Re: [PATCH] trace: skip hwasan

2019-02-21 Thread James Morse
Hi! On 18/02/2019 13:59, Will Deacon wrote: > [+James, who knows how to decode these things] Decode is a strong term! This stuff is printed by Cavium's secure-world software. All I'm doing is spotting the bits that vary between the out we've seen! > On Mon, Feb 18, 2019 at 02:56:47PM +0100, D

Re: [PATCH] trace: skip hwasan

2019-02-18 Thread Steven Rostedt
On Mon, 18 Feb 2019 16:56:44 +0100 Andrey Konovalov wrote: > On Mon, Feb 18, 2019 at 4:53 PM Qian Cai wrote: > > > > > > > > On 2/18/19 10:25 AM, Andrey Konovalov wrote: > > > On Sun, Feb 17, 2019 at 5:34 AM Qian Cai wrote: > > >> > > >> Enabling function tracer with CONFIG_KASAN_SW_TAGS=y

Re: [PATCH] trace: skip hwasan

2019-02-18 Thread Andrey Konovalov
On Mon, Feb 18, 2019 at 4:53 PM Qian Cai wrote: > > > > On 2/18/19 10:25 AM, Andrey Konovalov wrote: > > On Sun, Feb 17, 2019 at 5:34 AM Qian Cai wrote: > >> > >> Enabling function tracer with CONFIG_KASAN_SW_TAGS=y (hwasan) tracer > >> causes the whole system frozen on ThunderX2 systems with 256

Re: [PATCH] trace: skip hwasan

2019-02-18 Thread Qian Cai
On 2/18/19 10:25 AM, Andrey Konovalov wrote: > On Sun, Feb 17, 2019 at 5:34 AM Qian Cai wrote: >> >> Enabling function tracer with CONFIG_KASAN_SW_TAGS=y (hwasan) tracer >> causes the whole system frozen on ThunderX2 systems with 256 CPUs, >> because there is a burst of too much pointer access,

Re: [PATCH] trace: skip hwasan

2019-02-18 Thread Andrey Konovalov
On Sun, Feb 17, 2019 at 5:34 AM Qian Cai wrote: > > Enabling function tracer with CONFIG_KASAN_SW_TAGS=y (hwasan) tracer > causes the whole system frozen on ThunderX2 systems with 256 CPUs, > because there is a burst of too much pointer access, and then KASAN will > dereference each byte of the sh

Re: [PATCH] trace: skip hwasan

2019-02-18 Thread Dmitry Vyukov
On Mon, Feb 18, 2019 at 2:27 PM Qian Cai wrote: > > > > On 2/17/19 2:30 AM, Dmitry Vyukov wrote: > > On Sun, Feb 17, 2019 at 5:34 AM Qian Cai wrote: > >> > >> Enabling function tracer with CONFIG_KASAN_SW_TAGS=y (hwasan) tracer > >> causes the whole system frozen on ThunderX2 systems with 256 CPU

Re: [PATCH] trace: skip hwasan

2019-02-18 Thread Will Deacon
[+James, who knows how to decode these things] On Mon, Feb 18, 2019 at 02:56:47PM +0100, Dmitry Vyukov wrote: > On Mon, Feb 18, 2019 at 2:27 PM Qian Cai wrote: > > On 2/17/19 2:30 AM, Dmitry Vyukov wrote: > > > On Sun, Feb 17, 2019 at 5:34 AM Qian Cai wrote: > > >> > > >> Enabling function trace

Re: [PATCH] trace: skip hwasan

2019-02-18 Thread Qian Cai
On 2/17/19 2:30 AM, Dmitry Vyukov wrote: > On Sun, Feb 17, 2019 at 5:34 AM Qian Cai wrote: >> >> Enabling function tracer with CONFIG_KASAN_SW_TAGS=y (hwasan) tracer >> causes the whole system frozen on ThunderX2 systems with 256 CPUs, >> because there is a burst of too much pointer access, and

Re: [PATCH] trace: skip hwasan

2019-02-18 Thread Will Deacon
On Sat, Feb 16, 2019 at 11:34:34PM -0500, Qian Cai wrote: > Enabling function tracer with CONFIG_KASAN_SW_TAGS=y (hwasan) tracer > causes the whole system frozen on ThunderX2 systems with 256 CPUs, > because there is a burst of too much pointer access, and then KASAN will > dereference each byte of

Re: [PATCH] trace: skip hwasan

2019-02-16 Thread Dmitry Vyukov
On Sun, Feb 17, 2019 at 5:34 AM Qian Cai wrote: > > Enabling function tracer with CONFIG_KASAN_SW_TAGS=y (hwasan) tracer > causes the whole system frozen on ThunderX2 systems with 256 CPUs, > because there is a burst of too much pointer access, and then KASAN will > dereference each byte of the sh

[PATCH] trace: skip hwasan

2019-02-16 Thread Qian Cai
Enabling function tracer with CONFIG_KASAN_SW_TAGS=y (hwasan) tracer causes the whole system frozen on ThunderX2 systems with 256 CPUs, because there is a burst of too much pointer access, and then KASAN will dereference each byte of the shadow address for the tag checking which will kill all the C