There are cases where we can use this_cpu_ptr and as the result
of using this_cpu_ptr() we no longer need to determine the
current executing cpu.
In those places no get/put_cpu combination is needed anymore.
The local cpu variable can be eliminated.
Preemption still needs to be disabled and enabled since the
modifications of the per cpu variables is not atomic. There may
be multiple per cpu variables modified and those must all
be from the same processor.
cc: Dan Williams <[email protected]>
cc: Eric Biederman <[email protected]>
cc: Stephen Hemminger <[email protected]>
cc: Trond Myklebust <[email protected]>
cc: Herbert Xu <[email protected]>
cc: David L Stevens <[email protected]>
Signed-off-by: Christoph Lameter <[email protected]>
---
drivers/dma/dmaengine.c | 36 +++++++++++++-----------------------
drivers/net/veth.c | 7 +++----
2 files changed, 16 insertions(+), 27 deletions(-)
Index: linux-2.6/drivers/dma/dmaengine.c
===================================================================
--- linux-2.6.orig/drivers/dma/dmaengine.c 2009-06-04 13:38:15.000000000 -0500
+++ linux-2.6/drivers/dma/dmaengine.c 2009-06-04 14:19:43.000000000 -0500
@@ -326,14 +326,7 @@ arch_initcall(dma_channel_table_init);
*/
struct dma_chan *dma_find_channel(enum dma_transaction_type tx_type)
{
- struct dma_chan *chan;
- int cpu;
-
- cpu = get_cpu();
- chan = per_cpu_ptr(channel_table[tx_type], cpu)->chan;
- put_cpu();
-
- return chan;
+ return this_cpu_read(channel_table[tx_type]->chan);
}
EXPORT_SYMBOL(dma_find_channel);
@@ -803,7 +796,6 @@ dma_async_memcpy_buf_to_buf(struct dma_c
struct dma_async_tx_descriptor *tx;
dma_addr_t dma_dest, dma_src;
dma_cookie_t cookie;
- int cpu;
unsigned long flags;
dma_src = dma_map_single(dev->dev, src, len, DMA_TO_DEVICE);
@@ -822,10 +814,10 @@ dma_async_memcpy_buf_to_buf(struct dma_c
tx->callback = NULL;
cookie = tx->tx_submit(tx);
- cpu = get_cpu();
- per_cpu_ptr(chan->local, cpu)->bytes_transferred += len;
- per_cpu_ptr(chan->local, cpu)->memcpy_count++;
- put_cpu();
+ preempt_disable();
+ __this_cpu_add(chan->local->bytes_transferred, len);
+ __this_cpu_inc(chan->local->memcpy_count);
+ preempt_enable();
return cookie;
}
@@ -852,7 +844,6 @@ dma_async_memcpy_buf_to_pg(struct dma_ch
struct dma_async_tx_descriptor *tx;
dma_addr_t dma_dest, dma_src;
dma_cookie_t cookie;
- int cpu;
unsigned long flags;
dma_src = dma_map_single(dev->dev, kdata, len, DMA_TO_DEVICE);
@@ -869,10 +860,10 @@ dma_async_memcpy_buf_to_pg(struct dma_ch
tx->callback = NULL;
cookie = tx->tx_submit(tx);
- cpu = get_cpu();
- per_cpu_ptr(chan->local, cpu)->bytes_transferred += len;
- per_cpu_ptr(chan->local, cpu)->memcpy_count++;
- put_cpu();
+ preempt_disable();
+ __this_cpu_add(chan->local->bytes_transferred, len);
+ __this_cpu_inc(chan->local->memcpy_count);
+ preempt_enable();
return cookie;
}
@@ -901,7 +892,6 @@ dma_async_memcpy_pg_to_pg(struct dma_cha
struct dma_async_tx_descriptor *tx;
dma_addr_t dma_dest, dma_src;
dma_cookie_t cookie;
- int cpu;
unsigned long flags;
dma_src = dma_map_page(dev->dev, src_pg, src_off, len, DMA_TO_DEVICE);
@@ -919,10 +909,10 @@ dma_async_memcpy_pg_to_pg(struct dma_cha
tx->callback = NULL;
cookie = tx->tx_submit(tx);
- cpu = get_cpu();
- per_cpu_ptr(chan->local, cpu)->bytes_transferred += len;
- per_cpu_ptr(chan->local, cpu)->memcpy_count++;
- put_cpu();
+ preempt_disable();
+ __this_cpu_add(chan->local->bytes_transferred, len);
+ __this_cpu_inc(chan->local->memcpy_count);
+ preempt_enable();
return cookie;
}
Index: linux-2.6/drivers/net/veth.c
===================================================================
--- linux-2.6.orig/drivers/net/veth.c 2009-06-04 13:38:15.000000000 -0500
+++ linux-2.6/drivers/net/veth.c 2009-06-04 14:18:00.000000000 -0500
@@ -153,7 +153,7 @@ static int veth_xmit(struct sk_buff *skb
struct net_device *rcv = NULL;
struct veth_priv *priv, *rcv_priv;
struct veth_net_stats *stats, *rcv_stats;
- int length, cpu;
+ int length;
skb_orphan(skb);
@@ -161,9 +161,8 @@ static int veth_xmit(struct sk_buff *skb
rcv = priv->peer;
rcv_priv = netdev_priv(rcv);
- cpu = smp_processor_id();
- stats = per_cpu_ptr(priv->stats, cpu);
- rcv_stats = per_cpu_ptr(rcv_priv->stats, cpu);
+ stats = this_cpu_ptr(priv->stats);
+ rcv_stats = this_cpu_ptr(rcv_priv->stats);
if (!(rcv->flags & IFF_UP))
goto tx_drop;
--
[ added Maciej to the cc ]
On Fri, Jun 5, 2009 at 12:18 PM, <[email protected]> wrote:
> There are cases where we can use this_cpu_ptr and as the result
> of using this_cpu_ptr() we no longer need to determine the
> current executing cpu.
>
> In those places no get/put_cpu combination is needed anymore.
> The local cpu variable can be eliminated.
>
> Preemption still needs to be disabled and enabled since the
> modifications of the per cpu variables is not atomic. There may
> be multiple per cpu variables modified and those must all
> be from the same processor.
>
> cc: Dan Williams <[email protected]>
Acked-by: Dan Williams <[email protected]>
Dan Williams wrote:
> [ added Maciej to the cc ]
Thanks Dan.
>
> On Fri, Jun 5, 2009 at 12:18 PM, <[email protected]> wrote:
>> There are cases where we can use this_cpu_ptr and as the result
>> of using this_cpu_ptr() we no longer need to determine the current executing cpu.
>>
>> In those places no get/put_cpu combination is needed anymore.
>> The local cpu variable can be eliminated.
>>
>> Preemption still needs to be disabled and enabled since the
>> modifications of the per cpu variables is not atomic. There may
>> be multiple per cpu variables modified and those must all
>> be from the same processor.
>>
>> cc: Dan Williams <[email protected]>
>
> Acked-by: Dan Williams <[email protected]>
Acked-by: Maciej Sosnowski <[email protected]>-