diff options
| author | Christoph Hellwig <hch@lst.de> | 2007-07-20 21:39:34 +0200 |
|---|---|---|
| committer | Arnd Bergmann <arnd@klappe.arndb.de> | 2007-07-20 21:41:52 +0200 |
| commit | 27b1ea091f0c088ecad0d492f37fbe7b8d54d7dc (patch) | |
| tree | 5d54369e0b21877ee9ea57dddfab9733bcd82490 /arch/powerpc/platforms/cell/spufs/coredump.c | |
| parent | 27ec41d3a1d4df2b7cd190e93aad22ab86a72aa1 (diff) | |
[CELL] spufs: make sure context are scheduled again after spu_acquire_saved
Currently a process is removed from the physical spu when spu_acquire_saved
is saved but never put back. This patch adds a new spu_release_saved
that is to be paired with spu_acquire_saved and put the process back if
it has been in RUNNABLE state before.
Niether Jeremy not be are entirely happy about this exact patch because
it adds another spu_activate call outside of the owner thread, but I
feel this is the best short-term fix we can come up with.
Signed-off-by: Christoph Hellwig <hch@lst.de>
Signed-off-by: Jeremy Kerr <jk@ozlabs.org>
Signed-off-by: Arnd Bergmann <arnd.bergmann@de.ibm.com>
Diffstat (limited to 'arch/powerpc/platforms/cell/spufs/coredump.c')
| -rw-r--r-- | arch/powerpc/platforms/cell/spufs/coredump.c | 2 |
1 files changed, 1 insertions, 1 deletions
diff --git a/arch/powerpc/platforms/cell/spufs/coredump.c b/arch/powerpc/platforms/cell/spufs/coredump.c index 5d9ad5a0307b..5e31799b1e3f 100644 --- a/arch/powerpc/platforms/cell/spufs/coredump.c +++ b/arch/powerpc/platforms/cell/spufs/coredump.c @@ -226,7 +226,7 @@ static void spufs_arch_write_notes(struct file *file) spu_acquire_saved(ctx_info->ctx); for (j = 0; j < spufs_coredump_num_notes; j++) spufs_arch_write_note(ctx_info, j, file); - spu_release(ctx_info->ctx); + spu_release_saved(ctx_info->ctx); list_del(&ctx_info->list); kfree(ctx_info); } |