[PATCH 1/3] x86: Add 'percpu_read_stable()' interface for cacheableaccesses

From: Tejun Heo
Date: Mon Aug 03 2009 - 01:09:30 EST


From: Linus Tolvards <torvalds@xxxxxxxxxxxxxxxxxxxx>

This is very useful for some common things like 'get_current()' and
'get_thread_info()', which can be used multiple times in a function, and
where the result is cacheable.

tj: added comment explaining the difference between percpu_read() and
percpu_read_stable()

Signed-off-by: Linus Torvalds <torvalds@xxxxxxxxxxxxxxxxxxxx>
Signed-off-by: Tejun Heo <tj@xxxxxxxxxx>
---
Three patches queued in my pending tree.

The second patch is a possible bug I've spotted while prepping the
third one. The last one puts current_task and kernel_stack into the
same cacheline as suggested by Linus. I'll hold for a few days for
response and then push them to linux-next.

Ingo, these patches might as well go through x86 tree. If you think
that would be better, please let me know.

Thanks.

arch/x86/include/asm/current.h | 2 +-
arch/x86/include/asm/percpu.h | 22 ++++++++++++++++------
arch/x86/include/asm/thread_info.h | 2 +-
3 files changed, 18 insertions(+), 8 deletions(-)

diff --git a/arch/x86/include/asm/current.h b/arch/x86/include/asm/current.h
index c68c361..4d447b7 100644
--- a/arch/x86/include/asm/current.h
+++ b/arch/x86/include/asm/current.h
@@ -11,7 +11,7 @@ DECLARE_PER_CPU(struct task_struct *, current_task);

static __always_inline struct task_struct *get_current(void)
{
- return percpu_read(current_task);
+ return percpu_read_stable(current_task);
}

#define current get_current()
diff --git a/arch/x86/include/asm/percpu.h b/arch/x86/include/asm/percpu.h
index a18c038..b421780 100644
--- a/arch/x86/include/asm/percpu.h
+++ b/arch/x86/include/asm/percpu.h
@@ -104,36 +104,46 @@ do { \
} \
} while (0)

-#define percpu_from_op(op, var) \
+#define percpu_from_op(op, var, constraint) \
({ \
typeof(var) ret__; \
switch (sizeof(var)) { \
case 1: \
asm(op "b "__percpu_arg(1)",%0" \
: "=q" (ret__) \
- : "m" (var)); \
+ : constraint); \
break; \
case 2: \
asm(op "w "__percpu_arg(1)",%0" \
: "=r" (ret__) \
- : "m" (var)); \
+ : constraint); \
break; \
case 4: \
asm(op "l "__percpu_arg(1)",%0" \
: "=r" (ret__) \
- : "m" (var)); \
+ : constraint); \
break; \
case 8: \
asm(op "q "__percpu_arg(1)",%0" \
: "=r" (ret__) \
- : "m" (var)); \
+ : constraint); \
break; \
default: __bad_percpu_size(); \
} \
ret__; \
})

-#define percpu_read(var) percpu_from_op("mov", per_cpu__##var)
+/*
+ * percpu_read() makes gcc load the percpu variable every time it is
+ * accessed while percpu_read_stable() allows the value to be cached.
+ * percpu_read_stable() is more efficient and can be used if its value
+ * is guaranteed to be valid across cpus. The current users include
+ * get_current() and get_thread_info() both of which are actually
+ * per-thread variables implemented as per-cpu variables and thus
+ * stable for the duration of the respective task.
+ */
+#define percpu_read(var) percpu_from_op("mov", per_cpu__##var,"m" (per_cpu__##var))
+#define percpu_read_stable(var) percpu_from_op("mov", per_cpu__##var,"p" (&per_cpu__##var))
#define percpu_write(var, val) percpu_to_op("mov", per_cpu__##var, val)
#define percpu_add(var, val) percpu_to_op("add", per_cpu__##var, val)
#define percpu_sub(var, val) percpu_to_op("sub", per_cpu__##var, val)
diff --git a/arch/x86/include/asm/thread_info.h b/arch/x86/include/asm/thread_info.h
index b078352..9fee589 100644
--- a/arch/x86/include/asm/thread_info.h
+++ b/arch/x86/include/asm/thread_info.h
@@ -213,7 +213,7 @@ DECLARE_PER_CPU(unsigned long, kernel_stack);
static inline struct thread_info *current_thread_info(void)
{
struct thread_info *ti;
- ti = (void *)(percpu_read(kernel_stack) +
+ ti = (void *)(percpu_read_stable(kernel_stack) +
KERNEL_STACK_OFFSET - THREAD_SIZE);
return ti;
}
--
1.6.0.2

--
To unsubscribe from this list: send the line "unsubscribe linux-kernel" in
the body of a message to majordomo@xxxxxxxxxxxxxxx
More majordomo info at http://vger.kernel.org/majordomo-info.html
Please read the FAQ at http://www.tux.org/lkml/