The data_head of a perf event data buffer grows indefinitely. Users are expected to compute data_head % data_size to find the location inside the perf event data buffer. The aux_head of a perf event aux buffer wraps around and always stays within the perf event aux buffer. Well, at least that's the behaviour for BTS and PT - where BTS uses the data buffer and PT the aux buffer. GDB does not read beyond data_head or aux_head. This is OK for BTS but wrong for PT. It causes only a portion of the trace to be considered by GDB. In the extreme case, the buffer may appear (almost) empty. Thanks to Tim Wiederhake <tim.wiederhake@intel.com> for reporting the anomaly. Change it to read the entire aux buffer for PT. The buffer is initially zero so any extra zeroes we read before aux_head wraps around the first time will be ignored when searching for the first PSB packet in order to synchronize onto the trace stream. gdb/ * nat/linux-btrace.c (perf_event_read): Allow data_head < size. * nat/linux-btrace.c (perf_event_read_all): Do not adjust size. Change-Id: If4f8049a2080a5f16f336309450b32a3eb1e3ec9 |
||
---|---|---|
.. | ||
aarch64-linux-hw-point.c | ||
aarch64-linux-hw-point.h | ||
aarch64-linux.c | ||
aarch64-linux.h | ||
amd64-linux-siginfo.c | ||
amd64-linux-siginfo.h | ||
gdb_ptrace.h | ||
gdb_thread_db.h | ||
glibc_thread_db.h | ||
linux-btrace.c | ||
linux-btrace.h | ||
linux-namespaces.c | ||
linux-namespaces.h | ||
linux-nat.h | ||
linux-osdata.c | ||
linux-osdata.h | ||
linux-personality.c | ||
linux-personality.h | ||
linux-procfs.c | ||
linux-procfs.h | ||
linux-ptrace.c | ||
linux-ptrace.h | ||
linux-waitpid.c | ||
linux-waitpid.h | ||
mips-linux-watch.c | ||
mips-linux-watch.h | ||
ppc-linux.c | ||
ppc-linux.h | ||
x86-cpuid.h | ||
x86-dregs.c | ||
x86-dregs.h | ||
x86-gcc-cpuid.h | ||
x86-linux-dregs.c | ||
x86-linux-dregs.h | ||
x86-linux.c | ||
x86-linux.h |