From: Jeremy Kerr <jk@ozlabs.org>
To: <linuxppc-dev@ozlabs.org>
Subject: [PATCH 08/25] Fix restore_decr_wrapped() to match CBE Handbook
Date: Fri, 14 Sep 2007 16:32:54 +1000 [thread overview]
Message-ID: <1189751574.103493.873307761185.8.gpush@pokey> (raw)
In-Reply-To: <1189751574.98527.127994196313.1.gpush@pokey>
Based on an original patch from Masato Noguchi
<Masato.Noguchi@jp.sony.com>.
We're currently not restoring the SPE decrementer as specified by the
CBE handbook. This change fixes our implementation to match, and makes
the function read more like the docs.
Signed-off-by: Jeremy Kerr <jk@ozlabs.org>
---
arch/powerpc/platforms/cell/spufs/switch.c | 16 ++++++++--------
1 file changed, 8 insertions(+), 8 deletions(-)
diff --git a/arch/powerpc/platforms/cell/spufs/switch.c b/arch/powerpc/platforms/cell/spufs/switch.c
index 2506619..de7e5ee 100644
--- a/arch/powerpc/platforms/cell/spufs/switch.c
+++ b/arch/powerpc/platforms/cell/spufs/switch.c
@@ -1559,15 +1559,15 @@ static inline void restore_decr_wrapped(struct spu_state *csa, struct spu *spu)
* "wrapped" flag is set, OR in a '1' to
* CSA.SPU_Event_Status[Tm].
*/
- if (csa->lscsa->decr_status.slot[0] & SPU_DECR_STATUS_WRAPPED) {
- csa->spu_chnldata_RW[0] |= 0x20;
- }
- if ((csa->lscsa->decr_status.slot[0] & SPU_DECR_STATUS_WRAPPED) &&
- (csa->spu_chnlcnt_RW[0] == 0 &&
- ((csa->spu_chnldata_RW[2] & 0x20) == 0x0) &&
- ((csa->spu_chnldata_RW[0] & 0x20) != 0x1))) {
+ if (!(csa->lscsa->decr_status.slot[0] & SPU_DECR_STATUS_WRAPPED))
+ return;
+
+ if ((csa->spu_chnlcnt_RW[0] == 0) &&
+ (csa->spu_chnldata_RW[1] & 0x20) &&
+ !(csa->spu_chnldata_RW[0] & 0x20))
csa->spu_chnlcnt_RW[0] = 1;
- }
+
+ csa->spu_chnldata_RW[0] |= 0x20;
}
static inline void restore_ch_part1(struct spu_state *csa, struct spu *spu)
next prev parent reply other threads:[~2007-09-14 6:32 UTC|newest]
Thread overview: 31+ messages / expand[flat|nested] mbox.gz Atom feed top
2007-09-14 6:32 [PATCH 01/25] spufs: staticify file-internal functions & variables Jeremy Kerr
2007-09-14 6:32 ` [PATCH 02/25] spufs: remove asmlinkage from do_spu_create Jeremy Kerr
2007-09-14 7:44 ` Christoph Hellwig
2007-09-14 6:32 ` [PATCH 03/25] spufs: remove spu_harvest Jeremy Kerr
2007-09-14 6:32 ` [PATCH 19/25] spufs: Internal __spufs_get_foo() routines should take a spu_context * Jeremy Kerr
2007-09-14 7:43 ` Christoph Hellwig
2007-09-14 6:32 ` [PATCH 14/25] spufs: Use computed sizes/#defines rather than literals in SPU coredump code Jeremy Kerr
2007-09-14 6:32 ` [PATCH 05/25] spufs: fix race condition on gang->aff_ref_spu Jeremy Kerr
2007-09-14 6:32 ` [PATCH 10/25] spusched: fix null pointer dereference in find_victim Jeremy Kerr
2007-09-14 7:44 ` Christoph Hellwig
2007-09-20 0:13 ` Jeremy Kerr
2007-09-14 6:32 ` [PATCH 24/25] spufs: Respect RLIMIT_CORE in spu coredump code Jeremy Kerr
2007-09-14 6:32 ` Jeremy Kerr [this message]
2007-09-14 6:32 ` [PATCH 09/25] cell: remove DEBUG for spu callbacks Jeremy Kerr
2007-09-14 7:43 ` Christoph Hellwig
2007-09-14 6:32 ` [PATCH 18/25] spufs: Get rid of spufs_coredump_num_notes, it's not needed if we NULL terminate Jeremy Kerr
2007-09-14 6:32 ` [PATCH 16/25] spufs: Correctly calculate the size of the local-store to dump Jeremy Kerr
2007-09-14 6:32 ` [PATCH 06/25] cell: unify spufs syscall path Jeremy Kerr
2007-09-14 6:32 ` [PATCH 21/25] spufs: Combine spufs_coredump_calls with spufs_calls Jeremy Kerr
2007-09-14 6:32 ` [PATCH 12/25] spufs: Remove ctx_info and ctx_info_list Jeremy Kerr
2007-09-14 6:32 ` [PATCH 11/25] spufs: Extract the file descriptor search logic in SPU coredump code Jeremy Kerr
2007-09-14 6:32 ` [PATCH 17/25] spufs: Don't return -ENOSYS as extra notes size if spufs is not loaded Jeremy Kerr
2007-09-14 6:32 ` [PATCH 15/25] spufs: Write some SPU coredump values as ASCII Jeremy Kerr
2007-09-14 6:32 ` [PATCH 23/25] spufs: Handle errors in SPU coredump code, and support coredump to a pipe Jeremy Kerr
2007-09-14 6:32 ` [PATCH 20/25] spufs: Add contents of npc file to SPU coredumps Jeremy Kerr
2007-09-14 6:32 ` [PATCH 04/25] spufs: make isolated loader properly aligned Jeremy Kerr
2007-09-14 6:32 ` [PATCH 25/25] spufs: Add DEFINE_SPUFS_ATTRIBUTE() Jeremy Kerr
2007-09-14 6:32 ` [PATCH 13/25] spufs: Call spu_acquire_saved() before calculating the SPU note sizes Jeremy Kerr
2007-09-14 6:32 ` [PATCH 22/25] spufs: Cleanup ELF coredump extra notes logic Jeremy Kerr
2007-09-14 6:32 ` [PATCH 07/25] spufs: remove asmlinkage from spufs_calls Jeremy Kerr
2007-09-14 7:42 ` [PATCH 01/25] spufs: staticify file-internal functions & variables Christoph Hellwig
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=1189751574.103493.873307761185.8.gpush@pokey \
--to=jk@ozlabs.org \
--cc=linuxppc-dev@ozlabs.org \
/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 a public inbox, see mirroring instructions
for how to clone and mirror all data and code used for this inbox