From: Leonard Crestez <leonard.crestez@xxxxxxx> commit 46d10a094353c05144f3b0530516bdac3ce7c435 upstream Use errors=replace because it is never desirable for lx-dmesg to fail on string decoding errors, not even if the log buffer is corrupt and we show incorrect info. The kernel will sometimes print utf8, for example the copyright symbol from jffs2. In order to make this work specify 'utf8' everywhere because python2 otherwise defaults to 'ascii'. In theory the second errors='replace' is not be required because everything that can be decoded as utf8 should also be encodable back to utf8. But it's better to be extra safe here. It's worth noting that this is definitely not true for encoding='ascii', unknown characters are replaced with U+FFFD REPLACEMENT CHARACTER and they fail to encode back to ascii. Link: http://lkml.kernel.org/r/acee067f3345954ed41efb77b80eebdc038619c6.1498481469.git.leonard.crestez@xxxxxxx Signed-off-by: Leonard Crestez <leonard.crestez@xxxxxxx> Acked-by: Jan Kiszka <jan.kiszka@xxxxxxxxxxx> Cc: Jason Wessel <jason.wessel@xxxxxxxxxxxxx> Cc: Kieran Bingham <kieran@xxxxxxxxxxxxxxx> Signed-off-by: Andrew Morton <akpm@xxxxxxxxxxxxxxxxxxxx> Signed-off-by: Linus Torvalds <torvalds@xxxxxxxxxxxxxxxxxxxx> Signed-off-by: Florian Fainelli <f.fainelli@xxxxxxxxx> --- scripts/gdb/linux/dmesg.py | 13 ++++++++++--- 1 file changed, 10 insertions(+), 3 deletions(-) diff --git a/scripts/gdb/linux/dmesg.py b/scripts/gdb/linux/dmesg.py index f5a030333dfd..6d2e09a2ad2f 100644 --- a/scripts/gdb/linux/dmesg.py +++ b/scripts/gdb/linux/dmesg.py @@ -12,6 +12,7 @@ # import gdb +import sys from linux import utils @@ -52,13 +53,19 @@ class LxDmesg(gdb.Command): continue text_len = utils.read_u16(log_buf[pos + 10:pos + 12]) - text = log_buf[pos + 16:pos + 16 + text_len].decode() + text = log_buf[pos + 16:pos + 16 + text_len].decode( + encoding='utf8', errors='replace') time_stamp = utils.read_u64(log_buf[pos:pos + 8]) for line in text.splitlines(): - gdb.write("[{time:12.6f}] {line}\n".format( + msg = u"[{time:12.6f}] {line}\n".format( time=time_stamp / 1000000000.0, - line=line)) + line=line) + # With python2 gdb.write will attempt to convert unicode to + # ascii and might fail so pass an utf8-encoded str instead. + if sys.hexversion < 0x03000000: + msg = msg.encode(encoding='utf8', errors='replace') + gdb.write(msg) pos += length -- 2.25.1
