[RFC v5 10/11] tools/damon/record: Support NUMA specific recording

[SeongJae Park <sjpark@amazon.com>]

From: SeongJae Park <sjpark@amazon.de>

This commit updates the DAMON user space tool (damo-record) for NUMA
specific physical memory monitoring.  With this change, users can
monitor accesses to physical memory of specific NUMA node.

Signed-off-by: SeongJae Park <sjpark@amazon.de>
---
 tools/damon/_paddr_layout.py | 158 +++++++++++++++++++++++++++++++++++
 tools/damon/record.py        |  21 ++++-
 2 files changed, 178 insertions(+), 1 deletion(-)
 create mode 100644 tools/damon/_paddr_layout.py

diff --git a/tools/damon/_paddr_layout.py b/tools/damon/_paddr_layout.py
new file mode 100644
index 000000000000..10056172db21
--- /dev/null
+++ b/tools/damon/_paddr_layout.py
@@ -0,0 +1,158 @@
+#!/usr/bin/env python3
+# SPDX-License-Identifier: GPL-2.0
+
+import os
+
+class PaddrRange:
+    start = None
+    end = None
+    nid = None
+    state = None
+    name = None
+
+    def __init__(self, start, end, nid, state, name):
+        self.start = start
+        self.end = end
+        self.nid = nid
+        self.state = state
+        self.name = name
+
+    def interleaved(self, prange):
+        if self.end <= prange.start:
+            return None
+        if prange.end <= self.start:
+            return None
+        return [max(self.start, prange.start), min(self.end, prange.end)]
+
+    def __str__(self):
+        return '%x-%x, nid %s, state %s, name %s' % (self.start, self.end,
+                self.nid, self.state, self.name)
+
+class MemBlock:
+    nid = None
+    index = None
+    state = None
+
+    def __init__(self, nid, index, state):
+        self.nid = nid
+        self.index = index
+        self.state = state
+
+    def __str__(self):
+        return '%d (%s)' % (self.index, self.state)
+
+    def __repr__(self):
+        return self.__str__()
+
+def readfile(file_path):
+    with open(file_path, 'r') as f:
+        return f.read()
+
+def collapse_ranges(ranges):
+    ranges = sorted(ranges, key=lambda x: x.start)
+    merged = []
+    for r in ranges:
+        if not merged:
+            merged.append(r)
+            continue
+        last = merged[-1]
+        if last.end != r.start or last.nid != r.nid or last.state != r.state:
+            merged.append(r)
+        else:
+            last.end = r.end
+    return merged
+
+def memblocks_to_ranges(blocks, block_size):
+    ranges = []
+    for b in blocks:
+        ranges.append(PaddrRange(b.index * block_size,
+            (b.index + 1) * block_size, b.nid, b.state, None))
+
+    return collapse_ranges(ranges)
+
+def memblock_ranges():
+    SYSFS='/sys/devices/system/node'
+    sz_block = int(readfile('/sys/devices/system/memory/block_size_bytes'), 16)
+    sys_nodes = [x for x in os.listdir(SYSFS) if x.startswith('node')]
+
+    blocks = []
+    for sys_node in sys_nodes:
+        nid = int(sys_node[4:])
+
+        sys_node_files = os.listdir(os.path.join(SYSFS, sys_node))
+        for f in sys_node_files:
+            if not f.startswith('memory'):
+                continue
+            index = int(f[6:])
+            sys_state = os.path.join(SYSFS, sys_node, f, 'state')
+            state = readfile(sys_state).strip()
+
+            blocks.append(MemBlock(nid, index, state))
+
+    return memblocks_to_ranges(blocks, sz_block)
+
+def iomem_ranges():
+    ranges = []
+
+    with open('/proc/iomem', 'r') as f:
+        # example of the line: '100000000-42b201fff : System RAM'
+        for line in f:
+            fields = line.split(':')
+            if len(fields) < 2:
+                continue
+            name = ':'.join(fields[1:]).strip()
+            addrs = fields[0].split('-')
+            if len(addrs) != 2:
+                continue
+            start = int(addrs[0], 16)
+            end = int(addrs[1], 16) + 1
+            ranges.append(PaddrRange(start, end, None, None, name))
+
+    return ranges
+
+def paddr_ranges():
+    ranges1 = memblock_ranges()
+    ranges2 = iomem_ranges()
+    merged = []
+
+    for r in ranges1:
+        subsets = []
+        for r2 in ranges2:
+            interleaved = r.interleaved(r2)
+            if interleaved == None:
+                continue
+
+            start, end = interleaved
+            left = None
+            if start > r.start:
+                left = PaddrRange(r.start, start, r.nid, r.state, r.name)
+                subsets.append(left)
+
+            middle = PaddrRange(start, end, r.nid, r.state, r.name)
+            if r2.nid:
+                middle.nid = r2.nid
+            if r2.state:
+                middle.state = r2.state
+            if r2.name:
+                middle.name = r2.name
+            subsets.append(middle)
+            r.start = end
+        if r.start < r.end:
+            subsets = [r]
+
+        merged += subsets
+    return merged
+
+def pr_ranges(ranges):
+    print('#%12s %13s\tnode\tstate\tresource\tsize' % ('start', 'end'))
+    for r in ranges:
+        print('%13d %13d\t%s\t%s\t%s\t%d' % (r.start, r.end, r.nid,
+            r.state, r.name, r.end - r.start))
+
+def main():
+    ranges = paddr_ranges()
+
+    pr_ranges(ranges)
+
+if __name__ == '__main__':
+    main()
diff --git a/tools/damon/record.py b/tools/damon/record.py
index 416dca940c1d..8440a9818810 100644
--- a/tools/damon/record.py
+++ b/tools/damon/record.py
@@ -12,6 +12,7 @@ import subprocess
 import time
 
 import _damon
+import _paddr_layout
 
 def do_record(target, is_target_cmd, init_regions, attrs, old_attrs):
     if os.path.isfile(attrs.rfile_path):
@@ -70,6 +71,8 @@ def set_argparser(parser):
             help='the target command or the pid to record')
     parser.add_argument('-l', '--rbuf', metavar='<len>', type=int,
             default=1024*1024, help='length of record result buffer')
+    parser.add_argument('--numa_node', metavar='<node id>', type=int,
+            help='if target is \'paddr\', limit it to the numa node')
     parser.add_argument('-o', '--out', metavar='<file path>', type=str,
             default='damon.data', help='output file path')
 
@@ -96,6 +99,18 @@ def default_paddr_region():
                 ret = [start, end]
     return ret
 
+def paddr_region_of(numa_node):
+    regions = []
+    default_region = default_paddr_region()
+    paddr_ranges = _paddr_layout.paddr_ranges()
+    for r in paddr_ranges:
+        if r.end <= default_region[0] or default_region[1] <= r.start:
+            continue
+        if r.nid == numa_node and r.name == 'System RAM':
+            regions.append([r.start, r.end])
+
+    return regions
+
 def main(args=None):
     global orig_attrs
     if not args:
@@ -113,12 +128,16 @@ def main(args=None):
     args.schemes = ''
     new_attrs = _damon.cmd_args_to_attrs(args)
     init_regions = _damon.cmd_args_to_init_regions(args)
+    numa_node = args.numa_node
     target = args.target
 
     target_fields = target.split()
     if target == 'paddr':   # physical memory address space
         if not init_regions:
-            init_regions = [default_paddr_region()]
+            if numa_node:
+                init_regions = paddr_region_of(numa_node)
+            else:
+                init_regions = [default_paddr_region()]
         do_record(target, False, init_regions, new_attrs, orig_attrs)
     elif not subprocess.call('which %s > /dev/null' % target_fields[0],
             shell=True, executable='/bin/bash'):
-- 
2.17.1