The ffsll function is a lot slower than the __ffs64 built-in which
compiles to a single instruction on 64-bit. It's also nice to avoid
custom versions of standard functions. Note that __ffs == ffs - 1.
Signed-off-by: Ilia Mirkin <imirkin at alum.mit.edu>
---
I wrote a user-space program to test these out and make sure that the
functions behaved as expected. The logic in abi16 had to be flipped around a
bit since __ffs doesn't distinguish between 0 and 1. There's a minor
difference in that init->channel is going to get returned as 0 for ENOSPC vs
-1, but I can't imagine that'd matter.
drivers/gpu/drm/nouveau/core/core/parent.c | 2 +-
drivers/gpu/drm/nouveau/core/os.h | 11 -----------
drivers/gpu/drm/nouveau/nouveau_abi16.c | 4 ++--
3 files changed, 3 insertions(+), 14 deletions(-)
diff --git a/drivers/gpu/drm/nouveau/core/core/parent.c
b/drivers/gpu/drm/nouveau/core/core/parent.c
index 313380c..dee5d12 100644
--- a/drivers/gpu/drm/nouveau/core/core/parent.c
+++ b/drivers/gpu/drm/nouveau/core/core/parent.c
@@ -49,7 +49,7 @@ nouveau_parent_sclass(struct nouveau_object *parent, u16
handle,
mask = nv_parent(parent)->engine;
while (mask) {
- int i = ffsll(mask) - 1;
+ int i = __ffs64(mask);
if (nv_iclass(parent, NV_CLIENT_CLASS))
engine = nv_engine(nv_client(parent)->device);
diff --git a/drivers/gpu/drm/nouveau/core/os.h
b/drivers/gpu/drm/nouveau/core/os.h
index 191e739..3cd6120 100644
--- a/drivers/gpu/drm/nouveau/core/os.h
+++ b/drivers/gpu/drm/nouveau/core/os.h
@@ -23,17 +23,6 @@
#include <asm/unaligned.h>
-static inline int
-ffsll(u64 mask)
-{
- int i;
- for (i = 0; i < 64; i++) {
- if (mask & (1ULL << i))
- return i + 1;
- }
- return 0;
-}
-
#ifndef ioread32_native
#ifdef __BIG_ENDIAN
#define ioread16_native ioread16be
diff --git a/drivers/gpu/drm/nouveau/nouveau_abi16.c
b/drivers/gpu/drm/nouveau/nouveau_abi16.c
index 900fae0..b701117 100644
--- a/drivers/gpu/drm/nouveau/nouveau_abi16.c
+++ b/drivers/gpu/drm/nouveau/nouveau_abi16.c
@@ -270,8 +270,8 @@ nouveau_abi16_ioctl_channel_alloc(ABI16_IOCTL_ARGS)
return nouveau_abi16_put(abi16, -EINVAL);
/* allocate "abi16 channel" data and make up a handle for it */
- init->channel = ffsll(~abi16->handles);
- if (!init->channel--)
+ init->channel = __ffs64(~abi16->handles);
+ if (~abi16->handles == 0)
return nouveau_abi16_put(abi16, -ENOSPC);
chan = kzalloc(sizeof(*chan), GFP_KERNEL);
--
1.8.3.2
