* it does tail-call optimization on the call; since you cannot compute the
* relative displacement across sections.
*/
-#define ARCH_DEFINE_STATIC_CALL_TRAMP(name, func) \
+
+#define __ARCH_DEFINE_STATIC_CALL_TRAMP(name, insns) \
asm(".pushsection .static_call.text, \"ax\" \n" \
".align 4 \n" \
".globl " STATIC_CALL_TRAMP_STR(name) " \n" \
STATIC_CALL_TRAMP_STR(name) ": \n" \
- " .byte 0xe9 # jmp.d32 \n" \
- " .long " #func " - (. + 4) \n" \
+ insns " \n" \
".type " STATIC_CALL_TRAMP_STR(name) ", @function \n" \
".size " STATIC_CALL_TRAMP_STR(name) ", . - " STATIC_CALL_TRAMP_STR(name) " \n" \
".popsection \n")
+#define ARCH_DEFINE_STATIC_CALL_TRAMP(name, func) \
+ __ARCH_DEFINE_STATIC_CALL_TRAMP(name, ".byte 0xe9; .long " #func " - (. + 4)")
+
+#define ARCH_DEFINE_STATIC_CALL_NULL_TRAMP(name) \
+ __ARCH_DEFINE_STATIC_CALL_TRAMP(name, "ret; nop; nop; nop; nop")
+
#endif /* _ASM_STATIC_CALL_H */
#include <linux/bug.h>
#include <asm/text-patching.h>
-static void __static_call_transform(void *insn, u8 opcode, void *func)
+enum insn_type {
+ CALL = 0, /* site call */
+ NOP = 1, /* site cond-call */
+ JMP = 2, /* tramp / site tail-call */
+ RET = 3, /* tramp / site cond-tail-call */
+};
+
+static void __static_call_transform(void *insn, enum insn_type type, void *func)
{
- const void *code = text_gen_insn(opcode, insn, func);
+ int size = CALL_INSN_SIZE;
+ const void *code;
- if (WARN_ONCE(*(u8 *)insn != opcode,
- "unexpected static call insn opcode 0x%x at %pS\n",
- opcode, insn))
- return;
+ switch (type) {
+ case CALL:
+ code = text_gen_insn(CALL_INSN_OPCODE, insn, func);
+ break;
+
+ case NOP:
+ code = ideal_nops[NOP_ATOMIC5];
+ break;
+
+ case JMP:
+ code = text_gen_insn(JMP32_INSN_OPCODE, insn, func);
+ break;
+
+ case RET:
+ code = text_gen_insn(RET_INSN_OPCODE, insn, func);
+ size = RET_INSN_SIZE;
+ break;
+ }
- if (memcmp(insn, code, CALL_INSN_SIZE) == 0)
+ if (memcmp(insn, code, size) == 0)
return;
- text_poke_bp(insn, code, CALL_INSN_SIZE, NULL);
+ text_poke_bp(insn, code, size, NULL);
}
void arch_static_call_transform(void *site, void *tramp, void *func)
mutex_lock(&text_mutex);
if (tramp)
- __static_call_transform(tramp, JMP32_INSN_OPCODE, func);
+ __static_call_transform(tramp, func ? JMP : RET, func);
if (IS_ENABLED(CONFIG_HAVE_STATIC_CALL_INLINE) && site)
- __static_call_transform(site, CALL_INSN_OPCODE, func);
+ __static_call_transform(site, func ? CALL : NOP, func);
mutex_unlock(&text_mutex);
}
*
* DECLARE_STATIC_CALL(name, func);
* DEFINE_STATIC_CALL(name, func);
+ * DEFINE_STATIC_CALL_NULL(name, typename);
* static_call(name)(args...);
+ * static_call_cond(name)(args...);
* static_call_update(name, func);
*
* Usage example:
* rather than calling through the trampoline. This requires objtool or a
* compiler plugin to detect all the static_call() sites and annotate them
* in the .static_call_sites section.
+ *
+ *
+ * Notes on NULL function pointers:
+ *
+ * Static_call()s support NULL functions, with many of the caveats that
+ * regular function pointers have.
+ *
+ * Clearly calling a NULL function pointer is 'BAD', so too for
+ * static_call()s (although when HAVE_STATIC_CALL it might not be immediately
+ * fatal). A NULL static_call can be the result of:
+ *
+ * DECLARE_STATIC_CALL_NULL(my_static_call, void (*)(int));
+ *
+ * which is equivalent to declaring a NULL function pointer with just a
+ * typename:
+ *
+ * void (*my_func_ptr)(int arg1) = NULL;
+ *
+ * or using static_call_update() with a NULL function. In both cases the
+ * HAVE_STATIC_CALL implementation will patch the trampoline with a RET
+ * instruction, instead of an immediate tail-call JMP. HAVE_STATIC_CALL_INLINE
+ * architectures can patch the trampoline call to a NOP.
+ *
+ * In all cases, any argument evaluation is unconditional. Unlike a regular
+ * conditional function pointer call:
+ *
+ * if (my_func_ptr)
+ * my_func_ptr(arg1)
+ *
+ * where the argument evaludation also depends on the pointer value.
+ *
+ * When calling a static_call that can be NULL, use:
+ *
+ * static_call_cond(name)(arg1);
+ *
+ * which will include the required value tests to avoid NULL-pointer
+ * dereferences.
*/
#include <linux/types.h>
}; \
ARCH_DEFINE_STATIC_CALL_TRAMP(name, _func)
+#define DEFINE_STATIC_CALL_NULL(name, _func) \
+ DECLARE_STATIC_CALL(name, _func); \
+ struct static_call_key STATIC_CALL_KEY(name) = { \
+ .func = NULL, \
+ .type = 1, \
+ }; \
+ ARCH_DEFINE_STATIC_CALL_NULL_TRAMP(name)
+
#define static_call(name) __static_call(name)
+#define static_call_cond(name) (void)__static_call(name)
#define EXPORT_STATIC_CALL(name) \
EXPORT_SYMBOL(STATIC_CALL_KEY(name)); \
}; \
ARCH_DEFINE_STATIC_CALL_TRAMP(name, _func)
+#define DEFINE_STATIC_CALL_NULL(name, _func) \
+ DECLARE_STATIC_CALL(name, _func); \
+ struct static_call_key STATIC_CALL_KEY(name) = { \
+ .func = NULL, \
+ }; \
+ ARCH_DEFINE_STATIC_CALL_NULL_TRAMP(name)
+
#define static_call(name) __static_call(name)
+#define static_call_cond(name) (void)__static_call(name)
static inline
void __static_call_update(struct static_call_key *key, void *tramp, void *func)
.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) \
((typeof(STATIC_CALL_TRAMP(name))*)(STATIC_CALL_KEY(name).func))
+static inline void __static_call_nop(void) { }
+
+/*
+ * This horrific hack takes care of two things:
+ *
+ * - it ensures the compiler will only load the function pointer ONCE,
+ * which avoids a reload race.
+ *
+ * - it ensures the argument evaluation is unconditional, similar
+ * to the HAVE_STATIC_CALL variant.
+ *
+ * Sadly current GCC/Clang (10 for both) do not optimize this properly
+ * and will emit an indirect call for the NULL case :-(
+ */
+#define __static_call_cond(name) \
+({ \
+ void *func = READ_ONCE(STATIC_CALL_KEY(name).func); \
+ if (!func) \
+ func = &__static_call_nop; \
+ (typeof(STATIC_CALL_TRAMP(name))*)func; \
+})
+
+#define static_call_cond(name) (void)__static_call_cond(name)
+
static inline
void __static_call_update(struct static_call_key *key, void *tramp, void *func)
{
projects / platform / kernel / linux-rpi.git / commitdiff