From: Benjamin Herrenschmidt <benh@kernel.crashing.org>
To: Thomas Huth <thuth@redhat.com>,
Peter Maydell <peter.maydell@linaro.org>,
David Gibson <david@gibson.dropbear.id.au>
Cc: peter.maydell@linearo.org,
"qemu-ppc@nongnu.org" <qemu-ppc@nongnu.org>,
Alexander Graf <agraf@suse.de>,
QEMU Developers <qemu-devel@nongnu.org>
Subject: Re: [Qemu-devel] [PULL 00/66] ppc-for-2.8 queue 20160906
Date: Wed, 07 Sep 2016 07:52:29 +1000 [thread overview]
Message-ID: <1473198749.8689.43.camel@kernel.crashing.org> (raw)
In-Reply-To: <762703d0-bb32-8b9f-a538-5541890c9781@redhat.com>
On Tue, 2016-09-06 at 23:09 +0200, Thomas Huth wrote:
> The bad commit is: "ppc: Speed up load/store multiple"
>
> There are two "#if defined(HOST_WORDS_BIGENDIAN)" sections in this patch
> which are both bad: The memcpy tries to copy 32-bit values into 64-bit
> registers, which of course does not work (unless you compile this code
> for a 32-bit host only where the size of a gpr is only 32-bit).
The instruction does that. It only copies 32-bits. I think it's
correct.
> I'd suggest to remove the "#if defined(HOST_WORDS_BIGENDIAN)" part and
> use cpu_to_be32() and friends instead of the bswap32() here?
I tried that but it prevents the faster memcpy, the whole point was to
speed things up...
Cheers,
Ben.
next prev parent reply other threads:[~2016-09-06 21:52 UTC|newest]
Thread overview: 79+ messages / expand[flat|nested] mbox.gz Atom feed top
2016-09-06 3:39 [Qemu-devel] [PULL 00/66] ppc-for-2.8 queue 20160906 David Gibson
2016-09-06 3:39 ` [Qemu-devel] [PULL 01/66] xics_kvm: drop extra checking of kernel_xics_fd David Gibson
2016-09-06 3:39 ` [Qemu-devel] [PULL 02/66] hw/ppc: include fdt helper routine in a common file David Gibson
2016-09-06 3:39 ` [Qemu-devel] [PULL 03/66] target-ppc: Introduce Power9 family David Gibson
2016-09-06 3:39 ` [Qemu-devel] [PULL 04/66] target-ppc: Introduce POWER ISA 3.0 flag David Gibson
2016-09-06 3:39 ` [Qemu-devel] [PULL 05/66] target-ppc: adding addpcis instruction David Gibson
2016-09-06 3:39 ` [Qemu-devel] [PULL 06/66] target-ppc: add cmprb instruction David Gibson
2016-09-06 3:39 ` [Qemu-devel] [PULL 07/66] target-ppc: add modulo word operations David Gibson
2016-09-06 3:39 ` [Qemu-devel] [PULL 08/66] target-ppc: add modulo dword operations David Gibson
2016-09-06 3:39 ` [Qemu-devel] [PULL 09/66] target-ppc: add cnttzd[.] instruction David Gibson
2016-09-06 3:39 ` [Qemu-devel] [PULL 10/66] target-ppc: add cnttzw[.] instruction David Gibson
2016-09-06 3:39 ` [Qemu-devel] [PULL 11/66] target-ppc: add cmpeqb instruction David Gibson
2016-09-06 3:39 ` [Qemu-devel] [PULL 12/66] target-ppc: add setb instruction David Gibson
2016-09-06 3:40 ` [Qemu-devel] [PULL 13/66] target-ppc: add maddld instruction David Gibson
2016-09-06 3:40 ` [Qemu-devel] [PULL 14/66] target-ppc: add maddhd and maddhdu instruction David Gibson
2016-09-06 3:40 ` [Qemu-devel] [PULL 15/66] target-ppc: introduce opc4 for Expanded Opcode David Gibson
2016-09-06 3:40 ` [Qemu-devel] [PULL 16/66] ppc: Provide basic raise_exception_* functions David Gibson
2016-09-06 3:40 ` [Qemu-devel] [PULL 17/66] ppc: Move classic fp ops out of translate.c David Gibson
2016-09-06 3:40 ` [Qemu-devel] [PULL 18/66] ppc: Move embedded spe " David Gibson
2016-09-06 3:40 ` [Qemu-devel] [PULL 19/66] ppc: Move DFP " David Gibson
2016-09-06 3:40 ` [Qemu-devel] [PULL 20/66] ppc: Move VMX " David Gibson
2016-09-06 3:40 ` [Qemu-devel] [PULL 21/66] ppc: Move VSX " David Gibson
2016-09-06 3:40 ` [Qemu-devel] [PULL 22/66] ppc: Rename fload_invalid_op_excp to float_invalid_op_excp David Gibson
2016-09-06 3:40 ` [Qemu-devel] [PULL 23/66] ppc: Make float_invalid_op_excp() pass the return address David Gibson
2016-09-06 3:40 ` [Qemu-devel] [PULL 24/66] ppc: Make float_check_status() " David Gibson
2016-09-06 3:40 ` [Qemu-devel] [PULL 25/66] ppc: Don't update the NIP in floating point generated code David Gibson
2016-09-06 3:40 ` [Qemu-devel] [PULL 26/66] ppc: FP exceptions are always precise David Gibson
2016-09-06 3:40 ` [Qemu-devel] [PULL 27/66] ppc: Don't update NIP in lswi/lswx/stswi/stswx David Gibson
2016-09-06 3:40 ` [Qemu-devel] [PULL 28/66] ppc: Don't update NIP in lmw/stmw/icbi David Gibson
2016-09-06 3:40 ` [Qemu-devel] [PULL 29/66] ppc: Make tlb_fill() use new exception helper David Gibson
2016-09-06 3:40 ` [Qemu-devel] [PULL 30/66] ppc: Rework NIP updates vs. exception generation David Gibson
2016-09-06 3:40 ` [Qemu-devel] [PULL 31/66] ppc: Fix source NIP on SLB related interrupts David Gibson
2016-09-06 3:40 ` [Qemu-devel] [PULL 32/66] ppc: Don't update NIP in DCR access routines David Gibson
2016-09-06 3:40 ` [Qemu-devel] [PULL 33/66] ppc: Don't update NIP in facility unavailable interrupts David Gibson
2016-09-06 3:40 ` [Qemu-devel] [PULL 34/66] ppc: Don't update NIP BookE 2.06 tlbwe David Gibson
2016-09-06 3:40 ` [Qemu-devel] [PULL 35/66] ppc: Don't update NIP on conditional trap instructions David Gibson
2016-09-06 3:40 ` [Qemu-devel] [PULL 36/66] ppc: Don't update NIP if not taking alignment exceptions David Gibson
2016-09-06 3:40 ` [Qemu-devel] [PULL 37/66] ppc: Don't update NIP in dcbz and lscbx David Gibson
2016-09-06 3:40 ` [Qemu-devel] [PULL 38/66] ppc: Make alignment exceptions suck less David Gibson
2016-09-06 3:40 ` [Qemu-devel] [PULL 39/66] ppc: Handle unconditional (always/never) traps at translation time David Gibson
2016-09-06 3:40 ` [Qemu-devel] [PULL 40/66] ppc: Speed up dcbz David Gibson
2016-09-06 3:40 ` [Qemu-devel] [PULL 41/66] ppc: Fix CFAR updates David Gibson
2016-09-06 3:40 ` [Qemu-devel] [PULL 42/66] ppc: Don't set access_type on all load/stores on hash64 David Gibson
2016-09-06 3:40 ` [Qemu-devel] [PULL 43/66] ppc: Use a helper to generate "LE unsupported" alignment interrupts David Gibson
2016-09-06 3:40 ` [Qemu-devel] [PULL 44/66] ppc: load/store multiple and string insns don't do LE David Gibson
2016-09-06 3:40 ` [Qemu-devel] [PULL 45/66] ppc: Speed up load/store multiple David Gibson
2016-09-06 3:40 ` [Qemu-devel] [PULL 46/66] target-ppc: implement branch-less divw[o][.] David Gibson
2016-09-06 3:40 ` [Qemu-devel] [PULL 47/66] target-ppc: implement branch-less divd[o][.] David Gibson
2016-09-06 3:40 ` [Qemu-devel] [PULL 48/66] target-ppc: add dtstsfi[q] instructions David Gibson
2016-09-06 3:40 ` [Qemu-devel] [PULL 49/66] target-ppc: add vabsdu[b, h, w] instructions David Gibson
2016-09-06 3:40 ` [Qemu-devel] [PULL 50/66] target-ppc: add vcmpnez[b, h, w][.] instructions David Gibson
2016-09-06 3:40 ` [Qemu-devel] [PULL 51/66] target-ppc: add vslv instruction David Gibson
2016-09-06 3:40 ` [Qemu-devel] [PULL 52/66] target-ppc: add vsrv instruction David Gibson
2016-09-06 3:40 ` [Qemu-devel] [PULL 53/66] target-ppc: add extswsli[.] instruction David Gibson
2016-09-06 3:40 ` [Qemu-devel] [PULL 54/66] ppc: Rename #include'd .c files to .inc.c David Gibson
2016-09-06 3:40 ` [Qemu-devel] [PULL 55/66] hw/ppc: use error_report instead of fprintf David Gibson
2016-09-06 3:40 ` [Qemu-devel] [PULL 56/66] hw/ppc: add a ppc_create_page_sizes_prop() helper routine David Gibson
2016-09-06 3:40 ` [Qemu-devel] [PULL 57/66] ppc: Fix macio ESCC legacy mapping David Gibson
2016-09-06 3:40 ` [Qemu-devel] [PULL 58/66] ppc: Fix catching some segfaults in user mode David Gibson
2016-09-06 3:40 ` [Qemu-devel] [PULL 59/66] ppc: Stop dumping state on all exceptions in linux-user David Gibson
2016-09-06 3:40 ` [Qemu-devel] [PULL 60/66] ppc: Don't generate dead code on unconditional branches David Gibson
2016-09-06 3:40 ` [Qemu-devel] [PULL 61/66] ppc: Improve flags for helpers loading/writing the time facilities David Gibson
2016-09-06 3:40 ` [Qemu-devel] [PULL 62/66] ppc: Improve the exception helpers flags David Gibson
2016-09-06 3:40 ` [Qemu-devel] [PULL 63/66] ppc: Improve a few more helper flags David Gibson
2016-09-06 3:40 ` [Qemu-devel] [PULL 64/66] spapr: implement H_CHANGE_LOGICAL_LAN_MAC h_call David Gibson
2016-09-06 3:40 ` [Qemu-devel] [PULL 65/66] tests: Resort check-qtest entries in Makefile.include David Gibson
2016-09-06 3:40 ` [Qemu-devel] [PULL 66/66] tests: Check serial output of firmware boot of some machines David Gibson
2016-09-06 5:14 ` [Qemu-devel] [PULL 00/66] ppc-for-2.8 queue 20160906 no-reply
2016-09-06 14:04 ` Peter Maydell
2016-09-06 19:35 ` Thomas Huth
2016-09-06 20:23 ` Paolo Bonzini
2016-09-06 20:55 ` Thomas Huth
2016-09-06 21:26 ` Thomas Huth
2016-09-07 1:13 ` David Gibson
2016-09-06 21:09 ` Thomas Huth
2016-09-06 21:52 ` Benjamin Herrenschmidt [this message]
2016-09-07 2:26 ` Benjamin Herrenschmidt
2016-09-06 3:42 David Gibson
2016-09-06 6:39 ` no-reply
Reply instructions:
You may reply publicly to this message via plain-text email
using any one of the following methods:
* Save the following mbox file, import it into your mail client,
and reply-to-all from there: mbox
Avoid top-posting and favor interleaved quoting:
https://en.wikipedia.org/wiki/Posting_style#Interleaved_style
* Reply using the --to, --cc, and --in-reply-to
switches of git-send-email(1):
git send-email \
--in-reply-to=1473198749.8689.43.camel@kernel.crashing.org \
--to=benh@kernel.crashing.org \
--cc=agraf@suse.de \
--cc=david@gibson.dropbear.id.au \
--cc=peter.maydell@linaro.org \
--cc=peter.maydell@linearo.org \
--cc=qemu-devel@nongnu.org \
--cc=qemu-ppc@nongnu.org \
--cc=thuth@redhat.com \
/path/to/YOUR_REPLY
https://kernel.org/pub/software/scm/git/docs/git-send-email.html
* If your mail client supports setting the In-Reply-To header
via mailto: links, try the mailto: link
Be sure your reply has a Subject: header at the top and a blank line
before the message body.
This is an external index of several public inboxes,
see mirroring instructions on how to clone and mirror
all data and code used by this external index.