OSDN Git Service

docs/memory-barriers.txt: Rewrite "KERNEL I/O BARRIER EFFECTS" section
authorWill Deacon <will.deacon@arm.com>
Mon, 11 Feb 2019 15:24:56 +0000 (15:24 +0000)
committerWill Deacon <will.deacon@arm.com>
Mon, 8 Apr 2019 10:59:30 +0000 (11:59 +0100)
commit4614bbdee35706ed77c130d23f12e21479b670ff
tree71342b4d66d5f23bcfe7b3764237fe2c93cecfa7
parent79a3aaa7b82e3106be97842dedfd8429248896e6
docs/memory-barriers.txt: Rewrite "KERNEL I/O BARRIER EFFECTS" section

The "KERNEL I/O BARRIER EFFECTS" section of memory-barriers.txt is vague,
x86-centric, out-of-date, incomplete and demonstrably incorrect in places.
This is largely because I/O ordering is a horrible can of worms, but also
because the document has stagnated as our understanding has evolved.

Attempt to address some of that, by rewriting the section based on
recent(-ish) discussions with Arnd, BenH and others. Maybe one day we'll
find a way to formalise this stuff, but for now let's at least try to
make the English easier to understand.

Cc: Benjamin Herrenschmidt <benh@kernel.crashing.org>
Cc: Michael Ellerman <mpe@ellerman.id.au>
Cc: Arnd Bergmann <arnd@arndb.de>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Andrea Parri <andrea.parri@amarulasolutions.com>
Cc: Palmer Dabbelt <palmer@sifive.com>
Cc: Daniel Lustig <dlustig@nvidia.com>
Cc: David Howells <dhowells@redhat.com>
Cc: Alan Stern <stern@rowland.harvard.edu>
Cc: "Maciej W. Rozycki" <macro@linux-mips.org>
Cc: Mikulas Patocka <mpatocka@redhat.com>
Acked-by: Linus Torvalds <torvalds@linux-foundation.org>
Reviewed-by: Paul E. McKenney <paulmck@linux.ibm.com>
Signed-off-by: Will Deacon <will.deacon@arm.com>
Documentation/memory-barriers.txt