From 8fd4ddda2f49a66bf5dd3d0c01966c4b1971308b Mon Sep 17 00:00:00 2001 From: Christophe Leroy Date: Mon, 14 Mar 2022 12:49:36 +0100 Subject: static_call: Don't make __static_call_return0 static System.map shows that vmlinux contains several instances of __static_call_return0(): c0004fc0 t __static_call_return0 c0011518 t __static_call_return0 c00d8160 t __static_call_return0 arch_static_call_transform() uses the middle one to check whether we are setting a call to __static_call_return0 or not: c0011520 : c0011520: 3d 20 c0 01 lis r9,-16383 <== r9 = 0xc001 << 16 c0011524: 39 29 15 18 addi r9,r9,5400 <== r9 += 0x1518 c0011528: 7c 05 48 00 cmpw r5,r9 <== r9 has value 0xc0011518 here So if static_call_update() is called with one of the other instances of __static_call_return0(), arch_static_call_transform() won't recognise it. In order to work properly, global single instance of __static_call_return0() is required. Fixes: 3f2a8fc4b15d ("static_call/x86: Add __static_call_return0()") Signed-off-by: Christophe Leroy Signed-off-by: Peter Zijlstra (Intel) Acked-by: Josh Poimboeuf Link: https://lkml.kernel.org/r/30821468a0e7d28251954b578e5051dc09300d04.1647258493.git.christophe.leroy@csgroup.eu --- include/linux/static_call.h | 5 +---- 1 file changed, 1 insertion(+), 4 deletions(-) (limited to 'include/linux/static_call.h') diff --git a/include/linux/static_call.h b/include/linux/static_call.h index 3e56a9751c06..fcc5b48989b3 100644 --- a/include/linux/static_call.h +++ b/include/linux/static_call.h @@ -248,10 +248,7 @@ static inline int static_call_text_reserved(void *start, void *end) return 0; } -static inline long __static_call_return0(void) -{ - return 0; -} +extern long __static_call_return0(void); #define EXPORT_STATIC_CALL(name) \ EXPORT_SYMBOL(STATIC_CALL_KEY(name)); \ -- cgit v1.2.3 From 5517d500829c683a358a8de04ecb2e28af629ae5 Mon Sep 17 00:00:00 2001 From: Christophe Leroy Date: Mon, 14 Mar 2022 11:27:35 +0100 Subject: static_call: Properly initialise DEFINE_STATIC_CALL_RET0() When a static call is updated with __static_call_return0() as target, arch_static_call_transform() set it to use an optimised set of instructions which are meant to lay in the same cacheline. But when initialising a static call with DEFINE_STATIC_CALL_RET0(), we get a branch to the real __static_call_return0() function instead of getting the optimised setup: c00d8120 <__SCT__perf_snapshot_branch_stack>: c00d8120: 4b ff ff f4 b c00d8114 <__static_call_return0> c00d8124: 3d 80 c0 0e lis r12,-16370 c00d8128: 81 8c 81 3c lwz r12,-32452(r12) c00d812c: 7d 89 03 a6 mtctr r12 c00d8130: 4e 80 04 20 bctr c00d8134: 38 60 00 00 li r3,0 c00d8138: 4e 80 00 20 blr c00d813c: 00 00 00 00 .long 0x0 Add ARCH_DEFINE_STATIC_CALL_RET0_TRAMP() defined by each architecture to setup the optimised configuration, and rework DEFINE_STATIC_CALL_RET0() to call it: c00d8120 <__SCT__perf_snapshot_branch_stack>: c00d8120: 48 00 00 14 b c00d8134 <__SCT__perf_snapshot_branch_stack+0x14> c00d8124: 3d 80 c0 0e lis r12,-16370 c00d8128: 81 8c 81 3c lwz r12,-32452(r12) c00d812c: 7d 89 03 a6 mtctr r12 c00d8130: 4e 80 04 20 bctr c00d8134: 38 60 00 00 li r3,0 c00d8138: 4e 80 00 20 blr c00d813c: 00 00 00 00 .long 0x0 Signed-off-by: Christophe Leroy Signed-off-by: Peter Zijlstra (Intel) Acked-by: Josh Poimboeuf Link: https://lore.kernel.org/r/1e0a61a88f52a460f62a58ffc2a5f847d1f7d9d8.1647253456.git.christophe.leroy@csgroup.eu --- arch/powerpc/include/asm/static_call.h | 1 + arch/x86/include/asm/static_call.h | 2 ++ include/linux/static_call.h | 20 +++++++++++++++++--- 3 files changed, 20 insertions(+), 3 deletions(-) (limited to 'include/linux/static_call.h') diff --git a/arch/powerpc/include/asm/static_call.h b/arch/powerpc/include/asm/static_call.h index 0a0bc79bd1fa..de1018cc522b 100644 --- a/arch/powerpc/include/asm/static_call.h +++ b/arch/powerpc/include/asm/static_call.h @@ -24,5 +24,6 @@ #define ARCH_DEFINE_STATIC_CALL_TRAMP(name, func) __PPC_SCT(name, "b " #func) #define ARCH_DEFINE_STATIC_CALL_NULL_TRAMP(name) __PPC_SCT(name, "blr") +#define ARCH_DEFINE_STATIC_CALL_RET0_TRAMP(name) __PPC_SCT(name, "b .+20") #endif /* _ASM_POWERPC_STATIC_CALL_H */ diff --git a/arch/x86/include/asm/static_call.h b/arch/x86/include/asm/static_call.h index ed4f8bb6c2d9..2455d721503e 100644 --- a/arch/x86/include/asm/static_call.h +++ b/arch/x86/include/asm/static_call.h @@ -38,6 +38,8 @@ #define ARCH_DEFINE_STATIC_CALL_NULL_TRAMP(name) \ __ARCH_DEFINE_STATIC_CALL_TRAMP(name, "ret; int3; nop; nop; nop") +#define ARCH_DEFINE_STATIC_CALL_RET0_TRAMP(name) \ + ARCH_DEFINE_STATIC_CALL_TRAMP(name, __static_call_return0) #define ARCH_ADD_TRAMP_KEY(name) \ asm(".pushsection .static_call_tramp_key, \"a\" \n" \ diff --git a/include/linux/static_call.h b/include/linux/static_call.h index fcc5b48989b3..3c50b0fdda16 100644 --- a/include/linux/static_call.h +++ b/include/linux/static_call.h @@ -196,6 +196,14 @@ extern long __static_call_return0(void); }; \ ARCH_DEFINE_STATIC_CALL_NULL_TRAMP(name) +#define DEFINE_STATIC_CALL_RET0(name, _func) \ + DECLARE_STATIC_CALL(name, _func); \ + struct static_call_key STATIC_CALL_KEY(name) = { \ + .func = __static_call_return0, \ + .type = 1, \ + }; \ + ARCH_DEFINE_STATIC_CALL_RET0_TRAMP(name) + #define static_call_cond(name) (void)__static_call(name) #define EXPORT_STATIC_CALL(name) \ @@ -231,6 +239,12 @@ static inline int static_call_init(void) { return 0; } }; \ ARCH_DEFINE_STATIC_CALL_NULL_TRAMP(name) +#define DEFINE_STATIC_CALL_RET0(name, _func) \ + DECLARE_STATIC_CALL(name, _func); \ + struct static_call_key STATIC_CALL_KEY(name) = { \ + .func = __static_call_return0, \ + }; \ + ARCH_DEFINE_STATIC_CALL_RET0_TRAMP(name) #define static_call_cond(name) (void)__static_call(name) @@ -284,6 +298,9 @@ static inline long __static_call_return0(void) .func = NULL, \ } +#define DEFINE_STATIC_CALL_RET0(name, _func) \ + __DEFINE_STATIC_CALL(name, _func, __static_call_return0) + static inline void __static_call_nop(void) { } /* @@ -327,7 +344,4 @@ static inline int static_call_text_reserved(void *start, void *end) #define DEFINE_STATIC_CALL(name, _func) \ __DEFINE_STATIC_CALL(name, _func, _func) -#define DEFINE_STATIC_CALL_RET0(name, _func) \ - __DEFINE_STATIC_CALL(name, _func, __static_call_return0) - #endif /* _LINUX_STATIC_CALL_H */ -- cgit v1.2.3 From df21c0d7a94db64a4e1a0d070e26fb02e60fefab Mon Sep 17 00:00:00 2001 From: Christophe Leroy Date: Mon, 14 Mar 2022 11:27:36 +0100 Subject: static_call: Remove __DEFINE_STATIC_CALL macro Only DEFINE_STATIC_CALL use __DEFINE_STATIC_CALL macro now when CONFIG_HAVE_STATIC_CALL is selected. Only keep __DEFINE_STATIC_CALL() for the generic fallback, and also use it to implement DEFINE_STATIC_CALL_NULL() in that case. Signed-off-by: Christophe Leroy Signed-off-by: Peter Zijlstra (Intel) Acked-by: Josh Poimboeuf Link: https://lore.kernel.org/r/329074f92d96e3220ebe15da7bbe2779beee31eb.1647253456.git.christophe.leroy@csgroup.eu --- include/linux/static_call.h | 23 ++++++++++------------- 1 file changed, 10 insertions(+), 13 deletions(-) (limited to 'include/linux/static_call.h') diff --git a/include/linux/static_call.h b/include/linux/static_call.h index 3c50b0fdda16..df53bed9d71f 100644 --- a/include/linux/static_call.h +++ b/include/linux/static_call.h @@ -180,13 +180,13 @@ extern int static_call_text_reserved(void *start, void *end); extern long __static_call_return0(void); -#define __DEFINE_STATIC_CALL(name, _func, _func_init) \ +#define DEFINE_STATIC_CALL(name, _func) \ DECLARE_STATIC_CALL(name, _func); \ struct static_call_key STATIC_CALL_KEY(name) = { \ - .func = _func_init, \ + .func = _func, \ .type = 1, \ }; \ - ARCH_DEFINE_STATIC_CALL_TRAMP(name, _func_init) + ARCH_DEFINE_STATIC_CALL_TRAMP(name, _func) #define DEFINE_STATIC_CALL_NULL(name, _func) \ DECLARE_STATIC_CALL(name, _func); \ @@ -225,12 +225,12 @@ extern long __static_call_return0(void); static inline int static_call_init(void) { return 0; } -#define __DEFINE_STATIC_CALL(name, _func, _func_init) \ +#define DEFINE_STATIC_CALL(name, _func) \ DECLARE_STATIC_CALL(name, _func); \ struct static_call_key STATIC_CALL_KEY(name) = { \ - .func = _func_init, \ + .func = _func, \ }; \ - ARCH_DEFINE_STATIC_CALL_TRAMP(name, _func_init) + ARCH_DEFINE_STATIC_CALL_TRAMP(name, _func) #define DEFINE_STATIC_CALL_NULL(name, _func) \ DECLARE_STATIC_CALL(name, _func); \ @@ -292,11 +292,11 @@ static inline long __static_call_return0(void) .func = _func_init, \ } +#define DEFINE_STATIC_CALL(name, _func) \ + __DEFINE_STATIC_CALL(name, _func, _func) + #define DEFINE_STATIC_CALL_NULL(name, _func) \ - DECLARE_STATIC_CALL(name, _func); \ - struct static_call_key STATIC_CALL_KEY(name) = { \ - .func = NULL, \ - } + __DEFINE_STATIC_CALL(name, _func, NULL) #define DEFINE_STATIC_CALL_RET0(name, _func) \ __DEFINE_STATIC_CALL(name, _func, __static_call_return0) @@ -341,7 +341,4 @@ static inline int static_call_text_reserved(void *start, void *end) #endif /* CONFIG_HAVE_STATIC_CALL */ -#define DEFINE_STATIC_CALL(name, _func) \ - __DEFINE_STATIC_CALL(name, _func, _func) - #endif /* _LINUX_STATIC_CALL_H */ -- cgit v1.2.3