Merge: bpf, ftrace: Support BPF trampolines on powerpc

MR: https://gitlab.com/redhat/centos-stream/src/kernel/centos-stream-10/-/merge_requests/988

Backport patches for BPF trampoline support on powerpc. This enables various BPF features such as fentry/fexit probes.

JIRA: https://issues.redhat.com/browse/RHEL-24555

Signed-off-by: Viktor Malik <vmalik@redhat.com>

Approved-by: Jerome Marchand <jmarchan@redhat.com>
Approved-by: Steve Best <sbest@redhat.com>

Merged-by: Julio Faracco <jfaracco@redhat.com>

Author: jcfaracco

arch/Kconfig

@@ -1729,4 +1729,10 @@ config CC_HAS_SANE_FUNCTION_ALIGNMENT
 config ARCH_NEED_CMPXCHG_1_EMU
 	bool
 
+config ARCH_WANTS_PRE_LINK_VMLINUX
+	bool
+	help
+	  An architecture can select this if it provides arch/<arch>/tools/Makefile
+	  with .arch.vmlinux.o target to be linked into vmlinux.
+
 endmenu

arch/powerpc/Kbuild

@@ -19,4 +19,4 @@ obj-$(CONFIG_KEXEC_CORE)  += kexec/
 obj-$(CONFIG_KEXEC_FILE)  += purgatory/
 
 # for cleaning
-subdir- += boot
+subdir- += boot tools

arch/powerpc/Kconfig

@@ -236,6 +236,8 @@ config PPC
 	select HAVE_DEBUG_STACKOVERFLOW
 	select HAVE_DYNAMIC_FTRACE
 	select HAVE_DYNAMIC_FTRACE_WITH_ARGS	if ARCH_USING_PATCHABLE_FUNCTION_ENTRY || MPROFILE_KERNEL || PPC32
+	select HAVE_DYNAMIC_FTRACE_WITH_CALL_OPS if PPC_FTRACE_OUT_OF_LINE || (PPC32 && ARCH_USING_PATCHABLE_FUNCTION_ENTRY)
+	select HAVE_DYNAMIC_FTRACE_WITH_DIRECT_CALLS if HAVE_DYNAMIC_FTRACE_WITH_CALL_OPS
 	select HAVE_DYNAMIC_FTRACE_WITH_REGS	if ARCH_USING_PATCHABLE_FUNCTION_ENTRY || MPROFILE_KERNEL || PPC32
 	select HAVE_EBPF_JIT
 	select HAVE_EFFICIENT_UNALIGNED_ACCESS
@@ -245,7 +247,7 @@ config PPC
 	select HAVE_FUNCTION_DESCRIPTORS	if PPC64_ELF_ABI_V1
 	select HAVE_FUNCTION_ERROR_INJECTION
 	select HAVE_FUNCTION_GRAPH_TRACER
-	select HAVE_FUNCTION_TRACER		if PPC64 || (PPC32 && CC_IS_GCC)
+	select HAVE_FUNCTION_TRACER		if !COMPILE_TEST && (PPC64 || (PPC32 && CC_IS_GCC))
 	select HAVE_GCC_PLUGINS			if GCC_VERSION >= 50200   # plugin support on gcc <= 5.1 is buggy on PPC
 	select HAVE_GENERIC_VDSO
 	select HAVE_HARDLOCKUP_DETECTOR_ARCH	if PPC_BOOK3S_64 && SMP
@@ -276,6 +278,8 @@ config PPC
 	select HAVE_REGS_AND_STACK_ACCESS_API
 	select HAVE_RELIABLE_STACKTRACE
 	select HAVE_RSEQ
+	select HAVE_SAMPLE_FTRACE_DIRECT	if HAVE_DYNAMIC_FTRACE_WITH_DIRECT_CALLS
+	select HAVE_SAMPLE_FTRACE_DIRECT_MULTI	if HAVE_DYNAMIC_FTRACE_WITH_DIRECT_CALLS
 	select HAVE_SETUP_PER_CPU_AREA		if PPC64
 	select HAVE_SOFTIRQ_ON_OWN_STACK
 	select HAVE_STACKPROTECTOR		if PPC32 && $(cc-option,-mstack-protector-guard=tls -mstack-protector-guard-reg=r2)
@@ -572,6 +576,22 @@ config ARCH_USING_PATCHABLE_FUNCTION_ENTRY
 	def_bool $(success,$(srctree)/arch/powerpc/tools/gcc-check-fpatchable-function-entry.sh $(CC) -mlittle-endian) if PPC64 && CPU_LITTLE_ENDIAN
 	def_bool $(success,$(srctree)/arch/powerpc/tools/gcc-check-fpatchable-function-entry.sh $(CC) -mbig-endian) if PPC64 && CPU_BIG_ENDIAN
 
+config PPC_FTRACE_OUT_OF_LINE
+	def_bool PPC64 && ARCH_USING_PATCHABLE_FUNCTION_ENTRY
+	select ARCH_WANTS_PRE_LINK_VMLINUX
+
+config PPC_FTRACE_OUT_OF_LINE_NUM_RESERVE
+	int "Number of ftrace out-of-line stubs to reserve within .text"
+	depends on PPC_FTRACE_OUT_OF_LINE
+	default 32768
+	help
+	  Number of stubs to reserve for use by ftrace. This space is
+	  reserved within .text, and is distinct from any additional space
+	  added at the end of .text before the final vmlinux link. Set to
+	  zero to have stubs only be generated at the end of vmlinux (only
+	  if the size of vmlinux is less than 32MB). Set to a higher value
+	  if building vmlinux larger than 48MB.
+
 config HOTPLUG_CPU
 	bool "Support for enabling/disabling CPUs"
 	depends on SMP && (PPC_PSERIES || \

arch/powerpc/Makefile

@@ -155,7 +155,15 @@ CC_FLAGS_NO_FPU		:= $(call cc-option,-msoft-float)
 ifdef CONFIG_FUNCTION_TRACER
 ifdef CONFIG_ARCH_USING_PATCHABLE_FUNCTION_ENTRY
 KBUILD_CPPFLAGS	+= -DCC_USING_PATCHABLE_FUNCTION_ENTRY
+ifdef CONFIG_PPC_FTRACE_OUT_OF_LINE
+CC_FLAGS_FTRACE := -fpatchable-function-entry=1
+else
+ifdef CONFIG_DYNAMIC_FTRACE_WITH_CALL_OPS # PPC32 only
+CC_FLAGS_FTRACE := -fpatchable-function-entry=3,1
+else
 CC_FLAGS_FTRACE := -fpatchable-function-entry=2
+endif
+endif
 else
 CC_FLAGS_FTRACE := -pg
 ifdef CONFIG_MPROFILE_KERNEL

arch/powerpc/Makefile.postlink

@@ -24,6 +24,9 @@ else
 	$(CONFIG_SHELL) $(srctree)/arch/powerpc/tools/relocs_check.sh "$(OBJDUMP)" "$(NM)" "$@"
 endif
 
+quiet_cmd_ftrace_check = CHKFTRC $@
+      cmd_ftrace_check = $(CONFIG_SHELL) $(srctree)/arch/powerpc/tools/ftrace_check.sh "$(NM)" "$@"
+
 # `@true` prevents complaint when there is nothing to be done
 
 vmlinux: FORCE
@@ -34,6 +37,11 @@ endif
 ifdef CONFIG_RELOCATABLE
 	$(call if_changed,relocs_check)
 endif
+ifdef CONFIG_FUNCTION_TRACER
+ifndef CONFIG_PPC64_ELF_ABI_V1
+	$(call cmd,ftrace_check)
+endif
+endif
 
 clean:
 	rm -f .tmp_symbols.txt

arch/powerpc/include/asm/ftrace.h

@@ -24,7 +24,10 @@ unsigned long prepare_ftrace_return(unsigned long parent, unsigned long ip,
 struct module;
 struct dyn_ftrace;
 struct dyn_arch_ftrace {
-	struct module *mod;
+#ifdef CONFIG_PPC_FTRACE_OUT_OF_LINE
+	/* pointer to the associated out-of-line stub */
+	unsigned long ool_stub;
+#endif
 };
 
 #ifdef CONFIG_DYNAMIC_FTRACE_WITH_ARGS
@@ -131,8 +134,36 @@ static inline u8 this_cpu_get_ftrace_enabled(void) { return 1; }
 
 #ifdef CONFIG_FUNCTION_TRACER
 extern unsigned int ftrace_tramp_text[], ftrace_tramp_init[];
+#ifdef CONFIG_PPC_FTRACE_OUT_OF_LINE
+struct ftrace_ool_stub {
+#ifdef CONFIG_DYNAMIC_FTRACE_WITH_CALL_OPS
+	struct ftrace_ops *ftrace_op;
+#endif
+	u32	insn[4];
+} __aligned(sizeof(unsigned long));
+extern struct ftrace_ool_stub ftrace_ool_stub_text_end[], ftrace_ool_stub_text[],
+			      ftrace_ool_stub_inittext[];
+extern unsigned int ftrace_ool_stub_text_end_count, ftrace_ool_stub_text_count,
+		    ftrace_ool_stub_inittext_count;
+#endif
 void ftrace_free_init_tramp(void);
 unsigned long ftrace_call_adjust(unsigned long addr);
+
+#ifdef CONFIG_DYNAMIC_FTRACE_WITH_DIRECT_CALLS
+/*
+ * When an ftrace registered caller is tracing a function that is also set by a
+ * register_ftrace_direct() call, it needs to be differentiated in the
+ * ftrace_caller trampoline so that the direct call can be invoked after the
+ * other ftrace ops. To do this, place the direct caller in the orig_gpr3 field
+ * of pt_regs. This tells ftrace_caller that there's a direct caller.
+ */
+static inline void arch_ftrace_set_direct_caller(struct ftrace_regs *fregs, unsigned long addr)
+{
+	struct pt_regs *regs = &fregs->regs;
+
+	regs->orig_gpr3 = addr;
+}
+#endif /* CONFIG_DYNAMIC_FTRACE_WITH_DIRECT_CALLS */
 #else
 static inline void ftrace_free_init_tramp(void) { }
 static inline unsigned long ftrace_call_adjust(unsigned long addr) { return addr; }

arch/powerpc/include/asm/module.h

@@ -47,6 +47,11 @@ struct mod_arch_specific {
 #ifdef CONFIG_DYNAMIC_FTRACE
 	unsigned long tramp;
 	unsigned long tramp_regs;
+#ifdef CONFIG_PPC_FTRACE_OUT_OF_LINE
+	struct ftrace_ool_stub *ool_stubs;
+	unsigned int ool_stub_count;
+	unsigned int ool_stub_index;
+#endif
 #endif
 };
 

arch/powerpc/include/asm/ppc-opcode.h

@@ -587,12 +587,26 @@
 #define PPC_RAW_MTSPR(spr, d)		(0x7c0003a6 | ___PPC_RS(d) | __PPC_SPR(spr))
 #define PPC_RAW_EIEIO()			(0x7c0006ac)
 
+/* bcl 20,31,$+4 */
+#define PPC_RAW_BCL4()			(0x429f0005)
 #define PPC_RAW_BRANCH(offset)		(0x48000000 | PPC_LI(offset))
 #define PPC_RAW_BL(offset)		(0x48000001 | PPC_LI(offset))
 #define PPC_RAW_TW(t0, a, b)		(0x7c000008 | ___PPC_RS(t0) | ___PPC_RA(a) | ___PPC_RB(b))
 #define PPC_RAW_TRAP()			PPC_RAW_TW(31, 0, 0)
 #define PPC_RAW_SETB(t, bfa)		(0x7c000100 | ___PPC_RT(t) | ___PPC_RA((bfa) << 2))
 
+#ifdef CONFIG_PPC32
+#define PPC_RAW_STL		PPC_RAW_STW
+#define PPC_RAW_STLU		PPC_RAW_STWU
+#define PPC_RAW_LL		PPC_RAW_LWZ
+#define PPC_RAW_CMPLI		PPC_RAW_CMPWI
+#else
+#define PPC_RAW_STL		PPC_RAW_STD
+#define PPC_RAW_STLU		PPC_RAW_STDU
+#define PPC_RAW_LL		PPC_RAW_LD
+#define PPC_RAW_CMPLI		PPC_RAW_CMPDI
+#endif
+
 /* Deal with instructions that older assemblers aren't aware of */
 #define	PPC_BCCTR_FLUSH		stringify_in_c(.long PPC_INST_BCCTR_FLUSH)
 #define	PPC_CP_ABORT		stringify_in_c(.long PPC_RAW_CP_ABORT)

arch/powerpc/kernel/asm-offsets.c

@@ -677,5 +677,16 @@ int main(void)
 	DEFINE(BPT_SIZE, BPT_SIZE);
 #endif
 
+#ifdef CONFIG_PPC_FTRACE_OUT_OF_LINE
+	DEFINE(FTRACE_OOL_STUB_SIZE, sizeof(struct ftrace_ool_stub));
+#endif
+
+#ifdef CONFIG_DYNAMIC_FTRACE_WITH_CALL_OPS
+	OFFSET(FTRACE_OPS_FUNC, ftrace_ops, func);
+#ifdef CONFIG_DYNAMIC_FTRACE_WITH_DIRECT_CALLS
+	OFFSET(FTRACE_OPS_DIRECT_CALL, ftrace_ops, direct_call);
+#endif
+#endif
+
 	return 0;
 }

arch/powerpc/kernel/kprobes.c

@@ -105,24 +105,22 @@ kprobe_opcode_t *kprobe_lookup_name(const char *name, unsigned int offset)
 	return addr;
 }
 
-static bool arch_kprobe_on_func_entry(unsigned long offset)
+static bool arch_kprobe_on_func_entry(unsigned long addr, unsigned long offset)
 {
-#ifdef CONFIG_PPC64_ELF_ABI_V2
-#ifdef CONFIG_KPROBES_ON_FTRACE
-	return offset <= 16;
-#else
-	return offset <= 8;
-#endif
-#else
+	unsigned long ip = ftrace_location(addr);
+
+	if (ip)
+		return offset <= (ip - addr);
+	if (IS_ENABLED(CONFIG_PPC64_ELF_ABI_V2) && !IS_ENABLED(CONFIG_PPC_KERNEL_PCREL))
+		return offset <= 8;
 	return !offset;
-#endif
 }
 
 /* XXX try and fold the magic of kprobe_lookup_name() in this */
 kprobe_opcode_t *arch_adjust_kprobe_addr(unsigned long addr, unsigned long offset,
 					 bool *on_func_entry)
 {
-	*on_func_entry = arch_kprobe_on_func_entry(offset);
+	*on_func_entry = arch_kprobe_on_func_entry(addr, offset);
 	return (kprobe_opcode_t *)(addr + offset);
 }