@@ -91,12 +91,14 @@ static __always_inline bool __try_cmpxchg64_local(volatile u64 *ptr, u64 *oldp,
union __u64_halves o = { .full = (_old), }, \
n = { .full = (_new), }; \
\
- asm volatile(ALTERNATIVE(_lock_loc \
- "call cmpxchg8b_emu", \
- _lock "cmpxchg8b %a[ptr]", X86_FEATURE_CX8) \
- : ALT_OUTPUT_SP("+a" (o.low), "+d" (o.high)) \
- : "b" (n.low), "c" (n.high), [ptr] "S" (_ptr) \
- : "memory"); \
+ asm_inline volatile( \
+ ALTERNATIVE(_lock_loc \
+ "call cmpxchg8b_emu", \
+ _lock "cmpxchg8b %a[ptr]", X86_FEATURE_CX8) \
+ : ALT_OUTPUT_SP("+a" (o.low), "+d" (o.high)) \
+ : "b" (n.low), "c" (n.high), \
+ [ptr] "S" (_ptr) \
+ : "memory"); \
\
o.full; \
})
@@ -119,14 +121,16 @@ static __always_inline u64 arch_cmpxchg64_local(volatile u64 *ptr, u64 old, u64
n = { .full = (_new), }; \
bool ret; \
\
- asm volatile(ALTERNATIVE(_lock_loc \
- "call cmpxchg8b_emu", \
- _lock "cmpxchg8b %a[ptr]", X86_FEATURE_CX8) \
- CC_SET(e) \
- : ALT_OUTPUT_SP(CC_OUT(e) (ret), \
- "+a" (o.low), "+d" (o.high)) \
- : "b" (n.low), "c" (n.high), [ptr] "S" (_ptr) \
- : "memory"); \
+ asm_inline volatile( \
+ ALTERNATIVE(_lock_loc \
+ "call cmpxchg8b_emu", \
+ _lock "cmpxchg8b %a[ptr]", X86_FEATURE_CX8) \
+ CC_SET(e) \
+ : ALT_OUTPUT_SP(CC_OUT(e) (ret), \
+ "+a" (o.low), "+d" (o.high)) \
+ : "b" (n.low), "c" (n.high), \
+ [ptr] "S" (_ptr) \
+ : "memory"); \
\
if (unlikely(!ret)) \
*(_oldp) = o.full; \
@@ -348,15 +348,14 @@ do { \
old__.var = _oval; \
new__.var = _nval; \
\
- asm qual (ALTERNATIVE("call this_cpu_cmpxchg8b_emu", \
- "cmpxchg8b " __percpu_arg([var]), X86_FEATURE_CX8) \
- : ALT_OUTPUT_SP([var] "+m" (__my_cpu_var(_var)), \
- "+a" (old__.low), \
- "+d" (old__.high)) \
- : "b" (new__.low), \
- "c" (new__.high), \
- "S" (&(_var)) \
- : "memory"); \
+ asm_inline qual ( \
+ ALTERNATIVE("call this_cpu_cmpxchg8b_emu", \
+ "cmpxchg8b " __percpu_arg([var]), X86_FEATURE_CX8) \
+ : ALT_OUTPUT_SP([var] "+m" (__my_cpu_var(_var)), \
+ "+a" (old__.low), "+d" (old__.high)) \
+ : "b" (new__.low), "c" (new__.high), \
+ "S" (&(_var)) \
+ : "memory"); \
\
old__.var; \
})
@@ -378,17 +377,16 @@ do { \
old__.var = *_oval; \
new__.var = _nval; \
\
- asm qual (ALTERNATIVE("call this_cpu_cmpxchg8b_emu", \
- "cmpxchg8b " __percpu_arg([var]), X86_FEATURE_CX8) \
- CC_SET(z) \
- : ALT_OUTPUT_SP(CC_OUT(z) (success), \
- [var] "+m" (__my_cpu_var(_var)), \
- "+a" (old__.low), \
- "+d" (old__.high)) \
- : "b" (new__.low), \
- "c" (new__.high), \
- "S" (&(_var)) \
- : "memory"); \
+ asm_inline qual ( \
+ ALTERNATIVE("call this_cpu_cmpxchg8b_emu", \
+ "cmpxchg8b " __percpu_arg([var]), X86_FEATURE_CX8) \
+ CC_SET(z) \
+ : ALT_OUTPUT_SP(CC_OUT(z) (success), \
+ [var] "+m" (__my_cpu_var(_var)), \
+ "+a" (old__.low), "+d" (old__.high)) \
+ : "b" (new__.low), "c" (new__.high), \
+ "S" (&(_var)) \
+ : "memory"); \
if (unlikely(!success)) \
*_oval = old__.var; \
\
@@ -419,15 +417,14 @@ do { \
old__.var = _oval; \
new__.var = _nval; \
\
- asm qual (ALTERNATIVE("call this_cpu_cmpxchg16b_emu", \
- "cmpxchg16b " __percpu_arg([var]), X86_FEATURE_CX16) \
- : ALT_OUTPUT_SP([var] "+m" (__my_cpu_var(_var)), \
- "+a" (old__.low), \
- "+d" (old__.high)) \
- : "b" (new__.low), \
- "c" (new__.high), \
- "S" (&(_var)) \
- : "memory"); \
+ asm_inline qual ( \
+ ALTERNATIVE("call this_cpu_cmpxchg16b_emu", \
+ "cmpxchg16b " __percpu_arg([var]), X86_FEATURE_CX16) \
+ : ALT_OUTPUT_SP([var] "+m" (__my_cpu_var(_var)), \
+ "+a" (old__.low), "+d" (old__.high)) \
+ : "b" (new__.low), "c" (new__.high), \
+ "S" (&(_var)) \
+ : "memory"); \
\
old__.var; \
})
@@ -449,19 +446,19 @@ do { \
old__.var = *_oval; \
new__.var = _nval; \
\
- asm qual (ALTERNATIVE("call this_cpu_cmpxchg16b_emu", \
- "cmpxchg16b " __percpu_arg([var]), X86_FEATURE_CX16) \
- CC_SET(z) \
- : ALT_OUTPUT_SP(CC_OUT(z) (success), \
- [var] "+m" (__my_cpu_var(_var)), \
- "+a" (old__.low), \
- "+d" (old__.high)) \
- : "b" (new__.low), \
- "c" (new__.high), \
- "S" (&(_var)) \
- : "memory"); \
+ asm_inline qual ( \
+ ALTERNATIVE("call this_cpu_cmpxchg16b_emu", \
+ "cmpxchg16b " __percpu_arg([var]), X86_FEATURE_CX16) \
+ CC_SET(z) \
+ : ALT_OUTPUT_SP(CC_OUT(z) (success), \
+ [var] "+m" (__my_cpu_var(_var)), \
+ "+a" (old__.low), "+d" (old__.high)) \
+ : "b" (new__.low), "c" (new__.high), \
+ "S" (&(_var)) \
+ : "memory"); \
if (unlikely(!success)) \
*_oval = old__.var; \
+ \
likely(success); \
})
According to [1], the usage of asm pseudo directives in the asm template can confuse the compiler to wrongly estimate the size of the generated code. ALTERNATIVE macro expands to several asm pseudo directives, so its usage in {,try_}cmpxchg{64,128} causes instruction length estimate to fail by an order of magnitude (the specially instrumented compiler reports the estimated length of these asm templates to be more than 20 instructions long). This wrong estimate further causes unoptimal inlining decisions, unoptimal instruction scheduling and unoptimal code block alignments for functions that use these locking primitives. Use asm_inline [2], a feature that makes GCC pretend some inline assembler code is tiny (while it would think it is huge), instead of just asm. For code size estimation, the size of the asm is then taken as the minimum size of one instruction, ignoring how many instructions compiler thinks it is. The effect of this patch on x86_64 target is minor, since 128-bit functions are rarely used on this target. The code size of the resulting defconfig object file stays the same: text data bss dec hex filename 27456612 4638523 814148 32909283 1f627e3 vmlinux-old.o 27456612 4638523 814148 32909283 1f627e3 vmlinux-new.o but the patch has minor effect on code layout due to the different scheduling decisions in functions containing changed macros. There is no effect on x64_32 target, the code size of the resulting defconfig object file and the code layout stays the same: text data bss dec hex filename 18883870 2679275 1707916 23271061 1631695 vmlinux-old.o 18883870 2679275 1707916 23271061 1631695 vmlinux-new.o [1] https://gcc.gnu.org/onlinedocs/gcc/Size-of-an-asm.html [2] https://gcc.gnu.org/pipermail/gcc-patches/2018-December/512349.html Signed-off-by: Uros Bizjak <ubizjak@gmail.com> Cc: Thomas Gleixner <tglx@linutronix.de> Cc: Ingo Molnar <mingo@kernel.org> Cc: Borislav Petkov <bp@alien8.de> Cc: Dave Hansen <dave.hansen@linux.intel.com> Cc: "H. Peter Anvin" <hpa@zytor.com> Cc: Dennis Zhou <dennis@kernel.org> Cc: Tejun Heo <tj@kernel.org> Cc: Christoph Lameter <cl@linux.com> Cc: "Peter Zijlstra (Intel)" <peterz@infradead.org> --- v2: Expand commit message with the explanation of asm_inline the explanation of benefits of the patch and with some code size measurements. --- arch/x86/include/asm/cmpxchg_32.h | 32 +++++++------ arch/x86/include/asm/percpu.h | 77 +++++++++++++++---------------- 2 files changed, 55 insertions(+), 54 deletions(-)