[PATCH] percpu: use DEFINE_PER_CPU_SHARED_ALIGNED()

[PATCH] percpu: use DEFINE_PER_CPU_SHARED_ALIGNED()

[Tejun Heo]

There are a few places where ___cacheline_aligned* is used with
DEFINE_PER_CPU().  Use DEFINE_PER_CPU_SHARED_ALIGNED() instead.

DEFINE_PER_CPU_SHARED_ALIGNED() applies alignment only on SMPs.  While
all other converted places used _in_smp variant or only get compiled
for SMP, net/rds used unconditional ____cacheline_aligned.  I don't
see any reason these data structures should be aligned on UP and thus
converted together.

Signed-off-by: Tejun Heo <tj@kernel.org>
Cc: Mike Frysinger <vapier@gentoo.org>
Cc: Tony Luck <tony.luck@intel.com>
Cc: Andy Grover <andy.grover@oracle.com>
---
I committed the following patch to percpu#for-next git tree.  Please
let me know if something doesn't look right.

 git://git.kernel.org/pub/scm/linux/kernel/git/tj/percpu.git for-next
 http://git.kernel.org/?p=linux/kernel/git/tj/percpu.git;a=shortlog;h=for-next

Thanks.

 arch/blackfin/mm/sram-alloc.c |    6 +++---
 arch/ia64/kernel/smp.c        |    3 ++-
 kernel/sched.c                |    4 ++--
 net/rds/ib_stats.c            |    2 +-
 net/rds/iw_stats.c            |    2 +-
 net/rds/page.c                |    2 +-
 6 files changed, 10 insertions(+), 9 deletions(-)

Index: work/arch/blackfin/mm/sram-alloc.c
===================================================================
--- work.orig/arch/blackfin/mm/sram-alloc.c
+++ work/arch/blackfin/mm/sram-alloc.c
@@ -42,9 +42,9 @@
 #include <asm/mem_map.h>
 #include "blackfin_sram.h"
 
-static DEFINE_PER_CPU(spinlock_t, l1sram_lock) ____cacheline_aligned_in_smp;
-static DEFINE_PER_CPU(spinlock_t, l1_data_sram_lock) ____cacheline_aligned_in_smp;
-static DEFINE_PER_CPU(spinlock_t, l1_inst_sram_lock) ____cacheline_aligned_in_smp;
+static DEFINE_PER_CPU_SHARED_ALIGNED(spinlock_t, l1sram_lock);
+static DEFINE_PER_CPU_SHARED_ALIGNED(spinlock_t, l1_data_sram_lock);
+static DEFINE_PER_CPU_SHARED_ALIGNED(spinlock_t, l1_inst_sram_lock);
 static spinlock_t l2_sram_lock ____cacheline_aligned_in_smp;
 
 /* the data structure for L1 scratchpad and DATA SRAM */
Index: work/arch/ia64/kernel/smp.c
===================================================================
--- work.orig/arch/ia64/kernel/smp.c
+++ work/arch/ia64/kernel/smp.c
@@ -58,7 +58,8 @@ static struct local_tlb_flush_counts {
 	unsigned int count;
 } __attribute__((__aligned__(32))) local_tlb_flush_counts[NR_CPUS];
 
-static DEFINE_PER_CPU(unsigned short [NR_CPUS], shadow_flush_counts) ____cacheline_aligned;
+static DEFINE_PER_CPU_SHARED_ALIGNED(unsigned short [NR_CPUS],
+				     shadow_flush_counts);
 
 #define IPI_CALL_FUNC		0
 #define IPI_CPU_STOP		1
Index: work/kernel/sched.c
===================================================================
--- work.orig/kernel/sched.c
+++ work/kernel/sched.c
@@ -318,12 +318,12 @@ struct task_group root_task_group;
 /* Default task group's sched entity on each cpu */
 static DEFINE_PER_CPU(struct sched_entity, init_sched_entity);
 /* Default task group's cfs_rq on each cpu */
-static DEFINE_PER_CPU(struct cfs_rq, init_cfs_rq) ____cacheline_aligned_in_smp;
+static DEFINE_PER_CPU_SHARED_ALIGNED(struct cfs_rq, init_cfs_rq);
 #endif /* CONFIG_FAIR_GROUP_SCHED */
 
 #ifdef CONFIG_RT_GROUP_SCHED
 static DEFINE_PER_CPU(struct sched_rt_entity, init_sched_rt_entity);
-static DEFINE_PER_CPU(struct rt_rq, init_rt_rq) ____cacheline_aligned_in_smp;
+static DEFINE_PER_CPU_SHARED_ALIGNED(struct rt_rq, init_rt_rq);
 #endif /* CONFIG_RT_GROUP_SCHED */
 #else /* !CONFIG_USER_SCHED */
 #define root_task_group init_task_group
Index: work/net/rds/ib_stats.c
===================================================================
--- work.orig/net/rds/ib_stats.c
+++ work/net/rds/ib_stats.c
@@ -37,7 +37,7 @@
 #include "rds.h"
 #include "ib.h"
 
-DEFINE_PER_CPU(struct rds_ib_statistics, rds_ib_stats) ____cacheline_aligned;
+DEFINE_PER_CPU_SHARED_ALIGNED(struct rds_ib_statistics, rds_ib_stats);
 
 static char *rds_ib_stat_names[] = {
 	"ib_connect_raced",
Index: work/net/rds/iw_stats.c
===================================================================
--- work.orig/net/rds/iw_stats.c
+++ work/net/rds/iw_stats.c
@@ -37,7 +37,7 @@
 #include "rds.h"
 #include "iw.h"
 
-DEFINE_PER_CPU(struct rds_iw_statistics, rds_iw_stats) ____cacheline_aligned;
+DEFINE_PER_CPU_SHARED_ALIGNED(struct rds_iw_statistics, rds_iw_stats);
 
 static char *rds_iw_stat_names[] = {
 	"iw_connect_raced",
Index: work/net/rds/page.c
===================================================================
--- work.orig/net/rds/page.c
+++ work/net/rds/page.c
@@ -39,7 +39,7 @@ struct rds_page_remainder {
 	unsigned long	r_offset;
 };
 
-DEFINE_PER_CPU(struct rds_page_remainder, rds_page_remainders) ____cacheline_aligned;
+DEFINE_PER_CPU_SHARED_ALIGNED(struct rds_page_remainder, rds_page_remainders);
 
 /*
  * returns 0 on success or -errno on failure.

Re: [PATCH] percpu: use DEFINE_PER_CPU_SHARED_ALIGNED()

[Andy Grover]

Ack, thanks! -- Andy

On Jun 18, 2009, at 7:34 PM, Tejun Heo <tj@kernel.org> wrote:

> There are a few places where ___cacheline_aligned* is used with
> DEFINE_PER_CPU().  Use DEFINE_PER_CPU_SHARED_ALIGNED() instead.
>
> DEFINE_PER_CPU_SHARED_ALIGNED() applies alignment only on SMPs.  While
> all other converted places used _in_smp variant or only get compiled
> for SMP, net/rds used unconditional ____cacheline_aligned.  I don't
> see any reason these data structures should be aligned on UP and thus
> converted together.
>
> Signed-off-by: Tejun Heo <tj@kernel.org>
> Cc: Mike Frysinger <vapier@gentoo.org>
> Cc: Tony Luck <tony.luck@intel.com>
> Cc: Andy Grover <andy.grover@oracle.com>
> ---
> I committed the following patch to percpu#for-next git tree.  Please
> let me know if something doesn't look right.
>
> git://git.kernel.org/pub/scm/linux/kernel/git/tj/percpu.git for-next
> http://git.kernel.org/?p=linux/kernel/git/tj/percpu.git;a=shortlog;h=for-next
>
> Thanks.
>
> arch/blackfin/mm/sram-alloc.c |    6 +++---
> arch/ia64/kernel/smp.c        |    3 ++-
> kernel/sched.c                |    4 ++--
> net/rds/ib_stats.c            |    2 +-
> net/rds/iw_stats.c            |    2 +-
> net/rds/page.c                |    2 +-
> 6 files changed, 10 insertions(+), 9 deletions(-)
>
> Index: work/arch/blackfin/mm/sram-alloc.c
> ===================================================================
> --- work.orig/arch/blackfin/mm/sram-alloc.c
> +++ work/arch/blackfin/mm/sram-alloc.c
> @@ -42,9 +42,9 @@
> #include <asm/mem_map.h>
> #include "blackfin_sram.h"
>
> -static DEFINE_PER_CPU(spinlock_t, l1sram_lock)  
> ____cacheline_aligned_in_smp;
> -static DEFINE_PER_CPU(spinlock_t, l1_data_sram_lock)  
> ____cacheline_aligned_in_smp;
> -static DEFINE_PER_CPU(spinlock_t, l1_inst_sram_lock)  
> ____cacheline_aligned_in_smp;
> +static DEFINE_PER_CPU_SHARED_ALIGNED(spinlock_t, l1sram_lock);
> +static DEFINE_PER_CPU_SHARED_ALIGNED(spinlock_t, l1_data_sram_lock);
> +static DEFINE_PER_CPU_SHARED_ALIGNED(spinlock_t, l1_inst_sram_lock);
> static spinlock_t l2_sram_lock ____cacheline_aligned_in_smp;
>
> /* the data structure for L1 scratchpad and DATA SRAM */
> Index: work/arch/ia64/kernel/smp.c
> ===================================================================
> --- work.orig/arch/ia64/kernel/smp.c
> +++ work/arch/ia64/kernel/smp.c
> @@ -58,7 +58,8 @@ static struct local_tlb_flush_counts {
>    unsigned int count;
> } __attribute__((__aligned__(32))) local_tlb_flush_counts[NR_CPUS];
>
> -static DEFINE_PER_CPU(unsigned short [NR_CPUS],  
> shadow_flush_counts) ____cacheline_aligned;
> +static DEFINE_PER_CPU_SHARED_ALIGNED(unsigned short [NR_CPUS],
> +                     shadow_flush_counts);
>
> #define IPI_CALL_FUNC        0
> #define IPI_CPU_STOP        1
> Index: work/kernel/sched.c
> ===================================================================
> --- work.orig/kernel/sched.c
> +++ work/kernel/sched.c
> @@ -318,12 +318,12 @@ struct task_group root_task_group;
> /* Default task group's sched entity on each cpu */
> static DEFINE_PER_CPU(struct sched_entity, init_sched_entity);
> /* Default task group's cfs_rq on each cpu */
> -static DEFINE_PER_CPU(struct cfs_rq, init_cfs_rq)  
> ____cacheline_aligned_in_smp;
> +static DEFINE_PER_CPU_SHARED_ALIGNED(struct cfs_rq, init_cfs_rq);
> #endif /* CONFIG_FAIR_GROUP_SCHED */
>
> #ifdef CONFIG_RT_GROUP_SCHED
> static DEFINE_PER_CPU(struct sched_rt_entity, init_sched_rt_entity);
> -static DEFINE_PER_CPU(struct rt_rq, init_rt_rq)  
> ____cacheline_aligned_in_smp;
> +static DEFINE_PER_CPU_SHARED_ALIGNED(struct rt_rq, init_rt_rq);
> #endif /* CONFIG_RT_GROUP_SCHED */
> #else /* !CONFIG_USER_SCHED */
> #define root_task_group init_task_group
> Index: work/net/rds/ib_stats.c
> ===================================================================
> --- work.orig/net/rds/ib_stats.c
> +++ work/net/rds/ib_stats.c
> @@ -37,7 +37,7 @@
> #include "rds.h"
> #include "ib.h"
>
> -DEFINE_PER_CPU(struct rds_ib_statistics, rds_ib_stats)  
> ____cacheline_aligned;
> +DEFINE_PER_CPU_SHARED_ALIGNED(struct rds_ib_statistics,  
> rds_ib_stats);
>
> static char *rds_ib_stat_names[] = {
>    "ib_connect_raced",
> Index: work/net/rds/iw_stats.c
> ===================================================================
> --- work.orig/net/rds/iw_stats.c
> +++ work/net/rds/iw_stats.c
> @@ -37,7 +37,7 @@
> #include "rds.h"
> #include "iw.h"
>
> -DEFINE_PER_CPU(struct rds_iw_statistics, rds_iw_stats)  
> ____cacheline_aligned;
> +DEFINE_PER_CPU_SHARED_ALIGNED(struct rds_iw_statistics,  
> rds_iw_stats);
>
> static char *rds_iw_stat_names[] = {
>    "iw_connect_raced",
> Index: work/net/rds/page.c
> ===================================================================
> --- work.orig/net/rds/page.c
> +++ work/net/rds/page.c
> @@ -39,7 +39,7 @@ struct rds_page_remainder {
>    unsigned long    r_offset;
> };
>
> -DEFINE_PER_CPU(struct rds_page_remainder, rds_page_remainders)  
> ____cacheline_aligned;
> +DEFINE_PER_CPU_SHARED_ALIGNED(struct rds_page_remainder,  
> rds_page_remainders);
>
> /*
>  * returns 0 on success or -errno on failure.