https://bugzilla.kernel.org/show_bug.cgi?id=216183

--- Comment #8 from Erhard F. (erhard_f@mailbox.org) ---

Created attachment 301425
  --> https://bugzilla.kernel.org/attachment.cgi?id=301425&action=edit
bisect.log

Successfully did a bisect which revealed this commit:

 # git bisect good
a008f8f9fd67ffb13d906ef4ea6235a3d62dfdb6 is the first bad commit
commit a008f8f9fd67ffb13d906ef4ea6235a3d62dfdb6
Author: Nicholas Piggin [off-list ref]
Date:   Sat Jan 30 23:08:41 2021 +1000

    powerpc/64s/hash: improve context tracking of hash faults

    This moves the 64s/hash context tracking from hash_page_mm() to
    __do_hash_fault(), so it's no longer called by OCXL / SPU
    accelerators, which was certainly the wrong thing to be doing,
    because those callers are not low level interrupt handlers, so
    should have entered a kernel context tracking already.

    Then remain in kernel context for the duration of the fault,
    rather than enter/exit for the hash fault then enter/exit for
    the page fault, which is pointless.

    Even still, calling exception_enter/exit in __do_hash_fault seems
    questionable because that's touching per-cpu variables, tracing,
    etc., which might have been interrupted by this hash fault or
    themselves cause hash faults. But maybe I miss something because
    hash_page_mm very deliberately calls trace_hash_fault too, for
    example. So for now go with it, it's no worse than before, in this
    regard.

    Signed-off-by: Nicholas Piggin [off-list ref]
    Signed-off-by: Michael Ellerman [off-list ref]
    Link: https://lore.kernel.org/r/20210130130852.2952424-32-npiggin@gmail.com (local)

 arch/powerpc/include/asm/bug.h        |  1 +
 arch/powerpc/mm/book3s64/hash_utils.c |  7 ++++---
 arch/powerpc/mm/fault.c               | 39 +++++++++++++++++++++++++----------
 3 files changed, 33 insertions(+), 14 deletions(-)

-- 
You may reply to this email to add a comment.

You are receiving this mail because:
You are watching the assignee of the bug.