[PATCH v4 26/58] perf mem-phys-addr: Port mem-phys-addr to use python module

[Ian Rogers <irogers@google.com>]

Give an example of using the perf python session API to load a
perf.data file and perform the behavior of
tools/perf/scripts/python/mem-phys-addr.py.

Assisted-by: Gemini:gemini-3.1-pro-preview
Signed-off-by: Ian Rogers <irogers@google.com>
---
v2: Added command line '-i' option and cleaned up pylint issues.
---
 tools/perf/python/mem-phys-addr.py | 117 +++++++++++++++++++++++++++++
 1 file changed, 117 insertions(+)
 create mode 100755 tools/perf/python/mem-phys-addr.py

diff --git a/tools/perf/python/mem-phys-addr.py b/tools/perf/python/mem-phys-addr.py
new file mode 100755
index 000000000000..ba874d7a2011
--- /dev/null
+++ b/tools/perf/python/mem-phys-addr.py
@@ -0,0 +1,117 @@
+#!/usr/bin/env python3
+# SPDX-License-Identifier: GPL-2.0
+"""mem-phys-addr.py: Resolve physical address samples"""
+import argparse
+import bisect
+import collections
+from dataclasses import dataclass
+import re
+from typing import (Dict, Optional)
+
+import perf
+
+@dataclass(frozen=True)
+class IomemEntry:
+    """Read from a line in /proc/iomem"""
+    begin: int
+    end: int
+    indent: int
+    label: str
+
+# Physical memory layout from /proc/iomem. Key is the indent and then
+# a list of ranges.
+iomem: Dict[int, list[IomemEntry]] = collections.defaultdict(list)
+# Child nodes from the iomem parent.
+children: Dict[IomemEntry, set[IomemEntry]] = collections.defaultdict(set)
+# Maximum indent seen before an entry in the iomem file.
+max_indent: int = 0
+# Count for each range of memory.
+load_mem_type_cnt: Dict[IomemEntry, int] = collections.Counter()
+# Perf event name set from the first sample in the data.
+event_name: Optional[str] = None
+
+def parse_iomem(iomem_path: str):
+    """Populate iomem from iomem file"""
+    global max_indent
+    with open(iomem_path, 'r', encoding='ascii') as f:
+        for line in f:
+            indent = 0
+            while line[indent] == ' ':
+                indent += 1
+            max_indent = max(max_indent, indent)
+            m = re.split('-|:', line, maxsplit=2)
+            begin = int(m[0], 16)
+            end = int(m[1], 16)
+            label = m[2].strip()
+            entry = IomemEntry(begin, end, indent, label)
+            # Before adding entry, search for a parent node using its begin.
+            if indent > 0:
+                parent = find_memory_type(begin)
+                assert parent, f"Given indent expected a parent for {label}"
+                children[parent].add(entry)
+            iomem[indent].append(entry)
+
+def find_memory_type(phys_addr) -> Optional[IomemEntry]:
+    """Search iomem for the range containing phys_addr with the maximum indent"""
+    for i in range(max_indent, -1, -1):
+        if i not in iomem:
+            continue
+        position = bisect.bisect_right(iomem[i], phys_addr,
+                                       key=lambda entry: entry.begin)
+        if position is None:
+            continue
+        iomem_entry = iomem[i][position-1]
+        if  iomem_entry.begin <= phys_addr <= iomem_entry.end:
+            return iomem_entry
+    print(f"Didn't find {phys_addr}")
+    return None
+
+def print_memory_type():
+    """Print the resolved memory types and their counts."""
+    print(f"Event: {event_name}")
+    print(f"{'Memory type':<40}  {'count':>10}  {'percentage':>10}")
+    print(f"{'-' * 40:<40}  {'-' * 10:>10}  {'-' * 10:>10}")
+    total = sum(load_mem_type_cnt.values())
+    # Add count from children into the parent.
+    for i in range(max_indent, -1, -1):
+        if i not in iomem:
+            continue
+        for entry in iomem[i]:
+            for child in children[entry]:
+                if load_mem_type_cnt[child] > 0:
+                    load_mem_type_cnt[entry] += load_mem_type_cnt[child]
+
+    def print_entries(entries):
+        """Print counts from parents down to their children"""
+        for entry in sorted(entries,
+                            key = lambda entry: load_mem_type_cnt[entry],
+                            reverse = True):
+            count = load_mem_type_cnt[entry]
+            if count > 0:
+                mem_type = ' ' * entry.indent + f"{entry.begin:x}-{entry.end:x} : {entry.label}"
+                percent = 100 * count / total
+                print(f"{mem_type:<40}  {count:>10}  {percent:>10.1f}")
+                print_entries(children[entry])
+
+    print_entries(iomem[0])
+
+if __name__ == "__main__":
+    ap = argparse.ArgumentParser(description="Resolve physical address samples")
+    ap.add_argument("-i", "--input", default="perf.data", help="Input file name")
+    ap.add_argument("--iomem", default="/proc/iomem", help="Path to iomem file")
+    args = ap.parse_args()
+
+    def process_event(sample):
+        """Process a single sample event."""
+        phys_addr  = sample.sample_phys_addr
+        entry = find_memory_type(phys_addr)
+        if entry:
+            load_mem_type_cnt[entry] += 1
+
+            global event_name
+            if event_name is None:
+                event_name  = str(sample.evsel)
+
+    parse_iomem(args.iomem)
+    perf.session(perf.data(args.input), sample=process_event).process_events()
+    print_memory_type()
-- 
2.54.0.rc2.533.g4f5dca5207-goog