From c2f0c7c356dc9ae15419f00c725a2fcc58eeff58 Mon Sep 17 00:00:00 2001 From: Steve Grubb Date: Fri, 6 May 2005 12:38:39 +0100 Subject: The attached patch addresses the problem with getting the audit daemon shutdown credential information. It creates a new message type AUDIT_TERM_INFO, which is used by the audit daemon to query who issued the shutdown. It requires the placement of a hook function that gathers the information. The hook is after the DAC & MAC checks and before the function returns. Racing threads could overwrite the uid & pid - but they would have to be root and have policy that allows signalling the audit daemon. That should be a manageable risk. The userspace component will be released later in audit 0.7.2. When it receives the TERM signal, it queries the kernel for shutdown information. When it receives it, it writes the message and exits. The message looks like this: type=DAEMON msg=auditd(1114551182.000) auditd normal halt, sending pid=2650 uid=525, auditd pid=1685 Signed-off-by: Steve Grubb Signed-off-by: David Woodhouse --- include/linux/audit.h | 25 +++++++++++++++++-------- 1 file changed, 17 insertions(+), 8 deletions(-) (limited to 'include/linux') diff --git a/include/linux/audit.h b/include/linux/audit.h index 19f04b049798..baa80760824c 100644 --- a/include/linux/audit.h +++ b/include/linux/audit.h @@ -28,14 +28,16 @@ #include /* Request and reply types */ -#define AUDIT_GET 1000 /* Get status */ -#define AUDIT_SET 1001 /* Set status (enable/disable/auditd) */ -#define AUDIT_LIST 1002 /* List filtering rules */ -#define AUDIT_ADD 1003 /* Add filtering rule */ -#define AUDIT_DEL 1004 /* Delete filtering rule */ -#define AUDIT_USER 1005 /* Send a message from user-space */ -#define AUDIT_LOGIN 1006 /* Define the login id and informaiton */ -#define AUDIT_KERNEL 2000 /* Asynchronous audit record. NOT A REQUEST. */ +#define AUDIT_GET 1000 /* Get status */ +#define AUDIT_SET 1001 /* Set status (enable/disable/auditd) */ +#define AUDIT_LIST 1002 /* List filtering rules */ +#define AUDIT_ADD 1003 /* Add filtering rule */ +#define AUDIT_DEL 1004 /* Delete filtering rule */ +#define AUDIT_USER 1005 /* Send a message from user-space */ +#define AUDIT_LOGIN 1006 /* Define the login id and information */ +#define AUDIT_SIGNAL_INFO 1010 /* Get information about sender of signal*/ + +#define AUDIT_KERNEL 2000 /* Asynchronous audit record. NOT A REQUEST. */ /* Rule flags */ #define AUDIT_PER_TASK 0x01 /* Apply rule at task creation (not syscall) */ @@ -161,6 +163,11 @@ struct audit_rule { /* for AUDIT_LIST, AUDIT_ADD, and AUDIT_DEL */ #ifdef __KERNEL__ +struct audit_sig_info { + uid_t uid; + pid_t pid; +}; + struct audit_buffer; struct audit_context; struct inode; @@ -190,6 +197,7 @@ extern void audit_get_stamp(struct audit_context *ctx, extern int audit_set_loginuid(struct task_struct *task, uid_t loginuid); extern uid_t audit_get_loginuid(struct audit_context *ctx); extern int audit_ipc_perms(unsigned long qbytes, uid_t uid, gid_t gid, mode_t mode); +extern void audit_signal_info(int sig, struct task_struct *t); #else #define audit_alloc(t) ({ 0; }) #define audit_free(t) do { ; } while (0) @@ -200,6 +208,7 @@ extern int audit_ipc_perms(unsigned long qbytes, uid_t uid, gid_t gid, mode_t mo #define audit_inode(n,i) do { ; } while (0) #define audit_get_loginuid(c) ({ -1; }) #define audit_ipc_perms(q,u,g,m) ({ 0; }) +#define audit_signal_info(s,t) do { ; } while (0) #endif #ifdef CONFIG_AUDIT -- cgit v1.2.3 From 197c69c6afd2deb7eec44040ff533d90d26c6161 Mon Sep 17 00:00:00 2001 From: Chris Wright Date: Wed, 11 May 2005 10:54:05 +0100 Subject: Move ifdef CONFIG_AUDITSYSCALL to header Remove code conditionally dependent on CONFIG_AUDITSYSCALL from audit.c. Move these dependencies to audit.h with the rest. Signed-off-by: Chris Wright Signed-off-by: David Woodhouse --- include/linux/audit.h | 4 +++- kernel/audit.c | 12 ++---------- kernel/auditsc.c | 7 +++---- 3 files changed, 8 insertions(+), 15 deletions(-) (limited to 'include/linux') diff --git a/include/linux/audit.h b/include/linux/audit.h index baa80760824c..58c5589b531f 100644 --- a/include/linux/audit.h +++ b/include/linux/audit.h @@ -192,7 +192,7 @@ extern void audit_inode(const char *name, const struct inode *inode); /* Private API (for audit.c only) */ extern int audit_receive_filter(int type, int pid, int uid, int seq, void *data, uid_t loginuid); -extern void audit_get_stamp(struct audit_context *ctx, +extern int audit_get_stamp(struct audit_context *ctx, struct timespec *t, unsigned int *serial); extern int audit_set_loginuid(struct task_struct *task, uid_t loginuid); extern uid_t audit_get_loginuid(struct audit_context *ctx); @@ -206,6 +206,8 @@ extern void audit_signal_info(int sig, struct task_struct *t); #define audit_getname(n) do { ; } while (0) #define audit_putname(n) do { ; } while (0) #define audit_inode(n,i) do { ; } while (0) +#define audit_receive_filter(t,p,u,s,d,l) ({ -EOPNOTSUPP; }) +#define audit_get_stamp(c,t,s) ({ 0; }) #define audit_get_loginuid(c) ({ -1; }) #define audit_ipc_perms(q,u,g,m) ({ 0; }) #define audit_signal_info(s,t) do { ; } while (0) diff --git a/kernel/audit.c b/kernel/audit.c index dc4aba21f30a..c18b769e23a2 100644 --- a/kernel/audit.c +++ b/kernel/audit.c @@ -416,12 +416,8 @@ static int audit_receive_msg(struct sk_buff *skb, struct nlmsghdr *nlh) return -EINVAL; /* fallthrough */ case AUDIT_LIST: -#ifdef CONFIG_AUDITSYSCALL err = audit_receive_filter(nlh->nlmsg_type, NETLINK_CB(skb).pid, uid, seq, data, loginuid); -#else - err = -EOPNOTSUPP; -#endif break; case AUDIT_SIGNAL_INFO: sig_data.uid = audit_sig_uid; @@ -636,15 +632,11 @@ struct audit_buffer *audit_log_start(struct audit_context *ctx) return NULL; } -#ifdef CONFIG_AUDITSYSCALL - if (ab->ctx) - audit_get_stamp(ab->ctx, &t, &serial); - else -#endif - { + if (!audit_get_stamp(ab->ctx, &t, &serial)) { t = CURRENT_TIME; serial = 0; } + audit_log_format(ab, "audit(%lu.%03lu:%u): ", t.tv_sec, t.tv_nsec/1000000, serial); return ab; diff --git a/kernel/auditsc.c b/kernel/auditsc.c index 680bb928343b..94338abf76f5 100644 --- a/kernel/auditsc.c +++ b/kernel/auditsc.c @@ -992,7 +992,7 @@ void audit_inode(const char *name, const struct inode *inode) context->names[idx].rdev = inode->i_rdev; } -void audit_get_stamp(struct audit_context *ctx, +int audit_get_stamp(struct audit_context *ctx, struct timespec *t, unsigned int *serial) { if (ctx) { @@ -1000,10 +1000,9 @@ void audit_get_stamp(struct audit_context *ctx, t->tv_nsec = ctx->ctime.tv_nsec; *serial = ctx->serial; ctx->auditable = 1; - } else { - *t = CURRENT_TIME; - *serial = 0; + return 1; } + return 0; } extern int audit_set_type(struct audit_buffer *ab, int type); -- cgit v1.2.3 From c1b773d87eadc3972d697444127e89a7291769a2 Mon Sep 17 00:00:00 2001 From: Chris Wright Date: Wed, 11 May 2005 10:55:10 +0100 Subject: Add audit_log_type Add audit_log_type to allow callers to specify type and pid when logging. Convert audit_log to wrapper around audit_log_type. Could have converted all audit_log callers directly, but common case is default of type AUDIT_KERNEL and pid 0. Update audit_log_start to take type and pid values when creating a new audit_buffer. Move sequences that did audit_log_start, audit_log_format, audit_set_type, audit_log_end, to simply call audit_log_type directly. This obsoletes audit_set_type and audit_set_pid, so remove them. Signed-off-by: Chris Wright Signed-off-by: David Woodhouse --- include/linux/audit.h | 16 ++++++++++------ kernel/audit.c | 48 +++++++++++++++--------------------------------- kernel/auditsc.c | 23 +++++++---------------- security/selinux/avc.c | 2 +- 4 files changed, 33 insertions(+), 56 deletions(-) (limited to 'include/linux') diff --git a/include/linux/audit.h b/include/linux/audit.h index 58c5589b531f..405332ebf3c6 100644 --- a/include/linux/audit.h +++ b/include/linux/audit.h @@ -216,11 +216,14 @@ extern void audit_signal_info(int sig, struct task_struct *t); #ifdef CONFIG_AUDIT /* These are defined in audit.c */ /* Public API */ -extern void audit_log(struct audit_context *ctx, - const char *fmt, ...) - __attribute__((format(printf,2,3))); +#define audit_log(ctx, fmt, args...) \ + audit_log_type(ctx, AUDIT_KERNEL, 0, fmt, ##args) +extern void audit_log_type(struct audit_context *ctx, int type, + int pid, const char *fmt, ...) + __attribute__((format(printf,4,5))); -extern struct audit_buffer *audit_log_start(struct audit_context *ctx); +extern struct audit_buffer *audit_log_start(struct audit_context *ctx, int type, + int pid); extern void audit_log_format(struct audit_buffer *ab, const char *fmt, ...) __attribute__((format(printf,2,3))); @@ -240,8 +243,9 @@ extern void audit_send_reply(int pid, int seq, int type, void *payload, int size); extern void audit_log_lost(const char *message); #else -#define audit_log(t,f,...) do { ; } while (0) -#define audit_log_start(t) ({ NULL; }) +#define audit_log(c,f,...) do { ; } while (0) +#define audit_log_type(c,t,p,f,...) do { ; } while (0) +#define audit_log_start(c,t,p) ({ NULL; }) #define audit_log_vformat(b,f,a) do { ; } while (0) #define audit_log_format(b,f,...) do { ; } while (0) #define audit_log_end(b) do { ; } while (0) diff --git a/kernel/audit.c b/kernel/audit.c index c18b769e23a2..060b554f481e 100644 --- a/kernel/audit.c +++ b/kernel/audit.c @@ -140,18 +140,6 @@ struct audit_buffer { struct audit_context *ctx; /* NULL or associated context */ }; -void audit_set_type(struct audit_buffer *ab, int type) -{ - struct nlmsghdr *nlh = (struct nlmsghdr *)ab->skb->data; - nlh->nlmsg_type = type; -} - -static void audit_set_pid(struct audit_buffer *ab, pid_t pid) -{ - struct nlmsghdr *nlh = (struct nlmsghdr *)ab->skb->data; - nlh->nlmsg_pid = pid; -} - struct audit_entry { struct list_head list; struct audit_rule rule; @@ -344,7 +332,6 @@ static int audit_receive_msg(struct sk_buff *skb, struct nlmsghdr *nlh) void *data; struct audit_status *status_get, status_set; int err; - struct audit_buffer *ab; u16 msg_type = nlh->nlmsg_type; uid_t loginuid; /* loginuid of sender */ struct audit_sig_info sig_data; @@ -396,19 +383,13 @@ static int audit_receive_msg(struct sk_buff *skb, struct nlmsghdr *nlh) loginuid); break; case AUDIT_USER: - ab = audit_log_start(NULL); - if (!ab) - break; /* audit_panic has been called */ - audit_log_format(ab, + audit_log_type(NULL, AUDIT_USER, pid, "user pid=%d uid=%d length=%d loginuid=%u" " msg='%.1024s'", pid, uid, (int)(nlh->nlmsg_len - ((char *)data - (char *)nlh)), loginuid, (char *)data); - audit_set_type(ab, AUDIT_USER); - audit_set_pid(ab, pid); - audit_log_end(ab); break; case AUDIT_ADD: case AUDIT_DEL: @@ -560,12 +541,10 @@ static void audit_buffer_free(struct audit_buffer *ab) spin_unlock_irqrestore(&audit_freelist_lock, flags); } -static struct audit_buffer * audit_buffer_alloc(struct audit_context *ctx, - int gfp_mask) +static struct audit_buffer * audit_buffer_alloc(int gfp_mask) { unsigned long flags; struct audit_buffer *ab = NULL; - struct nlmsghdr *nlh; spin_lock_irqsave(&audit_freelist_lock, flags); if (!list_empty(&audit_freelist)) { @@ -587,12 +566,6 @@ static struct audit_buffer * audit_buffer_alloc(struct audit_context *ctx, if (!ab->skb) goto err; - ab->ctx = ctx; - nlh = (struct nlmsghdr *)skb_put(ab->skb, NLMSG_SPACE(0)); - nlh->nlmsg_type = AUDIT_KERNEL; - nlh->nlmsg_flags = 0; - nlh->nlmsg_pid = 0; - nlh->nlmsg_seq = 0; return ab; err: audit_buffer_free(ab); @@ -605,11 +578,12 @@ err: * syscall, then the syscall is marked as auditable and an audit record * will be written at syscall exit. If there is no associated task, tsk * should be NULL. */ -struct audit_buffer *audit_log_start(struct audit_context *ctx) +struct audit_buffer *audit_log_start(struct audit_context *ctx, int type, int pid) { struct audit_buffer *ab = NULL; struct timespec t; unsigned int serial; + struct nlmsghdr *nlh; if (!audit_initialized) return NULL; @@ -626,12 +600,19 @@ struct audit_buffer *audit_log_start(struct audit_context *ctx) return NULL; } - ab = audit_buffer_alloc(ctx, GFP_ATOMIC); + ab = audit_buffer_alloc(GFP_ATOMIC); if (!ab) { audit_log_lost("out of memory in audit_log_start"); return NULL; } + ab->ctx = ctx; + nlh = (struct nlmsghdr *)skb_put(ab->skb, NLMSG_SPACE(0)); + nlh->nlmsg_type = type; + nlh->nlmsg_flags = 0; + nlh->nlmsg_pid = pid; + nlh->nlmsg_seq = 0; + if (!audit_get_stamp(ab->ctx, &t, &serial)) { t = CURRENT_TIME; serial = 0; @@ -828,12 +809,13 @@ void audit_log_end(struct audit_buffer *ab) /* Log an audit record. This is a convenience function that calls * audit_log_start, audit_log_vformat, and audit_log_end. It may be * called in any context. */ -void audit_log(struct audit_context *ctx, const char *fmt, ...) +void audit_log_type(struct audit_context *ctx, int type, int pid, + const char *fmt, ...) { struct audit_buffer *ab; va_list args; - ab = audit_log_start(ctx); + ab = audit_log_start(ctx, type, pid); if (ab) { va_start(args, fmt); audit_log_vformat(ab, fmt, args); diff --git a/kernel/auditsc.c b/kernel/auditsc.c index 94338abf76f5..d089263253a7 100644 --- a/kernel/auditsc.c +++ b/kernel/auditsc.c @@ -648,7 +648,7 @@ static void audit_log_exit(struct audit_context *context) int i; struct audit_buffer *ab; - ab = audit_log_start(context); + ab = audit_log_start(context, AUDIT_KERNEL, 0); if (!ab) return; /* audit_panic has been called */ audit_log_format(ab, "syscall=%d", context->major); @@ -680,7 +680,7 @@ static void audit_log_exit(struct audit_context *context) while (context->aux) { struct audit_aux_data *aux; - ab = audit_log_start(context); + ab = audit_log_start(context, AUDIT_KERNEL, 0); if (!ab) continue; /* audit_panic has been called */ @@ -701,7 +701,7 @@ static void audit_log_exit(struct audit_context *context) } for (i = 0; i < context->name_count; i++) { - ab = audit_log_start(context); + ab = audit_log_start(context, AUDIT_KERNEL, 0); if (!ab) continue; /* audit_panic has been called */ audit_log_format(ab, "item=%d", i); @@ -1005,22 +1005,13 @@ int audit_get_stamp(struct audit_context *ctx, return 0; } -extern int audit_set_type(struct audit_buffer *ab, int type); - int audit_set_loginuid(struct task_struct *task, uid_t loginuid) { if (task->audit_context) { - struct audit_buffer *ab; - - ab = audit_log_start(NULL); - if (ab) { - audit_log_format(ab, "login pid=%d uid=%u " - "old loginuid=%u new loginuid=%u", - task->pid, task->uid, - task->audit_context->loginuid, loginuid); - audit_set_type(ab, AUDIT_LOGIN); - audit_log_end(ab); - } + audit_log_type(NULL, AUDIT_LOGIN, 0, + "login pid=%d uid=%u old loginuid=%u new loginuid=%u", + task->pid, task->uid, task->audit_context->loginuid, + loginuid); task->audit_context->loginuid = loginuid; } return 0; diff --git a/security/selinux/avc.c b/security/selinux/avc.c index 85a6f66a873f..9e71a1bbe011 100644 --- a/security/selinux/avc.c +++ b/security/selinux/avc.c @@ -549,7 +549,7 @@ void avc_audit(u32 ssid, u32 tsid, return; } - ab = audit_log_start(current->audit_context); + ab = audit_log_start(current->audit_context, AUDIT_KERNEL, 0); if (!ab) return; /* audit_panic has been called */ audit_log_format(ab, "avc: %s ", denied ? "denied" : "granted"); -- cgit v1.2.3 From 6f2f38128170814e151cfedf79532e19cd179567 Mon Sep 17 00:00:00 2001 From: Brad Campbell Date: Thu, 12 May 2005 15:07:47 -0400 Subject: [PATCH] libata basic detection and errata for PATA->SATA bridges This patch works around an issue with WD drives (and possibly others) over SiL PATA->SATA Bridges on SATA controllers locking up with transfers > 200 sectors. Signed-off-by: Brad Campbell --- drivers/scsi/libata-core.c | 35 +++++++++++++++++++++++++++++++++-- include/linux/ata.h | 1 + include/linux/libata.h | 1 + 3 files changed, 35 insertions(+), 2 deletions(-) (limited to 'include/linux') diff --git a/drivers/scsi/libata-core.c b/drivers/scsi/libata-core.c index 0b5d3a5b7eda..8b5a3f00083d 100644 --- a/drivers/scsi/libata-core.c +++ b/drivers/scsi/libata-core.c @@ -1186,6 +1186,37 @@ err_out: DPRINTK("EXIT, err\n"); } + +static inline u8 ata_dev_knobble(struct ata_port *ap) +{ + return ((ap->cbl == ATA_CBL_SATA) && (!ata_id_is_sata(ap->device->id))); +} + +/** + * ata_dev_config - Run device specific handlers and check for + * SATA->PATA bridges + * @ap: Bus + * @i: Device + * + * LOCKING: + */ + +void ata_dev_config(struct ata_port *ap, unsigned int i) +{ + /* limit bridge transfers to udma5, 200 sectors */ + if (ata_dev_knobble(ap)) { + printk(KERN_INFO "ata%u(%u): applying bridge limits\n", + ap->id, ap->device->devno); + ap->udma_mask &= ATA_UDMA5; + ap->host->max_sectors = ATA_MAX_SECTORS; + ap->host->hostt->max_sectors = ATA_MAX_SECTORS; + ap->device->flags |= ATA_DFLAG_LOCK_SECTORS; + } + + if (ap->ops->dev_config) + ap->ops->dev_config(ap, &ap->device[i]); +} + /** * ata_bus_probe - Reset and probe ATA bus * @ap: Bus to probe @@ -1208,8 +1239,7 @@ static int ata_bus_probe(struct ata_port *ap) ata_dev_identify(ap, i); if (ata_dev_present(&ap->device[i])) { found = 1; - if (ap->ops->dev_config) - ap->ops->dev_config(ap, &ap->device[i]); + ata_dev_config(ap,i); } } @@ -4014,6 +4044,7 @@ EXPORT_SYMBOL_GPL(ata_scsi_release); EXPORT_SYMBOL_GPL(ata_host_intr); EXPORT_SYMBOL_GPL(ata_dev_classify); EXPORT_SYMBOL_GPL(ata_dev_id_string); +EXPORT_SYMBOL_GPL(ata_dev_config); EXPORT_SYMBOL_GPL(ata_scsi_simulate); #ifdef CONFIG_PCI diff --git a/include/linux/ata.h b/include/linux/ata.h index f178894edd04..ca5fcadf9981 100644 --- a/include/linux/ata.h +++ b/include/linux/ata.h @@ -224,6 +224,7 @@ struct ata_taskfile { }; #define ata_id_is_ata(id) (((id)[0] & (1 << 15)) == 0) +#define ata_id_is_sata(id) ((id)[93] == 0) #define ata_id_rahead_enabled(id) ((id)[85] & (1 << 6)) #define ata_id_wcache_enabled(id) ((id)[85] & (1 << 5)) #define ata_id_has_flush(id) ((id)[83] & (1 << 12)) diff --git a/include/linux/libata.h b/include/linux/libata.h index 505160ab472b..d33e70361a7d 100644 --- a/include/linux/libata.h +++ b/include/linux/libata.h @@ -420,6 +420,7 @@ extern void ata_sg_init(struct ata_queued_cmd *qc, struct scatterlist *sg, extern unsigned int ata_dev_classify(struct ata_taskfile *tf); extern void ata_dev_id_string(u16 *id, unsigned char *s, unsigned int ofs, unsigned int len); +extern void ata_dev_config(struct ata_port *ap, unsigned int i); extern void ata_bmdma_setup (struct ata_queued_cmd *qc); extern void ata_bmdma_start (struct ata_queued_cmd *qc); extern void ata_bmdma_stop(struct ata_port *ap); -- cgit v1.2.3 From 7d17c1d606f6e89778f05554ddea43791d5c92a0 Mon Sep 17 00:00:00 2001 From: Date: Thu, 12 May 2005 19:45:25 -0400 Subject: [netdrvrs] Use netif_carrier_* instead of IFF_RUNNING --- drivers/net/au1000_eth.c | 10 ++-------- drivers/net/bmac.c | 2 -- drivers/net/sk98lin/skge.c | 8 +++----- drivers/net/tlan.c | 4 ++-- drivers/net/tokenring/ibmtr.c | 11 +++-------- drivers/net/wan/lmc/lmc_main.c | 8 ++------ include/linux/if.h | 2 +- 7 files changed, 13 insertions(+), 32 deletions(-) (limited to 'include/linux') diff --git a/drivers/net/au1000_eth.c b/drivers/net/au1000_eth.c index 5a2efd343db4..c82b9cd1c924 100644 --- a/drivers/net/au1000_eth.c +++ b/drivers/net/au1000_eth.c @@ -1681,10 +1681,6 @@ static int au1000_init(struct net_device *dev) control |= MAC_FULL_DUPLEX; } - /* fix for startup without cable */ - if (!link) - dev->flags &= ~IFF_RUNNING; - aup->mac->control = control; aup->mac->vlan1_tag = 0x8100; /* activate vlan support */ au_sync(); @@ -1709,16 +1705,14 @@ static void au1000_timer(unsigned long data) if_port = dev->if_port; if (aup->phy_ops->phy_status(dev, aup->phy_addr, &link, &speed) == 0) { if (link) { - if (!(dev->flags & IFF_RUNNING)) { + if (!netif_carrier_ok(dev)) { netif_carrier_on(dev); - dev->flags |= IFF_RUNNING; printk(KERN_INFO "%s: link up\n", dev->name); } } else { - if (dev->flags & IFF_RUNNING) { + if (netif_carrier_ok(dev)) { netif_carrier_off(dev); - dev->flags &= ~IFF_RUNNING; dev->if_port = 0; printk(KERN_INFO "%s: link down\n", dev->name); } diff --git a/drivers/net/bmac.c b/drivers/net/bmac.c index 734bd4ee3f9b..00e5257b176f 100644 --- a/drivers/net/bmac.c +++ b/drivers/net/bmac.c @@ -1412,7 +1412,6 @@ static int bmac_open(struct net_device *dev) bp->opened = 1; bmac_reset_and_enable(dev); enable_irq(dev->irq); - dev->flags |= IFF_RUNNING; return 0; } @@ -1425,7 +1424,6 @@ static int bmac_close(struct net_device *dev) int i; bp->sleeping = 1; - dev->flags &= ~(IFF_UP | IFF_RUNNING); /* disable rx and tx */ config = bmread(dev, RXCFG); diff --git a/drivers/net/sk98lin/skge.c b/drivers/net/sk98lin/skge.c index 05b827f79f54..1ccb2989001c 100644 --- a/drivers/net/sk98lin/skge.c +++ b/drivers/net/sk98lin/skge.c @@ -4212,7 +4212,7 @@ SK_BOOL DualNet; Flags); SkGeStopPort(pAC, IoC, FromPort, SK_STOP_ALL, SK_HARD_RST); - pAC->dev[Param.Para32[0]]->flags &= ~IFF_RUNNING; + netif_carrier_off(pAC->dev[Param.Para32[0]]); spin_unlock_irqrestore( &pAC->TxPort[FromPort][TX_PRIO_LOW].TxDesRingLock, Flags); @@ -4355,7 +4355,7 @@ SK_BOOL DualNet; } /* Inform the world that link protocol is up. */ - pAC->dev[Param.Para32[0]]->flags |= IFF_RUNNING; + netif_carrier_on(pAC->dev[Param.Para32[0]]); break; case SK_DRV_NET_DOWN: /* SK_U32 Reason */ @@ -4368,7 +4368,7 @@ SK_BOOL DualNet; } else { DoPrintInterfaceChange = SK_TRUE; } - pAC->dev[Param.Para32[1]]->flags &= ~IFF_RUNNING; + netif_carrier_off(pAC->dev[Param.Para32[1]]); break; case SK_DRV_SWITCH_HARD: /* SK_U32 FromPortIdx SK_U32 ToPortIdx */ SK_DBG_MSG(NULL, SK_DBGMOD_DRV, SK_DBGCAT_DRV_EVENT, @@ -4961,7 +4961,6 @@ static int __devinit skge_probe_one(struct pci_dev *pdev, #ifdef CONFIG_NET_POLL_CONTROLLER dev->poll_controller = &SkGePollController; #endif - dev->flags &= ~IFF_RUNNING; SET_NETDEV_DEV(dev, &pdev->dev); SET_ETHTOOL_OPS(dev, &SkGeEthtoolOps); @@ -5035,7 +5034,6 @@ static int __devinit skge_probe_one(struct pci_dev *pdev, dev->set_mac_address = &SkGeSetMacAddr; dev->do_ioctl = &SkGeIoctl; dev->change_mtu = &SkGeChangeMtu; - dev->flags &= ~IFF_RUNNING; SET_NETDEV_DEV(dev, &pdev->dev); SET_ETHTOOL_OPS(dev, &SkGeEthtoolOps); diff --git a/drivers/net/tlan.c b/drivers/net/tlan.c index a7ffa64502dd..ce116624f136 100644 --- a/drivers/net/tlan.c +++ b/drivers/net/tlan.c @@ -2807,7 +2807,7 @@ void TLan_PhyMonitor( struct net_device *dev ) if (priv->link) { priv->link = 0; printk(KERN_DEBUG "TLAN: %s has lost link\n", dev->name); - dev->flags &= ~IFF_RUNNING; + netif_carrier_off(dev); TLan_SetTimer( dev, (2*HZ), TLAN_TIMER_LINK_BEAT ); return; } @@ -2817,7 +2817,7 @@ void TLan_PhyMonitor( struct net_device *dev ) if ((phy_status & MII_GS_LINK) && !priv->link) { priv->link = 1; printk(KERN_DEBUG "TLAN: %s has reestablished link\n", dev->name); - dev->flags |= IFF_RUNNING; + netif_carrier_on(dev); } /* Setup a new monitor */ diff --git a/drivers/net/tokenring/ibmtr.c b/drivers/net/tokenring/ibmtr.c index c098863bdd9d..3873917a9c22 100644 --- a/drivers/net/tokenring/ibmtr.c +++ b/drivers/net/tokenring/ibmtr.c @@ -888,11 +888,6 @@ static int tok_open(struct net_device *dev) ti->sap_status = CLOSED; /* CLOSED or OPEN */ ti->open_failure = NO; /* NO or YES */ ti->open_mode = MANUAL; /* MANUAL or AUTOMATIC */ - /* 12/2000 not typical Linux, but we can use RUNNING to let us know when - the network has crapped out or cables are disconnected. Useful because - the IFF_UP flag stays up the whole time, until ifconfig tr0 down. - */ - dev->flags &= ~IFF_RUNNING; ti->sram_phys &= ~1; /* to reverse what we do in tok_close */ /* init the spinlock */ @@ -1242,7 +1237,7 @@ irqreturn_t tok_interrupt(int irq, void *dev_id, struct pt_regs *regs) ti->open_status = CLOSED; ti->sap_status = CLOSED; ti->open_mode = AUTOMATIC; - dev->flags &= ~IFF_RUNNING; + netif_carrier_off(dev); netif_stop_queue(dev); ti->open_action = RESTART; outb(0, dev->base_addr + ADAPTRESET); @@ -1323,7 +1318,7 @@ irqreturn_t tok_interrupt(int irq, void *dev_id, struct pt_regs *regs) break; } netif_wake_queue(dev); - dev->flags |= IFF_RUNNING;/*BMS 12/2000*/ + netif_carrier_on(dev); break; case DIR_INTERRUPT: case DIR_MOD_OPEN_PARAMS: @@ -1427,7 +1422,7 @@ irqreturn_t tok_interrupt(int irq, void *dev_id, struct pt_regs *regs) ring_status); if(ring_status& (REMOVE_RECV|AUTO_REMOVAL|LOBE_FAULT)){ netif_stop_queue(dev); - dev->flags &= ~IFF_RUNNING;/*not typical Linux*/ + netif_carrier_off(dev); DPRINTK("Remove received, or Auto-removal error" ", or Lobe fault\n"); DPRINTK("We'll try to reopen the closed adapter" diff --git a/drivers/net/wan/lmc/lmc_main.c b/drivers/net/wan/lmc/lmc_main.c index 15e545f66cd7..2b948ea397d5 100644 --- a/drivers/net/wan/lmc/lmc_main.c +++ b/drivers/net/wan/lmc/lmc_main.c @@ -723,7 +723,7 @@ static void lmc_watchdog (unsigned long data) /*fold00*/ /* lmc_reset (sc); Why reset??? The link can go down ok */ /* Inform the world that link has been lost */ - dev->flags &= ~IFF_RUNNING; + netif_carrier_off(dev); } /* @@ -736,7 +736,7 @@ static void lmc_watchdog (unsigned long data) /*fold00*/ /* lmc_reset (sc); Again why reset??? */ /* Inform the world that link protocol is back up. */ - dev->flags |= IFF_RUNNING; + netif_carrier_on(dev); /* Now we have to tell the syncppp that we had an outage * and that it should deal. Calling sppp_reopen here @@ -1168,8 +1168,6 @@ static void lmc_running_reset (struct net_device *dev) /*fold00*/ sc->lmc_media->set_link_status (sc, 1); sc->lmc_media->set_status (sc, NULL); - //dev->flags |= IFF_RUNNING; - netif_wake_queue(dev); sc->lmc_txfull = 0; @@ -1233,8 +1231,6 @@ static int lmc_ifdown (struct net_device *dev) /*fold00*/ csr6 &= ~LMC_DEC_SR; /* Turn off the Receive bit */ LMC_CSR_WRITE (sc, csr_command, csr6); - dev->flags &= ~IFF_RUNNING; - sc->stats.rx_missed_errors += LMC_CSR_READ (sc, csr_missed_frames) & 0xffff; diff --git a/include/linux/if.h b/include/linux/if.h index d73a9d62f208..ce627d9092ef 100644 --- a/include/linux/if.h +++ b/include/linux/if.h @@ -33,7 +33,7 @@ #define IFF_LOOPBACK 0x8 /* is a loopback net */ #define IFF_POINTOPOINT 0x10 /* interface is has p-p link */ #define IFF_NOTRAILERS 0x20 /* avoid use of trailers */ -#define IFF_RUNNING 0x40 /* resources allocated */ +#define IFF_RUNNING 0x40 /* interface running and carrier ok */ #define IFF_NOARP 0x80 /* no ARP protocol */ #define IFF_PROMISC 0x100 /* receive all packets */ #define IFF_ALLMULTI 0x200 /* receive all multicast packets*/ -- cgit v1.2.3 From fff9cfd99c0f88645c3f50d7476d6c8cef99f140 Mon Sep 17 00:00:00 2001 From: Date: Thu, 12 May 2005 20:24:19 -0400 Subject: [PATCH] Wireless Extensions 18 (aka WPA) This is version 18 of the Wireless Extensions. The main change is that it adds all the necessary APIs for WPA and WPA2 support. This work was entirely done by Jouni Malinen, so let's thank him for both his hard work and deep expertise on the subject ;-) This APIs obviously doesn't do much by itself and works in concert with driver support (Jouni already sent you the HostAP changes) and userspace (Jouni is updating wpa_supplicant). This is also orthogonal with the ongoing work on in-kernel IEEE support (but potentially useful). The patch is attached, tested with 2.6.11. Normally, I would ask you to push that directly in the kernel (99% of the patch has been on my web page for ages and it does not affect non-WPA stuff), but Jouni convinced me that it should bake a few weeks in wireless-2.6 first, so that other driver maintainers can get up to speed with it. Signed-off-by: Jeff Garzik --- include/linux/wireless.h | 283 ++++++++++++++++++++++++++++++++++++++++++++++- net/core/wireless.c | 74 ++++++++++++- 2 files changed, 352 insertions(+), 5 deletions(-) (limited to 'include/linux') diff --git a/include/linux/wireless.h b/include/linux/wireless.h index 2f51f2b6562e..ae485f9c916e 100644 --- a/include/linux/wireless.h +++ b/include/linux/wireless.h @@ -1,10 +1,10 @@ /* * This file define a set of standard wireless extensions * - * Version : 17 21.6.04 + * Version : 18 12.3.05 * * Authors : Jean Tourrilhes - HPL - - * Copyright (c) 1997-2004 Jean Tourrilhes, All Rights Reserved. + * Copyright (c) 1997-2005 Jean Tourrilhes, All Rights Reserved. */ #ifndef _LINUX_WIRELESS_H @@ -82,7 +82,7 @@ * (there is some stuff that will be added in the future...) * I just plan to increment with each new version. */ -#define WIRELESS_EXT 17 +#define WIRELESS_EXT 18 /* * Changes : @@ -182,6 +182,21 @@ * - Document (struct iw_quality *)->updated, add new flags (INVALID) * - Wireless Event capability in struct iw_range * - Add support for relative TxPower (yick !) + * + * V17 to V18 (From Jouni Malinen ) + * ---------- + * - Add support for WPA/WPA2 + * - Add extended encoding configuration (SIOCSIWENCODEEXT and + * SIOCGIWENCODEEXT) + * - Add SIOCSIWGENIE/SIOCGIWGENIE + * - Add SIOCSIWMLME + * - Add SIOCSIWPMKSA + * - Add struct iw_range bit field for supported encoding capabilities + * - Add optional scan request parameters for SIOCSIWSCAN + * - Add SIOCSIWAUTH/SIOCGIWAUTH for setting authentication and WPA + * related parameters (extensible up to 4096 parameter values) + * - Add wireless events: IWEVGENIE, IWEVMICHAELMICFAILURE, + * IWEVASSOCREQIE, IWEVASSOCRESPIE, IWEVPMKIDCAND */ /**************************** CONSTANTS ****************************/ @@ -256,6 +271,30 @@ #define SIOCSIWPOWER 0x8B2C /* set Power Management settings */ #define SIOCGIWPOWER 0x8B2D /* get Power Management settings */ +/* WPA : Generic IEEE 802.11 informatiom element (e.g., for WPA/RSN/WMM). + * This ioctl uses struct iw_point and data buffer that includes IE id and len + * fields. More than one IE may be included in the request. Setting the generic + * IE to empty buffer (len=0) removes the generic IE from the driver. Drivers + * are allowed to generate their own WPA/RSN IEs, but in these cases, drivers + * are required to report the used IE as a wireless event, e.g., when + * associating with an AP. */ +#define SIOCSIWGENIE 0x8B30 /* set generic IE */ +#define SIOCGIWGENIE 0x8B31 /* get generic IE */ + +/* WPA : IEEE 802.11 MLME requests */ +#define SIOCSIWMLME 0x8B16 /* request MLME operation; uses + * struct iw_mlme */ +/* WPA : Authentication mode parameters */ +#define SIOCSIWAUTH 0x8B32 /* set authentication mode params */ +#define SIOCGIWAUTH 0x8B33 /* get authentication mode params */ + +/* WPA : Extended version of encoding configuration */ +#define SIOCSIWENCODEEXT 0x8B34 /* set encoding token & mode */ +#define SIOCGIWENCODEEXT 0x8B35 /* get encoding token & mode */ + +/* WPA2 : PMKSA cache management */ +#define SIOCSIWPMKSA 0x8B36 /* PMKSA cache operation */ + /* -------------------- DEV PRIVATE IOCTL LIST -------------------- */ /* These 32 ioctl are wireless device private, for 16 commands. @@ -297,6 +336,34 @@ #define IWEVCUSTOM 0x8C02 /* Driver specific ascii string */ #define IWEVREGISTERED 0x8C03 /* Discovered a new node (AP mode) */ #define IWEVEXPIRED 0x8C04 /* Expired a node (AP mode) */ +#define IWEVGENIE 0x8C05 /* Generic IE (WPA, RSN, WMM, ..) + * (scan results); This includes id and + * length fields. One IWEVGENIE may + * contain more than one IE. Scan + * results may contain one or more + * IWEVGENIE events. */ +#define IWEVMICHAELMICFAILURE 0x8C06 /* Michael MIC failure + * (struct iw_michaelmicfailure) + */ +#define IWEVASSOCREQIE 0x8C07 /* IEs used in (Re)Association Request. + * The data includes id and length + * fields and may contain more than one + * IE. This event is required in + * Managed mode if the driver + * generates its own WPA/RSN IE. This + * should be sent just before + * IWEVREGISTERED event for the + * association. */ +#define IWEVASSOCRESPIE 0x8C08 /* IEs used in (Re)Association + * Response. The data includes id and + * length fields and may contain more + * than one IE. This may be sent + * between IWEVASSOCREQIE and + * IWEVREGISTERED events for the + * association. */ +#define IWEVPMKIDCAND 0x8C09 /* PMKID candidate for RSN + * pre-authentication + * (struct iw_pmkid_cand) */ #define IWEVFIRST 0x8C00 @@ -432,12 +499,94 @@ #define IW_SCAN_THIS_MODE 0x0020 /* Scan only this Mode */ #define IW_SCAN_ALL_RATE 0x0040 /* Scan all Bit-Rates */ #define IW_SCAN_THIS_RATE 0x0080 /* Scan only this Bit-Rate */ +/* struct iw_scan_req scan_type */ +#define IW_SCAN_TYPE_ACTIVE 0 +#define IW_SCAN_TYPE_PASSIVE 1 /* Maximum size of returned data */ #define IW_SCAN_MAX_DATA 4096 /* In bytes */ /* Max number of char in custom event - use multiple of them if needed */ #define IW_CUSTOM_MAX 256 /* In bytes */ +/* Generic information element */ +#define IW_GENERIC_IE_MAX 1024 + +/* MLME requests (SIOCSIWMLME / struct iw_mlme) */ +#define IW_MLME_DEAUTH 0 +#define IW_MLME_DISASSOC 1 + +/* SIOCSIWAUTH/SIOCGIWAUTH struct iw_param flags */ +#define IW_AUTH_INDEX 0x0FFF +#define IW_AUTH_FLAGS 0xF000 +/* SIOCSIWAUTH/SIOCGIWAUTH parameters (0 .. 4095) + * (IW_AUTH_INDEX mask in struct iw_param flags; this is the index of the + * parameter that is being set/get to; value will be read/written to + * struct iw_param value field) */ +#define IW_AUTH_WPA_VERSION 0 +#define IW_AUTH_CIPHER_PAIRWISE 1 +#define IW_AUTH_CIPHER_GROUP 2 +#define IW_AUTH_KEY_MGMT 3 +#define IW_AUTH_TKIP_COUNTERMEASURES 4 +#define IW_AUTH_DROP_UNENCRYPTED 5 +#define IW_AUTH_80211_AUTH_ALG 6 +#define IW_AUTH_WPA_ENABLED 7 +#define IW_AUTH_RX_UNENCRYPTED_EAPOL 8 +#define IW_AUTH_ROAMING_CONTROL 9 +#define IW_AUTH_PRIVACY_INVOKED 10 + +/* IW_AUTH_WPA_VERSION values (bit field) */ +#define IW_AUTH_WPA_VERSION_DISABLED 0x00000001 +#define IW_AUTH_WPA_VERSION_WPA 0x00000002 +#define IW_AUTH_WPA_VERSION_WPA2 0x00000004 + +/* IW_AUTH_PAIRWISE_CIPHER and IW_AUTH_GROUP_CIPHER values (bit field) */ +#define IW_AUTH_CIPHER_NONE 0x00000001 +#define IW_AUTH_CIPHER_WEP40 0x00000002 +#define IW_AUTH_CIPHER_TKIP 0x00000004 +#define IW_AUTH_CIPHER_CCMP 0x00000008 +#define IW_AUTH_CIPHER_WEP104 0x00000010 + +/* IW_AUTH_KEY_MGMT values (bit field) */ +#define IW_AUTH_KEY_MGMT_802_1X 1 +#define IW_AUTH_KEY_MGMT_PSK 2 + +/* IW_AUTH_80211_AUTH_ALG values (bit field) */ +#define IW_AUTH_ALG_OPEN_SYSTEM 0x00000001 +#define IW_AUTH_ALG_SHARED_KEY 0x00000002 +#define IW_AUTH_ALG_LEAP 0x00000004 + +/* IW_AUTH_ROAMING_CONTROL values */ +#define IW_AUTH_ROAMING_ENABLE 0 /* driver/firmware based roaming */ +#define IW_AUTH_ROAMING_DISABLE 1 /* user space program used for roaming + * control */ + +/* SIOCSIWENCODEEXT definitions */ +#define IW_ENCODE_SEQ_MAX_SIZE 8 +/* struct iw_encode_ext ->alg */ +#define IW_ENCODE_ALG_NONE 0 +#define IW_ENCODE_ALG_WEP 1 +#define IW_ENCODE_ALG_TKIP 2 +#define IW_ENCODE_ALG_CCMP 3 +/* struct iw_encode_ext ->ext_flags */ +#define IW_ENCODE_EXT_TX_SEQ_VALID 0x00000001 +#define IW_ENCODE_EXT_RX_SEQ_VALID 0x00000002 +#define IW_ENCODE_EXT_GROUP_KEY 0x00000004 +#define IW_ENCODE_EXT_SET_TX_KEY 0x00000008 + +/* IWEVMICHAELMICFAILURE : struct iw_michaelmicfailure ->flags */ +#define IW_MICFAILURE_KEY_ID 0x00000003 /* Key ID 0..3 */ +#define IW_MICFAILURE_GROUP 0x00000004 +#define IW_MICFAILURE_PAIRWISE 0x00000008 +#define IW_MICFAILURE_STAKEY 0x00000010 +#define IW_MICFAILURE_COUNT 0x00000060 /* 1 or 2 (0 = count not supported) + */ + +/* Bit field values for enc_capa in struct iw_range */ +#define IW_ENC_CAPA_WPA 0x00000001 +#define IW_ENC_CAPA_WPA2 0x00000002 +#define IW_ENC_CAPA_CIPHER_TKIP 0x00000004 +#define IW_ENC_CAPA_CIPHER_CCMP 0x00000008 + /* Event capability macros - in (struct iw_range *)->event_capa * Because we have more than 32 possible events, we use an array of * 32 bit bitmasks. Note : 32 bits = 0x20 = 2^5. */ @@ -546,6 +695,132 @@ struct iw_thrspy struct iw_quality high; /* High threshold */ }; +/* + * Optional data for scan request + * + * Note: these optional parameters are controlling parameters for the + * scanning behavior, these do not apply to getting scan results + * (SIOCGIWSCAN). Drivers are expected to keep a local BSS table and + * provide a merged results with all BSSes even if the previous scan + * request limited scanning to a subset, e.g., by specifying an SSID. + * Especially, scan results are required to include an entry for the + * current BSS if the driver is in Managed mode and associated with an AP. + */ +struct iw_scan_req +{ + __u8 scan_type; /* IW_SCAN_TYPE_{ACTIVE,PASSIVE} */ + __u8 essid_len; + __u8 num_channels; /* num entries in channel_list; + * 0 = scan all allowed channels */ + __u8 flags; /* reserved as padding; use zero, this may + * be used in the future for adding flags + * to request different scan behavior */ + struct sockaddr bssid; /* ff:ff:ff:ff:ff:ff for broadcast BSSID or + * individual address of a specific BSS */ + + /* + * Use this ESSID if IW_SCAN_THIS_ESSID flag is used instead of using + * the current ESSID. This allows scan requests for specific ESSID + * without having to change the current ESSID and potentially breaking + * the current association. + */ + __u8 essid[IW_ESSID_MAX_SIZE]; + + /* + * Optional parameters for changing the default scanning behavior. + * These are based on the MLME-SCAN.request from IEEE Std 802.11. + * TU is 1.024 ms. If these are set to 0, driver is expected to use + * reasonable default values. min_channel_time defines the time that + * will be used to wait for the first reply on each channel. If no + * replies are received, next channel will be scanned after this. If + * replies are received, total time waited on the channel is defined by + * max_channel_time. + */ + __u32 min_channel_time; /* in TU */ + __u32 max_channel_time; /* in TU */ + + struct iw_freq channel_list[IW_MAX_FREQUENCIES]; +}; + +/* ------------------------- WPA SUPPORT ------------------------- */ + +/* + * Extended data structure for get/set encoding (this is used with + * SIOCSIWENCODEEXT/SIOCGIWENCODEEXT. struct iw_point and IW_ENCODE_* + * flags are used in the same way as with SIOCSIWENCODE/SIOCGIWENCODE and + * only the data contents changes (key data -> this structure, including + * key data). + * + * If the new key is the first group key, it will be set as the default + * TX key. Otherwise, default TX key index is only changed if + * IW_ENCODE_EXT_SET_TX_KEY flag is set. + * + * Key will be changed with SIOCSIWENCODEEXT in all cases except for + * special "change TX key index" operation which is indicated by setting + * key_len = 0 and ext_flags |= IW_ENCODE_EXT_SET_TX_KEY. + * + * tx_seq/rx_seq are only used when respective + * IW_ENCODE_EXT_{TX,RX}_SEQ_VALID flag is set in ext_flags. Normal + * TKIP/CCMP operation is to set RX seq with SIOCSIWENCODEEXT and start + * TX seq from zero whenever key is changed. SIOCGIWENCODEEXT is normally + * used only by an Authenticator (AP or an IBSS station) to get the + * current TX sequence number. Using TX_SEQ_VALID for SIOCSIWENCODEEXT and + * RX_SEQ_VALID for SIOCGIWENCODEEXT are optional, but can be useful for + * debugging/testing. + */ +struct iw_encode_ext +{ + __u32 ext_flags; /* IW_ENCODE_EXT_* */ + __u8 tx_seq[IW_ENCODE_SEQ_MAX_SIZE]; /* LSB first */ + __u8 rx_seq[IW_ENCODE_SEQ_MAX_SIZE]; /* LSB first */ + struct sockaddr addr; /* ff:ff:ff:ff:ff:ff for broadcast/multicast + * (group) keys or unicast address for + * individual keys */ + __u16 alg; /* IW_ENCODE_ALG_* */ + __u16 key_len; + __u8 key[0]; +}; + +/* SIOCSIWMLME data */ +struct iw_mlme +{ + __u16 cmd; /* IW_MLME_* */ + __u16 reason_code; + struct sockaddr addr; +}; + +/* SIOCSIWPMKSA data */ +#define IW_PMKSA_ADD 1 +#define IW_PMKSA_REMOVE 2 +#define IW_PMKSA_FLUSH 3 + +#define IW_PMKID_LEN 16 + +struct iw_pmksa +{ + __u32 cmd; /* IW_PMKSA_* */ + struct sockaddr bssid; + __u8 pmkid[IW_PMKID_LEN]; +}; + +/* IWEVMICHAELMICFAILURE data */ +struct iw_michaelmicfailure +{ + __u32 flags; + struct sockaddr src_addr; + __u8 tsc[IW_ENCODE_SEQ_MAX_SIZE]; /* LSB first */ +}; + +/* IWEVPMKIDCAND data */ +#define IW_PMKID_CAND_PREAUTH 0x00000001 /* RNS pre-authentication enabled */ +struct iw_pmkid_cand +{ + __u32 flags; /* IW_PMKID_CAND_* */ + __u32 index; /* the smaller the index, the higher the + * priority */ + struct sockaddr bssid; +}; + /* ------------------------ WIRELESS STATS ------------------------ */ /* * Wireless statistics (used for /proc/net/wireless) @@ -725,6 +1000,8 @@ struct iw_range struct iw_freq freq[IW_MAX_FREQUENCIES]; /* list */ /* Note : this frequency list doesn't need to fit channel numbers, * because each entry contain its channel index */ + + __u32 enc_capa; /* IW_ENC_CAPA_* bit field */ }; /* diff --git a/net/core/wireless.c b/net/core/wireless.c index 750cc5daeb03..b2fe378dfbf8 100644 --- a/net/core/wireless.c +++ b/net/core/wireless.c @@ -2,7 +2,7 @@ * This file implement the Wireless Extensions APIs. * * Authors : Jean Tourrilhes - HPL - - * Copyright (c) 1997-2004 Jean Tourrilhes, All Rights Reserved. + * Copyright (c) 1997-2005 Jean Tourrilhes, All Rights Reserved. * * (As all part of the Linux kernel, this file is GPL) */ @@ -187,6 +187,12 @@ static const struct iw_ioctl_description standard_ioctl[] = { .header_type = IW_HEADER_TYPE_ADDR, .flags = IW_DESCR_FLAG_DUMP, }, + [SIOCSIWMLME - SIOCIWFIRST] = { + .header_type = IW_HEADER_TYPE_POINT, + .token_size = 1, + .min_tokens = sizeof(struct iw_mlme), + .max_tokens = sizeof(struct iw_mlme), + }, [SIOCGIWAPLIST - SIOCIWFIRST] = { .header_type = IW_HEADER_TYPE_POINT, .token_size = sizeof(struct sockaddr) + @@ -195,7 +201,10 @@ static const struct iw_ioctl_description standard_ioctl[] = { .flags = IW_DESCR_FLAG_NOMAX, }, [SIOCSIWSCAN - SIOCIWFIRST] = { - .header_type = IW_HEADER_TYPE_PARAM, + .header_type = IW_HEADER_TYPE_POINT, + .token_size = 1, + .min_tokens = 0, + .max_tokens = sizeof(struct iw_scan_req), }, [SIOCGIWSCAN - SIOCIWFIRST] = { .header_type = IW_HEADER_TYPE_POINT, @@ -273,6 +282,42 @@ static const struct iw_ioctl_description standard_ioctl[] = { [SIOCGIWPOWER - SIOCIWFIRST] = { .header_type = IW_HEADER_TYPE_PARAM, }, + [SIOCSIWGENIE - SIOCIWFIRST] = { + .header_type = IW_HEADER_TYPE_POINT, + .token_size = 1, + .max_tokens = IW_GENERIC_IE_MAX, + }, + [SIOCGIWGENIE - SIOCIWFIRST] = { + .header_type = IW_HEADER_TYPE_POINT, + .token_size = 1, + .max_tokens = IW_GENERIC_IE_MAX, + }, + [SIOCSIWAUTH - SIOCIWFIRST] = { + .header_type = IW_HEADER_TYPE_PARAM, + }, + [SIOCGIWAUTH - SIOCIWFIRST] = { + .header_type = IW_HEADER_TYPE_PARAM, + }, + [SIOCSIWENCODEEXT - SIOCIWFIRST] = { + .header_type = IW_HEADER_TYPE_POINT, + .token_size = 1, + .min_tokens = sizeof(struct iw_encode_ext), + .max_tokens = sizeof(struct iw_encode_ext) + + IW_ENCODING_TOKEN_MAX, + }, + [SIOCGIWENCODEEXT - SIOCIWFIRST] = { + .header_type = IW_HEADER_TYPE_POINT, + .token_size = 1, + .min_tokens = sizeof(struct iw_encode_ext), + .max_tokens = sizeof(struct iw_encode_ext) + + IW_ENCODING_TOKEN_MAX, + }, + [SIOCSIWPMKSA - SIOCIWFIRST] = { + .header_type = IW_HEADER_TYPE_POINT, + .token_size = 1, + .min_tokens = sizeof(struct iw_pmksa), + .max_tokens = sizeof(struct iw_pmksa), + }, }; static const int standard_ioctl_num = (sizeof(standard_ioctl) / sizeof(struct iw_ioctl_description)); @@ -299,6 +344,31 @@ static const struct iw_ioctl_description standard_event[] = { [IWEVEXPIRED - IWEVFIRST] = { .header_type = IW_HEADER_TYPE_ADDR, }, + [IWEVGENIE - IWEVFIRST] = { + .header_type = IW_HEADER_TYPE_POINT, + .token_size = 1, + .max_tokens = IW_GENERIC_IE_MAX, + }, + [IWEVMICHAELMICFAILURE - IWEVFIRST] = { + .header_type = IW_HEADER_TYPE_POINT, + .token_size = 1, + .max_tokens = sizeof(struct iw_michaelmicfailure), + }, + [IWEVASSOCREQIE - IWEVFIRST] = { + .header_type = IW_HEADER_TYPE_POINT, + .token_size = 1, + .max_tokens = IW_GENERIC_IE_MAX, + }, + [IWEVASSOCRESPIE - IWEVFIRST] = { + .header_type = IW_HEADER_TYPE_POINT, + .token_size = 1, + .max_tokens = IW_GENERIC_IE_MAX, + }, + [IWEVPMKIDCAND - IWEVFIRST] = { + .header_type = IW_HEADER_TYPE_POINT, + .token_size = 1, + .max_tokens = sizeof(struct iw_pmkid_cand), + }, }; static const int standard_event_num = (sizeof(standard_event) / sizeof(struct iw_ioctl_description)); -- cgit v1.2.3 From c04049939f88b29e235d2da217bce6e8ead44f32 Mon Sep 17 00:00:00 2001 From: Steve Grubb Date: Fri, 13 May 2005 18:17:42 +0100 Subject: AUDIT: Add message types to audit records This patch adds more messages types to the audit subsystem so that audit analysis is quicker, intuitive, and more useful. Signed-off-by: Steve Grubb --- I forgot one type in the big patch. I need to add one for user space originating SE Linux avc messages. This is used by dbus and nscd. -Steve --- Updated to 2.6.12-rc4-mm1. -dwmw2 Signed-off-by: David Woodhouse --- include/linux/audit.h | 66 ++++++++++++++++++++++++++--------- kernel/audit.c | 78 +++++++++++++++++++++++++++++------------- kernel/auditsc.c | 42 ++++++++++++++--------- security/selinux/avc.c | 4 +-- security/selinux/hooks.c | 2 +- security/selinux/nlmsgtab.c | 8 +++++ security/selinux/ss/services.c | 4 +-- 7 files changed, 143 insertions(+), 61 deletions(-) (limited to 'include/linux') diff --git a/include/linux/audit.h b/include/linux/audit.h index 405332ebf3c6..1a15ba38c660 100644 --- a/include/linux/audit.h +++ b/include/linux/audit.h @@ -27,15 +27,53 @@ #include #include -/* Request and reply types */ +/* The netlink messages for the audit system is divided into blocks: + * 1000 - 1099 are for commanding the audit system + * 1100 - 1199 user space trusted application messages + * 1200 - 1299 messages internal to the audit daemon + * 1300 - 1399 audit event messages + * 1400 - 1499 SE Linux use + * 1500 - 1999 future use + * 2000 is for otherwise unclassified kernel audit messages + * + * Messages from 1000-1199 are bi-directional. 1200-1299 are exclusively user + * space. Anything over that is kernel --> user space communication. + */ #define AUDIT_GET 1000 /* Get status */ #define AUDIT_SET 1001 /* Set status (enable/disable/auditd) */ -#define AUDIT_LIST 1002 /* List filtering rules */ -#define AUDIT_ADD 1003 /* Add filtering rule */ -#define AUDIT_DEL 1004 /* Delete filtering rule */ -#define AUDIT_USER 1005 /* Send a message from user-space */ +#define AUDIT_LIST 1002 /* List syscall filtering rules */ +#define AUDIT_ADD 1003 /* Add syscall filtering rule */ +#define AUDIT_DEL 1004 /* Delete syscall filtering rule */ +#define AUDIT_USER 1005 /* Message from userspace -- deprecated */ #define AUDIT_LOGIN 1006 /* Define the login id and information */ -#define AUDIT_SIGNAL_INFO 1010 /* Get information about sender of signal*/ +#define AUDIT_WATCH_INS 1007 /* Insert file/dir watch entry */ +#define AUDIT_WATCH_REM 1008 /* Remove file/dir watch entry */ +#define AUDIT_WATCH_LIST 1009 /* List all file/dir watches */ +#define AUDIT_SIGNAL_INFO 1010 /* Get info about sender of signal to auditd */ + +#define AUDIT_USER_AUTH 1100 /* User space authentication */ +#define AUDIT_USER_ACCT 1101 /* User space acct change */ +#define AUDIT_USER_MGMT 1102 /* User space acct management */ +#define AUDIT_CRED_ACQ 1103 /* User space credential acquired */ +#define AUDIT_CRED_DISP 1104 /* User space credential disposed */ +#define AUDIT_USER_START 1105 /* User space session start */ +#define AUDIT_USER_END 1106 /* User space session end */ +#define AUDIT_USER_AVC 1107 /* User space avc message */ + +#define AUDIT_DAEMON_START 1200 /* Daemon startup record */ +#define AUDIT_DAEMON_END 1201 /* Daemon normal stop record */ +#define AUDIT_DAEMON_ABORT 1202 /* Daemon error stop record */ +#define AUDIT_DAEMON_CONFIG 1203 /* Daemon config change */ + +#define AUDIT_SYSCALL 1300 /* Syscall event */ +#define AUDIT_FS_WATCH 1301 /* Filesystem watch event */ +#define AUDIT_PATH 1302 /* Filname path information */ +#define AUDIT_IPC 1303 /* IPC record */ +#define AUDIT_SOCKET 1304 /* Socket record */ +#define AUDIT_CONFIG_CHANGE 1305 /* Audit system configuration change */ + +#define AUDIT_AVC 1400 /* SE Linux avc denial or grant */ +#define AUDIT_SELINUX_ERR 1401 /* Internal SE Linux Errors */ #define AUDIT_KERNEL 2000 /* Asynchronous audit record. NOT A REQUEST. */ @@ -216,14 +254,11 @@ extern void audit_signal_info(int sig, struct task_struct *t); #ifdef CONFIG_AUDIT /* These are defined in audit.c */ /* Public API */ -#define audit_log(ctx, fmt, args...) \ - audit_log_type(ctx, AUDIT_KERNEL, 0, fmt, ##args) -extern void audit_log_type(struct audit_context *ctx, int type, - int pid, const char *fmt, ...) - __attribute__((format(printf,4,5))); +extern void audit_log(struct audit_context *ctx, int type, + const char *fmt, ...) + __attribute__((format(printf,3,4))); -extern struct audit_buffer *audit_log_start(struct audit_context *ctx, int type, - int pid); +extern struct audit_buffer *audit_log_start(struct audit_context *ctx,int type); extern void audit_log_format(struct audit_buffer *ab, const char *fmt, ...) __attribute__((format(printf,2,3))); @@ -243,9 +278,8 @@ extern void audit_send_reply(int pid, int seq, int type, void *payload, int size); extern void audit_log_lost(const char *message); #else -#define audit_log(c,f,...) do { ; } while (0) -#define audit_log_type(c,t,p,f,...) do { ; } while (0) -#define audit_log_start(c,t,p) ({ NULL; }) +#define audit_log(c,t,f,...) do { ; } while (0) +#define audit_log_start(c,t) ({ NULL; }) #define audit_log_vformat(b,f,a) do { ; } while (0) #define audit_log_format(b,f,...) do { ; } while (0) #define audit_log_end(b) do { ; } while (0) diff --git a/kernel/audit.c b/kernel/audit.c index 187164572bd0..4e940c05ede8 100644 --- a/kernel/audit.c +++ b/kernel/audit.c @@ -140,6 +140,12 @@ struct audit_buffer { struct audit_context *ctx; /* NULL or associated context */ }; +static void audit_set_pid(struct audit_buffer *ab, pid_t pid) +{ + struct nlmsghdr *nlh = (struct nlmsghdr *)ab->skb->data; + nlh->nlmsg_pid = pid; +} + struct audit_entry { struct list_head list; struct audit_rule rule; @@ -233,7 +239,8 @@ static int audit_set_rate_limit(int limit, uid_t loginuid) { int old = audit_rate_limit; audit_rate_limit = limit; - audit_log(NULL, "audit_rate_limit=%d old=%d by auid %u", + audit_log(NULL, AUDIT_CONFIG_CHANGE, + "audit_rate_limit=%d old=%d by auid %u", audit_rate_limit, old, loginuid); return old; } @@ -242,7 +249,8 @@ static int audit_set_backlog_limit(int limit, uid_t loginuid) { int old = audit_backlog_limit; audit_backlog_limit = limit; - audit_log(NULL, "audit_backlog_limit=%d old=%d by auid %u", + audit_log(NULL, AUDIT_CONFIG_CHANGE, + "audit_backlog_limit=%d old=%d by auid %u", audit_backlog_limit, old, loginuid); return old; } @@ -253,8 +261,9 @@ static int audit_set_enabled(int state, uid_t loginuid) if (state != 0 && state != 1) return -EINVAL; audit_enabled = state; - audit_log(NULL, "audit_enabled=%d old=%d by auid %u", - audit_enabled, old, loginuid); + audit_log(NULL, AUDIT_CONFIG_CHANGE, + "audit_enabled=%d old=%d by auid %u", + audit_enabled, old, loginuid); return old; } @@ -266,8 +275,9 @@ static int audit_set_failure(int state, uid_t loginuid) && state != AUDIT_FAIL_PANIC) return -EINVAL; audit_failure = state; - audit_log(NULL, "audit_failure=%d old=%d by auid %u", - audit_failure, old, loginuid); + audit_log(NULL, AUDIT_CONFIG_CHANGE, + "audit_failure=%d old=%d by auid %u", + audit_failure, old, loginuid); return old; } @@ -316,6 +326,14 @@ static int audit_netlink_ok(kernel_cap_t eff_cap, u16 msg_type) err = -EPERM; break; case AUDIT_USER: + case AUDIT_USER_AUTH: + case AUDIT_USER_ACCT: + case AUDIT_USER_MGMT: + case AUDIT_CRED_ACQ: + case AUDIT_CRED_DISP: + case AUDIT_USER_START: + case AUDIT_USER_END: + case AUDIT_USER_AVC: if (!cap_raised(eff_cap, CAP_AUDIT_WRITE)) err = -EPERM; break; @@ -332,6 +350,7 @@ static int audit_receive_msg(struct sk_buff *skb, struct nlmsghdr *nlh) void *data; struct audit_status *status_get, status_set; int err; + struct audit_buffer *ab; u16 msg_type = nlh->nlmsg_type; uid_t loginuid; /* loginuid of sender */ struct audit_sig_info sig_data; @@ -373,7 +392,8 @@ static int audit_receive_msg(struct sk_buff *skb, struct nlmsghdr *nlh) if (status_get->mask & AUDIT_STATUS_PID) { int old = audit_pid; audit_pid = status_get->pid; - audit_log(NULL, "audit_pid=%d old=%d by auid %u", + audit_log(NULL, AUDIT_CONFIG_CHANGE, + "audit_pid=%d old=%d by auid %u", audit_pid, old, loginuid); } if (status_get->mask & AUDIT_STATUS_RATE_LIMIT) @@ -383,13 +403,26 @@ static int audit_receive_msg(struct sk_buff *skb, struct nlmsghdr *nlh) loginuid); break; case AUDIT_USER: - audit_log_type(NULL, AUDIT_USER, pid, + case AUDIT_USER_AUTH: + case AUDIT_USER_ACCT: + case AUDIT_USER_MGMT: + case AUDIT_CRED_ACQ: + case AUDIT_CRED_DISP: + case AUDIT_USER_START: + case AUDIT_USER_END: + case AUDIT_USER_AVC: + ab = audit_log_start(NULL, msg_type); + if (!ab) + break; /* audit_panic has been called */ + audit_log_format(ab, "user pid=%d uid=%d length=%d loginuid=%u" " msg='%.1024s'", pid, uid, (int)(nlh->nlmsg_len - ((char *)data - (char *)nlh)), loginuid, (char *)data); + audit_set_pid(ab, pid); + audit_log_end(ab); break; case AUDIT_ADD: case AUDIT_DEL: @@ -504,7 +537,7 @@ static int __init audit_init(void) audit_initialized = 1; audit_enabled = audit_default; - audit_log(NULL, "initialized"); + audit_log(NULL, AUDIT_KERNEL, "initialized"); return 0; } __initcall(audit_init); @@ -541,10 +574,12 @@ static void audit_buffer_free(struct audit_buffer *ab) spin_unlock_irqrestore(&audit_freelist_lock, flags); } -static struct audit_buffer * audit_buffer_alloc(int gfp_mask) +static struct audit_buffer * audit_buffer_alloc(struct audit_context *ctx, + int gfp_mask, int type) { unsigned long flags; struct audit_buffer *ab = NULL; + struct nlmsghdr *nlh; spin_lock_irqsave(&audit_freelist_lock, flags); if (!list_empty(&audit_freelist)) { @@ -566,6 +601,12 @@ static struct audit_buffer * audit_buffer_alloc(int gfp_mask) if (!ab->skb) goto err; + ab->ctx = ctx; + nlh = (struct nlmsghdr *)skb_put(ab->skb, NLMSG_SPACE(0)); + nlh->nlmsg_type = type; + nlh->nlmsg_flags = 0; + nlh->nlmsg_pid = 0; + nlh->nlmsg_seq = 0; return ab; err: audit_buffer_free(ab); @@ -578,12 +619,11 @@ err: * syscall, then the syscall is marked as auditable and an audit record * will be written at syscall exit. If there is no associated task, tsk * should be NULL. */ -struct audit_buffer *audit_log_start(struct audit_context *ctx, int type, int pid) +struct audit_buffer *audit_log_start(struct audit_context *ctx, int type) { struct audit_buffer *ab = NULL; struct timespec t; unsigned int serial; - struct nlmsghdr *nlh; if (!audit_initialized) return NULL; @@ -600,19 +640,12 @@ struct audit_buffer *audit_log_start(struct audit_context *ctx, int type, int pi return NULL; } - ab = audit_buffer_alloc(GFP_ATOMIC); + ab = audit_buffer_alloc(ctx, GFP_ATOMIC, type); if (!ab) { audit_log_lost("out of memory in audit_log_start"); return NULL; } - ab->ctx = ctx; - nlh = (struct nlmsghdr *)skb_put(ab->skb, NLMSG_SPACE(0)); - nlh->nlmsg_type = type; - nlh->nlmsg_flags = 0; - nlh->nlmsg_pid = pid; - nlh->nlmsg_seq = 0; - if (!audit_get_stamp(ab->ctx, &t, &serial)) { t = CURRENT_TIME; serial = 0; @@ -809,13 +842,12 @@ void audit_log_end(struct audit_buffer *ab) /* Log an audit record. This is a convenience function that calls * audit_log_start, audit_log_vformat, and audit_log_end. It may be * called in any context. */ -void audit_log_type(struct audit_context *ctx, int type, int pid, - const char *fmt, ...) +void audit_log(struct audit_context *ctx, int type, const char *fmt, ...) { struct audit_buffer *ab; va_list args; - ab = audit_log_start(ctx, type, pid); + ab = audit_log_start(ctx, type); if (ab) { va_start(args, fmt); audit_log_vformat(ab, fmt, args); diff --git a/kernel/auditsc.c b/kernel/auditsc.c index d089263253a7..1b7c91f9d5ff 100644 --- a/kernel/auditsc.c +++ b/kernel/auditsc.c @@ -286,7 +286,8 @@ int audit_receive_filter(int type, int pid, int uid, int seq, void *data, err = audit_add_rule(entry, &audit_entlist); if (!err && (flags & AUDIT_AT_EXIT)) err = audit_add_rule(entry, &audit_extlist); - audit_log(NULL, "auid %u added an audit rule\n", loginuid); + audit_log(NULL, AUDIT_CONFIG_CHANGE, + "auid %u added an audit rule\n", loginuid); break; case AUDIT_DEL: flags =((struct audit_rule *)data)->flags; @@ -296,7 +297,8 @@ int audit_receive_filter(int type, int pid, int uid, int seq, void *data, err = audit_del_rule(data, &audit_entlist); if (!err && (flags & AUDIT_AT_EXIT)) err = audit_del_rule(data, &audit_extlist); - audit_log(NULL, "auid %u removed an audit rule\n", loginuid); + audit_log(NULL, AUDIT_CONFIG_CHANGE, + "auid %u removed an audit rule\n", loginuid); break; default: return -EINVAL; @@ -648,7 +650,7 @@ static void audit_log_exit(struct audit_context *context) int i; struct audit_buffer *ab; - ab = audit_log_start(context, AUDIT_KERNEL, 0); + ab = audit_log_start(context, AUDIT_SYSCALL); if (!ab) return; /* audit_panic has been called */ audit_log_format(ab, "syscall=%d", context->major); @@ -680,28 +682,28 @@ static void audit_log_exit(struct audit_context *context) while (context->aux) { struct audit_aux_data *aux; - ab = audit_log_start(context, AUDIT_KERNEL, 0); + aux = context->aux; + + ab = audit_log_start(context, aux->type); if (!ab) continue; /* audit_panic has been called */ - aux = context->aux; - context->aux = aux->next; - - audit_log_format(ab, "auxitem=%d", aux->type); switch (aux->type) { - case AUDIT_AUX_IPCPERM: { + case AUDIT_IPC: { struct audit_aux_data_ipcctl *axi = (void *)aux; audit_log_format(ab, - " qbytes=%lx uid=%d gid=%d mode=%x", + " qbytes=%lx iuid=%d igid=%d mode=%x", axi->qbytes, axi->uid, axi->gid, axi->mode); } } audit_log_end(ab); + + context->aux = aux->next; kfree(aux); } for (i = 0; i < context->name_count; i++) { - ab = audit_log_start(context, AUDIT_KERNEL, 0); + ab = audit_log_start(context, AUDIT_PATH); if (!ab) continue; /* audit_panic has been called */ audit_log_format(ab, "item=%d", i); @@ -711,7 +713,7 @@ static void audit_log_exit(struct audit_context *context) } if (context->names[i].ino != (unsigned long)-1) audit_log_format(ab, " inode=%lu dev=%02x:%02x mode=%#o" - " uid=%d gid=%d rdev=%02x:%02x", + " ouid=%d ogid=%d rdev=%02x:%02x", context->names[i].ino, MAJOR(context->names[i].dev), MINOR(context->names[i].dev), @@ -1008,10 +1010,16 @@ int audit_get_stamp(struct audit_context *ctx, int audit_set_loginuid(struct task_struct *task, uid_t loginuid) { if (task->audit_context) { - audit_log_type(NULL, AUDIT_LOGIN, 0, - "login pid=%d uid=%u old loginuid=%u new loginuid=%u", - task->pid, task->uid, task->audit_context->loginuid, - loginuid); + struct audit_buffer *ab; + + ab = audit_log_start(NULL, AUDIT_LOGIN); + if (ab) { + audit_log_format(ab, "login pid=%d uid=%u " + "old loginuid=%u new loginuid=%u", + task->pid, task->uid, + task->audit_context->loginuid, loginuid); + audit_log_end(ab); + } task->audit_context->loginuid = loginuid; } return 0; @@ -1039,7 +1047,7 @@ int audit_ipc_perms(unsigned long qbytes, uid_t uid, gid_t gid, mode_t mode) ax->gid = gid; ax->mode = mode; - ax->d.type = AUDIT_AUX_IPCPERM; + ax->d.type = AUDIT_IPC; ax->d.next = context->aux; context->aux = (void *)ax; return 0; diff --git a/security/selinux/avc.c b/security/selinux/avc.c index 9e71a1bbe011..042f91e9f9d2 100644 --- a/security/selinux/avc.c +++ b/security/selinux/avc.c @@ -242,7 +242,7 @@ void __init avc_init(void) avc_node_cachep = kmem_cache_create("avc_node", sizeof(struct avc_node), 0, SLAB_PANIC, NULL, NULL); - audit_log(current->audit_context, "AVC INITIALIZED\n"); + audit_log(current->audit_context, AUDIT_KERNEL, "AVC INITIALIZED\n"); } int avc_get_hash_stats(char *page) @@ -549,7 +549,7 @@ void avc_audit(u32 ssid, u32 tsid, return; } - ab = audit_log_start(current->audit_context, AUDIT_KERNEL, 0); + ab = audit_log_start(current->audit_context, AUDIT_AVC); if (!ab) return; /* audit_panic has been called */ audit_log_format(ab, "avc: %s ", denied ? "denied" : "granted"); diff --git a/security/selinux/hooks.c b/security/selinux/hooks.c index aae1e794fe48..db845cbd5841 100644 --- a/security/selinux/hooks.c +++ b/security/selinux/hooks.c @@ -3419,7 +3419,7 @@ static int selinux_nlmsg_perm(struct sock *sk, struct sk_buff *skb) err = selinux_nlmsg_lookup(isec->sclass, nlh->nlmsg_type, &perm); if (err) { if (err == -EINVAL) { - audit_log(current->audit_context, + audit_log(current->audit_context, AUDIT_SELINUX_ERR, "SELinux: unrecognized netlink message" " type=%hu for sclass=%hu\n", nlh->nlmsg_type, isec->sclass); diff --git a/security/selinux/nlmsgtab.c b/security/selinux/nlmsgtab.c index deac14367d43..67e77acc4795 100644 --- a/security/selinux/nlmsgtab.c +++ b/security/selinux/nlmsgtab.c @@ -98,6 +98,14 @@ static struct nlmsg_perm nlmsg_audit_perms[] = { AUDIT_DEL, NETLINK_AUDIT_SOCKET__NLMSG_WRITE }, { AUDIT_USER, NETLINK_AUDIT_SOCKET__NLMSG_RELAY }, { AUDIT_SIGNAL_INFO, NETLINK_AUDIT_SOCKET__NLMSG_READ }, + { AUDIT_USER_AUTH, NETLINK_AUDIT_SOCKET__NLMSG_RELAY }, + { AUDIT_USER_ACCT, NETLINK_AUDIT_SOCKET__NLMSG_RELAY }, + { AUDIT_USER_MGMT, NETLINK_AUDIT_SOCKET__NLMSG_RELAY }, + { AUDIT_CRED_ACQ, NETLINK_AUDIT_SOCKET__NLMSG_RELAY }, + { AUDIT_CRED_DISP, NETLINK_AUDIT_SOCKET__NLMSG_RELAY }, + { AUDIT_USER_START, NETLINK_AUDIT_SOCKET__NLMSG_RELAY }, + { AUDIT_USER_END, NETLINK_AUDIT_SOCKET__NLMSG_RELAY }, + { AUDIT_USER_AVC, NETLINK_AUDIT_SOCKET__NLMSG_RELAY }, }; diff --git a/security/selinux/ss/services.c b/security/selinux/ss/services.c index 5a820cf88c9c..07fdf6ee6148 100644 --- a/security/selinux/ss/services.c +++ b/security/selinux/ss/services.c @@ -365,7 +365,7 @@ static int security_validtrans_handle_fail(struct context *ocontext, goto out; if (context_struct_to_string(tcontext, &t, &tlen) < 0) goto out; - audit_log(current->audit_context, + audit_log(current->audit_context, AUDIT_SELINUX_ERR, "security_validate_transition: denied for" " oldcontext=%s newcontext=%s taskcontext=%s tclass=%s", o, n, t, policydb.p_class_val_to_name[tclass-1]); @@ -742,7 +742,7 @@ static int compute_sid_handle_invalid_context( goto out; if (context_struct_to_string(newcontext, &n, &nlen) < 0) goto out; - audit_log(current->audit_context, + audit_log(current->audit_context, AUDIT_SELINUX_ERR, "security_compute_sid: invalid context %s" " for scontext=%s" " tcontext=%s" -- cgit v1.2.3 From 23f32d18aa589e228c5a9e12e0d0c67c9b5bcdce Mon Sep 17 00:00:00 2001 From: Steve Grubb Date: Fri, 13 May 2005 18:35:15 +0100 Subject: AUDIT: Fix some spelling errors I'm going through the kernel code and have a patch that corrects several spelling errors in comments. From: Steve Grubb Signed-off-by: David Woodhouse --- include/linux/audit.h | 2 +- kernel/audit.c | 4 ++-- kernel/auditsc.c | 4 ++-- 3 files changed, 5 insertions(+), 5 deletions(-) (limited to 'include/linux') diff --git a/include/linux/audit.h b/include/linux/audit.h index 1a15ba38c660..51e5879af7fc 100644 --- a/include/linux/audit.h +++ b/include/linux/audit.h @@ -181,7 +181,7 @@ struct audit_message { struct audit_status { __u32 mask; /* Bit mask for valid entries */ - __u32 enabled; /* 1 = enabled, 0 = disbaled */ + __u32 enabled; /* 1 = enabled, 0 = disabled */ __u32 failure; /* Failure-to-log action */ __u32 pid; /* pid of auditd process */ __u32 rate_limit; /* messages rate limit (per second) */ diff --git a/kernel/audit.c b/kernel/audit.c index 4e940c05ede8..74779d3769fa 100644 --- a/kernel/audit.c +++ b/kernel/audit.c @@ -116,7 +116,7 @@ static LIST_HEAD(audit_entlist); static LIST_HEAD(audit_extlist); /* The netlink socket is only to be read by 1 CPU, which lets us assume - * that list additions and deletions never happen simultaneiously in + * that list additions and deletions never happen simultaneously in * auditsc.c */ static DECLARE_MUTEX(audit_netlink_sem); @@ -775,7 +775,7 @@ void audit_log_d_path(struct audit_buffer *ab, const char *prefix, } } -/* Remove queued messages from the audit_txlist and send them to userspace. */ +/* Remove queued messages from the audit_txlist and send them to user space. */ static void audit_tasklet_handler(unsigned long arg) { LIST_HEAD(list); diff --git a/kernel/auditsc.c b/kernel/auditsc.c index 1b7c91f9d5ff..773d28a3f701 100644 --- a/kernel/auditsc.c +++ b/kernel/auditsc.c @@ -444,7 +444,7 @@ static enum audit_state audit_filter_task(struct task_struct *tsk) /* At syscall entry and exit time, this filter is called if the * audit_state is not low enough that auditing cannot take place, but is - * also not high enough that we already know we have to write and audit + * also not high enough that we already know we have to write an audit * record (i.e., the state is AUDIT_SETUP_CONTEXT or AUDIT_BUILD_CONTEXT). */ static enum audit_state audit_filter_syscall(struct task_struct *tsk, @@ -750,7 +750,7 @@ void audit_free(struct task_struct *tsk) /* Compute a serial number for the audit record. Audit records are * written to user-space as soon as they are generated, so a complete * audit record may be written in several pieces. The timestamp of the - * record and this serial number are used by the user-space daemon to + * record and this serial number are used by the user-space tools to * determine which pieces belong to the same audit record. The * (timestamp,serial) tuple is unique for each syscall and is live from * syscall entry to syscall exit. -- cgit v1.2.3 From a1365275e745bb0a173c918a52bcdfa6ce122f7e Mon Sep 17 00:00:00 2001 From: Sascha Hauer Date: Thu, 5 May 2005 15:14:15 -0700 Subject: [PATCH] DM9000 network driver This patch adds support for the davicom dm9000 network driver. The dm9000 is found on some embedded arm boards such as the pimx1 or the scb9328. Signed-off-by: Sascha Hauer Signed-off-by: Ben Dooks Signed-off-by: Andrew Morton diff -puN /dev/null drivers/net/dm9000.c --- drivers/net/Kconfig | 12 + drivers/net/Makefile | 1 + drivers/net/dm9000.c | 1219 ++++++++++++++++++++++++++++++++++++++++++++++++ drivers/net/dm9000.h | 135 ++++++ include/linux/dm9000.h | 36 ++ 5 files changed, 1403 insertions(+) create mode 100644 drivers/net/dm9000.c create mode 100644 drivers/net/dm9000.h create mode 100644 include/linux/dm9000.h (limited to 'include/linux') diff --git a/drivers/net/Kconfig b/drivers/net/Kconfig index 3a0a55b62aaf..4d0c1fb15c7c 100644 --- a/drivers/net/Kconfig +++ b/drivers/net/Kconfig @@ -824,6 +824,18 @@ config SMC9194 . The module will be called smc9194. +config DM9000 + tristate "DM9000 support" + depends on ARM && NET_ETHERNET + select CRC32 + select MII + ---help--- + Support for DM9000 chipset. + + To compile this driver as a module, choose M here and read + . The module will be + called dm9000. + config NET_VENDOR_RACAL bool "Racal-Interlan (Micom) NI cards" depends on NET_ETHERNET && ISA diff --git a/drivers/net/Makefile b/drivers/net/Makefile index 6202b10dbb4d..cbd11688608e 100644 --- a/drivers/net/Makefile +++ b/drivers/net/Makefile @@ -179,6 +179,7 @@ obj-$(CONFIG_AMD8111_ETH) += amd8111e.o obj-$(CONFIG_IBMVETH) += ibmveth.o obj-$(CONFIG_S2IO) += s2io.o obj-$(CONFIG_SMC91X) += smc91x.o +obj-$(CONFIG_DM9000) += dm9000.o obj-$(CONFIG_FEC_8XX) += fec_8xx/ obj-$(CONFIG_ARM) += arm/ diff --git a/drivers/net/dm9000.c b/drivers/net/dm9000.c new file mode 100644 index 000000000000..f4ba0ffb8637 --- /dev/null +++ b/drivers/net/dm9000.c @@ -0,0 +1,1219 @@ +/* + * dm9000.c: Version 1.2 03/18/2003 + * + * A Davicom DM9000 ISA NIC fast Ethernet driver for Linux. + * Copyright (C) 1997 Sten Wang + * + * 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. + * + * This program is distributed in the hope that it will be useful, + * but WITHOUT ANY WARRANTY; without even the implied warranty of + * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the + * GNU General Public License for more details. + * + * (C)Copyright 1997-1998 DAVICOM Semiconductor,Inc. All Rights Reserved. + * + * V0.11 06/20/2001 REG_0A bit3=1, default enable BP with DA match + * 06/22/2001 Support DM9801 progrmming + * E3: R25 = ((R24 + NF) & 0x00ff) | 0xf000 + * E4: R25 = ((R24 + NF) & 0x00ff) | 0xc200 + * R17 = (R17 & 0xfff0) | NF + 3 + * E5: R25 = ((R24 + NF - 3) & 0x00ff) | 0xc200 + * R17 = (R17 & 0xfff0) | NF + * + * v1.00 modify by simon 2001.9.5 + * change for kernel 2.4.x + * + * v1.1 11/09/2001 fix force mode bug + * + * v1.2 03/18/2003 Weilun Huang : + * Fixed phy reset. + * Added tx/rx 32 bit mode. + * Cleaned up for kernel merge. + * + * 03/03/2004 Sascha Hauer + * Port to 2.6 kernel + * + * 24-Sep-2004 Ben Dooks + * Cleanup of code to remove ifdefs + * Allowed platform device data to influence access width + * Reformatting areas of code + * + * 17-Mar-2005 Sascha Hauer + * * removed 2.4 style module parameters + * * removed removed unused stat counter and fixed + * net_device_stats + * * introduced tx_timeout function + * * reworked locking + */ + +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include + +#include +#include +#include + +#include "dm9000.h" + +/* Board/System/Debug information/definition ---------------- */ + +#define DM9000_PHY 0x40 /* PHY address 0x01 */ + +#define TRUE 1 +#define FALSE 0 + +#define CARDNAME "dm9000" +#define PFX CARDNAME ": " + +#define DM9000_TIMER_WUT jiffies+(HZ*2) /* timer wakeup time : 2 second */ + +#define DM9000_DEBUG 0 + +#if DM9000_DEBUG > 2 +#define PRINTK3(args...) printk(CARDNAME ": " args) +#else +#define PRINTK3(args...) do { } while(0) +#endif + +#if DM9000_DEBUG > 1 +#define PRINTK2(args...) printk(CARDNAME ": " args) +#else +#define PRINTK2(args...) do { } while(0) +#endif + +#if DM9000_DEBUG > 0 +#define PRINTK1(args...) printk(CARDNAME ": " args) +#define PRINTK(args...) printk(CARDNAME ": " args) +#else +#define PRINTK1(args...) do { } while(0) +#define PRINTK(args...) printk(KERN_DEBUG args) +#endif + +/* + * Transmit timeout, default 5 seconds. + */ +static int watchdog = 5000; +module_param(watchdog, int, 0400); +MODULE_PARM_DESC(watchdog, "transmit timeout in milliseconds"); + +/* Structure/enum declaration ------------------------------- */ +typedef struct board_info { + + void __iomem *io_addr; /* Register I/O base address */ + void __iomem *io_data; /* Data I/O address */ + u16 irq; /* IRQ */ + + u16 tx_pkt_cnt; + u16 queue_pkt_len; + u16 queue_start_addr; + u16 dbug_cnt; + u8 io_mode; /* 0:word, 2:byte */ + u8 phy_addr; + + void (*inblk)(void __iomem *port, void *data, int length); + void (*outblk)(void __iomem *port, void *data, int length); + void (*dumpblk)(void __iomem *port, int length); + + struct resource *addr_res; /* resources found */ + struct resource *data_res; + struct resource *addr_req; /* resources requested */ + struct resource *data_req; + struct resource *irq_res; + + struct timer_list timer; + struct net_device_stats stats; + unsigned char srom[128]; + spinlock_t lock; + + struct mii_if_info mii; + u32 msg_enable; +} board_info_t; + +/* function declaration ------------------------------------- */ +static int dm9000_probe(struct device *); +static int dm9000_open(struct net_device *); +static int dm9000_start_xmit(struct sk_buff *, struct net_device *); +static int dm9000_stop(struct net_device *); +static int dm9000_do_ioctl(struct net_device *, struct ifreq *, int); + + +static void dm9000_timer(unsigned long); +static void dm9000_init_dm9000(struct net_device *); + +static struct net_device_stats *dm9000_get_stats(struct net_device *); + +static irqreturn_t dm9000_interrupt(int, void *, struct pt_regs *); + +static int dm9000_phy_read(struct net_device *dev, int phyaddr_unsused, int reg); +static void dm9000_phy_write(struct net_device *dev, int phyaddr_unused, int reg, + int value); +static u16 read_srom_word(board_info_t *, int); +static void dm9000_rx(struct net_device *); +static void dm9000_hash_table(struct net_device *); + +//#define DM9000_PROGRAM_EEPROM +#ifdef DM9000_PROGRAM_EEPROM +static void program_eeprom(board_info_t * db); +#endif +/* DM9000 network board routine ---------------------------- */ + +static void +dm9000_reset(board_info_t * db) +{ + PRINTK1("dm9000x: resetting\n"); + /* RESET device */ + writeb(DM9000_NCR, db->io_addr); + udelay(200); + writeb(NCR_RST, db->io_data); + udelay(200); +} + +/* + * Read a byte from I/O port + */ +static u8 +ior(board_info_t * db, int reg) +{ + writeb(reg, db->io_addr); + return readb(db->io_data); +} + +/* + * Write a byte to I/O port + */ + +static void +iow(board_info_t * db, int reg, int value) +{ + writeb(reg, db->io_addr); + writeb(value, db->io_data); +} + +/* routines for sending block to chip */ + +static void dm9000_outblk_8bit(void __iomem *reg, void *data, int count) +{ + writesb(reg, data, count); +} + +static void dm9000_outblk_16bit(void __iomem *reg, void *data, int count) +{ + writesw(reg, data, (count+1) >> 1); +} + +static void dm9000_outblk_32bit(void __iomem *reg, void *data, int count) +{ + writesl(reg, data, (count+3) >> 2); +} + +/* input block from chip to memory */ + +static void dm9000_inblk_8bit(void __iomem *reg, void *data, int count) +{ + readsb(reg, data, count+1); +} + + +static void dm9000_inblk_16bit(void __iomem *reg, void *data, int count) +{ + readsw(reg, data, (count+1) >> 1); +} + +static void dm9000_inblk_32bit(void __iomem *reg, void *data, int count) +{ + readsl(reg, data, (count+3) >> 2); +} + +/* dump block from chip to null */ + +static void dm9000_dumpblk_8bit(void __iomem *reg, int count) +{ + int i; + int tmp; + + for (i = 0; i < count; i++) + tmp = readb(reg); +} + +static void dm9000_dumpblk_16bit(void __iomem *reg, int count) +{ + int i; + int tmp; + + count = (count + 1) >> 1; + + for (i = 0; i < count; i++) + tmp = readw(reg); +} + +static void dm9000_dumpblk_32bit(void __iomem *reg, int count) +{ + int i; + int tmp; + + count = (count + 3) >> 2; + + for (i = 0; i < count; i++) + tmp = readl(reg); +} + +/* dm9000_set_io + * + * select the specified set of io routines to use with the + * device + */ + +static void dm9000_set_io(struct board_info *db, int byte_width) +{ + /* use the size of the data resource to work out what IO + * routines we want to use + */ + + switch (byte_width) { + case 1: + db->dumpblk = dm9000_dumpblk_8bit; + db->outblk = dm9000_outblk_8bit; + db->inblk = dm9000_inblk_8bit; + break; + + case 2: + db->dumpblk = dm9000_dumpblk_16bit; + db->outblk = dm9000_outblk_16bit; + db->inblk = dm9000_inblk_16bit; + break; + + case 3: + printk(KERN_ERR PFX ": 3 byte IO, falling back to 16bit\n"); + db->dumpblk = dm9000_dumpblk_16bit; + db->outblk = dm9000_outblk_16bit; + db->inblk = dm9000_inblk_16bit; + break; + + case 4: + default: + db->dumpblk = dm9000_dumpblk_32bit; + db->outblk = dm9000_outblk_32bit; + db->inblk = dm9000_inblk_32bit; + break; + } +} + + +/* Our watchdog timed out. Called by the networking layer */ +static void dm9000_timeout(struct net_device *dev) +{ + board_info_t *db = (board_info_t *) dev->priv; + u8 reg_save; + unsigned long flags; + + /* Save previous register address */ + reg_save = readb(db->io_addr); + spin_lock_irqsave(db->lock,flags); + + netif_stop_queue(dev); + dm9000_reset(db); + dm9000_init_dm9000(dev); + /* We can accept TX packets again */ + dev->trans_start = jiffies; + netif_wake_queue(dev); + + /* Restore previous register address */ + writeb(reg_save, db->io_addr); + spin_unlock_irqrestore(db->lock,flags); +} + + +/* dm9000_release_board + * + * release a board, and any mapped resources + */ + +static void +dm9000_release_board(struct platform_device *pdev, struct board_info *db) +{ + if (db->data_res == NULL) { + if (db->addr_res != NULL) + release_mem_region((unsigned long)db->io_addr, 4); + return; + } + + /* unmap our resources */ + + iounmap(db->io_addr); + iounmap(db->io_data); + + /* release the resources */ + + if (db->data_req != NULL) { + release_resource(db->data_req); + kfree(db->data_req); + } + + if (db->addr_res != NULL) { + release_resource(db->data_req); + kfree(db->addr_req); + } +} + +#define res_size(_r) (((_r)->end - (_r)->start) + 1) + +/* + * Search DM9000 board, allocate space and register it + */ +static int +dm9000_probe(struct device *dev) +{ + struct platform_device *pdev = to_platform_device(dev); + struct dm9000_plat_data *pdata = pdev->dev.platform_data; + struct board_info *db; /* Point a board information structure */ + struct net_device *ndev; + unsigned long base; + int ret = 0; + int iosize; + int i; + u32 id_val; + + printk(KERN_INFO "%s Ethernet Driver\n", CARDNAME); + + /* Init network device */ + ndev = alloc_etherdev(sizeof (struct board_info)); + if (!ndev) { + printk("%s: could not allocate device.\n", CARDNAME); + return -ENOMEM; + } + + SET_MODULE_OWNER(ndev); + SET_NETDEV_DEV(ndev, dev); + + PRINTK2("dm9000_probe()"); + + /* setup board info structure */ + db = (struct board_info *) ndev->priv; + memset(db, 0, sizeof (*db)); + + if (pdev->num_resources < 2) { + ret = -ENODEV; + goto out; + } + + switch (pdev->num_resources) { + case 2: + base = pdev->resource[0].start; + + if (!request_mem_region(base, 4, ndev->name)) { + ret = -EBUSY; + goto out; + } + + ndev->base_addr = base; + ndev->irq = pdev->resource[1].start; + db->io_addr = (void *)base; + db->io_data = (void *)(base + 4); + + break; + + case 3: + db->addr_res = platform_get_resource(pdev, IORESOURCE_MEM, 0); + db->data_res = platform_get_resource(pdev, IORESOURCE_MEM, 1); + db->irq_res = platform_get_resource(pdev, IORESOURCE_IRQ, 0); + + if (db->addr_res == NULL || db->data_res == NULL) { + printk(KERN_ERR PFX "insufficient resources\n"); + ret = -ENOENT; + goto out; + } + + i = res_size(db->addr_res); + db->addr_req = request_mem_region(db->addr_res->start, i, + pdev->name); + + if (db->addr_req == NULL) { + printk(KERN_ERR PFX "cannot claim address reg area\n"); + ret = -EIO; + goto out; + } + + db->io_addr = ioremap(db->addr_res->start, i); + + if (db->io_addr == NULL) { + printk(KERN_ERR "failed to ioremap address reg\n"); + ret = -EINVAL; + goto out; + } + + iosize = res_size(db->data_res); + db->data_req = request_mem_region(db->data_res->start, iosize, + pdev->name); + + if (db->data_req == NULL) { + printk(KERN_ERR PFX "cannot claim data reg area\n"); + ret = -EIO; + goto out; + } + + db->io_data = ioremap(db->data_res->start, iosize); + + if (db->io_data == NULL) { + printk(KERN_ERR "failed to ioremap data reg\n"); + ret = -EINVAL; + goto out; + } + + /* fill in parameters for net-dev structure */ + + ndev->base_addr = (unsigned long)db->io_addr; + ndev->irq = db->irq_res->start; + + /* ensure at least we have a default set of IO routines */ + dm9000_set_io(db, iosize); + + } + + /* check to see if anything is being over-ridden */ + if (pdata != NULL) { + /* check to see if the driver wants to over-ride the + * default IO width */ + + if (pdata->flags & DM9000_PLATF_8BITONLY) + dm9000_set_io(db, 1); + + if (pdata->flags & DM9000_PLATF_16BITONLY) + dm9000_set_io(db, 2); + + if (pdata->flags & DM9000_PLATF_32BITONLY) + dm9000_set_io(db, 4); + + /* check to see if there are any IO routine + * over-rides */ + + if (pdata->inblk != NULL) + db->inblk = pdata->inblk; + + if (pdata->outblk != NULL) + db->outblk = pdata->outblk; + + if (pdata->dumpblk != NULL) + db->dumpblk = pdata->dumpblk; + } + + dm9000_reset(db); + + /* try two times, DM9000 sometimes gets the first read wrong */ + for (i = 0; i < 2; i++) { + id_val = ior(db, DM9000_VIDL); + id_val |= (u32)ior(db, DM9000_VIDH) << 8; + id_val |= (u32)ior(db, DM9000_PIDL) << 16; + id_val |= (u32)ior(db, DM9000_PIDH) << 24; + + if (id_val == DM9000_ID) + break; + printk("%s: read wrong id 0x%08x\n", CARDNAME, id_val); + } + + if (id_val != DM9000_ID) { + printk("%s: wrong id: 0x%08x\n", CARDNAME, id_val); + goto release; + } + + /* from this point we assume that we have found a DM9000 */ + + /* driver system function */ + ether_setup(ndev); + + ndev->open = &dm9000_open; + ndev->hard_start_xmit = &dm9000_start_xmit; + ndev->tx_timeout = &dm9000_timeout; + ndev->watchdog_timeo = msecs_to_jiffies(watchdog); + ndev->stop = &dm9000_stop; + ndev->get_stats = &dm9000_get_stats; + ndev->set_multicast_list = &dm9000_hash_table; + ndev->do_ioctl = &dm9000_do_ioctl; + +#ifdef DM9000_PROGRAM_EEPROM + program_eeprom(db); +#endif + db->msg_enable = NETIF_MSG_LINK; + db->mii.phy_id_mask = 0x1f; + db->mii.reg_num_mask = 0x1f; + db->mii.force_media = 0; + db->mii.full_duplex = 0; + db->mii.dev = ndev; + db->mii.mdio_read = dm9000_phy_read; + db->mii.mdio_write = dm9000_phy_write; + + /* Read SROM content */ + for (i = 0; i < 64; i++) + ((u16 *) db->srom)[i] = read_srom_word(db, i); + + /* Set Node Address */ + for (i = 0; i < 6; i++) + ndev->dev_addr[i] = db->srom[i]; + + if (!is_valid_ether_addr(ndev->dev_addr)) + printk("%s: Invalid ethernet MAC address. Please " + "set using ifconfig\n", ndev->name); + + dev_set_drvdata(dev, ndev); + ret = register_netdev(ndev); + + if (ret == 0) { + printk("%s: dm9000 at %p,%p IRQ %d MAC: ", + ndev->name, db->io_addr, db->io_data, ndev->irq); + for (i = 0; i < 5; i++) + printk("%02x:", ndev->dev_addr[i]); + printk("%02x\n", ndev->dev_addr[5]); + } + return 0; + + release: + out: + printk("%s: not found (%d).\n", CARDNAME, ret); + + dm9000_release_board(pdev, db); + kfree(ndev); + + return ret; +} + +/* + * Open the interface. + * The interface is opened whenever "ifconfig" actives it. + */ +static int +dm9000_open(struct net_device *dev) +{ + board_info_t *db = (board_info_t *) dev->priv; + + PRINTK2("entering dm9000_open\n"); + + if (request_irq(dev->irq, &dm9000_interrupt, SA_SHIRQ, dev->name, dev)) + return -EAGAIN; + + /* Initialize DM9000 board */ + dm9000_reset(db); + dm9000_init_dm9000(dev); + + /* Init driver variable */ + db->dbug_cnt = 0; + + /* set and active a timer process */ + init_timer(&db->timer); + db->timer.expires = DM9000_TIMER_WUT * 2; + db->timer.data = (unsigned long) dev; + db->timer.function = &dm9000_timer; + add_timer(&db->timer); + + mii_check_media(&db->mii, netif_msg_link(db), 1); + netif_start_queue(dev); + + return 0; +} + +/* + * Initilize dm9000 board + */ +static void +dm9000_init_dm9000(struct net_device *dev) +{ + board_info_t *db = (board_info_t *) dev->priv; + + PRINTK1("entering %s\n",__FUNCTION__); + + /* I/O mode */ + db->io_mode = ior(db, DM9000_ISR) >> 6; /* ISR bit7:6 keeps I/O mode */ + + /* GPIO0 on pre-activate PHY */ + iow(db, DM9000_GPR, 0); /* REG_1F bit0 activate phyxcer */ + iow(db, DM9000_GPCR, GPCR_GEP_CNTL); /* Let GPIO0 output */ + iow(db, DM9000_GPR, 0); /* Enable PHY */ + + /* Program operating register */ + iow(db, DM9000_TCR, 0); /* TX Polling clear */ + iow(db, DM9000_BPTR, 0x3f); /* Less 3Kb, 200us */ + iow(db, DM9000_FCR, 0xff); /* Flow Control */ + iow(db, DM9000_SMCR, 0); /* Special Mode */ + /* clear TX status */ + iow(db, DM9000_NSR, NSR_WAKEST | NSR_TX2END | NSR_TX1END); + iow(db, DM9000_ISR, ISR_CLR_STATUS); /* Clear interrupt status */ + + /* Set address filter table */ + dm9000_hash_table(dev); + + /* Activate DM9000 */ + iow(db, DM9000_RCR, RCR_DIS_LONG | RCR_DIS_CRC | RCR_RXEN); + /* Enable TX/RX interrupt mask */ + iow(db, DM9000_IMR, IMR_PAR | IMR_PTM | IMR_PRM); + + /* Init Driver variable */ + db->tx_pkt_cnt = 0; + db->queue_pkt_len = 0; + dev->trans_start = 0; + spin_lock_init(&db->lock); +} + +/* + * Hardware start transmission. + * Send a packet to media from the upper layer. + */ +static int +dm9000_start_xmit(struct sk_buff *skb, struct net_device *dev) +{ + board_info_t *db = (board_info_t *) dev->priv; + + PRINTK3("dm9000_start_xmit\n"); + + if (db->tx_pkt_cnt > 1) + return 1; + + netif_stop_queue(dev); + + /* Disable all interrupts */ + iow(db, DM9000_IMR, IMR_PAR); + + /* Move data to DM9000 TX RAM */ + writeb(DM9000_MWCMD, db->io_addr); + + (db->outblk)(db->io_data, skb->data, skb->len); + db->stats.tx_bytes += skb->len; + + /* TX control: First packet immediately send, second packet queue */ + if (db->tx_pkt_cnt == 0) { + + /* First Packet */ + db->tx_pkt_cnt++; + + /* Set TX length to DM9000 */ + iow(db, DM9000_TXPLL, skb->len & 0xff); + iow(db, DM9000_TXPLH, (skb->len >> 8) & 0xff); + + /* Issue TX polling command */ + iow(db, DM9000_TCR, TCR_TXREQ); /* Cleared after TX complete */ + + dev->trans_start = jiffies; /* save the time stamp */ + + } else { + /* Second packet */ + db->tx_pkt_cnt++; + db->queue_pkt_len = skb->len; + } + + /* free this SKB */ + dev_kfree_skb(skb); + + /* Re-enable resource check */ + if (db->tx_pkt_cnt == 1) + netif_wake_queue(dev); + + /* Re-enable interrupt */ + iow(db, DM9000_IMR, IMR_PAR | IMR_PTM | IMR_PRM); + + return 0; +} + +static void +dm9000_shutdown(struct net_device *dev) +{ + board_info_t *db = (board_info_t *) dev->priv; + + /* RESET device */ + dm9000_phy_write(dev, 0, MII_BMCR, BMCR_RESET); /* PHY RESET */ + iow(db, DM9000_GPR, 0x01); /* Power-Down PHY */ + iow(db, DM9000_IMR, IMR_PAR); /* Disable all interrupt */ + iow(db, DM9000_RCR, 0x00); /* Disable RX */ +} + +/* + * Stop the interface. + * The interface is stopped when it is brought. + */ +static int +dm9000_stop(struct net_device *ndev) +{ + board_info_t *db = (board_info_t *) ndev->priv; + + PRINTK1("entering %s\n",__FUNCTION__); + + /* deleted timer */ + del_timer(&db->timer); + + netif_stop_queue(ndev); + netif_carrier_off(ndev); + + /* free interrupt */ + free_irq(ndev->irq, ndev); + + dm9000_shutdown(ndev); + + return 0; +} + +/* + * DM9000 interrupt handler + * receive the packet to upper layer, free the transmitted packet + */ + +void +dm9000_tx_done(struct net_device *dev, board_info_t * db) +{ + int tx_status = ior(db, DM9000_NSR); /* Got TX status */ + + if (tx_status & (NSR_TX2END | NSR_TX1END)) { + /* One packet sent complete */ + db->tx_pkt_cnt--; + db->stats.tx_packets++; + + /* Queue packet check & send */ + if (db->tx_pkt_cnt > 0) { + iow(db, DM9000_TXPLL, db->queue_pkt_len & 0xff); + iow(db, DM9000_TXPLH, (db->queue_pkt_len >> 8) & 0xff); + iow(db, DM9000_TCR, TCR_TXREQ); + dev->trans_start = jiffies; + } + netif_wake_queue(dev); + } +} + +static irqreturn_t +dm9000_interrupt(int irq, void *dev_id, struct pt_regs *regs) +{ + struct net_device *dev = dev_id; + board_info_t *db; + int int_status; + u8 reg_save; + + PRINTK3("entering %s\n",__FUNCTION__); + + if (!dev) { + PRINTK1("dm9000_interrupt() without DEVICE arg\n"); + return IRQ_HANDLED; + } + + /* A real interrupt coming */ + db = (board_info_t *) dev->priv; + spin_lock(&db->lock); + + /* Save previous register address */ + reg_save = readb(db->io_addr); + + /* Disable all interrupts */ + iow(db, DM9000_IMR, IMR_PAR); + + /* Got DM9000 interrupt status */ + int_status = ior(db, DM9000_ISR); /* Got ISR */ + iow(db, DM9000_ISR, int_status); /* Clear ISR status */ + + /* Received the coming packet */ + if (int_status & ISR_PRS) + dm9000_rx(dev); + + /* Trnasmit Interrupt check */ + if (int_status & ISR_PTS) + dm9000_tx_done(dev, db); + + /* Re-enable interrupt mask */ + iow(db, DM9000_IMR, IMR_PAR | IMR_PTM | IMR_PRM); + + /* Restore previous register address */ + writeb(reg_save, db->io_addr); + + spin_unlock(&db->lock); + + return IRQ_HANDLED; +} + +/* + * Get statistics from driver. + */ +static struct net_device_stats * +dm9000_get_stats(struct net_device *dev) +{ + board_info_t *db = (board_info_t *) dev->priv; + return &db->stats; +} + +/* + * Process the upper socket ioctl command + */ +static int +dm9000_do_ioctl(struct net_device *dev, struct ifreq *ifr, int cmd) +{ + PRINTK1("entering %s\n",__FUNCTION__); + return 0; +} + +/* + * A periodic timer routine + * Dynamic media sense, allocated Rx buffer... + */ +static void +dm9000_timer(unsigned long data) +{ + struct net_device *dev = (struct net_device *) data; + board_info_t *db = (board_info_t *) dev->priv; + u8 reg_save; + unsigned long flags; + + PRINTK3("dm9000_timer()\n"); + + spin_lock_irqsave(db->lock,flags); + /* Save previous register address */ + reg_save = readb(db->io_addr); + + mii_check_media(&db->mii, netif_msg_link(db), 0); + + /* Restore previous register address */ + writeb(reg_save, db->io_addr); + spin_unlock_irqrestore(db->lock,flags); + + /* Set timer again */ + db->timer.expires = DM9000_TIMER_WUT; + add_timer(&db->timer); +} + +struct dm9000_rxhdr { + u16 RxStatus; + u16 RxLen; +} __attribute__((__packed__)); + +/* + * Received a packet and pass to upper layer + */ +static void +dm9000_rx(struct net_device *dev) +{ + board_info_t *db = (board_info_t *) dev->priv; + struct dm9000_rxhdr rxhdr; + struct sk_buff *skb; + u8 rxbyte, *rdptr; + int GoodPacket; + int RxLen; + + /* Check packet ready or not */ + do { + ior(db, DM9000_MRCMDX); /* Dummy read */ + + /* Get most updated data */ + rxbyte = readb(db->io_data); + + /* Status check: this byte must be 0 or 1 */ + if (rxbyte > DM9000_PKT_RDY) { + printk("status check failed: %d\n", rxbyte); + iow(db, DM9000_RCR, 0x00); /* Stop Device */ + iow(db, DM9000_ISR, IMR_PAR); /* Stop INT request */ + return; + } + + if (rxbyte != DM9000_PKT_RDY) + return; + + /* A packet ready now & Get status/length */ + GoodPacket = TRUE; + writeb(DM9000_MRCMD, db->io_addr); + + (db->inblk)(db->io_data, &rxhdr, sizeof(rxhdr)); + + RxLen = rxhdr.RxLen; + + /* Packet Status check */ + if (RxLen < 0x40) { + GoodPacket = FALSE; + PRINTK1("Bad Packet received (runt)\n"); + } + + if (RxLen > DM9000_PKT_MAX) { + PRINTK1("RST: RX Len:%x\n", RxLen); + } + + if (rxhdr.RxStatus & 0xbf00) { + GoodPacket = FALSE; + if (rxhdr.RxStatus & 0x100) { + PRINTK1("fifo error\n"); + db->stats.rx_fifo_errors++; + } + if (rxhdr.RxStatus & 0x200) { + PRINTK1("crc error\n"); + db->stats.rx_crc_errors++; + } + if (rxhdr.RxStatus & 0x8000) { + PRINTK1("length error\n"); + db->stats.rx_length_errors++; + } + } + + /* Move data from DM9000 */ + if (GoodPacket + && ((skb = dev_alloc_skb(RxLen + 4)) != NULL)) { + skb->dev = dev; + skb_reserve(skb, 2); + rdptr = (u8 *) skb_put(skb, RxLen - 4); + + /* Read received packet from RX SRAM */ + + (db->inblk)(db->io_data, rdptr, RxLen); + db->stats.rx_bytes += RxLen; + + /* Pass to upper layer */ + skb->protocol = eth_type_trans(skb, dev); + netif_rx(skb); + db->stats.rx_packets++; + + } else { + /* need to dump the packet's data */ + + (db->dumpblk)(db->io_data, RxLen); + } + } while (rxbyte == DM9000_PKT_RDY); +} + +/* + * Read a word data from SROM + */ +static u16 +read_srom_word(board_info_t * db, int offset) +{ + iow(db, DM9000_EPAR, offset); + iow(db, DM9000_EPCR, EPCR_ERPRR); + mdelay(8); /* according to the datasheet 200us should be enough, + but it doesn't work */ + iow(db, DM9000_EPCR, 0x0); + return (ior(db, DM9000_EPDRL) + (ior(db, DM9000_EPDRH) << 8)); +} + +#ifdef DM9000_PROGRAM_EEPROM +/* + * Write a word data to SROM + */ +static void +write_srom_word(board_info_t * db, int offset, u16 val) +{ + iow(db, DM9000_EPAR, offset); + iow(db, DM9000_EPDRH, ((val >> 8) & 0xff)); + iow(db, DM9000_EPDRL, (val & 0xff)); + iow(db, DM9000_EPCR, EPCR_WEP | EPCR_ERPRW); + mdelay(8); /* same shit */ + iow(db, DM9000_EPCR, 0); +} + +/* + * Only for development: + * Here we write static data to the eeprom in case + * we don't have valid content on a new board + */ +static void +program_eeprom(board_info_t * db) +{ + u16 eeprom[] = { 0x0c00, 0x007f, 0x1300, /* MAC Address */ + 0x0000, /* Autoload: accept nothing */ + 0x0a46, 0x9000, /* Vendor / Product ID */ + 0x0000, /* pin control */ + 0x0000, + }; /* Wake-up mode control */ + int i; + for (i = 0; i < 8; i++) + write_srom_word(db, i, eeprom[i]); +} +#endif + + +/* + * Calculate the CRC valude of the Rx packet + * flag = 1 : return the reverse CRC (for the received packet CRC) + * 0 : return the normal CRC (for Hash Table index) + */ + +static unsigned long +cal_CRC(unsigned char *Data, unsigned int Len, u8 flag) +{ + + u32 crc = ether_crc_le(Len, Data); + + if (flag) + return ~crc; + + return crc; +} + +/* + * Set DM9000 multicast address + */ +static void +dm9000_hash_table(struct net_device *dev) +{ + board_info_t *db = (board_info_t *) dev->priv; + struct dev_mc_list *mcptr = dev->mc_list; + int mc_cnt = dev->mc_count; + u32 hash_val; + u16 i, oft, hash_table[4]; + unsigned long flags; + + PRINTK2("dm9000_hash_table()\n"); + + spin_lock_irqsave(&db->lock,flags); + + for (i = 0, oft = 0x10; i < 6; i++, oft++) + iow(db, oft, dev->dev_addr[i]); + + /* Clear Hash Table */ + for (i = 0; i < 4; i++) + hash_table[i] = 0x0; + + /* broadcast address */ + hash_table[3] = 0x8000; + + /* the multicast address in Hash Table : 64 bits */ + for (i = 0; i < mc_cnt; i++, mcptr = mcptr->next) { + hash_val = cal_CRC((char *) mcptr->dmi_addr, 6, 0) & 0x3f; + hash_table[hash_val / 16] |= (u16) 1 << (hash_val % 16); + } + + /* Write the hash table to MAC MD table */ + for (i = 0, oft = 0x16; i < 4; i++) { + iow(db, oft++, hash_table[i] & 0xff); + iow(db, oft++, (hash_table[i] >> 8) & 0xff); + } + + spin_unlock_irqrestore(&db->lock,flags); +} + + +/* + * Read a word from phyxcer + */ +static int +dm9000_phy_read(struct net_device *dev, int phy_reg_unused, int reg) +{ + board_info_t *db = (board_info_t *) dev->priv; + unsigned long flags; + int ret; + + spin_lock_irqsave(&db->lock,flags); + /* Fill the phyxcer register into REG_0C */ + iow(db, DM9000_EPAR, DM9000_PHY | reg); + + iow(db, DM9000_EPCR, 0xc); /* Issue phyxcer read command */ + udelay(100); /* Wait read complete */ + iow(db, DM9000_EPCR, 0x0); /* Clear phyxcer read command */ + + /* The read data keeps on REG_0D & REG_0E */ + ret = (ior(db, DM9000_EPDRH) << 8) | ior(db, DM9000_EPDRL); + + spin_unlock_irqrestore(&db->lock,flags); + + return ret; +} + +/* + * Write a word to phyxcer + */ +static void +dm9000_phy_write(struct net_device *dev, int phyaddr_unused, int reg, int value) +{ + board_info_t *db = (board_info_t *) dev->priv; + unsigned long flags; + + spin_lock_irqsave(&db->lock,flags); + + /* Fill the phyxcer register into REG_0C */ + iow(db, DM9000_EPAR, DM9000_PHY | reg); + + /* Fill the written data into REG_0D & REG_0E */ + iow(db, DM9000_EPDRL, (value & 0xff)); + iow(db, DM9000_EPDRH, ((value >> 8) & 0xff)); + + iow(db, DM9000_EPCR, 0xa); /* Issue phyxcer write command */ + udelay(500); /* Wait write complete */ + iow(db, DM9000_EPCR, 0x0); /* Clear phyxcer write command */ + + spin_unlock_irqrestore(&db->lock,flags); +} + +static int +dm9000_drv_suspend(struct device *dev, u32 state, u32 level) +{ + struct net_device *ndev = dev_get_drvdata(dev); + + if (ndev && level == SUSPEND_DISABLE) { + if (netif_running(ndev)) { + netif_device_detach(ndev); + dm9000_shutdown(ndev); + } + } + return 0; +} + +static int +dm9000_drv_resume(struct device *dev, u32 level) +{ + struct net_device *ndev = dev_get_drvdata(dev); + board_info_t *db = (board_info_t *) ndev->priv; + + if (ndev && level == RESUME_ENABLE) { + + if (netif_running(ndev)) { + dm9000_reset(db); + dm9000_init_dm9000(ndev); + + netif_device_attach(ndev); + } + } + return 0; +} + +static int +dm9000_drv_remove(struct device *dev) +{ + struct platform_device *pdev = to_platform_device(dev); + struct net_device *ndev = dev_get_drvdata(dev); + + dev_set_drvdata(dev, NULL); + + unregister_netdev(ndev); + dm9000_release_board(pdev, (board_info_t *) ndev->priv); + kfree(ndev); /* free device structure */ + + PRINTK1("clean_module() exit\n"); + + return 0; +} + +static struct device_driver dm9000_driver = { + .name = "dm9000", + .bus = &platform_bus_type, + .probe = dm9000_probe, + .remove = dm9000_drv_remove, + .suspend = dm9000_drv_suspend, + .resume = dm9000_drv_resume, +}; + +static int __init +dm9000_init(void) +{ + return driver_register(&dm9000_driver); /* search board and register */ +} + +static void __exit +dm9000_cleanup(void) +{ + driver_unregister(&dm9000_driver); +} + +module_init(dm9000_init); +module_exit(dm9000_cleanup); + +MODULE_AUTHOR("Sascha Hauer, Ben Dooks"); +MODULE_DESCRIPTION("Davicom DM9000 network driver"); +MODULE_LICENSE("GPL"); diff --git a/drivers/net/dm9000.h b/drivers/net/dm9000.h new file mode 100644 index 000000000000..82cad360bafc --- /dev/null +++ b/drivers/net/dm9000.h @@ -0,0 +1,135 @@ +/* + * dm9000 Ethernet + */ + +#ifndef _DM9000X_H_ +#define _DM9000X_H_ + +#define DM9000_ID 0x90000A46 + +/* although the registers are 16 bit, they are 32-bit aligned. + */ + +#define DM9000_NCR 0x00 +#define DM9000_NSR 0x01 +#define DM9000_TCR 0x02 +#define DM9000_TSR1 0x03 +#define DM9000_TSR2 0x04 +#define DM9000_RCR 0x05 +#define DM9000_RSR 0x06 +#define DM9000_ROCR 0x07 +#define DM9000_BPTR 0x08 +#define DM9000_FCTR 0x09 +#define DM9000_FCR 0x0A +#define DM9000_EPCR 0x0B +#define DM9000_EPAR 0x0C +#define DM9000_EPDRL 0x0D +#define DM9000_EPDRH 0x0E +#define DM9000_WCR 0x0F + +#define DM9000_PAR 0x10 +#define DM9000_MAR 0x16 + +#define DM9000_GPCR 0x1e +#define DM9000_GPR 0x1f +#define DM9000_TRPAL 0x22 +#define DM9000_TRPAH 0x23 +#define DM9000_RWPAL 0x24 +#define DM9000_RWPAH 0x25 + +#define DM9000_VIDL 0x28 +#define DM9000_VIDH 0x29 +#define DM9000_PIDL 0x2A +#define DM9000_PIDH 0x2B + +#define DM9000_CHIPR 0x2C +#define DM9000_SMCR 0x2F + +#define DM9000_MRCMDX 0xF0 +#define DM9000_MRCMD 0xF2 +#define DM9000_MRRL 0xF4 +#define DM9000_MRRH 0xF5 +#define DM9000_MWCMDX 0xF6 +#define DM9000_MWCMD 0xF8 +#define DM9000_MWRL 0xFA +#define DM9000_MWRH 0xFB +#define DM9000_TXPLL 0xFC +#define DM9000_TXPLH 0xFD +#define DM9000_ISR 0xFE +#define DM9000_IMR 0xFF + +#define NCR_EXT_PHY (1<<7) +#define NCR_WAKEEN (1<<6) +#define NCR_FCOL (1<<4) +#define NCR_FDX (1<<3) +#define NCR_LBK (3<<1) +#define NCR_RST (1<<0) + +#define NSR_SPEED (1<<7) +#define NSR_LINKST (1<<6) +#define NSR_WAKEST (1<<5) +#define NSR_TX2END (1<<3) +#define NSR_TX1END (1<<2) +#define NSR_RXOV (1<<1) + +#define TCR_TJDIS (1<<6) +#define TCR_EXCECM (1<<5) +#define TCR_PAD_DIS2 (1<<4) +#define TCR_CRC_DIS2 (1<<3) +#define TCR_PAD_DIS1 (1<<2) +#define TCR_CRC_DIS1 (1<<1) +#define TCR_TXREQ (1<<0) + +#define TSR_TJTO (1<<7) +#define TSR_LC (1<<6) +#define TSR_NC (1<<5) +#define TSR_LCOL (1<<4) +#define TSR_COL (1<<3) +#define TSR_EC (1<<2) + +#define RCR_WTDIS (1<<6) +#define RCR_DIS_LONG (1<<5) +#define RCR_DIS_CRC (1<<4) +#define RCR_ALL (1<<3) +#define RCR_RUNT (1<<2) +#define RCR_PRMSC (1<<1) +#define RCR_RXEN (1<<0) + +#define RSR_RF (1<<7) +#define RSR_MF (1<<6) +#define RSR_LCS (1<<5) +#define RSR_RWTO (1<<4) +#define RSR_PLE (1<<3) +#define RSR_AE (1<<2) +#define RSR_CE (1<<1) +#define RSR_FOE (1<<0) + +#define FCTR_HWOT(ot) (( ot & 0xf ) << 4 ) +#define FCTR_LWOT(ot) ( ot & 0xf ) + +#define IMR_PAR (1<<7) +#define IMR_ROOM (1<<3) +#define IMR_ROM (1<<2) +#define IMR_PTM (1<<1) +#define IMR_PRM (1<<0) + +#define ISR_ROOS (1<<3) +#define ISR_ROS (1<<2) +#define ISR_PTS (1<<1) +#define ISR_PRS (1<<0) +#define ISR_CLR_STATUS (ISR_ROOS | ISR_ROS | ISR_PTS | ISR_PRS) + +#define EPCR_REEP (1<<5) +#define EPCR_WEP (1<<4) +#define EPCR_EPOS (1<<3) +#define EPCR_ERPRR (1<<2) +#define EPCR_ERPRW (1<<1) +#define EPCR_ERRE (1<<0) + +#define GPCR_GEP_CNTL (1<<0) + +#define DM9000_PKT_RDY 0x01 /* Packet ready to receive */ +#define DM9000_PKT_MAX 1536 /* Received packet max size */ + +#endif /* _DM9000X_H_ */ + diff --git a/include/linux/dm9000.h b/include/linux/dm9000.h new file mode 100644 index 000000000000..0008e2ad0c9f --- /dev/null +++ b/include/linux/dm9000.h @@ -0,0 +1,36 @@ +/* include/linux/dm9000.h + * + * Copyright (c) 2004 Simtec Electronics + * Ben Dooks + * + * Header file for dm9000 platform data + * + * This program is free software; you can redistribute it and/or modify + * it under the terms of the GNU General Public License version 2 as + * published by the Free Software Foundation. + * +*/ + +#ifndef __DM9000_PLATFORM_DATA +#define __DM9000_PLATFORM_DATA __FILE__ + +/* IO control flags */ + +#define DM9000_PLATF_8BITONLY (0x0001) +#define DM9000_PLATF_16BITONLY (0x0002) +#define DM9000_PLATF_32BITONLY (0x0004) + +/* platfrom data for platfrom device structure's platfrom_data field */ + +struct dm9000_plat_data { + unsigned int flags; + + /* allow replacement IO routines */ + + void (*inblk)(void __iomem *reg, void *data, int len); + void (*outblk)(void __iomem *reg, void *data, int len); + void (*dumpblk)(void __iomem *reg, int len); +}; + +#endif /* __DM9000_PLATFORM_DATA */ + -- cgit v1.2.3 From b3dd65f958354226275522b5a64157834bdc5415 Mon Sep 17 00:00:00 2001 From: Krzysztof Halasa Date: Thu, 21 Apr 2005 15:57:25 +0200 Subject: [PATCH] Generic HDLC update The attached patch updates generic HDLC to version 1.18. FR Cisco LMI production-tested. Please apply to Linux 2.6. Thanks. Changes: - doc updates - added Cisco LMI support to Frame-Relay code - cleaned hdlc_fr.c a bit, removed some orphaned #defines etc. - fixed a problem with non-functional LMI in FR DCE mode. - changed diagnostic messages to better conform to FR standards - all protocols: information about carrier changes (DCD line) is now printed to kernel logs. Signed-Off-By: Krzysztof Halasa --- Documentation/networking/generic-hdlc.txt | 51 ++--- drivers/net/wan/hdlc_fr.c | 320 ++++++++++++++++-------------- drivers/net/wan/hdlc_generic.c | 16 +- include/linux/hdlc.h | 4 +- 4 files changed, 216 insertions(+), 175 deletions(-) (limited to 'include/linux') diff --git a/Documentation/networking/generic-hdlc.txt b/Documentation/networking/generic-hdlc.txt index 7d1dc6b884f3..31bc8b759b75 100644 --- a/Documentation/networking/generic-hdlc.txt +++ b/Documentation/networking/generic-hdlc.txt @@ -1,21 +1,21 @@ Generic HDLC layer Krzysztof Halasa -January, 2003 Generic HDLC layer currently supports: -- Frame Relay (ANSI, CCITT and no LMI), with ARP support (no InARP). - Normal (routed) and Ethernet-bridged (Ethernet device emulation) - interfaces can share a single PVC. -- raw HDLC - either IP (IPv4) interface or Ethernet device emulation. -- Cisco HDLC, -- PPP (uses syncppp.c), -- X.25 (uses X.25 routines). - -There are hardware drivers for the following cards: -- C101 by Moxa Technologies Co., Ltd. -- RISCom/N2 by SDL Communications Inc. -- and others, some not in the official kernel. +1. Frame Relay (ANSI, CCITT, Cisco and no LMI). + - Normal (routed) and Ethernet-bridged (Ethernet device emulation) + interfaces can share a single PVC. + - ARP support (no InARP support in the kernel - there is an + experimental InARP user-space daemon available on: + http://www.kernel.org/pub/linux/utils/net/hdlc/). +2. raw HDLC - either IP (IPv4) interface or Ethernet device emulation. +3. Cisco HDLC. +4. PPP (uses syncppp.c). +5. X.25 (uses X.25 routines). + +Generic HDLC is a protocol driver only - it needs a low-level driver +for your particular hardware. Ethernet device emulation (using HDLC or Frame-Relay PVC) is compatible with IEEE 802.1Q (VLANs) and 802.1D (Ethernet bridging). @@ -24,7 +24,7 @@ with IEEE 802.1Q (VLANs) and 802.1D (Ethernet bridging). Make sure the hdlc.o and the hardware driver are loaded. It should create a number of "hdlc" (hdlc0 etc) network devices, one for each WAN port. You'll need the "sethdlc" utility, get it from: - http://hq.pm.waw.pl/hdlc/ + http://www.kernel.org/pub/linux/utils/net/hdlc/ Compile sethdlc.c utility: gcc -O2 -Wall -o sethdlc sethdlc.c @@ -52,12 +52,12 @@ Setting interface: * v35 | rs232 | x21 | t1 | e1 - sets physical interface for a given port if the card has software-selectable interfaces loopback - activate hardware loopback (for testing only) -* clock ext - external clock (uses DTE RX and TX clock) -* clock int - internal clock (provides clock signal on DCE clock output) -* clock txint - TX internal, RX external (provides TX clock on DCE output) -* clock txfromrx - TX clock derived from RX clock (TX clock on DCE output) -* rate - sets clock rate in bps (not required for external clock or - for txfromrx) +* clock ext - both RX clock and TX clock external +* clock int - both RX clock and TX clock internal +* clock txint - RX clock external, TX clock internal +* clock txfromrx - RX clock external, TX clock derived from RX clock +* rate - sets clock rate in bps (for "int" or "txint" clock only) + Setting protocol: @@ -79,7 +79,7 @@ Setting protocol: * x25 - sets X.25 mode * fr - Frame Relay mode - lmi ansi / ccitt / none - LMI (link management) type + lmi ansi / ccitt / cisco / none - LMI (link management) type dce - Frame Relay DCE (network) side LMI instead of default DTE (user). It has nothing to do with clocks! t391 - link integrity verification polling timer (in seconds) - user @@ -119,13 +119,14 @@ or -If you have a problem with N2 or C101 card, you can issue the "private" -command to see port's packet descriptor rings (in kernel logs): +If you have a problem with N2, C101 or PLX200SYN card, you can issue the +"private" command to see port's packet descriptor rings (in kernel logs): sethdlc hdlc0 private -The hardware driver has to be build with CONFIG_HDLC_DEBUG_RINGS. +The hardware driver has to be build with #define DEBUG_RINGS. Attaching this info to bug reports would be helpful. Anyway, let me know if you have problems using this. -For patches and other info look at http://hq.pm.waw.pl/hdlc/ +For patches and other info look at: +. diff --git a/drivers/net/wan/hdlc_fr.c b/drivers/net/wan/hdlc_fr.c index 7f450b51a6cb..a5d6891c9d4c 100644 --- a/drivers/net/wan/hdlc_fr.c +++ b/drivers/net/wan/hdlc_fr.c @@ -2,7 +2,7 @@ * Generic HDLC support routines for Linux * Frame Relay support * - * Copyright (C) 1999 - 2003 Krzysztof Halasa + * Copyright (C) 1999 - 2005 Krzysztof Halasa * * This program is free software; you can redistribute it and/or modify it * under the terms of version 2 of the GNU General Public License @@ -27,6 +27,10 @@ active = open and "link reliable" exist = new = not used + CCITT LMI: ITU-T Q.933 Annex A + ANSI LMI: ANSI T1.617 Annex D + CISCO LMI: the original, aka "Gang of Four" LMI + */ #include @@ -49,45 +53,41 @@ #undef DEBUG_ECN #undef DEBUG_LINK -#define MAXLEN_LMISTAT 20 /* max size of status enquiry frame */ - -#define PVC_STATE_NEW 0x01 -#define PVC_STATE_ACTIVE 0x02 -#define PVC_STATE_FECN 0x08 /* FECN condition */ -#define PVC_STATE_BECN 0x10 /* BECN condition */ - - -#define FR_UI 0x03 -#define FR_PAD 0x00 - -#define NLPID_IP 0xCC -#define NLPID_IPV6 0x8E -#define NLPID_SNAP 0x80 -#define NLPID_PAD 0x00 -#define NLPID_Q933 0x08 - - -#define LMI_DLCI 0 /* LMI DLCI */ -#define LMI_PROTO 0x08 -#define LMI_CALLREF 0x00 /* Call Reference */ -#define LMI_ANSI_LOCKSHIFT 0x95 /* ANSI lockshift */ -#define LMI_REPTYPE 1 /* report type */ -#define LMI_CCITT_REPTYPE 0x51 -#define LMI_ALIVE 3 /* keep alive */ -#define LMI_CCITT_ALIVE 0x53 -#define LMI_PVCSTAT 7 /* pvc status */ -#define LMI_CCITT_PVCSTAT 0x57 -#define LMI_FULLREP 0 /* full report */ -#define LMI_INTEGRITY 1 /* link integrity report */ -#define LMI_SINGLE 2 /* single pvc report */ +#define FR_UI 0x03 +#define FR_PAD 0x00 + +#define NLPID_IP 0xCC +#define NLPID_IPV6 0x8E +#define NLPID_SNAP 0x80 +#define NLPID_PAD 0x00 +#define NLPID_CCITT_ANSI_LMI 0x08 +#define NLPID_CISCO_LMI 0x09 + + +#define LMI_CCITT_ANSI_DLCI 0 /* LMI DLCI */ +#define LMI_CISCO_DLCI 1023 + +#define LMI_CALLREF 0x00 /* Call Reference */ +#define LMI_ANSI_LOCKSHIFT 0x95 /* ANSI locking shift */ +#define LMI_ANSI_CISCO_REPTYPE 0x01 /* report type */ +#define LMI_CCITT_REPTYPE 0x51 +#define LMI_ANSI_CISCO_ALIVE 0x03 /* keep alive */ +#define LMI_CCITT_ALIVE 0x53 +#define LMI_ANSI_CISCO_PVCSTAT 0x07 /* PVC status */ +#define LMI_CCITT_PVCSTAT 0x57 + +#define LMI_FULLREP 0x00 /* full report */ +#define LMI_INTEGRITY 0x01 /* link integrity report */ +#define LMI_SINGLE 0x02 /* single PVC report */ + #define LMI_STATUS_ENQUIRY 0x75 #define LMI_STATUS 0x7D /* reply */ #define LMI_REPT_LEN 1 /* report type element length */ #define LMI_INTEG_LEN 2 /* link integrity element length */ -#define LMI_LENGTH 13 /* standard LMI frame length */ -#define LMI_ANSI_LENGTH 14 +#define LMI_CCITT_CISCO_LENGTH 13 /* LMI frame lengths */ +#define LMI_ANSI_LENGTH 14 typedef struct { @@ -223,51 +223,34 @@ static inline struct net_device** get_dev_p(pvc_device *pvc, int type) } -static inline u16 status_to_dlci(u8 *status, int *active, int *new) -{ - *new = (status[2] & 0x08) ? 1 : 0; - *active = (status[2] & 0x02) ? 1 : 0; - - return ((status[0] & 0x3F) << 4) | ((status[1] & 0x78) >> 3); -} - - -static inline void dlci_to_status(u16 dlci, u8 *status, int active, int new) -{ - status[0] = (dlci >> 4) & 0x3F; - status[1] = ((dlci << 3) & 0x78) | 0x80; - status[2] = 0x80; - - if (new) - status[2] |= 0x08; - else if (active) - status[2] |= 0x02; -} - - - static int fr_hard_header(struct sk_buff **skb_p, u16 dlci) { u16 head_len; struct sk_buff *skb = *skb_p; switch (skb->protocol) { - case __constant_ntohs(ETH_P_IP): + case __constant_ntohs(NLPID_CCITT_ANSI_LMI): head_len = 4; skb_push(skb, head_len); - skb->data[3] = NLPID_IP; + skb->data[3] = NLPID_CCITT_ANSI_LMI; break; - case __constant_ntohs(ETH_P_IPV6): + case __constant_ntohs(NLPID_CISCO_LMI): head_len = 4; skb_push(skb, head_len); - skb->data[3] = NLPID_IPV6; + skb->data[3] = NLPID_CISCO_LMI; break; - case __constant_ntohs(LMI_PROTO): + case __constant_ntohs(ETH_P_IP): + head_len = 4; + skb_push(skb, head_len); + skb->data[3] = NLPID_IP; + break; + + case __constant_ntohs(ETH_P_IPV6): head_len = 4; skb_push(skb, head_len); - skb->data[3] = LMI_PROTO; + skb->data[3] = NLPID_IPV6; break; case __constant_ntohs(ETH_P_802_3): @@ -461,13 +444,14 @@ static void fr_lmi_send(struct net_device *dev, int fullrep) hdlc_device *hdlc = dev_to_hdlc(dev); struct sk_buff *skb; pvc_device *pvc = hdlc->state.fr.first_pvc; - int len = (hdlc->state.fr.settings.lmi == LMI_ANSI) ? LMI_ANSI_LENGTH - : LMI_LENGTH; - int stat_len = 3; + int lmi = hdlc->state.fr.settings.lmi; + int dce = hdlc->state.fr.settings.dce; + int len = lmi == LMI_ANSI ? LMI_ANSI_LENGTH : LMI_CCITT_CISCO_LENGTH; + int stat_len = (lmi == LMI_CISCO) ? 6 : 3; u8 *data; int i = 0; - if (hdlc->state.fr.settings.dce && fullrep) { + if (dce && fullrep) { len += hdlc->state.fr.dce_pvc_count * (2 + stat_len); if (len > HDLC_MAX_MRU) { printk(KERN_WARNING "%s: Too many PVCs while sending " @@ -484,29 +468,31 @@ static void fr_lmi_send(struct net_device *dev, int fullrep) } memset(skb->data, 0, len); skb_reserve(skb, 4); - skb->protocol = __constant_htons(LMI_PROTO); - fr_hard_header(&skb, LMI_DLCI); + if (lmi == LMI_CISCO) { + skb->protocol = __constant_htons(NLPID_CISCO_LMI); + fr_hard_header(&skb, LMI_CISCO_DLCI); + } else { + skb->protocol = __constant_htons(NLPID_CCITT_ANSI_LMI); + fr_hard_header(&skb, LMI_CCITT_ANSI_DLCI); + } data = skb->tail; data[i++] = LMI_CALLREF; - data[i++] = hdlc->state.fr.settings.dce - ? LMI_STATUS : LMI_STATUS_ENQUIRY; - if (hdlc->state.fr.settings.lmi == LMI_ANSI) + data[i++] = dce ? LMI_STATUS : LMI_STATUS_ENQUIRY; + if (lmi == LMI_ANSI) data[i++] = LMI_ANSI_LOCKSHIFT; - data[i++] = (hdlc->state.fr.settings.lmi == LMI_CCITT) - ? LMI_CCITT_REPTYPE : LMI_REPTYPE; + data[i++] = lmi == LMI_CCITT ? LMI_CCITT_REPTYPE : + LMI_ANSI_CISCO_REPTYPE; data[i++] = LMI_REPT_LEN; data[i++] = fullrep ? LMI_FULLREP : LMI_INTEGRITY; - - data[i++] = (hdlc->state.fr.settings.lmi == LMI_CCITT) - ? LMI_CCITT_ALIVE : LMI_ALIVE; + data[i++] = lmi == LMI_CCITT ? LMI_CCITT_ALIVE : LMI_ANSI_CISCO_ALIVE; data[i++] = LMI_INTEG_LEN; data[i++] = hdlc->state.fr.txseq =fr_lmi_nextseq(hdlc->state.fr.txseq); data[i++] = hdlc->state.fr.rxseq; - if (hdlc->state.fr.settings.dce && fullrep) { + if (dce && fullrep) { while (pvc) { - data[i++] = (hdlc->state.fr.settings.lmi == LMI_CCITT) - ? LMI_CCITT_PVCSTAT : LMI_PVCSTAT; + data[i++] = lmi == LMI_CCITT ? LMI_CCITT_PVCSTAT : + LMI_ANSI_CISCO_PVCSTAT; data[i++] = stat_len; /* LMI start/restart */ @@ -523,8 +509,20 @@ static void fr_lmi_send(struct net_device *dev, int fullrep) fr_log_dlci_active(pvc); } - dlci_to_status(pvc->dlci, data + i, - pvc->state.active, pvc->state.new); + if (lmi == LMI_CISCO) { + data[i] = pvc->dlci >> 8; + data[i + 1] = pvc->dlci & 0xFF; + } else { + data[i] = (pvc->dlci >> 4) & 0x3F; + data[i + 1] = ((pvc->dlci << 3) & 0x78) | 0x80; + data[i + 2] = 0x80; + } + + if (pvc->state.new) + data[i + 2] |= 0x08; + else if (pvc->state.active) + data[i + 2] |= 0x02; + i += stat_len; pvc = pvc->next; } @@ -569,6 +567,8 @@ static void fr_set_link_state(int reliable, struct net_device *dev) pvc_carrier(0, pvc); pvc->state.exist = pvc->state.active = 0; pvc->state.new = 0; + if (!hdlc->state.fr.settings.dce) + pvc->state.bandwidth = 0; pvc = pvc->next; } } @@ -583,11 +583,12 @@ static void fr_timer(unsigned long arg) int i, cnt = 0, reliable; u32 list; - if (hdlc->state.fr.settings.dce) + if (hdlc->state.fr.settings.dce) { reliable = hdlc->state.fr.request && time_before(jiffies, hdlc->state.fr.last_poll + hdlc->state.fr.settings.t392 * HZ); - else { + hdlc->state.fr.request = 0; + } else { hdlc->state.fr.last_errors <<= 1; /* Shift the list */ if (hdlc->state.fr.request) { if (hdlc->state.fr.reliable) @@ -634,65 +635,88 @@ static void fr_timer(unsigned long arg) static int fr_lmi_recv(struct net_device *dev, struct sk_buff *skb) { hdlc_device *hdlc = dev_to_hdlc(dev); - int stat_len; pvc_device *pvc; - int reptype = -1, error, no_ram; u8 rxseq, txseq; - int i; + int lmi = hdlc->state.fr.settings.lmi; + int dce = hdlc->state.fr.settings.dce; + int stat_len = (lmi == LMI_CISCO) ? 6 : 3, reptype, error, no_ram, i; - if (skb->len < ((hdlc->state.fr.settings.lmi == LMI_ANSI) - ? LMI_ANSI_LENGTH : LMI_LENGTH)) { + if (skb->len < (lmi == LMI_ANSI ? LMI_ANSI_LENGTH : + LMI_CCITT_CISCO_LENGTH)) { printk(KERN_INFO "%s: Short LMI frame\n", dev->name); return 1; } - if (skb->data[5] != (!hdlc->state.fr.settings.dce ? - LMI_STATUS : LMI_STATUS_ENQUIRY)) { - printk(KERN_INFO "%s: LMI msgtype=%x, Not LMI status %s\n", - dev->name, skb->data[2], - hdlc->state.fr.settings.dce ? "enquiry" : "reply"); + if (skb->data[3] != (lmi == LMI_CISCO ? NLPID_CISCO_LMI : + NLPID_CCITT_ANSI_LMI)) { + printk(KERN_INFO "%s: Received non-LMI frame with LMI" + " DLCI\n", dev->name); + return 1; + } + + if (skb->data[4] != LMI_CALLREF) { + printk(KERN_INFO "%s: Invalid LMI Call reference (0x%02X)\n", + dev->name, skb->data[4]); + return 1; + } + + if (skb->data[5] != (dce ? LMI_STATUS_ENQUIRY : LMI_STATUS)) { + printk(KERN_INFO "%s: Invalid LMI Message type (0x%02X)\n", + dev->name, skb->data[5]); return 1; } - i = (hdlc->state.fr.settings.lmi == LMI_ANSI) ? 7 : 6; + if (lmi == LMI_ANSI) { + if (skb->data[6] != LMI_ANSI_LOCKSHIFT) { + printk(KERN_INFO "%s: Not ANSI locking shift in LMI" + " message (0x%02X)\n", dev->name, skb->data[6]); + return 1; + } + i = 7; + } else + i = 6; - if (skb->data[i] != - ((hdlc->state.fr.settings.lmi == LMI_CCITT) - ? LMI_CCITT_REPTYPE : LMI_REPTYPE)) { - printk(KERN_INFO "%s: Not a report type=%x\n", + if (skb->data[i] != (lmi == LMI_CCITT ? LMI_CCITT_REPTYPE : + LMI_ANSI_CISCO_REPTYPE)) { + printk(KERN_INFO "%s: Not an LMI Report type IE (0x%02X)\n", dev->name, skb->data[i]); return 1; } - i++; - i++; /* Skip length field */ + if (skb->data[++i] != LMI_REPT_LEN) { + printk(KERN_INFO "%s: Invalid LMI Report type IE length" + " (%u)\n", dev->name, skb->data[i]); + return 1; + } - reptype = skb->data[i++]; + reptype = skb->data[++i]; + if (reptype != LMI_INTEGRITY && reptype != LMI_FULLREP) { + printk(KERN_INFO "%s: Unsupported LMI Report type (0x%02X)\n", + dev->name, reptype); + return 1; + } - if (skb->data[i]!= - ((hdlc->state.fr.settings.lmi == LMI_CCITT) - ? LMI_CCITT_ALIVE : LMI_ALIVE)) { - printk(KERN_INFO "%s: Unsupported status element=%x\n", - dev->name, skb->data[i]); + if (skb->data[++i] != (lmi == LMI_CCITT ? LMI_CCITT_ALIVE : + LMI_ANSI_CISCO_ALIVE)) { + printk(KERN_INFO "%s: Not an LMI Link integrity verification" + " IE (0x%02X)\n", dev->name, skb->data[i]); return 1; } - i++; - i++; /* Skip length field */ + if (skb->data[++i] != LMI_INTEG_LEN) { + printk(KERN_INFO "%s: Invalid LMI Link integrity verification" + " IE length (%u)\n", dev->name, skb->data[i]); + return 1; + } + i++; hdlc->state.fr.rxseq = skb->data[i++]; /* TX sequence from peer */ rxseq = skb->data[i++]; /* Should confirm our sequence */ txseq = hdlc->state.fr.txseq; - if (hdlc->state.fr.settings.dce) { - if (reptype != LMI_FULLREP && reptype != LMI_INTEGRITY) { - printk(KERN_INFO "%s: Unsupported report type=%x\n", - dev->name, reptype); - return 1; - } + if (dce) hdlc->state.fr.last_poll = jiffies; - } error = 0; if (!hdlc->state.fr.reliable) @@ -703,7 +727,7 @@ static int fr_lmi_recv(struct net_device *dev, struct sk_buff *skb) error = 1; } - if (hdlc->state.fr.settings.dce) { + if (dce) { if (hdlc->state.fr.fullrep_sent && !error) { /* Stop sending full report - the last one has been confirmed by DTE */ hdlc->state.fr.fullrep_sent = 0; @@ -725,6 +749,7 @@ static int fr_lmi_recv(struct net_device *dev, struct sk_buff *skb) hdlc->state.fr.dce_changed = 0; } + hdlc->state.fr.request = 1; /* got request */ fr_lmi_send(dev, reptype == LMI_FULLREP ? 1 : 0); return 0; } @@ -739,7 +764,6 @@ static int fr_lmi_recv(struct net_device *dev, struct sk_buff *skb) if (reptype != LMI_FULLREP) return 0; - stat_len = 3; pvc = hdlc->state.fr.first_pvc; while (pvc) { @@ -750,24 +774,35 @@ static int fr_lmi_recv(struct net_device *dev, struct sk_buff *skb) no_ram = 0; while (skb->len >= i + 2 + stat_len) { u16 dlci; + u32 bw; unsigned int active, new; - if (skb->data[i] != ((hdlc->state.fr.settings.lmi == LMI_CCITT) - ? LMI_CCITT_PVCSTAT : LMI_PVCSTAT)) { - printk(KERN_WARNING "%s: Invalid PVCSTAT ID: %x\n", - dev->name, skb->data[i]); + if (skb->data[i] != (lmi == LMI_CCITT ? LMI_CCITT_PVCSTAT : + LMI_ANSI_CISCO_PVCSTAT)) { + printk(KERN_INFO "%s: Not an LMI PVC status IE" + " (0x%02X)\n", dev->name, skb->data[i]); return 1; } - i++; - if (skb->data[i] != stat_len) { - printk(KERN_WARNING "%s: Invalid PVCSTAT length: %x\n", - dev->name, skb->data[i]); + if (skb->data[++i] != stat_len) { + printk(KERN_INFO "%s: Invalid LMI PVC status IE length" + " (%u)\n", dev->name, skb->data[i]); return 1; } i++; - dlci = status_to_dlci(skb->data + i, &active, &new); + new = !! (skb->data[i + 2] & 0x08); + active = !! (skb->data[i + 2] & 0x02); + if (lmi == LMI_CISCO) { + dlci = (skb->data[i] << 8) | skb->data[i + 1]; + bw = (skb->data[i + 3] << 16) | + (skb->data[i + 4] << 8) | + (skb->data[i + 5]); + } else { + dlci = ((skb->data[i] & 0x3F) << 4) | + ((skb->data[i + 1] & 0x78) >> 3); + bw = 0; + } pvc = add_pvc(dev, dlci); @@ -783,9 +818,11 @@ static int fr_lmi_recv(struct net_device *dev, struct sk_buff *skb) pvc->state.deleted = 0; if (active != pvc->state.active || new != pvc->state.new || + bw != pvc->state.bandwidth || !pvc->state.exist) { pvc->state.new = new; pvc->state.active = active; + pvc->state.bandwidth = bw; pvc_carrier(active, pvc); fr_log_dlci_active(pvc); } @@ -801,6 +838,7 @@ static int fr_lmi_recv(struct net_device *dev, struct sk_buff *skb) pvc_carrier(0, pvc); pvc->state.active = pvc->state.new = 0; pvc->state.exist = 0; + pvc->state.bandwidth = 0; fr_log_dlci_active(pvc); } pvc = pvc->next; @@ -829,22 +867,15 @@ static int fr_rx(struct sk_buff *skb) dlci = q922_to_dlci(skb->data); - if (dlci == LMI_DLCI) { - if (hdlc->state.fr.settings.lmi == LMI_NONE) - goto rx_error; /* LMI packet with no LMI? */ - - if (data[3] == LMI_PROTO) { - if (fr_lmi_recv(ndev, skb)) - goto rx_error; - else { - dev_kfree_skb_any(skb); - return NET_RX_SUCCESS; - } - } - - printk(KERN_INFO "%s: Received non-LMI frame with LMI DLCI\n", - ndev->name); - goto rx_error; + if ((dlci == LMI_CCITT_ANSI_DLCI && + (hdlc->state.fr.settings.lmi == LMI_ANSI || + hdlc->state.fr.settings.lmi == LMI_CCITT)) || + (dlci == LMI_CISCO_DLCI && + hdlc->state.fr.settings.lmi == LMI_CISCO)) { + if (fr_lmi_recv(ndev, skb)) + goto rx_error; + dev_kfree_skb_any(skb); + return NET_RX_SUCCESS; } pvc = find_pvc(hdlc, dlci); @@ -1170,7 +1201,8 @@ int hdlc_fr_ioctl(struct net_device *dev, struct ifreq *ifr) if ((new_settings.lmi != LMI_NONE && new_settings.lmi != LMI_ANSI && - new_settings.lmi != LMI_CCITT) || + new_settings.lmi != LMI_CCITT && + new_settings.lmi != LMI_CISCO) || new_settings.t391 < 1 || new_settings.t392 < 2 || new_settings.n391 < 1 || diff --git a/drivers/net/wan/hdlc_generic.c b/drivers/net/wan/hdlc_generic.c index 6ed064cb4469..a63f6a2cc4f7 100644 --- a/drivers/net/wan/hdlc_generic.c +++ b/drivers/net/wan/hdlc_generic.c @@ -1,7 +1,7 @@ /* * Generic HDLC support routines for Linux * - * Copyright (C) 1999 - 2003 Krzysztof Halasa + * Copyright (C) 1999 - 2005 Krzysztof Halasa * * This program is free software; you can redistribute it and/or modify it * under the terms of version 2 of the GNU General Public License @@ -38,7 +38,7 @@ #include -static const char* version = "HDLC support module revision 1.17"; +static const char* version = "HDLC support module revision 1.18"; #undef DEBUG_LINK @@ -126,10 +126,13 @@ void hdlc_set_carrier(int on, struct net_device *dev) if (!hdlc->open) goto carrier_exit; - if (hdlc->carrier) + if (hdlc->carrier) { + printk(KERN_INFO "%s: Carrier detected\n", dev->name); __hdlc_set_carrier_on(dev); - else + } else { + printk(KERN_INFO "%s: Carrier lost\n", dev->name); __hdlc_set_carrier_off(dev); + } carrier_exit: spin_unlock_irqrestore(&hdlc->state_lock, flags); @@ -157,8 +160,11 @@ int hdlc_open(struct net_device *dev) spin_lock_irq(&hdlc->state_lock); - if (hdlc->carrier) + if (hdlc->carrier) { + printk(KERN_INFO "%s: Carrier detected\n", dev->name); __hdlc_set_carrier_on(dev); + } else + printk(KERN_INFO "%s: No carrier\n", dev->name); hdlc->open = 1; diff --git a/include/linux/hdlc.h b/include/linux/hdlc.h index 503194e62fe1..ed2927ef1ff7 100644 --- a/include/linux/hdlc.h +++ b/include/linux/hdlc.h @@ -1,7 +1,7 @@ /* * Generic HDLC support routines for Linux * - * Copyright (C) 1999-2003 Krzysztof Halasa + * Copyright (C) 1999-2005 Krzysztof Halasa * * This program is free software; you can redistribute it and/or modify it * under the terms of version 2 of the GNU General Public License @@ -41,6 +41,7 @@ #define LMI_NONE 1 /* No LMI, all PVCs are static */ #define LMI_ANSI 2 /* ANSI Annex D */ #define LMI_CCITT 3 /* ITU-T Annex A */ +#define LMI_CISCO 4 /* The "original" LMI, aka Gang of Four */ #define HDLC_MAX_MTU 1500 /* Ethernet 1500 bytes */ #define HDLC_MAX_MRU (HDLC_MAX_MTU + 10 + 14 + 4) /* for ETH+VLAN over FR */ @@ -89,6 +90,7 @@ typedef struct pvc_device_struct { unsigned int deleted: 1; unsigned int fecn: 1; unsigned int becn: 1; + unsigned int bandwidth; /* Cisco LMI reporting only */ }state; }pvc_device; -- cgit v1.2.3 From 3ec3b2fba526ead2fa3f3d7c91924f39a0733749 Mon Sep 17 00:00:00 2001 From: David Woodhouse Date: Tue, 17 May 2005 12:08:48 +0100 Subject: AUDIT: Capture sys_socketcall arguments and sockaddrs Signed-off-by: David Woodhouse --- include/linux/audit.h | 7 ++++- kernel/auditsc.c | 73 +++++++++++++++++++++++++++++++++++++++++++++++++-- net/socket.c | 9 +++++-- 3 files changed, 84 insertions(+), 5 deletions(-) (limited to 'include/linux') diff --git a/include/linux/audit.h b/include/linux/audit.h index 51e5879af7fc..2f5dc60f8bbd 100644 --- a/include/linux/audit.h +++ b/include/linux/audit.h @@ -69,8 +69,9 @@ #define AUDIT_FS_WATCH 1301 /* Filesystem watch event */ #define AUDIT_PATH 1302 /* Filname path information */ #define AUDIT_IPC 1303 /* IPC record */ -#define AUDIT_SOCKET 1304 /* Socket record */ +#define AUDIT_SOCKETCALL 1304 /* sys_socketcall arguments */ #define AUDIT_CONFIG_CHANGE 1305 /* Audit system configuration change */ +#define AUDIT_SOCKADDR 1306 /* sockaddr copied as syscall arg */ #define AUDIT_AVC 1400 /* SE Linux avc denial or grant */ #define AUDIT_SELINUX_ERR 1401 /* Internal SE Linux Errors */ @@ -235,6 +236,8 @@ extern int audit_get_stamp(struct audit_context *ctx, extern int audit_set_loginuid(struct task_struct *task, uid_t loginuid); extern uid_t audit_get_loginuid(struct audit_context *ctx); extern int audit_ipc_perms(unsigned long qbytes, uid_t uid, gid_t gid, mode_t mode); +extern int audit_socketcall(int nargs, unsigned long *args); +extern int audit_sockaddr(int len, void *addr); extern void audit_signal_info(int sig, struct task_struct *t); #else #define audit_alloc(t) ({ 0; }) @@ -248,6 +251,8 @@ extern void audit_signal_info(int sig, struct task_struct *t); #define audit_get_stamp(c,t,s) ({ 0; }) #define audit_get_loginuid(c) ({ -1; }) #define audit_ipc_perms(q,u,g,m) ({ 0; }) +#define audit_socketcall(n,a) ({ 0; }) +#define audit_sockaddr(len, addr) ({ 0; }) #define audit_signal_info(s,t) do { ; } while (0) #endif diff --git a/kernel/auditsc.c b/kernel/auditsc.c index 773d28a3f701..818778d5b6ad 100644 --- a/kernel/auditsc.c +++ b/kernel/auditsc.c @@ -34,7 +34,7 @@ #include #include #include - +#include #include #include #include @@ -112,6 +112,18 @@ struct audit_aux_data_ipcctl { mode_t mode; }; +struct audit_aux_data_socketcall { + struct audit_aux_data d; + int nargs; + unsigned long args[0]; +}; + +struct audit_aux_data_sockaddr { + struct audit_aux_data d; + int len; + char a[0]; +}; + /* The per-task audit context. */ struct audit_context { @@ -694,7 +706,22 @@ static void audit_log_exit(struct audit_context *context) audit_log_format(ab, " qbytes=%lx iuid=%d igid=%d mode=%x", axi->qbytes, axi->uid, axi->gid, axi->mode); - } + break; } + + case AUDIT_SOCKETCALL: { + int i; + struct audit_aux_data_socketcall *axs = (void *)aux; + audit_log_format(ab, "nargs=%d", axs->nargs); + for (i=0; inargs; i++) + audit_log_format(ab, " a%d=%lx", i, axs->args[i]); + break; } + + case AUDIT_SOCKADDR: { + struct audit_aux_data_sockaddr *axs = (void *)aux; + + audit_log_format(ab, "saddr="); + audit_log_hex(ab, axs->a, axs->len); + break; } } audit_log_end(ab); @@ -1053,6 +1080,48 @@ int audit_ipc_perms(unsigned long qbytes, uid_t uid, gid_t gid, mode_t mode) return 0; } +int audit_socketcall(int nargs, unsigned long *args) +{ + struct audit_aux_data_socketcall *ax; + struct audit_context *context = current->audit_context; + + if (likely(!context)) + return 0; + + ax = kmalloc(sizeof(*ax) + nargs * sizeof(unsigned long), GFP_KERNEL); + if (!ax) + return -ENOMEM; + + ax->nargs = nargs; + memcpy(ax->args, args, nargs * sizeof(unsigned long)); + + ax->d.type = AUDIT_SOCKETCALL; + ax->d.next = context->aux; + context->aux = (void *)ax; + return 0; +} + +int audit_sockaddr(int len, void *a) +{ + struct audit_aux_data_sockaddr *ax; + struct audit_context *context = current->audit_context; + + if (likely(!context)) + return 0; + + ax = kmalloc(sizeof(*ax) + len, GFP_KERNEL); + if (!ax) + return -ENOMEM; + + ax->len = len; + memcpy(ax->a, a, len); + + ax->d.type = AUDIT_SOCKADDR; + ax->d.next = context->aux; + context->aux = (void *)ax; + return 0; +} + void audit_signal_info(int sig, struct task_struct *t) { extern pid_t audit_sig_pid; diff --git a/net/socket.c b/net/socket.c index cec0cb38b9ce..6b7c3b51a7c1 100644 --- a/net/socket.c +++ b/net/socket.c @@ -81,6 +81,7 @@ #include #include #include +#include #ifdef CONFIG_NET_RADIO #include /* Note : will define WIRELESS_EXT */ @@ -226,7 +227,7 @@ int move_addr_to_kernel(void __user *uaddr, int ulen, void *kaddr) return 0; if(copy_from_user(kaddr,uaddr,ulen)) return -EFAULT; - return 0; + return audit_sockaddr(ulen, kaddr); } /** @@ -1906,7 +1907,11 @@ asmlinkage long sys_socketcall(int call, unsigned long __user *args) /* copy_from_user should be SMP safe. */ if (copy_from_user(a, args, nargs[call])) return -EFAULT; - + + err = audit_socketcall(nargs[call]/sizeof(unsigned long), args); + if (err) + return err; + a0=a[0]; a1=a[1]; -- cgit v1.2.3 From 209aba03243ee42a22f8df8d08aa9963f62aec64 Mon Sep 17 00:00:00 2001 From: David Woodhouse Date: Wed, 18 May 2005 10:21:07 +0100 Subject: AUDIT: Treat all user messages identically. It's silly to have to add explicit entries for new userspace messages as we invent them. Just treat all messages in the user range the same. Signed-off-by: David Woodhouse --- include/linux/audit.h | 17 ++--------------- kernel/audit.c | 20 ++------------------ security/selinux/nlmsgtab.c | 17 +++++++---------- 3 files changed, 11 insertions(+), 43 deletions(-) (limited to 'include/linux') diff --git a/include/linux/audit.h b/include/linux/audit.h index 2f5dc60f8bbd..17ea5d522d81 100644 --- a/include/linux/audit.h +++ b/include/linux/audit.h @@ -51,14 +51,8 @@ #define AUDIT_WATCH_LIST 1009 /* List all file/dir watches */ #define AUDIT_SIGNAL_INFO 1010 /* Get info about sender of signal to auditd */ -#define AUDIT_USER_AUTH 1100 /* User space authentication */ -#define AUDIT_USER_ACCT 1101 /* User space acct change */ -#define AUDIT_USER_MGMT 1102 /* User space acct management */ -#define AUDIT_CRED_ACQ 1103 /* User space credential acquired */ -#define AUDIT_CRED_DISP 1104 /* User space credential disposed */ -#define AUDIT_USER_START 1105 /* User space session start */ -#define AUDIT_USER_END 1106 /* User space session end */ -#define AUDIT_USER_AVC 1107 /* User space avc message */ +#define AUDIT_FIRST_USER_MSG 1100 /* Userspace messages uninteresting to kernel */ +#define AUDIT_LAST_USER_MSG 1199 #define AUDIT_DAEMON_START 1200 /* Daemon startup record */ #define AUDIT_DAEMON_END 1201 /* Daemon normal stop record */ @@ -173,13 +167,6 @@ #define AUDIT_ARCH_V850 (EM_V850|__AUDIT_ARCH_LE) #define AUDIT_ARCH_X86_64 (EM_X86_64|__AUDIT_ARCH_64BIT|__AUDIT_ARCH_LE) -#ifndef __KERNEL__ -struct audit_message { - struct nlmsghdr nlh; - char data[1200]; -}; -#endif - struct audit_status { __u32 mask; /* Bit mask for valid entries */ __u32 enabled; /* 1 = enabled, 0 = disabled */ diff --git a/kernel/audit.c b/kernel/audit.c index a0e33b6897d7..e6d88635032c 100644 --- a/kernel/audit.c +++ b/kernel/audit.c @@ -325,15 +325,7 @@ static int audit_netlink_ok(kernel_cap_t eff_cap, u16 msg_type) if (!cap_raised(eff_cap, CAP_AUDIT_CONTROL)) err = -EPERM; break; - case AUDIT_USER: - case AUDIT_USER_AUTH: - case AUDIT_USER_ACCT: - case AUDIT_USER_MGMT: - case AUDIT_CRED_ACQ: - case AUDIT_CRED_DISP: - case AUDIT_USER_START: - case AUDIT_USER_END: - case AUDIT_USER_AVC: + case AUDIT_FIRST_USER_MSG...AUDIT_LAST_USER_MSG: if (!cap_raised(eff_cap, CAP_AUDIT_WRITE)) err = -EPERM; break; @@ -402,15 +394,7 @@ static int audit_receive_msg(struct sk_buff *skb, struct nlmsghdr *nlh) audit_set_backlog_limit(status_get->backlog_limit, loginuid); break; - case AUDIT_USER: - case AUDIT_USER_AUTH: - case AUDIT_USER_ACCT: - case AUDIT_USER_MGMT: - case AUDIT_CRED_ACQ: - case AUDIT_CRED_DISP: - case AUDIT_USER_START: - case AUDIT_USER_END: - case AUDIT_USER_AVC: + case AUDIT_FIRST_USER_MSG...AUDIT_LAST_USER_MSG: ab = audit_log_start(NULL, msg_type); if (!ab) break; /* audit_panic has been called */ diff --git a/security/selinux/nlmsgtab.c b/security/selinux/nlmsgtab.c index 67e77acc4795..f0fb6d76f7c5 100644 --- a/security/selinux/nlmsgtab.c +++ b/security/selinux/nlmsgtab.c @@ -98,14 +98,6 @@ static struct nlmsg_perm nlmsg_audit_perms[] = { AUDIT_DEL, NETLINK_AUDIT_SOCKET__NLMSG_WRITE }, { AUDIT_USER, NETLINK_AUDIT_SOCKET__NLMSG_RELAY }, { AUDIT_SIGNAL_INFO, NETLINK_AUDIT_SOCKET__NLMSG_READ }, - { AUDIT_USER_AUTH, NETLINK_AUDIT_SOCKET__NLMSG_RELAY }, - { AUDIT_USER_ACCT, NETLINK_AUDIT_SOCKET__NLMSG_RELAY }, - { AUDIT_USER_MGMT, NETLINK_AUDIT_SOCKET__NLMSG_RELAY }, - { AUDIT_CRED_ACQ, NETLINK_AUDIT_SOCKET__NLMSG_RELAY }, - { AUDIT_CRED_DISP, NETLINK_AUDIT_SOCKET__NLMSG_RELAY }, - { AUDIT_USER_START, NETLINK_AUDIT_SOCKET__NLMSG_RELAY }, - { AUDIT_USER_END, NETLINK_AUDIT_SOCKET__NLMSG_RELAY }, - { AUDIT_USER_AVC, NETLINK_AUDIT_SOCKET__NLMSG_RELAY }, }; @@ -150,8 +142,13 @@ int selinux_nlmsg_lookup(u16 sclass, u16 nlmsg_type, u32 *perm) break; case SECCLASS_NETLINK_AUDIT_SOCKET: - err = nlmsg_perm(nlmsg_type, perm, nlmsg_audit_perms, - sizeof(nlmsg_audit_perms)); + if (nlmsg_type >= AUDIT_FIRST_USER_MSG && + nlmsg_type <= AUDIT_LAST_USER_MSG) { + *perm = NETLINK_AUDIT_SOCKET__NLMSG_RELAY; + } else { + err = nlmsg_perm(nlmsg_type, perm, nlmsg_audit_perms, + sizeof(nlmsg_audit_perms)); + } break; /* No messaging from userspace, or class unknown/unhandled */ -- cgit v1.2.3 From 867d1191fca388a79e4bb500dd85a9e871c96b99 Mon Sep 17 00:00:00 2001 From: Tejun Heo Date: Sun, 24 Apr 2005 02:06:05 -0500 Subject: [SCSI] remove requeue feature from blk_insert_request() blk_insert_request() has a unobivous feature of requeuing a request setting REQ_SPECIAL|REQ_SOFTBARRIER. SCSI midlayer was the only user and as previous patches removed the usage, remove the feature from blk_insert_request(). Only special requests should be queued with blk_insert_request(). All requeueing should go through blk_requeue_request(). Signed-off-by: Tejun Heo Signed-off-by: James Bottomley --- drivers/block/ll_rw_blk.c | 20 ++++++-------------- drivers/block/paride/pd.c | 2 +- drivers/block/sx8.c | 4 ++-- drivers/scsi/scsi_lib.c | 2 +- include/linux/blkdev.h | 2 +- 5 files changed, 11 insertions(+), 19 deletions(-) (limited to 'include/linux') diff --git a/drivers/block/ll_rw_blk.c b/drivers/block/ll_rw_blk.c index 11ef9d9ea139..f20eba22b14b 100644 --- a/drivers/block/ll_rw_blk.c +++ b/drivers/block/ll_rw_blk.c @@ -2038,7 +2038,6 @@ EXPORT_SYMBOL(blk_requeue_request); * @rq: request to be inserted * @at_head: insert request at head or tail of queue * @data: private data - * @reinsert: true if request it a reinsertion of previously processed one * * Description: * Many block devices need to execute commands asynchronously, so they don't @@ -2053,8 +2052,9 @@ EXPORT_SYMBOL(blk_requeue_request); * host that is unable to accept a particular command. */ void blk_insert_request(request_queue_t *q, struct request *rq, - int at_head, void *data, int reinsert) + int at_head, void *data) { + int where = at_head ? ELEVATOR_INSERT_FRONT : ELEVATOR_INSERT_BACK; unsigned long flags; /* @@ -2071,20 +2071,12 @@ void blk_insert_request(request_queue_t *q, struct request *rq, /* * If command is tagged, release the tag */ - if (reinsert) - blk_requeue_request(q, rq); - else { - int where = ELEVATOR_INSERT_BACK; - - if (at_head) - where = ELEVATOR_INSERT_FRONT; + if (blk_rq_tagged(rq)) + blk_queue_end_tag(q, rq); - if (blk_rq_tagged(rq)) - blk_queue_end_tag(q, rq); + drive_stat_acct(rq, rq->nr_sectors, 1); + __elv_add_request(q, rq, where, 0); - drive_stat_acct(rq, rq->nr_sectors, 1); - __elv_add_request(q, rq, where, 0); - } if (blk_queue_plugged(q)) __generic_unplug_device(q); else diff --git a/drivers/block/paride/pd.c b/drivers/block/paride/pd.c index 202a5a74ad37..fa49d62626ba 100644 --- a/drivers/block/paride/pd.c +++ b/drivers/block/paride/pd.c @@ -723,7 +723,7 @@ static int pd_special_command(struct pd_unit *disk, rq.ref_count = 1; rq.waiting = &wait; rq.end_io = blk_end_sync_rq; - blk_insert_request(disk->gd->queue, &rq, 0, func, 0); + blk_insert_request(disk->gd->queue, &rq, 0, func); wait_for_completion(&wait); rq.waiting = NULL; if (rq.errors) diff --git a/drivers/block/sx8.c b/drivers/block/sx8.c index 797f5988c2b5..5ed3a6379452 100644 --- a/drivers/block/sx8.c +++ b/drivers/block/sx8.c @@ -614,7 +614,7 @@ static int carm_array_info (struct carm_host *host, unsigned int array_idx) spin_unlock_irq(&host->lock); DPRINTK("blk_insert_request, tag == %u\n", idx); - blk_insert_request(host->oob_q, crq->rq, 1, crq, 0); + blk_insert_request(host->oob_q, crq->rq, 1, crq); return 0; @@ -653,7 +653,7 @@ static int carm_send_special (struct carm_host *host, carm_sspc_t func) crq->msg_bucket = (u32) rc; DPRINTK("blk_insert_request, tag == %u\n", idx); - blk_insert_request(host->oob_q, crq->rq, 1, crq, 0); + blk_insert_request(host->oob_q, crq->rq, 1, crq); return 0; } diff --git a/drivers/scsi/scsi_lib.c b/drivers/scsi/scsi_lib.c index 861d5f5c9722..47a4ad40bf4e 100644 --- a/drivers/scsi/scsi_lib.c +++ b/drivers/scsi/scsi_lib.c @@ -92,7 +92,7 @@ int scsi_insert_special_req(struct scsi_request *sreq, int at_head) */ sreq->sr_request->flags &= ~REQ_DONTPREP; blk_insert_request(sreq->sr_device->request_queue, sreq->sr_request, - at_head, sreq, 0); + at_head, sreq); return 0; } diff --git a/include/linux/blkdev.h b/include/linux/blkdev.h index ef1afc178c0a..4a99b76c5a33 100644 --- a/include/linux/blkdev.h +++ b/include/linux/blkdev.h @@ -544,7 +544,7 @@ extern void blk_end_sync_rq(struct request *rq); extern void blk_attempt_remerge(request_queue_t *, struct request *); extern void __blk_attempt_remerge(request_queue_t *, struct request *); extern struct request *blk_get_request(request_queue_t *, int, int); -extern void blk_insert_request(request_queue_t *, struct request *, int, void *, int); +extern void blk_insert_request(request_queue_t *, struct request *, int, void *); extern void blk_requeue_request(request_queue_t *, struct request *); extern void blk_plug_device(request_queue_t *); extern int blk_remove_plug(request_queue_t *); -- cgit v1.2.3 From daa6eda65a53e5addf86c6bc829129ff51b08bda Mon Sep 17 00:00:00 2001 From: Gerd Knorr Date: Tue, 10 May 2005 10:59:13 +0200 Subject: [SCSI] add scsi changer driver This patch adds a device driver for scsi media changer devices. Signed-off-by: Gerd Knorr Signed-off-by: James Bottomley --- Documentation/scsi/scsi-changer.txt | 180 ++++++ drivers/scsi/Kconfig | 18 + drivers/scsi/Makefile | 1 + drivers/scsi/ch.c | 1025 +++++++++++++++++++++++++++++++++++ include/linux/chio.h | 168 ++++++ include/linux/major.h | 1 + include/scsi/scsi.h | 3 + 7 files changed, 1396 insertions(+) create mode 100644 Documentation/scsi/scsi-changer.txt create mode 100644 drivers/scsi/ch.c create mode 100644 include/linux/chio.h (limited to 'include/linux') diff --git a/Documentation/scsi/scsi-changer.txt b/Documentation/scsi/scsi-changer.txt new file mode 100644 index 000000000000..c132687b017a --- /dev/null +++ b/Documentation/scsi/scsi-changer.txt @@ -0,0 +1,180 @@ + +README for the SCSI media changer driver +======================================== + +This is a driver for SCSI Medium Changer devices, which are listed +with "Type: Medium Changer" in /proc/scsi/scsi. + +This is for *real* Jukeboxes. It is *not* supported to work with +common small CD-ROM changers, neither one-lun-per-slot SCSI changers +nor IDE drives. + +Userland tools available from here: + http://linux.bytesex.org/misc/changer.html + + +General Information +------------------- + +First some words about how changers work: A changer has 2 (possibly +more) SCSI ID's. One for the changer device which controls the robot, +and one for the device which actually reads and writes the data. The +later may be anything, a MOD, a CD-ROM, a tape or whatever. For the +changer device this is a "don't care", he *only* shuffles around the +media, nothing else. + + +The SCSI changer model is complex, compared to - for example - IDE-CD +changers. But it allows to handle nearly all possible cases. It knows +4 different types of changer elements: + + media transport - this one shuffles around the media, i.e. the + transport arm. Also known as "picker". + storage - a slot which can hold a media. + import/export - the same as above, but is accessable from outside, + i.e. there the operator (you !) can use this to + fill in and remove media from the changer. + Sometimes named "mailslot". + data transfer - this is the device which reads/writes, i.e. the + CD-ROM / Tape / whatever drive. + +None of these is limited to one: A huge Jukebox could have slots for +123 CD-ROM's, 5 CD-ROM readers (and therefore 6 SCSI ID's: the changer +and each CD-ROM) and 2 transport arms. No problem to handle. + + +How it is implemented +--------------------- + +I implemented the driver as character device driver with a NetBSD-like +ioctl interface. Just grabbed NetBSD's header file and one of the +other linux SCSI device drivers as starting point. The interface +should be source code compatible with NetBSD. So if there is any +software (anybody knows ???) which supports a BSDish changer driver, +it should work with this driver too. + +Over time a few more ioctls where added, volume tag support for example +wasn't covered by the NetBSD ioctl API. + + +Current State +------------- + +Support for more than one transport arm is not implemented yet (and +nobody asked for it so far...). + +I test and use the driver myself with a 35 slot cdrom jukebox from +Grundig. I got some reports telling it works ok with tape autoloaders +(Exabyte, HP and DEC). Some People use this driver with amanda. It +works fine with small (11 slots) and a huge (4 MOs, 88 slots) +magneto-optical Jukebox. Probably with lots of other changers too, most +(but not all :-) people mail me only if it does *not* work... + +I don't have any device lists, neither black-list nor white-list. Thus +it is quite useless to ask me whenever a specific device is supported or +not. In theory every changer device which supports the SCSI-2 media +changer command set should work out-of-the-box with this driver. If it +doesn't, it is a bug. Either within the driver or within the firmware +of the changer device. + + +Using it +-------- + +This is a character device with major number is 86, so use +"mknod /dev/sch0 c 86 0" to create the special file for the driver. + +If the module finds the changer, it prints some messages about the +device [ try "dmesg" if you don't see anything ] and should show up in +/proc/devices. If not.... some changers use ID ? / LUN 0 for the +device and ID ? / LUN 1 for the robot mechanism. But Linux does *not* +look for LUN's other than 0 as default, becauce there are to many +broken devices. So you can try: + + 1) echo "scsi add-single-device 0 0 ID 1" > /proc/scsi/scsi + (replace ID with the SCSI-ID of the device) + 2) boot the kernel with "max_scsi_luns=1" on the command line + (append="max_scsi_luns=1" in lilo.conf should do the trick) + + +Trouble? +-------- + +If you insmod the driver with "insmod debug=1", it will be verbose and +prints a lot of stuff to the syslog. Compiling the kernel with +CONFIG_SCSI_CONSTANTS=y improves the quality of the error messages alot +because the kernel will translate the error codes into human-readable +strings then. + +You can display these messages with the dmesg command (or check the +logfiles). If you email me some question becauce of a problem with the +driver, please include these messages. + + +Insmod options +-------------- + +debug=0/1 + Enable debug messages (see above, default: 0). + +verbose=0/1 + Be verbose (default: 1). + +init=0/1 + Send INITIALIZE ELEMENT STATUS command to the changer + at insmod time (default: 1). + +timeout_init= + timeout for the INITIALIZE ELEMENT STATUS command + (default: 3600). + +timeout_move= + timeout for all other commands (default: 120). + +dt_id=,,... +dt_lun=,,... + These two allow to specify the SCSI ID and LUN for the data + transfer elements. You likely don't need this as the jukebox + should provide this information. But some devices don't ... + +vendor_firsts= +vendor_counts= +vendor_labels= + These insmod options can be used to tell the driver that there + are some vendor-specific element types. Grundig for example + does this. Some jukeboxes have a printer to label fresh burned + CDs, which is addressed as element 0xc000 (type 5). To tell the + driver about this vendor-specific element, use this: + $ insmod ch \ + vendor_firsts=0xc000 \ + vendor_counts=1 \ + vendor_labels=printer + All three insmod options accept up to four comma-separated + values, this way you can configure the element types 5-8. + You likely need the SCSI specs for the device in question to + find the correct values as they are not covered by the SCSI-2 + standard. + + +Credits +------- + +I wrote this driver using the famous mailing-patches-around-the-world +method. With (more or less) help from: + + Daniel Moehwald + Dane Jasper + R. Scott Bailey + Jonathan Corbet + +Special thanks go to + Martin Kuehne +for a old, second-hand (but full functional) cdrom jukebox which I use +to develop/test driver and tools now. + +Have fun, + + Gerd + +-- +Gerd Knorr diff --git a/drivers/scsi/Kconfig b/drivers/scsi/Kconfig index 2ef5aee86b29..ba88be399a59 100644 --- a/drivers/scsi/Kconfig +++ b/drivers/scsi/Kconfig @@ -137,6 +137,24 @@ config CHR_DEV_SG If unsure, say N. +config CHR_DEV_SCH + tristate "SCSI media changer support" + depends on SCSI + ---help--- + This is a driver for SCSI media changers. Most common devices are + tape libraries and MOD/CDROM jukeboxes. *Real* jukeboxes, you + don't need this for those tiny 6-slot cdrom changers. Media + changers are listed as "Type: Medium Changer" in /proc/scsi/scsi. + If you have such hardware and want to use it with linux, say Y + here. Check for details. + + If you want to compile this as a module ( = code which can be + inserted in and removed from the running kernel whenever you want), + say M here and read and + . The module will be called ch.o. + If unsure, say N. + + comment "Some SCSI devices (e.g. CD jukebox) support multiple LUNs" depends on SCSI diff --git a/drivers/scsi/Makefile b/drivers/scsi/Makefile index 51d9c1e1884b..3746fb9fa2f5 100644 --- a/drivers/scsi/Makefile +++ b/drivers/scsi/Makefile @@ -140,6 +140,7 @@ obj-$(CONFIG_CHR_DEV_OSST) += osst.o obj-$(CONFIG_BLK_DEV_SD) += sd_mod.o obj-$(CONFIG_BLK_DEV_SR) += sr_mod.o obj-$(CONFIG_CHR_DEV_SG) += sg.o +obj-$(CONFIG_CHR_DEV_SCH) += ch.o scsi_mod-y += scsi.o hosts.o scsi_ioctl.o constants.o \ scsicam.o scsi_error.o scsi_lib.o \ diff --git a/drivers/scsi/ch.c b/drivers/scsi/ch.c new file mode 100644 index 000000000000..44f5a71ec34a --- /dev/null +++ b/drivers/scsi/ch.c @@ -0,0 +1,1025 @@ +/* + * SCSI Media Changer device driver for Linux 2.6 + * + * (c) 1996-2003 Gerd Knorr + * + */ + +#define VERSION "0.25" + +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include /* here are all the ioctls */ + +#include +#include +#include +#include +#include +#include +#include +#include + +#define CH_DT_MAX 16 +#define CH_TYPES 8 + +MODULE_DESCRIPTION("device driver for scsi media changer devices"); +MODULE_AUTHOR("Gerd Knorr "); +MODULE_LICENSE("GPL"); + +static int init = 1; +module_param(init, int, 0444); +MODULE_PARM_DESC(init, \ + "initialize element status on driver load (default: on)"); + +static int timeout_move = 300; +module_param(timeout_move, int, 0644); +MODULE_PARM_DESC(timeout_move,"timeout for move commands " + "(default: 300 seconds)"); + +static int timeout_init = 3600; +module_param(timeout_init, int, 0644); +MODULE_PARM_DESC(timeout_init,"timeout for INITIALIZE ELEMENT STATUS " + "(default: 3600 seconds)"); + +static int verbose = 1; +module_param(verbose, int, 0644); +MODULE_PARM_DESC(verbose,"be verbose (default: on)"); + +static int debug = 0; +module_param(debug, int, 0644); +MODULE_PARM_DESC(debug,"enable/disable debug messages, also prints more " + "detailed sense codes on scsi errors (default: off)"); + +static int dt_id[CH_DT_MAX] = { [ 0 ... (CH_DT_MAX-1) ] = -1 }; +static int dt_lun[CH_DT_MAX]; +module_param_array(dt_id, int, NULL, 0444); +module_param_array(dt_lun, int, NULL, 0444); + +/* tell the driver about vendor-specific slots */ +static int vendor_firsts[CH_TYPES-4]; +static int vendor_counts[CH_TYPES-4]; +module_param_array(vendor_firsts, int, NULL, 0444); +module_param_array(vendor_counts, int, NULL, 0444); + +static char *vendor_labels[CH_TYPES-4] = { + "v0", "v1", "v2", "v3" +}; +// module_param_string_array(vendor_labels, NULL, 0444); + +#define dprintk(fmt, arg...) if (debug) \ + printk(KERN_DEBUG "%s: " fmt, ch->name , ## arg) +#define vprintk(fmt, arg...) if (verbose) \ + printk(KERN_INFO "%s: " fmt, ch->name , ## arg) + +/* ------------------------------------------------------------------- */ + +#define MAX_RETRIES 1 + +static int ch_probe(struct device *); +static int ch_remove(struct device *); +static int ch_open(struct inode * inode, struct file * filp); +static int ch_release(struct inode * inode, struct file * filp); +static int ch_ioctl(struct inode * inode, struct file * filp, + unsigned int cmd, unsigned long arg); +#ifdef CONFIG_COMPAT +static long ch_ioctl_compat(struct file * filp, + unsigned int cmd, unsigned long arg); +#endif + +static struct class_simple * ch_sysfs_class; + +typedef struct { + struct list_head list; + int minor; + char name[8]; + struct scsi_device *device; + struct scsi_device **dt; /* ptrs to data transfer elements */ + u_int firsts[CH_TYPES]; + u_int counts[CH_TYPES]; + u_int unit_attention; + u_int voltags; + struct semaphore lock; +} scsi_changer; + +static LIST_HEAD(ch_devlist); +static spinlock_t ch_devlist_lock = SPIN_LOCK_UNLOCKED; +static int ch_devcount; + +static struct scsi_driver ch_template = +{ + .owner = THIS_MODULE, + .gendrv = { + .name = "ch", + .probe = ch_probe, + .remove = ch_remove, + }, +}; + +static struct file_operations changer_fops = +{ + .owner = THIS_MODULE, + .open = ch_open, + .release = ch_release, + .ioctl = ch_ioctl, +#ifdef CONFIG_COMPAT + .compat_ioctl = ch_ioctl_compat, +#endif +}; + +static struct { + unsigned char sense; + unsigned char asc; + unsigned char ascq; + int errno; +} err[] = { +/* Just filled in what looks right. Hav'nt checked any standard paper for + these errno assignments, so they may be wrong... */ + { + .sense = ILLEGAL_REQUEST, + .asc = 0x21, + .ascq = 0x01, + .errno = EBADSLT, /* Invalid element address */ + },{ + .sense = ILLEGAL_REQUEST, + .asc = 0x28, + .ascq = 0x01, + .errno = EBADE, /* Import or export element accessed */ + },{ + .sense = ILLEGAL_REQUEST, + .asc = 0x3B, + .ascq = 0x0D, + .errno = EXFULL, /* Medium destination element full */ + },{ + .sense = ILLEGAL_REQUEST, + .asc = 0x3B, + .ascq = 0x0E, + .errno = EBADE, /* Medium source element empty */ + },{ + .sense = ILLEGAL_REQUEST, + .asc = 0x20, + .ascq = 0x00, + .errno = EBADRQC, /* Invalid command operation code */ + },{ + /* end of list */ + } +}; + +/* ------------------------------------------------------------------- */ + +static int ch_find_errno(unsigned char *sense_buffer) +{ + int i,errno = 0; + + /* Check to see if additional sense information is available */ + if (sense_buffer[7] > 5 && + sense_buffer[12] != 0) { + for (i = 0; err[i].errno != 0; i++) { + if (err[i].sense == sense_buffer[ 2] && + err[i].asc == sense_buffer[12] && + err[i].ascq == sense_buffer[13]) { + errno = -err[i].errno; + break; + } + } + } + if (errno == 0) + errno = -EIO; + return errno; +} + +static int +ch_do_scsi(scsi_changer *ch, unsigned char *cmd, + void *buffer, unsigned buflength, + enum dma_data_direction direction) +{ + int errno, retries = 0, timeout; + struct scsi_request *sr; + + sr = scsi_allocate_request(ch->device, GFP_KERNEL); + if (NULL == sr) + return -ENOMEM; + + timeout = (cmd[0] == INITIALIZE_ELEMENT_STATUS) + ? timeout_init : timeout_move; + + retry: + errno = 0; + if (debug) { + dprintk("command: "); + __scsi_print_command(cmd); + } + + scsi_wait_req(sr, cmd, buffer, buflength, + timeout * HZ, MAX_RETRIES); + + dprintk("result: 0x%x\n",sr->sr_result); + if (driver_byte(sr->sr_result) & DRIVER_SENSE) { + if (debug) + scsi_print_req_sense(ch->name, sr); + errno = ch_find_errno(sr->sr_sense_buffer); + + switch(sr->sr_sense_buffer[2] & 0xf) { + case UNIT_ATTENTION: + ch->unit_attention = 1; + if (retries++ < 3) + goto retry; + break; + } + } + scsi_release_request(sr); + return errno; +} + +/* ------------------------------------------------------------------------ */ + +static int +ch_elem_to_typecode(scsi_changer *ch, u_int elem) +{ + int i; + + for (i = 0; i < CH_TYPES; i++) { + if (elem >= ch->firsts[i] && + elem < ch->firsts[i] + + ch->counts[i]) + return i+1; + } + return 0; +} + +static int +ch_read_element_status(scsi_changer *ch, u_int elem, char *data) +{ + u_char cmd[12]; + u_char *buffer; + int result; + + buffer = kmalloc(512, GFP_KERNEL | GFP_DMA); + if(!buffer) + return -ENOMEM; + + retry: + memset(cmd,0,sizeof(cmd)); + cmd[0] = READ_ELEMENT_STATUS; + cmd[1] = (ch->device->lun << 5) | + (ch->voltags ? 0x10 : 0) | + ch_elem_to_typecode(ch,elem); + cmd[2] = (elem >> 8) & 0xff; + cmd[3] = elem & 0xff; + cmd[5] = 1; + cmd[9] = 255; + if (0 == (result = ch_do_scsi(ch, cmd, buffer, 256, DMA_FROM_DEVICE))) { + if (((buffer[16] << 8) | buffer[17]) != elem) { + dprintk("asked for element 0x%02x, got 0x%02x\n", + elem,(buffer[16] << 8) | buffer[17]); + kfree(buffer); + return -EIO; + } + memcpy(data,buffer+16,16); + } else { + if (ch->voltags) { + ch->voltags = 0; + vprintk("device has no volume tag support\n"); + goto retry; + } + dprintk("READ ELEMENT STATUS for element 0x%x failed\n",elem); + } + kfree(buffer); + return result; +} + +static int +ch_init_elem(scsi_changer *ch) +{ + int err; + u_char cmd[6]; + + vprintk("INITIALIZE ELEMENT STATUS, may take some time ...\n"); + memset(cmd,0,sizeof(cmd)); + cmd[0] = INITIALIZE_ELEMENT_STATUS; + cmd[1] = ch->device->lun << 5; + err = ch_do_scsi(ch, cmd, NULL, 0, DMA_NONE); + vprintk("... finished\n"); + return err; +} + +static int +ch_readconfig(scsi_changer *ch) +{ + u_char cmd[10], data[16]; + u_char *buffer; + int result,id,lun,i; + u_int elem; + + buffer = kmalloc(512, GFP_KERNEL | GFP_DMA); + if (!buffer) + return -ENOMEM; + memset(buffer,0,512); + + memset(cmd,0,sizeof(cmd)); + cmd[0] = MODE_SENSE; + cmd[1] = ch->device->lun << 5; + cmd[2] = 0x1d; + cmd[4] = 255; + result = ch_do_scsi(ch, cmd, buffer, 255, DMA_FROM_DEVICE); + if (0 != result) { + cmd[1] |= (1<<3); + result = ch_do_scsi(ch, cmd, buffer, 255, DMA_FROM_DEVICE); + } + if (0 == result) { + ch->firsts[CHET_MT] = + (buffer[buffer[3]+ 6] << 8) | buffer[buffer[3]+ 7]; + ch->counts[CHET_MT] = + (buffer[buffer[3]+ 8] << 8) | buffer[buffer[3]+ 9]; + ch->firsts[CHET_ST] = + (buffer[buffer[3]+10] << 8) | buffer[buffer[3]+11]; + ch->counts[CHET_ST] = + (buffer[buffer[3]+12] << 8) | buffer[buffer[3]+13]; + ch->firsts[CHET_IE] = + (buffer[buffer[3]+14] << 8) | buffer[buffer[3]+15]; + ch->counts[CHET_IE] = + (buffer[buffer[3]+16] << 8) | buffer[buffer[3]+17]; + ch->firsts[CHET_DT] = + (buffer[buffer[3]+18] << 8) | buffer[buffer[3]+19]; + ch->counts[CHET_DT] = + (buffer[buffer[3]+20] << 8) | buffer[buffer[3]+21]; + vprintk("type #1 (mt): 0x%x+%d [medium transport]\n", + ch->firsts[CHET_MT], + ch->counts[CHET_MT]); + vprintk("type #2 (st): 0x%x+%d [storage]\n", + ch->firsts[CHET_ST], + ch->counts[CHET_ST]); + vprintk("type #3 (ie): 0x%x+%d [import/export]\n", + ch->firsts[CHET_IE], + ch->counts[CHET_IE]); + vprintk("type #4 (dt): 0x%x+%d [data transfer]\n", + ch->firsts[CHET_DT], + ch->counts[CHET_DT]); + } else { + vprintk("reading element address assigment page failed!\n"); + } + + /* vendor specific element types */ + for (i = 0; i < 4; i++) { + if (0 == vendor_counts[i]) + continue; + if (NULL == vendor_labels[i]) + continue; + ch->firsts[CHET_V1+i] = vendor_firsts[i]; + ch->counts[CHET_V1+i] = vendor_counts[i]; + vprintk("type #%d (v%d): 0x%x+%d [%s, vendor specific]\n", + i+5,i+1,vendor_firsts[i],vendor_counts[i], + vendor_labels[i]); + } + + /* look up the devices of the data transfer elements */ + ch->dt = kmalloc(ch->counts[CHET_DT]*sizeof(struct scsi_device), + GFP_KERNEL); + for (elem = 0; elem < ch->counts[CHET_DT]; elem++) { + id = -1; + lun = 0; + if (elem < CH_DT_MAX && -1 != dt_id[elem]) { + id = dt_id[elem]; + lun = dt_lun[elem]; + vprintk("dt 0x%x: [insmod option] ", + elem+ch->firsts[CHET_DT]); + } else if (0 != ch_read_element_status + (ch,elem+ch->firsts[CHET_DT],data)) { + vprintk("dt 0x%x: READ ELEMENT STATUS failed\n", + elem+ch->firsts[CHET_DT]); + } else { + vprintk("dt 0x%x: ",elem+ch->firsts[CHET_DT]); + if (data[6] & 0x80) { + if (verbose) + printk("not this SCSI bus\n"); + ch->dt[elem] = NULL; + } else if (0 == (data[6] & 0x30)) { + if (verbose) + printk("ID/LUN unknown\n"); + ch->dt[elem] = NULL; + } else { + id = ch->device->id; + lun = 0; + if (data[6] & 0x20) id = data[7]; + if (data[6] & 0x10) lun = data[6] & 7; + } + } + if (-1 != id) { + if (verbose) + printk("ID %i, LUN %i, ",id,lun); + ch->dt[elem] = + scsi_device_lookup(ch->device->host, + ch->device->channel, + id,lun); + if (!ch->dt[elem]) { + /* should not happen */ + if (verbose) + printk("Huh? device not found!\n"); + } else { + if (verbose) + printk("name: %8.8s %16.16s %4.4s\n", + ch->dt[elem]->vendor, + ch->dt[elem]->model, + ch->dt[elem]->rev); + } + } + } + ch->voltags = 1; + kfree(buffer); + + return 0; +} + +/* ------------------------------------------------------------------------ */ + +static int +ch_position(scsi_changer *ch, u_int trans, u_int elem, int rotate) +{ + u_char cmd[10]; + + dprintk("position: 0x%x\n",elem); + if (0 == trans) + trans = ch->firsts[CHET_MT]; + memset(cmd,0,sizeof(cmd)); + cmd[0] = POSITION_TO_ELEMENT; + cmd[1] = ch->device->lun << 5; + cmd[2] = (trans >> 8) & 0xff; + cmd[3] = trans & 0xff; + cmd[4] = (elem >> 8) & 0xff; + cmd[5] = elem & 0xff; + cmd[8] = rotate ? 1 : 0; + return ch_do_scsi(ch, cmd, NULL, 0, DMA_NONE); +} + +static int +ch_move(scsi_changer *ch, u_int trans, u_int src, u_int dest, int rotate) +{ + u_char cmd[12]; + + dprintk("move: 0x%x => 0x%x\n",src,dest); + if (0 == trans) + trans = ch->firsts[CHET_MT]; + memset(cmd,0,sizeof(cmd)); + cmd[0] = MOVE_MEDIUM; + cmd[1] = ch->device->lun << 5; + cmd[2] = (trans >> 8) & 0xff; + cmd[3] = trans & 0xff; + cmd[4] = (src >> 8) & 0xff; + cmd[5] = src & 0xff; + cmd[6] = (dest >> 8) & 0xff; + cmd[7] = dest & 0xff; + cmd[10] = rotate ? 1 : 0; + return ch_do_scsi(ch, cmd, NULL,0, DMA_NONE); +} + +static int +ch_exchange(scsi_changer *ch, u_int trans, u_int src, + u_int dest1, u_int dest2, int rotate1, int rotate2) +{ + u_char cmd[12]; + + dprintk("exchange: 0x%x => 0x%x => 0x%x\n", + src,dest1,dest2); + if (0 == trans) + trans = ch->firsts[CHET_MT]; + memset(cmd,0,sizeof(cmd)); + cmd[0] = EXCHANGE_MEDIUM; + cmd[1] = ch->device->lun << 5; + cmd[2] = (trans >> 8) & 0xff; + cmd[3] = trans & 0xff; + cmd[4] = (src >> 8) & 0xff; + cmd[5] = src & 0xff; + cmd[6] = (dest1 >> 8) & 0xff; + cmd[7] = dest1 & 0xff; + cmd[8] = (dest2 >> 8) & 0xff; + cmd[9] = dest2 & 0xff; + cmd[10] = (rotate1 ? 1 : 0) | (rotate2 ? 2 : 0); + + return ch_do_scsi(ch, cmd, NULL,0, DMA_NONE); +} + +static void +ch_check_voltag(char *tag) +{ + int i; + + for (i = 0; i < 32; i++) { + /* restrict to ascii */ + if (tag[i] >= 0x7f || tag[i] < 0x20) + tag[i] = ' '; + /* don't allow search wildcards */ + if (tag[i] == '?' || + tag[i] == '*') + tag[i] = ' '; + } +} + +static int +ch_set_voltag(scsi_changer *ch, u_int elem, + int alternate, int clear, u_char *tag) +{ + u_char cmd[12]; + u_char *buffer; + int result; + + buffer = kmalloc(512, GFP_KERNEL); + if (!buffer) + return -ENOMEM; + memset(buffer,0,512); + + dprintk("%s %s voltag: 0x%x => \"%s\"\n", + clear ? "clear" : "set", + alternate ? "alternate" : "primary", + elem, tag); + memset(cmd,0,sizeof(cmd)); + cmd[0] = SEND_VOLUME_TAG; + cmd[1] = (ch->device->lun << 5) | + ch_elem_to_typecode(ch,elem); + cmd[2] = (elem >> 8) & 0xff; + cmd[3] = elem & 0xff; + cmd[5] = clear + ? (alternate ? 0x0d : 0x0c) + : (alternate ? 0x0b : 0x0a); + + cmd[9] = 255; + + memcpy(buffer,tag,32); + ch_check_voltag(buffer); + + result = ch_do_scsi(ch, cmd, buffer, 256, DMA_TO_DEVICE); + kfree(buffer); + return result; +} + +static int ch_gstatus(scsi_changer *ch, int type, unsigned char *dest) +{ + int retval = 0; + u_char data[16]; + unsigned int i; + + down(&ch->lock); + for (i = 0; i < ch->counts[type]; i++) { + if (0 != ch_read_element_status + (ch, ch->firsts[type]+i,data)) { + retval = -EIO; + break; + } + put_user(data[2], dest+i); + if (data[2] & CESTATUS_EXCEPT) + vprintk("element 0x%x: asc=0x%x, ascq=0x%x\n", + ch->firsts[type]+i, + (int)data[4],(int)data[5]); + retval = ch_read_element_status + (ch, ch->firsts[type]+i,data); + if (0 != retval) + break; + } + up(&ch->lock); + return retval; +} + +/* ------------------------------------------------------------------------ */ + +static int +ch_release(struct inode *inode, struct file *file) +{ + scsi_changer *ch = file->private_data; + + scsi_device_put(ch->device); + file->private_data = NULL; + return 0; +} + +static int +ch_open(struct inode *inode, struct file *file) +{ + scsi_changer *tmp, *ch; + int minor = iminor(inode); + + spin_lock(&ch_devlist_lock); + ch = NULL; + list_for_each_entry(tmp,&ch_devlist,list) { + if (tmp->minor == minor) + ch = tmp; + } + if (NULL == ch || scsi_device_get(ch->device)) { + spin_unlock(&ch_devlist_lock); + return -ENXIO; + } + spin_unlock(&ch_devlist_lock); + + file->private_data = ch; + return 0; +} + +static int +ch_checkrange(scsi_changer *ch, unsigned int type, unsigned int unit) +{ + if (type >= CH_TYPES || unit >= ch->counts[type]) + return -1; + return 0; +} + +static int ch_ioctl(struct inode * inode, struct file * file, + unsigned int cmd, unsigned long arg) +{ + scsi_changer *ch = file->private_data; + int retval; + + switch (cmd) { + case CHIOGPARAMS: + { + struct changer_params params; + + params.cp_curpicker = 0; + params.cp_npickers = ch->counts[CHET_MT]; + params.cp_nslots = ch->counts[CHET_ST]; + params.cp_nportals = ch->counts[CHET_IE]; + params.cp_ndrives = ch->counts[CHET_DT]; + + if (copy_to_user((void *) arg, ¶ms, sizeof(params))) + return -EFAULT; + return 0; + } + case CHIOGVPARAMS: + { + struct changer_vendor_params vparams; + + memset(&vparams,0,sizeof(vparams)); + if (ch->counts[CHET_V1]) { + vparams.cvp_n1 = ch->counts[CHET_V1]; + strncpy(vparams.cvp_label1,vendor_labels[0],16); + } + if (ch->counts[CHET_V2]) { + vparams.cvp_n2 = ch->counts[CHET_V2]; + strncpy(vparams.cvp_label2,vendor_labels[1],16); + } + if (ch->counts[CHET_V3]) { + vparams.cvp_n3 = ch->counts[CHET_V3]; + strncpy(vparams.cvp_label3,vendor_labels[2],16); + } + if (ch->counts[CHET_V4]) { + vparams.cvp_n4 = ch->counts[CHET_V4]; + strncpy(vparams.cvp_label4,vendor_labels[3],16); + } + if (copy_to_user((void *) arg, &vparams, sizeof(vparams))) + return -EFAULT; + return 0; + } + + case CHIOPOSITION: + { + struct changer_position pos; + + if (copy_from_user(&pos, (void*)arg, sizeof (pos))) + return -EFAULT; + + if (0 != ch_checkrange(ch, pos.cp_type, pos.cp_unit)) { + dprintk("CHIOPOSITION: invalid parameter\n"); + return -EBADSLT; + } + down(&ch->lock); + retval = ch_position(ch,0, + ch->firsts[pos.cp_type] + pos.cp_unit, + pos.cp_flags & CP_INVERT); + up(&ch->lock); + return retval; + } + + case CHIOMOVE: + { + struct changer_move mv; + + if (copy_from_user(&mv, (void*)arg, sizeof (mv))) + return -EFAULT; + + if (0 != ch_checkrange(ch, mv.cm_fromtype, mv.cm_fromunit) || + 0 != ch_checkrange(ch, mv.cm_totype, mv.cm_tounit )) { + dprintk("CHIOMOVE: invalid parameter\n"); + return -EBADSLT; + } + + down(&ch->lock); + retval = ch_move(ch,0, + ch->firsts[mv.cm_fromtype] + mv.cm_fromunit, + ch->firsts[mv.cm_totype] + mv.cm_tounit, + mv.cm_flags & CM_INVERT); + up(&ch->lock); + return retval; + } + + case CHIOEXCHANGE: + { + struct changer_exchange mv; + + if (copy_from_user(&mv, (void*)arg, sizeof (mv))) + return -EFAULT; + + if (0 != ch_checkrange(ch, mv.ce_srctype, mv.ce_srcunit ) || + 0 != ch_checkrange(ch, mv.ce_fdsttype, mv.ce_fdstunit) || + 0 != ch_checkrange(ch, mv.ce_sdsttype, mv.ce_sdstunit)) { + dprintk("CHIOEXCHANGE: invalid parameter\n"); + return -EBADSLT; + } + + down(&ch->lock); + retval = ch_exchange + (ch,0, + ch->firsts[mv.ce_srctype] + mv.ce_srcunit, + ch->firsts[mv.ce_fdsttype] + mv.ce_fdstunit, + ch->firsts[mv.ce_sdsttype] + mv.ce_sdstunit, + mv.ce_flags & CE_INVERT1, mv.ce_flags & CE_INVERT2); + up(&ch->lock); + return retval; + } + + case CHIOGSTATUS: + { + struct changer_element_status ces; + + if (copy_from_user(&ces, (void*)arg, sizeof (ces))) + return -EFAULT; + if (ces.ces_type < 0 || ces.ces_type >= CH_TYPES) + return -EINVAL; + + return ch_gstatus(ch, ces.ces_type, ces.ces_data); + } + + case CHIOGELEM: + { + struct changer_get_element cge; + u_char cmd[12]; + u_char *buffer; + unsigned int elem; + int result,i; + + if (copy_from_user(&cge, (void*)arg, sizeof (cge))) + return -EFAULT; + + if (0 != ch_checkrange(ch, cge.cge_type, cge.cge_unit)) + return -EINVAL; + elem = ch->firsts[cge.cge_type] + cge.cge_unit; + + buffer = kmalloc(512, GFP_KERNEL | GFP_DMA); + if (!buffer) + return -ENOMEM; + down(&ch->lock); + + voltag_retry: + memset(cmd,0,sizeof(cmd)); + cmd[0] = READ_ELEMENT_STATUS; + cmd[1] = (ch->device->lun << 5) | + (ch->voltags ? 0x10 : 0) | + ch_elem_to_typecode(ch,elem); + cmd[2] = (elem >> 8) & 0xff; + cmd[3] = elem & 0xff; + cmd[5] = 1; + cmd[9] = 255; + + if (0 == (result = ch_do_scsi(ch, cmd, buffer, 256, DMA_FROM_DEVICE))) { + cge.cge_status = buffer[18]; + cge.cge_flags = 0; + if (buffer[18] & CESTATUS_EXCEPT) { + cge.cge_errno = EIO; + } + if (buffer[25] & 0x80) { + cge.cge_flags |= CGE_SRC; + if (buffer[25] & 0x40) + cge.cge_flags |= CGE_INVERT; + elem = (buffer[26]<<8) | buffer[27]; + for (i = 0; i < 4; i++) { + if (elem >= ch->firsts[i] && + elem < ch->firsts[i] + ch->counts[i]) { + cge.cge_srctype = i; + cge.cge_srcunit = elem-ch->firsts[i]; + } + } + } + if ((buffer[22] & 0x30) == 0x30) { + cge.cge_flags |= CGE_IDLUN; + cge.cge_id = buffer[23]; + cge.cge_lun = buffer[22] & 7; + } + if (buffer[9] & 0x80) { + cge.cge_flags |= CGE_PVOLTAG; + memcpy(cge.cge_pvoltag,buffer+28,36); + } + if (buffer[9] & 0x40) { + cge.cge_flags |= CGE_AVOLTAG; + memcpy(cge.cge_avoltag,buffer+64,36); + } + } else if (ch->voltags) { + ch->voltags = 0; + vprintk("device has no volume tag support\n"); + goto voltag_retry; + } + kfree(buffer); + up(&ch->lock); + + if (copy_to_user((void*)arg, &cge, sizeof (cge))) + return -EFAULT; + return result; + } + + case CHIOINITELEM: + { + down(&ch->lock); + retval = ch_init_elem(ch); + up(&ch->lock); + return retval; + } + + case CHIOSVOLTAG: + { + struct changer_set_voltag csv; + int elem; + + if (copy_from_user(&csv, (void*)arg, sizeof(csv))) + return -EFAULT; + + if (0 != ch_checkrange(ch, csv.csv_type, csv.csv_unit)) { + dprintk("CHIOSVOLTAG: invalid parameter\n"); + return -EBADSLT; + } + elem = ch->firsts[csv.csv_type] + csv.csv_unit; + down(&ch->lock); + retval = ch_set_voltag(ch, elem, + csv.csv_flags & CSV_AVOLTAG, + csv.csv_flags & CSV_CLEARTAG, + csv.csv_voltag); + up(&ch->lock); + return retval; + } + + default: + return scsi_ioctl(ch->device, cmd, (void*)arg); + + } +} + +#ifdef CONFIG_COMPAT + +struct changer_element_status32 { + int ces_type; + compat_uptr_t ces_data; +}; +#define CHIOGSTATUS32 _IOW('c', 8,struct changer_element_status32) + +static long ch_ioctl_compat(struct file * file, + unsigned int cmd, unsigned long arg) +{ + scsi_changer *ch = file->private_data; + + switch (cmd) { + case CHIOGPARAMS: + case CHIOGVPARAMS: + case CHIOPOSITION: + case CHIOMOVE: + case CHIOEXCHANGE: + case CHIOGELEM: + case CHIOINITELEM: + case CHIOSVOLTAG: + /* compatible */ + return ch_ioctl(NULL /* inode, unused */, + file, cmd, arg); + case CHIOGSTATUS32: + { + struct changer_element_status32 ces32; + unsigned char *data; + + if (copy_from_user(&ces32, (void*)arg, sizeof (ces32))) + return -EFAULT; + if (ces32.ces_type < 0 || ces32.ces_type >= CH_TYPES) + return -EINVAL; + + data = compat_ptr(ces32.ces_data); + return ch_gstatus(ch, ces32.ces_type, data); + } + default: + // return scsi_ioctl_compat(ch->device, cmd, (void*)arg); + return -ENOIOCTLCMD; + + } +} +#endif + +/* ------------------------------------------------------------------------ */ + +static int ch_probe(struct device *dev) +{ + struct scsi_device *sd = to_scsi_device(dev); + scsi_changer *ch; + + if (sd->type != TYPE_MEDIUM_CHANGER) + return -ENODEV; + + ch = kmalloc(sizeof(*ch), GFP_KERNEL); + if (NULL == ch) + return -ENOMEM; + + memset(ch,0,sizeof(*ch)); + ch->minor = ch_devcount; + sprintf(ch->name,"ch%d",ch->minor); + init_MUTEX(&ch->lock); + ch->device = sd; + ch_readconfig(ch); + if (init) + ch_init_elem(ch); + + devfs_mk_cdev(MKDEV(SCSI_CHANGER_MAJOR,ch->minor), + S_IFCHR | S_IRUGO | S_IWUGO, ch->name); + class_simple_device_add(ch_sysfs_class, + MKDEV(SCSI_CHANGER_MAJOR,ch->minor), + dev, "s%s", ch->name); + + printk(KERN_INFO "Attached scsi changer %s " + "at scsi%d, channel %d, id %d, lun %d\n", + ch->name, sd->host->host_no, sd->channel, sd->id, sd->lun); + + spin_lock(&ch_devlist_lock); + list_add_tail(&ch->list,&ch_devlist); + ch_devcount++; + spin_unlock(&ch_devlist_lock); + return 0; +} + +static int ch_remove(struct device *dev) +{ + struct scsi_device *sd = to_scsi_device(dev); + scsi_changer *tmp, *ch; + + spin_lock(&ch_devlist_lock); + ch = NULL; + list_for_each_entry(tmp,&ch_devlist,list) { + if (tmp->device == sd) + ch = tmp; + } + BUG_ON(NULL == ch); + list_del(&ch->list); + spin_unlock(&ch_devlist_lock); + + class_simple_device_remove(MKDEV(SCSI_CHANGER_MAJOR,ch->minor)); + devfs_remove(ch->name); + kfree(ch->dt); + kfree(ch); + ch_devcount--; + return 0; +} + +static int __init init_ch_module(void) +{ + int rc; + + printk(KERN_INFO "SCSI Media Changer driver v" VERSION " \n"); + ch_sysfs_class = class_simple_create(THIS_MODULE, "scsi_changer"); + if (IS_ERR(ch_sysfs_class)) { + rc = PTR_ERR(ch_sysfs_class); + return rc; + } + rc = register_chrdev(SCSI_CHANGER_MAJOR,"ch",&changer_fops); + if (rc < 0) { + printk("Unable to get major %d for SCSI-Changer\n", + SCSI_CHANGER_MAJOR); + goto fail1; + } + rc = scsi_register_driver(&ch_template.gendrv); + if (rc < 0) + goto fail2; + return 0; + + fail2: + unregister_chrdev(SCSI_CHANGER_MAJOR, "ch"); + fail1: + class_simple_destroy(ch_sysfs_class); + return rc; +} + +static void __exit exit_ch_module(void) +{ + scsi_unregister_driver(&ch_template.gendrv); + unregister_chrdev(SCSI_CHANGER_MAJOR, "ch"); + class_simple_destroy(ch_sysfs_class); +} + +module_init(init_ch_module); +module_exit(exit_ch_module); + +/* + * Local variables: + * c-basic-offset: 8 + * End: + */ diff --git a/include/linux/chio.h b/include/linux/chio.h new file mode 100644 index 000000000000..63035ae67e63 --- /dev/null +++ b/include/linux/chio.h @@ -0,0 +1,168 @@ +/* + * ioctl interface for the scsi media changer driver + */ + +/* changer element types */ +#define CHET_MT 0 /* media transport element (robot) */ +#define CHET_ST 1 /* storage element (media slots) */ +#define CHET_IE 2 /* import/export element */ +#define CHET_DT 3 /* data transfer element (tape/cdrom/whatever) */ +#define CHET_V1 4 /* vendor specific #1 */ +#define CHET_V2 5 /* vendor specific #2 */ +#define CHET_V3 6 /* vendor specific #3 */ +#define CHET_V4 7 /* vendor specific #4 */ + + +/* + * CHIOGPARAMS + * query changer properties + * + * CHIOVGPARAMS + * query vendor-specific element types + * + * accessing elements works by specifing type and unit of the element. + * for eample, storage elements are addressed with type = CHET_ST and + * unit = 0 .. cp_nslots-1 + * + */ +struct changer_params { + int cp_curpicker; /* current transport element */ + int cp_npickers; /* number of transport elements (CHET_MT) */ + int cp_nslots; /* number of storage elements (CHET_ST) */ + int cp_nportals; /* number of import/export elements (CHET_IE) */ + int cp_ndrives; /* number of data transfer elements (CHET_DT) */ +}; +struct changer_vendor_params { + int cvp_n1; /* number of vendor specific elems (CHET_V1) */ + char cvp_label1[16]; + int cvp_n2; /* number of vendor specific elems (CHET_V2) */ + char cvp_label2[16]; + int cvp_n3; /* number of vendor specific elems (CHET_V3) */ + char cvp_label3[16]; + int cvp_n4; /* number of vendor specific elems (CHET_V4) */ + char cvp_label4[16]; + int reserved[8]; +}; + + +/* + * CHIOMOVE + * move a medium from one element to another + */ +struct changer_move { + int cm_fromtype; /* type/unit of source element */ + int cm_fromunit; + int cm_totype; /* type/unit of destination element */ + int cm_tounit; + int cm_flags; +}; +#define CM_INVERT 1 /* flag: rotate media (for double-sided like MOD) */ + + +/* + * CHIOEXCHANGE + * move one medium from element #1 to element #2, + * and another one from element #2 to element #3. + * element #1 and #3 are allowed to be identical. + */ +struct changer_exchange { + int ce_srctype; /* type/unit of element #1 */ + int ce_srcunit; + int ce_fdsttype; /* type/unit of element #2 */ + int ce_fdstunit; + int ce_sdsttype; /* type/unit of element #3 */ + int ce_sdstunit; + int ce_flags; +}; +#define CE_INVERT1 1 +#define CE_INVERT2 2 + + +/* + * CHIOPOSITION + * move the transport element (robot arm) to a specific element. + */ +struct changer_position { + int cp_type; + int cp_unit; + int cp_flags; +}; +#define CP_INVERT 1 + + +/* + * CHIOGSTATUS + * get element status for all elements of a specific type + */ +struct changer_element_status { + int ces_type; + unsigned char *ces_data; +}; +#define CESTATUS_FULL 0x01 /* full */ +#define CESTATUS_IMPEXP 0x02 /* media was imported (inserted by sysop) */ +#define CESTATUS_EXCEPT 0x04 /* error condition */ +#define CESTATUS_ACCESS 0x08 /* access allowed */ +#define CESTATUS_EXENAB 0x10 /* element can export media */ +#define CESTATUS_INENAB 0x20 /* element can import media */ + + +/* + * CHIOGELEM + * get more detailed status informtion for a single element + */ +struct changer_get_element { + int cge_type; /* type/unit */ + int cge_unit; + int cge_status; /* status */ + int cge_errno; /* errno */ + int cge_srctype; /* source element of the last move/exchange */ + int cge_srcunit; + int cge_id; /* scsi id (for data transfer elements) */ + int cge_lun; /* scsi lun (for data transfer elements) */ + char cge_pvoltag[36]; /* primary volume tag */ + char cge_avoltag[36]; /* alternate volume tag */ + int cge_flags; +}; +/* flags */ +#define CGE_ERRNO 0x01 /* errno available */ +#define CGE_INVERT 0x02 /* media inverted */ +#define CGE_SRC 0x04 /* media src available */ +#define CGE_IDLUN 0x08 /* ID+LUN available */ +#define CGE_PVOLTAG 0x10 /* primary volume tag available */ +#define CGE_AVOLTAG 0x20 /* alternate volume tag available */ + + +/* + * CHIOSVOLTAG + * set volume tag + */ +struct changer_set_voltag { + int csv_type; /* type/unit */ + int csv_unit; + char csv_voltag[36]; /* volume tag */ + int csv_flags; +}; +#define CSV_PVOLTAG 0x01 /* primary volume tag */ +#define CSV_AVOLTAG 0x02 /* alternate volume tag */ +#define CSV_CLEARTAG 0x04 /* clear volume tag */ + +/* ioctls */ +#define CHIOMOVE _IOW('c', 1,struct changer_move) +#define CHIOEXCHANGE _IOW('c', 2,struct changer_exchange) +#define CHIOPOSITION _IOW('c', 3,struct changer_position) +#define CHIOGPICKER _IOR('c', 4,int) /* not impl. */ +#define CHIOSPICKER _IOW('c', 5,int) /* not impl. */ +#define CHIOGPARAMS _IOR('c', 6,struct changer_params) +#define CHIOGSTATUS _IOW('c', 8,struct changer_element_status) +#define CHIOGELEM _IOW('c',16,struct changer_get_element) +#define CHIOINITELEM _IO('c',17) +#define CHIOSVOLTAG _IOW('c',18,struct changer_set_voltag) +#define CHIOGVPARAMS _IOR('c',19,struct changer_vendor_params) + +/* ---------------------------------------------------------------------- */ + +/* + * Local variables: + * c-basic-offset: 8 + * End: + */ diff --git a/include/linux/major.h b/include/linux/major.h index 4b62c42b842c..e36a46702d94 100644 --- a/include/linux/major.h +++ b/include/linux/major.h @@ -100,6 +100,7 @@ #define I2O_MAJOR 80 /* 80->87 */ #define SHMIQ_MAJOR 85 /* Linux/mips, SGI /dev/shmiq */ +#define SCSI_CHANGER_MAJOR 86 #define IDE6_MAJOR 88 #define IDE7_MAJOR 89 diff --git a/include/scsi/scsi.h b/include/scsi/scsi.h index 659ecf48fb4a..ca1e3b4a3183 100644 --- a/include/scsi/scsi.h +++ b/include/scsi/scsi.h @@ -41,6 +41,7 @@ extern const char *const scsi_device_types[MAX_SCSI_DEVICE_CODE]; #define FORMAT_UNIT 0x04 #define READ_BLOCK_LIMITS 0x05 #define REASSIGN_BLOCKS 0x07 +#define INITIALIZE_ELEMENT_STATUS 0x07 #define READ_6 0x08 #define WRITE_6 0x0a #define SEEK_6 0x0b @@ -65,6 +66,7 @@ extern const char *const scsi_device_types[MAX_SCSI_DEVICE_CODE]; #define READ_10 0x28 #define WRITE_10 0x2a #define SEEK_10 0x2b +#define POSITION_TO_ELEMENT 0x2b #define WRITE_VERIFY 0x2e #define VERIFY 0x2f #define SEARCH_HIGH 0x30 @@ -97,6 +99,7 @@ extern const char *const scsi_device_types[MAX_SCSI_DEVICE_CODE]; #define PERSISTENT_RESERVE_OUT 0x5f #define REPORT_LUNS 0xa0 #define MOVE_MEDIUM 0xa5 +#define EXCHANGE_MEDIUM 0xa6 #define READ_12 0xa8 #define WRITE_12 0xaa #define WRITE_VERIFY_12 0xae -- cgit v1.2.3 From 011161051bbc25f7f8b7df059dbd934c534443f0 Mon Sep 17 00:00:00 2001 From: Stephen Smalley Date: Sat, 21 May 2005 00:15:52 +0100 Subject: AUDIT: Avoid sleeping function in SElinux AVC audit. This patch changes the SELinux AVC to defer logging of paths to the audit framework upon syscall exit, by saving a reference to the (dentry,vfsmount) pair in an auxiliary audit item on the current audit context for processing by audit_log_exit. Signed-off-by: Stephen Smalley Signed-off-by: David Woodhouse --- include/linux/audit.h | 3 +++ kernel/auditsc.c | 40 ++++++++++++++++++++++++++++++++++++++++ security/selinux/avc.c | 17 ++++++++--------- 3 files changed, 51 insertions(+), 9 deletions(-) (limited to 'include/linux') diff --git a/include/linux/audit.h b/include/linux/audit.h index 17ea5d522d81..4b7caf0c6e10 100644 --- a/include/linux/audit.h +++ b/include/linux/audit.h @@ -69,6 +69,7 @@ #define AUDIT_AVC 1400 /* SE Linux avc denial or grant */ #define AUDIT_SELINUX_ERR 1401 /* Internal SE Linux Errors */ +#define AUDIT_AVC_PATH 1402 /* dentry, vfsmount pair from avc */ #define AUDIT_KERNEL 2000 /* Asynchronous audit record. NOT A REQUEST. */ @@ -225,6 +226,7 @@ extern uid_t audit_get_loginuid(struct audit_context *ctx); extern int audit_ipc_perms(unsigned long qbytes, uid_t uid, gid_t gid, mode_t mode); extern int audit_socketcall(int nargs, unsigned long *args); extern int audit_sockaddr(int len, void *addr); +extern int audit_avc_path(struct dentry *dentry, struct vfsmount *mnt); extern void audit_signal_info(int sig, struct task_struct *t); #else #define audit_alloc(t) ({ 0; }) @@ -240,6 +242,7 @@ extern void audit_signal_info(int sig, struct task_struct *t); #define audit_ipc_perms(q,u,g,m) ({ 0; }) #define audit_socketcall(n,a) ({ 0; }) #define audit_sockaddr(len, addr) ({ 0; }) +#define audit_avc_path(dentry, mnt) ({ 0; }) #define audit_signal_info(s,t) do { ; } while (0) #endif diff --git a/kernel/auditsc.c b/kernel/auditsc.c index 78d7a13fc86f..8dc5b2767145 100644 --- a/kernel/auditsc.c +++ b/kernel/auditsc.c @@ -34,6 +34,7 @@ #include #include #include +#include #include #include #include @@ -124,6 +125,11 @@ struct audit_aux_data_sockaddr { char a[0]; }; +struct audit_aux_data_path { + struct audit_aux_data d; + struct dentry *dentry; + struct vfsmount *mnt; +}; /* The per-task audit context. */ struct audit_context { @@ -553,6 +559,11 @@ static inline void audit_free_aux(struct audit_context *context) struct audit_aux_data *aux; while ((aux = context->aux)) { + if (aux->type == AUDIT_AVC_PATH) { + struct audit_aux_data_path *axi = (void *)aux; + dput(axi->dentry); + mntput(axi->mnt); + } context->aux = aux->next; kfree(aux); } @@ -724,6 +735,14 @@ static void audit_log_exit(struct audit_context *context) audit_log_format(ab, "saddr="); audit_log_hex(ab, axs->a, axs->len); break; } + + case AUDIT_AVC_PATH: { + struct audit_aux_data_path *axi = (void *)aux; + audit_log_d_path(ab, "path=", axi->dentry, axi->mnt); + dput(axi->dentry); + mntput(axi->mnt); + break; } + } audit_log_end(ab); @@ -1124,6 +1143,27 @@ int audit_sockaddr(int len, void *a) return 0; } +int audit_avc_path(struct dentry *dentry, struct vfsmount *mnt) +{ + struct audit_aux_data_path *ax; + struct audit_context *context = current->audit_context; + + if (likely(!context)) + return 0; + + ax = kmalloc(sizeof(*ax), GFP_ATOMIC); + if (!ax) + return -ENOMEM; + + ax->dentry = dget(dentry); + ax->mnt = mntget(mnt); + + ax->d.type = AUDIT_AVC_PATH; + ax->d.next = context->aux; + context->aux = (void *)ax; + return 0; +} + void audit_signal_info(int sig, struct task_struct *t) { extern pid_t audit_sig_pid; diff --git a/security/selinux/avc.c b/security/selinux/avc.c index 62b963aca275..0fbc3e98c5ea 100644 --- a/security/selinux/avc.c +++ b/security/selinux/avc.c @@ -573,13 +573,10 @@ void avc_audit(u32 ssid, u32 tsid, case AVC_AUDIT_DATA_FS: if (a->u.fs.dentry) { struct dentry *dentry = a->u.fs.dentry; - if (a->u.fs.mnt) { - audit_log_d_path(ab, "path=", dentry, - a->u.fs.mnt); - } else { - audit_log_format(ab, " name=%s", - dentry->d_name.name); - } + if (a->u.fs.mnt) + audit_avc_path(dentry, a->u.fs.mnt); + audit_log_format(ab, " name=%s", + dentry->d_name.name); inode = dentry->d_inode; } else if (a->u.fs.inode) { struct dentry *dentry; @@ -630,8 +627,10 @@ void avc_audit(u32 ssid, u32 tsid, case AF_UNIX: u = unix_sk(sk); if (u->dentry) { - audit_log_d_path(ab, "path=", - u->dentry, u->mnt); + audit_avc_path(u->dentry, u->mnt); + audit_log_format(ab, " name=%s", + u->dentry->d_name.name); + break; } if (!u->addr) -- cgit v1.2.3 From bfb4496e7239c9132d732a65cdcf3d6a7431ad1a Mon Sep 17 00:00:00 2001 From: David Woodhouse Date: Sat, 21 May 2005 21:08:09 +0100 Subject: AUDIT: Assign serial number to non-syscall messages Move audit_serial() into audit.c and use it to generate serial numbers on messages even when there is no audit context from syscall auditing. This allows us to disambiguate audit records when more than one is generated in the same millisecond. Based on a patch by Steve Grubb after he observed the problem. Signed-off-by: David Woodhouse --- include/linux/audit.h | 7 ++++--- kernel/audit.c | 46 ++++++++++++++++++++++++++++++++++++++++++---- kernel/auditsc.c | 46 ++++++---------------------------------------- 3 files changed, 52 insertions(+), 47 deletions(-) (limited to 'include/linux') diff --git a/include/linux/audit.h b/include/linux/audit.h index 4b7caf0c6e10..3278ddf41ce6 100644 --- a/include/linux/audit.h +++ b/include/linux/audit.h @@ -219,8 +219,9 @@ extern void audit_inode(const char *name, const struct inode *inode); /* Private API (for audit.c only) */ extern int audit_receive_filter(int type, int pid, int uid, int seq, void *data, uid_t loginuid); -extern int audit_get_stamp(struct audit_context *ctx, - struct timespec *t, unsigned int *serial); +extern unsigned int audit_serial(void); +extern void auditsc_get_stamp(struct audit_context *ctx, + struct timespec *t, unsigned int *serial); extern int audit_set_loginuid(struct task_struct *task, uid_t loginuid); extern uid_t audit_get_loginuid(struct audit_context *ctx); extern int audit_ipc_perms(unsigned long qbytes, uid_t uid, gid_t gid, mode_t mode); @@ -237,7 +238,7 @@ extern void audit_signal_info(int sig, struct task_struct *t); #define audit_putname(n) do { ; } while (0) #define audit_inode(n,i) do { ; } while (0) #define audit_receive_filter(t,p,u,s,d,l) ({ -EOPNOTSUPP; }) -#define audit_get_stamp(c,t,s) ({ 0; }) +#define auditsc_get_stamp(c,t,s) do { BUG(); } while (0) #define audit_get_loginuid(c) ({ -1; }) #define audit_ipc_perms(q,u,g,m) ({ 0; }) #define audit_socketcall(n,a) ({ 0; }) diff --git a/kernel/audit.c b/kernel/audit.c index f0a003acf621..35306f4369e7 100644 --- a/kernel/audit.c +++ b/kernel/audit.c @@ -597,6 +597,47 @@ err: return NULL; } +/* Compute a serial number for the audit record. Audit records are + * written to user-space as soon as they are generated, so a complete + * audit record may be written in several pieces. The timestamp of the + * record and this serial number are used by the user-space tools to + * determine which pieces belong to the same audit record. The + * (timestamp,serial) tuple is unique for each syscall and is live from + * syscall entry to syscall exit. + * + * Atomic values are only guaranteed to be 24-bit, so we count down. + * + * NOTE: Another possibility is to store the formatted records off the + * audit context (for those records that have a context), and emit them + * all at syscall exit. However, this could delay the reporting of + * significant errors until syscall exit (or never, if the system + * halts). */ +unsigned int audit_serial(void) +{ + static atomic_t serial = ATOMIC_INIT(0xffffff); + unsigned int a, b; + + do { + a = atomic_read(&serial); + if (atomic_dec_and_test(&serial)) + atomic_set(&serial, 0xffffff); + b = atomic_read(&serial); + } while (b != a - 1); + + return 0xffffff - b; +} + +static inline void audit_get_stamp(struct audit_context *ctx, + struct timespec *t, unsigned int *serial) +{ + if (ctx) + auditsc_get_stamp(ctx, t, serial); + else { + *t = CURRENT_TIME; + *serial = audit_serial(); + } +} + /* Obtain an audit buffer. This routine does locking to obtain the * audit buffer, but then no locking is required for calls to * audit_log_*format. If the tsk is a task that is currently in a @@ -630,10 +671,7 @@ struct audit_buffer *audit_log_start(struct audit_context *ctx, int type) return NULL; } - if (!audit_get_stamp(ab->ctx, &t, &serial)) { - t = CURRENT_TIME; - serial = 0; - } + audit_get_stamp(ab->ctx, &t, &serial); audit_log_format(ab, "audit(%lu.%03lu:%u): ", t.tv_sec, t.tv_nsec/1000000, serial); diff --git a/kernel/auditsc.c b/kernel/auditsc.c index 4193811d4fe1..74c2ae804ca8 100644 --- a/kernel/auditsc.c +++ b/kernel/auditsc.c @@ -795,36 +795,6 @@ void audit_free(struct task_struct *tsk) audit_free_context(context); } -/* Compute a serial number for the audit record. Audit records are - * written to user-space as soon as they are generated, so a complete - * audit record may be written in several pieces. The timestamp of the - * record and this serial number are used by the user-space tools to - * determine which pieces belong to the same audit record. The - * (timestamp,serial) tuple is unique for each syscall and is live from - * syscall entry to syscall exit. - * - * Atomic values are only guaranteed to be 24-bit, so we count down. - * - * NOTE: Another possibility is to store the formatted records off the - * audit context (for those records that have a context), and emit them - * all at syscall exit. However, this could delay the reporting of - * significant errors until syscall exit (or never, if the system - * halts). */ -static inline unsigned int audit_serial(void) -{ - static atomic_t serial = ATOMIC_INIT(0xffffff); - unsigned int a, b; - - do { - a = atomic_read(&serial); - if (atomic_dec_and_test(&serial)) - atomic_set(&serial, 0xffffff); - b = atomic_read(&serial); - } while (b != a - 1); - - return 0xffffff - b; -} - /* Fill in audit context at syscall entry. This only happens if the * audit context was created when the task was created and the state or * filters demand the audit context be built. If the state from the @@ -1042,17 +1012,13 @@ void audit_inode(const char *name, const struct inode *inode) context->names[idx].rdev = inode->i_rdev; } -int audit_get_stamp(struct audit_context *ctx, - struct timespec *t, unsigned int *serial) +void auditsc_get_stamp(struct audit_context *ctx, + struct timespec *t, unsigned int *serial) { - if (ctx) { - t->tv_sec = ctx->ctime.tv_sec; - t->tv_nsec = ctx->ctime.tv_nsec; - *serial = ctx->serial; - ctx->auditable = 1; - return 1; - } - return 0; + t->tv_sec = ctx->ctime.tv_sec; + t->tv_nsec = ctx->ctime.tv_nsec; + *serial = ctx->serial; + ctx->auditable = 1; } int audit_set_loginuid(struct task_struct *task, uid_t loginuid) -- cgit v1.2.3 From 8f37d47c9bf74cb48692691086b482e315d07f40 Mon Sep 17 00:00:00 2001 From: David Woodhouse Date: Fri, 27 May 2005 12:17:28 +0100 Subject: AUDIT: Record working directory when syscall arguments are pathnames Signed-off-by: David Woodhouse --- include/linux/audit.h | 3 ++- kernel/auditsc.c | 23 +++++++++++++++++++++++ 2 files changed, 25 insertions(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/audit.h b/include/linux/audit.h index 3278ddf41ce6..bf2ad3ba72eb 100644 --- a/include/linux/audit.h +++ b/include/linux/audit.h @@ -61,11 +61,12 @@ #define AUDIT_SYSCALL 1300 /* Syscall event */ #define AUDIT_FS_WATCH 1301 /* Filesystem watch event */ -#define AUDIT_PATH 1302 /* Filname path information */ +#define AUDIT_PATH 1302 /* Filename path information */ #define AUDIT_IPC 1303 /* IPC record */ #define AUDIT_SOCKETCALL 1304 /* sys_socketcall arguments */ #define AUDIT_CONFIG_CHANGE 1305 /* Audit system configuration change */ #define AUDIT_SOCKADDR 1306 /* sockaddr copied as syscall arg */ +#define AUDIT_CWD 1307 /* Current working directory */ #define AUDIT_AVC 1400 /* SE Linux avc denial or grant */ #define AUDIT_SELINUX_ERR 1401 /* Internal SE Linux Errors */ diff --git a/kernel/auditsc.c b/kernel/auditsc.c index 7556c479d5af..e75f84e1a1a0 100644 --- a/kernel/auditsc.c +++ b/kernel/auditsc.c @@ -145,6 +145,8 @@ struct audit_context { int auditable; /* 1 if record should be written */ int name_count; struct audit_names names[AUDIT_NAMES]; + struct dentry * pwd; + struct vfsmount * pwdmnt; struct audit_context *previous; /* For nested syscalls */ struct audit_aux_data *aux; @@ -552,6 +554,12 @@ static inline void audit_free_names(struct audit_context *context) if (context->names[i].name) __putname(context->names[i].name); context->name_count = 0; + if (context->pwd) + dput(context->pwd); + if (context->pwdmnt) + mntput(context->pwdmnt); + context->pwd = NULL; + context->pwdmnt = NULL; } static inline void audit_free_aux(struct audit_context *context) @@ -745,10 +753,18 @@ static void audit_log_exit(struct audit_context *context) audit_log_end(ab); } + if (context->pwd && context->pwdmnt) { + ab = audit_log_start(context, AUDIT_CWD); + if (ab) { + audit_log_d_path(ab, "cwd=", context->pwd, context->pwdmnt); + audit_log_end(ab); + } + } for (i = 0; i < context->name_count; i++) { ab = audit_log_start(context, AUDIT_PATH); if (!ab) continue; /* audit_panic has been called */ + audit_log_format(ab, "item=%d", i); if (context->names[i].name) { audit_log_format(ab, " name="); @@ -929,6 +945,13 @@ void audit_getname(const char *name) context->names[context->name_count].name = name; context->names[context->name_count].ino = (unsigned long)-1; ++context->name_count; + if (!context->pwd) { + read_lock(¤t->fs->lock); + context->pwd = dget(current->fs->pwd); + context->pwdmnt = mntget(current->fs->pwdmnt); + read_unlock(¤t->fs->lock); + } + } /* Intercept a putname request. Called from -- cgit v1.2.3 From 0baab86b00cdf9785ac2bb2ce1ab63995b3866ca Mon Sep 17 00:00:00 2001 From: Edward Falk Date: Thu, 2 Jun 2005 18:17:13 -0400 Subject: libata: update inline source docs --- drivers/scsi/libata-core.c | 283 +++++++++++++++++++++++++++++++++++++++++++-- include/linux/libata.h | 58 ++++++++++ 2 files changed, 334 insertions(+), 7 deletions(-) (limited to 'include/linux') diff --git a/drivers/scsi/libata-core.c b/drivers/scsi/libata-core.c index 31b2984f379a..86e84ed87bee 100644 --- a/drivers/scsi/libata-core.c +++ b/drivers/scsi/libata-core.c @@ -186,6 +186,28 @@ static void ata_tf_load_mmio(struct ata_port *ap, struct ata_taskfile *tf) ata_wait_idle(ap); } + +/** + * ata_tf_load - send taskfile registers to host controller + * @ap: Port to which output is sent + * @tf: ATA taskfile register set + * + * Outputs ATA taskfile to standard ATA host controller using MMIO + * or PIO as indicated by the ATA_FLAG_MMIO flag. + * Writes the control, feature, nsect, lbal, lbam, and lbah registers. + * Optionally (ATA_TFLAG_LBA48) writes hob_feature, hob_nsect, + * hob_lbal, hob_lbam, and hob_lbah. + * + * This function waits for idle (!BUSY and !DRQ) after writing + * registers. If the control register has a new value, this + * function also waits for idle after writing control and before + * writing the remaining registers. + * + * May be used as the tf_load() entry in ata_port_operations. + * + * LOCKING: + * Inherited from caller. + */ void ata_tf_load(struct ata_port *ap, struct ata_taskfile *tf) { if (ap->flags & ATA_FLAG_MMIO) @@ -195,11 +217,11 @@ void ata_tf_load(struct ata_port *ap, struct ata_taskfile *tf) } /** - * ata_exec_command - issue ATA command to host controller + * ata_exec_command_pio - issue ATA command to host controller * @ap: port to which command is being issued * @tf: ATA taskfile register set * - * Issues PIO/MMIO write to ATA command register, with proper + * Issues PIO write to ATA command register, with proper * synchronization with interrupt handler / other threads. * * LOCKING: @@ -235,6 +257,18 @@ static void ata_exec_command_mmio(struct ata_port *ap, struct ata_taskfile *tf) ata_pause(ap); } + +/** + * ata_exec_command - issue ATA command to host controller + * @ap: port to which command is being issued + * @tf: ATA taskfile register set + * + * Issues PIO/MMIO write to ATA command register, with proper + * synchronization with interrupt handler / other threads. + * + * LOCKING: + * spin_lock_irqsave(host_set lock) + */ void ata_exec_command(struct ata_port *ap, struct ata_taskfile *tf) { if (ap->flags & ATA_FLAG_MMIO) @@ -305,7 +339,7 @@ void ata_tf_to_host_nolock(struct ata_port *ap, struct ata_taskfile *tf) } /** - * ata_tf_read - input device's ATA taskfile shadow registers + * ata_tf_read_pio - input device's ATA taskfile shadow registers * @ap: Port from which input is read * @tf: ATA taskfile register set for storing input * @@ -368,6 +402,23 @@ static void ata_tf_read_mmio(struct ata_port *ap, struct ata_taskfile *tf) } } + +/** + * ata_tf_read - input device's ATA taskfile shadow registers + * @ap: Port from which input is read + * @tf: ATA taskfile register set for storing input + * + * Reads ATA taskfile registers for currently-selected device + * into @tf. + * + * Reads nsect, lbal, lbam, lbah, and device. If ATA_TFLAG_LBA48 + * is set, also reads the hob registers. + * + * May be used as the tf_read() entry in ata_port_operations. + * + * LOCKING: + * Inherited from caller. + */ void ata_tf_read(struct ata_port *ap, struct ata_taskfile *tf) { if (ap->flags & ATA_FLAG_MMIO) @@ -381,7 +432,7 @@ void ata_tf_read(struct ata_port *ap, struct ata_taskfile *tf) * @ap: port where the device is * * Reads ATA taskfile status register for currently-selected device - * and return it's value. This also clears pending interrupts + * and return its value. This also clears pending interrupts * from this device * * LOCKING: @@ -397,7 +448,7 @@ static u8 ata_check_status_pio(struct ata_port *ap) * @ap: port where the device is * * Reads ATA taskfile status register for currently-selected device - * via MMIO and return it's value. This also clears pending interrupts + * via MMIO and return its value. This also clears pending interrupts * from this device * * LOCKING: @@ -408,6 +459,20 @@ static u8 ata_check_status_mmio(struct ata_port *ap) return readb((void __iomem *) ap->ioaddr.status_addr); } + +/** + * ata_check_status - Read device status reg & clear interrupt + * @ap: port where the device is + * + * Reads ATA taskfile status register for currently-selected device + * and return its value. This also clears pending interrupts + * from this device + * + * May be used as the check_status() entry in ata_port_operations. + * + * LOCKING: + * Inherited from caller. + */ u8 ata_check_status(struct ata_port *ap) { if (ap->flags & ATA_FLAG_MMIO) @@ -415,6 +480,20 @@ u8 ata_check_status(struct ata_port *ap) return ata_check_status_pio(ap); } + +/** + * ata_altstatus - Read device alternate status reg + * @ap: port where the device is + * + * Reads ATA taskfile alternate status register for + * currently-selected device and return its value. + * + * Note: may NOT be used as the check_altstatus() entry in + * ata_port_operations. + * + * LOCKING: + * Inherited from caller. + */ u8 ata_altstatus(struct ata_port *ap) { if (ap->ops->check_altstatus) @@ -425,6 +504,20 @@ u8 ata_altstatus(struct ata_port *ap) return inb(ap->ioaddr.altstatus_addr); } + +/** + * ata_chk_err - Read device error reg + * @ap: port where the device is + * + * Reads ATA taskfile error register for + * currently-selected device and return its value. + * + * Note: may NOT be used as the check_err() entry in + * ata_port_operations. + * + * LOCKING: + * Inherited from caller. + */ u8 ata_chk_err(struct ata_port *ap) { if (ap->ops->check_err) @@ -873,10 +966,24 @@ void ata_dev_id_string(u16 *id, unsigned char *s, } } + +/** + * ata_noop_dev_select - Select device 0/1 on ATA bus + * @ap: ATA channel to manipulate + * @device: ATA device (numbered from zero) to select + * + * This function performs no actual function. + * + * May be used as the dev_select() entry in ata_port_operations. + * + * LOCKING: + * caller. + */ void ata_noop_dev_select (struct ata_port *ap, unsigned int device) { } + /** * ata_std_dev_select - Select device 0/1 on ATA bus * @ap: ATA channel to manipulate @@ -884,7 +991,9 @@ void ata_noop_dev_select (struct ata_port *ap, unsigned int device) * * Use the method defined in the ATA specification to * make either device 0, or device 1, active on the - * ATA channel. + * ATA channel. Works with both PIO and MMIO. + * + * May be used as the dev_select() entry in ata_port_operations. * * LOCKING: * caller. @@ -2127,6 +2236,19 @@ void ata_qc_prep(struct ata_queued_cmd *qc) * spin_lock_irqsave(host_set lock) */ + + +/** + * ata_sg_init_one - Prepare a one-entry scatter-gather list. + * @qc: Queued command + * @buf: transfer buffer + * @buflen: length of buf + * + * Builds a single-entry scatter-gather list to initiate a + * transfer utilizing the specified buffer. + * + * LOCKING: + */ void ata_sg_init_one(struct ata_queued_cmd *qc, void *buf, unsigned int buflen) { struct scatterlist *sg; @@ -2158,6 +2280,18 @@ void ata_sg_init_one(struct ata_queued_cmd *qc, void *buf, unsigned int buflen) * spin_lock_irqsave(host_set lock) */ + +/** + * ata_sg_init - Assign a scatter gather list to a queued command + * @qc: Queued command + * @sg: Scatter-gather list + * @n_elem: length of sg list + * + * Attaches a scatter-gather list to a queued command. + * + * LOCKING: + */ + void ata_sg_init(struct ata_queued_cmd *qc, struct scatterlist *sg, unsigned int n_elem) { @@ -2331,6 +2465,18 @@ static void ata_pio_complete (struct ata_port *ap) ata_qc_complete(qc, drv_stat); } + +/** + * swap_buf_le16 - + * @buf: Buffer to swap + * @buf_words: Number of 16-bit words in buffer. + * + * Swap halves of 16-bit words if needed to convert from + * little-endian byte order to native cpu byte order, or + * vice-versa. + * + * LOCKING: + */ void swap_buf_le16(u16 *buf, unsigned int buf_words) { #ifdef __BIG_ENDIAN @@ -2992,6 +3138,7 @@ err_out: return -1; } + /** * ata_qc_issue_prot - issue taskfile to device in proto-dependent manner * @qc: command to issue to device @@ -3001,6 +3148,8 @@ err_out: * classes called "protocols", and issuing each type of protocol * is slightly different. * + * May be used as the qc_issue() entry in ata_port_operations. + * * LOCKING: * spin_lock_irqsave(host_set lock) * @@ -3058,7 +3207,7 @@ int ata_qc_issue_prot(struct ata_queued_cmd *qc) } /** - * ata_bmdma_setup - Set up PCI IDE BMDMA transaction + * ata_bmdma_setup_mmio - Set up PCI IDE BMDMA transaction * @qc: Info associated with this ATA transaction. * * LOCKING: @@ -3165,6 +3314,18 @@ static void ata_bmdma_start_pio (struct ata_queued_cmd *qc) ap->ioaddr.bmdma_addr + ATA_DMA_CMD); } + +/** + * ata_bmdma_start - Start a PCI IDE BMDMA transaction + * @qc: Info associated with this ATA transaction. + * + * Writes the ATA_DMA_START flag to the DMA command register. + * + * May be used as the bmdma_start() entry in ata_port_operations. + * + * LOCKING: + * spin_lock_irqsave(host_set lock) + */ void ata_bmdma_start(struct ata_queued_cmd *qc) { if (qc->ap->flags & ATA_FLAG_MMIO) @@ -3173,6 +3334,20 @@ void ata_bmdma_start(struct ata_queued_cmd *qc) ata_bmdma_start_pio(qc); } + +/** + * ata_bmdma_setup - Set up PCI IDE BMDMA transaction + * @qc: Info associated with this ATA transaction. + * + * Writes address of PRD table to device's PRD Table Address + * register, sets the DMA control register, and calls + * ops->exec_command() to start the transfer. + * + * May be used as the bmdma_setup() entry in ata_port_operations. + * + * LOCKING: + * spin_lock_irqsave(host_set lock) + */ void ata_bmdma_setup(struct ata_queued_cmd *qc) { if (qc->ap->flags & ATA_FLAG_MMIO) @@ -3181,6 +3356,19 @@ void ata_bmdma_setup(struct ata_queued_cmd *qc) ata_bmdma_setup_pio(qc); } + +/** + * ata_bmdma_irq_clear - Clear PCI IDE BMDMA interrupt. + * @qc: Info associated with this ATA transaction. + * + * Clear interrupt and error flags in DMA status register. + * + * May be used as the irq_clear() entry in ata_port_operations. + * + * LOCKING: + * spin_lock_irqsave(host_set lock) + */ + void ata_bmdma_irq_clear(struct ata_port *ap) { if (ap->flags & ATA_FLAG_MMIO) { @@ -3193,6 +3381,19 @@ void ata_bmdma_irq_clear(struct ata_port *ap) } + +/** + * ata_bmdma_status - Read PCI IDE BMDMA status + * @qc: Info associated with this ATA transaction. + * + * Read and return BMDMA status register. + * + * May be used as the bmdma_status() entry in ata_port_operations. + * + * LOCKING: + * spin_lock_irqsave(host_set lock) + */ + u8 ata_bmdma_status(struct ata_port *ap) { u8 host_stat; @@ -3204,6 +3405,19 @@ u8 ata_bmdma_status(struct ata_port *ap) return host_stat; } + +/** + * ata_bmdma_stop - Stop PCI IDE BMDMA transfer + * @qc: Info associated with this ATA transaction. + * + * Clears the ATA_DMA_START flag in the dma control register + * + * May be used as the bmdma_stop() entry in ata_port_operations. + * + * LOCKING: + * spin_lock_irqsave(host_set lock) + */ + void ata_bmdma_stop(struct ata_port *ap) { if (ap->flags & ATA_FLAG_MMIO) { @@ -3407,6 +3621,19 @@ err_out: ata_qc_complete(qc, ATA_ERR); } + +/** + * ata_port_start - Set port up for dma. + * @ap: Port to initialize + * + * Called just after data structures for each port are + * initialized. Allocates space for PRD table. + * + * May be used as the port_start() entry in ata_port_operations. + * + * LOCKING: + */ + int ata_port_start (struct ata_port *ap) { struct device *dev = ap->host_set->dev; @@ -3420,6 +3647,18 @@ int ata_port_start (struct ata_port *ap) return 0; } + +/** + * ata_port_stop - Undo ata_port_start() + * @ap: Port to shut down + * + * Frees the PRD table. + * + * May be used as the port_stop() entry in ata_port_operations. + * + * LOCKING: + */ + void ata_port_stop (struct ata_port *ap) { struct device *dev = ap->host_set->dev; @@ -3720,7 +3959,15 @@ int ata_scsi_release(struct Scsi_Host *host) /** * ata_std_ports - initialize ioaddr with standard port offsets. * @ioaddr: IO address structure to be initialized + * + * Utility function which initializes data_addr, error_addr, + * feature_addr, nsect_addr, lbal_addr, lbam_addr, lbah_addr, + * device_addr, status_addr, and command_addr to standard offsets + * relative to cmd_addr. + * + * Does not set ctl_addr, altstatus_addr, bmdma_addr, or scr_addr. */ + void ata_std_ports(struct ata_ioports *ioaddr) { ioaddr->data_addr = ioaddr->cmd_addr + ATA_REG_DATA; @@ -3762,6 +4009,20 @@ ata_probe_ent_alloc(struct device *dev, struct ata_port_info *port) return probe_ent; } + + +/** + * ata_pci_init_native_mode - Initialize native-mode driver + * @pdev: pci device to be initialized + * @port: array[2] of pointers to port info structures. + * + * Utility function which allocates and initializes an + * ata_probe_ent structure for a standard dual-port + * PIO-based IDE controller. The returned ata_probe_ent + * structure can be passed to ata_device_add(). The returned + * ata_probe_ent structure should then be freed with kfree(). + */ + #ifdef CONFIG_PCI struct ata_probe_ent * ata_pci_init_native_mode(struct pci_dev *pdev, struct ata_port_info **port) @@ -3843,6 +4104,14 @@ ata_pci_init_legacy_mode(struct pci_dev *pdev, struct ata_port_info **port, * @port_info: Information from low-level host driver * @n_ports: Number of ports attached to host controller * + * This is a helper function which can be called from a driver's + * xxx_init_one() probe function if the hardware uses traditional + * IDE taskfile registers. + * + * This function calls pci_enable_device(), reserves its register + * regions, sets the dma mask, enables bus master mode, and calls + * ata_device_add() + * * LOCKING: * Inherited from PCI layer (may sleep). * diff --git a/include/linux/libata.h b/include/linux/libata.h index 1f7e2039a04e..ad410590664f 100644 --- a/include/linux/libata.h +++ b/include/linux/libata.h @@ -466,12 +466,34 @@ static inline u8 ata_chk_status(struct ata_port *ap) return ap->ops->check_status(ap); } + +/** + * ata_pause - Flush writes and pause 400 nanoseconds. + * @ap: Port to wait for. + * + * LOCKING: + * Inherited from caller. + */ + static inline void ata_pause(struct ata_port *ap) { ata_altstatus(ap); ndelay(400); } + +/** + * ata_busy_wait - Wait for a port status register + * @ap: Port to wait for. + * + * Waits up to max*10 microseconds for the selected bits in the port's + * status register to be cleared. + * Returns final value of status register. + * + * LOCKING: + * Inherited from caller. + */ + static inline u8 ata_busy_wait(struct ata_port *ap, unsigned int bits, unsigned int max) { @@ -486,6 +508,18 @@ static inline u8 ata_busy_wait(struct ata_port *ap, unsigned int bits, return status; } + +/** + * ata_wait_idle - Wait for a port to be idle. + * @ap: Port to wait for. + * + * Waits up to 10ms for port's BUSY and DRQ signals to clear. + * Returns final value of status register. + * + * LOCKING: + * Inherited from caller. + */ + static inline u8 ata_wait_idle(struct ata_port *ap) { u8 status = ata_busy_wait(ap, ATA_BUSY | ATA_DRQ, 1000); @@ -524,6 +558,18 @@ static inline void ata_tf_init(struct ata_port *ap, struct ata_taskfile *tf, uns tf->device = ATA_DEVICE_OBS | ATA_DEV1; } + +/** + * ata_irq_on - Enable interrupts on a port. + * @ap: Port on which interrupts are enabled. + * + * Enable interrupts on a legacy IDE device using MMIO or PIO, + * wait for idle, clear any pending interrupts. + * + * LOCKING: + * Inherited from caller. + */ + static inline u8 ata_irq_on(struct ata_port *ap) { struct ata_ioports *ioaddr = &ap->ioaddr; @@ -543,6 +589,18 @@ static inline u8 ata_irq_on(struct ata_port *ap) return tmp; } + +/** + * ata_irq_ack - Acknowledge a device interrupt. + * @ap: Port on which interrupts are enabled. + * + * Wait up to 10 ms for legacy IDE device to become idle (BUSY + * or BUSY+DRQ clear). Obtain dma status and port status from + * device. Clear the interrupt. Return port status. + * + * LOCKING: + */ + static inline u8 ata_irq_ack(struct ata_port *ap, unsigned int chk_drq) { unsigned int bits = chk_drq ? ATA_BUSY | ATA_DRQ : ATA_BUSY; -- cgit v1.2.3 From b597ef4712c05c962640a655386a7f06cc1a1fbc Mon Sep 17 00:00:00 2001 From: Christoph Hellwig Date: Thu, 2 Jun 2005 16:36:00 -0700 Subject: [NET]: Fix locking in shaper driver. o use a semaphore instead of an opencoded and racy lock o move locking out of shaper_kick and into the callers - most just released the lock before calling shaper_kick o remove in_interrupt() tests. from ->close we can always block, from ->hard_start_xmit and timer context never Signed-off-by: Christoph Hellwig Signed-off-by: David S. Miller --- drivers/net/shaper.c | 86 +++++++++++------------------------------------ include/linux/if_shaper.h | 3 +- 2 files changed, 20 insertions(+), 69 deletions(-) (limited to 'include/linux') diff --git a/drivers/net/shaper.c b/drivers/net/shaper.c index e68cf5fb4920..20edeb345792 100644 --- a/drivers/net/shaper.c +++ b/drivers/net/shaper.c @@ -100,35 +100,8 @@ static int sh_debug; /* Debug flag */ #define SHAPER_BANNER "CymruNet Traffic Shaper BETA 0.04 for Linux 2.1\n" -/* - * Locking - */ - -static int shaper_lock(struct shaper *sh) -{ - /* - * Lock in an interrupt must fail - */ - while (test_and_set_bit(0, &sh->locked)) - { - if (!in_interrupt()) - sleep_on(&sh->wait_queue); - else - return 0; - - } - return 1; -} - static void shaper_kick(struct shaper *sh); -static void shaper_unlock(struct shaper *sh) -{ - clear_bit(0, &sh->locked); - wake_up(&sh->wait_queue); - shaper_kick(sh); -} - /* * Compute clocks on a buffer */ @@ -157,17 +130,15 @@ static void shaper_setspeed(struct shaper *shaper, int bitspersec) * Throw a frame at a shaper. */ -static int shaper_qframe(struct shaper *shaper, struct sk_buff *skb) + +static int shaper_start_xmit(struct sk_buff *skb, struct net_device *dev) { + struct shaper *shaper = dev->priv; struct sk_buff *ptr; - /* - * Get ready to work on this shaper. Lock may fail if its - * an interrupt and locked. - */ - - if(!shaper_lock(shaper)) - return -1; + if (down_trylock(&shaper->sem)) + return -1; + ptr=shaper->sendq.prev; /* @@ -260,7 +231,8 @@ static int shaper_qframe(struct shaper *shaper, struct sk_buff *skb) dev_kfree_skb(ptr); shaper->stats.collisions++; } - shaper_unlock(shaper); + shaper_kick(shaper); + up(&shaper->sem); return 0; } @@ -297,8 +269,13 @@ static void shaper_queue_xmit(struct shaper *shaper, struct sk_buff *skb) static void shaper_timer(unsigned long data) { - struct shaper *sh=(struct shaper *)data; - shaper_kick(sh); + struct shaper *shaper = (struct shaper *)data; + + if (!down_trylock(&shaper->sem)) { + shaper_kick(shaper); + up(&shaper->sem); + } else + mod_timer(&shaper->timer, jiffies); } /* @@ -310,19 +287,6 @@ static void shaper_kick(struct shaper *shaper) { struct sk_buff *skb; - /* - * Shaper unlock will kick - */ - - if (test_and_set_bit(0, &shaper->locked)) - { - if(sh_debug) - printk("Shaper locked.\n"); - mod_timer(&shaper->timer, jiffies); - return; - } - - /* * Walk the list (may be empty) */ @@ -364,8 +328,6 @@ static void shaper_kick(struct shaper *shaper) if(skb!=NULL) mod_timer(&shaper->timer, SHAPERCB(skb)->shapeclock); - - clear_bit(0, &shaper->locked); } @@ -376,14 +338,12 @@ static void shaper_kick(struct shaper *shaper) static void shaper_flush(struct shaper *shaper) { struct sk_buff *skb; - if(!shaper_lock(shaper)) - { - printk(KERN_ERR "shaper: shaper_flush() called by an irq!\n"); - return; - } + + down(&shaper->sem); while((skb=skb_dequeue(&shaper->sendq))!=NULL) dev_kfree_skb(skb); - shaper_unlock(shaper); + shaper_kick(shaper); + up(&shaper->sem); } /* @@ -426,13 +386,6 @@ static int shaper_close(struct net_device *dev) * ARP and other resolutions and not before. */ - -static int shaper_start_xmit(struct sk_buff *skb, struct net_device *dev) -{ - struct shaper *sh=dev->priv; - return shaper_qframe(sh, skb); -} - static struct net_device_stats *shaper_get_stats(struct net_device *dev) { struct shaper *sh=dev->priv; @@ -623,7 +576,6 @@ static void shaper_init_priv(struct net_device *dev) init_timer(&sh->timer); sh->timer.function=shaper_timer; sh->timer.data=(unsigned long)sh; - init_waitqueue_head(&sh->wait_queue); } /* diff --git a/include/linux/if_shaper.h b/include/linux/if_shaper.h index 0485b256d043..004e6f09a6e2 100644 --- a/include/linux/if_shaper.h +++ b/include/linux/if_shaper.h @@ -23,7 +23,7 @@ struct shaper __u32 shapeclock; unsigned long recovery; /* Time we can next clock a packet out on an empty queue */ - unsigned long locked; + struct semaphore sem; struct net_device_stats stats; struct net_device *dev; int (*hard_start_xmit) (struct sk_buff *skb, @@ -38,7 +38,6 @@ struct shaper int (*hard_header_cache)(struct neighbour *neigh, struct hh_cache *hh); void (*header_cache_update)(struct hh_cache *hh, struct net_device *dev, unsigned char * haddr); struct net_device_stats* (*get_stats)(struct net_device *dev); - wait_queue_head_t wait_queue; struct timer_list timer; }; -- cgit v1.2.3 From 5ba0eac6e0b7e2889649a1105d97c600595e2bb1 Mon Sep 17 00:00:00 2001 From: Jiri Benc Date: Thu, 2 Jun 2005 16:48:05 -0700 Subject: [NET]: Fix HH_DATA_OFF. When the hardware header size is a multiple of HH_DATA_MOD, HH_DATA_OFF() incorrectly returns HH_DATA_MOD (instead of 0). This affects ieee80211 layer as 802.11 header is 32 bytes long. Signed-off-by: Jiri Benc Signed-off-by: David S. Miller --- include/linux/netdevice.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/netdevice.h b/include/linux/netdevice.h index 470af8c1a4a0..ba5d1236aa17 100644 --- a/include/linux/netdevice.h +++ b/include/linux/netdevice.h @@ -204,7 +204,7 @@ struct hh_cache /* cached hardware header; allow for machine alignment needs. */ #define HH_DATA_MOD 16 #define HH_DATA_OFF(__len) \ - (HH_DATA_MOD - ((__len) & (HH_DATA_MOD - 1))) + (HH_DATA_MOD - (((__len - 1) & (HH_DATA_MOD - 1)) + 1)) #define HH_DATA_ALIGN(__len) \ (((__len)+(HH_DATA_MOD-1))&~(HH_DATA_MOD - 1)) unsigned long hh_data[HH_DATA_ALIGN(LL_MAX_HEADER) / sizeof(long)]; -- cgit v1.2.3 From 719df469cb51199316ae2a11c75a8046be34b899 Mon Sep 17 00:00:00 2001 From: Roman Kagan Date: Fri, 6 May 2005 00:55:56 +0400 Subject: [PATCH] USB: update urb documentation On Wed, May 04, 2005 at 01:37:30PM -0700, David Brownell wrote: > On Wednesday 04 May 2005 12:19 pm, Roman Kagan wrote: > > struct urb { > > /* private, usb core and host controller only fields in the urb */ > > ... > > struct list_head urb_list; /* list pointer to all active urbs */ > > ... > > }; > > > > Is it safe to use it for driver's purposes when the driver owns the urb, > > that is, starting from the completion routine until the urb is submitted > > with usb_submit_urb()? > > Right now, it should be. Great! FWIW I've briefly tested a modified version of usbatm using the list head in struct urb instead of creating a wrapper struct, and I haven't seen any failures yet. So I tend to believe that your "should be" actually means "is" :) > > If it is, can it be guaranteed in future, e.g. > > by moving the list head into the public section of struct urb? > > In fact I'm not sure why it ever got called "private" to usbcore/hcds. > I thought the idea was that it should be like urb->status, reserved for > whoever controls the URB. OK then how about the following (essentially documentation) patch? Signed-off-by: Roman Kagan Acked-by: David Brownell Signed-off-by: Greg Kroah-Hartman --- include/linux/usb.h | 6 +++++- 1 file changed, 5 insertions(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/usb.h b/include/linux/usb.h index 41d1a644c9d4..2d1ac5058534 100644 --- a/include/linux/usb.h +++ b/include/linux/usb.h @@ -796,6 +796,10 @@ typedef void (*usb_complete_t)(struct urb *, struct pt_regs *); * of the iso_frame_desc array, and the number of errors is reported in * error_count. Completion callbacks for ISO transfers will normally * (re)submit URBs to ensure a constant transfer rate. + * + * Note that even fields marked "public" should not be touched by the driver + * when the urb is owned by the hcd, that is, since the call to + * usb_submit_urb() till the entry into the completion routine. */ struct urb { @@ -803,12 +807,12 @@ struct urb struct kref kref; /* reference count of the URB */ spinlock_t lock; /* lock for the URB */ void *hcpriv; /* private data for host controller */ - struct list_head urb_list; /* list pointer to all active urbs */ int bandwidth; /* bandwidth for INT/ISO request */ atomic_t use_count; /* concurrent submissions counter */ u8 reject; /* submissions will fail */ /* public, documented fields in the urb that can be used by drivers */ + struct list_head urb_list; /* list head for use by the urb owner */ struct usb_device *dev; /* (in) pointer to associated device */ unsigned int pipe; /* (in) pipe information */ int status; /* (return) non-ISO status */ -- cgit v1.2.3 From 3f5948fa2cbbda1261eec9a39ef3004b3caf73fb Mon Sep 17 00:00:00 2001 From: David Mosberger Date: Mon, 6 Jun 2005 15:50:09 -0700 Subject: [PATCH] Include before testing CONFIG_ACPI I'm not sure why this issue is suddenly showing, but without this patchlet, the zx1 config won't compile anymore (e.g., to see the compilation-error, look for "***" in [1]). [1] http://www.gelato.unsw.edu.au/kerncomp/results//2005-06-06-17-00/zx1_defconfig-log.html Signed-off-by: David Mosberger-Tang Cc: "Brown, Len" Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/acpi.h | 2 ++ 1 file changed, 2 insertions(+) (limited to 'include/linux') diff --git a/include/linux/acpi.h b/include/linux/acpi.h index d5a55bdb9c3c..b123cc08773d 100644 --- a/include/linux/acpi.h +++ b/include/linux/acpi.h @@ -25,6 +25,8 @@ #ifndef _LINUX_ACPI_H #define _LINUX_ACPI_H +#include + #ifdef CONFIG_ACPI #ifndef _LINUX -- cgit v1.2.3 From d0de98fa16169562bd74913c6c9b3857f9065c79 Mon Sep 17 00:00:00 2001 From: Alan Hourihane Date: Tue, 31 May 2005 19:50:49 +0100 Subject: [PATCH] i945G patch for agpgart Attached is a small patch for i945G support against 2.6.11.11. From: Alan Hourihane Signed-off-by: Dave Jones --- drivers/char/agp/intel-agp.c | 15 +++++++++++++-- include/linux/pci_ids.h | 2 ++ 2 files changed, 15 insertions(+), 2 deletions(-) (limited to 'include/linux') diff --git a/drivers/char/agp/intel-agp.c b/drivers/char/agp/intel-agp.c index 8c7d727432bb..6a5047e0d333 100644 --- a/drivers/char/agp/intel-agp.c +++ b/drivers/char/agp/intel-agp.c @@ -418,7 +418,8 @@ static void intel_i830_init_gtt_entries(void) case I915_GMCH_GMS_STOLEN_48M: /* Check it's really I915G */ if (agp_bridge->dev->device == PCI_DEVICE_ID_INTEL_82915G_HB || - agp_bridge->dev->device == PCI_DEVICE_ID_INTEL_82915GM_HB) + agp_bridge->dev->device == PCI_DEVICE_ID_INTEL_82915GM_HB || + agp_bridge->dev->device == PCI_DEVICE_ID_INTEL_82945G_HB) gtt_entries = MB(48) - KB(size); else gtt_entries = 0; @@ -426,7 +427,8 @@ static void intel_i830_init_gtt_entries(void) case I915_GMCH_GMS_STOLEN_64M: /* Check it's really I915G */ if (agp_bridge->dev->device == PCI_DEVICE_ID_INTEL_82915G_HB || - agp_bridge->dev->device == PCI_DEVICE_ID_INTEL_82915GM_HB) + agp_bridge->dev->device == PCI_DEVICE_ID_INTEL_82915GM_HB || + agp_bridge->dev->device == PCI_DEVICE_ID_INTEL_82945G_HB) gtt_entries = MB(64) - KB(size); else gtt_entries = 0; @@ -1662,6 +1664,14 @@ static int __devinit agp_intel_probe(struct pci_dev *pdev, } name = "915GM"; break; + case PCI_DEVICE_ID_INTEL_82945G_HB: + if (find_i830(PCI_DEVICE_ID_INTEL_82945G_IG)) { + bridge->driver = &intel_915_driver; + } else { + bridge->driver = &intel_845_driver; + } + name = "945G"; + break; case PCI_DEVICE_ID_INTEL_7505_0: bridge->driver = &intel_7505_driver; name = "E7505"; @@ -1801,6 +1811,7 @@ static struct pci_device_id agp_intel_pci_table[] = { ID(PCI_DEVICE_ID_INTEL_7205_0), ID(PCI_DEVICE_ID_INTEL_82915G_HB), ID(PCI_DEVICE_ID_INTEL_82915GM_HB), + ID(PCI_DEVICE_ID_INTEL_82945G_HB), { } }; diff --git a/include/linux/pci_ids.h b/include/linux/pci_ids.h index b0d6134e1ee6..18f734ec9181 100644 --- a/include/linux/pci_ids.h +++ b/include/linux/pci_ids.h @@ -2382,6 +2382,8 @@ #define PCI_DEVICE_ID_INTEL_82915G_IG 0x2582 #define PCI_DEVICE_ID_INTEL_82915GM_HB 0x2590 #define PCI_DEVICE_ID_INTEL_82915GM_IG 0x2592 +#define PCI_DEVICE_ID_INTEL_82945G_HB 0x2770 +#define PCI_DEVICE_ID_INTEL_82945G_IG 0x2772 #define PCI_DEVICE_ID_INTEL_ICH6_0 0x2640 #define PCI_DEVICE_ID_INTEL_ICH6_1 0x2641 #define PCI_DEVICE_ID_INTEL_ICH6_2 0x2642 -- cgit v1.2.3 From 6d1cfbab4de64f2d0c5b0f81177ade0d75b69288 Mon Sep 17 00:00:00 2001 From: Michael Chan Date: Wed, 8 Jun 2005 14:13:14 -0700 Subject: [TG3]: Fix 5700/5701 DMA corruption on Apple G4. Fix 5700/5701 DMA write corruption on Apple G4 by detecting the Apple UniNorth PCI 1.5 chipset and adjusting the DMA write boundary to 16. DMA test fails to detect the problem with this chipset. Thanks to Manuel Perez Ayala for reporting the problem and helping to debug it. Signed-off-by: Michael Chan Signed-off-by: David S. Miller --- drivers/net/tg3.c | 18 ++++++++++++++++-- include/linux/pci_ids.h | 1 + 2 files changed, 17 insertions(+), 2 deletions(-) (limited to 'include/linux') diff --git a/drivers/net/tg3.c b/drivers/net/tg3.c index e944aac258e3..77337c3b4285 100644 --- a/drivers/net/tg3.c +++ b/drivers/net/tg3.c @@ -9695,10 +9695,24 @@ static int __devinit tg3_test_dma(struct tg3 *tp) } if ((tp->dma_rwctrl & DMA_RWCTRL_WRITE_BNDRY_MASK) != DMA_RWCTRL_WRITE_BNDRY_16) { + static struct pci_device_id dma_wait_state_chipsets[] = { + { PCI_DEVICE(PCI_VENDOR_ID_APPLE, + PCI_DEVICE_ID_APPLE_UNI_N_PCI15) }, + { }, + }; + /* DMA test passed without adjusting DMA boundary, - * just restore the calculated DMA boundary + * now look for chipsets that are known to expose the + * DMA bug without failing the test. */ - tp->dma_rwctrl = saved_dma_rwctrl; + if (pci_dev_present(dma_wait_state_chipsets)) { + tp->dma_rwctrl &= ~DMA_RWCTRL_WRITE_BNDRY_MASK; + tp->dma_rwctrl |= DMA_RWCTRL_WRITE_BNDRY_16; + } + else + /* Safe to use the calculated DMA boundary. */ + tp->dma_rwctrl = saved_dma_rwctrl; + tw32(TG3PCI_DMA_RW_CTRL, tp->dma_rwctrl); } diff --git a/include/linux/pci_ids.h b/include/linux/pci_ids.h index 18f734ec9181..b8b4ebf9abf1 100644 --- a/include/linux/pci_ids.h +++ b/include/linux/pci_ids.h @@ -874,6 +874,7 @@ #define PCI_DEVICE_ID_APPLE_KL_USB_P 0x0026 #define PCI_DEVICE_ID_APPLE_UNI_N_AGP_P 0x0027 #define PCI_DEVICE_ID_APPLE_UNI_N_AGP15 0x002d +#define PCI_DEVICE_ID_APPLE_UNI_N_PCI15 0x002e #define PCI_DEVICE_ID_APPLE_UNI_N_FW2 0x0030 #define PCI_DEVICE_ID_APPLE_UNI_N_GMAC2 0x0032 #define PCI_DEVIEC_ID_APPLE_UNI_N_ATA 0x0033 -- cgit v1.2.3 From 4890062960cbc4d3cebdbd8261a68bc85efcf5d4 Mon Sep 17 00:00:00 2001 From: Thomas Graf Date: Wed, 8 Jun 2005 15:10:48 -0700 Subject: [PKT_SCHED]: Allow socket attributes to be matched on via meta ematch Adds meta collectors for all socket attributes that make sense to be filtered upon. Some of them are only useful for debugging but having them doesn't hurt. Signed-off-by: Thomas Graf Signed-off-by: David S. Miller --- include/linux/tc_ematch/tc_em_meta.h | 30 ++++ net/sched/em_meta.c | 291 ++++++++++++++++++++++++++++++++--- 2 files changed, 297 insertions(+), 24 deletions(-) (limited to 'include/linux') diff --git a/include/linux/tc_ematch/tc_em_meta.h b/include/linux/tc_ematch/tc_em_meta.h index aa6b48bb4dcd..a6b2cc530af5 100644 --- a/include/linux/tc_ematch/tc_em_meta.h +++ b/include/linux/tc_ematch/tc_em_meta.h @@ -56,6 +56,36 @@ enum TCF_META_ID_TCCLASSID, TCF_META_ID_RTCLASSID, TCF_META_ID_RTIIF, + TCF_META_ID_SK_FAMILY, + TCF_META_ID_SK_STATE, + TCF_META_ID_SK_REUSE, + TCF_META_ID_SK_BOUND_IF, + TCF_META_ID_SK_REFCNT, + TCF_META_ID_SK_SHUTDOWN, + TCF_META_ID_SK_PROTO, + TCF_META_ID_SK_TYPE, + TCF_META_ID_SK_RCVBUF, + TCF_META_ID_SK_RMEM_ALLOC, + TCF_META_ID_SK_WMEM_ALLOC, + TCF_META_ID_SK_OMEM_ALLOC, + TCF_META_ID_SK_WMEM_QUEUED, + TCF_META_ID_SK_RCV_QLEN, + TCF_META_ID_SK_SND_QLEN, + TCF_META_ID_SK_ERR_QLEN, + TCF_META_ID_SK_FORWARD_ALLOCS, + TCF_META_ID_SK_SNDBUF, + TCF_META_ID_SK_ALLOCS, + TCF_META_ID_SK_ROUTE_CAPS, + TCF_META_ID_SK_HASHENT, + TCF_META_ID_SK_LINGERTIME, + TCF_META_ID_SK_ACK_BACKLOG, + TCF_META_ID_SK_MAX_ACK_BACKLOG, + TCF_META_ID_SK_PRIO, + TCF_META_ID_SK_RCVLOWAT, + TCF_META_ID_SK_RCVTIMEO, + TCF_META_ID_SK_SNDTIMEO, + TCF_META_ID_SK_SENDMSG_OFF, + TCF_META_ID_SK_WRITE_PENDING, __TCF_META_ID_MAX }; #define TCF_META_ID_MAX (__TCF_META_ID_MAX - 1) diff --git a/net/sched/em_meta.c b/net/sched/em_meta.c index f1eeaf65cee5..ed2a46cbb67f 100644 --- a/net/sched/em_meta.c +++ b/net/sched/em_meta.c @@ -32,7 +32,7 @@ * +-----------+ +-----------+ * | | * ---> meta_ops[INT][INDEV](...) | - * | | + * | | * ----------- | * V V * +-----------+ +-----------+ @@ -70,6 +70,7 @@ #include #include #include +#include struct meta_obj { @@ -283,6 +284,214 @@ META_COLLECTOR(int_rtiif) dst->value = ((struct rtable*) skb->dst)->fl.iif; } +/************************************************************************** + * Socket Attributes + **************************************************************************/ + +#define SKIP_NONLOCAL(skb) \ + if (unlikely(skb->sk == NULL)) { \ + *err = -1; \ + return; \ + } + +META_COLLECTOR(int_sk_family) +{ + SKIP_NONLOCAL(skb); + dst->value = skb->sk->sk_family; +} + +META_COLLECTOR(int_sk_state) +{ + SKIP_NONLOCAL(skb); + dst->value = skb->sk->sk_state; +} + +META_COLLECTOR(int_sk_reuse) +{ + SKIP_NONLOCAL(skb); + dst->value = skb->sk->sk_reuse; +} + +META_COLLECTOR(int_sk_bound_if) +{ + SKIP_NONLOCAL(skb); + /* No error if bound_dev_if is 0, legal userspace check */ + dst->value = skb->sk->sk_bound_dev_if; +} + +META_COLLECTOR(var_sk_bound_if) +{ + SKIP_NONLOCAL(skb); + + if (skb->sk->sk_bound_dev_if == 0) { + dst->value = (unsigned long) "any"; + dst->len = 3; + } else { + struct net_device *dev; + + dev = dev_get_by_index(skb->sk->sk_bound_dev_if); + *err = var_dev(dev, dst); + if (dev) + dev_put(dev); + } +} + +META_COLLECTOR(int_sk_refcnt) +{ + SKIP_NONLOCAL(skb); + dst->value = atomic_read(&skb->sk->sk_refcnt); +} + +META_COLLECTOR(int_sk_rcvbuf) +{ + SKIP_NONLOCAL(skb); + dst->value = skb->sk->sk_rcvbuf; +} + +META_COLLECTOR(int_sk_shutdown) +{ + SKIP_NONLOCAL(skb); + dst->value = skb->sk->sk_shutdown; +} + +META_COLLECTOR(int_sk_proto) +{ + SKIP_NONLOCAL(skb); + dst->value = skb->sk->sk_protocol; +} + +META_COLLECTOR(int_sk_type) +{ + SKIP_NONLOCAL(skb); + dst->value = skb->sk->sk_type; +} + +META_COLLECTOR(int_sk_rmem_alloc) +{ + SKIP_NONLOCAL(skb); + dst->value = atomic_read(&skb->sk->sk_rmem_alloc); +} + +META_COLLECTOR(int_sk_wmem_alloc) +{ + SKIP_NONLOCAL(skb); + dst->value = atomic_read(&skb->sk->sk_wmem_alloc); +} + +META_COLLECTOR(int_sk_omem_alloc) +{ + SKIP_NONLOCAL(skb); + dst->value = atomic_read(&skb->sk->sk_omem_alloc); +} + +META_COLLECTOR(int_sk_rcv_qlen) +{ + SKIP_NONLOCAL(skb); + dst->value = skb->sk->sk_receive_queue.qlen; +} + +META_COLLECTOR(int_sk_snd_qlen) +{ + SKIP_NONLOCAL(skb); + dst->value = skb->sk->sk_write_queue.qlen; +} + +META_COLLECTOR(int_sk_wmem_queued) +{ + SKIP_NONLOCAL(skb); + dst->value = skb->sk->sk_wmem_queued; +} + +META_COLLECTOR(int_sk_fwd_alloc) +{ + SKIP_NONLOCAL(skb); + dst->value = skb->sk->sk_forward_alloc; +} + +META_COLLECTOR(int_sk_sndbuf) +{ + SKIP_NONLOCAL(skb); + dst->value = skb->sk->sk_sndbuf; +} + +META_COLLECTOR(int_sk_alloc) +{ + SKIP_NONLOCAL(skb); + dst->value = skb->sk->sk_allocation; +} + +META_COLLECTOR(int_sk_route_caps) +{ + SKIP_NONLOCAL(skb); + dst->value = skb->sk->sk_route_caps; +} + +META_COLLECTOR(int_sk_hashent) +{ + SKIP_NONLOCAL(skb); + dst->value = skb->sk->sk_hashent; +} + +META_COLLECTOR(int_sk_lingertime) +{ + SKIP_NONLOCAL(skb); + dst->value = skb->sk->sk_lingertime / HZ; +} + +META_COLLECTOR(int_sk_err_qlen) +{ + SKIP_NONLOCAL(skb); + dst->value = skb->sk->sk_error_queue.qlen; +} + +META_COLLECTOR(int_sk_ack_bl) +{ + SKIP_NONLOCAL(skb); + dst->value = skb->sk->sk_ack_backlog; +} + +META_COLLECTOR(int_sk_max_ack_bl) +{ + SKIP_NONLOCAL(skb); + dst->value = skb->sk->sk_max_ack_backlog; +} + +META_COLLECTOR(int_sk_prio) +{ + SKIP_NONLOCAL(skb); + dst->value = skb->sk->sk_priority; +} + +META_COLLECTOR(int_sk_rcvlowat) +{ + SKIP_NONLOCAL(skb); + dst->value = skb->sk->sk_rcvlowat; +} + +META_COLLECTOR(int_sk_rcvtimeo) +{ + SKIP_NONLOCAL(skb); + dst->value = skb->sk->sk_rcvtimeo / HZ; +} + +META_COLLECTOR(int_sk_sndtimeo) +{ + SKIP_NONLOCAL(skb); + dst->value = skb->sk->sk_sndtimeo / HZ; +} + +META_COLLECTOR(int_sk_sendmsg_off) +{ + SKIP_NONLOCAL(skb); + dst->value = skb->sk->sk_sndmsg_off; +} + +META_COLLECTOR(int_sk_write_pend) +{ + SKIP_NONLOCAL(skb); + dst->value = skb->sk->sk_write_pending; +} + /************************************************************************** * Meta value collectors assignment table **************************************************************************/ @@ -293,41 +502,75 @@ struct meta_ops struct meta_value *, struct meta_obj *, int *); }; +#define META_ID(name) TCF_META_ID_##name +#define META_FUNC(name) { .get = meta_##name } + /* Meta value operations table listing all meta value collectors and * assigns them to a type and meta id. */ static struct meta_ops __meta_ops[TCF_META_TYPE_MAX+1][TCF_META_ID_MAX+1] = { [TCF_META_TYPE_VAR] = { - [TCF_META_ID_DEV] = { .get = meta_var_dev }, - [TCF_META_ID_INDEV] = { .get = meta_var_indev }, - [TCF_META_ID_REALDEV] = { .get = meta_var_realdev } + [META_ID(DEV)] = META_FUNC(var_dev), + [META_ID(INDEV)] = META_FUNC(var_indev), + [META_ID(REALDEV)] = META_FUNC(var_realdev), + [META_ID(SK_BOUND_IF)] = META_FUNC(var_sk_bound_if), }, [TCF_META_TYPE_INT] = { - [TCF_META_ID_RANDOM] = { .get = meta_int_random }, - [TCF_META_ID_LOADAVG_0] = { .get = meta_int_loadavg_0 }, - [TCF_META_ID_LOADAVG_1] = { .get = meta_int_loadavg_1 }, - [TCF_META_ID_LOADAVG_2] = { .get = meta_int_loadavg_2 }, - [TCF_META_ID_DEV] = { .get = meta_int_dev }, - [TCF_META_ID_INDEV] = { .get = meta_int_indev }, - [TCF_META_ID_REALDEV] = { .get = meta_int_realdev }, - [TCF_META_ID_PRIORITY] = { .get = meta_int_priority }, - [TCF_META_ID_PROTOCOL] = { .get = meta_int_protocol }, - [TCF_META_ID_SECURITY] = { .get = meta_int_security }, - [TCF_META_ID_PKTTYPE] = { .get = meta_int_pkttype }, - [TCF_META_ID_PKTLEN] = { .get = meta_int_pktlen }, - [TCF_META_ID_DATALEN] = { .get = meta_int_datalen }, - [TCF_META_ID_MACLEN] = { .get = meta_int_maclen }, + [META_ID(RANDOM)] = META_FUNC(int_random), + [META_ID(LOADAVG_0)] = META_FUNC(int_loadavg_0), + [META_ID(LOADAVG_1)] = META_FUNC(int_loadavg_1), + [META_ID(LOADAVG_2)] = META_FUNC(int_loadavg_2), + [META_ID(DEV)] = META_FUNC(int_dev), + [META_ID(INDEV)] = META_FUNC(int_indev), + [META_ID(REALDEV)] = META_FUNC(int_realdev), + [META_ID(PRIORITY)] = META_FUNC(int_priority), + [META_ID(PROTOCOL)] = META_FUNC(int_protocol), + [META_ID(SECURITY)] = META_FUNC(int_security), + [META_ID(PKTTYPE)] = META_FUNC(int_pkttype), + [META_ID(PKTLEN)] = META_FUNC(int_pktlen), + [META_ID(DATALEN)] = META_FUNC(int_datalen), + [META_ID(MACLEN)] = META_FUNC(int_maclen), #ifdef CONFIG_NETFILTER - [TCF_META_ID_NFMARK] = { .get = meta_int_nfmark }, + [META_ID(NFMARK)] = META_FUNC(int_nfmark), #endif - [TCF_META_ID_TCINDEX] = { .get = meta_int_tcindex }, + [META_ID(TCINDEX)] = META_FUNC(int_tcindex), #ifdef CONFIG_NET_CLS_ACT - [TCF_META_ID_TCVERDICT] = { .get = meta_int_tcverd }, - [TCF_META_ID_TCCLASSID] = { .get = meta_int_tcclassid }, + [META_ID(TCVERDICT)] = META_FUNC(int_tcverd), + [META_ID(TCCLASSID)] = META_FUNC(int_tcclassid), #endif #ifdef CONFIG_NET_CLS_ROUTE - [TCF_META_ID_RTCLASSID] = { .get = meta_int_rtclassid }, + [META_ID(RTCLASSID)] = META_FUNC(int_rtclassid), #endif - [TCF_META_ID_RTIIF] = { .get = meta_int_rtiif } + [META_ID(RTIIF)] = META_FUNC(int_rtiif), + [META_ID(SK_FAMILY)] = META_FUNC(int_sk_family), + [META_ID(SK_STATE)] = META_FUNC(int_sk_state), + [META_ID(SK_REUSE)] = META_FUNC(int_sk_reuse), + [META_ID(SK_BOUND_IF)] = META_FUNC(int_sk_bound_if), + [META_ID(SK_REFCNT)] = META_FUNC(int_sk_refcnt), + [META_ID(SK_RCVBUF)] = META_FUNC(int_sk_rcvbuf), + [META_ID(SK_SNDBUF)] = META_FUNC(int_sk_sndbuf), + [META_ID(SK_SHUTDOWN)] = META_FUNC(int_sk_shutdown), + [META_ID(SK_PROTO)] = META_FUNC(int_sk_proto), + [META_ID(SK_TYPE)] = META_FUNC(int_sk_type), + [META_ID(SK_RMEM_ALLOC)] = META_FUNC(int_sk_rmem_alloc), + [META_ID(SK_WMEM_ALLOC)] = META_FUNC(int_sk_wmem_alloc), + [META_ID(SK_OMEM_ALLOC)] = META_FUNC(int_sk_omem_alloc), + [META_ID(SK_WMEM_QUEUED)] = META_FUNC(int_sk_wmem_queued), + [META_ID(SK_RCV_QLEN)] = META_FUNC(int_sk_rcv_qlen), + [META_ID(SK_SND_QLEN)] = META_FUNC(int_sk_snd_qlen), + [META_ID(SK_ERR_QLEN)] = META_FUNC(int_sk_err_qlen), + [META_ID(SK_FORWARD_ALLOCS)] = META_FUNC(int_sk_fwd_alloc), + [META_ID(SK_ALLOCS)] = META_FUNC(int_sk_alloc), + [META_ID(SK_ROUTE_CAPS)] = META_FUNC(int_sk_route_caps), + [META_ID(SK_HASHENT)] = META_FUNC(int_sk_hashent), + [META_ID(SK_LINGERTIME)] = META_FUNC(int_sk_lingertime), + [META_ID(SK_ACK_BACKLOG)] = META_FUNC(int_sk_ack_bl), + [META_ID(SK_MAX_ACK_BACKLOG)] = META_FUNC(int_sk_max_ack_bl), + [META_ID(SK_PRIO)] = META_FUNC(int_sk_prio), + [META_ID(SK_RCVLOWAT)] = META_FUNC(int_sk_rcvlowat), + [META_ID(SK_RCVTIMEO)] = META_FUNC(int_sk_rcvtimeo), + [META_ID(SK_SNDTIMEO)] = META_FUNC(int_sk_sndtimeo), + [META_ID(SK_SENDMSG_OFF)] = META_FUNC(int_sk_sendmsg_off), + [META_ID(SK_WRITE_PENDING)] = META_FUNC(int_sk_write_pend), } }; -- cgit v1.2.3 From a58e76f25432dc5e3e84d04c27bec03347ca365b Mon Sep 17 00:00:00 2001 From: Geert Uytterhoeven Date: Sun, 12 Jun 2005 10:56:26 +0200 Subject: [PATCH] Remove obsolete HAVE_ARCH_GET_SIGNAL_TO_DELIVER? Now m68k no longer sets HAVE_ARCH_GET_SIGNAL_TO_DELIVER, can it be removed completely? Or may ARM26 still need it? Note that its usage was removed from kernel/signal.c about 2 months ago. Signed-off-by: Geert Uytterhoeven Signed-off-by: Linus Torvalds --- include/asm-arm26/signal.h | 3 --- include/linux/signal.h | 2 -- 2 files changed, 5 deletions(-) (limited to 'include/linux') diff --git a/include/asm-arm26/signal.h b/include/asm-arm26/signal.h index dedb29280303..37ad25355591 100644 --- a/include/asm-arm26/signal.h +++ b/include/asm-arm26/signal.h @@ -166,9 +166,6 @@ typedef struct sigaltstack { #include #define sigmask(sig) (1UL << ((sig) - 1)) -//FIXME!!! -//#define HAVE_ARCH_GET_SIGNAL_TO_DELIVER - #endif diff --git a/include/linux/signal.h b/include/linux/signal.h index 0a98f5ec5cae..7be18b5e2fb4 100644 --- a/include/linux/signal.h +++ b/include/linux/signal.h @@ -231,10 +231,8 @@ extern int __group_send_sig_info(int, struct siginfo *, struct task_struct *); extern long do_sigpending(void __user *, unsigned long); extern int sigprocmask(int, sigset_t *, sigset_t *); -#ifndef HAVE_ARCH_GET_SIGNAL_TO_DELIVER struct pt_regs; extern int get_signal_to_deliver(siginfo_t *info, struct k_sigaction *return_ka, struct pt_regs *regs, void *cookie); -#endif #endif /* __KERNEL__ */ -- cgit v1.2.3 From 03722adce90a248d0bea77d390decbd05991e2d2 Mon Sep 17 00:00:00 2001 From: Tom Rini Date: Mon, 13 Jun 2005 13:57:10 -0700 Subject: [NET]: linux/if_tr.h needs asm/byteorder.h uses __be16, but does not directly include . Add this in, so that dhcp/net-tools token ring code can compile again. Signed-off-by: Tom Rini Signed-off-by: David S. Miller --- include/linux/if_tr.h | 2 ++ 1 file changed, 2 insertions(+) (limited to 'include/linux') diff --git a/include/linux/if_tr.h b/include/linux/if_tr.h index 6688b414c529..3fba9e2f5427 100644 --- a/include/linux/if_tr.h +++ b/include/linux/if_tr.h @@ -19,6 +19,8 @@ #ifndef _LINUX_IF_TR_H #define _LINUX_IF_TR_H +#include /* For __be16 */ + /* IEEE 802.5 Token-Ring magic constants. The frame sizes omit the preamble and FCS/CRC (frame check sequence). */ #define TR_ALEN 6 /* Octets in one token-ring addr */ -- cgit v1.2.3 From 1c2fb7f93cb20621772bf304f3dba0849942e5db Mon Sep 17 00:00:00 2001 From: "J. Simonetti" Date: Mon, 13 Jun 2005 15:19:03 -0700 Subject: [IPV4]: Sysctl configurable icmp error source address. This patch alows you to change the source address of icmp error messages. It applies cleanly to 2.6.11.11 and retains the default behaviour. In the old (default) behaviour icmp error messages are sent with the ip of the exiting interface. The new behaviour (when the sysctl variable is toggled on), it will send the message with the ip of the interface that received the packet that caused the icmp error. This is the behaviour network administrators will expect from a router. It makes debugging complicated network layouts much easier. Also, all 'vendor routers' I know of have the later behaviour. Signed-off-by: David S. Miller --- include/linux/sysctl.h | 1 + net/ipv4/icmp.c | 9 +++++++-- net/ipv4/sysctl_net_ipv4.c | 9 +++++++++ 3 files changed, 17 insertions(+), 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/sysctl.h b/include/linux/sysctl.h index 23032d9d6071..a17745c80a91 100644 --- a/include/linux/sysctl.h +++ b/include/linux/sysctl.h @@ -346,6 +346,7 @@ enum NET_TCP_MODERATE_RCVBUF=106, NET_TCP_TSO_WIN_DIVISOR=107, NET_TCP_BIC_BETA=108, + NET_IPV4_ICMP_ERRORS_USE_INBOUND_IFADDR=109, }; enum { diff --git a/net/ipv4/icmp.c b/net/ipv4/icmp.c index 85bf0d3e294b..cb759484979d 100644 --- a/net/ipv4/icmp.c +++ b/net/ipv4/icmp.c @@ -207,6 +207,7 @@ int sysctl_icmp_ignore_bogus_error_responses; int sysctl_icmp_ratelimit = 1 * HZ; int sysctl_icmp_ratemask = 0x1818; +int sysctl_icmp_errors_use_inbound_ifaddr; /* * ICMP control array. This specifies what to do with each ICMP. @@ -511,8 +512,12 @@ void icmp_send(struct sk_buff *skb_in, int type, int code, u32 info) */ saddr = iph->daddr; - if (!(rt->rt_flags & RTCF_LOCAL)) - saddr = 0; + if (!(rt->rt_flags & RTCF_LOCAL)) { + if (sysctl_icmp_errors_use_inbound_ifaddr) + saddr = inet_select_addr(skb_in->dev, 0, RT_SCOPE_LINK); + else + saddr = 0; + } tos = icmp_pointers[type].error ? ((iph->tos & IPTOS_TOS_MASK) | IPTOS_PREC_INTERNETCONTROL) : diff --git a/net/ipv4/sysctl_net_ipv4.c b/net/ipv4/sysctl_net_ipv4.c index 3aafb298c1c1..23068bddbf0b 100644 --- a/net/ipv4/sysctl_net_ipv4.c +++ b/net/ipv4/sysctl_net_ipv4.c @@ -23,6 +23,7 @@ extern int sysctl_ip_nonlocal_bind; extern int sysctl_icmp_echo_ignore_all; extern int sysctl_icmp_echo_ignore_broadcasts; extern int sysctl_icmp_ignore_bogus_error_responses; +extern int sysctl_icmp_errors_use_inbound_ifaddr; /* From ip_fragment.c */ extern int sysctl_ipfrag_low_thresh; @@ -395,6 +396,14 @@ ctl_table ipv4_table[] = { .mode = 0644, .proc_handler = &proc_dointvec }, + { + .ctl_name = NET_IPV4_ICMP_ERRORS_USE_INBOUND_IFADDR, + .procname = "icmp_errors_use_inbound_ifaddr", + .data = &sysctl_icmp_errors_use_inbound_ifaddr, + .maxlen = sizeof(int), + .mode = 0644, + .proc_handler = &proc_dointvec + }, { .ctl_name = NET_IPV4_ROUTE, .procname = "route", -- cgit v1.2.3 From b8112df71cae7d6a86158caeb19d215f56c4f9ab Mon Sep 17 00:00:00 2001 From: Lee Revell Date: Wed, 15 Jun 2005 14:19:03 -0400 Subject: [SCSI] Add DMA mask constants other than 32 and 64 bit Signed-Off-By: Lee Revell Signed-off-by: James Bottomley --- include/linux/dma-mapping.h | 5 +++++ 1 file changed, 5 insertions(+) (limited to 'include/linux') diff --git a/include/linux/dma-mapping.h b/include/linux/dma-mapping.h index 806c305332c1..2d80cc761a15 100644 --- a/include/linux/dma-mapping.h +++ b/include/linux/dma-mapping.h @@ -14,7 +14,12 @@ enum dma_data_direction { }; #define DMA_64BIT_MASK 0xffffffffffffffffULL +#define DMA_40BIT_MASK 0x000000ffffffffffULL +#define DMA_39BIT_MASK 0x0000007fffffffffULL #define DMA_32BIT_MASK 0x00000000ffffffffULL +#define DMA_31BIT_MASK 0x000000007fffffffULL +#define DMA_30BIT_MASK 0x000000003fffffffULL +#define DMA_29BIT_MASK 0x000000001fffffffULL #include -- cgit v1.2.3 From 26b15dad9f1c19d6d4f7b999b07eaa6d98e4b375 Mon Sep 17 00:00:00 2001 From: Jamal Hadi Salim Date: Sat, 18 Jun 2005 22:42:13 -0700 Subject: [IPSEC] Add complete xfrm event notification Heres the final patch. What this patch provides - netlink xfrm events - ability to have events generated by netlink propagated to pfkey and vice versa. - fixes the acquire lets-be-happy-with-one-success issue Signed-off-by: Jamal Hadi Salim Signed-off-by: Herbert Xu --- include/linux/xfrm.h | 2 + include/net/xfrm.h | 29 +++- net/key/af_key.c | 357 +++++++++++++++++++++++++++++++++++++------------- net/xfrm/xfrm_state.c | 74 ++++++++--- net/xfrm/xfrm_user.c | 272 +++++++++++++++++++++++++++++++++++++- 5 files changed, 616 insertions(+), 118 deletions(-) (limited to 'include/linux') diff --git a/include/linux/xfrm.h b/include/linux/xfrm.h index fd2ef742a9fd..03bc600516ea 100644 --- a/include/linux/xfrm.h +++ b/include/linux/xfrm.h @@ -257,5 +257,7 @@ struct xfrm_usersa_flush { #define XFRMGRP_ACQUIRE 1 #define XFRMGRP_EXPIRE 2 +#define XFRMGRP_SA 4 +#define XFRMGRP_POLICY 8 #endif /* _LINUX_XFRM_H */ diff --git a/include/net/xfrm.h b/include/net/xfrm.h index d675836ba6c3..a159655ebede 100644 --- a/include/net/xfrm.h +++ b/include/net/xfrm.h @@ -158,6 +158,27 @@ enum { XFRM_STATE_DEAD }; +/* events that could be sent by kernel */ +enum { + XFRM_SAP_INVALID, + XFRM_SAP_EXPIRED, + XFRM_SAP_ADDED, + XFRM_SAP_UPDATED, + XFRM_SAP_DELETED, + XFRM_SAP_FLUSHED, + __XFRM_SAP_MAX +}; +#define XFRM_SAP_MAX (__XFRM_SAP_MAX - 1) + +/* callback structure passed from either netlink or pfkey */ +struct km_event +{ + u32 data; + u32 seq; + u32 pid; + u32 event; +}; + struct xfrm_type; struct xfrm_dst; struct xfrm_policy_afinfo { @@ -179,6 +200,8 @@ struct xfrm_policy_afinfo { extern int xfrm_policy_register_afinfo(struct xfrm_policy_afinfo *afinfo); extern int xfrm_policy_unregister_afinfo(struct xfrm_policy_afinfo *afinfo); +extern void km_policy_notify(struct xfrm_policy *xp, int dir, struct km_event *c); +extern void km_state_notify(struct xfrm_state *x, struct km_event *c); #define XFRM_ACQ_EXPIRES 30 @@ -290,11 +313,11 @@ struct xfrm_mgr { struct list_head list; char *id; - int (*notify)(struct xfrm_state *x, int event); + int (*notify)(struct xfrm_state *x, struct km_event *c); int (*acquire)(struct xfrm_state *x, struct xfrm_tmpl *, struct xfrm_policy *xp, int dir); struct xfrm_policy *(*compile_policy)(u16 family, int opt, u8 *data, int len, int *dir); int (*new_mapping)(struct xfrm_state *x, xfrm_address_t *ipaddr, u16 sport); - int (*notify_policy)(struct xfrm_policy *x, int dir, int event); + int (*notify_policy)(struct xfrm_policy *x, int dir, struct km_event *c); }; extern int xfrm_register_km(struct xfrm_mgr *km); @@ -817,7 +840,7 @@ extern int xfrm_state_add(struct xfrm_state *x); extern int xfrm_state_update(struct xfrm_state *x); extern struct xfrm_state *xfrm_state_lookup(xfrm_address_t *daddr, u32 spi, u8 proto, unsigned short family); extern struct xfrm_state *xfrm_find_acq_byseq(u32 seq); -extern void xfrm_state_delete(struct xfrm_state *x); +extern int xfrm_state_delete(struct xfrm_state *x); extern void xfrm_state_flush(u8 proto); extern int xfrm_replay_check(struct xfrm_state *x, u32 seq); extern void xfrm_replay_advance(struct xfrm_state *x, u32 seq); diff --git a/net/key/af_key.c b/net/key/af_key.c index ce980aa94ed8..d086c117f5f0 100644 --- a/net/key/af_key.c +++ b/net/key/af_key.c @@ -1240,13 +1240,85 @@ static int pfkey_acquire(struct sock *sk, struct sk_buff *skb, struct sadb_msg * return 0; } +static inline int event2poltype(int event) +{ + switch (event) { + case XFRM_SAP_DELETED: + return SADB_X_SPDDELETE; + case XFRM_SAP_ADDED: + return SADB_X_SPDADD; + case XFRM_SAP_UPDATED: + return SADB_X_SPDUPDATE; + case XFRM_SAP_EXPIRED: + // return SADB_X_SPDEXPIRE; + default: + printk("pfkey: Unknown policy event %d\n", event); + break; + } + + return 0; +} + +static inline int event2keytype(int event) +{ + switch (event) { + case XFRM_SAP_DELETED: + return SADB_DELETE; + case XFRM_SAP_ADDED: + return SADB_ADD; + case XFRM_SAP_UPDATED: + return SADB_UPDATE; + case XFRM_SAP_EXPIRED: + return SADB_EXPIRE; + default: + printk("pfkey: Unknown SA event %d\n", event); + break; + } + + return 0; +} + +/* ADD/UPD/DEL */ +static int key_notify_sa(struct xfrm_state *x, struct km_event *c) +{ + struct sk_buff *skb; + struct sadb_msg *hdr; + int hsc = 3; + + if (c->event == XFRM_SAP_DELETED) + hsc = 0; + + if (c->event == XFRM_SAP_EXPIRED) { + if (c->data) + hsc = 2; + else + hsc = 1; + } + + skb = pfkey_xfrm_state2msg(x, 0, hsc); + + if (IS_ERR(skb)) + return PTR_ERR(skb); + + hdr = (struct sadb_msg *) skb->data; + hdr->sadb_msg_version = PF_KEY_V2; + hdr->sadb_msg_type = event2keytype(c->event); + hdr->sadb_msg_satype = pfkey_proto2satype(x->id.proto); + hdr->sadb_msg_errno = 0; + hdr->sadb_msg_reserved = 0; + hdr->sadb_msg_seq = c->seq; + hdr->sadb_msg_pid = c->pid; + + pfkey_broadcast(skb, GFP_ATOMIC, BROADCAST_ALL, NULL); + + return 0; +} static int pfkey_add(struct sock *sk, struct sk_buff *skb, struct sadb_msg *hdr, void **ext_hdrs) { - struct sk_buff *out_skb; - struct sadb_msg *out_hdr; struct xfrm_state *x; int err; + struct km_event c; xfrm_probe_algs(); @@ -1254,6 +1326,7 @@ static int pfkey_add(struct sock *sk, struct sk_buff *skb, struct sadb_msg *hdr, if (IS_ERR(x)) return PTR_ERR(x); + xfrm_state_hold(x); if (hdr->sadb_msg_type == SADB_ADD) err = xfrm_state_add(x); else @@ -1265,27 +1338,23 @@ static int pfkey_add(struct sock *sk, struct sk_buff *skb, struct sadb_msg *hdr, return err; } - out_skb = pfkey_xfrm_state2msg(x, 0, 3); - if (IS_ERR(out_skb)) - return PTR_ERR(out_skb); /* XXX Should we return 0 here ? */ - - out_hdr = (struct sadb_msg *) out_skb->data; - out_hdr->sadb_msg_version = hdr->sadb_msg_version; - out_hdr->sadb_msg_type = hdr->sadb_msg_type; - out_hdr->sadb_msg_satype = pfkey_proto2satype(x->id.proto); - out_hdr->sadb_msg_errno = 0; - out_hdr->sadb_msg_reserved = 0; - out_hdr->sadb_msg_seq = hdr->sadb_msg_seq; - out_hdr->sadb_msg_pid = hdr->sadb_msg_pid; - - pfkey_broadcast(out_skb, GFP_ATOMIC, BROADCAST_ALL, sk); + if (hdr->sadb_msg_type == SADB_ADD) + c.event = XFRM_SAP_ADDED; + else + c.event = XFRM_SAP_UPDATED; + c.seq = hdr->sadb_msg_seq; + c.pid = hdr->sadb_msg_pid; + km_state_notify(x, &c); + xfrm_state_put(x); - return 0; + return err; } static int pfkey_delete(struct sock *sk, struct sk_buff *skb, struct sadb_msg *hdr, void **ext_hdrs) { struct xfrm_state *x; + struct km_event c; + int err; if (!ext_hdrs[SADB_EXT_SA-1] || !present_and_same_family(ext_hdrs[SADB_EXT_ADDRESS_SRC-1], @@ -1301,13 +1370,19 @@ static int pfkey_delete(struct sock *sk, struct sk_buff *skb, struct sadb_msg *h return -EPERM; } - xfrm_state_delete(x); - xfrm_state_put(x); + err = xfrm_state_delete(x); + if (err < 0) { + xfrm_state_put(x); + return err; + } - pfkey_broadcast(skb_clone(skb, GFP_KERNEL), GFP_KERNEL, - BROADCAST_ALL, sk); + c.seq = hdr->sadb_msg_seq; + c.pid = hdr->sadb_msg_pid; + c.event = XFRM_SAP_DELETED; + km_state_notify(x, &c); + xfrm_state_put(x); - return 0; + return err; } static int pfkey_get(struct sock *sk, struct sk_buff *skb, struct sadb_msg *hdr, void **ext_hdrs) @@ -1445,28 +1520,42 @@ static int pfkey_register(struct sock *sk, struct sk_buff *skb, struct sadb_msg return 0; } +static int key_notify_sa_flush(struct km_event *c) +{ + struct sk_buff *skb; + struct sadb_msg *hdr; + + skb = alloc_skb(sizeof(struct sadb_msg) + 16, GFP_ATOMIC); + if (!skb) + return -ENOBUFS; + hdr = (struct sadb_msg *) skb_put(skb, sizeof(struct sadb_msg)); + hdr->sadb_msg_satype = pfkey_proto2satype(c->data); + hdr->sadb_msg_seq = c->seq; + hdr->sadb_msg_pid = c->pid; + hdr->sadb_msg_version = PF_KEY_V2; + hdr->sadb_msg_errno = (uint8_t) 0; + hdr->sadb_msg_len = (sizeof(struct sadb_msg) / sizeof(uint64_t)); + + pfkey_broadcast(skb, GFP_ATOMIC, BROADCAST_ALL, NULL); + + return 0; +} + static int pfkey_flush(struct sock *sk, struct sk_buff *skb, struct sadb_msg *hdr, void **ext_hdrs) { unsigned proto; - struct sk_buff *skb_out; - struct sadb_msg *hdr_out; + struct km_event c; proto = pfkey_satype2proto(hdr->sadb_msg_satype); if (proto == 0) return -EINVAL; - skb_out = alloc_skb(sizeof(struct sadb_msg) + 16, GFP_KERNEL); - if (!skb_out) - return -ENOBUFS; - xfrm_state_flush(proto); - - hdr_out = (struct sadb_msg *) skb_put(skb_out, sizeof(struct sadb_msg)); - pfkey_hdr_dup(hdr_out, hdr); - hdr_out->sadb_msg_errno = (uint8_t) 0; - hdr_out->sadb_msg_len = (sizeof(struct sadb_msg) / sizeof(uint64_t)); - - pfkey_broadcast(skb_out, GFP_KERNEL, BROADCAST_ALL, NULL); + c.data = proto; + c.seq = hdr->sadb_msg_seq; + c.pid = hdr->sadb_msg_pid; + c.event = XFRM_SAP_FLUSHED; + km_state_notify(NULL, &c); return 0; } @@ -1859,6 +1948,35 @@ static void pfkey_xfrm_policy2msg(struct sk_buff *skb, struct xfrm_policy *xp, i hdr->sadb_msg_reserved = atomic_read(&xp->refcnt); } +static int key_notify_policy(struct xfrm_policy *xp, int dir, struct km_event *c) +{ + struct sk_buff *out_skb; + struct sadb_msg *out_hdr; + int err; + + out_skb = pfkey_xfrm_policy2msg_prep(xp); + if (IS_ERR(out_skb)) { + err = PTR_ERR(out_skb); + goto out; + } + pfkey_xfrm_policy2msg(out_skb, xp, dir); + + out_hdr = (struct sadb_msg *) out_skb->data; + out_hdr->sadb_msg_version = PF_KEY_V2; + + if (c->data && c->event == XFRM_SAP_DELETED) + out_hdr->sadb_msg_type = SADB_X_SPDDELETE2; + else + out_hdr->sadb_msg_type = event2poltype(c->event); + out_hdr->sadb_msg_errno = 0; + out_hdr->sadb_msg_seq = c->seq; + out_hdr->sadb_msg_pid = c->pid; + pfkey_broadcast(out_skb, GFP_ATOMIC, BROADCAST_ALL, NULL); +out: + return 0; + +} + static int pfkey_spdadd(struct sock *sk, struct sk_buff *skb, struct sadb_msg *hdr, void **ext_hdrs) { int err; @@ -1866,8 +1984,7 @@ static int pfkey_spdadd(struct sock *sk, struct sk_buff *skb, struct sadb_msg *h struct sadb_address *sa; struct sadb_x_policy *pol; struct xfrm_policy *xp; - struct sk_buff *out_skb; - struct sadb_msg *out_hdr; + struct km_event c; if (!present_and_same_family(ext_hdrs[SADB_EXT_ADDRESS_SRC-1], ext_hdrs[SADB_EXT_ADDRESS_DST-1]) || @@ -1935,31 +2052,23 @@ static int pfkey_spdadd(struct sock *sk, struct sk_buff *skb, struct sadb_msg *h (err = parse_ipsecrequests(xp, pol)) < 0) goto out; - out_skb = pfkey_xfrm_policy2msg_prep(xp); - if (IS_ERR(out_skb)) { - err = PTR_ERR(out_skb); - goto out; - } - err = xfrm_policy_insert(pol->sadb_x_policy_dir-1, xp, hdr->sadb_msg_type != SADB_X_SPDUPDATE); if (err) { - kfree_skb(out_skb); - goto out; + kfree(xp); + return err; } - pfkey_xfrm_policy2msg(out_skb, xp, pol->sadb_x_policy_dir-1); + if (hdr->sadb_msg_type == SADB_X_SPDUPDATE) + c.event = XFRM_SAP_UPDATED; + else + c.event = XFRM_SAP_ADDED; - xfrm_pol_put(xp); + c.seq = hdr->sadb_msg_seq; + c.pid = hdr->sadb_msg_pid; - out_hdr = (struct sadb_msg *) out_skb->data; - out_hdr->sadb_msg_version = hdr->sadb_msg_version; - out_hdr->sadb_msg_type = hdr->sadb_msg_type; - out_hdr->sadb_msg_satype = 0; - out_hdr->sadb_msg_errno = 0; - out_hdr->sadb_msg_seq = hdr->sadb_msg_seq; - out_hdr->sadb_msg_pid = hdr->sadb_msg_pid; - pfkey_broadcast(out_skb, GFP_ATOMIC, BROADCAST_ALL, sk); + km_policy_notify(xp, pol->sadb_x_policy_dir-1, &c); + xfrm_pol_put(xp); return 0; out: @@ -1973,9 +2082,8 @@ static int pfkey_spddelete(struct sock *sk, struct sk_buff *skb, struct sadb_msg struct sadb_address *sa; struct sadb_x_policy *pol; struct xfrm_policy *xp; - struct sk_buff *out_skb; - struct sadb_msg *out_hdr; struct xfrm_selector sel; + struct km_event c; if (!present_and_same_family(ext_hdrs[SADB_EXT_ADDRESS_SRC-1], ext_hdrs[SADB_EXT_ADDRESS_DST-1]) || @@ -2010,25 +2118,40 @@ static int pfkey_spddelete(struct sock *sk, struct sk_buff *skb, struct sadb_msg err = 0; + c.seq = hdr->sadb_msg_seq; + c.pid = hdr->sadb_msg_pid; + c.event = XFRM_SAP_DELETED; + km_policy_notify(xp, pol->sadb_x_policy_dir-1, &c); + + xfrm_pol_put(xp); + return err; +} + +static int key_pol_get_resp(struct sock *sk, struct xfrm_policy *xp, struct sadb_msg *hdr, int dir) +{ + int err; + struct sk_buff *out_skb; + struct sadb_msg *out_hdr; + err = 0; + out_skb = pfkey_xfrm_policy2msg_prep(xp); if (IS_ERR(out_skb)) { err = PTR_ERR(out_skb); goto out; } - pfkey_xfrm_policy2msg(out_skb, xp, pol->sadb_x_policy_dir-1); + pfkey_xfrm_policy2msg(out_skb, xp, dir); out_hdr = (struct sadb_msg *) out_skb->data; out_hdr->sadb_msg_version = hdr->sadb_msg_version; - out_hdr->sadb_msg_type = SADB_X_SPDDELETE; + out_hdr->sadb_msg_type = hdr->sadb_msg_type; out_hdr->sadb_msg_satype = 0; out_hdr->sadb_msg_errno = 0; out_hdr->sadb_msg_seq = hdr->sadb_msg_seq; out_hdr->sadb_msg_pid = hdr->sadb_msg_pid; - pfkey_broadcast(out_skb, GFP_ATOMIC, BROADCAST_ALL, sk); + pfkey_broadcast(out_skb, GFP_ATOMIC, BROADCAST_ONE, sk); err = 0; out: - xfrm_pol_put(xp); return err; } @@ -2037,8 +2160,7 @@ static int pfkey_spdget(struct sock *sk, struct sk_buff *skb, struct sadb_msg *h int err; struct sadb_x_policy *pol; struct xfrm_policy *xp; - struct sk_buff *out_skb; - struct sadb_msg *out_hdr; + struct km_event c; if ((pol = ext_hdrs[SADB_X_EXT_POLICY-1]) == NULL) return -EINVAL; @@ -2050,24 +2172,16 @@ static int pfkey_spdget(struct sock *sk, struct sk_buff *skb, struct sadb_msg *h err = 0; - out_skb = pfkey_xfrm_policy2msg_prep(xp); - if (IS_ERR(out_skb)) { - err = PTR_ERR(out_skb); - goto out; + c.seq = hdr->sadb_msg_seq; + c.pid = hdr->sadb_msg_pid; + if (hdr->sadb_msg_type == SADB_X_SPDDELETE2) { + c.data = 1; // to signal pfkey of SADB_X_SPDDELETE2 + c.event = XFRM_SAP_DELETED; + km_policy_notify(xp, pol->sadb_x_policy_dir-1, &c); + } else { + err = key_pol_get_resp(sk, xp, hdr, pol->sadb_x_policy_dir-1); } - pfkey_xfrm_policy2msg(out_skb, xp, pol->sadb_x_policy_dir-1); - out_hdr = (struct sadb_msg *) out_skb->data; - out_hdr->sadb_msg_version = hdr->sadb_msg_version; - out_hdr->sadb_msg_type = hdr->sadb_msg_type; - out_hdr->sadb_msg_satype = 0; - out_hdr->sadb_msg_errno = 0; - out_hdr->sadb_msg_seq = hdr->sadb_msg_seq; - out_hdr->sadb_msg_pid = hdr->sadb_msg_pid; - pfkey_broadcast(out_skb, GFP_ATOMIC, BROADCAST_ALL, sk); - err = 0; - -out: xfrm_pol_put(xp); return err; } @@ -2102,22 +2216,34 @@ static int pfkey_spddump(struct sock *sk, struct sk_buff *skb, struct sadb_msg * return xfrm_policy_walk(dump_sp, &data); } -static int pfkey_spdflush(struct sock *sk, struct sk_buff *skb, struct sadb_msg *hdr, void **ext_hdrs) +static int key_notify_policy_flush(struct km_event *c) { struct sk_buff *skb_out; - struct sadb_msg *hdr_out; + struct sadb_msg *hdr; - skb_out = alloc_skb(sizeof(struct sadb_msg) + 16, GFP_KERNEL); + skb_out = alloc_skb(sizeof(struct sadb_msg) + 16, GFP_ATOMIC); if (!skb_out) return -ENOBUFS; + hdr = (struct sadb_msg *) skb_put(skb_out, sizeof(struct sadb_msg)); + hdr->sadb_msg_seq = c->seq; + hdr->sadb_msg_pid = c->pid; + hdr->sadb_msg_version = PF_KEY_V2; + hdr->sadb_msg_errno = (uint8_t) 0; + hdr->sadb_msg_len = (sizeof(struct sadb_msg) / sizeof(uint64_t)); + pfkey_broadcast(skb_out, GFP_ATOMIC, BROADCAST_ALL, NULL); + return 0; - xfrm_policy_flush(); +} + +static int pfkey_spdflush(struct sock *sk, struct sk_buff *skb, struct sadb_msg *hdr, void **ext_hdrs) +{ + struct km_event c; - hdr_out = (struct sadb_msg *) skb_put(skb_out, sizeof(struct sadb_msg)); - pfkey_hdr_dup(hdr_out, hdr); - hdr_out->sadb_msg_errno = (uint8_t) 0; - hdr_out->sadb_msg_len = (sizeof(struct sadb_msg) / sizeof(uint64_t)); - pfkey_broadcast(skb_out, GFP_KERNEL, BROADCAST_ALL, NULL); + xfrm_policy_flush(); + c.event = XFRM_SAP_FLUSHED; + c.pid = hdr->sadb_msg_pid; + c.seq = hdr->sadb_msg_seq; + km_policy_notify(NULL, 0, &c); return 0; } @@ -2317,11 +2443,23 @@ static void dump_esp_combs(struct sk_buff *skb, struct xfrm_tmpl *t) } } -static int pfkey_send_notify(struct xfrm_state *x, int hard) +static int key_notify_policy_expire(struct xfrm_policy *xp, struct km_event *c) +{ + return 0; +} + +static int key_notify_sa_expire(struct xfrm_state *x, struct km_event *c) { struct sk_buff *out_skb; struct sadb_msg *out_hdr; - int hsc = (hard ? 2 : 1); + int hard; + int hsc; + + hard = c->data; + if (hard) + hsc = 2; + else + hsc = 1; out_skb = pfkey_xfrm_state2msg(x, 0, hsc); if (IS_ERR(out_skb)) @@ -2340,6 +2478,44 @@ static int pfkey_send_notify(struct xfrm_state *x, int hard) return 0; } +static int pfkey_send_notify(struct xfrm_state *x, struct km_event *c) +{ + switch (c->event) { + case XFRM_SAP_EXPIRED: + return key_notify_sa_expire(x, c); + case XFRM_SAP_DELETED: + case XFRM_SAP_ADDED: + case XFRM_SAP_UPDATED: + return key_notify_sa(x, c); + case XFRM_SAP_FLUSHED: + return key_notify_sa_flush(c); + default: + printk("pfkey: Unknown SA event %d\n", c->event); + break; + } + + return 0; +} + +static int pfkey_send_policy_notify(struct xfrm_policy *xp, int dir, struct km_event *c) +{ + switch (c->event) { + case XFRM_SAP_EXPIRED: + return key_notify_policy_expire(xp, c); + case XFRM_SAP_DELETED: + case XFRM_SAP_ADDED: + case XFRM_SAP_UPDATED: + return key_notify_policy(xp, dir, c); + case XFRM_SAP_FLUSHED: + return key_notify_policy_flush(c); + default: + printk("pfkey: Unknown policy event %d\n", c->event); + break; + } + + return 0; +} + static u32 get_acqseq(void) { u32 res; @@ -2856,6 +3032,7 @@ static struct xfrm_mgr pfkeyv2_mgr = .acquire = pfkey_send_acquire, .compile_policy = pfkey_compile_policy, .new_mapping = pfkey_send_new_mapping, + .notify_policy = pfkey_send_policy_notify, }; static void __exit ipsec_pfkey_exit(void) diff --git a/net/xfrm/xfrm_state.c b/net/xfrm/xfrm_state.c index d11747c2a763..918a94c552a5 100644 --- a/net/xfrm/xfrm_state.c +++ b/net/xfrm/xfrm_state.c @@ -50,7 +50,7 @@ static DEFINE_SPINLOCK(xfrm_state_gc_lock); static int xfrm_state_gc_flush_bundles; -static void __xfrm_state_delete(struct xfrm_state *x); +static int __xfrm_state_delete(struct xfrm_state *x); static struct xfrm_state_afinfo *xfrm_state_get_afinfo(unsigned short family); static void xfrm_state_put_afinfo(struct xfrm_state_afinfo *afinfo); @@ -215,8 +215,10 @@ void __xfrm_state_destroy(struct xfrm_state *x) } EXPORT_SYMBOL(__xfrm_state_destroy); -static void __xfrm_state_delete(struct xfrm_state *x) +static int __xfrm_state_delete(struct xfrm_state *x) { + int err = -ESRCH; + if (x->km.state != XFRM_STATE_DEAD) { x->km.state = XFRM_STATE_DEAD; spin_lock(&xfrm_state_lock); @@ -245,14 +247,21 @@ static void __xfrm_state_delete(struct xfrm_state *x) * is what we are dropping here. */ atomic_dec(&x->refcnt); + err = 0; } + + return err; } -void xfrm_state_delete(struct xfrm_state *x) +int xfrm_state_delete(struct xfrm_state *x) { + int err; + spin_lock_bh(&x->lock); - __xfrm_state_delete(x); + err = __xfrm_state_delete(x); spin_unlock_bh(&x->lock); + + return err; } EXPORT_SYMBOL(xfrm_state_delete); @@ -796,34 +805,60 @@ EXPORT_SYMBOL(xfrm_replay_advance); static struct list_head xfrm_km_list = LIST_HEAD_INIT(xfrm_km_list); static DEFINE_RWLOCK(xfrm_km_lock); -static void km_state_expired(struct xfrm_state *x, int hard) +void km_policy_notify(struct xfrm_policy *xp, int dir, struct km_event *c) { struct xfrm_mgr *km; - if (hard) - x->km.state = XFRM_STATE_EXPIRED; - else - x->km.dying = 1; + read_lock(&xfrm_km_lock); + list_for_each_entry(km, &xfrm_km_list, list) + if (km->notify_policy) + km->notify_policy(xp, dir, c); + read_unlock(&xfrm_km_lock); +} +void km_state_notify(struct xfrm_state *x, struct km_event *c) +{ + struct xfrm_mgr *km; read_lock(&xfrm_km_lock); list_for_each_entry(km, &xfrm_km_list, list) - km->notify(x, hard); + if (km->notify) + km->notify(x, c); read_unlock(&xfrm_km_lock); +} + +EXPORT_SYMBOL(km_policy_notify); +EXPORT_SYMBOL(km_state_notify); + +static void km_state_expired(struct xfrm_state *x, int hard) +{ + struct km_event c; + + if (hard) + x->km.state = XFRM_STATE_EXPIRED; + else + x->km.dying = 1; + c.data = hard; + c.event = XFRM_SAP_EXPIRED; + km_state_notify(x, &c); if (hard) wake_up(&km_waitq); } +/* + * We send to all registered managers regardless of failure + * We are happy with one success +*/ static int km_query(struct xfrm_state *x, struct xfrm_tmpl *t, struct xfrm_policy *pol) { - int err = -EINVAL; + int err = -EINVAL, acqret; struct xfrm_mgr *km; read_lock(&xfrm_km_lock); list_for_each_entry(km, &xfrm_km_list, list) { - err = km->acquire(x, t, pol, XFRM_POLICY_OUT); - if (!err) - break; + acqret = km->acquire(x, t, pol, XFRM_POLICY_OUT); + if (!acqret) + err = acqret; } read_unlock(&xfrm_km_lock); return err; @@ -848,13 +883,12 @@ EXPORT_SYMBOL(km_new_mapping); void km_policy_expired(struct xfrm_policy *pol, int dir, int hard) { - struct xfrm_mgr *km; + struct km_event c; - read_lock(&xfrm_km_lock); - list_for_each_entry(km, &xfrm_km_list, list) - if (km->notify_policy) - km->notify_policy(pol, dir, hard); - read_unlock(&xfrm_km_lock); + c.data = hard; + c.data = hard; + c.event = XFRM_SAP_EXPIRED; + km_policy_notify(pol, dir, &c); if (hard) wake_up(&km_waitq); diff --git a/net/xfrm/xfrm_user.c b/net/xfrm/xfrm_user.c index 97509011c274..bd8e6882c083 100644 --- a/net/xfrm/xfrm_user.c +++ b/net/xfrm/xfrm_user.c @@ -277,6 +277,7 @@ static int xfrm_add_sa(struct sk_buff *skb, struct nlmsghdr *nlh, void **xfrma) struct xfrm_usersa_info *p = NLMSG_DATA(nlh); struct xfrm_state *x; int err; + struct km_event c; err = verify_newsa_info(p, (struct rtattr **) xfrma); if (err) @@ -286,6 +287,7 @@ static int xfrm_add_sa(struct sk_buff *skb, struct nlmsghdr *nlh, void **xfrma) if (!x) return err; + xfrm_state_hold(x); if (nlh->nlmsg_type == XFRM_MSG_NEWSA) err = xfrm_state_add(x); else @@ -294,14 +296,27 @@ static int xfrm_add_sa(struct sk_buff *skb, struct nlmsghdr *nlh, void **xfrma) if (err < 0) { x->km.state = XFRM_STATE_DEAD; xfrm_state_put(x); + return err; } + c.seq = nlh->nlmsg_seq; + c.pid = nlh->nlmsg_pid; + if (nlh->nlmsg_type == XFRM_MSG_NEWSA) + c.event = XFRM_SAP_ADDED; + else + c.event = XFRM_SAP_UPDATED; + + km_state_notify(x, &c); + xfrm_state_put(x); + return err; } static int xfrm_del_sa(struct sk_buff *skb, struct nlmsghdr *nlh, void **xfrma) { struct xfrm_state *x; + int err; + struct km_event c; struct xfrm_usersa_id *p = NLMSG_DATA(nlh); x = xfrm_state_lookup(&p->daddr, p->spi, p->proto, p->family); @@ -313,10 +328,19 @@ static int xfrm_del_sa(struct sk_buff *skb, struct nlmsghdr *nlh, void **xfrma) return -EPERM; } - xfrm_state_delete(x); + err = xfrm_state_delete(x); + if (err < 0) { + xfrm_state_put(x); + return err; + } + + c.seq = nlh->nlmsg_seq; + c.pid = nlh->nlmsg_pid; + c.event = XFRM_SAP_DELETED; + km_state_notify(x, &c); xfrm_state_put(x); - return 0; + return err; } static void copy_to_user_state(struct xfrm_state *x, struct xfrm_usersa_info *p) @@ -681,6 +705,7 @@ static int xfrm_add_policy(struct sk_buff *skb, struct nlmsghdr *nlh, void **xfr { struct xfrm_userpolicy_info *p = NLMSG_DATA(nlh); struct xfrm_policy *xp; + struct km_event c; int err; int excl; @@ -692,6 +717,10 @@ static int xfrm_add_policy(struct sk_buff *skb, struct nlmsghdr *nlh, void **xfr if (!xp) return err; + /* shouldnt excl be based on nlh flags?? + * Aha! this is anti-netlink really i.e more pfkey derived + * in netlink excl is a flag and you wouldnt need + * a type XFRM_MSG_UPDPOLICY - JHS */ excl = nlh->nlmsg_type == XFRM_MSG_NEWPOLICY; err = xfrm_policy_insert(p->dir, xp, excl); if (err) { @@ -699,6 +728,15 @@ static int xfrm_add_policy(struct sk_buff *skb, struct nlmsghdr *nlh, void **xfr return err; } + if (!excl) + c.event = XFRM_SAP_UPDATED; + else + c.event = XFRM_SAP_ADDED; + + c.seq = nlh->nlmsg_seq; + c.pid = nlh->nlmsg_pid; + km_policy_notify(xp, p->dir, &c); + xfrm_pol_put(xp); return 0; @@ -816,6 +854,7 @@ static int xfrm_get_policy(struct sk_buff *skb, struct nlmsghdr *nlh, void **xfr struct xfrm_policy *xp; struct xfrm_userpolicy_id *p; int err; + struct km_event c; int delete; p = NLMSG_DATA(nlh); @@ -843,6 +882,11 @@ static int xfrm_get_policy(struct sk_buff *skb, struct nlmsghdr *nlh, void **xfr NETLINK_CB(skb).pid, MSG_DONTWAIT); } + } else { + c.event = XFRM_SAP_DELETED; + c.seq = nlh->nlmsg_seq; + c.pid = nlh->nlmsg_pid; + km_policy_notify(xp, p->dir, &c); } xfrm_pol_put(xp); @@ -852,15 +896,28 @@ static int xfrm_get_policy(struct sk_buff *skb, struct nlmsghdr *nlh, void **xfr static int xfrm_flush_sa(struct sk_buff *skb, struct nlmsghdr *nlh, void **xfrma) { + struct km_event c; struct xfrm_usersa_flush *p = NLMSG_DATA(nlh); xfrm_state_flush(p->proto); + c.data = p->proto; + c.event = XFRM_SAP_FLUSHED; + c.seq = nlh->nlmsg_seq; + c.pid = nlh->nlmsg_pid; + km_state_notify(NULL, &c); + return 0; } static int xfrm_flush_policy(struct sk_buff *skb, struct nlmsghdr *nlh, void **xfrma) { + struct km_event c; + xfrm_policy_flush(); + c.event = XFRM_SAP_FLUSHED; + c.seq = nlh->nlmsg_seq; + c.pid = nlh->nlmsg_pid; + km_policy_notify(NULL, 0, &c); return 0; } @@ -1069,10 +1126,12 @@ nlmsg_failure: return -1; } -static int xfrm_send_state_notify(struct xfrm_state *x, int hard) +static int xfrm_exp_state_notify(struct xfrm_state *x, struct km_event *c) { struct sk_buff *skb; + int hard = c ->data; + /* fix to do alloc using NLM macros */ skb = alloc_skb(sizeof(struct xfrm_user_expire) + 16, GFP_ATOMIC); if (skb == NULL) return -ENOMEM; @@ -1085,6 +1144,122 @@ static int xfrm_send_state_notify(struct xfrm_state *x, int hard) return netlink_broadcast(xfrm_nl, skb, 0, XFRMGRP_EXPIRE, GFP_ATOMIC); } +static int xfrm_notify_sa_flush(struct km_event *c) +{ + struct xfrm_usersa_flush *p; + struct nlmsghdr *nlh; + struct sk_buff *skb; + unsigned char *b; + int len = NLMSG_LENGTH(sizeof(struct xfrm_usersa_flush)); + + skb = alloc_skb(len, GFP_ATOMIC); + if (skb == NULL) + return -ENOMEM; + b = skb->tail; + + nlh = NLMSG_PUT(skb, c->pid, c->seq, + XFRM_MSG_FLUSHSA, sizeof(*p)); + nlh->nlmsg_flags = 0; + + p = NLMSG_DATA(nlh); + p->proto = c->data; + + nlh->nlmsg_len = skb->tail - b; + + return netlink_broadcast(xfrm_nl, skb, 0, XFRMGRP_SA, GFP_ATOMIC); + +nlmsg_failure: + kfree_skb(skb); + return -1; +} + +static int inline xfrm_sa_len(struct xfrm_state *x) +{ + int l = NLMSG_LENGTH(sizeof(struct xfrm_usersa_info)); + if (x->aalg) + l += RTA_SPACE(sizeof(*x->aalg) + (x->aalg->alg_key_len+7)/8); + if (x->ealg) + l += RTA_SPACE(sizeof(*x->ealg) + (x->ealg->alg_key_len+7)/8); + if (x->calg) + l += RTA_SPACE(sizeof(*x->calg)); + if (x->encap) + l += RTA_SPACE(sizeof(*x->encap)); + + return l; +} + +static int xfrm_notify_sa(struct xfrm_state *x, struct km_event *c) +{ + struct xfrm_usersa_info *p; + struct nlmsghdr *nlh; + struct sk_buff *skb; + u32 nlt; + unsigned char *b; + int len = xfrm_sa_len(x); + + skb = alloc_skb(len, GFP_ATOMIC); + if (skb == NULL) + return -ENOMEM; + b = skb->tail; + + if (c->event == XFRM_SAP_ADDED) + nlt = XFRM_MSG_NEWSA; + else if (c->event == XFRM_SAP_UPDATED) + nlt = XFRM_MSG_UPDSA; + else if (c->event == XFRM_SAP_DELETED) + nlt = XFRM_MSG_DELSA; + else + goto nlmsg_failure; + + nlh = NLMSG_PUT(skb, c->pid, c->seq, nlt, sizeof(*p)); + nlh->nlmsg_flags = 0; + + p = NLMSG_DATA(nlh); + copy_to_user_state(x, p); + + if (x->aalg) + RTA_PUT(skb, XFRMA_ALG_AUTH, + sizeof(*(x->aalg))+(x->aalg->alg_key_len+7)/8, x->aalg); + if (x->ealg) + RTA_PUT(skb, XFRMA_ALG_CRYPT, + sizeof(*(x->ealg))+(x->ealg->alg_key_len+7)/8, x->ealg); + if (x->calg) + RTA_PUT(skb, XFRMA_ALG_COMP, sizeof(*(x->calg)), x->calg); + + if (x->encap) + RTA_PUT(skb, XFRMA_ENCAP, sizeof(*x->encap), x->encap); + + nlh->nlmsg_len = skb->tail - b; + + return netlink_broadcast(xfrm_nl, skb, 0, XFRMGRP_SA, GFP_ATOMIC); + +nlmsg_failure: +rtattr_failure: + kfree_skb(skb); + return -1; +} + +static int xfrm_send_state_notify(struct xfrm_state *x, struct km_event *c) +{ + + switch (c->event) { + case XFRM_SAP_EXPIRED: + return xfrm_exp_state_notify(x, c); + case XFRM_SAP_DELETED: + case XFRM_SAP_UPDATED: + case XFRM_SAP_ADDED: + return xfrm_notify_sa(x, c); + case XFRM_SAP_FLUSHED: + return xfrm_notify_sa_flush(c); + default: + printk("xfrm_user: Unknown SA event %d\n", c->event); + break; + } + + return 0; + +} + static int build_acquire(struct sk_buff *skb, struct xfrm_state *x, struct xfrm_tmpl *xt, struct xfrm_policy *xp, int dir) @@ -1218,7 +1393,7 @@ nlmsg_failure: return -1; } -static int xfrm_send_policy_notify(struct xfrm_policy *xp, int dir, int hard) +static int xfrm_exp_policy_notify(struct xfrm_policy *xp, int dir, struct km_event *c) { struct sk_buff *skb; size_t len; @@ -1229,7 +1404,7 @@ static int xfrm_send_policy_notify(struct xfrm_policy *xp, int dir, int hard) if (skb == NULL) return -ENOMEM; - if (build_polexpire(skb, xp, dir, hard) < 0) + if (build_polexpire(skb, xp, dir, c->data) < 0) BUG(); NETLINK_CB(skb).dst_groups = XFRMGRP_EXPIRE; @@ -1237,6 +1412,93 @@ static int xfrm_send_policy_notify(struct xfrm_policy *xp, int dir, int hard) return netlink_broadcast(xfrm_nl, skb, 0, XFRMGRP_EXPIRE, GFP_ATOMIC); } +static int xfrm_notify_policy(struct xfrm_policy *xp, int dir, struct km_event *c) +{ + struct xfrm_userpolicy_info *p; + struct nlmsghdr *nlh; + struct sk_buff *skb; + u32 nlt = 0 ; + unsigned char *b; + int len = RTA_SPACE(sizeof(struct xfrm_user_tmpl) * xp->xfrm_nr); + len += NLMSG_SPACE(sizeof(struct xfrm_userpolicy_info)); + + skb = alloc_skb(len, GFP_ATOMIC); + if (skb == NULL) + return -ENOMEM; + b = skb->tail; + + if (c->event == XFRM_SAP_ADDED) + nlt = XFRM_MSG_NEWPOLICY; + else if (c->event == XFRM_SAP_UPDATED) + nlt = XFRM_MSG_UPDPOLICY; + else if (c->event == XFRM_SAP_DELETED) + nlt = XFRM_MSG_DELPOLICY; + else + goto nlmsg_failure; + + nlh = NLMSG_PUT(skb, c->pid, c->seq, nlt, sizeof(*p)); + + p = NLMSG_DATA(nlh); + + nlh->nlmsg_flags = 0; + + copy_to_user_policy(xp, p, dir); + if (copy_to_user_tmpl(xp, skb) < 0) + goto nlmsg_failure; + + nlh->nlmsg_len = skb->tail - b; + + return netlink_broadcast(xfrm_nl, skb, 0, XFRMGRP_POLICY, GFP_ATOMIC); + +nlmsg_failure: + kfree_skb(skb); + return -1; +} + +static int xfrm_notify_policy_flush(struct km_event *c) +{ + struct nlmsghdr *nlh; + struct sk_buff *skb; + unsigned char *b; + int len = NLMSG_LENGTH(0); + + skb = alloc_skb(len, GFP_ATOMIC); + if (skb == NULL) + return -ENOMEM; + b = skb->tail; + + + nlh = NLMSG_PUT(skb, c->pid, c->seq, XFRM_MSG_FLUSHPOLICY, 0); + + nlh->nlmsg_len = skb->tail - b; + + return netlink_broadcast(xfrm_nl, skb, 0, XFRMGRP_POLICY, GFP_ATOMIC); + +nlmsg_failure: + kfree_skb(skb); + return -1; +} + +static int xfrm_send_policy_notify(struct xfrm_policy *xp, int dir, struct km_event *c) +{ + + switch (c->event) { + case XFRM_SAP_ADDED: + case XFRM_SAP_UPDATED: + case XFRM_SAP_DELETED: + return xfrm_notify_policy(xp, dir, c); + case XFRM_SAP_FLUSHED: + return xfrm_notify_policy_flush(c); + case XFRM_SAP_EXPIRED: + return xfrm_exp_policy_notify(xp, dir, c); + default: + printk("xfrm_user: Unknown Policy event %d\n", c->event); + } + + return 0; + +} + static struct xfrm_mgr netlink_mgr = { .id = "netlink", .notify = xfrm_send_state_notify, -- cgit v1.2.3 From 1944972d3bb651474a5021c9da8d0166ae19f1eb Mon Sep 17 00:00:00 2001 From: Arnaldo Carvalho de Melo Date: Sat, 18 Jun 2005 22:46:19 -0700 Subject: [SLAB] Introduce kmem_cache_name This is for use with slab users that pass a dynamically allocated slab name in kmem_cache_create, so that before destroying the slab one can retrieve the name and free its memory. Signed-off-by: Arnaldo Carvalho de Melo Signed-off-by: David S. Miller --- include/linux/slab.h | 1 + mm/slab.c | 6 ++++++ 2 files changed, 7 insertions(+) (limited to 'include/linux') diff --git a/include/linux/slab.h b/include/linux/slab.h index 7d66385ae750..76cf7e60216c 100644 --- a/include/linux/slab.h +++ b/include/linux/slab.h @@ -64,6 +64,7 @@ extern int kmem_cache_shrink(kmem_cache_t *); extern void *kmem_cache_alloc(kmem_cache_t *, unsigned int __nocast); extern void kmem_cache_free(kmem_cache_t *, void *); extern unsigned int kmem_cache_size(kmem_cache_t *); +extern const char *kmem_cache_name(kmem_cache_t *); extern kmem_cache_t *kmem_find_general_cachep(size_t size, int gfpflags); /* Size description struct for general caches. */ diff --git a/mm/slab.c b/mm/slab.c index 840742641152..c78d343b3c5f 100644 --- a/mm/slab.c +++ b/mm/slab.c @@ -2620,6 +2620,12 @@ unsigned int kmem_cache_size(kmem_cache_t *cachep) } EXPORT_SYMBOL(kmem_cache_size); +const char *kmem_cache_name(kmem_cache_t *cachep) +{ + return cachep->name; +} +EXPORT_SYMBOL_GPL(kmem_cache_name); + struct ccupdate_struct { kmem_cache_t *cachep; struct array_cache *new[NR_CPUS]; -- cgit v1.2.3 From 2e6599cb899ba4b133f42cbf9d2b1883d2dc583a Mon Sep 17 00:00:00 2001 From: Arnaldo Carvalho de Melo Date: Sat, 18 Jun 2005 22:46:52 -0700 Subject: [NET] Generalise TCP's struct open_request minisock infrastructure Kept this first changeset minimal, without changing existing names to ease peer review. Basicaly tcp_openreq_alloc now receives the or_calltable, that in turn has two new members: ->slab, that replaces tcp_openreq_cachep ->obj_size, to inform the size of the openreq descendant for a specific protocol The protocol specific fields in struct open_request were moved to a class hierarchy, with the things that are common to all connection oriented PF_INET protocols in struct inet_request_sock, the TCP ones in tcp_request_sock, that is an inet_request_sock, that is an open_request. I.e. this uses the same approach used for the struct sock class hierarchy, with sk_prot indicating if the protocol wants to use the open_request infrastructure by filling in sk_prot->rsk_prot with an or_calltable. Results? Performance is improved and TCP v4 now uses only 64 bytes per open request minisock, down from 96 without this patch :-) Next changeset will rename some of the structs, fields and functions mentioned above, struct or_calltable is way unclear, better name it struct request_sock_ops, s/struct open_request/struct request_sock/g, etc. Signed-off-by: Arnaldo Carvalho de Melo Signed-off-by: David S. Miller --- include/linux/ip.h | 21 ++++++++++ include/linux/ipv6.h | 13 +++++++ include/linux/tcp.h | 11 ++++++ include/net/request_sock.h | 77 +++++++++++++++++++++++++++++++++++++ include/net/sock.h | 4 ++ include/net/tcp.h | 87 ++++++----------------------------------- include/net/tcp_ecn.h | 7 ++-- net/core/sock.c | 35 +++++++++++++++++ net/ipv4/syncookies.c | 39 ++++++++++--------- net/ipv4/tcp.c | 9 ----- net/ipv4/tcp_diag.c | 25 ++++++------ net/ipv4/tcp_ipv4.c | 72 +++++++++++++++++++--------------- net/ipv4/tcp_minisocks.c | 48 ++++++++++++----------- net/ipv4/tcp_output.c | 25 ++++++------ net/ipv4/tcp_timer.c | 2 +- net/ipv6/tcp_ipv6.c | 96 ++++++++++++++++++++++++---------------------- 16 files changed, 341 insertions(+), 230 deletions(-) create mode 100644 include/net/request_sock.h (limited to 'include/linux') diff --git a/include/linux/ip.h b/include/linux/ip.h index 8438c68591f9..d5b7c907204e 100644 --- a/include/linux/ip.h +++ b/include/linux/ip.h @@ -81,6 +81,7 @@ #ifdef __KERNEL__ #include #include +#include #include #include #include @@ -107,6 +108,26 @@ struct ip_options { #define optlength(opt) (sizeof(struct ip_options) + opt->optlen) +struct inet_request_sock { + struct open_request req; + u32 loc_addr; + u32 rmt_addr; + u16 rmt_port; + u16 snd_wscale : 4, + rcv_wscale : 4, + tstamp_ok : 1, + sack_ok : 1, + wscale_ok : 1, + ecn_ok : 1, + acked : 1; + struct ip_options *opt; +}; + +static inline struct inet_request_sock *inet_rsk(const struct open_request *sk) +{ + return (struct inet_request_sock *)sk; +} + struct ipv6_pinfo; struct inet_sock { diff --git a/include/linux/ipv6.h b/include/linux/ipv6.h index ab0d0efbf240..98acdbf3d446 100644 --- a/include/linux/ipv6.h +++ b/include/linux/ipv6.h @@ -193,6 +193,19 @@ struct inet6_skb_parm { #define IP6CB(skb) ((struct inet6_skb_parm*)((skb)->cb)) +struct tcp6_request_sock { + struct tcp_request_sock req; + struct in6_addr loc_addr; + struct in6_addr rmt_addr; + struct sk_buff *pktopts; + int iif; +}; + +static inline struct tcp6_request_sock *tcp6_rsk(const struct open_request *sk) +{ + return (struct tcp6_request_sock *)sk; +} + /** * struct ipv6_pinfo - ipv6 private area * diff --git a/include/linux/tcp.h b/include/linux/tcp.h index 14a55e3e3a50..86771b37b80d 100644 --- a/include/linux/tcp.h +++ b/include/linux/tcp.h @@ -230,6 +230,17 @@ struct tcp_options_received { __u16 mss_clamp; /* Maximal mss, negotiated at connection setup */ }; +struct tcp_request_sock { + struct inet_request_sock req; + __u32 rcv_isn; + __u32 snt_isn; +}; + +static inline struct tcp_request_sock *tcp_rsk(const struct open_request *req) +{ + return (struct tcp_request_sock *)req; +} + struct tcp_sock { /* inet_sock has to be the first member of tcp_sock */ struct inet_sock inet; diff --git a/include/net/request_sock.h b/include/net/request_sock.h new file mode 100644 index 000000000000..9502f5587931 --- /dev/null +++ b/include/net/request_sock.h @@ -0,0 +1,77 @@ +/* + * NET Generic infrastructure for Network protocols. + * + * Definitions for request_sock + * + * Authors: Arnaldo Carvalho de Melo + * + * From code originally in include/net/tcp.h + * + * 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 _REQUEST_SOCK_H +#define _REQUEST_SOCK_H + +#include +#include +#include + +struct open_request; +struct sk_buff; +struct dst_entry; +struct proto; + +struct or_calltable { + int family; + kmem_cache_t *slab; + int obj_size; + int (*rtx_syn_ack)(struct sock *sk, + struct open_request *req, + struct dst_entry *dst); + void (*send_ack)(struct sk_buff *skb, + struct open_request *req); + void (*send_reset)(struct sk_buff *skb); + void (*destructor)(struct open_request *req); +}; + +/* struct open_request - mini sock to represent a connection request + */ +struct open_request { + struct open_request *dl_next; /* Must be first member! */ + u16 mss; + u8 retrans; + u8 __pad; + /* The following two fields can be easily recomputed I think -AK */ + u32 window_clamp; /* window clamp at creation time */ + u32 rcv_wnd; /* rcv_wnd offered first time */ + u32 ts_recent; + unsigned long expires; + struct or_calltable *class; + struct sock *sk; +}; + +static inline struct open_request *tcp_openreq_alloc(struct or_calltable *class) +{ + struct open_request *req = kmem_cache_alloc(class->slab, SLAB_ATOMIC); + + if (req != NULL) + req->class = class; + + return req; +} + +static inline void tcp_openreq_fastfree(struct open_request *req) +{ + kmem_cache_free(req->class->slab, req); +} + +static inline void tcp_openreq_free(struct open_request *req) +{ + req->class->destructor(req); + tcp_openreq_fastfree(req); +} + +#endif /* _REQUEST_SOCK_H */ diff --git a/include/net/sock.h b/include/net/sock.h index a9ef3a6a13f3..6919276af8af 100644 --- a/include/net/sock.h +++ b/include/net/sock.h @@ -484,6 +484,8 @@ extern void sk_stream_kill_queues(struct sock *sk); extern int sk_wait_data(struct sock *sk, long *timeo); +struct or_calltable; + /* Networking protocol blocks we attach to sockets. * socket layer -> transport layer interface * transport -> network interface is defined by struct inet_proto @@ -547,6 +549,8 @@ struct proto { kmem_cache_t *slab; unsigned int obj_size; + struct or_calltable *rsk_prot; + struct module *owner; char name[32]; diff --git a/include/net/tcp.h b/include/net/tcp.h index e71f8ba3e101..d438ba566b89 100644 --- a/include/net/tcp.h +++ b/include/net/tcp.h @@ -31,6 +31,7 @@ #include #include #include +#include #include #include #include @@ -613,74 +614,6 @@ extern atomic_t tcp_memory_allocated; extern atomic_t tcp_sockets_allocated; extern int tcp_memory_pressure; -struct open_request; - -struct or_calltable { - int family; - int (*rtx_syn_ack) (struct sock *sk, struct open_request *req, struct dst_entry*); - void (*send_ack) (struct sk_buff *skb, struct open_request *req); - void (*destructor) (struct open_request *req); - void (*send_reset) (struct sk_buff *skb); -}; - -struct tcp_v4_open_req { - __u32 loc_addr; - __u32 rmt_addr; - struct ip_options *opt; -}; - -#if defined(CONFIG_IPV6) || defined (CONFIG_IPV6_MODULE) -struct tcp_v6_open_req { - struct in6_addr loc_addr; - struct in6_addr rmt_addr; - struct sk_buff *pktopts; - int iif; -}; -#endif - -/* this structure is too big */ -struct open_request { - struct open_request *dl_next; /* Must be first member! */ - __u32 rcv_isn; - __u32 snt_isn; - __u16 rmt_port; - __u16 mss; - __u8 retrans; - __u8 __pad; - __u16 snd_wscale : 4, - rcv_wscale : 4, - tstamp_ok : 1, - sack_ok : 1, - wscale_ok : 1, - ecn_ok : 1, - acked : 1; - /* The following two fields can be easily recomputed I think -AK */ - __u32 window_clamp; /* window clamp at creation time */ - __u32 rcv_wnd; /* rcv_wnd offered first time */ - __u32 ts_recent; - unsigned long expires; - struct or_calltable *class; - struct sock *sk; - union { - struct tcp_v4_open_req v4_req; -#if defined(CONFIG_IPV6) || defined (CONFIG_IPV6_MODULE) - struct tcp_v6_open_req v6_req; -#endif - } af; -}; - -/* SLAB cache for open requests. */ -extern kmem_cache_t *tcp_openreq_cachep; - -#define tcp_openreq_alloc() kmem_cache_alloc(tcp_openreq_cachep, SLAB_ATOMIC) -#define tcp_openreq_fastfree(req) kmem_cache_free(tcp_openreq_cachep, req) - -static inline void tcp_openreq_free(struct open_request *req) -{ - req->class->destructor(req); - tcp_openreq_fastfree(req); -} - #if defined(CONFIG_IPV6) || defined(CONFIG_IPV6_MODULE) #define TCP_INET_FAMILY(fam) ((fam) == AF_INET) #else @@ -1832,17 +1765,19 @@ static __inline__ void tcp_openreq_init(struct open_request *req, struct tcp_options_received *rx_opt, struct sk_buff *skb) { + struct inet_request_sock *ireq = inet_rsk(req); + req->rcv_wnd = 0; /* So that tcp_send_synack() knows! */ - req->rcv_isn = TCP_SKB_CB(skb)->seq; + tcp_rsk(req)->rcv_isn = TCP_SKB_CB(skb)->seq; req->mss = rx_opt->mss_clamp; req->ts_recent = rx_opt->saw_tstamp ? rx_opt->rcv_tsval : 0; - req->tstamp_ok = rx_opt->tstamp_ok; - req->sack_ok = rx_opt->sack_ok; - req->snd_wscale = rx_opt->snd_wscale; - req->wscale_ok = rx_opt->wscale_ok; - req->acked = 0; - req->ecn_ok = 0; - req->rmt_port = skb->h.th->source; + ireq->tstamp_ok = rx_opt->tstamp_ok; + ireq->sack_ok = rx_opt->sack_ok; + ireq->snd_wscale = rx_opt->snd_wscale; + ireq->wscale_ok = rx_opt->wscale_ok; + ireq->acked = 0; + ireq->ecn_ok = 0; + ireq->rmt_port = skb->h.th->source; } extern void tcp_enter_memory_pressure(void); diff --git a/include/net/tcp_ecn.h b/include/net/tcp_ecn.h index dc1456389a97..94ad970e844a 100644 --- a/include/net/tcp_ecn.h +++ b/include/net/tcp_ecn.h @@ -2,6 +2,7 @@ #define _NET_TCP_ECN_H_ 1 #include +#include #define TCP_HP_BITS (~(TCP_RESERVED_BITS|TCP_FLAG_PSH)) @@ -40,7 +41,7 @@ static inline void TCP_ECN_send_syn(struct sock *sk, struct tcp_sock *tp, static __inline__ void TCP_ECN_make_synack(struct open_request *req, struct tcphdr *th) { - if (req->ecn_ok) + if (inet_rsk(req)->ecn_ok) th->ece = 1; } @@ -113,14 +114,14 @@ static inline int TCP_ECN_rcv_ecn_echo(struct tcp_sock *tp, struct tcphdr *th) static inline void TCP_ECN_openreq_child(struct tcp_sock *tp, struct open_request *req) { - tp->ecn_flags = req->ecn_ok ? TCP_ECN_OK : 0; + tp->ecn_flags = inet_rsk(req)->ecn_ok ? TCP_ECN_OK : 0; } static __inline__ void TCP_ECN_create_request(struct open_request *req, struct tcphdr *th) { if (sysctl_tcp_ecn && th->ece && th->cwr) - req->ecn_ok = 1; + inet_rsk(req)->ecn_ok = 1; } #endif diff --git a/net/core/sock.c b/net/core/sock.c index 96e00b08698f..a6ec3ada7f9e 100644 --- a/net/core/sock.c +++ b/net/core/sock.c @@ -118,6 +118,7 @@ #include #include #include +#include #include #include #include @@ -1363,6 +1364,7 @@ static LIST_HEAD(proto_list); int proto_register(struct proto *prot, int alloc_slab) { + char *request_sock_slab_name; int rc = -ENOBUFS; if (alloc_slab) { @@ -1374,6 +1376,25 @@ int proto_register(struct proto *prot, int alloc_slab) prot->name); goto out; } + + if (prot->rsk_prot != NULL) { + static const char mask[] = "request_sock_%s"; + + request_sock_slab_name = kmalloc(strlen(prot->name) + sizeof(mask) - 1, GFP_KERNEL); + if (request_sock_slab_name == NULL) + goto out_free_sock_slab; + + sprintf(request_sock_slab_name, mask, prot->name); + prot->rsk_prot->slab = kmem_cache_create(request_sock_slab_name, + prot->rsk_prot->obj_size, 0, + SLAB_HWCACHE_ALIGN, NULL, NULL); + + if (prot->rsk_prot->slab == NULL) { + printk(KERN_CRIT "%s: Can't create request sock SLAB cache!\n", + prot->name); + goto out_free_request_sock_slab_name; + } + } } write_lock(&proto_list_lock); @@ -1382,6 +1403,12 @@ int proto_register(struct proto *prot, int alloc_slab) rc = 0; out: return rc; +out_free_request_sock_slab_name: + kfree(request_sock_slab_name); +out_free_sock_slab: + kmem_cache_destroy(prot->slab); + prot->slab = NULL; + goto out; } EXPORT_SYMBOL(proto_register); @@ -1395,6 +1422,14 @@ void proto_unregister(struct proto *prot) prot->slab = NULL; } + if (prot->rsk_prot != NULL && prot->rsk_prot->slab != NULL) { + const char *name = kmem_cache_name(prot->rsk_prot->slab); + + kmem_cache_destroy(prot->rsk_prot->slab); + kfree(name); + prot->rsk_prot->slab = NULL; + } + list_del(&prot->node); write_unlock(&proto_list_lock); } diff --git a/net/ipv4/syncookies.c b/net/ipv4/syncookies.c index e923d2f021aa..dd47e6da6fb3 100644 --- a/net/ipv4/syncookies.c +++ b/net/ipv4/syncookies.c @@ -190,6 +190,8 @@ static inline struct sock *get_cookie_sock(struct sock *sk, struct sk_buff *skb, struct sock *cookie_v4_check(struct sock *sk, struct sk_buff *skb, struct ip_options *opt) { + struct inet_request_sock *ireq; + struct tcp_request_sock *treq; struct tcp_sock *tp = tcp_sk(sk); __u32 cookie = ntohl(skb->h.th->ack_seq) - 1; struct sock *ret = sk; @@ -209,19 +211,20 @@ struct sock *cookie_v4_check(struct sock *sk, struct sk_buff *skb, NET_INC_STATS_BH(LINUX_MIB_SYNCOOKIESRECV); - req = tcp_openreq_alloc(); ret = NULL; + req = tcp_openreq_alloc(&or_ipv4); /* for safety */ if (!req) goto out; - req->rcv_isn = htonl(skb->h.th->seq) - 1; - req->snt_isn = cookie; + ireq = inet_rsk(req); + treq = tcp_rsk(req); + treq->rcv_isn = htonl(skb->h.th->seq) - 1; + treq->snt_isn = cookie; req->mss = mss; - req->rmt_port = skb->h.th->source; - req->af.v4_req.loc_addr = skb->nh.iph->daddr; - req->af.v4_req.rmt_addr = skb->nh.iph->saddr; - req->class = &or_ipv4; /* for savety */ - req->af.v4_req.opt = NULL; + ireq->rmt_port = skb->h.th->source; + ireq->loc_addr = skb->nh.iph->daddr; + ireq->rmt_addr = skb->nh.iph->saddr; + ireq->opt = NULL; /* We throwed the options of the initial SYN away, so we hope * the ACK carries the same options again (see RFC1122 4.2.3.8) @@ -229,17 +232,15 @@ struct sock *cookie_v4_check(struct sock *sk, struct sk_buff *skb, if (opt && opt->optlen) { int opt_size = sizeof(struct ip_options) + opt->optlen; - req->af.v4_req.opt = kmalloc(opt_size, GFP_ATOMIC); - if (req->af.v4_req.opt) { - if (ip_options_echo(req->af.v4_req.opt, skb)) { - kfree(req->af.v4_req.opt); - req->af.v4_req.opt = NULL; - } + ireq->opt = kmalloc(opt_size, GFP_ATOMIC); + if (ireq->opt != NULL && ip_options_echo(ireq->opt, skb)) { + kfree(ireq->opt); + ireq->opt = NULL; } } - req->snd_wscale = req->rcv_wscale = req->tstamp_ok = 0; - req->wscale_ok = req->sack_ok = 0; + ireq->snd_wscale = ireq->rcv_wscale = ireq->tstamp_ok = 0; + ireq->wscale_ok = ireq->sack_ok = 0; req->expires = 0UL; req->retrans = 0; @@ -253,8 +254,8 @@ struct sock *cookie_v4_check(struct sock *sk, struct sk_buff *skb, struct flowi fl = { .nl_u = { .ip4_u = { .daddr = ((opt && opt->srr) ? opt->faddr : - req->af.v4_req.rmt_addr), - .saddr = req->af.v4_req.loc_addr, + ireq->rmt_addr), + .saddr = ireq->loc_addr, .tos = RT_CONN_FLAGS(sk) } }, .proto = IPPROTO_TCP, .uli_u = { .ports = @@ -272,7 +273,7 @@ struct sock *cookie_v4_check(struct sock *sk, struct sk_buff *skb, &req->rcv_wnd, &req->window_clamp, 0, &rcv_wscale); /* BTW win scale with syncookies is 0 by definition */ - req->rcv_wscale = rcv_wscale; + ireq->rcv_wscale = rcv_wscale; ret = get_cookie_sock(sk, skb, req, &rt->u.dst); out: return ret; diff --git a/net/ipv4/tcp.c b/net/ipv4/tcp.c index 0d9a4fd5f1a4..a3cabfa2022a 100644 --- a/net/ipv4/tcp.c +++ b/net/ipv4/tcp.c @@ -271,7 +271,6 @@ int sysctl_tcp_fin_timeout = TCP_FIN_TIMEOUT; DEFINE_SNMP_STAT(struct tcp_mib, tcp_statistics); -kmem_cache_t *tcp_openreq_cachep; kmem_cache_t *tcp_bucket_cachep; kmem_cache_t *tcp_timewait_cachep; @@ -2271,13 +2270,6 @@ void __init tcp_init(void) __skb_cb_too_small_for_tcp(sizeof(struct tcp_skb_cb), sizeof(skb->cb)); - tcp_openreq_cachep = kmem_cache_create("tcp_open_request", - sizeof(struct open_request), - 0, SLAB_HWCACHE_ALIGN, - NULL, NULL); - if (!tcp_openreq_cachep) - panic("tcp_init: Cannot alloc open_request cache."); - tcp_bucket_cachep = kmem_cache_create("tcp_bind_bucket", sizeof(struct tcp_bind_bucket), 0, SLAB_HWCACHE_ALIGN, @@ -2374,7 +2366,6 @@ EXPORT_SYMBOL(tcp_destroy_sock); EXPORT_SYMBOL(tcp_disconnect); EXPORT_SYMBOL(tcp_getsockopt); EXPORT_SYMBOL(tcp_ioctl); -EXPORT_SYMBOL(tcp_openreq_cachep); EXPORT_SYMBOL(tcp_poll); EXPORT_SYMBOL(tcp_read_sock); EXPORT_SYMBOL(tcp_recvmsg); diff --git a/net/ipv4/tcp_diag.c b/net/ipv4/tcp_diag.c index 8faa8948f75c..700ff2413588 100644 --- a/net/ipv4/tcp_diag.c +++ b/net/ipv4/tcp_diag.c @@ -458,6 +458,7 @@ static int tcpdiag_fill_req(struct sk_buff *skb, struct sock *sk, struct open_request *req, u32 pid, u32 seq) { + const struct inet_request_sock *ireq = inet_rsk(req); struct inet_sock *inet = inet_sk(sk); unsigned char *b = skb->tail; struct tcpdiagmsg *r; @@ -482,9 +483,9 @@ static int tcpdiag_fill_req(struct sk_buff *skb, struct sock *sk, tmo = 0; r->id.tcpdiag_sport = inet->sport; - r->id.tcpdiag_dport = req->rmt_port; - r->id.tcpdiag_src[0] = req->af.v4_req.loc_addr; - r->id.tcpdiag_dst[0] = req->af.v4_req.rmt_addr; + r->id.tcpdiag_dport = ireq->rmt_port; + r->id.tcpdiag_src[0] = ireq->loc_addr; + r->id.tcpdiag_dst[0] = ireq->rmt_addr; r->tcpdiag_expires = jiffies_to_msecs(tmo), r->tcpdiag_rqueue = 0; r->tcpdiag_wqueue = 0; @@ -493,9 +494,9 @@ static int tcpdiag_fill_req(struct sk_buff *skb, struct sock *sk, #ifdef CONFIG_IP_TCPDIAG_IPV6 if (r->tcpdiag_family == AF_INET6) { ipv6_addr_copy((struct in6_addr *)r->id.tcpdiag_src, - &req->af.v6_req.loc_addr); + &tcp6_rsk(req)->loc_addr); ipv6_addr_copy((struct in6_addr *)r->id.tcpdiag_dst, - &req->af.v6_req.rmt_addr); + &tcp6_rsk(req)->rmt_addr); } #endif nlh->nlmsg_len = skb->tail - b; @@ -545,9 +546,11 @@ static int tcpdiag_dump_reqs(struct sk_buff *skb, struct sock *sk, reqnum = 0; for (req = head; req; reqnum++, req = req->dl_next) { + struct inet_request_sock *ireq = inet_rsk(req); + if (reqnum < s_reqnum) continue; - if (r->id.tcpdiag_dport != req->rmt_port && + if (r->id.tcpdiag_dport != ireq->rmt_port && r->id.tcpdiag_dport) continue; @@ -555,16 +558,16 @@ static int tcpdiag_dump_reqs(struct sk_buff *skb, struct sock *sk, entry.saddr = #ifdef CONFIG_IP_TCPDIAG_IPV6 (entry.family == AF_INET6) ? - req->af.v6_req.loc_addr.s6_addr32 : + tcp6_rsk(req)->loc_addr.s6_addr32 : #endif - &req->af.v4_req.loc_addr; + &ireq->loc_addr; entry.daddr = #ifdef CONFIG_IP_TCPDIAG_IPV6 (entry.family == AF_INET6) ? - req->af.v6_req.rmt_addr.s6_addr32 : + tcp6_rsk(req)->rmt_addr.s6_addr32 : #endif - &req->af.v4_req.rmt_addr; - entry.dport = ntohs(req->rmt_port); + &ireq->rmt_addr; + entry.dport = ntohs(ireq->rmt_port); if (!tcpdiag_bc_run(RTA_DATA(bc), RTA_PAYLOAD(bc), &entry)) diff --git a/net/ipv4/tcp_ipv4.c b/net/ipv4/tcp_ipv4.c index dad98e4a5043..e156be90df14 100644 --- a/net/ipv4/tcp_ipv4.c +++ b/net/ipv4/tcp_ipv4.c @@ -880,9 +880,11 @@ static struct open_request *tcp_v4_search_req(struct tcp_sock *tp, for (prev = &lopt->syn_table[tcp_v4_synq_hash(raddr, rport, lopt->hash_rnd)]; (req = *prev) != NULL; prev = &req->dl_next) { - if (req->rmt_port == rport && - req->af.v4_req.rmt_addr == raddr && - req->af.v4_req.loc_addr == laddr && + const struct inet_request_sock *ireq = inet_rsk(req); + + if (ireq->rmt_port == rport && + ireq->rmt_addr == raddr && + ireq->loc_addr == laddr && TCP_INET_FAMILY(req->class->family)) { BUG_TRAP(!req->sk); *prevp = prev; @@ -897,7 +899,7 @@ static void tcp_v4_synq_add(struct sock *sk, struct open_request *req) { struct tcp_sock *tp = tcp_sk(sk); struct tcp_listen_opt *lopt = tp->listen_opt; - u32 h = tcp_v4_synq_hash(req->af.v4_req.rmt_addr, req->rmt_port, lopt->hash_rnd); + u32 h = tcp_v4_synq_hash(inet_rsk(req)->rmt_addr, inet_rsk(req)->rmt_port, lopt->hash_rnd); req->expires = jiffies + TCP_TIMEOUT_INIT; req->retrans = 0; @@ -1065,7 +1067,7 @@ void tcp_v4_err(struct sk_buff *skb, u32 info) */ BUG_TRAP(!req->sk); - if (seq != req->snt_isn) { + if (seq != tcp_rsk(req)->snt_isn) { NET_INC_STATS_BH(LINUX_MIB_OUTOFWINDOWICMPS); goto out; } @@ -1256,7 +1258,7 @@ static void tcp_v4_timewait_ack(struct sock *sk, struct sk_buff *skb) static void tcp_v4_or_send_ack(struct sk_buff *skb, struct open_request *req) { - tcp_v4_send_ack(skb, req->snt_isn + 1, req->rcv_isn + 1, req->rcv_wnd, + tcp_v4_send_ack(skb, tcp_rsk(req)->snt_isn + 1, tcp_rsk(req)->rcv_isn + 1, req->rcv_wnd, req->ts_recent); } @@ -1264,18 +1266,19 @@ static struct dst_entry* tcp_v4_route_req(struct sock *sk, struct open_request *req) { struct rtable *rt; - struct ip_options *opt = req->af.v4_req.opt; + const struct inet_request_sock *ireq = inet_rsk(req); + struct ip_options *opt = inet_rsk(req)->opt; struct flowi fl = { .oif = sk->sk_bound_dev_if, .nl_u = { .ip4_u = { .daddr = ((opt && opt->srr) ? opt->faddr : - req->af.v4_req.rmt_addr), - .saddr = req->af.v4_req.loc_addr, + ireq->rmt_addr), + .saddr = ireq->loc_addr, .tos = RT_CONN_FLAGS(sk) } }, .proto = IPPROTO_TCP, .uli_u = { .ports = { .sport = inet_sk(sk)->sport, - .dport = req->rmt_port } } }; + .dport = ireq->rmt_port } } }; if (ip_route_output_flow(&rt, &fl, sk, 0)) { IP_INC_STATS_BH(IPSTATS_MIB_OUTNOROUTES); @@ -1297,6 +1300,7 @@ static struct dst_entry* tcp_v4_route_req(struct sock *sk, static int tcp_v4_send_synack(struct sock *sk, struct open_request *req, struct dst_entry *dst) { + const struct inet_request_sock *ireq = inet_rsk(req); int err = -1; struct sk_buff * skb; @@ -1310,14 +1314,14 @@ static int tcp_v4_send_synack(struct sock *sk, struct open_request *req, struct tcphdr *th = skb->h.th; th->check = tcp_v4_check(th, skb->len, - req->af.v4_req.loc_addr, - req->af.v4_req.rmt_addr, + ireq->loc_addr, + ireq->rmt_addr, csum_partial((char *)th, skb->len, skb->csum)); - err = ip_build_and_send_pkt(skb, sk, req->af.v4_req.loc_addr, - req->af.v4_req.rmt_addr, - req->af.v4_req.opt); + err = ip_build_and_send_pkt(skb, sk, ireq->loc_addr, + ireq->rmt_addr, + ireq->opt); if (err == NET_XMIT_CN) err = 0; } @@ -1332,8 +1336,8 @@ out: */ static void tcp_v4_or_free(struct open_request *req) { - if (req->af.v4_req.opt) - kfree(req->af.v4_req.opt); + if (inet_rsk(req)->opt) + kfree(inet_rsk(req)->opt); } static inline void syn_flood_warning(struct sk_buff *skb) @@ -1387,6 +1391,7 @@ int sysctl_max_syn_backlog = 256; struct or_calltable or_ipv4 = { .family = PF_INET, + .obj_size = sizeof(struct tcp_request_sock), .rtx_syn_ack = tcp_v4_send_synack, .send_ack = tcp_v4_or_send_ack, .destructor = tcp_v4_or_free, @@ -1395,6 +1400,7 @@ struct or_calltable or_ipv4 = { int tcp_v4_conn_request(struct sock *sk, struct sk_buff *skb) { + struct inet_request_sock *ireq; struct tcp_options_received tmp_opt; struct open_request *req; __u32 saddr = skb->nh.iph->saddr; @@ -1433,7 +1439,7 @@ int tcp_v4_conn_request(struct sock *sk, struct sk_buff *skb) if (sk_acceptq_is_full(sk) && tcp_synq_young(sk) > 1) goto drop; - req = tcp_openreq_alloc(); + req = tcp_openreq_alloc(&or_ipv4); if (!req) goto drop; @@ -1461,10 +1467,10 @@ int tcp_v4_conn_request(struct sock *sk, struct sk_buff *skb) tcp_openreq_init(req, &tmp_opt, skb); - req->af.v4_req.loc_addr = daddr; - req->af.v4_req.rmt_addr = saddr; - req->af.v4_req.opt = tcp_v4_save_options(sk, skb); - req->class = &or_ipv4; + ireq = inet_rsk(req); + ireq->loc_addr = daddr; + ireq->rmt_addr = saddr; + ireq->opt = tcp_v4_save_options(sk, skb); if (!want_cookie) TCP_ECN_create_request(req, skb->h.th); @@ -1523,7 +1529,7 @@ int tcp_v4_conn_request(struct sock *sk, struct sk_buff *skb) isn = tcp_v4_init_sequence(sk, skb); } - req->snt_isn = isn; + tcp_rsk(req)->snt_isn = isn; if (tcp_v4_send_synack(sk, req, dst)) goto drop_and_free; @@ -1551,6 +1557,7 @@ struct sock *tcp_v4_syn_recv_sock(struct sock *sk, struct sk_buff *skb, struct open_request *req, struct dst_entry *dst) { + struct inet_request_sock *ireq; struct inet_sock *newinet; struct tcp_sock *newtp; struct sock *newsk; @@ -1570,11 +1577,12 @@ struct sock *tcp_v4_syn_recv_sock(struct sock *sk, struct sk_buff *skb, newtp = tcp_sk(newsk); newinet = inet_sk(newsk); - newinet->daddr = req->af.v4_req.rmt_addr; - newinet->rcv_saddr = req->af.v4_req.loc_addr; - newinet->saddr = req->af.v4_req.loc_addr; - newinet->opt = req->af.v4_req.opt; - req->af.v4_req.opt = NULL; + ireq = inet_rsk(req); + newinet->daddr = ireq->rmt_addr; + newinet->rcv_saddr = ireq->loc_addr; + newinet->saddr = ireq->loc_addr; + newinet->opt = ireq->opt; + ireq->opt = NULL; newinet->mc_index = tcp_v4_iif(skb); newinet->mc_ttl = skb->nh.iph->ttl; newtp->ext_header_len = 0; @@ -2454,15 +2462,16 @@ void tcp_proc_unregister(struct tcp_seq_afinfo *afinfo) static void get_openreq4(struct sock *sk, struct open_request *req, char *tmpbuf, int i, int uid) { + const struct inet_request_sock *ireq = inet_rsk(req); int ttd = req->expires - jiffies; sprintf(tmpbuf, "%4d: %08X:%04X %08X:%04X" " %02X %08X:%08X %02X:%08lX %08X %5d %8d %u %d %p", i, - req->af.v4_req.loc_addr, + ireq->loc_addr, ntohs(inet_sk(sk)->sport), - req->af.v4_req.rmt_addr, - ntohs(req->rmt_port), + ireq->rmt_addr, + ntohs(ireq->rmt_port), TCP_SYN_RECV, 0, 0, /* could print option size, but that is af dependent. */ 1, /* timers active (only the expire timer) */ @@ -2618,6 +2627,7 @@ struct proto tcp_prot = { .sysctl_rmem = sysctl_tcp_rmem, .max_header = MAX_TCP_HEADER, .obj_size = sizeof(struct tcp_sock), + .rsk_prot = &or_ipv4, }; diff --git a/net/ipv4/tcp_minisocks.c b/net/ipv4/tcp_minisocks.c index eea1a17a9ac2..1037401c7cc8 100644 --- a/net/ipv4/tcp_minisocks.c +++ b/net/ipv4/tcp_minisocks.c @@ -692,6 +692,8 @@ struct sock *tcp_create_openreq_child(struct sock *sk, struct open_request *req, struct sock *newsk = sk_alloc(PF_INET, GFP_ATOMIC, sk->sk_prot, 0); if(newsk != NULL) { + struct inet_request_sock *ireq = inet_rsk(req); + struct tcp_request_sock *treq = tcp_rsk(req); struct tcp_sock *newtp; struct sk_filter *filter; @@ -703,7 +705,7 @@ struct sock *tcp_create_openreq_child(struct sock *sk, struct open_request *req, tcp_sk(newsk)->bind_hash = NULL; /* Clone the TCP header template */ - inet_sk(newsk)->dport = req->rmt_port; + inet_sk(newsk)->dport = ireq->rmt_port; sock_lock_init(newsk); bh_lock_sock(newsk); @@ -739,14 +741,14 @@ struct sock *tcp_create_openreq_child(struct sock *sk, struct open_request *req, /* Now setup tcp_sock */ newtp = tcp_sk(newsk); newtp->pred_flags = 0; - newtp->rcv_nxt = req->rcv_isn + 1; - newtp->snd_nxt = req->snt_isn + 1; - newtp->snd_una = req->snt_isn + 1; - newtp->snd_sml = req->snt_isn + 1; + newtp->rcv_nxt = treq->rcv_isn + 1; + newtp->snd_nxt = treq->snt_isn + 1; + newtp->snd_una = treq->snt_isn + 1; + newtp->snd_sml = treq->snt_isn + 1; tcp_prequeue_init(newtp); - tcp_init_wl(newtp, req->snt_isn, req->rcv_isn); + tcp_init_wl(newtp, treq->snt_isn, treq->rcv_isn); newtp->retransmits = 0; newtp->backoff = 0; @@ -775,10 +777,10 @@ struct sock *tcp_create_openreq_child(struct sock *sk, struct open_request *req, tcp_set_ca_state(newtp, TCP_CA_Open); tcp_init_xmit_timers(newsk); skb_queue_head_init(&newtp->out_of_order_queue); - newtp->rcv_wup = req->rcv_isn + 1; - newtp->write_seq = req->snt_isn + 1; + newtp->rcv_wup = treq->rcv_isn + 1; + newtp->write_seq = treq->snt_isn + 1; newtp->pushed_seq = newtp->write_seq; - newtp->copied_seq = req->rcv_isn + 1; + newtp->copied_seq = treq->rcv_isn + 1; newtp->rx_opt.saw_tstamp = 0; @@ -808,18 +810,18 @@ struct sock *tcp_create_openreq_child(struct sock *sk, struct open_request *req, newsk->sk_socket = NULL; newsk->sk_sleep = NULL; - newtp->rx_opt.tstamp_ok = req->tstamp_ok; - if((newtp->rx_opt.sack_ok = req->sack_ok) != 0) { + newtp->rx_opt.tstamp_ok = ireq->tstamp_ok; + if((newtp->rx_opt.sack_ok = ireq->sack_ok) != 0) { if (sysctl_tcp_fack) newtp->rx_opt.sack_ok |= 2; } newtp->window_clamp = req->window_clamp; newtp->rcv_ssthresh = req->rcv_wnd; newtp->rcv_wnd = req->rcv_wnd; - newtp->rx_opt.wscale_ok = req->wscale_ok; + newtp->rx_opt.wscale_ok = ireq->wscale_ok; if (newtp->rx_opt.wscale_ok) { - newtp->rx_opt.snd_wscale = req->snd_wscale; - newtp->rx_opt.rcv_wscale = req->rcv_wscale; + newtp->rx_opt.snd_wscale = ireq->snd_wscale; + newtp->rx_opt.rcv_wscale = ireq->rcv_wscale; } else { newtp->rx_opt.snd_wscale = newtp->rx_opt.rcv_wscale = 0; newtp->window_clamp = min(newtp->window_clamp, 65535U); @@ -881,7 +883,7 @@ struct sock *tcp_check_req(struct sock *sk,struct sk_buff *skb, } /* Check for pure retransmitted SYN. */ - if (TCP_SKB_CB(skb)->seq == req->rcv_isn && + if (TCP_SKB_CB(skb)->seq == tcp_rsk(req)->rcv_isn && flg == TCP_FLAG_SYN && !paws_reject) { /* @@ -959,7 +961,7 @@ struct sock *tcp_check_req(struct sock *sk,struct sk_buff *skb, * Invalid ACK: reset will be sent by listening socket */ if ((flg & TCP_FLAG_ACK) && - (TCP_SKB_CB(skb)->ack_seq != req->snt_isn+1)) + (TCP_SKB_CB(skb)->ack_seq != tcp_rsk(req)->snt_isn + 1)) return sk; /* Also, it would be not so bad idea to check rcv_tsecr, which @@ -970,7 +972,7 @@ struct sock *tcp_check_req(struct sock *sk,struct sk_buff *skb, /* RFC793: "first check sequence number". */ if (paws_reject || !tcp_in_window(TCP_SKB_CB(skb)->seq, TCP_SKB_CB(skb)->end_seq, - req->rcv_isn+1, req->rcv_isn+1+req->rcv_wnd)) { + tcp_rsk(req)->rcv_isn + 1, tcp_rsk(req)->rcv_isn + 1 + req->rcv_wnd)) { /* Out of window: send ACK and drop. */ if (!(flg & TCP_FLAG_RST)) req->class->send_ack(skb, req); @@ -981,12 +983,12 @@ struct sock *tcp_check_req(struct sock *sk,struct sk_buff *skb, /* In sequence, PAWS is OK. */ - if (tmp_opt.saw_tstamp && !after(TCP_SKB_CB(skb)->seq, req->rcv_isn+1)) + if (tmp_opt.saw_tstamp && !after(TCP_SKB_CB(skb)->seq, tcp_rsk(req)->rcv_isn + 1)) req->ts_recent = tmp_opt.rcv_tsval; - if (TCP_SKB_CB(skb)->seq == req->rcv_isn) { + if (TCP_SKB_CB(skb)->seq == tcp_rsk(req)->rcv_isn) { /* Truncate SYN, it is out of window starting - at req->rcv_isn+1. */ + at tcp_rsk(req)->rcv_isn + 1. */ flg &= ~TCP_FLAG_SYN; } @@ -1003,8 +1005,8 @@ struct sock *tcp_check_req(struct sock *sk,struct sk_buff *skb, return NULL; /* If TCP_DEFER_ACCEPT is set, drop bare ACK. */ - if (tp->defer_accept && TCP_SKB_CB(skb)->end_seq == req->rcv_isn+1) { - req->acked = 1; + if (tp->defer_accept && TCP_SKB_CB(skb)->end_seq == tcp_rsk(req)->rcv_isn + 1) { + inet_rsk(req)->acked = 1; return NULL; } @@ -1026,7 +1028,7 @@ struct sock *tcp_check_req(struct sock *sk,struct sk_buff *skb, listen_overflow: if (!sysctl_tcp_abort_on_overflow) { - req->acked = 1; + inet_rsk(req)->acked = 1; return NULL; } diff --git a/net/ipv4/tcp_output.c b/net/ipv4/tcp_output.c index fa24e7ae1f40..f3c8747caf91 100644 --- a/net/ipv4/tcp_output.c +++ b/net/ipv4/tcp_output.c @@ -1358,6 +1358,7 @@ int tcp_send_synack(struct sock *sk) struct sk_buff * tcp_make_synack(struct sock *sk, struct dst_entry *dst, struct open_request *req) { + struct inet_request_sock *ireq = inet_rsk(req); struct tcp_sock *tp = tcp_sk(sk); struct tcphdr *th; int tcp_header_size; @@ -1373,47 +1374,47 @@ struct sk_buff * tcp_make_synack(struct sock *sk, struct dst_entry *dst, skb->dst = dst_clone(dst); tcp_header_size = (sizeof(struct tcphdr) + TCPOLEN_MSS + - (req->tstamp_ok ? TCPOLEN_TSTAMP_ALIGNED : 0) + - (req->wscale_ok ? TCPOLEN_WSCALE_ALIGNED : 0) + + (ireq->tstamp_ok ? TCPOLEN_TSTAMP_ALIGNED : 0) + + (ireq->wscale_ok ? TCPOLEN_WSCALE_ALIGNED : 0) + /* SACK_PERM is in the place of NOP NOP of TS */ - ((req->sack_ok && !req->tstamp_ok) ? TCPOLEN_SACKPERM_ALIGNED : 0)); + ((ireq->sack_ok && !ireq->tstamp_ok) ? TCPOLEN_SACKPERM_ALIGNED : 0)); skb->h.th = th = (struct tcphdr *) skb_push(skb, tcp_header_size); memset(th, 0, sizeof(struct tcphdr)); th->syn = 1; th->ack = 1; if (dst->dev->features&NETIF_F_TSO) - req->ecn_ok = 0; + ireq->ecn_ok = 0; TCP_ECN_make_synack(req, th); th->source = inet_sk(sk)->sport; - th->dest = req->rmt_port; - TCP_SKB_CB(skb)->seq = req->snt_isn; + th->dest = ireq->rmt_port; + TCP_SKB_CB(skb)->seq = tcp_rsk(req)->snt_isn; TCP_SKB_CB(skb)->end_seq = TCP_SKB_CB(skb)->seq + 1; TCP_SKB_CB(skb)->sacked = 0; skb_shinfo(skb)->tso_segs = 1; skb_shinfo(skb)->tso_size = 0; th->seq = htonl(TCP_SKB_CB(skb)->seq); - th->ack_seq = htonl(req->rcv_isn + 1); + th->ack_seq = htonl(tcp_rsk(req)->rcv_isn + 1); if (req->rcv_wnd == 0) { /* ignored for retransmitted syns */ __u8 rcv_wscale; /* Set this up on the first call only */ req->window_clamp = tp->window_clamp ? : dst_metric(dst, RTAX_WINDOW); /* tcp_full_space because it is guaranteed to be the first packet */ tcp_select_initial_window(tcp_full_space(sk), - dst_metric(dst, RTAX_ADVMSS) - (req->tstamp_ok ? TCPOLEN_TSTAMP_ALIGNED : 0), + dst_metric(dst, RTAX_ADVMSS) - (ireq->tstamp_ok ? TCPOLEN_TSTAMP_ALIGNED : 0), &req->rcv_wnd, &req->window_clamp, - req->wscale_ok, + ireq->wscale_ok, &rcv_wscale); - req->rcv_wscale = rcv_wscale; + ireq->rcv_wscale = rcv_wscale; } /* RFC1323: The window in SYN & SYN/ACK segments is never scaled. */ th->window = htons(req->rcv_wnd); TCP_SKB_CB(skb)->when = tcp_time_stamp; - tcp_syn_build_options((__u32 *)(th + 1), dst_metric(dst, RTAX_ADVMSS), req->tstamp_ok, - req->sack_ok, req->wscale_ok, req->rcv_wscale, + tcp_syn_build_options((__u32 *)(th + 1), dst_metric(dst, RTAX_ADVMSS), ireq->tstamp_ok, + ireq->sack_ok, ireq->wscale_ok, ireq->rcv_wscale, TCP_SKB_CB(skb)->when, req->ts_recent); diff --git a/net/ipv4/tcp_timer.c b/net/ipv4/tcp_timer.c index 799ebe061e2c..ba30ca0aa6a3 100644 --- a/net/ipv4/tcp_timer.c +++ b/net/ipv4/tcp_timer.c @@ -513,7 +513,7 @@ static void tcp_synack_timer(struct sock *sk) while ((req = *reqp) != NULL) { if (time_after_eq(now, req->expires)) { if ((req->retrans < thresh || - (req->acked && req->retrans < max_retries)) + (inet_rsk(req)->acked && req->retrans < max_retries)) && !req->class->rtx_syn_ack(sk, req, NULL)) { unsigned long timeo; diff --git a/net/ipv6/tcp_ipv6.c b/net/ipv6/tcp_ipv6.c index 0f69e800a0ad..9199ad2fde0d 100644 --- a/net/ipv6/tcp_ipv6.c +++ b/net/ipv6/tcp_ipv6.c @@ -407,11 +407,13 @@ static struct open_request *tcp_v6_search_req(struct tcp_sock *tp, for (prev = &lopt->syn_table[tcp_v6_synq_hash(raddr, rport, lopt->hash_rnd)]; (req = *prev) != NULL; prev = &req->dl_next) { - if (req->rmt_port == rport && + const struct tcp6_request_sock *treq = tcp6_rsk(req); + + if (inet_rsk(req)->rmt_port == rport && req->class->family == AF_INET6 && - ipv6_addr_equal(&req->af.v6_req.rmt_addr, raddr) && - ipv6_addr_equal(&req->af.v6_req.loc_addr, laddr) && - (!req->af.v6_req.iif || req->af.v6_req.iif == iif)) { + ipv6_addr_equal(&treq->rmt_addr, raddr) && + ipv6_addr_equal(&treq->loc_addr, laddr) && + (!treq->iif || treq->iif == iif)) { BUG_TRAP(req->sk == NULL); *prevp = prev; return req; @@ -923,7 +925,7 @@ static void tcp_v6_err(struct sk_buff *skb, struct inet6_skb_parm *opt, */ BUG_TRAP(req->sk == NULL); - if (seq != req->snt_isn) { + if (seq != tcp_rsk(req)->snt_isn) { NET_INC_STATS_BH(LINUX_MIB_OUTOFWINDOWICMPS); goto out; } @@ -960,6 +962,7 @@ out: static int tcp_v6_send_synack(struct sock *sk, struct open_request *req, struct dst_entry *dst) { + struct tcp6_request_sock *treq = tcp6_rsk(req); struct ipv6_pinfo *np = inet6_sk(sk); struct sk_buff * skb; struct ipv6_txoptions *opt = NULL; @@ -969,19 +972,19 @@ static int tcp_v6_send_synack(struct sock *sk, struct open_request *req, memset(&fl, 0, sizeof(fl)); fl.proto = IPPROTO_TCP; - ipv6_addr_copy(&fl.fl6_dst, &req->af.v6_req.rmt_addr); - ipv6_addr_copy(&fl.fl6_src, &req->af.v6_req.loc_addr); + ipv6_addr_copy(&fl.fl6_dst, &treq->rmt_addr); + ipv6_addr_copy(&fl.fl6_src, &treq->loc_addr); fl.fl6_flowlabel = 0; - fl.oif = req->af.v6_req.iif; - fl.fl_ip_dport = req->rmt_port; + fl.oif = treq->iif; + fl.fl_ip_dport = inet_rsk(req)->rmt_port; fl.fl_ip_sport = inet_sk(sk)->sport; if (dst == NULL) { opt = np->opt; if (opt == NULL && np->rxopt.bits.srcrt == 2 && - req->af.v6_req.pktopts) { - struct sk_buff *pktopts = req->af.v6_req.pktopts; + treq->pktopts) { + struct sk_buff *pktopts = treq->pktopts; struct inet6_skb_parm *rxopt = IP6CB(pktopts); if (rxopt->srcrt) opt = ipv6_invert_rthdr(sk, (struct ipv6_rt_hdr*)(pktopts->nh.raw + rxopt->srcrt)); @@ -1008,10 +1011,10 @@ static int tcp_v6_send_synack(struct sock *sk, struct open_request *req, struct tcphdr *th = skb->h.th; th->check = tcp_v6_check(th, skb->len, - &req->af.v6_req.loc_addr, &req->af.v6_req.rmt_addr, + &treq->loc_addr, &treq->rmt_addr, csum_partial((char *)th, skb->len, skb->csum)); - ipv6_addr_copy(&fl.fl6_dst, &req->af.v6_req.rmt_addr); + ipv6_addr_copy(&fl.fl6_dst, &treq->rmt_addr); err = ip6_xmit(sk, skb, &fl, opt, 0); if (err == NET_XMIT_CN) err = 0; @@ -1026,12 +1029,13 @@ done: static void tcp_v6_or_free(struct open_request *req) { - if (req->af.v6_req.pktopts) - kfree_skb(req->af.v6_req.pktopts); + if (tcp6_rsk(req)->pktopts) + kfree_skb(tcp6_rsk(req)->pktopts); } static struct or_calltable or_ipv6 = { .family = AF_INET6, + .obj_size = sizeof(struct tcp6_request_sock), .rtx_syn_ack = tcp_v6_send_synack, .send_ack = tcp_v6_or_send_ack, .destructor = tcp_v6_or_free, @@ -1221,7 +1225,7 @@ static void tcp_v6_timewait_ack(struct sock *sk, struct sk_buff *skb) static void tcp_v6_or_send_ack(struct sk_buff *skb, struct open_request *req) { - tcp_v6_send_ack(skb, req->snt_isn+1, req->rcv_isn+1, req->rcv_wnd, req->ts_recent); + tcp_v6_send_ack(skb, tcp_rsk(req)->snt_isn + 1, tcp_rsk(req)->rcv_isn + 1, req->rcv_wnd, req->ts_recent); } @@ -1264,7 +1268,7 @@ static void tcp_v6_synq_add(struct sock *sk, struct open_request *req) { struct tcp_sock *tp = tcp_sk(sk); struct tcp_listen_opt *lopt = tp->listen_opt; - u32 h = tcp_v6_synq_hash(&req->af.v6_req.rmt_addr, req->rmt_port, lopt->hash_rnd); + u32 h = tcp_v6_synq_hash(&tcp6_rsk(req)->rmt_addr, inet_rsk(req)->rmt_port, lopt->hash_rnd); req->sk = NULL; req->expires = jiffies + TCP_TIMEOUT_INIT; @@ -1284,6 +1288,7 @@ static void tcp_v6_synq_add(struct sock *sk, struct open_request *req) */ static int tcp_v6_conn_request(struct sock *sk, struct sk_buff *skb) { + struct tcp6_request_sock *treq; struct ipv6_pinfo *np = inet6_sk(sk); struct tcp_options_received tmp_opt; struct tcp_sock *tp = tcp_sk(sk); @@ -1308,7 +1313,7 @@ static int tcp_v6_conn_request(struct sock *sk, struct sk_buff *skb) if (sk_acceptq_is_full(sk) && tcp_synq_young(sk) > 1) goto drop; - req = tcp_openreq_alloc(); + req = tcp_openreq_alloc(&or_ipv6); if (req == NULL) goto drop; @@ -1321,28 +1326,28 @@ static int tcp_v6_conn_request(struct sock *sk, struct sk_buff *skb) tmp_opt.tstamp_ok = tmp_opt.saw_tstamp; tcp_openreq_init(req, &tmp_opt, skb); - req->class = &or_ipv6; - ipv6_addr_copy(&req->af.v6_req.rmt_addr, &skb->nh.ipv6h->saddr); - ipv6_addr_copy(&req->af.v6_req.loc_addr, &skb->nh.ipv6h->daddr); + treq = tcp6_rsk(req); + ipv6_addr_copy(&treq->rmt_addr, &skb->nh.ipv6h->saddr); + ipv6_addr_copy(&treq->loc_addr, &skb->nh.ipv6h->daddr); TCP_ECN_create_request(req, skb->h.th); - req->af.v6_req.pktopts = NULL; + treq->pktopts = NULL; if (ipv6_opt_accepted(sk, skb) || np->rxopt.bits.rxinfo || np->rxopt.bits.rxhlim) { atomic_inc(&skb->users); - req->af.v6_req.pktopts = skb; + treq->pktopts = skb; } - req->af.v6_req.iif = sk->sk_bound_dev_if; + treq->iif = sk->sk_bound_dev_if; /* So that link locals have meaning */ if (!sk->sk_bound_dev_if && - ipv6_addr_type(&req->af.v6_req.rmt_addr) & IPV6_ADDR_LINKLOCAL) - req->af.v6_req.iif = tcp_v6_iif(skb); + ipv6_addr_type(&treq->rmt_addr) & IPV6_ADDR_LINKLOCAL) + treq->iif = tcp_v6_iif(skb); if (isn == 0) isn = tcp_v6_init_sequence(sk,skb); - req->snt_isn = isn; + tcp_rsk(req)->snt_isn = isn; if (tcp_v6_send_synack(sk, req, NULL)) goto drop; @@ -1363,6 +1368,7 @@ static struct sock * tcp_v6_syn_recv_sock(struct sock *sk, struct sk_buff *skb, struct open_request *req, struct dst_entry *dst) { + struct tcp6_request_sock *treq = tcp6_rsk(req); struct ipv6_pinfo *newnp, *np = inet6_sk(sk); struct tcp6_sock *newtcp6sk; struct inet_sock *newinet; @@ -1426,10 +1432,10 @@ static struct sock * tcp_v6_syn_recv_sock(struct sock *sk, struct sk_buff *skb, goto out_overflow; if (np->rxopt.bits.srcrt == 2 && - opt == NULL && req->af.v6_req.pktopts) { - struct inet6_skb_parm *rxopt = IP6CB(req->af.v6_req.pktopts); + opt == NULL && treq->pktopts) { + struct inet6_skb_parm *rxopt = IP6CB(treq->pktopts); if (rxopt->srcrt) - opt = ipv6_invert_rthdr(sk, (struct ipv6_rt_hdr*)(req->af.v6_req.pktopts->nh.raw+rxopt->srcrt)); + opt = ipv6_invert_rthdr(sk, (struct ipv6_rt_hdr *)(treq->pktopts->nh.raw + rxopt->srcrt)); } if (dst == NULL) { @@ -1438,16 +1444,16 @@ static struct sock * tcp_v6_syn_recv_sock(struct sock *sk, struct sk_buff *skb, memset(&fl, 0, sizeof(fl)); fl.proto = IPPROTO_TCP; - ipv6_addr_copy(&fl.fl6_dst, &req->af.v6_req.rmt_addr); + ipv6_addr_copy(&fl.fl6_dst, &treq->rmt_addr); if (opt && opt->srcrt) { struct rt0_hdr *rt0 = (struct rt0_hdr *) opt->srcrt; ipv6_addr_copy(&final, &fl.fl6_dst); ipv6_addr_copy(&fl.fl6_dst, rt0->addr); final_p = &final; } - ipv6_addr_copy(&fl.fl6_src, &req->af.v6_req.loc_addr); + ipv6_addr_copy(&fl.fl6_src, &treq->loc_addr); fl.oif = sk->sk_bound_dev_if; - fl.fl_ip_dport = req->rmt_port; + fl.fl_ip_dport = inet_rsk(req)->rmt_port; fl.fl_ip_sport = inet_sk(sk)->sport; if (ip6_dst_lookup(sk, &dst, &fl)) @@ -1482,10 +1488,10 @@ static struct sock * tcp_v6_syn_recv_sock(struct sock *sk, struct sk_buff *skb, memcpy(newnp, np, sizeof(struct ipv6_pinfo)); - ipv6_addr_copy(&newnp->daddr, &req->af.v6_req.rmt_addr); - ipv6_addr_copy(&newnp->saddr, &req->af.v6_req.loc_addr); - ipv6_addr_copy(&newnp->rcv_saddr, &req->af.v6_req.loc_addr); - newsk->sk_bound_dev_if = req->af.v6_req.iif; + ipv6_addr_copy(&newnp->daddr, &treq->rmt_addr); + ipv6_addr_copy(&newnp->saddr, &treq->loc_addr); + ipv6_addr_copy(&newnp->rcv_saddr, &treq->loc_addr); + newsk->sk_bound_dev_if = treq->iif; /* Now IPv6 options... @@ -1498,11 +1504,10 @@ static struct sock * tcp_v6_syn_recv_sock(struct sock *sk, struct sk_buff *skb, /* Clone pktoptions received with SYN */ newnp->pktoptions = NULL; - if (req->af.v6_req.pktopts) { - newnp->pktoptions = skb_clone(req->af.v6_req.pktopts, - GFP_ATOMIC); - kfree_skb(req->af.v6_req.pktopts); - req->af.v6_req.pktopts = NULL; + if (treq->pktopts != NULL) { + newnp->pktoptions = skb_clone(treq->pktopts, GFP_ATOMIC); + kfree_skb(treq->pktopts); + treq->pktopts = NULL; if (newnp->pktoptions) skb_set_owner_r(newnp->pktoptions, newsk); } @@ -2058,8 +2063,8 @@ static void get_openreq6(struct seq_file *seq, if (ttd < 0) ttd = 0; - src = &req->af.v6_req.loc_addr; - dest = &req->af.v6_req.rmt_addr; + src = &tcp6_rsk(req)->loc_addr; + dest = &tcp6_rsk(req)->rmt_addr; seq_printf(seq, "%4d: %08X%08X%08X%08X:%04X %08X%08X%08X%08X:%04X " "%02X %08X:%08X %02X:%08lX %08X %5d %8d %d %d %p\n", @@ -2069,7 +2074,7 @@ static void get_openreq6(struct seq_file *seq, ntohs(inet_sk(sk)->sport), dest->s6_addr32[0], dest->s6_addr32[1], dest->s6_addr32[2], dest->s6_addr32[3], - ntohs(req->rmt_port), + ntohs(inet_rsk(req)->rmt_port), TCP_SYN_RECV, 0,0, /* could print option size, but that is af dependent. */ 1, /* timers active (only the expire timer) */ @@ -2239,6 +2244,7 @@ struct proto tcpv6_prot = { .sysctl_rmem = sysctl_tcp_rmem, .max_header = MAX_TCP_HEADER, .obj_size = sizeof(struct tcp6_sock), + .rsk_prot = &or_ipv6, }; static struct inet6_protocol tcpv6_protocol = { -- cgit v1.2.3 From 60236fdd08b2169045a3bbfc5ffe1576e6c3c17b Mon Sep 17 00:00:00 2001 From: Arnaldo Carvalho de Melo Date: Sat, 18 Jun 2005 22:47:21 -0700 Subject: [NET] Rename open_request to request_sock Ok, this one just renames some stuff to have a better namespace and to dissassociate it from TCP: struct open_request -> struct request_sock tcp_openreq_alloc -> reqsk_alloc tcp_openreq_free -> reqsk_free tcp_openreq_fastfree -> __reqsk_free With this most of the infrastructure closely resembles a struct sock methods subset. Signed-off-by: Arnaldo Carvalho de Melo Signed-off-by: David S. Miller --- include/linux/ip.h | 4 ++-- include/linux/ipv6.h | 2 +- include/linux/tcp.h | 6 ++--- include/net/request_sock.h | 34 ++++++++++++++-------------- include/net/sock.h | 4 ++-- include/net/tcp.h | 30 ++++++++++++------------- include/net/tcp_ecn.h | 6 ++--- net/ipv4/syncookies.c | 12 +++++----- net/ipv4/tcp.c | 12 +++++----- net/ipv4/tcp_diag.c | 4 ++-- net/ipv4/tcp_ipv4.c | 56 +++++++++++++++++++++++----------------------- net/ipv4/tcp_minisocks.c | 14 ++++++------ net/ipv4/tcp_output.c | 2 +- net/ipv4/tcp_timer.c | 6 ++--- net/ipv6/tcp_ipv6.c | 42 +++++++++++++++++----------------- 15 files changed, 117 insertions(+), 117 deletions(-) (limited to 'include/linux') diff --git a/include/linux/ip.h b/include/linux/ip.h index d5b7c907204e..31e7cedd9f84 100644 --- a/include/linux/ip.h +++ b/include/linux/ip.h @@ -109,7 +109,7 @@ struct ip_options { #define optlength(opt) (sizeof(struct ip_options) + opt->optlen) struct inet_request_sock { - struct open_request req; + struct request_sock req; u32 loc_addr; u32 rmt_addr; u16 rmt_port; @@ -123,7 +123,7 @@ struct inet_request_sock { struct ip_options *opt; }; -static inline struct inet_request_sock *inet_rsk(const struct open_request *sk) +static inline struct inet_request_sock *inet_rsk(const struct request_sock *sk) { return (struct inet_request_sock *)sk; } diff --git a/include/linux/ipv6.h b/include/linux/ipv6.h index 98acdbf3d446..6fcd6a0ade24 100644 --- a/include/linux/ipv6.h +++ b/include/linux/ipv6.h @@ -201,7 +201,7 @@ struct tcp6_request_sock { int iif; }; -static inline struct tcp6_request_sock *tcp6_rsk(const struct open_request *sk) +static inline struct tcp6_request_sock *tcp6_rsk(const struct request_sock *sk) { return (struct tcp6_request_sock *)sk; } diff --git a/include/linux/tcp.h b/include/linux/tcp.h index 86771b37b80d..fb54292a15aa 100644 --- a/include/linux/tcp.h +++ b/include/linux/tcp.h @@ -236,7 +236,7 @@ struct tcp_request_sock { __u32 snt_isn; }; -static inline struct tcp_request_sock *tcp_rsk(const struct open_request *req) +static inline struct tcp_request_sock *tcp_rsk(const struct request_sock *req) { return (struct tcp_request_sock *)req; } @@ -393,8 +393,8 @@ struct tcp_sock { struct tcp_listen_opt *listen_opt; /* FIFO of established children */ - struct open_request *accept_queue; - struct open_request *accept_queue_tail; + struct request_sock *accept_queue; + struct request_sock *accept_queue_tail; unsigned int keepalive_time; /* time before keep alive takes place */ unsigned int keepalive_intvl; /* time interval between keep alive probes */ diff --git a/include/net/request_sock.h b/include/net/request_sock.h index 9502f5587931..08a8fd1d1610 100644 --- a/include/net/request_sock.h +++ b/include/net/request_sock.h @@ -19,28 +19,28 @@ #include #include -struct open_request; +struct request_sock; struct sk_buff; struct dst_entry; struct proto; -struct or_calltable { +struct request_sock_ops { int family; kmem_cache_t *slab; int obj_size; int (*rtx_syn_ack)(struct sock *sk, - struct open_request *req, + struct request_sock *req, struct dst_entry *dst); void (*send_ack)(struct sk_buff *skb, - struct open_request *req); + struct request_sock *req); void (*send_reset)(struct sk_buff *skb); - void (*destructor)(struct open_request *req); + void (*destructor)(struct request_sock *req); }; -/* struct open_request - mini sock to represent a connection request +/* struct request_sock - mini sock to represent a connection request */ -struct open_request { - struct open_request *dl_next; /* Must be first member! */ +struct request_sock { + struct request_sock *dl_next; /* Must be first member! */ u16 mss; u8 retrans; u8 __pad; @@ -49,29 +49,29 @@ struct open_request { u32 rcv_wnd; /* rcv_wnd offered first time */ u32 ts_recent; unsigned long expires; - struct or_calltable *class; + struct request_sock_ops *rsk_ops; struct sock *sk; }; -static inline struct open_request *tcp_openreq_alloc(struct or_calltable *class) +static inline struct request_sock *reqsk_alloc(struct request_sock_ops *ops) { - struct open_request *req = kmem_cache_alloc(class->slab, SLAB_ATOMIC); + struct request_sock *req = kmem_cache_alloc(ops->slab, SLAB_ATOMIC); if (req != NULL) - req->class = class; + req->rsk_ops = ops; return req; } -static inline void tcp_openreq_fastfree(struct open_request *req) +static inline void __reqsk_free(struct request_sock *req) { - kmem_cache_free(req->class->slab, req); + kmem_cache_free(req->rsk_ops->slab, req); } -static inline void tcp_openreq_free(struct open_request *req) +static inline void reqsk_free(struct request_sock *req) { - req->class->destructor(req); - tcp_openreq_fastfree(req); + req->rsk_ops->destructor(req); + __reqsk_free(req); } #endif /* _REQUEST_SOCK_H */ diff --git a/include/net/sock.h b/include/net/sock.h index 6919276af8af..e593af5b1ecc 100644 --- a/include/net/sock.h +++ b/include/net/sock.h @@ -484,7 +484,7 @@ extern void sk_stream_kill_queues(struct sock *sk); extern int sk_wait_data(struct sock *sk, long *timeo); -struct or_calltable; +struct request_sock_ops; /* Networking protocol blocks we attach to sockets. * socket layer -> transport layer interface @@ -549,7 +549,7 @@ struct proto { kmem_cache_t *slab; unsigned int obj_size; - struct or_calltable *rsk_prot; + struct request_sock_ops *rsk_prot; struct module *owner; diff --git a/include/net/tcp.h b/include/net/tcp.h index d438ba566b89..6663086a5e35 100644 --- a/include/net/tcp.h +++ b/include/net/tcp.h @@ -641,7 +641,7 @@ struct tcp_func { struct sock * (*syn_recv_sock) (struct sock *sk, struct sk_buff *skb, - struct open_request *req, + struct request_sock *req, struct dst_entry *dst); int (*remember_stamp) (struct sock *sk); @@ -785,8 +785,8 @@ extern enum tcp_tw_status tcp_timewait_state_process(struct tcp_tw_bucket *tw, unsigned len); extern struct sock * tcp_check_req(struct sock *sk,struct sk_buff *skb, - struct open_request *req, - struct open_request **prev); + struct request_sock *req, + struct request_sock **prev); extern int tcp_child_process(struct sock *parent, struct sock *child, struct sk_buff *skb); @@ -836,12 +836,12 @@ extern int tcp_v4_conn_request(struct sock *sk, struct sk_buff *skb); extern struct sock * tcp_create_openreq_child(struct sock *sk, - struct open_request *req, + struct request_sock *req, struct sk_buff *skb); extern struct sock * tcp_v4_syn_recv_sock(struct sock *sk, struct sk_buff *skb, - struct open_request *req, + struct request_sock *req, struct dst_entry *dst); extern int tcp_v4_do_rcv(struct sock *sk, @@ -855,7 +855,7 @@ extern int tcp_connect(struct sock *sk); extern struct sk_buff * tcp_make_synack(struct sock *sk, struct dst_entry *dst, - struct open_request *req); + struct request_sock *req); extern int tcp_disconnect(struct sock *sk, int flags); @@ -1683,7 +1683,7 @@ static inline int tcp_full_space(const struct sock *sk) return tcp_win_from_space(sk->sk_rcvbuf); } -static inline void tcp_acceptq_queue(struct sock *sk, struct open_request *req, +static inline void tcp_acceptq_queue(struct sock *sk, struct request_sock *req, struct sock *child) { struct tcp_sock *tp = tcp_sk(sk); @@ -1707,11 +1707,11 @@ struct tcp_listen_opt int qlen_young; int clock_hand; u32 hash_rnd; - struct open_request *syn_table[TCP_SYNQ_HSIZE]; + struct request_sock *syn_table[TCP_SYNQ_HSIZE]; }; static inline void -tcp_synq_removed(struct sock *sk, struct open_request *req) +tcp_synq_removed(struct sock *sk, struct request_sock *req) { struct tcp_listen_opt *lopt = tcp_sk(sk)->listen_opt; @@ -1745,23 +1745,23 @@ static inline int tcp_synq_is_full(struct sock *sk) return tcp_synq_len(sk) >> tcp_sk(sk)->listen_opt->max_qlen_log; } -static inline void tcp_synq_unlink(struct tcp_sock *tp, struct open_request *req, - struct open_request **prev) +static inline void tcp_synq_unlink(struct tcp_sock *tp, struct request_sock *req, + struct request_sock **prev) { write_lock(&tp->syn_wait_lock); *prev = req->dl_next; write_unlock(&tp->syn_wait_lock); } -static inline void tcp_synq_drop(struct sock *sk, struct open_request *req, - struct open_request **prev) +static inline void tcp_synq_drop(struct sock *sk, struct request_sock *req, + struct request_sock **prev) { tcp_synq_unlink(tcp_sk(sk), req, prev); tcp_synq_removed(sk, req); - tcp_openreq_free(req); + reqsk_free(req); } -static __inline__ void tcp_openreq_init(struct open_request *req, +static __inline__ void tcp_openreq_init(struct request_sock *req, struct tcp_options_received *rx_opt, struct sk_buff *skb) { diff --git a/include/net/tcp_ecn.h b/include/net/tcp_ecn.h index 94ad970e844a..64980ee8c92a 100644 --- a/include/net/tcp_ecn.h +++ b/include/net/tcp_ecn.h @@ -39,7 +39,7 @@ static inline void TCP_ECN_send_syn(struct sock *sk, struct tcp_sock *tp, } static __inline__ void -TCP_ECN_make_synack(struct open_request *req, struct tcphdr *th) +TCP_ECN_make_synack(struct request_sock *req, struct tcphdr *th) { if (inet_rsk(req)->ecn_ok) th->ece = 1; @@ -112,13 +112,13 @@ static inline int TCP_ECN_rcv_ecn_echo(struct tcp_sock *tp, struct tcphdr *th) } static inline void TCP_ECN_openreq_child(struct tcp_sock *tp, - struct open_request *req) + struct request_sock *req) { tp->ecn_flags = inet_rsk(req)->ecn_ok ? TCP_ECN_OK : 0; } static __inline__ void -TCP_ECN_create_request(struct open_request *req, struct tcphdr *th) +TCP_ECN_create_request(struct request_sock *req, struct tcphdr *th) { if (sysctl_tcp_ecn && th->ece && th->cwr) inet_rsk(req)->ecn_ok = 1; diff --git a/net/ipv4/syncookies.c b/net/ipv4/syncookies.c index dd47e6da6fb3..72d014442185 100644 --- a/net/ipv4/syncookies.c +++ b/net/ipv4/syncookies.c @@ -169,10 +169,10 @@ static inline int cookie_check(struct sk_buff *skb, __u32 cookie) return mssind < NUM_MSS ? msstab[mssind] + 1 : 0; } -extern struct or_calltable or_ipv4; +extern struct request_sock_ops tcp_request_sock_ops; static inline struct sock *get_cookie_sock(struct sock *sk, struct sk_buff *skb, - struct open_request *req, + struct request_sock *req, struct dst_entry *dst) { struct tcp_sock *tp = tcp_sk(sk); @@ -182,7 +182,7 @@ static inline struct sock *get_cookie_sock(struct sock *sk, struct sk_buff *skb, if (child) tcp_acceptq_queue(sk, req, child); else - tcp_openreq_free(req); + reqsk_free(req); return child; } @@ -195,7 +195,7 @@ struct sock *cookie_v4_check(struct sock *sk, struct sk_buff *skb, struct tcp_sock *tp = tcp_sk(sk); __u32 cookie = ntohl(skb->h.th->ack_seq) - 1; struct sock *ret = sk; - struct open_request *req; + struct request_sock *req; int mss; struct rtable *rt; __u8 rcv_wscale; @@ -212,7 +212,7 @@ struct sock *cookie_v4_check(struct sock *sk, struct sk_buff *skb, NET_INC_STATS_BH(LINUX_MIB_SYNCOOKIESRECV); ret = NULL; - req = tcp_openreq_alloc(&or_ipv4); /* for safety */ + req = reqsk_alloc(&tcp_request_sock_ops); /* for safety */ if (!req) goto out; @@ -262,7 +262,7 @@ struct sock *cookie_v4_check(struct sock *sk, struct sk_buff *skb, { .sport = skb->h.th->dest, .dport = skb->h.th->source } } }; if (ip_route_output_key(&rt, &fl)) { - tcp_openreq_free(req); + reqsk_free(req); goto out; } } diff --git a/net/ipv4/tcp.c b/net/ipv4/tcp.c index a3cabfa2022a..1c29feb6b35f 100644 --- a/net/ipv4/tcp.c +++ b/net/ipv4/tcp.c @@ -516,8 +516,8 @@ static void tcp_listen_stop (struct sock *sk) { struct tcp_sock *tp = tcp_sk(sk); struct tcp_listen_opt *lopt = tp->listen_opt; - struct open_request *acc_req = tp->accept_queue; - struct open_request *req; + struct request_sock *acc_req = tp->accept_queue; + struct request_sock *req; int i; tcp_delete_keepalive_timer(sk); @@ -533,7 +533,7 @@ static void tcp_listen_stop (struct sock *sk) while ((req = lopt->syn_table[i]) != NULL) { lopt->syn_table[i] = req->dl_next; lopt->qlen--; - tcp_openreq_free(req); + reqsk_free(req); /* Following specs, it would be better either to send FIN * (and enter FIN-WAIT-1, it is normal close) @@ -573,7 +573,7 @@ static void tcp_listen_stop (struct sock *sk) sock_put(child); sk_acceptq_removed(sk); - tcp_openreq_fastfree(req); + __reqsk_free(req); } BUG_TRAP(!sk->sk_ack_backlog); } @@ -1894,7 +1894,7 @@ static int wait_for_connect(struct sock *sk, long timeo) struct sock *tcp_accept(struct sock *sk, int flags, int *err) { struct tcp_sock *tp = tcp_sk(sk); - struct open_request *req; + struct request_sock *req; struct sock *newsk; int error; @@ -1927,7 +1927,7 @@ struct sock *tcp_accept(struct sock *sk, int flags, int *err) newsk = req->sk; sk_acceptq_removed(sk); - tcp_openreq_fastfree(req); + __reqsk_free(req); BUG_TRAP(newsk->sk_state != TCP_SYN_RECV); release_sock(sk); return newsk; diff --git a/net/ipv4/tcp_diag.c b/net/ipv4/tcp_diag.c index 700ff2413588..67277800d0c1 100644 --- a/net/ipv4/tcp_diag.c +++ b/net/ipv4/tcp_diag.c @@ -455,7 +455,7 @@ static int tcpdiag_dump_sock(struct sk_buff *skb, struct sock *sk, } static int tcpdiag_fill_req(struct sk_buff *skb, struct sock *sk, - struct open_request *req, + struct request_sock *req, u32 pid, u32 seq) { const struct inet_request_sock *ireq = inet_rsk(req); @@ -542,7 +542,7 @@ static int tcpdiag_dump_reqs(struct sk_buff *skb, struct sock *sk, } for (j = s_j; j < TCP_SYNQ_HSIZE; j++) { - struct open_request *req, *head = lopt->syn_table[j]; + struct request_sock *req, *head = lopt->syn_table[j]; reqnum = 0; for (req = head; req; reqnum++, req = req->dl_next) { diff --git a/net/ipv4/tcp_ipv4.c b/net/ipv4/tcp_ipv4.c index e156be90df14..95528a75a63d 100644 --- a/net/ipv4/tcp_ipv4.c +++ b/net/ipv4/tcp_ipv4.c @@ -36,7 +36,7 @@ * ACK bit. * Andi Kleen : Implemented fast path mtu discovery. * Fixed many serious bugs in the - * open_request handling and moved + * request_sock handling and moved * most of it into the af independent code. * Added tail drop and some other bugfixes. * Added new listen sematics. @@ -869,13 +869,13 @@ static __inline__ u32 tcp_v4_synq_hash(u32 raddr, u16 rport, u32 rnd) return (jhash_2words(raddr, (u32) rport, rnd) & (TCP_SYNQ_HSIZE - 1)); } -static struct open_request *tcp_v4_search_req(struct tcp_sock *tp, - struct open_request ***prevp, +static struct request_sock *tcp_v4_search_req(struct tcp_sock *tp, + struct request_sock ***prevp, __u16 rport, __u32 raddr, __u32 laddr) { struct tcp_listen_opt *lopt = tp->listen_opt; - struct open_request *req, **prev; + struct request_sock *req, **prev; for (prev = &lopt->syn_table[tcp_v4_synq_hash(raddr, rport, lopt->hash_rnd)]; (req = *prev) != NULL; @@ -885,7 +885,7 @@ static struct open_request *tcp_v4_search_req(struct tcp_sock *tp, if (ireq->rmt_port == rport && ireq->rmt_addr == raddr && ireq->loc_addr == laddr && - TCP_INET_FAMILY(req->class->family)) { + TCP_INET_FAMILY(req->rsk_ops->family)) { BUG_TRAP(!req->sk); *prevp = prev; break; @@ -895,7 +895,7 @@ static struct open_request *tcp_v4_search_req(struct tcp_sock *tp, return req; } -static void tcp_v4_synq_add(struct sock *sk, struct open_request *req) +static void tcp_v4_synq_add(struct sock *sk, struct request_sock *req) { struct tcp_sock *tp = tcp_sk(sk); struct tcp_listen_opt *lopt = tp->listen_opt; @@ -1052,7 +1052,7 @@ void tcp_v4_err(struct sk_buff *skb, u32 info) } switch (sk->sk_state) { - struct open_request *req, **prev; + struct request_sock *req, **prev; case TCP_LISTEN: if (sock_owned_by_user(sk)) goto out; @@ -1256,14 +1256,14 @@ static void tcp_v4_timewait_ack(struct sock *sk, struct sk_buff *skb) tcp_tw_put(tw); } -static void tcp_v4_or_send_ack(struct sk_buff *skb, struct open_request *req) +static void tcp_v4_reqsk_send_ack(struct sk_buff *skb, struct request_sock *req) { tcp_v4_send_ack(skb, tcp_rsk(req)->snt_isn + 1, tcp_rsk(req)->rcv_isn + 1, req->rcv_wnd, req->ts_recent); } static struct dst_entry* tcp_v4_route_req(struct sock *sk, - struct open_request *req) + struct request_sock *req) { struct rtable *rt; const struct inet_request_sock *ireq = inet_rsk(req); @@ -1294,10 +1294,10 @@ static struct dst_entry* tcp_v4_route_req(struct sock *sk, /* * Send a SYN-ACK after having received an ACK. - * This still operates on a open_request only, not on a big + * This still operates on a request_sock only, not on a big * socket. */ -static int tcp_v4_send_synack(struct sock *sk, struct open_request *req, +static int tcp_v4_send_synack(struct sock *sk, struct request_sock *req, struct dst_entry *dst) { const struct inet_request_sock *ireq = inet_rsk(req); @@ -1332,9 +1332,9 @@ out: } /* - * IPv4 open_request destructor. + * IPv4 request_sock destructor. */ -static void tcp_v4_or_free(struct open_request *req) +static void tcp_v4_reqsk_destructor(struct request_sock *req) { if (inet_rsk(req)->opt) kfree(inet_rsk(req)->opt); @@ -1353,7 +1353,7 @@ static inline void syn_flood_warning(struct sk_buff *skb) } /* - * Save and compile IPv4 options into the open_request if needed. + * Save and compile IPv4 options into the request_sock if needed. */ static inline struct ip_options *tcp_v4_save_options(struct sock *sk, struct sk_buff *skb) @@ -1389,12 +1389,12 @@ static inline struct ip_options *tcp_v4_save_options(struct sock *sk, */ int sysctl_max_syn_backlog = 256; -struct or_calltable or_ipv4 = { +struct request_sock_ops tcp_request_sock_ops = { .family = PF_INET, .obj_size = sizeof(struct tcp_request_sock), .rtx_syn_ack = tcp_v4_send_synack, - .send_ack = tcp_v4_or_send_ack, - .destructor = tcp_v4_or_free, + .send_ack = tcp_v4_reqsk_send_ack, + .destructor = tcp_v4_reqsk_destructor, .send_reset = tcp_v4_send_reset, }; @@ -1402,7 +1402,7 @@ int tcp_v4_conn_request(struct sock *sk, struct sk_buff *skb) { struct inet_request_sock *ireq; struct tcp_options_received tmp_opt; - struct open_request *req; + struct request_sock *req; __u32 saddr = skb->nh.iph->saddr; __u32 daddr = skb->nh.iph->daddr; __u32 isn = TCP_SKB_CB(skb)->when; @@ -1439,7 +1439,7 @@ int tcp_v4_conn_request(struct sock *sk, struct sk_buff *skb) if (sk_acceptq_is_full(sk) && tcp_synq_young(sk) > 1) goto drop; - req = tcp_openreq_alloc(&or_ipv4); + req = reqsk_alloc(&tcp_request_sock_ops); if (!req) goto drop; @@ -1535,14 +1535,14 @@ int tcp_v4_conn_request(struct sock *sk, struct sk_buff *skb) goto drop_and_free; if (want_cookie) { - tcp_openreq_free(req); + reqsk_free(req); } else { tcp_v4_synq_add(sk, req); } return 0; drop_and_free: - tcp_openreq_free(req); + reqsk_free(req); drop: TCP_INC_STATS_BH(TCP_MIB_ATTEMPTFAILS); return 0; @@ -1554,7 +1554,7 @@ drop: * now create the new socket. */ struct sock *tcp_v4_syn_recv_sock(struct sock *sk, struct sk_buff *skb, - struct open_request *req, + struct request_sock *req, struct dst_entry *dst) { struct inet_request_sock *ireq; @@ -1613,9 +1613,9 @@ static struct sock *tcp_v4_hnd_req(struct sock *sk, struct sk_buff *skb) struct iphdr *iph = skb->nh.iph; struct tcp_sock *tp = tcp_sk(sk); struct sock *nsk; - struct open_request **prev; + struct request_sock **prev; /* Find possible connection requests. */ - struct open_request *req = tcp_v4_search_req(tp, &prev, th->source, + struct request_sock *req = tcp_v4_search_req(tp, &prev, th->source, iph->saddr, iph->daddr); if (req) return tcp_check_req(sk, skb, req, prev); @@ -2152,13 +2152,13 @@ static void *listening_get_next(struct seq_file *seq, void *cur) ++st->num; if (st->state == TCP_SEQ_STATE_OPENREQ) { - struct open_request *req = cur; + struct request_sock *req = cur; tp = tcp_sk(st->syn_wait_sk); req = req->dl_next; while (1) { while (req) { - if (req->class->family == st->family) { + if (req->rsk_ops->family == st->family) { cur = req; goto out; } @@ -2459,7 +2459,7 @@ void tcp_proc_unregister(struct tcp_seq_afinfo *afinfo) memset(afinfo->seq_fops, 0, sizeof(*afinfo->seq_fops)); } -static void get_openreq4(struct sock *sk, struct open_request *req, +static void get_openreq4(struct sock *sk, struct request_sock *req, char *tmpbuf, int i, int uid) { const struct inet_request_sock *ireq = inet_rsk(req); @@ -2627,7 +2627,7 @@ struct proto tcp_prot = { .sysctl_rmem = sysctl_tcp_rmem, .max_header = MAX_TCP_HEADER, .obj_size = sizeof(struct tcp_sock), - .rsk_prot = &or_ipv4, + .rsk_prot = &tcp_request_sock_ops, }; diff --git a/net/ipv4/tcp_minisocks.c b/net/ipv4/tcp_minisocks.c index 1037401c7cc8..0e6d525a8341 100644 --- a/net/ipv4/tcp_minisocks.c +++ b/net/ipv4/tcp_minisocks.c @@ -684,7 +684,7 @@ out: * Actually, we could lots of memory writes here. tp of listening * socket contains all necessary default parameters. */ -struct sock *tcp_create_openreq_child(struct sock *sk, struct open_request *req, struct sk_buff *skb) +struct sock *tcp_create_openreq_child(struct sock *sk, struct request_sock *req, struct sk_buff *skb) { /* allocate the newsk from the same slab of the master sock, * if not, at sk_free time we'll try to free it from the wrong @@ -853,12 +853,12 @@ struct sock *tcp_create_openreq_child(struct sock *sk, struct open_request *req, /* * Process an incoming packet for SYN_RECV sockets represented - * as an open_request. + * as a request_sock. */ struct sock *tcp_check_req(struct sock *sk,struct sk_buff *skb, - struct open_request *req, - struct open_request **prev) + struct request_sock *req, + struct request_sock **prev) { struct tcphdr *th = skb->h.th; struct tcp_sock *tp = tcp_sk(sk); @@ -903,7 +903,7 @@ struct sock *tcp_check_req(struct sock *sk,struct sk_buff *skb, * Enforce "SYN-ACK" according to figure 8, figure 6 * of RFC793, fixed by RFC1122. */ - req->class->rtx_syn_ack(sk, req, NULL); + req->rsk_ops->rtx_syn_ack(sk, req, NULL); return NULL; } @@ -975,7 +975,7 @@ struct sock *tcp_check_req(struct sock *sk,struct sk_buff *skb, tcp_rsk(req)->rcv_isn + 1, tcp_rsk(req)->rcv_isn + 1 + req->rcv_wnd)) { /* Out of window: send ACK and drop. */ if (!(flg & TCP_FLAG_RST)) - req->class->send_ack(skb, req); + req->rsk_ops->send_ack(skb, req); if (paws_reject) NET_INC_STATS_BH(LINUX_MIB_PAWSESTABREJECTED); return NULL; @@ -1035,7 +1035,7 @@ struct sock *tcp_check_req(struct sock *sk,struct sk_buff *skb, embryonic_reset: NET_INC_STATS_BH(LINUX_MIB_EMBRYONICRSTS); if (!(flg & TCP_FLAG_RST)) - req->class->send_reset(skb); + req->rsk_ops->send_reset(skb); tcp_synq_drop(sk, req, prev); return NULL; diff --git a/net/ipv4/tcp_output.c b/net/ipv4/tcp_output.c index f3c8747caf91..f17c6577e337 100644 --- a/net/ipv4/tcp_output.c +++ b/net/ipv4/tcp_output.c @@ -1356,7 +1356,7 @@ int tcp_send_synack(struct sock *sk) * Prepare a SYN-ACK. */ struct sk_buff * tcp_make_synack(struct sock *sk, struct dst_entry *dst, - struct open_request *req) + struct request_sock *req) { struct inet_request_sock *ireq = inet_rsk(req); struct tcp_sock *tp = tcp_sk(sk); diff --git a/net/ipv4/tcp_timer.c b/net/ipv4/tcp_timer.c index ba30ca0aa6a3..f03efe5fb76a 100644 --- a/net/ipv4/tcp_timer.c +++ b/net/ipv4/tcp_timer.c @@ -468,7 +468,7 @@ static void tcp_synack_timer(struct sock *sk) int max_retries = tp->syn_retries ? : sysctl_tcp_synack_retries; int thresh = max_retries; unsigned long now = jiffies; - struct open_request **reqp, *req; + struct request_sock **reqp, *req; int i, budget; if (lopt == NULL || lopt->qlen == 0) @@ -514,7 +514,7 @@ static void tcp_synack_timer(struct sock *sk) if (time_after_eq(now, req->expires)) { if ((req->retrans < thresh || (inet_rsk(req)->acked && req->retrans < max_retries)) - && !req->class->rtx_syn_ack(sk, req, NULL)) { + && !req->rsk_ops->rtx_syn_ack(sk, req, NULL)) { unsigned long timeo; if (req->retrans++ == 0) @@ -533,7 +533,7 @@ static void tcp_synack_timer(struct sock *sk) lopt->qlen--; if (req->retrans == 0) lopt->qlen_young--; - tcp_openreq_free(req); + reqsk_free(req); continue; } reqp = &req->dl_next; diff --git a/net/ipv6/tcp_ipv6.c b/net/ipv6/tcp_ipv6.c index 9199ad2fde0d..068cd4a8c292 100644 --- a/net/ipv6/tcp_ipv6.c +++ b/net/ipv6/tcp_ipv6.c @@ -65,7 +65,7 @@ #include static void tcp_v6_send_reset(struct sk_buff *skb); -static void tcp_v6_or_send_ack(struct sk_buff *skb, struct open_request *req); +static void tcp_v6_reqsk_send_ack(struct sk_buff *skb, struct request_sock *req); static void tcp_v6_send_check(struct sock *sk, struct tcphdr *th, int len, struct sk_buff *skb); @@ -394,15 +394,15 @@ static u32 tcp_v6_synq_hash(struct in6_addr *raddr, u16 rport, u32 rnd) return c & (TCP_SYNQ_HSIZE - 1); } -static struct open_request *tcp_v6_search_req(struct tcp_sock *tp, - struct open_request ***prevp, +static struct request_sock *tcp_v6_search_req(struct tcp_sock *tp, + struct request_sock ***prevp, __u16 rport, struct in6_addr *raddr, struct in6_addr *laddr, int iif) { struct tcp_listen_opt *lopt = tp->listen_opt; - struct open_request *req, **prev; + struct request_sock *req, **prev; for (prev = &lopt->syn_table[tcp_v6_synq_hash(raddr, rport, lopt->hash_rnd)]; (req = *prev) != NULL; @@ -410,7 +410,7 @@ static struct open_request *tcp_v6_search_req(struct tcp_sock *tp, const struct tcp6_request_sock *treq = tcp6_rsk(req); if (inet_rsk(req)->rmt_port == rport && - req->class->family == AF_INET6 && + req->rsk_ops->family == AF_INET6 && ipv6_addr_equal(&treq->rmt_addr, raddr) && ipv6_addr_equal(&treq->loc_addr, laddr) && (!treq->iif || treq->iif == iif)) { @@ -908,9 +908,9 @@ static void tcp_v6_err(struct sk_buff *skb, struct inet6_skb_parm *opt, icmpv6_err_convert(type, code, &err); - /* Might be for an open_request */ + /* Might be for an request_sock */ switch (sk->sk_state) { - struct open_request *req, **prev; + struct request_sock *req, **prev; case TCP_LISTEN: if (sock_owned_by_user(sk)) goto out; @@ -959,7 +959,7 @@ out: } -static int tcp_v6_send_synack(struct sock *sk, struct open_request *req, +static int tcp_v6_send_synack(struct sock *sk, struct request_sock *req, struct dst_entry *dst) { struct tcp6_request_sock *treq = tcp6_rsk(req); @@ -1027,18 +1027,18 @@ done: return err; } -static void tcp_v6_or_free(struct open_request *req) +static void tcp_v6_reqsk_destructor(struct request_sock *req) { if (tcp6_rsk(req)->pktopts) kfree_skb(tcp6_rsk(req)->pktopts); } -static struct or_calltable or_ipv6 = { +static struct request_sock_ops tcp6_request_sock_ops = { .family = AF_INET6, .obj_size = sizeof(struct tcp6_request_sock), .rtx_syn_ack = tcp_v6_send_synack, - .send_ack = tcp_v6_or_send_ack, - .destructor = tcp_v6_or_free, + .send_ack = tcp_v6_reqsk_send_ack, + .destructor = tcp_v6_reqsk_destructor, .send_reset = tcp_v6_send_reset }; @@ -1223,7 +1223,7 @@ static void tcp_v6_timewait_ack(struct sock *sk, struct sk_buff *skb) tcp_tw_put(tw); } -static void tcp_v6_or_send_ack(struct sk_buff *skb, struct open_request *req) +static void tcp_v6_reqsk_send_ack(struct sk_buff *skb, struct request_sock *req) { tcp_v6_send_ack(skb, tcp_rsk(req)->snt_isn + 1, tcp_rsk(req)->rcv_isn + 1, req->rcv_wnd, req->ts_recent); } @@ -1231,7 +1231,7 @@ static void tcp_v6_or_send_ack(struct sk_buff *skb, struct open_request *req) static struct sock *tcp_v6_hnd_req(struct sock *sk,struct sk_buff *skb) { - struct open_request *req, **prev; + struct request_sock *req, **prev; struct tcphdr *th = skb->h.th; struct tcp_sock *tp = tcp_sk(sk); struct sock *nsk; @@ -1264,7 +1264,7 @@ static struct sock *tcp_v6_hnd_req(struct sock *sk,struct sk_buff *skb) return sk; } -static void tcp_v6_synq_add(struct sock *sk, struct open_request *req) +static void tcp_v6_synq_add(struct sock *sk, struct request_sock *req) { struct tcp_sock *tp = tcp_sk(sk); struct tcp_listen_opt *lopt = tp->listen_opt; @@ -1292,7 +1292,7 @@ static int tcp_v6_conn_request(struct sock *sk, struct sk_buff *skb) struct ipv6_pinfo *np = inet6_sk(sk); struct tcp_options_received tmp_opt; struct tcp_sock *tp = tcp_sk(sk); - struct open_request *req = NULL; + struct request_sock *req = NULL; __u32 isn = TCP_SKB_CB(skb)->when; if (skb->protocol == htons(ETH_P_IP)) @@ -1313,7 +1313,7 @@ static int tcp_v6_conn_request(struct sock *sk, struct sk_buff *skb) if (sk_acceptq_is_full(sk) && tcp_synq_young(sk) > 1) goto drop; - req = tcp_openreq_alloc(&or_ipv6); + req = reqsk_alloc(&tcp6_request_sock_ops); if (req == NULL) goto drop; @@ -1358,14 +1358,14 @@ static int tcp_v6_conn_request(struct sock *sk, struct sk_buff *skb) drop: if (req) - tcp_openreq_free(req); + reqsk_free(req); TCP_INC_STATS_BH(TCP_MIB_ATTEMPTFAILS); return 0; /* don't send reset */ } static struct sock * tcp_v6_syn_recv_sock(struct sock *sk, struct sk_buff *skb, - struct open_request *req, + struct request_sock *req, struct dst_entry *dst) { struct tcp6_request_sock *treq = tcp6_rsk(req); @@ -2055,7 +2055,7 @@ static int tcp_v6_destroy_sock(struct sock *sk) /* Proc filesystem TCPv6 sock list dumping. */ static void get_openreq6(struct seq_file *seq, - struct sock *sk, struct open_request *req, int i, int uid) + struct sock *sk, struct request_sock *req, int i, int uid) { struct in6_addr *dest, *src; int ttd = req->expires - jiffies; @@ -2244,7 +2244,7 @@ struct proto tcpv6_prot = { .sysctl_rmem = sysctl_tcp_rmem, .max_header = MAX_TCP_HEADER, .obj_size = sizeof(struct tcp6_sock), - .rsk_prot = &or_ipv6, + .rsk_prot = &tcp6_request_sock_ops, }; static struct inet6_protocol tcpv6_protocol = { -- cgit v1.2.3 From 0e87506fcc734647c7b2497eee4eb81e785c857a Mon Sep 17 00:00:00 2001 From: Arnaldo Carvalho de Melo Date: Sat, 18 Jun 2005 22:47:59 -0700 Subject: [NET] Generalise tcp_listen_opt This chunks out the accept_queue and tcp_listen_opt code and moves them to net/core/request_sock.c and include/net/request_sock.h, to make it useful for other transport protocols, DCCP being the first one to use it. Next patches will rename tcp_listen_opt to accept_sock and remove the inline tcp functions that just call a reqsk_queue_ function. Signed-off-by: Arnaldo Carvalho de Melo Signed-off-by: David S. Miller --- include/linux/tcp.h | 17 +---- include/net/request_sock.h | 178 +++++++++++++++++++++++++++++++++++++++++++++ include/net/tcp.h | 46 ++---------- net/core/Makefile | 3 +- net/core/request_sock.c | 48 ++++++++++++ net/ipv4/tcp.c | 67 ++++++----------- net/ipv4/tcp_diag.c | 6 +- net/ipv4/tcp_ipv4.c | 32 +++----- net/ipv4/tcp_minisocks.c | 6 +- net/ipv4/tcp_timer.c | 10 +-- net/ipv6/tcp_ipv6.c | 14 +--- 11 files changed, 281 insertions(+), 146 deletions(-) create mode 100644 net/core/request_sock.c (limited to 'include/linux') diff --git a/include/linux/tcp.h b/include/linux/tcp.h index fb54292a15aa..97a7c9e03df5 100644 --- a/include/linux/tcp.h +++ b/include/linux/tcp.h @@ -379,22 +379,7 @@ struct tcp_sock { __u32 total_retrans; /* Total retransmits for entire connection */ - /* The syn_wait_lock is necessary only to avoid proc interface having - * to grab the main lock sock while browsing the listening hash - * (otherwise it's deadlock prone). - * This lock is acquired in read mode only from listening_get_next() - * and it's acquired in write mode _only_ from code that is actively - * changing the syn_wait_queue. All readers that are holding - * the master sock lock don't need to grab this lock in read mode - * too as the syn_wait_queue writes are always protected from - * the main sock lock. - */ - rwlock_t syn_wait_lock; - struct tcp_listen_opt *listen_opt; - - /* FIFO of established children */ - struct request_sock *accept_queue; - struct request_sock *accept_queue_tail; + struct request_sock_queue accept_queue; /* FIFO of established children */ unsigned int keepalive_time; /* time before keep alive takes place */ unsigned int keepalive_intvl; /* time interval between keep alive probes */ diff --git a/include/net/request_sock.h b/include/net/request_sock.h index 08a8fd1d1610..38943ed04e73 100644 --- a/include/net/request_sock.h +++ b/include/net/request_sock.h @@ -16,7 +16,9 @@ #define _REQUEST_SOCK_H #include +#include #include + #include struct request_sock; @@ -74,4 +76,180 @@ static inline void reqsk_free(struct request_sock *req) __reqsk_free(req); } +extern int sysctl_max_syn_backlog; + +/** struct tcp_listen_opt - listen state + * + * @max_qlen_log - log_2 of maximal queued SYNs/REQUESTs + */ +struct tcp_listen_opt { + u8 max_qlen_log; + /* 3 bytes hole, try to use */ + int qlen; + int qlen_young; + int clock_hand; + u32 hash_rnd; + struct request_sock *syn_table[0]; +}; + +/** struct request_sock_queue - queue of request_socks + * + * @rskq_accept_head - FIFO head of established children + * @rskq_accept_tail - FIFO tail of established children + * @syn_wait_lock - serializer + * + * %syn_wait_lock is necessary only to avoid proc interface having to grab the main + * lock sock while browsing the listening hash (otherwise it's deadlock prone). + * + * This lock is acquired in read mode only from listening_get_next() seq_file + * op and it's acquired in write mode _only_ from code that is actively + * changing rskq_accept_head. All readers that are holding the master sock lock + * don't need to grab this lock in read mode too as rskq_accept_head. writes + * are always protected from the main sock lock. + */ +struct request_sock_queue { + struct request_sock *rskq_accept_head; + struct request_sock *rskq_accept_tail; + rwlock_t syn_wait_lock; + struct tcp_listen_opt *listen_opt; +}; + +extern int reqsk_queue_alloc(struct request_sock_queue *queue, + const int nr_table_entries); + +static inline struct tcp_listen_opt *reqsk_queue_yank_listen_sk(struct request_sock_queue *queue) +{ + struct tcp_listen_opt *lopt; + + write_lock_bh(&queue->syn_wait_lock); + lopt = queue->listen_opt; + queue->listen_opt = NULL; + write_unlock_bh(&queue->syn_wait_lock); + + return lopt; +} + +static inline void reqsk_queue_destroy(struct request_sock_queue *queue) +{ + kfree(reqsk_queue_yank_listen_sk(queue)); +} + +static inline struct request_sock * + reqsk_queue_yank_acceptq(struct request_sock_queue *queue) +{ + struct request_sock *req = queue->rskq_accept_head; + + queue->rskq_accept_head = queue->rskq_accept_head = NULL; + return req; +} + +static inline int reqsk_queue_empty(struct request_sock_queue *queue) +{ + return queue->rskq_accept_head == NULL; +} + +static inline void reqsk_queue_unlink(struct request_sock_queue *queue, + struct request_sock *req, + struct request_sock **prev_req) +{ + write_lock(&queue->syn_wait_lock); + *prev_req = req->dl_next; + write_unlock(&queue->syn_wait_lock); +} + +static inline void reqsk_queue_add(struct request_sock_queue *queue, + struct request_sock *req, + struct sock *parent, + struct sock *child) +{ + req->sk = child; + sk_acceptq_added(parent); + + if (queue->rskq_accept_head == NULL) + queue->rskq_accept_head = req; + else + queue->rskq_accept_tail->dl_next = req; + + queue->rskq_accept_tail = req; + req->dl_next = NULL; +} + +static inline struct request_sock *reqsk_queue_remove(struct request_sock_queue *queue) +{ + struct request_sock *req = queue->rskq_accept_head; + + BUG_TRAP(req != NULL); + + queue->rskq_accept_head = req->dl_next; + if (queue->rskq_accept_head == NULL) + queue->rskq_accept_tail = NULL; + + return req; +} + +static inline struct sock *reqsk_queue_get_child(struct request_sock_queue *queue, + struct sock *parent) +{ + struct request_sock *req = reqsk_queue_remove(queue); + struct sock *child = req->sk; + + BUG_TRAP(child != NULL); + + sk_acceptq_removed(parent); + __reqsk_free(req); + return child; +} + +static inline int reqsk_queue_removed(struct request_sock_queue *queue, + struct request_sock *req) +{ + struct tcp_listen_opt *lopt = queue->listen_opt; + + if (req->retrans == 0) + --lopt->qlen_young; + + return --lopt->qlen; +} + +static inline int reqsk_queue_added(struct request_sock_queue *queue) +{ + struct tcp_listen_opt *lopt = queue->listen_opt; + const int prev_qlen = lopt->qlen; + + lopt->qlen_young++; + lopt->qlen++; + return prev_qlen; +} + +static inline int reqsk_queue_len(struct request_sock_queue *queue) +{ + return queue->listen_opt != NULL ? queue->listen_opt->qlen : 0; +} + +static inline int reqsk_queue_len_young(struct request_sock_queue *queue) +{ + return queue->listen_opt->qlen_young; +} + +static inline int reqsk_queue_is_full(struct request_sock_queue *queue) +{ + return queue->listen_opt->qlen >> queue->listen_opt->max_qlen_log; +} + +static inline void reqsk_queue_hash_req(struct request_sock_queue *queue, + u32 hash, struct request_sock *req, + unsigned timeout) +{ + struct tcp_listen_opt *lopt = queue->listen_opt; + + req->expires = jiffies + timeout; + req->retrans = 0; + req->sk = NULL; + req->dl_next = lopt->syn_table[hash]; + + write_lock(&queue->syn_wait_lock); + lopt->syn_table[hash] = req; + write_unlock(&queue->syn_wait_lock); +} + #endif /* _REQUEST_SOCK_H */ diff --git a/include/net/tcp.h b/include/net/tcp.h index 6663086a5e35..a2e323c54457 100644 --- a/include/net/tcp.h +++ b/include/net/tcp.h @@ -1686,71 +1686,41 @@ static inline int tcp_full_space(const struct sock *sk) static inline void tcp_acceptq_queue(struct sock *sk, struct request_sock *req, struct sock *child) { - struct tcp_sock *tp = tcp_sk(sk); - - req->sk = child; - sk_acceptq_added(sk); - - if (!tp->accept_queue_tail) { - tp->accept_queue = req; - } else { - tp->accept_queue_tail->dl_next = req; - } - tp->accept_queue_tail = req; - req->dl_next = NULL; + reqsk_queue_add(&tcp_sk(sk)->accept_queue, req, sk, child); } -struct tcp_listen_opt -{ - u8 max_qlen_log; /* log_2 of maximal queued SYNs */ - int qlen; - int qlen_young; - int clock_hand; - u32 hash_rnd; - struct request_sock *syn_table[TCP_SYNQ_HSIZE]; -}; - static inline void tcp_synq_removed(struct sock *sk, struct request_sock *req) { - struct tcp_listen_opt *lopt = tcp_sk(sk)->listen_opt; - - if (--lopt->qlen == 0) + if (reqsk_queue_removed(&tcp_sk(sk)->accept_queue, req) == 0) tcp_delete_keepalive_timer(sk); - if (req->retrans == 0) - lopt->qlen_young--; } static inline void tcp_synq_added(struct sock *sk) { - struct tcp_listen_opt *lopt = tcp_sk(sk)->listen_opt; - - if (lopt->qlen++ == 0) + if (reqsk_queue_added(&tcp_sk(sk)->accept_queue) == 0) tcp_reset_keepalive_timer(sk, TCP_TIMEOUT_INIT); - lopt->qlen_young++; } static inline int tcp_synq_len(struct sock *sk) { - return tcp_sk(sk)->listen_opt->qlen; + return reqsk_queue_len(&tcp_sk(sk)->accept_queue); } static inline int tcp_synq_young(struct sock *sk) { - return tcp_sk(sk)->listen_opt->qlen_young; + return reqsk_queue_len_young(&tcp_sk(sk)->accept_queue); } static inline int tcp_synq_is_full(struct sock *sk) { - return tcp_synq_len(sk) >> tcp_sk(sk)->listen_opt->max_qlen_log; + return reqsk_queue_is_full(&tcp_sk(sk)->accept_queue); } static inline void tcp_synq_unlink(struct tcp_sock *tp, struct request_sock *req, - struct request_sock **prev) + struct request_sock **prev) { - write_lock(&tp->syn_wait_lock); - *prev = req->dl_next; - write_unlock(&tp->syn_wait_lock); + reqsk_queue_unlink(&tp->accept_queue, req, prev); } static inline void tcp_synq_drop(struct sock *sk, struct request_sock *req, diff --git a/net/core/Makefile b/net/core/Makefile index 81f03243fe2f..5e0c56b7f607 100644 --- a/net/core/Makefile +++ b/net/core/Makefile @@ -2,7 +2,8 @@ # Makefile for the Linux networking core. # -obj-y := sock.o skbuff.o iovec.o datagram.o stream.o scm.o gen_stats.o gen_estimator.o +obj-y := sock.o request_sock.o skbuff.o iovec.o datagram.o stream.o scm.o \ + gen_stats.o gen_estimator.o obj-$(CONFIG_SYSCTL) += sysctl_net_core.o diff --git a/net/core/request_sock.c b/net/core/request_sock.c new file mode 100644 index 000000000000..1258333ca007 --- /dev/null +++ b/net/core/request_sock.c @@ -0,0 +1,48 @@ +/* + * NET Generic infrastructure for Network protocols. + * + * Authors: Arnaldo Carvalho de Melo + * + * From code originally in include/net/tcp.h + * + * 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 +#include +#include +#include + +#include + +int reqsk_queue_alloc(struct request_sock_queue *queue, + const int nr_table_entries) +{ + const int lopt_size = sizeof(struct tcp_listen_opt) + + nr_table_entries * sizeof(struct request_sock *); + struct tcp_listen_opt *lopt = kmalloc(lopt_size, GFP_KERNEL); + + if (lopt == NULL) + return -ENOMEM; + + memset(lopt, 0, lopt_size); + + for (lopt->max_qlen_log = 6; + (1 << lopt->max_qlen_log) < sysctl_max_syn_backlog; + lopt->max_qlen_log++); + + get_random_bytes(&lopt->hash_rnd, sizeof(lopt->hash_rnd)); + rwlock_init(&queue->syn_wait_lock); + queue->rskq_accept_head = queue->rskq_accept_head = NULL; + + write_lock_bh(&queue->syn_wait_lock); + queue->listen_opt = lopt; + write_unlock_bh(&queue->syn_wait_lock); + + return 0; +} + +EXPORT_SYMBOL(reqsk_queue_alloc); diff --git a/net/ipv4/tcp.c b/net/ipv4/tcp.c index 1c29feb6b35f..b85a46dd40a0 100644 --- a/net/ipv4/tcp.c +++ b/net/ipv4/tcp.c @@ -316,7 +316,7 @@ EXPORT_SYMBOL(tcp_enter_memory_pressure); static __inline__ unsigned int tcp_listen_poll(struct sock *sk, poll_table *wait) { - return tcp_sk(sk)->accept_queue ? (POLLIN | POLLRDNORM) : 0; + return !reqsk_queue_empty(&tcp_sk(sk)->accept_queue) ? (POLLIN | POLLRDNORM) : 0; } /* @@ -462,28 +462,15 @@ int tcp_listen_start(struct sock *sk) { struct inet_sock *inet = inet_sk(sk); struct tcp_sock *tp = tcp_sk(sk); - struct tcp_listen_opt *lopt; + int rc = reqsk_queue_alloc(&tp->accept_queue, TCP_SYNQ_HSIZE); + + if (rc != 0) + return rc; sk->sk_max_ack_backlog = 0; sk->sk_ack_backlog = 0; - tp->accept_queue = tp->accept_queue_tail = NULL; - rwlock_init(&tp->syn_wait_lock); tcp_delack_init(tp); - lopt = kmalloc(sizeof(struct tcp_listen_opt), GFP_KERNEL); - if (!lopt) - return -ENOMEM; - - memset(lopt, 0, sizeof(struct tcp_listen_opt)); - for (lopt->max_qlen_log = 6; ; lopt->max_qlen_log++) - if ((1 << lopt->max_qlen_log) >= sysctl_max_syn_backlog) - break; - get_random_bytes(&lopt->hash_rnd, 4); - - write_lock_bh(&tp->syn_wait_lock); - tp->listen_opt = lopt; - write_unlock_bh(&tp->syn_wait_lock); - /* There is race window here: we announce ourselves listening, * but this transition is still not validated by get_port(). * It is OK, because this socket enters to hash table only @@ -500,10 +487,7 @@ int tcp_listen_start(struct sock *sk) } sk->sk_state = TCP_CLOSE; - write_lock_bh(&tp->syn_wait_lock); - tp->listen_opt = NULL; - write_unlock_bh(&tp->syn_wait_lock); - kfree(lopt); + reqsk_queue_destroy(&tp->accept_queue); return -EADDRINUSE; } @@ -515,18 +499,16 @@ int tcp_listen_start(struct sock *sk) static void tcp_listen_stop (struct sock *sk) { struct tcp_sock *tp = tcp_sk(sk); - struct tcp_listen_opt *lopt = tp->listen_opt; - struct request_sock *acc_req = tp->accept_queue; + struct tcp_listen_opt *lopt; + struct request_sock *acc_req; struct request_sock *req; int i; tcp_delete_keepalive_timer(sk); /* make all the listen_opt local to us */ - write_lock_bh(&tp->syn_wait_lock); - tp->listen_opt = NULL; - write_unlock_bh(&tp->syn_wait_lock); - tp->accept_queue = tp->accept_queue_tail = NULL; + lopt = reqsk_queue_yank_listen_sk(&tp->accept_queue); + acc_req = reqsk_queue_yank_acceptq(&tp->accept_queue); if (lopt->qlen) { for (i = 0; i < TCP_SYNQ_HSIZE; i++) { @@ -1867,11 +1849,11 @@ static int wait_for_connect(struct sock *sk, long timeo) prepare_to_wait_exclusive(sk->sk_sleep, &wait, TASK_INTERRUPTIBLE); release_sock(sk); - if (!tp->accept_queue) + if (reqsk_queue_empty(&tp->accept_queue)) timeo = schedule_timeout(timeo); lock_sock(sk); err = 0; - if (tp->accept_queue) + if (!reqsk_queue_empty(&tp->accept_queue)) break; err = -EINVAL; if (sk->sk_state != TCP_LISTEN) @@ -1894,7 +1876,6 @@ static int wait_for_connect(struct sock *sk, long timeo) struct sock *tcp_accept(struct sock *sk, int flags, int *err) { struct tcp_sock *tp = tcp_sk(sk); - struct request_sock *req; struct sock *newsk; int error; @@ -1905,37 +1886,31 @@ struct sock *tcp_accept(struct sock *sk, int flags, int *err) */ error = -EINVAL; if (sk->sk_state != TCP_LISTEN) - goto out; + goto out_err; /* Find already established connection */ - if (!tp->accept_queue) { + if (reqsk_queue_empty(&tp->accept_queue)) { long timeo = sock_rcvtimeo(sk, flags & O_NONBLOCK); /* If this is a non blocking socket don't sleep */ error = -EAGAIN; if (!timeo) - goto out; + goto out_err; error = wait_for_connect(sk, timeo); if (error) - goto out; + goto out_err; } - req = tp->accept_queue; - if ((tp->accept_queue = req->dl_next) == NULL) - tp->accept_queue_tail = NULL; - - newsk = req->sk; - sk_acceptq_removed(sk); - __reqsk_free(req); + newsk = reqsk_queue_get_child(&tp->accept_queue, sk); BUG_TRAP(newsk->sk_state != TCP_SYN_RECV); - release_sock(sk); - return newsk; - out: release_sock(sk); + return newsk; +out_err: + newsk = NULL; *err = error; - return NULL; + goto out; } /* diff --git a/net/ipv4/tcp_diag.c b/net/ipv4/tcp_diag.c index 67277800d0c1..c3328fa48837 100644 --- a/net/ipv4/tcp_diag.c +++ b/net/ipv4/tcp_diag.c @@ -529,9 +529,9 @@ static int tcpdiag_dump_reqs(struct sk_buff *skb, struct sock *sk, entry.family = sk->sk_family; - read_lock_bh(&tp->syn_wait_lock); + read_lock_bh(&tp->accept_queue.syn_wait_lock); - lopt = tp->listen_opt; + lopt = tp->accept_queue.listen_opt; if (!lopt || !lopt->qlen) goto out; @@ -588,7 +588,7 @@ static int tcpdiag_dump_reqs(struct sk_buff *skb, struct sock *sk, } out: - read_unlock_bh(&tp->syn_wait_lock); + read_unlock_bh(&tp->accept_queue.syn_wait_lock); return err; } diff --git a/net/ipv4/tcp_ipv4.c b/net/ipv4/tcp_ipv4.c index 95528a75a63d..1745dc8d25e6 100644 --- a/net/ipv4/tcp_ipv4.c +++ b/net/ipv4/tcp_ipv4.c @@ -874,7 +874,7 @@ static struct request_sock *tcp_v4_search_req(struct tcp_sock *tp, __u16 rport, __u32 raddr, __u32 laddr) { - struct tcp_listen_opt *lopt = tp->listen_opt; + struct tcp_listen_opt *lopt = tp->accept_queue.listen_opt; struct request_sock *req, **prev; for (prev = &lopt->syn_table[tcp_v4_synq_hash(raddr, rport, lopt->hash_rnd)]; @@ -898,18 +898,10 @@ static struct request_sock *tcp_v4_search_req(struct tcp_sock *tp, static void tcp_v4_synq_add(struct sock *sk, struct request_sock *req) { struct tcp_sock *tp = tcp_sk(sk); - struct tcp_listen_opt *lopt = tp->listen_opt; + struct tcp_listen_opt *lopt = tp->accept_queue.listen_opt; u32 h = tcp_v4_synq_hash(inet_rsk(req)->rmt_addr, inet_rsk(req)->rmt_port, lopt->hash_rnd); - req->expires = jiffies + TCP_TIMEOUT_INIT; - req->retrans = 0; - req->sk = NULL; - req->dl_next = lopt->syn_table[h]; - - write_lock(&tp->syn_wait_lock); - lopt->syn_table[h] = req; - write_unlock(&tp->syn_wait_lock); - + reqsk_queue_hash_req(&tp->accept_queue, h, req, TCP_TIMEOUT_INIT); tcp_synq_added(sk); } @@ -2167,17 +2159,17 @@ static void *listening_get_next(struct seq_file *seq, void *cur) if (++st->sbucket >= TCP_SYNQ_HSIZE) break; get_req: - req = tp->listen_opt->syn_table[st->sbucket]; + req = tp->accept_queue.listen_opt->syn_table[st->sbucket]; } sk = sk_next(st->syn_wait_sk); st->state = TCP_SEQ_STATE_LISTENING; - read_unlock_bh(&tp->syn_wait_lock); + read_unlock_bh(&tp->accept_queue.syn_wait_lock); } else { tp = tcp_sk(sk); - read_lock_bh(&tp->syn_wait_lock); - if (tp->listen_opt && tp->listen_opt->qlen) + read_lock_bh(&tp->accept_queue.syn_wait_lock); + if (reqsk_queue_len(&tp->accept_queue)) goto start_req; - read_unlock_bh(&tp->syn_wait_lock); + read_unlock_bh(&tp->accept_queue.syn_wait_lock); sk = sk_next(sk); } get_sk: @@ -2187,8 +2179,8 @@ get_sk: goto out; } tp = tcp_sk(sk); - read_lock_bh(&tp->syn_wait_lock); - if (tp->listen_opt && tp->listen_opt->qlen) { + read_lock_bh(&tp->accept_queue.syn_wait_lock); + if (reqsk_queue_len(&tp->accept_queue)) { start_req: st->uid = sock_i_uid(sk); st->syn_wait_sk = sk; @@ -2196,7 +2188,7 @@ start_req: st->sbucket = 0; goto get_req; } - read_unlock_bh(&tp->syn_wait_lock); + read_unlock_bh(&tp->accept_queue.syn_wait_lock); } if (++st->bucket < TCP_LHTABLE_SIZE) { sk = sk_head(&tcp_listening_hash[st->bucket]); @@ -2383,7 +2375,7 @@ static void tcp_seq_stop(struct seq_file *seq, void *v) case TCP_SEQ_STATE_OPENREQ: if (v) { struct tcp_sock *tp = tcp_sk(st->syn_wait_sk); - read_unlock_bh(&tp->syn_wait_lock); + read_unlock_bh(&tp->accept_queue.syn_wait_lock); } case TCP_SEQ_STATE_LISTENING: if (v != SEQ_START_TOKEN) diff --git a/net/ipv4/tcp_minisocks.c b/net/ipv4/tcp_minisocks.c index 0e6d525a8341..b3943e7562f3 100644 --- a/net/ipv4/tcp_minisocks.c +++ b/net/ipv4/tcp_minisocks.c @@ -790,10 +790,8 @@ struct sock *tcp_create_openreq_child(struct sock *sk, struct request_sock *req, newtp->probes_out = 0; newtp->rx_opt.num_sacks = 0; newtp->urg_data = 0; - newtp->listen_opt = NULL; - newtp->accept_queue = newtp->accept_queue_tail = NULL; - /* Deinitialize syn_wait_lock to trap illegal accesses. */ - memset(&newtp->syn_wait_lock, 0, sizeof(newtp->syn_wait_lock)); + /* Deinitialize accept_queue to trap illegal accesses. */ + memset(&newtp->accept_queue, 0, sizeof(newtp->accept_queue)); /* Back to base struct sock members. */ newsk->sk_err = 0; diff --git a/net/ipv4/tcp_timer.c b/net/ipv4/tcp_timer.c index f03efe5fb76a..d97d191149c1 100644 --- a/net/ipv4/tcp_timer.c +++ b/net/ipv4/tcp_timer.c @@ -464,7 +464,7 @@ out_unlock: static void tcp_synack_timer(struct sock *sk) { struct tcp_sock *tp = tcp_sk(sk); - struct tcp_listen_opt *lopt = tp->listen_opt; + struct tcp_listen_opt *lopt = tp->accept_queue.listen_opt; int max_retries = tp->syn_retries ? : sysctl_tcp_synack_retries; int thresh = max_retries; unsigned long now = jiffies; @@ -527,12 +527,8 @@ static void tcp_synack_timer(struct sock *sk) } /* Drop this request */ - write_lock(&tp->syn_wait_lock); - *reqp = req->dl_next; - write_unlock(&tp->syn_wait_lock); - lopt->qlen--; - if (req->retrans == 0) - lopt->qlen_young--; + tcp_synq_unlink(tp, req, reqp); + reqsk_queue_removed(&tp->accept_queue, req); reqsk_free(req); continue; } diff --git a/net/ipv6/tcp_ipv6.c b/net/ipv6/tcp_ipv6.c index 068cd4a8c292..84091daad6b5 100644 --- a/net/ipv6/tcp_ipv6.c +++ b/net/ipv6/tcp_ipv6.c @@ -401,7 +401,7 @@ static struct request_sock *tcp_v6_search_req(struct tcp_sock *tp, struct in6_addr *laddr, int iif) { - struct tcp_listen_opt *lopt = tp->listen_opt; + struct tcp_listen_opt *lopt = tp->accept_queue.listen_opt; struct request_sock *req, **prev; for (prev = &lopt->syn_table[tcp_v6_synq_hash(raddr, rport, lopt->hash_rnd)]; @@ -1267,18 +1267,10 @@ static struct sock *tcp_v6_hnd_req(struct sock *sk,struct sk_buff *skb) static void tcp_v6_synq_add(struct sock *sk, struct request_sock *req) { struct tcp_sock *tp = tcp_sk(sk); - struct tcp_listen_opt *lopt = tp->listen_opt; + struct tcp_listen_opt *lopt = tp->accept_queue.listen_opt; u32 h = tcp_v6_synq_hash(&tcp6_rsk(req)->rmt_addr, inet_rsk(req)->rmt_port, lopt->hash_rnd); - req->sk = NULL; - req->expires = jiffies + TCP_TIMEOUT_INIT; - req->retrans = 0; - req->dl_next = lopt->syn_table[h]; - - write_lock(&tp->syn_wait_lock); - lopt->syn_table[h] = req; - write_unlock(&tp->syn_wait_lock); - + reqsk_queue_hash_req(&tp->accept_queue, h, req, TCP_TIMEOUT_INIT); tcp_synq_added(sk); } -- cgit v1.2.3 From f88a10d65620d97b6d0a7e352a3493c1b7e7409b Mon Sep 17 00:00:00 2001 From: Thomas Graf Date: Sat, 18 Jun 2005 22:50:12 -0700 Subject: [NETLINK]: New message building macros NLMSG_PUT_ANSWER(skb, nlcb, type, length) Start a new netlink message as answer to a request, returns the message header. NLMSG_END(skb, nlh) End a netlink message, fixes total message length, returns skb->len. NLMSG_CANCEL(skb, nlh) Cancel the building process and trim whole message from skb again, returns -1. Signed-off-by: Thomas Graf Signed-off-by: David S. Miller --- include/linux/netlink.h | 17 +++++++++++++++-- 1 file changed, 15 insertions(+), 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/netlink.h b/include/linux/netlink.h index b2738ac8bc99..8d1cb419a930 100644 --- a/include/linux/netlink.h +++ b/include/linux/netlink.h @@ -171,8 +171,21 @@ __nlmsg_put(struct sk_buff *skb, u32 pid, u32 seq, int type, int len) } #define NLMSG_PUT(skb, pid, seq, type, len) \ -({ if (skb_tailroom(skb) < (int)NLMSG_SPACE(len)) goto nlmsg_failure; \ - __nlmsg_put(skb, pid, seq, type, len); }) +({ if (skb_tailroom(skb) < (int)NLMSG_SPACE(len)) \ + goto nlmsg_failure; \ + __nlmsg_put(skb, pid, seq, type, len); }) + +#define NLMSG_PUT_ANSWER(skb, cb, type, len) \ + NLMSG_PUT(skb, NETLINK_CB((cb)->skb).pid, \ + (cb)->nlh->nlmsg_seq, type, len) + +#define NLMSG_END(skb, nlh) \ +({ (nlh)->nlmsg_len = (skb)->tail - (unsigned char *) (nlh); \ + (skb)->len; }) + +#define NLMSG_CANCEL(skb, nlh) \ +({ skb_trim(skb, (unsigned char *) (nlh) - (skb)->data); \ + -1; }) extern int netlink_dump_start(struct sock *ssk, struct sk_buff *skb, struct nlmsghdr *nlh, -- cgit v1.2.3 From 00768244923f66801958a8d2d103f7b65608c9b6 Mon Sep 17 00:00:00 2001 From: Thomas Graf Date: Sat, 18 Jun 2005 22:50:38 -0700 Subject: [NETLINK] Routing attribute related shortcuts RTA_GET_U(32|64)(tlv) Assumes TLV is a u32/u64 field and returns its value. RTA_GET_[M]SECS(tlv) Assumes TLV is a u64 and transports jiffies converted to seconds or milliseconds and returns its value. RTA_PUT_U(32|64)(skb, type, value) Appends %value as fixed u32/u64 to %skb as TLV %type. RTA_PUT_[M]SECS(skb, type, jiffies) Converts %jiffies to secs/msecs and appends it as u64 to %skb as TLV %type. RTA_PUT_STRING(skb, type, string) Appends %NUL terminated %string to %skb as TLV %type. RTA_NEST(skb, type) Starts a nested TLV %type and returns the nesting handle. RTA_NEST_END(skb, nesting_handle) Finishes the nested TLV %nesting_handle, must be called symmetric to RTA_NEST(). Returns skb->len RTA_NEST_CANCEL(skb, nesting_handle) Cancel the nested TLV %nesting_handle and trim nested TLV from skb again, returns -1. Signed-off-by: Thomas Graf Signed-off-by: David S. Miller --- include/linux/rtnetlink.h | 45 +++++++++++++++++++++++++++++++++++++++++++++ 1 file changed, 45 insertions(+) (limited to 'include/linux') diff --git a/include/linux/rtnetlink.h b/include/linux/rtnetlink.h index 91ac97c20777..a09b5d42babf 100644 --- a/include/linux/rtnetlink.h +++ b/include/linux/rtnetlink.h @@ -789,6 +789,51 @@ extern void __rta_fill(struct sk_buff *skb, int attrtype, int attrlen, const voi ({ if (unlikely(skb_tailroom(skb) < (int)(attrlen))) \ goto rtattr_failure; \ memcpy(skb_put(skb, RTA_ALIGN(attrlen)), data, attrlen); }) + +#define RTA_PUT_U32(skb, attrtype, value) \ +({ u32 _tmp = (value); \ + RTA_PUT(skb, attrtype, sizeof(u32), &_tmp); }) + +#define RTA_PUT_U64(skb, attrtype, value) \ +({ u64 _tmp = (value); \ + RTA_PUT(skb, attrtype, sizeof(u64), &_tmp); }) + +#define RTA_PUT_SECS(skb, attrtype, value) \ + RTA_PUT_U64(skb, attrtype, (value) / HZ) + +#define RTA_PUT_MSECS(skb, attrtype, value) \ + RTA_PUT_U64(skb, attrtype, jiffies_to_msecs(value)) + +#define RTA_PUT_STRING(skb, attrtype, value) \ + RTA_PUT(skb, attrtype, strlen(value) + 1, value) + +#define RTA_NEST(skb, type) \ +({ struct rtattr *__start = (struct rtattr *) (skb)->tail; \ + RTA_PUT(skb, type, 0, NULL); \ + __start; }) + +#define RTA_NEST_END(skb, start) \ +({ (start)->rta_len = ((skb)->tail - (unsigned char *) (start)); \ + (skb)->len; }) + +#define RTA_NEST_CANCEL(skb, start) \ +({ skb_trim(skb, (unsigned char *) (start) - (skb)->data); \ + -1; }) + +#define RTA_GET_U32(rta) \ +({ if (!rta || RTA_PAYLOAD(rta) < sizeof(u32)) \ + goto rtattr_failure; \ + *(u32 *) RTA_DATA(rta); }) + +#define RTA_GET_U64(rta) \ +({ u64 _tmp; \ + if (!rta || RTA_PAYLOAD(rta) < sizeof(u64)) \ + goto rtattr_failure; \ + memcpy(&_tmp, RTA_DATA(rta), sizeof(_tmp)); \ + _tmp; }) + +#define RTA_GET_SECS(rta) ((unsigned long) RTA_GET_U64(rta) * HZ) +#define RTA_GET_MSECS(rta) (msecs_to_jiffies((unsigned long) RTA_GET_U64(rta))) static inline struct rtattr * __rta_reserve(struct sk_buff *skb, int attrtype, int attrlen) -- cgit v1.2.3 From c7fb64db001f83ece669c76a02d8ec2fdb1dd307 Mon Sep 17 00:00:00 2001 From: Thomas Graf Date: Sat, 18 Jun 2005 22:50:55 -0700 Subject: [NETLINK]: Neighbour table configuration and statistics via rtnetlink To retrieve the neighbour tables send RTM_GETNEIGHTBL with the NLM_F_DUMP flag set. Every neighbour table configuration is spread over multiple messages to avoid running into message size limits on systems with many interfaces. The first message in the sequence transports all not device specific data such as statistics, configuration, and the default parameter set. This message is followed by 0..n messages carrying device specific parameter sets. Although the ordering should be sufficient, NDTA_NAME can be used to identify sequences. The initial message can be identified by checking for NDTA_CONFIG. The device specific messages do not contain this TLV but have NDTPA_IFINDEX set to the corresponding interface index. To change neighbour table attributes, send RTM_SETNEIGHTBL with NDTA_NAME set. Changeable attribute include NDTA_THRESH[1-3], NDTA_GC_INTERVAL, and all TLVs in NDTA_PARMS unless marked otherwise. Device specific parameter sets can be changed by setting NDTPA_IFINDEX to the interface index of the corresponding device. Signed-off-by: Thomas Graf Signed-off-by: David S. Miller --- include/linux/rtnetlink.h | 107 +++++++++++++++ include/net/neighbour.h | 4 + net/core/neighbour.c | 317 +++++++++++++++++++++++++++++++++++++++++++- net/core/rtnetlink.c | 20 +-- security/selinux/nlmsgtab.c | 2 + 5 files changed, 439 insertions(+), 11 deletions(-) (limited to 'include/linux') diff --git a/include/linux/rtnetlink.h b/include/linux/rtnetlink.h index a09b5d42babf..5a5cda160267 100644 --- a/include/linux/rtnetlink.h +++ b/include/linux/rtnetlink.h @@ -89,6 +89,13 @@ enum { RTM_GETANYCAST = 62, #define RTM_GETANYCAST RTM_GETANYCAST + RTM_NEWNEIGHTBL = 64, +#define RTM_NEWNEIGHTBL RTM_NEWNEIGHTBL + RTM_GETNEIGHTBL = 66, +#define RTM_GETNEIGHTBL RTM_GETNEIGHTBL + RTM_SETNEIGHTBL, +#define RTM_SETNEIGHTBL RTM_SETNEIGHTBL + __RTM_MAX, #define RTM_MAX (((__RTM_MAX + 3) & ~3) - 1) }; @@ -493,6 +500,106 @@ struct nda_cacheinfo __u32 ndm_refcnt; }; + +/***************************************************************** + * Neighbour tables specific messages. + * + * To retrieve the neighbour tables send RTM_GETNEIGHTBL with the + * NLM_F_DUMP flag set. Every neighbour table configuration is + * spread over multiple messages to avoid running into message + * size limits on systems with many interfaces. The first message + * in the sequence transports all not device specific data such as + * statistics, configuration, and the default parameter set. + * This message is followed by 0..n messages carrying device + * specific parameter sets. + * Although the ordering should be sufficient, NDTA_NAME can be + * used to identify sequences. The initial message can be identified + * by checking for NDTA_CONFIG. The device specific messages do + * not contain this TLV but have NDTPA_IFINDEX set to the + * corresponding interface index. + * + * To change neighbour table attributes, send RTM_SETNEIGHTBL + * with NDTA_NAME set. Changeable attribute include NDTA_THRESH[1-3], + * NDTA_GC_INTERVAL, and all TLVs in NDTA_PARMS unless marked + * otherwise. Device specific parameter sets can be changed by + * setting NDTPA_IFINDEX to the interface index of the corresponding + * device. + ****/ + +struct ndt_stats +{ + __u64 ndts_allocs; + __u64 ndts_destroys; + __u64 ndts_hash_grows; + __u64 ndts_res_failed; + __u64 ndts_lookups; + __u64 ndts_hits; + __u64 ndts_rcv_probes_mcast; + __u64 ndts_rcv_probes_ucast; + __u64 ndts_periodic_gc_runs; + __u64 ndts_forced_gc_runs; +}; + +enum { + NDTPA_UNSPEC, + NDTPA_IFINDEX, /* u32, unchangeable */ + NDTPA_REFCNT, /* u32, read-only */ + NDTPA_REACHABLE_TIME, /* u64, read-only, msecs */ + NDTPA_BASE_REACHABLE_TIME, /* u64, msecs */ + NDTPA_RETRANS_TIME, /* u64, msecs */ + NDTPA_GC_STALETIME, /* u64, msecs */ + NDTPA_DELAY_PROBE_TIME, /* u64, msecs */ + NDTPA_QUEUE_LEN, /* u32 */ + NDTPA_APP_PROBES, /* u32 */ + NDTPA_UCAST_PROBES, /* u32 */ + NDTPA_MCAST_PROBES, /* u32 */ + NDTPA_ANYCAST_DELAY, /* u64, msecs */ + NDTPA_PROXY_DELAY, /* u64, msecs */ + NDTPA_PROXY_QLEN, /* u32 */ + NDTPA_LOCKTIME, /* u64, msecs */ + __NDTPA_MAX +}; +#define NDTPA_MAX (__NDTPA_MAX - 1) + +struct ndtmsg +{ + __u8 ndtm_family; + __u8 ndtm_pad1; + __u16 ndtm_pad2; +}; + +struct ndt_config +{ + __u16 ndtc_key_len; + __u16 ndtc_entry_size; + __u32 ndtc_entries; + __u32 ndtc_last_flush; /* delta to now in msecs */ + __u32 ndtc_last_rand; /* delta to now in msecs */ + __u32 ndtc_hash_rnd; + __u32 ndtc_hash_mask; + __u32 ndtc_hash_chain_gc; + __u32 ndtc_proxy_qlen; +}; + +enum { + NDTA_UNSPEC, + NDTA_NAME, /* char *, unchangeable */ + NDTA_THRESH1, /* u32 */ + NDTA_THRESH2, /* u32 */ + NDTA_THRESH3, /* u32 */ + NDTA_CONFIG, /* struct ndt_config, read-only */ + NDTA_PARMS, /* nested TLV NDTPA_* */ + NDTA_STATS, /* struct ndt_stats, read-only */ + NDTA_GC_INTERVAL, /* u64, msecs */ + __NDTA_MAX +}; +#define NDTA_MAX (__NDTA_MAX - 1) + +#define NDTA_RTA(r) ((struct rtattr*)(((char*)(r)) + \ + NLMSG_ALIGN(sizeof(struct ndtmsg)))) +#define NDTA_PAYLOAD(n) NLMSG_PAYLOAD(n,sizeof(struct ndtmsg)) + + /**** * General form of address family dependent message. ****/ diff --git a/include/net/neighbour.h b/include/net/neighbour.h index 4f33bbc21e7f..17191ac9be70 100644 --- a/include/net/neighbour.h +++ b/include/net/neighbour.h @@ -65,6 +65,7 @@ struct neighbour; struct neigh_parms { + struct net_device *dev; struct neigh_parms *next; int (*neigh_setup)(struct neighbour *); struct neigh_table *tbl; @@ -252,6 +253,9 @@ extern int neigh_add(struct sk_buff *skb, struct nlmsghdr *nlh, void *arg); extern int neigh_delete(struct sk_buff *skb, struct nlmsghdr *nlh, void *arg); extern void neigh_app_ns(struct neighbour *n); +extern int neightbl_dump_info(struct sk_buff *skb, struct netlink_callback *cb); +extern int neightbl_set(struct sk_buff *skb, struct nlmsghdr *nlh, void *arg); + extern void neigh_for_each(struct neigh_table *tbl, void (*cb)(struct neighbour *, void *), void *cookie); extern void __neigh_for_each_release(struct neigh_table *tbl, int (*cb)(struct neighbour *)); extern void pneigh_for_each(struct neigh_table *tbl, void (*cb)(struct pneigh_entry *)); diff --git a/net/core/neighbour.c b/net/core/neighbour.c index 43bdc521e20d..0841ac78c67d 100644 --- a/net/core/neighbour.c +++ b/net/core/neighbour.c @@ -1276,9 +1276,14 @@ struct neigh_parms *neigh_parms_alloc(struct net_device *dev, INIT_RCU_HEAD(&p->rcu_head); p->reachable_time = neigh_rand_reach_time(p->base_reachable_time); - if (dev && dev->neigh_setup && dev->neigh_setup(dev, p)) { - kfree(p); - return NULL; + if (dev) { + if (dev->neigh_setup && dev->neigh_setup(dev, p)) { + kfree(p); + return NULL; + } + + dev_hold(dev); + p->dev = dev; } p->sysctl_table = NULL; write_lock_bh(&tbl->lock); @@ -1309,6 +1314,8 @@ void neigh_parms_release(struct neigh_table *tbl, struct neigh_parms *parms) *p = parms->next; parms->dead = 1; write_unlock_bh(&tbl->lock); + if (parms->dev) + dev_put(parms->dev); call_rcu(&parms->rcu_head, neigh_rcu_free_parms); return; } @@ -1546,6 +1553,308 @@ out: return err; } +static int neightbl_fill_parms(struct sk_buff *skb, struct neigh_parms *parms) +{ + struct rtattr *nest = RTA_NEST(skb, NDTA_PARMS); + + if (parms->dev) + RTA_PUT_U32(skb, NDTPA_IFINDEX, parms->dev->ifindex); + + RTA_PUT_U32(skb, NDTPA_REFCNT, atomic_read(&parms->refcnt)); + RTA_PUT_U32(skb, NDTPA_QUEUE_LEN, parms->queue_len); + RTA_PUT_U32(skb, NDTPA_PROXY_QLEN, parms->proxy_qlen); + RTA_PUT_U32(skb, NDTPA_APP_PROBES, parms->app_probes); + RTA_PUT_U32(skb, NDTPA_UCAST_PROBES, parms->ucast_probes); + RTA_PUT_U32(skb, NDTPA_MCAST_PROBES, parms->mcast_probes); + RTA_PUT_MSECS(skb, NDTPA_REACHABLE_TIME, parms->reachable_time); + RTA_PUT_MSECS(skb, NDTPA_BASE_REACHABLE_TIME, + parms->base_reachable_time); + RTA_PUT_MSECS(skb, NDTPA_GC_STALETIME, parms->gc_staletime); + RTA_PUT_MSECS(skb, NDTPA_DELAY_PROBE_TIME, parms->delay_probe_time); + RTA_PUT_MSECS(skb, NDTPA_RETRANS_TIME, parms->retrans_time); + RTA_PUT_MSECS(skb, NDTPA_ANYCAST_DELAY, parms->anycast_delay); + RTA_PUT_MSECS(skb, NDTPA_PROXY_DELAY, parms->proxy_delay); + RTA_PUT_MSECS(skb, NDTPA_LOCKTIME, parms->locktime); + + return RTA_NEST_END(skb, nest); + +rtattr_failure: + return RTA_NEST_CANCEL(skb, nest); +} + +static int neightbl_fill_info(struct neigh_table *tbl, struct sk_buff *skb, + struct netlink_callback *cb) +{ + struct nlmsghdr *nlh; + struct ndtmsg *ndtmsg; + + nlh = NLMSG_PUT_ANSWER(skb, cb, RTM_NEWNEIGHTBL, sizeof(struct ndtmsg)); + ndtmsg = NLMSG_DATA(nlh); + + NLMSG_SET_MULTIPART(nlh); + + read_lock_bh(&tbl->lock); + ndtmsg->ndtm_family = tbl->family; + + RTA_PUT_STRING(skb, NDTA_NAME, tbl->id); + RTA_PUT_MSECS(skb, NDTA_GC_INTERVAL, tbl->gc_interval); + RTA_PUT_U32(skb, NDTA_THRESH1, tbl->gc_thresh1); + RTA_PUT_U32(skb, NDTA_THRESH2, tbl->gc_thresh2); + RTA_PUT_U32(skb, NDTA_THRESH3, tbl->gc_thresh3); + + { + unsigned long now = jiffies; + unsigned int flush_delta = now - tbl->last_flush; + unsigned int rand_delta = now - tbl->last_rand; + + struct ndt_config ndc = { + .ndtc_key_len = tbl->key_len, + .ndtc_entry_size = tbl->entry_size, + .ndtc_entries = atomic_read(&tbl->entries), + .ndtc_last_flush = jiffies_to_msecs(flush_delta), + .ndtc_last_rand = jiffies_to_msecs(rand_delta), + .ndtc_hash_rnd = tbl->hash_rnd, + .ndtc_hash_mask = tbl->hash_mask, + .ndtc_hash_chain_gc = tbl->hash_chain_gc, + .ndtc_proxy_qlen = tbl->proxy_queue.qlen, + }; + + RTA_PUT(skb, NDTA_CONFIG, sizeof(ndc), &ndc); + } + + { + int cpu; + struct ndt_stats ndst; + + memset(&ndst, 0, sizeof(ndst)); + + for (cpu = 0; cpu < NR_CPUS; cpu++) { + struct neigh_statistics *st; + + if (!cpu_possible(cpu)) + continue; + + st = per_cpu_ptr(tbl->stats, cpu); + ndst.ndts_allocs += st->allocs; + ndst.ndts_destroys += st->destroys; + ndst.ndts_hash_grows += st->hash_grows; + ndst.ndts_res_failed += st->res_failed; + ndst.ndts_lookups += st->lookups; + ndst.ndts_hits += st->hits; + ndst.ndts_rcv_probes_mcast += st->rcv_probes_mcast; + ndst.ndts_rcv_probes_ucast += st->rcv_probes_ucast; + ndst.ndts_periodic_gc_runs += st->periodic_gc_runs; + ndst.ndts_forced_gc_runs += st->forced_gc_runs; + } + + RTA_PUT(skb, NDTA_STATS, sizeof(ndst), &ndst); + } + + BUG_ON(tbl->parms.dev); + if (neightbl_fill_parms(skb, &tbl->parms) < 0) + goto rtattr_failure; + + read_unlock_bh(&tbl->lock); + return NLMSG_END(skb, nlh); + +rtattr_failure: + read_unlock_bh(&tbl->lock); + return NLMSG_CANCEL(skb, nlh); + +nlmsg_failure: + return -1; +} + +static int neightbl_fill_param_info(struct neigh_table *tbl, + struct neigh_parms *parms, + struct sk_buff *skb, + struct netlink_callback *cb) +{ + struct ndtmsg *ndtmsg; + struct nlmsghdr *nlh; + + nlh = NLMSG_PUT_ANSWER(skb, cb, RTM_NEWNEIGHTBL, sizeof(struct ndtmsg)); + ndtmsg = NLMSG_DATA(nlh); + + NLMSG_SET_MULTIPART(nlh); + + read_lock_bh(&tbl->lock); + ndtmsg->ndtm_family = tbl->family; + RTA_PUT_STRING(skb, NDTA_NAME, tbl->id); + + if (neightbl_fill_parms(skb, parms) < 0) + goto rtattr_failure; + + read_unlock_bh(&tbl->lock); + return NLMSG_END(skb, nlh); + +rtattr_failure: + read_unlock_bh(&tbl->lock); + return NLMSG_CANCEL(skb, nlh); + +nlmsg_failure: + return -1; +} + +static inline struct neigh_parms *lookup_neigh_params(struct neigh_table *tbl, + int ifindex) +{ + struct neigh_parms *p; + + for (p = &tbl->parms; p; p = p->next) + if ((p->dev && p->dev->ifindex == ifindex) || + (!p->dev && !ifindex)) + return p; + + return NULL; +} + +int neightbl_set(struct sk_buff *skb, struct nlmsghdr *nlh, void *arg) +{ + struct neigh_table *tbl; + struct ndtmsg *ndtmsg = NLMSG_DATA(nlh); + struct rtattr **tb = arg; + int err = -EINVAL; + + if (!tb[NDTA_NAME - 1] || !RTA_PAYLOAD(tb[NDTA_NAME - 1])) + return -EINVAL; + + read_lock(&neigh_tbl_lock); + for (tbl = neigh_tables; tbl; tbl = tbl->next) { + if (ndtmsg->ndtm_family && tbl->family != ndtmsg->ndtm_family) + continue; + + if (!rtattr_strcmp(tb[NDTA_NAME - 1], tbl->id)) + break; + } + + if (tbl == NULL) { + err = -ENOENT; + goto errout; + } + + /* + * We acquire tbl->lock to be nice to the periodic timers and + * make sure they always see a consistent set of values. + */ + write_lock_bh(&tbl->lock); + + if (tb[NDTA_THRESH1 - 1]) + tbl->gc_thresh1 = RTA_GET_U32(tb[NDTA_THRESH1 - 1]); + + if (tb[NDTA_THRESH2 - 1]) + tbl->gc_thresh2 = RTA_GET_U32(tb[NDTA_THRESH2 - 1]); + + if (tb[NDTA_THRESH3 - 1]) + tbl->gc_thresh3 = RTA_GET_U32(tb[NDTA_THRESH3 - 1]); + + if (tb[NDTA_GC_INTERVAL - 1]) + tbl->gc_interval = RTA_GET_MSECS(tb[NDTA_GC_INTERVAL - 1]); + + if (tb[NDTA_PARMS - 1]) { + struct rtattr *tbp[NDTPA_MAX]; + struct neigh_parms *p; + u32 ifindex = 0; + + if (rtattr_parse_nested(tbp, NDTPA_MAX, tb[NDTA_PARMS - 1]) < 0) + goto rtattr_failure; + + if (tbp[NDTPA_IFINDEX - 1]) + ifindex = RTA_GET_U32(tbp[NDTPA_IFINDEX - 1]); + + p = lookup_neigh_params(tbl, ifindex); + if (p == NULL) { + err = -ENOENT; + goto rtattr_failure; + } + + if (tbp[NDTPA_QUEUE_LEN - 1]) + p->queue_len = RTA_GET_U32(tbp[NDTPA_QUEUE_LEN - 1]); + + if (tbp[NDTPA_PROXY_QLEN - 1]) + p->proxy_qlen = RTA_GET_U32(tbp[NDTPA_PROXY_QLEN - 1]); + + if (tbp[NDTPA_APP_PROBES - 1]) + p->app_probes = RTA_GET_U32(tbp[NDTPA_APP_PROBES - 1]); + + if (tbp[NDTPA_UCAST_PROBES - 1]) + p->ucast_probes = + RTA_GET_U32(tbp[NDTPA_UCAST_PROBES - 1]); + + if (tbp[NDTPA_MCAST_PROBES - 1]) + p->mcast_probes = + RTA_GET_U32(tbp[NDTPA_MCAST_PROBES - 1]); + + if (tbp[NDTPA_BASE_REACHABLE_TIME - 1]) + p->base_reachable_time = + RTA_GET_MSECS(tbp[NDTPA_BASE_REACHABLE_TIME - 1]); + + if (tbp[NDTPA_GC_STALETIME - 1]) + p->gc_staletime = + RTA_GET_MSECS(tbp[NDTPA_GC_STALETIME - 1]); + + if (tbp[NDTPA_DELAY_PROBE_TIME - 1]) + p->delay_probe_time = + RTA_GET_MSECS(tbp[NDTPA_DELAY_PROBE_TIME - 1]); + + if (tbp[NDTPA_RETRANS_TIME - 1]) + p->retrans_time = + RTA_GET_MSECS(tbp[NDTPA_RETRANS_TIME - 1]); + + if (tbp[NDTPA_ANYCAST_DELAY - 1]) + p->anycast_delay = + RTA_GET_MSECS(tbp[NDTPA_ANYCAST_DELAY - 1]); + + if (tbp[NDTPA_PROXY_DELAY - 1]) + p->proxy_delay = + RTA_GET_MSECS(tbp[NDTPA_PROXY_DELAY - 1]); + + if (tbp[NDTPA_LOCKTIME - 1]) + p->locktime = RTA_GET_MSECS(tbp[NDTPA_LOCKTIME - 1]); + } + + err = 0; + +rtattr_failure: + write_unlock_bh(&tbl->lock); +errout: + read_unlock(&neigh_tbl_lock); + return err; +} + +int neightbl_dump_info(struct sk_buff *skb, struct netlink_callback *cb) +{ + int idx, family; + int s_idx = cb->args[0]; + struct neigh_table *tbl; + + family = ((struct rtgenmsg *)NLMSG_DATA(cb->nlh))->rtgen_family; + + read_lock(&neigh_tbl_lock); + for (tbl = neigh_tables, idx = 0; tbl; tbl = tbl->next) { + struct neigh_parms *p; + + if (idx < s_idx || (family && tbl->family != family)) + continue; + + if (neightbl_fill_info(tbl, skb, cb) <= 0) + break; + + for (++idx, p = tbl->parms.next; p; p = p->next, idx++) { + if (idx < s_idx) + continue; + + if (neightbl_fill_param_info(tbl, p, skb, cb) <= 0) + goto out; + } + + } +out: + read_unlock(&neigh_tbl_lock); + cb->args[0] = idx; + + return skb->len; +} static int neigh_fill_info(struct sk_buff *skb, struct neighbour *n, u32 pid, u32 seq, int event) @@ -2352,6 +2661,8 @@ EXPORT_SYMBOL(neigh_update); EXPORT_SYMBOL(neigh_update_hhs); EXPORT_SYMBOL(pneigh_enqueue); EXPORT_SYMBOL(pneigh_lookup); +EXPORT_SYMBOL(neightbl_dump_info); +EXPORT_SYMBOL(neightbl_set); #ifdef CONFIG_ARPD EXPORT_SYMBOL(neigh_app_ns); diff --git a/net/core/rtnetlink.c b/net/core/rtnetlink.c index 00caf4b318b2..56a20f014b8a 100644 --- a/net/core/rtnetlink.c +++ b/net/core/rtnetlink.c @@ -100,6 +100,7 @@ static const int rtm_min[RTM_NR_FAMILIES] = [RTM_FAM(RTM_NEWPREFIX)] = NLMSG_LENGTH(sizeof(struct rtgenmsg)), [RTM_FAM(RTM_GETMULTICAST)] = NLMSG_LENGTH(sizeof(struct rtgenmsg)), [RTM_FAM(RTM_GETANYCAST)] = NLMSG_LENGTH(sizeof(struct rtgenmsg)), + [RTM_FAM(RTM_NEWNEIGHTBL)] = NLMSG_LENGTH(sizeof(struct ndtmsg)), }; static const int rta_max[RTM_NR_FAMILIES] = @@ -113,6 +114,7 @@ static const int rta_max[RTM_NR_FAMILIES] = [RTM_FAM(RTM_NEWTCLASS)] = TCA_MAX, [RTM_FAM(RTM_NEWTFILTER)] = TCA_MAX, [RTM_FAM(RTM_NEWACTION)] = TCAA_MAX, + [RTM_FAM(RTM_NEWNEIGHTBL)] = NDTA_MAX, }; void __rta_fill(struct sk_buff *skb, int attrtype, int attrlen, const void *data) @@ -649,14 +651,16 @@ static void rtnetlink_rcv(struct sock *sk, int len) static struct rtnetlink_link link_rtnetlink_table[RTM_NR_MSGTYPES] = { - [RTM_GETLINK - RTM_BASE] = { .dumpit = rtnetlink_dump_ifinfo }, - [RTM_SETLINK - RTM_BASE] = { .doit = do_setlink }, - [RTM_GETADDR - RTM_BASE] = { .dumpit = rtnetlink_dump_all }, - [RTM_GETROUTE - RTM_BASE] = { .dumpit = rtnetlink_dump_all }, - [RTM_NEWNEIGH - RTM_BASE] = { .doit = neigh_add }, - [RTM_DELNEIGH - RTM_BASE] = { .doit = neigh_delete }, - [RTM_GETNEIGH - RTM_BASE] = { .dumpit = neigh_dump_info }, - [RTM_GETRULE - RTM_BASE] = { .dumpit = rtnetlink_dump_all }, + [RTM_GETLINK - RTM_BASE] = { .dumpit = rtnetlink_dump_ifinfo }, + [RTM_SETLINK - RTM_BASE] = { .doit = do_setlink }, + [RTM_GETADDR - RTM_BASE] = { .dumpit = rtnetlink_dump_all }, + [RTM_GETROUTE - RTM_BASE] = { .dumpit = rtnetlink_dump_all }, + [RTM_NEWNEIGH - RTM_BASE] = { .doit = neigh_add }, + [RTM_DELNEIGH - RTM_BASE] = { .doit = neigh_delete }, + [RTM_GETNEIGH - RTM_BASE] = { .dumpit = neigh_dump_info }, + [RTM_GETRULE - RTM_BASE] = { .dumpit = rtnetlink_dump_all }, + [RTM_GETNEIGHTBL - RTM_BASE] = { .dumpit = neightbl_dump_info }, + [RTM_SETNEIGHTBL - RTM_BASE] = { .doit = neightbl_set }, }; static int rtnetlink_event(struct notifier_block *this, unsigned long event, void *ptr) diff --git a/security/selinux/nlmsgtab.c b/security/selinux/nlmsgtab.c index f0fb6d76f7c5..92b057becb4b 100644 --- a/security/selinux/nlmsgtab.c +++ b/security/selinux/nlmsgtab.c @@ -63,6 +63,8 @@ static struct nlmsg_perm nlmsg_route_perms[] = { RTM_GETPREFIX, NETLINK_ROUTE_SOCKET__NLMSG_READ }, { RTM_GETMULTICAST, NETLINK_ROUTE_SOCKET__NLMSG_READ }, { RTM_GETANYCAST, NETLINK_ROUTE_SOCKET__NLMSG_READ }, + { RTM_GETNEIGHTBL, NETLINK_ROUTE_SOCKET__NLMSG_READ }, + { RTM_SETNEIGHTBL, NETLINK_ROUTE_SOCKET__NLMSG_WRITE }, }; static struct nlmsg_perm nlmsg_firewall_perms[] = -- cgit v1.2.3 From c52a3f89f882b84fc422000655c023fe73e701cf Mon Sep 17 00:00:00 2001 From: Thomas Graf Date: Sat, 18 Jun 2005 22:51:26 -0700 Subject: [NETLINK]: Fix RTA_NEST_CANCEL(). Only skb_trim() if 'start' is non-NULL. Signed-off-by: Thomas Graf Signed-off-by: David S. Miller --- include/linux/rtnetlink.h | 3 ++- 1 file changed, 2 insertions(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/rtnetlink.h b/include/linux/rtnetlink.h index 5a5cda160267..6fff8c4c99c7 100644 --- a/include/linux/rtnetlink.h +++ b/include/linux/rtnetlink.h @@ -924,7 +924,8 @@ extern void __rta_fill(struct sk_buff *skb, int attrtype, int attrlen, const voi (skb)->len; }) #define RTA_NEST_CANCEL(skb, start) \ -({ skb_trim(skb, (unsigned char *) (start) - (skb)->data); \ +({ if (start) \ + skb_trim(skb, (unsigned char *) (start) - (skb)->data); \ -1; }) #define RTA_GET_U32(rta) \ -- cgit v1.2.3 From 8f48bcd4ef11a69add178fc3111a77e7ee95bacd Mon Sep 17 00:00:00 2001 From: Thomas Graf Date: Sat, 18 Jun 2005 22:52:36 -0700 Subject: [RTNETLINK]: Add RTA_(PUT|GET) shortcuts for u8, u16, and flag Signed-off-by: Thomas Graf Signed-off-by: David S. Miller --- include/linux/rtnetlink.h | 23 +++++++++++++++++++++++ 1 file changed, 23 insertions(+) (limited to 'include/linux') diff --git a/include/linux/rtnetlink.h b/include/linux/rtnetlink.h index 6fff8c4c99c7..e68dbf0bf579 100644 --- a/include/linux/rtnetlink.h +++ b/include/linux/rtnetlink.h @@ -897,6 +897,14 @@ extern void __rta_fill(struct sk_buff *skb, int attrtype, int attrlen, const voi goto rtattr_failure; \ memcpy(skb_put(skb, RTA_ALIGN(attrlen)), data, attrlen); }) +#define RTA_PUT_U8(skb, attrtype, value) \ +({ u8 _tmp = (value); \ + RTA_PUT(skb, attrtype, sizeof(u8), &_tmp); }) + +#define RTA_PUT_U16(skb, attrtype, value) \ +({ u16 _tmp = (value); \ + RTA_PUT(skb, attrtype, sizeof(u16), &_tmp); }) + #define RTA_PUT_U32(skb, attrtype, value) \ ({ u32 _tmp = (value); \ RTA_PUT(skb, attrtype, sizeof(u32), &_tmp); }) @@ -914,6 +922,9 @@ extern void __rta_fill(struct sk_buff *skb, int attrtype, int attrlen, const voi #define RTA_PUT_STRING(skb, attrtype, value) \ RTA_PUT(skb, attrtype, strlen(value) + 1, value) +#define RTA_PUT_FLAG(skb, attrtype) \ + RTA_PUT(skb, attrtype, 0, NULL); + #define RTA_NEST(skb, type) \ ({ struct rtattr *__start = (struct rtattr *) (skb)->tail; \ RTA_PUT(skb, type, 0, NULL); \ @@ -928,6 +939,16 @@ extern void __rta_fill(struct sk_buff *skb, int attrtype, int attrlen, const voi skb_trim(skb, (unsigned char *) (start) - (skb)->data); \ -1; }) +#define RTA_GET_U8(rta) \ +({ if (!rta || RTA_PAYLOAD(rta) < sizeof(u8)) \ + goto rtattr_failure; \ + *(u8 *) RTA_DATA(rta); }) + +#define RTA_GET_U16(rta) \ +({ if (!rta || RTA_PAYLOAD(rta) < sizeof(u16)) \ + goto rtattr_failure; \ + *(u16 *) RTA_DATA(rta); }) + #define RTA_GET_U32(rta) \ ({ if (!rta || RTA_PAYLOAD(rta) < sizeof(u32)) \ goto rtattr_failure; \ @@ -940,6 +961,8 @@ extern void __rta_fill(struct sk_buff *skb, int attrtype, int attrlen, const voi memcpy(&_tmp, RTA_DATA(rta), sizeof(_tmp)); \ _tmp; }) +#define RTA_GET_FLAG(rta) (!!(rta)) + #define RTA_GET_SECS(rta) ((unsigned long) RTA_GET_U64(rta) * HZ) #define RTA_GET_MSECS(rta) (msecs_to_jiffies((unsigned long) RTA_GET_U64(rta))) -- cgit v1.2.3 From 1797754ea7ee5e0d859b0a32506ff999f8d5fb71 Mon Sep 17 00:00:00 2001 From: Thomas Graf Date: Sat, 18 Jun 2005 22:53:48 -0700 Subject: [NETLINK]: Introduce NLMSG_NEW macro to better handle netlink flags Introduces a new macro NLMSG_NEW which extends NLMSG_PUT but takes a flags argument. NLMSG_PUT stays there for compatibility but now calls NLMSG_NEW with flags == 0. NLMSG_PUT_ANSWER is renamed to NLMSG_NEW_ANSWER which now also takes a flags argument. Also converts the users of NLMSG_PUT_ANSWER to use NLMSG_NEW_ANSWER and fixes the two direct users of __nlmsg_put to either provide the flags or use NLMSG_NEW(_ANSWER). Signed-off-by: Thomas Graf Signed-off-by: David S. Miller --- include/linux/netlink.h | 17 ++++++++++------- net/core/neighbour.c | 8 ++++---- net/netlink/af_netlink.c | 8 +++++--- 3 files changed, 19 insertions(+), 14 deletions(-) (limited to 'include/linux') diff --git a/include/linux/netlink.h b/include/linux/netlink.h index 8d1cb419a930..e38407a23d04 100644 --- a/include/linux/netlink.h +++ b/include/linux/netlink.h @@ -156,7 +156,7 @@ struct netlink_notify }; static __inline__ struct nlmsghdr * -__nlmsg_put(struct sk_buff *skb, u32 pid, u32 seq, int type, int len) +__nlmsg_put(struct sk_buff *skb, u32 pid, u32 seq, int type, int len, int flags) { struct nlmsghdr *nlh; int size = NLMSG_LENGTH(len); @@ -164,20 +164,23 @@ __nlmsg_put(struct sk_buff *skb, u32 pid, u32 seq, int type, int len) nlh = (struct nlmsghdr*)skb_put(skb, NLMSG_ALIGN(size)); nlh->nlmsg_type = type; nlh->nlmsg_len = size; - nlh->nlmsg_flags = 0; + nlh->nlmsg_flags = flags; nlh->nlmsg_pid = pid; nlh->nlmsg_seq = seq; return nlh; } -#define NLMSG_PUT(skb, pid, seq, type, len) \ +#define NLMSG_NEW(skb, pid, seq, type, len, flags) \ ({ if (skb_tailroom(skb) < (int)NLMSG_SPACE(len)) \ goto nlmsg_failure; \ - __nlmsg_put(skb, pid, seq, type, len); }) + __nlmsg_put(skb, pid, seq, type, len, flags); }) + +#define NLMSG_PUT(skb, pid, seq, type, len) \ + NLMSG_NEW(skb, pid, seq, type, len, 0) -#define NLMSG_PUT_ANSWER(skb, cb, type, len) \ - NLMSG_PUT(skb, NETLINK_CB((cb)->skb).pid, \ - (cb)->nlh->nlmsg_seq, type, len) +#define NLMSG_NEW_ANSWER(skb, cb, type, len, flags) \ + NLMSG_NEW(skb, NETLINK_CB((cb)->skb).pid, \ + (cb)->nlh->nlmsg_seq, type, len, flags) #define NLMSG_END(skb, nlh) \ ({ (nlh)->nlmsg_len = (skb)->tail - (unsigned char *) (nlh); \ diff --git a/net/core/neighbour.c b/net/core/neighbour.c index 2296a145fb78..0fb742e228cc 100644 --- a/net/core/neighbour.c +++ b/net/core/neighbour.c @@ -1590,8 +1590,8 @@ static int neightbl_fill_info(struct neigh_table *tbl, struct sk_buff *skb, struct nlmsghdr *nlh; struct ndtmsg *ndtmsg; - nlh = NLMSG_PUT_ANSWER(skb, cb, RTM_NEWNEIGHTBL, sizeof(struct ndtmsg)); - nlh->nlmsg_flags |= NLM_F_MULTI; + nlh = NLMSG_NEW_ANSWER(skb, cb, RTM_NEWNEIGHTBL, sizeof(struct ndtmsg), + NLM_F_MULTI); ndtmsg = NLMSG_DATA(nlh); @@ -1675,8 +1675,8 @@ static int neightbl_fill_param_info(struct neigh_table *tbl, struct ndtmsg *ndtmsg; struct nlmsghdr *nlh; - nlh = NLMSG_PUT_ANSWER(skb, cb, RTM_NEWNEIGHTBL, sizeof(struct ndtmsg)); - nlh->nlmsg_flags |= NLM_F_MULTI; + nlh = NLMSG_NEW_ANSWER(skb, cb, RTM_NEWNEIGHTBL, sizeof(struct ndtmsg), + NLM_F_MULTI); ndtmsg = NLMSG_DATA(nlh); diff --git a/net/netlink/af_netlink.c b/net/netlink/af_netlink.c index e41ce458c2a9..70bcd4744d93 100644 --- a/net/netlink/af_netlink.c +++ b/net/netlink/af_netlink.c @@ -1095,8 +1095,7 @@ static int netlink_dump(struct sock *sk) return 0; } - nlh = __nlmsg_put(skb, NETLINK_CB(cb->skb).pid, cb->nlh->nlmsg_seq, NLMSG_DONE, sizeof(int)); - nlh->nlmsg_flags |= NLM_F_MULTI; + nlh = NLMSG_NEW_ANSWER(skb, cb, NLMSG_DONE, sizeof(len), NLM_F_MULTI); memcpy(NLMSG_DATA(nlh), &len, sizeof(len)); skb_queue_tail(&sk->sk_receive_queue, skb); sk->sk_data_ready(sk, skb->len); @@ -1107,6 +1106,9 @@ static int netlink_dump(struct sock *sk) netlink_destroy_callback(cb); return 0; + +nlmsg_failure: + return -ENOBUFS; } int netlink_dump_start(struct sock *ssk, struct sk_buff *skb, @@ -1178,7 +1180,7 @@ void netlink_ack(struct sk_buff *in_skb, struct nlmsghdr *nlh, int err) } rep = __nlmsg_put(skb, NETLINK_CB(in_skb).pid, nlh->nlmsg_seq, - NLMSG_ERROR, sizeof(struct nlmsgerr)); + NLMSG_ERROR, sizeof(struct nlmsgerr), 0); errmsg = NLMSG_DATA(rep); errmsg->error = err; memcpy(&errmsg->msg, nlh, err ? nlh->nlmsg_len : sizeof(struct nlmsghdr)); -- cgit v1.2.3 From 0603eac0d6b77acac5924a2734228cbaf072f993 Mon Sep 17 00:00:00 2001 From: Herbert Xu Date: Sat, 18 Jun 2005 22:54:36 -0700 Subject: [IPSEC]: Add XFRMA_SA/XFRMA_POLICY for delete notification This patch changes the format of the XFRM_MSG_DELSA and XFRM_MSG_DELPOLICY notification so that the main message sent is of the same format as that received by the kernel if the original message was via netlink. This also means that we won't lose the byid information carried in km_event. Since this user interface is introduced by Jamal's patch we can still afford to change it. Signed-off-by: Herbert Xu Signed-off-by: David S. Miller --- include/linux/xfrm.h | 2 ++ net/xfrm/xfrm_user.c | 47 +++++++++++++++++++++++++++++++++++++++++++---- 2 files changed, 45 insertions(+), 4 deletions(-) (limited to 'include/linux') diff --git a/include/linux/xfrm.h b/include/linux/xfrm.h index 03bc600516ea..d68391a9b9f3 100644 --- a/include/linux/xfrm.h +++ b/include/linux/xfrm.h @@ -174,6 +174,8 @@ enum xfrm_attr_type_t { XFRMA_ALG_COMP, /* struct xfrm_algo */ XFRMA_ENCAP, /* struct xfrm_algo + struct xfrm_encap_tmpl */ XFRMA_TMPL, /* 1 or more struct xfrm_user_tmpl */ + XFRMA_SA, + XFRMA_POLICY, __XFRMA_MAX #define XFRMA_MAX (__XFRMA_MAX - 1) diff --git a/net/xfrm/xfrm_user.c b/net/xfrm/xfrm_user.c index ffe1b217347c..5ce8558eac91 100644 --- a/net/xfrm/xfrm_user.c +++ b/net/xfrm/xfrm_user.c @@ -1168,7 +1168,7 @@ nlmsg_failure: static int inline xfrm_sa_len(struct xfrm_state *x) { - int l = NLMSG_LENGTH(sizeof(struct xfrm_usersa_info)); + int l = 0; if (x->aalg) l += RTA_SPACE(sizeof(*x->aalg) + (x->aalg->alg_key_len+7)/8); if (x->ealg) @@ -1184,20 +1184,39 @@ static int inline xfrm_sa_len(struct xfrm_state *x) static int xfrm_notify_sa(struct xfrm_state *x, struct km_event *c) { struct xfrm_usersa_info *p; + struct xfrm_usersa_id *id; struct nlmsghdr *nlh; struct sk_buff *skb; unsigned char *b; int len = xfrm_sa_len(x); + int headlen; + + headlen = sizeof(*p); + if (c->event == XFRM_MSG_DELSA) { + len += RTA_SPACE(headlen); + headlen = sizeof(*id); + } + len += NLMSG_SPACE(headlen); skb = alloc_skb(len, GFP_ATOMIC); if (skb == NULL) return -ENOMEM; b = skb->tail; - nlh = NLMSG_PUT(skb, c->pid, c->seq, c->event, sizeof(*p)); + nlh = NLMSG_PUT(skb, c->pid, c->seq, c->event, headlen); nlh->nlmsg_flags = 0; p = NLMSG_DATA(nlh); + if (c->event == XFRM_MSG_DELSA) { + id = NLMSG_DATA(nlh); + memcpy(&id->daddr, &x->id.daddr, sizeof(id->daddr)); + id->spi = x->id.spi; + id->family = x->props.family; + id->proto = x->id.proto; + + p = RTA_DATA(__RTA_PUT(skb, XFRMA_SA, sizeof(*p))); + } + copy_to_user_state(x, p); if (x->aalg) @@ -1398,20 +1417,39 @@ static int xfrm_exp_policy_notify(struct xfrm_policy *xp, int dir, struct km_eve static int xfrm_notify_policy(struct xfrm_policy *xp, int dir, struct km_event *c) { struct xfrm_userpolicy_info *p; + struct xfrm_userpolicy_id *id; struct nlmsghdr *nlh; struct sk_buff *skb; unsigned char *b; int len = RTA_SPACE(sizeof(struct xfrm_user_tmpl) * xp->xfrm_nr); - len += NLMSG_SPACE(sizeof(struct xfrm_userpolicy_info)); + int headlen; + + headlen = sizeof(*p); + if (c->event == XFRM_MSG_DELPOLICY) { + len += RTA_SPACE(headlen); + headlen = sizeof(*id); + } + len += NLMSG_SPACE(headlen); skb = alloc_skb(len, GFP_ATOMIC); if (skb == NULL) return -ENOMEM; b = skb->tail; - nlh = NLMSG_PUT(skb, c->pid, c->seq, c->event, sizeof(*p)); + nlh = NLMSG_PUT(skb, c->pid, c->seq, c->event, headlen); p = NLMSG_DATA(nlh); + if (c->event == XFRM_MSG_DELPOLICY) { + id = NLMSG_DATA(nlh); + memset(id, 0, sizeof(*id)); + id->dir = dir; + if (c->data.byid) + id->index = xp->index; + else + memcpy(&id->sel, &xp->selector, sizeof(id->sel)); + + p = RTA_DATA(__RTA_PUT(skb, XFRMA_POLICY, sizeof(*p))); + } nlh->nlmsg_flags = 0; @@ -1424,6 +1462,7 @@ static int xfrm_notify_policy(struct xfrm_policy *xp, int dir, struct km_event * return netlink_broadcast(xfrm_nl, skb, 0, XFRMGRP_POLICY, GFP_ATOMIC); nlmsg_failure: +rtattr_failure: kfree_skb(skb); return -1; } -- cgit v1.2.3