Update Linux to v5.10.109
Sourced from [1]
[1] https://cdn.kernel.org/pub/linux/kernel/v5.x/linux-5.10.109.tar.xz
Change-Id: I19bca9fc6762d4e63bcf3e4cba88bbe560d9c76c
Signed-off-by: Olivier Deprez <olivier.deprez@arm.com>
diff --git a/tools/cgroup/.gitignore b/tools/cgroup/.gitignore
index 633cd9b..46a8277 100644
--- a/tools/cgroup/.gitignore
+++ b/tools/cgroup/.gitignore
@@ -1 +1,2 @@
+# SPDX-License-Identifier: GPL-2.0-only
cgroup_event_listener
diff --git a/tools/cgroup/iocost_monitor.py b/tools/cgroup/iocost_monitor.py
index b8c082c..c4ff907 100644
--- a/tools/cgroup/iocost_monitor.py
+++ b/tools/cgroup/iocost_monitor.py
@@ -28,7 +28,8 @@
parser.add_argument('--cgroup', action='append', metavar='REGEX',
help='Regex for target cgroups, ')
parser.add_argument('--interval', '-i', metavar='SECONDS', type=float, default=1,
- help='Monitoring interval in seconds')
+ help='Monitoring interval in seconds (0 exits immediately '
+ 'after checking requirements)')
parser.add_argument('--json', action='store_true',
help='Output in json')
args = parser.parse_args()
@@ -44,8 +45,7 @@
err('The kernel does not have iocost enabled')
IOC_RUNNING = prog['IOC_RUNNING'].value_()
-NR_USAGE_SLOTS = prog['NR_USAGE_SLOTS'].value_()
-HWEIGHT_WHOLE = prog['HWEIGHT_WHOLE'].value_()
+WEIGHT_ONE = prog['WEIGHT_ONE'].value_()
VTIME_PER_SEC = prog['VTIME_PER_SEC'].value_()
VTIME_PER_USEC = prog['VTIME_PER_USEC'].value_()
AUTOP_SSD_FAST = prog['AUTOP_SSD_FAST'].value_()
@@ -72,7 +72,7 @@
name = BlkgIterator.blkcg_name(blkcg)
path = parent_path + '/' + name if parent_path else name
blkg = drgn.Object(prog, 'struct blkcg_gq',
- address=radix_tree_lookup(blkcg.blkg_tree, q_id))
+ address=radix_tree_lookup(blkcg.blkg_tree.address_of_(), q_id))
if not blkg.address_:
return
@@ -99,7 +99,7 @@
self.period_ms = ioc.period_us.value_() / 1_000
self.period_at = ioc.period_at.value_() / 1_000_000
self.vperiod_at = ioc.period_at_vtime.value_() / VTIME_PER_SEC
- self.vrate_pct = ioc.vtime_rate.counter.value_() * 100 / VTIME_PER_USEC
+ self.vrate_pct = ioc.vtime_base_rate.value_() * 100 / VTIME_PER_USEC
self.busy_level = ioc.busy_level.value_()
self.autop_idx = ioc.autop_idx.value_()
self.user_cost_model = ioc.user_cost_model.value_()
@@ -135,7 +135,7 @@
def table_header_str(self):
return f'{"":25} active {"weight":>9} {"hweight%":>13} {"inflt%":>6} ' \
- f'{"dbt":>3} {"delay":>6} {"usages%"}'
+ f'{"debt":>7} {"delay":>7} {"usage%"}'
class IocgStat:
def __init__(self, iocg):
@@ -143,11 +143,11 @@
blkg = iocg.pd.blkg
self.is_active = not list_empty(iocg.active_list.address_of_())
- self.weight = iocg.weight.value_()
- self.active = iocg.active.value_()
- self.inuse = iocg.inuse.value_()
- self.hwa_pct = iocg.hweight_active.value_() * 100 / HWEIGHT_WHOLE
- self.hwi_pct = iocg.hweight_inuse.value_() * 100 / HWEIGHT_WHOLE
+ self.weight = iocg.weight.value_() / WEIGHT_ONE
+ self.active = iocg.active.value_() / WEIGHT_ONE
+ self.inuse = iocg.inuse.value_() / WEIGHT_ONE
+ self.hwa_pct = iocg.hweight_active.value_() * 100 / WEIGHT_ONE
+ self.hwi_pct = iocg.hweight_inuse.value_() * 100 / WEIGHT_ONE
self.address = iocg.value_()
vdone = iocg.done_vtime.counter.value_()
@@ -159,23 +159,13 @@
else:
self.inflight_pct = 0
- # vdebt used to be an atomic64_t and is now u64, support both
- try:
- self.debt_ms = iocg.abs_vdebt.counter.value_() / VTIME_PER_USEC / 1000
- except:
- self.debt_ms = iocg.abs_vdebt.value_() / VTIME_PER_USEC / 1000
-
- self.use_delay = blkg.use_delay.counter.value_()
- self.delay_ms = blkg.delay_nsec.counter.value_() / 1_000_000
-
- usage_idx = iocg.usage_idx.value_()
- self.usages = []
- self.usage = 0
- for i in range(NR_USAGE_SLOTS):
- usage = iocg.usages[(usage_idx + i) % NR_USAGE_SLOTS].value_()
- upct = usage * 100 / HWEIGHT_WHOLE
- self.usages.append(upct)
- self.usage = max(self.usage, upct)
+ self.usage = (100 * iocg.usage_delta_us.value_() /
+ ioc.period_us.value_()) if self.active else 0
+ self.debt_ms = iocg.abs_vdebt.value_() / VTIME_PER_USEC / 1000
+ if blkg.use_delay.counter.value_() != 0:
+ self.delay_ms = blkg.delay_nsec.counter.value_() / 1_000_000
+ else:
+ self.delay_ms = 0
def dict(self, now, path):
out = { 'cgroup' : path,
@@ -188,25 +178,20 @@
'hweight_inuse_pct' : self.hwi_pct,
'inflight_pct' : self.inflight_pct,
'debt_ms' : self.debt_ms,
- 'use_delay' : self.use_delay,
'delay_ms' : self.delay_ms,
'usage_pct' : self.usage,
'address' : self.address }
- for i in range(len(self.usages)):
- out[f'usage_pct_{i}'] = str(self.usages[i])
return out
def table_row_str(self, path):
out = f'{path[-28:]:28} ' \
f'{"*" if self.is_active else " "} ' \
- f'{self.inuse:5}/{self.active:5} ' \
+ f'{round(self.inuse):5}/{round(self.active):5} ' \
f'{self.hwi_pct:6.2f}/{self.hwa_pct:6.2f} ' \
f'{self.inflight_pct:6.2f} ' \
- f'{min(math.ceil(self.debt_ms), 999):3} ' \
- f'{min(self.use_delay, 99):2}*'\
- f'{min(math.ceil(self.delay_ms), 999):03} '
- for u in self.usages:
- out += f'{min(round(u), 999):03d}:'
+ f'{self.debt_ms:7.2f} ' \
+ f'{self.delay_ms:7.2f} '\
+ f'{min(self.usage, 999):6.2f}'
out = out.rstrip(':')
return out
@@ -233,7 +218,7 @@
root_iocg = None
ioc = None
-for i, ptr in radix_tree_for_each(blkcg_root.blkg_tree):
+for i, ptr in radix_tree_for_each(blkcg_root.blkg_tree.address_of_()):
blkg = drgn.Object(prog, 'struct blkcg_gq', address=ptr)
try:
if devname == blkg.q.kobj.parent.name.string_().decode('utf-8'):
@@ -248,6 +233,9 @@
if ioc is None:
err(f'Could not find ioc for {devname}');
+if interval == 0:
+ sys.exit(0)
+
# Keep printing
while True:
now = time.time()
diff --git a/tools/cgroup/memcg_slabinfo.py b/tools/cgroup/memcg_slabinfo.py
new file mode 100644
index 0000000..1600b17
--- /dev/null
+++ b/tools/cgroup/memcg_slabinfo.py
@@ -0,0 +1,226 @@
+#!/usr/bin/env drgn
+#
+# Copyright (C) 2020 Roman Gushchin <guro@fb.com>
+# Copyright (C) 2020 Facebook
+
+from os import stat
+import argparse
+import sys
+
+from drgn.helpers.linux import list_for_each_entry, list_empty
+from drgn.helpers.linux import for_each_page
+from drgn.helpers.linux.cpumask import for_each_online_cpu
+from drgn.helpers.linux.percpu import per_cpu_ptr
+from drgn import container_of, FaultError, Object
+
+
+DESC = """
+This is a drgn script to provide slab statistics for memory cgroups.
+It supports cgroup v2 and v1 and can emulate memory.kmem.slabinfo
+interface of cgroup v1.
+For drgn, visit https://github.com/osandov/drgn.
+"""
+
+
+MEMCGS = {}
+
+OO_SHIFT = 16
+OO_MASK = ((1 << OO_SHIFT) - 1)
+
+
+def err(s):
+ print('slabinfo.py: error: %s' % s, file=sys.stderr, flush=True)
+ sys.exit(1)
+
+
+def find_memcg_ids(css=prog['root_mem_cgroup'].css, prefix=''):
+ if not list_empty(css.children.address_of_()):
+ for css in list_for_each_entry('struct cgroup_subsys_state',
+ css.children.address_of_(),
+ 'sibling'):
+ name = prefix + '/' + css.cgroup.kn.name.string_().decode('utf-8')
+ memcg = container_of(css, 'struct mem_cgroup', 'css')
+ MEMCGS[css.cgroup.kn.id.value_()] = memcg
+ find_memcg_ids(css, name)
+
+
+def is_root_cache(s):
+ try:
+ return False if s.memcg_params.root_cache else True
+ except AttributeError:
+ return True
+
+
+def cache_name(s):
+ if is_root_cache(s):
+ return s.name.string_().decode('utf-8')
+ else:
+ return s.memcg_params.root_cache.name.string_().decode('utf-8')
+
+
+# SLUB
+
+def oo_order(s):
+ return s.oo.x >> OO_SHIFT
+
+
+def oo_objects(s):
+ return s.oo.x & OO_MASK
+
+
+def count_partial(n, fn):
+ nr_pages = 0
+ for page in list_for_each_entry('struct page', n.partial.address_of_(),
+ 'lru'):
+ nr_pages += fn(page)
+ return nr_pages
+
+
+def count_free(page):
+ return page.objects - page.inuse
+
+
+def slub_get_slabinfo(s, cfg):
+ nr_slabs = 0
+ nr_objs = 0
+ nr_free = 0
+
+ for node in range(cfg['nr_nodes']):
+ n = s.node[node]
+ nr_slabs += n.nr_slabs.counter.value_()
+ nr_objs += n.total_objects.counter.value_()
+ nr_free += count_partial(n, count_free)
+
+ return {'active_objs': nr_objs - nr_free,
+ 'num_objs': nr_objs,
+ 'active_slabs': nr_slabs,
+ 'num_slabs': nr_slabs,
+ 'objects_per_slab': oo_objects(s),
+ 'cache_order': oo_order(s),
+ 'limit': 0,
+ 'batchcount': 0,
+ 'shared': 0,
+ 'shared_avail': 0}
+
+
+def cache_show(s, cfg, objs):
+ if cfg['allocator'] == 'SLUB':
+ sinfo = slub_get_slabinfo(s, cfg)
+ else:
+ err('SLAB isn\'t supported yet')
+
+ if cfg['shared_slab_pages']:
+ sinfo['active_objs'] = objs
+ sinfo['num_objs'] = objs
+
+ print('%-17s %6lu %6lu %6u %4u %4d'
+ ' : tunables %4u %4u %4u'
+ ' : slabdata %6lu %6lu %6lu' % (
+ cache_name(s), sinfo['active_objs'], sinfo['num_objs'],
+ s.size, sinfo['objects_per_slab'], 1 << sinfo['cache_order'],
+ sinfo['limit'], sinfo['batchcount'], sinfo['shared'],
+ sinfo['active_slabs'], sinfo['num_slabs'],
+ sinfo['shared_avail']))
+
+
+def detect_kernel_config():
+ cfg = {}
+
+ cfg['nr_nodes'] = prog['nr_online_nodes'].value_()
+
+ if prog.type('struct kmem_cache').members[1].name == 'flags':
+ cfg['allocator'] = 'SLUB'
+ elif prog.type('struct kmem_cache').members[1].name == 'batchcount':
+ cfg['allocator'] = 'SLAB'
+ else:
+ err('Can\'t determine the slab allocator')
+
+ cfg['shared_slab_pages'] = False
+ try:
+ if prog.type('struct obj_cgroup'):
+ cfg['shared_slab_pages'] = True
+ except:
+ pass
+
+ return cfg
+
+
+def for_each_slab_page(prog):
+ PGSlab = 1 << prog.constant('PG_slab')
+ PGHead = 1 << prog.constant('PG_head')
+
+ for page in for_each_page(prog):
+ try:
+ if page.flags.value_() & PGSlab:
+ yield page
+ except FaultError:
+ pass
+
+
+def main():
+ parser = argparse.ArgumentParser(description=DESC,
+ formatter_class=
+ argparse.RawTextHelpFormatter)
+ parser.add_argument('cgroup', metavar='CGROUP',
+ help='Target memory cgroup')
+ args = parser.parse_args()
+
+ try:
+ cgroup_id = stat(args.cgroup).st_ino
+ find_memcg_ids()
+ memcg = MEMCGS[cgroup_id]
+ except KeyError:
+ err('Can\'t find the memory cgroup')
+
+ cfg = detect_kernel_config()
+
+ print('# name <active_objs> <num_objs> <objsize> <objperslab> <pagesperslab>'
+ ' : tunables <limit> <batchcount> <sharedfactor>'
+ ' : slabdata <active_slabs> <num_slabs> <sharedavail>')
+
+ if cfg['shared_slab_pages']:
+ obj_cgroups = set()
+ stats = {}
+ caches = {}
+
+ # find memcg pointers belonging to the specified cgroup
+ obj_cgroups.add(memcg.objcg.value_())
+ for ptr in list_for_each_entry('struct obj_cgroup',
+ memcg.objcg_list.address_of_(),
+ 'list'):
+ obj_cgroups.add(ptr.value_())
+
+ # look over all slab pages, belonging to non-root memcgs
+ # and look for objects belonging to the given memory cgroup
+ for page in for_each_slab_page(prog):
+ objcg_vec_raw = page.memcg_data.value_()
+ if objcg_vec_raw == 0:
+ continue
+ cache = page.slab_cache
+ if not cache:
+ continue
+ addr = cache.value_()
+ caches[addr] = cache
+ # clear the lowest bit to get the true obj_cgroups
+ objcg_vec = Object(prog, 'struct obj_cgroup **',
+ value=objcg_vec_raw & ~1)
+
+ if addr not in stats:
+ stats[addr] = 0
+
+ for i in range(oo_objects(cache)):
+ if objcg_vec[i].value_() in obj_cgroups:
+ stats[addr] += 1
+
+ for addr in caches:
+ if stats[addr] > 0:
+ cache_show(caches[addr], cfg, stats[addr])
+
+ else:
+ for s in list_for_each_entry('struct kmem_cache',
+ memcg.kmem_caches.address_of_(),
+ 'memcg_params.kmem_caches_node'):
+ cache_show(s, cfg, None)
+
+
+main()