x86/percpu: Use C for percpu read/write accessors

The percpu code mostly uses inline assembly. Using segment qualifiers
allows to use C code instead, which enables the compiler to perform
various optimizations (e.g. propagation of memory arguments). Convert
percpu read and write accessors to C code, so the memory argument can
be propagated to the instruction that uses this argument.

Some examples of propagations:

a) into sign/zero extensions:

the code improves from:

    65 8a 05 00 00 00 00    mov    %gs:0x0(%rip),%al
    0f b6 c0                movzbl %al,%eax

to:

    65 0f b6 05 00 00 00    movzbl %gs:0x0(%rip),%eax
    00

and in a similar way for:

    movzbl %gs:0x0(%rip),%edx
    movzwl %gs:0x0(%rip),%esi
    movzbl %gs:0x78(%rbx),%eax

    movslq %gs:0x0(%rip),%rdx
    movslq %gs:(%rdi),%rbx

b) into compares:

the code improves from:

    65 8b 05 00 00 00 00    mov    %gs:0x0(%rip),%eax
    a9 00 00 0f 00          test   $0xf0000,%eax

to:

    65 f7 05 00 00 00 00    testl  $0xf0000,%gs:0x0(%rip)
    00 00 0f 00

and in a similar way for:

    testl  $0xf0000,%gs:0x0(%rip)
    testb  $0x1,%gs:0x0(%rip)
    testl  $0xff00,%gs:0x0(%rip)

    cmpb   $0x0,%gs:0x0(%rip)
    cmp    %gs:0x0(%rip),%r14d
    cmpw   $0x8,%gs:0x0(%rip)
    cmpb   $0x0,%gs:(%rax)

c) into other insns:

the code improves from:

   1a355:	83 fa ff             	cmp    $0xffffffff,%edx
   1a358:	75 07                	jne    1a361 <...>
   1a35a:	65 8b 15 00 00 00 00 	mov    %gs:0x0(%rip),%edx
   1a361:

to:

   1a35a:	83 fa ff             	cmp    $0xffffffff,%edx
   1a35d:	65 0f 44 15 00 00 00 	cmove  %gs:0x0(%rip),%edx
   1a364:	00

The above propagations result in the following code size
improvements for current mainline kernel (with the default config),
compiled with:

   # gcc (GCC) 12.3.1 20230508 (Red Hat 12.3.1-1)

   text            data     bss    dec             filename
   25508862        4386540  808388 30703790        vmlinux-vanilla.o
   25500922        4386532  808388 30695842        vmlinux-new.o

Co-developed-by: Nadav Amit <namit@vmware.com>
Signed-off-by: Nadav Amit <namit@vmware.com>
Signed-off-by: Uros Bizjak <ubizjak@gmail.com>
Signed-off-by: Ingo Molnar <mingo@kernel.org>
Cc: Andy Lutomirski <luto@kernel.org>
Cc: Brian Gerst <brgerst@gmail.com>
Cc: Denys Vlasenko <dvlasenk@redhat.com>
Cc: H. Peter Anvin <hpa@zytor.com>
Cc: Linus Torvalds <torvalds@linux-foundation.org>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Thomas Gleixner <tglx@linutronix.de>
Cc: Josh Poimboeuf <jpoimboe@redhat.com>
Link: https://lore.kernel.org/r/20231004192404.31733-1-ubizjak@gmail.com

1 files changed, 54 insertions, 11 deletions

diff --git a/arch/x86/include/asm/percpu.h b/arch/x86/include/asm/percpu.h
index da451202a1b9..60ea7755c0fe 100644
--- a/arch/x86/include/asm/percpu.h
+++ b/arch/x86/include/asm/percpu.h
@@ -400,13 +400,66 @@ do {									\
 #define this_cpu_read_stable_8(pcp)	percpu_stable_op(8, "mov", pcp)
 #define this_cpu_read_stable(pcp)	__pcpu_size_call_return(this_cpu_read_stable_, pcp)
 
+#ifdef CONFIG_USE_X86_SEG_SUPPORT
+
+#define __raw_cpu_read(qual, pcp)					\
+({									\
+	*(qual __my_cpu_type(pcp) *)__my_cpu_ptr(&(pcp));		\
+})
+
+#define __raw_cpu_write(qual, pcp, val)					\
+do {									\
+	*(qual __my_cpu_type(pcp) *)__my_cpu_ptr(&(pcp)) = (val);	\
+} while (0)
+
+#define raw_cpu_read_1(pcp)		__raw_cpu_read(, pcp)
+#define raw_cpu_read_2(pcp)		__raw_cpu_read(, pcp)
+#define raw_cpu_read_4(pcp)		__raw_cpu_read(, pcp)
+#define raw_cpu_write_1(pcp, val)	__raw_cpu_write(, pcp, val)
+#define raw_cpu_write_2(pcp, val)	__raw_cpu_write(, pcp, val)
+#define raw_cpu_write_4(pcp, val)	__raw_cpu_write(, pcp, val)
+
+#define this_cpu_read_1(pcp)		__raw_cpu_read(volatile, pcp)
+#define this_cpu_read_2(pcp)		__raw_cpu_read(volatile, pcp)
+#define this_cpu_read_4(pcp)		__raw_cpu_read(volatile, pcp)
+#define this_cpu_write_1(pcp, val)	__raw_cpu_write(volatile, pcp, val)
+#define this_cpu_write_2(pcp, val)	__raw_cpu_write(volatile, pcp, val)
+#define this_cpu_write_4(pcp, val)	__raw_cpu_write(volatile, pcp, val)
+
+#ifdef CONFIG_X86_64
+#define raw_cpu_read_8(pcp)		__raw_cpu_read(, pcp)
+#define raw_cpu_write_8(pcp, val)	__raw_cpu_write(, pcp, val)
+
+#define this_cpu_read_8(pcp)		__raw_cpu_read(volatile, pcp)
+#define this_cpu_write_8(pcp, val)	__raw_cpu_write(volatile, pcp, val)
+#endif
+
+#else /* CONFIG_USE_X86_SEG_SUPPORT */
+
 #define raw_cpu_read_1(pcp)		percpu_from_op(1, , "mov", pcp)
 #define raw_cpu_read_2(pcp)		percpu_from_op(2, , "mov", pcp)
 #define raw_cpu_read_4(pcp)		percpu_from_op(4, , "mov", pcp)
-
 #define raw_cpu_write_1(pcp, val)	percpu_to_op(1, , "mov", (pcp), val)
 #define raw_cpu_write_2(pcp, val)	percpu_to_op(2, , "mov", (pcp), val)
 #define raw_cpu_write_4(pcp, val)	percpu_to_op(4, , "mov", (pcp), val)
+
+#define this_cpu_read_1(pcp)		percpu_from_op(1, volatile, "mov", pcp)
+#define this_cpu_read_2(pcp)		percpu_from_op(2, volatile, "mov", pcp)
+#define this_cpu_read_4(pcp)		percpu_from_op(4, volatile, "mov", pcp)
+#define this_cpu_write_1(pcp, val)	percpu_to_op(1, volatile, "mov", (pcp), val)
+#define this_cpu_write_2(pcp, val)	percpu_to_op(2, volatile, "mov", (pcp), val)
+#define this_cpu_write_4(pcp, val)	percpu_to_op(4, volatile, "mov", (pcp), val)
+
+#ifdef CONFIG_X86_64
+#define raw_cpu_read_8(pcp)		percpu_from_op(8, , "mov", pcp)
+#define raw_cpu_write_8(pcp, val)	percpu_to_op(8, , "mov", (pcp), val)
+
+#define this_cpu_read_8(pcp)		percpu_from_op(8, volatile, "mov", pcp)
+#define this_cpu_write_8(pcp, val)	percpu_to_op(8, volatile, "mov", (pcp), val)
+#endif
+
+#endif /* CONFIG_USE_X86_SEG_SUPPORT */
+
 #define raw_cpu_add_1(pcp, val)		percpu_add_op(1, , (pcp), val)
 #define raw_cpu_add_2(pcp, val)		percpu_add_op(2, , (pcp), val)
 #define raw_cpu_add_4(pcp, val)		percpu_add_op(4, , (pcp), val)
@@ -432,12 +485,6 @@ do {									\
 #define raw_cpu_xchg_2(pcp, val)	raw_percpu_xchg_op(pcp, val)
 #define raw_cpu_xchg_4(pcp, val)	raw_percpu_xchg_op(pcp, val)
 
-#define this_cpu_read_1(pcp)		percpu_from_op(1, volatile, "mov", pcp)
-#define this_cpu_read_2(pcp)		percpu_from_op(2, volatile, "mov", pcp)
-#define this_cpu_read_4(pcp)		percpu_from_op(4, volatile, "mov", pcp)
-#define this_cpu_write_1(pcp, val)	percpu_to_op(1, volatile, "mov", (pcp), val)
-#define this_cpu_write_2(pcp, val)	percpu_to_op(2, volatile, "mov", (pcp), val)
-#define this_cpu_write_4(pcp, val)	percpu_to_op(4, volatile, "mov", (pcp), val)
 #define this_cpu_add_1(pcp, val)	percpu_add_op(1, volatile, (pcp), val)
 #define this_cpu_add_2(pcp, val)	percpu_add_op(2, volatile, (pcp), val)
 #define this_cpu_add_4(pcp, val)	percpu_add_op(4, volatile, (pcp), val)
@@ -476,8 +523,6 @@ do {									\
  * 32 bit must fall back to generic operations.
  */
 #ifdef CONFIG_X86_64
-#define raw_cpu_read_8(pcp)			percpu_from_op(8, , "mov", pcp)
-#define raw_cpu_write_8(pcp, val)		percpu_to_op(8, , "mov", (pcp), val)
 #define raw_cpu_add_8(pcp, val)			percpu_add_op(8, , (pcp), val)
 #define raw_cpu_and_8(pcp, val)			percpu_to_op(8, , "and", (pcp), val)
 #define raw_cpu_or_8(pcp, val)			percpu_to_op(8, , "or", (pcp), val)
@@ -486,8 +531,6 @@ do {									\
 #define raw_cpu_cmpxchg_8(pcp, oval, nval)	percpu_cmpxchg_op(8, , pcp, oval, nval)
 #define raw_cpu_try_cmpxchg_8(pcp, ovalp, nval)	percpu_try_cmpxchg_op(8, , pcp, ovalp, nval)
 
-#define this_cpu_read_8(pcp)			percpu_from_op(8, volatile, "mov", pcp)
-#define this_cpu_write_8(pcp, val)		percpu_to_op(8, volatile, "mov", (pcp), val)
 #define this_cpu_add_8(pcp, val)		percpu_add_op(8, volatile, (pcp), val)
 #define this_cpu_and_8(pcp, val)		percpu_to_op(8, volatile, "and", (pcp), val)
 #define this_cpu_or_8(pcp, val)			percpu_to_op(8, volatile, "or", (pcp), val)