Revision 0251d196b0e1a19c870be882e5d4f496de8ab758 authored by Guangbin Huang on 27 October 2021, 12:11:45 UTC, committed by David S. Miller on 27 October 2021, 13:47:33 UTC
Currently, if there is a reset event triggered by RAS during device in
initialization process, driver may run reset process concurrently with
initialization process. In this case, it may cause problem. For example,
the RSS indirection table may has not been alloc memory in initialization
process yet, but it is used in reset process, it will cause a call trace
like this:

[61228.744836] Unable to handle kernel NULL pointer dereference at virtual address 0000000000000000
...
[61228.897677] Workqueue: hclgevf hclgevf_service_task [hclgevf]
[61228.911390] pstate: 40400009 (nZcv daif +PAN -UAO -TCO BTYPE=--)
[61228.918670] pc : hclgevf_set_rss_indir_table+0xb4/0x190 [hclgevf]
[61228.927812] lr : hclgevf_set_rss_indir_table+0x90/0x190 [hclgevf]
[61228.937248] sp : ffff8000162ebb50
[61228.941087] x29: ffff8000162ebb50 x28: ffffb77add72dbc0 x27: ffff0820c7dc8080
[61228.949516] x26: 0000000000000000 x25: ffff0820ad4fc880 x24: ffff0820c7dc8080
[61228.958220] x23: ffff0820c7dc8090 x22: 00000000ffffffff x21: 0000000000000040
[61228.966360] x20: ffffb77add72b9c0 x19: 0000000000000000 x18: 0000000000000030
[61228.974646] x17: 0000000000000000 x16: ffffb77ae713feb0 x15: ffff0820ad4fcce8
[61228.982808] x14: ffffffffffffffff x13: ffff8000962eb7f7 x12: 00003834ec70c960
[61228.991990] x11: 00e0fafa8c206982 x10: 9670facc78a8f9a8 x9 : ffffb77add717530
[61229.001123] x8 : ffff0820ad4fd6b8 x7 : 0000000000000000 x6 : 0000000000000011
[61229.010249] x5 : 00000000000cb1b0 x4 : 0000000000002adb x3 : 0000000000000049
[61229.018662] x2 : ffff8000162ebbb8 x1 : 0000000000000000 x0 : 0000000000000480
[61229.027002] Call trace:
[61229.030177]  hclgevf_set_rss_indir_table+0xb4/0x190 [hclgevf]
[61229.039009]  hclgevf_rss_init_hw+0x128/0x1b4 [hclgevf]
[61229.046809]  hclgevf_reset_rebuild+0x17c/0x69c [hclgevf]
[61229.053862]  hclgevf_reset_service_task+0x4cc/0xa80 [hclgevf]
[61229.061306]  hclgevf_service_task+0x6c/0x630 [hclgevf]
[61229.068491]  process_one_work+0x1dc/0x48c
[61229.074121]  worker_thread+0x15c/0x464
[61229.078562]  kthread+0x168/0x16c
[61229.082873]  ret_from_fork+0x10/0x18
[61229.088221] Code: 7900e7f6 f904a683 d503201f 9101a3e2 (38616b43)
[61229.095357] ---[ end trace 153661a538f6768c ]---

To fix this problem, don't schedule reset task before initialization
process is done.

Signed-off-by: Guangbin Huang <huangguangbin2@huawei.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
1 parent f29da40
Raw File
show_delta
#!/usr/bin/env python
# SPDX-License-Identifier: GPL-2.0-only
#
# show_deltas: Read list of printk messages instrumented with
# time data, and format with time deltas.
#
# Also, you can show the times relative to a fixed point.
#
# Copyright 2003 Sony Corporation
#

import sys
import string

def usage():
	print ("""usage: show_delta [<options>] <filename>

This program parses the output from a set of printk message lines which
have time data prefixed because the CONFIG_PRINTK_TIME option is set, or
the kernel command line option "time" is specified. When run with no
options, the time information is converted to show the time delta between
each printk line and the next.  When run with the '-b' option, all times
are relative to a single (base) point in time.

Options:
  -h            Show this usage help.
  -b <base>	Specify a base for time references.
		<base> can be a number or a string.
		If it is a string, the first message line
		which matches (at the beginning of the
		line) is used as the time reference.

ex: $ dmesg >timefile
    $ show_delta -b NET4 timefile

will show times relative to the line in the kernel output
starting with "NET4".
""")
	sys.exit(1)

# returns a tuple containing the seconds and text for each message line
# seconds is returned as a float
# raise an exception if no timing data was found
def get_time(line):
	if line[0]!="[":
		raise ValueError

	# split on closing bracket
	(time_str, rest) = string.split(line[1:],']',1)
	time = string.atof(time_str)

	#print "time=", time
	return (time, rest)


# average line looks like:
# [    0.084282] VFS: Mounted root (romfs filesystem) readonly
# time data is expressed in seconds.useconds,
# convert_line adds a delta for each line
last_time = 0.0
def convert_line(line, base_time):
	global last_time

	try:
		(time, rest) = get_time(line)
	except:
		# if any problem parsing time, don't convert anything
		return line

	if base_time:
		# show time from base
		delta = time - base_time
	else:
		# just show time from last line
		delta = time - last_time
		last_time = time

	return ("[%5.6f < %5.6f >]" % (time, delta)) + rest

def main():
	base_str = ""
	filein = ""
	for arg in sys.argv[1:]:
		if arg=="-b":
			base_str = sys.argv[sys.argv.index("-b")+1]
		elif arg=="-h":
			usage()
		else:
			filein = arg

	if not filein:
		usage()

	try:
		lines = open(filein,"r").readlines()
	except:
		print ("Problem opening file: %s" % filein)
		sys.exit(1)

	if base_str:
		print ('base= "%s"' % base_str)
		# assume a numeric base.  If that fails, try searching
		# for a matching line.
		try:
			base_time = float(base_str)
		except:
			# search for line matching <base> string
			found = 0
			for line in lines:
				try:
					(time, rest) = get_time(line)
				except:
					continue
				if string.find(rest, base_str)==1:
					base_time = time
					found = 1
					# stop at first match
					break
			if not found:
				print ('Couldn\'t find line matching base pattern "%s"' % base_str)
				sys.exit(1)
	else:
		base_time = 0.0

	for line in lines:
		print (convert_line(line, base_time),)

main()
back to top