From 4ea9448a9c045dda5c554b026e07080df4480f10 Mon Sep 17 00:00:00 2001 From: Derrick Stolee Date: Mon, 31 Aug 2026 17:25:38 +0000 Subject: [PATCH] trace2: tolerate failed timestamp formatting Some users reported issues of repeated messages: fatal: recursion detected in die handler This wasn't happening every time, but we eventually captured a GIT_TRACE2_PERF log file with this issue and revealed an interesting internal detail, failing with this message: unable to format message: %4d-%02d-%02dT%02d:%02d:%02d.%06ldZ This specific format string tracks to tr2_tbuf_utc_datetime_extended() in trace2/tr2_tbuf.c. This logic began as tr2_tbuf_utc_time() in ee4512ed481 (trace2: create new combined trace facility, 2019-02-22) but was later split in bad229aef23 (trace2: clarify UTC datetime formatting, 2019-04-15). This use of xsnprintf() is writing a very specific datetime format into a 32-character buffer. The format requires that the input data will not overflow the format digits or the buffer will not hold the result. Since we are using xsnprintf() here, those failures turn into die() events. This method and its siblings, tr2_tbuf_local_time() and tr2_tbuf_utc_datetime(), are used in the tracing library. The extended form is used only for the 'event' format, which these users were using via a config setting for use in client-side telemetry. The non-extended form is used to help generate the 'SID' that defines the process in the traces. Not only are these inappropriate times for a failure, but the extended method is called specifially during the 'atexit' event, which was triggering this problem in a loop as the 'atexit' event would be retriggered by the die(). Based on other symptoms impacting users on the version reporting these failures, it is most likely that this is actually a failure to allocate memory, which is a specific symptom in Git for Windows. That fork uses a different library for its implementation of vsprintf() which allocates an array when seven or more positional arguments exist in the formatting string, such as this one. Ultimately, the trace2 machinery is so low-level that it should not rely on any helper functions that perform error handling with die(), as that can trigger issues that would then be traced, causing this kind of recursive loop. These changes help remove any use of die() within this file: 1. Both 'tv' and 'tm' structs are initialized with zero values, allowing an erroring gettimeofday() or gmtime_r() method to leave them zero-valued. A zero-valued date is better than a die() here. 2. Replace the use of xsnprintf() with snprintf() to avoid the possibility of calling die() here. Instead, check the response to see if there was a failure. On failure, put a blank value into the buffer instead of possibly allowing a value that would not format correctly for a trace2 consumer. This value should be seen as obviously wrong and therefore signals a problem. As the core issue in this code seems to require a system method returning an error, no test accompanies this change. This change removes all uses of xsnprintf() from the trace2/ directory. There are two uses of xstrdup() that could be considered for removal, but they only die() on out-of-memory errors instead of formatting issues. I chose to leave those in place for now. Helped-by: Taylor Blau Signed-off-by: Derrick Stolee Signed-off-by: Junio C Hamano --- banned-die.h | 3 +++ trace2/tr2_tbuf.c | 49 ++++++++++++++++++++++++++++++++--------------- 2 files changed, 37 insertions(+), 15 deletions(-) diff --git a/banned-die.h b/banned-die.h index 1cde4035c1..589e9cc2bd 100644 --- a/banned-die.h +++ b/banned-die.h @@ -11,4 +11,7 @@ #undef die #define die BANNED(die) +#undef xsnprintf +#define xsnprintf(...) BANNED(xsnprintf) + #endif /* BANNED_DIE_H */ diff --git a/trace2/tr2_tbuf.c b/trace2/tr2_tbuf.c index d623e55a81..9b9cdab025 100644 --- a/trace2/tr2_tbuf.c +++ b/trace2/tr2_tbuf.c @@ -5,45 +5,64 @@ void tr2_tbuf_local_time(struct tr2_tbuf *tb) { - struct timeval tv; - struct tm tm; + struct timeval tv = { 0 }; + struct tm tm = { 0 }; time_t secs; + int len; gettimeofday(&tv, NULL); secs = tv.tv_sec; localtime_r(&secs, &tm); - xsnprintf(tb->buf, sizeof(tb->buf), "%02d:%02d:%02d.%06ld", tm.tm_hour, - tm.tm_min, tm.tm_sec, (long)tv.tv_usec); + len = snprintf(tb->buf, sizeof(tb->buf), "%02d:%02d:%02d.%06ld", + tm.tm_hour, tm.tm_min, tm.tm_sec, (long)tv.tv_usec); + + if (len < 0 || (size_t)len >= sizeof(tb->buf)) { + const char *blank = "00:00:00.000000"; + strlcpy(tb->buf, blank, sizeof(tb->buf)); + } } void tr2_tbuf_utc_datetime_extended(struct tr2_tbuf *tb) { - struct timeval tv; - struct tm tm; + struct timeval tv = { 0 }; + struct tm tm = { 0 }; time_t secs; + int len; gettimeofday(&tv, NULL); secs = tv.tv_sec; gmtime_r(&secs, &tm); - xsnprintf(tb->buf, sizeof(tb->buf), - "%4d-%02d-%02dT%02d:%02d:%02d.%06ldZ", tm.tm_year + 1900, - tm.tm_mon + 1, tm.tm_mday, tm.tm_hour, tm.tm_min, tm.tm_sec, - (long)tv.tv_usec); + len = snprintf(tb->buf, sizeof(tb->buf), + "%4d-%02d-%02dT%02d:%02d:%02d.%06ldZ", + tm.tm_year + 1900, tm.tm_mon + 1, tm.tm_mday, + tm.tm_hour, tm.tm_min, tm.tm_sec, (long)tv.tv_usec); + + if (len < 0 || (size_t)len >= sizeof(tb->buf)) { + const char *blank = "1900-00-00T00:00:00.000000Z"; + strlcpy(tb->buf, blank, sizeof(tb->buf)); + } } void tr2_tbuf_utc_datetime(struct tr2_tbuf *tb) { - struct timeval tv; - struct tm tm; + struct timeval tv = { 0 }; + struct tm tm = { 0 }; time_t secs; + int len; gettimeofday(&tv, NULL); secs = tv.tv_sec; gmtime_r(&secs, &tm); - xsnprintf(tb->buf, sizeof(tb->buf), "%4d%02d%02dT%02d%02d%02d.%06ldZ", - tm.tm_year + 1900, tm.tm_mon + 1, tm.tm_mday, tm.tm_hour, - tm.tm_min, tm.tm_sec, (long)tv.tv_usec); + len = snprintf(tb->buf, sizeof(tb->buf), + "%4d%02d%02dT%02d%02d%02d.%06ldZ", + tm.tm_year + 1900, tm.tm_mon + 1, tm.tm_mday, + tm.tm_hour, tm.tm_min, tm.tm_sec, (long)tv.tv_usec); + + if (len < 0 || (size_t)len >= sizeof(tb->buf)) { + const char *blank = "19000000T000000.000000Z"; + strlcpy(tb->buf, blank, sizeof(tb->buf)); + } }