perf: Extend branch type classification

branch_entry.type now has ran out of space to accommodate more branch types
classification. This will prevent perf branch stack implementation on arm64
(via BRBE) to capture all available branch types. Extending this bit field
i.e branch_entry.type [4 bits] is not an option as it will break user space
ABI both for little and big endian perf tools.

Extend branch classification with a new field branch_entry.new_type via a
new branch type PERF_BR_EXTEND_ABI in branch_entry.type. Perf tools which
could decode PERF_BR_EXTEND_ABI, will then parse branch_entry.new_type as
well.

branch_entry.new_type is a 4 bit field which can hold upto 16 branch types.
The first three branch types will hold various generic page faults followed
by five architecture specific branch types, which can be overridden by the
platform for specific use cases. These architecture specific branch types
gets overridden on arm64 platform for BRBE implementation.

New generic branch types

 - PERF_BR_NEW_FAULT_ALGN
 - PERF_BR_NEW_FAULT_DATA
 - PERF_BR_NEW_FAULT_INST

New arch specific branch types

 - PERF_BR_NEW_ARCH_1
 - PERF_BR_NEW_ARCH_2
 - PERF_BR_NEW_ARCH_3
 - PERF_BR_NEW_ARCH_4
 - PERF_BR_NEW_ARCH_5

Signed-off-by: Anshuman Khandual <anshuman.khandual@arm.com>
Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org>
Reviewed-by: James Clark <james.clark@arm.com>
Link: https://lkml.kernel.org/r/20220824044822.70230-3-anshuman.khandual@arm.com

diff --git a/include/uapi/linux/perf_event.h b/include/uapi/linux/perf_event.h
index a79cc0eb4de71082aebe2ab1abde2ee7bcd3313d..fed60e6b10e52340b26d6045baa81b2b5f3b742a 100644 (file)
--- a/include/uapi/linux/perf_event.h
+++ b/include/uapi/linux/perf_event.h
@@ -255,6 +255,7 @@ enum {
        PERF_BR_IRQ             = 12,   /* irq */
        PERF_BR_SERROR          = 13,   /* system error */
        PERF_BR_NO_TX           = 14,   /* not in transaction */
+       PERF_BR_EXTEND_ABI      = 15,   /* extend ABI */
        PERF_BR_MAX,
 };
 
@@ -269,6 +270,18 @@ enum {
        PERF_BR_SPEC_MAX,
 };
 
+enum {
+       PERF_BR_NEW_FAULT_ALGN          = 0,    /* Alignment fault */
+       PERF_BR_NEW_FAULT_DATA          = 1,    /* Data fault */
+       PERF_BR_NEW_FAULT_INST          = 2,    /* Inst fault */
+       PERF_BR_NEW_ARCH_1              = 3,    /* Architecture specific */
+       PERF_BR_NEW_ARCH_2              = 4,    /* Architecture specific */
+       PERF_BR_NEW_ARCH_3              = 5,    /* Architecture specific */
+       PERF_BR_NEW_ARCH_4              = 6,    /* Architecture specific */
+       PERF_BR_NEW_ARCH_5              = 7,    /* Architecture specific */
+       PERF_BR_NEW_MAX,
+};
+
 #define PERF_SAMPLE_BRANCH_PLM_ALL \
        (PERF_SAMPLE_BRANCH_USER|\
         PERF_SAMPLE_BRANCH_KERNEL|\
@@ -1388,7 +1401,8 @@ struct perf_branch_entry {
                cycles:16,  /* cycle count to last branch */
                type:4,     /* branch type */
                spec:2,     /* branch speculation info */
-               reserved:38;
+               new_type:4, /* additional branch type */
+               reserved:34;
 };
 
 union perf_sample_weight {