ptr = media_list; i < media_count; i++, m_ptr++) { + if (m_ptr->type_id == media_type) + break; + } + + if ((i < media_count) && (m_ptr->addr2str != NULL)) { + char addr_str[MAX_ADDR_STR]; + + tipc_printf(pb, "%s(%s) ", m_ptr->name, + m_ptr->addr2str(a, addr_str, sizeof(addr_str))); + } else { + unchar *addr = (unchar *)&a->dev_addr; + + tipc_printf(pb, "UNKNOWN(%u):", media_type); + for (i = 0; i < (sizeof(*a) - sizeof(a->type)); i++) { + tipc_printf(pb, "%02x ", addr[i]); + } + } +} + +/** + * media_get_names - record names of registered media in buffer + */ + +struct sk_buff *media_get_names(void) +{ + struct sk_buff *buf; + struct media *m_ptr; + int i; + + buf = cfg_reply_alloc(MAX_MEDIA * TLV_SPACE(TIPC_MAX_MEDIA_NAME)); + if (!buf) + return NULL; + + read_lock_bh(&net_lock); + for (i = 0, m_ptr = media_list; i < media_count; i++, m_ptr++) { + cfg_append_tlv(buf, TIPC_TLV_MEDIA_NAME, m_ptr->name, + strlen(m_ptr->name) + 1); + } + read_unlock_bh(&net_lock); + return buf; +} + +/** + * bearer_name_validate - validate & (optionally) deconstruct bearer name + * @name - ptr to bearer name string + * @name_parts - ptr to area for bearer name components (or NULL if not needed) + * + * Returns 1 if bearer name is valid, otherwise 0. + */ + +static int bearer_name_validate(const char *name, + struct bearer_name *name_parts) +{ + char name_copy[TIPC_MAX_BEARER_NAME]; + char *media_name; + char *if_name; + u32 media_len; + u32 if_len; + + /* copy bearer name & ensure length is OK */ + + name_copy[TIPC_MAX_BEARER_NAME - 1] = 0; + /* need above in case non-Posix strncpy() doesn't pad with nulls */ + strncpy(name_copy, name, TIPC_MAX_BEARER_NAME); + if (name_copy[TIPC_MAX_BEARER_NAME - 1] != 0) + return 0; + + /* ensure all component parts of bearer name are present */ + + media_name = name_copy; + if ((if_name = strchr(media_name, ':')) == NULL) + return 0; + *(if_name++) = 0; + media_len = if_name - media_name; + if_len = strlen(if_name) + 1; + + /* validate component parts of bearer name */ + + if ((media_len <= 1) || (media_len > TIPC_MAX_MEDIA_NAME) || + (if_len <= 1) || (if_len > TIPC_MAX_IF_NAME) || + (strspn(media_name, tipc_alphabet) != (media_len - 1)) || + (strspn(if_name, tipc_alphabet) != (if_len - 1))) + return 0; + + /* return bearer name components, if necessary */ + + if (name_parts) { + strcpy(name_parts->media_name, media_name); + strcpy(name_parts->if_name, if_name); + } + return 1; +} + +/** + * bearer_find - locates bearer object with matching bearer name + */ + +static struct bearer *bearer_find(const char *name) +{ + struct bearer *b_ptr; + u32 i; + + for (i = 0, b_ptr = bearers; i < MAX_BEARERS; i++, b_ptr++) { + if (b_ptr->active && (!strcmp(b_ptr->publ.name, name))) + return b_ptr; + } + return 0; +} + +/** + * bearer_find - locates bearer object with matching interface name + */ + +struct bearer *bearer_find_interface(const char *if_name) +{ + struct bearer *b_ptr; + char *b_if_name; + u32 i; + + for (i = 0, b_ptr = bearers; i < MAX_BEARERS; i++, b_ptr++) { + if (!b_ptr->active) + continue; + b_if_name = strchr(b_ptr->publ.name, ':') + 1; + if (!strcmp(b_if_name, if_name)) + return b_ptr; + } + return 0; +} + +/** + * bearer_get_names - record names of bearers in buffer + */ + +struct sk_buff *bearer_get_names(void) +{ + struct sk_buff *buf; + struct media *m_ptr; + struct bearer *b_ptr; + int i, j; + + buf = cfg_reply_alloc(MAX_BEARERS * TLV_SPACE(TIPC_MAX_BEARER_NAME)); + if (!buf) + return NULL; + + read_lock_bh(&net_lock); + for (i = 0, m_ptr = media_list; i < media_count; i++, m_ptr++) { + for (j = 0; j < MAX_BEARERS; j++) { + b_ptr = &bearers[j]; + if (b_ptr->active && (b_ptr->media == m_ptr)) { + cfg_append_tlv(buf, TIPC_TLV_BEARER_NAME, + b_ptr->publ.name, + strlen(b_ptr->publ.name) + 1); + } + } + } + read_unlock_bh(&net_lock); + return buf; +} + +void bearer_add_dest(struct bearer *b_ptr, u32 dest) +{ + nmap_add(&b_ptr->nodes, dest); + disc_update_link_req(b_ptr->link_req); + bcbearer_sort(); +} + +void bearer_remove_dest(struct bearer *b_ptr, u32 dest) +{ + nmap_remove(&b_ptr->nodes, dest); + disc_update_link_req(b_ptr->link_req); + bcbearer_sort(); +} + +/* + * bearer_push(): Resolve bearer congestion. Force the waiting + * links to push out their unsent packets, one packet per link + * per iteration, until all packets are gone or congestion reoccurs. + * 'net_lock' is read_locked when this function is called + * bearer.lock must be taken before calling + * Returns binary true(1) ore false(0) + */ +static int bearer_push(struct bearer *b_ptr) +{ + u32 res = TIPC_OK; + struct link *ln, *tln; + + if (b_ptr->publ.blocked) + return 0; + + while (!list_empty(&b_ptr->cong_links) && (res != PUSH_FAILED)) { + list_for_each_entry_safe(ln, tln, &b_ptr->cong_links, link_list) { + res = link_push_packet(ln); + if (res == PUSH_FAILED) + break; + if (res == PUSH_FINISHED) + list_move_tail(&ln->link_list, &b_ptr->links); + } + } + return list_empty(&b_ptr->cong_links); +} + +void bearer_lock_push(struct bearer *b_ptr) +{ + int res; + + spin_lock_bh(&b_ptr->publ.lock); + res = bearer_push(b_ptr); + spin_unlock_bh(&b_ptr->publ.lock); + if (res) + bcbearer_push(); +} + + +/* + * Interrupt enabling new requests after bearer congestion or blocking: + * See bearer_send(). + */ +void tipc_continue(struct tipc_bearer *tb_ptr) +{ + struct bearer *b_ptr = (struct bearer *)tb_ptr; + + spin_lock_bh(&b_ptr->publ.lock); + b_ptr->continue_count++; + if (!list_empty(&b_ptr->cong_links)) + k_signal((Handler)bearer_lock_push, (unsigned long)b_ptr); + b_ptr->publ.blocked = 0; + spin_unlock_bh(&b_ptr->publ.lock); +} + +/* + * Schedule link for sending of messages after the bearer + * has been deblocked by 'continue()'. This method is called + * when somebody tries to send a message via this link while + * the bearer is congested. 'net_lock' is in read_lock here + * bearer.lock is busy + */ + +static void bearer_schedule_unlocked(struct bearer *b_ptr, struct link *l_ptr) +{ + list_move_tail(&l_ptr->link_list, &b_ptr->cong_links); +} + +/* + * Schedule link for sending of messages after the bearer + * has been deblocked by 'continue()'. This method is called + * when somebody tries to send a message via this link while + * the bearer is congested. 'net_lock' is in read_lock here, + * bearer.lock is free + */ + +void bearer_schedule(struct bearer *b_ptr, struct link *l_ptr) +{ + spin_lock_bh(&b_ptr->publ.lock); + bearer_schedule_unlocked(b_ptr, l_ptr); + spin_unlock_bh(&b_ptr->publ.lock); +} + + +/* + * bearer_resolve_congestion(): Check if there is bearer congestion, + * and if there is, try to resolve it before returning. + * 'net_lock' is read_locked when this function is called + */ +int bearer_resolve_congestion(struct bearer *b_ptr, struct link *l_ptr) +{ + int res = 1; + + if (list_empty(&b_ptr->cong_links)) + return 1; + spin_lock_bh(&b_ptr->publ.lock); + if (!bearer_push(b_ptr)) { + bearer_schedule_unlocked(b_ptr, l_ptr); + res = 0; + } + spin_unlock_bh(&b_ptr->publ.lock); + return res; +} + + +/** + * tipc_enable_bearer - enable bearer with the given name + */ + +int tipc_enable_bearer(const char *name, u32 bcast_scope, u32 priority) +{ + struct bearer *b_ptr; + struct media *m_ptr; + struct bearer_name b_name; + char addr_string[16]; + u32 bearer_id; + u32 with_this_prio; + u32 i; + int res = -EINVAL; + + if (tipc_mode != TIPC_NET_MODE) + return -ENOPROTOOPT; + if (!bearer_name_validate(name, &b_name) || + !addr_domain_valid(bcast_scope) || + !in_scope(bcast_scope, tipc_own_addr) || + (priority > TIPC_NUM_LINK_PRI)) + return -EINVAL; + + write_lock_bh(&net_lock); + if (!bearers) + goto failed; + + m_ptr = media_find(b_name.media_name); + if (!m_ptr) { + warn("No media <%s>\n", b_name.media_name); + goto failed; + } + if (priority == TIPC_NUM_LINK_PRI) + priority = m_ptr->priority; + +restart: + bearer_id = MAX_BEARERS; + with_this_prio = 1; + for (i = MAX_BEARERS; i-- != 0; ) { + if (!bearers[i].active) { + bearer_id = i; + continue; + } + if (!strcmp(name, bearers[i].publ.name)) { + warn("Bearer <%s> already enabled\n", name); + goto failed; + } + if ((bearers[i].priority == priority) && + (++with_this_prio > 2)) { + if (priority-- == 0) { + warn("Third bearer <%s> with priority %u, unable to lower to %u\n", + name, priority + 1, priority); + goto failed; + } + warn("Third bearer <%s> with priority %u, lowering to %u\n", + name, priority + 1, priority); + goto restart; + } + } + if (bearer_id >= MAX_BEARERS) { + warn("Attempt to enable more than %d bearers\n", MAX_BEARERS); + goto failed; + } + + b_ptr = &bearers[bearer_id]; + memset(b_ptr, 0, sizeof(struct bearer)); + + strcpy(b_ptr->publ.name, name); + res = m_ptr->enable_bearer(&b_ptr->publ); + if (res) { + warn("Failed to enable bearer <%s>\n", name); + goto failed; + } + + b_ptr->identity = bearer_id; + b_ptr->media = m_ptr; + b_ptr->net_plane = bearer_id + 'A'; + b_ptr->active = 1; + b_ptr->detect_scope = bcast_scope; + b_ptr->priority = priority; + INIT_LIST_HEAD(&b_ptr->cong_links); + INIT_LIST_HEAD(&b_ptr->links); + if (m_ptr->bcast) { + b_ptr->link_req = disc_init_link_req(b_ptr, &m_ptr->bcast_addr, + bcast_scope, 2); + } + b_ptr->publ.lock = SPIN_LOCK_UNLOCKED; + write_unlock_bh(&net_lock); + info("Enabled bearer <%s>, discovery domain %s\n", + name, addr_string_fill(addr_string, bcast_scope)); + return 0; +failed: + write_unlock_bh(&net_lock); + return res; +} + +/** + * tipc_block_bearer(): Block the bearer with the given name, + * and reset all its links + */ + +int tipc_block_bearer(const char *name) +{ + struct bearer *b_ptr = 0; + struct link *l_ptr; + struct link *temp_l_ptr; + + if (tipc_mode != TIPC_NET_MODE) + return -ENOPROTOOPT; + + read_lock_bh(&net_lock); + b_ptr = bearer_find(name); + if (!b_ptr) { + warn("Attempt to block unknown bearer <%s>\n", name); + read_unlock_bh(&net_lock); + return -EINVAL; + } + + spin_lock_bh(&b_ptr->publ.lock); + b_ptr->publ.blocked = 1; + list_for_each_entry_safe(l_ptr, temp_l_ptr, &b_ptr->links, link_list) { + struct node *n_ptr = l_ptr->owner; + + spin_lock_bh(&n_ptr->lock); + link_reset(l_ptr); + spin_unlock_bh(&n_ptr->lock); + } + spin_unlock_bh(&b_ptr->publ.lock); + read_unlock_bh(&net_lock); + info("Blocked bearer <%s>\n", name); + return TIPC_OK; +} + +/** + * bearer_disable - + * + * Note: This routine assumes caller holds net_lock. + */ + +static int bearer_disable(const char *name) +{ + struct bearer *b_ptr; + struct link *l_ptr; + struct link *temp_l_ptr; + + if (tipc_mode != TIPC_NET_MODE) + return -ENOPROTOOPT; + + b_ptr = bearer_find(name); + if (!b_ptr) { + warn("Attempt to disable unknown bearer <%s>\n", name); + return -EINVAL; + } + + disc_stop_link_req(b_ptr->link_req); + spin_lock_bh(&b_ptr->publ.lock); + b_ptr->link_req = NULL; + b_ptr->publ.blocked = 1; + if (b_ptr->media->disable_bearer) { + spin_unlock_bh(&b_ptr->publ.lock); + write_unlock_bh(&net_lock); + b_ptr->media->disable_bearer(&b_ptr->publ); + write_lock_bh(&net_lock); + spin_lock_bh(&b_ptr->publ.lock); + } + list_for_each_entry_safe(l_ptr, temp_l_ptr, &b_ptr->links, link_list) { + link_delete(l_ptr); + } + spin_unlock_bh(&b_ptr->publ.lock); + info("Disabled bearer <%s>\n", name); + memset(b_ptr, 0, sizeof(struct bearer)); + return TIPC_OK; +} + +int tipc_disable_bearer(const char *name) +{ + int res; + + write_lock_bh(&net_lock); + res = bearer_disable(name); + write_unlock_bh(&net_lock); + return res; +} + + + +int bearer_init(void) +{ + int res; + + write_lock_bh(&net_lock); + bearers = kmalloc(MAX_BEARERS * sizeof(struct bearer), GFP_ATOMIC); + media_list = kmalloc(MAX_MEDIA * sizeof(struct media), GFP_ATOMIC); + if (bearers && media_list) { + memset(bearers, 0, MAX_BEARERS * sizeof(struct bearer)); + memset(media_list, 0, MAX_MEDIA * sizeof(struct media)); + res = TIPC_OK; + } else { + kfree(bearers); + kfree(media_list); + bearers = 0; + media_list = 0; + res = -ENOMEM; + } + write_unlock_bh(&net_lock); + return res; +} + +void bearer_stop(void) +{ + u32 i; + + if (!bearers) + return; + + for (i = 0; i < MAX_BEARERS; i++) { + if (bearers[i].active) + bearers[i].publ.blocked = 1; + } + for (i = 0; i < MAX_BEARERS; i++) { + if (bearers[i].active) + bearer_disable(bearers[i].publ.name); + } + kfree(bearers); + kfree(media_list); + bearers = 0; + media_list = 0; + media_count = 0; +} + + diff --git a/net/tipc/bearer.h b/net/tipc/bearer.h new file mode 100644 index 00000000000..21e63d3f018 --- /dev/null +++ b/net/tipc/bearer.h @@ -0,0 +1,172 @@ +/* + * net/tipc/bearer.h: Include file for TIPC bearer code + * + * Copyright (c) 1996-2006, Ericsson AB + * Copyright (c) 2005, Wind River Systems + * All rights reserved. + * + * Redistribution and use in source and binary forms, with or without + * modification, are permitted provided that the following conditions are met: + * + * 1. Redistributions of source code must retain the above copyright + * notice, this list of conditions and the following disclaimer. + * 2. Redistributions in binary form must reproduce the above copyright + * notice, this list of conditions and the following disclaimer in the + * documentation and/or other materials provided with the distribution. + * 3. Neither the names of the copyright holders nor the names of its + * contributors may be used to endorse or promote products derived from + * this software without specific prior written permission. + * + * Alternatively, this software may be distributed under the terms of the + * GNU General Public License ("GPL") version 2 as published by the Free + * Software Foundation. + * + * THIS SOFTWARE IS PROVIDED BY THE COPYRIGHT HOLDERS AND CONTRIBUTORS "AS IS" + * AND ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT LIMITED TO, THE + * IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR A PARTICULAR PURPOSE + * ARE DISCLAIMED. IN NO EVENT SHALL THE COPYRIGHT OWNER OR CONTRIBUTORS BE + * LIABLE FOR ANY DIRECT, INDIRECT, INCIDENTAL, SPECIAL, EXEMPLARY, OR + * CONSEQUENTIAL DAMAGES (INCLUDING, BUT NOT LIMITED TO, PROCUREMENT OF + * SUBSTITUTE GOODS OR SERVICES; LOSS OF USE, DATA, OR PROFITS; OR BUSINESS + * INTERRUPTION) HOWEVER CAUSED AND ON ANY THEORY OF LIABILITY, WHETHER IN + * CONTRACT, STRICT LIABILITY, OR TORT (INCLUDING NEGLIGENCE OR OTHERWISE) + * ARISING IN ANY WAY OUT OF THE USE OF THIS SOFTWARE, EVEN IF ADVISED OF THE + * POSSIBILITY OF SUCH DAMAGE. + */ + +#ifndef _TIPC_BEARER_H +#define _TIPC_BEARER_H + +#include <net/tipc/tipc_bearer.h> +#include "bcast.h" + +#define MAX_BEARERS 8 +#define MAX_MEDIA 4 + + +/** + * struct media - TIPC media information available to internal users + * @send_msg: routine which handles buffer transmission + * @enable_bearer: routine which enables a bearer + * @disable_bearer: routine which disables a bearer + * @addr2str: routine which converts bearer's address to string form + * @bcast_addr: media address used in broadcasting + * @bcast: non-zero if media supports broadcasting [currently mandatory] + * @priority: default link (and bearer) priority + * @tolerance: default time (in ms) before declaring link failure + * @window: default window (in packets) before declaring link congestion + * @type_id: TIPC media identifier [defined in tipc_bearer.h] + * @name: media name + */ + +struct media { + int (*send_msg)(struct sk_buff *buf, + struct tipc_bearer *b_ptr, + struct tipc_media_addr *dest); + int (*enable_bearer)(struct tipc_bearer *b_ptr); + void (*disable_bearer)(struct tipc_bearer *b_ptr); + char *(*addr2str)(struct tipc_media_addr *a, + char *str_buf, int str_size); + struct tipc_media_addr bcast_addr; + int bcast; + u32 priority; + u32 tolerance; + u32 window; + u32 type_id; + char name[TIPC_MAX_MEDIA_NAME]; +}; + +/** + * struct bearer - TIPC bearer information available to internal users + * @publ: bearer information available to privileged users + * @media: ptr to media structure associated with bearer + * @priority: default link priority for bearer + * @detect_scope: network address mask used during automatic link creation + * @identity: array index of this bearer within TIPC bearer array + * @link_req: ptr to (optional) structure making periodic link setup requests + * @links: list of non-congested links associated with bearer + * @cong_links: list of congested links associated with bearer + * @continue_count: # of times bearer has resumed after congestion or blocking + * @active: non-zero if bearer structure is represents a bearer + * @net_plane: network plane ('A' through 'H') currently associated with bearer + * @nodes: indicates which nodes in cluster can be reached through bearer + */ + +struct bearer { + struct tipc_bearer publ; + struct media *media; + u32 priority; + u32 detect_scope; + u32 identity; + struct link_req *link_req; + struct list_head links; + struct list_head cong_links; + u32 continue_count; + int active; + char net_plane; + struct node_map nodes; +}; + +struct bearer_name { + char media_name[TIPC_MAX_MEDIA_NAME]; + char if_name[TIPC_MAX_IF_NAME]; +}; + +struct link; + +extern struct bearer *bearers; + +void media_addr_printf(struct print_buf *pb, struct tipc_media_addr *a); +struct sk_buff *media_get_names(void); + +struct sk_buff *bearer_get_names(void); +void bearer_add_dest(struct bearer *b_ptr, u32 dest); +void bearer_remove_dest(struct bearer *b_ptr, u32 dest); +void bearer_schedule(struct bearer *b_ptr, struct link *l_ptr); +struct bearer *bearer_find_interface(const char *if_name); +int bearer_resolve_congestion(struct bearer *b_ptr, struct link *l_ptr); +int bearer_init(void); +void bearer_stop(void); +int bearer_broadcast(struct sk_buff *buf, struct tipc_bearer *b_ptr, + struct tipc_media_addr *dest); +void bearer_lock_push(struct bearer *b_ptr); + + +/** + * bearer_send- sends buffer to destination over bearer + * + * Returns true (1) if successful, or false (0) if unable to send + * + * IMPORTANT: + * The media send routine must not alter the buffer being passed in + * as it may be needed for later retransmission! + * + * If the media send routine returns a non-zero value (indicating that + * it was unable to send the buffer), it must: + * 1) mark the bearer as blocked, + * 2) call tipc_continue() once the bearer is able to send again. + * Media types that are unable to meet these two critera must ensure their + * send routine always returns success -- even if the buffer was not sent -- + * and let TIPC's link code deal with the undelivered message. + */ + +static inline int bearer_send(struct bearer *b_ptr, struct sk_buff *buf, + struct tipc_media_addr *dest) +{ + return !b_ptr->media->send_msg(buf, &b_ptr->publ, dest); +} + +/** + * bearer_congested - determines if bearer is currently congested + */ + +static inline int bearer_congested(struct bearer *b_ptr, struct link *l_ptr) +{ + if (unlikely(b_ptr->publ.blocked)) + return 1; + if (likely(list_empty(&b_ptr->cong_links))) + return 0; + return !bearer_resolve_congestion(b_ptr, l_ptr); +} + +#endif diff --git a/net/tipc/cluster.c b/net/tipc/cluster.c new file mode 100644 index 00000000000..f0f7bac51d4 --- /dev/null +++ b/net/tipc/cluster.c @@ -0,0 +1,576 @@ +/* + * net/tipc/cluster.c: TIPC cluster management routines + * + * Copyright (c) 2000-2006, Ericsson AB + * Copyright (c) 2005, Wind River Systems + * All rights reserved. + * + * Redistribution and use in source and binary forms, with or without + * modification, are permitted provided that the following conditions are met: + * + * 1. Redistributions of source code must retain the above copyright + * notice, this list of conditions and the following disclaimer. + * 2. Redistributions in binary form must reproduce the above copyright + * notice, this list of conditions and the following disclaimer in the + * documentation and/or other materials provided with the distribution. + * 3. Neither the names of the copyright holders nor the names of its + * contributors may be used to endorse or promote products derived from + * this software without specific prior written permission. + * + * Alternatively, this software may be distributed under the terms of the + * GNU General Public License ("GPL") version 2 as published by the Free + * Software Foundation. + * + * THIS SOFTWARE IS PROVIDED BY THE COPYRIGHT HOLDERS AND CONTRIBUTORS "AS IS" + * AND ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT LIMITED TO, THE + * IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR A PARTICULAR PURPOSE + * ARE DISCLAIMED. IN NO EVENT SHALL THE COPYRIGHT OWNER OR CONTRIBUTORS BE + * LIABLE FOR ANY DIRECT, INDIRECT, INCIDENTAL, SPECIAL, EXEMPLARY, OR + * CONSEQUENTIAL DAMAGES (INCLUDING, BUT NOT LIMITED TO, PROCUREMENT OF + * SUBSTITUTE GOODS OR SERVICES; LOSS OF USE, DATA, OR PROFITS; OR BUSINESS + * INTERRUPTION) HOWEVER CAUSED AND ON ANY THEORY OF LIABILITY, WHETHER IN + * CONTRACT, STRICT LIABILITY, OR TORT (INCLUDING NEGLIGENCE OR OTHERWISE) + * ARISING IN ANY WAY OUT OF THE USE OF THIS SOFTWARE, EVEN IF ADVISED OF THE + * POSSIBILITY OF SUCH DAMAGE. + */ + +#include "core.h" +#include "cluster.h" +#include "addr.h" +#include "node_subscr.h" +#include "link.h" +#include "node.h" +#include "net.h" +#include "msg.h" +#include "bearer.h" + +void cluster_multicast(struct cluster *c_ptr, struct sk_buff *buf, + u32 lower, u32 upper); +struct sk_buff *cluster_prepare_routing_msg(u32 data_size, u32 dest); + +struct node **local_nodes = 0; +struct node_map cluster_bcast_nodes = {0,{0,}}; +u32 highest_allowed_slave = 0; + +struct cluster *cluster_create(u32 addr) +{ + struct _zone *z_ptr; + struct cluster *c_ptr; + int max_nodes; + int alloc; + + c_ptr = (struct cluster *)kmalloc(sizeof(*c_ptr), GFP_ATOMIC); + if (c_ptr == NULL) + return 0; + memset(c_ptr, 0, sizeof(*c_ptr)); + + c_ptr->addr = tipc_addr(tipc_zone(addr), tipc_cluster(addr), 0); + if (in_own_cluster(addr)) + max_nodes = LOWEST_SLAVE + tipc_max_slaves; + else + max_nodes = tipc_max_nodes + 1; + alloc = sizeof(void *) * (max_nodes + 1); + c_ptr->nodes = (struct node **)kmalloc(alloc, GFP_ATOMIC); + if (c_ptr->nodes == NULL) { + kfree(c_ptr); + return 0; + } + memset(c_ptr->nodes, 0, alloc); + if (in_own_cluster(addr)) + local_nodes = c_ptr->nodes; + c_ptr->highest_slave = LOWEST_SLAVE - 1; + c_ptr->highest_node = 0; + + z_ptr = zone_find(tipc_zone(addr)); + if (z_ptr == NULL) { + z_ptr = zone_create(addr); + } + if (z_ptr != NULL) { + zone_attach_cluster(z_ptr, c_ptr); + c_ptr->owner = z_ptr; + } + else { + kfree(c_ptr); + c_ptr = 0; + } + + return c_ptr; +} + +void cluster_delete(struct cluster *c_ptr) +{ + u32 n_num; + + if (!c_ptr) + return; + for (n_num = 1; n_num <= c_ptr->highest_node; n_num++) { + node_delete(c_ptr->nodes[n_num]); + } + for (n_num = LOWEST_SLAVE; n_num <= c_ptr->highest_slave; n_num++) { + node_delete(c_ptr->nodes[n_num]); + } + kfree(c_ptr->nodes); + kfree(c_ptr); +} + +u32 cluster_next_node(struct cluster *c_ptr, u32 addr) +{ + struct node *n_ptr; + u32 n_num = tipc_node(addr) + 1; + + if (!c_ptr) + return addr; + for (; n_num <= c_ptr->highest_node; n_num++) { + n_ptr = c_ptr->nodes[n_num]; + if (n_ptr && node_has_active_links(n_ptr)) + return n_ptr->addr; + } + for (n_num = 1; n_num < tipc_node(addr); n_num++) { + n_ptr = c_ptr->nodes[n_num]; + if (n_ptr && node_has_active_links(n_ptr)) + return n_ptr->addr; + } + return 0; +} + +void cluster_attach_node(struct cluster *c_ptr, struct node *n_ptr) +{ + u32 n_num = tipc_node(n_ptr->addr); + u32 max_n_num = tipc_max_nodes; + + if (in_own_cluster(n_ptr->addr)) + max_n_num = highest_allowed_slave; + assert(n_num > 0); + assert(n_num <= max_n_num); + assert(c_ptr->nodes[n_num] == 0); + c_ptr->nodes[n_num] = n_ptr; + if (n_num > c_ptr->highest_node) + c_ptr->highest_node = n_num; +} + +/** + * cluster_select_router - select router to a cluster + * + * Uses deterministic and fair algorithm. + */ + +u32 cluster_select_router(struct cluster *c_ptr, u32 ref) +{ + u32 n_num; + u32 ulim = c_ptr->highest_node; + u32 mask; + u32 tstart; + + assert(!in_own_cluster(c_ptr->addr)); + if (!ulim) + return 0; + + /* Start entry must be random */ + mask = tipc_max_nodes; + while (mask > ulim) + mask >>= 1; + tstart = ref & mask; + n_num = tstart; + + /* Lookup upwards with wrap-around */ + do { + if (node_is_up(c_ptr->nodes[n_num])) + break; + } while (++n_num <= ulim); + if (n_num > ulim) { + n_num = 1; + do { + if (node_is_up(c_ptr->nodes[n_num])) + break; + } while (++n_num < tstart); + if (n_num == tstart) + return 0; + } + assert(n_num <= ulim); + return node_select_router(c_ptr->nodes[n_num], ref); +} + +/** + * cluster_select_node - select destination node within a remote cluster + * + * Uses deterministic and fair algorithm. + */ + +struct node *cluster_select_node(struct cluster *c_ptr, u32 selector) +{ + u32 n_num; + u32 mask = tipc_max_nodes; + u32 start_entry; + + assert(!in_own_cluster(c_ptr->addr)); + if (!c_ptr->highest_node) + return 0; + + /* Start entry must be random */ + while (mask > c_ptr->highest_node) { + mask >>= 1; + } + start_entry = (selector & mask) ? selector & mask : 1u; + assert(start_entry <= c_ptr->highest_node); + + /* Lookup upwards with wrap-around */ + for (n_num = start_entry; n_num <= c_ptr->highest_node; n_num++) { + if (node_has_active_links(c_ptr->nodes[n_num])) + return c_ptr->nodes[n_num]; + } + for (n_num = 1; n_num < start_entry; n_num++) { + if (node_has_active_links(c_ptr->nodes[n_num])) + return c_ptr->nodes[n_num]; + } + return 0; +} + +/* + * Routing table management: See description in node.c + */ + +struct sk_buff *cluster_prepare_routing_msg(u32 data_size, u32 dest) +{ + u32 size = INT_H_SIZE + data_size; + struct sk_buff *buf = buf_acquire(size); + struct tipc_msg *msg; + + if (buf) { + msg = buf_msg(buf); + memset((char *)msg, 0, size); + msg_init(msg, ROUTE_DISTRIBUTOR, 0, TIPC_OK, INT_H_SIZE, dest); + } + return buf; +} + +void cluster_bcast_new_route(struct cluster *c_ptr, u32 dest, + u32 lower, u32 upper) +{ + struct sk_buff *buf = cluster_prepare_routing_msg(0, c_ptr->addr); + struct tipc_msg *msg; + + if (buf) { + msg = buf_msg(buf); + msg_set_remote_node(msg, dest); + msg_set_type(msg, ROUTE_ADDITION); + cluster_multicast(c_ptr, buf, lower, upper); + } else { + warn("Memory squeeze: broadcast of new route failed\n"); + } +} + +void cluster_bcast_lost_route(struct cluster *c_ptr, u32 dest, + u32 lower, u32 upper) +{ + struct sk_buff *buf = cluster_prepare_routing_msg(0, c_ptr->addr); + struct tipc_msg *msg; + + if (buf) { + msg = buf_msg(buf); + msg_set_remote_node(msg, dest); + msg_set_type(msg, ROUTE_REMOVAL); + cluster_multicast(c_ptr, buf, lower, upper); + } else { + warn("Memory squeeze: broadcast of lost route failed\n"); + } +} + +void cluster_send_slave_routes(struct cluster *c_ptr, u32 dest) +{ + struct sk_buff *buf; + struct tipc_msg *msg; + u32 highest = c_ptr->highest_slave; + u32 n_num; + int send = 0; + + assert(!is_slave(dest)); + assert(in_own_cluster(dest)); + assert(in_own_cluster(c_ptr->addr)); + if (highest <= LOWEST_SLAVE) + return; + buf = cluster_prepare_routing_msg(highest - LOWEST_SLAVE + 1, + c_ptr->addr); + if (buf) { + msg = buf_msg(buf); + msg_set_remote_node(msg, c_ptr->addr); + msg_set_type(msg, SLAVE_ROUTING_TABLE); + for (n_num = LOWEST_SLAVE; n_num <= highest; n_num++) { + if (c_ptr->nodes[n_num] && + node_has_active_links(c_ptr->nodes[n_num])) { + send = 1; + msg_set_dataoctet(msg, n_num); + } + } + if (send) + link_send(buf, dest, dest); + else + buf_discard(buf); + } else { + warn("Memory squeeze: broadcast of lost route failed\n"); + } +} + +void cluster_send_ext_routes(struct cluster *c_ptr, u32 dest) +{ + struct sk_buff *buf; + struct tipc_msg *msg; + u32 highest = c_ptr->highest_node; + u32 n_num; + int send = 0; + + if (in_own_cluster(c_ptr->addr)) + return; + assert(!is_slave(dest)); + assert(in_own_cluster(dest)); + highest = c_ptr->highest_node; + buf = cluster_prepare_routing_msg(highest + 1, c_ptr->addr); + if (buf) { + msg = buf_msg(buf); + msg_set_remote_node(msg, c_ptr->addr); + msg_set_type(msg, EXT_ROUTING_TABLE); + for (n_num = 1; n_num <= highest; n_num++) { + if (c_ptr->nodes[n_num] && + node_has_active_links(c_ptr->nodes[n_num])) { + send = 1; + msg_set_dataoctet(msg, n_num); + } + } + if (send) + link_send(buf, dest, dest); + else + buf_discard(buf); + } else { + warn("Memory squeeze: broadcast of external route failed\n"); + } +} + +void cluster_send_local_routes(struct cluster *c_ptr, u32 dest) +{ + struct sk_buff *buf; + struct tipc_msg *msg; + u32 highest = c_ptr->highest_node; + u32 n_num; + int send = 0; + + assert(is_slave(dest)); + assert(in_own_cluster(c_ptr->addr)); + buf = cluster_prepare_routing_msg(highest, c_ptr->addr); + if (buf) { + msg = buf_msg(buf); + msg_set_remote_node(msg, c_ptr->addr); + msg_set_type(msg, LOCAL_ROUTING_TABLE); + for (n_num = 1; n_num <= highest; n_num++) { + if (c_ptr->nodes[n_num] && + node_has_active_links(c_ptr->nodes[n_num])) { + send = 1; + msg_set_dataoctet(msg, n_num); + } + } + if (send) + link_send(buf, dest, dest); + else + buf_discard(buf); + } else { + warn("Memory squeeze: broadcast of local route failed\n"); + } +} + +void cluster_recv_routing_table(struct sk_buff *buf) +{ + struct tipc_msg *msg = buf_msg(buf); + struct cluster *c_ptr; + struct node *n_ptr; + unchar *node_table; + u32 table_size; + u32 router; + u32 rem_node = msg_remote_node(msg); + u32 z_num; + u32 c_num; + u32 n_num; + + c_ptr = cluster_find(rem_node); + if (!c_ptr) { + c_ptr = cluster_create(rem_node); + if (!c_ptr) { + buf_discard(buf); + return; + } + } + + node_table = buf->data + msg_hdr_sz(msg); + table_size = msg_size(msg) - msg_hdr_sz(msg); + router = msg_prevnode(msg); + z_num = tipc_zone(rem_node); + c_num = tipc_cluster(rem_node); + + switch (msg_type(msg)) { + case LOCAL_ROUTING_TABLE: + assert(is_slave(tipc_own_addr)); + case EXT_ROUTING_TABLE: + for (n_num = 1; n_num < table_size; n_num++) { + if (node_table[n_num]) { + u32 addr = tipc_addr(z_num, c_num, n_num); + n_ptr = c_ptr->nodes[n_num]; + if (!n_ptr) { + n_ptr = node_create(addr); + } + if (n_ptr) + node_add_router(n_ptr, router); + } + } + break; + case SLAVE_ROUTING_TABLE: + assert(!is_slave(tipc_own_addr)); + assert(in_own_cluster(c_ptr->addr)); + for (n_num = 1; n_num < table_size; n_num++) { + if (node_table[n_num]) { + u32 slave_num = n_num + LOWEST_SLAVE; + u32 addr = tipc_addr(z_num, c_num, slave_num); + n_ptr = c_ptr->nodes[slave_num]; + if (!n_ptr) { + n_ptr = node_create(addr); + } + if (n_ptr) + node_add_router(n_ptr, router); + } + } + break; + case ROUTE_ADDITION: + if (!is_slave(tipc_own_addr)) { + assert(!in_own_cluster(c_ptr->addr) + || is_slave(rem_node)); + } else { + assert(in_own_cluster(c_ptr->addr) + && !is_slave(rem_node)); + } + n_ptr = c_ptr->nodes[tipc_node(rem_node)]; + if (!n_ptr) + n_ptr = node_create(rem_node); + if (n_ptr) + node_add_router(n_ptr, router); + break; + case ROUTE_REMOVAL: + if (!is_slave(tipc_own_addr)) { + assert(!in_own_cluster(c_ptr->addr) + || is_slave(rem_node)); + } else { + assert(in_own_cluster(c_ptr->addr) + && !is_slave(rem_node)); + } + n_ptr = c_ptr->nodes[tipc_node(rem_node)]; + if (n_ptr) + node_remove_router(n_ptr, router); + break; + default: + assert(!"Illegal routing manager message received\n"); + } + buf_discard(buf); +} + +void cluster_remove_as_router(struct cluster *c_ptr, u32 router) +{ + u32 start_entry; + u32 tstop; + u32 n_num; + + if (is_slave(router)) + return; /* Slave nodes can not be routers */ + + if (in_own_cluster(c_ptr->addr)) { + start_entry = LOWEST_SLAVE; + tstop = c_ptr->highest_slave; + } else { + start_entry = 1; + tstop = c_ptr->highest_node; + } + + for (n_num = start_entry; n_num <= tstop; n_num++) { + if (c_ptr->nodes[n_num]) { + node_remove_router(c_ptr->nodes[n_num], router); + } + } +} + +/** + * cluster_multicast - multicast message to local nodes + */ + +void cluster_multicast(struct cluster *c_ptr, struct sk_buff *buf, + u32 lower, u32 upper) +{ + struct sk_buff *buf_copy; + struct node *n_ptr; + u32 n_num; + u32 tstop; + + assert(lower <= upper); + assert(((lower >= 1) && (lower <= tipc_max_nodes)) || + ((lower >= LOWEST_SLAVE) && (lower <= highest_allowed_slave))); + assert(((upper >= 1) && (upper <= tipc_max_nodes)) || + ((upper >= LOWEST_SLAVE) && (upper <= highest_allowed_slave))); + assert(in_own_cluster(c_ptr->addr)); + + tstop = is_slave(upper) ? c_ptr->highest_slave : c_ptr->highest_node; + if (tstop > upper) + tstop = upper; + for (n_num = lower; n_num <= tstop; n_num++) { + n_ptr = c_ptr->nodes[n_num]; + if (n_ptr && node_has_active_links(n_ptr)) { + buf_copy = skb_copy(buf, GFP_ATOMIC); + if (buf_copy == NULL) + break; + msg_set_destnode(buf_msg(buf_copy), n_ptr->addr); + link_send(buf_copy, n_ptr->addr, n_ptr->addr); + } + } + buf_discard(buf); +} + +/** + * cluster_broadcast - broadcast message to all nodes within cluster + */ + +void cluster_broadcast(struct sk_buff *buf) +{ + struct sk_buff *buf_copy; + struct cluster *c_ptr; + struct node *n_ptr; + u32 n_num; + u32 tstart; + u32 tstop; + u32 node_type; + + if (tipc_mode == TIPC_NET_MODE) { + c_ptr = cluster_find(tipc_own_addr); + assert(in_own_cluster(c_ptr->addr)); /* For now */ + + /* Send to standard nodes, then repeat loop sending to slaves */ + tstart = 1; + tstop = c_ptr->highest_node; + for (node_type = 1; node_type <= 2; node_type++) { + for (n_num = tstart; n_num <= tstop; n_num++) { + n_ptr = c_ptr->nodes[n_num]; + if (n_ptr && node_has_active_links(n_ptr)) { + buf_copy = skb_copy(buf, GFP_ATOMIC); + if (buf_copy == NULL) + goto exit; + msg_set_destnode(buf_msg(buf_copy), + n_ptr->addr); + link_send(buf_copy, n_ptr->addr, + n_ptr->addr); + } + } + tstart = LOWEST_SLAVE; + tstop = c_ptr->highest_slave; + } + } +exit: + buf_discard(buf); +} + +int cluster_init(void) +{ + highest_allowed_slave = LOWEST_SLAVE + tipc_max_slaves; + return cluster_create(tipc_own_addr) ? TIPC_OK : -ENOMEM; +} + diff --git a/net/tipc/cluster.h b/net/tipc/cluster.h new file mode 100644 index 00000000000..1ffb095991d --- /dev/null +++ b/net/tipc/cluster.h @@ -0,0 +1,92 @@ +/* + * net/tipc/cluster.h: Include file for TIPC cluster management routines + * + * Copyright (c) 2000-2006, Ericsson AB + * Copyright (c) 2005, Wind River Systems + * All rights reserved. + * + * Redistribution and use in source and binary forms, with or without + * modification, are permitted provided that the following conditions are met: + * + * 1. Redistributions of source code must retain the above copyright + * notice, this list of conditions and the following disclaimer. + * 2. Redistributions in binary form must reproduce the above copyright + * notice, this list of conditions and the following disclaimer in the + * documentation and/or other materials provided with the distribution. + * 3. Neither the names of the copyright holders nor the names of its + * contributors may be used to endorse or promote products derived from + * this software without specific prior written permission. + * + * Alternatively, this software may be distributed under the terms of the + * GNU General Public License ("GPL") version 2 as published by the Free + * Software Foundation. + * + * THIS SOFTWARE IS PROVIDED BY THE COPYRIGHT HOLDERS AND CONTRIBUTORS "AS IS" + * AND ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT LIMITED TO, THE + * IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR A PARTICULAR PURPOSE + * ARE DISCLAIMED. IN NO EVENT SHALL THE COPYRIGHT OWNER OR CONTRIBUTORS BE + * LIABLE FOR ANY DIRECT, INDIRECT, INCIDENTAL, SPECIAL, EXEMPLARY, OR + * CONSEQUENTIAL DAMAGES (INCLUDING, BUT NOT LIMITED TO, PROCUREMENT OF + * SUBSTITUTE GOODS OR SERVICES; LOSS OF USE, DATA, OR PROFITS; OR BUSINESS + * INTERRUPTION) HOWEVER CAUSED AND ON ANY THEORY OF LIABILITY, WHETHER IN + * CONTRACT, STRICT LIABILITY, OR TORT (INCLUDING NEGLIGENCE OR OTHERWISE) + * ARISING IN ANY WAY OUT OF THE USE OF THIS SOFTWARE, EVEN IF ADVISED OF THE + * POSSIBILITY OF SUCH DAMAGE. + */ + +#ifndef _TIPC_CLUSTER_H +#define _TIPC_CLUSTER_H + +#include "addr.h" +#include "zone.h" + +#define LOWEST_SLAVE 2048u + +/** + * struct cluster - TIPC cluster structure + * @addr: network address of cluster + * @owner: pointer to zone that cluster belongs to + * @nodes: array of pointers to all nodes within cluster + * @highest_node: id of highest numbered node within cluster + * @highest_slave: (used for secondary node support) + */ + +struct cluster { + u32 addr; + struct _zone *owner; + struct node **nodes; + u32 highest_node; + u32 highest_slave; +}; + + +extern struct node **local_nodes; +extern u32 highest_allowed_slave; +extern struct node_map cluster_bcast_nodes; + +void cluster_remove_as_router(struct cluster *c_ptr, u32 router); +void cluster_send_ext_routes(struct cluster *c_ptr, u32 dest); +struct node *cluster_select_node(struct cluster *c_ptr, u32 selector); +u32 cluster_select_router(struct cluster *c_ptr, u32 ref); +void cluster_recv_routing_table(struct sk_buff *buf); +struct cluster *cluster_create(u32 addr); +void cluster_delete(struct cluster *c_ptr); +void cluster_attach_node(struct cluster *c_ptr, struct node *n_ptr); +void cluster_send_slave_routes(struct cluster *c_ptr, u32 dest); +void cluster_broadcast(struct sk_buff *buf); +int cluster_init(void); +u32 cluster_next_node(struct cluster *c_ptr, u32 addr); +void cluster_bcast_new_route(struct cluster *c_ptr, u32 dest, u32 lo, u32 hi); +void cluster_send_local_routes(struct cluster *c_ptr, u32 dest); +void cluster_bcast_lost_route(struct cluster *c_ptr, u32 dest, u32 lo, u32 hi); + +static inline struct cluster *cluster_find(u32 addr) +{ + struct _zone *z_ptr = zone_find(addr); + + if (z_ptr) + return z_ptr->clusters[1]; + return 0; +} + +#endif diff --git a/net/tipc/config.c b/net/tipc/config.c new file mode 100644 index 00000000000..8ddef4fce2c --- /dev/null +++ b/net/tipc/config.c @@ -0,0 +1,718 @@ +/* + * net/tipc/config.c: TIPC configuration management code + * + * Copyright (c) 2002-2006, Ericsson AB + * Copyright (c) 2004-2005, Wind River Systems + * All rights reserved. + * + * Redistribution and use in source and binary forms, with or without + * modification, are permitted provided that the following conditions are met: + * + * 1. Redistributions of source code must retain the above copyright + * notice, this list of conditions and the following disclaimer. + * 2. Redistributions in binary form must reproduce the above copyright + * notice, this list of conditions and the following disclaimer in the + * documentation and/or other materials provided with the distribution. + * 3. Neither the names of the copyright holders nor the names of its + * contributors may be used to endorse or promote products derived from + * this software without specific prior written permission. + * + * Alternatively, this software may be distributed under the terms of the + * GNU General Public License ("GPL") version 2 as published by the Free + * Software Foundation. + * + * THIS SOFTWARE IS PROVIDED BY THE COPYRIGHT HOLDERS AND CONTRIBUTORS "AS IS" + * AND ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT LIMITED TO, THE + * IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR A PARTICULAR PURPOSE + * ARE DISCLAIMED. IN NO EVENT SHALL THE COPYRIGHT OWNER OR CONTRIBUTORS BE + * LIABLE FOR ANY DIRECT, INDIRECT, INCIDENTAL, SPECIAL, EXEMPLARY, OR + * CONSEQUENTIAL DAMAGES (INCLUDING, BUT NOT LIMITED TO, PROCUREMENT OF + * SUBSTITUTE GOODS OR SERVICES; LOSS OF USE, DATA, OR PROFITS; OR BUSINESS + * INTERRUPTION) HOWEVER CAUSED AND ON ANY THEORY OF LIABILITY, WHETHER IN + * CONTRACT, STRICT LIABILITY, OR TORT (INCLUDING NEGLIGENCE OR OTHERWISE) + * ARISING IN ANY WAY OUT OF THE USE OF THIS SOFTWARE, EVEN IF ADVISED OF THE + * POSSIBILITY OF SUCH DAMAGE. + */ + +#include "core.h" +#include "dbg.h" +#include "bearer.h" +#include "port.h" +#include "link.h" +#include "zone.h" +#include "addr.h" +#include "name_table.h" +#include "node.h" +#include "config.h" +#include "discover.h" + +struct subscr_data { + char usr_handle[8]; + u32 domain; + u32 port_ref; + struct list_head subd_list; +}; + +struct manager { + u32 user_ref; + u32 port_ref; + u32 subscr_ref; + u32 link_subscriptions; + struct list_head link_subscribers; +}; + +static struct manager mng = { 0}; + +static spinlock_t config_lock = SPIN_LOCK_UNLOCKED; + +static const void *req_tlv_area; /* request message TLV area */ +static int req_tlv_space; /* request message TLV area size */ +static int rep_headroom; /* reply message headroom to use */ + + +void cfg_link_event(u32 addr, char *name, int up) +{ + /* TIPC DOESN'T HANDLE LINK EVENT SUBSCRIPTIONS AT THE MOMENT */ +} + + +struct sk_buff *cfg_reply_alloc(int payload_size) +{ + struct sk_buff *buf; + + buf = alloc_skb(rep_headroom + payload_size, GFP_ATOMIC); + if (buf) + skb_reserve(buf, rep_headroom); + return buf; +} + +int cfg_append_tlv(struct sk_buff *buf, int tlv_type, + void *tlv_data, int tlv_data_size) +{ + struct tlv_desc *tlv = (struct tlv_desc *)buf->tail; + int new_tlv_space = TLV_SPACE(tlv_data_size); + + if (skb_tailroom(buf) < new_tlv_space) { + dbg("cfg_append_tlv unable to append TLV\n"); + return 0; + } + skb_put(buf, new_tlv_space); + tlv->tlv_type = htons(tlv_type); + tlv->tlv_len = htons(TLV_LENGTH(tlv_data_size)); + if (tlv_data_size && tlv_data) + memcpy(TLV_DATA(tlv), tlv_data, tlv_data_size); + return 1; +} + +struct sk_buff *cfg_reply_unsigned_type(u16 tlv_type, u32 value) +{ + struct sk_buff *buf; + u32 value_net; + + buf = cfg_reply_alloc(TLV_SPACE(sizeof(value))); + if (buf) { + value_net = htonl(value); + cfg_append_tlv(buf, tlv_type, &value_net, + sizeof(value_net)); + } + return buf; +} + +struct sk_buff *cfg_reply_string_type(u16 tlv_type, char *string) +{ + struct sk_buff *buf; + int string_len = strlen(string) + 1; + + buf = cfg_reply_alloc(TLV_SPACE(string_len)); + if (buf) + cfg_append_tlv(buf, tlv_type, string, string_len); + return buf; +} + + + + +#if 0 + +/* Now obsolete code for handling commands not yet implemented the new way */ + +int tipc_cfg_cmd(const struct tipc_cmd_msg * msg, + char *data, + u32 sz, + u32 *ret_size, + struct tipc_portid *orig) +{ + int rv = -EINVAL; + u32 cmd = msg->cmd; + + *ret_size = 0; + switch (cmd) { + case TIPC_REMOVE_LINK: + case TIPC_CMD_BLOCK_LINK: + case TIPC_CMD_UNBLOCK_LINK: + if (!cfg_check_connection(orig)) + rv = link_control(msg->argv.link_name, msg->cmd, 0); + break; + case TIPC_ESTABLISH: + { + int connected; + + tipc_isconnected(mng.conn_port_ref, &connected); + if (connected || !orig) { + rv = TIPC_FAILURE; + break; + } + rv = tipc_connect2port(mng.conn_port_ref, orig); + if (rv == TIPC_OK) + orig = 0; + break; + } + case TIPC_GET_PEER_ADDRESS: + *ret_size = link_peer_addr(msg->argv.link_name, data, sz); + break; + case TIPC_GET_ROUTES: + rv = TIPC_OK; + break; + default: {} + } + if (*ret_size) + rv = TIPC_OK; + return rv; +} + +static void cfg_cmd_event(struct tipc_cmd_msg *msg, + char *data, + u32 sz, + struct tipc_portid const *orig) +{ + int rv = -EINVAL; + struct tipc_cmd_result_msg rmsg; + struct iovec msg_sect[2]; + int *arg; + + msg->cmd = ntohl(msg->cmd); + + cfg_prepare_res_msg(msg->cmd, msg->usr_handle, rv, &rmsg, msg_sect, + data, 0); + if (ntohl(msg->magic) != TIPC_MAGIC) + goto exit; + + switch (msg->cmd) { + case TIPC_CREATE_LINK: + if (!cfg_check_connection(orig)) + rv = disc_create_link(&msg->argv.create_link); + break; + case TIPC_LINK_SUBSCRIBE: + { + struct subscr_data *sub; + + if (mng.link_subscriptions > 64) + break; + sub = (struct subscr_data *)kmalloc(sizeof(*sub), + GFP_ATOMIC); + if (sub == NULL) { + warn("Memory squeeze; dropped remote link subscription\n"); + break; + } + INIT_LIST_HEAD(&sub->subd_list); + tipc_createport(mng.user_ref, + (void *)sub, + TIPC_HIGH_IMPORTANCE, + 0, + 0, + (tipc_conn_shutdown_event)cfg_linksubscr_cancel, + 0, + 0, + (tipc_conn_msg_event)cfg_linksubscr_cancel, + 0, + &sub->port_ref); + if (!sub->port_ref) { + kfree(sub); + break; + } + memcpy(sub->usr_handle,msg->usr_handle, + sizeof(sub->usr_handle)); + sub->domain = msg->argv.domain; + list_add_tail(&sub->subd_list, &mng.link_subscribers); + tipc_connect2port(sub->port_ref, orig); + rmsg.retval = TIPC_OK; + tipc_send(sub->port_ref, 2u, msg_sect); + mng.link_subscriptions++; + return; + } + default: + rv = tipc_cfg_cmd(msg, data, sz, (u32 *)&msg_sect[1].iov_len, orig); + } + exit: + rmsg.result_len = htonl(msg_sect[1].iov_len); + rmsg.retval = htonl(rv); + cfg_respond(msg_sect, 2u, orig); +} +#endif + +static struct sk_buff *cfg_enable_bearer(void) +{ + struct tipc_bearer_config *args; + + if (!TLV_CHECK(req_tlv_area, req_tlv_space, TIPC_TLV_BEARER_CONFIG)) + return cfg_reply_error_string(TIPC_CFG_TLV_ERROR); + + args = (struct tipc_bearer_config *)TLV_DATA(req_tlv_area); + if (tipc_enable_bearer(args->name, + ntohl(args->detect_scope), + ntohl(args->priority))) + return cfg_reply_error_string("unable to enable bearer"); + + return cfg_reply_none(); +} + +static struct sk_buff *cfg_disable_bearer(void) +{ + if (!TLV_CHECK(req_tlv_area, req_tlv_space, TIPC_TLV_BEARER_NAME)) + return cfg_reply_error_string(TIPC_CFG_TLV_ERROR); + + if (tipc_disable_bearer((char *)TLV_DATA(req_tlv_area))) + return cfg_reply_error_string("unable to disable bearer"); + + return cfg_reply_none(); +} + +static struct sk_buff *cfg_set_own_addr(void) +{ + u32 addr; + + if (!TLV_CHECK(req_tlv_area, req_tlv_space, TIPC_TLV_NET_ADDR)) + return cfg_reply_error_string(TIPC_CFG_TLV_ERROR); + + addr = *(u32 *)TLV_DATA(req_tlv_area); + addr = ntohl(addr); + if (addr == tipc_own_addr) + return cfg_reply_none(); + if (!addr_node_valid(addr)) + return cfg_reply_error_string(TIPC_CFG_INVALID_VALUE + " (node address)"); + if (tipc_own_addr) + return cfg_reply_error_string(TIPC_CFG_NOT_SUPPORTED + " (cannot change node address once assigned)"); + + spin_unlock_bh(&config_lock); + stop_net(); + tipc_own_addr = addr; + start_net(); + spin_lock_bh(&config_lock); + return cfg_reply_none(); +} + +static struct sk_buff *cfg_set_remote_mng(void) +{ + u32 value; + + if (!TLV_CHECK(req_tlv_area, req_tlv_space, TIPC_TLV_UNSIGNED)) + return cfg_reply_error_string(TIPC_CFG_TLV_ERROR); + + value = *(u32 *)TLV_DATA(req_tlv_area); + value = ntohl(value); + tipc_remote_management = (value != 0); + return cfg_reply_none(); +} + +static struct sk_buff *cfg_set_max_publications(void) +{ + u32 value; + + if (!TLV_CHECK(req_tlv_area, req_tlv_space, TIPC_TLV_UNSIGNED)) + return cfg_reply_error_string(TIPC_CFG_TLV_ERROR); + + value = *(u32 *)TLV_DATA(req_tlv_area); + value = ntohl(value); + if (value != delimit(value, 1, 65535)) + return cfg_reply_error_string(TIPC_CFG_INVALID_VALUE + " (max publications must be 1-65535)"); + tipc_max_publications = value; + return cfg_reply_none(); +} + +static struct sk_buff *cfg_set_max_subscriptions(void) +{ + u32 value; + + if (!TLV_CHECK(req_tlv_area, req_tlv_space, TIPC_TLV_UNSIGNED)) + return cfg_reply_error_string(TIPC_CFG_TLV_ERROR); + + value = *(u32 *)TLV_DATA(req_tlv_area); + value = ntohl(value); + if (value != delimit(value, 1, 65535)) + return cfg_reply_error_string(TIPC_CFG_INVALID_VALUE + " (max subscriptions must be 1-65535"); + tipc_max_subscriptions = value; + return cfg_reply_none(); +} + +static struct sk_buff *cfg_set_max_ports(void) +{ + int orig_mode; + u32 value; + + if (!TLV_CHECK(req_tlv_area, req_tlv_space, TIPC_TLV_UNSIGNED)) + return cfg_reply_error_string(TIPC_CFG_TLV_ERROR); + value = *(u32 *)TLV_DATA(req_tlv_area); + value = ntohl(value); + if (value != delimit(value, 127, 65535)) + return cfg_reply_error_string(TIPC_CFG_INVALID_VALUE + " (max ports must be 127-65535)"); + + if (value == tipc_max_ports) + return cfg_reply_none(); + + if (atomic_read(&tipc_user_count) > 2) + return cfg_reply_error_string(TIPC_CFG_NOT_SUPPORTED + " (cannot change max ports while TIPC users exist)"); + + spin_unlock_bh(&config_lock); + orig_mode = tipc_get_mode(); + if (orig_mode == TIPC_NET_MODE) + stop_net(); + stop_core(); + tipc_max_ports = value; + start_core(); + if (orig_mode == TIPC_NET_MODE) + start_net(); + spin_lock_bh(&config_lock); + return cfg_reply_none(); +} + +static struct sk_buff *set_net_max(int value, int *parameter) +{ + int orig_mode; + + if (value != *parameter) { + orig_mode = tipc_get_mode(); + if (orig_mode == TIPC_NET_MODE) + stop_net(); + *parameter = value; + if (orig_mode == TIPC_NET_MODE) + start_net(); + } + + return cfg_reply_none(); +} + +static struct sk_buff *cfg_set_max_zones(void) +{ + u32 value; + + if (!TLV_CHECK(req_tlv_area, req_tlv_space, TIPC_TLV_UNSIGNED)) + return cfg_reply_error_string(TIPC_CFG_TLV_ERROR); + value = *(u32 *)TLV_DATA(req_tlv_area); + value = ntohl(value); + if (value != delimit(value, 1, 255)) + return cfg_reply_error_string(TIPC_CFG_INVALID_VALUE + " (max zones must be 1-255)"); + return set_net_max(value, &tipc_max_zones); +} + +static struct sk_buff *cfg_set_max_clusters(void) +{ + u32 value; + + if (!TLV_CHECK(req_tlv_area, req_tlv_space, TIPC_TLV_UNSIGNED)) + return cfg_reply_error_string(TIPC_CFG_TLV_ERROR); + value = *(u32 *)TLV_DATA(req_tlv_area); + value = ntohl(value); + if (value != 1) + return cfg_reply_error_string(TIPC_CFG_NOT_SUPPORTED + " (max clusters fixed at 1)"); + return cfg_reply_none(); +} + +static struct sk_buff *cfg_set_max_nodes(void) +{ + u32 value; + + if (!TLV_CHECK(req_tlv_area, req_tlv_space, TIPC_TLV_UNSIGNED)) + return cfg_reply_error_string(TIPC_CFG_TLV_ERROR); + value = *(u32 *)TLV_DATA(req_tlv_area); + value = ntohl(value); + if (value != delimit(value, 8, 2047)) + return cfg_reply_error_string(TIPC_CFG_INVALID_VALUE + " (max nodes must be 8-2047)"); + return set_net_max(value, &tipc_max_nodes); +} + +static struct sk_buff *cfg_set_max_slaves(void) +{ + u32 value; + + if (!TLV_CHECK(req_tlv_area, req_tlv_space, TIPC_TLV_UNSIGNED)) + return cfg_reply_error_string(TIPC_CFG_TLV_ERROR); + value = *(u32 *)TLV_DATA(req_tlv_area); + value = ntohl(value); + if (value != 0) + return cfg_reply_error_string(TIPC_CFG_NOT_SUPPORTED + " (max secondary nodes fixed at 0)"); + return cfg_reply_none(); +} + +static struct sk_buff *cfg_set_netid(void) +{ + u32 value; + + if (!TLV_CHECK(req_tlv_area, req_tlv_space, TIPC_TLV_UNSIGNED)) + return cfg_reply_error_string(TIPC_CFG_TLV_ERROR); + value = *(u32 *)TLV_DATA(req_tlv_area); + value = ntohl(value); + if (value != delimit(value, 1, 9999)) + return cfg_reply_error_string(TIPC_CFG_INVALID_VALUE + " (network id must be 1-9999)"); + + if (tipc_own_addr) + return cfg_reply_error_string(TIPC_CFG_NOT_SUPPORTED + " (cannot change network id once part of network)"); + + return set_net_max(value, &tipc_net_id); +} + +struct sk_buff *cfg_do_cmd(u32 orig_node, u16 cmd, const void *request_area, + int request_space, int reply_headroom) +{ + struct sk_buff *rep_tlv_buf; + + spin_lock_bh(&config_lock); + + /* Save request and reply details in a well-known location */ + + req_tlv_area = request_area; + req_tlv_space = request_space; + rep_headroom = reply_headroom; + + /* Check command authorization */ + + if (likely(orig_node == tipc_own_addr)) { + /* command is permitted */ + } else if (cmd >= 0x8000) { + rep_tlv_buf = cfg_reply_error_string(TIPC_CFG_NOT_SUPPORTED + " (cannot be done remotely)"); + goto exit; + } else if (!tipc_remote_management) { + rep_tlv_buf = cfg_reply_error_string(TIPC_CFG_NO_REMOTE); + goto exit; + } + else if (cmd >= 0x4000) { + u32 domain = 0; + + if ((nametbl_translate(TIPC_ZM_SRV, 0, &domain) == 0) || + (domain != orig_node)) { + rep_tlv_buf = cfg_reply_error_string(TIPC_CFG_NOT_ZONE_MSTR); + goto exit; + } + } + + /* Call appropriate processing routine */ + + switch (cmd) { + case TIPC_CMD_NOOP: + rep_tlv_buf = cfg_reply_none(); + break; + case TIPC_CMD_GET_NODES: + rep_tlv_buf = node_get_nodes(req_tlv_area, req_tlv_space); + break; + case TIPC_CMD_GET_LINKS: + rep_tlv_buf = node_get_links(req_tlv_area, req_tlv_space); + break; + case TIPC_CMD_SHOW_LINK_STATS: + rep_tlv_buf = link_cmd_show_stats(req_tlv_area, req_tlv_space); + break; + case TIPC_CMD_RESET_LINK_STATS: + rep_tlv_buf = link_cmd_reset_stats(req_tlv_area, req_tlv_space); + break; + case TIPC_CMD_SHOW_NAME_TABLE: + rep_tlv_buf = nametbl_get(req_tlv_area, req_tlv_space); + break; + case TIPC_CMD_GET_BEARER_NAMES: + rep_tlv_buf = bearer_get_names(); + break; + case TIPC_CMD_GET_MEDIA_NAMES: + rep_tlv_buf = media_get_names(); + break; + case TIPC_CMD_SHOW_PORTS: + rep_tlv_buf = port_get_ports(); + break; +#if 0 + case TIPC_CMD_SHOW_PORT_STATS: + rep_tlv_buf = port_show_stats(req_tlv_area, req_tlv_space); + break; + case TIPC_CMD_RESET_PORT_STATS: + rep_tlv_buf = cfg_reply_error_string(TIPC_CFG_NOT_SUPPORTED); + break; +#endif + case TIPC_CMD_SET_LOG_SIZE: + rep_tlv_buf = log_resize(req_tlv_area, req_tlv_space); + break; + case TIPC_CMD_DUMP_LOG: + rep_tlv_buf = log_dump(); + break; + case TIPC_CMD_SET_LINK_TOL: + case TIPC_CMD_SET_LINK_PRI: + case TIPC_CMD_SET_LINK_WINDOW: + rep_tlv_buf = link_cmd_config(req_tlv_area, req_tlv_space, cmd); + break; + case TIPC_CMD_ENABLE_BEARER: + rep_tlv_buf = cfg_enable_bearer(); + break; + case TIPC_CMD_DISABLE_BEARER: + rep_tlv_buf = cfg_disable_bearer(); + break; + case TIPC_CMD_SET_NODE_ADDR: + rep_tlv_buf = cfg_set_own_addr(); + break; + case TIPC_CMD_SET_REMOTE_MNG: + rep_tlv_buf = cfg_set_remote_mng(); + break; + case TIPC_CMD_SET_MAX_PORTS: + rep_tlv_buf = cfg_set_max_ports(); + break; + case TIPC_CMD_SET_MAX_PUBL: + rep_tlv_buf = cfg_set_max_publications(); + break; + case TIPC_CMD_SET_MAX_SUBSCR: + rep_tlv_buf = cfg_set_max_subscriptions(); + break; + case TIPC_CMD_SET_MAX_ZONES: + rep_tlv_buf = cfg_set_max_zones(); + break; + case TIPC_CMD_SET_MAX_CLUSTERS: + rep_tlv_buf = cfg_set_max_clusters(); + break; + case TIPC_CMD_SET_MAX_NODES: + rep_tlv_buf = cfg_set_max_nodes(); + break; + case TIPC_CMD_SET_MAX_SLAVES: + rep_tlv_buf = cfg_set_max_slaves(); + break; + case TIPC_CMD_SET_NETID: + rep_tlv_buf = cfg_set_netid(); + break; + case TIPC_CMD_GET_REMOTE_MNG: + rep_tlv_buf = cfg_reply_unsigned(tipc_remote_management); + break; + case TIPC_CMD_GET_MAX_PORTS: + rep_tlv_buf = cfg_reply_unsigned(tipc_max_ports); + break; + case TIPC_CMD_GET_MAX_PUBL: + rep_tlv_buf = cfg_reply_unsigned(tipc_max_publications); + break; + case TIPC_CMD_GET_MAX_SUBSCR: + rep_tlv_buf = cfg_reply_unsigned(tipc_max_subscriptions); + break; + case TIPC_CMD_GET_MAX_ZONES: + rep_tlv_buf = cfg_reply_unsigned(tipc_max_zones); + break; + case TIPC_CMD_GET_MAX_CLUSTERS: + rep_tlv_buf = cfg_reply_unsigned(tipc_max_clusters); + break; + case TIPC_CMD_GET_MAX_NODES: + rep_tlv_buf = cfg_reply_unsigned(tipc_max_nodes); + break; + case TIPC_CMD_GET_MAX_SLAVES: + rep_tlv_buf = cfg_reply_unsigned(tipc_max_slaves); + break; + case TIPC_CMD_GET_NETID: + rep_tlv_buf = cfg_reply_unsigned(tipc_net_id); + break; + default: + rep_tlv_buf = NULL; + break; + } + + /* Return reply buffer */ +exit: + spin_unlock_bh(&config_lock); + return rep_tlv_buf; +} + +static void cfg_named_msg_event(void *userdata, + u32 port_ref, + struct sk_buff **buf, + const unchar *msg, + u32 size, + u32 importance, + struct tipc_portid const *orig, + struct tipc_name_seq const *dest) +{ + struct tipc_cfg_msg_hdr *req_hdr; + struct tipc_cfg_msg_hdr *rep_hdr; + struct sk_buff *rep_buf; + + /* Validate configuration message header (ignore invalid message) */ + + req_hdr = (struct tipc_cfg_msg_hdr *)msg; + if ((size < sizeof(*req_hdr)) || + (size != TCM_ALIGN(ntohl(req_hdr->tcm_len))) || + (ntohs(req_hdr->tcm_flags) != TCM_F_REQUEST)) { + warn("discarded invalid configuration message\n"); + return; + } + + /* Generate reply for request (if can't, return request) */ + + rep_buf = cfg_do_cmd(orig->node, + ntohs(req_hdr->tcm_type), + msg + sizeof(*req_hdr), + size - sizeof(*req_hdr), + BUF_HEADROOM + MAX_H_SIZE + sizeof(*rep_hdr)); + if (rep_buf) { + skb_push(rep_buf, sizeof(*rep_hdr)); + rep_hdr = (struct tipc_cfg_msg_hdr *)rep_buf->data; + memcpy(rep_hdr, req_hdr, sizeof(*rep_hdr)); + rep_hdr->tcm_len = htonl(rep_buf->len); + rep_hdr->tcm_flags &= htons(~TCM_F_REQUEST); + } else { + rep_buf = *buf; + *buf = NULL; + } + + /* NEED TO ADD CODE TO HANDLE FAILED SEND (SUCH AS CONGESTION) */ + tipc_send_buf2port(port_ref, orig, rep_buf, rep_buf->len); +} + +int cfg_init(void) +{ + struct tipc_name_seq seq; + int res; + + memset(&mng, 0, sizeof(mng)); + INIT_LIST_HEAD(&mng.link_subscribers); + + res = tipc_attach(&mng.user_ref, 0, 0); + if (res) + goto failed; + + res = tipc_createport(mng.user_ref, 0, TIPC_CRITICAL_IMPORTANCE, + NULL, NULL, NULL, + NULL, cfg_named_msg_event, NULL, + NULL, &mng.port_ref); + if (res) + goto failed; + + seq.type = TIPC_CFG_SRV; + seq.lower = seq.upper = tipc_own_addr; + res = nametbl_publish_rsv(mng.port_ref, TIPC_ZONE_SCOPE, &seq); + if (res) + goto failed; + + return 0; + +failed: + err("Unable to create configuration service\n"); + tipc_detach(mng.user_ref); + mng.user_ref = 0; + return res; +} + +void cfg_stop(void) +{ + if (mng.user_ref) { + tipc_detach(mng.user_ref); + mng.user_ref = 0; + } +} diff --git a/net/tipc/config.h b/net/tipc/config.h new file mode 100644 index 00000000000..646377d4045 --- /dev/null +++ b/net/tipc/config.h @@ -0,0 +1,80 @@ +/* + * net/tipc/config.h: Include file for TIPC configuration service code + * + * Copyright (c) 2003-2006, Ericsson AB + * Copyright (c) 2005, Wind River Systems + * All rights reserved. + * + * Redistribution and use in source and binary forms, with or without + * modification, are permitted provided that the following conditions are met: + * + * 1. Redistributions of source code must retain the above copyright + * notice, this list of conditions and the following disclaimer. + * 2. Redistributions in binary form must reproduce the above copyright + * notice, this list of conditions and the following disclaimer in the + * documentation and/or other materials provided with the distribution. + * 3. Neither the names of the copyright holders nor the names of its + * contributors may be used to endorse or promote products derived from + * this software without specific prior written permission. + * + * Alternatively, this software may be distributed under the terms of the + * GNU General Public License ("GPL") version 2 as published by the Free + * Software Foundation. + * + * THIS SOFTWARE IS PROVIDED BY THE COPYRIGHT HOLDERS AND CONTRIBUTORS "AS IS" + * AND ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT LIMITED TO, THE + * IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR A PARTICULAR PURPOSE + * ARE DISCLAIMED. IN NO EVENT SHALL THE COPYRIGHT OWNER OR CONTRIBUTORS BE + * LIABLE FOR ANY DIRECT, INDIRECT, INCIDENTAL, SPECIAL, EXEMPLARY, OR + * CONSEQUENTIAL DAMAGES (INCLUDING, BUT NOT LIMITED TO, PROCUREMENT OF + * SUBSTITUTE GOODS OR SERVICES; LOSS OF USE, DATA, OR PROFITS; OR BUSINESS + * INTERRUPTION) HOWEVER CAUSED AND ON ANY THEORY OF LIABILITY, WHETHER IN + * CONTRACT, STRICT LIABILITY, OR TORT (INCLUDING NEGLIGENCE OR OTHERWISE) + * ARISING IN ANY WAY OUT OF THE USE OF THIS SOFTWARE, EVEN IF ADVISED OF THE + * POSSIBILITY OF SUCH DAMAGE. + */ + +#ifndef _TIPC_CONFIG_H +#define _TIPC_CONFIG_H + +/* ---------------------------------------------------------------------- */ + +#include <linux/tipc.h> +#include <linux/tipc_config.h> +#include "link.h" + +struct sk_buff *cfg_reply_alloc(int payload_size); +int cfg_append_tlv(struct sk_buff *buf, int tlv_type, + void *tlv_data, int tlv_data_size); +struct sk_buff *cfg_reply_unsigned_type(u16 tlv_type, u32 value); +struct sk_buff *cfg_reply_string_type(u16 tlv_type, char *string); + +static inline struct sk_buff *cfg_reply_none(void) +{ + return cfg_reply_alloc(0); +} + +static inline struct sk_buff *cfg_reply_unsigned(u32 value) +{ + return cfg_reply_unsigned_type(TIPC_TLV_UNSIGNED, value); +} + +static inline struct sk_buff *cfg_reply_error_string(char *string) +{ + return cfg_reply_string_type(TIPC_TLV_ERROR_STRING, string); +} + +static inline struct sk_buff *cfg_reply_ultra_string(char *string) +{ + return cfg_reply_string_type(TIPC_TLV_ULTRA_STRING, string); +} + +struct sk_buff *cfg_do_cmd(u32 orig_node, u16 cmd, + const void *req_tlv_area, int req_tlv_space, + int headroom); + +void cfg_link_event(u32 addr, char *name, int up); +int cfg_init(void); +void cfg_stop(void); + +#endif diff --git a/net/tipc/core.c b/net/tipc/core.c new file mode 100644 index 00000000000..e83ac06e31b --- /dev/null +++ b/net/tipc/core.c @@ -0,0 +1,285 @@ +/* + * net/tipc/core.c: TIPC module code + * + * Copyright (c) 2003-2006, Ericsson AB + * Copyright (c) 2005, Wind River Systems + * All rights reserved. + * + * Redistribution and use in source and binary forms, with or without + * modification, are permitted provided that the following conditions are met: + * + * 1. Redistributions of source code must retain the above copyright + * notice, this list of conditions and the following disclaimer. + * 2. Redistributions in binary form must reproduce the above copyright + * notice, this list of conditions and the following disclaimer in the + * documentation and/or other materials provided with the distribution. + * 3. Neither the names of the copyright holders nor the names of its + * contributors may be used to endorse or promote products derived from + * this software without specific prior written permission. + * + * Alternatively, this software may be distributed under the terms of the + * GNU General Public License ("GPL") version 2 as published by the Free + * Software Foundation. + * + * THIS SOFTWARE IS PROVIDED BY THE COPYRIGHT HOLDERS AND CONTRIBUTORS "AS IS" + * AND ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT LIMITED TO, THE + * IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR A PARTICULAR PURPOSE + * ARE DISCLAIMED. IN NO EVENT SHALL THE COPYRIGHT OWNER OR CONTRIBUTORS BE + * LIABLE FOR ANY DIRECT, INDIRECT, INCIDENTAL, SPECIAL, EXEMPLARY, OR + * CONSEQUENTIAL DAMAGES (INCLUDING, BUT NOT LIMITED TO, PROCUREMENT OF + * SUBSTITUTE GOODS OR SERVICES; LOSS OF USE, DATA, OR PROFITS; OR BUSINESS + * INTERRUPTION) HOWEVER CAUSED AND ON ANY THEORY OF LIABILITY, WHETHER IN + * CONTRACT, STRICT LIABILITY, OR TORT (INCLUDING NEGLIGENCE OR OTHERWISE) + * ARISING IN ANY WAY OUT OF THE USE OF THIS SOFTWARE, EVEN IF ADVISED OF THE + * POSSIBILITY OF SUCH DAMAGE. + */ + +#include <linux/init.h> +#include <linux/module.h> +#include <linux/kernel.h> +#include <linux/version.h> +#include <linux/random.h> + +#include "core.h" +#include "dbg.h" +#include "ref.h" +#include "net.h" +#include "user_reg.h" +#include "name_table.h" +#include "subscr.h" +#include "config.h" + +int eth_media_start(void); +void eth_media_stop(void); +int handler_start(void); +void handler_stop(void); +int socket_init(void); +void socket_stop(void); +int netlink_start(void); +void netlink_stop(void); + +#define MOD_NAME "tipc_start: " + +#ifndef CONFIG_TIPC_ZONES +#define CONFIG_TIPC_ZONES 3 +#endif + +#ifndef CONFIG_TIPC_CLUSTERS +#define CONFIG_TIPC_CLUSTERS 1 +#endif + +#ifndef CONFIG_TIPC_NODES +#define CONFIG_TIPC_NODES 255 +#endif + +#ifndef CONFIG_TIPC_SLAVE_NODES +#define CONFIG_TIPC_SLAVE_NODES 0 +#endif + +#ifndef CONFIG_TIPC_PORTS +#define CONFIG_TIPC_PORTS 8191 +#endif + +#ifndef CONFIG_TIPC_LOG +#define CONFIG_TIPC_LOG 0 +#endif + +/* global variables used by multiple sub-systems within TIPC */ + +int tipc_mode = TIPC_NOT_RUNNING; +int tipc_random; +atomic_t tipc_user_count = ATOMIC_INIT(0); + +const char tipc_alphabet[] = + "ABCDEFGHIJKLMNOPQRSTUVWXYZabcdefghijklmnopqrstuvwxyz0123456789_"; + +/* configurable TIPC parameters */ + +u32 tipc_own_addr; +int tipc_max_zones; +int tipc_max_clusters; +int tipc_max_nodes; +int tipc_max_slaves; +int tipc_max_ports; +int tipc_max_subscriptions; +int tipc_max_publications; +int tipc_net_id; +int tipc_remote_management; + + +int tipc_get_mode(void) +{ + return tipc_mode; +} + +/** + * stop_net - shut down TIPC networking sub-systems + */ + +void stop_net(void) +{ + eth_media_stop(); + tipc_stop_net(); +} + +/** + * start_net - start TIPC networking sub-systems + */ + +int start_net(void) +{ + int res; + + if ((res = tipc_start_net()) || + (res = eth_media_start())) { + stop_net(); + } + return res; +} + +/** + * stop_core - switch TIPC from SINGLE NODE to NOT RUNNING mode + */ + +void stop_core(void) +{ + if (tipc_mode != TIPC_NODE_MODE) + return; + + tipc_mode = TIPC_NOT_RUNNING; + + netlink_stop(); + handler_stop(); + cfg_stop(); + subscr_stop(); + reg_stop(); + nametbl_stop(); + ref_table_stop(); + socket_stop(); +} + +/** + * start_core - switch TIPC from NOT RUNNING to SINGLE NODE mode + */ + +int start_core(void) +{ + int res; + + if (tipc_mode != TIPC_NOT_RUNNING) + return -ENOPROTOOPT; + + get_random_bytes(&tipc_random, sizeof(tipc_random)); + tipc_mode = TIPC_NODE_MODE; + + if ((res = handler_start()) || + (res = ref_table_init(tipc_max_ports + tipc_max_subscriptions, + tipc_random)) || + (res = reg_start()) || + (res = nametbl_init()) || + (res = k_signal((Handler)subscr_start, 0)) || + (res = k_signal((Handler)cfg_init, 0)) || + (res = netlink_start()) || + (res = socket_init())) { + stop_core(); + } + return res; +} + + +static int __init tipc_init(void) +{ + int res; + + log_reinit(CONFIG_TIPC_LOG); + info("Activated (compiled " __DATE__ " " __TIME__ ")\n"); + + tipc_own_addr = 0; + tipc_remote_management = 1; + tipc_max_publications = 10000; + tipc_max_subscriptions = 2000; + tipc_max_ports = delimit(CONFIG_TIPC_PORTS, 127, 65536); + tipc_max_zones = delimit(CONFIG_TIPC_ZONES, 1, 511); + tipc_max_clusters = delimit(CONFIG_TIPC_CLUSTERS, 1, 1); + tipc_max_nodes = delimit(CONFIG_TIPC_NODES, 8, 2047); + tipc_max_slaves = delimit(CONFIG_TIPC_SLAVE_NODES, 0, 2047); + tipc_net_id = 4711; + + if ((res = start_core())) + err("Unable to start in single node mode\n"); + else + info("Started in single node mode\n"); + return res; +} + +static void __exit tipc_exit(void) +{ + stop_net(); + stop_core(); + info("Deactivated\n"); + log_stop(); +} + +module_init(tipc_init); +module_exit(tipc_exit); + +MODULE_DESCRIPTION("TIPC: Transparent Inter Process Communication"); +MODULE_LICENSE("Dual BSD/GPL"); + +/* Native TIPC API for kernel-space applications (see tipc.h) */ + +EXPORT_SYMBOL(tipc_attach); +EXPORT_SYMBOL(tipc_detach); +EXPORT_SYMBOL(tipc_get_addr); +EXPORT_SYMBOL(tipc_get_mode); +EXPORT_SYMBOL(tipc_createport); +EXPORT_SYMBOL(tipc_deleteport); +EXPORT_SYMBOL(tipc_ownidentity); +EXPORT_SYMBOL(tipc_portimportance); +EXPORT_SYMBOL(tipc_set_portimportance); +EXPORT_SYMBOL(tipc_portunreliable); +EXPORT_SYMBOL(tipc_set_portunreliable); +EXPORT_SYMBOL(tipc_portunreturnable); +EXPORT_SYMBOL(tipc_set_portunreturnable); +EXPORT_SYMBOL(tipc_publish); +EXPORT_SYMBOL(tipc_withdraw); +EXPORT_SYMBOL(tipc_connect2port); +EXPORT_SYMBOL(tipc_disconnect); +EXPORT_SYMBOL(tipc_shutdown); +EXPORT_SYMBOL(tipc_isconnected); +EXPORT_SYMBOL(tipc_peer); +EXPORT_SYMBOL(tipc_ref_valid); +EXPORT_SYMBOL(tipc_send); +EXPORT_SYMBOL(tipc_send_buf); +EXPORT_SYMBOL(tipc_send2name); +EXPORT_SYMBOL(tipc_forward2name); +EXPORT_SYMBOL(tipc_send_buf2name); +EXPORT_SYMBOL(tipc_forward_buf2name); +EXPORT_SYMBOL(tipc_send2port); +EXPORT_SYMBOL(tipc_forward2port); +EXPORT_SYMBOL(tipc_send_buf2port); +EXPORT_SYMBOL(tipc_forward_buf2port); +EXPORT_SYMBOL(tipc_multicast); +/* EXPORT_SYMBOL(tipc_multicast_buf); not available yet */ +EXPORT_SYMBOL(tipc_ispublished); +EXPORT_SYMBOL(tipc_available_nodes); + +/* TIPC API for external bearers (see tipc_bearer.h) */ + +EXPORT_SYMBOL(tipc_block_bearer); +EXPORT_SYMBOL(tipc_continue); +EXPORT_SYMBOL(tipc_disable_bearer); +EXPORT_SYMBOL(tipc_enable_bearer); +EXPORT_SYMBOL(tipc_recv_msg); +EXPORT_SYMBOL(tipc_register_media); + +/* TIPC API for external APIs (see tipc_port.h) */ + +EXPORT_SYMBOL(tipc_createport_raw); +EXPORT_SYMBOL(tipc_set_msg_option); +EXPORT_SYMBOL(tipc_reject_msg); +EXPORT_SYMBOL(tipc_send_buf_fast); +EXPORT_SYMBOL(tipc_acknowledge); +EXPORT_SYMBOL(tipc_get_port); +EXPORT_SYMBOL(tipc_get_handle); + diff --git a/net/tipc/core.h b/net/tipc/core.h new file mode 100644 index 00000000000..b69b60b2cc8 --- /dev/null +++ b/net/tipc/core.h @@ -0,0 +1,316 @@ +/* + * net/tipc/core.h: Include file for TIPC global declarations + * + * Copyright (c) 2005-2006, Ericsson AB + * Copyright (c) 2005, Wind River Systems + * All rights reserved. + * + * Redistribution and use in source and binary forms, with or without + * modification, are permitted provided that the following conditions are met: + * + * 1. Redistributions of source code must retain the above copyright + * notice, this list of conditions and the following disclaimer. + * 2. Redistributions in binary form must reproduce the above copyright + * notice, this list of conditions and the following disclaimer in the + * documentation and/or other materials provided with the distribution. + * 3. Neither the names of the copyright holders nor the names of its + * contributors may be used to endorse or promote products derived from + * this software without specific prior written permission. + * + * Alternatively, this software may be distributed under the terms of the + * GNU General Public License ("GPL") version 2 as published by the Free + * Software Foundation. + * + * THIS SOFTWARE IS PROVIDED BY THE COPYRIGHT HOLDERS AND CONTRIBUTORS "AS IS" + * AND ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT LIMITED TO, THE + * IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR A PARTICULAR PURPOSE + * ARE DISCLAIMED. IN NO EVENT SHALL THE COPYRIGHT OWNER OR CONTRIBUTORS BE + * LIABLE FOR ANY DIRECT, INDIRECT, INCIDENTAL, SPECIAL, EXEMPLARY, OR + * CONSEQUENTIAL DAMAGES (INCLUDING, BUT NOT LIMITED TO, PROCUREMENT OF + * SUBSTITUTE GOODS OR SERVICES; LOSS OF USE, DATA, OR PROFITS; OR BUSINESS + * INTERRUPTION) HOWEVER CAUSED AND ON ANY THEORY OF LIABILITY, WHETHER IN + * CONTRACT, STRICT LIABILITY, OR TORT (INCLUDING NEGLIGENCE OR OTHERWISE) + * ARISING IN ANY WAY OUT OF THE USE OF THIS SOFTWARE, EVEN IF ADVISED OF THE + * POSSIBILITY OF SUCH DAMAGE. + */ + +#ifndef _TIPC_CORE_H +#define _TIPC_CORE_H + +#include <net/tipc/tipc.h> +#include <linux/types.h> +#include <linux/kernel.h> +#include <linux/errno.h> +#include <linux/mm.h> +#include <linux/timer.h> +#include <linux/string.h> +#include <asm/uaccess.h> +#include <linux/interrupt.h> +#include <asm/atomic.h> +#include <asm/hardirq.h> +#include <linux/netdevice.h> +#include <linux/in.h> +#include <linux/list.h> +#include <linux/vmalloc.h> + +/* + * TIPC debugging code + */ + +#define assert(i) BUG_ON(!(i)) + +struct tipc_msg; +extern struct print_buf *CONS, *LOG; +extern struct print_buf *TEE(struct print_buf *, struct print_buf *); +void msg_print(struct print_buf*,struct tipc_msg *,const char*); +void tipc_printf(struct print_buf *, const char *fmt, ...); +void tipc_dump(struct print_buf*,const char *fmt, ...); + +#ifdef CONFIG_TIPC_DEBUG + +/* + * TIPC debug support included: + * - system messages are printed to TIPC_OUTPUT print buffer + * - debug messages are printed to DBG_OUTPUT print buffer + */ + +#define err(fmt, arg...) tipc_printf(TIPC_OUTPUT, KERN_ERR "TIPC: " fmt, ## arg) +#define warn(fmt, arg...) tipc_printf(TIPC_OUTPUT, KERN_WARNING "TIPC: " fmt, ## arg) +#define info(fmt, arg...) tipc_printf(TIPC_OUTPUT, KERN_NOTICE "TIPC: " fmt, ## arg) + +#define dbg(fmt, arg...) do {if (DBG_OUTPUT) tipc_printf(DBG_OUTPUT, fmt, ## arg);} while(0) +#define msg_dbg(msg, txt) do {if (DBG_OUTPUT) msg_print(DBG_OUTPUT, msg, txt);} while(0) +#define dump(fmt, arg...) do {if (DBG_OUTPUT) tipc_dump(DBG_OUTPUT, fmt, ##arg);} while(0) + + +/* + * By default, TIPC_OUTPUT is defined to be system console and TIPC log buffer, + * while DBG_OUTPUT is the null print buffer. These defaults can be changed + * here, or on a per .c file basis, by redefining these symbols. The following + * print buffer options are available: + * + * NULL : Output to null print buffer (i.e. print nowhere) + * CONS : Output to system console + * LOG : Output to TIPC log buffer + * &buf : Output to user-defined buffer (struct print_buf *) + * TEE(&buf_a,&buf_b) : Output to two print buffers (eg. TEE(CONS,LOG) ) + */ + +#ifndef TIPC_OUTPUT +#define TIPC_OUTPUT TEE(CONS,LOG) +#endif + +#ifndef DBG_OUTPUT +#define DBG_OUTPUT NULL +#endif + +#else + +#ifndef DBG_OUTPUT +#define DBG_OUTPUT NULL +#endif + +/* + * TIPC debug support not included: + * - system messages are printed to system console + * - debug messages are not printed + */ + +#define err(fmt, arg...) printk(KERN_ERR "TIPC: " fmt , ## arg) +#define info(fmt, arg...) printk(KERN_INFO "TIPC: " fmt , ## arg) +#define warn(fmt, arg...) printk(KERN_WARNING "TIPC: " fmt , ## arg) + +#define dbg(fmt, arg...) do {} while (0) +#define msg_dbg(msg,txt) do {} while (0) +#define dump(fmt,arg...) do {} while (0) + +#endif + + +/* + * TIPC-specific error codes + */ + +#define ELINKCONG EAGAIN /* link congestion <=> resource unavailable */ + +/* + * Global configuration variables + */ + +extern u32 tipc_own_addr; +extern int tipc_max_zones; +extern int tipc_max_clusters; +extern int tipc_max_nodes; +extern int tipc_max_slaves; +extern int tipc_max_ports; +extern int tipc_max_subscriptions; +extern int tipc_max_publications; +extern int tipc_net_id; +extern int tipc_remote_management; + +/* + * Other global variables + */ + +extern int tipc_mode; +extern int tipc_random; +extern const char tipc_alphabet[]; +extern atomic_t tipc_user_count; + + +/* + * Routines available to privileged subsystems + */ + +extern int start_core(void); +extern void stop_core(void); +extern int start_net(void); +extern void stop_net(void); + +static inline int delimit(int val, int min, int max) +{ + if (val > max) + return max; + if (val < min) + return min; + return val; +} + + +/* + * TIPC timer and signal code + */ + +typedef void (*Handler) (unsigned long); + +u32 k_signal(Handler routine, unsigned long argument); + +/** + * k_init_timer - initialize a timer + * @timer: pointer to timer structure + * @routine: pointer to routine to invoke when timer expires + * @argument: value to pass to routine when timer expires + * + * Timer must be initialized before use (and terminated when no longer needed). + */ + +static inline void k_init_timer(struct timer_list *timer, Handler routine, + unsigned long argument) +{ + dbg("initializing timer %p\n", timer); + init_timer(timer); + timer->function = routine; + timer->data = argument; +} + +/** + * k_start_timer - start a timer + * @timer: pointer to timer structure + * @msec: time to delay (in ms) + * + * Schedules a previously initialized timer for later execution. + * If timer is already running, the new timeout overrides the previous request. + * + * To ensure the timer doesn't expire before the specified delay elapses, + * the amount of delay is rounded up when converting to the jiffies + * then an additional jiffy is added to account for the fact that + * the starting time may be in the middle of the current jiffy. + */ + +static inline void k_start_timer(struct timer_list *timer, unsigned long msec) +{ + dbg("starting timer %p for %u\n", timer, msec); + mod_timer(timer, jiffies + msecs_to_jiffies(msec) + 1); +} + +/** + * k_cancel_timer - cancel a timer + * @timer: pointer to timer structure + * + * Cancels a previously initialized timer. + * Can be called safely even if the timer is already inactive. + * + * WARNING: Must not be called when holding locks required by the timer's + * timeout routine, otherwise deadlock can occur on SMP systems! + */ + +static inline void k_cancel_timer(struct timer_list *timer) +{ + dbg("cancelling timer %p\n", timer); + del_timer_sync(timer); +} + +/** + * k_term_timer - terminate a timer + * @timer: pointer to timer structure + * + * Prevents further use of a previously initialized timer. + * + * WARNING: Caller must ensure timer isn't currently running. + * + * (Do not "enhance" this routine to automatically cancel an active timer, + * otherwise deadlock can arise when a timeout routine calls k_term_timer.) + */ + +static inline void k_term_timer(struct timer_list *timer) +{ + dbg("terminating timer %p\n", timer); +} + + +/* + * TIPC message buffer code + * + * TIPC message buffer headroom leaves room for 14 byte Ethernet header, + * while ensuring TIPC header is word aligned for quicker access + */ + +#define BUF_HEADROOM 16u + +struct tipc_skb_cb { + void *handle; +}; + +#define TIPC_SKB_CB(__skb) ((struct tipc_skb_cb *)&((__skb)->cb[0])) + + +static inline struct tipc_msg *buf_msg(struct sk_buff *skb) +{ + return (struct tipc_msg *)skb->data; +} + +/** + * buf_acquire - creates a TIPC message buffer + * @size: message size (including TIPC header) + * + * Returns a new buffer. Space is reserved for a data link header. + */ + +static inline struct sk_buff *buf_acquire(u32 size) +{ + struct sk_buff *skb; + unsigned int buf_size = (BUF_HEADROOM + size + 3) & ~3u; + + skb = alloc_skb(buf_size, GFP_ATOMIC); + if (skb) { + skb_reserve(skb, BUF_HEADROOM); + skb_put(skb, size); + skb->next = NULL; + } + return skb; +} + +/** + * buf_discard - frees a TIPC message buffer + * @skb: message buffer + * + * Frees a new buffer. If passed NULL, just returns. + */ + +static inline void buf_discard(struct sk_buff *skb) +{ + if (likely(skb != NULL)) + kfree_skb(skb); +} + +#endif diff --git a/net/tipc/dbg.c b/net/tipc/dbg.c new file mode 100644 index 00000000000..7ed60a1cfbb --- /dev/null +++ b/net/tipc/dbg.c @@ -0,0 +1,395 @@ +/* + * net/tipc/dbg.c: TIPC print buffer routines for debuggign + * + * Copyright (c) 1996-2006, Ericsson AB + * Copyright (c) 2005, Wind River Systems + * All rights reserved. + * + * Redistribution and use in source and binary forms, with or without + * modification, are permitted provided that the following conditions are met: + * + * 1. Redistributions of source code must retain the above copyright + * notice, this list of conditions and the following disclaimer. + * 2. Redistributions in binary form must reproduce the above copyright + * notice, this list of conditions and the following disclaimer in the + * documentation and/or other materials provided with the distribution. + * 3. Neither the names of the copyright holders nor the names of its + * contributors may be used to endorse or promote products derived from + * this software without specific prior written permission. + * + * Alternatively, this software may be distributed under the terms of the + * GNU General Public License ("GPL") version 2 as published by the Free + * Software Foundation. + * + * THIS SOFTWARE IS PROVIDED BY THE COPYRIGHT HOLDERS AND CONTRIBUTORS "AS IS" + * AND ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT LIMITED TO, THE + * IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR A PARTICULAR PURPOSE + * ARE DISCLAIMED. IN NO EVENT SHALL THE COPYRIGHT OWNER OR CONTRIBUTORS BE + * LIABLE FOR ANY DIRECT, INDIRECT, INCIDENTAL, SPECIAL, EXEMPLARY, OR + * CONSEQUENTIAL DAMAGES (INCLUDING, BUT NOT LIMITED TO, PROCUREMENT OF + * SUBSTITUTE GOODS OR SERVICES; LOSS OF USE, DATA, OR PROFITS; OR BUSINESS + * INTERRUPTION) HOWEVER CAUSED AND ON ANY THEORY OF LIABILITY, WHETHER IN + * CONTRACT, STRICT LIABILITY, OR TORT (INCLUDING NEGLIGENCE OR OTHERWISE) + * ARISING IN ANY WAY OUT OF THE USE OF THIS SOFTWARE, EVEN IF ADVISED OF THE + * POSSIBILITY OF SUCH DAMAGE. + */ + +#include "core.h" +#include "config.h" +#include "dbg.h" + +#define MAX_STRING 512 + +static char print_string[MAX_STRING]; +static spinlock_t print_lock = SPIN_LOCK_UNLOCKED; + +static struct print_buf cons_buf = { NULL, 0, NULL, NULL }; +struct print_buf *CONS = &cons_buf; + +static struct print_buf log_buf = { NULL, 0, NULL, NULL }; +struct print_buf *LOG = &log_buf; + + +#define FORMAT(PTR,LEN,FMT) \ +{\ + va_list args;\ + va_start(args, FMT);\ + LEN = vsprintf(PTR, FMT, args);\ + va_end(args);\ + *(PTR + LEN) = '\0';\ +} + +/* + * Locking policy when using print buffers. + * + * 1) Routines of the form printbuf_XXX() rely on the caller to prevent + * simultaneous use of the print buffer(s) being manipulated. + * 2) tipc_printf() uses 'print_lock' to prevent simultaneous use of + * 'print_string' and to protect its print buffer(s). + * 3) TEE() uses 'print_lock' to protect its print buffer(s). + * 4) Routines of the form log_XXX() uses 'print_lock' to protect LOG. + */ + +/** + * printbuf_init - initialize print buffer to empty + */ + +void printbuf_init(struct print_buf *pb, char *raw, u32 sz) +{ + if (!pb || !raw || (sz < (MAX_STRING + 1))) + return; + + pb->crs = pb->buf = raw; + pb->size = sz; + pb->next = 0; + pb->buf[0] = 0; + pb->buf[sz-1] = ~0; +} + +/** + * printbuf_reset - reinitialize print buffer to empty state + */ + +void printbuf_reset(struct print_buf *pb) +{ + if (pb && pb->buf) + printbuf_init(pb, pb->buf, pb->size); +} + +/** + * printbuf_empty - test if print buffer is in empty state + */ + +int printbuf_empty(struct print_buf *pb) +{ + return (!pb || !pb->buf || (pb->crs == pb->buf)); +} + +/** + * printbuf_validate - check for print buffer overflow + * + * Verifies that a print buffer has captured all data written to it. + * If data has been lost, linearize buffer and prepend an error message + * + * Returns length of print buffer data string (including trailing NULL) + */ + +int printbuf_validate(struct print_buf *pb) +{ + char *err = " *** PRINT BUFFER WRAPPED AROUND ***\n"; + char *cp_buf; + struct print_buf cb; + + if (!pb || !pb->buf) + return 0; + + if (pb->buf[pb->size - 1] == '\0') { + cp_buf = kmalloc(pb->size, GFP_ATOMIC); + if (cp_buf != NULL){ + printbuf_init(&cb, cp_buf, pb->size); + printbuf_move(&cb, pb); + printbuf_move(pb, &cb); + kfree(cp_buf); + memcpy(pb->buf, err, strlen(err)); + } else { + printbuf_reset(pb); + tipc_printf(pb, err); + } + } + return (pb->crs - pb->buf + 1); +} + +/** + * printbuf_move - move print buffer contents to another print buffer + * + * Current contents of destination print buffer (if any) are discarded. + * Source print buffer becomes empty if a successful move occurs. + */ + +void printbuf_move(struct print_buf *pb_to, struct print_buf *pb_from) +{ + int len; + + /* Handle the cases where contents can't be moved */ + + if (!pb_to || !pb_to->buf) + return; + + if (!pb_from || !pb_from->buf) { + printbuf_reset(pb_to); + return; + } + + if (pb_to->size < pb_from->size) { + printbuf_reset(pb_to); + tipc_printf(pb_to, "*** PRINT BUFFER OVERFLOW ***"); + return; + } + + /* Copy data from char after cursor to end (if used) */ + len = pb_from->buf + pb_from->size - pb_from->crs - 2; + if ((pb_from->buf[pb_from->size-1] == 0) && (len > 0)) { + strcpy(pb_to->buf, pb_from->crs + 1); + pb_to->crs = pb_to->buf + len; + } else + pb_to->crs = pb_to->buf; + + /* Copy data from start to cursor (always) */ + len = pb_from->crs - pb_from->buf; + strcpy(pb_to->crs, pb_from->buf); + pb_to->crs += len; + + printbuf_reset(pb_from); +} + +/** + * tipc_printf - append formatted output to print buffer chain + */ + +void tipc_printf(struct print_buf *pb, const char *fmt, ...) +{ + int chars_to_add; + int chars_left; + char save_char; + struct print_buf *pb_next; + + spin_lock_bh(&print_lock); + FORMAT(print_string, chars_to_add, fmt); + if (chars_to_add >= MAX_STRING) + strcpy(print_string, "*** STRING TOO LONG ***"); + + while (pb) { + if (pb == CONS) + printk(print_string); + else if (pb->buf) { + chars_left = pb->buf + pb->size - pb->crs - 1; + if (chars_to_add <= chars_left) { + strcpy(pb->crs, print_string); + pb->crs += chars_to_add; + } else { + strcpy(pb->buf, print_string + chars_left); + save_char = print_string[chars_left]; + print_string[chars_left] = 0; + strcpy(pb->crs, print_string); + print_string[chars_left] = save_char; + pb->crs = pb->buf + chars_to_add - chars_left; + } + } + pb_next = pb->next; + pb->next = 0; + pb = pb_next; + } + spin_unlock_bh(&print_lock); +} + +/** + * TEE - perform next output operation on both print buffers + */ + +struct print_buf *TEE(struct print_buf *b0, struct print_buf *b1) +{ + struct print_buf *pb = b0; + + if (!b0 || (b0 == b1)) + return b1; + if (!b1) + return b0; + + spin_lock_bh(&print_lock); + while (pb->next) { + if ((pb->next == b1) || (pb->next == b0)) + pb->next = pb->next->next; + else + pb = pb->next; + } + pb->next = b1; + spin_unlock_bh(&print_lock); + return b0; +} + +/** + * print_to_console - write string of bytes to console in multiple chunks + */ + +static void print_to_console(char *crs, int len) +{ + int rest = len; + + while (rest > 0) { + int sz = rest < MAX_STRING ? rest : MAX_STRING; + char c = crs[sz]; + + crs[sz] = 0; + printk((const char *)crs); + crs[sz] = c; + rest -= sz; + crs += sz; + } +} + +/** + * printbuf_dump - write print buffer contents to console + */ + +static void printbuf_dump(struct print_buf *pb) +{ + int len; + + /* Dump print buffer from char after cursor to end (if used) */ + len = pb->buf + pb->size - pb->crs - 2; + if ((pb->buf[pb->size - 1] == 0) && (len > 0)) + print_to_console(pb->crs + 1, len); + + /* Dump print buffer from start to cursor (always) */ + len = pb->crs - pb->buf; + print_to_console(pb->buf, len); +} + +/** + * tipc_dump - dump non-console print buffer(s) to console + */ + +void tipc_dump(struct print_buf *pb, const char *fmt, ...) +{ + int len; + + spin_lock_bh(&print_lock); + FORMAT(CONS->buf, len, fmt); + printk(CONS->buf); + + for (; pb; pb = pb->next) { + if (pb == CONS) + continue; + printk("\n---- Start of dump,%s log ----\n\n", + (pb == LOG) ? "global" : "local"); + printbuf_dump(pb); + printbuf_reset(pb); + printk("\n-------- End of dump --------\n"); + } + spin_unlock_bh(&print_lock); +} + +/** + * log_stop - free up TIPC log print buffer + */ + +void log_stop(void) +{ + spin_lock_bh(&print_lock); + if (LOG->buf) { + kfree(LOG->buf); + LOG->buf = NULL; + } + spin_unlock_bh(&print_lock); +} + +/** + * log_reinit - set TIPC log print buffer to specified size + */ + +void log_reinit(int log_size) +{ + log_stop(); + + if (log_size) { + if (log_size <= MAX_STRING) + log_size = MAX_STRING + 1; + spin_lock_bh(&print_lock); + printbuf_init(LOG, kmalloc(log_size, GFP_ATOMIC), log_size); + spin_unlock_bh(&print_lock); + } +} + +/** + * log_resize - reconfigure size of TIPC log buffer + */ + +struct sk_buff *log_resize(const void *req_tlv_area, int req_tlv_space) +{ + u32 value; + + if (!TLV_CHECK(req_tlv_area, req_tlv_space, TIPC_TLV_UNSIGNED)) + return cfg_reply_error_string(TIPC_CFG_TLV_ERROR); + + value = *(u32 *)TLV_DATA(req_tlv_area); + value = ntohl(value); + if (value != delimit(value, 0, 32768)) + return cfg_reply_error_string(TIPC_CFG_INVALID_VALUE + " (log size must be 0-32768)"); + log_reinit(value); + return cfg_reply_none(); +} + +/** + * log_dump - capture TIPC log buffer contents in configuration message + */ + +struct sk_buff *log_dump(void) +{ + struct sk_buff *reply; + + spin_lock_bh(&print_lock); + if (!LOG->buf) + reply = cfg_reply_ultra_string("log not activated\n"); + else if (printbuf_empty(LOG)) + reply = cfg_reply_ultra_string("log is empty\n"); + else { + struct tlv_desc *rep_tlv; + struct print_buf pb; + int str_len; + + str_len = min(LOG->size, 32768u); + reply = cfg_reply_alloc(TLV_SPACE(str_len)); + if (reply) { + rep_tlv = (struct tlv_desc *)reply->data; + printbuf_init(&pb, TLV_DATA(rep_tlv), str_len); + printbuf_move(&pb, LOG); + str_len = strlen(TLV_DATA(rep_tlv)) + 1; + skb_put(reply, TLV_SPACE(str_len)); + TLV_SET(rep_tlv, TIPC_TLV_ULTRA_STRING, NULL, str_len); + } + } + spin_unlock_bh(&print_lock); + return reply; +} + diff --git a/net/tipc/dbg.h b/net/tipc/dbg.h new file mode 100644 index 00000000000..c6b2a64c224 --- /dev/null +++ b/net/tipc/dbg.h @@ -0,0 +1,59 @@ +/* + * net/tipc/dbg.h: Include file for TIPC print buffer routines + * + * Copyright (c) 1997-2006, Ericsson AB + * Copyright (c) 2005, Wind River Systems + * All rights reserved. + * + * Redistribution and use in source and binary forms, with or without + * modification, are permitted provided that the following conditions are met: + * + * 1. Redistributions of source code must retain the above copyright + * notice, this list of conditions and the following disclaimer. + * 2. Redistributions in binary form must reproduce the above copyright + * notice, this list of conditions and the following disclaimer in the + * documentation and/or other materials provided with the distribution. + * 3. Neither the names of the copyright holders nor the names of its + * contributors may be used to endorse or promote products derived from + * this software without specific prior written permission. + * + * Alternatively, this software may be distributed under the terms of the + * GNU General Public License ("GPL") version 2 as published by the Free + * Software Foundation. + * + * THIS SOFTWARE IS PROVIDED BY THE COPYRIGHT HOLDERS AND CONTRIBUTORS "AS IS" + * AND ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT LIMITED TO, THE + * IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR A PARTICULAR PURPOSE + * ARE DISCLAIMED. IN NO EVENT SHALL THE COPYRIGHT OWNER OR CONTRIBUTORS BE + * LIABLE FOR ANY DIRECT, INDIRECT, INCIDENTAL, SPECIAL, EXEMPLARY, OR + * CONSEQUENTIAL DAMAGES (INCLUDING, BUT NOT LIMITED TO, PROCUREMENT OF + * SUBSTITUTE GOODS OR SERVICES; LOSS OF USE, DATA, OR PROFITS; OR BUSINESS + * INTERRUPTION) HOWEVER CAUSED AND ON ANY THEORY OF LIABILITY, WHETHER IN + * CONTRACT, STRICT LIABILITY, OR TORT (INCLUDING NEGLIGENCE OR OTHERWISE) + * ARISING IN ANY WAY OUT OF THE USE OF THIS SOFTWARE, EVEN IF ADVISED OF THE + * POSSIBILITY OF SUCH DAMAGE. + */ + +#ifndef _TIPC_DBG_H +#define _TIPC_DBG_H + +struct print_buf { + char *buf; + u32 size; + char *crs; + struct print_buf *next; +}; + +void printbuf_init(struct print_buf *pb, char *buf, u32 sz); +void printbuf_reset(struct print_buf *pb); +int printbuf_empty(struct print_buf *pb); +int printbuf_validate(struct print_buf *pb); +void printbuf_move(struct print_buf *pb_to, struct print_buf *pb_from); + +void log_reinit(int log_size); +void log_stop(void); + +struct sk_buff *log_resize(const void *req_tlv_area, int req_tlv_space); +struct sk_buff *log_dump(void); + +#endif diff --git a/net/tipc/discover.c b/net/tipc/discover.c new file mode 100644 index 00000000000..b106ef1621c --- /dev/null +++ b/net/tipc/discover.c @@ -0,0 +1,318 @@ +/* + * net/tipc/discover.c + * + * Copyright (c) 2003-2006, Ericsson AB + * Copyright (c) 2005, Wind River Systems + * All rights reserved. + * + * Redistribution and use in source and binary forms, with or without + * modification, are permitted provided that the following conditions are met: + * + * 1. Redistributions of source code must retain the above copyright + * notice, this list of conditions and the following disclaimer. + * 2. Redistributions in binary form must reproduce the above copyright + * notice, this list of conditions and the following disclaimer in the + * documentation and/or other materials provided with the distribution. + * 3. Neither the names of the copyright holders nor the names of its + * contributors may be used to endorse or promote products derived from + * this software without specific prior written permission. + * + * Alternatively, this software may be distributed under the terms of the + * GNU General Public License ("GPL") version 2 as published by the Free + * Software Foundation. + * + * THIS SOFTWARE IS PROVIDED BY THE COPYRIGHT HOLDERS AND CONTRIBUTORS "AS IS" + * AND ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT LIMITED TO, THE + * IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR A PARTICULAR PURPOSE + * ARE DISCLAIMED. IN NO EVENT SHALL THE COPYRIGHT OWNER OR CONTRIBUTORS BE + * LIABLE FOR ANY DIRECT, INDIRECT, INCIDENTAL, SPECIAL, EXEMPLARY, OR + * CONSEQUENTIAL DAMAGES (INCLUDING, BUT NOT LIMITED TO, PROCUREMENT OF + * SUBSTITUTE GOODS OR SERVICES; LOSS OF USE, DATA, OR PROFITS; OR BUSINESS + * INTERRUPTION) HOWEVER CAUSED AND ON ANY THEORY OF LIABILITY, WHETHER IN + * CONTRACT, STRICT LIABILITY, OR TORT (INCLUDING NEGLIGENCE OR OTHERWISE) + * ARISING IN ANY WAY OUT OF THE USE OF THIS SOFTWARE, EVEN IF ADVISED OF THE + * POSSIBILITY OF SUCH DAMAGE. + */ + +#include "core.h" +#include "dbg.h" +#include "link.h" +#include "zone.h" +#include "discover.h" +#include "port.h" +#include "name_table.h" + +#define TIPC_LINK_REQ_INIT 125 /* min delay during bearer start up */ +#define TIPC_LINK_REQ_FAST 2000 /* normal delay if bearer has no links */ +#define TIPC_LINK_REQ_SLOW 600000 /* normal delay if bearer has links */ + +#if 0 +#define GET_NODE_INFO 300 +#define GET_NODE_INFO_RESULT 301 +#define FORWARD_LINK_PROBE 302 +#define LINK_REQUEST_REJECTED 303 +#define LINK_REQUEST_ACCEPTED 304 +#define DROP_LINK_REQUEST 305 +#define CHECK_LINK_COUNT 306 +#endif + +/* + * TODO: Most of the inter-cluster setup stuff should be + * rewritten, and be made conformant with specification. + */ + + +/** + * struct link_req - information about an ongoing link setup request + * @bearer: bearer issuing requests + * @dest: destination address for request messages + * @buf: request message to be (repeatedly) sent + * @timer: timer governing period between requests + * @timer_intv: current interval between requests (in ms) + */ +struct link_req { + struct bearer *bearer; + struct tipc_media_addr dest; + struct sk_buff *buf; + struct timer_list timer; + unsigned int timer_intv; +}; + + +#if 0 +int disc_create_link(const struct tipc_link_create *argv) +{ + /* + * Code for inter cluster link setup here + */ + return TIPC_OK; +} +#endif + +/* + * disc_lost_link(): A link has lost contact + */ + +void disc_link_event(u32 addr, char *name, int up) +{ + if (in_own_cluster(addr)) + return; + /* + * Code for inter cluster link setup here + */ +} + +/** + * disc_init_msg - initialize a link setup message + * @type: message type (request or response) + * @req_links: number of links associated with message + * @dest_domain: network domain of node(s) which should respond to message + * @b_ptr: ptr to bearer issuing message + */ + +struct sk_buff *disc_init_msg(u32 type, + u32 req_links, + u32 dest_domain, + struct bearer *b_ptr) +{ + struct sk_buff *buf = buf_acquire(DSC_H_SIZE); + struct tipc_msg *msg; + + if (buf) { + msg = buf_msg(buf); + msg_init(msg, LINK_CONFIG, type, TIPC_OK, DSC_H_SIZE, + dest_domain); + msg_set_non_seq(msg); + msg_set_req_links(msg, req_links); + msg_set_dest_domain(msg, dest_domain); + msg_set_bc_netid(msg, tipc_net_id); + msg_set_media_addr(msg, &b_ptr->publ.addr); + } + return buf; +} + +/** + * disc_recv_msg - handle incoming link setup message (request or response) + * @buf: buffer containing message + */ + +void disc_recv_msg(struct sk_buff *buf) +{ + struct bearer *b_ptr = (struct bearer *)TIPC_SKB_CB(buf)->handle; + struct link *link; + struct tipc_media_addr media_addr; + struct tipc_msg *msg = buf_msg(buf); + u32 dest = msg_dest_domain(msg); + u32 orig = msg_prevnode(msg); + u32 net_id = msg_bc_netid(msg); + u32 type = msg_type(msg); + + msg_get_media_addr(msg,&media_addr); + msg_dbg(msg, "RECV:"); + buf_discard(buf); + + if (net_id != tipc_net_id) + return; + if (!addr_domain_valid(dest)) + return; + if (!addr_node_valid(orig)) + return; + if (orig == tipc_own_addr) + return; + if (!in_scope(dest, tipc_own_addr)) + return; + if (is_slave(tipc_own_addr) && is_slave(orig)) + return; + if (is_slave(orig) && !in_own_cluster(orig)) + return; + if (in_own_cluster(orig)) { + /* Always accept link here */ + struct sk_buff *rbuf; + struct tipc_media_addr *addr; + struct node *n_ptr = node_find(orig); + int link_up; + dbg(" in own cluster\n"); + if (n_ptr == NULL) { + n_ptr = node_create(orig); + } + if (n_ptr == NULL) { + warn("Memory squeeze; Failed to create node\n"); + return; + } + spin_lock_bh(&n_ptr->lock); + link = n_ptr->links[b_ptr->identity]; + if (!link) { + dbg("creating link\n"); + link = link_create(b_ptr, orig, &media_addr); + if (!link) { + spin_unlock_bh(&n_ptr->lock); + return; + } + } + addr = &link->media_addr; + if (memcmp(addr, &media_addr, sizeof(*addr))) { + char addr_string[16]; + + warn("New bearer address for %s\n", + addr_string_fill(addr_string, orig)); + memcpy(addr, &media_addr, sizeof(*addr)); + link_reset(link); + } + link_up = link_is_up(link); + spin_unlock_bh(&n_ptr->lock); + if ((type == DSC_RESP_MSG) || link_up) + return; + rbuf = disc_init_msg(DSC_RESP_MSG, 1, orig, b_ptr); + if (rbuf != NULL) { + msg_dbg(buf_msg(rbuf),"SEND:"); + b_ptr->media->send_msg(rbuf, &b_ptr->publ, &media_addr); + buf_discard(rbuf); + } + } +} + +/** + * disc_stop_link_req - stop sending periodic link setup requests + * @req: ptr to link request structure + */ + +void disc_stop_link_req(struct link_req *req) +{ + if (!req) + return; + + k_cancel_timer(&req->timer); + k_term_timer(&req->timer); + buf_discard(req->buf); + kfree(req); +} + +/** + * disc_update_link_req - update frequency of periodic link setup requests + * @req: ptr to link request structure + */ + +void disc_update_link_req(struct link_req *req) +{ + if (!req) + return; + + if (req->timer_intv == TIPC_LINK_REQ_SLOW) { + if (!req->bearer->nodes.count) { + req->timer_intv = TIPC_LINK_REQ_FAST; + k_start_timer(&req->timer, req->timer_intv); + } + } else if (req->timer_intv == TIPC_LINK_REQ_FAST) { + if (req->bearer->nodes.count) { + req->timer_intv = TIPC_LINK_REQ_SLOW; + k_start_timer(&req->timer, req->timer_intv); + } + } else { + /* leave timer "as is" if haven't yet reached a "normal" rate */ + } +} + +/** + * disc_timeout - send a periodic link setup request + * @req: ptr to link request structure + * + * Called whenever a link setup request timer associated with a bearer expires. + */ + +static void disc_timeout(struct link_req *req) +{ + spin_lock_bh(&req->bearer->publ.lock); + + req->bearer->media->send_msg(req->buf, &req->bearer->publ, &req->dest); + + if ((req->timer_intv == TIPC_LINK_REQ_SLOW) || + (req->timer_intv == TIPC_LINK_REQ_FAST)) { + /* leave timer interval "as is" if already at a "normal" rate */ + } else { + req->timer_intv *= 2; + if (req->timer_intv > TIPC_LINK_REQ_SLOW) + req->timer_intv = TIPC_LINK_REQ_SLOW; + if ((req->timer_intv == TIPC_LINK_REQ_FAST) && + (req->bearer->nodes.count)) + req->timer_intv = TIPC_LINK_REQ_SLOW; + } + k_start_timer(&req->timer, req->timer_intv); + + spin_unlock_bh(&req->bearer->publ.lock); +} + +/** + * disc_init_link_req - start sending periodic link setup requests + * @b_ptr: ptr to bearer issuing requests + * @dest: destination address for request messages + * @dest_domain: network domain of node(s) which should respond to message + * @req_links: max number of desired links + * + * Returns pointer to link request structure, or NULL if unable to create. + */ + +struct link_req *disc_init_link_req(struct bearer *b_ptr, + const struct tipc_media_addr *dest, + u32 dest_domain, + u32 req_links) +{ + struct link_req *req; + + req = (struct link_req *)kmalloc(sizeof(*req), GFP_ATOMIC); + if (!req) + return NULL; + + req->buf = disc_init_msg(DSC_REQ_MSG, req_links, dest_domain, b_ptr); + if (!req->buf) { + kfree(req); + return NULL; + } + + memcpy(&req->dest, dest, sizeof(*dest)); + req->bearer = b_ptr; + req->timer_intv = TIPC_LINK_REQ_INIT; + k_init_timer(&req->timer, (Handler)disc_timeout, (unsigned long)req); + k_start_timer(&req->timer, req->timer_intv); + return req; +} + diff --git a/net/tipc/discover.h b/net/tipc/discover.h new file mode 100644 index 00000000000..2a6114d9162 --- /dev/null +++ b/net/tipc/discover.h @@ -0,0 +1,58 @@ +/* + * net/tipc/discover.h + * + * Copyright (c) 2003-2006, Ericsson AB + * Copyright (c) 2005, Wind River Systems + * All rights reserved. + * + * Redistribution and use in source and binary forms, with or without + * modification, are permitted provided that the following conditions are met: + * + * 1. Redistributions of source code must retain the above copyright + * notice, this list of conditions and the following disclaimer. + * 2. Redistributions in binary form must reproduce the above copyright + * notice, this list of conditions and the following disclaimer in the + * documentation and/or other materials provided with the distribution. + * 3. Neither the names of the copyright holders nor the names of its + * contributors may be used to endorse or promote products derived from + * this software without specific prior written permission. + * + * Alternatively, this software may be distributed under the terms of the + * GNU General Public License ("GPL") version 2 as published by the Free + * Software Foundation. + * + * THIS SOFTWARE IS PROVIDED BY THE COPYRIGHT HOLDERS AND CONTRIBUTORS "AS IS" + * AND ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT LIMITED TO, THE + * IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR A PARTICULAR PURPOSE + * ARE DISCLAIMED. IN NO EVENT SHALL THE COPYRIGHT OWNER OR CONTRIBUTORS BE + * LIABLE FOR ANY DIRECT, INDIRECT, INCIDENTAL, SPECIAL, EXEMPLARY, OR + * CONSEQUENTIAL DAMAGES (INCLUDING, BUT NOT LIMITED TO, PROCUREMENT OF + * SUBSTITUTE GOODS OR SERVICES; LOSS OF USE, DATA, OR PROFITS; OR BUSINESS + * INTERRUPTION) HOWEVER CAUSED AND ON ANY THEORY OF LIABILITY, WHETHER IN + * CONTRACT, STRICT LIABILITY, OR TORT (INCLUDING NEGLIGENCE OR OTHERWISE) + * ARISING IN ANY WAY OUT OF THE USE OF THIS SOFTWARE, EVEN IF ADVISED OF THE + * POSSIBILITY OF SUCH DAMAGE. + */ + +#ifndef _TIPC_DISCOVER_H +#define _TIPC_DISCOVER_H + +#include <linux/tipc.h> + +struct link_req; + +struct link_req *disc_init_link_req(struct bearer *b_ptr, + const struct tipc_media_addr *dest, + u32 dest_domain, + u32 req_links); +void disc_update_link_req(struct link_req *req); +void disc_stop_link_req(struct link_req *req); + +void disc_recv_msg(struct sk_buff *buf); + +void disc_link_event(u32 addr, char *name, int up); +#if 0 +int disc_create_link(const struct tipc_link_create *argv); +#endif + +#endif diff --git a/net/tipc/eth_media.c b/net/tipc/eth_media.c new file mode 100644 index 00000000000..34d0462db3a --- /dev/null +++ b/net/tipc/eth_media.c @@ -0,0 +1,299 @@ +/* + * net/tipc/eth_media.c: Ethernet bearer support for TIPC + * + * Copyright (c) 2001-2006, Ericsson AB + * Copyright (c) 2005, Wind River Systems + * All rights reserved. + * + * Redistribution and use in source and binary forms, with or without + * modification, are permitted provided that the following conditions are met: + * + * 1. Redistributions of source code must retain the above copyright + * notice, this list of conditions and the following disclaimer. + * 2. Redistributions in binary form must reproduce the above copyright + * notice, this list of conditions and the following disclaimer in the + * documentation and/or other materials provided with the distribution. + * 3. Neither the names of the copyright holders nor the names of its + * contributors may be used to endorse or promote products derived from + * this software without specific prior written permission. + * + * Alternatively, this software may be distributed under the terms of the + * GNU General Public License ("GPL") version 2 as published by the Free + * Software Foundation. + * + * THIS SOFTWARE IS PROVIDED BY THE COPYRIGHT HOLDERS AND CONTRIBUTORS "AS IS" + * AND ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT LIMITED TO, THE + * IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR A PARTICULAR PURPOSE + * ARE DISCLAIMED. IN NO EVENT SHALL THE COPYRIGHT OWNER OR CONTRIBUTORS BE + * LIABLE FOR ANY DIRECT, INDIRECT, INCIDENTAL, SPECIAL, EXEMPLARY, OR + * CONSEQUENTIAL DAMAGES (INCLUDING, BUT NOT LIMITED TO, PROCUREMENT OF + * SUBSTITUTE GOODS OR SERVICES; LOSS OF USE, DATA, OR PROFITS; OR BUSINESS + * INTERRUPTION) HOWEVER CAUSED AND ON ANY THEORY OF LIABILITY, WHETHER IN + * CONTRACT, STRICT LIABILITY, OR TORT (INCLUDING NEGLIGENCE OR OTHERWISE) + * ARISING IN ANY WAY OUT OF THE USE OF THIS SOFTWARE, EVEN IF ADVISED OF THE + * POSSIBILITY OF SUCH DAMAGE. + */ + +#include <net/tipc/tipc.h> +#include <net/tipc/tipc_bearer.h> +#include <net/tipc/tipc_msg.h> +#include <linux/netdevice.h> +#include <linux/version.h> + +#define MAX_ETH_BEARERS 2 +#define TIPC_PROTOCOL 0x88ca +#define ETH_LINK_PRIORITY 10 +#define ETH_LINK_TOLERANCE TIPC_DEF_LINK_TOL + + +/** + * struct eth_bearer - Ethernet bearer data structure + * @bearer: ptr to associated "generic" bearer structure + * @dev: ptr to associated Ethernet network device + * @tipc_packet_type: used in binding TIPC to Ethernet driver + */ + +struct eth_bearer { + struct tipc_bearer *bearer; + struct net_device *dev; + struct packet_type tipc_packet_type; +}; + +static struct eth_bearer eth_bearers[MAX_ETH_BEARERS]; +static int eth_started = 0; +static struct notifier_block notifier; + +/** + * send_msg - send a TIPC message out over an Ethernet interface + */ + +static int send_msg(struct sk_buff *buf, struct tipc_bearer *tb_ptr, + struct tipc_media_addr *dest) +{ + struct sk_buff *clone; + struct net_device *dev; + + clone = skb_clone(buf, GFP_ATOMIC); + if (clone) { + clone->nh.raw = clone->data; + dev = ((struct eth_bearer *)(tb_ptr->usr_handle))->dev; + clone->dev = dev; + dev->hard_header(clone, dev, TIPC_PROTOCOL, + &dest->dev_addr.eth_addr, + dev->dev_addr, clone->len); + dev_queue_xmit(clone); + } + return TIPC_OK; +} + +/** + * recv_msg - handle incoming TIPC message from an Ethernet interface + * + * Routine truncates any Ethernet padding/CRC appended to the message, + * and ensures message size matches actual length + */ + +static int recv_msg(struct sk_buff *buf, struct net_device *dev, + struct packet_type *pt, struct net_device *orig_dev) +{ + struct eth_bearer *eb_ptr = (struct eth_bearer *)pt->af_packet_priv; + u32 size; + + if (likely(eb_ptr->bearer)) { + size = msg_size((struct tipc_msg *)buf->data); + skb_trim(buf, size); + if (likely(buf->len == size)) { + buf->next = NULL; + tipc_recv_msg(buf, eb_ptr->bearer); + } else { + kfree_skb(buf); + } + } else { + kfree_skb(buf); + } + return TIPC_OK; +} + +/** + * enable_bearer - attach TIPC bearer to an Ethernet interface + */ + +static int enable_bearer(struct tipc_bearer *tb_ptr) +{ + struct net_device *dev = dev_base; + struct eth_bearer *eb_ptr = ð_bearers[0]; + struct eth_bearer *stop = ð_bearers[MAX_ETH_BEARERS]; + char *driver_name = strchr((const char *)tb_ptr->name, ':') + 1; + + /* Find device with specified name */ + + while (dev && dev->name && + (memcmp(dev->name, driver_name, strlen(dev->name)))) { + dev = dev->next; + } + if (!dev) + return -ENODEV; + + /* Find Ethernet bearer for device (or create one) */ + + for (;(eb_ptr != stop) && eb_ptr->dev && (eb_ptr->dev != dev); eb_ptr++); + if (eb_ptr == stop) + return -EDQUOT; + if (!eb_ptr->dev) { + eb_ptr->dev = dev; + eb_ptr->tipc_packet_type.type = __constant_htons(TIPC_PROTOCOL); + eb_ptr->tipc_packet_type.dev = dev; + eb_ptr->tipc_packet_type.func = recv_msg; + eb_ptr->tipc_packet_type.af_packet_priv = eb_ptr; + INIT_LIST_HEAD(&(eb_ptr->tipc_packet_type.list)); + dev_hold(dev); + dev_add_pack(&eb_ptr->tipc_packet_type); + } + + /* Associate TIPC bearer with Ethernet bearer */ + + eb_ptr->bearer = tb_ptr; + tb_ptr->usr_handle = (void *)eb_ptr; + tb_ptr->mtu = dev->mtu; + tb_ptr->blocked = 0; + tb_ptr->addr.type = htonl(TIPC_MEDIA_TYPE_ETH); + memcpy(&tb_ptr->addr.dev_addr, &dev->dev_addr, ETH_ALEN); + return 0; +} + +/** + * disable_bearer - detach TIPC bearer from an Ethernet interface + * + * We really should do dev_remove_pack() here, but this function can not be + * called at tasklet level. => Use eth_bearer->bearer as a flag to throw away + * incoming buffers, & postpone dev_remove_pack() to eth_media_stop() on exit. + */ + +static void disable_bearer(struct tipc_bearer *tb_ptr) +{ + ((struct eth_bearer *)tb_ptr->usr_handle)->bearer = 0; +} + +/** + * recv_notification - handle device updates from OS + * + * Change the state of the Ethernet bearer (if any) associated with the + * specified device. + */ + +static int recv_notification(struct notifier_block *nb, unsigned long evt, + void *dv) +{ + struct net_device *dev = (struct net_device *)dv; + struct eth_bearer *eb_ptr = ð_bearers[0]; + struct eth_bearer *stop = ð_bearers[MAX_ETH_BEARERS]; + + while ((eb_ptr->dev != dev)) { + if (++eb_ptr == stop) + return NOTIFY_DONE; /* couldn't find device */ + } + if (!eb_ptr->bearer) + return NOTIFY_DONE; /* bearer had been disabled */ + + eb_ptr->bearer->mtu = dev->mtu; + + switch (evt) { + case NETDEV_CHANGE: + if (netif_carrier_ok(dev)) + tipc_continue(eb_ptr->bearer); + else + tipc_block_bearer(eb_ptr->bearer->name); + break; + case NETDEV_UP: + tipc_continue(eb_ptr->bearer); + break; + case NETDEV_DOWN: + tipc_block_bearer(eb_ptr->bearer->name); + break; + case NETDEV_CHANGEMTU: + case NETDEV_CHANGEADDR: + tipc_block_bearer(eb_ptr->bearer->name); + tipc_continue(eb_ptr->bearer); + break; + case NETDEV_UNREGISTER: + case NETDEV_CHANGENAME: + tipc_disable_bearer(eb_ptr->bearer->name); + break; + } + return NOTIFY_OK; +} + +/** + * eth_addr2str - convert Ethernet address to string + */ + +static char *eth_addr2str(struct tipc_media_addr *a, char *str_buf, int str_size) +{ + unchar *addr = (unchar *)&a->dev_addr; + + if (str_size < 18) + *str_buf = '\0'; + else + sprintf(str_buf, "%02x:%02x:%02x:%02x:%02x:%02x", + addr[0], addr[1], addr[2], addr[3], addr[4], addr[5]); + return str_buf; +} + +/** + * eth_media_start - activate Ethernet bearer support + * + * Register Ethernet media type with TIPC bearer code. Also register + * with OS for notifications about device state changes. + */ + +int eth_media_start(void) +{ + struct tipc_media_addr bcast_addr; + int res; + + if (eth_started) + return -EINVAL; + + memset(&bcast_addr, 0xff, sizeof(bcast_addr)); + memset(eth_bearers, 0, sizeof(eth_bearers)); + + res = tipc_register_media(TIPC_MEDIA_TYPE_ETH, "eth", + enable_bearer, disable_bearer, send_msg, + eth_addr2str, &bcast_addr, ETH_LINK_PRIORITY, + ETH_LINK_TOLERANCE, TIPC_DEF_LINK_WIN); + if (res) + return res; + + notifier.notifier_call = &recv_notification; + notifier.priority = 0; + res = register_netdevice_notifier(¬ifier); + if (!res) + eth_started = 1; + return res; +} + +/** + * eth_media_stop - deactivate Ethernet bearer support + */ + +void eth_media_stop(void) +{ + int i; + + if (!eth_started) + return; + + unregister_netdevice_notifier(¬ifier); + for (i = 0; i < MAX_ETH_BEARERS ; i++) { + if (eth_bearers[i].bearer) { + eth_bearers[i].bearer->blocked = 1; + eth_bearers[i].bearer = 0; + } + if (eth_bearers[i].dev) { + dev_remove_pack(ð_bearers[i].tipc_packet_type); + dev_put(eth_bearers[i].dev); + } + } + memset(ð_bearers, 0, sizeof(eth_bearers)); + eth_started = 0; +} diff --git a/net/tipc/handler.c b/net/tipc/handler.c new file mode 100644 index 00000000000..f320010f8a6 --- /dev/null +++ b/net/tipc/handler.c @@ -0,0 +1,132 @@ +/* + * net/tipc/handler.c: TIPC signal handling + * + * Copyright (c) 2000-2006, Ericsson AB + * Copyright (c) 2005, Wind River Systems + * All rights reserved. + * + * Redistribution and use in source and binary forms, with or without + * modification, are permitted provided that the following conditions are met: + * + * 1. Redistributions of source code must retain the above copyright + * notice, this list of conditions and the following disclaimer. + * 2. Redistributions in binary form must reproduce the above copyright + * notice, this list of conditions and the following disclaimer in the + * documentation and/or other materials provided with the distribution. + * 3. Neither the names of the copyright holders nor the names of its + * contributors may be used to endorse or promote products derived from + * this software without specific prior written permission. + * + * Alternatively, this software may be distributed under the terms of the + * GNU General Public License ("GPL") version 2 as published by the Free + * Software Foundation. + * + * THIS SOFTWARE IS PROVIDED BY THE COPYRIGHT HOLDERS AND CONTRIBUTORS "AS IS" + * AND ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT LIMITED TO, THE + * IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR A PARTICULAR PURPOSE + * ARE DISCLAIMED. IN NO EVENT SHALL THE COPYRIGHT OWNER OR CONTRIBUTORS BE + * LIABLE FOR ANY DIRECT, INDIRECT, INCIDENTAL, SPECIAL, EXEMPLARY, OR + * CONSEQUENTIAL DAMAGES (INCLUDING, BUT NOT LIMITED TO, PROCUREMENT OF + * SUBSTITUTE GOODS OR SERVICES; LOSS OF USE, DATA, OR PROFITS; OR BUSINESS + * INTERRUPTION) HOWEVER CAUSED AND ON ANY THEORY OF LIABILITY, WHETHER IN + * CONTRACT, STRICT LIABILITY, OR TORT (INCLUDING NEGLIGENCE OR OTHERWISE) + * ARISING IN ANY WAY OUT OF THE USE OF THIS SOFTWARE, EVEN IF ADVISED OF THE + * POSSIBILITY OF SUCH DAMAGE. + */ + +#include "core.h" + +struct queue_item { + struct list_head next_signal; + void (*handler) (unsigned long); + unsigned long data; +}; + +static kmem_cache_t *tipc_queue_item_cache; +static struct list_head signal_queue_head; +static spinlock_t qitem_lock = SPIN_LOCK_UNLOCKED; +static int handler_enabled = 0; + +static void process_signal_queue(unsigned long dummy); + +static DECLARE_TASKLET_DISABLED(tipc_tasklet, process_signal_queue, 0); + + +unsigned int k_signal(Handler routine, unsigned long argument) +{ + struct queue_item *item; + + if (!handler_enabled) { + err("Signal request ignored by handler\n"); + return -ENOPROTOOPT; + } + + spin_lock_bh(&qitem_lock); + item = kmem_cache_alloc(tipc_queue_item_cache, GFP_ATOMIC); + if (!item) { + err("Signal queue out of memory\n"); + spin_unlock_bh(&qitem_lock); + return -ENOMEM; + } + item->handler = routine; + item->data = argument; + list_add_tail(&item->next_signal, &signal_queue_head); + spin_unlock_bh(&qitem_lock); + tasklet_schedule(&tipc_tasklet); + return 0; +} + +static void process_signal_queue(unsigned long dummy) +{ + struct queue_item *__volatile__ item; + struct list_head *l, *n; + + spin_lock_bh(&qitem_lock); + list_for_each_safe(l, n, &signal_queue_head) { + item = list_entry(l, struct queue_item, next_signal); + list_del(&item->next_signal); + spin_unlock_bh(&qitem_lock); + item->handler(item->data); + spin_lock_bh(&qitem_lock); + kmem_cache_free(tipc_queue_item_cache, item); + } + spin_unlock_bh(&qitem_lock); +} + +int handler_start(void) +{ + tipc_queue_item_cache = + kmem_cache_create("tipc_queue_items", sizeof(struct queue_item), + 0, SLAB_HWCACHE_ALIGN, NULL, NULL); + if (!tipc_queue_item_cache) + return -ENOMEM; + + INIT_LIST_HEAD(&signal_queue_head); + tasklet_enable(&tipc_tasklet); + handler_enabled = 1; + return 0; +} + +void handler_stop(void) +{ + struct list_head *l, *n; + struct queue_item *item; + + if (!handler_enabled) + return; + + handler_enabled = 0; + tasklet_disable(&tipc_tasklet); + tasklet_kill(&tipc_tasklet); + + spin_lock_bh(&qitem_lock); + list_for_each_safe(l, n, &signal_queue_head) { + item = list_entry(l, struct queue_item, next_signal); + list_del(&item->next_signal); + kmem_cache_free(tipc_queue_item_cache, item); + } + spin_unlock_bh(&qitem_lock); + + kmem_cache_destroy(tipc_queue_item_cache); +} + diff --git a/net/tipc/link.c b/net/tipc/link.c new file mode 100644 index 00000000000..7265f4be476 --- /dev/null +++ b/net/tipc/link.c @@ -0,0 +1,3167 @@ +/* + * net/tipc/link.c: TIPC link code + * + * Copyright (c) 1996-2006, Ericsson AB + * Copyright (c) 2004-2005, Wind River Systems + * All rights reserved. + * + * Redistribution and use in source and binary forms, with or without + * modification, are permitted provided that the following conditions are met: + * + * 1. Redistributions of source code must retain the above copyright + * notice, this list of conditions and the following disclaimer. + * 2. Redistributions in binary form must reproduce the above copyright + * notice, this list of conditions and the following disclaimer in the + * documentation and/or other materials provided with the distribution. + * 3. Neither the names of the copyright holders nor the names of its + * contributors may be used to endorse or promote products derived from + * this software without specific prior written permission. + * + * Alternatively, this software may be distributed under the terms of the + * GNU General Public License ("GPL") version 2 as published by the Free + * Software Foundation. + * + * THIS SOFTWARE IS PROVIDED BY THE COPYRIGHT HOLDERS AND CONTRIBUTORS "AS IS" + * AND ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT LIMITED TO, THE + * IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR A PARTICULAR PURPOSE + * ARE DISCLAIMED. IN NO EVENT SHALL THE COPYRIGHT OWNER OR CONTRIBUTORS BE + * LIABLE FOR ANY DIRECT, INDIRECT, INCIDENTAL, SPECIAL, EXEMPLARY, OR + * CONSEQUENTIAL DAMAGES (INCLUDING, BUT NOT LIMITED TO, PROCUREMENT OF + * SUBSTITUTE GOODS OR SERVICES; LOSS OF USE, DATA, OR PROFITS; OR BUSINESS + * INTERRUPTION) HOWEVER CAUSED AND ON ANY THEORY OF LIABILITY, WHETHER IN + * CONTRACT, STRICT LIABILITY, OR TORT (INCLUDING NEGLIGENCE OR OTHERWISE) + * ARISING IN ANY WAY OUT OF THE USE OF THIS SOFTWARE, EVEN IF ADVISED OF THE + * POSSIBILITY OF SUCH DAMAGE. + */ + +#include "core.h" +#include "dbg.h" +#include "link.h" +#include "net.h" +#include "node.h" +#include "port.h" +#include "addr.h" +#include "node_subscr.h" +#include "name_distr.h" +#include "bearer.h" +#include "name_table.h" +#include "discover.h" +#include "config.h" +#include "bcast.h" + + +/* + * Limit for deferred reception queue: + */ + +#define DEF_QUEUE_LIMIT 256u + +/* + * Link state events: + */ + +#define STARTING_EVT 856384768 /* link processing trigger */ +#define TRAFFIC_MSG_EVT 560815u /* rx'd ??? */ +#define TIMEOUT_EVT 560817u /* link timer expired */ + +/* + * The following two 'message types' is really just implementation + * data conveniently stored in the message header. + * They must not be considered part of the protocol + */ +#define OPEN_MSG 0 +#define CLOSED_MSG 1 + +/* + * State value stored in 'exp_msg_count' + */ + +#define START_CHANGEOVER 100000u + +/** + * struct link_name - deconstructed link name + * @addr_local: network address of node at this end + * @if_local: name of interface at this end + * @addr_peer: network address of node at far end + * @if_peer: name of interface at far end + */ + +struct link_name { + u32 addr_local; + char if_local[TIPC_MAX_IF_NAME]; + u32 addr_peer; + char if_peer[TIPC_MAX_IF_NAME]; +}; + +#if 0 + +/* LINK EVENT CODE IS NOT SUPPORTED AT PRESENT */ + +/** + * struct link_event - link up/down event notification + */ + +struct link_event { + u32 addr; + int up; + void (*fcn)(u32, char *, int); + char name[TIPC_MAX_LINK_NAME]; +}; + +#endif + +static void link_handle_out_of_seq_msg(struct link *l_ptr, + struct sk_buff *buf); +static void link_recv_proto_msg(struct link *l_ptr, struct sk_buff *buf); +static int link_recv_changeover_msg(struct link **l_ptr, struct sk_buff **buf); +static void link_set_supervision_props(struct link *l_ptr, u32 tolerance); +static int link_send_sections_long(struct port *sender, + struct iovec const *msg_sect, + u32 num_sect, u32 destnode); +static void link_check_defragm_bufs(struct link *l_ptr); +static void link_state_event(struct link *l_ptr, u32 event); +static void link_reset_statistics(struct link *l_ptr); +static void link_print(struct link *l_ptr, struct print_buf *buf, + const char *str); + +/* + * Debugging code used by link routines only + * + * When debugging link problems on a system that has multiple links, + * the standard TIPC debugging routines may not be useful since they + * allow the output from multiple links to be intermixed. For this reason + * routines of the form "dbg_link_XXX()" have been created that will capture + * debug info into a link's personal print buffer, which can then be dumped + * into the TIPC system log (LOG) upon request. + * + * To enable per-link debugging, use LINK_LOG_BUF_SIZE to specify the size + * of the print buffer used by each link. If LINK_LOG_BUF_SIZE is set to 0, + * the dbg_link_XXX() routines simply send their output to the standard + * debug print buffer (DBG_OUTPUT), if it has been defined; this can be useful + * when there is only a single link in the system being debugged. + * + * Notes: + * - When enabled, LINK_LOG_BUF_SIZE should be set to at least 1000 (bytes) + * - "l_ptr" must be valid when using dbg_link_XXX() macros + */ + +#define LINK_LOG_BUF_SIZE 0 + +#define dbg_link(fmt, arg...) do {if (LINK_LOG_BUF_SIZE) tipc_printf(&l_ptr->print_buf, fmt, ## arg); } while(0) +#define dbg_link_msg(msg, txt) do {if (LINK_LOG_BUF_SIZE) msg_print(&l_ptr->print_buf, msg, txt); } while(0) +#define dbg_link_state(txt) do {if (LINK_LOG_BUF_SIZE) link_print(l_ptr, &l_ptr->print_buf, txt); } while(0) +#define dbg_link_dump() do { \ + if (LINK_LOG_BUF_SIZE) { \ + tipc_printf(LOG, "\n\nDumping link <%s>:\n", l_ptr->name); \ + printbuf_move(LOG, &l_ptr->print_buf); \ + } \ +} while (0) + +static inline void dbg_print_link(struct link *l_ptr, const char *str) +{ + if (DBG_OUTPUT) + link_print(l_ptr, DBG_OUTPUT, str); +} + +static inline void dbg_print_buf_chain(struct sk_buff *root_buf) +{ + if (DBG_OUTPUT) { + struct sk_buff *buf = root_buf; + + while (buf) { + msg_dbg(buf_msg(buf), "In chain: "); + buf = buf->next; + } + } +} + +/* + * Simple inlined link routines + */ + +static inline unsigned int align(unsigned int i) +{ + return (i + 3) & ~3u; +} + +static inline int link_working_working(struct link *l_ptr) +{ + return (l_ptr->state == WORKING_WORKING); +} + +static inline int link_working_unknown(struct link *l_ptr) +{ + return (l_ptr->state == WORKING_UNKNOWN); +} + +static inline int link_reset_unknown(struct link *l_ptr) +{ + return (l_ptr->state == RESET_UNKNOWN); +} + +static inline int link_reset_reset(struct link *l_ptr) +{ + return (l_ptr->state == RESET_RESET); +} + +static inline int link_blocked(struct link *l_ptr) +{ + return (l_ptr->exp_msg_count || l_ptr->blocked); +} + +static inline int link_congested(struct link *l_ptr) +{ + return (l_ptr->out_queue_size >= l_ptr->queue_limit[0]); +} + +static inline u32 link_max_pkt(struct link *l_ptr) +{ + return l_ptr->max_pkt; +} + +static inline void link_init_max_pkt(struct link *l_ptr) +{ + u32 max_pkt; + + max_pkt = (l_ptr->b_ptr->publ.mtu & ~3); + if (max_pkt > MAX_MSG_SIZE) + max_pkt = MAX_MSG_SIZE; + + l_ptr->max_pkt_target = max_pkt; + if (l_ptr->max_pkt_target < MAX_PKT_DEFAULT) + l_ptr->max_pkt = l_ptr->max_pkt_target; + else + l_ptr->max_pkt = MAX_PKT_DEFAULT; + + l_ptr->max_pkt_probes = 0; +} + +static inline u32 link_next_sent(struct link *l_ptr) +{ + if (l_ptr->next_out) + return msg_seqno(buf_msg(l_ptr->next_out)); + return mod(l_ptr->next_out_no); +} + +static inline u32 link_last_sent(struct link *l_ptr) +{ + return mod(link_next_sent(l_ptr) - 1); +} + +/* + * Simple non-inlined link routines (i.e. referenced outside this file) + */ + +int link_is_up(struct link *l_ptr) +{ + if (!l_ptr) + return 0; + return (link_working_working(l_ptr) || link_working_unknown(l_ptr)); +} + +int link_is_active(struct link *l_ptr) +{ + return ((l_ptr->owner->active_links[0] == l_ptr) || + (l_ptr->owner->active_links[1] == l_ptr)); +} + +/** + * link_name_validate - validate & (optionally) deconstruct link name + * @name - ptr to link name string + * @name_parts - ptr to area for link name components (or NULL if not needed) + * + * Returns 1 if link name is valid, otherwise 0. + */ + +static int link_name_validate(const char *name, struct link_name *name_parts) +{ + char name_copy[TIPC_MAX_LINK_NAME]; + char *addr_local; + char *if_local; + char *addr_peer; + char *if_peer; + char dummy; + u32 z_local, c_local, n_local; + u32 z_peer, c_peer, n_peer; + u32 if_local_len; + u32 if_peer_len; + + /* copy link name & ensure length is OK */ + + name_copy[TIPC_MAX_LINK_NAME - 1] = 0; + /* need above in case non-Posix strncpy() doesn't pad with nulls */ + strncpy(name_copy, name, TIPC_MAX_LINK_NAME); + if (name_copy[TIPC_MAX_LINK_NAME - 1] != 0) + return 0; + + /* ensure all component parts of link name are present */ + + addr_local = name_copy; + if ((if_local = strchr(addr_local, ':')) == NULL) + return 0; + *(if_local++) = 0; + if ((addr_peer = strchr(if_local, '-')) == NULL) + return 0; + *(addr_peer++) = 0; + if_local_len = addr_peer - if_local; + if ((if_peer = strchr(addr_peer, ':')) == NULL) + return 0; + *(if_peer++) = 0; + if_peer_len = strlen(if_peer) + 1; + + /* validate component parts of link name */ + + if ((sscanf(addr_local, "%u.%u.%u%c", + &z_local, &c_local, &n_local, &dummy) != 3) || + (sscanf(addr_peer, "%u.%u.%u%c", + &z_peer, &c_peer, &n_peer, &dummy) != 3) || + (z_local > 255) || (c_local > 4095) || (n_local > 4095) || + (z_peer > 255) || (c_peer > 4095) || (n_peer > 4095) || + (if_local_len <= 1) || (if_local_len > TIPC_MAX_IF_NAME) || + (if_peer_len <= 1) || (if_peer_len > TIPC_MAX_IF_NAME) || + (strspn(if_local, tipc_alphabet) != (if_local_len - 1)) || + (strspn(if_peer, tipc_alphabet) != (if_peer_len - 1))) + return 0; + + /* return link name components, if necessary */ + + if (name_parts) { + name_parts->addr_local = tipc_addr(z_local, c_local, n_local); + strcpy(name_parts->if_local, if_local); + name_parts->addr_peer = tipc_addr(z_peer, c_peer, n_peer); + strcpy(name_parts->if_peer, if_peer); + } + return 1; +} + +/** + * link_timeout - handle expiration of link timer + * @l_ptr: pointer to link + * + * This routine must not grab "net_lock" to avoid a potential deadlock conflict + * with link_delete(). (There is no risk that the node will be deleted by + * another thread because link_delete() always cancels the link timer before + * node_delete() is called.) + */ + +static void link_timeout(struct link *l_ptr) +{ + node_lock(l_ptr->owner); + + /* update counters used in statistical profiling of send traffic */ + + l_ptr->stats.accu_queue_sz += l_ptr->out_queue_size; + l_ptr->stats.queue_sz_counts++; + + if (l_ptr->out_queue_size > l_ptr->stats.max_queue_sz) + l_ptr->stats.max_queue_sz = l_ptr->out_queue_size; + + if (l_ptr->first_out) { + struct tipc_msg *msg = buf_msg(l_ptr->first_out); + u32 length = msg_size(msg); + + if ((msg_user(msg) == MSG_FRAGMENTER) + && (msg_type(msg) == FIRST_FRAGMENT)) { + length = msg_size(msg_get_wrapped(msg)); + } + if (length) { + l_ptr->stats.msg_lengths_total += length; + l_ptr->stats.msg_length_counts++; + if (length <= 64) + l_ptr->stats.msg_length_profile[0]++; + else if (length <= 256) + l_ptr->stats.msg_length_profile[1]++; + else if (length <= 1024) + l_ptr->stats.msg_length_profile[2]++; + else if (length <= 4096) + l_ptr->stats.msg_length_profile[3]++; + else if (length <= 16384) + l_ptr->stats.msg_length_profile[4]++; + else if (length <= 32768) + l_ptr->stats.msg_length_profile[5]++; + else + l_ptr->stats.msg_length_profile[6]++; + } + } + + /* do all other link processing performed on a periodic basis */ + + link_check_defragm_bufs(l_ptr); + + link_state_event(l_ptr, TIMEOUT_EVT); + + if (l_ptr->next_out) + link_push_queue(l_ptr); + + node_unlock(l_ptr->owner); +} + +static inline void link_set_timer(struct link *l_ptr, u32 time) +{ + k_start_timer(&l_ptr->timer, time); +} + +/** + * link_create - create a new link + * @b_ptr: pointer to associated bearer + * @peer: network address of node at other end of link + * @media_addr: media address to use when sending messages over link + * + * Returns pointer to link. + */ + +struct link *link_create(struct bearer *b_ptr, const u32 peer, + const struct tipc_media_addr *media_addr) +{ + struct link *l_ptr; + struct tipc_msg *msg; + char *if_name; + + l_ptr = (struct link *)kmalloc(sizeof(*l_ptr), GFP_ATOMIC); + if (!l_ptr) { + warn("Memory squeeze; Failed to create link\n"); + return NULL; + } + memset(l_ptr, 0, sizeof(*l_ptr)); + + l_ptr->addr = peer; + if_name = strchr(b_ptr->publ.name, ':') + 1; + sprintf(l_ptr->name, "%u.%u.%u:%s-%u.%u.%u:", + tipc_zone(tipc_own_addr), tipc_cluster(tipc_own_addr), + tipc_node(tipc_own_addr), + if_name, + tipc_zone(peer), tipc_cluster(peer), tipc_node(peer)); + /* note: peer i/f is appended to link name by reset/activate */ + memcpy(&l_ptr->media_addr, media_addr, sizeof(*media_addr)); + k_init_timer(&l_ptr->timer, (Handler)link_timeout, (unsigned long)l_ptr); + list_add_tail(&l_ptr->link_list, &b_ptr->links); + l_ptr->checkpoint = 1; + l_ptr->b_ptr = b_ptr; + link_set_supervision_props(l_ptr, b_ptr->media->tolerance); + l_ptr->state = RESET_UNKNOWN; + + l_ptr->pmsg = (struct tipc_msg *)&l_ptr->proto_msg; + msg = l_ptr->pmsg; + msg_init(msg, LINK_PROTOCOL, RESET_MSG, TIPC_OK, INT_H_SIZE, l_ptr->addr); + msg_set_size(msg, sizeof(l_ptr->proto_msg)); + msg_set_session(msg, tipc_random); + msg_set_bearer_id(msg, b_ptr->identity); + strcpy((char *)msg_data(msg), if_name); + + l_ptr->priority = b_ptr->priority; + link_set_queue_limits(l_ptr, b_ptr->media->window); + + link_init_max_pkt(l_ptr); + + l_ptr->next_out_no = 1; + INIT_LIST_HEAD(&l_ptr->waiting_ports); + + link_reset_statistics(l_ptr); + + l_ptr->owner = node_attach_link(l_ptr); + if (!l_ptr->owner) { + kfree(l_ptr); + return NULL; + } + + if (LINK_LOG_BUF_SIZE) { + char *pb = kmalloc(LINK_LOG_BUF_SIZE, GFP_ATOMIC); + + if (!pb) { + kfree(l_ptr); + warn("Memory squeeze; Failed to create link\n"); + return NULL; + } + printbuf_init(&l_ptr->print_buf, pb, LINK_LOG_BUF_SIZE); + } + + k_signal((Handler)link_start, (unsigned long)l_ptr); + + dbg("link_create(): tolerance = %u,cont intv = %u, abort_limit = %u\n", + l_ptr->tolerance, l_ptr->continuity_interval, l_ptr->abort_limit); + + return l_ptr; +} + +/** + * link_delete - delete a link + * @l_ptr: pointer to link + * + * Note: 'net_lock' is write_locked, bearer is locked. + * This routine must not grab the node lock until after link timer cancellation + * to avoid a potential deadlock situation. + */ + +void link_delete(struct link *l_ptr) +{ + if (!l_ptr) { + err("Attempt to delete non-existent link\n"); + return; + } + + dbg("link_delete()\n"); + + k_cancel_timer(&l_ptr->timer); + + node_lock(l_ptr->owner); + link_reset(l_ptr); + node_detach_link(l_ptr->owner, l_ptr); + link_stop(l_ptr); + list_del_init(&l_ptr->link_list); + if (LINK_LOG_BUF_SIZE) + kfree(l_ptr->print_buf.buf); + node_unlock(l_ptr->owner); + k_term_timer(&l_ptr->timer); + kfree(l_ptr); +} + +void link_start(struct link *l_ptr) +{ + dbg("link_start %x\n", l_ptr); + link_state_event(l_ptr, STARTING_EVT); +} + +/** + * link_schedule_port - schedule port for deferred sending + * @l_ptr: pointer to link + * @origport: reference to sending port + * @sz: amount of data to be sent + * + * Schedules port for renewed sending of messages after link congestion + * has abated. + */ + +static int link_schedule_port(struct link *l_ptr, u32 origport, u32 sz) +{ + struct port *p_ptr; + + spin_lock_bh(&port_list_lock); + p_ptr = port_lock(origport); + if (p_ptr) { + if (!p_ptr->wakeup) + goto exit; + if (!list_empty(&p_ptr->wait_list)) + goto exit; + p_ptr->congested_link = l_ptr; + p_ptr->publ.congested = 1; + p_ptr->waiting_pkts = 1 + ((sz - 1) / link_max_pkt(l_ptr)); + list_add_tail(&p_ptr->wait_list, &l_ptr->waiting_ports); + l_ptr->stats.link_congs++; +exit: + port_unlock(p_ptr); + } + spin_unlock_bh(&port_list_lock); + return -ELINKCONG; +} + +void link_wakeup_ports(struct link *l_ptr, int all) +{ + struct port *p_ptr; + struct port *temp_p_ptr; + int win = l_ptr->queue_limit[0] - l_ptr->out_queue_size; + + if (all) + win = 100000; + if (win <= 0) + return; + if (!spin_trylock_bh(&port_list_lock)) + return; + if (link_congested(l_ptr)) + goto exit; + list_for_each_entry_safe(p_ptr, temp_p_ptr, &l_ptr->waiting_ports, + wait_list) { + if (win <= 0) + break; + list_del_init(&p_ptr->wait_list); + p_ptr->congested_link = 0; + assert(p_ptr->wakeup); + spin_lock_bh(p_ptr->publ.lock); + p_ptr->publ.congested = 0; + p_ptr->wakeup(&p_ptr->publ); + win -= p_ptr->waiting_pkts; + spin_unlock_bh(p_ptr->publ.lock); + } + +exit: + spin_unlock_bh(&port_list_lock); +} + +/** + * link_release_outqueue - purge link's outbound message queue + * @l_ptr: pointer to link + */ + +static void link_release_outqueue(struct link *l_ptr) +{ + struct sk_buff *buf = l_ptr->first_out; + struct sk_buff *next; + + while (buf) { + next = buf->next; + buf_discard(buf); + buf = next; + } + l_ptr->first_out = NULL; + l_ptr->out_queue_size = 0; +} + +/** + * link_reset_fragments - purge link's inbound message fragments queue + * @l_ptr: pointer to link + */ + +void link_reset_fragments(struct link *l_ptr) +{ + struct sk_buff *buf = l_ptr->defragm_buf; + struct sk_buff *next; + + while (buf) { + next = buf->next; + buf_discard(buf); + buf = next; + } + l_ptr->defragm_buf = NULL; +} + +/** + * link_stop - purge all inbound and outbound messages associated with link + * @l_ptr: pointer to link + */ + +void link_stop(struct link *l_ptr) +{ + struct sk_buff *buf; + struct sk_buff *next; + + buf = l_ptr->oldest_deferred_in; + while (buf) { + next = buf->next; + buf_discard(buf); + buf = next; + } + + buf = l_ptr->first_out; + while (buf) { + next = buf->next; + buf_discard(buf); + buf = next; + } + + link_reset_fragments(l_ptr); + + buf_discard(l_ptr->proto_msg_queue); + l_ptr->proto_msg_queue = NULL; +} + +#if 0 + +/* LINK EVENT CODE IS NOT SUPPORTED AT PRESENT */ + +static void link_recv_event(struct link_event *ev) +{ + ev->fcn(ev->addr, ev->name, ev->up); + kfree(ev); +} + +static void link_send_event(void (*fcn)(u32 a, char *n, int up), + struct link *l_ptr, int up) +{ + struct link_event *ev; + + ev = kmalloc(sizeof(*ev), GFP_ATOMIC); + if (!ev) { + warn("Link event allocation failure\n"); + return; + } + ev->addr = l_ptr->addr; + ev->up = up; + ev->fcn = fcn; + memcpy(ev->name, l_ptr->name, TIPC_MAX_LINK_NAME); + k_signal((Handler)link_recv_event, (unsigned long)ev); +} + +#else + +#define link_send_event(fcn, l_ptr, up) do { } while (0) + +#endif + +void link_reset(struct link *l_ptr) +{ + struct sk_buff *buf; + u32 prev_state = l_ptr->state; + u32 checkpoint = l_ptr->next_in_no; + + msg_set_session(l_ptr->pmsg, msg_session(l_ptr->pmsg) + 1); + + /* Link is down, accept any session: */ + l_ptr->peer_session = 0; + + /* Prepare for max packet size negotiation */ + link_init_max_pkt(l_ptr); + + l_ptr->state = RESET_UNKNOWN; + dbg_link_state("Resetting Link\n"); + + if ((prev_state == RESET_UNKNOWN) || (prev_state == RESET_RESET)) + return; + + node_link_down(l_ptr->owner, l_ptr); + bearer_remove_dest(l_ptr->b_ptr, l_ptr->addr); +#if 0 + tipc_printf(CONS, "\nReset link <%s>\n", l_ptr->name); + dbg_link_dump(); +#endif + if (node_has_active_links(l_ptr->owner) && + l_ptr->owner->permit_changeover) { + l_ptr->reset_checkpoint = checkpoint; + l_ptr->exp_msg_count = START_CHANGEOVER; + } + + /* Clean up all queues: */ + + link_release_outqueue(l_ptr); + buf_discard(l_ptr->proto_msg_queue); + l_ptr->proto_msg_queue = NULL; + buf = l_ptr->oldest_deferred_in; + while (buf) { + struct sk_buff *next = buf->next; + buf_discard(buf); + buf = next; + } + if (!list_empty(&l_ptr->waiting_ports)) + link_wakeup_ports(l_ptr, 1); + + l_ptr->retransm_queue_head = 0; + l_ptr->retransm_queue_size = 0; + l_ptr->last_out = NULL; + l_ptr->first_out = NULL; + l_ptr->next_out = NULL; + l_ptr->unacked_window = 0; + l_ptr->checkpoint = 1; + l_ptr->next_out_no = 1; + l_ptr->deferred_inqueue_sz = 0; + l_ptr->oldest_deferred_in = NULL; + l_ptr->newest_deferred_in = NULL; + l_ptr->fsm_msg_cnt = 0; + l_ptr->stale_count = 0; + link_reset_statistics(l_ptr); + + link_send_event(cfg_link_event, l_ptr, 0); + if (!in_own_cluster(l_ptr->addr)) + link_send_event(disc_link_event, l_ptr, 0); +} + + +static void link_activate(struct link *l_ptr) +{ + l_ptr->next_in_no = 1; + node_link_up(l_ptr->owner, l_ptr); + bearer_add_dest(l_ptr->b_ptr, l_ptr->addr); + link_send_event(cfg_link_event, l_ptr, 1); + if (!in_own_cluster(l_ptr->addr)) + link_send_event(disc_link_event, l_ptr, 1); +} + +/** + * link_state_event - link finite state machine + * @l_ptr: pointer to link + * @event: state machine event to process + */ + +static void link_state_event(struct link *l_ptr, unsigned event) +{ + struct link *other; + u32 cont_intv = l_ptr->continuity_interval; + + if (!l_ptr->started && (event != STARTING_EVT)) + return; /* Not yet. */ + + if (link_blocked(l_ptr)) { + if (event == TIMEOUT_EVT) { + link_set_timer(l_ptr, cont_intv); + } + return; /* Changeover going on */ + } + dbg_link("STATE_EV: <%s> ", l_ptr->name); + + switch (l_ptr->state) { + case WORKING_WORKING: + dbg_link("WW/"); + switch (event) { + case TRAFFIC_MSG_EVT: + dbg_link("TRF-"); + /* fall through */ + case ACTIVATE_MSG: + dbg_link("ACT\n"); + break; + case TIMEOUT_EVT: + dbg_link("TIM "); + if (l_ptr->next_in_no != l_ptr->checkpoint) { + l_ptr->checkpoint = l_ptr->next_in_no; + if (bclink_acks_missing(l_ptr->owner)) { + link_send_proto_msg(l_ptr, STATE_MSG, + 0, 0, 0, 0, 0); + l_ptr->fsm_msg_cnt++; + } else if (l_ptr->max_pkt < l_ptr->max_pkt_target) { + link_send_proto_msg(l_ptr, STATE_MSG, + 1, 0, 0, 0, 0); + l_ptr->fsm_msg_cnt++; + } + link_set_timer(l_ptr, cont_intv); + break; + } + dbg_link(" -> WU\n"); + l_ptr->state = WORKING_UNKNOWN; + l_ptr->fsm_msg_cnt = 0; + link_send_proto_msg(l_ptr, STATE_MSG, 1, 0, 0, 0, 0); + l_ptr->fsm_msg_cnt++; + link_set_timer(l_ptr, cont_intv / 4); + break; + case RESET_MSG: + dbg_link("RES -> RR\n"); + link_reset(l_ptr); + l_ptr->state = RESET_RESET; + l_ptr->fsm_msg_cnt = 0; + link_send_proto_msg(l_ptr, ACTIVATE_MSG, 0, 0, 0, 0, 0); + l_ptr->fsm_msg_cnt++; + link_set_timer(l_ptr, cont_intv); + break; + default: + err("Unknown link event %u in WW state\n", event); + } + break; + case WORKING_UNKNOWN: + dbg_link("WU/"); + switch (event) { + case TRAFFIC_MSG_EVT: + dbg_link("TRF-"); + case ACTIVATE_MSG: + dbg_link("ACT -> WW\n"); + l_ptr->state = WORKING_WORKING; + l_ptr->fsm_msg_cnt = 0; + link_set_timer(l_ptr, cont_intv); + break; + case RESET_MSG: + dbg_link("RES -> RR\n"); + link_reset(l_ptr); + l_ptr->state = RESET_RESET; + l_ptr->fsm_msg_cnt = 0; + link_send_proto_msg(l_ptr, ACTIVATE_MSG, 0, 0, 0, 0, 0); + l_ptr->fsm_msg_cnt++; + link_set_timer(l_ptr, cont_intv); + break; + case TIMEOUT_EVT: + dbg_link("TIM "); + if (l_ptr->next_in_no != l_ptr->checkpoint) { + dbg_link("-> WW \n"); + l_ptr->state = WORKING_WORKING; + l_ptr->fsm_msg_cnt = 0; + l_ptr->checkpoint = l_ptr->next_in_no; + if (bclink_acks_missing(l_ptr->owner)) { + link_send_proto_msg(l_ptr, STATE_MSG, + 0, 0, 0, 0, 0); + l_ptr->fsm_msg_cnt++; + } + link_set_timer(l_ptr, cont_intv); + } else if (l_ptr->fsm_msg_cnt < l_ptr->abort_limit) { + dbg_link("Probing %u/%u,timer = %u ms)\n", + l_ptr->fsm_msg_cnt, l_ptr->abort_limit, + cont_intv / 4); + link_send_proto_msg(l_ptr, STATE_MSG, + 1, 0, 0, 0, 0); + l_ptr->fsm_msg_cnt++; + link_set_timer(l_ptr, cont_intv / 4); + } else { /* Link has failed */ + dbg_link("-> RU (%u probes unanswered)\n", + l_ptr->fsm_msg_cnt); + link_reset(l_ptr); + l_ptr->state = RESET_UNKNOWN; + l_ptr->fsm_msg_cnt = 0; + link_send_proto_msg(l_ptr, RESET_MSG, + 0, 0, 0, 0, 0); + l_ptr->fsm_msg_cnt++; + link_set_timer(l_ptr, cont_intv); + } + break; + default: + err("Unknown link event %u in WU state\n", event); + } + break; + case RESET_UNKNOWN: + dbg_link("RU/"); + switch (event) { + case TRAFFIC_MSG_EVT: + dbg_link("TRF-\n"); + break; + case ACTIVATE_MSG: + other = l_ptr->owner->active_links[0]; + if (other && link_working_unknown(other)) { + dbg_link("ACT\n"); + break; + } + dbg_link("ACT -> WW\n"); + l_ptr->state = WORKING_WORKING; + l_ptr->fsm_msg_cnt = 0; + link_activate(l_ptr); + link_send_proto_msg(l_ptr, STATE_MSG, 1, 0, 0, 0, 0); + l_ptr->fsm_msg_cnt++; + link_set_timer(l_ptr, cont_intv); + break; + case RESET_MSG: + dbg_link("RES \n"); + dbg_link(" -> RR\n"); + l_ptr->state = RESET_RESET; + l_ptr->fsm_msg_cnt = 0; + link_send_proto_msg(l_ptr, ACTIVATE_MSG, 1, 0, 0, 0, 0); + l_ptr->fsm_msg_cnt++; + link_set_timer(l_ptr, cont_intv); + break; + case STARTING_EVT: + dbg_link("START-"); + l_ptr->started = 1; + /* fall through */ + case TIMEOUT_EVT: + dbg_link("TIM \n"); + link_send_proto_msg(l_ptr, RESET_MSG, 0, 0, 0, 0, 0); + l_ptr->fsm_msg_cnt++; + link_set_timer(l_ptr, cont_intv); + break; + default: + err("Unknown link event %u in RU state\n", event); + } + break; + case RESET_RESET: + dbg_link("RR/ "); + switch (event) { + case TRAFFIC_MSG_EVT: + dbg_link("TRF-"); + /* fall through */ + case ACTIVATE_MSG: + other = l_ptr->owner->active_links[0]; + if (other && link_working_unknown(other)) { + dbg_link("ACT\n"); + break; + } + dbg_link("ACT -> WW\n"); + l_ptr->state = WORKING_WORKING; + l_ptr->fsm_msg_cnt = 0; + link_activate(l_ptr); + link_send_proto_msg(l_ptr, STATE_MSG, 1, 0, 0, 0, 0); + l_ptr->fsm_msg_cnt++; + link_set_timer(l_ptr, cont_intv); + break; + case RESET_MSG: + dbg_link("RES\n"); + break; + case TIMEOUT_EVT: + dbg_link("TIM\n"); + link_send_proto_msg(l_ptr, ACTIVATE_MSG, 0, 0, 0, 0, 0); + l_ptr->fsm_msg_cnt++; + link_set_timer(l_ptr, cont_intv); + dbg_link("fsm_msg_cnt %u\n", l_ptr->fsm_msg_cnt); + break; + default: + err("Unknown link event %u in RR state\n", event); + } + break; + default: + err("Unknown link state %u/%u\n", l_ptr->state, event); + } +} + +/* + * link_bundle_buf(): Append contents of a buffer to + * the tail of an existing one. + */ + +static int link_bundle_buf(struct link *l_ptr, + struct sk_buff *bundler, + struct sk_buff *buf) +{ + struct tipc_msg *bundler_msg = buf_msg(bundler); + struct tipc_msg *msg = buf_msg(buf); + u32 size = msg_size(msg); + u32 to_pos = align(msg_size(bundler_msg)); + u32 rest = link_max_pkt(l_ptr) - to_pos; + + if (msg_user(bundler_msg) != MSG_BUNDLER) + return 0; + if (msg_type(bundler_msg) != OPEN_MSG) + return 0; + if (rest < align(size)) + return 0; + + skb_put(bundler, (to_pos - msg_size(bundler_msg)) + size); + memcpy(bundler->data + to_pos, buf->data, size); + msg_set_size(bundler_msg, to_pos + size); + msg_set_msgcnt(bundler_msg, msg_msgcnt(bundler_msg) + 1); + dbg("Packed msg # %u(%u octets) into pos %u in buf(#%u)\n", + msg_msgcnt(bundler_msg), size, to_pos, msg_seqno(bundler_msg)); + msg_dbg(msg, "PACKD:"); + buf_discard(buf); + l_ptr->stats.sent_bundled++; + return 1; +} + +static inline void link_add_to_outqueue(struct link *l_ptr, + struct sk_buff *buf, + struct tipc_msg *msg) +{ + u32 ack = mod(l_ptr->next_in_no - 1); + u32 seqno = mod(l_ptr->next_out_no++); + + msg_set_word(msg, 2, ((ack << 16) | seqno)); + msg_set_bcast_ack(msg, l_ptr->owner->bclink.last_in); + buf->next = NULL; + if (l_ptr->first_out) { + l_ptr->last_out->next = buf; + l_ptr->last_out = buf; + } else + l_ptr->first_out = l_ptr->last_out = buf; + l_ptr->out_queue_size++; +} + +/* + * link_send_buf() is the 'full path' for messages, called from + * inside TIPC when the 'fast path' in tipc_send_buf + * has failed, and from link_send() + */ + +int link_send_buf(struct link *l_ptr, struct sk_buff *buf) +{ + struct tipc_msg *msg = buf_msg(buf); + u32 size = msg_size(msg); + u32 dsz = msg_data_sz(msg); + u32 queue_size = l_ptr->out_queue_size; + u32 imp = msg_tot_importance(msg); + u32 queue_limit = l_ptr->queue_limit[imp]; + u32 max_packet = link_max_pkt(l_ptr); + + msg_set_prevnode(msg, tipc_own_addr); /* If routed message */ + + /* Match msg importance against queue limits: */ + + if (unlikely(queue_size >= queue_limit)) { + if (imp <= TIPC_CRITICAL_IMPORTANCE) { + return link_schedule_port(l_ptr, msg_origport(msg), + size); + } + msg_dbg(msg, "TIPC: Congestion, throwing away\n"); + buf_discard(buf); + if (imp > CONN_MANAGER) { + warn("Resetting <%s>, send queue full", l_ptr->name); + link_reset(l_ptr); + } + return dsz; + } + + /* Fragmentation needed ? */ + + if (size > max_packet) + return link_send_long_buf(l_ptr, buf); + + /* Packet can be queued or sent: */ + + if (queue_size > l_ptr->stats.max_queue_sz) + l_ptr->stats.max_queue_sz = queue_size; + + if (likely(!bearer_congested(l_ptr->b_ptr, l_ptr) && + !link_congested(l_ptr))) { + link_add_to_outqueue(l_ptr, buf, msg); + + if (likely(bearer_send(l_ptr->b_ptr, buf, &l_ptr->media_addr))) { + l_ptr->unacked_window = 0; + } else { + bearer_schedule(l_ptr->b_ptr, l_ptr); + l_ptr->stats.bearer_congs++; + l_ptr->next_out = buf; + } + return dsz; + } + /* Congestion: can message be bundled ?: */ + + if ((msg_user(msg) != CHANGEOVER_PROTOCOL) && + (msg_user(msg) != MSG_FRAGMENTER)) { + + /* Try adding message to an existing bundle */ + + if (l_ptr->next_out && + link_bundle_buf(l_ptr, l_ptr->last_out, buf)) { + bearer_resolve_congestion(l_ptr->b_ptr, l_ptr); + return dsz; + } + + /* Try creating a new bundle */ + + if (size <= max_packet * 2 / 3) { + struct sk_buff *bundler = buf_acquire(max_packet); + struct tipc_msg bundler_hdr; + + if (bundler) { + msg_init(&bundler_hdr, MSG_BUNDLER, OPEN_MSG, + TIPC_OK, INT_H_SIZE, l_ptr->addr); + memcpy(bundler->data, (unchar *)&bundler_hdr, + INT_H_SIZE); + skb_trim(bundler, INT_H_SIZE); + link_bundle_buf(l_ptr, bundler, buf); + buf = bundler; + msg = buf_msg(buf); + l_ptr->stats.sent_bundles++; + } + } + } + if (!l_ptr->next_out) + l_ptr->next_out = buf; + link_add_to_outqueue(l_ptr, buf, msg); + bearer_resolve_congestion(l_ptr->b_ptr, l_ptr); + return dsz; +} + +/* + * link_send(): same as link_send_buf(), but the link to use has + * not been selected yet, and the the owner node is not locked + * Called by TIPC internal users, e.g. the name distributor + */ + +int link_send(struct sk_buff *buf, u32 dest, u32 selector) +{ + struct link *l_ptr; + struct node *n_ptr; + int res = -ELINKCONG; + + read_lock_bh(&net_lock); + n_ptr = node_select(dest, selector); + if (n_ptr) { + node_lock(n_ptr); + l_ptr = n_ptr->active_links[selector & 1]; + dbg("link_send: found link %x for dest %x\n", l_ptr, dest); + if (l_ptr) { + res = link_send_buf(l_ptr, buf); + } + node_unlock(n_ptr); + } else { + dbg("Attempt to send msg to unknown node:\n"); + msg_dbg(buf_msg(buf),">>>"); + buf_discard(buf); + } + read_unlock_bh(&net_lock); + return res; +} + +/* + * link_send_buf_fast: Entry for data messages where the + * destination link is known and the header is complete, + * inclusive total message length. Very time critical. + * Link is locked. Returns user data length. + */ + +static inline int link_send_buf_fast(struct link *l_ptr, struct sk_buff *buf, + u32 *used_max_pkt) +{ + struct tipc_msg *msg = buf_msg(buf); + int res = msg_data_sz(msg); + + if (likely(!link_congested(l_ptr))) { + if (likely(msg_size(msg) <= link_max_pkt(l_ptr))) { + if (likely(list_empty(&l_ptr->b_ptr->cong_links))) { + link_add_to_outqueue(l_ptr, buf, msg); + if (likely(bearer_send(l_ptr->b_ptr, buf, + &l_ptr->media_addr))) { + l_ptr->unacked_window = 0; + msg_dbg(msg,"SENT_FAST:"); + return res; + } + dbg("failed sent fast...\n"); + bearer_schedule(l_ptr->b_ptr, l_ptr); + l_ptr->stats.bearer_congs++; + l_ptr->next_out = buf; + return res; + } + } + else + *used_max_pkt = link_max_pkt(l_ptr); + } + return link_send_buf(l_ptr, buf); /* All other cases */ +} + +/* + * tipc_send_buf_fast: Entry for data messages where the + * destination node is known and the header is complete, + * inclusive total message length. + * Returns user data length. + */ +int tipc_send_buf_fast(struct sk_buff *buf, u32 destnode) +{ + struct link *l_ptr; + struct node *n_ptr; + int res; + u32 selector = msg_origport(buf_msg(buf)) & 1; + u32 dummy; + + if (destnode == tipc_own_addr) + return port_recv_msg(buf); + + read_lock_bh(&net_lock); + n_ptr = node_select(destnode, selector); + if (likely(n_ptr)) { + node_lock(n_ptr); + l_ptr = n_ptr->active_links[selector]; + dbg("send_fast: buf %x selected %x, destnode = %x\n", + buf, l_ptr, destnode); + if (likely(l_ptr)) { + res = link_send_buf_fast(l_ptr, buf, &dummy); + node_unlock(n_ptr); + read_unlock_bh(&net_lock); + return res; + } + node_unlock(n_ptr); + } + read_unlock_bh(&net_lock); + res = msg_data_sz(buf_msg(buf)); + tipc_reject_msg(buf, TIPC_ERR_NO_NODE); + return res; +} + + +/* + * link_send_sections_fast: Entry for messages where the + * destination processor is known and the header is complete, + * except for total message length. + * Returns user data length or errno. + */ +int link_send_sections_fast(struct port *sender, + struct iovec const *msg_sect, + const u32 num_sect, + u32 destaddr) +{ + struct tipc_msg *hdr = &sender->publ.phdr; + struct link *l_ptr; + struct sk_buff *buf; + struct node *node; + int res; + u32 selector = msg_origport(hdr) & 1; + + assert(destaddr != tipc_own_addr); + +again: + /* + * Try building message using port's max_pkt hint. + * (Must not hold any locks while building message.) + */ + + res = msg_build(hdr, msg_sect, num_sect, sender->max_pkt, + !sender->user_port, &buf); + + read_lock_bh(&net_lock); + node = node_select(destaddr, selector); + if (likely(node)) { + node_lock(node); + l_ptr = node->active_links[selector]; + if (likely(l_ptr)) { + if (likely(buf)) { + res = link_send_buf_fast(l_ptr, buf, + &sender->max_pkt); + if (unlikely(res < 0)) + buf_discard(buf); +exit: + node_unlock(node); + read_unlock_bh(&net_lock); + return res; + } + + /* Exit if build request was invalid */ + + if (unlikely(res < 0)) + goto exit; + + /* Exit if link (or bearer) is congested */ + + if (link_congested(l_ptr) || + !list_empty(&l_ptr->b_ptr->cong_links)) { + res = link_schedule_port(l_ptr, + sender->publ.ref, res); + goto exit; + } + + /* + * Message size exceeds max_pkt hint; update hint, + * then re-try fast path or fragment the message + */ + + sender->max_pkt = link_max_pkt(l_ptr); + node_unlock(node); + read_unlock_bh(&net_lock); + + + if ((msg_hdr_sz(hdr) + res) <= sender->max_pkt) + goto again; + + return link_send_sections_long(sender, msg_sect, + num_sect, destaddr); + } + node_unlock(node); + } + read_unlock_bh(&net_lock); + + /* Couldn't find a link to the destination node */ + + if (buf) + return tipc_reject_msg(buf, TIPC_ERR_NO_NODE); + if (res >= 0) + return port_reject_sections(sender, hdr, msg_sect, num_sect, + TIPC_ERR_NO_NODE); + return res; +} + +/* + * link_send_sections_long(): Entry for long messages where the + * destination node is known and the header is complete, + * inclusive total message length. + * Link and bearer congestion status have been checked to be ok, + * and are ignored if they change. + * + * Note that fragments do not use the full link MTU so that they won't have + * to undergo refragmentation if link changeover causes them to be sent + * over another link with an additional tunnel header added as prefix. + * (Refragmentation will still occur if the other link has a smaller MTU.) + * + * Returns user data length or errno. + */ +static int link_send_sections_long(struct port *sender, + struct iovec const *msg_sect, + u32 num_sect, + u32 destaddr) +{ + struct link *l_ptr; + struct node *node; + struct tipc_msg *hdr = &sender->publ.phdr; + u32 dsz = msg_data_sz(hdr); + u32 max_pkt,fragm_sz,rest; + struct tipc_msg fragm_hdr; + struct sk_buff *buf,*buf_chain,*prev; + u32 fragm_crs,fragm_rest,hsz,sect_rest; + const unchar *sect_crs; + int curr_sect; + u32 fragm_no; + +again: + fragm_no = 1; + max_pkt = sender->max_pkt - INT_H_SIZE; + /* leave room for tunnel header in case of link changeover */ + fragm_sz = max_pkt - INT_H_SIZE; + /* leave room for fragmentation header in each fragment */ + rest = dsz; + fragm_crs = 0; + fragm_rest = 0; + sect_rest = 0; + sect_crs = 0; + curr_sect = -1; + + /* Prepare reusable fragment header: */ + + msg_dbg(hdr, ">FRAGMENTING>"); + msg_init(&fragm_hdr, MSG_FRAGMENTER, FIRST_FRAGMENT, + TIPC_OK, INT_H_SIZE, msg_destnode(hdr)); + msg_set_link_selector(&fragm_hdr, sender->publ.ref); + msg_set_size(&fragm_hdr, max_pkt); + msg_set_fragm_no(&fragm_hdr, 1); + + /* Prepare header of first fragment: */ + + buf_chain = buf = buf_acquire(max_pkt); + if (!buf) + return -ENOMEM; + buf->next = NULL; + memcpy(buf->data, (unchar *)&fragm_hdr, INT_H_SIZE); + hsz = msg_hdr_sz(hdr); + memcpy(buf->data + INT_H_SIZE, (unchar *)hdr, hsz); + msg_dbg(buf_msg(buf), ">BUILD>"); + + /* Chop up message: */ + + fragm_crs = INT_H_SIZE + hsz; + fragm_rest = fragm_sz - hsz; + + do { /* For all sections */ + u32 sz; + + if (!sect_rest) { + sect_rest = msg_sect[++curr_sect].iov_len; + sect_crs = (const unchar *)msg_sect[curr_sect].iov_base; + } + + if (sect_rest < fragm_rest) + sz = sect_rest; + else + sz = fragm_rest; + + if (likely(!sender->user_port)) { + if (copy_from_user(buf->data + fragm_crs, sect_crs, sz)) { +error: + for (; buf_chain; buf_chain = buf) { + buf = buf_chain->next; + buf_discard(buf_chain); + } + return -EFAULT; + } + } else + memcpy(buf->data + fragm_crs, sect_crs, sz); + + sect_crs += sz; + sect_rest -= sz; + fragm_crs += sz; + fragm_rest -= sz; + rest -= sz; + + if (!fragm_rest && rest) { + + /* Initiate new fragment: */ + if (rest <= fragm_sz) { + fragm_sz = rest; + msg_set_type(&fragm_hdr,LAST_FRAGMENT); + } else { + msg_set_type(&fragm_hdr, FRAGMENT); + } + msg_set_size(&fragm_hdr, fragm_sz + INT_H_SIZE); + msg_set_fragm_no(&fragm_hdr, ++fragm_no); + prev = buf; + buf = buf_acquire(fragm_sz + INT_H_SIZE); + if (!buf) + goto error; + + buf->next = NULL; + prev->next = buf; + memcpy(buf->data, (unchar *)&fragm_hdr, INT_H_SIZE); + fragm_crs = INT_H_SIZE; + fragm_rest = fragm_sz; + msg_dbg(buf_msg(buf)," >BUILD>"); + } + } + while (rest > 0); + + /* + * Now we have a buffer chain. Select a link and check + * that packet size is still OK + */ + node = node_select(destaddr, sender->publ.ref & 1); + if (likely(node)) { + node_lock(node); + l_ptr = node->active_links[sender->publ.ref & 1]; + if (!l_ptr) { + node_unlock(node); + goto reject; + } + if (link_max_pkt(l_ptr) < max_pkt) { + sender->max_pkt = link_max_pkt(l_ptr); + node_unlock(node); + for (; buf_chain; buf_chain = buf) { + buf = buf_chain->next; + buf_discard(buf_chain); + } + goto again; + } + } else { +reject: + for (; buf_chain; buf_chain = buf) { + buf = buf_chain->next; + buf_discard(buf_chain); + } + return port_reject_sections(sender, hdr, msg_sect, num_sect, + TIPC_ERR_NO_NODE); + } + + /* Append whole chain to send queue: */ + + buf = buf_chain; + l_ptr->long_msg_seq_no = mod(l_ptr->long_msg_seq_no + 1); + if (!l_ptr->next_out) + l_ptr->next_out = buf_chain; + l_ptr->stats.sent_fragmented++; + while (buf) { + struct sk_buff *next = buf->next; + struct tipc_msg *msg = buf_msg(buf); + + l_ptr->stats.sent_fragments++; + msg_set_long_msgno(msg, l_ptr->long_msg_seq_no); + link_add_to_outqueue(l_ptr, buf, msg); + msg_dbg(msg, ">ADD>"); + buf = next; + } + + /* Send it, if possible: */ + + link_push_queue(l_ptr); + node_unlock(node); + return dsz; +} + +/* + * link_push_packet: Push one unsent packet to the media + */ +u32 link_push_packet(struct link *l_ptr) +{ + struct sk_buff *buf = l_ptr->first_out; + u32 r_q_size = l_ptr->retransm_queue_size; + u32 r_q_head = l_ptr->retransm_queue_head; + + /* Step to position where retransmission failed, if any, */ + /* consider that buffers may have been released in meantime */ + + if (r_q_size && buf) { + u32 last = lesser(mod(r_q_head + r_q_size), + link_last_sent(l_ptr)); + u32 first = msg_seqno(buf_msg(buf)); + + while (buf && less(first, r_q_head)) { + first = mod(first + 1); + buf = buf->next; + } + l_ptr->retransm_queue_head = r_q_head = first; + l_ptr->retransm_queue_size = r_q_size = mod(last - first); + } + + /* Continue retransmission now, if there is anything: */ + + if (r_q_size && buf && !skb_cloned(buf)) { + msg_set_ack(buf_msg(buf), mod(l_ptr->next_in_no - 1)); + msg_set_bcast_ack(buf_msg(buf), l_ptr->owner->bclink.last_in); + if (bearer_send(l_ptr->b_ptr, buf, &l_ptr->media_addr)) { + msg_dbg(buf_msg(buf), ">DEF-RETR>"); + l_ptr->retransm_queue_head = mod(++r_q_head); + l_ptr->retransm_queue_size = --r_q_size; + l_ptr->stats.retransmitted++; + return TIPC_OK; + } else { + l_ptr->stats.bearer_congs++; + msg_dbg(buf_msg(buf), "|>DEF-RETR>"); + return PUSH_FAILED; + } + } + + /* Send deferred protocol message, if any: */ + + buf = l_ptr->proto_msg_queue; + if (buf) { + msg_set_ack(buf_msg(buf), mod(l_ptr->next_in_no - 1)); + msg_set_bcast_ack(buf_msg(buf),l_ptr->owner->bclink.last_in); + if (bearer_send(l_ptr->b_ptr, buf, &l_ptr->media_addr)) { + msg_dbg(buf_msg(buf), ">DEF-PROT>"); + l_ptr->unacked_window = 0; + buf_discard(buf); + l_ptr->proto_msg_queue = 0; + return TIPC_OK; + } else { + msg_dbg(buf_msg(buf), "|>DEF-PROT>"); + l_ptr->stats.bearer_congs++; + return PUSH_FAILED; + } + } + + /* Send one deferred data message, if send window not full: */ + + buf = l_ptr->next_out; + if (buf) { + struct tipc_msg *msg = buf_msg(buf); + u32 next = msg_seqno(msg); + u32 first = msg_seqno(buf_msg(l_ptr->first_out)); + + if (mod(next - first) < l_ptr->queue_limit[0]) { + msg_set_ack(msg, mod(l_ptr->next_in_no - 1)); + msg_set_bcast_ack(msg, l_ptr->owner->bclink.last_in); + if (bearer_send(l_ptr->b_ptr, buf, &l_ptr->media_addr)) { + if (msg_user(msg) == MSG_BUNDLER) + msg_set_type(msg, CLOSED_MSG); + msg_dbg(msg, ">PUSH-DATA>"); + l_ptr->next_out = buf->next; + return TIPC_OK; + } else { + msg_dbg(msg, "|PUSH-DATA|"); + l_ptr->stats.bearer_congs++; + return PUSH_FAILED; + } + } + } + return PUSH_FINISHED; +} + +/* + * push_queue(): push out the unsent messages of a link where + * congestion has abated. Node is locked + */ +void link_push_queue(struct link *l_ptr) +{ + u32 res; + + if (bearer_congested(l_ptr->b_ptr, l_ptr)) + return; + + do { + res = link_push_packet(l_ptr); + } + while (res == TIPC_OK); + if (res == PUSH_FAILED) + bearer_schedule(l_ptr->b_ptr, l_ptr); +} + +void link_retransmit(struct link *l_ptr, struct sk_buff *buf, + u32 retransmits) +{ + struct tipc_msg *msg; + + dbg("Retransmitting %u in link %x\n", retransmits, l_ptr); + + if (bearer_congested(l_ptr->b_ptr, l_ptr) && buf && !skb_cloned(buf)) { + msg_dbg(buf_msg(buf), ">NO_RETR->BCONG>"); + dbg_print_link(l_ptr, " "); + l_ptr->retransm_queue_head = msg_seqno(buf_msg(buf)); + l_ptr->retransm_queue_size = retransmits; + return; + } + while (retransmits && (buf != l_ptr->next_out) && buf && !skb_cloned(buf)) { + msg = buf_msg(buf); + msg_set_ack(msg, mod(l_ptr->next_in_no - 1)); + msg_set_bcast_ack(msg, l_ptr->owner->bclink.last_in); + if (bearer_send(l_ptr->b_ptr, buf, &l_ptr->media_addr)) { + /* Catch if retransmissions fail repeatedly: */ + if (l_ptr->last_retransmitted == msg_seqno(msg)) { + if (++l_ptr->stale_count > 100) { + msg_print(CONS, buf_msg(buf), ">RETR>"); + info("...Retransmitted %u times\n", + l_ptr->stale_count); + link_print(l_ptr, CONS, "Resetting Link\n");; + link_reset(l_ptr); + break; + } + } else { + l_ptr->stale_count = 0; + } + l_ptr->last_retransmitted = msg_seqno(msg); + + msg_dbg(buf_msg(buf), ">RETR>"); + buf = buf->next; + retransmits--; + l_ptr->stats.retransmitted++; + } else { + bearer_schedule(l_ptr->b_ptr, l_ptr); + l_ptr->stats.bearer_congs++; + l_ptr->retransm_queue_head = msg_seqno(buf_msg(buf)); + l_ptr->retransm_queue_size = retransmits; + return; + } + } + l_ptr->retransm_queue_head = l_ptr->retransm_queue_size = 0; +} + +/* + * link_recv_non_seq: Receive packets which are outside + * the link sequence flow + */ + +static void link_recv_non_seq(struct sk_buff *buf) +{ + struct tipc_msg *msg = buf_msg(buf); + + if (msg_user(msg) == LINK_CONFIG) + disc_recv_msg(buf); + else + bclink_recv_pkt(buf); +} + +/** + * link_insert_deferred_queue - insert deferred messages back into receive chain + */ + +static struct sk_buff *link_insert_deferred_queue(struct link *l_ptr, + struct sk_buff *buf) +{ + u32 seq_no; + + if (l_ptr->oldest_deferred_in == NULL) + return buf; + + seq_no = msg_seqno(buf_msg(l_ptr->oldest_deferred_in)); + if (seq_no == mod(l_ptr->next_in_no)) { + l_ptr->newest_deferred_in->next = buf; + buf = l_ptr->oldest_deferred_in; + l_ptr->oldest_deferred_in = NULL; + l_ptr->deferred_inqueue_sz = 0; + } + return buf; +} + +void tipc_recv_msg(struct sk_buff *head, struct tipc_bearer *tb_ptr) +{ + read_lock_bh(&net_lock); + while (head) { + struct bearer *b_ptr; + struct node *n_ptr; + struct link *l_ptr; + struct sk_buff *crs; + struct sk_buff *buf = head; + struct tipc_msg *msg = buf_msg(buf); + u32 seq_no = msg_seqno(msg); + u32 ackd = msg_ack(msg); + u32 released = 0; + int type; + + b_ptr = (struct bearer *)tb_ptr; + TIPC_SKB_CB(buf)->handle = b_ptr; + + head = head->next; + if (unlikely(msg_version(msg) != TIPC_VERSION)) + goto cont; +#if 0 + if (msg_user(msg) != LINK_PROTOCOL) +#endif + msg_dbg(msg,"<REC<"); + + if (unlikely(msg_non_seq(msg))) { + link_recv_non_seq(buf); + continue; + } + n_ptr = node_find(msg_prevnode(msg)); + if (unlikely(!n_ptr)) + goto cont; + + node_lock(n_ptr); + l_ptr = n_ptr->links[b_ptr->identity]; + if (unlikely(!l_ptr)) { + node_unlock(n_ptr); + goto cont; + } + /* + * Release acked messages + */ + if (less(n_ptr->bclink.acked, msg_bcast_ack(msg))) { + if (node_is_up(n_ptr) && n_ptr->bclink.supported) + bclink_acknowledge(n_ptr, msg_bcast_ack(msg)); + } + + crs = l_ptr->first_out; + while ((crs != l_ptr->next_out) && + less_eq(msg_seqno(buf_msg(crs)), ackd)) { + struct sk_buff *next = crs->next; + + buf_discard(crs); + crs = next; + released++; + } + if (released) { + l_ptr->first_out = crs; + l_ptr->out_queue_size -= released; + } + if (unlikely(l_ptr->next_out)) + link_push_queue(l_ptr); + if (unlikely(!list_empty(&l_ptr->waiting_ports))) + link_wakeup_ports(l_ptr, 0); + if (unlikely(++l_ptr->unacked_window >= TIPC_MIN_LINK_WIN)) { + l_ptr->stats.sent_acks++; + link_send_proto_msg(l_ptr, STATE_MSG, 0, 0, 0, 0, 0); + } + +protocol_check: + if (likely(link_working_working(l_ptr))) { + if (likely(seq_no == mod(l_ptr->next_in_no))) { + l_ptr->next_in_no++; + if (unlikely(l_ptr->oldest_deferred_in)) + head = link_insert_deferred_queue(l_ptr, + head); + if (likely(msg_is_dest(msg, tipc_own_addr))) { +deliver: + if (likely(msg_isdata(msg))) { + node_unlock(n_ptr); + port_recv_msg(buf); + continue; + } + switch (msg_user(msg)) { + case MSG_BUNDLER: + l_ptr->stats.recv_bundles++; + l_ptr->stats.recv_bundled += + msg_msgcnt(msg); + node_unlock(n_ptr); + link_recv_bundle(buf); + continue; + case ROUTE_DISTRIBUTOR: + node_unlock(n_ptr); + cluster_recv_routing_table(buf); + continue; + case NAME_DISTRIBUTOR: + node_unlock(n_ptr); + named_recv(buf); + continue; + case CONN_MANAGER: + node_unlock(n_ptr); + port_recv_proto_msg(buf); + continue; + case MSG_FRAGMENTER: + l_ptr->stats.recv_fragments++; + if (link_recv_fragment( + &l_ptr->defragm_buf, + &buf, &msg)) { + l_ptr->stats.recv_fragmented++; + goto deliver; + } + break; + case CHANGEOVER_PROTOCOL: + type = msg_type(msg); + if (link_recv_changeover_msg( + &l_ptr, &buf)) { + msg = buf_msg(buf); + seq_no = msg_seqno(msg); + TIPC_SKB_CB(buf)->handle + = b_ptr; + if (type == ORIGINAL_MSG) + goto deliver; + goto protocol_check; + } + break; + } + } + node_unlock(n_ptr); + net_route_msg(buf); + continue; + } + link_handle_out_of_seq_msg(l_ptr, buf); + head = link_insert_deferred_queue(l_ptr, head); + node_unlock(n_ptr); + continue; + } + + if (msg_user(msg) == LINK_PROTOCOL) { + link_recv_proto_msg(l_ptr, buf); + head = link_insert_deferred_queue(l_ptr, head); + node_unlock(n_ptr); + continue; + } + msg_dbg(msg,"NSEQ<REC<"); + link_state_event(l_ptr, TRAFFIC_MSG_EVT); + + if (link_working_working(l_ptr)) { + /* Re-insert in front of queue */ + msg_dbg(msg,"RECV-REINS:"); + buf->next = head; + head = buf; + node_unlock(n_ptr); + continue; + } + node_unlock(n_ptr); +cont: + buf_discard(buf); + } + read_unlock_bh(&net_lock); +} + +/* + * link_defer_buf(): Sort a received out-of-sequence packet + * into the deferred reception queue. + * Returns the increase of the queue length,i.e. 0 or 1 + */ + +u32 link_defer_pkt(struct sk_buff **head, + struct sk_buff **tail, + struct sk_buff *buf) +{ + struct sk_buff *prev = 0; + struct sk_buff *crs = *head; + u32 seq_no = msg_seqno(buf_msg(buf)); + + buf->next = NULL; + + /* Empty queue ? */ + if (*head == NULL) { + *head = *tail = buf; + return 1; + } + + /* Last ? */ + if (less(msg_seqno(buf_msg(*tail)), seq_no)) { + (*tail)->next = buf; + *tail = buf; + return 1; + } + + /* Scan through queue and sort it in */ + do { + struct tipc_msg *msg = buf_msg(crs); + + if (less(seq_no, msg_seqno(msg))) { + buf->next = crs; + if (prev) + prev->next = buf; + else + *head = buf; + return 1; + } + if (seq_no == msg_seqno(msg)) { + break; + } + prev = crs; + crs = crs->next; + } + while (crs); + + /* Message is a duplicate of an existing message */ + + buf_discard(buf); + return 0; +} + +/** + * link_handle_out_of_seq_msg - handle arrival of out-of-sequence packet + */ + +static void link_handle_out_of_seq_msg(struct link *l_ptr, + struct sk_buff *buf) +{ + u32 seq_no = msg_seqno(buf_msg(buf)); + + if (likely(msg_user(buf_msg(buf)) == LINK_PROTOCOL)) { + link_recv_proto_msg(l_ptr, buf); + return; + } + + dbg("rx OOS msg: seq_no %u, expecting %u (%u)\n", + seq_no, mod(l_ptr->next_in_no), l_ptr->next_in_no); + + /* Record OOS packet arrival (force mismatch on next timeout) */ + + l_ptr->checkpoint--; + + /* + * Discard packet if a duplicate; otherwise add it to deferred queue + * and notify peer of gap as per protocol specification + */ + + if (less(seq_no, mod(l_ptr->next_in_no))) { + l_ptr->stats.duplicates++; + buf_discard(buf); + return; + } + + if (link_defer_pkt(&l_ptr->oldest_deferred_in, + &l_ptr->newest_deferred_in, buf)) { + l_ptr->deferred_inqueue_sz++; + l_ptr->stats.deferred_recv++; + if ((l_ptr->deferred_inqueue_sz % 16) == 1) + link_send_proto_msg(l_ptr, STATE_MSG, 0, 0, 0, 0, 0); + } else + l_ptr->stats.duplicates++; +} + +/* + * Send protocol message to the other endpoint. + */ +void link_send_proto_msg(struct link *l_ptr, u32 msg_typ, int probe_msg, + u32 gap, u32 tolerance, u32 priority, u32 ack_mtu) +{ + struct sk_buff *buf = 0; + struct tipc_msg *msg = l_ptr->pmsg; + u32 msg_size = sizeof(l_ptr->proto_msg); + + if (link_blocked(l_ptr)) + return; + msg_set_type(msg, msg_typ); + msg_set_net_plane(msg, l_ptr->b_ptr->net_plane); + msg_set_bcast_ack(msg, mod(l_ptr->owner->bclink.last_in)); + msg_set_last_bcast(msg, bclink_get_last_sent()); + + if (msg_typ == STATE_MSG) { + u32 next_sent = mod(l_ptr->next_out_no); + + if (!link_is_up(l_ptr)) + return; + if (l_ptr->next_out) + next_sent = msg_seqno(buf_msg(l_ptr->next_out)); + msg_set_next_sent(msg, next_sent); + if (l_ptr->oldest_deferred_in) { + u32 rec = msg_seqno(buf_msg(l_ptr->oldest_deferred_in)); + gap = mod(rec - mod(l_ptr->next_in_no)); + } + msg_set_seq_gap(msg, gap); + if (gap) + l_ptr->stats.sent_nacks++; + msg_set_link_tolerance(msg, tolerance); + msg_set_linkprio(msg, priority); + msg_set_max_pkt(msg, ack_mtu); + msg_set_ack(msg, mod(l_ptr->next_in_no - 1)); + msg_set_probe(msg, probe_msg != 0); + if (probe_msg) { + u32 mtu = l_ptr->max_pkt; + + if ((mtu < l_ptr->max_pkt_target) && + link_working_working(l_ptr) && + l_ptr->fsm_msg_cnt) { + msg_size = (mtu + (l_ptr->max_pkt_target - mtu)/2 + 2) & ~3; + if (l_ptr->max_pkt_probes == 10) { + l_ptr->max_pkt_target = (msg_size - 4); + l_ptr->max_pkt_probes = 0; + msg_size = (mtu + (l_ptr->max_pkt_target - mtu)/2 + 2) & ~3; + } + l_ptr->max_pkt_probes++; + } + + l_ptr->stats.sent_probes++; + } + l_ptr->stats.sent_states++; + } else { /* RESET_MSG or ACTIVATE_MSG */ + msg_set_ack(msg, mod(l_ptr->reset_checkpoint - 1)); + msg_set_seq_gap(msg, 0); + msg_set_next_sent(msg, 1); + msg_set_link_tolerance(msg, l_ptr->tolerance); + msg_set_linkprio(msg, l_ptr->priority); + msg_set_max_pkt(msg, l_ptr->max_pkt_target); + } + + if (node_has_redundant_links(l_ptr->owner)) { + msg_set_redundant_link(msg); + } else { + msg_clear_redundant_link(msg); + } + msg_set_linkprio(msg, l_ptr->priority); + + /* Ensure sequence number will not fit : */ + + msg_set_seqno(msg, mod(l_ptr->next_out_no + (0xffff/2))); + + /* Congestion? */ + + if (bearer_congested(l_ptr->b_ptr, l_ptr)) { + if (!l_ptr->proto_msg_queue) { + l_ptr->proto_msg_queue = + buf_acquire(sizeof(l_ptr->proto_msg)); + } + buf = l_ptr->proto_msg_queue; + if (!buf) + return; + memcpy(buf->data, (unchar *)msg, sizeof(l_ptr->proto_msg)); + return; + } + msg_set_timestamp(msg, jiffies_to_msecs(jiffies)); + + /* Message can be sent */ + + msg_dbg(msg, ">>"); + + buf = buf_acquire(msg_size); + if (!buf) + return; + + memcpy(buf->data, (unchar *)msg, sizeof(l_ptr->proto_msg)); + msg_set_size(buf_msg(buf), msg_size); + + if (bearer_send(l_ptr->b_ptr, buf, &l_ptr->media_addr)) { + l_ptr->unacked_window = 0; + buf_discard(buf); + return; + } + + /* New congestion */ + bearer_schedule(l_ptr->b_ptr, l_ptr); + l_ptr->proto_msg_queue = buf; + l_ptr->stats.bearer_congs++; +} + +/* + * Receive protocol message : + * Note that network plane id propagates through the network, and may + * change at any time. The node with lowest address rules + */ + +static void link_recv_proto_msg(struct link *l_ptr, struct sk_buff *buf) +{ + u32 rec_gap = 0; + u32 max_pkt_info; + u32 max_pkt_ack; + u32 msg_tol; + struct tipc_msg *msg = buf_msg(buf); + + dbg("AT(%u):", jiffies_to_msecs(jiffies)); + msg_dbg(msg, "<<"); + if (link_blocked(l_ptr)) + goto exit; + + /* record unnumbered packet arrival (force mismatch on next timeout) */ + + l_ptr->checkpoint--; + + if (l_ptr->b_ptr->net_plane != msg_net_plane(msg)) + if (tipc_own_addr > msg_prevnode(msg)) + l_ptr->b_ptr->net_plane = msg_net_plane(msg); + + l_ptr->owner->permit_changeover = msg_redundant_link(msg); + + switch (msg_type(msg)) { + + case RESET_MSG: + if (!link_working_unknown(l_ptr) && l_ptr->peer_session) { + if (msg_session(msg) == l_ptr->peer_session) { + dbg("Duplicate RESET: %u<->%u\n", + msg_session(msg), l_ptr->peer_session); + break; /* duplicate: ignore */ + } + } + /* fall thru' */ + case ACTIVATE_MSG: + /* Update link settings according other endpoint's values */ + + strcpy((strrchr(l_ptr->name, ':') + 1), (char *)msg_data(msg)); + + if ((msg_tol = msg_link_tolerance(msg)) && + (msg_tol > l_ptr->tolerance)) + link_set_supervision_props(l_ptr, msg_tol); + + if (msg_linkprio(msg) > l_ptr->priority) + l_ptr->priority = msg_linkprio(msg); + + max_pkt_info = msg_max_pkt(msg); + if (max_pkt_info) { + if (max_pkt_info < l_ptr->max_pkt_target) + l_ptr->max_pkt_target = max_pkt_info; + if (l_ptr->max_pkt > l_ptr->max_pkt_target) + l_ptr->max_pkt = l_ptr->max_pkt_target; + } else { + l_ptr->max_pkt = l_ptr->max_pkt_target; + } + l_ptr->owner->bclink.supported = (max_pkt_info != 0); + + link_state_event(l_ptr, msg_type(msg)); + + l_ptr->peer_session = msg_session(msg); + l_ptr->peer_bearer_id = msg_bearer_id(msg); + + /* Synchronize broadcast sequence numbers */ + if (!node_has_redundant_links(l_ptr->owner)) { + l_ptr->owner->bclink.last_in = mod(msg_last_bcast(msg)); + } + break; + case STATE_MSG: + + if ((msg_tol = msg_link_tolerance(msg))) + link_set_supervision_props(l_ptr, msg_tol); + + if (msg_linkprio(msg) && + (msg_linkprio(msg) != l_ptr->priority)) { + warn("Changing prio <%s>: %u->%u\n", + l_ptr->name, l_ptr->priority, msg_linkprio(msg)); + l_ptr->priority = msg_linkprio(msg); + link_reset(l_ptr); /* Enforce change to take effect */ + break; + } + link_state_event(l_ptr, TRAFFIC_MSG_EVT); + l_ptr->stats.recv_states++; + if (link_reset_unknown(l_ptr)) + break; + + if (less_eq(mod(l_ptr->next_in_no), msg_next_sent(msg))) { + rec_gap = mod(msg_next_sent(msg) - + mod(l_ptr->next_in_no)); + } + + max_pkt_ack = msg_max_pkt(msg); + if (max_pkt_ack > l_ptr->max_pkt) { + dbg("Link <%s> updated MTU %u -> %u\n", + l_ptr->name, l_ptr->max_pkt, max_pkt_ack); + l_ptr->max_pkt = max_pkt_ack; + l_ptr->max_pkt_probes = 0; + } + + max_pkt_ack = 0; + if (msg_probe(msg)) { + l_ptr->stats.recv_probes++; + if (msg_size(msg) > sizeof(l_ptr->proto_msg)) { + max_pkt_ack = msg_size(msg); + } + } + + /* Protocol message before retransmits, reduce loss risk */ + + bclink_check_gap(l_ptr->owner, msg_last_bcast(msg)); + + if (rec_gap || (msg_probe(msg))) { + link_send_proto_msg(l_ptr, STATE_MSG, + 0, rec_gap, 0, 0, max_pkt_ack); + } + if (msg_seq_gap(msg)) { + msg_dbg(msg, "With Gap:"); + l_ptr->stats.recv_nacks++; + link_retransmit(l_ptr, l_ptr->first_out, + msg_seq_gap(msg)); + } + break; + default: + msg_dbg(buf_msg(buf), "<DISCARDING UNKNOWN<"); + } +exit: + buf_discard(buf); +} + + +/* + * link_tunnel(): Send one message via a link belonging to + * another bearer. Owner node is locked. + */ +void link_tunnel(struct link *l_ptr, + struct tipc_msg *tunnel_hdr, + struct tipc_msg *msg, + u32 selector) +{ + struct link *tunnel; + struct sk_buff *buf; + u32 length = msg_size(msg); + + tunnel = l_ptr->owner->active_links[selector & 1]; + if (!link_is_up(tunnel)) + return; + msg_set_size(tunnel_hdr, length + INT_H_SIZE); + buf = buf_acquire(length + INT_H_SIZE); + if (!buf) + return; + memcpy(buf->data, (unchar *)tunnel_hdr, INT_H_SIZE); + memcpy(buf->data + INT_H_SIZE, (unchar *)msg, length); + dbg("%c->%c:", l_ptr->b_ptr->net_plane, tunnel->b_ptr->net_plane); + msg_dbg(buf_msg(buf), ">SEND>"); + assert(tunnel); + link_send_buf(tunnel, buf); +} + + + +/* + * changeover(): Send whole message queue via the remaining link + * Owner node is locked. + */ + +void link_changeover(struct link *l_ptr) +{ + u32 msgcount = l_ptr->out_queue_size; + struct sk_buff *crs = l_ptr->first_out; + struct link *tunnel = l_ptr->owner->active_links[0]; + int split_bundles = node_has_redundant_links(l_ptr->owner); + struct tipc_msg tunnel_hdr; + + if (!tunnel) + return; + + if (!l_ptr->owner->permit_changeover) + return; + + msg_init(&tunnel_hdr, CHANGEOVER_PROTOCOL, + ORIGINAL_MSG, TIPC_OK, INT_H_SIZE, l_ptr->addr); + msg_set_bearer_id(&tunnel_hdr, l_ptr->peer_bearer_id); + msg_set_msgcnt(&tunnel_hdr, msgcount); + if (!l_ptr->first_out) { + struct sk_buff *buf; + + assert(!msgcount); + buf = buf_acquire(INT_H_SIZE); + if (buf) { + memcpy(buf->data, (unchar *)&tunnel_hdr, INT_H_SIZE); + msg_set_size(&tunnel_hdr, INT_H_SIZE); + dbg("%c->%c:", l_ptr->b_ptr->net_plane, + tunnel->b_ptr->net_plane); + msg_dbg(&tunnel_hdr, "EMPTY>SEND>"); + link_send_buf(tunnel, buf); + } else { + warn("Memory squeeze; link changeover failed\n"); + } + return; + } + while (crs) { + struct tipc_msg *msg = buf_msg(crs); + + if ((msg_user(msg) == MSG_BUNDLER) && split_bundles) { + u32 msgcount = msg_msgcnt(msg); + struct tipc_msg *m = msg_get_wrapped(msg); + unchar* pos = (unchar*)m; + + while (msgcount--) { + msg_set_seqno(m,msg_seqno(msg)); + link_tunnel(l_ptr, &tunnel_hdr, m, + msg_link_selector(m)); + pos += align(msg_size(m)); + m = (struct tipc_msg *)pos; + } + } else { + link_tunnel(l_ptr, &tunnel_hdr, msg, + msg_link_selector(msg)); + } + crs = crs->next; + } +} + +void link_send_duplicate(struct link *l_ptr, struct link *tunnel) +{ + struct sk_buff *iter; + struct tipc_msg tunnel_hdr; + + msg_init(&tunnel_hdr, CHANGEOVER_PROTOCOL, + DUPLICATE_MSG, TIPC_OK, INT_H_SIZE, l_ptr->addr); + msg_set_msgcnt(&tunnel_hdr, l_ptr->out_queue_size); + msg_set_bearer_id(&tunnel_hdr, l_ptr->peer_bearer_id); + iter = l_ptr->first_out; + while (iter) { + struct sk_buff *outbuf; + struct tipc_msg *msg = buf_msg(iter); + u32 length = msg_size(msg); + + if (msg_user(msg) == MSG_BUNDLER) + msg_set_type(msg, CLOSED_MSG); + msg_set_ack(msg, mod(l_ptr->next_in_no - 1)); /* Update */ + msg_set_bcast_ack(msg, l_ptr->owner->bclink.last_in); + msg_set_size(&tunnel_hdr, length + INT_H_SIZE); + outbuf = buf_acquire(length + INT_H_SIZE); + if (outbuf == NULL) { + warn("Memory squeeze; buffer duplication failed\n"); + return; + } + memcpy(outbuf->data, (unchar *)&tunnel_hdr, INT_H_SIZE); + memcpy(outbuf->data + INT_H_SIZE, iter->data, length); + dbg("%c->%c:", l_ptr->b_ptr->net_plane, + tunnel->b_ptr->net_plane); + msg_dbg(buf_msg(outbuf), ">SEND>"); + link_send_buf(tunnel, outbuf); + if (!link_is_up(l_ptr)) + return; + iter = iter->next; + } +} + + + +/** + * buf_extract - extracts embedded TIPC message from another message + * @skb: encapsulating message buffer + * @from_pos: offset to extract from + * + * Returns a new message buffer containing an embedded message. The + * encapsulating message itself is left unchanged. + */ + +static struct sk_buff *buf_extract(struct sk_buff *skb, u32 from_pos) +{ + struct tipc_msg *msg = (struct tipc_msg *)(skb->data + from_pos); + u32 size = msg_size(msg); + struct sk_buff *eb; + + eb = buf_acquire(size); + if (eb) + memcpy(eb->data, (unchar *)msg, size); + return eb; +} + +/* + * link_recv_changeover_msg(): Receive tunneled packet sent + * via other link. Node is locked. Return extracted buffer. + */ + +static int link_recv_changeover_msg(struct link **l_ptr, + struct sk_buff **buf) +{ + struct sk_buff *tunnel_buf = *buf; + struct link *dest_link; + struct tipc_msg *msg; + struct tipc_msg *tunnel_msg = buf_msg(tunnel_buf); + u32 msg_typ = msg_type(tunnel_msg); + u32 msg_count = msg_msgcnt(tunnel_msg); + + dest_link = (*l_ptr)->owner->links[msg_bearer_id(tunnel_msg)]; + assert(dest_link != *l_ptr); + if (!dest_link) { + msg_dbg(tunnel_msg, "NOLINK/<REC<"); + goto exit; + } + dbg("%c<-%c:", dest_link->b_ptr->net_plane, + (*l_ptr)->b_ptr->net_plane); + *l_ptr = dest_link; + msg = msg_get_wrapped(tunnel_msg); + + if (msg_typ == DUPLICATE_MSG) { + if (less(msg_seqno(msg), mod(dest_link->next_in_no))) { + msg_dbg(tunnel_msg, "DROP/<REC<"); + goto exit; + } + *buf = buf_extract(tunnel_buf,INT_H_SIZE); + if (*buf == NULL) { + warn("Memory squeeze; failed to extract msg\n"); + goto exit; + } + msg_dbg(tunnel_msg, "TNL<REC<"); + buf_discard(tunnel_buf); + return 1; + } + + /* First original message ?: */ + + if (link_is_up(dest_link)) { + msg_dbg(tunnel_msg, "UP/FIRST/<REC<"); + link_reset(dest_link); + dest_link->exp_msg_count = msg_count; + if (!msg_count) + goto exit; + } else if (dest_link->exp_msg_count == START_CHANGEOVER) { + msg_dbg(tunnel_msg, "BLK/FIRST/<REC<"); + dest_link->exp_msg_count = msg_count; + if (!msg_count) + goto exit; + } + + /* Receive original message */ + + if (dest_link->exp_msg_count == 0) { + msg_dbg(tunnel_msg, "OVERDUE/DROP/<REC<"); + dbg_print_link(dest_link, "LINK:"); + goto exit; + } + dest_link->exp_msg_count--; + if (less(msg_seqno(msg), dest_link->reset_checkpoint)) { + msg_dbg(tunnel_msg, "DROP/DUPL/<REC<"); + goto exit; + } else { + *buf = buf_extract(tunnel_buf, INT_H_SIZE); + if (*buf != NULL) { + msg_dbg(tunnel_msg, "TNL<REC<"); + buf_discard(tunnel_buf); + return 1; + } else { + warn("Memory squeeze; dropped incoming msg\n"); + } + } +exit: + *buf = 0; + buf_discard(tunnel_buf); + return 0; +} + +/* + * Bundler functionality: + */ +void link_recv_bundle(struct sk_buff *buf) +{ + u32 msgcount = msg_msgcnt(buf_msg(buf)); + u32 pos = INT_H_SIZE; + struct sk_buff *obuf; + + msg_dbg(buf_msg(buf), "<BNDL<: "); + while (msgcount--) { + obuf = buf_extract(buf, pos); + if (obuf == NULL) { + char addr_string[16]; + + warn("Buffer allocation failure;\n"); + warn(" incoming message(s) from %s lost\n", + addr_string_fill(addr_string, + msg_orignode(buf_msg(buf)))); + return; + }; + pos += align(msg_size(buf_msg(obuf))); + msg_dbg(buf_msg(obuf), " /"); + net_route_msg(obuf); + } + buf_discard(buf); +} + +/* + * Fragmentation/defragmentation: + */ + + +/* + * link_send_long_buf: Entry for buffers needing fragmentation. + * The buffer is complete, inclusive total message length. + * Returns user data length. + */ +int link_send_long_buf(struct link *l_ptr, struct sk_buff *buf) +{ + struct tipc_msg *inmsg = buf_msg(buf); + struct tipc_msg fragm_hdr; + u32 insize = msg_size(inmsg); + u32 dsz = msg_data_sz(inmsg); + unchar *crs = buf->data; + u32 rest = insize; + u32 pack_sz = link_max_pkt(l_ptr); + u32 fragm_sz = pack_sz - INT_H_SIZE; + u32 fragm_no = 1; + u32 destaddr = msg_destnode(inmsg); + + if (msg_short(inmsg)) + destaddr = l_ptr->addr; + + if (msg_routed(inmsg)) + msg_set_prevnode(inmsg, tipc_own_addr); + + /* Prepare reusable fragment header: */ + + msg_init(&fragm_hdr, MSG_FRAGMENTER, FIRST_FRAGMENT, + TIPC_OK, INT_H_SIZE, destaddr); + msg_set_link_selector(&fragm_hdr, msg_link_selector(inmsg)); + msg_set_long_msgno(&fragm_hdr, mod(l_ptr->long_msg_seq_no++)); + msg_set_fragm_no(&fragm_hdr, fragm_no); + l_ptr->stats.sent_fragmented++; + + /* Chop up message: */ + + while (rest > 0) { + struct sk_buff *fragm; + + if (rest <= fragm_sz) { + fragm_sz = rest; + msg_set_type(&fragm_hdr, LAST_FRAGMENT); + } + fragm = buf_acquire(fragm_sz + INT_H_SIZE); + if (fragm == NULL) { + warn("Memory squeeze; failed to fragment msg\n"); + dsz = -ENOMEM; + goto exit; + } + msg_set_size(&fragm_hdr, fragm_sz + INT_H_SIZE); + memcpy(fragm->data, (unchar *)&fragm_hdr, INT_H_SIZE); + memcpy(fragm->data + INT_H_SIZE, crs, fragm_sz); + + /* Send queued messages first, if any: */ + + l_ptr->stats.sent_fragments++; + link_send_buf(l_ptr, fragm); + if (!link_is_up(l_ptr)) + return dsz; + msg_set_fragm_no(&fragm_hdr, ++fragm_no); + rest -= fragm_sz; + crs += fragm_sz; + msg_set_type(&fragm_hdr, FRAGMENT); + } +exit: + buf_discard(buf); + return dsz; +} + +/* + * A pending message being re-assembled must store certain values + * to handle subsequent fragments correctly. The following functions + * help storing these values in unused, available fields in the + * pending message. This makes dynamic memory allocation unecessary. + */ + +static inline u32 get_long_msg_seqno(struct sk_buff *buf) +{ + return msg_seqno(buf_msg(buf)); +} + +static inline void set_long_msg_seqno(struct sk_buff *buf, u32 seqno) +{ + msg_set_seqno(buf_msg(buf), seqno); +} + +static inline u32 get_fragm_size(struct sk_buff *buf) +{ + return msg_ack(buf_msg(buf)); +} + +static inline void set_fragm_size(struct sk_buff *buf, u32 sz) +{ + msg_set_ack(buf_msg(buf), sz); +} + +static inline u32 get_expected_frags(struct sk_buff *buf) +{ + return msg_bcast_ack(buf_msg(buf)); +} + +static inline void set_expected_frags(struct sk_buff *buf, u32 exp) +{ + msg_set_bcast_ack(buf_msg(buf), exp); +} + +static inline u32 get_timer_cnt(struct sk_buff *buf) +{ + return msg_reroute_cnt(buf_msg(buf)); +} + +static inline void incr_timer_cnt(struct sk_buff *buf) +{ + msg_incr_reroute_cnt(buf_msg(buf)); +} + +/* + * link_recv_fragment(): Called with node lock on. Returns + * the reassembled buffer if message is complete. + */ +int link_recv_fragment(struct sk_buff **pending, struct sk_buff **fb, + struct tipc_msg **m) +{ + struct sk_buff *prev = 0; + struct sk_buff *fbuf = *fb; + struct tipc_msg *fragm = buf_msg(fbuf); + struct sk_buff *pbuf = *pending; + u32 long_msg_seq_no = msg_long_msgno(fragm); + + *fb = 0; + msg_dbg(fragm,"FRG<REC<"); + + /* Is there an incomplete message waiting for this fragment? */ + + while (pbuf && ((msg_seqno(buf_msg(pbuf)) != long_msg_seq_no) + || (msg_orignode(fragm) != msg_orignode(buf_msg(pbuf))))) { + prev = pbuf; + pbuf = pbuf->next; + } + + if (!pbuf && (msg_type(fragm) == FIRST_FRAGMENT)) { + struct tipc_msg *imsg = (struct tipc_msg *)msg_data(fragm); + u32 msg_sz = msg_size(imsg); + u32 fragm_sz = msg_data_sz(fragm); + u32 exp_fragm_cnt = msg_sz/fragm_sz + !!(msg_sz % fragm_sz); + u32 max = TIPC_MAX_USER_MSG_SIZE + LONG_H_SIZE; + if (msg_type(imsg) == TIPC_MCAST_MSG) + max = TIPC_MAX_USER_MSG_SIZE + MCAST_H_SIZE; + if (msg_size(imsg) > max) { + msg_dbg(fragm,"<REC<Oversized: "); + buf_discard(fbuf); + return 0; + } + pbuf = buf_acquire(msg_size(imsg)); + if (pbuf != NULL) { + pbuf->next = *pending; + *pending = pbuf; + memcpy(pbuf->data, (unchar *)imsg, msg_data_sz(fragm)); + + /* Prepare buffer for subsequent fragments. */ + + set_long_msg_seqno(pbuf, long_msg_seq_no); + set_fragm_size(pbuf,fragm_sz); + set_expected_frags(pbuf,exp_fragm_cnt - 1); + } else { + warn("Memory squeeze; got no defragmenting buffer\n"); + } + buf_discard(fbuf); + return 0; + } else if (pbuf && (msg_type(fragm) != FIRST_FRAGMENT)) { + u32 dsz = msg_data_sz(fragm); + u32 fsz = get_fragm_size(pbuf); + u32 crs = ((msg_fragm_no(fragm) - 1) * fsz); + u32 exp_frags = get_expected_frags(pbuf) - 1; + memcpy(pbuf->data + crs, msg_data(fragm), dsz); + buf_discard(fbuf); + + /* Is message complete? */ + + if (exp_frags == 0) { + if (prev) + prev->next = pbuf->next; + else + *pending = pbuf->next; + msg_reset_reroute_cnt(buf_msg(pbuf)); + *fb = pbuf; + *m = buf_msg(pbuf); + return 1; + } + set_expected_frags(pbuf,exp_frags); + return 0; + } + dbg(" Discarding orphan fragment %x\n",fbuf); + msg_dbg(fragm,"ORPHAN:"); + dbg("Pending long buffers:\n"); + dbg_print_buf_chain(*pending); + buf_discard(fbuf); + return 0; +} + +/** + * link_check_defragm_bufs - flush stale incoming message fragments + * @l_ptr: pointer to link + */ + +static void link_check_defragm_bufs(struct link *l_ptr) +{ + struct sk_buff *prev = 0; + struct sk_buff *next = 0; + struct sk_buff *buf = l_ptr->defragm_buf; + + if (!buf) + return; + if (!link_working_working(l_ptr)) + return; + while (buf) { + u32 cnt = get_timer_cnt(buf); + + next = buf->next; + if (cnt < 4) { + incr_timer_cnt(buf); + prev = buf; + } else { + dbg(" Discarding incomplete long buffer\n"); + msg_dbg(buf_msg(buf), "LONG:"); + dbg_print_link(l_ptr, "curr:"); + dbg("Pending long buffers:\n"); + dbg_print_buf_chain(l_ptr->defragm_buf); + if (prev) + prev->next = buf->next; + else + l_ptr->defragm_buf = buf->next; + buf_discard(buf); + } + buf = next; + } +} + + + +static void link_set_supervision_props(struct link *l_ptr, u32 tolerance) +{ + l_ptr->tolerance = tolerance; + l_ptr->continuity_interval = + ((tolerance / 4) > 500) ? 500 : tolerance / 4; + l_ptr->abort_limit = tolerance / (l_ptr->continuity_interval / 4); +} + + +void link_set_queue_limits(struct link *l_ptr, u32 window) +{ + /* Data messages from this node, inclusive FIRST_FRAGM */ + l_ptr->queue_limit[DATA_LOW] = window; + l_ptr->queue_limit[DATA_MEDIUM] = (window / 3) * 4; + l_ptr->queue_limit[DATA_HIGH] = (window / 3) * 5; + l_ptr->queue_limit[DATA_CRITICAL] = (window / 3) * 6; + /* Transiting data messages,inclusive FIRST_FRAGM */ + l_ptr->queue_limit[DATA_LOW + 4] = 300; + l_ptr->queue_limit[DATA_MEDIUM + 4] = 600; + l_ptr->queue_limit[DATA_HIGH + 4] = 900; + l_ptr->queue_limit[DATA_CRITICAL + 4] = 1200; + l_ptr->queue_limit[CONN_MANAGER] = 1200; + l_ptr->queue_limit[ROUTE_DISTRIBUTOR] = 1200; + l_ptr->queue_limit[CHANGEOVER_PROTOCOL] = 2500; + l_ptr->queue_limit[NAME_DISTRIBUTOR] = 3000; + /* FRAGMENT and LAST_FRAGMENT packets */ + l_ptr->queue_limit[MSG_FRAGMENTER] = 4000; +} + +/** + * link_find_link - locate link by name + * @name - ptr to link name string + * @node - ptr to area to be filled with ptr to associated node + * + * Caller must hold 'net_lock' to ensure node and bearer are not deleted; + * this also prevents link deletion. + * + * Returns pointer to link (or 0 if invalid link name). + */ + +static struct link *link_find_link(const char *name, struct node **node) +{ + struct link_name link_name_parts; + struct bearer *b_ptr; + struct link *l_ptr; + + if (!link_name_validate(name, &link_name_parts)) + return 0; + + b_ptr = bearer_find_interface(link_name_parts.if_local); + if (!b_ptr) + return 0; + + *node = node_find(link_name_parts.addr_peer); + if (!*node) + return 0; + + l_ptr = (*node)->links[b_ptr->identity]; + if (!l_ptr || strcmp(l_ptr->name, name)) + return 0; + + return l_ptr; +} + +struct sk_buff *link_cmd_config(const void *req_tlv_area, int req_tlv_space, + u16 cmd) +{ + struct tipc_link_config *args; + u32 new_value; + struct link *l_ptr; + struct node *node; + int res; + + if (!TLV_CHECK(req_tlv_area, req_tlv_space, TIPC_TLV_LINK_CONFIG)) + return cfg_reply_error_string(TIPC_CFG_TLV_ERROR); + + args = (struct tipc_link_config *)TLV_DATA(req_tlv_area); + new_value = ntohl(args->value); + + if (!strcmp(args->name, bc_link_name)) { + if ((cmd == TIPC_CMD_SET_LINK_WINDOW) && + (bclink_set_queue_limits(new_value) == 0)) + return cfg_reply_none(); + return cfg_reply_error_string(TIPC_CFG_NOT_SUPPORTED + " (cannot change setting on broadcast link)"); + } + + read_lock_bh(&net_lock); + l_ptr = link_find_link(args->name, &node); + if (!l_ptr) { + read_unlock_bh(&net_lock); + return cfg_reply_error_string("link not found"); + } + + node_lock(node); + res = -EINVAL; + switch (cmd) { + case TIPC_CMD_SET_LINK_TOL: + if ((new_value >= TIPC_MIN_LINK_TOL) && + (new_value <= TIPC_MAX_LINK_TOL)) { + link_set_supervision_props(l_ptr, new_value); + link_send_proto_msg(l_ptr, STATE_MSG, + 0, 0, new_value, 0, 0); + res = TIPC_OK; + } + break; + case TIPC_CMD_SET_LINK_PRI: + if (new_value < TIPC_NUM_LINK_PRI) { + l_ptr->priority = new_value; + link_send_proto_msg(l_ptr, STATE_MSG, + 0, 0, 0, new_value, 0); + res = TIPC_OK; + } + break; + case TIPC_CMD_SET_LINK_WINDOW: + if ((new_value >= TIPC_MIN_LINK_WIN) && + (new_value <= TIPC_MAX_LINK_WIN)) { + link_set_queue_limits(l_ptr, new_value); + res = TIPC_OK; + } + break; + } + node_unlock(node); + + read_unlock_bh(&net_lock); + if (res) + return cfg_reply_error_string("cannot change link setting"); + + return cfg_reply_none(); +} + +/** + * link_reset_statistics - reset link statistics + * @l_ptr: pointer to link + */ + +static void link_reset_statistics(struct link *l_ptr) +{ + memset(&l_ptr->stats, 0, sizeof(l_ptr->stats)); + l_ptr->stats.sent_info = l_ptr->next_out_no; + l_ptr->stats.recv_info = l_ptr->next_in_no; +} + +struct sk_buff *link_cmd_reset_stats(const void *req_tlv_area, int req_tlv_space) +{ + char *link_name; + struct link *l_ptr; + struct node *node; + + if (!TLV_CHECK(req_tlv_area, req_tlv_space, TIPC_TLV_LINK_NAME)) + return cfg_reply_error_string(TIPC_CFG_TLV_ERROR); + + link_name = (char *)TLV_DATA(req_tlv_area); + if (!strcmp(link_name, bc_link_name)) { + if (bclink_reset_stats()) + return cfg_reply_error_string("link not found"); + return cfg_reply_none(); + } + + read_lock_bh(&net_lock); + l_ptr = link_find_link(link_name, &node); + if (!l_ptr) { + read_unlock_bh(&net_lock); + return cfg_reply_error_string("link not found"); + } + + node_lock(node); + link_reset_statistics(l_ptr); + node_unlock(node); + read_unlock_bh(&net_lock); + return cfg_reply_none(); +} + +/** + * percent - convert count to a percentage of total (rounding up or down) + */ + +static u32 percent(u32 count, u32 total) +{ + return (count * 100 + (total / 2)) / total; +} + +/** + * link_stats - print link statistics + * @name: link name + * @buf: print buffer area + * @buf_size: size of print buffer area + * + * Returns length of print buffer data string (or 0 if error) + */ + +static int link_stats(const char *name, char *buf, const u32 buf_size) +{ + struct print_buf pb; + struct link *l_ptr; + struct node *node; + char *status; + u32 profile_total = 0; + + if (!strcmp(name, bc_link_name)) + return bclink_stats(buf, buf_size); + + printbuf_init(&pb, buf, buf_size); + + read_lock_bh(&net_lock); + l_ptr = link_find_link(name, &node); + if (!l_ptr) { + read_unlock_bh(&net_lock); + return 0; + } + node_lock(node); + + if (link_is_active(l_ptr)) + status = "ACTIVE"; + else if (link_is_up(l_ptr)) + status = "STANDBY"; + else + status = "DEFUNCT"; + tipc_printf(&pb, "Link <%s>\n" + " %s MTU:%u Priority:%u Tolerance:%u ms" + " Window:%u packets\n", + l_ptr->name, status, link_max_pkt(l_ptr), + l_ptr->priority, l_ptr->tolerance, l_ptr->queue_limit[0]); + tipc_printf(&pb, " RX packets:%u fragments:%u/%u bundles:%u/%u\n", + l_ptr->next_in_no - l_ptr->stats.recv_info, + l_ptr->stats.recv_fragments, + l_ptr->stats.recv_fragmented, + l_ptr->stats.recv_bundles, + l_ptr->stats.recv_bundled); + tipc_printf(&pb, " TX packets:%u fragments:%u/%u bundles:%u/%u\n", + l_ptr->next_out_no - l_ptr->stats.sent_info, + l_ptr->stats.sent_fragments, + l_ptr->stats.sent_fragmented, + l_ptr->stats.sent_bundles, + l_ptr->stats.sent_bundled); + profile_total = l_ptr->stats.msg_length_counts; + if (!profile_total) + profile_total = 1; + tipc_printf(&pb, " TX profile sample:%u packets average:%u octets\n" + " 0-64:%u%% -256:%u%% -1024:%u%% -4096:%u%% " + "-16354:%u%% -32768:%u%% -66000:%u%%\n", + l_ptr->stats.msg_length_counts, + l_ptr->stats.msg_lengths_total / profile_total, + percent(l_ptr->stats.msg_length_profile[0], profile_total), + percent(l_ptr->stats.msg_length_profile[1], profile_total), + percent(l_ptr->stats.msg_length_profile[2], profile_total), + percent(l_ptr->stats.msg_length_profile[3], profile_total), + percent(l_ptr->stats.msg_length_profile[4], profile_total), + percent(l_ptr->stats.msg_length_profile[5], profile_total), + percent(l_ptr->stats.msg_length_profile[6], profile_total)); + tipc_printf(&pb, " RX states:%u probes:%u naks:%u defs:%u dups:%u\n", + l_ptr->stats.recv_states, + l_ptr->stats.recv_probes, + l_ptr->stats.recv_nacks, + l_ptr->stats.deferred_recv, + l_ptr->stats.duplicates); + tipc_printf(&pb, " TX states:%u probes:%u naks:%u acks:%u dups:%u\n", + l_ptr->stats.sent_states, + l_ptr->stats.sent_probes, + l_ptr->stats.sent_nacks, + l_ptr->stats.sent_acks, + l_ptr->stats.retransmitted); + tipc_printf(&pb, " Congestion bearer:%u link:%u Send queue max:%u avg:%u\n", + l_ptr->stats.bearer_congs, + l_ptr->stats.link_congs, + l_ptr->stats.max_queue_sz, + l_ptr->stats.queue_sz_counts + ? (l_ptr->stats.accu_queue_sz / l_ptr->stats.queue_sz_counts) + : 0); + + node_unlock(node); + read_unlock_bh(&net_lock); + return printbuf_validate(&pb); +} + +#define MAX_LINK_STATS_INFO 2000 + +struct sk_buff *link_cmd_show_stats(const void *req_tlv_area, int req_tlv_space) +{ + struct sk_buff *buf; + struct tlv_desc *rep_tlv; + int str_len; + + if (!TLV_CHECK(req_tlv_area, req_tlv_space, TIPC_TLV_LINK_NAME)) + return cfg_reply_error_string(TIPC_CFG_TLV_ERROR); + + buf = cfg_reply_alloc(TLV_SPACE(MAX_LINK_STATS_INFO)); + if (!buf) + return NULL; + + rep_tlv = (struct tlv_desc *)buf->data; + + str_len = link_stats((char *)TLV_DATA(req_tlv_area), + (char *)TLV_DATA(rep_tlv), MAX_LINK_STATS_INFO); + if (!str_len) { + buf_discard(buf); + return cfg_reply_error_string("link not found"); + } + + skb_put(buf, TLV_SPACE(str_len)); + TLV_SET(rep_tlv, TIPC_TLV_ULTRA_STRING, NULL, str_len); + + return buf; +} + +#if 0 +int link_control(const char *name, u32 op, u32 val) +{ + int res = -EINVAL; + struct link *l_ptr; + u32 bearer_id; + struct node * node; + u32 a; + + a = link_name2addr(name, &bearer_id); + read_lock_bh(&net_lock); + node = node_find(a); + if (node) { + node_lock(node); + l_ptr = node->links[bearer_id]; + if (l_ptr) { + if (op == TIPC_REMOVE_LINK) { + struct bearer *b_ptr = l_ptr->b_ptr; + spin_lock_bh(&b_ptr->publ.lock); + link_delete(l_ptr); + spin_unlock_bh(&b_ptr->publ.lock); + } + if (op == TIPC_CMD_BLOCK_LINK) { + link_reset(l_ptr); + l_ptr->blocked = 1; + } + if (op == TIPC_CMD_UNBLOCK_LINK) { + l_ptr->blocked = 0; + } + res = TIPC_OK; + } + node_unlock(node); + } + read_unlock_bh(&net_lock); + return res; +} +#endif + +/** + * link_get_max_pkt - get maximum packet size to use when sending to destination + * @dest: network address of destination node + * @selector: used to select from set of active links + * + * If no active link can be found, uses default maximum packet size. + */ + +u32 link_get_max_pkt(u32 dest, u32 selector) +{ + struct node *n_ptr; + struct link *l_ptr; + u32 res = MAX_PKT_DEFAULT; + + if (dest == tipc_own_addr) + return MAX_MSG_SIZE; + + read_lock_bh(&net_lock); + n_ptr = node_select(dest, selector); + if (n_ptr) { + node_lock(n_ptr); + l_ptr = n_ptr->active_links[selector & 1]; + if (l_ptr) + res = link_max_pkt(l_ptr); + node_unlock(n_ptr); + } + read_unlock_bh(&net_lock); + return res; +} + +#if 0 +static void link_dump_rec_queue(struct link *l_ptr) +{ + struct sk_buff *crs; + + if (!l_ptr->oldest_deferred_in) { + info("Reception queue empty\n"); + return; + } + info("Contents of Reception queue:\n"); + crs = l_ptr->oldest_deferred_in; + while (crs) { + if (crs->data == (void *)0x0000a3a3) { + info("buffer %x invalid\n", crs); + return; + } + msg_dbg(buf_msg(crs), "In rec queue: \n"); + crs = crs->next; + } +} +#endif + +static void link_dump_send_queue(struct link *l_ptr) +{ + if (l_ptr->next_out) { + info("\nContents of unsent queue:\n"); + dbg_print_buf_chain(l_ptr->next_out); + } + info("\nContents of send queue:\n"); + if (l_ptr->first_out) { + dbg_print_buf_chain(l_ptr->first_out); + } + info("Empty send queue\n"); +} + +static void link_print(struct link *l_ptr, struct print_buf *buf, + const char *str) +{ + tipc_printf(buf, str); + if (link_reset_reset(l_ptr) || link_reset_unknown(l_ptr)) + return; + tipc_printf(buf, "Link %x<%s>:", + l_ptr->addr, l_ptr->b_ptr->publ.name); + tipc_printf(buf, ": NXO(%u):", mod(l_ptr->next_out_no)); + tipc_printf(buf, "NXI(%u):", mod(l_ptr->next_in_no)); + tipc_printf(buf, "SQUE"); + if (l_ptr->first_out) { + tipc_printf(buf, "[%u..", msg_seqno(buf_msg(l_ptr->first_out))); + if (l_ptr->next_out) + tipc_printf(buf, "%u..", + msg_seqno(buf_msg(l_ptr->next_out))); + tipc_printf(buf, "%u]", + msg_seqno(buf_msg + (l_ptr->last_out)), l_ptr->out_queue_size); + if ((mod(msg_seqno(buf_msg(l_ptr->last_out)) - + msg_seqno(buf_msg(l_ptr->first_out))) + != (l_ptr->out_queue_size - 1)) + || (l_ptr->last_out->next != 0)) { + tipc_printf(buf, "\nSend queue inconsistency\n"); + tipc_printf(buf, "first_out= %x ", l_ptr->first_out); + tipc_printf(buf, "next_out= %x ", l_ptr->next_out); + tipc_printf(buf, "last_out= %x ", l_ptr->last_out); + link_dump_send_queue(l_ptr); + } + } else + tipc_printf(buf, "[]"); + tipc_printf(buf, "SQSIZ(%u)", l_ptr->out_queue_size); + if (l_ptr->oldest_deferred_in) { + u32 o = msg_seqno(buf_msg(l_ptr->oldest_deferred_in)); + u32 n = msg_seqno(buf_msg(l_ptr->newest_deferred_in)); + tipc_printf(buf, ":RQUE[%u..%u]", o, n); + if (l_ptr->deferred_inqueue_sz != mod((n + 1) - o)) { + tipc_printf(buf, ":RQSIZ(%u)", + l_ptr->deferred_inqueue_sz); + } + } + if (link_working_unknown(l_ptr)) + tipc_printf(buf, ":WU"); + if (link_reset_reset(l_ptr)) + tipc_printf(buf, ":RR"); + if (link_reset_unknown(l_ptr)) + tipc_printf(buf, ":RU"); + if (link_working_working(l_ptr)) + tipc_printf(buf, ":WW"); + tipc_printf(buf, "\n"); +} + diff --git a/net/tipc/link.h b/net/tipc/link.h new file mode 100644 index 00000000000..c2553f07375 --- /dev/null +++ b/net/tipc/link.h @@ -0,0 +1,296 @@ +/* + * net/tipc/link.h: Include file for TIPC link code + * + * Copyright (c) 1995-2006, Ericsson AB + * Copyright (c) 2004-2005, Wind River Systems + * All rights reserved. + * + * Redistribution and use in source and binary forms, with or without + * modification, are permitted provided that the following conditions are met: + * + * 1. Redistributions of source code must retain the above copyright + * notice, this list of conditions and the following disclaimer. + * 2. Redistributions in binary form must reproduce the above copyright + * notice, this list of conditions and the following disclaimer in the + * documentation and/or other materials provided with the distribution. + * 3. Neither the names of the copyright holders nor the names of its + * contributors may be used to endorse or promote products derived from + * this software without specific prior written permission. + * + * Alternatively, this software may be distributed under the terms of the + * GNU General Public License ("GPL") version 2 as published by the Free + * Software Foundation. + * + * THIS SOFTWARE IS PROVIDED BY THE COPYRIGHT HOLDERS AND CONTRIBUTORS "AS IS" + * AND ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT LIMITED TO, THE + * IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR A PARTICULAR PURPOSE + * ARE DISCLAIMED. IN NO EVENT SHALL THE COPYRIGHT OWNER OR CONTRIBUTORS BE + * LIABLE FOR ANY DIRECT, INDIRECT, INCIDENTAL, SPECIAL, EXEMPLARY, OR + * CONSEQUENTIAL DAMAGES (INCLUDING, BUT NOT LIMITED TO, PROCUREMENT OF + * SUBSTITUTE GOODS OR SERVICES; LOSS OF USE, DATA, OR PROFITS; OR BUSINESS + * INTERRUPTION) HOWEVER CAUSED AND ON ANY THEORY OF LIABILITY, WHETHER IN + * CONTRACT, STRICT LIABILITY, OR TORT (INCLUDING NEGLIGENCE OR OTHERWISE) + * ARISING IN ANY WAY OUT OF THE USE OF THIS SOFTWARE, EVEN IF ADVISED OF THE + * POSSIBILITY OF SUCH DAMAGE. + */ + +#ifndef _TIPC_LINK_H +#define _TIPC_LINK_H + +#include "dbg.h" +#include "msg.h" +#include "bearer.h" +#include "node.h" + +#define PUSH_FAILED 1 +#define PUSH_FINISHED 2 + +/* + * Link states + */ + +#define WORKING_WORKING 560810u +#define WORKING_UNKNOWN 560811u +#define RESET_UNKNOWN 560812u +#define RESET_RESET 560813u + +/* + * Starting value for maximum packet size negotiation on unicast links + * (unless bearer MTU is less) + */ + +#define MAX_PKT_DEFAULT 1500 + +/** + * struct link - TIPC link data structure + * @addr: network address of link's peer node + * @name: link name character string + * @media_addr: media address to use when sending messages over link + * @timer: link timer + * @owner: pointer to peer node + * @link_list: adjacent links in bearer's list of links + * @started: indicates if link has been started + * @checkpoint: reference point for triggering link continuity checking + * @peer_session: link session # being used by peer end of link + * @peer_bearer_id: bearer id used by link's peer endpoint + * @b_ptr: pointer to bearer used by link + * @tolerance: minimum link continuity loss needed to reset link [in ms] + * @continuity_interval: link continuity testing interval [in ms] + * @abort_limit: # of unacknowledged continuity probes needed to reset link + * @state: current state of link FSM + * @blocked: indicates if link has been administratively blocked + * @fsm_msg_cnt: # of protocol messages link FSM has sent in current state + * @proto_msg: template for control messages generated by link + * @pmsg: convenience pointer to "proto_msg" field + * @priority: current link priority + * @queue_limit: outbound message queue congestion thresholds (indexed by user) + * @exp_msg_count: # of tunnelled messages expected during link changeover + * @reset_checkpoint: seq # of last acknowledged message at time of link reset + * @max_pkt: current maximum packet size for this link + * @max_pkt_target: desired maximum packet size for this link + * @max_pkt_probes: # of probes based on current (max_pkt, max_pkt_target) + * @out_queue_size: # of messages in outbound message queue + * @first_out: ptr to first outbound message in queue + * @last_out: ptr to last outbound message in queue + * @next_out_no: next sequence number to use for outbound messages + * @last_retransmitted: sequence number of most recently retransmitted message + * @stale_count: # of identical retransmit requests made by peer + * @next_in_no: next sequence number to expect for inbound messages + * @deferred_inqueue_sz: # of messages in inbound message queue + * @oldest_deferred_in: ptr to first inbound message in queue + * @newest_deferred_in: ptr to last inbound message in queue + * @unacked_window: # of inbound messages rx'd without ack'ing back to peer + * @proto_msg_queue: ptr to (single) outbound control message + * @retransm_queue_size: number of messages to retransmit + * @retransm_queue_head: sequence number of first message to retransmit + * @next_out: ptr to first unsent outbound message in queue + * @waiting_ports: linked list of ports waiting for link congestion to abate + * @long_msg_seq_no: next identifier to use for outbound fragmented messages + * @defragm_buf: list of partially reassembled inbound message fragments + * @stats: collects statistics regarding link activity + * @print_buf: print buffer used to log link activity + */ + +struct link { + u32 addr; + char name[TIPC_MAX_LINK_NAME]; + struct tipc_media_addr media_addr; + struct timer_list timer; + struct node *owner; + struct list_head link_list; + + /* Management and link supervision data */ + int started; + u32 checkpoint; + u32 peer_session; + u32 peer_bearer_id; + struct bearer *b_ptr; + u32 tolerance; + u32 continuity_interval; + u32 abort_limit; + int state; + int blocked; + u32 fsm_msg_cnt; + struct { + unchar hdr[INT_H_SIZE]; + unchar body[TIPC_MAX_IF_NAME]; + } proto_msg; + struct tipc_msg *pmsg; + u32 priority; + u32 queue_limit[15]; /* queue_limit[0]==window limit */ + + /* Changeover */ + u32 exp_msg_count; + u32 reset_checkpoint; + + /* Max packet negotiation */ + u32 max_pkt; + u32 max_pkt_target; + u32 max_pkt_probes; + + /* Sending */ + u32 out_queue_size; + struct sk_buff *first_out; + struct sk_buff *last_out; + u32 next_out_no; + u32 last_retransmitted; + u32 stale_count; + + /* Reception */ + u32 next_in_no; + u32 deferred_inqueue_sz; + struct sk_buff *oldest_deferred_in; + struct sk_buff *newest_deferred_in; + u32 unacked_window; + + /* Congestion handling */ + struct sk_buff *proto_msg_queue; + u32 retransm_queue_size; + u32 retransm_queue_head; + struct sk_buff *next_out; + struct list_head waiting_ports; + + /* Fragmentation/defragmentation */ + u32 long_msg_seq_no; + struct sk_buff *defragm_buf; + + /* Statistics */ + struct { + u32 sent_info; /* used in counting # sent packets */ + u32 recv_info; /* used in counting # recv'd packets */ + u32 sent_states; + u32 recv_states; + u32 sent_probes; + u32 recv_probes; + u32 sent_nacks; + u32 recv_nacks; + u32 sent_acks; + u32 sent_bundled; + u32 sent_bundles; + u32 recv_bundled; + u32 recv_bundles; + u32 retransmitted; + u32 sent_fragmented; + u32 sent_fragments; + u32 recv_fragmented; + u32 recv_fragments; + u32 link_congs; /* # port sends blocked by congestion */ + u32 bearer_congs; + u32 deferred_recv; + u32 duplicates; + + /* for statistical profiling of send queue size */ + + u32 max_queue_sz; + u32 accu_queue_sz; + u32 queue_sz_counts; + + /* for statistical profiling of message lengths */ + + u32 msg_length_counts; + u32 msg_lengths_total; + u32 msg_length_profile[7]; +#if 0 + u32 sent_tunneled; + u32 recv_tunneled; +#endif + } stats; + + struct print_buf print_buf; +}; + +struct port; + +struct link *link_create(struct bearer *b_ptr, const u32 peer, + const struct tipc_media_addr *media_addr); +void link_delete(struct link *l_ptr); +void link_changeover(struct link *l_ptr); +void link_send_duplicate(struct link *l_ptr, struct link *dest); +void link_reset_fragments(struct link *l_ptr); +int link_is_up(struct link *l_ptr); +int link_is_active(struct link *l_ptr); +void link_start(struct link *l_ptr); +u32 link_push_packet(struct link *l_ptr); +void link_stop(struct link *l_ptr); +struct sk_buff *link_cmd_config(const void *req_tlv_area, int req_tlv_space, u16 cmd); +struct sk_buff *link_cmd_show_stats(const void *req_tlv_area, int req_tlv_space); +struct sk_buff *link_cmd_reset_stats(const void *req_tlv_area, int req_tlv_space); +void link_reset(struct link *l_ptr); +int link_send(struct sk_buff *buf, u32 dest, u32 selector); +int link_send_buf(struct link *l_ptr, struct sk_buff *buf); +u32 link_get_max_pkt(u32 dest,u32 selector); +int link_send_sections_fast(struct port* sender, + struct iovec const *msg_sect, + const u32 num_sect, + u32 destnode); + +int link_send_long_buf(struct link *l_ptr, struct sk_buff *buf); +void link_tunnel(struct link *l_ptr, struct tipc_msg *tnl_hdr, + struct tipc_msg *msg, u32 selector); +void link_recv_bundle(struct sk_buff *buf); +int link_recv_fragment(struct sk_buff **pending, + struct sk_buff **fb, + struct tipc_msg **msg); +void link_send_proto_msg(struct link *l_ptr, u32 msg_typ, int prob, u32 gap, + u32 tolerance, u32 priority, u32 acked_mtu); +void link_push_queue(struct link *l_ptr); +u32 link_defer_pkt(struct sk_buff **head, struct sk_buff **tail, + struct sk_buff *buf); +void link_wakeup_ports(struct link *l_ptr, int all); +void link_set_queue_limits(struct link *l_ptr, u32 window); +void link_retransmit(struct link *l_ptr, struct sk_buff *start, u32 retransmits); + +/* + * Link sequence number manipulation routines (uses modulo 2**16 arithmetic) + */ + +static inline u32 mod(u32 x) +{ + return x & 0xffffu; +} + +static inline int between(u32 lower, u32 upper, u32 n) +{ + if ((lower < n) && (n < upper)) + return 1; + if ((upper < lower) && ((n > lower) || (n < upper))) + return 1; + return 0; +} + +static inline int less_eq(u32 left, u32 right) +{ + return (mod(right - left) < 32768u); +} + +static inline int less(u32 left, u32 right) +{ + return (less_eq(left, right) && (mod(right) != mod(left))); +} + +static inline u32 lesser(u32 left, u32 right) +{ + return less_eq(left, right) ? left : right; +} + +#endif diff --git a/net/tipc/msg.c b/net/tipc/msg.c new file mode 100644 index 00000000000..03dbc55cb04 --- /dev/null +++ b/net/tipc/msg.c @@ -0,0 +1,334 @@ +/* + * net/tipc/msg.c: TIPC message header routines + * + * Copyright (c) 2000-2006, Ericsson AB + * Copyright (c) 2005, Wind River Systems + * All rights reserved. + * + * Redistribution and use in source and binary forms, with or without + * modification, are permitted provided that the following conditions are met: + * + * 1. Redistributions of source code must retain the above copyright + * notice, this list of conditions and the following disclaimer. + * 2. Redistributions in binary form must reproduce the above copyright + * notice, this list of conditions and the following disclaimer in the + * documentation and/or other materials provided with the distribution. + * 3. Neither the names of the copyright holders nor the names of its + * contributors may be used to endorse or promote products derived from + * this software without specific prior written permission. + * + * Alternatively, this software may be distributed under the terms of the + * GNU General Public License ("GPL") version 2 as published by the Free + * Software Foundation. + * + * THIS SOFTWARE IS PROVIDED BY THE COPYRIGHT HOLDERS AND CONTRIBUTORS "AS IS" + * AND ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT LIMITED TO, THE + * IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR A PARTICULAR PURPOSE + * ARE DISCLAIMED. IN NO EVENT SHALL THE COPYRIGHT OWNER OR CONTRIBUTORS BE + * LIABLE FOR ANY DIRECT, INDIRECT, INCIDENTAL, SPECIAL, EXEMPLARY, OR + * CONSEQUENTIAL DAMAGES (INCLUDING, BUT NOT LIMITED TO, PROCUREMENT OF + * SUBSTITUTE GOODS OR SERVICES; LOSS OF USE, DATA, OR PROFITS; OR BUSINESS + * INTERRUPTION) HOWEVER CAUSED AND ON ANY THEORY OF LIABILITY, WHETHER IN + * CONTRACT, STRICT LIABILITY, OR TORT (INCLUDING NEGLIGENCE OR OTHERWISE) + * ARISING IN ANY WAY OUT OF THE USE OF THIS SOFTWARE, EVEN IF ADVISED OF THE + * POSSIBILITY OF SUCH DAMAGE. + */ + +#include "core.h" +#include "addr.h" +#include "dbg.h" +#include "msg.h" +#include "bearer.h" + + +void msg_set_media_addr(struct tipc_msg *m, struct tipc_media_addr *a) +{ + memcpy(&((int *)m)[5], a, sizeof(*a)); +} + +void msg_get_media_addr(struct tipc_msg *m, struct tipc_media_addr *a) +{ + memcpy(a, &((int*)m)[5], sizeof(*a)); +} + + +void msg_print(struct print_buf *buf, struct tipc_msg *msg, const char *str) +{ + u32 usr = msg_user(msg); + tipc_printf(buf, str); + + switch (usr) { + case MSG_BUNDLER: + tipc_printf(buf, "BNDL::"); + tipc_printf(buf, "MSGS(%u):", msg_msgcnt(msg)); + break; + case BCAST_PROTOCOL: + tipc_printf(buf, "BCASTP::"); + break; + case MSG_FRAGMENTER: + tipc_printf(buf, "FRAGM::"); + switch (msg_type(msg)) { + case FIRST_FRAGMENT: + tipc_printf(buf, "FIRST:"); + break; + case FRAGMENT: + tipc_printf(buf, "BODY:"); + break; + case LAST_FRAGMENT: + tipc_printf(buf, "LAST:"); + break; + default: + tipc_printf(buf, "UNKNOWN:%x",msg_type(msg)); + + } + tipc_printf(buf, "NO(%u/%u):",msg_long_msgno(msg), + msg_fragm_no(msg)); + break; + case DATA_LOW: + case DATA_MEDIUM: + case DATA_HIGH: + case DATA_CRITICAL: + tipc_printf(buf, "DAT%u:", msg_user(msg)); + if (msg_short(msg)) { + tipc_printf(buf, "CON:"); + break; + } + switch (msg_type(msg)) { + case TIPC_CONN_MSG: + tipc_printf(buf, "CON:"); + break; + case TIPC_MCAST_MSG: + tipc_printf(buf, "MCST:"); + break; + case TIPC_NAMED_MSG: + tipc_printf(buf, "NAM:"); + break; + case TIPC_DIRECT_MSG: + tipc_printf(buf, "DIR:"); + break; + default: + tipc_printf(buf, "UNKNOWN TYPE %u",msg_type(msg)); + } + if (msg_routed(msg) && !msg_non_seq(msg)) + tipc_printf(buf, "ROUT:"); + if (msg_reroute_cnt(msg)) + tipc_printf(buf, "REROUTED(%u):", + msg_reroute_cnt(msg)); + break; + case NAME_DISTRIBUTOR: + tipc_printf(buf, "NMD::"); + switch (msg_type(msg)) { + case PUBLICATION: + tipc_printf(buf, "PUBL(%u):", (msg_size(msg) - msg_hdr_sz(msg)) / 20); /* Items */ + break; + case WITHDRAWAL: + tipc_printf(buf, "WDRW:"); + break; + default: + tipc_printf(buf, "UNKNOWN:%x",msg_type(msg)); + } + if (msg_routed(msg)) + tipc_printf(buf, "ROUT:"); + if (msg_reroute_cnt(msg)) + tipc_printf(buf, "REROUTED(%u):", + msg_reroute_cnt(msg)); + break; + case CONN_MANAGER: + tipc_printf(buf, "CONN_MNG:"); + switch (msg_type(msg)) { + case CONN_PROBE: + tipc_printf(buf, "PROBE:"); + break; + case CONN_PROBE_REPLY: + tipc_printf(buf, "PROBE_REPLY:"); + break; + case CONN_ACK: + tipc_printf(buf, "CONN_ACK:"); + tipc_printf(buf, "ACK(%u):",msg_msgcnt(msg)); + break; + default: + tipc_printf(buf, "UNKNOWN TYPE:%x",msg_type(msg)); + } + if (msg_routed(msg)) + tipc_printf(buf, "ROUT:"); + if (msg_reroute_cnt(msg)) + tipc_printf(buf, "REROUTED(%u):",msg_reroute_cnt(msg)); + break; + case LINK_PROTOCOL: + tipc_printf(buf, "PROT:TIM(%u):",msg_timestamp(msg)); + switch (msg_type(msg)) { + case STATE_MSG: + tipc_printf(buf, "STATE:"); + tipc_printf(buf, "%s:",msg_probe(msg) ? "PRB" :""); + tipc_printf(buf, "NXS(%u):",msg_next_sent(msg)); + tipc_printf(buf, "GAP(%u):",msg_seq_gap(msg)); + tipc_printf(buf, "LSTBC(%u):",msg_last_bcast(msg)); + break; + case RESET_MSG: + tipc_printf(buf, "RESET:"); + if (msg_size(msg) != msg_hdr_sz(msg)) + tipc_printf(buf, "BEAR:%s:",msg_data(msg)); + break; + case ACTIVATE_MSG: + tipc_printf(buf, "ACTIVATE:"); + break; + default: + tipc_printf(buf, "UNKNOWN TYPE:%x",msg_type(msg)); + } + tipc_printf(buf, "PLANE(%c):",msg_net_plane(msg)); + tipc_printf(buf, "SESS(%u):",msg_session(msg)); + break; + case CHANGEOVER_PROTOCOL: + tipc_printf(buf, "TUNL:"); + switch (msg_type(msg)) { + case DUPLICATE_MSG: + tipc_printf(buf, "DUPL:"); + break; + case ORIGINAL_MSG: + tipc_printf(buf, "ORIG:"); + tipc_printf(buf, "EXP(%u)",msg_msgcnt(msg)); + break; + default: + tipc_printf(buf, "UNKNOWN TYPE:%x",msg_type(msg)); + } + break; + case ROUTE_DISTRIBUTOR: + tipc_printf(buf, "ROUTING_MNG:"); + switch (msg_type(msg)) { + case EXT_ROUTING_TABLE: + tipc_printf(buf, "EXT_TBL:"); + tipc_printf(buf, "TO:%x:",msg_remote_node(msg)); + break; + case LOCAL_ROUTING_TABLE: + tipc_printf(buf, "LOCAL_TBL:"); + tipc_printf(buf, "TO:%x:",msg_remote_node(msg)); + break; + case SLAVE_ROUTING_TABLE: + tipc_printf(buf, "DP_TBL:"); + tipc_printf(buf, "TO:%x:",msg_remote_node(msg)); + break; + case ROUTE_ADDITION: + tipc_printf(buf, "ADD:"); + tipc_printf(buf, "TO:%x:",msg_remote_node(msg)); + break; + case ROUTE_REMOVAL: + tipc_printf(buf, "REMOVE:"); + tipc_printf(buf, "TO:%x:",msg_remote_node(msg)); + break; + default: + tipc_printf(buf, "UNKNOWN TYPE:%x",msg_type(msg)); + } + break; + case LINK_CONFIG: + tipc_printf(buf, "CFG:"); + switch (msg_type(msg)) { + case DSC_REQ_MSG: + tipc_printf(buf, "DSC_REQ:"); + break; + case DSC_RESP_MSG: + tipc_printf(buf, "DSC_RESP:"); + break; + default: + tipc_printf(buf, "UNKNOWN TYPE:%x:",msg_type(msg)); + break; + } + break; + default: + tipc_printf(buf, "UNKNOWN USER:"); + } + + switch (usr) { + case CONN_MANAGER: + case NAME_DISTRIBUTOR: + case DATA_LOW: + case DATA_MEDIUM: + case DATA_HIGH: + case DATA_CRITICAL: + if (msg_short(msg)) + break; /* No error */ + switch (msg_errcode(msg)) { + case TIPC_OK: + break; + case TIPC_ERR_NO_NAME: + tipc_printf(buf, "NO_NAME:"); + break; + case TIPC_ERR_NO_PORT: + tipc_printf(buf, "NO_PORT:"); + break; + case TIPC_ERR_NO_NODE: + tipc_printf(buf, "NO_PROC:"); + break; + case TIPC_ERR_OVERLOAD: + tipc_printf(buf, "OVERLOAD:"); + break; + case TIPC_CONN_SHUTDOWN: + tipc_printf(buf, "SHUTDOWN:"); + break; + default: + tipc_printf(buf, "UNKNOWN ERROR(%x):", + msg_errcode(msg)); + } + default:{} + } + + tipc_printf(buf, "HZ(%u):", msg_hdr_sz(msg)); + tipc_printf(buf, "SZ(%u):", msg_size(msg)); + tipc_printf(buf, "SQNO(%u):", msg_seqno(msg)); + + if (msg_non_seq(msg)) + tipc_printf(buf, "NOSEQ:"); + else { + tipc_printf(buf, "ACK(%u):", msg_ack(msg)); + } + tipc_printf(buf, "BACK(%u):", msg_bcast_ack(msg)); + tipc_printf(buf, "PRND(%x)", msg_prevnode(msg)); + + if (msg_isdata(msg)) { + if (msg_named(msg)) { + tipc_printf(buf, "NTYP(%u):", msg_nametype(msg)); + tipc_printf(buf, "NINST(%u)", msg_nameinst(msg)); + } + } + + if ((usr != LINK_PROTOCOL) && (usr != LINK_CONFIG) && + (usr != MSG_BUNDLER)) { + if (!msg_short(msg)) { + tipc_printf(buf, ":ORIG(%x:%u):", + msg_orignode(msg), msg_origport(msg)); + tipc_printf(buf, ":DEST(%x:%u):", + msg_destnode(msg), msg_destport(msg)); + } else { + tipc_printf(buf, ":OPRT(%u):", msg_origport(msg)); + tipc_printf(buf, ":DPRT(%u):", msg_destport(msg)); + } + if (msg_routed(msg) && !msg_non_seq(msg)) + tipc_printf(buf, ":TSEQN(%u)", msg_transp_seqno(msg)); + } + if (msg_user(msg) == NAME_DISTRIBUTOR) { + tipc_printf(buf, ":ONOD(%x):", msg_orignode(msg)); + tipc_printf(buf, ":DNOD(%x):", msg_destnode(msg)); + if (msg_routed(msg)) { + tipc_printf(buf, ":CSEQN(%u)", msg_transp_seqno(msg)); + } + } + + if (msg_user(msg) == LINK_CONFIG) { + u32* raw = (u32*)msg; + struct tipc_media_addr* orig = (struct tipc_media_addr*)&raw[5]; + tipc_printf(buf, ":REQL(%u):", msg_req_links(msg)); + tipc_printf(buf, ":DDOM(%x):", msg_dest_domain(msg)); + tipc_printf(buf, ":NETID(%u):", msg_bc_netid(msg)); + media_addr_printf(buf, orig); + } + if (msg_user(msg) == BCAST_PROTOCOL) { + tipc_printf(buf, "BCNACK:AFTER(%u):", msg_bcgap_after(msg)); + tipc_printf(buf, "TO(%u):", msg_bcgap_to(msg)); + } + tipc_printf(buf, "\n"); + if ((usr == CHANGEOVER_PROTOCOL) && (msg_msgcnt(msg))) { + msg_print(buf,msg_get_wrapped(msg)," /"); + } + if ((usr == MSG_FRAGMENTER) && (msg_type(msg) == FIRST_FRAGMENT)) { + msg_print(buf,msg_get_wrapped(msg)," /"); + } +} diff --git a/net/tipc/msg.h b/net/tipc/msg.h new file mode 100644 index 00000000000..662c81862a0 --- /dev/null +++ b/net/tipc/msg.h @@ -0,0 +1,818 @@ +/* + * net/tipc/msg.h: Include file for TIPC message header routines + * + * Copyright (c) 2000-2006, Ericsson AB + * Copyright (c) 2005, Wind River Systems + * All rights reserved. + * + * Redistribution and use in source and binary forms, with or without + * modification, are permitted provided that the following conditions are met: + * + * 1. Redistributions of source code must retain the above copyright + * notice, this list of conditions and the following disclaimer. + * 2. Redistributions in binary form must reproduce the above copyright + * notice, this list of conditions and the following disclaimer in the + * documentation and/or other materials provided with the distribution. + * 3. Neither the names of the copyright holders nor the names of its + * contributors may be used to endorse or promote products derived from + * this software without specific prior written permission. + * + * Alternatively, this software may be distributed under the terms of the + * GNU General Public License ("GPL") version 2 as published by the Free + * Software Foundation. + * + * THIS SOFTWARE IS PROVIDED BY THE COPYRIGHT HOLDERS AND CONTRIBUTORS "AS IS" + * AND ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT LIMITED TO, THE + * IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR A PARTICULAR PURPOSE + * ARE DISCLAIMED. IN NO EVENT SHALL THE COPYRIGHT OWNER OR CONTRIBUTORS BE + * LIABLE FOR ANY DIRECT, INDIRECT, INCIDENTAL, SPECIAL, EXEMPLARY, OR + * CONSEQUENTIAL DAMAGES (INCLUDING, BUT NOT LIMITED TO, PROCUREMENT OF + * SUBSTITUTE GOODS OR SERVICES; LOSS OF USE, DATA, OR PROFITS; OR BUSINESS + * INTERRUPTION) HOWEVER CAUSED AND ON ANY THEORY OF LIABILITY, WHETHER IN + * CONTRACT, STRICT LIABILITY, OR TORT (INCLUDING NEGLIGENCE OR OTHERWISE) + * ARISING IN ANY WAY OUT OF THE USE OF THIS SOFTWARE, EVEN IF ADVISED OF THE + * POSSIBILITY OF SUCH DAMAGE. + */ + +#ifndef _TIPC_MSG_H +#define _TIPC_MSG_H + +#include <net/tipc/tipc_msg.h> + +#define TIPC_VERSION 2 +#define DATA_LOW TIPC_LOW_IMPORTANCE +#define DATA_MEDIUM TIPC_MEDIUM_IMPORTANCE +#define DATA_HIGH TIPC_HIGH_IMPORTANCE +#define DATA_CRITICAL TIPC_CRITICAL_IMPORTANCE +#define SHORT_H_SIZE 24 /* Connected,in cluster */ +#define DIR_MSG_H_SIZE 32 /* Directly addressed messages */ +#define CONN_MSG_H_SIZE 36 /* Routed connected msgs*/ +#define LONG_H_SIZE 40 /* Named Messages */ +#define MCAST_H_SIZE 44 /* Multicast messages */ +#define MAX_H_SIZE 60 /* Inclusive full options */ +#define MAX_MSG_SIZE (MAX_H_SIZE + TIPC_MAX_USER_MSG_SIZE) +#define LINK_CONFIG 13 + + +/* + TIPC user data message header format, version 2 + + - Fundamental definitions available to privileged TIPC users + are located in tipc_msg.h. + - Remaining definitions available to TIPC internal users appear below. +*/ + + +static inline void msg_set_word(struct tipc_msg *m, u32 w, u32 val) +{ + m->hdr[w] = htonl(val); +} + +static inline void msg_set_bits(struct tipc_msg *m, u32 w, + u32 pos, u32 mask, u32 val) +{ + u32 word = msg_word(m,w) & ~(mask << pos); + msg_set_word(m, w, (word |= (val << pos))); +} + +/* + * Word 0 + */ + +static inline u32 msg_version(struct tipc_msg *m) +{ + return msg_bits(m, 0, 29, 7); +} + +static inline void msg_set_version(struct tipc_msg *m) +{ + msg_set_bits(m, 0, 29, 0xf, TIPC_VERSION); +} + +static inline u32 msg_user(struct tipc_msg *m) +{ + return msg_bits(m, 0, 25, 0xf); +} + +static inline u32 msg_isdata(struct tipc_msg *m) +{ + return (msg_user(m) <= DATA_CRITICAL); +} + +static inline void msg_set_user(struct tipc_msg *m, u32 n) +{ + msg_set_bits(m, 0, 25, 0xf, n); +} + +static inline void msg_set_importance(struct tipc_msg *m, u32 i) +{ + msg_set_user(m, i); +} + +static inline void msg_set_hdr_sz(struct tipc_msg *m,u32 n) +{ + msg_set_bits(m, 0, 21, 0xf, n>>2); +} + +static inline int msg_non_seq(struct tipc_msg *m) +{ + return msg_bits(m, 0, 20, 1); +} + +static inline void msg_set_non_seq(struct tipc_msg *m) +{ + msg_set_bits(m, 0, 20, 1, 1); +} + +static inline int msg_dest_droppable(struct tipc_msg *m) +{ + return msg_bits(m, 0, 19, 1); +} + +static inline void msg_set_dest_droppable(struct tipc_msg *m, u32 d) +{ + msg_set_bits(m, 0, 19, 1, d); +} + +static inline int msg_src_droppable(struct tipc_msg *m) +{ + return msg_bits(m, 0, 18, 1); +} + +static inline void msg_set_src_droppable(struct tipc_msg *m, u32 d) +{ + msg_set_bits(m, 0, 18, 1, d); +} + +static inline void msg_set_size(struct tipc_msg *m, u32 sz) +{ + m->hdr[0] = htonl((msg_word(m, 0) & ~0x1ffff) | sz); +} + + +/* + * Word 1 + */ + +static inline void msg_set_type(struct tipc_msg *m, u32 n) +{ + msg_set_bits(m, 1, 29, 0x7, n); +} + +static inline void msg_set_errcode(struct tipc_msg *m, u32 err) +{ + msg_set_bits(m, 1, 25, 0xf, err); +} + +static inline u32 msg_reroute_cnt(struct tipc_msg *m) +{ + return msg_bits(m, 1, 21, 0xf); +} + +static inline void msg_incr_reroute_cnt(struct tipc_msg *m) +{ + msg_set_bits(m, 1, 21, 0xf, msg_reroute_cnt(m) + 1); +} + +static inline void msg_reset_reroute_cnt(struct tipc_msg *m) +{ + msg_set_bits(m, 1, 21, 0xf, 0); +} + +static inline u32 msg_lookup_scope(struct tipc_msg *m) +{ + return msg_bits(m, 1, 19, 0x3); +} + +static inline void msg_set_lookup_scope(struct tipc_msg *m, u32 n) +{ + msg_set_bits(m, 1, 19, 0x3, n); +} + +static inline void msg_set_options(struct tipc_msg *m, const char *opt, u32 sz) +{ + u32 hsz = msg_hdr_sz(m); + char *to = (char *)&m->hdr[hsz/4]; + + if ((hsz < DIR_MSG_H_SIZE) || ((hsz + sz) > MAX_H_SIZE)) + return; + msg_set_bits(m, 1, 16, 0x7, (hsz - 28)/4); + msg_set_hdr_sz(m, hsz + sz); + memcpy(to, opt, sz); +} + +static inline u32 msg_bcast_ack(struct tipc_msg *m) +{ + return msg_bits(m, 1, 0, 0xffff); +} + +static inline void msg_set_bcast_ack(struct tipc_msg *m, u32 n) +{ + msg_set_bits(m, 1, 0, 0xffff, n); +} + + +/* + * Word 2 + */ + +static inline u32 msg_ack(struct tipc_msg *m) +{ + return msg_bits(m, 2, 16, 0xffff); +} + +static inline void msg_set_ack(struct tipc_msg *m, u32 n) +{ + msg_set_bits(m, 2, 16, 0xffff, n); +} + +static inline u32 msg_seqno(struct tipc_msg *m) +{ + return msg_bits(m, 2, 0, 0xffff); +} + +static inline void msg_set_seqno(struct tipc_msg *m, u32 n) +{ + msg_set_bits(m, 2, 0, 0xffff, n); +} + + +/* + * Words 3-10 + */ + + +static inline void msg_set_prevnode(struct tipc_msg *m, u32 a) +{ + msg_set_word(m, 3, a); +} + +static inline void msg_set_origport(struct tipc_msg *m, u32 p) +{ + msg_set_word(m, 4, p); +} + +static inline void msg_set_destport(struct tipc_msg *m, u32 p) +{ + msg_set_word(m, 5, p); +} + +static inline void msg_set_mc_netid(struct tipc_msg *m, u32 p) +{ + msg_set_word(m, 5, p); +} + +static inline void msg_set_orignode(struct tipc_msg *m, u32 a) +{ + msg_set_word(m, 6, a); +} + +static inline void msg_set_destnode(struct tipc_msg *m, u32 a) +{ + msg_set_word(m, 7, a); +} + +static inline int msg_is_dest(struct tipc_msg *m, u32 d) +{ + return(msg_short(m) || (msg_destnode(m) == d)); +} + +static inline u32 msg_routed(struct tipc_msg *m) +{ + if (likely(msg_short(m))) + return 0; + return(msg_destnode(m) ^ msg_orignode(m)) >> 11; +} + +static inline void msg_set_nametype(struct tipc_msg *m, u32 n) +{ + msg_set_word(m, 8, n); +} + +static inline u32 msg_transp_seqno(struct tipc_msg *m) +{ + return msg_word(m, 8); +} + +static inline void msg_set_timestamp(struct tipc_msg *m, u32 n) +{ + msg_set_word(m, 8, n); +} + +static inline u32 msg_timestamp(struct tipc_msg *m) +{ + return msg_word(m, 8); +} + +static inline void msg_set_transp_seqno(struct tipc_msg *m, u32 n) +{ + msg_set_word(m, 8, n); +} + +static inline void msg_set_namelower(struct tipc_msg *m, u32 n) +{ + msg_set_word(m, 9, n); +} + +static inline void msg_set_nameinst(struct tipc_msg *m, u32 n) +{ + msg_set_namelower(m, n); +} + +static inline void msg_set_nameupper(struct tipc_msg *m, u32 n) +{ + msg_set_word(m, 10, n); +} + +static inline struct tipc_msg *msg_get_wrapped(struct tipc_msg *m) +{ + return (struct tipc_msg *)msg_data(m); +} + +static inline void msg_expand(struct tipc_msg *m, u32 destnode) +{ + if (!msg_short(m)) + return; + msg_set_hdr_sz(m, LONG_H_SIZE); + msg_set_orignode(m, msg_prevnode(m)); + msg_set_destnode(m, destnode); + memset(&m->hdr[8], 0, 12); +} + + + +/* + TIPC internal message header format, version 2 + + 1 0 9 8 7 6 5 4|3 2 1 0 9 8 7 6|5 4 3 2 1 0 9 8|7 6 5 4 3 2 1 0 + +-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+ + w0:|vers |msg usr|hdr sz |n|resrv| packet size | + +-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+ + w1:|m typ|rsv=0| sequence gap | broadcast ack no | + +-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+ + w2:| link level ack no/bc_gap_from | seq no / bcast_gap_to | + +-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+ + w3:| previous node | + +-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+ + w4:| next sent broadcast/fragm no | next sent pkt/ fragm msg no | + +-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+ + w5:| session no |rsv=0|r|berid|link prio|netpl|p| + +-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+ + w6:| originating node | + +-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+ + w7:| destination node | + +-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+ + w8:| transport sequence number | + +-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+ + w9:| msg count / bcast tag | link tolerance | + +-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+ + \ \ + / User Specific Data / + \ \ + +-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+ + + NB: CONN_MANAGER use data message format. LINK_CONFIG has own format. +*/ + +/* + * Internal users + */ + +#define BCAST_PROTOCOL 5 +#define MSG_BUNDLER 6 +#define LINK_PROTOCOL 7 +#define CONN_MANAGER 8 +#define ROUTE_DISTRIBUTOR 9 +#define CHANGEOVER_PROTOCOL 10 +#define NAME_DISTRIBUTOR 11 +#define MSG_FRAGMENTER 12 +#define LINK_CONFIG 13 +#define INT_H_SIZE 40 +#define DSC_H_SIZE 40 + +/* + * Connection management protocol messages + */ + +#define CONN_PROBE 0 +#define CONN_PROBE_REPLY 1 +#define CONN_ACK 2 + +/* + * Name distributor messages + */ + +#define PUBLICATION 0 +#define WITHDRAWAL 1 + + +/* + * Word 1 + */ + +static inline u32 msg_seq_gap(struct tipc_msg *m) +{ + return msg_bits(m, 1, 16, 0xff); +} + +static inline void msg_set_seq_gap(struct tipc_msg *m, u32 n) +{ + msg_set_bits(m, 1, 16, 0xff, n); +} + +static inline u32 msg_req_links(struct tipc_msg *m) +{ + return msg_bits(m, 1, 16, 0xfff); +} + +static inline void msg_set_req_links(struct tipc_msg *m, u32 n) +{ + msg_set_bits(m, 1, 16, 0xfff, n); +} + + +/* + * Word 2 + */ + +static inline u32 msg_dest_domain(struct tipc_msg *m) +{ + return msg_word(m, 2); +} + +static inline void msg_set_dest_domain(struct tipc_msg *m, u32 n) +{ + msg_set_word(m, 2, n); +} + +static inline u32 msg_bcgap_after(struct tipc_msg *m) +{ + return msg_bits(m, 2, 16, 0xffff); +} + +static inline void msg_set_bcgap_after(struct tipc_msg *m, u32 n) +{ + msg_set_bits(m, 2, 16, 0xffff, n); +} + +static inline u32 msg_bcgap_to(struct tipc_msg *m) +{ + return msg_bits(m, 2, 0, 0xffff); +} + +static inline void msg_set_bcgap_to(struct tipc_msg *m, u32 n) +{ + msg_set_bits(m, 2, 0, 0xffff, n); +} + + +/* + * Word 4 + */ + +static inline u32 msg_last_bcast(struct tipc_msg *m) +{ + return msg_bits(m, 4, 16, 0xffff); +} + +static inline void msg_set_last_bcast(struct tipc_msg *m, u32 n) +{ + msg_set_bits(m, 4, 16, 0xffff, n); +} + + +static inline u32 msg_fragm_no(struct tipc_msg *m) +{ + return msg_bits(m, 4, 16, 0xffff); +} + +static inline void msg_set_fragm_no(struct tipc_msg *m, u32 n) +{ + msg_set_bits(m, 4, 16, 0xffff, n); +} + + +static inline u32 msg_next_sent(struct tipc_msg *m) +{ + return msg_bits(m, 4, 0, 0xffff); +} + +static inline void msg_set_next_sent(struct tipc_msg *m, u32 n) +{ + msg_set_bits(m, 4, 0, 0xffff, n); +} + + +static inline u32 msg_long_msgno(struct tipc_msg *m) +{ + return msg_bits(m, 4, 0, 0xffff); +} + +static inline void msg_set_long_msgno(struct tipc_msg *m, u32 n) +{ + msg_set_bits(m, 4, 0, 0xffff, n); +} + +static inline u32 msg_bc_netid(struct tipc_msg *m) +{ + return msg_word(m, 4); +} + +static inline void msg_set_bc_netid(struct tipc_msg *m, u32 id) +{ + msg_set_word(m, 4, id); +} + +static inline u32 msg_link_selector(struct tipc_msg *m) +{ + return msg_bits(m, 4, 0, 1); +} + +static inline void msg_set_link_selector(struct tipc_msg *m, u32 n) +{ + msg_set_bits(m, 4, 0, 1, (n & 1)); +} + +/* + * Word 5 + */ + +static inline u32 msg_session(struct tipc_msg *m) +{ + return msg_bits(m, 5, 16, 0xffff); +} + +static inline void msg_set_session(struct tipc_msg *m, u32 n) +{ + msg_set_bits(m, 5, 16, 0xffff, n); +} + +static inline u32 msg_probe(struct tipc_msg *m) +{ + return msg_bits(m, 5, 0, 1); +} + +static inline void msg_set_probe(struct tipc_msg *m, u32 val) +{ + msg_set_bits(m, 5, 0, 1, (val & 1)); +} + +static inline char msg_net_plane(struct tipc_msg *m) +{ + return msg_bits(m, 5, 1, 7) + 'A'; +} + +static inline void msg_set_net_plane(struct tipc_msg *m, char n) +{ + msg_set_bits(m, 5, 1, 7, (n - 'A')); +} + +static inline u32 msg_linkprio(struct tipc_msg *m) +{ + return msg_bits(m, 5, 4, 0x1f); +} + +static inline void msg_set_linkprio(struct tipc_msg *m, u32 n) +{ + msg_set_bits(m, 5, 4, 0x1f, n); +} + +static inline u32 msg_bearer_id(struct tipc_msg *m) +{ + return msg_bits(m, 5, 9, 0x7); +} + +static inline void msg_set_bearer_id(struct tipc_msg *m, u32 n) +{ + msg_set_bits(m, 5, 9, 0x7, n); +} + +static inline u32 msg_redundant_link(struct tipc_msg *m) +{ + return msg_bits(m, 5, 12, 0x1); +} + +static inline void msg_set_redundant_link(struct tipc_msg *m) +{ + msg_set_bits(m, 5, 12, 0x1, 1); +} + +static inline void msg_clear_redundant_link(struct tipc_msg *m) +{ + msg_set_bits(m, 5, 12, 0x1, 0); +} + + +/* + * Word 9 + */ + +static inline u32 msg_msgcnt(struct tipc_msg *m) +{ + return msg_bits(m, 9, 16, 0xffff); +} + +static inline void msg_set_msgcnt(struct tipc_msg *m, u32 n) +{ + msg_set_bits(m, 9, 16, 0xffff, n); +} + +static inline u32 msg_bcast_tag(struct tipc_msg *m) +{ + return msg_bits(m, 9, 16, 0xffff); +} + +static inline void msg_set_bcast_tag(struct tipc_msg *m, u32 n) +{ + msg_set_bits(m, 9, 16, 0xffff, n); +} + +static inline u32 msg_max_pkt(struct tipc_msg *m) +{ + return (msg_bits(m, 9, 16, 0xffff) * 4); +} + +static inline void msg_set_max_pkt(struct tipc_msg *m, u32 n) +{ + msg_set_bits(m, 9, 16, 0xffff, (n / 4)); +} + +static inline u32 msg_link_tolerance(struct tipc_msg *m) +{ + return msg_bits(m, 9, 0, 0xffff); +} + +static inline void msg_set_link_tolerance(struct tipc_msg *m, u32 n) +{ + msg_set_bits(m, 9, 0, 0xffff, n); +} + +/* + * Routing table message data + */ + + +static inline u32 msg_remote_node(struct tipc_msg *m) +{ + return msg_word(m, msg_hdr_sz(m)/4); +} + +static inline void msg_set_remote_node(struct tipc_msg *m, u32 a) +{ + msg_set_word(m, msg_hdr_sz(m)/4, a); +} + +static inline int msg_dataoctet(struct tipc_msg *m, u32 pos) +{ + return(msg_data(m)[pos + 4] != 0); +} + +static inline void msg_set_dataoctet(struct tipc_msg *m, u32 pos) +{ + msg_data(m)[pos + 4] = 1; +} + +/* + * Segmentation message types + */ + +#define FIRST_FRAGMENT 0 +#define FRAGMENT 1 +#define LAST_FRAGMENT 2 + +/* + * Link management protocol message types + */ + +#define STATE_MSG 0 +#define RESET_MSG 1 +#define ACTIVATE_MSG 2 + +/* + * Changeover tunnel message types + */ +#define DUPLICATE_MSG 0 +#define ORIGINAL_MSG 1 + +/* + * Routing table message types + */ +#define EXT_ROUTING_TABLE 0 +#define LOCAL_ROUTING_TABLE 1 +#define SLAVE_ROUTING_TABLE 2 +#define ROUTE_ADDITION 3 +#define ROUTE_REMOVAL 4 + +/* + * Config protocol message types + */ + +#define DSC_REQ_MSG 0 +#define DSC_RESP_MSG 1 + +static inline u32 msg_tot_importance(struct tipc_msg *m) +{ + if (likely(msg_isdata(m))) { + if (likely(msg_orignode(m) == tipc_own_addr)) + return msg_importance(m); + return msg_importance(m) + 4; + } + if ((msg_user(m) == MSG_FRAGMENTER) && + (msg_type(m) == FIRST_FRAGMENT)) + return msg_importance(msg_get_wrapped(m)); + return msg_importance(m); +} + + +static inline void msg_init(struct tipc_msg *m, u32 user, u32 type, + u32 err, u32 hsize, u32 destnode) +{ + memset(m, 0, hsize); + msg_set_version(m); + msg_set_user(m, user); + msg_set_hdr_sz(m, hsize); + msg_set_size(m, hsize); + msg_set_prevnode(m, tipc_own_addr); + msg_set_type(m, type); + msg_set_errcode(m, err); + if (!msg_short(m)) { + msg_set_orignode(m, tipc_own_addr); + msg_set_destnode(m, destnode); + } +} + +/** + * msg_calc_data_size - determine total data size for message + */ + +static inline int msg_calc_data_size(struct iovec const *msg_sect, u32 num_sect) +{ + int dsz = 0; + int i; + + for (i = 0; i < num_sect; i++) + dsz += msg_sect[i].iov_len; + return dsz; +} + +/** + * msg_build - create message using specified header and data + * + * Note: Caller must not hold any locks in case copy_from_user() is interrupted! + * + * Returns message data size or errno + */ + +static inline int msg_build(struct tipc_msg *hdr, + struct iovec const *msg_sect, u32 num_sect, + int max_size, int usrmem, struct sk_buff** buf) +{ + int dsz, sz, hsz, pos, res, cnt; + + dsz = msg_calc_data_size(msg_sect, num_sect); + if (unlikely(dsz > TIPC_MAX_USER_MSG_SIZE)) { + *buf = NULL; + return -EINVAL; + } + + pos = hsz = msg_hdr_sz(hdr); + sz = hsz + dsz; + msg_set_size(hdr, sz); + if (unlikely(sz > max_size)) { + *buf = NULL; + return dsz; + } + + *buf = buf_acquire(sz); + if (!(*buf)) + return -ENOMEM; + memcpy((*buf)->data, (unchar *)hdr, hsz); + for (res = 1, cnt = 0; res && (cnt < num_sect); cnt++) { + if (likely(usrmem)) + res = !copy_from_user((*buf)->data + pos, + msg_sect[cnt].iov_base, + msg_sect[cnt].iov_len); + else + memcpy((*buf)->data + pos, msg_sect[cnt].iov_base, + msg_sect[cnt].iov_len); + pos += msg_sect[cnt].iov_len; + } + if (likely(res)) + return dsz; + + buf_discard(*buf); + *buf = NULL; + return -EFAULT; +} + + +struct tipc_media_addr; + +extern void msg_set_media_addr(struct tipc_msg *m, + struct tipc_media_addr *a); + +extern void msg_get_media_addr(struct tipc_msg *m, + struct tipc_media_addr *a); + + +#endif diff --git a/net/tipc/name_distr.c b/net/tipc/name_distr.c new file mode 100644 index 00000000000..41cbaf1a4a7 --- /dev/null +++ b/net/tipc/name_distr.c @@ -0,0 +1,309 @@ +/* + * net/tipc/name_distr.c: TIPC name distribution code + * + * Copyright (c) 2000-2006, Ericsson AB + * Copyright (c) 2005, Wind River Systems + * All rights reserved. + * + * Redistribution and use in source and binary forms, with or without + * modification, are permitted provided that the following conditions are met: + * + * 1. Redistributions of source code must retain the above copyright + * notice, this list of conditions and the following disclaimer. + * 2. Redistributions in binary form must reproduce the above copyright + * notice, this list of conditions and the following disclaimer in the + * documentation and/or other materials provided with the distribution. + * 3. Neither the names of the copyright holders nor the names of its + * contributors may be used to endorse or promote products derived from + * this software without specific prior written permission. + * + * Alternatively, this software may be distributed under the terms of the + * GNU General Public License ("GPL") version 2 as published by the Free + * Software Foundation. + * + * THIS SOFTWARE IS PROVIDED BY THE COPYRIGHT HOLDERS AND CONTRIBUTORS "AS IS" + * AND ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT LIMITED TO, THE + * IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR A PARTICULAR PURPOSE + * ARE DISCLAIMED. IN NO EVENT SHALL THE COPYRIGHT OWNER OR CONTRIBUTORS BE + * LIABLE FOR ANY DIRECT, INDIRECT, INCIDENTAL, SPECIAL, EXEMPLARY, OR + * CONSEQUENTIAL DAMAGES (INCLUDING, BUT NOT LIMITED TO, PROCUREMENT OF + * SUBSTITUTE GOODS OR SERVICES; LOSS OF USE, DATA, OR PROFITS; OR BUSINESS + * INTERRUPTION) HOWEVER CAUSED AND ON ANY THEORY OF LIABILITY, WHETHER IN + * CONTRACT, STRICT LIABILITY, OR TORT (INCLUDING NEGLIGENCE OR OTHERWISE) + * ARISING IN ANY WAY OUT OF THE USE OF THIS SOFTWARE, EVEN IF ADVISED OF THE + * POSSIBILITY OF SUCH DAMAGE. + */ + +#include "core.h" +#include "cluster.h" +#include "dbg.h" +#include "link.h" +#include "msg.h" +#include "name_distr.h" + +#undef DBG_OUTPUT +#define DBG_OUTPUT NULL + +#define ITEM_SIZE sizeof(struct distr_item) + +/** + * struct distr_item - publication info distributed to other nodes + * @type: name sequence type + * @lower: name sequence lower bound + * @upper: name sequence upper bound + * @ref: publishing port reference + * @key: publication key + * + * ===> All fields are stored in network byte order. <=== + * + * First 3 fields identify (name or) name sequence being published. + * Reference field uniquely identifies port that published name sequence. + * Key field uniquely identifies publication, in the event a port has + * multiple publications of the same name sequence. + * + * Note: There is no field that identifies the publishing node because it is + * the same for all items contained within a publication message. + */ + +struct distr_item { + u32 type; + u32 lower; + u32 upper; + u32 ref; + u32 key; +}; + +/** + * List of externally visible publications by this node -- + * that is, all publications having scope > TIPC_NODE_SCOPE. + */ + +static LIST_HEAD(publ_root); +static u32 publ_cnt = 0; + +/** + * publ_to_item - add publication info to a publication message + */ + +static void publ_to_item(struct distr_item *i, struct publication *p) +{ + i->type = htonl(p->type); + i->lower = htonl(p->lower); + i->upper = htonl(p->upper); + i->ref = htonl(p->ref); + i->key = htonl(p->key); + dbg("publ_to_item: %u, %u, %u\n", p->type, p->lower, p->upper); +} + +/** + * named_prepare_buf - allocate & initialize a publication message + */ + +static struct sk_buff *named_prepare_buf(u32 type, u32 size, u32 dest) +{ + struct sk_buff *buf = buf_acquire(LONG_H_SIZE + size); + struct tipc_msg *msg; + + if (buf != NULL) { + msg = buf_msg(buf); + msg_init(msg, NAME_DISTRIBUTOR, type, TIPC_OK, + LONG_H_SIZE, dest); + msg_set_size(msg, LONG_H_SIZE + size); + } + return buf; +} + +/** + * named_publish - tell other nodes about a new publication by this node + */ + +void named_publish(struct publication *publ) +{ + struct sk_buff *buf; + struct distr_item *item; + + list_add(&publ->local_list, &publ_root); + publ_cnt++; + + buf = named_prepare_buf(PUBLICATION, ITEM_SIZE, 0); + if (!buf) { + warn("Memory squeeze; failed to distribute publication\n"); + return; + } + + item = (struct distr_item *)msg_data(buf_msg(buf)); + publ_to_item(item, publ); + dbg("named_withdraw: broadcasting publish msg\n"); + cluster_broadcast(buf); +} + +/** + * named_withdraw - tell other nodes about a withdrawn publication by this node + */ + +void named_withdraw(struct publication *publ) +{ + struct sk_buff *buf; + struct distr_item *item; + + list_del(&publ->local_list); + publ_cnt--; + + buf = named_prepare_buf(WITHDRAWAL, ITEM_SIZE, 0); + if (!buf) { + warn("Memory squeeze; failed to distribute withdrawal\n"); + return; + } + + item = (struct distr_item *)msg_data(buf_msg(buf)); + publ_to_item(item, publ); + dbg("named_withdraw: broadcasting withdraw msg\n"); + cluster_broadcast(buf); +} + +/** + * named_node_up - tell specified node about all publications by this node + */ + +void named_node_up(unsigned long node) +{ + struct publication *publ; + struct distr_item *item = 0; + struct sk_buff *buf = 0; + u32 left = 0; + u32 rest; + u32 max_item_buf; + + assert(in_own_cluster(node)); + read_lock_bh(&nametbl_lock); + max_item_buf = TIPC_MAX_USER_MSG_SIZE / ITEM_SIZE; + max_item_buf *= ITEM_SIZE; + rest = publ_cnt * ITEM_SIZE; + + list_for_each_entry(publ, &publ_root, local_list) { + if (!buf) { + left = (rest <= max_item_buf) ? rest : max_item_buf; + rest -= left; + buf = named_prepare_buf(PUBLICATION, left, node); + if (buf == NULL) { + warn("Memory Squeeze; could not send publication\n"); + goto exit; + } + item = (struct distr_item *)msg_data(buf_msg(buf)); + } + publ_to_item(item, publ); + item++; + left -= ITEM_SIZE; + if (!left) { + msg_set_link_selector(buf_msg(buf), node); + dbg("named_node_up: sending publish msg to " + "<%u.%u.%u>\n", tipc_zone(node), + tipc_cluster(node), tipc_node(node)); + link_send(buf, node, node); + buf = 0; + } + } +exit: + read_unlock_bh(&nametbl_lock); +} + +/** + * node_is_down - remove publication associated with a failed node + * + * Invoked for each publication issued by a newly failed node. + * Removes publication structure from name table & deletes it. + * In rare cases the link may have come back up again when this + * function is called, and we have two items representing the same + * publication. Nudge this item's key to distinguish it from the other. + * (Note: Publication's node subscription is already unsubscribed.) + */ + +static void node_is_down(struct publication *publ) +{ + struct publication *p; + write_lock_bh(&nametbl_lock); + dbg("node_is_down: withdrawing %u, %u, %u\n", + publ->type, publ->lower, publ->upper); + publ->key += 1222345; + p = nametbl_remove_publ(publ->type, publ->lower, + publ->node, publ->ref, publ->key); + assert(p == publ); + write_unlock_bh(&nametbl_lock); + if (publ) + kfree(publ); +} + +/** + * named_recv - process name table update message sent by another node + */ + +void named_recv(struct sk_buff *buf) +{ + struct publication *publ; + struct tipc_msg *msg = buf_msg(buf); + struct distr_item *item = (struct distr_item *)msg_data(msg); + u32 count = msg_data_sz(msg) / ITEM_SIZE; + + write_lock_bh(&nametbl_lock); + while (count--) { + if (msg_type(msg) == PUBLICATION) { + dbg("named_recv: got publication for %u, %u, %u\n", + ntohl(item->type), ntohl(item->lower), + ntohl(item->upper)); + publ = nametbl_insert_publ(ntohl(item->type), + ntohl(item->lower), + ntohl(item->upper), + TIPC_CLUSTER_SCOPE, + msg_orignode(msg), + ntohl(item->ref), + ntohl(item->key)); + if (publ) { + nodesub_subscribe(&publ->subscr, + msg_orignode(msg), + publ, + (net_ev_handler)node_is_down); + } + } else if (msg_type(msg) == WITHDRAWAL) { + dbg("named_recv: got withdrawl for %u, %u, %u\n", + ntohl(item->type), ntohl(item->lower), + ntohl(item->upper)); + publ = nametbl_remove_publ(ntohl(item->type), + ntohl(item->lower), + msg_orignode(msg), + ntohl(item->ref), + ntohl(item->key)); + + if (publ) { + nodesub_unsubscribe(&publ->subscr); + kfree(publ); + } + } else { + warn("named_recv: unknown msg\n"); + } + item++; + } + write_unlock_bh(&nametbl_lock); + buf_discard(buf); +} + +/** + * named_reinit - re-initialize local publication list + * + * This routine is called whenever TIPC networking is (re)enabled. + * All existing publications by this node that have "cluster" or "zone" scope + * are updated to reflect the node's current network address. + * (If the node's address is unchanged, the update loop terminates immediately.) + */ + +void named_reinit(void) +{ + struct publication *publ; + + write_lock_bh(&nametbl_lock); + list_for_each_entry(publ, &publ_root, local_list) { + if (publ->node == tipc_own_addr) + break; + publ->node = tipc_own_addr; + } + write_unlock_bh(&nametbl_lock); +} diff --git a/net/tipc/name_distr.h b/net/tipc/name_distr.h new file mode 100644 index 00000000000..a04bdeac84e --- /dev/null +++ b/net/tipc/name_distr.h @@ -0,0 +1,48 @@ +/* + * net/tipc/name_distr.h: Include file for TIPC name distribution code + * + * Copyright (c) 2000-2006, Ericsson AB + * Copyright (c) 2005, Wind River Systems + * All rights reserved. + * + * Redistribution and use in source and binary forms, with or without + * modification, are permitted provided that the following conditions are met: + * + * 1. Redistributions of source code must retain the above copyright + * notice, this list of conditions and the following disclaimer. + * 2. Redistributions in binary form must reproduce the above copyright + * notice, this list of conditions and the following disclaimer in the + * documentation and/or other materials provided with the distribution. + * 3. Neither the names of the copyright holders nor the names of its + * contributors may be used to endorse or promote products derived from + * this software without specific prior written permission. + * + * Alternatively, this software may be distributed under the terms of the + * GNU General Public License ("GPL") version 2 as published by the Free + * Software Foundation. + * + * THIS SOFTWARE IS PROVIDED BY THE COPYRIGHT HOLDERS AND CONTRIBUTORS "AS IS" + * AND ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT LIMITED TO, THE + * IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR A PARTICULAR PURPOSE + * ARE DISCLAIMED. IN NO EVENT SHALL THE COPYRIGHT OWNER OR CONTRIBUTORS BE + * LIABLE FOR ANY DIRECT, INDIRECT, INCIDENTAL, SPECIAL, EXEMPLARY, OR + * CONSEQUENTIAL DAMAGES (INCLUDING, BUT NOT LIMITED TO, PROCUREMENT OF + * SUBSTITUTE GOODS OR SERVICES; LOSS OF USE, DATA, OR PROFITS; OR BUSINESS + * INTERRUPTION) HOWEVER CAUSED AND ON ANY THEORY OF LIABILITY, WHETHER IN + * CONTRACT, STRICT LIABILITY, OR TORT (INCLUDING NEGLIGENCE OR OTHERWISE) + * ARISING IN ANY WAY OUT OF THE USE OF THIS SOFTWARE, EVEN IF ADVISED OF THE + * POSSIBILITY OF SUCH DAMAGE. + */ + +#ifndef _TIPC_NAME_DISTR_H +#define _TIPC_NAME_DISTR_H + +#include "name_table.h" + +void named_publish(struct publication *publ); +void named_withdraw(struct publication *publ); +void named_node_up(unsigned long node); +void named_recv(struct sk_buff *buf); +void named_reinit(void); + +#endif diff --git a/net/tipc/name_table.c b/net/tipc/name_table.c new file mode 100644 index 00000000000..972c83eb83b --- /dev/null +++ b/net/tipc/name_table.c @@ -0,0 +1,1079 @@ +/* + * net/tipc/name_table.c: TIPC name table code + * + * Copyright (c) 2000-2006, Ericsson AB + * Copyright (c) 2004-2005, Wind River Systems + * All rights reserved. + * + * Redistribution and use in source and binary forms, with or without + * modification, are permitted provided that the following conditions are met: + * + * 1. Redistributions of source code must retain the above copyright + * notice, this list of conditions and the following disclaimer. + * 2. Redistributions in binary form must reproduce the above copyright + * notice, this list of conditions and the following disclaimer in the + * documentation and/or other materials provided with the distribution. + * 3. Neither the names of the copyright holders nor the names of its + * contributors may be used to endorse or promote products derived from + * this software without specific prior written permission. + * + * Alternatively, this software may be distributed under the terms of the + * GNU General Public License ("GPL") version 2 as published by the Free + * Software Foundation. + * + * THIS SOFTWARE IS PROVIDED BY THE COPYRIGHT HOLDERS AND CONTRIBUTORS "AS IS" + * AND ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT LIMITED TO, THE + * IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR A PARTICULAR PURPOSE + * ARE DISCLAIMED. IN NO EVENT SHALL THE COPYRIGHT OWNER OR CONTRIBUTORS BE + * LIABLE FOR ANY DIRECT, INDIRECT, INCIDENTAL, SPECIAL, EXEMPLARY, OR + * CONSEQUENTIAL DAMAGES (INCLUDING, BUT NOT LIMITED TO, PROCUREMENT OF + * SUBSTITUTE GOODS OR SERVICES; LOSS OF USE, DATA, OR PROFITS; OR BUSINESS + * INTERRUPTION) HOWEVER CAUSED AND ON ANY THEORY OF LIABILITY, WHETHER IN + * CONTRACT, STRICT LIABILITY, OR TORT (INCLUDING NEGLIGENCE OR OTHERWISE) + * ARISING IN ANY WAY OUT OF THE USE OF THIS SOFTWARE, EVEN IF ADVISED OF THE + * POSSIBILITY OF SUCH DAMAGE. + */ + +#include "core.h" +#include "config.h" +#include "dbg.h" +#include "name_table.h" +#include "name_distr.h" +#include "addr.h" +#include "node_subscr.h" +#include "subscr.h" +#include "port.h" +#include "cluster.h" +#include "bcast.h" + +int tipc_nametbl_size = 1024; /* must be a power of 2 */ + +/** + * struct sub_seq - container for all published instances of a name sequence + * @lower: name sequence lower bound + * @upper: name sequence upper bound + * @node_list: circular list of matching publications with >= node scope + * @cluster_list: circular list of matching publications with >= cluster scope + * @zone_list: circular list of matching publications with >= zone scope + */ + +struct sub_seq { + u32 lower; + u32 upper; + struct publication *node_list; + struct publication *cluster_list; + struct publication *zone_list; +}; + +/** + * struct name_seq - container for all published instances of a name type + * @type: 32 bit 'type' value for name sequence + * @sseq: pointer to dynamically-sized array of sub-sequences of this 'type'; + * sub-sequences are sorted in ascending order + * @alloc: number of sub-sequences currently in array + * @first_free: upper bound of highest sub-sequence + 1 + * @ns_list: links to adjacent name sequences in hash chain + * @subscriptions: list of subscriptions for this 'type' + * @lock: spinlock controlling access to name sequence structure + */ + +struct name_seq { + u32 type; + struct sub_seq *sseqs; + u32 alloc; + u32 first_free; + struct hlist_node ns_list; + struct list_head subscriptions; + spinlock_t lock; +}; + +/** + * struct name_table - table containing all existing port name publications + * @types: pointer to fixed-sized array of name sequence lists, + * accessed via hashing on 'type'; name sequence lists are *not* sorted + * @local_publ_count: number of publications issued by this node + */ + +struct name_table { + struct hlist_head *types; + u32 local_publ_count; +}; + +struct name_table table = { NULL } ; +static atomic_t rsv_publ_ok = ATOMIC_INIT(0); +rwlock_t nametbl_lock = RW_LOCK_UNLOCKED; + + +static inline int hash(int x) +{ + return(x & (tipc_nametbl_size - 1)); +} + +/** + * publ_create - create a publication structure + */ + +static struct publication *publ_create(u32 type, u32 lower, u32 upper, + u32 scope, u32 node, u32 port_ref, + u32 key) +{ + struct publication *publ = + (struct publication *)kmalloc(sizeof(*publ), GFP_ATOMIC); + if (publ == NULL) { + warn("Memory squeeze; failed to create publication\n"); + return 0; + } + + memset(publ, 0, sizeof(*publ)); + publ->type = type; + publ->lower = lower; + publ->upper = upper; + publ->scope = scope; + publ->node = node; + publ->ref = port_ref; + publ->key = key; + INIT_LIST_HEAD(&publ->local_list); + INIT_LIST_HEAD(&publ->pport_list); + INIT_LIST_HEAD(&publ->subscr.nodesub_list); + return publ; +} + +/** + * subseq_alloc - allocate a specified number of sub-sequence structures + */ + +struct sub_seq *subseq_alloc(u32 cnt) +{ + u32 sz = cnt * sizeof(struct sub_seq); + struct sub_seq *sseq = (struct sub_seq *)kmalloc(sz, GFP_ATOMIC); + + if (sseq) + memset(sseq, 0, sz); + return sseq; +} + +/** + * nameseq_create - create a name sequence structure for the specified 'type' + * + * Allocates a single sub-sequence structure and sets it to all 0's. + */ + +struct name_seq *nameseq_create(u32 type, struct hlist_head *seq_head) +{ + struct name_seq *nseq = + (struct name_seq *)kmalloc(sizeof(*nseq), GFP_ATOMIC); + struct sub_seq *sseq = subseq_alloc(1); + + if (!nseq || !sseq) { + warn("Memory squeeze; failed to create name sequence\n"); + kfree(nseq); + kfree(sseq); + return 0; + } + + memset(nseq, 0, sizeof(*nseq)); + nseq->lock = SPIN_LOCK_UNLOCKED; + nseq->type = type; + nseq->sseqs = sseq; + dbg("nameseq_create() nseq = %x type %u, ssseqs %x, ff: %u\n", + nseq, type, nseq->sseqs, nseq->first_free); + nseq->alloc = 1; + INIT_HLIST_NODE(&nseq->ns_list); + INIT_LIST_HEAD(&nseq->subscriptions); + hlist_add_head(&nseq->ns_list, seq_head); + return nseq; +} + +/** + * nameseq_find_subseq - find sub-sequence (if any) matching a name instance + * + * Very time-critical, so binary searches through sub-sequence array. + */ + +static inline struct sub_seq *nameseq_find_subseq(struct name_seq *nseq, + u32 instance) +{ + struct sub_seq *sseqs = nseq->sseqs; + int low = 0; + int high = nseq->first_free - 1; + int mid; + + while (low <= high) { + mid = (low + high) / 2; + if (instance < sseqs[mid].lower) + high = mid - 1; + else if (instance > sseqs[mid].upper) + low = mid + 1; + else + return &sseqs[mid]; + } + return 0; +} + +/** + * nameseq_locate_subseq - determine position of name instance in sub-sequence + * + * Returns index in sub-sequence array of the entry that contains the specified + * instance value; if no entry contains that value, returns the position + * where a new entry for it would be inserted in the array. + * + * Note: Similar to binary search code for locating a sub-sequence. + */ + +static u32 nameseq_locate_subseq(struct name_seq *nseq, u32 instance) +{ + struct sub_seq *sseqs = nseq->sseqs; + int low = 0; + int high = nseq->first_free - 1; + int mid; + + while (low <= high) { + mid = (low + high) / 2; + if (instance < sseqs[mid].lower) + high = mid - 1; + else if (instance > sseqs[mid].upper) + low = mid + 1; + else + return mid; + } + return low; +} + +/** + * nameseq_insert_publ - + */ + +struct publication *nameseq_insert_publ(struct name_seq *nseq, + u32 type, u32 lower, u32 upper, + u32 scope, u32 node, u32 port, u32 key) +{ + struct subscription *s; + struct subscription *st; + struct publication *publ; + struct sub_seq *sseq; + int created_subseq = 0; + + assert(nseq->first_free <= nseq->alloc); + sseq = nameseq_find_subseq(nseq, lower); + dbg("nameseq_ins: for seq %x,<%u,%u>, found sseq %x\n", + nseq, type, lower, sseq); + if (sseq) { + + /* Lower end overlaps existing entry => need an exact match */ + + if ((sseq->lower != lower) || (sseq->upper != upper)) { + warn("Overlapping publ <%u,%u,%u>\n", type, lower, upper); + return 0; + } + } else { + u32 inspos; + struct sub_seq *freesseq; + + /* Find where lower end should be inserted */ + + inspos = nameseq_locate_subseq(nseq, lower); + + /* Fail if upper end overlaps into an existing entry */ + + if ((inspos < nseq->first_free) && + (upper >= nseq->sseqs[inspos].lower)) { + warn("Overlapping publ <%u,%u,%u>\n", type, lower, upper); + return 0; + } + + /* Ensure there is space for new sub-sequence */ + + if (nseq->first_free == nseq->alloc) { + struct sub_seq *sseqs = nseq->sseqs; + nseq->sseqs = subseq_alloc(nseq->alloc * 2); + if (nseq->sseqs != NULL) { + memcpy(nseq->sseqs, sseqs, + nseq->alloc * sizeof (struct sub_seq)); + kfree(sseqs); + dbg("Allocated %u sseqs\n", nseq->alloc); + nseq->alloc *= 2; + } else { + warn("Memory squeeze; failed to create sub-sequence\n"); + return 0; + } + } + dbg("Have %u sseqs for type %u\n", nseq->alloc, type); + + /* Insert new sub-sequence */ + + dbg("ins in pos %u, ff = %u\n", inspos, nseq->first_free); + sseq = &nseq->sseqs[inspos]; + freesseq = &nseq->sseqs[nseq->first_free]; + memmove(sseq + 1, sseq, (freesseq - sseq) * sizeof (*sseq)); + memset(sseq, 0, sizeof (*sseq)); + nseq->first_free++; + sseq->lower = lower; + sseq->upper = upper; + created_subseq = 1; + } + dbg("inserting (%u %u %u) from %x:%u into sseq %x(%u,%u) of seq %x\n", + type, lower, upper, node, port, sseq, + sseq->lower, sseq->upper, nseq); + + /* Insert a publication: */ + + publ = publ_create(type, lower, upper, scope, node, port, key); + if (!publ) + return 0; + dbg("inserting publ %x, node=%x publ->node=%x, subscr->node=%x\n", + publ, node, publ->node, publ->subscr.node); + + if (!sseq->zone_list) + sseq->zone_list = publ->zone_list_next = publ; + else { + publ->zone_list_next = sseq->zone_list->zone_list_next; + sseq->zone_list->zone_list_next = publ; + } + + if (in_own_cluster(node)) { + if (!sseq->cluster_list) + sseq->cluster_list = publ->cluster_list_next = publ; + else { + publ->cluster_list_next = + sseq->cluster_list->cluster_list_next; + sseq->cluster_list->cluster_list_next = publ; + } + } + + if (node == tipc_own_addr) { + if (!sseq->node_list) + sseq->node_list = publ->node_list_next = publ; + else { + publ->node_list_next = sseq->node_list->node_list_next; + sseq->node_list->node_list_next = publ; + } + } + + /* + * Any subscriptions waiting for notification? + */ + list_for_each_entry_safe(s, st, &nseq->subscriptions, nameseq_list) { + dbg("calling report_overlap()\n"); + subscr_report_overlap(s, + publ->lower, + publ->upper, + TIPC_PUBLISHED, + publ->ref, + publ->node, + created_subseq); + } + return publ; +} + +/** + * nameseq_remove_publ - + */ + +struct publication *nameseq_remove_publ(struct name_seq *nseq, u32 inst, + u32 node, u32 ref, u32 key) +{ + struct publication *publ; + struct publication *prev; + struct sub_seq *sseq = nameseq_find_subseq(nseq, inst); + struct sub_seq *free; + struct subscription *s, *st; + int removed_subseq = 0; + + assert(nseq); + + if (!sseq) { + int i; + + warn("Withdraw unknown <%u,%u>?\n", nseq->type, inst); + assert(nseq->sseqs); + dbg("Dumping subseqs %x for %x, alloc = %u,ff=%u\n", + nseq->sseqs, nseq, nseq->alloc, + nseq->first_free); + for (i = 0; i < nseq->first_free; i++) { + dbg("Subseq %u(%x): lower = %u,upper = %u\n", + i, &nseq->sseqs[i], nseq->sseqs[i].lower, + nseq->sseqs[i].upper); + } + return 0; + } + dbg("nameseq_remove: seq: %x, sseq %x, <%u,%u> key %u\n", + nseq, sseq, nseq->type, inst, key); + + prev = sseq->zone_list; + publ = sseq->zone_list->zone_list_next; + while ((publ->key != key) || (publ->ref != ref) || + (publ->node && (publ->node != node))) { + prev = publ; + publ = publ->zone_list_next; + assert(prev != sseq->zone_list); + } + if (publ != sseq->zone_list) + prev->zone_list_next = publ->zone_list_next; + else if (publ->zone_list_next != publ) { + prev->zone_list_next = publ->zone_list_next; + sseq->zone_list = publ->zone_list_next; + } else { + sseq->zone_list = 0; + } + + if (in_own_cluster(node)) { + prev = sseq->cluster_list; + publ = sseq->cluster_list->cluster_list_next; + while ((publ->key != key) || (publ->ref != ref) || + (publ->node && (publ->node != node))) { + prev = publ; + publ = publ->cluster_list_next; + assert(prev != sseq->cluster_list); + } + if (publ != sseq->cluster_list) + prev->cluster_list_next = publ->cluster_list_next; + else if (publ->cluster_list_next != publ) { + prev->cluster_list_next = publ->cluster_list_next; + sseq->cluster_list = publ->cluster_list_next; + } else { + sseq->cluster_list = 0; + } + } + + if (node == tipc_own_addr) { + prev = sseq->node_list; + publ = sseq->node_list->node_list_next; + while ((publ->key != key) || (publ->ref != ref) || + (publ->node && (publ->node != node))) { + prev = publ; + publ = publ->node_list_next; + assert(prev != sseq->node_list); + } + if (publ != sseq->node_list) + prev->node_list_next = publ->node_list_next; + else if (publ->node_list_next != publ) { + prev->node_list_next = publ->node_list_next; + sseq->node_list = publ->node_list_next; + } else { + sseq->node_list = 0; + } + } + assert(!publ->node || (publ->node == node)); + assert(publ->ref == ref); + assert(publ->key == key); + + /* + * Contract subseq list if no more publications: + */ + if (!sseq->node_list && !sseq->cluster_list && !sseq->zone_list) { + free = &nseq->sseqs[nseq->first_free--]; + memmove(sseq, sseq + 1, (free - (sseq + 1)) * sizeof (*sseq)); + removed_subseq = 1; + } + + /* + * Any subscriptions waiting ? + */ + list_for_each_entry_safe(s, st, &nseq->subscriptions, nameseq_list) { + subscr_report_overlap(s, + publ->lower, + publ->upper, + TIPC_WITHDRAWN, + publ->ref, + publ->node, + removed_subseq); + } + return publ; +} + +/** + * nameseq_subscribe: attach a subscription, and issue + * the prescribed number of events if there is any sub- + * sequence overlapping with the requested sequence + */ + +void nameseq_subscribe(struct name_seq *nseq, struct subscription *s) +{ + struct sub_seq *sseq = nseq->sseqs; + + list_add(&s->nameseq_list, &nseq->subscriptions); + + if (!sseq) + return; + + while (sseq != &nseq->sseqs[nseq->first_free]) { + struct publication *zl = sseq->zone_list; + if (zl && subscr_overlap(s,sseq->lower,sseq->upper)) { + struct publication *crs = zl; + int must_report = 1; + + do { + subscr_report_overlap(s, + sseq->lower, + sseq->upper, + TIPC_PUBLISHED, + crs->ref, + crs->node, + must_report); + must_report = 0; + crs = crs->zone_list_next; + } while (crs != zl); + } + sseq++; + } +} + +static struct name_seq *nametbl_find_seq(u32 type) +{ + struct hlist_head *seq_head; + struct hlist_node *seq_node; + struct name_seq *ns; + + dbg("find_seq %u,(%u,0x%x) table = %p, hash[type] = %u\n", + type, ntohl(type), type, table.types, hash(type)); + + seq_head = &table.types[hash(type)]; + hlist_for_each_entry(ns, seq_node, seq_head, ns_list) { + if (ns->type == type) { + dbg("found %x\n", ns); + return ns; + } + } + + return 0; +}; + +struct publication *nametbl_insert_publ(u32 type, u32 lower, u32 upper, + u32 scope, u32 node, u32 port, u32 key) +{ + struct name_seq *seq = nametbl_find_seq(type); + + dbg("ins_publ: <%u,%x,%x> found %x\n", type, lower, upper, seq); + if (lower > upper) { + warn("Failed to publish illegal <%u,%u,%u>\n", + type, lower, upper); + return 0; + } + + dbg("Publishing <%u,%u,%u> from %x\n", type, lower, upper, node); + if (!seq) { + seq = nameseq_create(type, &table.types[hash(type)]); + dbg("nametbl_insert_publ: created %x\n", seq); + } + if (!seq) + return 0; + + assert(seq->type == type); + return nameseq_insert_publ(seq, type, lower, upper, + scope, node, port, key); +} + +struct publication *nametbl_remove_publ(u32 type, u32 lower, + u32 node, u32 ref, u32 key) +{ + struct publication *publ; + struct name_seq *seq = nametbl_find_seq(type); + + if (!seq) + return 0; + + dbg("Withdrawing <%u,%u> from %x\n", type, lower, node); + publ = nameseq_remove_publ(seq, lower, node, ref, key); + + if (!seq->first_free && list_empty(&seq->subscriptions)) { + hlist_del_init(&seq->ns_list); + kfree(seq->sseqs); + kfree(seq); + } + return publ; +} + +/* + * nametbl_translate(): Translate tipc_name -> tipc_portid. + * Very time-critical. + * + * Note: on entry 'destnode' is the search domain used during translation; + * on exit it passes back the node address of the matching port (if any) + */ + +u32 nametbl_translate(u32 type, u32 instance, u32 *destnode) +{ + struct sub_seq *sseq; + struct publication *publ = 0; + struct name_seq *seq; + u32 ref; + + if (!in_scope(*destnode, tipc_own_addr)) + return 0; + + read_lock_bh(&nametbl_lock); + seq = nametbl_find_seq(type); + if (unlikely(!seq)) + goto not_found; + sseq = nameseq_find_subseq(seq, instance); + if (unlikely(!sseq)) + goto not_found; + spin_lock_bh(&seq->lock); + + /* Closest-First Algorithm: */ + if (likely(!*destnode)) { + publ = sseq->node_list; + if (publ) { + sseq->node_list = publ->node_list_next; +found: + ref = publ->ref; + *destnode = publ->node; + spin_unlock_bh(&seq->lock); + read_unlock_bh(&nametbl_lock); + return ref; + } + publ = sseq->cluster_list; + if (publ) { + sseq->cluster_list = publ->cluster_list_next; + goto found; + } + publ = sseq->zone_list; + if (publ) { + sseq->zone_list = publ->zone_list_next; + goto found; + } + } + + /* Round-Robin Algorithm: */ + else if (*destnode == tipc_own_addr) { + publ = sseq->node_list; + if (publ) { + sseq->node_list = publ->node_list_next; + goto found; + } + } else if (in_own_cluster(*destnode)) { + publ = sseq->cluster_list; + if (publ) { + sseq->cluster_list = publ->cluster_list_next; + goto found; + } + } else { + publ = sseq->zone_list; + if (publ) { + sseq->zone_list = publ->zone_list_next; + goto found; + } + } + spin_unlock_bh(&seq->lock); +not_found: + *destnode = 0; + read_unlock_bh(&nametbl_lock); + return 0; +} + +/** + * nametbl_mc_translate - find multicast destinations + * + * Creates list of all local ports that overlap the given multicast address; + * also determines if any off-node ports overlap. + * + * Note: Publications with a scope narrower than 'limit' are ignored. + * (i.e. local node-scope publications mustn't receive messages arriving + * from another node, even if the multcast link brought it here) + * + * Returns non-zero if any off-node ports overlap + */ + +int nametbl_mc_translate(u32 type, u32 lower, u32 upper, u32 limit, + struct port_list *dports) +{ + struct name_seq *seq; + struct sub_seq *sseq; + struct sub_seq *sseq_stop; + int res = 0; + + read_lock_bh(&nametbl_lock); + seq = nametbl_find_seq(type); + if (!seq) + goto exit; + + spin_lock_bh(&seq->lock); + + sseq = seq->sseqs + nameseq_locate_subseq(seq, lower); + sseq_stop = seq->sseqs + seq->first_free; + for (; sseq != sseq_stop; sseq++) { + struct publication *publ; + + if (sseq->lower > upper) + break; + publ = sseq->cluster_list; + if (publ && (publ->scope <= limit)) + do { + if (publ->node == tipc_own_addr) + port_list_add(dports, publ->ref); + else + res = 1; + publ = publ->cluster_list_next; + } while (publ != sseq->cluster_list); + } + + spin_unlock_bh(&seq->lock); +exit: + read_unlock_bh(&nametbl_lock); + return res; +} + +/** + * nametbl_publish_rsv - publish port name using a reserved name type + */ + +int nametbl_publish_rsv(u32 ref, unsigned int scope, + struct tipc_name_seq const *seq) +{ + int res; + + atomic_inc(&rsv_publ_ok); + res = tipc_publish(ref, scope, seq); + atomic_dec(&rsv_publ_ok); + return res; +} + +/** + * nametbl_publish - add name publication to network name tables + */ + +struct publication *nametbl_publish(u32 type, u32 lower, u32 upper, + u32 scope, u32 port_ref, u32 key) +{ + struct publication *publ; + + if (table.local_publ_count >= tipc_max_publications) { + warn("Failed publish: max %u local publication\n", + tipc_max_publications); + return 0; + } + if ((type < TIPC_RESERVED_TYPES) && !atomic_read(&rsv_publ_ok)) { + warn("Failed to publish reserved name <%u,%u,%u>\n", + type, lower, upper); + return 0; + } + + write_lock_bh(&nametbl_lock); + table.local_publ_count++; + publ = nametbl_insert_publ(type, lower, upper, scope, + tipc_own_addr, port_ref, key); + if (publ && (scope != TIPC_NODE_SCOPE)) { + named_publish(publ); + } + write_unlock_bh(&nametbl_lock); + return publ; +} + +/** + * nametbl_withdraw - withdraw name publication from network name tables + */ + +int nametbl_withdraw(u32 type, u32 lower, u32 ref, u32 key) +{ + struct publication *publ; + + dbg("nametbl_withdraw:<%d,%d,%d>\n", type, lower, key); + write_lock_bh(&nametbl_lock); + publ = nametbl_remove_publ(type, lower, tipc_own_addr, ref, key); + if (publ) { + table.local_publ_count--; + if (publ->scope != TIPC_NODE_SCOPE) + named_withdraw(publ); + write_unlock_bh(&nametbl_lock); + list_del_init(&publ->pport_list); + kfree(publ); + return 1; + } + write_unlock_bh(&nametbl_lock); + return 0; +} + +/** + * nametbl_subscribe - add a subscription object to the name table + */ + +void +nametbl_subscribe(struct subscription *s) +{ + u32 type = s->seq.type; + struct name_seq *seq; + + write_lock_bh(&nametbl_lock); + seq = nametbl_find_seq(type); + if (!seq) { + seq = nameseq_create(type, &table.types[hash(type)]); + } + if (seq){ + spin_lock_bh(&seq->lock); + dbg("nametbl_subscribe:found %x for <%u,%u,%u>\n", + seq, type, s->seq.lower, s->seq.upper); + assert(seq->type == type); + nameseq_subscribe(seq, s); + spin_unlock_bh(&seq->lock); + } + write_unlock_bh(&nametbl_lock); +} + +/** + * nametbl_unsubscribe - remove a subscription object from name table + */ + +void +nametbl_unsubscribe(struct subscription *s) +{ + struct name_seq *seq; + + write_lock_bh(&nametbl_lock); + seq = nametbl_find_seq(s->seq.type); + if (seq != NULL){ + spin_lock_bh(&seq->lock); + list_del_init(&s->nameseq_list); + spin_unlock_bh(&seq->lock); + if ((seq->first_free == 0) && list_empty(&seq->subscriptions)) { + hlist_del_init(&seq->ns_list); + kfree(seq->sseqs); + kfree(seq); + } + } + write_unlock_bh(&nametbl_lock); +} + + +/** + * subseq_list: print specified sub-sequence contents into the given buffer + */ + +static void subseq_list(struct sub_seq *sseq, struct print_buf *buf, u32 depth, + u32 index) +{ + char portIdStr[27]; + char *scopeStr; + struct publication *publ = sseq->zone_list; + + tipc_printf(buf, "%-10u %-10u ", sseq->lower, sseq->upper); + + if (depth == 2 || !publ) { + tipc_printf(buf, "\n"); + return; + } + + do { + sprintf (portIdStr, "<%u.%u.%u:%u>", + tipc_zone(publ->node), tipc_cluster(publ->node), + tipc_node(publ->node), publ->ref); + tipc_printf(buf, "%-26s ", portIdStr); + if (depth > 3) { + if (publ->node != tipc_own_addr) + scopeStr = ""; + else if (publ->scope == TIPC_NODE_SCOPE) + scopeStr = "node"; + else if (publ->scope == TIPC_CLUSTER_SCOPE) + scopeStr = "cluster"; + else + scopeStr = "zone"; + tipc_printf(buf, "%-10u %s", publ->key, scopeStr); + } + + publ = publ->zone_list_next; + if (publ == sseq->zone_list) + break; + + tipc_printf(buf, "\n%33s", " "); + } while (1); + + tipc_printf(buf, "\n"); +} + +/** + * nameseq_list: print specified name sequence contents into the given buffer + */ + +static void nameseq_list(struct name_seq *seq, struct print_buf *buf, u32 depth, + u32 type, u32 lowbound, u32 upbound, u32 index) +{ + struct sub_seq *sseq; + char typearea[11]; + + sprintf(typearea, "%-10u", seq->type); + + if (depth == 1) { + tipc_printf(buf, "%s\n", typearea); + return; + } + + for (sseq = seq->sseqs; sseq != &seq->sseqs[seq->first_free]; sseq++) { + if ((lowbound <= sseq->upper) && (upbound >= sseq->lower)) { + tipc_printf(buf, "%s ", typearea); + subseq_list(sseq, buf, depth, index); + sprintf(typearea, "%10s", " "); + } + } +} + +/** + * nametbl_header - print name table header into the given buffer + */ + +static void nametbl_header(struct print_buf *buf, u32 depth) +{ + tipc_printf(buf, "Type "); + + if (depth > 1) + tipc_printf(buf, "Lower Upper "); + if (depth > 2) + tipc_printf(buf, "Port Identity "); + if (depth > 3) + tipc_printf(buf, "Publication"); + + tipc_printf(buf, "\n-----------"); + + if (depth > 1) + tipc_printf(buf, "--------------------- "); + if (depth > 2) + tipc_printf(buf, "-------------------------- "); + if (depth > 3) + tipc_printf(buf, "------------------"); + + tipc_printf(buf, "\n"); +} + +/** + * nametbl_list - print specified name table contents into the given buffer + */ + +static void nametbl_list(struct print_buf *buf, u32 depth_info, + u32 type, u32 lowbound, u32 upbound) +{ + struct hlist_head *seq_head; + struct hlist_node *seq_node; + struct name_seq *seq; + int all_types; + u32 depth; + u32 i; + + all_types = (depth_info & TIPC_NTQ_ALLTYPES); + depth = (depth_info & ~TIPC_NTQ_ALLTYPES); + + if (depth == 0) + return; + + if (all_types) { + /* display all entries in name table to specified depth */ + nametbl_header(buf, depth); + lowbound = 0; + upbound = ~0; + for (i = 0; i < tipc_nametbl_size; i++) { + seq_head = &table.types[i]; + hlist_for_each_entry(seq, seq_node, seq_head, ns_list) { + nameseq_list(seq, buf, depth, seq->type, + lowbound, upbound, i); + } + } + } else { + /* display only the sequence that matches the specified type */ + if (upbound < lowbound) { + tipc_printf(buf, "invalid name sequence specified\n"); + return; + } + nametbl_header(buf, depth); + i = hash(type); + seq_head = &table.types[i]; + hlist_for_each_entry(seq, seq_node, seq_head, ns_list) { + if (seq->type == type) { + nameseq_list(seq, buf, depth, type, + lowbound, upbound, i); + break; + } + } + } +} + +void nametbl_print(struct print_buf *buf, const char *str) +{ + tipc_printf(buf, str); + read_lock_bh(&nametbl_lock); + nametbl_list(buf, 0, 0, 0, 0); + read_unlock_bh(&nametbl_lock); +} + +#define MAX_NAME_TBL_QUERY 32768 + +struct sk_buff *nametbl_get(const void *req_tlv_area, int req_tlv_space) +{ + struct sk_buff *buf; + struct tipc_name_table_query *argv; + struct tlv_desc *rep_tlv; + struct print_buf b; + int str_len; + + if (!TLV_CHECK(req_tlv_area, req_tlv_space, TIPC_TLV_NAME_TBL_QUERY)) + return cfg_reply_error_string(TIPC_CFG_TLV_ERROR); + + buf = cfg_reply_alloc(TLV_SPACE(MAX_NAME_TBL_QUERY)); + if (!buf) + return NULL; + + rep_tlv = (struct tlv_desc *)buf->data; + printbuf_init(&b, TLV_DATA(rep_tlv), MAX_NAME_TBL_QUERY); + argv = (struct tipc_name_table_query *)TLV_DATA(req_tlv_area); + read_lock_bh(&nametbl_lock); + nametbl_list(&b, ntohl(argv->depth), ntohl(argv->type), + ntohl(argv->lowbound), ntohl(argv->upbound)); + read_unlock_bh(&nametbl_lock); + str_len = printbuf_validate(&b); + + skb_put(buf, TLV_SPACE(str_len)); + TLV_SET(rep_tlv, TIPC_TLV_ULTRA_STRING, NULL, str_len); + + return buf; +} + +void nametbl_dump(void) +{ + nametbl_list(CONS, 0, 0, 0, 0); +} + +int nametbl_init(void) +{ + int array_size = sizeof(struct hlist_head) * tipc_nametbl_size; + + table.types = (struct hlist_head *)kmalloc(array_size, GFP_ATOMIC); + if (!table.types) + return -ENOMEM; + + write_lock_bh(&nametbl_lock); + memset(table.types, 0, array_size); + table.local_publ_count = 0; + write_unlock_bh(&nametbl_lock); + return 0; +} + +void nametbl_stop(void) +{ + struct hlist_head *seq_head; + struct hlist_node *seq_node; + struct hlist_node *tmp; + struct name_seq *seq; + u32 i; + + if (!table.types) + return; + + write_lock_bh(&nametbl_lock); + for (i = 0; i < tipc_nametbl_size; i++) { + seq_head = &table.types[i]; + hlist_for_each_entry_safe(seq, seq_node, tmp, seq_head, ns_list) { + struct sub_seq *sseq = seq->sseqs; + + for (; sseq != &seq->sseqs[seq->first_free]; sseq++) { + struct publication *publ = sseq->zone_list; + assert(publ); + do { + struct publication *next = + publ->zone_list_next; + kfree(publ); + publ = next; + } + while (publ != sseq->zone_list); + } + } + } + kfree(table.types); + table.types = NULL; + write_unlock_bh(&nametbl_lock); +} diff --git a/net/tipc/name_table.h b/net/tipc/name_table.h new file mode 100644 index 00000000000..f82693384f6 --- /dev/null +++ b/net/tipc/name_table.h @@ -0,0 +1,108 @@ +/* + * net/tipc/name_table.h: Include file for TIPC name table code + * + * Copyright (c) 2000-2006, Ericsson AB + * Copyright (c) 2004-2005, Wind River Systems + * All rights reserved. + * + * Redistribution and use in source and binary forms, with or without + * modification, are permitted provided that the following conditions are met: + * + * 1. Redistributions of source code must retain the above copyright + * notice, this list of conditions and the following disclaimer. + * 2. Redistributions in binary form must reproduce the above copyright + * notice, this list of conditions and the following disclaimer in the + * documentation and/or other materials provided with the distribution. + * 3. Neither the names of the copyright holders nor the names of its + * contributors may be used to endorse or promote products derived from + * this software without specific prior written permission. + * + * Alternatively, this software may be distributed under the terms of the + * GNU General Public License ("GPL") version 2 as published by the Free + * Software Foundation. + * + * THIS SOFTWARE IS PROVIDED BY THE COPYRIGHT HOLDERS AND CONTRIBUTORS "AS IS" + * AND ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT LIMITED TO, THE + * IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR A PARTICULAR PURPOSE + * ARE DISCLAIMED. IN NO EVENT SHALL THE COPYRIGHT OWNER OR CONTRIBUTORS BE + * LIABLE FOR ANY DIRECT, INDIRECT, INCIDENTAL, SPECIAL, EXEMPLARY, OR + * CONSEQUENTIAL DAMAGES (INCLUDING, BUT NOT LIMITED TO, PROCUREMENT OF + * SUBSTITUTE GOODS OR SERVICES; LOSS OF USE, DATA, OR PROFITS; OR BUSINESS + * INTERRUPTION) HOWEVER CAUSED AND ON ANY THEORY OF LIABILITY, WHETHER IN + * CONTRACT, STRICT LIABILITY, OR TORT (INCLUDING NEGLIGENCE OR OTHERWISE) + * ARISING IN ANY WAY OUT OF THE USE OF THIS SOFTWARE, EVEN IF ADVISED OF THE + * POSSIBILITY OF SUCH DAMAGE. + */ + +#ifndef _TIPC_NAME_TABLE_H +#define _TIPC_NAME_TABLE_H + +#include "node_subscr.h" + +struct subscription; +struct port_list; + +/* + * TIPC name types reserved for internal TIPC use (both current and planned) + */ + +#define TIPC_ZM_SRV 3 /* zone master service name type */ + + +/** + * struct publication - info about a published (name or) name sequence + * @type: name sequence type + * @lower: name sequence lower bound + * @upper: name sequence upper bound + * @scope: scope of publication + * @node: network address of publishing port's node + * @ref: publishing port + * @key: publication key + * @subscr: subscription to "node down" event (for off-node publications only) + * @local_list: adjacent entries in list of publications made by this node + * @pport_list: adjacent entries in list of publications made by this port + * @node_list: next matching name seq publication with >= node scope + * @cluster_list: next matching name seq publication with >= cluster scope + * @zone_list: next matching name seq publication with >= zone scope + * + * Note that the node list, cluster list, and zone list are circular lists. + */ + +struct publication { + u32 type; + u32 lower; + u32 upper; + u32 scope; + u32 node; + u32 ref; + u32 key; + struct node_subscr subscr; + struct list_head local_list; + struct list_head pport_list; + struct publication *node_list_next; + struct publication *cluster_list_next; + struct publication *zone_list_next; +}; + + +extern rwlock_t nametbl_lock; + +struct sk_buff *nametbl_get(const void *req_tlv_area, int req_tlv_space); +u32 nametbl_translate(u32 type, u32 instance, u32 *node); +int nametbl_mc_translate(u32 type, u32 lower, u32 upper, u32 limit, + struct port_list *dports); +int nametbl_publish_rsv(u32 ref, unsigned int scope, + struct tipc_name_seq const *seq); +struct publication *nametbl_publish(u32 type, u32 lower, u32 upper, + u32 scope, u32 port_ref, u32 key); +int nametbl_withdraw(u32 type, u32 lower, u32 ref, u32 key); +struct publication *nametbl_insert_publ(u32 type, u32 lower, u32 upper, + u32 scope, u32 node, u32 ref, u32 key); +struct publication *nametbl_remove_publ(u32 type, u32 lower, + u32 node, u32 ref, u32 key); +void nametbl_subscribe(struct subscription *s); +void nametbl_unsubscribe(struct subscription *s); +int nametbl_init(void); +void nametbl_stop(void); + +#endif diff --git a/net/tipc/net.c b/net/tipc/net.c new file mode 100644 index 00000000000..6826b493c1d --- /dev/null +++ b/net/tipc/net.c @@ -0,0 +1,311 @@ +/* + * net/tipc/net.c: TIPC network routing code + * + * Copyright (c) 1995-2006, Ericsson AB + * Copyright (c) 2005, Wind River Systems + * All rights reserved. + * + * Redistribution and use in source and binary forms, with or without + * modification, are permitted provided that the following conditions are met: + * + * 1. Redistributions of source code must retain the above copyright + * notice, this list of conditions and the following disclaimer. + * 2. Redistributions in binary form must reproduce the above copyright + * notice, this list of conditions and the following disclaimer in the + * documentation and/or other materials provided with the distribution. + * 3. Neither the names of the copyright holders nor the names of its + * contributors may be used to endorse or promote products derived from + * this software without specific prior written permission. + * + * Alternatively, this software may be distributed under the terms of the + * GNU General Public License ("GPL") version 2 as published by the Free + * Software Foundation. + * + * THIS SOFTWARE IS PROVIDED BY THE COPYRIGHT HOLDERS AND CONTRIBUTORS "AS IS" + * AND ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT LIMITED TO, THE + * IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR A PARTICULAR PURPOSE + * ARE DISCLAIMED. IN NO EVENT SHALL THE COPYRIGHT OWNER OR CONTRIBUTORS BE + * LIABLE FOR ANY DIRECT, INDIRECT, INCIDENTAL, SPECIAL, EXEMPLARY, OR + * CONSEQUENTIAL DAMAGES (INCLUDING, BUT NOT LIMITED TO, PROCUREMENT OF + * SUBSTITUTE GOODS OR SERVICES; LOSS OF USE, DATA, OR PROFITS; OR BUSINESS + * INTERRUPTION) HOWEVER CAUSED AND ON ANY THEORY OF LIABILITY, WHETHER IN + * CONTRACT, STRICT LIABILITY, OR TORT (INCLUDING NEGLIGENCE OR OTHERWISE) + * ARISING IN ANY WAY OUT OF THE USE OF THIS SOFTWARE, EVEN IF ADVISED OF THE + * POSSIBILITY OF SUCH DAMAGE. + */ + +#include "core.h" +#include "bearer.h" +#include "net.h" +#include "zone.h" +#include "addr.h" +#include "name_table.h" +#include "name_distr.h" +#include "subscr.h" +#include "link.h" +#include "msg.h" +#include "port.h" +#include "bcast.h" +#include "discover.h" +#include "config.h" + +/* + * The TIPC locking policy is designed to ensure a very fine locking + * granularity, permitting complete parallel access to individual + * port and node/link instances. The code consists of three major + * locking domains, each protected with their own disjunct set of locks. + * + * 1: The routing hierarchy. + * Comprises the structures 'zone', 'cluster', 'node', 'link' + * and 'bearer'. The whole hierarchy is protected by a big + * read/write lock, net_lock, to enssure that nothing is added + * or removed while code is accessing any of these structures. + * This layer must not be called from the two others while they + * hold any of their own locks. + * Neither must it itself do any upcalls to the other two before + * it has released net_lock and other protective locks. + * + * Within the net_lock domain there are two sub-domains;'node' and + * 'bearer', where local write operations are permitted, + * provided that those are protected by individual spin_locks + * per instance. Code holding net_lock(read) and a node spin_lock + * is permitted to poke around in both the node itself and its + * subordinate links. I.e, it can update link counters and queues, + * change link state, send protocol messages, and alter the + * "active_links" array in the node; but it can _not_ remove a link + * or a node from the overall structure. + * Correspondingly, individual bearers may change status within a + * net_lock(read), protected by an individual spin_lock ber bearer + * instance, but it needs net_lock(write) to remove/add any bearers. + * + * + * 2: The transport level of the protocol. + * This consists of the structures port, (and its user level + * representations, such as user_port and tipc_sock), reference and + * tipc_user (port.c, reg.c, socket.c). + * + * This layer has four different locks: + * - The tipc_port spin_lock. This is protecting each port instance + * from parallel data access and removal. Since we can not place + * this lock in the port itself, it has been placed in the + * corresponding reference table entry, which has the same life + * cycle as the module. This entry is difficult to access from + * outside the TIPC core, however, so a pointer to the lock has + * been added in the port instance, -to be used for unlocking + * only. + * - A read/write lock to protect the reference table itself (teg.c). + * (Nobody is using read-only access to this, so it can just as + * well be changed to a spin_lock) + * - A spin lock to protect the registry of kernel/driver users (reg.c) + * - A global spin_lock (port_lock), which only task is to ensure + * consistency where more than one port is involved in an operation, + * i.e., whe a port is part of a linked list of ports. + * There are two such lists; 'port_list', which is used for management, + * and 'wait_list', which is used to queue ports during congestion. + * + * 3: The name table (name_table.c, name_distr.c, subscription.c) + * - There is one big read/write-lock (nametbl_lock) protecting the + * overall name table structure. Nothing must be added/removed to + * this structure without holding write access to it. + * - There is one local spin_lock per sub_sequence, which can be seen + * as a sub-domain to the nametbl_lock domain. It is used only + * for translation operations, and is needed because a translation + * steps the root of the 'publication' linked list between each lookup. + * This is always used within the scope of a nametbl_lock(read). + * - A local spin_lock protecting the queue of subscriber events. +*/ + +rwlock_t net_lock = RW_LOCK_UNLOCKED; +struct network net = { 0 }; + +struct node *net_select_remote_node(u32 addr, u32 ref) +{ + return zone_select_remote_node(net.zones[tipc_zone(addr)], addr, ref); +} + +u32 net_select_router(u32 addr, u32 ref) +{ + return zone_select_router(net.zones[tipc_zone(addr)], addr, ref); +} + + +u32 net_next_node(u32 a) +{ + if (net.zones[tipc_zone(a)]) + return zone_next_node(a); + return 0; +} + +void net_remove_as_router(u32 router) +{ + u32 z_num; + + for (z_num = 1; z_num <= tipc_max_zones; z_num++) { + if (!net.zones[z_num]) + continue; + zone_remove_as_router(net.zones[z_num], router); + } +} + +void net_send_external_routes(u32 dest) +{ + u32 z_num; + + for (z_num = 1; z_num <= tipc_max_zones; z_num++) { + if (net.zones[z_num]) + zone_send_external_routes(net.zones[z_num], dest); + } +} + +int net_init(void) +{ + u32 sz = sizeof(struct _zone *) * (tipc_max_zones + 1); + + memset(&net, 0, sizeof(net)); + net.zones = (struct _zone **)kmalloc(sz, GFP_ATOMIC); + if (!net.zones) { + return -ENOMEM; + } + memset(net.zones, 0, sz); + return TIPC_OK; +} + +void net_stop(void) +{ + u32 z_num; + + if (!net.zones) + return; + + for (z_num = 1; z_num <= tipc_max_zones; z_num++) { + zone_delete(net.zones[z_num]); + } + kfree(net.zones); + net.zones = 0; +} + +static void net_route_named_msg(struct sk_buff *buf) +{ + struct tipc_msg *msg = buf_msg(buf); + u32 dnode; + u32 dport; + + if (!msg_named(msg)) { + msg_dbg(msg, "net->drop_nam:"); + buf_discard(buf); + return; + } + + dnode = addr_domain(msg_lookup_scope(msg)); + dport = nametbl_translate(msg_nametype(msg), msg_nameinst(msg), &dnode); + dbg("net->lookup<%u,%u>-><%u,%x>\n", + msg_nametype(msg), msg_nameinst(msg), dport, dnode); + if (dport) { + msg_set_destnode(msg, dnode); + msg_set_destport(msg, dport); + net_route_msg(buf); + return; + } + msg_dbg(msg, "net->rej:NO NAME: "); + tipc_reject_msg(buf, TIPC_ERR_NO_NAME); +} + +void net_route_msg(struct sk_buff *buf) +{ + struct tipc_msg *msg; + u32 dnode; + + if (!buf) + return; + msg = buf_msg(buf); + + msg_incr_reroute_cnt(msg); + if (msg_reroute_cnt(msg) > 6) { + if (msg_errcode(msg)) { + msg_dbg(msg, "NET>DISC>:"); + buf_discard(buf); + } else { + msg_dbg(msg, "NET>REJ>:"); + tipc_reject_msg(buf, msg_destport(msg) ? + TIPC_ERR_NO_PORT : TIPC_ERR_NO_NAME); + } + return; + } + + msg_dbg(msg, "net->rout: "); + + /* Handle message for this node */ + dnode = msg_short(msg) ? tipc_own_addr : msg_destnode(msg); + if (in_scope(dnode, tipc_own_addr)) { + if (msg_isdata(msg)) { + if (msg_mcast(msg)) + port_recv_mcast(buf, NULL); + else if (msg_destport(msg)) + port_recv_msg(buf); + else + net_route_named_msg(buf); + return; + } + switch (msg_user(msg)) { + case ROUTE_DISTRIBUTOR: + cluster_recv_routing_table(buf); + break; + case NAME_DISTRIBUTOR: + named_recv(buf); + break; + case CONN_MANAGER: + port_recv_proto_msg(buf); + break; + default: + msg_dbg(msg,"DROP/NET/<REC<"); + buf_discard(buf); + } + return; + } + + /* Handle message for another node */ + msg_dbg(msg, "NET>SEND>: "); + link_send(buf, dnode, msg_link_selector(msg)); +} + +int tipc_start_net(void) +{ + char addr_string[16]; + int res; + + if (tipc_mode != TIPC_NODE_MODE) + return -ENOPROTOOPT; + + tipc_mode = TIPC_NET_MODE; + named_reinit(); + port_reinit(); + + if ((res = bearer_init()) || + (res = net_init()) || + (res = cluster_init()) || + (res = bclink_init())) { + return res; + } + subscr_stop(); + cfg_stop(); + k_signal((Handler)subscr_start, 0); + k_signal((Handler)cfg_init, 0); + info("Started in network mode\n"); + info("Own node address %s, network identity %u\n", + addr_string_fill(addr_string, tipc_own_addr), tipc_net_id); + return TIPC_OK; +} + +void tipc_stop_net(void) +{ + if (tipc_mode != TIPC_NET_MODE) + return; + write_lock_bh(&net_lock); + bearer_stop(); + tipc_mode = TIPC_NODE_MODE; + bclink_stop(); + net_stop(); + write_unlock_bh(&net_lock); + info("Left network mode \n"); +} + diff --git a/net/tipc/net.h b/net/tipc/net.h new file mode 100644 index 00000000000..948c6d42102 --- /dev/null +++ b/net/tipc/net.h @@ -0,0 +1,66 @@ +/* + * net/tipc/net.h: Include file for TIPC network routing code + * + * Copyright (c) 1995-2006, Ericsson AB + * Copyright (c) 2005, Wind River Systems + * All rights reserved. + * + * Redistribution and use in source and binary forms, with or without + * modification, are permitted provided that the following conditions are met: + * + * 1. Redistributions of source code must retain the above copyright + * notice, this list of conditions and the following disclaimer. + * 2. Redistributions in binary form must reproduce the above copyright + * notice, this list of conditions and the following disclaimer in the + * documentation and/or other materials provided with the distribution. + * 3. Neither the names of the copyright holders nor the names of its + * contributors may be used to endorse or promote products derived from + * this software without specific prior written permission. + * + * Alternatively, this software may be distributed under the terms of the + * GNU General Public License ("GPL") version 2 as published by the Free + * Software Foundation. + * + * THIS SOFTWARE IS PROVIDED BY THE COPYRIGHT HOLDERS AND CONTRIBUTORS "AS IS" + * AND ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT LIMITED TO, THE + * IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR A PARTICULAR PURPOSE + * ARE DISCLAIMED. IN NO EVENT SHALL THE COPYRIGHT OWNER OR CONTRIBUTORS BE + * LIABLE FOR ANY DIRECT, INDIRECT, INCIDENTAL, SPECIAL, EXEMPLARY, OR + * CONSEQUENTIAL DAMAGES (INCLUDING, BUT NOT LIMITED TO, PROCUREMENT OF + * SUBSTITUTE GOODS OR SERVICES; LOSS OF USE, DATA, OR PROFITS; OR BUSINESS + * INTERRUPTION) HOWEVER CAUSED AND ON ANY THEORY OF LIABILITY, WHETHER IN + * CONTRACT, STRICT LIABILITY, OR TORT (INCLUDING NEGLIGENCE OR OTHERWISE) + * ARISING IN ANY WAY OUT OF THE USE OF THIS SOFTWARE, EVEN IF ADVISED OF THE + * POSSIBILITY OF SUCH DAMAGE. + */ + +#ifndef _TIPC_NET_H +#define _TIPC_NET_H + +struct _zone; + +/** + * struct network - TIPC network structure + * @zones: array of pointers to all zones within network + */ + +struct network { + struct _zone **zones; +}; + + +extern struct network net; +extern rwlock_t net_lock; + +int net_init(void); +void net_stop(void); +void net_remove_as_router(u32 router); +void net_send_external_routes(u32 dest); +void net_route_msg(struct sk_buff *buf); +struct node *net_select_remote_node(u32 addr, u32 ref); +u32 net_select_router(u32 addr, u32 ref); + +int tipc_start_net(void); +void tipc_stop_net(void); + +#endif diff --git a/net/tipc/netlink.c b/net/tipc/netlink.c new file mode 100644 index 00000000000..19b3f402253 --- /dev/null +++ b/net/tipc/netlink.c @@ -0,0 +1,112 @@ +/* + * net/tipc/netlink.c: TIPC configuration handling + * + * Copyright (c) 2005-2006, Ericsson AB + * Copyright (c) 2005, Wind River Systems + * All rights reserved. + * + * Redistribution and use in source and binary forms, with or without + * modification, are permitted provided that the following conditions are met: + * + * 1. Redistributions of source code must retain the above copyright + * notice, this list of conditions and the following disclaimer. + * 2. Redistributions in binary form must reproduce the above copyright + * notice, this list of conditions and the following disclaimer in the + * documentation and/or other materials provided with the distribution. + * 3. Neither the names of the copyright holders nor the names of its + * contributors may be used to endorse or promote products derived from + * this software without specific prior written permission. + * + * Alternatively, this software may be distributed under the terms of the + * GNU General Public License ("GPL") version 2 as published by the Free + * Software Foundation. + * + * THIS SOFTWARE IS PROVIDED BY THE COPYRIGHT HOLDERS AND CONTRIBUTORS "AS IS" + * AND ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT LIMITED TO, THE + * IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR A PARTICULAR PURPOSE + * ARE DISCLAIMED. IN NO EVENT SHALL THE COPYRIGHT OWNER OR CONTRIBUTORS BE + * LIABLE FOR ANY DIRECT, INDIRECT, INCIDENTAL, SPECIAL, EXEMPLARY, OR + * CONSEQUENTIAL DAMAGES (INCLUDING, BUT NOT LIMITED TO, PROCUREMENT OF + * SUBSTITUTE GOODS OR SERVICES; LOSS OF USE, DATA, OR PROFITS; OR BUSINESS + * INTERRUPTION) HOWEVER CAUSED AND ON ANY THEORY OF LIABILITY, WHETHER IN + * CONTRACT, STRICT LIABILITY, OR TORT (INCLUDING NEGLIGENCE OR OTHERWISE) + * ARISING IN ANY WAY OUT OF THE USE OF THIS SOFTWARE, EVEN IF ADVISED OF THE + * POSSIBILITY OF SUCH DAMAGE. + */ + +#include "core.h" +#include "config.h" +#include <net/genetlink.h> + +static int handle_cmd(struct sk_buff *skb, struct genl_info *info) +{ + struct sk_buff *rep_buf; + struct nlmsghdr *rep_nlh; + struct nlmsghdr *req_nlh = info->nlhdr; + struct tipc_genlmsghdr *req_userhdr = info->userhdr; + int hdr_space = NLMSG_SPACE(GENL_HDRLEN + TIPC_GENL_HDRLEN); + + if ((req_userhdr->cmd & 0xC000) && (!capable(CAP_NET_ADMIN))) + rep_buf = cfg_reply_error_string(TIPC_CFG_NOT_NET_ADMIN); + else + rep_buf = cfg_do_cmd(req_userhdr->dest, + req_userhdr->cmd, + NLMSG_DATA(req_nlh) + GENL_HDRLEN + TIPC_GENL_HDRLEN, + NLMSG_PAYLOAD(req_nlh, GENL_HDRLEN + TIPC_GENL_HDRLEN), + hdr_space); + + if (rep_buf) { + skb_push(rep_buf, hdr_space); + rep_nlh = (struct nlmsghdr *)rep_buf->data; + memcpy(rep_nlh, req_nlh, hdr_space); + rep_nlh->nlmsg_len = rep_buf->len; + genlmsg_unicast(rep_buf, req_nlh->nlmsg_pid); + } + + return 0; +} + +static struct genl_family family = { + .id = GENL_ID_GENERATE, + .name = TIPC_GENL_NAME, + .version = TIPC_GENL_VERSION, + .hdrsize = TIPC_GENL_HDRLEN, + .maxattr = 0, +}; + +static struct genl_ops ops = { + .cmd = TIPC_GENL_CMD, + .doit = handle_cmd, +}; + +static int family_registered = 0; + +int netlink_start(void) +{ + + + if (genl_register_family(&family)) + goto err; + + family_registered = 1; + + if (genl_register_ops(&family, &ops)) + goto err_unregister; + + return 0; + + err_unregister: + genl_unregister_family(&family); + family_registered = 0; + err: + err("Failed to register netlink interface\n"); + return -EFAULT; +} + +void netlink_stop(void) +{ + if (family_registered) { + genl_unregister_family(&family); + family_registered = 0; + } +} diff --git a/net/tipc/node.c b/net/tipc/node.c new file mode 100644 index 00000000000..05688d01138 --- /dev/null +++ b/net/tipc/node.c @@ -0,0 +1,679 @@ +/* + * net/tipc/node.c: TIPC node management routines + * + * Copyright (c) 2000-2006, Ericsson AB + * Copyright (c) 2005, Wind River Systems + * All rights reserved. + * + * Redistribution and use in source and binary forms, with or without + * modification, are permitted provided that the following conditions are met: + * + * 1. Redistributions of source code must retain the above copyright + * notice, this list of conditions and the following disclaimer. + * 2. Redistributions in binary form must reproduce the above copyright + * notice, this list of conditions and the following disclaimer in the + * documentation and/or other materials provided with the distribution. + * 3. Neither the names of the copyright holders nor the names of its + * contributors may be used to endorse or promote products derived from + * this software without specific prior written permission. + * + * Alternatively, this software may be distributed under the terms of the + * GNU General Public License ("GPL") version 2 as published by the Free + * Software Foundation. + * + * THIS SOFTWARE IS PROVIDED BY THE COPYRIGHT HOLDERS AND CONTRIBUTORS "AS IS" + * AND ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT LIMITED TO, THE + * IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR A PARTICULAR PURPOSE + * ARE DISCLAIMED. IN NO EVENT SHALL THE COPYRIGHT OWNER OR CONTRIBUTORS BE + * LIABLE FOR ANY DIRECT, INDIRECT, INCIDENTAL, SPECIAL, EXEMPLARY, OR + * CONSEQUENTIAL DAMAGES (INCLUDING, BUT NOT LIMITED TO, PROCUREMENT OF + * SUBSTITUTE GOODS OR SERVICES; LOSS OF USE, DATA, OR PROFITS; OR BUSINESS + * INTERRUPTION) HOWEVER CAUSED AND ON ANY THEORY OF LIABILITY, WHETHER IN + * CONTRACT, STRICT LIABILITY, OR TORT (INCLUDING NEGLIGENCE OR OTHERWISE) + * ARISING IN ANY WAY OUT OF THE USE OF THIS SOFTWARE, EVEN IF ADVISED OF THE + * POSSIBILITY OF SUCH DAMAGE. + */ + +#include "core.h" +#include "config.h" +#include "node.h" +#include "cluster.h" +#include "net.h" +#include "addr.h" +#include "node_subscr.h" +#include "link.h" +#include "port.h" +#include "bearer.h" +#include "name_distr.h" +#include "net.h" + +void node_print(struct print_buf *buf, struct node *n_ptr, char *str); +static void node_lost_contact(struct node *n_ptr); +static void node_established_contact(struct node *n_ptr); + +struct node *nodes = NULL; /* sorted list of nodes within cluster */ + +u32 tipc_own_tag = 0; + +struct node *node_create(u32 addr) +{ + struct cluster *c_ptr; + struct node *n_ptr; + struct node **curr_node; + + n_ptr = kmalloc(sizeof(*n_ptr),GFP_ATOMIC); + if (n_ptr != NULL) { + memset(n_ptr, 0, sizeof(*n_ptr)); + n_ptr->addr = addr; + n_ptr->lock = SPIN_LOCK_UNLOCKED; + INIT_LIST_HEAD(&n_ptr->nsub); + + c_ptr = cluster_find(addr); + if (c_ptr == NULL) + c_ptr = cluster_create(addr); + if (c_ptr != NULL) { + n_ptr->owner = c_ptr; + cluster_attach_node(c_ptr, n_ptr); + n_ptr->last_router = -1; + + /* Insert node into ordered list */ + for (curr_node = &nodes; *curr_node; + curr_node = &(*curr_node)->next) { + if (addr < (*curr_node)->addr) { + n_ptr->next = *curr_node; + break; + } + } + (*curr_node) = n_ptr; + } else { + kfree(n_ptr); + n_ptr = NULL; + } + } + return n_ptr; +} + +void node_delete(struct node *n_ptr) +{ + if (!n_ptr) + return; + +#if 0 + /* Not needed because links are already deleted via bearer_stop() */ + + u32 l_num; + + for (l_num = 0; l_num < MAX_BEARERS; l_num++) { + link_delete(n_ptr->links[l_num]); + } +#endif + + dbg("node %x deleted\n", n_ptr->addr); + kfree(n_ptr); +} + + +/** + * node_link_up - handle addition of link + * + * Link becomes active (alone or shared) or standby, depending on its priority. + */ + +void node_link_up(struct node *n_ptr, struct link *l_ptr) +{ + struct link **active = &n_ptr->active_links[0]; + + info("Established link <%s> on network plane %c\n", + l_ptr->name, l_ptr->b_ptr->net_plane); + + if (!active[0]) { + dbg(" link %x into %x/%x\n", l_ptr, &active[0], &active[1]); + active[0] = active[1] = l_ptr; + node_established_contact(n_ptr); + return; + } + if (l_ptr->priority < active[0]->priority) { + info("Link is standby\n"); + return; + } + link_send_duplicate(active[0], l_ptr); + if (l_ptr->priority == active[0]->priority) { + active[0] = l_ptr; + return; + } + info("Link <%s> on network plane %c becomes standby\n", + active[0]->name, active[0]->b_ptr->net_plane); + active[0] = active[1] = l_ptr; +} + +/** + * node_select_active_links - select active link + */ + +static void node_select_active_links(struct node *n_ptr) +{ + struct link **active = &n_ptr->active_links[0]; + u32 i; + u32 highest_prio = 0; + + active[0] = active[1] = 0; + + for (i = 0; i < MAX_BEARERS; i++) { + struct link *l_ptr = n_ptr->links[i]; + + if (!l_ptr || !link_is_up(l_ptr) || + (l_ptr->priority < highest_prio)) + continue; + + if (l_ptr->priority > highest_prio) { + highest_prio = l_ptr->priority; + active[0] = active[1] = l_ptr; + } else { + active[1] = l_ptr; + } + } +} + +/** + * node_link_down - handle loss of link + */ + +void node_link_down(struct node *n_ptr, struct link *l_ptr) +{ + struct link **active; + + if (!link_is_active(l_ptr)) { + info("Lost standby link <%s> on network plane %c\n", + l_ptr->name, l_ptr->b_ptr->net_plane); + return; + } + info("Lost link <%s> on network plane %c\n", + l_ptr->name, l_ptr->b_ptr->net_plane); + + active = &n_ptr->active_links[0]; + if (active[0] == l_ptr) + active[0] = active[1]; + if (active[1] == l_ptr) + active[1] = active[0]; + if (active[0] == l_ptr) + node_select_active_links(n_ptr); + if (node_is_up(n_ptr)) + link_changeover(l_ptr); + else + node_lost_contact(n_ptr); +} + +int node_has_active_links(struct node *n_ptr) +{ + return (n_ptr && + ((n_ptr->active_links[0]) || (n_ptr->active_links[1]))); +} + +int node_has_redundant_links(struct node *n_ptr) +{ + return (node_has_active_links(n_ptr) && + (n_ptr->active_links[0] != n_ptr->active_links[1])); +} + +int node_has_active_routes(struct node *n_ptr) +{ + return (n_ptr && (n_ptr->last_router >= 0)); +} + +int node_is_up(struct node *n_ptr) +{ + return (node_has_active_links(n_ptr) || node_has_active_routes(n_ptr)); +} + +struct node *node_attach_link(struct link *l_ptr) +{ + struct node *n_ptr = node_find(l_ptr->addr); + + if (!n_ptr) + n_ptr = node_create(l_ptr->addr); + if (n_ptr) { + u32 bearer_id = l_ptr->b_ptr->identity; + char addr_string[16]; + + assert(bearer_id < MAX_BEARERS); + if (n_ptr->link_cnt >= 2) { + char addr_string[16]; + + err("Attempt to create third link to %s\n", + addr_string_fill(addr_string, n_ptr->addr)); + return 0; + } + + if (!n_ptr->links[bearer_id]) { + n_ptr->links[bearer_id] = l_ptr; + net.zones[tipc_zone(l_ptr->addr)]->links++; + n_ptr->link_cnt++; + return n_ptr; + } + err("Attempt to establish second link on <%s> to <%s> \n", + l_ptr->b_ptr->publ.name, + addr_string_fill(addr_string, l_ptr->addr)); + } + return 0; +} + +void node_detach_link(struct node *n_ptr, struct link *l_ptr) +{ + n_ptr->links[l_ptr->b_ptr->identity] = 0; + net.zones[tipc_zone(l_ptr->addr)]->links--; + n_ptr->link_cnt--; +} + +/* + * Routing table management - five cases to handle: + * + * 1: A link towards a zone/cluster external node comes up. + * => Send a multicast message updating routing tables of all + * system nodes within own cluster that the new destination + * can be reached via this node. + * (node.establishedContact()=>cluster.multicastNewRoute()) + * + * 2: A link towards a slave node comes up. + * => Send a multicast message updating routing tables of all + * system nodes within own cluster that the new destination + * can be reached via this node. + * (node.establishedContact()=>cluster.multicastNewRoute()) + * => Send a message to the slave node about existence + * of all system nodes within cluster: + * (node.establishedContact()=>cluster.sendLocalRoutes()) + * + * 3: A new cluster local system node becomes available. + * => Send message(s) to this particular node containing + * information about all cluster external and slave + * nodes which can be reached via this node. + * (node.establishedContact()==>network.sendExternalRoutes()) + * (node.establishedContact()==>network.sendSlaveRoutes()) + * => Send messages to all directly connected slave nodes + * containing information about the existence of the new node + * (node.establishedContact()=>cluster.multicastNewRoute()) + * + * 4: The link towards a zone/cluster external node or slave + * node goes down. + * => Send a multcast message updating routing tables of all + * nodes within cluster that the new destination can not any + * longer be reached via this node. + * (node.lostAllLinks()=>cluster.bcastLostRoute()) + * + * 5: A cluster local system node becomes unavailable. + * => Remove all references to this node from the local + * routing tables. Note: This is a completely node + * local operation. + * (node.lostAllLinks()=>network.removeAsRouter()) + * => Send messages to all directly connected slave nodes + * containing information about loss of the node + * (node.establishedContact()=>cluster.multicastLostRoute()) + * + */ + +static void node_established_contact(struct node *n_ptr) +{ + struct cluster *c_ptr; + + dbg("node_established_contact:-> %x\n", n_ptr->addr); + if (!node_has_active_routes(n_ptr)) { + k_signal((Handler)named_node_up, n_ptr->addr); + } + + /* Syncronize broadcast acks */ + n_ptr->bclink.acked = bclink_get_last_sent(); + + if (is_slave(tipc_own_addr)) + return; + if (!in_own_cluster(n_ptr->addr)) { + /* Usage case 1 (see above) */ + c_ptr = cluster_find(tipc_own_addr); + if (!c_ptr) + c_ptr = cluster_create(tipc_own_addr); + if (c_ptr) + cluster_bcast_new_route(c_ptr, n_ptr->addr, 1, + tipc_max_nodes); + return; + } + + c_ptr = n_ptr->owner; + if (is_slave(n_ptr->addr)) { + /* Usage case 2 (see above) */ + cluster_bcast_new_route(c_ptr, n_ptr->addr, 1, tipc_max_nodes); + cluster_send_local_routes(c_ptr, n_ptr->addr); + return; + } + + if (n_ptr->bclink.supported) { + nmap_add(&cluster_bcast_nodes, n_ptr->addr); + if (n_ptr->addr < tipc_own_addr) + tipc_own_tag++; + } + + /* Case 3 (see above) */ + net_send_external_routes(n_ptr->addr); + cluster_send_slave_routes(c_ptr, n_ptr->addr); + cluster_bcast_new_route(c_ptr, n_ptr->addr, LOWEST_SLAVE, + highest_allowed_slave); +} + +static void node_lost_contact(struct node *n_ptr) +{ + struct cluster *c_ptr; + struct node_subscr *ns, *tns; + char addr_string[16]; + u32 i; + + /* Clean up broadcast reception remains */ + n_ptr->bclink.gap_after = n_ptr->bclink.gap_to = 0; + while (n_ptr->bclink.deferred_head) { + struct sk_buff* buf = n_ptr->bclink.deferred_head; + n_ptr->bclink.deferred_head = buf->next; + buf_discard(buf); + } + if (n_ptr->bclink.defragm) { + buf_discard(n_ptr->bclink.defragm); + n_ptr->bclink.defragm = NULL; + } + if (in_own_cluster(n_ptr->addr) && n_ptr->bclink.supported) { + bclink_acknowledge(n_ptr, mod(n_ptr->bclink.acked + 10000)); + } + + /* Update routing tables */ + if (is_slave(tipc_own_addr)) { + net_remove_as_router(n_ptr->addr); + } else { + if (!in_own_cluster(n_ptr->addr)) { + /* Case 4 (see above) */ + c_ptr = cluster_find(tipc_own_addr); + cluster_bcast_lost_route(c_ptr, n_ptr->addr, 1, + tipc_max_nodes); + } else { + /* Case 5 (see above) */ + c_ptr = cluster_find(n_ptr->addr); + if (is_slave(n_ptr->addr)) { + cluster_bcast_lost_route(c_ptr, n_ptr->addr, 1, + tipc_max_nodes); + } else { + if (n_ptr->bclink.supported) { + nmap_remove(&cluster_bcast_nodes, + n_ptr->addr); + if (n_ptr->addr < tipc_own_addr) + tipc_own_tag--; + } + net_remove_as_router(n_ptr->addr); + cluster_bcast_lost_route(c_ptr, n_ptr->addr, + LOWEST_SLAVE, + highest_allowed_slave); + } + } + } + if (node_has_active_routes(n_ptr)) + return; + + info("Lost contact with %s\n", + addr_string_fill(addr_string, n_ptr->addr)); + + /* Abort link changeover */ + for (i = 0; i < MAX_BEARERS; i++) { + struct link *l_ptr = n_ptr->links[i]; + if (!l_ptr) + continue; + l_ptr->reset_checkpoint = l_ptr->next_in_no; + l_ptr->exp_msg_count = 0; + link_reset_fragments(l_ptr); + } + + /* Notify subscribers */ + list_for_each_entry_safe(ns, tns, &n_ptr->nsub, nodesub_list) { + ns->node = 0; + list_del_init(&ns->nodesub_list); + k_signal((Handler)ns->handle_node_down, + (unsigned long)ns->usr_handle); + } +} + +/** + * node_select_next_hop - find the next-hop node for a message + * + * Called by when cluster local lookup has failed. + */ + +struct node *node_select_next_hop(u32 addr, u32 selector) +{ + struct node *n_ptr; + u32 router_addr; + + if (!addr_domain_valid(addr)) + return 0; + + /* Look for direct link to destination processsor */ + n_ptr = node_find(addr); + if (n_ptr && node_has_active_links(n_ptr)) + return n_ptr; + + /* Cluster local system nodes *must* have direct links */ + if (!is_slave(addr) && in_own_cluster(addr)) + return 0; + + /* Look for cluster local router with direct link to node */ + router_addr = node_select_router(n_ptr, selector); + if (router_addr) + return node_select(router_addr, selector); + + /* Slave nodes can only be accessed within own cluster via a + known router with direct link -- if no router was found,give up */ + if (is_slave(addr)) + return 0; + + /* Inter zone/cluster -- find any direct link to remote cluster */ + addr = tipc_addr(tipc_zone(addr), tipc_cluster(addr), 0); + n_ptr = net_select_remote_node(addr, selector); + if (n_ptr && node_has_active_links(n_ptr)) + return n_ptr; + + /* Last resort -- look for any router to anywhere in remote zone */ + router_addr = net_select_router(addr, selector); + if (router_addr) + return node_select(router_addr, selector); + + return 0; +} + +/** + * node_select_router - select router to reach specified node + * + * Uses a deterministic and fair algorithm for selecting router node. + */ + +u32 node_select_router(struct node *n_ptr, u32 ref) +{ + u32 ulim; + u32 mask; + u32 start; + u32 r; + + if (!n_ptr) + return 0; + + if (n_ptr->last_router < 0) + return 0; + ulim = ((n_ptr->last_router + 1) * 32) - 1; + + /* Start entry must be random */ + mask = tipc_max_nodes; + while (mask > ulim) + mask >>= 1; + start = ref & mask; + r = start; + + /* Lookup upwards with wrap-around */ + do { + if (((n_ptr->routers[r / 32]) >> (r % 32)) & 1) + break; + } while (++r <= ulim); + if (r > ulim) { + r = 1; + do { + if (((n_ptr->routers[r / 32]) >> (r % 32)) & 1) + break; + } while (++r < start); + assert(r != start); + } + assert(r && (r <= ulim)); + return tipc_addr(own_zone(), own_cluster(), r); +} + +void node_add_router(struct node *n_ptr, u32 router) +{ + u32 r_num = tipc_node(router); + + n_ptr->routers[r_num / 32] = + ((1 << (r_num % 32)) | n_ptr->routers[r_num / 32]); + n_ptr->last_router = tipc_max_nodes / 32; + while ((--n_ptr->last_router >= 0) && + !n_ptr->routers[n_ptr->last_router]); +} + +void node_remove_router(struct node *n_ptr, u32 router) +{ + u32 r_num = tipc_node(router); + + if (n_ptr->last_router < 0) + return; /* No routes */ + + n_ptr->routers[r_num / 32] = + ((~(1 << (r_num % 32))) & (n_ptr->routers[r_num / 32])); + n_ptr->last_router = tipc_max_nodes / 32; + while ((--n_ptr->last_router >= 0) && + !n_ptr->routers[n_ptr->last_router]); + + if (!node_is_up(n_ptr)) + node_lost_contact(n_ptr); +} + +#if 0 +void node_print(struct print_buf *buf, struct node *n_ptr, char *str) +{ + u32 i; + + tipc_printf(buf, "\n\n%s", str); + for (i = 0; i < MAX_BEARERS; i++) { + if (!n_ptr->links[i]) + continue; + tipc_printf(buf, "Links[%u]: %x, ", i, n_ptr->links[i]); + } + tipc_printf(buf, "Active links: [%x,%x]\n", + n_ptr->active_links[0], n_ptr->active_links[1]); +} +#endif + +u32 tipc_available_nodes(const u32 domain) +{ + struct node *n_ptr; + u32 cnt = 0; + + for (n_ptr = nodes; n_ptr; n_ptr = n_ptr->next) { + if (!in_scope(domain, n_ptr->addr)) + continue; + if (node_is_up(n_ptr)) + cnt++; + } + return cnt; +} + +struct sk_buff *node_get_nodes(const void *req_tlv_area, int req_tlv_space) +{ + u32 domain; + struct sk_buff *buf; + struct node *n_ptr; + struct tipc_node_info node_info; + + if (!TLV_CHECK(req_tlv_area, req_tlv_space, TIPC_TLV_NET_ADDR)) + return cfg_reply_error_string(TIPC_CFG_TLV_ERROR); + + domain = *(u32 *)TLV_DATA(req_tlv_area); + domain = ntohl(domain); + if (!addr_domain_valid(domain)) + return cfg_reply_error_string(TIPC_CFG_INVALID_VALUE + " (network address)"); + + if (!nodes) + return cfg_reply_none(); + + /* For now, get space for all other nodes + (will need to modify this when slave nodes are supported */ + + buf = cfg_reply_alloc(TLV_SPACE(sizeof(node_info)) * + (tipc_max_nodes - 1)); + if (!buf) + return NULL; + + /* Add TLVs for all nodes in scope */ + + for (n_ptr = nodes; n_ptr; n_ptr = n_ptr->next) { + if (!in_scope(domain, n_ptr->addr)) + continue; + node_info.addr = htonl(n_ptr->addr); + node_info.up = htonl(node_is_up(n_ptr)); + cfg_append_tlv(buf, TIPC_TLV_NODE_INFO, + &node_info, sizeof(node_info)); + } + + return buf; +} + +struct sk_buff *node_get_links(const void *req_tlv_area, int req_tlv_space) +{ + u32 domain; + struct sk_buff *buf; + struct node *n_ptr; + struct tipc_link_info link_info; + + if (!TLV_CHECK(req_tlv_area, req_tlv_space, TIPC_TLV_NET_ADDR)) + return cfg_reply_error_string(TIPC_CFG_TLV_ERROR); + + domain = *(u32 *)TLV_DATA(req_tlv_area); + domain = ntohl(domain); + if (!addr_domain_valid(domain)) + return cfg_reply_error_string(TIPC_CFG_INVALID_VALUE + " (network address)"); + + if (!nodes) + return cfg_reply_none(); + + /* For now, get space for 2 links to all other nodes + bcast link + (will need to modify this when slave nodes are supported */ + + buf = cfg_reply_alloc(TLV_SPACE(sizeof(link_info)) * + (2 * (tipc_max_nodes - 1) + 1)); + if (!buf) + return NULL; + + /* Add TLV for broadcast link */ + + link_info.dest = tipc_own_addr & 0xfffff00; + link_info.dest = htonl(link_info.dest); + link_info.up = htonl(1); + sprintf(link_info.str, bc_link_name); + cfg_append_tlv(buf, TIPC_TLV_LINK_INFO, &link_info, sizeof(link_info)); + + /* Add TLVs for any other links in scope */ + + for (n_ptr = nodes; n_ptr; n_ptr = n_ptr->next) { + u32 i; + + if (!in_scope(domain, n_ptr->addr)) + continue; + for (i = 0; i < MAX_BEARERS; i++) { + if (!n_ptr->links[i]) + continue; + link_info.dest = htonl(n_ptr->addr); + link_info.up = htonl(link_is_up(n_ptr->links[i])); + strcpy(link_info.str, n_ptr->links[i]->name); + cfg_append_tlv(buf, TIPC_TLV_LINK_INFO, + &link_info, sizeof(link_info)); + } + } + + return buf; +} diff --git a/net/tipc/node.h b/net/tipc/node.h new file mode 100644 index 00000000000..b39442badcc --- /dev/null +++ b/net/tipc/node.h @@ -0,0 +1,144 @@ +/* + * net/tipc/node.h: Include file for TIPC node management routines + * + * Copyright (c) 2000-2006, Ericsson AB + * Copyright (c) 2005, Wind River Systems + * All rights reserved. + * + * Redistribution and use in source and binary forms, with or without + * modification, are permitted provided that the following conditions are met: + * + * 1. Redistributions of source code must retain the above copyright + * notice, this list of conditions and the following disclaimer. + * 2. Redistributions in binary form must reproduce the above copyright + * notice, this list of conditions and the following disclaimer in the + * documentation and/or other materials provided with the distribution. + * 3. Neither the names of the copyright holders nor the names of its + * contributors may be used to endorse or promote products derived from + * this software without specific prior written permission. + * + * Alternatively, this software may be distributed under the terms of the + * GNU General Public License ("GPL") version 2 as published by the Free + * Software Foundation. + * + * THIS SOFTWARE IS PROVIDED BY THE COPYRIGHT HOLDERS AND CONTRIBUTORS "AS IS" + * AND ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT LIMITED TO, THE + * IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR A PARTICULAR PURPOSE + * ARE DISCLAIMED. IN NO EVENT SHALL THE COPYRIGHT OWNER OR CONTRIBUTORS BE + * LIABLE FOR ANY DIRECT, INDIRECT, INCIDENTAL, SPECIAL, EXEMPLARY, OR + * CONSEQUENTIAL DAMAGES (INCLUDING, BUT NOT LIMITED TO, PROCUREMENT OF + * SUBSTITUTE GOODS OR SERVICES; LOSS OF USE, DATA, OR PROFITS; OR BUSINESS + * INTERRUPTION) HOWEVER CAUSED AND ON ANY THEORY OF LIABILITY, WHETHER IN + * CONTRACT, STRICT LIABILITY, OR TORT (INCLUDING NEGLIGENCE OR OTHERWISE) + * ARISING IN ANY WAY OUT OF THE USE OF THIS SOFTWARE, EVEN IF ADVISED OF THE + * POSSIBILITY OF SUCH DAMAGE. + */ + +#ifndef _TIPC_NODE_H +#define _TIPC_NODE_H + +#include "node_subscr.h" +#include "addr.h" +#include "cluster.h" +#include "bearer.h" + +/** + * struct node - TIPC node structure + * @addr: network address of node + * @lock: spinlock governing access to structure + * @owner: pointer to cluster that node belongs to + * @next: pointer to next node in sorted list of cluster's nodes + * @nsub: list of "node down" subscriptions monitoring node + * @active_links: pointers to active links to node + * @links: pointers to all links to node + * @link_cnt: number of links to node + * @permit_changeover: non-zero if node has redundant links to this system + * @routers: bitmap (used for multicluster communication) + * @last_router: (used for multicluster communication) + * @bclink: broadcast-related info + * @supported: non-zero if node supports TIPC b'cast capability + * @acked: sequence # of last outbound b'cast message acknowledged by node + * @last_in: sequence # of last in-sequence b'cast message received from node + * @gap_after: sequence # of last message not requiring a NAK request + * @gap_to: sequence # of last message requiring a NAK request + * @nack_sync: counter that determines when NAK requests should be sent + * @deferred_head: oldest OOS b'cast message received from node + * @deferred_tail: newest OOS b'cast message received from node + * @defragm: list of partially reassembled b'cast message fragments from node + */ + +struct node { + u32 addr; + spinlock_t lock; + struct cluster *owner; + struct node *next; + struct list_head nsub; + struct link *active_links[2]; + struct link *links[MAX_BEARERS]; + int link_cnt; + int permit_changeover; + u32 routers[512/32]; + int last_router; + struct { + int supported; + u32 acked; + u32 last_in; + u32 gap_after; + u32 gap_to; + u32 nack_sync; + struct sk_buff *deferred_head; + struct sk_buff *deferred_tail; + struct sk_buff *defragm; + } bclink; +}; + +extern struct node *nodes; +extern u32 tipc_own_tag; + +struct node *node_create(u32 addr); +void node_delete(struct node *n_ptr); +struct node *node_attach_link(struct link *l_ptr); +void node_detach_link(struct node *n_ptr, struct link *l_ptr); +void node_link_down(struct node *n_ptr, struct link *l_ptr); +void node_link_up(struct node *n_ptr, struct link *l_ptr); +int node_has_active_links(struct node *n_ptr); +int node_has_redundant_links(struct node *n_ptr); +u32 node_select_router(struct node *n_ptr, u32 ref); +struct node *node_select_next_hop(u32 addr, u32 selector); +int node_is_up(struct node *n_ptr); +void node_add_router(struct node *n_ptr, u32 router); +void node_remove_router(struct node *n_ptr, u32 router); +struct sk_buff *node_get_links(const void *req_tlv_area, int req_tlv_space); +struct sk_buff *node_get_nodes(const void *req_tlv_area, int req_tlv_space); + +static inline struct node *node_find(u32 addr) +{ + if (likely(in_own_cluster(addr))) + return local_nodes[tipc_node(addr)]; + else if (addr_domain_valid(addr)) { + struct cluster *c_ptr = cluster_find(addr); + + if (c_ptr) + return c_ptr->nodes[tipc_node(addr)]; + } + return 0; +} + +static inline struct node *node_select(u32 addr, u32 selector) +{ + if (likely(in_own_cluster(addr))) + return local_nodes[tipc_node(addr)]; + return node_select_next_hop(addr, selector); +} + +static inline void node_lock(struct node *n_ptr) +{ + spin_lock_bh(&n_ptr->lock); +} + +static inline void node_unlock(struct node *n_ptr) +{ + spin_unlock_bh(&n_ptr->lock); +} + +#endif diff --git a/net/tipc/node_subscr.c b/net/tipc/node_subscr.c new file mode 100644 index 00000000000..79375927916 --- /dev/null +++ b/net/tipc/node_subscr.c @@ -0,0 +1,79 @@ +/* + * net/tipc/node_subscr.c: TIPC "node down" subscription handling + * + * Copyright (c) 1995-2006, Ericsson AB + * Copyright (c) 2005, Wind River Systems + * All rights reserved. + * + * Redistribution and use in source and binary forms, with or without + * modification, are permitted provided that the following conditions are met: + * + * 1. Redistributions of source code must retain the above copyright + * notice, this list of conditions and the following disclaimer. + * 2. Redistributions in binary form must reproduce the above copyright + * notice, this list of conditions and the following disclaimer in the + * documentation and/or other materials provided with the distribution. + * 3. Neither the names of the copyright holders nor the names of its + * contributors may be used to endorse or promote products derived from + * this software without specific prior written permission. + * + * Alternatively, this software may be distributed under the terms of the + * GNU General Public License ("GPL") version 2 as published by the Free + * Software Foundation. + * + * THIS SOFTWARE IS PROVIDED BY THE COPYRIGHT HOLDERS AND CONTRIBUTORS "AS IS" + * AND ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT LIMITED TO, THE + * IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR A PARTICULAR PURPOSE + * ARE DISCLAIMED. IN NO EVENT SHALL THE COPYRIGHT OWNER OR CONTRIBUTORS BE + * LIABLE FOR ANY DIRECT, INDIRECT, INCIDENTAL, SPECIAL, EXEMPLARY, OR + * CONSEQUENTIAL DAMAGES (INCLUDING, BUT NOT LIMITED TO, PROCUREMENT OF + * SUBSTITUTE GOODS OR SERVICES; LOSS OF USE, DATA, OR PROFITS; OR BUSINESS + * INTERRUPTION) HOWEVER CAUSED AND ON ANY THEORY OF LIABILITY, WHETHER IN + * CONTRACT, STRICT LIABILITY, OR TORT (INCLUDING NEGLIGENCE OR OTHERWISE) + * ARISING IN ANY WAY OUT OF THE USE OF THIS SOFTWARE, EVEN IF ADVISED OF THE + * POSSIBILITY OF SUCH DAMAGE. + */ + +#include "core.h" +#include "dbg.h" +#include "node_subscr.h" +#include "node.h" +#include "addr.h" + +/** + * nodesub_subscribe - create "node down" subscription for specified node + */ + +void nodesub_subscribe(struct node_subscr *node_sub, u32 addr, + void *usr_handle, net_ev_handler handle_down) +{ + node_sub->node = 0; + if (addr == tipc_own_addr) + return; + if (!addr_node_valid(addr)) { + warn("node_subscr with illegal %x\n", addr); + return; + } + + node_sub->handle_node_down = handle_down; + node_sub->usr_handle = usr_handle; + node_sub->node = node_find(addr); + assert(node_sub->node); + node_lock(node_sub->node); + list_add_tail(&node_sub->nodesub_list, &node_sub->node->nsub); + node_unlock(node_sub->node); +} + +/** + * nodesub_unsubscribe - cancel "node down" subscription (if any) + */ + +void nodesub_unsubscribe(struct node_subscr *node_sub) +{ + if (!node_sub->node) + return; + + node_lock(node_sub->node); + list_del_init(&node_sub->nodesub_list); + node_unlock(node_sub->node); +} diff --git a/net/tipc/node_subscr.h b/net/tipc/node_subscr.h new file mode 100644 index 00000000000..a3b87ac4859 --- /dev/null +++ b/net/tipc/node_subscr.h @@ -0,0 +1,63 @@ +/* + * net/tipc/node_subscr.h: Include file for TIPC "node down" subscription handling + * + * Copyright (c) 1995-2006, Ericsson AB + * Copyright (c) 2005, Wind River Systems + * All rights reserved. + * + * Redistribution and use in source and binary forms, with or without + * modification, are permitted provided that the following conditions are met: + * + * 1. Redistributions of source code must retain the above copyright + * notice, this list of conditions and the following disclaimer. + * 2. Redistributions in binary form must reproduce the above copyright + * notice, this list of conditions and the following disclaimer in the + * documentation and/or other materials provided with the distribution. + * 3. Neither the names of the copyright holders nor the names of its + * contributors may be used to endorse or promote products derived from + * this software without specific prior written permission. + * + * Alternatively, this software may be distributed under the terms of the + * GNU General Public License ("GPL") version 2 as published by the Free + * Software Foundation. + * + * THIS SOFTWARE IS PROVIDED BY THE COPYRIGHT HOLDERS AND CONTRIBUTORS "AS IS" + * AND ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT LIMITED TO, THE + * IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR A PARTICULAR PURPOSE + * ARE DISCLAIMED. IN NO EVENT SHALL THE COPYRIGHT OWNER OR CONTRIBUTORS BE + * LIABLE FOR ANY DIRECT, INDIRECT, INCIDENTAL, SPECIAL, EXEMPLARY, OR + * CONSEQUENTIAL DAMAGES (INCLUDING, BUT NOT LIMITED TO, PROCUREMENT OF + * SUBSTITUTE GOODS OR SERVICES; LOSS OF USE, DATA, OR PROFITS; OR BUSINESS + * INTERRUPTION) HOWEVER CAUSED AND ON ANY THEORY OF LIABILITY, WHETHER IN + * CONTRACT, STRICT LIABILITY, OR TORT (INCLUDING NEGLIGENCE OR OTHERWISE) + * ARISING IN ANY WAY OUT OF THE USE OF THIS SOFTWARE, EVEN IF ADVISED OF THE + * POSSIBILITY OF SUCH DAMAGE. + */ + +#ifndef _TIPC_NODE_SUBSCR_H +#define _TIPC_NODE_SUBSCR_H + +#include "addr.h" + +typedef void (*net_ev_handler) (void *usr_handle); + +/** + * struct node_subscr - "node down" subscription entry + * @node: ptr to node structure of interest (or NULL, if none) + * @handle_node_down: routine to invoke when node fails + * @usr_handle: argument to pass to routine when node fails + * @nodesub_list: adjacent entries in list of subscriptions for the node + */ + +struct node_subscr { + struct node *node; + net_ev_handler handle_node_down; + void *usr_handle; + struct list_head nodesub_list; +}; + +void nodesub_subscribe(struct node_subscr *node_sub, u32 addr, + void *usr_handle, net_ev_handler handle_down); +void nodesub_unsubscribe(struct node_subscr *node_sub); + +#endif diff --git a/net/tipc/port.c b/net/tipc/port.c new file mode 100644 index 00000000000..66caca7abe9 --- /dev/null +++ b/net/tipc/port.c @@ -0,0 +1,1708 @@ +/* + * net/tipc/port.c: TIPC port code + * + * Copyright (c) 1992-2006, Ericsson AB + * Copyright (c) 2004-2005, Wind River Systems + * All rights reserved. + * + * Redistribution and use in source and binary forms, with or without + * modification, are permitted provided that the following conditions are met: + * + * 1. Redistributions of source code must retain the above copyright + * notice, this list of conditions and the following disclaimer. + * 2. Redistributions in binary form must reproduce the above copyright + * notice, this list of conditions and the following disclaimer in the + * documentation and/or other materials provided with the distribution. + * 3. Neither the names of the copyright holders nor the names of its + * contributors may be used to endorse or promote products derived from + * this software without specific prior written permission. + * + * Alternatively, this software may be distributed under the terms of the + * GNU General Public License ("GPL") version 2 as published by the Free + * Software Foundation. + * + * THIS SOFTWARE IS PROVIDED BY THE COPYRIGHT HOLDERS AND CONTRIBUTORS "AS IS" + * AND ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT LIMITED TO, THE + * IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR A PARTICULAR PURPOSE + * ARE DISCLAIMED. IN NO EVENT SHALL THE COPYRIGHT OWNER OR CONTRIBUTORS BE + * LIABLE FOR ANY DIRECT, INDIRECT, INCIDENTAL, SPECIAL, EXEMPLARY, OR + * CONSEQUENTIAL DAMAGES (INCLUDING, BUT NOT LIMITED TO, PROCUREMENT OF + * SUBSTITUTE GOODS OR SERVICES; LOSS OF USE, DATA, OR PROFITS; OR BUSINESS + * INTERRUPTION) HOWEVER CAUSED AND ON ANY THEORY OF LIABILITY, WHETHER IN + * CONTRACT, STRICT LIABILITY, OR TORT (INCLUDING NEGLIGENCE OR OTHERWISE) + * ARISING IN ANY WAY OUT OF THE USE OF THIS SOFTWARE, EVEN IF ADVISED OF THE + * POSSIBILITY OF SUCH DAMAGE. + */ + +#include "core.h" +#include "config.h" +#include "dbg.h" +#include "port.h" +#include "addr.h" +#include "link.h" +#include "node.h" +#include "port.h" +#include "name_table.h" +#include "user_reg.h" +#include "msg.h" +#include "bcast.h" + +/* Connection management: */ +#define PROBING_INTERVAL 3600000 /* [ms] => 1 h */ +#define CONFIRMED 0 +#define PROBING 1 + +#define MAX_REJECT_SIZE 1024 + +static struct sk_buff *msg_queue_head = 0; +static struct sk_buff *msg_queue_tail = 0; + +spinlock_t port_list_lock = SPIN_LOCK_UNLOCKED; +static spinlock_t queue_lock = SPIN_LOCK_UNLOCKED; + +LIST_HEAD(ports); +static void port_handle_node_down(unsigned long ref); +static struct sk_buff* port_build_self_abort_msg(struct port *,u32 err); +static struct sk_buff* port_build_peer_abort_msg(struct port *,u32 err); +static void port_timeout(unsigned long ref); + + +static inline u32 port_peernode(struct port *p_ptr) +{ + return msg_destnode(&p_ptr->publ.phdr); +} + +static inline u32 port_peerport(struct port *p_ptr) +{ + return msg_destport(&p_ptr->publ.phdr); +} + +static inline u32 port_out_seqno(struct port *p_ptr) +{ + return msg_transp_seqno(&p_ptr->publ.phdr); +} + +static inline void port_set_out_seqno(struct port *p_ptr, u32 seqno) +{ + msg_set_transp_seqno(&p_ptr->publ.phdr,seqno); +} + +static inline void port_incr_out_seqno(struct port *p_ptr) +{ + struct tipc_msg *m = &p_ptr->publ.phdr; + + if (likely(!msg_routed(m))) + return; + msg_set_transp_seqno(m, (msg_transp_seqno(m) + 1)); +} + +/** + * tipc_multicast - send a multicast message to local and remote destinations + */ + +int tipc_multicast(u32 ref, struct tipc_name_seq const *seq, u32 domain, + u32 num_sect, struct iovec const *msg_sect) +{ + struct tipc_msg *hdr; + struct sk_buff *buf; + struct sk_buff *ibuf = NULL; + struct port_list dports = {0, NULL, }; + struct port *oport = port_deref(ref); + int ext_targets; + int res; + + if (unlikely(!oport)) + return -EINVAL; + + /* Create multicast message */ + + hdr = &oport->publ.phdr; + msg_set_type(hdr, TIPC_MCAST_MSG); + msg_set_nametype(hdr, seq->type); + msg_set_namelower(hdr, seq->lower); + msg_set_nameupper(hdr, seq->upper); + msg_set_hdr_sz(hdr, MCAST_H_SIZE); + res = msg_build(hdr, msg_sect, num_sect, MAX_MSG_SIZE, + !oport->user_port, &buf); + if (unlikely(!buf)) + return res; + + /* Figure out where to send multicast message */ + + ext_targets = nametbl_mc_translate(seq->type, seq->lower, seq->upper, + TIPC_NODE_SCOPE, &dports); + + /* Send message to destinations (duplicate it only if necessary) */ + + if (ext_targets) { + if (dports.count != 0) { + ibuf = skb_copy(buf, GFP_ATOMIC); + if (ibuf == NULL) { + port_list_free(&dports); + buf_discard(buf); + return -ENOMEM; + } + } + res = bclink_send_msg(buf); + if ((res < 0) && (dports.count != 0)) { + buf_discard(ibuf); + } + } else { + ibuf = buf; + } + + if (res >= 0) { + if (ibuf) + port_recv_mcast(ibuf, &dports); + } else { + port_list_free(&dports); + } + return res; +} + +/** + * port_recv_mcast - deliver multicast message to all destination ports + * + * If there is no port list, perform a lookup to create one + */ + +void port_recv_mcast(struct sk_buff *buf, struct port_list *dp) +{ + struct tipc_msg* msg; + struct port_list dports = {0, NULL, }; + struct port_list *item = dp; + int cnt = 0; + + assert(buf); + msg = buf_msg(buf); + + /* Create destination port list, if one wasn't supplied */ + + if (dp == NULL) { + nametbl_mc_translate(msg_nametype(msg), + msg_namelower(msg), + msg_nameupper(msg), + TIPC_CLUSTER_SCOPE, + &dports); + item = dp = &dports; + } + + /* Deliver a copy of message to each destination port */ + + if (dp->count != 0) { + if (dp->count == 1) { + msg_set_destport(msg, dp->ports[0]); + port_recv_msg(buf); + port_list_free(dp); + return; + } + for (; cnt < dp->count; cnt++) { + int index = cnt % PLSIZE; + struct sk_buff *b = skb_clone(buf, GFP_ATOMIC); + + if (b == NULL) { + warn("Buffer allocation failure\n"); + msg_dbg(msg, "LOST:"); + goto exit; + } + if ((index == 0) && (cnt != 0)) { + item = item->next; + } + msg_set_destport(buf_msg(b),item->ports[index]); + port_recv_msg(b); + } + } +exit: + buf_discard(buf); + port_list_free(dp); +} + +/** + * tipc_createport_raw - create a native TIPC port + * + * Returns local port reference + */ + +u32 tipc_createport_raw(void *usr_handle, + u32 (*dispatcher)(struct tipc_port *, struct sk_buff *), + void (*wakeup)(struct tipc_port *), + const u32 importance) +{ + struct port *p_ptr; + struct tipc_msg *msg; + u32 ref; + + p_ptr = kmalloc(sizeof(*p_ptr), GFP_ATOMIC); + if (p_ptr == NULL) { + warn("Memory squeeze; failed to create port\n"); + return 0; + } + memset(p_ptr, 0, sizeof(*p_ptr)); + ref = ref_acquire(p_ptr, &p_ptr->publ.lock); + if (!ref) { + warn("Reference Table Exhausted\n"); + kfree(p_ptr); + return 0; + } + + port_lock(ref); + p_ptr->publ.ref = ref; + msg = &p_ptr->publ.phdr; + msg_init(msg, DATA_LOW, TIPC_NAMED_MSG, TIPC_OK, LONG_H_SIZE, 0); + msg_set_orignode(msg, tipc_own_addr); + msg_set_prevnode(msg, tipc_own_addr); + msg_set_origport(msg, ref); + msg_set_importance(msg,importance); + p_ptr->last_in_seqno = 41; + p_ptr->sent = 1; + p_ptr->publ.usr_handle = usr_handle; + INIT_LIST_HEAD(&p_ptr->wait_list); + INIT_LIST_HEAD(&p_ptr->subscription.nodesub_list); + p_ptr->congested_link = 0; + p_ptr->max_pkt = MAX_PKT_DEFAULT; + p_ptr->dispatcher = dispatcher; + p_ptr->wakeup = wakeup; + p_ptr->user_port = 0; + k_init_timer(&p_ptr->timer, (Handler)port_timeout, ref); + spin_lock_bh(&port_list_lock); + INIT_LIST_HEAD(&p_ptr->publications); + INIT_LIST_HEAD(&p_ptr->port_list); + list_add_tail(&p_ptr->port_list, &ports); + spin_unlock_bh(&port_list_lock); + port_unlock(p_ptr); + return ref; +} + +int tipc_deleteport(u32 ref) +{ + struct port *p_ptr; + struct sk_buff *buf = 0; + + tipc_withdraw(ref, 0, 0); + p_ptr = port_lock(ref); + if (!p_ptr) + return -EINVAL; + + ref_discard(ref); + port_unlock(p_ptr); + + k_cancel_timer(&p_ptr->timer); + if (p_ptr->publ.connected) { + buf = port_build_peer_abort_msg(p_ptr, TIPC_ERR_NO_PORT); + nodesub_unsubscribe(&p_ptr->subscription); + } + if (p_ptr->user_port) { + reg_remove_port(p_ptr->user_port); + kfree(p_ptr->user_port); + } + + spin_lock_bh(&port_list_lock); + list_del(&p_ptr->port_list); + list_del(&p_ptr->wait_list); + spin_unlock_bh(&port_list_lock); + k_term_timer(&p_ptr->timer); + kfree(p_ptr); + dbg("Deleted port %u\n", ref); + net_route_msg(buf); + return TIPC_OK; +} + +/** + * tipc_get_port() - return port associated with 'ref' + * + * Note: Port is not locked. + */ + +struct tipc_port *tipc_get_port(const u32 ref) +{ + return (struct tipc_port *)ref_deref(ref); +} + +/** + * tipc_get_handle - return user handle associated to port 'ref' + */ + +void *tipc_get_handle(const u32 ref) +{ + struct port *p_ptr; + void * handle; + + p_ptr = port_lock(ref); + if (!p_ptr) + return 0; + handle = p_ptr->publ.usr_handle; + port_unlock(p_ptr); + return handle; +} + +static inline int port_unreliable(struct port *p_ptr) +{ + return msg_src_droppable(&p_ptr->publ.phdr); +} + +int tipc_portunreliable(u32 ref, unsigned int *isunreliable) +{ + struct port *p_ptr; + + p_ptr = port_lock(ref); + if (!p_ptr) + return -EINVAL; + *isunreliable = port_unreliable(p_ptr); + spin_unlock_bh(p_ptr->publ.lock); + return TIPC_OK; +} + +int tipc_set_portunreliable(u32 ref, unsigned int isunreliable) +{ + struct port *p_ptr; + + p_ptr = port_lock(ref); + if (!p_ptr) + return -EINVAL; + msg_set_src_droppable(&p_ptr->publ.phdr, (isunreliable != 0)); + port_unlock(p_ptr); + return TIPC_OK; +} + +static inline int port_unreturnable(struct port *p_ptr) +{ + return msg_dest_droppable(&p_ptr->publ.phdr); +} + +int tipc_portunreturnable(u32 ref, unsigned int *isunrejectable) +{ + struct port *p_ptr; + + p_ptr = port_lock(ref); + if (!p_ptr) + return -EINVAL; + *isunrejectable = port_unreturnable(p_ptr); + spin_unlock_bh(p_ptr->publ.lock); + return TIPC_OK; +} + +int tipc_set_portunreturnable(u32 ref, unsigned int isunrejectable) +{ + struct port *p_ptr; + + p_ptr = port_lock(ref); + if (!p_ptr) + return -EINVAL; + msg_set_dest_droppable(&p_ptr->publ.phdr, (isunrejectable != 0)); + port_unlock(p_ptr); + return TIPC_OK; +} + +/* + * port_build_proto_msg(): build a port level protocol + * or a connection abortion message. Called with + * tipc_port lock on. + */ +static struct sk_buff *port_build_proto_msg(u32 destport, u32 destnode, + u32 origport, u32 orignode, + u32 usr, u32 type, u32 err, + u32 seqno, u32 ack) +{ + struct sk_buff *buf; + struct tipc_msg *msg; + + buf = buf_acquire(LONG_H_SIZE); + if (buf) { + msg = buf_msg(buf); + msg_init(msg, usr, type, err, LONG_H_SIZE, destnode); + msg_set_destport(msg, destport); + msg_set_origport(msg, origport); + msg_set_destnode(msg, destnode); + msg_set_orignode(msg, orignode); + msg_set_transp_seqno(msg, seqno); + msg_set_msgcnt(msg, ack); + msg_dbg(msg, "PORT>SEND>:"); + } + return buf; +} + +int tipc_set_msg_option(struct tipc_port *tp_ptr, const char *opt, const u32 sz) +{ + msg_expand(&tp_ptr->phdr, msg_destnode(&tp_ptr->phdr)); + msg_set_options(&tp_ptr->phdr, opt, sz); + return TIPC_OK; +} + +int tipc_reject_msg(struct sk_buff *buf, u32 err) +{ + struct tipc_msg *msg = buf_msg(buf); + struct sk_buff *rbuf; + struct tipc_msg *rmsg; + int hdr_sz; + u32 imp = msg_importance(msg); + u32 data_sz = msg_data_sz(msg); + + if (data_sz > MAX_REJECT_SIZE) + data_sz = MAX_REJECT_SIZE; + if (msg_connected(msg) && (imp < TIPC_CRITICAL_IMPORTANCE)) + imp++; + msg_dbg(msg, "port->rej: "); + + /* discard rejected message if it shouldn't be returned to sender */ + if (msg_errcode(msg) || msg_dest_droppable(msg)) { + buf_discard(buf); + return data_sz; + } + + /* construct rejected message */ + if (msg_mcast(msg)) + hdr_sz = MCAST_H_SIZE; + else + hdr_sz = LONG_H_SIZE; + rbuf = buf_acquire(data_sz + hdr_sz); + if (rbuf == NULL) { + buf_discard(buf); + return data_sz; + } + rmsg = buf_msg(rbuf); + msg_init(rmsg, imp, msg_type(msg), err, hdr_sz, msg_orignode(msg)); + msg_set_destport(rmsg, msg_origport(msg)); + msg_set_prevnode(rmsg, tipc_own_addr); + msg_set_origport(rmsg, msg_destport(msg)); + if (msg_short(msg)) + msg_set_orignode(rmsg, tipc_own_addr); + else + msg_set_orignode(rmsg, msg_destnode(msg)); + msg_set_size(rmsg, data_sz + hdr_sz); + msg_set_nametype(rmsg, msg_nametype(msg)); + msg_set_nameinst(rmsg, msg_nameinst(msg)); + memcpy(rbuf->data + hdr_sz, msg_data(msg), data_sz); + + /* send self-abort message when rejecting on a connected port */ + if (msg_connected(msg)) { + struct sk_buff *abuf = 0; + struct port *p_ptr = port_lock(msg_destport(msg)); + + if (p_ptr) { + if (p_ptr->publ.connected) + abuf = port_build_self_abort_msg(p_ptr, err); + port_unlock(p_ptr); + } + net_route_msg(abuf); + } + + /* send rejected message */ + buf_discard(buf); + net_route_msg(rbuf); + return data_sz; +} + +int port_reject_sections(struct port *p_ptr, struct tipc_msg *hdr, + struct iovec const *msg_sect, u32 num_sect, + int err) +{ + struct sk_buff *buf; + int res; + + res = msg_build(hdr, msg_sect, num_sect, MAX_MSG_SIZE, + !p_ptr->user_port, &buf); + if (!buf) + return res; + + return tipc_reject_msg(buf, err); +} + +static void port_timeout(unsigned long ref) +{ + struct port *p_ptr = port_lock(ref); + struct sk_buff *buf = 0; + + if (!p_ptr || !p_ptr->publ.connected) + return; + + /* Last probe answered ? */ + if (p_ptr->probing_state == PROBING) { + buf = port_build_self_abort_msg(p_ptr, TIPC_ERR_NO_PORT); + } else { + buf = port_build_proto_msg(port_peerport(p_ptr), + port_peernode(p_ptr), + p_ptr->publ.ref, + tipc_own_addr, + CONN_MANAGER, + CONN_PROBE, + TIPC_OK, + port_out_seqno(p_ptr), + 0); + port_incr_out_seqno(p_ptr); + p_ptr->probing_state = PROBING; + k_start_timer(&p_ptr->timer, p_ptr->probing_interval); + } + port_unlock(p_ptr); + net_route_msg(buf); +} + + +static void port_handle_node_down(unsigned long ref) +{ + struct port *p_ptr = port_lock(ref); + struct sk_buff* buf = 0; + + if (!p_ptr) + return; + buf = port_build_self_abort_msg(p_ptr, TIPC_ERR_NO_NODE); + port_unlock(p_ptr); + net_route_msg(buf); +} + + +static struct sk_buff *port_build_self_abort_msg(struct port *p_ptr, u32 err) +{ + u32 imp = msg_importance(&p_ptr->publ.phdr); + + if (!p_ptr->publ.connected) + return 0; + if (imp < TIPC_CRITICAL_IMPORTANCE) + imp++; + return port_build_proto_msg(p_ptr->publ.ref, + tipc_own_addr, + port_peerport(p_ptr), + port_peernode(p_ptr), + imp, + TIPC_CONN_MSG, + err, + p_ptr->last_in_seqno + 1, + 0); +} + + +static struct sk_buff *port_build_peer_abort_msg(struct port *p_ptr, u32 err) +{ + u32 imp = msg_importance(&p_ptr->publ.phdr); + + if (!p_ptr->publ.connected) + return 0; + if (imp < TIPC_CRITICAL_IMPORTANCE) + imp++; + return port_build_proto_msg(port_peerport(p_ptr), + port_peernode(p_ptr), + p_ptr->publ.ref, + tipc_own_addr, + imp, + TIPC_CONN_MSG, + err, + port_out_seqno(p_ptr), + 0); +} + +void port_recv_proto_msg(struct sk_buff *buf) +{ + struct tipc_msg *msg = buf_msg(buf); + struct port *p_ptr = port_lock(msg_destport(msg)); + u32 err = TIPC_OK; + struct sk_buff *r_buf = 0; + struct sk_buff *abort_buf = 0; + + msg_dbg(msg, "PORT<RECV<:"); + + if (!p_ptr) { + err = TIPC_ERR_NO_PORT; + } else if (p_ptr->publ.connected) { + if (port_peernode(p_ptr) != msg_orignode(msg)) + err = TIPC_ERR_NO_PORT; + if (port_peerport(p_ptr) != msg_origport(msg)) + err = TIPC_ERR_NO_PORT; + if (!err && msg_routed(msg)) { + u32 seqno = msg_transp_seqno(msg); + u32 myno = ++p_ptr->last_in_seqno; + if (seqno != myno) { + err = TIPC_ERR_NO_PORT; + abort_buf = port_build_self_abort_msg(p_ptr, err); + } + } + if (msg_type(msg) == CONN_ACK) { + int wakeup = port_congested(p_ptr) && + p_ptr->publ.congested && + p_ptr->wakeup; + p_ptr->acked += msg_msgcnt(msg); + if (port_congested(p_ptr)) + goto exit; + p_ptr->publ.congested = 0; + if (!wakeup) + goto exit; + p_ptr->wakeup(&p_ptr->publ); + goto exit; + } + } else if (p_ptr->publ.published) { + err = TIPC_ERR_NO_PORT; + } + if (err) { + r_buf = port_build_proto_msg(msg_origport(msg), + msg_orignode(msg), + msg_destport(msg), + tipc_own_addr, + DATA_HIGH, + TIPC_CONN_MSG, + err, + 0, + 0); + goto exit; + } + + /* All is fine */ + if (msg_type(msg) == CONN_PROBE) { + r_buf = port_build_proto_msg(msg_origport(msg), + msg_orignode(msg), + msg_destport(msg), + tipc_own_addr, + CONN_MANAGER, + CONN_PROBE_REPLY, + TIPC_OK, + port_out_seqno(p_ptr), + 0); + } + p_ptr->probing_state = CONFIRMED; + port_incr_out_seqno(p_ptr); +exit: + if (p_ptr) + port_unlock(p_ptr); + net_route_msg(r_buf); + net_route_msg(abort_buf); + buf_discard(buf); +} + +static void port_print(struct port *p_ptr, struct print_buf *buf, int full_id) +{ + struct publication *publ; + + if (full_id) + tipc_printf(buf, "<%u.%u.%u:%u>:", + tipc_zone(tipc_own_addr), tipc_cluster(tipc_own_addr), + tipc_node(tipc_own_addr), p_ptr->publ.ref); + else + tipc_printf(buf, "%-10u:", p_ptr->publ.ref); + + if (p_ptr->publ.connected) { + u32 dport = port_peerport(p_ptr); + u32 destnode = port_peernode(p_ptr); + + tipc_printf(buf, " connected to <%u.%u.%u:%u>", + tipc_zone(destnode), tipc_cluster(destnode), + tipc_node(destnode), dport); + if (p_ptr->publ.conn_type != 0) + tipc_printf(buf, " via {%u,%u}", + p_ptr->publ.conn_type, + p_ptr->publ.conn_instance); + } + else if (p_ptr->publ.published) { + tipc_printf(buf, " bound to"); + list_for_each_entry(publ, &p_ptr->publications, pport_list) { + if (publ->lower == publ->upper) + tipc_printf(buf, " {%u,%u}", publ->type, + publ->lower); + else + tipc_printf(buf, " {%u,%u,%u}", publ->type, + publ->lower, publ->upper); + } + } + tipc_printf(buf, "\n"); +} + +#define MAX_PORT_QUERY 32768 + +struct sk_buff *port_get_ports(void) +{ + struct sk_buff *buf; + struct tlv_desc *rep_tlv; + struct print_buf pb; + struct port *p_ptr; + int str_len; + + buf = cfg_reply_alloc(TLV_SPACE(MAX_PORT_QUERY)); + if (!buf) + return NULL; + rep_tlv = (struct tlv_desc *)buf->data; + + printbuf_init(&pb, TLV_DATA(rep_tlv), MAX_PORT_QUERY); + spin_lock_bh(&port_list_lock); + list_for_each_entry(p_ptr, &ports, port_list) { + spin_lock_bh(p_ptr->publ.lock); + port_print(p_ptr, &pb, 0); + spin_unlock_bh(p_ptr->publ.lock); + } + spin_unlock_bh(&port_list_lock); + str_len = printbuf_validate(&pb); + + skb_put(buf, TLV_SPACE(str_len)); + TLV_SET(rep_tlv, TIPC_TLV_ULTRA_STRING, NULL, str_len); + + return buf; +} + +#if 0 + +#define MAX_PORT_STATS 2000 + +struct sk_buff *port_show_stats(const void *req_tlv_area, int req_tlv_space) +{ + u32 ref; + struct port *p_ptr; + struct sk_buff *buf; + struct tlv_desc *rep_tlv; + struct print_buf pb; + int str_len; + + if (!TLV_CHECK(req_tlv_area, req_tlv_space, TIPC_TLV_PORT_REF)) + return cfg_reply_error_string(TIPC_CFG_TLV_ERROR); + + ref = *(u32 *)TLV_DATA(req_tlv_area); + ref = ntohl(ref); + + p_ptr = port_lock(ref); + if (!p_ptr) + return cfg_reply_error_string("port not found"); + + buf = cfg_reply_alloc(TLV_SPACE(MAX_PORT_STATS)); + if (!buf) { + port_unlock(p_ptr); + return NULL; + } + rep_tlv = (struct tlv_desc *)buf->data; + + printbuf_init(&pb, TLV_DATA(rep_tlv), MAX_PORT_STATS); + port_print(p_ptr, &pb, 1); + /* NEED TO FILL IN ADDITIONAL PORT STATISTICS HERE */ + port_unlock(p_ptr); + str_len = printbuf_validate(&pb); + + skb_put(buf, TLV_SPACE(str_len)); + TLV_SET(rep_tlv, TIPC_TLV_ULTRA_STRING, NULL, str_len); + + return buf; +} + +#endif + +void port_reinit(void) +{ + struct port *p_ptr; + struct tipc_msg *msg; + + spin_lock_bh(&port_list_lock); + list_for_each_entry(p_ptr, &ports, port_list) { + msg = &p_ptr->publ.phdr; + if (msg_orignode(msg) == tipc_own_addr) + break; + msg_set_orignode(msg, tipc_own_addr); + } + spin_unlock_bh(&port_list_lock); +} + + +/* + * port_dispatcher_sigh(): Signal handler for messages destinated + * to the tipc_port interface. + */ + +static void port_dispatcher_sigh(void *dummy) +{ + struct sk_buff *buf; + + spin_lock_bh(&queue_lock); + buf = msg_queue_head; + msg_queue_head = 0; + spin_unlock_bh(&queue_lock); + + while (buf) { + struct port *p_ptr; + struct user_port *up_ptr; + struct tipc_portid orig; + struct tipc_name_seq dseq; + void *usr_handle; + int connected; + int published; + + struct sk_buff *next = buf->next; + struct tipc_msg *msg = buf_msg(buf); + u32 dref = msg_destport(msg); + + p_ptr = port_lock(dref); + if (!p_ptr) { + /* Port deleted while msg in queue */ + tipc_reject_msg(buf, TIPC_ERR_NO_PORT); + buf = next; + continue; + } + orig.ref = msg_origport(msg); + orig.node = msg_orignode(msg); + up_ptr = p_ptr->user_port; + usr_handle = up_ptr->usr_handle; + connected = p_ptr->publ.connected; + published = p_ptr->publ.published; + + if (unlikely(msg_errcode(msg))) + goto err; + + switch (msg_type(msg)) { + + case TIPC_CONN_MSG:{ + tipc_conn_msg_event cb = up_ptr->conn_msg_cb; + u32 peer_port = port_peerport(p_ptr); + u32 peer_node = port_peernode(p_ptr); + + spin_unlock_bh(p_ptr->publ.lock); + if (unlikely(!connected)) { + if (unlikely(published)) + goto reject; + tipc_connect2port(dref,&orig); + } + if (unlikely(msg_origport(msg) != peer_port)) + goto reject; + if (unlikely(msg_orignode(msg) != peer_node)) + goto reject; + if (unlikely(!cb)) + goto reject; + if (unlikely(++p_ptr->publ.conn_unacked >= + TIPC_FLOW_CONTROL_WIN)) + tipc_acknowledge(dref, + p_ptr->publ.conn_unacked); + skb_pull(buf, msg_hdr_sz(msg)); + cb(usr_handle, dref, &buf, msg_data(msg), + msg_data_sz(msg)); + break; + } + case TIPC_DIRECT_MSG:{ + tipc_msg_event cb = up_ptr->msg_cb; + + spin_unlock_bh(p_ptr->publ.lock); + if (unlikely(connected)) + goto reject; + if (unlikely(!cb)) + goto reject; + skb_pull(buf, msg_hdr_sz(msg)); + cb(usr_handle, dref, &buf, msg_data(msg), + msg_data_sz(msg), msg_importance(msg), + &orig); + break; + } + case TIPC_NAMED_MSG:{ + tipc_named_msg_event cb = up_ptr->named_msg_cb; + + spin_unlock_bh(p_ptr->publ.lock); + if (unlikely(connected)) + goto reject; + if (unlikely(!cb)) + goto reject; + if (unlikely(!published)) + goto reject; + dseq.type = msg_nametype(msg); + dseq.lower = msg_nameinst(msg); + dseq.upper = dseq.lower; + skb_pull(buf, msg_hdr_sz(msg)); + cb(usr_handle, dref, &buf, msg_data(msg), + msg_data_sz(msg), msg_importance(msg), + &orig, &dseq); + break; + } + } + if (buf) + buf_discard(buf); + buf = next; + continue; +err: + switch (msg_type(msg)) { + + case TIPC_CONN_MSG:{ + tipc_conn_shutdown_event cb = + up_ptr->conn_err_cb; + u32 peer_port = port_peerport(p_ptr); + u32 peer_node = port_peernode(p_ptr); + + spin_unlock_bh(p_ptr->publ.lock); + if (!connected || !cb) + break; + if (msg_origport(msg) != peer_port) + break; + if (msg_orignode(msg) != peer_node) + break; + tipc_disconnect(dref); + skb_pull(buf, msg_hdr_sz(msg)); + cb(usr_handle, dref, &buf, msg_data(msg), + msg_data_sz(msg), msg_errcode(msg)); + break; + } + case TIPC_DIRECT_MSG:{ + tipc_msg_err_event cb = up_ptr->err_cb; + + spin_unlock_bh(p_ptr->publ.lock); + if (connected || !cb) + break; + skb_pull(buf, msg_hdr_sz(msg)); + cb(usr_handle, dref, &buf, msg_data(msg), + msg_data_sz(msg), msg_errcode(msg), &orig); + break; + } + case TIPC_NAMED_MSG:{ + tipc_named_msg_err_event cb = + up_ptr->named_err_cb; + + spin_unlock_bh(p_ptr->publ.lock); + if (connected || !cb) + break; + dseq.type = msg_nametype(msg); + dseq.lower = msg_nameinst(msg); + dseq.upper = dseq.lower; + skb_pull(buf, msg_hdr_sz(msg)); + cb(usr_handle, dref, &buf, msg_data(msg), + msg_data_sz(msg), msg_errcode(msg), &dseq); + break; + } + } + if (buf) + buf_discard(buf); + buf = next; + continue; +reject: + tipc_reject_msg(buf, TIPC_ERR_NO_PORT); + buf = next; + } +} + +/* + * port_dispatcher(): Dispatcher for messages destinated + * to the tipc_port interface. Called with port locked. + */ + +static u32 port_dispatcher(struct tipc_port *dummy, struct sk_buff *buf) +{ + buf->next = NULL; + spin_lock_bh(&queue_lock); + if (msg_queue_head) { + msg_queue_tail->next = buf; + msg_queue_tail = buf; + } else { + msg_queue_tail = msg_queue_head = buf; + k_signal((Handler)port_dispatcher_sigh, 0); + } + spin_unlock_bh(&queue_lock); + return TIPC_OK; +} + +/* + * Wake up port after congestion: Called with port locked, + * + */ + +static void port_wakeup_sh(unsigned long ref) +{ + struct port *p_ptr; + struct user_port *up_ptr; + tipc_continue_event cb = 0; + void *uh = 0; + + p_ptr = port_lock(ref); + if (p_ptr) { + up_ptr = p_ptr->user_port; + if (up_ptr) { + cb = up_ptr->continue_event_cb; + uh = up_ptr->usr_handle; + } + port_unlock(p_ptr); + } + if (cb) + cb(uh, ref); +} + + +static void port_wakeup(struct tipc_port *p_ptr) +{ + k_signal((Handler)port_wakeup_sh, p_ptr->ref); +} + +void tipc_acknowledge(u32 ref, u32 ack) +{ + struct port *p_ptr; + struct sk_buff *buf = 0; + + p_ptr = port_lock(ref); + if (!p_ptr) + return; + if (p_ptr->publ.connected) { + p_ptr->publ.conn_unacked -= ack; + buf = port_build_proto_msg(port_peerport(p_ptr), + port_peernode(p_ptr), + ref, + tipc_own_addr, + CONN_MANAGER, + CONN_ACK, + TIPC_OK, + port_out_seqno(p_ptr), + ack); + } + port_unlock(p_ptr); + net_route_msg(buf); +} + +/* + * tipc_createport(): user level call. Will add port to + * registry if non-zero user_ref. + */ + +int tipc_createport(u32 user_ref, + void *usr_handle, + unsigned int importance, + tipc_msg_err_event error_cb, + tipc_named_msg_err_event named_error_cb, + tipc_conn_shutdown_event conn_error_cb, + tipc_msg_event msg_cb, + tipc_named_msg_event named_msg_cb, + tipc_conn_msg_event conn_msg_cb, + tipc_continue_event continue_event_cb,/* May be zero */ + u32 *portref) +{ + struct user_port *up_ptr; + struct port *p_ptr; + u32 ref; + + up_ptr = (struct user_port *)kmalloc(sizeof(*up_ptr), GFP_ATOMIC); + if (up_ptr == NULL) { + return -ENOMEM; + } + ref = tipc_createport_raw(0, port_dispatcher, port_wakeup, importance); + p_ptr = port_lock(ref); + if (!p_ptr) { + kfree(up_ptr); + return -ENOMEM; + } + + p_ptr->user_port = up_ptr; + up_ptr->user_ref = user_ref; + up_ptr->usr_handle = usr_handle; + up_ptr->ref = p_ptr->publ.ref; + up_ptr->err_cb = error_cb; + up_ptr->named_err_cb = named_error_cb; + up_ptr->conn_err_cb = conn_error_cb; + up_ptr->msg_cb = msg_cb; + up_ptr->named_msg_cb = named_msg_cb; + up_ptr->conn_msg_cb = conn_msg_cb; + up_ptr->continue_event_cb = continue_event_cb; + INIT_LIST_HEAD(&up_ptr->uport_list); + reg_add_port(up_ptr); + *portref = p_ptr->publ.ref; + dbg(" tipc_createport: %x with ref %u\n", p_ptr, p_ptr->publ.ref); + port_unlock(p_ptr); + return TIPC_OK; +} + +int tipc_ownidentity(u32 ref, struct tipc_portid *id) +{ + id->ref = ref; + id->node = tipc_own_addr; + return TIPC_OK; +} + +int tipc_portimportance(u32 ref, unsigned int *importance) +{ + struct port *p_ptr; + + p_ptr = port_lock(ref); + if (!p_ptr) + return -EINVAL; + *importance = (unsigned int)msg_importance(&p_ptr->publ.phdr); + spin_unlock_bh(p_ptr->publ.lock); + return TIPC_OK; +} + +int tipc_set_portimportance(u32 ref, unsigned int imp) +{ + struct port *p_ptr; + + if (imp > TIPC_CRITICAL_IMPORTANCE) + return -EINVAL; + + p_ptr = port_lock(ref); + if (!p_ptr) + return -EINVAL; + msg_set_importance(&p_ptr->publ.phdr, (u32)imp); + spin_unlock_bh(p_ptr->publ.lock); + return TIPC_OK; +} + + +int tipc_publish(u32 ref, unsigned int scope, struct tipc_name_seq const *seq) +{ + struct port *p_ptr; + struct publication *publ; + u32 key; + int res = -EINVAL; + + p_ptr = port_lock(ref); + dbg("tipc_publ %u, p_ptr = %x, conn = %x, scope = %x, " + "lower = %u, upper = %u\n", + ref, p_ptr, p_ptr->publ.connected, scope, seq->lower, seq->upper); + if (!p_ptr) + return -EINVAL; + if (p_ptr->publ.connected) + goto exit; + if (seq->lower > seq->upper) + goto exit; + if ((scope < TIPC_ZONE_SCOPE) || (scope > TIPC_NODE_SCOPE)) + goto exit; + key = ref + p_ptr->pub_count + 1; + if (key == ref) { + res = -EADDRINUSE; + goto exit; + } + publ = nametbl_publish(seq->type, seq->lower, seq->upper, + scope, p_ptr->publ.ref, key); + if (publ) { + list_add(&publ->pport_list, &p_ptr->publications); + p_ptr->pub_count++; + p_ptr->publ.published = 1; + res = TIPC_OK; + } +exit: + port_unlock(p_ptr); + return res; +} + +int tipc_withdraw(u32 ref, unsigned int scope, struct tipc_name_seq const *seq) +{ + struct port *p_ptr; + struct publication *publ; + struct publication *tpubl; + int res = -EINVAL; + + p_ptr = port_lock(ref); + if (!p_ptr) + return -EINVAL; + if (!p_ptr->publ.published) + goto exit; + if (!seq) { + list_for_each_entry_safe(publ, tpubl, + &p_ptr->publications, pport_list) { + nametbl_withdraw(publ->type, publ->lower, + publ->ref, publ->key); + } + res = TIPC_OK; + } else { + list_for_each_entry_safe(publ, tpubl, + &p_ptr->publications, pport_list) { + if (publ->scope != scope) + continue; + if (publ->type != seq->type) + continue; + if (publ->lower != seq->lower) + continue; + if (publ->upper != seq->upper) + break; + nametbl_withdraw(publ->type, publ->lower, + publ->ref, publ->key); + res = TIPC_OK; + break; + } + } + if (list_empty(&p_ptr->publications)) + p_ptr->publ.published = 0; +exit: + port_unlock(p_ptr); + return res; +} + +int tipc_connect2port(u32 ref, struct tipc_portid const *peer) +{ + struct port *p_ptr; + struct tipc_msg *msg; + int res = -EINVAL; + + p_ptr = port_lock(ref); + if (!p_ptr) + return -EINVAL; + if (p_ptr->publ.published || p_ptr->publ.connected) + goto exit; + if (!peer->ref) + goto exit; + + msg = &p_ptr->publ.phdr; + msg_set_destnode(msg, peer->node); + msg_set_destport(msg, peer->ref); + msg_set_orignode(msg, tipc_own_addr); + msg_set_origport(msg, p_ptr->publ.ref); + msg_set_transp_seqno(msg, 42); + msg_set_type(msg, TIPC_CONN_MSG); + if (!may_route(peer->node)) + msg_set_hdr_sz(msg, SHORT_H_SIZE); + else + msg_set_hdr_sz(msg, LONG_H_SIZE); + + p_ptr->probing_interval = PROBING_INTERVAL; + p_ptr->probing_state = CONFIRMED; + p_ptr->publ.connected = 1; + k_start_timer(&p_ptr->timer, p_ptr->probing_interval); + + nodesub_subscribe(&p_ptr->subscription,peer->node, + (void *)(unsigned long)ref, + (net_ev_handler)port_handle_node_down); + res = TIPC_OK; +exit: + port_unlock(p_ptr); + p_ptr->max_pkt = link_get_max_pkt(peer->node, ref); + return res; +} + +/* + * tipc_disconnect(): Disconnect port form peer. + * This is a node local operation. + */ + +int tipc_disconnect(u32 ref) +{ + struct port *p_ptr; + int res = -ENOTCONN; + + p_ptr = port_lock(ref); + if (!p_ptr) + return -EINVAL; + if (p_ptr->publ.connected) { + p_ptr->publ.connected = 0; + /* let timer expire on it's own to avoid deadlock! */ + nodesub_unsubscribe(&p_ptr->subscription); + res = TIPC_OK; + } + port_unlock(p_ptr); + return res; +} + +/* + * tipc_shutdown(): Send a SHUTDOWN msg to peer and disconnect + */ +int tipc_shutdown(u32 ref) +{ + struct port *p_ptr; + struct sk_buff *buf = 0; + + p_ptr = port_lock(ref); + if (!p_ptr) + return -EINVAL; + + if (p_ptr->publ.connected) { + u32 imp = msg_importance(&p_ptr->publ.phdr); + if (imp < TIPC_CRITICAL_IMPORTANCE) + imp++; + buf = port_build_proto_msg(port_peerport(p_ptr), + port_peernode(p_ptr), + ref, + tipc_own_addr, + imp, + TIPC_CONN_MSG, + TIPC_CONN_SHUTDOWN, + port_out_seqno(p_ptr), + 0); + } + port_unlock(p_ptr); + net_route_msg(buf); + return tipc_disconnect(ref); +} + +int tipc_isconnected(u32 ref, int *isconnected) +{ + struct port *p_ptr; + + p_ptr = port_lock(ref); + if (!p_ptr) + return -EINVAL; + *isconnected = p_ptr->publ.connected; + port_unlock(p_ptr); + return TIPC_OK; +} + +int tipc_peer(u32 ref, struct tipc_portid *peer) +{ + struct port *p_ptr; + int res; + + p_ptr = port_lock(ref); + if (!p_ptr) + return -EINVAL; + if (p_ptr->publ.connected) { + peer->ref = port_peerport(p_ptr); + peer->node = port_peernode(p_ptr); + res = TIPC_OK; + } else + res = -ENOTCONN; + port_unlock(p_ptr); + return res; +} + +int tipc_ref_valid(u32 ref) +{ + /* Works irrespective of type */ + return !!ref_deref(ref); +} + + +/* + * port_recv_sections(): Concatenate and deliver sectioned + * message for this node. + */ + +int port_recv_sections(struct port *sender, unsigned int num_sect, + struct iovec const *msg_sect) +{ + struct sk_buff *buf; + int res; + + res = msg_build(&sender->publ.phdr, msg_sect, num_sect, + MAX_MSG_SIZE, !sender->user_port, &buf); + if (likely(buf)) + port_recv_msg(buf); + return res; +} + +/** + * tipc_send - send message sections on connection + */ + +int tipc_send(u32 ref, unsigned int num_sect, struct iovec const *msg_sect) +{ + struct port *p_ptr; + u32 destnode; + int res; + + p_ptr = port_deref(ref); + if (!p_ptr || !p_ptr->publ.connected) + return -EINVAL; + + p_ptr->publ.congested = 1; + if (!port_congested(p_ptr)) { + destnode = port_peernode(p_ptr); + if (likely(destnode != tipc_own_addr)) + res = link_send_sections_fast(p_ptr, msg_sect, num_sect, + destnode); + else + res = port_recv_sections(p_ptr, num_sect, msg_sect); + + if (likely(res != -ELINKCONG)) { + port_incr_out_seqno(p_ptr); + p_ptr->publ.congested = 0; + p_ptr->sent++; + return res; + } + } + if (port_unreliable(p_ptr)) { + p_ptr->publ.congested = 0; + /* Just calculate msg length and return */ + return msg_calc_data_size(msg_sect, num_sect); + } + return -ELINKCONG; +} + +/** + * tipc_send_buf - send message buffer on connection + */ + +int tipc_send_buf(u32 ref, struct sk_buff *buf, unsigned int dsz) +{ + struct port *p_ptr; + struct tipc_msg *msg; + u32 destnode; + u32 hsz; + u32 sz; + u32 res; + + p_ptr = port_deref(ref); + if (!p_ptr || !p_ptr->publ.connected) + return -EINVAL; + + msg = &p_ptr->publ.phdr; + hsz = msg_hdr_sz(msg); + sz = hsz + dsz; + msg_set_size(msg, sz); + if (skb_cow(buf, hsz)) + return -ENOMEM; + + skb_push(buf, hsz); + memcpy(buf->data, (unchar *)msg, hsz); + destnode = msg_destnode(msg); + p_ptr->publ.congested = 1; + if (!port_congested(p_ptr)) { + if (likely(destnode != tipc_own_addr)) + res = tipc_send_buf_fast(buf, destnode); + else { + port_recv_msg(buf); + res = sz; + } + if (likely(res != -ELINKCONG)) { + port_incr_out_seqno(p_ptr); + p_ptr->sent++; + p_ptr->publ.congested = 0; + return res; + } + } + if (port_unreliable(p_ptr)) { + p_ptr->publ.congested = 0; + return dsz; + } + return -ELINKCONG; +} + +/** + * tipc_forward2name - forward message sections to port name + */ + +int tipc_forward2name(u32 ref, + struct tipc_name const *name, + u32 domain, + u32 num_sect, + struct iovec const *msg_sect, + struct tipc_portid const *orig, + unsigned int importance) +{ + struct port *p_ptr; + struct tipc_msg *msg; + u32 destnode = domain; + u32 destport = 0; + int res; + + p_ptr = port_deref(ref); + if (!p_ptr || p_ptr->publ.connected) + return -EINVAL; + + msg = &p_ptr->publ.phdr; + msg_set_type(msg, TIPC_NAMED_MSG); + msg_set_orignode(msg, orig->node); + msg_set_origport(msg, orig->ref); + msg_set_hdr_sz(msg, LONG_H_SIZE); + msg_set_nametype(msg, name->type); + msg_set_nameinst(msg, name->instance); + msg_set_lookup_scope(msg, addr_scope(domain)); + if (importance <= TIPC_CRITICAL_IMPORTANCE) + msg_set_importance(msg,importance); + destport = nametbl_translate(name->type, name->instance, &destnode); + msg_set_destnode(msg, destnode); + msg_set_destport(msg, destport); + + if (likely(destport || destnode)) { + p_ptr->sent++; + if (likely(destnode == tipc_own_addr)) + return port_recv_sections(p_ptr, num_sect, msg_sect); + res = link_send_sections_fast(p_ptr, msg_sect, num_sect, + destnode); + if (likely(res != -ELINKCONG)) + return res; + if (port_unreliable(p_ptr)) { + /* Just calculate msg length and return */ + return msg_calc_data_size(msg_sect, num_sect); + } + return -ELINKCONG; + } + return port_reject_sections(p_ptr, msg, msg_sect, num_sect, + TIPC_ERR_NO_NAME); +} + +/** + * tipc_send2name - send message sections to port name + */ + +int tipc_send2name(u32 ref, + struct tipc_name const *name, + unsigned int domain, + unsigned int num_sect, + struct iovec const *msg_sect) +{ + struct tipc_portid orig; + + orig.ref = ref; + orig.node = tipc_own_addr; + return tipc_forward2name(ref, name, domain, num_sect, msg_sect, &orig, + TIPC_PORT_IMPORTANCE); +} + +/** + * tipc_forward_buf2name - forward message buffer to port name + */ + +int tipc_forward_buf2name(u32 ref, + struct tipc_name const *name, + u32 domain, + struct sk_buff *buf, + unsigned int dsz, + struct tipc_portid const *orig, + unsigned int importance) +{ + struct port *p_ptr; + struct tipc_msg *msg; + u32 destnode = domain; + u32 destport = 0; + int res; + + p_ptr = (struct port *)ref_deref(ref); + if (!p_ptr || p_ptr->publ.connected) + return -EINVAL; + + msg = &p_ptr->publ.phdr; + if (importance <= TIPC_CRITICAL_IMPORTANCE) + msg_set_importance(msg, importance); + msg_set_type(msg, TIPC_NAMED_MSG); + msg_set_orignode(msg, orig->node); + msg_set_origport(msg, orig->ref); + msg_set_nametype(msg, name->type); + msg_set_nameinst(msg, name->instance); + msg_set_lookup_scope(msg, addr_scope(domain)); + msg_set_hdr_sz(msg, LONG_H_SIZE); + msg_set_size(msg, LONG_H_SIZE + dsz); + destport = nametbl_translate(name->type, name->instance, &destnode); + msg_set_destnode(msg, destnode); + msg_set_destport(msg, destport); + msg_dbg(msg, "forw2name ==> "); + if (skb_cow(buf, LONG_H_SIZE)) + return -ENOMEM; + skb_push(buf, LONG_H_SIZE); + memcpy(buf->data, (unchar *)msg, LONG_H_SIZE); + msg_dbg(buf_msg(buf),"PREP:"); + if (likely(destport || destnode)) { + p_ptr->sent++; + if (destnode == tipc_own_addr) + return port_recv_msg(buf); + res = tipc_send_buf_fast(buf, destnode); + if (likely(res != -ELINKCONG)) + return res; + if (port_unreliable(p_ptr)) + return dsz; + return -ELINKCONG; + } + return tipc_reject_msg(buf, TIPC_ERR_NO_NAME); +} + +/** + * tipc_send_buf2name - send message buffer to port name + */ + +int tipc_send_buf2name(u32 ref, + struct tipc_name const *dest, + u32 domain, + struct sk_buff *buf, + unsigned int dsz) +{ + struct tipc_portid orig; + + orig.ref = ref; + orig.node = tipc_own_addr; + return tipc_forward_buf2name(ref, dest, domain, buf, dsz, &orig, + TIPC_PORT_IMPORTANCE); +} + +/** + * tipc_forward2port - forward message sections to port identity + */ + +int tipc_forward2port(u32 ref, + struct tipc_portid const *dest, + unsigned int num_sect, + struct iovec const *msg_sect, + struct tipc_portid const *orig, + unsigned int importance) +{ + struct port *p_ptr; + struct tipc_msg *msg; + int res; + + p_ptr = port_deref(ref); + if (!p_ptr || p_ptr->publ.connected) + return -EINVAL; + + msg = &p_ptr->publ.phdr; + msg_set_type(msg, TIPC_DIRECT_MSG); + msg_set_orignode(msg, orig->node); + msg_set_origport(msg, orig->ref); + msg_set_destnode(msg, dest->node); + msg_set_destport(msg, dest->ref); + msg_set_hdr_sz(msg, DIR_MSG_H_SIZE); + if (importance <= TIPC_CRITICAL_IMPORTANCE) + msg_set_importance(msg, importance); + p_ptr->sent++; + if (dest->node == tipc_own_addr) + return port_recv_sections(p_ptr, num_sect, msg_sect); + res = link_send_sections_fast(p_ptr, msg_sect, num_sect, dest->node); + if (likely(res != -ELINKCONG)) + return res; + if (port_unreliable(p_ptr)) { + /* Just calculate msg length and return */ + return msg_calc_data_size(msg_sect, num_sect); + } + return -ELINKCONG; +} + +/** + * tipc_send2port - send message sections to port identity + */ + +int tipc_send2port(u32 ref, + struct tipc_portid const *dest, + unsigned int num_sect, + struct iovec const *msg_sect) +{ + struct tipc_portid orig; + + orig.ref = ref; + orig.node = tipc_own_addr; + return tipc_forward2port(ref, dest, num_sect, msg_sect, &orig, + TIPC_PORT_IMPORTANCE); +} + +/** + * tipc_forward_buf2port - forward message buffer to port identity + */ +int tipc_forward_buf2port(u32 ref, + struct tipc_portid const *dest, + struct sk_buff *buf, + unsigned int dsz, + struct tipc_portid const *orig, + unsigned int importance) +{ + struct port *p_ptr; + struct tipc_msg *msg; + int res; + + p_ptr = (struct port *)ref_deref(ref); + if (!p_ptr || p_ptr->publ.connected) + return -EINVAL; + + msg = &p_ptr->publ.phdr; + msg_set_type(msg, TIPC_DIRECT_MSG); + msg_set_orignode(msg, orig->node); + msg_set_origport(msg, orig->ref); + msg_set_destnode(msg, dest->node); + msg_set_destport(msg, dest->ref); + msg_set_hdr_sz(msg, DIR_MSG_H_SIZE); + if (importance <= TIPC_CRITICAL_IMPORTANCE) + msg_set_importance(msg, importance); + msg_set_size(msg, DIR_MSG_H_SIZE + dsz); + if (skb_cow(buf, DIR_MSG_H_SIZE)) + return -ENOMEM; + + skb_push(buf, DIR_MSG_H_SIZE); + memcpy(buf->data, (unchar *)msg, DIR_MSG_H_SIZE); + msg_dbg(msg, "buf2port: "); + p_ptr->sent++; + if (dest->node == tipc_own_addr) + return port_recv_msg(buf); + res = tipc_send_buf_fast(buf, dest->node); + if (likely(res != -ELINKCONG)) + return res; + if (port_unreliable(p_ptr)) + return dsz; + return -ELINKCONG; +} + +/** + * tipc_send_buf2port - send message buffer to port identity + */ + +int tipc_send_buf2port(u32 ref, + struct tipc_portid const *dest, + struct sk_buff *buf, + unsigned int dsz) +{ + struct tipc_portid orig; + + orig.ref = ref; + orig.node = tipc_own_addr; + return tipc_forward_buf2port(ref, dest, buf, dsz, &orig, + TIPC_PORT_IMPORTANCE); +} + diff --git a/net/tipc/port.h b/net/tipc/port.h new file mode 100644 index 00000000000..e829a99d3b7 --- /dev/null +++ b/net/tipc/port.h @@ -0,0 +1,209 @@ +/* + * net/tipc/port.h: Include file for TIPC port code + * + * Copyright (c) 1994-2006, Ericsson AB + * Copyright (c) 2004-2005, Wind River Systems + * All rights reserved. + * + * Redistribution and use in source and binary forms, with or without + * modification, are permitted provided that the following conditions are met: + * + * 1. Redistributions of source code must retain the above copyright + * notice, this list of conditions and the following disclaimer. + * 2. Redistributions in binary form must reproduce the above copyright + * notice, this list of conditions and the following disclaimer in the + * documentation and/or other materials provided with the distribution. + * 3. Neither the names of the copyright holders nor the names of its + * contributors may be used to endorse or promote products derived from + * this software without specific prior written permission. + * + * Alternatively, this software may be distributed under the terms of the + * GNU General Public License ("GPL") version 2 as published by the Free + * Software Foundation. + * + * THIS SOFTWARE IS PROVIDED BY THE COPYRIGHT HOLDERS AND CONTRIBUTORS "AS IS" + * AND ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT LIMITED TO, THE + * IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR A PARTICULAR PURPOSE + * ARE DISCLAIMED. IN NO EVENT SHALL THE COPYRIGHT OWNER OR CONTRIBUTORS BE + * LIABLE FOR ANY DIRECT, INDIRECT, INCIDENTAL, SPECIAL, EXEMPLARY, OR + * CONSEQUENTIAL DAMAGES (INCLUDING, BUT NOT LIMITED TO, PROCUREMENT OF + * SUBSTITUTE GOODS OR SERVICES; LOSS OF USE, DATA, OR PROFITS; OR BUSINESS + * INTERRUPTION) HOWEVER CAUSED AND ON ANY THEORY OF LIABILITY, WHETHER IN + * CONTRACT, STRICT LIABILITY, OR TORT (INCLUDING NEGLIGENCE OR OTHERWISE) + * ARISING IN ANY WAY OUT OF THE USE OF THIS SOFTWARE, EVEN IF ADVISED OF THE + * POSSIBILITY OF SUCH DAMAGE. + */ + +#ifndef _TIPC_PORT_H +#define _TIPC_PORT_H + +#include <net/tipc/tipc_port.h> +#include "ref.h" +#include "net.h" +#include "msg.h" +#include "dbg.h" +#include "node_subscr.h" + +/** + * struct user_port - TIPC user port (used with native API) + * @user_ref: id of user who created user port + * @usr_handle: user-specified field + * @ref: object reference to associated TIPC port + * <various callback routines> + * @uport_list: adjacent user ports in list of ports held by user + */ + +struct user_port { + u32 user_ref; + void *usr_handle; + u32 ref; + tipc_msg_err_event err_cb; + tipc_named_msg_err_event named_err_cb; + tipc_conn_shutdown_event conn_err_cb; + tipc_msg_event msg_cb; + tipc_named_msg_event named_msg_cb; + tipc_conn_msg_event conn_msg_cb; + tipc_continue_event continue_event_cb; + struct list_head uport_list; +}; + +/** + * struct port - TIPC port structure + * @publ: TIPC port info available to privileged users + * @port_list: adjacent ports in TIPC's global list of ports + * @dispatcher: ptr to routine which handles received messages + * @wakeup: ptr to routine to call when port is no longer congested + * @user_port: ptr to user port associated with port (if any) + * @wait_list: adjacent ports in list of ports waiting on link congestion + * @congested_link: ptr to congested link port is waiting on + * @waiting_pkts: + * @sent: + * @acked: + * @publications: list of publications for port + * @pub_count: total # of publications port has made during its lifetime + * @max_pkt: maximum packet size "hint" used when building messages sent by port + * @probing_state: + * @probing_interval: + * @last_in_seqno: + * @timer_ref: + * @subscription: "node down" subscription used to terminate failed connections + */ + +struct port { + struct tipc_port publ; + struct list_head port_list; + u32 (*dispatcher)(struct tipc_port *, struct sk_buff *); + void (*wakeup)(struct tipc_port *); + struct user_port *user_port; + struct list_head wait_list; + struct link *congested_link; + u32 waiting_pkts; + u32 sent; + u32 acked; + struct list_head publications; + u32 pub_count; + u32 max_pkt; + u32 probing_state; + u32 probing_interval; + u32 last_in_seqno; + struct timer_list timer; + struct node_subscr subscription; +}; + +extern spinlock_t port_list_lock; +struct port_list; + +int port_recv_sections(struct port *p_ptr, u32 num_sect, + struct iovec const *msg_sect); +int port_reject_sections(struct port *p_ptr, struct tipc_msg *hdr, + struct iovec const *msg_sect, u32 num_sect, + int err); +struct sk_buff *port_get_ports(void); +struct sk_buff *port_show_stats(const void *req_tlv_area, int req_tlv_space); +void port_recv_proto_msg(struct sk_buff *buf); +void port_recv_mcast(struct sk_buff *buf, struct port_list *dp); +void port_reinit(void); + +/** + * port_lock - lock port instance referred to and return its pointer + */ + +static inline struct port *port_lock(u32 ref) +{ + return (struct port *)ref_lock(ref); +} + +/** + * port_unlock - unlock a port instance + * + * Can use pointer instead of ref_unlock() since port is already locked. + */ + +static inline void port_unlock(struct port *p_ptr) +{ + spin_unlock_bh(p_ptr->publ.lock); +} + +static inline struct port* port_deref(u32 ref) +{ + return (struct port *)ref_deref(ref); +} + +static inline u32 peer_port(struct port *p_ptr) +{ + return msg_destport(&p_ptr->publ.phdr); +} + +static inline u32 peer_node(struct port *p_ptr) +{ + return msg_destnode(&p_ptr->publ.phdr); +} + +static inline int port_congested(struct port *p_ptr) +{ + return((p_ptr->sent - p_ptr->acked) >= (TIPC_FLOW_CONTROL_WIN * 2)); +} + +/** + * port_recv_msg - receive message from lower layer and deliver to port user + */ + +static inline int port_recv_msg(struct sk_buff *buf) +{ + struct port *p_ptr; + struct tipc_msg *msg = buf_msg(buf); + u32 destport = msg_destport(msg); + u32 dsz = msg_data_sz(msg); + u32 err; + + /* forward unresolved named message */ + if (unlikely(!destport)) { + net_route_msg(buf); + return dsz; + } + + /* validate destination & pass to port, otherwise reject message */ + p_ptr = port_lock(destport); + if (likely(p_ptr)) { + if (likely(p_ptr->publ.connected)) { + if ((unlikely(msg_origport(msg) != peer_port(p_ptr))) || + (unlikely(msg_orignode(msg) != peer_node(p_ptr))) || + (unlikely(!msg_connected(msg)))) { + err = TIPC_ERR_NO_PORT; + port_unlock(p_ptr); + goto reject; + } + } + err = p_ptr->dispatcher(&p_ptr->publ, buf); + port_unlock(p_ptr); + if (likely(!err)) + return dsz; + } else { + err = TIPC_ERR_NO_PORT; + } +reject: + dbg("port->rejecting, err = %x..\n",err); + return tipc_reject_msg(buf, err); +} + +#endif diff --git a/net/tipc/ref.c b/net/tipc/ref.c new file mode 100644 index 00000000000..944093fe246 --- /dev/null +++ b/net/tipc/ref.c @@ -0,0 +1,189 @@ +/* + * net/tipc/ref.c: TIPC object registry code + * + * Copyright (c) 1991-2006, Ericsson AB + * Copyright (c) 2004-2005, Wind River Systems + * All rights reserved. + * + * Redistribution and use in source and binary forms, with or without + * modification, are permitted provided that the following conditions are met: + * + * 1. Redistributions of source code must retain the above copyright + * notice, this list of conditions and the following disclaimer. + * 2. Redistributions in binary form must reproduce the above copyright + * notice, this list of conditions and the following disclaimer in the + * documentation and/or other materials provided with the distribution. + * 3. Neither the names of the copyright holders nor the names of its + * contributors may be used to endorse or promote products derived from + * this software without specific prior written permission. + * + * Alternatively, this software may be distributed under the terms of the + * GNU General Public License ("GPL") version 2 as published by the Free + * Software Foundation. + * + * THIS SOFTWARE IS PROVIDED BY THE COPYRIGHT HOLDERS AND CONTRIBUTORS "AS IS" + * AND ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT LIMITED TO, THE + * IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR A PARTICULAR PURPOSE + * ARE DISCLAIMED. IN NO EVENT SHALL THE COPYRIGHT OWNER OR CONTRIBUTORS BE + * LIABLE FOR ANY DIRECT, INDIRECT, INCIDENTAL, SPECIAL, EXEMPLARY, OR + * CONSEQUENTIAL DAMAGES (INCLUDING, BUT NOT LIMITED TO, PROCUREMENT OF + * SUBSTITUTE GOODS OR SERVICES; LOSS OF USE, DATA, OR PROFITS; OR BUSINESS + * INTERRUPTION) HOWEVER CAUSED AND ON ANY THEORY OF LIABILITY, WHETHER IN + * CONTRACT, STRICT LIABILITY, OR TORT (INCLUDING NEGLIGENCE OR OTHERWISE) + * ARISING IN ANY WAY OUT OF THE USE OF THIS SOFTWARE, EVEN IF ADVISED OF THE + * POSSIBILITY OF SUCH DAMAGE. + */ + +#include "core.h" +#include "ref.h" +#include "port.h" +#include "subscr.h" +#include "name_distr.h" +#include "name_table.h" +#include "config.h" +#include "discover.h" +#include "bearer.h" +#include "node.h" +#include "bcast.h" + +/* + * Object reference table consists of 2**N entries. + * + * A used entry has object ptr != 0, reference == XXXX|own index + * (XXXX changes each time entry is acquired) + * A free entry has object ptr == 0, reference == YYYY|next free index + * (YYYY is one more than last used XXXX) + * + * Free list is initially chained from entry (2**N)-1 to entry 1. + * Entry 0 is not used to allow index 0 to indicate the end of the free list. + * + * Note: Any accidental reference of the form XXXX|0--0 won't match entry 0 + * because entry 0's reference field has the form XXXX|1--1. + */ + +struct ref_table ref_table = { 0 }; + +rwlock_t reftbl_lock = RW_LOCK_UNLOCKED; + +/** + * ref_table_init - create reference table for objects + */ + +int ref_table_init(u32 requested_size, u32 start) +{ + struct reference *table; + u32 sz = 1 << 4; + u32 index_mask; + int i; + + while (sz < requested_size) { + sz <<= 1; + } + table = (struct reference *)vmalloc(sz * sizeof(struct reference)); + if (table == NULL) + return -ENOMEM; + + write_lock_bh(&reftbl_lock); + index_mask = sz - 1; + for (i = sz - 1; i >= 0; i--) { + table[i].object = 0; + table[i].lock = SPIN_LOCK_UNLOCKED; + table[i].data.next_plus_upper = (start & ~index_mask) + i - 1; + } + ref_table.entries = table; + ref_table.index_mask = index_mask; + ref_table.first_free = sz - 1; + ref_table.last_free = 1; + write_unlock_bh(&reftbl_lock); + return TIPC_OK; +} + +/** + * ref_table_stop - destroy reference table for objects + */ + +void ref_table_stop(void) +{ + if (!ref_table.entries) + return; + + vfree(ref_table.entries); + ref_table.entries = 0; +} + +/** + * ref_acquire - create reference to an object + * + * Return a unique reference value which can be translated back to the pointer + * 'object' at a later time. Also, pass back a pointer to the lock protecting + * the object, but without locking it. + */ + +u32 ref_acquire(void *object, spinlock_t **lock) +{ + struct reference *entry; + u32 index; + u32 index_mask; + u32 next_plus_upper; + u32 reference = 0; + + assert(ref_table.entries && object); + + write_lock_bh(&reftbl_lock); + if (ref_table.first_free) { + index = ref_table.first_free; + entry = &(ref_table.entries[index]); + index_mask = ref_table.index_mask; + /* take lock in case a previous user of entry still holds it */ + spin_lock_bh(&entry->lock); + next_plus_upper = entry->data.next_plus_upper; + ref_table.first_free = next_plus_upper & index_mask; + reference = (next_plus_upper & ~index_mask) + index; + entry->data.reference = reference; + entry->object = object; + if (lock != 0) + *lock = &entry->lock; + spin_unlock_bh(&entry->lock); + } + write_unlock_bh(&reftbl_lock); + return reference; +} + +/** + * ref_discard - invalidate references to an object + * + * Disallow future references to an object and free up the entry for re-use. + * Note: The entry's spin_lock may still be busy after discard + */ + +void ref_discard(u32 ref) +{ + struct reference *entry; + u32 index; + u32 index_mask; + + assert(ref_table.entries); + assert(ref != 0); + + write_lock_bh(&reftbl_lock); + index_mask = ref_table.index_mask; + index = ref & index_mask; + entry = &(ref_table.entries[index]); + assert(entry->object != 0); + assert(entry->data.reference == ref); + + /* mark entry as unused */ + entry->object = 0; + if (ref_table.first_free == 0) + ref_table.first_free = index; + else + /* next_plus_upper is always XXXX|0--0 for last free entry */ + ref_table.entries[ref_table.last_free].data.next_plus_upper + |= index; + ref_table.last_free = index; + + /* increment upper bits of entry to invalidate subsequent references */ + entry->data.next_plus_upper = (ref & ~index_mask) + (index_mask + 1); + write_unlock_bh(&reftbl_lock); +} + diff --git a/net/tipc/ref.h b/net/tipc/ref.h new file mode 100644 index 00000000000..429cde57228 --- /dev/null +++ b/net/tipc/ref.h @@ -0,0 +1,131 @@ +/* + * net/tipc/ref.h: Include file for TIPC object registry code + * + * Copyright (c) 1991-2006, Ericsson AB + * Copyright (c) 2005, Wind River Systems + * All rights reserved. + * + * Redistribution and use in source and binary forms, with or without + * modification, are permitted provided that the following conditions are met: + * + * 1. Redistributions of source code must retain the above copyright + * notice, this list of conditions and the following disclaimer. + * 2. Redistributions in binary form must reproduce the above copyright + * notice, this list of conditions and the following disclaimer in the + * documentation and/or other materials provided with the distribution. + * 3. Neither the names of the copyright holders nor the names of its + * contributors may be used to endorse or promote products derived from + * this software without specific prior written permission. + * + * Alternatively, this software may be distributed under the terms of the + * GNU General Public License ("GPL") version 2 as published by the Free + * Software Foundation. + * + * THIS SOFTWARE IS PROVIDED BY THE COPYRIGHT HOLDERS AND CONTRIBUTORS "AS IS" + * AND ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT LIMITED TO, THE + * IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR A PARTICULAR PURPOSE + * ARE DISCLAIMED. IN NO EVENT SHALL THE COPYRIGHT OWNER OR CONTRIBUTORS BE + * LIABLE FOR ANY DIRECT, INDIRECT, INCIDENTAL, SPECIAL, EXEMPLARY, OR + * CONSEQUENTIAL DAMAGES (INCLUDING, BUT NOT LIMITED TO, PROCUREMENT OF + * SUBSTITUTE GOODS OR SERVICES; LOSS OF USE, DATA, OR PROFITS; OR BUSINESS + * INTERRUPTION) HOWEVER CAUSED AND ON ANY THEORY OF LIABILITY, WHETHER IN + * CONTRACT, STRICT LIABILITY, OR TORT (INCLUDING NEGLIGENCE OR OTHERWISE) + * ARISING IN ANY WAY OUT OF THE USE OF THIS SOFTWARE, EVEN IF ADVISED OF THE + * POSSIBILITY OF SUCH DAMAGE. + */ + +#ifndef _TIPC_REF_H +#define _TIPC_REF_H + +/** + * struct reference - TIPC object reference entry + * @object: pointer to object associated with reference entry + * @lock: spinlock controlling access to object + * @data: reference value associated with object (or link to next unused entry) + */ + +struct reference { + void *object; + spinlock_t lock; + union { + u32 next_plus_upper; + u32 reference; + } data; +}; + +/** + * struct ref_table - table of TIPC object reference entries + * @entries: pointer to array of reference entries + * @index_mask: bitmask for array index portion of reference values + * @first_free: array index of first unused object reference entry + * @last_free: array index of last unused object reference entry + */ + +struct ref_table { + struct reference *entries; + u32 index_mask; + u32 first_free; + u32 last_free; +}; + +extern struct ref_table ref_table; + +int ref_table_init(u32 requested_size, u32 start); +void ref_table_stop(void); + +u32 ref_acquire(void *object, spinlock_t **lock); +void ref_discard(u32 ref); + + +/** + * ref_lock - lock referenced object and return pointer to it + */ + +static inline void *ref_lock(u32 ref) +{ + if (likely(ref_table.entries)) { + struct reference *r = + &ref_table.entries[ref & ref_table.index_mask]; + + spin_lock_bh(&r->lock); + if (likely(r->data.reference == ref)) + return r->object; + spin_unlock_bh(&r->lock); + } + return 0; +} + +/** + * ref_unlock - unlock referenced object + */ + +static inline void ref_unlock(u32 ref) +{ + if (likely(ref_table.entries)) { + struct reference *r = + &ref_table.entries[ref & ref_table.index_mask]; + + if (likely(r->data.reference == ref)) + spin_unlock_bh(&r->lock); + else + err("ref_unlock() invoked using obsolete reference\n"); + } +} + +/** + * ref_deref - return pointer referenced object (without locking it) + */ + +static inline void *ref_deref(u32 ref) +{ + if (likely(ref_table.entries)) { + struct reference *r = + &ref_table.entries[ref & ref_table.index_mask]; + + if (likely(r->data.reference == ref)) + return r->object; + } + return 0; +} + +#endif diff --git a/net/tipc/socket.c b/net/tipc/socket.c new file mode 100644 index 00000000000..d21f8c0cd25 --- /dev/null +++ b/net/tipc/socket.c @@ -0,0 +1,1726 @@ +/* + * net/tipc/socket.c: TIPC socket API + * + * Copyright (c) 2001-2006, Ericsson AB + * Copyright (c) 2004-2005, Wind River Systems + * All rights reserved. + * + * Redistribution and use in source and binary forms, with or without + * modification, are permitted provided that the following conditions are met: + * + * 1. Redistributions of source code must retain the above copyright + * notice, this list of conditions and the following disclaimer. + * 2. Redistributions in binary form must reproduce the above copyright + * notice, this list of conditions and the following disclaimer in the + * documentation and/or other materials provided with the distribution. + * 3. Neither the names of the copyright holders nor the names of its + * contributors may be used to endorse or promote products derived from + * this software without specific prior written permission. + * + * Alternatively, this software may be distributed under the terms of the + * GNU General Public License ("GPL") version 2 as published by the Free + * Software Foundation. + * + * THIS SOFTWARE IS PROVIDED BY THE COPYRIGHT HOLDERS AND CONTRIBUTORS "AS IS" + * AND ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT LIMITED TO, THE + * IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR A PARTICULAR PURPOSE + * ARE DISCLAIMED. IN NO EVENT SHALL THE COPYRIGHT OWNER OR CONTRIBUTORS BE + * LIABLE FOR ANY DIRECT, INDIRECT, INCIDENTAL, SPECIAL, EXEMPLARY, OR + * CONSEQUENTIAL DAMAGES (INCLUDING, BUT NOT LIMITED TO, PROCUREMENT OF + * SUBSTITUTE GOODS OR SERVICES; LOSS OF USE, DATA, OR PROFITS; OR BUSINESS + * INTERRUPTION) HOWEVER CAUSED AND ON ANY THEORY OF LIABILITY, WHETHER IN + * CONTRACT, STRICT LIABILITY, OR TORT (INCLUDING NEGLIGENCE OR OTHERWISE) + * ARISING IN ANY WAY OUT OF THE USE OF THIS SOFTWARE, EVEN IF ADVISED OF THE + * POSSIBILITY OF SUCH DAMAGE. + */ + +#include <linux/module.h> +#include <linux/types.h> +#include <linux/net.h> +#include <linux/socket.h> +#include <linux/errno.h> +#include <linux/mm.h> +#include <linux/slab.h> +#include <linux/poll.h> +#include <linux/version.h> +#include <linux/fcntl.h> +#include <linux/version.h> +#include <asm/semaphore.h> +#include <asm/string.h> +#include <asm/atomic.h> +#include <net/sock.h> + +#include <linux/tipc.h> +#include <linux/tipc_config.h> +#include <net/tipc/tipc_msg.h> +#include <net/tipc/tipc_port.h> + +#include "core.h" + +#define SS_LISTENING -1 /* socket is listening */ +#define SS_READY -2 /* socket is connectionless */ + +#define OVERLOAD_LIMIT_BASE 5000 + +struct tipc_sock { + struct sock sk; + struct tipc_port *p; + struct semaphore sem; +}; + +#define tipc_sk(sk) ((struct tipc_sock*)sk) + +static u32 dispatch(struct tipc_port *tport, struct sk_buff *buf); +static void wakeupdispatch(struct tipc_port *tport); + +static struct proto_ops packet_ops; +static struct proto_ops stream_ops; +static struct proto_ops msg_ops; + +static struct proto tipc_proto; + +static int sockets_enabled = 0; + +static atomic_t tipc_queue_size = ATOMIC_INIT(0); + + +/* + * sock_lock(): Lock a port/socket pair. lock_sock() can + * not be used here, since the same lock must protect ports + * with non-socket interfaces. + * See net.c for description of locking policy. + */ +static inline void sock_lock(struct tipc_sock* tsock) +{ + spin_lock_bh(tsock->p->lock); +} + +/* + * sock_unlock(): Unlock a port/socket pair + */ +static inline void sock_unlock(struct tipc_sock* tsock) +{ + spin_unlock_bh(tsock->p->lock); +} + +/** + * pollmask - determine the current set of poll() events for a socket + * @sock: socket structure + * + * TIPC sets the returned events as follows: + * a) POLLRDNORM and POLLIN are set if the socket's receive queue is non-empty + * or if a connection-oriented socket is does not have an active connection + * (i.e. a read operation will not block). + * b) POLLOUT is set except when a socket's connection has been terminated + * (i.e. a write operation will not block). + * c) POLLHUP is set when a socket's connection has been terminated. + * + * IMPORTANT: The fact that a read or write operation will not block does NOT + * imply that the operation will succeed! + * + * Returns pollmask value + */ + +static inline u32 pollmask(struct socket *sock) +{ + u32 mask; + + if ((skb_queue_len(&sock->sk->sk_receive_queue) != 0) || + (sock->state == SS_UNCONNECTED) || + (sock->state == SS_DISCONNECTING)) + mask = (POLLRDNORM | POLLIN); + else + mask = 0; + + if (sock->state == SS_DISCONNECTING) + mask |= POLLHUP; + else + mask |= POLLOUT; + + return mask; +} + + +/** + * advance_queue - discard first buffer in queue + * @tsock: TIPC socket + */ + +static inline void advance_queue(struct tipc_sock *tsock) +{ + sock_lock(tsock); + buf_discard(skb_dequeue(&tsock->sk.sk_receive_queue)); + sock_unlock(tsock); + atomic_dec(&tipc_queue_size); +} + +/** + * tipc_create - create a TIPC socket + * @sock: pre-allocated socket structure + * @protocol: protocol indicator (must be 0) + * + * This routine creates and attaches a 'struct sock' to the 'struct socket', + * then create and attaches a TIPC port to the 'struct sock' part. + * + * Returns 0 on success, errno otherwise + */ +static int tipc_create(struct socket *sock, int protocol) +{ + struct tipc_sock *tsock; + struct tipc_port *port; + struct sock *sk; + u32 ref; + + if ((sock->type != SOCK_STREAM) && + (sock->type != SOCK_SEQPACKET) && + (sock->type != SOCK_DGRAM) && + (sock->type != SOCK_RDM)) + return -EPROTOTYPE; + + if (unlikely(protocol != 0)) + return -EPROTONOSUPPORT; + + ref = tipc_createport_raw(0, &dispatch, &wakeupdispatch, TIPC_LOW_IMPORTANCE); + if (unlikely(!ref)) + return -ENOMEM; + + sock->state = SS_UNCONNECTED; + + switch (sock->type) { + case SOCK_STREAM: + sock->ops = &stream_ops; + break; + case SOCK_SEQPACKET: + sock->ops = &packet_ops; + break; + case SOCK_DGRAM: + tipc_set_portunreliable(ref, 1); + /* fall through */ + case SOCK_RDM: + tipc_set_portunreturnable(ref, 1); + sock->ops = &msg_ops; + sock->state = SS_READY; + break; + } + + sk = sk_alloc(AF_TIPC, GFP_KERNEL, &tipc_proto, 1); + if (!sk) { + tipc_deleteport(ref); + return -ENOMEM; + } + + sock_init_data(sock, sk); + init_waitqueue_head(sk->sk_sleep); + sk->sk_rcvtimeo = 8 * HZ; /* default connect timeout = 8s */ + + tsock = tipc_sk(sk); + port = tipc_get_port(ref); + + tsock->p = port; + port->usr_handle = tsock; + + init_MUTEX(&tsock->sem); + + dbg("sock_create: %x\n",tsock); + + atomic_inc(&tipc_user_count); + + return 0; +} + +/** + * release - destroy a TIPC socket + * @sock: socket to destroy + * + * This routine cleans up any messages that are still queued on the socket. + * For DGRAM and RDM socket types, all queued messages are rejected. + * For SEQPACKET and STREAM socket types, the first message is rejected + * and any others are discarded. (If the first message on a STREAM socket + * is partially-read, it is discarded and the next one is rejected instead.) + * + * NOTE: Rejected messages are not necessarily returned to the sender! They + * are returned or discarded according to the "destination droppable" setting + * specified for the message by the sender. + * + * Returns 0 on success, errno otherwise + */ + +static int release(struct socket *sock) +{ + struct tipc_sock *tsock = tipc_sk(sock->sk); + struct sock *sk = sock->sk; + int res = TIPC_OK; + struct sk_buff *buf; + + dbg("sock_delete: %x\n",tsock); + if (!tsock) + return 0; + down_interruptible(&tsock->sem); + if (!sock->sk) { + up(&tsock->sem); + return 0; + } + + /* Reject unreceived messages, unless no longer connected */ + + while (sock->state != SS_DISCONNECTING) { + sock_lock(tsock); + buf = skb_dequeue(&sk->sk_receive_queue); + if (!buf) + tsock->p->usr_handle = 0; + sock_unlock(tsock); + if (!buf) + break; + if (TIPC_SKB_CB(buf)->handle != msg_data(buf_msg(buf))) + buf_discard(buf); + else + tipc_reject_msg(buf, TIPC_ERR_NO_PORT); + atomic_dec(&tipc_queue_size); + } + + /* Delete TIPC port */ + + res = tipc_deleteport(tsock->p->ref); + sock->sk = NULL; + + /* Discard any remaining messages */ + + while ((buf = skb_dequeue(&sk->sk_receive_queue))) { + buf_discard(buf); + atomic_dec(&tipc_queue_size); + } + + up(&tsock->sem); + + sock_put(sk); + + atomic_dec(&tipc_user_count); + return res; +} + +/** + * bind - associate or disassocate TIPC name(s) with a socket + * @sock: socket structure + * @uaddr: socket address describing name(s) and desired operation + * @uaddr_len: size of socket address data structure + * + * Name and name sequence binding is indicated using a positive scope value; + * a negative scope value unbinds the specified name. Specifying no name + * (i.e. a socket address length of 0) unbinds all names from the socket. + * + * Returns 0 on success, errno otherwise + */ + +static int bind(struct socket *sock, struct sockaddr *uaddr, int uaddr_len) +{ + struct tipc_sock *tsock = tipc_sk(sock->sk); + struct sockaddr_tipc *addr = (struct sockaddr_tipc *)uaddr; + int res; + + if (down_interruptible(&tsock->sem)) + return -ERESTARTSYS; + + if (unlikely(!uaddr_len)) { + res = tipc_withdraw(tsock->p->ref, 0, 0); + goto exit; + } + + if (uaddr_len < sizeof(struct sockaddr_tipc)) { + res = -EINVAL; + goto exit; + } + + if (addr->family != AF_TIPC) { + res = -EAFNOSUPPORT; + goto exit; + } + if (addr->addrtype == TIPC_ADDR_NAME) + addr->addr.nameseq.upper = addr->addr.nameseq.lower; + else if (addr->addrtype != TIPC_ADDR_NAMESEQ) { + res = -EAFNOSUPPORT; + goto exit; + } + + if (addr->scope > 0) + res = tipc_publish(tsock->p->ref, addr->scope, + &addr->addr.nameseq); + else + res = tipc_withdraw(tsock->p->ref, -addr->scope, + &addr->addr.nameseq); +exit: + up(&tsock->sem); + return res; +} + +/** + * get_name - get port ID of socket or peer socket + * @sock: socket structure + * @uaddr: area for returned socket address + * @uaddr_len: area for returned length of socket address + * @peer: 0 to obtain socket name, 1 to obtain peer socket name + * + * Returns 0 on success, errno otherwise + */ + +static int get_name(struct socket *sock, struct sockaddr *uaddr, + int *uaddr_len, int peer) +{ + struct tipc_sock *tsock = tipc_sk(sock->sk); + struct sockaddr_tipc *addr = (struct sockaddr_tipc *)uaddr; + u32 res; + + if (down_interruptible(&tsock->sem)) + return -ERESTARTSYS; + + *uaddr_len = sizeof(*addr); + addr->addrtype = TIPC_ADDR_ID; + addr->family = AF_TIPC; + addr->scope = 0; + if (peer) + res = tipc_peer(tsock->p->ref, &addr->addr.id); + else + res = tipc_ownidentity(tsock->p->ref, &addr->addr.id); + addr->addr.name.domain = 0; + + up(&tsock->sem); + return res; +} + +/** + * poll - read and possibly block on pollmask + * @file: file structure associated with the socket + * @sock: socket for which to calculate the poll bits + * @wait: ??? + * + * Returns the pollmask + */ + +static unsigned int poll(struct file *file, struct socket *sock, + poll_table *wait) +{ + poll_wait(file, sock->sk->sk_sleep, wait); + /* NEED LOCK HERE? */ + return pollmask(sock); +} + +/** + * dest_name_check - verify user is permitted to send to specified port name + * @dest: destination address + * @m: descriptor for message to be sent + * + * Prevents restricted configuration commands from being issued by + * unauthorized users. + * + * Returns 0 if permission is granted, otherwise errno + */ + +static inline int dest_name_check(struct sockaddr_tipc *dest, struct msghdr *m) +{ + struct tipc_cfg_msg_hdr hdr; + + if (likely(dest->addr.name.name.type >= TIPC_RESERVED_TYPES)) + return 0; + if (likely(dest->addr.name.name.type == TIPC_TOP_SRV)) + return 0; + + if (likely(dest->addr.name.name.type != TIPC_CFG_SRV)) + return -EACCES; + + if (copy_from_user(&hdr, m->msg_iov[0].iov_base, sizeof(hdr))) + return -EFAULT; + if ((ntohs(hdr.tcm_type) & 0xC000) & (!capable(CAP_NET_ADMIN))) + return -EACCES; + + return 0; +} + +/** + * send_msg - send message in connectionless manner + * @iocb: (unused) + * @sock: socket structure + * @m: message to send + * @total_len: (unused) + * + * Message must have an destination specified explicitly. + * Used for SOCK_RDM and SOCK_DGRAM messages, + * and for 'SYN' messages on SOCK_SEQPACKET and SOCK_STREAM connections. + * (Note: 'SYN+' is prohibited on SOCK_STREAM.) + * + * Returns the number of bytes sent on success, or errno otherwise + */ + +static int send_msg(struct kiocb *iocb, struct socket *sock, + struct msghdr *m, size_t total_len) +{ + struct tipc_sock *tsock = tipc_sk(sock->sk); + struct sockaddr_tipc *dest = (struct sockaddr_tipc *)m->msg_name; + struct sk_buff *buf; + int needs_conn; + int res = -EINVAL; + + if (unlikely(!dest)) + return -EDESTADDRREQ; + if (unlikely(dest->family != AF_TIPC)) + return -EINVAL; + + needs_conn = (sock->state != SS_READY); + if (unlikely(needs_conn)) { + if (sock->state == SS_LISTENING) + return -EPIPE; + if (sock->state != SS_UNCONNECTED) + return -EISCONN; + if ((tsock->p->published) || + ((sock->type == SOCK_STREAM) && (total_len != 0))) + return -EOPNOTSUPP; + } + + if (down_interruptible(&tsock->sem)) + return -ERESTARTSYS; + + if (needs_conn) { + + /* Abort any pending connection attempts (very unlikely) */ + + while ((buf = skb_dequeue(&sock->sk->sk_receive_queue))) { + tipc_reject_msg(buf, TIPC_ERR_NO_PORT); + atomic_dec(&tipc_queue_size); + } + + sock->state = SS_CONNECTING; + } + + do { + if (dest->addrtype == TIPC_ADDR_NAME) { + if ((res = dest_name_check(dest, m))) + goto exit; + res = tipc_send2name(tsock->p->ref, + &dest->addr.name.name, + dest->addr.name.domain, + m->msg_iovlen, + m->msg_iov); + } + else if (dest->addrtype == TIPC_ADDR_ID) { + res = tipc_send2port(tsock->p->ref, + &dest->addr.id, + m->msg_iovlen, + m->msg_iov); + } + else if (dest->addrtype == TIPC_ADDR_MCAST) { + if (needs_conn) { + res = -EOPNOTSUPP; + goto exit; + } + if ((res = dest_name_check(dest, m))) + goto exit; + res = tipc_multicast(tsock->p->ref, + &dest->addr.nameseq, + 0, + m->msg_iovlen, + m->msg_iov); + } + if (likely(res != -ELINKCONG)) { +exit: + up(&tsock->sem); + return res; + } + if (m->msg_flags & MSG_DONTWAIT) { + res = -EWOULDBLOCK; + goto exit; + } + if (wait_event_interruptible(*sock->sk->sk_sleep, + !tsock->p->congested)) { + res = -ERESTARTSYS; + goto exit; + } + } while (1); +} + +/** + * send_packet - send a connection-oriented message + * @iocb: (unused) + * @sock: socket structure + * @m: message to send + * @total_len: (unused) + * + * Used for SOCK_SEQPACKET messages and SOCK_STREAM data. + * + * Returns the number of bytes sent on success, or errno otherwise + */ + +static int send_packet(struct kiocb *iocb, struct socket *sock, + struct msghdr *m, size_t total_len) +{ + struct tipc_sock *tsock = tipc_sk(sock->sk); + struct sockaddr_tipc *dest = (struct sockaddr_tipc *)m->msg_name; + int res; + + /* Handle implied connection establishment */ + + if (unlikely(dest)) + return send_msg(iocb, sock, m, total_len); + + if (down_interruptible(&tsock->sem)) { + return -ERESTARTSYS; + } + + if (unlikely(sock->state != SS_CONNECTED)) { + if (sock->state == SS_DISCONNECTING) + res = -EPIPE; + else + res = -ENOTCONN; + goto exit; + } + + do { + res = tipc_send(tsock->p->ref, m->msg_iovlen, m->msg_iov); + if (likely(res != -ELINKCONG)) { +exit: + up(&tsock->sem); + return res; + } + if (m->msg_flags & MSG_DONTWAIT) { + res = -EWOULDBLOCK; + goto exit; + } + if (wait_event_interruptible(*sock->sk->sk_sleep, + !tsock->p->congested)) { + res = -ERESTARTSYS; + goto exit; + } + } while (1); +} + +/** + * send_stream - send stream-oriented data + * @iocb: (unused) + * @sock: socket structure + * @m: data to send + * @total_len: total length of data to be sent + * + * Used for SOCK_STREAM data. + * + * Returns the number of bytes sent on success, or errno otherwise + */ + + +static int send_stream(struct kiocb *iocb, struct socket *sock, + struct msghdr *m, size_t total_len) +{ + struct msghdr my_msg; + struct iovec my_iov; + struct iovec *curr_iov; + int curr_iovlen; + char __user *curr_start; + int curr_left; + int bytes_to_send; + int res; + + if (likely(total_len <= TIPC_MAX_USER_MSG_SIZE)) + return send_packet(iocb, sock, m, total_len); + + /* Can only send large data streams if already connected */ + + if (unlikely(sock->state != SS_CONNECTED)) { + if (sock->state == SS_DISCONNECTING) + return -EPIPE; + else + return -ENOTCONN; + } + + /* + * Send each iovec entry using one or more messages + * + * Note: This algorithm is good for the most likely case + * (i.e. one large iovec entry), but could be improved to pass sets + * of small iovec entries into send_packet(). + */ + + my_msg = *m; + curr_iov = my_msg.msg_iov; + curr_iovlen = my_msg.msg_iovlen; + my_msg.msg_iov = &my_iov; + my_msg.msg_iovlen = 1; + + while (curr_iovlen--) { + curr_start = curr_iov->iov_base; + curr_left = curr_iov->iov_len; + + while (curr_left) { + bytes_to_send = (curr_left < TIPC_MAX_USER_MSG_SIZE) + ? curr_left : TIPC_MAX_USER_MSG_SIZE; + my_iov.iov_base = curr_start; + my_iov.iov_len = bytes_to_send; + if ((res = send_packet(iocb, sock, &my_msg, 0)) < 0) + return res; + curr_left -= bytes_to_send; + curr_start += bytes_to_send; + } + + curr_iov++; + } + + return total_len; +} + +/** + * auto_connect - complete connection setup to a remote port + * @sock: socket structure + * @tsock: TIPC-specific socket structure + * @msg: peer's response message + * + * Returns 0 on success, errno otherwise + */ + +static int auto_connect(struct socket *sock, struct tipc_sock *tsock, + struct tipc_msg *msg) +{ + struct tipc_portid peer; + + if (msg_errcode(msg)) { + sock->state = SS_DISCONNECTING; + return -ECONNREFUSED; + } + + peer.ref = msg_origport(msg); + peer.node = msg_orignode(msg); + tipc_connect2port(tsock->p->ref, &peer); + tipc_set_portimportance(tsock->p->ref, msg_importance(msg)); + sock->state = SS_CONNECTED; + return 0; +} + +/** + * set_orig_addr - capture sender's address for received message + * @m: descriptor for message info + * @msg: received message header + * + * Note: Address is not captured if not requested by receiver. + */ + +static inline void set_orig_addr(struct msghdr *m, struct tipc_msg *msg) +{ + struct sockaddr_tipc *addr = (struct sockaddr_tipc *)m->msg_name; + + if (addr) { + addr->family = AF_TIPC; + addr->addrtype = TIPC_ADDR_ID; + addr->addr.id.ref = msg_origport(msg); + addr->addr.id.node = msg_orignode(msg); + addr->addr.name.domain = 0; /* could leave uninitialized */ + addr->scope = 0; /* could leave uninitialized */ + m->msg_namelen = sizeof(struct sockaddr_tipc); + } +} + +/** + * anc_data_recv - optionally capture ancillary data for received message + * @m: descriptor for message info + * @msg: received message header + * @tport: TIPC port associated with message + * + * Note: Ancillary data is not captured if not requested by receiver. + * + * Returns 0 if successful, otherwise errno + */ + +static inline int anc_data_recv(struct msghdr *m, struct tipc_msg *msg, + struct tipc_port *tport) +{ + u32 anc_data[3]; + u32 err; + u32 dest_type; + int res; + + if (likely(m->msg_controllen == 0)) + return 0; + + /* Optionally capture errored message object(s) */ + + err = msg ? msg_errcode(msg) : 0; + if (unlikely(err)) { + anc_data[0] = err; + anc_data[1] = msg_data_sz(msg); + if ((res = put_cmsg(m, SOL_SOCKET, TIPC_ERRINFO, 8, anc_data))) + return res; + if (anc_data[1] && + (res = put_cmsg(m, SOL_SOCKET, TIPC_RETDATA, anc_data[1], + msg_data(msg)))) + return res; + } + + /* Optionally capture message destination object */ + + dest_type = msg ? msg_type(msg) : TIPC_DIRECT_MSG; + switch (dest_type) { + case TIPC_NAMED_MSG: + anc_data[0] = msg_nametype(msg); + anc_data[1] = msg_namelower(msg); + anc_data[2] = msg_namelower(msg); + break; + case TIPC_MCAST_MSG: + anc_data[0] = msg_nametype(msg); + anc_data[1] = msg_namelower(msg); + anc_data[2] = msg_nameupper(msg); + break; + case TIPC_CONN_MSG: + anc_data[0] = tport->conn_type; + anc_data[1] = tport->conn_instance; + anc_data[2] = tport->conn_instance; + break; + default: + anc_data[0] = 0; + } + if (anc_data[0] && + (res = put_cmsg(m, SOL_SOCKET, TIPC_DESTNAME, 12, anc_data))) + return res; + + return 0; +} + +/** + * recv_msg - receive packet-oriented message + * @iocb: (unused) + * @m: descriptor for message info + * @buf_len: total size of user buffer area + * @flags: receive flags + * + * Used for SOCK_DGRAM, SOCK_RDM, and SOCK_SEQPACKET messages. + * If the complete message doesn't fit in user area, truncate it. + * + * Returns size of returned message data, errno otherwise + */ + +static int recv_msg(struct kiocb *iocb, struct socket *sock, + struct msghdr *m, size_t buf_len, int flags) +{ + struct tipc_sock *tsock = tipc_sk(sock->sk); + struct sk_buff *buf; + struct tipc_msg *msg; + unsigned int q_len; + unsigned int sz; + u32 err; + int res; + + /* Currently doesn't support receiving into multiple iovec entries */ + + if (m->msg_iovlen != 1) + return -EOPNOTSUPP; + + /* Catch invalid receive attempts */ + + if (unlikely(!buf_len)) + return -EINVAL; + + if (sock->type == SOCK_SEQPACKET) { + if (unlikely(sock->state == SS_UNCONNECTED)) + return -ENOTCONN; + if (unlikely((sock->state == SS_DISCONNECTING) && + (skb_queue_len(&sock->sk->sk_receive_queue) == 0))) + return -ENOTCONN; + } + + /* Look for a message in receive queue; wait if necessary */ + + if (unlikely(down_interruptible(&tsock->sem))) + return -ERESTARTSYS; + +restart: + if (unlikely((skb_queue_len(&sock->sk->sk_receive_queue) == 0) && + (flags & MSG_DONTWAIT))) { + res = -EWOULDBLOCK; + goto exit; + } + + if ((res = wait_event_interruptible( + *sock->sk->sk_sleep, + ((q_len = skb_queue_len(&sock->sk->sk_receive_queue)) || + (sock->state == SS_DISCONNECTING))) )) { + goto exit; + } + + /* Catch attempt to receive on an already terminated connection */ + /* [THIS CHECK MAY OVERLAP WITH AN EARLIER CHECK] */ + + if (!q_len) { + res = -ENOTCONN; + goto exit; + } + + /* Get access to first message in receive queue */ + + buf = skb_peek(&sock->sk->sk_receive_queue); + msg = buf_msg(buf); + sz = msg_data_sz(msg); + err = msg_errcode(msg); + + /* Complete connection setup for an implied connect */ + + if (unlikely(sock->state == SS_CONNECTING)) { + if ((res = auto_connect(sock, tsock, msg))) + goto exit; + } + + /* Discard an empty non-errored message & try again */ + + if ((!sz) && (!err)) { + advance_queue(tsock); + goto restart; + } + + /* Capture sender's address (optional) */ + + set_orig_addr(m, msg); + + /* Capture ancillary data (optional) */ + + if ((res = anc_data_recv(m, msg, tsock->p))) + goto exit; + + /* Capture message data (if valid) & compute return value (always) */ + + if (!err) { + if (unlikely(buf_len < sz)) { + sz = buf_len; + m->msg_flags |= MSG_TRUNC; + } + if (unlikely(copy_to_user(m->msg_iov->iov_base, msg_data(msg), + sz))) { + res = -EFAULT; + goto exit; + } + res = sz; + } else { + if ((sock->state == SS_READY) || + ((err == TIPC_CONN_SHUTDOWN) || m->msg_control)) + res = 0; + else + res = -ECONNRESET; + } + + /* Consume received message (optional) */ + + if (likely(!(flags & MSG_PEEK))) { + if (unlikely(++tsock->p->conn_unacked >= TIPC_FLOW_CONTROL_WIN)) + tipc_acknowledge(tsock->p->ref, tsock->p->conn_unacked); + advance_queue(tsock); + } +exit: + up(&tsock->sem); + return res; +} + +/** + * recv_stream - receive stream-oriented data + * @iocb: (unused) + * @m: descriptor for message info + * @buf_len: total size of user buffer area + * @flags: receive flags + * + * Used for SOCK_STREAM messages only. If not enough data is available + * will optionally wait for more; never truncates data. + * + * Returns size of returned message data, errno otherwise + */ + +static int recv_stream(struct kiocb *iocb, struct socket *sock, + struct msghdr *m, size_t buf_len, int flags) +{ + struct tipc_sock *tsock = tipc_sk(sock->sk); + struct sk_buff *buf; + struct tipc_msg *msg; + unsigned int q_len; + unsigned int sz; + int sz_to_copy; + int sz_copied = 0; + int needed; + char *crs = m->msg_iov->iov_base; + unsigned char *buf_crs; + u32 err; + int res; + + /* Currently doesn't support receiving into multiple iovec entries */ + + if (m->msg_iovlen != 1) + return -EOPNOTSUPP; + + /* Catch invalid receive attempts */ + + if (unlikely(!buf_len)) + return -EINVAL; + + if (unlikely(sock->state == SS_DISCONNECTING)) { + if (skb_queue_len(&sock->sk->sk_receive_queue) == 0) + return -ENOTCONN; + } else if (unlikely(sock->state != SS_CONNECTED)) + return -ENOTCONN; + + /* Look for a message in receive queue; wait if necessary */ + + if (unlikely(down_interruptible(&tsock->sem))) + return -ERESTARTSYS; + +restart: + if (unlikely((skb_queue_len(&sock->sk->sk_receive_queue) == 0) && + (flags & MSG_DONTWAIT))) { + res = (sz_copied == 0) ? -EWOULDBLOCK : 0; + goto exit; + } + + if ((res = wait_event_interruptible( + *sock->sk->sk_sleep, + ((q_len = skb_queue_len(&sock->sk->sk_receive_queue)) || + (sock->state == SS_DISCONNECTING))) )) { + goto exit; + } + + /* Catch attempt to receive on an already terminated connection */ + /* [THIS CHECK MAY OVERLAP WITH AN EARLIER CHECK] */ + + if (!q_len) { + res = -ENOTCONN; + goto exit; + } + + /* Get access to first message in receive queue */ + + buf = skb_peek(&sock->sk->sk_receive_queue); + msg = buf_msg(buf); + sz = msg_data_sz(msg); + err = msg_errcode(msg); + + /* Discard an empty non-errored message & try again */ + + if ((!sz) && (!err)) { + advance_queue(tsock); + goto restart; + } + + /* Optionally capture sender's address & ancillary data of first msg */ + + if (sz_copied == 0) { + set_orig_addr(m, msg); + if ((res = anc_data_recv(m, msg, tsock->p))) + goto exit; + } + + /* Capture message data (if valid) & compute return value (always) */ + + if (!err) { + buf_crs = (unsigned char *)(TIPC_SKB_CB(buf)->handle); + sz = buf->tail - buf_crs; + + needed = (buf_len - sz_copied); + sz_to_copy = (sz <= needed) ? sz : needed; + if (unlikely(copy_to_user(crs, buf_crs, sz_to_copy))) { + res = -EFAULT; + goto exit; + } + sz_copied += sz_to_copy; + + if (sz_to_copy < sz) { + if (!(flags & MSG_PEEK)) + TIPC_SKB_CB(buf)->handle = buf_crs + sz_to_copy; + goto exit; + } + + crs += sz_to_copy; + } else { + if (sz_copied != 0) + goto exit; /* can't add error msg to valid data */ + + if ((err == TIPC_CONN_SHUTDOWN) || m->msg_control) + res = 0; + else + res = -ECONNRESET; + } + + /* Consume received message (optional) */ + + if (likely(!(flags & MSG_PEEK))) { + if (unlikely(++tsock->p->conn_unacked >= TIPC_FLOW_CONTROL_WIN)) + tipc_acknowledge(tsock->p->ref, tsock->p->conn_unacked); + advance_queue(tsock); + } + + /* Loop around if more data is required */ + + if ((sz_copied < buf_len) /* didn't get all requested data */ + && (flags & MSG_WAITALL) /* ... and need to wait for more */ + && (!(flags & MSG_PEEK)) /* ... and aren't just peeking at data */ + && (!err) /* ... and haven't reached a FIN */ + ) + goto restart; + +exit: + up(&tsock->sem); + return res ? res : sz_copied; +} + +/** + * queue_overloaded - test if queue overload condition exists + * @queue_size: current size of queue + * @base: nominal maximum size of queue + * @msg: message to be added to queue + * + * Returns 1 if queue is currently overloaded, 0 otherwise + */ + +static int queue_overloaded(u32 queue_size, u32 base, struct tipc_msg *msg) +{ + u32 threshold; + u32 imp = msg_importance(msg); + + if (imp == TIPC_LOW_IMPORTANCE) + threshold = base; + else if (imp == TIPC_MEDIUM_IMPORTANCE) + threshold = base * 2; + else if (imp == TIPC_HIGH_IMPORTANCE) + threshold = base * 100; + else + return 0; + + if (msg_connected(msg)) + threshold *= 4; + + return (queue_size > threshold); +} + +/** + * async_disconnect - wrapper function used to disconnect port + * @portref: TIPC port reference (passed as pointer-sized value) + */ + +static void async_disconnect(unsigned long portref) +{ + tipc_disconnect((u32)portref); +} + +/** + * dispatch - handle arriving message + * @tport: TIPC port that received message + * @buf: message + * + * Called with port locked. Must not take socket lock to avoid deadlock risk. + * + * Returns TIPC error status code (TIPC_OK if message is not to be rejected) + */ + +static u32 dispatch(struct tipc_port *tport, struct sk_buff *buf) +{ + struct tipc_msg *msg = buf_msg(buf); + struct tipc_sock *tsock = (struct tipc_sock *)tport->usr_handle; + struct socket *sock; + u32 recv_q_len; + + /* Reject message if socket is closing */ + + if (!tsock) + return TIPC_ERR_NO_PORT; + + /* Reject message if it is wrong sort of message for socket */ + + /* + * WOULD IT BE BETTER TO JUST DISCARD THESE MESSAGES INSTEAD? + * "NO PORT" ISN'T REALLY THE RIGHT ERROR CODE, AND THERE MAY + * BE SECURITY IMPLICATIONS INHERENT IN REJECTING INVALID TRAFFIC + */ + sock = tsock->sk.sk_socket; + if (sock->state == SS_READY) { + if (msg_connected(msg)) { + msg_dbg(msg, "dispatch filter 1\n"); + return TIPC_ERR_NO_PORT; + } + } else { + if (msg_mcast(msg)) { + msg_dbg(msg, "dispatch filter 2\n"); + return TIPC_ERR_NO_PORT; + } + if (sock->state == SS_CONNECTED) { + if (!msg_connected(msg)) { + msg_dbg(msg, "dispatch filter 3\n"); + return TIPC_ERR_NO_PORT; + } + } + else if (sock->state == SS_CONNECTING) { + if (!msg_connected(msg) && (msg_errcode(msg) == 0)) { + msg_dbg(msg, "dispatch filter 4\n"); + return TIPC_ERR_NO_PORT; + } + } + else if (sock->state == SS_LISTENING) { + if (msg_connected(msg) || msg_errcode(msg)) { + msg_dbg(msg, "dispatch filter 5\n"); + return TIPC_ERR_NO_PORT; + } + } + else if (sock->state == SS_DISCONNECTING) { + msg_dbg(msg, "dispatch filter 6\n"); + return TIPC_ERR_NO_PORT; + } + else /* (sock->state == SS_UNCONNECTED) */ { + if (msg_connected(msg) || msg_errcode(msg)) { + msg_dbg(msg, "dispatch filter 7\n"); + return TIPC_ERR_NO_PORT; + } + } + } + + /* Reject message if there isn't room to queue it */ + + if (unlikely((u32)atomic_read(&tipc_queue_size) > + OVERLOAD_LIMIT_BASE)) { + if (queue_overloaded(atomic_read(&tipc_queue_size), + OVERLOAD_LIMIT_BASE, msg)) + return TIPC_ERR_OVERLOAD; + } + recv_q_len = skb_queue_len(&tsock->sk.sk_receive_queue); + if (unlikely(recv_q_len > (OVERLOAD_LIMIT_BASE / 2))) { + if (queue_overloaded(recv_q_len, + OVERLOAD_LIMIT_BASE / 2, msg)) + return TIPC_ERR_OVERLOAD; + } + + /* Initiate connection termination for an incoming 'FIN' */ + + if (unlikely(msg_errcode(msg) && (sock->state == SS_CONNECTED))) { + sock->state = SS_DISCONNECTING; + /* Note: Use signal since port lock is already taken! */ + k_signal((Handler)async_disconnect, tport->ref); + } + + /* Enqueue message (finally!) */ + + msg_dbg(msg,"<DISP<: "); + TIPC_SKB_CB(buf)->handle = msg_data(msg); + atomic_inc(&tipc_queue_size); + skb_queue_tail(&sock->sk->sk_receive_queue, buf); + + wake_up_interruptible(sock->sk->sk_sleep); + return TIPC_OK; +} + +/** + * wakeupdispatch - wake up port after congestion + * @tport: port to wakeup + * + * Called with port lock on. + */ + +static void wakeupdispatch(struct tipc_port *tport) +{ + struct tipc_sock *tsock = (struct tipc_sock *)tport->usr_handle; + + wake_up_interruptible(tsock->sk.sk_sleep); +} + +/** + * connect - establish a connection to another TIPC port + * @sock: socket structure + * @dest: socket address for destination port + * @destlen: size of socket address data structure + * @flags: (unused) + * + * Returns 0 on success, errno otherwise + */ + +static int connect(struct socket *sock, struct sockaddr *dest, int destlen, + int flags) +{ + struct tipc_sock *tsock = tipc_sk(sock->sk); + struct sockaddr_tipc *dst = (struct sockaddr_tipc *)dest; + struct msghdr m = {0,}; + struct sk_buff *buf; + struct tipc_msg *msg; + int res; + + /* For now, TIPC does not allow use of connect() with DGRAM or RDM types */ + + if (sock->state == SS_READY) + return -EOPNOTSUPP; + + /* MOVE THE REST OF THIS ERROR CHECKING TO send_msg()? */ + if (sock->state == SS_LISTENING) + return -EOPNOTSUPP; + if (sock->state == SS_CONNECTING) + return -EALREADY; + if (sock->state != SS_UNCONNECTED) + return -EISCONN; + + if ((dst->family != AF_TIPC) || + ((dst->addrtype != TIPC_ADDR_NAME) && (dst->addrtype != TIPC_ADDR_ID))) + return -EINVAL; + + /* Send a 'SYN-' to destination */ + + m.msg_name = dest; + if ((res = send_msg(0, sock, &m, 0)) < 0) { + sock->state = SS_DISCONNECTING; + return res; + } + + if (down_interruptible(&tsock->sem)) + return -ERESTARTSYS; + + /* Wait for destination's 'ACK' response */ + + res = wait_event_interruptible_timeout(*sock->sk->sk_sleep, + skb_queue_len(&sock->sk->sk_receive_queue), + sock->sk->sk_rcvtimeo); + buf = skb_peek(&sock->sk->sk_receive_queue); + if (res > 0) { + msg = buf_msg(buf); + res = auto_connect(sock, tsock, msg); + if (!res) { + if (dst->addrtype == TIPC_ADDR_NAME) { + tsock->p->conn_type = dst->addr.name.name.type; + tsock->p->conn_instance = dst->addr.name.name.instance; + } + if (!msg_data_sz(msg)) + advance_queue(tsock); + } + } else { + if (res == 0) { + res = -ETIMEDOUT; + } else + { /* leave "res" unchanged */ } + sock->state = SS_DISCONNECTING; + } + + up(&tsock->sem); + return res; +} + +/** + * listen - allow socket to listen for incoming connections + * @sock: socket structure + * @len: (unused) + * + * Returns 0 on success, errno otherwise + */ + +static int listen(struct socket *sock, int len) +{ + /* REQUIRES SOCKET LOCKING OF SOME SORT? */ + + if (sock->state == SS_READY) + return -EOPNOTSUPP; + if (sock->state != SS_UNCONNECTED) + return -EINVAL; + sock->state = SS_LISTENING; + return 0; +} + +/** + * accept - wait for connection request + * @sock: listening socket + * @newsock: new socket that is to be connected + * @flags: file-related flags associated with socket + * + * Returns 0 on success, errno otherwise + */ + +static int accept(struct socket *sock, struct socket *newsock, int flags) +{ + struct tipc_sock *tsock = tipc_sk(sock->sk); + struct sk_buff *buf; + int res = -EFAULT; + + if (sock->state == SS_READY) + return -EOPNOTSUPP; + if (sock->state != SS_LISTENING) + return -EINVAL; + + if (unlikely((skb_queue_len(&sock->sk->sk_receive_queue) == 0) && + (flags & O_NONBLOCK))) + return -EWOULDBLOCK; + + if (down_interruptible(&tsock->sem)) + return -ERESTARTSYS; + + if (wait_event_interruptible(*sock->sk->sk_sleep, + skb_queue_len(&sock->sk->sk_receive_queue))) { + res = -ERESTARTSYS; + goto exit; + } + buf = skb_peek(&sock->sk->sk_receive_queue); + + res = tipc_create(newsock, 0); + if (!res) { + struct tipc_sock *new_tsock = tipc_sk(newsock->sk); + struct tipc_portid id; + struct tipc_msg *msg = buf_msg(buf); + u32 new_ref = new_tsock->p->ref; + + id.ref = msg_origport(msg); + id.node = msg_orignode(msg); + tipc_connect2port(new_ref, &id); + newsock->state = SS_CONNECTED; + + tipc_set_portimportance(new_ref, msg_importance(msg)); + if (msg_named(msg)) { + new_tsock->p->conn_type = msg_nametype(msg); + new_tsock->p->conn_instance = msg_nameinst(msg); + } + + /* + * Respond to 'SYN-' by discarding it & returning 'ACK'-. + * Respond to 'SYN+' by queuing it on new socket. + */ + + msg_dbg(msg,"<ACC<: "); + if (!msg_data_sz(msg)) { + struct msghdr m = {0,}; + + send_packet(0, newsock, &m, 0); + advance_queue(tsock); + } else { + sock_lock(tsock); + skb_dequeue(&sock->sk->sk_receive_queue); + sock_unlock(tsock); + skb_queue_head(&newsock->sk->sk_receive_queue, buf); + } + } +exit: + up(&tsock->sem); + return res; +} + +/** + * shutdown - shutdown socket connection + * @sock: socket structure + * @how: direction to close (always treated as read + write) + * + * Terminates connection (if necessary), then purges socket's receive queue. + * + * Returns 0 on success, errno otherwise + */ + +static int shutdown(struct socket *sock, int how) +{ + struct tipc_sock* tsock = tipc_sk(sock->sk); + struct sk_buff *buf; + int res; + + /* Could return -EINVAL for an invalid "how", but why bother? */ + + if (down_interruptible(&tsock->sem)) + return -ERESTARTSYS; + + sock_lock(tsock); + + switch (sock->state) { + case SS_CONNECTED: + + /* Send 'FIN+' or 'FIN-' message to peer */ + + sock_unlock(tsock); +restart: + if ((buf = skb_dequeue(&sock->sk->sk_receive_queue))) { + atomic_dec(&tipc_queue_size); + if (TIPC_SKB_CB(buf)->handle != msg_data(buf_msg(buf))) { + buf_discard(buf); + goto restart; + } + tipc_reject_msg(buf, TIPC_CONN_SHUTDOWN); + } + else { + tipc_shutdown(tsock->p->ref); + } + sock_lock(tsock); + + /* fall through */ + + case SS_DISCONNECTING: + + /* Discard any unreceived messages */ + + while ((buf = skb_dequeue(&sock->sk->sk_receive_queue))) { + atomic_dec(&tipc_queue_size); + buf_discard(buf); + } + tsock->p->conn_unacked = 0; + + /* fall through */ + + case SS_CONNECTING: + sock->state = SS_DISCONNECTING; + res = 0; + break; + + default: + res = -ENOTCONN; + } + + sock_unlock(tsock); + + up(&tsock->sem); + return res; +} + +/** + * setsockopt - set socket option + * @sock: socket structure + * @lvl: option level + * @opt: option identifier + * @ov: pointer to new option value + * @ol: length of option value + * + * For stream sockets only, accepts and ignores all IPPROTO_TCP options + * (to ease compatibility). + * + * Returns 0 on success, errno otherwise + */ + +static int setsockopt(struct socket *sock, int lvl, int opt, char *ov, int ol) +{ + struct tipc_sock *tsock = tipc_sk(sock->sk); + u32 value; + int res; + + if ((lvl == IPPROTO_TCP) && (sock->type == SOCK_STREAM)) + return 0; + if (lvl != SOL_TIPC) + return -ENOPROTOOPT; + if (ol < sizeof(value)) + return -EINVAL; + if ((res = get_user(value, (u32 *)ov))) + return res; + + if (down_interruptible(&tsock->sem)) + return -ERESTARTSYS; + + switch (opt) { + case TIPC_IMPORTANCE: + res = tipc_set_portimportance(tsock->p->ref, value); + break; + case TIPC_SRC_DROPPABLE: + if (sock->type != SOCK_STREAM) + res = tipc_set_portunreliable(tsock->p->ref, value); + else + res = -ENOPROTOOPT; + break; + case TIPC_DEST_DROPPABLE: + res = tipc_set_portunreturnable(tsock->p->ref, value); + break; + case TIPC_CONN_TIMEOUT: + sock->sk->sk_rcvtimeo = (value * HZ / 1000); + break; + default: + res = -EINVAL; + } + + up(&tsock->sem); + return res; +} + +/** + * getsockopt - get socket option + * @sock: socket structure + * @lvl: option level + * @opt: option identifier + * @ov: receptacle for option value + * @ol: receptacle for length of option value + * + * For stream sockets only, returns 0 length result for all IPPROTO_TCP options + * (to ease compatibility). + * + * Returns 0 on success, errno otherwise + */ + +static int getsockopt(struct socket *sock, int lvl, int opt, char *ov, int *ol) +{ + struct tipc_sock *tsock = tipc_sk(sock->sk); + int len; + u32 value; + int res; + + if ((lvl == IPPROTO_TCP) && (sock->type == SOCK_STREAM)) + return put_user(0, ol); + if (lvl != SOL_TIPC) + return -ENOPROTOOPT; + if ((res = get_user(len, ol))) + return res; + + if (down_interruptible(&tsock->sem)) + return -ERESTARTSYS; + + switch (opt) { + case TIPC_IMPORTANCE: + res = tipc_portimportance(tsock->p->ref, &value); + break; + case TIPC_SRC_DROPPABLE: + res = tipc_portunreliable(tsock->p->ref, &value); + break; + case TIPC_DEST_DROPPABLE: + res = tipc_portunreturnable(tsock->p->ref, &value); + break; + case TIPC_CONN_TIMEOUT: + value = (sock->sk->sk_rcvtimeo * 1000) / HZ; + break; + default: + res = -EINVAL; + } + + if (res) { + /* "get" failed */ + } + else if (len < sizeof(value)) { + res = -EINVAL; + } + else if ((res = copy_to_user(ov, &value, sizeof(value)))) { + /* couldn't return value */ + } + else { + res = put_user(sizeof(value), ol); + } + + up(&tsock->sem); + return res; +} + +/** + * Placeholders for non-implemented functionality + * + * Returns error code (POSIX-compliant where defined) + */ + +static int ioctl(struct socket *s, u32 cmd, unsigned long arg) +{ + return -EINVAL; +} + +static int no_mmap(struct file *file, struct socket *sock, + struct vm_area_struct *vma) +{ + return -EINVAL; +} +static ssize_t no_sendpage(struct socket *sock, struct page *page, + int offset, size_t size, int flags) +{ + return -EINVAL; +} + +static int no_skpair(struct socket *s1, struct socket *s2) +{ + return -EOPNOTSUPP; +} + +/** + * Protocol switches for the various types of TIPC sockets + */ + +static struct proto_ops msg_ops = { + .owner = THIS_MODULE, + .family = AF_TIPC, + .release = release, + .bind = bind, + .connect = connect, + .socketpair = no_skpair, + .accept = accept, + .getname = get_name, + .poll = poll, + .ioctl = ioctl, + .listen = listen, + .shutdown = shutdown, + .setsockopt = setsockopt, + .getsockopt = getsockopt, + .sendmsg = send_msg, + .recvmsg = recv_msg, + .mmap = no_mmap, + .sendpage = no_sendpage +}; + +static struct proto_ops packet_ops = { + .owner = THIS_MODULE, + .family = AF_TIPC, + .release = release, + .bind = bind, + .connect = connect, + .socketpair = no_skpair, + .accept = accept, + .getname = get_name, + .poll = poll, + .ioctl = ioctl, + .listen = listen, + .shutdown = shutdown, + .setsockopt = setsockopt, + .getsockopt = getsockopt, + .sendmsg = send_packet, + .recvmsg = recv_msg, + .mmap = no_mmap, + .sendpage = no_sendpage +}; + +static struct proto_ops stream_ops = { + .owner = THIS_MODULE, + .family = AF_TIPC, + .release = release, + .bind = bind, + .connect = connect, + .socketpair = no_skpair, + .accept = accept, + .getname = get_name, + .poll = poll, + .ioctl = ioctl, + .listen = listen, + .shutdown = shutdown, + .setsockopt = setsockopt, + .getsockopt = getsockopt, + .sendmsg = send_stream, + .recvmsg = recv_stream, + .mmap = no_mmap, + .sendpage = no_sendpage +}; + +static struct net_proto_family tipc_family_ops = { + .owner = THIS_MODULE, + .family = AF_TIPC, + .create = tipc_create +}; + +static struct proto tipc_proto = { + .name = "TIPC", + .owner = THIS_MODULE, + .obj_size = sizeof(struct tipc_sock) +}; + +/** + * socket_init - initialize TIPC socket interface + * + * Returns 0 on success, errno otherwise + */ +int socket_init(void) +{ + int res; + + res = proto_register(&tipc_proto, 1); + if (res) { + err("Failed to register TIPC protocol type\n"); + goto out; + } + + res = sock_register(&tipc_family_ops); + if (res) { + err("Failed to register TIPC socket type\n"); + proto_unregister(&tipc_proto); + goto out; + } + + sockets_enabled = 1; + out: + return res; +} + +/** + * sock_stop - stop TIPC socket interface + */ +void socket_stop(void) +{ + if (!sockets_enabled) + return; + + sockets_enabled = 0; + sock_unregister(tipc_family_ops.family); + proto_unregister(&tipc_proto); +} + diff --git a/net/tipc/subscr.c b/net/tipc/subscr.c new file mode 100644 index 00000000000..80e219ba527 --- /dev/null +++ b/net/tipc/subscr.c @@ -0,0 +1,527 @@ +/* + * net/tipc/subscr.c: TIPC subscription service + * + * Copyright (c) 2000-2006, Ericsson AB + * Copyright (c) 2005, Wind River Systems + * All rights reserved. + * + * Redistribution and use in source and binary forms, with or without + * modification, are permitted provided that the following conditions are met: + * + * 1. Redistributions of source code must retain the above copyright + * notice, this list of conditions and the following disclaimer. + * 2. Redistributions in binary form must reproduce the above copyright + * notice, this list of conditions and the following disclaimer in the + * documentation and/or other materials provided with the distribution. + * 3. Neither the names of the copyright holders nor the names of its + * contributors may be used to endorse or promote products derived from + * this software without specific prior written permission. + * + * Alternatively, this software may be distributed under the terms of the + * GNU General Public License ("GPL") version 2 as published by the Free + * Software Foundation. + * + * THIS SOFTWARE IS PROVIDED BY THE COPYRIGHT HOLDERS AND CONTRIBUTORS "AS IS" + * AND ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT LIMITED TO, THE + * IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR A PARTICULAR PURPOSE + * ARE DISCLAIMED. IN NO EVENT SHALL THE COPYRIGHT OWNER OR CONTRIBUTORS BE + * LIABLE FOR ANY DIRECT, INDIRECT, INCIDENTAL, SPECIAL, EXEMPLARY, OR + * CONSEQUENTIAL DAMAGES (INCLUDING, BUT NOT LIMITED TO, PROCUREMENT OF + * SUBSTITUTE GOODS OR SERVICES; LOSS OF USE, DATA, OR PROFITS; OR BUSINESS + * INTERRUPTION) HOWEVER CAUSED AND ON ANY THEORY OF LIABILITY, WHETHER IN + * CONTRACT, STRICT LIABILITY, OR TORT (INCLUDING NEGLIGENCE OR OTHERWISE) + * ARISING IN ANY WAY OUT OF THE USE OF THIS SOFTWARE, EVEN IF ADVISED OF THE + * POSSIBILITY OF SUCH DAMAGE. + */ + +#include "core.h" +#include "dbg.h" +#include "subscr.h" +#include "name_table.h" +#include "ref.h" + +/** + * struct subscriber - TIPC network topology subscriber + * @ref: object reference to subscriber object itself + * @lock: pointer to spinlock controlling access to subscriber object + * @subscriber_list: adjacent subscribers in top. server's list of subscribers + * @subscription_list: list of subscription objects for this subscriber + * @port_ref: object reference to port used to communicate with subscriber + * @swap: indicates if subscriber uses opposite endianness in its messages + */ + +struct subscriber { + u32 ref; + spinlock_t *lock; + struct list_head subscriber_list; + struct list_head subscription_list; + u32 port_ref; + int swap; +}; + +/** + * struct top_srv - TIPC network topology subscription service + * @user_ref: TIPC userid of subscription service + * @setup_port: reference to TIPC port that handles subscription requests + * @subscription_count: number of active subscriptions (not subscribers!) + * @subscriber_list: list of ports subscribing to service + * @lock: spinlock govering access to subscriber list + */ + +struct top_srv { + u32 user_ref; + u32 setup_port; + atomic_t subscription_count; + struct list_head subscriber_list; + spinlock_t lock; +}; + +static struct top_srv topsrv = { 0 }; + +/** + * htohl - convert value to endianness used by destination + * @in: value to convert + * @swap: non-zero if endianness must be reversed + * + * Returns converted value + */ + +static inline u32 htohl(u32 in, int swap) +{ + char *c = (char *)∈ + + return swap ? ((c[3] << 3) + (c[2] << 2) + (c[1] << 1) + c[0]) : in; +} + +/** + * subscr_send_event - send a message containing a tipc_event to the subscriber + */ + +static void subscr_send_event(struct subscription *sub, + u32 found_lower, + u32 found_upper, + u32 event, + u32 port_ref, + u32 node) +{ + struct iovec msg_sect; + + msg_sect.iov_base = (void *)&sub->evt; + msg_sect.iov_len = sizeof(struct tipc_event); + + sub->evt.event = htohl(event, sub->owner->swap); + sub->evt.found_lower = htohl(found_lower, sub->owner->swap); + sub->evt.found_upper = htohl(found_upper, sub->owner->swap); + sub->evt.port.ref = htohl(port_ref, sub->owner->swap); + sub->evt.port.node = htohl(node, sub->owner->swap); + tipc_send(sub->owner->port_ref, 1, &msg_sect); +} + +/** + * subscr_overlap - test for subscription overlap with the given values + * + * Returns 1 if there is overlap, otherwise 0. + */ + +int subscr_overlap(struct subscription *sub, + u32 found_lower, + u32 found_upper) + +{ + if (found_lower < sub->seq.lower) + found_lower = sub->seq.lower; + if (found_upper > sub->seq.upper) + found_upper = sub->seq.upper; + if (found_lower > found_upper) + return 0; + return 1; +} + +/** + * subscr_report_overlap - issue event if there is subscription overlap + * + * Protected by nameseq.lock in name_table.c + */ + +void subscr_report_overlap(struct subscription *sub, + u32 found_lower, + u32 found_upper, + u32 event, + u32 port_ref, + u32 node, + int must) +{ + dbg("Rep overlap %u:%u,%u<->%u,%u\n", sub->seq.type, sub->seq.lower, + sub->seq.upper, found_lower, found_upper); + if (!subscr_overlap(sub, found_lower, found_upper)) + return; + if (!must && (sub->filter != TIPC_SUB_PORTS)) + return; + subscr_send_event(sub, found_lower, found_upper, event, port_ref, node); +} + +/** + * subscr_timeout - subscription timeout has occurred + */ + +static void subscr_timeout(struct subscription *sub) +{ + struct subscriber *subscriber; + u32 subscriber_ref; + + /* Validate subscriber reference (in case subscriber is terminating) */ + + subscriber_ref = sub->owner->ref; + subscriber = (struct subscriber *)ref_lock(subscriber_ref); + if (subscriber == NULL) + return; + + /* Unlink subscription from name table */ + + nametbl_unsubscribe(sub); + + /* Notify subscriber of timeout, then unlink subscription */ + + subscr_send_event(sub, + sub->evt.s.seq.lower, + sub->evt.s.seq.upper, + TIPC_SUBSCR_TIMEOUT, + 0, + 0); + list_del(&sub->subscription_list); + + /* Now destroy subscription */ + + ref_unlock(subscriber_ref); + k_term_timer(&sub->timer); + kfree(sub); + atomic_dec(&topsrv.subscription_count); +} + +/** + * subscr_terminate - terminate communication with a subscriber + * + * Called with subscriber locked. Routine must temporarily release this lock + * to enable subscription timeout routine(s) to finish without deadlocking; + * the lock is then reclaimed to allow caller to release it upon return. + * (This should work even in the unlikely event some other thread creates + * a new object reference in the interim that uses this lock; this routine will + * simply wait for it to be released, then claim it.) + */ + +static void subscr_terminate(struct subscriber *subscriber) +{ + struct subscription *sub; + struct subscription *sub_temp; + + /* Invalidate subscriber reference */ + + ref_discard(subscriber->ref); + spin_unlock_bh(subscriber->lock); + + /* Destroy any existing subscriptions for subscriber */ + + list_for_each_entry_safe(sub, sub_temp, &subscriber->subscription_list, + subscription_list) { + if (sub->timeout != TIPC_WAIT_FOREVER) { + k_cancel_timer(&sub->timer); + k_term_timer(&sub->timer); + } + nametbl_unsubscribe(sub); + list_del(&sub->subscription_list); + dbg("Term: Removed sub %u,%u,%u from subscriber %x list\n", + sub->seq.type, sub->seq.lower, sub->seq.upper, subscriber); + kfree(sub); + atomic_dec(&topsrv.subscription_count); + } + + /* Sever connection to subscriber */ + + tipc_shutdown(subscriber->port_ref); + tipc_deleteport(subscriber->port_ref); + + /* Remove subscriber from topology server's subscriber list */ + + spin_lock_bh(&topsrv.lock); + list_del(&subscriber->subscriber_list); + spin_unlock_bh(&topsrv.lock); + + /* Now destroy subscriber */ + + spin_lock_bh(subscriber->lock); + kfree(subscriber); +} + +/** + * subscr_subscribe - create subscription for subscriber + * + * Called with subscriber locked + */ + +static void subscr_subscribe(struct tipc_subscr *s, + struct subscriber *subscriber) +{ + struct subscription *sub; + + /* Refuse subscription if global limit exceeded */ + + if (atomic_read(&topsrv.subscription_count) >= tipc_max_subscriptions) { + warn("Failed: max %u subscriptions\n", tipc_max_subscriptions); + subscr_terminate(subscriber); + return; + } + + /* Allocate subscription object */ + + sub = kmalloc(sizeof(*sub), GFP_ATOMIC); + if (sub == NULL) { + warn("Memory squeeze; ignoring subscription\n"); + subscr_terminate(subscriber); + return; + } + + /* Determine/update subscriber's endianness */ + + if ((s->filter == TIPC_SUB_PORTS) || (s->filter == TIPC_SUB_SERVICE)) + subscriber->swap = 0; + else + subscriber->swap = 1; + + /* Initialize subscription object */ + + memset(sub, 0, sizeof(*sub)); + sub->seq.type = htohl(s->seq.type, subscriber->swap); + sub->seq.lower = htohl(s->seq.lower, subscriber->swap); + sub->seq.upper = htohl(s->seq.upper, subscriber->swap); + sub->timeout = htohl(s->timeout, subscriber->swap); + sub->filter = htohl(s->filter, subscriber->swap); + if ((((sub->filter != TIPC_SUB_PORTS) + && (sub->filter != TIPC_SUB_SERVICE))) + || (sub->seq.lower > sub->seq.upper)) { + warn("Rejecting illegal subscription %u,%u,%u\n", + sub->seq.type, sub->seq.lower, sub->seq.upper); + kfree(sub); + subscr_terminate(subscriber); + return; + } + memcpy(&sub->evt.s, s, sizeof(struct tipc_subscr)); + INIT_LIST_HEAD(&sub->subscription_list); + INIT_LIST_HEAD(&sub->nameseq_list); + list_add(&sub->subscription_list, &subscriber->subscription_list); + atomic_inc(&topsrv.subscription_count); + if (sub->timeout != TIPC_WAIT_FOREVER) { + k_init_timer(&sub->timer, + (Handler)subscr_timeout, (unsigned long)sub); + k_start_timer(&sub->timer, sub->timeout); + } + sub->owner = subscriber; + nametbl_subscribe(sub); +} + +/** + * subscr_conn_shutdown_event - handle termination request from subscriber + */ + +static void subscr_conn_shutdown_event(void *usr_handle, + u32 portref, + struct sk_buff **buf, + unsigned char const *data, + unsigned int size, + int reason) +{ + struct subscriber *subscriber; + spinlock_t *subscriber_lock; + + subscriber = ref_lock((u32)(unsigned long)usr_handle); + if (subscriber == NULL) + return; + + subscriber_lock = subscriber->lock; + subscr_terminate(subscriber); + spin_unlock_bh(subscriber_lock); +} + +/** + * subscr_conn_msg_event - handle new subscription request from subscriber + */ + +static void subscr_conn_msg_event(void *usr_handle, + u32 port_ref, + struct sk_buff **buf, + const unchar *data, + u32 size) +{ + struct subscriber *subscriber; + spinlock_t *subscriber_lock; + + subscriber = ref_lock((u32)(unsigned long)usr_handle); + if (subscriber == NULL) + return; + + subscriber_lock = subscriber->lock; + if (size != sizeof(struct tipc_subscr)) + subscr_terminate(subscriber); + else + subscr_subscribe((struct tipc_subscr *)data, subscriber); + + spin_unlock_bh(subscriber_lock); +} + +/** + * subscr_named_msg_event - handle request to establish a new subscriber + */ + +static void subscr_named_msg_event(void *usr_handle, + u32 port_ref, + struct sk_buff **buf, + const unchar *data, + u32 size, + u32 importance, + struct tipc_portid const *orig, + struct tipc_name_seq const *dest) +{ + struct subscriber *subscriber; + struct iovec msg_sect = {0, 0}; + spinlock_t *subscriber_lock; + + dbg("subscr_named_msg_event: orig = %x own = %x,\n", + orig->node, tipc_own_addr); + if (size && (size != sizeof(struct tipc_subscr))) { + warn("Received tipc_subscr of invalid size\n"); + return; + } + + /* Create subscriber object */ + + subscriber = kmalloc(sizeof(struct subscriber), GFP_ATOMIC); + if (subscriber == NULL) { + warn("Memory squeeze; ignoring subscriber setup\n"); + return; + } + memset(subscriber, 0, sizeof(struct subscriber)); + INIT_LIST_HEAD(&subscriber->subscription_list); + INIT_LIST_HEAD(&subscriber->subscriber_list); + subscriber->ref = ref_acquire(subscriber, &subscriber->lock); + if (subscriber->ref == 0) { + warn("Failed to acquire subscriber reference\n"); + kfree(subscriber); + return; + } + + /* Establish a connection to subscriber */ + + tipc_createport(topsrv.user_ref, + (void *)(unsigned long)subscriber->ref, + importance, + 0, + 0, + subscr_conn_shutdown_event, + 0, + 0, + subscr_conn_msg_event, + 0, + &subscriber->port_ref); + if (subscriber->port_ref == 0) { + warn("Memory squeeze; failed to create subscription port\n"); + ref_discard(subscriber->ref); + kfree(subscriber); + return; + } + tipc_connect2port(subscriber->port_ref, orig); + + + /* Add subscriber to topology server's subscriber list */ + + ref_lock(subscriber->ref); + spin_lock_bh(&topsrv.lock); + list_add(&subscriber->subscriber_list, &topsrv.subscriber_list); + spin_unlock_bh(&topsrv.lock); + + /* + * Subscribe now if message contains a subscription, + * otherwise send an empty response to complete connection handshaking + */ + + subscriber_lock = subscriber->lock; + if (size) + subscr_subscribe((struct tipc_subscr *)data, subscriber); + else + tipc_send(subscriber->port_ref, 1, &msg_sect); + + spin_unlock_bh(subscriber_lock); +} + +int subscr_start(void) +{ + struct tipc_name_seq seq = {TIPC_TOP_SRV, TIPC_TOP_SRV, TIPC_TOP_SRV}; + int res = -1; + + memset(&topsrv, 0, sizeof (topsrv)); + topsrv.lock = SPIN_LOCK_UNLOCKED; + INIT_LIST_HEAD(&topsrv.subscriber_list); + + spin_lock_bh(&topsrv.lock); + res = tipc_attach(&topsrv.user_ref, 0, 0); + if (res) { + spin_unlock_bh(&topsrv.lock); + return res; + } + + res = tipc_createport(topsrv.user_ref, + 0, + TIPC_CRITICAL_IMPORTANCE, + 0, + 0, + 0, + 0, + subscr_named_msg_event, + 0, + 0, + &topsrv.setup_port); + if (res) + goto failed; + + res = nametbl_publish_rsv(topsrv.setup_port, TIPC_NODE_SCOPE, &seq); + if (res) + goto failed; + + spin_unlock_bh(&topsrv.lock); + return 0; + +failed: + err("Failed to create subscription service\n"); + tipc_detach(topsrv.user_ref); + topsrv.user_ref = 0; + spin_unlock_bh(&topsrv.lock); + return res; +} + +void subscr_stop(void) +{ + struct subscriber *subscriber; + struct subscriber *subscriber_temp; + spinlock_t *subscriber_lock; + + if (topsrv.user_ref) { + tipc_deleteport(topsrv.setup_port); + list_for_each_entry_safe(subscriber, subscriber_temp, + &topsrv.subscriber_list, + subscriber_list) { + ref_lock(subscriber->ref); + subscriber_lock = subscriber->lock; + subscr_terminate(subscriber); + spin_unlock_bh(subscriber_lock); + } + tipc_detach(topsrv.user_ref); + topsrv.user_ref = 0; + } +} + + +int tipc_ispublished(struct tipc_name const *name) +{ + u32 domain = 0; + + return(nametbl_translate(name->type, name->instance,&domain) != 0); +} + diff --git a/net/tipc/subscr.h b/net/tipc/subscr.h new file mode 100644 index 00000000000..ccff4efcb75 --- /dev/null +++ b/net/tipc/subscr.h @@ -0,0 +1,80 @@ +/* + * net/tipc/subscr.h: Include file for TIPC subscription service + * + * Copyright (c) 2003-2006, Ericsson AB + * Copyright (c) 2005, Wind River Systems + * All rights reserved. + * + * Redistribution and use in source and binary forms, with or without + * modification, are permitted provided that the following conditions are met: + * + * 1. Redistributions of source code must retain the above copyright + * notice, this list of conditions and the following disclaimer. + * 2. Redistributions in binary form must reproduce the above copyright + * notice, this list of conditions and the following disclaimer in the + * documentation and/or other materials provided with the distribution. + * 3. Neither the names of the copyright holders nor the names of its + * contributors may be used to endorse or promote products derived from + * this software without specific prior written permission. + * + * Alternatively, this software may be distributed under the terms of the + * GNU General Public License ("GPL") version 2 as published by the Free + * Software Foundation. + * + * THIS SOFTWARE IS PROVIDED BY THE COPYRIGHT HOLDERS AND CONTRIBUTORS "AS IS" + * AND ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT LIMITED TO, THE + * IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR A PARTICULAR PURPOSE + * ARE DISCLAIMED. IN NO EVENT SHALL THE COPYRIGHT OWNER OR CONTRIBUTORS BE + * LIABLE FOR ANY DIRECT, INDIRECT, INCIDENTAL, SPECIAL, EXEMPLARY, OR + * CONSEQUENTIAL DAMAGES (INCLUDING, BUT NOT LIMITED TO, PROCUREMENT OF + * SUBSTITUTE GOODS OR SERVICES; LOSS OF USE, DATA, OR PROFITS; OR BUSINESS + * INTERRUPTION) HOWEVER CAUSED AND ON ANY THEORY OF LIABILITY, WHETHER IN + * CONTRACT, STRICT LIABILITY, OR TORT (INCLUDING NEGLIGENCE OR OTHERWISE) + * ARISING IN ANY WAY OUT OF THE USE OF THIS SOFTWARE, EVEN IF ADVISED OF THE + * POSSIBILITY OF SUCH DAMAGE. + */ + +#ifndef _TIPC_SUBSCR_H +#define _TIPC_SUBSCR_H + +/** + * struct subscription - TIPC network topology subscription object + * @seq: name sequence associated with subscription + * @timeout: duration of subscription (in ms) + * @filter: event filtering to be done for subscription + * @evt: template for events generated by subscription + * @subscription_list: adjacent subscriptions in subscriber's subscription list + * @nameseq_list: adjacent subscriptions in name sequence's subscription list + * @timer_ref: reference to timer governing subscription duration (may be NULL) + * @owner: pointer to subscriber object associated with this subscription + */ + +struct subscription { + struct tipc_name_seq seq; + u32 timeout; + u32 filter; + struct tipc_event evt; + struct list_head subscription_list; + struct list_head nameseq_list; + struct timer_list timer; + struct subscriber *owner; +}; + +int subscr_overlap(struct subscription * sub, + u32 found_lower, + u32 found_upper); + +void subscr_report_overlap(struct subscription * sub, + u32 found_lower, + u32 found_upper, + u32 event, + u32 port_ref, + u32 node, + int must_report); + +int subscr_start(void); + +void subscr_stop(void); + + +#endif diff --git a/net/tipc/user_reg.c b/net/tipc/user_reg.c new file mode 100644 index 00000000000..35ec7dc8211 --- /dev/null +++ b/net/tipc/user_reg.c @@ -0,0 +1,265 @@ +/* + * net/tipc/user_reg.c: TIPC user registry code + * + * Copyright (c) 2000-2006, Ericsson AB + * Copyright (c) 2004-2005, Wind River Systems + * All rights reserved. + * + * Redistribution and use in source and binary forms, with or without + * modification, are permitted provided that the following conditions are met: + * + * 1. Redistributions of source code must retain the above copyright + * notice, this list of conditions and the following disclaimer. + * 2. Redistributions in binary form must reproduce the above copyright + * notice, this list of conditions and the following disclaimer in the + * documentation and/or other materials provided with the distribution. + * 3. Neither the names of the copyright holders nor the names of its + * contributors may be used to endorse or promote products derived from + * this software without specific prior written permission. + * + * Alternatively, this software may be distributed under the terms of the + * GNU General Public License ("GPL") version 2 as published by the Free + * Software Foundation. + * + * THIS SOFTWARE IS PROVIDED BY THE COPYRIGHT HOLDERS AND CONTRIBUTORS "AS IS" + * AND ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT LIMITED TO, THE + * IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR A PARTICULAR PURPOSE + * ARE DISCLAIMED. IN NO EVENT SHALL THE COPYRIGHT OWNER OR CONTRIBUTORS BE + * LIABLE FOR ANY DIRECT, INDIRECT, INCIDENTAL, SPECIAL, EXEMPLARY, OR + * CONSEQUENTIAL DAMAGES (INCLUDING, BUT NOT LIMITED TO, PROCUREMENT OF + * SUBSTITUTE GOODS OR SERVICES; LOSS OF USE, DATA, OR PROFITS; OR BUSINESS + * INTERRUPTION) HOWEVER CAUSED AND ON ANY THEORY OF LIABILITY, WHETHER IN + * CONTRACT, STRICT LIABILITY, OR TORT (INCLUDING NEGLIGENCE OR OTHERWISE) + * ARISING IN ANY WAY OUT OF THE USE OF THIS SOFTWARE, EVEN IF ADVISED OF THE + * POSSIBILITY OF SUCH DAMAGE. + */ + +#include "core.h" +#include "user_reg.h" + +/* + * TIPC user registry keeps track of users of the tipc_port interface. + * + * The registry utilizes an array of "TIPC user" entries; + * a user's ID is the index of their associated array entry. + * Array entry 0 is not used, so userid 0 is not valid; + * TIPC sometimes uses this value to denote an anonymous user. + * The list of free entries is initially chained from last entry to entry 1. + */ + +/** + * struct tipc_user - registered TIPC user info + * @next: index of next free registry entry (or -1 for an allocated entry) + * @callback: ptr to routine to call when TIPC mode changes (NULL if none) + * @usr_handle: user-defined value passed to callback routine + * @ports: list of user ports owned by the user + */ + +struct tipc_user { + int next; + tipc_mode_event callback; + void *usr_handle; + struct list_head ports; +}; + +#define MAX_USERID 64 +#define USER_LIST_SIZE ((MAX_USERID + 1) * sizeof(struct tipc_user)) + +static struct tipc_user *users = 0; +static u32 next_free_user = MAX_USERID + 1; +static spinlock_t reg_lock = SPIN_LOCK_UNLOCKED; + +/** + * reg_init - create TIPC user registry (but don't activate it) + * + * If registry has been pre-initialized it is left "as is". + * NOTE: This routine may be called when TIPC is inactive. + */ + +static int reg_init(void) +{ + u32 i; + + spin_lock_bh(®_lock); + if (!users) { + users = (struct tipc_user *)kmalloc(USER_LIST_SIZE, GFP_ATOMIC); + if (users) { + memset(users, 0, USER_LIST_SIZE); + for (i = 1; i <= MAX_USERID; i++) { + users[i].next = i - 1; + } + next_free_user = MAX_USERID; + } + } + spin_unlock_bh(®_lock); + return users ? TIPC_OK : -ENOMEM; +} + +/** + * reg_callback - inform TIPC user about current operating mode + */ + +static void reg_callback(struct tipc_user *user_ptr) +{ + tipc_mode_event cb; + void *arg; + + spin_lock_bh(®_lock); + cb = user_ptr->callback; + arg = user_ptr->usr_handle; + spin_unlock_bh(®_lock); + + if (cb) + cb(arg, tipc_mode, tipc_own_addr); +} + +/** + * reg_start - activate TIPC user registry + */ + +int reg_start(void) +{ + u32 u; + int res; + + if ((res = reg_init())) + return res; + + for (u = 1; u <= MAX_USERID; u++) { + if (users[u].callback) + k_signal((Handler)reg_callback, + (unsigned long)&users[u]); + } + return TIPC_OK; +} + +/** + * reg_stop - shut down & delete TIPC user registry + */ + +void reg_stop(void) +{ + int id; + + if (!users) + return; + + for (id = 1; id <= MAX_USERID; id++) { + if (users[id].callback) + reg_callback(&users[id]); + } + kfree(users); + users = 0; +} + +/** + * tipc_attach - register a TIPC user + * + * NOTE: This routine may be called when TIPC is inactive. + */ + +int tipc_attach(u32 *userid, tipc_mode_event cb, void *usr_handle) +{ + struct tipc_user *user_ptr; + + if ((tipc_mode == TIPC_NOT_RUNNING) && !cb) + return -ENOPROTOOPT; + if (!users) + reg_init(); + + spin_lock_bh(®_lock); + if (!next_free_user) { + spin_unlock_bh(®_lock); + return -EBUSY; + } + user_ptr = &users[next_free_user]; + *userid = next_free_user; + next_free_user = user_ptr->next; + user_ptr->next = -1; + spin_unlock_bh(®_lock); + + user_ptr->callback = cb; + user_ptr->usr_handle = usr_handle; + INIT_LIST_HEAD(&user_ptr->ports); + atomic_inc(&tipc_user_count); + + if (cb && (tipc_mode != TIPC_NOT_RUNNING)) + k_signal((Handler)reg_callback, (unsigned long)user_ptr); + return TIPC_OK; +} + +/** + * tipc_detach - deregister a TIPC user + */ + +void tipc_detach(u32 userid) +{ + struct tipc_user *user_ptr; + struct list_head ports_temp; + struct user_port *up_ptr, *temp_up_ptr; + + if ((userid == 0) || (userid > MAX_USERID)) + return; + + spin_lock_bh(®_lock); + if ((!users) || (users[userid].next >= 0)) { + spin_unlock_bh(®_lock); + return; + } + + user_ptr = &users[userid]; + user_ptr->callback = NULL; + INIT_LIST_HEAD(&ports_temp); + list_splice(&user_ptr->ports, &ports_temp); + user_ptr->next = next_free_user; + next_free_user = userid; + spin_unlock_bh(®_lock); + + atomic_dec(&tipc_user_count); + + list_for_each_entry_safe(up_ptr, temp_up_ptr, &ports_temp, uport_list) { + tipc_deleteport(up_ptr->ref); + } +} + +/** + * reg_add_port - register a user's driver port + */ + +int reg_add_port(struct user_port *up_ptr) +{ + struct tipc_user *user_ptr; + + if (up_ptr->user_ref == 0) + return TIPC_OK; + if (up_ptr->user_ref > MAX_USERID) + return -EINVAL; + if ((tipc_mode == TIPC_NOT_RUNNING) || !users ) + return -ENOPROTOOPT; + + spin_lock_bh(®_lock); + user_ptr = &users[up_ptr->user_ref]; + list_add(&up_ptr->uport_list, &user_ptr->ports); + spin_unlock_bh(®_lock); + return TIPC_OK; +} + +/** + * reg_remove_port - deregister a user's driver port + */ + +int reg_remove_port(struct user_port *up_ptr) +{ + if (up_ptr->user_ref == 0) + return TIPC_OK; + if (up_ptr->user_ref > MAX_USERID) + return -EINVAL; + if (!users ) + return -ENOPROTOOPT; + + spin_lock_bh(®_lock); + list_del_init(&up_ptr->uport_list); + spin_unlock_bh(®_lock); + return TIPC_OK; +} + diff --git a/net/tipc/user_reg.h b/net/tipc/user_reg.h new file mode 100644 index 00000000000..122ca9be367 --- /dev/null +++ b/net/tipc/user_reg.h @@ -0,0 +1,48 @@ +/* + * net/tipc/user_reg.h: Include file for TIPC user registry code + * + * Copyright (c) 2000-2006, Ericsson AB + * Copyright (c) 2005, Wind River Systems + * All rights reserved. + * + * Redistribution and use in source and binary forms, with or without + * modification, are permitted provided that the following conditions are met: + * + * 1. Redistributions of source code must retain the above copyright + * notice, this list of conditions and the following disclaimer. + * 2. Redistributions in binary form must reproduce the above copyright + * notice, this list of conditions and the following disclaimer in the + * documentation and/or other materials provided with the distribution. + * 3. Neither the names of the copyright holders nor the names of its + * contributors may be used to endorse or promote products derived from + * this software without specific prior written permission. + * + * Alternatively, this software may be distributed under the terms of the + * GNU General Public License ("GPL") version 2 as published by the Free + * Software Foundation. + * + * THIS SOFTWARE IS PROVIDED BY THE COPYRIGHT HOLDERS AND CONTRIBUTORS "AS IS" + * AND ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT LIMITED TO, THE + * IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR A PARTICULAR PURPOSE + * ARE DISCLAIMED. IN NO EVENT SHALL THE COPYRIGHT OWNER OR CONTRIBUTORS BE + * LIABLE FOR ANY DIRECT, INDIRECT, INCIDENTAL, SPECIAL, EXEMPLARY, OR + * CONSEQUENTIAL DAMAGES (INCLUDING, BUT NOT LIMITED TO, PROCUREMENT OF + * SUBSTITUTE GOODS OR SERVICES; LOSS OF USE, DATA, OR PROFITS; OR BUSINESS + * INTERRUPTION) HOWEVER CAUSED AND ON ANY THEORY OF LIABILITY, WHETHER IN + * CONTRACT, STRICT LIABILITY, OR TORT (INCLUDING NEGLIGENCE OR OTHERWISE) + * ARISING IN ANY WAY OUT OF THE USE OF THIS SOFTWARE, EVEN IF ADVISED OF THE + * POSSIBILITY OF SUCH DAMAGE. + */ + +#ifndef _TIPC_USER_REG_H +#define _TIPC_USER_REG_H + +#include "port.h" + +int reg_start(void); +void reg_stop(void); + +int reg_add_port(struct user_port *up_ptr); +int reg_remove_port(struct user_port *up_ptr); + +#endif diff --git a/net/tipc/zone.c b/net/tipc/zone.c new file mode 100644 index 00000000000..4eaef662d56 --- /dev/null +++ b/net/tipc/zone.c @@ -0,0 +1,169 @@ +/* + * net/tipc/zone.c: TIPC zone management routines + * + * Copyright (c) 2000-2006, Ericsson AB + * Copyright (c) 2005, Wind River Systems + * All rights reserved. + * + * Redistribution and use in source and binary forms, with or without + * modification, are permitted provided that the following conditions are met: + * + * 1. Redistributions of source code must retain the above copyright + * notice, this list of conditions and the following disclaimer. + * 2. Redistributions in binary form must reproduce the above copyright + * notice, this list of conditions and the following disclaimer in the + * documentation and/or other materials provided with the distribution. + * 3. Neither the names of the copyright holders nor the names of its + * contributors may be used to endorse or promote products derived from + * this software without specific prior written permission. + * + * Alternatively, this software may be distributed under the terms of the + * GNU General Public License ("GPL") version 2 as published by the Free + * Software Foundation. + * + * THIS SOFTWARE IS PROVIDED BY THE COPYRIGHT HOLDERS AND CONTRIBUTORS "AS IS" + * AND ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT LIMITED TO, THE + * IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR A PARTICULAR PURPOSE + * ARE DISCLAIMED. IN NO EVENT SHALL THE COPYRIGHT OWNER OR CONTRIBUTORS BE + * LIABLE FOR ANY DIRECT, INDIRECT, INCIDENTAL, SPECIAL, EXEMPLARY, OR + * CONSEQUENTIAL DAMAGES (INCLUDING, BUT NOT LIMITED TO, PROCUREMENT OF + * SUBSTITUTE GOODS OR SERVICES; LOSS OF USE, DATA, OR PROFITS; OR BUSINESS + * INTERRUPTION) HOWEVER CAUSED AND ON ANY THEORY OF LIABILITY, WHETHER IN + * CONTRACT, STRICT LIABILITY, OR TORT (INCLUDING NEGLIGENCE OR OTHERWISE) + * ARISING IN ANY WAY OUT OF THE USE OF THIS SOFTWARE, EVEN IF ADVISED OF THE + * POSSIBILITY OF SUCH DAMAGE. + */ + +#include "core.h" +#include "zone.h" +#include "net.h" +#include "addr.h" +#include "node_subscr.h" +#include "cluster.h" +#include "node.h" + +struct _zone *zone_create(u32 addr) +{ + struct _zone *z_ptr = 0; + u32 z_num; + + if (!addr_domain_valid(addr)) + return 0; + + z_ptr = (struct _zone *)kmalloc(sizeof(*z_ptr), GFP_ATOMIC); + if (z_ptr != NULL) { + memset(z_ptr, 0, sizeof(*z_ptr)); + z_num = tipc_zone(addr); + z_ptr->addr = tipc_addr(z_num, 0, 0); + net.zones[z_num] = z_ptr; + } + return z_ptr; +} + +void zone_delete(struct _zone *z_ptr) +{ + u32 c_num; + + if (!z_ptr) + return; + for (c_num = 1; c_num <= tipc_max_clusters; c_num++) { + cluster_delete(z_ptr->clusters[c_num]); + } + kfree(z_ptr); +} + +void zone_attach_cluster(struct _zone *z_ptr, struct cluster *c_ptr) +{ + u32 c_num = tipc_cluster(c_ptr->addr); + + assert(c_ptr->addr); + assert(c_num <= tipc_max_clusters); + assert(z_ptr->clusters[c_num] == 0); + z_ptr->clusters[c_num] = c_ptr; +} + +void zone_remove_as_router(struct _zone *z_ptr, u32 router) +{ + u32 c_num; + + for (c_num = 1; c_num <= tipc_max_clusters; c_num++) { + if (z_ptr->clusters[c_num]) { + cluster_remove_as_router(z_ptr->clusters[c_num], + router); + } + } +} + +void zone_send_external_routes(struct _zone *z_ptr, u32 dest) +{ + u32 c_num; + + for (c_num = 1; c_num <= tipc_max_clusters; c_num++) { + if (z_ptr->clusters[c_num]) { + if (in_own_cluster(z_ptr->addr)) + continue; + cluster_send_ext_routes(z_ptr->clusters[c_num], dest); + } + } +} + +struct node *zone_select_remote_node(struct _zone *z_ptr, u32 addr, u32 ref) +{ + struct cluster *c_ptr; + struct node *n_ptr; + u32 c_num; + + if (!z_ptr) + return 0; + c_ptr = z_ptr->clusters[tipc_cluster(addr)]; + if (!c_ptr) + return 0; + n_ptr = cluster_select_node(c_ptr, ref); + if (n_ptr) + return n_ptr; + + /* Links to any other clusters within this zone ? */ + for (c_num = 1; c_num <= tipc_max_clusters; c_num++) { + c_ptr = z_ptr->clusters[c_num]; + if (!c_ptr) + return 0; + n_ptr = cluster_select_node(c_ptr, ref); + if (n_ptr) + return n_ptr; + } + return 0; +} + +u32 zone_select_router(struct _zone *z_ptr, u32 addr, u32 ref) +{ + struct cluster *c_ptr; + u32 c_num; + u32 router; + + if (!z_ptr) + return 0; + c_ptr = z_ptr->clusters[tipc_cluster(addr)]; + router = c_ptr ? cluster_select_router(c_ptr, ref) : 0; + if (router) + return router; + + /* Links to any other clusters within the zone? */ + for (c_num = 1; c_num <= tipc_max_clusters; c_num++) { + c_ptr = z_ptr->clusters[c_num]; + router = c_ptr ? cluster_select_router(c_ptr, ref) : 0; + if (router) + return router; + } + return 0; +} + + +u32 zone_next_node(u32 addr) +{ + struct cluster *c_ptr = cluster_find(addr); + + if (c_ptr) + return cluster_next_node(c_ptr, addr); + return 0; +} + diff --git a/net/tipc/zone.h b/net/tipc/zone.h new file mode 100644 index 00000000000..4326f78d829 --- /dev/null +++ b/net/tipc/zone.h @@ -0,0 +1,71 @@ +/* + * net/tipc/zone.h: Include file for TIPC zone management routines + * + * Copyright (c) 2000-2006, Ericsson AB + * Copyright (c) 2005, Wind River Systems + * All rights reserved. + * + * Redistribution and use in source and binary forms, with or without + * modification, are permitted provided that the following conditions are met: + * + * 1. Redistributions of source code must retain the above copyright + * notice, this list of conditions and the following disclaimer. + * 2. Redistributions in binary form must reproduce the above copyright + * notice, this list of conditions and the following disclaimer in the + * documentation and/or other materials provided with the distribution. + * 3. Neither the names of the copyright holders nor the names of its + * contributors may be used to endorse or promote products derived from + * this software without specific prior written permission. + * + * Alternatively, this software may be distributed under the terms of the + * GNU General Public License ("GPL") version 2 as published by the Free + * Software Foundation. + * + * THIS SOFTWARE IS PROVIDED BY THE COPYRIGHT HOLDERS AND CONTRIBUTORS "AS IS" + * AND ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT LIMITED TO, THE + * IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR A PARTICULAR PURPOSE + * ARE DISCLAIMED. IN NO EVENT SHALL THE COPYRIGHT OWNER OR CONTRIBUTORS BE + * LIABLE FOR ANY DIRECT, INDIRECT, INCIDENTAL, SPECIAL, EXEMPLARY, OR + * CONSEQUENTIAL DAMAGES (INCLUDING, BUT NOT LIMITED TO, PROCUREMENT OF + * SUBSTITUTE GOODS OR SERVICES; LOSS OF USE, DATA, OR PROFITS; OR BUSINESS + * INTERRUPTION) HOWEVER CAUSED AND ON ANY THEORY OF LIABILITY, WHETHER IN + * CONTRACT, STRICT LIABILITY, OR TORT (INCLUDING NEGLIGENCE OR OTHERWISE) + * ARISING IN ANY WAY OUT OF THE USE OF THIS SOFTWARE, EVEN IF ADVISED OF THE + * POSSIBILITY OF SUCH DAMAGE. + */ + +#ifndef _TIPC_ZONE_H +#define _TIPC_ZONE_H + +#include "node_subscr.h" +#include "net.h" + + +/** + * struct _zone - TIPC zone structure + * @addr: network address of zone + * @clusters: array of pointers to all clusters within zone + * @links: (used for inter-zone communication) + */ + +struct _zone { + u32 addr; + struct cluster *clusters[2]; /* currently limited to just 1 cluster */ + u32 links; +}; + +struct node *zone_select_remote_node(struct _zone *z_ptr, u32 addr, u32 ref); +u32 zone_select_router(struct _zone *z_ptr, u32 addr, u32 ref); +void zone_remove_as_router(struct _zone *z_ptr, u32 router); +void zone_send_external_routes(struct _zone *z_ptr, u32 dest); +struct _zone *zone_create(u32 addr); +void zone_delete(struct _zone *z_ptr); +void zone_attach_cluster(struct _zone *z_ptr, struct cluster *c_ptr); +u32 zone_next_node(u32 addr); + +static inline struct _zone *zone_find(u32 addr) +{ + return net.zones[tipc_zone(addr)]; +} + +#endif diff --git a/security/selinux/avc.c b/security/selinux/avc.c index 12e4fb72bf0..53d6c7bbf56 100644 --- a/security/selinux/avc.c +++ b/security/selinux/avc.c @@ -494,8 +494,7 @@ static inline void avc_print_ipv6_addr(struct audit_buffer *ab, char *name1, char *name2) { if (!ipv6_addr_any(addr)) - audit_log_format(ab, " %s=%04x:%04x:%04x:%04x:%04x:" - "%04x:%04x:%04x", name1, NIP6(*addr)); + audit_log_format(ab, " %s=" NIP6_FMT, name1, NIP6(*addr)); if (port) audit_log_format(ab, " %s=%d", name2, ntohs(port)); } @@ -504,7 +503,7 @@ static inline void avc_print_ipv4_addr(struct audit_buffer *ab, u32 addr, __be16 port, char *name1, char *name2) { if (addr) - audit_log_format(ab, " %s=%d.%d.%d.%d", name1, NIPQUAD(addr)); + audit_log_format(ab, " %s=" NIPQUAD_FMT, name1, NIPQUAD(addr)); if (port) audit_log_format(ab, " %s=%d", name2, ntohs(port)); } |