From ceacc2c1c85ac498ca4cf297bdfe5b4aaa9fd0e0 Mon Sep 17 00:00:00 2001 From: Peter Zijlstra Date: Fri, 16 Jan 2009 14:46:40 +0100 Subject: sched: make plist a library facility Ingo Molnar wrote: > here's a new build failure with tip/sched/rt: > > LD .tmp_vmlinux1 > kernel/built-in.o: In function `set_curr_task_rt': > sched.c:(.text+0x3675): undefined reference to `plist_del' > kernel/built-in.o: In function `pick_next_task_rt': > sched.c:(.text+0x37ce): undefined reference to `plist_del' > kernel/built-in.o: In function `enqueue_pushable_task': > sched.c:(.text+0x381c): undefined reference to `plist_del' Eliminate the plist library kconfig and make it available unconditionally. Signed-off-by: Peter Zijlstra Signed-off-by: Ingo Molnar --- lib/Kconfig | 6 ------ lib/Makefile | 4 ++-- 2 files changed, 2 insertions(+), 8 deletions(-) (limited to 'lib') diff --git a/lib/Kconfig b/lib/Kconfig index 03c2c24b9083..fc8ea1ca59d8 100644 --- a/lib/Kconfig +++ b/lib/Kconfig @@ -136,12 +136,6 @@ config TEXTSEARCH_BM config TEXTSEARCH_FSM tristate -# -# plist support is select#ed if needed -# -config PLIST - boolean - config HAS_IOMEM boolean depends on !NO_IOMEM diff --git a/lib/Makefile b/lib/Makefile index 32b0e64ded27..902d73851044 100644 --- a/lib/Makefile +++ b/lib/Makefile @@ -11,7 +11,8 @@ lib-y := ctype.o string.o vsprintf.o cmdline.o \ rbtree.o radix-tree.o dump_stack.o \ idr.o int_sqrt.o extable.o prio_tree.o \ sha1.o irq_regs.o reciprocal_div.o argv_split.o \ - proportions.o prio_heap.o ratelimit.o show_mem.o is_single_threaded.o + proportions.o prio_heap.o ratelimit.o show_mem.o \ + is_single_threaded.o plist.o lib-$(CONFIG_MMU) += ioremap.o lib-$(CONFIG_SMP) += cpumask.o @@ -40,7 +41,6 @@ lib-$(CONFIG_GENERIC_FIND_NEXT_BIT) += find_next_bit.o lib-$(CONFIG_GENERIC_FIND_LAST_BIT) += find_last_bit.o obj-$(CONFIG_GENERIC_HWEIGHT) += hweight.o obj-$(CONFIG_LOCK_KERNEL) += kernel_lock.o -obj-$(CONFIG_PLIST) += plist.o obj-$(CONFIG_DEBUG_PREEMPT) += smp_processor_id.o obj-$(CONFIG_DEBUG_LIST) += list_debug.o obj-$(CONFIG_DEBUG_OBJECTS) += debugobjects.o -- cgit v1.2.3-59-g8ed1b From ff491a7334acfd74e515c896632e37e401f52676 Mon Sep 17 00:00:00 2001 From: Pablo Neira Ayuso Date: Thu, 5 Feb 2009 23:56:36 -0800 Subject: netlink: change return-value logic of netlink_broadcast() Currently, netlink_broadcast() reports errors to the caller if no messages at all were delivered: 1) If, at least, one message has been delivered correctly, returns 0. 2) Otherwise, if no messages at all were delivered due to skb_clone() failure, return -ENOBUFS. 3) Otherwise, if there are no listeners, return -ESRCH. With this patch, the caller knows if the delivery of any of the messages to the listeners have failed: 1) If it fails to deliver any message (for whatever reason), return -ENOBUFS. 2) Otherwise, if all messages were delivered OK, returns 0. 3) Otherwise, if no listeners, return -ESRCH. In the current ctnetlink code and in Netfilter in general, we can add reliable logging and connection tracking event delivery by dropping the packets whose events were not successfully delivered over Netlink. Of course, this option would be settable via /proc as this approach reduces performance (in terms of filtered connections per seconds by a stateful firewall) but providing reliable logging and event delivery (for conntrackd) in return. This patch also changes some clients of netlink_broadcast() that may report ENOBUFS errors via printk. This error handling is not of any help. Instead, the userspace daemons that are listening to those netlink messages should resync themselves with the kernel-side if they hit ENOBUFS. BTW, netlink_broadcast() clients include those that call cn_netlink_send(), nlmsg_multicast() and genlmsg_multicast() since they internally call netlink_broadcast() and return its error value. Signed-off-by: Pablo Neira Ayuso Signed-off-by: David S. Miller --- drivers/acpi/event.c | 6 +----- drivers/scsi/scsi_transport_fc.c | 16 ++++------------ drivers/scsi/scsi_transport_iscsi.c | 12 ++---------- drivers/video/uvesafb.c | 5 ++++- fs/dquot.c | 5 +---- lib/kobject_uevent.c | 3 +++ net/netlink/af_netlink.c | 8 ++++++-- net/wimax/op-msg.c | 9 +++------ net/wimax/stack.c | 12 ++++-------- 9 files changed, 28 insertions(+), 48 deletions(-) (limited to 'lib') diff --git a/drivers/acpi/event.c b/drivers/acpi/event.c index 0c24bd4d6562..aeb7e5fb4a04 100644 --- a/drivers/acpi/event.c +++ b/drivers/acpi/event.c @@ -235,11 +235,7 @@ int acpi_bus_generate_netlink_event(const char *device_class, return result; } - result = - genlmsg_multicast(skb, 0, acpi_event_mcgrp.id, GFP_ATOMIC); - if (result) - ACPI_DEBUG_PRINT((ACPI_DB_INFO, - "Failed to send a Genetlink message!\n")); + genlmsg_multicast(skb, 0, acpi_event_mcgrp.id, GFP_ATOMIC); return 0; } diff --git a/drivers/scsi/scsi_transport_fc.c b/drivers/scsi/scsi_transport_fc.c index 5f77417ed585..3ee4eb40abcf 100644 --- a/drivers/scsi/scsi_transport_fc.c +++ b/drivers/scsi/scsi_transport_fc.c @@ -533,12 +533,8 @@ fc_host_post_event(struct Scsi_Host *shost, u32 event_number, event->event_code = event_code; event->event_data = event_data; - err = nlmsg_multicast(scsi_nl_sock, skb, 0, SCSI_NL_GRP_FC_EVENTS, - GFP_KERNEL); - if (err && (err != -ESRCH)) /* filter no recipient errors */ - /* nlmsg_multicast already kfree_skb'd */ - goto send_fail; - + nlmsg_multicast(scsi_nl_sock, skb, 0, SCSI_NL_GRP_FC_EVENTS, + GFP_KERNEL); return; send_fail_skb: @@ -607,12 +603,8 @@ fc_host_post_vendor_event(struct Scsi_Host *shost, u32 event_number, event->event_code = FCH_EVT_VENDOR_UNIQUE; memcpy(&event->event_data, data_buf, data_len); - err = nlmsg_multicast(scsi_nl_sock, skb, 0, SCSI_NL_GRP_FC_EVENTS, - GFP_KERNEL); - if (err && (err != -ESRCH)) /* filter no recipient errors */ - /* nlmsg_multicast already kfree_skb'd */ - goto send_vendor_fail; - + nlmsg_multicast(scsi_nl_sock, skb, 0, SCSI_NL_GRP_FC_EVENTS, + GFP_KERNEL); return; send_vendor_fail_skb: diff --git a/drivers/scsi/scsi_transport_iscsi.c b/drivers/scsi/scsi_transport_iscsi.c index 75c9297694cb..2adfab8c11c1 100644 --- a/drivers/scsi/scsi_transport_iscsi.c +++ b/drivers/scsi/scsi_transport_iscsi.c @@ -966,15 +966,7 @@ iscsi_if_transport_lookup(struct iscsi_transport *tt) static int iscsi_broadcast_skb(struct sk_buff *skb, gfp_t gfp) { - int rc; - - rc = netlink_broadcast(nls, skb, 0, 1, gfp); - if (rc < 0) { - printk(KERN_ERR "iscsi: can not broadcast skb (%d)\n", rc); - return rc; - } - - return 0; + return netlink_broadcast(nls, skb, 0, 1, gfp); } static int @@ -1207,7 +1199,7 @@ int iscsi_session_event(struct iscsi_cls_session *session, * the user and when the daemon is restarted it will handle it */ rc = iscsi_broadcast_skb(skb, GFP_KERNEL); - if (rc < 0) + if (rc == -ESRCH) iscsi_cls_session_printk(KERN_ERR, session, "Cannot notify userspace of session " "event %u. Check iscsi daemon\n", diff --git a/drivers/video/uvesafb.c b/drivers/video/uvesafb.c index 6c2d37fdd3b9..74ae75899009 100644 --- a/drivers/video/uvesafb.c +++ b/drivers/video/uvesafb.c @@ -204,8 +204,11 @@ static int uvesafb_exec(struct uvesafb_ktask *task) } else { v86d_started = 1; err = cn_netlink_send(m, 0, gfp_any()); + if (err == -ENOBUFS) + err = 0; } - } + } else if (err == -ENOBUFS) + err = 0; if (!err && !(task->t.flags & TF_EXIT)) err = !wait_for_completion_timeout(task->done, diff --git a/fs/dquot.c b/fs/dquot.c index bca3cac4bee7..d6add0bf5ad3 100644 --- a/fs/dquot.c +++ b/fs/dquot.c @@ -1057,10 +1057,7 @@ static void send_warning(const struct dquot *dquot, const char warntype) goto attr_err_out; genlmsg_end(skb, msg_head); - ret = genlmsg_multicast(skb, 0, quota_genl_family.id, GFP_NOFS); - if (ret < 0 && ret != -ESRCH) - printk(KERN_ERR - "VFS: Failed to send notification message: %d\n", ret); + genlmsg_multicast(skb, 0, quota_genl_family.id, GFP_NOFS); return; attr_err_out: printk(KERN_ERR "VFS: Not enough space to compose quota message!\n"); diff --git a/lib/kobject_uevent.c b/lib/kobject_uevent.c index 318328ddbd1c..38131028d16f 100644 --- a/lib/kobject_uevent.c +++ b/lib/kobject_uevent.c @@ -227,6 +227,9 @@ int kobject_uevent_env(struct kobject *kobj, enum kobject_action action, NETLINK_CB(skb).dst_group = 1; retval = netlink_broadcast(uevent_sock, skb, 0, 1, GFP_KERNEL); + /* ENOBUFS should be handled in userspace */ + if (retval == -ENOBUFS) + retval = 0; } else retval = -ENOMEM; } diff --git a/net/netlink/af_netlink.c b/net/netlink/af_netlink.c index 9eb895c7a2a9..6ee69c27f806 100644 --- a/net/netlink/af_netlink.c +++ b/net/netlink/af_netlink.c @@ -950,6 +950,7 @@ struct netlink_broadcast_data { u32 pid; u32 group; int failure; + int delivery_failure; int congested; int delivered; gfp_t allocation; @@ -999,6 +1000,7 @@ static inline int do_one_broadcast(struct sock *sk, p->skb2 = NULL; } else if ((val = netlink_broadcast_deliver(sk, p->skb2)) < 0) { netlink_overrun(sk); + p->delivery_failure = 1; } else { p->congested |= val; p->delivered = 1; @@ -1025,6 +1027,7 @@ int netlink_broadcast(struct sock *ssk, struct sk_buff *skb, u32 pid, info.pid = pid; info.group = group; info.failure = 0; + info.delivery_failure = 0; info.congested = 0; info.delivered = 0; info.allocation = allocation; @@ -1045,13 +1048,14 @@ int netlink_broadcast(struct sock *ssk, struct sk_buff *skb, u32 pid, if (info.skb2) kfree_skb(info.skb2); + if (info.delivery_failure || info.failure) + return -ENOBUFS; + if (info.delivered) { if (info.congested && (allocation & __GFP_WAIT)) yield(); return 0; } - if (info.failure) - return -ENOBUFS; return -ESRCH; } EXPORT_SYMBOL(netlink_broadcast); diff --git a/net/wimax/op-msg.c b/net/wimax/op-msg.c index cb3b4ad53683..5d149c1b5f0d 100644 --- a/net/wimax/op-msg.c +++ b/net/wimax/op-msg.c @@ -258,7 +258,6 @@ EXPORT_SYMBOL_GPL(wimax_msg_len); */ int wimax_msg_send(struct wimax_dev *wimax_dev, struct sk_buff *skb) { - int result; struct device *dev = wimax_dev->net_dev->dev.parent; void *msg = skb->data; size_t size = skb->len; @@ -266,11 +265,9 @@ int wimax_msg_send(struct wimax_dev *wimax_dev, struct sk_buff *skb) d_printf(1, dev, "CTX: wimax msg, %zu bytes\n", size); d_dump(2, dev, msg, size); - result = genlmsg_multicast(skb, 0, wimax_gnl_mcg.id, GFP_KERNEL); - d_printf(1, dev, "CTX: genl multicast result %d\n", result); - if (result == -ESRCH) /* Nobody connected, ignore it */ - result = 0; /* btw, the skb is freed already */ - return result; + genlmsg_multicast(skb, 0, wimax_gnl_mcg.id, GFP_KERNEL); + d_printf(1, dev, "CTX: genl multicast done\n"); + return 0; } EXPORT_SYMBOL_GPL(wimax_msg_send); diff --git a/net/wimax/stack.c b/net/wimax/stack.c index 3869c0327882..a0ee76b52510 100644 --- a/net/wimax/stack.c +++ b/net/wimax/stack.c @@ -163,16 +163,12 @@ int wimax_gnl_re_state_change_send( struct device *dev = wimax_dev_to_dev(wimax_dev); d_fnstart(3, dev, "(wimax_dev %p report_skb %p)\n", wimax_dev, report_skb); - if (report_skb == NULL) + if (report_skb == NULL) { + result = -ENOMEM; goto out; - genlmsg_end(report_skb, header); - result = genlmsg_multicast(report_skb, 0, wimax_gnl_mcg.id, GFP_KERNEL); - if (result == -ESRCH) /* Nobody connected, ignore it */ - result = 0; /* btw, the skb is freed already */ - if (result < 0) { - dev_err(dev, "RE_STCH: Error sending: %d\n", result); - nlmsg_free(report_skb); } + genlmsg_end(report_skb, header); + genlmsg_multicast(report_skb, 0, wimax_gnl_mcg.id, GFP_KERNEL); out: d_fnend(3, dev, "(wimax_dev %p report_skb %p) = %d\n", wimax_dev, report_skb, result); -- cgit v1.2.3-59-g8ed1b From e9cc8bddaea3944fabfebb968bc88d603239beed Mon Sep 17 00:00:00 2001 From: Geert Uytterhoeven Date: Wed, 4 Mar 2009 14:53:30 +0800 Subject: netlink: Move netlink attribute parsing support to lib Netlink attribute parsing may be used even if CONFIG_NET is not set. Move it from net/netlink to lib and control its inclusion based on the new config symbol CONFIG_NLATTR, which is selected by CONFIG_NET. Signed-off-by: Geert Uytterhoeven Acked-by: David S. Miller Signed-off-by: Herbert Xu --- lib/Kconfig | 6 + lib/Makefile | 2 + lib/nlattr.c | 473 +++++++++++++++++++++++++++++++++++++++++++++++++++ net/Kconfig | 1 + net/netlink/Makefile | 2 +- net/netlink/attr.c | 473 --------------------------------------------------- 6 files changed, 483 insertions(+), 474 deletions(-) create mode 100644 lib/nlattr.c delete mode 100644 net/netlink/attr.c (limited to 'lib') diff --git a/lib/Kconfig b/lib/Kconfig index 03c2c24b9083..cea9e30a88ff 100644 --- a/lib/Kconfig +++ b/lib/Kconfig @@ -174,4 +174,10 @@ config DISABLE_OBSOLETE_CPUMASK_FUNCTIONS bool "Disable obsolete cpumask functions" if DEBUG_PER_CPU_MAPS depends on EXPERIMENTAL && BROKEN +# +# Netlink attribute parsing support is select'ed if needed +# +config NLATTR + bool + endmenu diff --git a/lib/Makefile b/lib/Makefile index 32b0e64ded27..b2c09da02cae 100644 --- a/lib/Makefile +++ b/lib/Makefile @@ -84,6 +84,8 @@ obj-$(CONFIG_HAVE_ARCH_TRACEHOOK) += syscall.o obj-$(CONFIG_DYNAMIC_PRINTK_DEBUG) += dynamic_printk.o +obj-$(CONFIG_NLATTR) += nlattr.o + hostprogs-y := gen_crc32table clean-files := crc32table.h diff --git a/lib/nlattr.c b/lib/nlattr.c new file mode 100644 index 000000000000..56c3ce7fe29a --- /dev/null +++ b/lib/nlattr.c @@ -0,0 +1,473 @@ +/* + * NETLINK Netlink attributes + * + * Authors: Thomas Graf + * Alexey Kuznetsov + */ + +#include +#include +#include +#include +#include +#include +#include +#include +#include + +static u16 nla_attr_minlen[NLA_TYPE_MAX+1] __read_mostly = { + [NLA_U8] = sizeof(u8), + [NLA_U16] = sizeof(u16), + [NLA_U32] = sizeof(u32), + [NLA_U64] = sizeof(u64), + [NLA_NESTED] = NLA_HDRLEN, +}; + +static int validate_nla(struct nlattr *nla, int maxtype, + const struct nla_policy *policy) +{ + const struct nla_policy *pt; + int minlen = 0, attrlen = nla_len(nla), type = nla_type(nla); + + if (type <= 0 || type > maxtype) + return 0; + + pt = &policy[type]; + + BUG_ON(pt->type > NLA_TYPE_MAX); + + switch (pt->type) { + case NLA_FLAG: + if (attrlen > 0) + return -ERANGE; + break; + + case NLA_NUL_STRING: + if (pt->len) + minlen = min_t(int, attrlen, pt->len + 1); + else + minlen = attrlen; + + if (!minlen || memchr(nla_data(nla), '\0', minlen) == NULL) + return -EINVAL; + /* fall through */ + + case NLA_STRING: + if (attrlen < 1) + return -ERANGE; + + if (pt->len) { + char *buf = nla_data(nla); + + if (buf[attrlen - 1] == '\0') + attrlen--; + + if (attrlen > pt->len) + return -ERANGE; + } + break; + + case NLA_BINARY: + if (pt->len && attrlen > pt->len) + return -ERANGE; + break; + + case NLA_NESTED_COMPAT: + if (attrlen < pt->len) + return -ERANGE; + if (attrlen < NLA_ALIGN(pt->len)) + break; + if (attrlen < NLA_ALIGN(pt->len) + NLA_HDRLEN) + return -ERANGE; + nla = nla_data(nla) + NLA_ALIGN(pt->len); + if (attrlen < NLA_ALIGN(pt->len) + NLA_HDRLEN + nla_len(nla)) + return -ERANGE; + break; + case NLA_NESTED: + /* a nested attributes is allowed to be empty; if its not, + * it must have a size of at least NLA_HDRLEN. + */ + if (attrlen == 0) + break; + default: + if (pt->len) + minlen = pt->len; + else if (pt->type != NLA_UNSPEC) + minlen = nla_attr_minlen[pt->type]; + + if (attrlen < minlen) + return -ERANGE; + } + + return 0; +} + +/** + * nla_validate - Validate a stream of attributes + * @head: head of attribute stream + * @len: length of attribute stream + * @maxtype: maximum attribute type to be expected + * @policy: validation policy + * + * Validates all attributes in the specified attribute stream against the + * specified policy. Attributes with a type exceeding maxtype will be + * ignored. See documenation of struct nla_policy for more details. + * + * Returns 0 on success or a negative error code. + */ +int nla_validate(struct nlattr *head, int len, int maxtype, + const struct nla_policy *policy) +{ + struct nlattr *nla; + int rem, err; + + nla_for_each_attr(nla, head, len, rem) { + err = validate_nla(nla, maxtype, policy); + if (err < 0) + goto errout; + } + + err = 0; +errout: + return err; +} + +/** + * nla_parse - Parse a stream of attributes into a tb buffer + * @tb: destination array with maxtype+1 elements + * @maxtype: maximum attribute type to be expected + * @head: head of attribute stream + * @len: length of attribute stream + * @policy: validation policy + * + * Parses a stream of attributes and stores a pointer to each attribute in + * the tb array accessable via the attribute type. Attributes with a type + * exceeding maxtype will be silently ignored for backwards compatibility + * reasons. policy may be set to NULL if no validation is required. + * + * Returns 0 on success or a negative error code. + */ +int nla_parse(struct nlattr *tb[], int maxtype, struct nlattr *head, int len, + const struct nla_policy *policy) +{ + struct nlattr *nla; + int rem, err; + + memset(tb, 0, sizeof(struct nlattr *) * (maxtype + 1)); + + nla_for_each_attr(nla, head, len, rem) { + u16 type = nla_type(nla); + + if (type > 0 && type <= maxtype) { + if (policy) { + err = validate_nla(nla, maxtype, policy); + if (err < 0) + goto errout; + } + + tb[type] = nla; + } + } + + if (unlikely(rem > 0)) + printk(KERN_WARNING "netlink: %d bytes leftover after parsing " + "attributes.\n", rem); + + err = 0; +errout: + return err; +} + +/** + * nla_find - Find a specific attribute in a stream of attributes + * @head: head of attribute stream + * @len: length of attribute stream + * @attrtype: type of attribute to look for + * + * Returns the first attribute in the stream matching the specified type. + */ +struct nlattr *nla_find(struct nlattr *head, int len, int attrtype) +{ + struct nlattr *nla; + int rem; + + nla_for_each_attr(nla, head, len, rem) + if (nla_type(nla) == attrtype) + return nla; + + return NULL; +} + +/** + * nla_strlcpy - Copy string attribute payload into a sized buffer + * @dst: where to copy the string to + * @nla: attribute to copy the string from + * @dstsize: size of destination buffer + * + * Copies at most dstsize - 1 bytes into the destination buffer. + * The result is always a valid NUL-terminated string. Unlike + * strlcpy the destination buffer is always padded out. + * + * Returns the length of the source buffer. + */ +size_t nla_strlcpy(char *dst, const struct nlattr *nla, size_t dstsize) +{ + size_t srclen = nla_len(nla); + char *src = nla_data(nla); + + if (srclen > 0 && src[srclen - 1] == '\0') + srclen--; + + if (dstsize > 0) { + size_t len = (srclen >= dstsize) ? dstsize - 1 : srclen; + + memset(dst, 0, dstsize); + memcpy(dst, src, len); + } + + return srclen; +} + +/** + * nla_memcpy - Copy a netlink attribute into another memory area + * @dest: where to copy to memcpy + * @src: netlink attribute to copy from + * @count: size of the destination area + * + * Note: The number of bytes copied is limited by the length of + * attribute's payload. memcpy + * + * Returns the number of bytes copied. + */ +int nla_memcpy(void *dest, const struct nlattr *src, int count) +{ + int minlen = min_t(int, count, nla_len(src)); + + memcpy(dest, nla_data(src), minlen); + + return minlen; +} + +/** + * nla_memcmp - Compare an attribute with sized memory area + * @nla: netlink attribute + * @data: memory area + * @size: size of memory area + */ +int nla_memcmp(const struct nlattr *nla, const void *data, + size_t size) +{ + int d = nla_len(nla) - size; + + if (d == 0) + d = memcmp(nla_data(nla), data, size); + + return d; +} + +/** + * nla_strcmp - Compare a string attribute against a string + * @nla: netlink string attribute + * @str: another string + */ +int nla_strcmp(const struct nlattr *nla, const char *str) +{ + int len = strlen(str) + 1; + int d = nla_len(nla) - len; + + if (d == 0) + d = memcmp(nla_data(nla), str, len); + + return d; +} + +/** + * __nla_reserve - reserve room for attribute on the skb + * @skb: socket buffer to reserve room on + * @attrtype: attribute type + * @attrlen: length of attribute payload + * + * Adds a netlink attribute header to a socket buffer and reserves + * room for the payload but does not copy it. + * + * The caller is responsible to ensure that the skb provides enough + * tailroom for the attribute header and payload. + */ +struct nlattr *__nla_reserve(struct sk_buff *skb, int attrtype, int attrlen) +{ + struct nlattr *nla; + + nla = (struct nlattr *) skb_put(skb, nla_total_size(attrlen)); + nla->nla_type = attrtype; + nla->nla_len = nla_attr_size(attrlen); + + memset((unsigned char *) nla + nla->nla_len, 0, nla_padlen(attrlen)); + + return nla; +} + +/** + * __nla_reserve_nohdr - reserve room for attribute without header + * @skb: socket buffer to reserve room on + * @attrlen: length of attribute payload + * + * Reserves room for attribute payload without a header. + * + * The caller is responsible to ensure that the skb provides enough + * tailroom for the payload. + */ +void *__nla_reserve_nohdr(struct sk_buff *skb, int attrlen) +{ + void *start; + + start = skb_put(skb, NLA_ALIGN(attrlen)); + memset(start, 0, NLA_ALIGN(attrlen)); + + return start; +} + +/** + * nla_reserve - reserve room for attribute on the skb + * @skb: socket buffer to reserve room on + * @attrtype: attribute type + * @attrlen: length of attribute payload + * + * Adds a netlink attribute header to a socket buffer and reserves + * room for the payload but does not copy it. + * + * Returns NULL if the tailroom of the skb is insufficient to store + * the attribute header and payload. + */ +struct nlattr *nla_reserve(struct sk_buff *skb, int attrtype, int attrlen) +{ + if (unlikely(skb_tailroom(skb) < nla_total_size(attrlen))) + return NULL; + + return __nla_reserve(skb, attrtype, attrlen); +} + +/** + * nla_reserve_nohdr - reserve room for attribute without header + * @skb: socket buffer to reserve room on + * @attrlen: length of attribute payload + * + * Reserves room for attribute payload without a header. + * + * Returns NULL if the tailroom of the skb is insufficient to store + * the attribute payload. + */ +void *nla_reserve_nohdr(struct sk_buff *skb, int attrlen) +{ + if (unlikely(skb_tailroom(skb) < NLA_ALIGN(attrlen))) + return NULL; + + return __nla_reserve_nohdr(skb, attrlen); +} + +/** + * __nla_put - Add a netlink attribute to a socket buffer + * @skb: socket buffer to add attribute to + * @attrtype: attribute type + * @attrlen: length of attribute payload + * @data: head of attribute payload + * + * The caller is responsible to ensure that the skb provides enough + * tailroom for the attribute header and payload. + */ +void __nla_put(struct sk_buff *skb, int attrtype, int attrlen, + const void *data) +{ + struct nlattr *nla; + + nla = __nla_reserve(skb, attrtype, attrlen); + memcpy(nla_data(nla), data, attrlen); +} + +/** + * __nla_put_nohdr - Add a netlink attribute without header + * @skb: socket buffer to add attribute to + * @attrlen: length of attribute payload + * @data: head of attribute payload + * + * The caller is responsible to ensure that the skb provides enough + * tailroom for the attribute payload. + */ +void __nla_put_nohdr(struct sk_buff *skb, int attrlen, const void *data) +{ + void *start; + + start = __nla_reserve_nohdr(skb, attrlen); + memcpy(start, data, attrlen); +} + +/** + * nla_put - Add a netlink attribute to a socket buffer + * @skb: socket buffer to add attribute to + * @attrtype: attribute type + * @attrlen: length of attribute payload + * @data: head of attribute payload + * + * Returns -EMSGSIZE if the tailroom of the skb is insufficient to store + * the attribute header and payload. + */ +int nla_put(struct sk_buff *skb, int attrtype, int attrlen, const void *data) +{ + if (unlikely(skb_tailroom(skb) < nla_total_size(attrlen))) + return -EMSGSIZE; + + __nla_put(skb, attrtype, attrlen, data); + return 0; +} + +/** + * nla_put_nohdr - Add a netlink attribute without header + * @skb: socket buffer to add attribute to + * @attrlen: length of attribute payload + * @data: head of attribute payload + * + * Returns -EMSGSIZE if the tailroom of the skb is insufficient to store + * the attribute payload. + */ +int nla_put_nohdr(struct sk_buff *skb, int attrlen, const void *data) +{ + if (unlikely(skb_tailroom(skb) < NLA_ALIGN(attrlen))) + return -EMSGSIZE; + + __nla_put_nohdr(skb, attrlen, data); + return 0; +} + +/** + * nla_append - Add a netlink attribute without header or padding + * @skb: socket buffer to add attribute to + * @attrlen: length of attribute payload + * @data: head of attribute payload + * + * Returns -EMSGSIZE if the tailroom of the skb is insufficient to store + * the attribute payload. + */ +int nla_append(struct sk_buff *skb, int attrlen, const void *data) +{ + if (unlikely(skb_tailroom(skb) < NLA_ALIGN(attrlen))) + return -EMSGSIZE; + + memcpy(skb_put(skb, attrlen), data, attrlen); + return 0; +} + +EXPORT_SYMBOL(nla_validate); +EXPORT_SYMBOL(nla_parse); +EXPORT_SYMBOL(nla_find); +EXPORT_SYMBOL(nla_strlcpy); +EXPORT_SYMBOL(__nla_reserve); +EXPORT_SYMBOL(__nla_reserve_nohdr); +EXPORT_SYMBOL(nla_reserve); +EXPORT_SYMBOL(nla_reserve_nohdr); +EXPORT_SYMBOL(__nla_put); +EXPORT_SYMBOL(__nla_put_nohdr); +EXPORT_SYMBOL(nla_put); +EXPORT_SYMBOL(nla_put_nohdr); +EXPORT_SYMBOL(nla_memcpy); +EXPORT_SYMBOL(nla_memcmp); +EXPORT_SYMBOL(nla_strcmp); +EXPORT_SYMBOL(nla_append); diff --git a/net/Kconfig b/net/Kconfig index cdb8fdef6c4a..eab40a481356 100644 --- a/net/Kconfig +++ b/net/Kconfig @@ -4,6 +4,7 @@ menuconfig NET bool "Networking support" + select NLATTR ---help--- Unless you really know what you are doing, you should say Y here. The reason is that some programs need kernel networking support even diff --git a/net/netlink/Makefile b/net/netlink/Makefile index e3589c2de49e..bdd6ddf4e95b 100644 --- a/net/netlink/Makefile +++ b/net/netlink/Makefile @@ -2,4 +2,4 @@ # Makefile for the netlink driver. # -obj-y := af_netlink.o attr.o genetlink.o +obj-y := af_netlink.o genetlink.o diff --git a/net/netlink/attr.c b/net/netlink/attr.c deleted file mode 100644 index 56c3ce7fe29a..000000000000 --- a/net/netlink/attr.c +++ /dev/null @@ -1,473 +0,0 @@ -/* - * NETLINK Netlink attributes - * - * Authors: Thomas Graf - * Alexey Kuznetsov - */ - -#include -#include -#include -#include -#include -#include -#include -#include -#include - -static u16 nla_attr_minlen[NLA_TYPE_MAX+1] __read_mostly = { - [NLA_U8] = sizeof(u8), - [NLA_U16] = sizeof(u16), - [NLA_U32] = sizeof(u32), - [NLA_U64] = sizeof(u64), - [NLA_NESTED] = NLA_HDRLEN, -}; - -static int validate_nla(struct nlattr *nla, int maxtype, - const struct nla_policy *policy) -{ - const struct nla_policy *pt; - int minlen = 0, attrlen = nla_len(nla), type = nla_type(nla); - - if (type <= 0 || type > maxtype) - return 0; - - pt = &policy[type]; - - BUG_ON(pt->type > NLA_TYPE_MAX); - - switch (pt->type) { - case NLA_FLAG: - if (attrlen > 0) - return -ERANGE; - break; - - case NLA_NUL_STRING: - if (pt->len) - minlen = min_t(int, attrlen, pt->len + 1); - else - minlen = attrlen; - - if (!minlen || memchr(nla_data(nla), '\0', minlen) == NULL) - return -EINVAL; - /* fall through */ - - case NLA_STRING: - if (attrlen < 1) - return -ERANGE; - - if (pt->len) { - char *buf = nla_data(nla); - - if (buf[attrlen - 1] == '\0') - attrlen--; - - if (attrlen > pt->len) - return -ERANGE; - } - break; - - case NLA_BINARY: - if (pt->len && attrlen > pt->len) - return -ERANGE; - break; - - case NLA_NESTED_COMPAT: - if (attrlen < pt->len) - return -ERANGE; - if (attrlen < NLA_ALIGN(pt->len)) - break; - if (attrlen < NLA_ALIGN(pt->len) + NLA_HDRLEN) - return -ERANGE; - nla = nla_data(nla) + NLA_ALIGN(pt->len); - if (attrlen < NLA_ALIGN(pt->len) + NLA_HDRLEN + nla_len(nla)) - return -ERANGE; - break; - case NLA_NESTED: - /* a nested attributes is allowed to be empty; if its not, - * it must have a size of at least NLA_HDRLEN. - */ - if (attrlen == 0) - break; - default: - if (pt->len) - minlen = pt->len; - else if (pt->type != NLA_UNSPEC) - minlen = nla_attr_minlen[pt->type]; - - if (attrlen < minlen) - return -ERANGE; - } - - return 0; -} - -/** - * nla_validate - Validate a stream of attributes - * @head: head of attribute stream - * @len: length of attribute stream - * @maxtype: maximum attribute type to be expected - * @policy: validation policy - * - * Validates all attributes in the specified attribute stream against the - * specified policy. Attributes with a type exceeding maxtype will be - * ignored. See documenation of struct nla_policy for more details. - * - * Returns 0 on success or a negative error code. - */ -int nla_validate(struct nlattr *head, int len, int maxtype, - const struct nla_policy *policy) -{ - struct nlattr *nla; - int rem, err; - - nla_for_each_attr(nla, head, len, rem) { - err = validate_nla(nla, maxtype, policy); - if (err < 0) - goto errout; - } - - err = 0; -errout: - return err; -} - -/** - * nla_parse - Parse a stream of attributes into a tb buffer - * @tb: destination array with maxtype+1 elements - * @maxtype: maximum attribute type to be expected - * @head: head of attribute stream - * @len: length of attribute stream - * @policy: validation policy - * - * Parses a stream of attributes and stores a pointer to each attribute in - * the tb array accessable via the attribute type. Attributes with a type - * exceeding maxtype will be silently ignored for backwards compatibility - * reasons. policy may be set to NULL if no validation is required. - * - * Returns 0 on success or a negative error code. - */ -int nla_parse(struct nlattr *tb[], int maxtype, struct nlattr *head, int len, - const struct nla_policy *policy) -{ - struct nlattr *nla; - int rem, err; - - memset(tb, 0, sizeof(struct nlattr *) * (maxtype + 1)); - - nla_for_each_attr(nla, head, len, rem) { - u16 type = nla_type(nla); - - if (type > 0 && type <= maxtype) { - if (policy) { - err = validate_nla(nla, maxtype, policy); - if (err < 0) - goto errout; - } - - tb[type] = nla; - } - } - - if (unlikely(rem > 0)) - printk(KERN_WARNING "netlink: %d bytes leftover after parsing " - "attributes.\n", rem); - - err = 0; -errout: - return err; -} - -/** - * nla_find - Find a specific attribute in a stream of attributes - * @head: head of attribute stream - * @len: length of attribute stream - * @attrtype: type of attribute to look for - * - * Returns the first attribute in the stream matching the specified type. - */ -struct nlattr *nla_find(struct nlattr *head, int len, int attrtype) -{ - struct nlattr *nla; - int rem; - - nla_for_each_attr(nla, head, len, rem) - if (nla_type(nla) == attrtype) - return nla; - - return NULL; -} - -/** - * nla_strlcpy - Copy string attribute payload into a sized buffer - * @dst: where to copy the string to - * @nla: attribute to copy the string from - * @dstsize: size of destination buffer - * - * Copies at most dstsize - 1 bytes into the destination buffer. - * The result is always a valid NUL-terminated string. Unlike - * strlcpy the destination buffer is always padded out. - * - * Returns the length of the source buffer. - */ -size_t nla_strlcpy(char *dst, const struct nlattr *nla, size_t dstsize) -{ - size_t srclen = nla_len(nla); - char *src = nla_data(nla); - - if (srclen > 0 && src[srclen - 1] == '\0') - srclen--; - - if (dstsize > 0) { - size_t len = (srclen >= dstsize) ? dstsize - 1 : srclen; - - memset(dst, 0, dstsize); - memcpy(dst, src, len); - } - - return srclen; -} - -/** - * nla_memcpy - Copy a netlink attribute into another memory area - * @dest: where to copy to memcpy - * @src: netlink attribute to copy from - * @count: size of the destination area - * - * Note: The number of bytes copied is limited by the length of - * attribute's payload. memcpy - * - * Returns the number of bytes copied. - */ -int nla_memcpy(void *dest, const struct nlattr *src, int count) -{ - int minlen = min_t(int, count, nla_len(src)); - - memcpy(dest, nla_data(src), minlen); - - return minlen; -} - -/** - * nla_memcmp - Compare an attribute with sized memory area - * @nla: netlink attribute - * @data: memory area - * @size: size of memory area - */ -int nla_memcmp(const struct nlattr *nla, const void *data, - size_t size) -{ - int d = nla_len(nla) - size; - - if (d == 0) - d = memcmp(nla_data(nla), data, size); - - return d; -} - -/** - * nla_strcmp - Compare a string attribute against a string - * @nla: netlink string attribute - * @str: another string - */ -int nla_strcmp(const struct nlattr *nla, const char *str) -{ - int len = strlen(str) + 1; - int d = nla_len(nla) - len; - - if (d == 0) - d = memcmp(nla_data(nla), str, len); - - return d; -} - -/** - * __nla_reserve - reserve room for attribute on the skb - * @skb: socket buffer to reserve room on - * @attrtype: attribute type - * @attrlen: length of attribute payload - * - * Adds a netlink attribute header to a socket buffer and reserves - * room for the payload but does not copy it. - * - * The caller is responsible to ensure that the skb provides enough - * tailroom for the attribute header and payload. - */ -struct nlattr *__nla_reserve(struct sk_buff *skb, int attrtype, int attrlen) -{ - struct nlattr *nla; - - nla = (struct nlattr *) skb_put(skb, nla_total_size(attrlen)); - nla->nla_type = attrtype; - nla->nla_len = nla_attr_size(attrlen); - - memset((unsigned char *) nla + nla->nla_len, 0, nla_padlen(attrlen)); - - return nla; -} - -/** - * __nla_reserve_nohdr - reserve room for attribute without header - * @skb: socket buffer to reserve room on - * @attrlen: length of attribute payload - * - * Reserves room for attribute payload without a header. - * - * The caller is responsible to ensure that the skb provides enough - * tailroom for the payload. - */ -void *__nla_reserve_nohdr(struct sk_buff *skb, int attrlen) -{ - void *start; - - start = skb_put(skb, NLA_ALIGN(attrlen)); - memset(start, 0, NLA_ALIGN(attrlen)); - - return start; -} - -/** - * nla_reserve - reserve room for attribute on the skb - * @skb: socket buffer to reserve room on - * @attrtype: attribute type - * @attrlen: length of attribute payload - * - * Adds a netlink attribute header to a socket buffer and reserves - * room for the payload but does not copy it. - * - * Returns NULL if the tailroom of the skb is insufficient to store - * the attribute header and payload. - */ -struct nlattr *nla_reserve(struct sk_buff *skb, int attrtype, int attrlen) -{ - if (unlikely(skb_tailroom(skb) < nla_total_size(attrlen))) - return NULL; - - return __nla_reserve(skb, attrtype, attrlen); -} - -/** - * nla_reserve_nohdr - reserve room for attribute without header - * @skb: socket buffer to reserve room on - * @attrlen: length of attribute payload - * - * Reserves room for attribute payload without a header. - * - * Returns NULL if the tailroom of the skb is insufficient to store - * the attribute payload. - */ -void *nla_reserve_nohdr(struct sk_buff *skb, int attrlen) -{ - if (unlikely(skb_tailroom(skb) < NLA_ALIGN(attrlen))) - return NULL; - - return __nla_reserve_nohdr(skb, attrlen); -} - -/** - * __nla_put - Add a netlink attribute to a socket buffer - * @skb: socket buffer to add attribute to - * @attrtype: attribute type - * @attrlen: length of attribute payload - * @data: head of attribute payload - * - * The caller is responsible to ensure that the skb provides enough - * tailroom for the attribute header and payload. - */ -void __nla_put(struct sk_buff *skb, int attrtype, int attrlen, - const void *data) -{ - struct nlattr *nla; - - nla = __nla_reserve(skb, attrtype, attrlen); - memcpy(nla_data(nla), data, attrlen); -} - -/** - * __nla_put_nohdr - Add a netlink attribute without header - * @skb: socket buffer to add attribute to - * @attrlen: length of attribute payload - * @data: head of attribute payload - * - * The caller is responsible to ensure that the skb provides enough - * tailroom for the attribute payload. - */ -void __nla_put_nohdr(struct sk_buff *skb, int attrlen, const void *data) -{ - void *start; - - start = __nla_reserve_nohdr(skb, attrlen); - memcpy(start, data, attrlen); -} - -/** - * nla_put - Add a netlink attribute to a socket buffer - * @skb: socket buffer to add attribute to - * @attrtype: attribute type - * @attrlen: length of attribute payload - * @data: head of attribute payload - * - * Returns -EMSGSIZE if the tailroom of the skb is insufficient to store - * the attribute header and payload. - */ -int nla_put(struct sk_buff *skb, int attrtype, int attrlen, const void *data) -{ - if (unlikely(skb_tailroom(skb) < nla_total_size(attrlen))) - return -EMSGSIZE; - - __nla_put(skb, attrtype, attrlen, data); - return 0; -} - -/** - * nla_put_nohdr - Add a netlink attribute without header - * @skb: socket buffer to add attribute to - * @attrlen: length of attribute payload - * @data: head of attribute payload - * - * Returns -EMSGSIZE if the tailroom of the skb is insufficient to store - * the attribute payload. - */ -int nla_put_nohdr(struct sk_buff *skb, int attrlen, const void *data) -{ - if (unlikely(skb_tailroom(skb) < NLA_ALIGN(attrlen))) - return -EMSGSIZE; - - __nla_put_nohdr(skb, attrlen, data); - return 0; -} - -/** - * nla_append - Add a netlink attribute without header or padding - * @skb: socket buffer to add attribute to - * @attrlen: length of attribute payload - * @data: head of attribute payload - * - * Returns -EMSGSIZE if the tailroom of the skb is insufficient to store - * the attribute payload. - */ -int nla_append(struct sk_buff *skb, int attrlen, const void *data) -{ - if (unlikely(skb_tailroom(skb) < NLA_ALIGN(attrlen))) - return -EMSGSIZE; - - memcpy(skb_put(skb, attrlen), data, attrlen); - return 0; -} - -EXPORT_SYMBOL(nla_validate); -EXPORT_SYMBOL(nla_parse); -EXPORT_SYMBOL(nla_find); -EXPORT_SYMBOL(nla_strlcpy); -EXPORT_SYMBOL(__nla_reserve); -EXPORT_SYMBOL(__nla_reserve_nohdr); -EXPORT_SYMBOL(nla_reserve); -EXPORT_SYMBOL(nla_reserve_nohdr); -EXPORT_SYMBOL(__nla_put); -EXPORT_SYMBOL(__nla_put_nohdr); -EXPORT_SYMBOL(nla_put); -EXPORT_SYMBOL(nla_put_nohdr); -EXPORT_SYMBOL(nla_memcpy); -EXPORT_SYMBOL(nla_memcmp); -EXPORT_SYMBOL(nla_strcmp); -EXPORT_SYMBOL(nla_append); -- cgit v1.2.3-59-g8ed1b From 5ed0cec0ac5f1b3759bdbe4d9df32ee4ff8afb5a Mon Sep 17 00:00:00 2001 From: Lai Jiangshan Date: Fri, 6 Mar 2009 19:40:20 +0800 Subject: sched: TIF_NEED_RESCHED -> need_reshed() cleanup Impact: cleanup Use test_tsk_need_resched(), set_tsk_need_resched(), need_resched() instead of using TIF_NEED_RESCHED. Signed-off-by: Lai Jiangshan Cc: Peter Zijlstra LKML-Reference: <49B10BA4.9070209@cn.fujitsu.com> Signed-off-by: Ingo Molnar --- kernel/sched.c | 10 +++++----- lib/kernel_lock.c | 2 +- 2 files changed, 6 insertions(+), 6 deletions(-) (limited to 'lib') diff --git a/kernel/sched.c b/kernel/sched.c index 8b92f40c147d..e0fa739a441b 100644 --- a/kernel/sched.c +++ b/kernel/sched.c @@ -1189,10 +1189,10 @@ static void resched_task(struct task_struct *p) assert_spin_locked(&task_rq(p)->lock); - if (unlikely(test_tsk_thread_flag(p, TIF_NEED_RESCHED))) + if (test_tsk_need_resched(p)) return; - set_tsk_thread_flag(p, TIF_NEED_RESCHED); + set_tsk_need_resched(p); cpu = task_cpu(p); if (cpu == smp_processor_id()) @@ -1248,7 +1248,7 @@ void wake_up_idle_cpu(int cpu) * lockless. The worst case is that the other CPU runs the * idle task through an additional NOOP schedule() */ - set_tsk_thread_flag(rq->idle, TIF_NEED_RESCHED); + set_tsk_need_resched(rq->idle); /* NEED_RESCHED must be visible before we test polling */ smp_mb(); @@ -4740,7 +4740,7 @@ asmlinkage void __sched preempt_schedule(void) * between schedule and now. */ barrier(); - } while (unlikely(test_thread_flag(TIF_NEED_RESCHED))); + } while (need_resched()); } EXPORT_SYMBOL(preempt_schedule); @@ -4769,7 +4769,7 @@ asmlinkage void __sched preempt_schedule_irq(void) * between schedule and now. */ barrier(); - } while (unlikely(test_thread_flag(TIF_NEED_RESCHED))); + } while (need_resched()); } #endif /* CONFIG_PREEMPT */ diff --git a/lib/kernel_lock.c b/lib/kernel_lock.c index 01a3c22c1b5a..39f1029e3525 100644 --- a/lib/kernel_lock.c +++ b/lib/kernel_lock.c @@ -39,7 +39,7 @@ static __cacheline_aligned_in_smp DEFINE_SPINLOCK(kernel_flag); int __lockfunc __reacquire_kernel_lock(void) { while (!_raw_spin_trylock(&kernel_flag)) { - if (test_thread_flag(TIF_NEED_RESCHED)) + if (need_resched()) return -EAGAIN; cpu_relax(); } -- cgit v1.2.3-59-g8ed1b From 908002161247e6e68c478052926b62d9a3d72418 Mon Sep 17 00:00:00 2001 From: Herbert Xu Date: Wed, 11 Mar 2009 23:18:32 +0800 Subject: nlattr: Fix build error with NET off We moved the netlink attribute support from net to lib in order for it to be available for general consumption. However, parts of the code (the bits that we don't need :) really depends on NET because the target object is sk_buff. This patch fixes this by wrapping them in CONFIG_NET. Some EXPORTs have been moved to make this work. Tested-by: Geert Uytterhoeven Signed-off-by: Herbert Xu --- lib/nlattr.c | 20 +++++++++++--------- 1 file changed, 11 insertions(+), 9 deletions(-) (limited to 'lib') diff --git a/lib/nlattr.c b/lib/nlattr.c index 56c3ce7fe29a..80009a24e21d 100644 --- a/lib/nlattr.c +++ b/lib/nlattr.c @@ -281,6 +281,7 @@ int nla_strcmp(const struct nlattr *nla, const char *str) return d; } +#ifdef CONFIG_NET /** * __nla_reserve - reserve room for attribute on the skb * @skb: socket buffer to reserve room on @@ -305,6 +306,7 @@ struct nlattr *__nla_reserve(struct sk_buff *skb, int attrtype, int attrlen) return nla; } +EXPORT_SYMBOL(__nla_reserve); /** * __nla_reserve_nohdr - reserve room for attribute without header @@ -325,6 +327,7 @@ void *__nla_reserve_nohdr(struct sk_buff *skb, int attrlen) return start; } +EXPORT_SYMBOL(__nla_reserve_nohdr); /** * nla_reserve - reserve room for attribute on the skb @@ -345,6 +348,7 @@ struct nlattr *nla_reserve(struct sk_buff *skb, int attrtype, int attrlen) return __nla_reserve(skb, attrtype, attrlen); } +EXPORT_SYMBOL(nla_reserve); /** * nla_reserve_nohdr - reserve room for attribute without header @@ -363,6 +367,7 @@ void *nla_reserve_nohdr(struct sk_buff *skb, int attrlen) return __nla_reserve_nohdr(skb, attrlen); } +EXPORT_SYMBOL(nla_reserve_nohdr); /** * __nla_put - Add a netlink attribute to a socket buffer @@ -382,6 +387,7 @@ void __nla_put(struct sk_buff *skb, int attrtype, int attrlen, nla = __nla_reserve(skb, attrtype, attrlen); memcpy(nla_data(nla), data, attrlen); } +EXPORT_SYMBOL(__nla_put); /** * __nla_put_nohdr - Add a netlink attribute without header @@ -399,6 +405,7 @@ void __nla_put_nohdr(struct sk_buff *skb, int attrlen, const void *data) start = __nla_reserve_nohdr(skb, attrlen); memcpy(start, data, attrlen); } +EXPORT_SYMBOL(__nla_put_nohdr); /** * nla_put - Add a netlink attribute to a socket buffer @@ -418,6 +425,7 @@ int nla_put(struct sk_buff *skb, int attrtype, int attrlen, const void *data) __nla_put(skb, attrtype, attrlen, data); return 0; } +EXPORT_SYMBOL(nla_put); /** * nla_put_nohdr - Add a netlink attribute without header @@ -436,6 +444,7 @@ int nla_put_nohdr(struct sk_buff *skb, int attrlen, const void *data) __nla_put_nohdr(skb, attrlen, data); return 0; } +EXPORT_SYMBOL(nla_put_nohdr); /** * nla_append - Add a netlink attribute without header or padding @@ -454,20 +463,13 @@ int nla_append(struct sk_buff *skb, int attrlen, const void *data) memcpy(skb_put(skb, attrlen), data, attrlen); return 0; } +EXPORT_SYMBOL(nla_append); +#endif EXPORT_SYMBOL(nla_validate); EXPORT_SYMBOL(nla_parse); EXPORT_SYMBOL(nla_find); EXPORT_SYMBOL(nla_strlcpy); -EXPORT_SYMBOL(__nla_reserve); -EXPORT_SYMBOL(__nla_reserve_nohdr); -EXPORT_SYMBOL(nla_reserve); -EXPORT_SYMBOL(nla_reserve_nohdr); -EXPORT_SYMBOL(__nla_put); -EXPORT_SYMBOL(__nla_put_nohdr); -EXPORT_SYMBOL(nla_put); -EXPORT_SYMBOL(nla_put_nohdr); EXPORT_SYMBOL(nla_memcpy); EXPORT_SYMBOL(nla_memcmp); EXPORT_SYMBOL(nla_strcmp); -EXPORT_SYMBOL(nla_append); -- cgit v1.2.3-59-g8ed1b From 1fa5ae857bb14f6046205171d98506d8112dd74e Mon Sep 17 00:00:00 2001 From: Kay Sievers Date: Sun, 25 Jan 2009 15:17:37 +0100 Subject: driver core: get rid of struct device's bus_id string array Now that all users of bus_id is gone, we can remove it from struct device. Signed-off-by: Kay Sievers Signed-off-by: Greg Kroah-Hartman --- drivers/base/core.c | 39 +++++++++++++++++++-------------------- include/linux/device.h | 4 +--- include/linux/kobject.h | 2 ++ lib/kobject.c | 2 +- 4 files changed, 23 insertions(+), 24 deletions(-) (limited to 'lib') diff --git a/drivers/base/core.c b/drivers/base/core.c index f3eae630e589..059966b617f6 100644 --- a/drivers/base/core.c +++ b/drivers/base/core.c @@ -777,17 +777,12 @@ static void device_remove_class_symlinks(struct device *dev) int dev_set_name(struct device *dev, const char *fmt, ...) { va_list vargs; - char *s; + int err; va_start(vargs, fmt); - vsnprintf(dev->bus_id, sizeof(dev->bus_id), fmt, vargs); + err = kobject_set_name_vargs(&dev->kobj, fmt, vargs); va_end(vargs); - - /* ewww... some of these buggers have / in the name... */ - while ((s = strchr(dev->bus_id, '/'))) - *s = '!'; - - return 0; + return err; } EXPORT_SYMBOL_GPL(dev_set_name); @@ -864,12 +859,17 @@ int device_add(struct device *dev) if (!dev) goto done; - /* Temporarily support init_name if it is set. - * It will override bus_id for now */ - if (dev->init_name) - dev_set_name(dev, "%s", dev->init_name); + /* + * for statically allocated devices, which should all be converted + * some day, we need to initialize the name. We prevent reading back + * the name, and force the use of dev_name() + */ + if (dev->init_name) { + dev_set_name(dev, dev->init_name); + dev->init_name = NULL; + } - if (!strlen(dev->bus_id)) + if (!dev_name(dev)) goto done; pr_debug("device: '%s': %s\n", dev_name(dev), __func__); @@ -1348,7 +1348,10 @@ struct device *device_create_vargs(struct class *class, struct device *parent, dev->release = device_create_release; dev_set_drvdata(dev, drvdata); - vsnprintf(dev->bus_id, BUS_ID_SIZE, fmt, args); + retval = kobject_set_name_vargs(&dev->kobj, fmt, args); + if (retval) + goto error; + retval = device_register(dev); if (retval) goto error; @@ -1452,19 +1455,15 @@ int device_rename(struct device *dev, char *new_name) old_class_name = make_class_name(dev->class->name, &dev->kobj); #endif - old_device_name = kmalloc(BUS_ID_SIZE, GFP_KERNEL); + old_device_name = kstrdup(dev_name(dev), GFP_KERNEL); if (!old_device_name) { error = -ENOMEM; goto out; } - strlcpy(old_device_name, dev->bus_id, BUS_ID_SIZE); - strlcpy(dev->bus_id, new_name, BUS_ID_SIZE); error = kobject_rename(&dev->kobj, new_name); - if (error) { - strlcpy(dev->bus_id, old_device_name, BUS_ID_SIZE); + if (error) goto out; - } #ifdef CONFIG_SYSFS_DEPRECATED if (old_class_name) { diff --git a/include/linux/device.h b/include/linux/device.h index 47f343c7bdda..d5706c448bcb 100644 --- a/include/linux/device.h +++ b/include/linux/device.h @@ -374,7 +374,6 @@ struct device { struct device *parent; struct kobject kobj; - char bus_id[BUS_ID_SIZE]; /* position on parent bus */ unsigned uevent_suppress:1; const char *init_name; /* initial name of the device */ struct device_type *type; @@ -427,8 +426,7 @@ struct device { static inline const char *dev_name(const struct device *dev) { - /* will be changed into kobject_name(&dev->kobj) in the near future */ - return dev->bus_id; + return kobject_name(&dev->kobj); } extern int dev_set_name(struct device *dev, const char *name, ...) diff --git a/include/linux/kobject.h b/include/linux/kobject.h index 5437ac0276e2..c9c214d7bba2 100644 --- a/include/linux/kobject.h +++ b/include/linux/kobject.h @@ -72,6 +72,8 @@ struct kobject { extern int kobject_set_name(struct kobject *kobj, const char *name, ...) __attribute__((format(printf, 2, 3))); +extern int kobject_set_name_vargs(struct kobject *kobj, const char *fmt, + va_list vargs); static inline const char *kobject_name(const struct kobject *kobj) { diff --git a/lib/kobject.c b/lib/kobject.c index 0487d1f64806..a6dec32f2ddd 100644 --- a/lib/kobject.c +++ b/lib/kobject.c @@ -212,7 +212,7 @@ static int kobject_add_internal(struct kobject *kobj) * @fmt: format string used to build the name * @vargs: vargs to format the string. */ -static int kobject_set_name_vargs(struct kobject *kobj, const char *fmt, +int kobject_set_name_vargs(struct kobject *kobj, const char *fmt, va_list vargs) { const char *old_name = kobj->name; -- cgit v1.2.3-59-g8ed1b From f67f129e519fa87f8ebd236b6336fe43f31ee141 Mon Sep 17 00:00:00 2001 From: Ming Lei Date: Sun, 1 Mar 2009 21:10:49 +0800 Subject: Driver core: implement uevent suppress in kobject This patch implements uevent suppress in kobject and removes it from struct device, based on the following ideas: 1,Uevent sending should be one attribute of kobject, so suppressing it in kobject layer is more natural than in device layer. By this way, we can do it for other objects embedded with kobject. 2,It may save several bytes for each instance of struct device.(On my omap3(32bit ARM) based box, can save 8bytes per device object) This patch also introduces dev_set|get_uevent_suppress() helpers to set and query uevent_suppress attribute in case to help kobject as private part of struct device in future. [This version is against the latest driver-core patch set of Greg,please ignore the last version.] Signed-off-by: Ming Lei Signed-off-by: Greg Kroah-Hartman --- drivers/acpi/dock.c | 2 +- drivers/base/core.c | 2 -- drivers/base/firmware_class.c | 4 ++-- drivers/i2c/i2c-core.c | 2 +- drivers/s390/cio/chsc_sch.c | 4 ++-- drivers/s390/cio/css.c | 4 ++-- drivers/s390/cio/device.c | 4 ++-- fs/partitions/check.c | 10 +++++----- include/linux/device.h | 11 ++++++++++- include/linux/kobject.h | 1 + lib/kobject_uevent.c | 7 +++++++ 11 files changed, 33 insertions(+), 18 deletions(-) (limited to 'lib') diff --git a/drivers/acpi/dock.c b/drivers/acpi/dock.c index 35094f230b1e..7af7db1ba8c4 100644 --- a/drivers/acpi/dock.c +++ b/drivers/acpi/dock.c @@ -977,7 +977,7 @@ static int dock_add(acpi_handle handle) sizeof(struct dock_station *)); /* we want the dock device to send uevents */ - dock_device->dev.uevent_suppress = 0; + dev_set_uevent_suppress(&dock_device->dev, 0); if (is_dock(handle)) dock_station->flags |= DOCK_IS_DOCK; diff --git a/drivers/base/core.c b/drivers/base/core.c index a90f56f64d6f..95c67ffd71da 100644 --- a/drivers/base/core.c +++ b/drivers/base/core.c @@ -136,8 +136,6 @@ static int dev_uevent_filter(struct kset *kset, struct kobject *kobj) if (ktype == &device_ktype) { struct device *dev = to_dev(kobj); - if (dev->uevent_suppress) - return 0; if (dev->bus) return 1; if (dev->class) diff --git a/drivers/base/firmware_class.c b/drivers/base/firmware_class.c index 44699d9dd85c..d3a59c688fe4 100644 --- a/drivers/base/firmware_class.c +++ b/drivers/base/firmware_class.c @@ -319,7 +319,7 @@ static int fw_register_device(struct device **dev_p, const char *fw_name, f_dev->parent = device; f_dev->class = &firmware_class; dev_set_drvdata(f_dev, fw_priv); - f_dev->uevent_suppress = 1; + dev_set_uevent_suppress(f_dev, 1); retval = device_register(f_dev); if (retval) { dev_err(device, "%s: device_register failed\n", __func__); @@ -366,7 +366,7 @@ static int fw_setup_device(struct firmware *fw, struct device **dev_p, } if (uevent) - f_dev->uevent_suppress = 0; + dev_set_uevent_suppress(f_dev, 0); *dev_p = f_dev; goto out; diff --git a/drivers/i2c/i2c-core.c b/drivers/i2c/i2c-core.c index e7d984866de0..fbb9030b68a5 100644 --- a/drivers/i2c/i2c-core.c +++ b/drivers/i2c/i2c-core.c @@ -841,7 +841,7 @@ int i2c_attach_client(struct i2c_client *client) if (client->driver && !is_newstyle_driver(client->driver)) { client->dev.release = i2c_client_release; - client->dev.uevent_suppress = 1; + dev_set_uevent_suppress(&client->dev, 1); } else client->dev.release = i2c_client_dev_release; diff --git a/drivers/s390/cio/chsc_sch.c b/drivers/s390/cio/chsc_sch.c index 0a2f2edafc03..93eca1731b81 100644 --- a/drivers/s390/cio/chsc_sch.c +++ b/drivers/s390/cio/chsc_sch.c @@ -84,8 +84,8 @@ static int chsc_subchannel_probe(struct subchannel *sch) kfree(private); } else { sch->private = private; - if (sch->dev.uevent_suppress) { - sch->dev.uevent_suppress = 0; + if (dev_get_uevent_suppress(&sch->dev)) { + dev_set_uevent_suppress(&sch->dev, 0); kobject_uevent(&sch->dev.kobj, KOBJ_ADD); } } diff --git a/drivers/s390/cio/css.c b/drivers/s390/cio/css.c index 8019288bc6de..427d11d88069 100644 --- a/drivers/s390/cio/css.c +++ b/drivers/s390/cio/css.c @@ -272,7 +272,7 @@ static int css_register_subchannel(struct subchannel *sch) * the subchannel driver can decide itself when it wants to inform * userspace of its existence. */ - sch->dev.uevent_suppress = 1; + dev_set_uevent_suppress(&sch->dev, 1); css_update_ssd_info(sch); /* make it known to the system */ ret = css_sch_device_register(sch); @@ -287,7 +287,7 @@ static int css_register_subchannel(struct subchannel *sch) * a fitting driver module may be loaded based on the * modalias. */ - sch->dev.uevent_suppress = 0; + dev_set_uevent_suppress(&sch->dev, 0); kobject_uevent(&sch->dev.kobj, KOBJ_ADD); } return ret; diff --git a/drivers/s390/cio/device.c b/drivers/s390/cio/device.c index 23d5752349b5..611d2e001dd5 100644 --- a/drivers/s390/cio/device.c +++ b/drivers/s390/cio/device.c @@ -981,7 +981,7 @@ io_subchannel_register(struct work_struct *work) * Now we know this subchannel will stay, we can throw * our delayed uevent. */ - sch->dev.uevent_suppress = 0; + dev_set_uevent_suppress(&sch->dev, 0); kobject_uevent(&sch->dev.kobj, KOBJ_ADD); /* make it known to the system */ ret = ccw_device_register(cdev); @@ -1243,7 +1243,7 @@ static int io_subchannel_probe(struct subchannel *sch) * the ccw_device and exit. This happens for all early * devices, e.g. the console. */ - sch->dev.uevent_suppress = 0; + dev_set_uevent_suppress(&sch->dev, 0); kobject_uevent(&sch->dev.kobj, KOBJ_ADD); cdev->dev.groups = ccwdev_attr_groups; device_initialize(&cdev->dev); diff --git a/fs/partitions/check.c b/fs/partitions/check.c index 6d720243f5f4..38e337d51ced 100644 --- a/fs/partitions/check.c +++ b/fs/partitions/check.c @@ -400,7 +400,7 @@ struct hd_struct *add_partition(struct gendisk *disk, int partno, pdev->devt = devt; /* delay uevent until 'holders' subdir is created */ - pdev->uevent_suppress = 1; + dev_set_uevent_suppress(pdev, 1); err = device_add(pdev); if (err) goto out_put; @@ -410,7 +410,7 @@ struct hd_struct *add_partition(struct gendisk *disk, int partno, if (!p->holder_dir) goto out_del; - pdev->uevent_suppress = 0; + dev_set_uevent_suppress(pdev, 0); if (flags & ADDPART_FLAG_WHOLEDISK) { err = device_create_file(pdev, &dev_attr_whole_disk); if (err) @@ -422,7 +422,7 @@ struct hd_struct *add_partition(struct gendisk *disk, int partno, rcu_assign_pointer(ptbl->part[partno], p); /* suppress uevent if the disk supresses it */ - if (!ddev->uevent_suppress) + if (!dev_get_uevent_suppress(pdev)) kobject_uevent(&pdev->kobj, KOBJ_ADD); return p; @@ -455,7 +455,7 @@ void register_disk(struct gendisk *disk) dev_set_name(ddev, disk->disk_name); /* delay uevents, until we scanned partition table */ - ddev->uevent_suppress = 1; + dev_set_uevent_suppress(ddev, 1); if (device_add(ddev)) return; @@ -490,7 +490,7 @@ void register_disk(struct gendisk *disk) exit: /* announce disk after possible partitions are created */ - ddev->uevent_suppress = 0; + dev_set_uevent_suppress(ddev, 0); kobject_uevent(&ddev->kobj, KOBJ_ADD); /* announce possible partitions */ diff --git a/include/linux/device.h b/include/linux/device.h index 4bea53fe8f4c..914c1016dd8f 100644 --- a/include/linux/device.h +++ b/include/linux/device.h @@ -373,7 +373,6 @@ struct device { struct device_private *p; struct kobject kobj; - unsigned uevent_suppress:1; const char *init_name; /* initial name of the device */ struct device_type *type; @@ -465,6 +464,16 @@ static inline void dev_set_drvdata(struct device *dev, void *data) dev->driver_data = data; } +static inline unsigned int dev_get_uevent_suppress(const struct device *dev) +{ + return dev->kobj.uevent_suppress; +} + +static inline void dev_set_uevent_suppress(struct device *dev, int val) +{ + dev->kobj.uevent_suppress = val; +} + static inline int device_is_registered(struct device *dev) { return dev->kobj.state_in_sysfs; diff --git a/include/linux/kobject.h b/include/linux/kobject.h index c9c214d7bba2..58ae8e00fcdd 100644 --- a/include/linux/kobject.h +++ b/include/linux/kobject.h @@ -68,6 +68,7 @@ struct kobject { unsigned int state_in_sysfs:1; unsigned int state_add_uevent_sent:1; unsigned int state_remove_uevent_sent:1; + unsigned int uevent_suppress:1; }; extern int kobject_set_name(struct kobject *kobj, const char *name, ...) diff --git a/lib/kobject_uevent.c b/lib/kobject_uevent.c index 318328ddbd1c..b2181cc8e4d8 100644 --- a/lib/kobject_uevent.c +++ b/lib/kobject_uevent.c @@ -118,6 +118,13 @@ int kobject_uevent_env(struct kobject *kobj, enum kobject_action action, kset = top_kobj->kset; uevent_ops = kset->uevent_ops; + /* skip the event, if uevent_suppress is set*/ + if (kobj->uevent_suppress) { + pr_debug("kobject: '%s' (%p): %s: uevent_suppress " + "caused the event to drop!\n", + kobject_name(kobj), kobj, __func__); + return 0; + } /* skip the event, if the filter returns zero. */ if (uevent_ops && uevent_ops->filter) if (!uevent_ops->filter(kset, kobj)) { -- cgit v1.2.3-59-g8ed1b From f520360d93cdc37de5d972dac4bf3bdef6a7f6a7 Mon Sep 17 00:00:00 2001 From: Arjan van de Ven Date: Thu, 19 Mar 2009 09:09:05 -0700 Subject: kobject: don't block for each kobject_uevent Right now, the kobject_uevent code blocks for each uevent that's being generated, due to using (for hystoric reasons) UHM_WAIT_EXEC as flag to call_usermode_helper(). Specifically, the effect is that each uevent that is being sent causes the code to wake up keventd, then block until keventd has processed the work. Needless to say, this happens many times during the system boot. This patches changes that to UHN_NO_WAIT (brilliant name for a constant btw) so that we only schedule the work to fire the uevent message, but do not wait for keventd to process the work. This removes one of the bottlenecks during boot; each one of them is only a small effect, but the sum of them does add up. [Note, distros that need this are broken, they should be setting CONFIG_UEVENT_HELPER_PATH to "", that way this code path will never be excuted at all -- gregkh] Signed-off-by: Arjan van de Ven Signed-off-by: Greg Kroah-Hartman --- lib/kobject_uevent.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'lib') diff --git a/lib/kobject_uevent.c b/lib/kobject_uevent.c index b2181cc8e4d8..e68e743bd861 100644 --- a/lib/kobject_uevent.c +++ b/lib/kobject_uevent.c @@ -255,7 +255,7 @@ int kobject_uevent_env(struct kobject *kobj, enum kobject_action action, goto exit; retval = call_usermodehelper(argv[0], argv, - env->envp, UMH_WAIT_EXEC); + env->envp, UMH_NO_WAIT); } exit: -- cgit v1.2.3-59-g8ed1b From e9d376f0fa66bd630fe27403669c6ae6c22a868f Mon Sep 17 00:00:00 2001 From: Jason Baron Date: Thu, 5 Feb 2009 11:51:38 -0500 Subject: dynamic debug: combine dprintk and dynamic printk This patch combines Greg Bank's dprintk() work with the existing dynamic printk patchset, we are now calling it 'dynamic debug'. The new feature of this patchset is a richer /debugfs control file interface, (an example output from my system is at the bottom), which allows fined grained control over the the debug output. The output can be controlled by function, file, module, format string, and line number. for example, enabled all debug messages in module 'nf_conntrack': echo -n 'module nf_conntrack +p' > /mnt/debugfs/dynamic_debug/control to disable them: echo -n 'module nf_conntrack -p' > /mnt/debugfs/dynamic_debug/control A further explanation can be found in the documentation patch. Signed-off-by: Greg Banks Signed-off-by: Jason Baron Signed-off-by: Greg Kroah-Hartman --- Documentation/kernel-parameters.txt | 5 - include/asm-generic/vmlinux.lds.h | 15 +- include/linux/device.h | 2 +- include/linux/dynamic_debug.h | 88 +++++ include/linux/dynamic_printk.h | 93 ----- include/linux/kernel.h | 4 +- kernel/module.c | 25 +- lib/Kconfig.debug | 2 +- lib/Makefile | 2 +- lib/dynamic_debug.c | 756 ++++++++++++++++++++++++++++++++++++ lib/dynamic_printk.c | 414 -------------------- net/netfilter/nf_conntrack_pptp.c | 2 +- scripts/Makefile.lib | 2 +- 13 files changed, 867 insertions(+), 543 deletions(-) create mode 100644 include/linux/dynamic_debug.h delete mode 100644 include/linux/dynamic_printk.h create mode 100644 lib/dynamic_debug.c delete mode 100644 lib/dynamic_printk.c (limited to 'lib') diff --git a/Documentation/kernel-parameters.txt b/Documentation/kernel-parameters.txt index 54f21a5c262b..3a1aa8a4affc 100644 --- a/Documentation/kernel-parameters.txt +++ b/Documentation/kernel-parameters.txt @@ -1816,11 +1816,6 @@ and is between 256 and 4096 characters. It is defined in the file autoconfiguration. Ranges are in pairs (memory base and size). - dynamic_printk Enables pr_debug()/dev_dbg() calls if - CONFIG_DYNAMIC_PRINTK_DEBUG has been enabled. - These can also be switched on/off via - /dynamic_printk/modules - print-fatal-signals= [KNL] debug: print fatal signals print-fatal-signals=1: print segfault info to diff --git a/include/asm-generic/vmlinux.lds.h b/include/asm-generic/vmlinux.lds.h index c61fab1dd2f8..aca40b93bd28 100644 --- a/include/asm-generic/vmlinux.lds.h +++ b/include/asm-generic/vmlinux.lds.h @@ -80,6 +80,11 @@ VMLINUX_SYMBOL(__start___tracepoints) = .; \ *(__tracepoints) \ VMLINUX_SYMBOL(__stop___tracepoints) = .; \ + /* implement dynamic printk debug */ \ + . = ALIGN(8); \ + VMLINUX_SYMBOL(__start___verbose) = .; \ + *(__verbose) \ + VMLINUX_SYMBOL(__stop___verbose) = .; \ LIKELY_PROFILE() \ BRANCH_PROFILE() @@ -309,15 +314,7 @@ CPU_DISCARD(init.data) \ CPU_DISCARD(init.rodata) \ MEM_DISCARD(init.data) \ - MEM_DISCARD(init.rodata) \ - /* implement dynamic printk debug */ \ - VMLINUX_SYMBOL(__start___verbose_strings) = .; \ - *(__verbose_strings) \ - VMLINUX_SYMBOL(__stop___verbose_strings) = .; \ - . = ALIGN(8); \ - VMLINUX_SYMBOL(__start___verbose) = .; \ - *(__verbose) \ - VMLINUX_SYMBOL(__stop___verbose) = .; + MEM_DISCARD(init.rodata) #define INIT_TEXT \ *(.init.text) \ diff --git a/include/linux/device.h b/include/linux/device.h index f98d0cfb4f81..2918c0e8fdfd 100644 --- a/include/linux/device.h +++ b/include/linux/device.h @@ -582,7 +582,7 @@ extern const char *dev_driver_string(const struct device *dev); #if defined(DEBUG) #define dev_dbg(dev, format, arg...) \ dev_printk(KERN_DEBUG , dev , format , ## arg) -#elif defined(CONFIG_DYNAMIC_PRINTK_DEBUG) +#elif defined(CONFIG_DYNAMIC_DEBUG) #define dev_dbg(dev, format, ...) do { \ dynamic_dev_dbg(dev, format, ##__VA_ARGS__); \ } while (0) diff --git a/include/linux/dynamic_debug.h b/include/linux/dynamic_debug.h new file mode 100644 index 000000000000..07781aaa1164 --- /dev/null +++ b/include/linux/dynamic_debug.h @@ -0,0 +1,88 @@ +#ifndef _DYNAMIC_DEBUG_H +#define _DYNAMIC_DEBUG_H + +/* dynamic_printk_enabled, and dynamic_printk_enabled2 are bitmasks in which + * bit n is set to 1 if any modname hashes into the bucket n, 0 otherwise. They + * use independent hash functions, to reduce the chance of false positives. + */ +extern long long dynamic_debug_enabled; +extern long long dynamic_debug_enabled2; + +/* + * An instance of this structure is created in a special + * ELF section at every dynamic debug callsite. At runtime, + * the special section is treated as an array of these. + */ +struct _ddebug { + /* + * These fields are used to drive the user interface + * for selecting and displaying debug callsites. + */ + const char *modname; + const char *function; + const char *filename; + const char *format; + char primary_hash; + char secondary_hash; + unsigned int lineno:24; + /* + * The flags field controls the behaviour at the callsite. + * The bits here are changed dynamically when the user + * writes commands to /dynamic_debug/ddebug + */ +#define _DPRINTK_FLAGS_PRINT (1<<0) /* printk() a message using the format */ +#define _DPRINTK_FLAGS_DEFAULT 0 + unsigned int flags:8; +} __attribute__((aligned(8))); + + +int ddebug_add_module(struct _ddebug *tab, unsigned int n, + const char *modname); + +#if defined(CONFIG_DYNAMIC_DEBUG) +extern int ddebug_remove_module(char *mod_name); + +#define __dynamic_dbg_enabled(dd) ({ \ + int __ret = 0; \ + if (unlikely((dynamic_debug_enabled & (1LL << DEBUG_HASH)) && \ + (dynamic_debug_enabled2 & (1LL << DEBUG_HASH2)))) \ + if (unlikely(dd.flags)) \ + __ret = 1; \ + __ret; }) + +#define dynamic_pr_debug(fmt, ...) do { \ + static struct _ddebug descriptor \ + __used \ + __attribute__((section("__verbose"), aligned(8))) = \ + { KBUILD_MODNAME, __func__, __FILE__, fmt, DEBUG_HASH, \ + DEBUG_HASH2, __LINE__, _DPRINTK_FLAGS_DEFAULT }; \ + if (__dynamic_dbg_enabled(descriptor)) \ + printk(KERN_DEBUG KBUILD_MODNAME ":" fmt, \ + ##__VA_ARGS__); \ + } while (0) + + +#define dynamic_dev_dbg(dev, fmt, ...) do { \ + static struct _ddebug descriptor \ + __used \ + __attribute__((section("__verbose"), aligned(8))) = \ + { KBUILD_MODNAME, __func__, __FILE__, fmt, DEBUG_HASH, \ + DEBUG_HASH2, __LINE__, _DPRINTK_FLAGS_DEFAULT }; \ + if (__dynamic_dbg_enabled(descriptor)) \ + dev_printk(KERN_DEBUG, dev, \ + KBUILD_MODNAME ": " fmt, \ + ##__VA_ARGS__); \ + } while (0) + +#else + +static inline int ddebug_remove_module(char *mod) +{ + return 0; +} + +#define dynamic_pr_debug(fmt, ...) do { } while (0) +#define dynamic_dev_dbg(dev, format, ...) do { } while (0) +#endif + +#endif diff --git a/include/linux/dynamic_printk.h b/include/linux/dynamic_printk.h deleted file mode 100644 index 2d528d009074..000000000000 --- a/include/linux/dynamic_printk.h +++ /dev/null @@ -1,93 +0,0 @@ -#ifndef _DYNAMIC_PRINTK_H -#define _DYNAMIC_PRINTK_H - -#define DYNAMIC_DEBUG_HASH_BITS 6 -#define DEBUG_HASH_TABLE_SIZE (1 << DYNAMIC_DEBUG_HASH_BITS) - -#define TYPE_BOOLEAN 1 - -#define DYNAMIC_ENABLED_ALL 0 -#define DYNAMIC_ENABLED_NONE 1 -#define DYNAMIC_ENABLED_SOME 2 - -extern int dynamic_enabled; - -/* dynamic_printk_enabled, and dynamic_printk_enabled2 are bitmasks in which - * bit n is set to 1 if any modname hashes into the bucket n, 0 otherwise. They - * use independent hash functions, to reduce the chance of false positives. - */ -extern long long dynamic_printk_enabled; -extern long long dynamic_printk_enabled2; - -struct mod_debug { - char *modname; - char *logical_modname; - char *flag_names; - int type; - int hash; - int hash2; -} __attribute__((aligned(8))); - -int register_dynamic_debug_module(char *mod_name, int type, char *share_name, - char *flags, int hash, int hash2); - -#if defined(CONFIG_DYNAMIC_PRINTK_DEBUG) -extern int unregister_dynamic_debug_module(char *mod_name); -extern int __dynamic_dbg_enabled_helper(char *modname, int type, - int value, int hash); - -#define __dynamic_dbg_enabled(module, type, value, level, hash) ({ \ - int __ret = 0; \ - if (unlikely((dynamic_printk_enabled & (1LL << DEBUG_HASH)) && \ - (dynamic_printk_enabled2 & (1LL << DEBUG_HASH2)))) \ - __ret = __dynamic_dbg_enabled_helper(module, type, \ - value, hash);\ - __ret; }) - -#define dynamic_pr_debug(fmt, ...) do { \ - static char mod_name[] \ - __attribute__((section("__verbose_strings"))) \ - = KBUILD_MODNAME; \ - static struct mod_debug descriptor \ - __used \ - __attribute__((section("__verbose"), aligned(8))) = \ - { mod_name, mod_name, NULL, TYPE_BOOLEAN, DEBUG_HASH, DEBUG_HASH2 };\ - if (__dynamic_dbg_enabled(KBUILD_MODNAME, TYPE_BOOLEAN, \ - 0, 0, DEBUG_HASH)) \ - printk(KERN_DEBUG KBUILD_MODNAME ":" fmt, \ - ##__VA_ARGS__); \ - } while (0) - -#define dynamic_dev_dbg(dev, format, ...) do { \ - static char mod_name[] \ - __attribute__((section("__verbose_strings"))) \ - = KBUILD_MODNAME; \ - static struct mod_debug descriptor \ - __used \ - __attribute__((section("__verbose"), aligned(8))) = \ - { mod_name, mod_name, NULL, TYPE_BOOLEAN, DEBUG_HASH, DEBUG_HASH2 };\ - if (__dynamic_dbg_enabled(KBUILD_MODNAME, TYPE_BOOLEAN, \ - 0, 0, DEBUG_HASH)) \ - dev_printk(KERN_DEBUG, dev, \ - KBUILD_MODNAME ": " format, \ - ##__VA_ARGS__); \ - } while (0) - -#else - -static inline int unregister_dynamic_debug_module(const char *mod_name) -{ - return 0; -} -static inline int __dynamic_dbg_enabled_helper(char *modname, int type, - int value, int hash) -{ - return 0; -} - -#define __dynamic_dbg_enabled(module, type, value, level, hash) ({ 0; }) -#define dynamic_pr_debug(fmt, ...) do { } while (0) -#define dynamic_dev_dbg(dev, format, ...) do { } while (0) -#endif - -#endif diff --git a/include/linux/kernel.h b/include/linux/kernel.h index 7fa371898e3e..b5496ecbec71 100644 --- a/include/linux/kernel.h +++ b/include/linux/kernel.h @@ -16,7 +16,7 @@ #include #include #include -#include +#include #include #include @@ -358,7 +358,7 @@ static inline char *pack_hex_byte(char *buf, u8 byte) #if defined(DEBUG) #define pr_debug(fmt, ...) \ printk(KERN_DEBUG pr_fmt(fmt), ##__VA_ARGS__) -#elif defined(CONFIG_DYNAMIC_PRINTK_DEBUG) +#elif defined(CONFIG_DYNAMIC_DEBUG) #define pr_debug(fmt, ...) do { \ dynamic_pr_debug(pr_fmt(fmt), ##__VA_ARGS__); \ } while (0) diff --git a/kernel/module.c b/kernel/module.c index 1196f5d11700..77672233387f 100644 --- a/kernel/module.c +++ b/kernel/module.c @@ -822,7 +822,7 @@ SYSCALL_DEFINE2(delete_module, const char __user *, name_user, mutex_lock(&module_mutex); /* Store the name of the last unloaded module for diagnostic purposes */ strlcpy(last_unloaded_module, mod->name, sizeof(last_unloaded_module)); - unregister_dynamic_debug_module(mod->name); + ddebug_remove_module(mod->name); free_module(mod); out: @@ -1827,19 +1827,13 @@ static inline void add_kallsyms(struct module *mod, } #endif /* CONFIG_KALLSYMS */ -static void dynamic_printk_setup(struct mod_debug *debug, unsigned int num) +static void dynamic_debug_setup(struct _ddebug *debug, unsigned int num) { -#ifdef CONFIG_DYNAMIC_PRINTK_DEBUG - unsigned int i; - - for (i = 0; i < num; i++) { - register_dynamic_debug_module(debug[i].modname, - debug[i].type, - debug[i].logical_modname, - debug[i].flag_names, - debug[i].hash, debug[i].hash2); - } -#endif /* CONFIG_DYNAMIC_PRINTK_DEBUG */ +#ifdef CONFIG_DYNAMIC_DEBUG + if (ddebug_add_module(debug, num, debug->modname)) + printk(KERN_ERR "dynamic debug error adding module: %s\n", + debug->modname); +#endif } static void *module_alloc_update_bounds(unsigned long size) @@ -2213,12 +2207,13 @@ static noinline struct module *load_module(void __user *umod, add_kallsyms(mod, sechdrs, symindex, strindex, secstrings); if (!mod->taints) { - struct mod_debug *debug; + struct _ddebug *debug; unsigned int num_debug; debug = section_objs(hdr, sechdrs, secstrings, "__verbose", sizeof(*debug), &num_debug); - dynamic_printk_setup(debug, num_debug); + if (debug) + dynamic_debug_setup(debug, num_debug); } /* sechdrs[0].sh_size is always zero */ diff --git a/lib/Kconfig.debug b/lib/Kconfig.debug index 1bcf9cd4baa0..0dd1c04c7323 100644 --- a/lib/Kconfig.debug +++ b/lib/Kconfig.debug @@ -847,7 +847,7 @@ config BUILD_DOCSRC Say N if you are unsure. -config DYNAMIC_PRINTK_DEBUG +config DYNAMIC_DEBUG bool "Enable dynamic printk() call support" default n depends on PRINTK diff --git a/lib/Makefile b/lib/Makefile index 32b0e64ded27..8633d6be9d21 100644 --- a/lib/Makefile +++ b/lib/Makefile @@ -82,7 +82,7 @@ obj-$(CONFIG_HAVE_LMB) += lmb.o obj-$(CONFIG_HAVE_ARCH_TRACEHOOK) += syscall.o -obj-$(CONFIG_DYNAMIC_PRINTK_DEBUG) += dynamic_printk.o +obj-$(CONFIG_DYNAMIC_DEBUG) += dynamic_debug.o hostprogs-y := gen_crc32table clean-files := crc32table.h diff --git a/lib/dynamic_debug.c b/lib/dynamic_debug.c new file mode 100644 index 000000000000..9e123ae326bc --- /dev/null +++ b/lib/dynamic_debug.c @@ -0,0 +1,756 @@ +/* + * lib/dynamic_debug.c + * + * make pr_debug()/dev_dbg() calls runtime configurable based upon their + * source module. + * + * Copyright (C) 2008 Jason Baron + * By Greg Banks + * Copyright (c) 2008 Silicon Graphics Inc. All Rights Reserved. + */ + +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include + +extern struct _ddebug __start___verbose[]; +extern struct _ddebug __stop___verbose[]; + +/* dynamic_debug_enabled, and dynamic_debug_enabled2 are bitmasks in which + * bit n is set to 1 if any modname hashes into the bucket n, 0 otherwise. They + * use independent hash functions, to reduce the chance of false positives. + */ +long long dynamic_debug_enabled; +EXPORT_SYMBOL_GPL(dynamic_debug_enabled); +long long dynamic_debug_enabled2; +EXPORT_SYMBOL_GPL(dynamic_debug_enabled2); + +struct ddebug_table { + struct list_head link; + char *mod_name; + unsigned int num_ddebugs; + unsigned int num_enabled; + struct _ddebug *ddebugs; +}; + +struct ddebug_query { + const char *filename; + const char *module; + const char *function; + const char *format; + unsigned int first_lineno, last_lineno; +}; + +struct ddebug_iter { + struct ddebug_table *table; + unsigned int idx; +}; + +static DEFINE_MUTEX(ddebug_lock); +static LIST_HEAD(ddebug_tables); +static int verbose = 0; + +/* Return the last part of a pathname */ +static inline const char *basename(const char *path) +{ + const char *tail = strrchr(path, '/'); + return tail ? tail+1 : path; +} + +/* format a string into buf[] which describes the _ddebug's flags */ +static char *ddebug_describe_flags(struct _ddebug *dp, char *buf, + size_t maxlen) +{ + char *p = buf; + + BUG_ON(maxlen < 4); + if (dp->flags & _DPRINTK_FLAGS_PRINT) + *p++ = 'p'; + if (p == buf) + *p++ = '-'; + *p = '\0'; + + return buf; +} + +/* + * must be called with ddebug_lock held + */ + +static int disabled_hash(char hash, bool first_table) +{ + struct ddebug_table *dt; + char table_hash_value; + + list_for_each_entry(dt, &ddebug_tables, link) { + if (first_table) + table_hash_value = dt->ddebugs->primary_hash; + else + table_hash_value = dt->ddebugs->secondary_hash; + if (dt->num_enabled && (hash == table_hash_value)) + return 0; + } + return 1; +} + +/* + * Search the tables for _ddebug's which match the given + * `query' and apply the `flags' and `mask' to them. Tells + * the user which ddebug's were changed, or whether none + * were matched. + */ +static void ddebug_change(const struct ddebug_query *query, + unsigned int flags, unsigned int mask) +{ + int i; + struct ddebug_table *dt; + unsigned int newflags; + unsigned int nfound = 0; + char flagbuf[8]; + + /* search for matching ddebugs */ + mutex_lock(&ddebug_lock); + list_for_each_entry(dt, &ddebug_tables, link) { + + /* match against the module name */ + if (query->module != NULL && + strcmp(query->module, dt->mod_name)) + continue; + + for (i = 0 ; i < dt->num_ddebugs ; i++) { + struct _ddebug *dp = &dt->ddebugs[i]; + + /* match against the source filename */ + if (query->filename != NULL && + strcmp(query->filename, dp->filename) && + strcmp(query->filename, basename(dp->filename))) + continue; + + /* match against the function */ + if (query->function != NULL && + strcmp(query->function, dp->function)) + continue; + + /* match against the format */ + if (query->format != NULL && + strstr(dp->format, query->format) == NULL) + continue; + + /* match against the line number range */ + if (query->first_lineno && + dp->lineno < query->first_lineno) + continue; + if (query->last_lineno && + dp->lineno > query->last_lineno) + continue; + + nfound++; + + newflags = (dp->flags & mask) | flags; + if (newflags == dp->flags) + continue; + + if (!newflags) + dt->num_enabled--; + else if (!dp-flags) + dt->num_enabled++; + dp->flags = newflags; + if (newflags) { + dynamic_debug_enabled |= + (1LL << dp->primary_hash); + dynamic_debug_enabled2 |= + (1LL << dp->secondary_hash); + } else { + if (disabled_hash(dp->primary_hash, true)) + dynamic_debug_enabled &= + ~(1LL << dp->primary_hash); + if (disabled_hash(dp->secondary_hash, false)) + dynamic_debug_enabled2 &= + ~(1LL << dp->secondary_hash); + } + if (verbose) + printk(KERN_INFO + "ddebug: changed %s:%d [%s]%s %s\n", + dp->filename, dp->lineno, + dt->mod_name, dp->function, + ddebug_describe_flags(dp, flagbuf, + sizeof(flagbuf))); + } + } + mutex_unlock(&ddebug_lock); + + if (!nfound && verbose) + printk(KERN_INFO "ddebug: no matches for query\n"); +} + +/* + * Wrapper around strsep() to collapse the multiple empty tokens + * that it returns when fed sequences of separator characters. + * Now, if we had strtok_r()... + */ +static inline char *nearly_strtok_r(char **p, const char *sep) +{ + char *r; + + while ((r = strsep(p, sep)) != NULL && *r == '\0') + ; + return r; +} + +/* + * Split the buffer `buf' into space-separated words. + * Return the number of such words or <0 on error. + */ +static int ddebug_tokenize(char *buf, char *words[], int maxwords) +{ + int nwords = 0; + + while (nwords < maxwords && + (words[nwords] = nearly_strtok_r(&buf, " \t\r\n")) != NULL) + nwords++; + if (buf) + return -EINVAL; /* ran out of words[] before bytes */ + + if (verbose) { + int i; + printk(KERN_INFO "%s: split into words:", __func__); + for (i = 0 ; i < nwords ; i++) + printk(" \"%s\"", words[i]); + printk("\n"); + } + + return nwords; +} + +/* + * Parse a single line number. Note that the empty string "" + * is treated as a special case and converted to zero, which + * is later treated as a "don't care" value. + */ +static inline int parse_lineno(const char *str, unsigned int *val) +{ + char *end = NULL; + BUG_ON(str == NULL); + if (*str == '\0') { + *val = 0; + return 0; + } + *val = simple_strtoul(str, &end, 10); + return end == NULL || end == str || *end != '\0' ? -EINVAL : 0; +} + +/* + * Undo octal escaping in a string, inplace. This is useful to + * allow the user to express a query which matches a format + * containing embedded spaces. + */ +#define isodigit(c) ((c) >= '0' && (c) <= '7') +static char *unescape(char *str) +{ + char *in = str; + char *out = str; + + while (*in) { + if (*in == '\\') { + if (in[1] == '\\') { + *out++ = '\\'; + in += 2; + continue; + } else if (in[1] == 't') { + *out++ = '\t'; + in += 2; + continue; + } else if (in[1] == 'n') { + *out++ = '\n'; + in += 2; + continue; + } else if (isodigit(in[1]) && + isodigit(in[2]) && + isodigit(in[3])) { + *out++ = ((in[1] - '0')<<6) | + ((in[2] - '0')<<3) | + (in[3] - '0'); + in += 4; + continue; + } + } + *out++ = *in++; + } + *out = '\0'; + + return str; +} + +/* + * Parse words[] as a ddebug query specification, which is a series + * of (keyword, value) pairs chosen from these possibilities: + * + * func + * file + * file + * module + * format + * line + * line - // where either may be empty + */ +static int ddebug_parse_query(char *words[], int nwords, + struct ddebug_query *query) +{ + unsigned int i; + + /* check we have an even number of words */ + if (nwords % 2 != 0) + return -EINVAL; + memset(query, 0, sizeof(*query)); + + for (i = 0 ; i < nwords ; i += 2) { + if (!strcmp(words[i], "func")) + query->function = words[i+1]; + else if (!strcmp(words[i], "file")) + query->filename = words[i+1]; + else if (!strcmp(words[i], "module")) + query->module = words[i+1]; + else if (!strcmp(words[i], "format")) + query->format = unescape(words[i+1]); + else if (!strcmp(words[i], "line")) { + char *first = words[i+1]; + char *last = strchr(first, '-'); + if (last) + *last++ = '\0'; + if (parse_lineno(first, &query->first_lineno) < 0) + return -EINVAL; + if (last != NULL) { + /* range - */ + if (parse_lineno(last, &query->last_lineno) < 0) + return -EINVAL; + } else { + query->last_lineno = query->first_lineno; + } + } else { + if (verbose) + printk(KERN_ERR "%s: unknown keyword \"%s\"\n", + __func__, words[i]); + return -EINVAL; + } + } + + if (verbose) + printk(KERN_INFO "%s: q->function=\"%s\" q->filename=\"%s\" " + "q->module=\"%s\" q->format=\"%s\" q->lineno=%u-%u\n", + __func__, query->function, query->filename, + query->module, query->format, query->first_lineno, + query->last_lineno); + + return 0; +} + +/* + * Parse `str' as a flags specification, format [-+=][p]+. + * Sets up *maskp and *flagsp to be used when changing the + * flags fields of matched _ddebug's. Returns 0 on success + * or <0 on error. + */ +static int ddebug_parse_flags(const char *str, unsigned int *flagsp, + unsigned int *maskp) +{ + unsigned flags = 0; + int op = '='; + + switch (*str) { + case '+': + case '-': + case '=': + op = *str++; + break; + default: + return -EINVAL; + } + if (verbose) + printk(KERN_INFO "%s: op='%c'\n", __func__, op); + + for ( ; *str ; ++str) { + switch (*str) { + case 'p': + flags |= _DPRINTK_FLAGS_PRINT; + break; + default: + return -EINVAL; + } + } + if (flags == 0) + return -EINVAL; + if (verbose) + printk(KERN_INFO "%s: flags=0x%x\n", __func__, flags); + + /* calculate final *flagsp, *maskp according to mask and op */ + switch (op) { + case '=': + *maskp = 0; + *flagsp = flags; + break; + case '+': + *maskp = ~0U; + *flagsp = flags; + break; + case '-': + *maskp = ~flags; + *flagsp = 0; + break; + } + if (verbose) + printk(KERN_INFO "%s: *flagsp=0x%x *maskp=0x%x\n", + __func__, *flagsp, *maskp); + return 0; +} + +/* + * File_ops->write method for /dynamic_debug/conrol. Gathers the + * command text from userspace, parses and executes it. + */ +static ssize_t ddebug_proc_write(struct file *file, const char __user *ubuf, + size_t len, loff_t *offp) +{ + unsigned int flags = 0, mask = 0; + struct ddebug_query query; +#define MAXWORDS 9 + int nwords; + char *words[MAXWORDS]; + char tmpbuf[256]; + + if (len == 0) + return 0; + /* we don't check *offp -- multiple writes() are allowed */ + if (len > sizeof(tmpbuf)-1) + return -E2BIG; + if (copy_from_user(tmpbuf, ubuf, len)) + return -EFAULT; + tmpbuf[len] = '\0'; + if (verbose) + printk(KERN_INFO "%s: read %d bytes from userspace\n", + __func__, (int)len); + + nwords = ddebug_tokenize(tmpbuf, words, MAXWORDS); + if (nwords < 0) + return -EINVAL; + if (ddebug_parse_query(words, nwords-1, &query)) + return -EINVAL; + if (ddebug_parse_flags(words[nwords-1], &flags, &mask)) + return -EINVAL; + + /* actually go and implement the change */ + ddebug_change(&query, flags, mask); + + *offp += len; + return len; +} + +/* + * Set the iterator to point to the first _ddebug object + * and return a pointer to that first object. Returns + * NULL if there are no _ddebugs at all. + */ +static struct _ddebug *ddebug_iter_first(struct ddebug_iter *iter) +{ + if (list_empty(&ddebug_tables)) { + iter->table = NULL; + iter->idx = 0; + return NULL; + } + iter->table = list_entry(ddebug_tables.next, + struct ddebug_table, link); + iter->idx = 0; + return &iter->table->ddebugs[iter->idx]; +} + +/* + * Advance the iterator to point to the next _ddebug + * object from the one the iterator currently points at, + * and returns a pointer to the new _ddebug. Returns + * NULL if the iterator has seen all the _ddebugs. + */ +static struct _ddebug *ddebug_iter_next(struct ddebug_iter *iter) +{ + if (iter->table == NULL) + return NULL; + if (++iter->idx == iter->table->num_ddebugs) { + /* iterate to next table */ + iter->idx = 0; + if (list_is_last(&iter->table->link, &ddebug_tables)) { + iter->table = NULL; + return NULL; + } + iter->table = list_entry(iter->table->link.next, + struct ddebug_table, link); + } + return &iter->table->ddebugs[iter->idx]; +} + +/* + * Seq_ops start method. Called at the start of every + * read() call from userspace. Takes the ddebug_lock and + * seeks the seq_file's iterator to the given position. + */ +static void *ddebug_proc_start(struct seq_file *m, loff_t *pos) +{ + struct ddebug_iter *iter = m->private; + struct _ddebug *dp; + int n = *pos; + + if (verbose) + printk(KERN_INFO "%s: called m=%p *pos=%lld\n", + __func__, m, (unsigned long long)*pos); + + mutex_lock(&ddebug_lock); + + if (!n) + return SEQ_START_TOKEN; + if (n < 0) + return NULL; + dp = ddebug_iter_first(iter); + while (dp != NULL && --n > 0) + dp = ddebug_iter_next(iter); + return dp; +} + +/* + * Seq_ops next method. Called several times within a read() + * call from userspace, with ddebug_lock held. Walks to the + * next _ddebug object with a special case for the header line. + */ +static void *ddebug_proc_next(struct seq_file *m, void *p, loff_t *pos) +{ + struct ddebug_iter *iter = m->private; + struct _ddebug *dp; + + if (verbose) + printk(KERN_INFO "%s: called m=%p p=%p *pos=%lld\n", + __func__, m, p, (unsigned long long)*pos); + + if (p == SEQ_START_TOKEN) + dp = ddebug_iter_first(iter); + else + dp = ddebug_iter_next(iter); + ++*pos; + return dp; +} + +/* + * Seq_ops show method. Called several times within a read() + * call from userspace, with ddebug_lock held. Formats the + * current _ddebug as a single human-readable line, with a + * special case for the header line. + */ +static int ddebug_proc_show(struct seq_file *m, void *p) +{ + struct ddebug_iter *iter = m->private; + struct _ddebug *dp = p; + char flagsbuf[8]; + + if (verbose) + printk(KERN_INFO "%s: called m=%p p=%p\n", + __func__, m, p); + + if (p == SEQ_START_TOKEN) { + seq_puts(m, + "# filename:lineno [module]function flags format\n"); + return 0; + } + + seq_printf(m, "%s:%u [%s]%s %s \"", + dp->filename, dp->lineno, + iter->table->mod_name, dp->function, + ddebug_describe_flags(dp, flagsbuf, sizeof(flagsbuf))); + seq_escape(m, dp->format, "\t\r\n\""); + seq_puts(m, "\"\n"); + + return 0; +} + +/* + * Seq_ops stop method. Called at the end of each read() + * call from userspace. Drops ddebug_lock. + */ +static void ddebug_proc_stop(struct seq_file *m, void *p) +{ + if (verbose) + printk(KERN_INFO "%s: called m=%p p=%p\n", + __func__, m, p); + mutex_unlock(&ddebug_lock); +} + +static const struct seq_operations ddebug_proc_seqops = { + .start = ddebug_proc_start, + .next = ddebug_proc_next, + .show = ddebug_proc_show, + .stop = ddebug_proc_stop +}; + +/* + * File_ops->open method for /dynamic_debug/control. Does the seq_file + * setup dance, and also creates an iterator to walk the _ddebugs. + * Note that we create a seq_file always, even for O_WRONLY files + * where it's not needed, as doing so simplifies the ->release method. + */ +static int ddebug_proc_open(struct inode *inode, struct file *file) +{ + struct ddebug_iter *iter; + int err; + + if (verbose) + printk(KERN_INFO "%s: called\n", __func__); + + iter = kzalloc(sizeof(*iter), GFP_KERNEL); + if (iter == NULL) + return -ENOMEM; + + err = seq_open(file, &ddebug_proc_seqops); + if (err) { + kfree(iter); + return err; + } + ((struct seq_file *) file->private_data)->private = iter; + return 0; +} + +static const struct file_operations ddebug_proc_fops = { + .owner = THIS_MODULE, + .open = ddebug_proc_open, + .read = seq_read, + .llseek = seq_lseek, + .release = seq_release_private, + .write = ddebug_proc_write +}; + +/* + * Allocate a new ddebug_table for the given module + * and add it to the global list. + */ +int ddebug_add_module(struct _ddebug *tab, unsigned int n, + const char *name) +{ + struct ddebug_table *dt; + char *new_name; + + dt = kzalloc(sizeof(*dt), GFP_KERNEL); + if (dt == NULL) + return -ENOMEM; + new_name = kstrdup(name, GFP_KERNEL); + if (new_name == NULL) { + kfree(dt); + return -ENOMEM; + } + dt->mod_name = new_name; + dt->num_ddebugs = n; + dt->num_enabled = 0; + dt->ddebugs = tab; + + mutex_lock(&ddebug_lock); + list_add_tail(&dt->link, &ddebug_tables); + mutex_unlock(&ddebug_lock); + + if (verbose) + printk(KERN_INFO "%u debug prints in module %s\n", + n, dt->mod_name); + return 0; +} +EXPORT_SYMBOL_GPL(ddebug_add_module); + +static void ddebug_table_free(struct ddebug_table *dt) +{ + list_del_init(&dt->link); + kfree(dt->mod_name); + kfree(dt); +} + +/* + * Called in response to a module being unloaded. Removes + * any ddebug_table's which point at the module. + */ +int ddebug_remove_module(char *mod_name) +{ + struct ddebug_table *dt, *nextdt; + int ret = -ENOENT; + + if (verbose) + printk(KERN_INFO "%s: removing module \"%s\"\n", + __func__, mod_name); + + mutex_lock(&ddebug_lock); + list_for_each_entry_safe(dt, nextdt, &ddebug_tables, link) { + if (!strcmp(dt->mod_name, mod_name)) { + ddebug_table_free(dt); + ret = 0; + } + } + mutex_unlock(&ddebug_lock); + return ret; +} +EXPORT_SYMBOL_GPL(ddebug_remove_module); + +static void ddebug_remove_all_tables(void) +{ + mutex_lock(&ddebug_lock); + while (!list_empty(&ddebug_tables)) { + struct ddebug_table *dt = list_entry(ddebug_tables.next, + struct ddebug_table, + link); + ddebug_table_free(dt); + } + mutex_unlock(&ddebug_lock); +} + +static int __init dynamic_debug_init(void) +{ + struct dentry *dir, *file; + struct _ddebug *iter, *iter_start; + const char *modname = NULL; + int ret = 0; + int n = 0; + + dir = debugfs_create_dir("dynamic_debug", NULL); + if (!dir) + return -ENOMEM; + file = debugfs_create_file("control", 0644, dir, NULL, + &ddebug_proc_fops); + if (!file) { + debugfs_remove(dir); + return -ENOMEM; + } + if (__start___verbose != __stop___verbose) { + iter = __start___verbose; + modname = iter->modname; + iter_start = iter; + for (; iter < __stop___verbose; iter++) { + if (strcmp(modname, iter->modname)) { + ret = ddebug_add_module(iter_start, n, modname); + if (ret) + goto out_free; + n = 0; + modname = iter->modname; + iter_start = iter; + } + n++; + } + ret = ddebug_add_module(iter_start, n, modname); + } +out_free: + if (ret) { + ddebug_remove_all_tables(); + debugfs_remove(dir); + debugfs_remove(file); + } + return 0; +} +module_init(dynamic_debug_init); diff --git a/lib/dynamic_printk.c b/lib/dynamic_printk.c deleted file mode 100644 index 165a19763dc9..000000000000 --- a/lib/dynamic_printk.c +++ /dev/null @@ -1,414 +0,0 @@ -/* - * lib/dynamic_printk.c - * - * make pr_debug()/dev_dbg() calls runtime configurable based upon their - * their source module. - * - * Copyright (C) 2008 Red Hat, Inc., Jason Baron - */ - -#include -#include -#include -#include -#include -#include - -extern struct mod_debug __start___verbose[]; -extern struct mod_debug __stop___verbose[]; - -struct debug_name { - struct hlist_node hlist; - struct hlist_node hlist2; - int hash1; - int hash2; - char *name; - int enable; - int type; -}; - -static int nr_entries; -static int num_enabled; -int dynamic_enabled = DYNAMIC_ENABLED_NONE; -static struct hlist_head module_table[DEBUG_HASH_TABLE_SIZE] = - { [0 ... DEBUG_HASH_TABLE_SIZE-1] = HLIST_HEAD_INIT }; -static struct hlist_head module_table2[DEBUG_HASH_TABLE_SIZE] = - { [0 ... DEBUG_HASH_TABLE_SIZE-1] = HLIST_HEAD_INIT }; -static DECLARE_MUTEX(debug_list_mutex); - -/* dynamic_printk_enabled, and dynamic_printk_enabled2 are bitmasks in which - * bit n is set to 1 if any modname hashes into the bucket n, 0 otherwise. They - * use independent hash functions, to reduce the chance of false positives. - */ -long long dynamic_printk_enabled; -EXPORT_SYMBOL_GPL(dynamic_printk_enabled); -long long dynamic_printk_enabled2; -EXPORT_SYMBOL_GPL(dynamic_printk_enabled2); - -/* returns the debug module pointer. */ -static struct debug_name *find_debug_module(char *module_name) -{ - int i; - struct hlist_head *head; - struct hlist_node *node; - struct debug_name *element; - - element = NULL; - for (i = 0; i < DEBUG_HASH_TABLE_SIZE; i++) { - head = &module_table[i]; - hlist_for_each_entry_rcu(element, node, head, hlist) - if (!strcmp(element->name, module_name)) - return element; - } - return NULL; -} - -/* returns the debug module pointer. */ -static struct debug_name *find_debug_module_hash(char *module_name, int hash) -{ - struct hlist_head *head; - struct hlist_node *node; - struct debug_name *element; - - element = NULL; - head = &module_table[hash]; - hlist_for_each_entry_rcu(element, node, head, hlist) - if (!strcmp(element->name, module_name)) - return element; - return NULL; -} - -/* caller must hold mutex*/ -static int __add_debug_module(char *mod_name, int hash, int hash2) -{ - struct debug_name *new; - char *module_name; - int ret = 0; - - if (find_debug_module(mod_name)) { - ret = -EINVAL; - goto out; - } - module_name = kmalloc(strlen(mod_name) + 1, GFP_KERNEL); - if (!module_name) { - ret = -ENOMEM; - goto out; - } - module_name = strcpy(module_name, mod_name); - module_name[strlen(mod_name)] = '\0'; - new = kzalloc(sizeof(struct debug_name), GFP_KERNEL); - if (!new) { - kfree(module_name); - ret = -ENOMEM; - goto out; - } - INIT_HLIST_NODE(&new->hlist); - INIT_HLIST_NODE(&new->hlist2); - new->name = module_name; - new->hash1 = hash; - new->hash2 = hash2; - hlist_add_head_rcu(&new->hlist, &module_table[hash]); - hlist_add_head_rcu(&new->hlist2, &module_table2[hash2]); - nr_entries++; -out: - return ret; -} - -int unregister_dynamic_debug_module(char *mod_name) -{ - struct debug_name *element; - int ret = 0; - - down(&debug_list_mutex); - element = find_debug_module(mod_name); - if (!element) { - ret = -EINVAL; - goto out; - } - hlist_del_rcu(&element->hlist); - hlist_del_rcu(&element->hlist2); - synchronize_rcu(); - kfree(element->name); - if (element->enable) - num_enabled--; - kfree(element); - nr_entries--; -out: - up(&debug_list_mutex); - return ret; -} -EXPORT_SYMBOL_GPL(unregister_dynamic_debug_module); - -int register_dynamic_debug_module(char *mod_name, int type, char *share_name, - char *flags, int hash, int hash2) -{ - struct debug_name *elem; - int ret = 0; - - down(&debug_list_mutex); - elem = find_debug_module(mod_name); - if (!elem) { - if (__add_debug_module(mod_name, hash, hash2)) - goto out; - elem = find_debug_module(mod_name); - if (dynamic_enabled == DYNAMIC_ENABLED_ALL && - !strcmp(mod_name, share_name)) { - elem->enable = true; - num_enabled++; - } - } - elem->type |= type; -out: - up(&debug_list_mutex); - return ret; -} -EXPORT_SYMBOL_GPL(register_dynamic_debug_module); - -int __dynamic_dbg_enabled_helper(char *mod_name, int type, int value, int hash) -{ - struct debug_name *elem; - int ret = 0; - - if (dynamic_enabled == DYNAMIC_ENABLED_ALL) - return 1; - rcu_read_lock(); - elem = find_debug_module_hash(mod_name, hash); - if (elem && elem->enable) - ret = 1; - rcu_read_unlock(); - return ret; -} -EXPORT_SYMBOL_GPL(__dynamic_dbg_enabled_helper); - -static void set_all(bool enable) -{ - struct debug_name *e; - struct hlist_node *node; - int i; - long long enable_mask; - - for (i = 0; i < DEBUG_HASH_TABLE_SIZE; i++) { - if (module_table[i].first != NULL) { - hlist_for_each_entry(e, node, &module_table[i], hlist) { - e->enable = enable; - } - } - } - if (enable) - enable_mask = ULLONG_MAX; - else - enable_mask = 0; - dynamic_printk_enabled = enable_mask; - dynamic_printk_enabled2 = enable_mask; -} - -static int disabled_hash(int i, bool first_table) -{ - struct debug_name *e; - struct hlist_node *node; - - if (first_table) { - hlist_for_each_entry(e, node, &module_table[i], hlist) { - if (e->enable) - return 0; - } - } else { - hlist_for_each_entry(e, node, &module_table2[i], hlist2) { - if (e->enable) - return 0; - } - } - return 1; -} - -static ssize_t pr_debug_write(struct file *file, const char __user *buf, - size_t length, loff_t *ppos) -{ - char *buffer, *s, *value_str, *setting_str; - int err, value; - struct debug_name *elem = NULL; - int all = 0; - - if (length > PAGE_SIZE || length < 0) - return -EINVAL; - - buffer = (char *)__get_free_page(GFP_KERNEL); - if (!buffer) - return -ENOMEM; - - err = -EFAULT; - if (copy_from_user(buffer, buf, length)) - goto out; - - err = -EINVAL; - if (length < PAGE_SIZE) - buffer[length] = '\0'; - else if (buffer[PAGE_SIZE-1]) - goto out; - - err = -EINVAL; - down(&debug_list_mutex); - - if (strncmp("set", buffer, 3)) - goto out_up; - s = buffer + 3; - setting_str = strsep(&s, "="); - if (s == NULL) - goto out_up; - setting_str = strstrip(setting_str); - value_str = strsep(&s, " "); - if (s == NULL) - goto out_up; - s = strstrip(s); - if (!strncmp(s, "all", 3)) - all = 1; - else - elem = find_debug_module(s); - if (!strncmp(setting_str, "enable", 6)) { - value = !!simple_strtol(value_str, NULL, 10); - if (all) { - if (value) { - set_all(true); - num_enabled = nr_entries; - dynamic_enabled = DYNAMIC_ENABLED_ALL; - } else { - set_all(false); - num_enabled = 0; - dynamic_enabled = DYNAMIC_ENABLED_NONE; - } - err = 0; - } else if (elem) { - if (value && (elem->enable == 0)) { - dynamic_printk_enabled |= (1LL << elem->hash1); - dynamic_printk_enabled2 |= (1LL << elem->hash2); - elem->enable = 1; - num_enabled++; - dynamic_enabled = DYNAMIC_ENABLED_SOME; - err = 0; - printk(KERN_DEBUG - "debugging enabled for module %s\n", - elem->name); - } else if (!value && (elem->enable == 1)) { - elem->enable = 0; - num_enabled--; - if (disabled_hash(elem->hash1, true)) - dynamic_printk_enabled &= - ~(1LL << elem->hash1); - if (disabled_hash(elem->hash2, false)) - dynamic_printk_enabled2 &= - ~(1LL << elem->hash2); - if (num_enabled) - dynamic_enabled = DYNAMIC_ENABLED_SOME; - else - dynamic_enabled = DYNAMIC_ENABLED_NONE; - err = 0; - printk(KERN_DEBUG - "debugging disabled for module %s\n", - elem->name); - } - } - } - if (!err) - err = length; -out_up: - up(&debug_list_mutex); -out: - free_page((unsigned long)buffer); - return err; -} - -static void *pr_debug_seq_start(struct seq_file *f, loff_t *pos) -{ - return (*pos < DEBUG_HASH_TABLE_SIZE) ? pos : NULL; -} - -static void *pr_debug_seq_next(struct seq_file *s, void *v, loff_t *pos) -{ - (*pos)++; - if (*pos >= DEBUG_HASH_TABLE_SIZE) - return NULL; - return pos; -} - -static void pr_debug_seq_stop(struct seq_file *s, void *v) -{ - /* Nothing to do */ -} - -static int pr_debug_seq_show(struct seq_file *s, void *v) -{ - struct hlist_head *head; - struct hlist_node *node; - struct debug_name *elem; - unsigned int i = *(loff_t *) v; - - rcu_read_lock(); - head = &module_table[i]; - hlist_for_each_entry_rcu(elem, node, head, hlist) { - seq_printf(s, "%s enabled=%d", elem->name, elem->enable); - seq_printf(s, "\n"); - } - rcu_read_unlock(); - return 0; -} - -static struct seq_operations pr_debug_seq_ops = { - .start = pr_debug_seq_start, - .next = pr_debug_seq_next, - .stop = pr_debug_seq_stop, - .show = pr_debug_seq_show -}; - -static int pr_debug_open(struct inode *inode, struct file *filp) -{ - return seq_open(filp, &pr_debug_seq_ops); -} - -static const struct file_operations pr_debug_operations = { - .open = pr_debug_open, - .read = seq_read, - .write = pr_debug_write, - .llseek = seq_lseek, - .release = seq_release, -}; - -static int __init dynamic_printk_init(void) -{ - struct dentry *dir, *file; - struct mod_debug *iter; - unsigned long value; - - dir = debugfs_create_dir("dynamic_printk", NULL); - if (!dir) - return -ENOMEM; - file = debugfs_create_file("modules", 0644, dir, NULL, - &pr_debug_operations); - if (!file) { - debugfs_remove(dir); - return -ENOMEM; - } - for (value = (unsigned long)__start___verbose; - value < (unsigned long)__stop___verbose; - value += sizeof(struct mod_debug)) { - iter = (struct mod_debug *)value; - register_dynamic_debug_module(iter->modname, - iter->type, - iter->logical_modname, - iter->flag_names, iter->hash, iter->hash2); - } - if (dynamic_enabled == DYNAMIC_ENABLED_ALL) - set_all(true); - return 0; -} -module_init(dynamic_printk_init); -/* may want to move this earlier so we can get traces as early as possible */ - -static int __init dynamic_printk_setup(char *str) -{ - if (str) - return -ENOENT; - dynamic_enabled = DYNAMIC_ENABLED_ALL; - return 0; -} -/* Use early_param(), so we can get debug output as early as possible */ -early_param("dynamic_printk", dynamic_printk_setup); diff --git a/net/netfilter/nf_conntrack_pptp.c b/net/netfilter/nf_conntrack_pptp.c index 9e169ef2e854..12bd09dbd36c 100644 --- a/net/netfilter/nf_conntrack_pptp.c +++ b/net/netfilter/nf_conntrack_pptp.c @@ -66,7 +66,7 @@ void struct nf_conntrack_expect *exp) __read_mostly; EXPORT_SYMBOL_GPL(nf_nat_pptp_hook_expectfn); -#if defined(DEBUG) || defined(CONFIG_DYNAMIC_PRINTK_DEBUG) +#if defined(DEBUG) || defined(CONFIG_DYNAMIC_DEBUG) /* PptpControlMessageType names */ const char *const pptp_msg_name[] = { "UNKNOWN_MESSAGE", diff --git a/scripts/Makefile.lib b/scripts/Makefile.lib index e06365775bdf..c18fa150b6fe 100644 --- a/scripts/Makefile.lib +++ b/scripts/Makefile.lib @@ -97,7 +97,7 @@ modname_flags = $(if $(filter 1,$(words $(modname))),\ -D"KBUILD_MODNAME=KBUILD_STR($(call name-fix,$(modname)))") #hash values -ifdef CONFIG_DYNAMIC_PRINTK_DEBUG +ifdef CONFIG_DYNAMIC_DEBUG debug_flags = -D"DEBUG_HASH=$(shell ./scripts/basic/hash djb2 $(@D)$(modname))"\ -D"DEBUG_HASH2=$(shell ./scripts/basic/hash r5 $(@D)$(modname))" else -- cgit v1.2.3-59-g8ed1b From 86151fdf38b3795f292b39defbff39d2684b9c8c Mon Sep 17 00:00:00 2001 From: Jason Baron Date: Thu, 5 Feb 2009 11:53:15 -0500 Subject: dynamic debug: update docs updates the documentation for 'dynamic debug' feature. Signed-off-by: Greg Banks Signed-off-by: Jason Baron Signed-off-by: Greg Kroah-Hartman --- Documentation/dynamic-debug-howto.txt | 232 ++++++++++++++++++++++++++++++++++ lib/Kconfig.debug | 72 ++++++----- 2 files changed, 273 insertions(+), 31 deletions(-) create mode 100644 Documentation/dynamic-debug-howto.txt (limited to 'lib') diff --git a/Documentation/dynamic-debug-howto.txt b/Documentation/dynamic-debug-howto.txt new file mode 100644 index 000000000000..68394825e86b --- /dev/null +++ b/Documentation/dynamic-debug-howto.txt @@ -0,0 +1,232 @@ + +Introduction +============ + +This document describes how to use the dynamic debug (ddebug) feature. + +Dynamic debug is designed to allow you to dynamically enable/disable kernel +code to obtain additional kernel information. Currently, if +CONFIG_DYNAMIC_DEBUG is set, then all pr_debug()/dev_debug() calls can be +dynamically enabled per-callsite. + +Dynamic debug has even more useful features: + + * Simple query language allows turning on and off debugging statements by + matching any combination of: + + - source filename + - function name + - line number (including ranges of line numbers) + - module name + - format string + + * Provides a debugfs control file: /dynamic_debug/control which can be + read to display the complete list of known debug statements, to help guide you + +Controlling dynamic debug Behaviour +=============================== + +The behaviour of pr_debug()/dev_debug()s are controlled via writing to a +control file in the 'debugfs' filesystem. Thus, you must first mount the debugfs +filesystem, in order to make use of this feature. Subsequently, we refer to the +control file as: /dynamic_debug/control. For example, if you want to +enable printing from source file 'svcsock.c', line 1603 you simply do: + +nullarbor:~ # echo 'file svcsock.c line 1603 +p' > + /dynamic_debug/control + +If you make a mistake with the syntax, the write will fail thus: + +nullarbor:~ # echo 'file svcsock.c wtf 1 +p' > + /dynamic_debug/control +-bash: echo: write error: Invalid argument + +Viewing Dynamic Debug Behaviour +=========================== + +You can view the currently configured behaviour of all the debug statements +via: + +nullarbor:~ # cat /dynamic_debug/control +# filename:lineno [module]function flags format +/usr/src/packages/BUILD/sgi-enhancednfs-1.4/default/net/sunrpc/svc_rdma.c:323 [svcxprt_rdma]svc_rdma_cleanup - "SVCRDMA\040Module\040Removed,\040deregister\040RPC\040RDMA\040transport\012" +/usr/src/packages/BUILD/sgi-enhancednfs-1.4/default/net/sunrpc/svc_rdma.c:341 [svcxprt_rdma]svc_rdma_init - "\011max_inline\040\040\040\040\040\040\040:\040%d\012" +/usr/src/packages/BUILD/sgi-enhancednfs-1.4/default/net/sunrpc/svc_rdma.c:340 [svcxprt_rdma]svc_rdma_init - "\011sq_depth\040\040\040\040\040\040\040\040\040:\040%d\012" +/usr/src/packages/BUILD/sgi-enhancednfs-1.4/default/net/sunrpc/svc_rdma.c:338 [svcxprt_rdma]svc_rdma_init - "\011max_requests\040\040\040\040\040:\040%d\012" +... + + +You can also apply standard Unix text manipulation filters to this +data, e.g. + +nullarbor:~ # grep -i rdma /dynamic_debug/control | wc -l +62 + +nullarbor:~ # grep -i tcp /dynamic_debug/control | wc -l +42 + +Note in particular that the third column shows the enabled behaviour +flags for each debug statement callsite (see below for definitions of the +flags). The default value, no extra behaviour enabled, is "-". So +you can view all the debug statement callsites with any non-default flags: + +nullarbor:~ # awk '$3 != "-"' /dynamic_debug/control +# filename:lineno [module]function flags format +/usr/src/packages/BUILD/sgi-enhancednfs-1.4/default/net/sunrpc/svcsock.c:1603 [sunrpc]svc_send p "svc_process:\040st_sendto\040returned\040%d\012" + + +Command Language Reference +========================== + +At the lexical level, a command comprises a sequence of words separated +by whitespace characters. Note that newlines are treated as word +separators and do *not* end a command or allow multiple commands to +be done together. So these are all equivalent: + +nullarbor:~ # echo -c 'file svcsock.c line 1603 +p' > + /dynamic_debug/control +nullarbor:~ # echo -c ' file svcsock.c line 1603 +p ' > + /dynamic_debug/control +nullarbor:~ # echo -c 'file svcsock.c\nline 1603 +p' > + /dynamic_debug/control +nullarbor:~ # echo -n 'file svcsock.c line 1603 +p' > + /dynamic_debug/control + +Commands are bounded by a write() system call. If you want to do +multiple commands you need to do a separate "echo" for each, like: + +nullarbor:~ # echo 'file svcsock.c line 1603 +p' > /proc/dprintk ;\ +> echo 'file svcsock.c line 1563 +p' > /proc/dprintk + +or even like: + +nullarbor:~ # ( +> echo 'file svcsock.c line 1603 +p' ;\ +> echo 'file svcsock.c line 1563 +p' ;\ +> ) > /proc/dprintk + +At the syntactical level, a command comprises a sequence of match +specifications, followed by a flags change specification. + +command ::= match-spec* flags-spec + +The match-spec's are used to choose a subset of the known dprintk() +callsites to which to apply the flags-spec. Think of them as a query +with implicit ANDs between each pair. Note that an empty list of +match-specs is possible, but is not very useful because it will not +match any debug statement callsites. + +A match specification comprises a keyword, which controls the attribute +of the callsite to be compared, and a value to compare against. Possible +keywords are: + +match-spec ::= 'func' string | + 'file' string | + 'module' string | + 'format' string | + 'line' line-range + +line-range ::= lineno | + '-'lineno | + lineno'-' | + lineno'-'lineno +// Note: line-range cannot contain space, e.g. +// "1-30" is valid range but "1 - 30" is not. + +lineno ::= unsigned-int + +The meanings of each keyword are: + +func + The given string is compared against the function name + of each callsite. Example: + + func svc_tcp_accept + +file + The given string is compared against either the full + pathname or the basename of the source file of each + callsite. Examples: + + file svcsock.c + file /usr/src/packages/BUILD/sgi-enhancednfs-1.4/default/net/sunrpc/svcsock.c + +module + The given string is compared against the module name + of each callsite. The module name is the string as + seen in "lsmod", i.e. without the directory or the .ko + suffix and with '-' changed to '_'. Examples: + + module sunrpc + module nfsd + +format + The given string is searched for in the dynamic debug format + string. Note that the string does not need to match the + entire format, only some part. Whitespace and other + special characters can be escaped using C octal character + escape \ooo notation, e.g. the space character is \040. + Examples: + + format svcrdma: // many of the NFS/RDMA server dprintks + format readahead // some dprintks in the readahead cache + format nfsd:\040SETATTR // how to match a format with whitespace + +line + The given line number or range of line numbers is compared + against the line number of each dprintk() callsite. A single + line number matches the callsite line number exactly. A + range of line numbers matches any callsite between the first + and last line number inclusive. An empty first number means + the first line in the file, an empty line number means the + last number in the file. Examples: + + line 1603 // exactly line 1603 + line 1600-1605 // the six lines from line 1600 to line 1605 + line -1605 // the 1605 lines from line 1 to line 1605 + line 1600- // all lines from line 1600 to the end of the file + +The flags specification comprises a change operation followed +by one or more flag characters. The change operation is one +of the characters: + +- + remove the given flags + ++ + add the given flags + += + set the flags to the given flags + +The flags are: + +p + Causes a printk() message to be emitted to dmesg + +Note the regexp ^[-+=][scp]+$ matches a flags specification. +Note also that there is no convenient syntax to remove all +the flags at once, you need to use "-psc". + +Examples +======== + +// enable the message at line 1603 of file svcsock.c +nullarbor:~ # echo -n 'file svcsock.c line 1603 +p' > + /dynamic_debug/control + +// enable all the messages in file svcsock.c +nullarbor:~ # echo -n 'file svcsock.c +p' > + /dynamic_debug/control + +// enable all the messages in the NFS server module +nullarbor:~ # echo -n 'module nfsd +p' > + /dynamic_debug/control + +// enable all 12 messages in the function svc_process() +nullarbor:~ # echo -n 'func svc_process +p' > + /dynamic_debug/control + +// disable all 12 messages in the function svc_process() +nullarbor:~ # echo -n 'func svc_process -p' > + /dynamic_debug/control diff --git a/lib/Kconfig.debug b/lib/Kconfig.debug index 0dd1c04c7323..8fee0a13ac58 100644 --- a/lib/Kconfig.debug +++ b/lib/Kconfig.debug @@ -848,59 +848,69 @@ config BUILD_DOCSRC Say N if you are unsure. config DYNAMIC_DEBUG - bool "Enable dynamic printk() call support" + bool "Enable dynamic printk() support" default n depends on PRINTK + depends on DEBUG_FS select PRINTK_DEBUG help Compiles debug level messages into the kernel, which would not otherwise be available at runtime. These messages can then be - enabled/disabled on a per module basis. This mechanism implicitly - enables all pr_debug() and dev_dbg() calls. The impact of this - compile option is a larger kernel text size of about 2%. + enabled/disabled based on various levels of scope - per source file, + function, module, format string, and line number. This mechanism + implicitly enables all pr_debug() and dev_dbg() calls. The impact of + this compile option is a larger kernel text size of about 2%. Usage: - Dynamic debugging is controlled by the debugfs file, - dynamic_printk/modules. This file contains a list of the modules that - can be enabled. The format of the file is the module name, followed - by a set of flags that can be enabled. The first flag is always the - 'enabled' flag. For example: + Dynamic debugging is controlled via the 'dynamic_debug/ddebug' file, + which is contained in the 'debugfs' filesystem. Thus, the debugfs + filesystem must first be mounted before making use of this feature. + We refer the control file as: /dynamic_debug/ddebug. This + file contains a list of the debug statements that can be enabled. The + format for each line of the file is: - - . - . - . + filename:lineno [module]function flags format - : Name of the module in which the debug call resides - : whether the messages are enabled or not + filename : source file of the debug statement + lineno : line number of the debug statement + module : module that contains the debug statement + function : function that contains the debug statement + flags : 'p' means the line is turned 'on' for printing + format : the format used for the debug statement From a live system: - snd_hda_intel enabled=0 - fixup enabled=0 - driver enabled=0 + nullarbor:~ # cat /dynamic_debug/ddebug + # filename:lineno [module]function flags format + fs/aio.c:222 [aio]__put_ioctx - "__put_ioctx:\040freeing\040%p\012" + fs/aio.c:248 [aio]ioctx_alloc - "ENOMEM:\040nr_events\040too\040high\012" + fs/aio.c:1770 [aio]sys_io_cancel - "calling\040cancel\012" - Enable a module: + Example usage: - $echo "set enabled=1 " > dynamic_printk/modules + // enable the message at line 1603 of file svcsock.c + nullarbor:~ # echo -n 'file svcsock.c line 1603 +p' > + /dynamic_debug/ddebug - Disable a module: + // enable all the messages in file svcsock.c + nullarbor:~ # echo -n 'file svcsock.c +p' > + /dynamic_debug/ddebug - $echo "set enabled=0 " > dynamic_printk/modules + // enable all the messages in the NFS server module + nullarbor:~ # echo -n 'module nfsd +p' > + /dynamic_debug/ddebug - Enable all modules: + // enable all 12 messages in the function svc_process() + nullarbor:~ # echo -n 'func svc_process +p' > + /dynamic_debug/ddebug - $echo "set enabled=1 all" > dynamic_printk/modules + // disable all 12 messages in the function svc_process() + nullarbor:~ # echo -n 'func svc_process -p' > + /dynamic_debug/ddebug - Disable all modules: - - $echo "set enabled=0 all" > dynamic_printk/modules - - Finally, passing "dynamic_printk" at the command line enables - debugging for all modules. This mode can be turned off via the above - disable command. + See Documentation/dynamic-debug-howto.txt for additional information. source "samples/Kconfig" -- cgit v1.2.3-59-g8ed1b From 9898abb3d23311fa227a7f46bf4e40fd2954057f Mon Sep 17 00:00:00 2001 From: Greg Banks Date: Fri, 6 Feb 2009 12:54:26 +1100 Subject: Dynamic debug: allow simple quoting of words Allow simple quoting of words in the dynamic debug control language. This allows more natural specification when using the control language to match against printk formats, e.g #echo -n 'format "Setting node for non-present cpu" +p' > /mnt/debugfs/dynamic_debug/control instead of #echo -n 'format Setting\040node\040for\040non-present\040cpu +p' > /mnt/debugfs/dynamic_debug/control Adjust the dynamic debug documention to describe that and provide a new example. Adjust the existing examples in the documentation to reflect the current whitespace escaping behaviour when reading the control file. Fix some minor documentation trailing whitespace. Signed-off-by: Greg Banks Acked-by: Jason Baron Signed-off-by: Greg Kroah-Hartman --- Documentation/dynamic-debug-howto.txt | 20 +++++++++---- lib/dynamic_debug.c | 53 ++++++++++++++++++++++------------- 2 files changed, 47 insertions(+), 26 deletions(-) (limited to 'lib') diff --git a/Documentation/dynamic-debug-howto.txt b/Documentation/dynamic-debug-howto.txt index 68394825e86b..674c5663d346 100644 --- a/Documentation/dynamic-debug-howto.txt +++ b/Documentation/dynamic-debug-howto.txt @@ -49,10 +49,10 @@ via: nullarbor:~ # cat /dynamic_debug/control # filename:lineno [module]function flags format -/usr/src/packages/BUILD/sgi-enhancednfs-1.4/default/net/sunrpc/svc_rdma.c:323 [svcxprt_rdma]svc_rdma_cleanup - "SVCRDMA\040Module\040Removed,\040deregister\040RPC\040RDMA\040transport\012" -/usr/src/packages/BUILD/sgi-enhancednfs-1.4/default/net/sunrpc/svc_rdma.c:341 [svcxprt_rdma]svc_rdma_init - "\011max_inline\040\040\040\040\040\040\040:\040%d\012" -/usr/src/packages/BUILD/sgi-enhancednfs-1.4/default/net/sunrpc/svc_rdma.c:340 [svcxprt_rdma]svc_rdma_init - "\011sq_depth\040\040\040\040\040\040\040\040\040:\040%d\012" -/usr/src/packages/BUILD/sgi-enhancednfs-1.4/default/net/sunrpc/svc_rdma.c:338 [svcxprt_rdma]svc_rdma_init - "\011max_requests\040\040\040\040\040:\040%d\012" +/usr/src/packages/BUILD/sgi-enhancednfs-1.4/default/net/sunrpc/svc_rdma.c:323 [svcxprt_rdma]svc_rdma_cleanup - "SVCRDMA Module Removed, deregister RPC RDMA transport\012" +/usr/src/packages/BUILD/sgi-enhancednfs-1.4/default/net/sunrpc/svc_rdma.c:341 [svcxprt_rdma]svc_rdma_init - "\011max_inline : %d\012" +/usr/src/packages/BUILD/sgi-enhancednfs-1.4/default/net/sunrpc/svc_rdma.c:340 [svcxprt_rdma]svc_rdma_init - "\011sq_depth : %d\012" +/usr/src/packages/BUILD/sgi-enhancednfs-1.4/default/net/sunrpc/svc_rdma.c:338 [svcxprt_rdma]svc_rdma_init - "\011max_requests : %d\012" ... @@ -72,7 +72,7 @@ you can view all the debug statement callsites with any non-default flags: nullarbor:~ # awk '$3 != "-"' /dynamic_debug/control # filename:lineno [module]function flags format -/usr/src/packages/BUILD/sgi-enhancednfs-1.4/default/net/sunrpc/svcsock.c:1603 [sunrpc]svc_send p "svc_process:\040st_sendto\040returned\040%d\012" +/usr/src/packages/BUILD/sgi-enhancednfs-1.4/default/net/sunrpc/svcsock.c:1603 [sunrpc]svc_send p "svc_process: st_sendto returned %d\012" Command Language Reference @@ -166,11 +166,15 @@ format entire format, only some part. Whitespace and other special characters can be escaped using C octal character escape \ooo notation, e.g. the space character is \040. + Alternatively, the string can be enclosed in double quote + characters (") or single quote characters ('). Examples: format svcrdma: // many of the NFS/RDMA server dprintks format readahead // some dprintks in the readahead cache - format nfsd:\040SETATTR // how to match a format with whitespace + format nfsd:\040SETATTR // one way to match a format with whitespace + format "nfsd: SETATTR" // a neater way to match a format with whitespace + format 'nfsd: SETATTR' // yet another way to match a format with whitespace line The given line number or range of line numbers is compared @@ -230,3 +234,7 @@ nullarbor:~ # echo -n 'func svc_process +p' > // disable all 12 messages in the function svc_process() nullarbor:~ # echo -n 'func svc_process -p' > /dynamic_debug/control + +// enable messages for NFS calls READ, READLINK, READDIR and READDIR+. +nullarbor:~ # echo -n 'format "nfsd: READ" +p' > + /dynamic_debug/control diff --git a/lib/dynamic_debug.c b/lib/dynamic_debug.c index 9e123ae326bc..833139ce1e22 100644 --- a/lib/dynamic_debug.c +++ b/lib/dynamic_debug.c @@ -195,33 +195,46 @@ static void ddebug_change(const struct ddebug_query *query, printk(KERN_INFO "ddebug: no matches for query\n"); } -/* - * Wrapper around strsep() to collapse the multiple empty tokens - * that it returns when fed sequences of separator characters. - * Now, if we had strtok_r()... - */ -static inline char *nearly_strtok_r(char **p, const char *sep) -{ - char *r; - - while ((r = strsep(p, sep)) != NULL && *r == '\0') - ; - return r; -} - /* * Split the buffer `buf' into space-separated words. - * Return the number of such words or <0 on error. + * Handles simple " and ' quoting, i.e. without nested, + * embedded or escaped \". Return the number of words + * or <0 on error. */ static int ddebug_tokenize(char *buf, char *words[], int maxwords) { int nwords = 0; - while (nwords < maxwords && - (words[nwords] = nearly_strtok_r(&buf, " \t\r\n")) != NULL) - nwords++; - if (buf) - return -EINVAL; /* ran out of words[] before bytes */ + while (*buf) { + char *end; + + /* Skip leading whitespace */ + while (*buf && isspace(*buf)) + buf++; + if (!*buf) + break; /* oh, it was trailing whitespace */ + + /* Run `end' over a word, either whitespace separated or quoted */ + if (*buf == '"' || *buf == '\'') { + int quote = *buf++; + for (end = buf ; *end && *end != quote ; end++) + ; + if (!*end) + return -EINVAL; /* unclosed quote */ + } else { + for (end = buf ; *end && !isspace(*end) ; end++) + ; + BUG_ON(end == buf); + } + /* Here `buf' is the start of the word, `end' is one past the end */ + + if (nwords == maxwords) + return -EINVAL; /* ran out of words[] before bytes */ + if (*end) + *end++ = '\0'; /* terminate the word */ + words[nwords++] = buf; + buf = end; + } if (verbose) { int i; -- cgit v1.2.3-59-g8ed1b