aboutsummaryrefslogtreecommitdiffstats
path: root/arch/x86/include/asm
diff options
context:
space:
mode:
authorLinus Torvalds <torvalds@linux-foundation.org>2009-09-14 08:01:28 -0700
committerLinus Torvalds <torvalds@linux-foundation.org>2009-09-14 08:01:28 -0700
commit55e0715f612f19b44c17497929091df2f3357e5d (patch)
tree31e139ebb4fcd98357b3af7af6c4becb41fa9563 /arch/x86/include/asm
parentMerge branch 'x86-mm-for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/linux-2.6-tip (diff)
parentx86, percpu: Collect hot percpu variables into one cacheline (diff)
downloadlinux-dev-55e0715f612f19b44c17497929091df2f3357e5d.tar.xz
linux-dev-55e0715f612f19b44c17497929091df2f3357e5d.zip
Merge branch 'x86-percpu-for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/linux-2.6-tip
* 'x86-percpu-for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/linux-2.6-tip: x86, percpu: Collect hot percpu variables into one cacheline x86, percpu: Fix DECLARE/DEFINE_PER_CPU_PAGE_ALIGNED() x86, percpu: Add 'percpu_read_stable()' interface for cacheable accesses
Diffstat (limited to 'arch/x86/include/asm')
-rw-r--r--arch/x86/include/asm/current.h2
-rw-r--r--arch/x86/include/asm/percpu.h26
-rw-r--r--arch/x86/include/asm/thread_info.h2
3 files changed, 21 insertions, 9 deletions
diff --git a/arch/x86/include/asm/current.h b/arch/x86/include/asm/current.h
index c68c361697e1..4d447b732d82 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 103f1ddb0d85..04eacefcfd26 100644
--- a/arch/x86/include/asm/percpu.h
+++ b/arch/x86/include/asm/percpu.h
@@ -49,7 +49,7 @@
#define __percpu_arg(x) "%%"__stringify(__percpu_seg)":%P" #x
#define __my_cpu_offset percpu_read(this_cpu_off)
#else
-#define __percpu_arg(x) "%" #x
+#define __percpu_arg(x) "%P" #x
#endif
/*
@@ -104,36 +104,48 @@ 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 6f7786aea4fc..d27d0a2fec4c 100644
--- a/arch/x86/include/asm/thread_info.h
+++ b/arch/x86/include/asm/thread_info.h
@@ -214,7 +214,7 @@ 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;
}