From 134e63756d5f3d0f7604dfcca847b09d1b14fd66 Mon Sep 17 00:00:00 2001 From: Johannes Berg Date: Fri, 10 Jul 2009 09:51:34 +0000 Subject: genetlink: make netns aware This makes generic netlink network namespace aware. No generic netlink families except for the controller family are made namespace aware, they need to be checked one by one and then set the family->netnsok member to true. A new function genlmsg_multicast_netns() is introduced to allow sending a multicast message in a given namespace, for example when it applies to an object that lives in that namespace, a new function genlmsg_multicast_allns() to send a message to all network namespaces (for objects that do not have an associated netns). The function genlmsg_multicast() is changed to multicast the message in just init_net, which is currently correct for all generic netlink families since they only work in init_net right now. Some will later want to work in all net namespaces because they do not care about the netns at all -- those will have to be converted to use one of the new functions genlmsg_multicast_allns() or genlmsg_multicast_netns() whenever they are made netns aware in some way. After this patch families can easily decide whether or not they should be available in all net namespaces. Many genl families us it for objects not related to networking and should therefore be available in all namespaces, but that will have to be done on a per family basis. Note that this doesn't touch on the checkpoint/restart problem where network namespaces could be used, genl families and multicast groups are numbered globally and I see no easy way of changing that, especially since it must be possible to multicast to all network namespaces for those families that do not care about netns. Signed-off-by: Johannes Berg Signed-off-by: David S. Miller --- kernel/taskstats.c | 10 +++++----- 1 file changed, 5 insertions(+), 5 deletions(-) (limited to 'kernel') diff --git a/kernel/taskstats.c b/kernel/taskstats.c index 888adbcca30c..ea8384d3caa7 100644 --- a/kernel/taskstats.c +++ b/kernel/taskstats.c @@ -108,7 +108,7 @@ static int prepare_reply(struct genl_info *info, u8 cmd, struct sk_buff **skbp, /* * Send taskstats data in @skb to listener with nl_pid @pid */ -static int send_reply(struct sk_buff *skb, pid_t pid) +static int send_reply(struct sk_buff *skb, struct genl_info *info) { struct genlmsghdr *genlhdr = nlmsg_data(nlmsg_hdr(skb)); void *reply = genlmsg_data(genlhdr); @@ -120,7 +120,7 @@ static int send_reply(struct sk_buff *skb, pid_t pid) return rc; } - return genlmsg_unicast(skb, pid); + return genlmsg_reply(skb, info); } /* @@ -150,7 +150,7 @@ static void send_cpu_listeners(struct sk_buff *skb, if (!skb_next) break; } - rc = genlmsg_unicast(skb_cur, s->pid); + rc = genlmsg_unicast(&init_net, skb_cur, s->pid); if (rc == -ECONNREFUSED) { s->valid = 0; delcount++; @@ -418,7 +418,7 @@ static int cgroupstats_user_cmd(struct sk_buff *skb, struct genl_info *info) goto err; } - rc = send_reply(rep_skb, info->snd_pid); + rc = send_reply(rep_skb, info); err: fput_light(file, fput_needed); @@ -487,7 +487,7 @@ free_return_rc: } else goto err; - return send_reply(rep_skb, info->snd_pid); + return send_reply(rep_skb, info); err: nlmsg_free(rep_skb); return rc; -- cgit v1.2.3 From 5a165657bef7c47e5ff4cd138f7758ef6278e87b Mon Sep 17 00:00:00 2001 From: Neil Horman Date: Thu, 13 Aug 2009 05:20:45 +0000 Subject: net: skb ftracer - Add config option to enable new ftracer (v3) skb allocation / consumption corelator - Add config option This patch adds a Kconfig option to enable the addtition of the skb source tracer. Signed-off-by: Neil Horman Kconfig | 10 ++++++++++ 1 file changed, 10 insertions(+) Signed-off-by: David S. Miller --- kernel/trace/Kconfig | 10 ++++++++++ 1 file changed, 10 insertions(+) (limited to 'kernel') diff --git a/kernel/trace/Kconfig b/kernel/trace/Kconfig index 019f380fd764..f09d7635c0e1 100644 --- a/kernel/trace/Kconfig +++ b/kernel/trace/Kconfig @@ -234,6 +234,16 @@ config BOOT_TRACER You must pass in initcall_debug and ftrace=initcall to the kernel command line to enable this on bootup. +config SKB_SOURCES_TRACER + bool "Trace skb source information" + select GENERIC_TRACER + help + This tracer helps developers/sysadmins correlate skb allocation and + consumption. The idea being that some processes will primarily consume data + that was allocated on certain numa nodes. By being able to visualize which + nodes the data was allocated on, a sysadmin or developer can optimize the + scheduling of those processes to cut back on cross node chatter. + config TRACE_BRANCH_PROFILING bool select GENERIC_TRACER -- cgit v1.2.3 From 9ec04da7489d2c9ae01ea6e9b5fa313ccf3d35fb Mon Sep 17 00:00:00 2001 From: Neil Horman Date: Thu, 13 Aug 2009 05:23:56 +0000 Subject: net: skb ftracer - Add actual ftrace code to kernel (v3) skb allocation / consumption correlator Add ftracer module to kernel to print out a list that correlates a process id, an skb it read, and the numa nodes on wich the process was running when it was read along with the numa node the skbuff was allocated on. Signed-off-by: Neil Horman Makefile | 1 trace.h | 19 ++++++ trace_skb_sources.c | 154 ++++++++++++++++++++++++++++++++++++++++++++++++++++ 3 files changed, 174 insertions(+) Signed-off-by: David S. Miller --- kernel/trace/Makefile | 1 + kernel/trace/trace.h | 19 +++++ kernel/trace/trace_skb_sources.c | 154 +++++++++++++++++++++++++++++++++++++++ 3 files changed, 174 insertions(+) create mode 100644 kernel/trace/trace_skb_sources.c (limited to 'kernel') diff --git a/kernel/trace/Makefile b/kernel/trace/Makefile index 844164dca90a..ee5e5b1b9282 100644 --- a/kernel/trace/Makefile +++ b/kernel/trace/Makefile @@ -49,6 +49,7 @@ obj-$(CONFIG_BLK_DEV_IO_TRACE) += blktrace.o ifeq ($(CONFIG_BLOCK),y) obj-$(CONFIG_EVENT_TRACING) += blktrace.o endif +obj-$(CONFIG_SKB_SOURCES_TRACER) += trace_skb_sources.o obj-$(CONFIG_EVENT_TRACING) += trace_events.o obj-$(CONFIG_EVENT_TRACING) += trace_export.o obj-$(CONFIG_FTRACE_SYSCALLS) += trace_syscalls.o diff --git a/kernel/trace/trace.h b/kernel/trace/trace.h index 8b9f4f6e9559..8a6281b2330b 100644 --- a/kernel/trace/trace.h +++ b/kernel/trace/trace.h @@ -11,6 +11,7 @@ #include #include #include +#include #include #include @@ -40,6 +41,7 @@ enum trace_type { TRACE_KMEM_FREE, TRACE_POWER, TRACE_BLK, + TRACE_SKB_SOURCE, __TRACE_LAST_TYPE, }; @@ -171,6 +173,21 @@ struct trace_power { struct power_trace state_data; }; +struct skb_record { + pid_t pid; /* pid of the copying process */ + int anid; /* node where skb was allocated */ + int cnid; /* node to which skb was copied in userspace */ + char ifname[IFNAMSIZ]; /* Name of the receiving interface */ + int rx_queue; /* The rx queue the skb was received on */ + int ccpu; /* Cpu the application got this frame from */ + int len; /* length of the data copied */ +}; + +struct trace_skb_event { + struct trace_entry ent; + struct skb_record event_data; +}; + enum kmemtrace_type_id { KMEMTRACE_TYPE_KMALLOC = 0, /* kmalloc() or kfree(). */ KMEMTRACE_TYPE_CACHE, /* kmem_cache_*(). */ @@ -323,6 +340,8 @@ extern void __ftrace_bad_type(void); TRACE_SYSCALL_ENTER); \ IF_ASSIGN(var, ent, struct syscall_trace_exit, \ TRACE_SYSCALL_EXIT); \ + IF_ASSIGN(var, ent, struct trace_skb_event, \ + TRACE_SKB_SOURCE); \ __ftrace_bad_type(); \ } while (0) diff --git a/kernel/trace/trace_skb_sources.c b/kernel/trace/trace_skb_sources.c new file mode 100644 index 000000000000..40eb071afdb4 --- /dev/null +++ b/kernel/trace/trace_skb_sources.c @@ -0,0 +1,154 @@ +/* + * ring buffer based tracer for analyzing per-socket skb sources + * + * Neil Horman + * Copyright (C) 2009 + * + * + */ + +#include +#include +#include +#include +#include +#include +#include +#include + +#include "trace.h" +#include "trace_output.h" + +EXPORT_TRACEPOINT_SYMBOL_GPL(skb_copy_datagram_iovec); + +static struct trace_array *skb_trace; +static int __read_mostly trace_skb_source_enabled; + +static void probe_skb_dequeue(const struct sk_buff *skb, int len) +{ + struct ring_buffer_event *event; + struct trace_skb_event *entry; + struct trace_array *tr = skb_trace; + struct net_device *dev; + + if (!trace_skb_source_enabled) + return; + + if (in_interrupt()) + return; + + event = trace_buffer_lock_reserve(tr, TRACE_SKB_SOURCE, + sizeof(*entry), 0, 0); + if (!event) + return; + entry = ring_buffer_event_data(event); + + entry->event_data.pid = current->pid; + entry->event_data.anid = page_to_nid(virt_to_page(skb->data)); + entry->event_data.cnid = cpu_to_node(smp_processor_id()); + entry->event_data.len = len; + entry->event_data.rx_queue = skb->queue_mapping; + entry->event_data.ccpu = smp_processor_id(); + + dev = dev_get_by_index(sock_net(skb->sk), skb->iif); + if (dev) { + memcpy(entry->event_data.ifname, dev->name, IFNAMSIZ); + dev_put(dev); + } else { + strcpy(entry->event_data.ifname, "Unknown"); + } + + trace_buffer_unlock_commit(tr, event, 0, 0); +} + +static int tracing_skb_source_register(void) +{ + int ret; + + ret = register_trace_skb_copy_datagram_iovec(probe_skb_dequeue); + if (ret) + pr_info("skb source trace: Couldn't activate dequeue tracepoint"); + + return ret; +} + +static void start_skb_source_trace(struct trace_array *tr) +{ + trace_skb_source_enabled = 1; +} + +static void stop_skb_source_trace(struct trace_array *tr) +{ + trace_skb_source_enabled = 0; +} + +static void skb_source_trace_reset(struct trace_array *tr) +{ + trace_skb_source_enabled = 0; + unregister_trace_skb_copy_datagram_iovec(probe_skb_dequeue); +} + + +static int skb_source_trace_init(struct trace_array *tr) +{ + int cpu; + skb_trace = tr; + + trace_skb_source_enabled = 1; + tracing_skb_source_register(); + + for_each_cpu(cpu, cpu_possible_mask) + tracing_reset(tr, cpu); + return 0; +} + +static enum print_line_t skb_source_print_line(struct trace_iterator *iter) +{ + int ret = 0; + struct trace_entry *entry = iter->ent; + struct trace_skb_event *event; + struct skb_record *record; + struct trace_seq *s = &iter->seq; + + trace_assign_type(event, entry); + record = &event->event_data; + if (entry->type != TRACE_SKB_SOURCE) + return TRACE_TYPE_UNHANDLED; + + ret = trace_seq_printf(s, " %d %d %d %s %d %d %d\n", + record->pid, + record->anid, + record->cnid, + record->ifname, + record->rx_queue, + record->ccpu, + record->len); + + if (!ret) + return TRACE_TYPE_PARTIAL_LINE; + + return TRACE_TYPE_HANDLED; +} + +static void skb_source_print_header(struct seq_file *s) +{ + seq_puts(s, "# PID ANID CNID IFC RXQ CCPU LEN\n"); + seq_puts(s, "# | | | | | | |\n"); +} + +static struct tracer skb_source_tracer __read_mostly = +{ + .name = "skb_sources", + .init = skb_source_trace_init, + .start = start_skb_source_trace, + .stop = stop_skb_source_trace, + .reset = skb_source_trace_reset, + .print_line = skb_source_print_line, + .print_header = skb_source_print_header, +}; + +static int init_skb_source_trace(void) +{ + return register_tracer(&skb_source_tracer); +} +device_initcall(init_skb_source_trace); -- cgit v1.2.3 From 3a5209e3b26386fd174820ee6e8e27479b24869a Mon Sep 17 00:00:00 2001 From: Randy Dunlap Date: Mon, 17 Aug 2009 16:00:30 -0700 Subject: trace_skb: fix build when CONFIG_NET is not enabled Fix trace_skb_sources build when CONFIG_NET is not enabled: kernel/built-in.o: In function `probe_skb_dequeue': trace_skb_sources.c:(.text+0xd9152): undefined reference to `init_net' trace_skb_sources.c:(.text+0xd9188): undefined reference to `dev_get_by_index' Signed-off-by: Randy Dunlap Signed-off-by: David S. Miller --- kernel/trace/Kconfig | 1 + 1 file changed, 1 insertion(+) (limited to 'kernel') diff --git a/kernel/trace/Kconfig b/kernel/trace/Kconfig index f09d7635c0e1..9a2f19bf0512 100644 --- a/kernel/trace/Kconfig +++ b/kernel/trace/Kconfig @@ -236,6 +236,7 @@ config BOOT_TRACER config SKB_SOURCES_TRACER bool "Trace skb source information" + depends on NET select GENERIC_TRACER help This tracer helps developers/sysadmins correlate skb allocation and -- cgit v1.2.3 From 31ffe249e5426d2648d68568fa00a7b66666a5db Mon Sep 17 00:00:00 2001 From: "David S. Miller" Date: Wed, 26 Aug 2009 16:32:37 -0700 Subject: net: Temporarily backout SKB sources tracer. Steven Rostedt has suggested that Neil work with the tracing folks, trying to use TRACE_EVENT as the mechanism for implementation. And if that doesn't workout we can investigate other solutions such as that one which was tried here. This reverts the following 2 commits: 5a165657bef7c47e5ff4cd138f7758ef6278e87b ("net: skb ftracer - Add config option to enable new ftracer (v3)") 9ec04da7489d2c9ae01ea6e9b5fa313ccf3d35fb ("net: skb ftracer - Add actual ftrace code to kernel (v3)") Signed-off-by: David S. Miller --- kernel/trace/Kconfig | 11 --- kernel/trace/Makefile | 1 - kernel/trace/trace.h | 19 ----- kernel/trace/trace_skb_sources.c | 154 --------------------------------------- 4 files changed, 185 deletions(-) delete mode 100644 kernel/trace/trace_skb_sources.c (limited to 'kernel') diff --git a/kernel/trace/Kconfig b/kernel/trace/Kconfig index 9a2f19bf0512..019f380fd764 100644 --- a/kernel/trace/Kconfig +++ b/kernel/trace/Kconfig @@ -234,17 +234,6 @@ config BOOT_TRACER You must pass in initcall_debug and ftrace=initcall to the kernel command line to enable this on bootup. -config SKB_SOURCES_TRACER - bool "Trace skb source information" - depends on NET - select GENERIC_TRACER - help - This tracer helps developers/sysadmins correlate skb allocation and - consumption. The idea being that some processes will primarily consume data - that was allocated on certain numa nodes. By being able to visualize which - nodes the data was allocated on, a sysadmin or developer can optimize the - scheduling of those processes to cut back on cross node chatter. - config TRACE_BRANCH_PROFILING bool select GENERIC_TRACER diff --git a/kernel/trace/Makefile b/kernel/trace/Makefile index ee5e5b1b9282..844164dca90a 100644 --- a/kernel/trace/Makefile +++ b/kernel/trace/Makefile @@ -49,7 +49,6 @@ obj-$(CONFIG_BLK_DEV_IO_TRACE) += blktrace.o ifeq ($(CONFIG_BLOCK),y) obj-$(CONFIG_EVENT_TRACING) += blktrace.o endif -obj-$(CONFIG_SKB_SOURCES_TRACER) += trace_skb_sources.o obj-$(CONFIG_EVENT_TRACING) += trace_events.o obj-$(CONFIG_EVENT_TRACING) += trace_export.o obj-$(CONFIG_FTRACE_SYSCALLS) += trace_syscalls.o diff --git a/kernel/trace/trace.h b/kernel/trace/trace.h index 8a6281b2330b..8b9f4f6e9559 100644 --- a/kernel/trace/trace.h +++ b/kernel/trace/trace.h @@ -11,7 +11,6 @@ #include #include #include -#include #include #include @@ -41,7 +40,6 @@ enum trace_type { TRACE_KMEM_FREE, TRACE_POWER, TRACE_BLK, - TRACE_SKB_SOURCE, __TRACE_LAST_TYPE, }; @@ -173,21 +171,6 @@ struct trace_power { struct power_trace state_data; }; -struct skb_record { - pid_t pid; /* pid of the copying process */ - int anid; /* node where skb was allocated */ - int cnid; /* node to which skb was copied in userspace */ - char ifname[IFNAMSIZ]; /* Name of the receiving interface */ - int rx_queue; /* The rx queue the skb was received on */ - int ccpu; /* Cpu the application got this frame from */ - int len; /* length of the data copied */ -}; - -struct trace_skb_event { - struct trace_entry ent; - struct skb_record event_data; -}; - enum kmemtrace_type_id { KMEMTRACE_TYPE_KMALLOC = 0, /* kmalloc() or kfree(). */ KMEMTRACE_TYPE_CACHE, /* kmem_cache_*(). */ @@ -340,8 +323,6 @@ extern void __ftrace_bad_type(void); TRACE_SYSCALL_ENTER); \ IF_ASSIGN(var, ent, struct syscall_trace_exit, \ TRACE_SYSCALL_EXIT); \ - IF_ASSIGN(var, ent, struct trace_skb_event, \ - TRACE_SKB_SOURCE); \ __ftrace_bad_type(); \ } while (0) diff --git a/kernel/trace/trace_skb_sources.c b/kernel/trace/trace_skb_sources.c deleted file mode 100644 index 40eb071afdb4..000000000000 --- a/kernel/trace/trace_skb_sources.c +++ /dev/null @@ -1,154 +0,0 @@ -/* - * ring buffer based tracer for analyzing per-socket skb sources - * - * Neil Horman - * Copyright (C) 2009 - * - * - */ - -#include -#include -#include -#include -#include -#include -#include -#include - -#include "trace.h" -#include "trace_output.h" - -EXPORT_TRACEPOINT_SYMBOL_GPL(skb_copy_datagram_iovec); - -static struct trace_array *skb_trace; -static int __read_mostly trace_skb_source_enabled; - -static void probe_skb_dequeue(const struct sk_buff *skb, int len) -{ - struct ring_buffer_event *event; - struct trace_skb_event *entry; - struct trace_array *tr = skb_trace; - struct net_device *dev; - - if (!trace_skb_source_enabled) - return; - - if (in_interrupt()) - return; - - event = trace_buffer_lock_reserve(tr, TRACE_SKB_SOURCE, - sizeof(*entry), 0, 0); - if (!event) - return; - entry = ring_buffer_event_data(event); - - entry->event_data.pid = current->pid; - entry->event_data.anid = page_to_nid(virt_to_page(skb->data)); - entry->event_data.cnid = cpu_to_node(smp_processor_id()); - entry->event_data.len = len; - entry->event_data.rx_queue = skb->queue_mapping; - entry->event_data.ccpu = smp_processor_id(); - - dev = dev_get_by_index(sock_net(skb->sk), skb->iif); - if (dev) { - memcpy(entry->event_data.ifname, dev->name, IFNAMSIZ); - dev_put(dev); - } else { - strcpy(entry->event_data.ifname, "Unknown"); - } - - trace_buffer_unlock_commit(tr, event, 0, 0); -} - -static int tracing_skb_source_register(void) -{ - int ret; - - ret = register_trace_skb_copy_datagram_iovec(probe_skb_dequeue); - if (ret) - pr_info("skb source trace: Couldn't activate dequeue tracepoint"); - - return ret; -} - -static void start_skb_source_trace(struct trace_array *tr) -{ - trace_skb_source_enabled = 1; -} - -static void stop_skb_source_trace(struct trace_array *tr) -{ - trace_skb_source_enabled = 0; -} - -static void skb_source_trace_reset(struct trace_array *tr) -{ - trace_skb_source_enabled = 0; - unregister_trace_skb_copy_datagram_iovec(probe_skb_dequeue); -} - - -static int skb_source_trace_init(struct trace_array *tr) -{ - int cpu; - skb_trace = tr; - - trace_skb_source_enabled = 1; - tracing_skb_source_register(); - - for_each_cpu(cpu, cpu_possible_mask) - tracing_reset(tr, cpu); - return 0; -} - -static enum print_line_t skb_source_print_line(struct trace_iterator *iter) -{ - int ret = 0; - struct trace_entry *entry = iter->ent; - struct trace_skb_event *event; - struct skb_record *record; - struct trace_seq *s = &iter->seq; - - trace_assign_type(event, entry); - record = &event->event_data; - if (entry->type != TRACE_SKB_SOURCE) - return TRACE_TYPE_UNHANDLED; - - ret = trace_seq_printf(s, " %d %d %d %s %d %d %d\n", - record->pid, - record->anid, - record->cnid, - record->ifname, - record->rx_queue, - record->ccpu, - record->len); - - if (!ret) - return TRACE_TYPE_PARTIAL_LINE; - - return TRACE_TYPE_HANDLED; -} - -static void skb_source_print_header(struct seq_file *s) -{ - seq_puts(s, "# PID ANID CNID IFC RXQ CCPU LEN\n"); - seq_puts(s, "# | | | | | | |\n"); -} - -static struct tracer skb_source_tracer __read_mostly = -{ - .name = "skb_sources", - .init = skb_source_trace_init, - .start = start_skb_source_trace, - .stop = stop_skb_source_trace, - .reset = skb_source_trace_reset, - .print_line = skb_source_print_line, - .print_header = skb_source_print_header, -}; - -static int init_skb_source_trace(void) -{ - return register_tracer(&skb_source_tracer); -} -device_initcall(init_skb_source_trace); -- cgit v1.2.3 From 2bc481cf433879f0e6cdd4d899fc21ee05dcea23 Mon Sep 17 00:00:00 2001 From: Stephen Hemminger Date: Fri, 28 Aug 2009 23:41:29 -0700 Subject: pktgen: spin using hrtimer This changes how the pktgen thread spins/waits between packets if delay is configured. It uses a high res timer to wait for time to arrive. Signed-off-by: Stephen Hemminger Signed-off-by: David S. Miller --- kernel/hrtimer.c | 2 ++ 1 file changed, 2 insertions(+) (limited to 'kernel') diff --git a/kernel/hrtimer.c b/kernel/hrtimer.c index 49da79ab8486..05071bf6a37b 100644 --- a/kernel/hrtimer.c +++ b/kernel/hrtimer.c @@ -485,6 +485,7 @@ void hrtimer_init_on_stack(struct hrtimer *timer, clockid_t clock_id, debug_object_init_on_stack(timer, &hrtimer_debug_descr); __hrtimer_init(timer, clock_id, mode); } +EXPORT_SYMBOL_GPL(hrtimer_init_on_stack); void destroy_hrtimer_on_stack(struct hrtimer *timer) { @@ -1477,6 +1478,7 @@ void hrtimer_init_sleeper(struct hrtimer_sleeper *sl, struct task_struct *task) sl->timer.function = hrtimer_wakeup; sl->task = task; } +EXPORT_SYMBOL_GPL(hrtimer_init_sleeper); static int __sched do_nanosleep(struct hrtimer_sleeper *t, enum hrtimer_mode mode) { -- cgit v1.2.3