From f9ac5a69edee0ee7e06a05727226e3f275306c8d Mon Sep 17 00:00:00 2001 From: Paul Mundt Date: Mon, 28 Sep 2009 16:55:40 +0900 Subject: kmemtrace: Fix up tracer registration Commit ddc1637af217dbd8bc51f30e6d24e84476a869a6 ("kmemtrace: Print binary output only if 'bin' option is set") ended up inverting the error detection logic. register_tracer() returns 0 on success, which this change caused to treat as an error, resulting in: [ 0.132000] Warning: could not register the kmem tracer as well as bailing out of the initcall with an error value. This restores the old logic. Signed-off-by: Paul Mundt Acked-by: Pekka Enberg Acked-by: Frederic Weisbecker Cc: Eduard - Gabriel Munteanu Cc: Steven Rostedt Cc: Li Zefan LKML-Reference: <20090928075540.GD6668@linux-sh.org> Signed-off-by: Ingo Molnar --- kernel/trace/kmemtrace.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'kernel/trace') diff --git a/kernel/trace/kmemtrace.c b/kernel/trace/kmemtrace.c index 81b1645c8549..a91da69f153a 100644 --- a/kernel/trace/kmemtrace.c +++ b/kernel/trace/kmemtrace.c @@ -501,7 +501,7 @@ static int __init init_kmem_tracer(void) return 1; } - if (!register_tracer(&kmem_tracer)) { + if (register_tracer(&kmem_tracer) != 0) { pr_warning("Warning: could not register the kmem tracer\n"); return 1; } -- cgit v1.2.3 From 48c0d4d4c04dd520c55e0fd756fa4e7c83de3d13 Mon Sep 17 00:00:00 2001 From: Zdenek Kabelac Date: Fri, 25 Sep 2009 06:19:26 +0200 Subject: Add missing blk_trace_remove_sysfs to be in pair with blk_trace_init_sysfs Add missing blk_trace_remove_sysfs to be in pair with blk_trace_init_sysfs introduced in commit 1d54ad6da9192fed5dd3b60224d9f2dfea0dcd82. Release kobject also in case the request_fn is NULL. Problem was noticed via kmemleak backtrace when some sysfs entries were note properly destroyed during device removal: unreferenced object 0xffff88001aa76640 (size 80): comm "lvcreate", pid 2120, jiffies 4294885144 hex dump (first 32 bytes): 01 00 00 00 00 00 00 00 f0 65 a7 1a 00 88 ff ff .........e...... 90 66 a7 1a 00 88 ff ff 86 1d 53 81 ff ff ff ff .f........S..... backtrace: [] kmemleak_alloc+0x26/0x60 [] kmem_cache_alloc+0x133/0x1c0 [] sysfs_new_dirent+0x41/0x120 [] sysfs_add_file_mode+0x3c/0xb0 [] internal_create_group+0xc1/0x1a0 [] sysfs_create_group+0x13/0x20 [] blk_trace_init_sysfs+0x14/0x20 [] blk_register_queue+0x3c/0xf0 [] add_disk+0x94/0x160 [] dm_create+0x598/0x6e0 [dm_mod] [] dev_create+0x51/0x350 [dm_mod] [] ctl_ioctl+0x1a3/0x240 [dm_mod] [] dm_compat_ctl_ioctl+0x12/0x20 [dm_mod] [] compat_sys_ioctl+0xcd/0x4f0 [] sysenter_dispatch+0x7/0x2c [] 0xffffffffffffffff Signed-off-by: Zdenek Kabelac Reviewed-by: Li Zefan Signed-off-by: Jens Axboe --- block/blk-sysfs.c | 11 ++++++----- include/linux/blktrace_api.h | 2 ++ kernel/trace/blktrace.c | 5 +++++ 3 files changed, 13 insertions(+), 5 deletions(-) (limited to 'kernel/trace') diff --git a/block/blk-sysfs.c b/block/blk-sysfs.c index b78c9c3e2670..8a6d81afb284 100644 --- a/block/blk-sysfs.c +++ b/block/blk-sysfs.c @@ -452,6 +452,7 @@ int blk_register_queue(struct gendisk *disk) if (ret) { kobject_uevent(&q->kobj, KOBJ_REMOVE); kobject_del(&q->kobj); + blk_trace_remove_sysfs(disk_to_dev(disk)); return ret; } @@ -465,11 +466,11 @@ void blk_unregister_queue(struct gendisk *disk) if (WARN_ON(!q)) return; - if (q->request_fn) { + if (q->request_fn) elv_unregister_queue(q); - kobject_uevent(&q->kobj, KOBJ_REMOVE); - kobject_del(&q->kobj); - kobject_put(&disk_to_dev(disk)->kobj); - } + kobject_uevent(&q->kobj, KOBJ_REMOVE); + kobject_del(&q->kobj); + blk_trace_remove_sysfs(disk_to_dev(disk)); + kobject_put(&disk_to_dev(disk)->kobj); } diff --git a/include/linux/blktrace_api.h b/include/linux/blktrace_api.h index 7e4350ece0f8..622939a23299 100644 --- a/include/linux/blktrace_api.h +++ b/include/linux/blktrace_api.h @@ -198,6 +198,7 @@ extern int blk_trace_setup(struct request_queue *q, char *name, dev_t dev, char __user *arg); extern int blk_trace_startstop(struct request_queue *q, int start); extern int blk_trace_remove(struct request_queue *q); +extern void blk_trace_remove_sysfs(struct device *dev); extern int blk_trace_init_sysfs(struct device *dev); extern struct attribute_group blk_trace_attr_group; @@ -211,6 +212,7 @@ extern struct attribute_group blk_trace_attr_group; # define blk_trace_startstop(q, start) (-ENOTTY) # define blk_trace_remove(q) (-ENOTTY) # define blk_add_trace_msg(q, fmt, ...) do { } while (0) +# define blk_trace_remove_sysfs(struct device *dev) do { } while (0) static inline int blk_trace_init_sysfs(struct device *dev) { return 0; diff --git a/kernel/trace/blktrace.c b/kernel/trace/blktrace.c index 3eb159c277c8..60b5c5a3d4b4 100644 --- a/kernel/trace/blktrace.c +++ b/kernel/trace/blktrace.c @@ -1657,6 +1657,11 @@ int blk_trace_init_sysfs(struct device *dev) return sysfs_create_group(&dev->kobj, &blk_trace_attr_group); } +void blk_trace_remove_sysfs(struct device *dev) +{ + sysfs_remove_group(&dev->kobj, &blk_trace_attr_group); +} + #endif /* CONFIG_BLK_DEV_IO_TRACE */ #ifdef CONFIG_EVENT_TRACING -- cgit v1.2.3 From b0da3f0dada78832c9da03ad2152ae76bd9a2496 Mon Sep 17 00:00:00 2001 From: Jun'ichi Nomura Date: Thu, 1 Oct 2009 21:16:13 +0200 Subject: Add a tracepoint for block request remapping Since 2.6.31 now has request-based device-mapper, it's useful to have a tracepoint for request-remapping as well as bio-remapping. This patch adds a tracepoint for request-remapping, trace_block_rq_remap(). Signed-off-by: Kiyoshi Ueda Signed-off-by: Jun'ichi Nomura Cc: Alasdair G Kergon Cc: Li Zefan Signed-off-by: Jens Axboe --- block/blk-core.c | 1 + include/linux/blktrace_api.h | 2 +- include/trace/events/block.h | 33 +++++++++++++++++++++++++++++++++ kernel/trace/blktrace.c | 34 ++++++++++++++++++++++++++++++++++ 4 files changed, 69 insertions(+), 1 deletion(-) (limited to 'kernel/trace') diff --git a/block/blk-core.c b/block/blk-core.c index 34504f309728..ddaaea4fdffc 100644 --- a/block/blk-core.c +++ b/block/blk-core.c @@ -34,6 +34,7 @@ #include "blk.h" EXPORT_TRACEPOINT_SYMBOL_GPL(block_remap); +EXPORT_TRACEPOINT_SYMBOL_GPL(block_rq_remap); EXPORT_TRACEPOINT_SYMBOL_GPL(block_bio_complete); static int __make_request(struct request_queue *q, struct bio *bio); diff --git a/include/linux/blktrace_api.h b/include/linux/blktrace_api.h index 622939a23299..3b73b9992b26 100644 --- a/include/linux/blktrace_api.h +++ b/include/linux/blktrace_api.h @@ -212,7 +212,7 @@ extern struct attribute_group blk_trace_attr_group; # define blk_trace_startstop(q, start) (-ENOTTY) # define blk_trace_remove(q) (-ENOTTY) # define blk_add_trace_msg(q, fmt, ...) do { } while (0) -# define blk_trace_remove_sysfs(struct device *dev) do { } while (0) +# define blk_trace_remove_sysfs(dev) do { } while (0) static inline int blk_trace_init_sysfs(struct device *dev) { return 0; diff --git a/include/trace/events/block.h b/include/trace/events/block.h index d86af94691c2..00405b5f624a 100644 --- a/include/trace/events/block.h +++ b/include/trace/events/block.h @@ -488,6 +488,39 @@ TRACE_EVENT(block_remap, (unsigned long long)__entry->old_sector) ); +TRACE_EVENT(block_rq_remap, + + TP_PROTO(struct request_queue *q, struct request *rq, dev_t dev, + sector_t from), + + TP_ARGS(q, rq, dev, from), + + TP_STRUCT__entry( + __field( dev_t, dev ) + __field( sector_t, sector ) + __field( unsigned int, nr_sector ) + __field( dev_t, old_dev ) + __field( sector_t, old_sector ) + __array( char, rwbs, 6 ) + ), + + TP_fast_assign( + __entry->dev = disk_devt(rq->rq_disk); + __entry->sector = blk_rq_pos(rq); + __entry->nr_sector = blk_rq_sectors(rq); + __entry->old_dev = dev; + __entry->old_sector = from; + blk_fill_rwbs_rq(__entry->rwbs, rq); + ), + + TP_printk("%d,%d %s %llu + %u <- (%d,%d) %llu", + MAJOR(__entry->dev), MINOR(__entry->dev), __entry->rwbs, + (unsigned long long)__entry->sector, + __entry->nr_sector, + MAJOR(__entry->old_dev), MINOR(__entry->old_dev), + (unsigned long long)__entry->old_sector) +); + #endif /* _TRACE_BLOCK_H */ /* This part must be outside protection */ diff --git a/kernel/trace/blktrace.c b/kernel/trace/blktrace.c index 60b5c5a3d4b4..d9d6206e0b14 100644 --- a/kernel/trace/blktrace.c +++ b/kernel/trace/blktrace.c @@ -855,6 +855,37 @@ static void blk_add_trace_remap(struct request_queue *q, struct bio *bio, sizeof(r), &r); } +/** + * blk_add_trace_rq_remap - Add a trace for a request-remap operation + * @q: queue the io is for + * @rq: the source request + * @dev: target device + * @from: source sector + * + * Description: + * Device mapper remaps request to other devices. + * Add a trace for that action. + * + **/ +static void blk_add_trace_rq_remap(struct request_queue *q, + struct request *rq, dev_t dev, + sector_t from) +{ + struct blk_trace *bt = q->blk_trace; + struct blk_io_trace_remap r; + + if (likely(!bt)) + return; + + r.device_from = cpu_to_be32(dev); + r.device_to = cpu_to_be32(disk_devt(rq->rq_disk)); + r.sector_from = cpu_to_be64(from); + + __blk_add_trace(bt, blk_rq_pos(rq), blk_rq_bytes(rq), + rq_data_dir(rq), BLK_TA_REMAP, !!rq->errors, + sizeof(r), &r); +} + /** * blk_add_driver_data - Add binary message with driver-specific data * @q: queue the io is for @@ -922,10 +953,13 @@ static void blk_register_tracepoints(void) WARN_ON(ret); ret = register_trace_block_remap(blk_add_trace_remap); WARN_ON(ret); + ret = register_trace_block_rq_remap(blk_add_trace_rq_remap); + WARN_ON(ret); } static void blk_unregister_tracepoints(void) { + unregister_trace_block_rq_remap(blk_add_trace_rq_remap); unregister_trace_block_remap(blk_add_trace_remap); unregister_trace_block_split(blk_add_trace_split); unregister_trace_block_unplug_io(blk_add_trace_unplug_io); -- cgit v1.2.3 From ee949a86b3aef15845ea677aa60231008de62672 Mon Sep 17 00:00:00 2001 From: Tom Zanussi Date: Tue, 6 Oct 2009 01:00:49 -0500 Subject: tracing/syscalls: Use long for syscall ret format and field definitions The syscall event definitions use long for the syscall exit ret value, but unsigned long for the same thing in the format and field definitions. Change them all to long. Signed-off-by: Tom Zanussi Acked-by: Frederic Weisbecker Cc: rostedt@goodmis.org Cc: lizf@cn.fujitsu.com Cc: Peter Zijlstra Cc: Mike Galbraith Cc: Paul Mackerras Cc: Arnaldo Carvalho de Melo LKML-Reference: <1254808849-7829-4-git-send-email-tzanussi@gmail.com> Signed-off-by: Ingo Molnar --- kernel/trace/trace_syscalls.c | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) (limited to 'kernel/trace') diff --git a/kernel/trace/trace_syscalls.c b/kernel/trace/trace_syscalls.c index 9fbce6c9d2e1..527e17eae575 100644 --- a/kernel/trace/trace_syscalls.c +++ b/kernel/trace/trace_syscalls.c @@ -166,7 +166,7 @@ int syscall_exit_format(struct ftrace_event_call *call, struct trace_seq *s) "\tfield:%s %s;\toffset:%zu;\tsize:%zu;\n" "\tfield:%s %s;\toffset:%zu;\tsize:%zu;\n", SYSCALL_FIELD(int, nr), - SYSCALL_FIELD(unsigned long, ret)); + SYSCALL_FIELD(long, ret)); if (!ret) return 0; @@ -212,7 +212,7 @@ int syscall_exit_define_fields(struct ftrace_event_call *call) if (ret) return ret; - ret = trace_define_field(call, SYSCALL_FIELD(unsigned long, ret), 0, + ret = trace_define_field(call, SYSCALL_FIELD(long, ret), 0, FILTER_OTHER); return ret; -- cgit v1.2.3 From cf8517cf905b5cd31d5790250b9ac39f7cb8aa53 Mon Sep 17 00:00:00 2001 From: Jiri Olsa Date: Fri, 23 Oct 2009 19:36:16 -0400 Subject: tracing: Update *ppos instead of filp->f_pos Instead of directly updating filp->f_pos we should update the *ppos argument. The filp->f_pos gets updated within the file_pos_write() function called from sys_write(). Signed-off-by: Jiri Olsa Signed-off-by: Steven Rostedt Cc: Frederic Weisbecker LKML-Reference: <20091023233646.399670810@goodmis.org> Signed-off-by: Ingo Molnar --- kernel/trace/ftrace.c | 2 +- kernel/trace/trace.c | 8 ++++---- 2 files changed, 5 insertions(+), 5 deletions(-) (limited to 'kernel/trace') diff --git a/kernel/trace/ftrace.c b/kernel/trace/ftrace.c index 37ba67e33265..9c451a1930b6 100644 --- a/kernel/trace/ftrace.c +++ b/kernel/trace/ftrace.c @@ -740,7 +740,7 @@ ftrace_profile_write(struct file *filp, const char __user *ubuf, out: mutex_unlock(&ftrace_profile_lock); - filp->f_pos += cnt; + *ppos += cnt; return cnt; } diff --git a/kernel/trace/trace.c b/kernel/trace/trace.c index c820b0310a12..b20d3ec75de9 100644 --- a/kernel/trace/trace.c +++ b/kernel/trace/trace.c @@ -2440,7 +2440,7 @@ tracing_trace_options_write(struct file *filp, const char __user *ubuf, return ret; } - filp->f_pos += cnt; + *ppos += cnt; return cnt; } @@ -2582,7 +2582,7 @@ tracing_ctrl_write(struct file *filp, const char __user *ubuf, } mutex_unlock(&trace_types_lock); - filp->f_pos += cnt; + *ppos += cnt; return cnt; } @@ -2764,7 +2764,7 @@ tracing_set_trace_write(struct file *filp, const char __user *ubuf, if (err) return err; - filp->f_pos += ret; + *ppos += ret; return ret; } @@ -3299,7 +3299,7 @@ tracing_entries_write(struct file *filp, const char __user *ubuf, } } - filp->f_pos += cnt; + *ppos += cnt; /* If check pages failed, return ENOMEM */ if (tracing_disabled) -- cgit v1.2.3 From 3e69533b51930a7169235db2caf703884e6e3bbb Mon Sep 17 00:00:00 2001 From: Jiri Olsa Date: Fri, 23 Oct 2009 19:36:17 -0400 Subject: tracing: Fix trace_seq_printf() return value trace_seq_printf() return value is a little ambiguous. It currently returns the length of the space available in the buffer. printf usually returns the amount written. This is not adequate here, because: trace_seq_printf(s, ""); is perfectly legal, and returning 0 would indicate that it failed. We can always see the amount written by looking at the before and after values of s->len. This is not quite the same use as printf. We only care if the string was successfully written to the buffer or not. Make trace_seq_printf() return 0 if the trace oversizes the buffer's free space, 1 otherwise. Signed-off-by: Jiri Olsa Signed-off-by: Steven Rostedt Cc: Frederic Weisbecker LKML-Reference: <20091023233646.631787612@goodmis.org> Signed-off-by: Ingo Molnar --- kernel/trace/trace_output.c | 5 ++++- 1 file changed, 4 insertions(+), 1 deletion(-) (limited to 'kernel/trace') diff --git a/kernel/trace/trace_output.c b/kernel/trace/trace_output.c index ed17565826b0..b6c12c6a1bcd 100644 --- a/kernel/trace/trace_output.c +++ b/kernel/trace/trace_output.c @@ -69,6 +69,9 @@ enum print_line_t trace_print_printk_msg_only(struct trace_iterator *iter) * @s: trace sequence descriptor * @fmt: printf format string * + * It returns 0 if the trace oversizes the buffer's free + * space, 1 otherwise. + * * The tracer may use either sequence operations or its own * copy to user routines. To simplify formating of a trace * trace_seq_printf is used to store strings into a special @@ -95,7 +98,7 @@ trace_seq_printf(struct trace_seq *s, const char *fmt, ...) s->len += ret; - return len; + return 1; } EXPORT_SYMBOL_GPL(trace_seq_printf); -- cgit v1.2.3 From 67b394f7f26d84edb7294cc6528ab7ca6daa2ad1 Mon Sep 17 00:00:00 2001 From: Jiri Olsa Date: Fri, 23 Oct 2009 19:36:18 -0400 Subject: tracing: Fix comment typo and documentation example Trivial patch to fix a documentation example and to fix a comment. Signed-off-by: Jiri Olsa Signed-off-by: Steven Rostedt Cc: Frederic Weisbecker LKML-Reference: <20091023233646.871719877@goodmis.org> Signed-off-by: Ingo Molnar --- Documentation/trace/ftrace.txt | 2 ++ kernel/trace/ring_buffer.c | 2 +- 2 files changed, 3 insertions(+), 1 deletion(-) (limited to 'kernel/trace') diff --git a/Documentation/trace/ftrace.txt b/Documentation/trace/ftrace.txt index 957b22fde2df..8179692fbb90 100644 --- a/Documentation/trace/ftrace.txt +++ b/Documentation/trace/ftrace.txt @@ -1231,6 +1231,7 @@ something like this simple program: #include #include #include +#include #define _STR(x) #x #define STR(x) _STR(x) @@ -1265,6 +1266,7 @@ const char *find_debugfs(void) return NULL; } + strcat(debugfs, "/tracing/"); debugfs_found = 1; return debugfs; diff --git a/kernel/trace/ring_buffer.c b/kernel/trace/ring_buffer.c index d4ff01970547..217f6991184f 100644 --- a/kernel/trace/ring_buffer.c +++ b/kernel/trace/ring_buffer.c @@ -2681,7 +2681,7 @@ unsigned long ring_buffer_entries(struct ring_buffer *buffer) EXPORT_SYMBOL_GPL(ring_buffer_entries); /** - * ring_buffer_overrun_cpu - get the number of overruns in buffer + * ring_buffer_overruns - get the number of overruns in buffer * @buffer: The ring buffer * * Returns the total number of overruns in the ring buffer -- cgit v1.2.3 From 6d3f1e12f46a2f9a1bb7e7aa433df8dd31ce5647 Mon Sep 17 00:00:00 2001 From: Jiri Olsa Date: Fri, 23 Oct 2009 19:36:19 -0400 Subject: tracing: Remove cpu arg from the rb_time_stamp() function The cpu argument is not used inside the rb_time_stamp() function. Plus fix a typo. Signed-off-by: Jiri Olsa Signed-off-by: Steven Rostedt Cc: Frederic Weisbecker LKML-Reference: <20091023233647.118547500@goodmis.org> Signed-off-by: Ingo Molnar --- include/linux/trace_seq.h | 2 +- kernel/trace/ring_buffer.c | 10 +++++----- 2 files changed, 6 insertions(+), 6 deletions(-) (limited to 'kernel/trace') diff --git a/include/linux/trace_seq.h b/include/linux/trace_seq.h index c134dd1fe6b6..09077f6ed128 100644 --- a/include/linux/trace_seq.h +++ b/include/linux/trace_seq.h @@ -7,7 +7,7 @@ /* * Trace sequences are used to allow a function to call several other functions - * to create a string of data to use (up to a max of PAGE_SIZE. + * to create a string of data to use (up to a max of PAGE_SIZE). */ struct trace_seq { diff --git a/kernel/trace/ring_buffer.c b/kernel/trace/ring_buffer.c index 217f6991184f..3ffa502fb243 100644 --- a/kernel/trace/ring_buffer.c +++ b/kernel/trace/ring_buffer.c @@ -483,7 +483,7 @@ struct ring_buffer_iter { /* Up this if you want to test the TIME_EXTENTS and normalization */ #define DEBUG_SHIFT 0 -static inline u64 rb_time_stamp(struct ring_buffer *buffer, int cpu) +static inline u64 rb_time_stamp(struct ring_buffer *buffer) { /* shift to debug/test normalization and TIME_EXTENTS */ return buffer->clock() << DEBUG_SHIFT; @@ -494,7 +494,7 @@ u64 ring_buffer_time_stamp(struct ring_buffer *buffer, int cpu) u64 time; preempt_disable_notrace(); - time = rb_time_stamp(buffer, cpu); + time = rb_time_stamp(buffer); preempt_enable_no_resched_notrace(); return time; @@ -599,7 +599,7 @@ static struct list_head *rb_list_head(struct list_head *list) } /* - * rb_is_head_page - test if the give page is the head page + * rb_is_head_page - test if the given page is the head page * * Because the reader may move the head_page pointer, we can * not trust what the head page is (it may be pointing to @@ -1868,7 +1868,7 @@ rb_move_tail(struct ring_buffer_per_cpu *cpu_buffer, * Nested commits always have zero deltas, so * just reread the time stamp */ - *ts = rb_time_stamp(buffer, cpu_buffer->cpu); + *ts = rb_time_stamp(buffer); next_page->page->time_stamp = *ts; } @@ -2111,7 +2111,7 @@ rb_reserve_next_event(struct ring_buffer *buffer, if (RB_WARN_ON(cpu_buffer, ++nr_loops > 1000)) goto out_fail; - ts = rb_time_stamp(cpu_buffer->buffer, cpu_buffer->cpu); + ts = rb_time_stamp(cpu_buffer->buffer); /* * Only the first commit can update the timestamp. -- cgit v1.2.3