This patch seris adds support for sample flags so can facilitate perf to print sample flags for branch instruction.
Patch 0001 is used to save last branch information in packet structure, this includes instruction type, subtype and condition flag to help making decision for which branch instruction it is. It passes related information from decoder layer to cs-etm.c, so we use cs-etm.c as a central place to set sample flags.
Patch 0002 is used to set sample flags for instruction range packet.
Patch 0003 is used to set sample flags for trace discontinuity packet.
Patches 0004/0005/0006 are preparation for exception packet handling: Patch 0004 addes exception number in packet; pacth 0005/0006 is to use traceID/metadata tuple to access metadata pointer based on traceID, this can help decide if the CPU is connected with ETMv3 or ETMv4, ETMv3 and ETMv4 have totally different definition for exception numbers.
Patch 0007 sets sample flags for exception packet; patch 0008 support sample flags for exception return packet.
As Mathieu pointed out, one most difficult thing is to handle nest interrupt and trace discontinuity for exception return packet; if we use one data structure to maintain the interrupt context and also track the nest interrupts, this will be complex. So in patch 0008 we simply to check if there have one SVC instruction prior to the return address, by this way we can simply get rid of the dependency between the exception packet and exception return packet for setting sample flags, thus this can let us to set sample flags for exception return packet only based on the sequential instruction range packet.
This patch series is applied on the acme's perf core branch [1] with the with latest commit ee412f14693a ("tools include uapi: Sync linux/vhost.h with the kernel sources").
After applying this patch series, we can verify sample flags with below command:
# perf script -F,-time,+flags,+ip,+sym,+dso,+addr,+symoff -k vmlinux
Changes from v4: * Fixed typos in comments, and removed redundant info from commit log; * Addressed Mathieu's suggestion to add helper functions for metadata fields (CS_ETM_CPU and CS_ETM_MAGIC) accessing; * Addressed Mathieu's suggestion to include headers with alphabetical order.
Changes from v3: * Fixed typos in commit logs; * Rearranged fields in cs_etm_packet by grouping with same variable types; * Fixed ETMv4 exception number which pointed by Mike; * Fixed ETMv4 SVC / SMC / HVC in the same CALL, by checking svc instruction to distinguish them; * Refine ETMv4 return exception packet handling.
Changes from v2: * Addressed Mathieu's suggestion to split one big patch to 3 small patches for setting sample flags, one is for instruction range packet, one is for discontinuity packet and one is for exception packet. * Added supporting for ETMv3 exception packet. * Followed Mathieu's suggestion to move all sample flags handling from decoder layer to cs-etm.c, thus it has enough info to set flags based on trace context in single place.
Changes from v1: * Moved exception packets handling patches into patch series 'perf cs-etm: Correct packets handling'. * Added sample flags fixing up for TRACE_OFF packet. * Created a new function which is used to maintain flags fixing up.
[1] https://git.kernel.org/pub/scm/linux/kernel/git/acme/linux.git/log/?h=perf/c...
Leo Yan (8): perf cs-etm: Add last instruction information in packet perf cs-etm: Set sample flags for instruction range packet perf cs-etm: Set sample flags for trace discontinuity perf cs-etm: Add exception number in exception packet perf cs-etm: Change tuple from traceID-CPU# to traceID-metadata perf cs-etm: Add traceID in packet perf cs-etm: Set sample flags for exception packet perf cs-etm: Set sample flags for exception return packet
.../perf/util/cs-etm-decoder/cs-etm-decoder.c | 41 +- .../perf/util/cs-etm-decoder/cs-etm-decoder.h | 6 + tools/perf/util/cs-etm.c | 405 +++++++++++++++++- tools/perf/util/cs-etm.h | 45 +- 4 files changed, 479 insertions(+), 18 deletions(-)