[PATCH 5.2 071/131] bpf: Disable GCC -fgcse optimization for ___bpf_prog_run()

[Greg Kroah-Hartman]

[ Upstream commit 3193c0836f203a91bef96d88c64cccf0be090d9c ]

On x86-64, with CONFIG_RETPOLINE=n, GCC's "global common subexpression
elimination" optimization results in ___bpf_prog_run()'s jumptable code
changing from this:

	select_insn:
		jmp *jumptable(, %rax, 8)
		...
	ALU64_ADD_X:
		...
		jmp *jumptable(, %rax, 8)
	ALU_ADD_X:
		...
		jmp *jumptable(, %rax, 8)

to this:

	select_insn:
		mov jumptable, %r12
		jmp *(%r12, %rax, 8)
		...
	ALU64_ADD_X:
		...
		jmp *(%r12, %rax, 8)
	ALU_ADD_X:
		...
		jmp *(%r12, %rax, 8)

The jumptable address is placed in a register once, at the beginning of
the function.  The function execution can then go through multiple
indirect jumps which rely on that same register value.  This has a few
issues:

1) Objtool isn't smart enough to be able to track such a register value
   across multiple recursive indirect jumps through the jump table.

2) With CONFIG_RETPOLINE enabled, this optimization actually results in
   a small slowdown.  I measured a ~4.7% slowdown in the test_bpf
   "tcpdump port 22" selftest.

   This slowdown is actually predicted by the GCC manual:

     Note: When compiling a program using computed gotos, a GCC
     extension, you may get better run-time performance if you
     disable the global common subexpression elimination pass by
     adding -fno-gcse to the command line.

So just disable the optimization for this function.

Fixes: e55a73251da3 ("bpf: Fix ORC unwinding in non-JIT BPF code")
Reported-by: Randy Dunlap <rdunlap@xxxxxxxxxxxxx>
Signed-off-by: Josh Poimboeuf <jpoimboe@xxxxxxxxxx>
Signed-off-by: Thomas Gleixner <tglx@xxxxxxxxxxxxx>
Acked-by: Alexei Starovoitov <ast@xxxxxxxxxx>
Acked-by: Peter Zijlstra (Intel) <peterz@xxxxxxxxxxxxx>
Link: https://lkml.kernel.org/r/30c3ca29ba037afcbd860a8672eef0021addf9fe.1563413318.git.jpoimboe@xxxxxxxxxx
Signed-off-by: Sasha Levin <sashal@xxxxxxxxxx>
---
 include/linux/compiler-gcc.h   | 2 ++
 include/linux/compiler_types.h | 4 ++++
 kernel/bpf/core.c              | 2 +-
 3 files changed, 7 insertions(+), 1 deletion(-)

diff --git a/include/linux/compiler-gcc.h b/include/linux/compiler-gcc.h
index e8579412ad214..d7ee4c6bad482 100644
--- a/include/linux/compiler-gcc.h
+++ b/include/linux/compiler-gcc.h
@@ -170,3 +170,5 @@
 #else
 #define __diag_GCC_8(s)
 #endif
+
+#define __no_fgcse __attribute__((optimize("-fno-gcse")))
diff --git a/include/linux/compiler_types.h b/include/linux/compiler_types.h
index 19e58b9138a04..0454d82f8bd82 100644
--- a/include/linux/compiler_types.h
+++ b/include/linux/compiler_types.h
@@ -187,6 +187,10 @@ struct ftrace_likely_data {
 #define asm_volatile_goto(x...) asm goto(x)
 #endif
 
+#ifndef __no_fgcse
+# define __no_fgcse
+#endif
+
 /* Are two types/vars the same type (ignoring qualifiers)? */
 #define __same_type(a, b) __builtin_types_compatible_p(typeof(a), typeof(b))
 
diff --git a/kernel/bpf/core.c b/kernel/bpf/core.c
index f2148db91439e..ceee0730fba58 100644
--- a/kernel/bpf/core.c
+++ b/kernel/bpf/core.c
@@ -1295,7 +1295,7 @@ bool bpf_opcode_in_insntable(u8 code)
  *
  * Decode and execute eBPF instructions.
  */
-static u64 ___bpf_prog_run(u64 *regs, const struct bpf_insn *insn, u64 *stack)
+static u64 __no_fgcse ___bpf_prog_run(u64 *regs, const struct bpf_insn *insn, u64 *stack)
 {
 #define BPF_INSN_2_LBL(x, y)    [BPF_##x | BPF_##y] = &&x##_##y
 #define BPF_INSN_3_LBL(x, y, z) [BPF_##x | BPF_##y | BPF_##z] = &&x##_##y##_##z
-- 
2.20.1