From 6ae2a0765ab764da11cc305058ee5333810228f4 Mon Sep 17 00:00:00 2001 From: Steven Rostedt Date: Mon, 13 Oct 2008 10:22:06 -0400 Subject: ring-buffer: fix free page The pages of a buffer was originally pointing to the page struct, it now points to the page address. The freeing of the page still uses the page frame free "__free_page" instead of the correct free_page to the address. Signed-off-by: Steven Rostedt Signed-off-by: Ingo Molnar --- kernel/trace/ring_buffer.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'kernel/trace/ring_buffer.c') diff --git a/kernel/trace/ring_buffer.c b/kernel/trace/ring_buffer.c index 94af1fe56bb4..091aeefe321e 100644 --- a/kernel/trace/ring_buffer.c +++ b/kernel/trace/ring_buffer.c @@ -130,7 +130,7 @@ struct buffer_page { static inline void free_buffer_page(struct buffer_page *bpage) { if (bpage->page) - __free_page(bpage->page); + free_page((unsigned long)bpage->page); kfree(bpage); } -- cgit v1.2.3 From e2862c9470beb842d3f1c1965b03a2112114c160 Mon Sep 17 00:00:00 2001 From: Stephen Rothwell Date: Mon, 27 Oct 2008 17:43:28 +1100 Subject: trace: fix printk warning for u64 A powerpc ppc64_defconfig build produces these warnings: kernel/trace/ring_buffer.c: In function 'rb_add_time_stamp': kernel/trace/ring_buffer.c:969: warning: format '%llu' expects type 'long long unsigned int', but argument 2 has type 'u64' kernel/trace/ring_buffer.c:969: warning: format '%llu' expects type 'long long unsigned int', but argument 3 has type 'u64' kernel/trace/ring_buffer.c:969: warning: format '%llu' expects type 'long long unsigned int', but argument 4 has type 'u64' Just cast the u64s to unsigned long long like we do everywhere else. Signed-off-by: Stephen Rothwell Acked-by: Steven Rostedt Signed-off-by: Ingo Molnar --- kernel/trace/ring_buffer.c | 4 +++- 1 file changed, 3 insertions(+), 1 deletion(-) (limited to 'kernel/trace/ring_buffer.c') diff --git a/kernel/trace/ring_buffer.c b/kernel/trace/ring_buffer.c index 091aeefe321e..cedf4e268285 100644 --- a/kernel/trace/ring_buffer.c +++ b/kernel/trace/ring_buffer.c @@ -966,7 +966,9 @@ rb_add_time_stamp(struct ring_buffer_per_cpu *cpu_buffer, if (unlikely(*delta > (1ULL << 59) && !once++)) { printk(KERN_WARNING "Delta way too big! %llu" " ts=%llu write stamp = %llu\n", - *delta, *ts, cpu_buffer->write_stamp); + (unsigned long long)*delta, + (unsigned long long)*ts, + (unsigned long long)cpu_buffer->write_stamp); WARN_ON(1); } -- cgit v1.2.3 From 818e3dd30a4ff34fff6d90e87ae59c73f6a53691 Mon Sep 17 00:00:00 2001 From: Steven Rostedt Date: Fri, 31 Oct 2008 09:58:35 -0400 Subject: tracing, ring-buffer: add paranoid checks for loops While writing a new tracer, I had a bug where I caused the ring-buffer to recurse in a bad way. The bug was with the tracer I was writing and not the ring-buffer itself. But it took a long time to find the problem. This patch adds paranoid checks into the ring-buffer infrastructure that will catch bugs of this nature. Note: I put the bug back in the tracer and this patch showed the error nicely and prevented the lockup. Signed-off-by: Steven Rostedt Signed-off-by: Ingo Molnar --- kernel/trace/ring_buffer.c | 56 ++++++++++++++++++++++++++++++++++++++++++++++ 1 file changed, 56 insertions(+) (limited to 'kernel/trace/ring_buffer.c') diff --git a/kernel/trace/ring_buffer.c b/kernel/trace/ring_buffer.c index cedf4e268285..3f3380638646 100644 --- a/kernel/trace/ring_buffer.c +++ b/kernel/trace/ring_buffer.c @@ -1022,8 +1022,23 @@ rb_reserve_next_event(struct ring_buffer_per_cpu *cpu_buffer, struct ring_buffer_event *event; u64 ts, delta; int commit = 0; + int nr_loops = 0; again: + /* + * We allow for interrupts to reenter here and do a trace. + * If one does, it will cause this original code to loop + * back here. Even with heavy interrupts happening, this + * should only happen a few times in a row. If this happens + * 1000 times in a row, there must be either an interrupt + * storm or we have something buggy. + * Bail! + */ + if (unlikely(++nr_loops > 1000)) { + RB_WARN_ON(cpu_buffer, 1); + return NULL; + } + ts = ring_buffer_time_stamp(cpu_buffer->cpu); /* @@ -1532,10 +1547,23 @@ rb_get_reader_page(struct ring_buffer_per_cpu *cpu_buffer) { struct buffer_page *reader = NULL; unsigned long flags; + int nr_loops = 0; spin_lock_irqsave(&cpu_buffer->lock, flags); again: + /* + * This should normally only loop twice. But because the + * start of the reader inserts an empty page, it causes + * a case where we will loop three times. There should be no + * reason to loop four times (that I know of). + */ + if (unlikely(++nr_loops > 3)) { + RB_WARN_ON(cpu_buffer, 1); + reader = NULL; + goto out; + } + reader = cpu_buffer->reader_page; /* If there's more to read, return this page */ @@ -1665,6 +1693,7 @@ ring_buffer_peek(struct ring_buffer *buffer, int cpu, u64 *ts) struct ring_buffer_per_cpu *cpu_buffer; struct ring_buffer_event *event; struct buffer_page *reader; + int nr_loops = 0; if (!cpu_isset(cpu, buffer->cpumask)) return NULL; @@ -1672,6 +1701,19 @@ ring_buffer_peek(struct ring_buffer *buffer, int cpu, u64 *ts) cpu_buffer = buffer->buffers[cpu]; again: + /* + * We repeat when a timestamp is encountered. It is possible + * to get multiple timestamps from an interrupt entering just + * as one timestamp is about to be written. The max times + * that this can happen is the number of nested interrupts we + * can have. Nesting 10 deep of interrupts is clearly + * an anomaly. + */ + if (unlikely(++nr_loops > 10)) { + RB_WARN_ON(cpu_buffer, 1); + return NULL; + } + reader = rb_get_reader_page(cpu_buffer); if (!reader) return NULL; @@ -1722,6 +1764,7 @@ ring_buffer_iter_peek(struct ring_buffer_iter *iter, u64 *ts) struct ring_buffer *buffer; struct ring_buffer_per_cpu *cpu_buffer; struct ring_buffer_event *event; + int nr_loops = 0; if (ring_buffer_iter_empty(iter)) return NULL; @@ -1730,6 +1773,19 @@ ring_buffer_iter_peek(struct ring_buffer_iter *iter, u64 *ts) buffer = cpu_buffer->buffer; again: + /* + * We repeat when a timestamp is encountered. It is possible + * to get multiple timestamps from an interrupt entering just + * as one timestamp is about to be written. The max times + * that this can happen is the number of nested interrupts we + * can have. Nesting 10 deep of interrupts is clearly + * an anomaly. + */ + if (unlikely(++nr_loops > 10)) { + RB_WARN_ON(cpu_buffer, 1); + return NULL; + } + if (rb_per_cpu_empty(cpu_buffer)) return NULL; -- cgit v1.2.3 From 4143c5cb36331155a1823af8b3a8c761a59fed71 Mon Sep 17 00:00:00 2001 From: Steven Rostedt Date: Mon, 10 Nov 2008 21:46:01 -0500 Subject: ring-buffer: prevent infinite looping on time stamping Impact: removal of unnecessary looping The lockless part of the ring buffer allows for reentry into the code from interrupts. A timestamp is taken, a test is preformed and if it detects that an interrupt occurred that did tracing, it tries again. The problem arises if the timestamp code itself causes a trace. The detection will detect this and loop again. The difference between this and an interrupt doing tracing, is that this will fail every time, and cause an infinite loop. Currently, we test if the loop happens 1000 times, and if so, it will produce a warning and disable the ring buffer. The problem with this approach is that it makes it difficult to perform some types of tracing (tracing the timestamp code itself). Each trace entry has a delta timestamp from the previous entry. If a trace entry is reserved but and interrupt occurs and traces before the previous entry is commited, the delta timestamp for that entry will be zero. This actually makes sense in terms of tracing, because the interrupt entry happened before the preempted entry was commited, so one may consider the two happening at the same time. The order is still preserved in the buffer. With this idea, instead of trying to get a new timestamp if an interrupt made it in between the timestamp and the test, the entry could simply make the delta zero and continue. This will prevent interrupts or tracers in the timer code from causing the above loop. Signed-off-by: Steven Rostedt --- kernel/trace/ring_buffer.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'kernel/trace/ring_buffer.c') diff --git a/kernel/trace/ring_buffer.c b/kernel/trace/ring_buffer.c index 3f3380638646..2f76193c3489 100644 --- a/kernel/trace/ring_buffer.c +++ b/kernel/trace/ring_buffer.c @@ -1060,7 +1060,7 @@ rb_reserve_next_event(struct ring_buffer_per_cpu *cpu_buffer, /* Did the write stamp get updated already? */ if (unlikely(ts < cpu_buffer->write_stamp)) - goto again; + delta = 0; if (test_time_stamp(delta)) { -- cgit v1.2.3