diff mbox series

[RFC,v4,14/17] powerpc/ftrace: Add support for DYNAMIC_FTRACE_WITH_CALL_OPS

Message ID 0e7a1344724c90c03834db1a246c78a1ea29c28b.1720942106.git.naveen@kernel.org (mailing list archive)
State RFC
Headers show
Series powerpc: Core ftrace rework, support for ftrace direct and bpf trampolines | expand

Checks

Context Check Description
netdev/tree_selection success Not a local patch
bpf/vmtest-bpf-PR success PR summary
bpf/vmtest-bpf-VM_Test-0 success Logs for Lint
bpf/vmtest-bpf-VM_Test-1 success Logs for ShellCheck
bpf/vmtest-bpf-VM_Test-3 success Logs for Validate matrix.py
bpf/vmtest-bpf-VM_Test-2 success Logs for Unittests
bpf/vmtest-bpf-VM_Test-5 success Logs for aarch64-gcc / build-release
bpf/vmtest-bpf-VM_Test-4 success Logs for aarch64-gcc / build / build for aarch64 with gcc
bpf/vmtest-bpf-VM_Test-9 success Logs for aarch64-gcc / test (test_verifier, false, 360) / test_verifier on aarch64 with gcc
bpf/vmtest-bpf-VM_Test-10 success Logs for aarch64-gcc / veristat
bpf/vmtest-bpf-VM_Test-11 success Logs for s390x-gcc / build / build for s390x with gcc
bpf/vmtest-bpf-VM_Test-12 success Logs for s390x-gcc / build-release
bpf/vmtest-bpf-VM_Test-13 success Logs for s390x-gcc / test (test_maps, false, 360) / test_maps on s390x with gcc
bpf/vmtest-bpf-VM_Test-16 success Logs for s390x-gcc / test (test_verifier, false, 360) / test_verifier on s390x with gcc
bpf/vmtest-bpf-VM_Test-17 success Logs for s390x-gcc / veristat
bpf/vmtest-bpf-VM_Test-18 success Logs for set-matrix
bpf/vmtest-bpf-VM_Test-19 success Logs for x86_64-gcc / build / build for x86_64 with gcc
bpf/vmtest-bpf-VM_Test-20 success Logs for x86_64-gcc / build-release
bpf/vmtest-bpf-VM_Test-21 success Logs for x86_64-gcc / test (test_maps, false, 360) / test_maps on x86_64 with gcc
bpf/vmtest-bpf-VM_Test-24 success Logs for x86_64-gcc / test (test_progs_no_alu32_parallel, true, 30) / test_progs_no_alu32_parallel on x86_64 with gcc
bpf/vmtest-bpf-VM_Test-25 success Logs for x86_64-gcc / test (test_progs_parallel, true, 30) / test_progs_parallel on x86_64 with gcc
bpf/vmtest-bpf-VM_Test-26 success Logs for x86_64-gcc / test (test_verifier, false, 360) / test_verifier on x86_64 with gcc
bpf/vmtest-bpf-VM_Test-27 success Logs for x86_64-gcc / veristat / veristat on x86_64 with gcc
bpf/vmtest-bpf-VM_Test-28 success Logs for x86_64-llvm-17 / build / build for x86_64 with llvm-17
bpf/vmtest-bpf-VM_Test-29 success Logs for x86_64-llvm-17 / build-release / build for x86_64 with llvm-17-O2
bpf/vmtest-bpf-VM_Test-30 success Logs for x86_64-llvm-17 / test (test_maps, false, 360) / test_maps on x86_64 with llvm-17
bpf/vmtest-bpf-VM_Test-33 success Logs for x86_64-llvm-17 / test (test_verifier, false, 360) / test_verifier on x86_64 with llvm-17
bpf/vmtest-bpf-VM_Test-34 success Logs for x86_64-llvm-17 / veristat
bpf/vmtest-bpf-VM_Test-35 success Logs for x86_64-llvm-18 / build / build for x86_64 with llvm-18
bpf/vmtest-bpf-VM_Test-36 success Logs for x86_64-llvm-18 / build-release / build for x86_64 with llvm-18-O2
bpf/vmtest-bpf-VM_Test-37 success Logs for x86_64-llvm-18 / test (test_maps, false, 360) / test_maps on x86_64 with llvm-18
bpf/vmtest-bpf-VM_Test-41 success Logs for x86_64-llvm-18 / test (test_verifier, false, 360) / test_verifier on x86_64 with llvm-18
bpf/vmtest-bpf-VM_Test-42 success Logs for x86_64-llvm-18 / veristat
bpf/vmtest-bpf-VM_Test-6 success Logs for aarch64-gcc / test (test_maps, false, 360) / test_maps on aarch64 with gcc
bpf/vmtest-bpf-VM_Test-7 success Logs for aarch64-gcc / test (test_progs, false, 360) / test_progs on aarch64 with gcc
bpf/vmtest-bpf-VM_Test-8 success Logs for aarch64-gcc / test (test_progs_no_alu32, false, 360) / test_progs_no_alu32 on aarch64 with gcc
bpf/vmtest-bpf-VM_Test-14 success Logs for s390x-gcc / test (test_progs, false, 360) / test_progs on s390x with gcc
bpf/vmtest-bpf-VM_Test-22 success Logs for x86_64-gcc / test (test_progs, false, 360) / test_progs on x86_64 with gcc
bpf/vmtest-bpf-VM_Test-23 success Logs for x86_64-gcc / test (test_progs_no_alu32, false, 360) / test_progs_no_alu32 on x86_64 with gcc
bpf/vmtest-bpf-VM_Test-31 success Logs for x86_64-llvm-17 / test (test_progs, false, 360) / test_progs on x86_64 with llvm-17
bpf/vmtest-bpf-VM_Test-32 success Logs for x86_64-llvm-17 / test (test_progs_no_alu32, false, 360) / test_progs_no_alu32 on x86_64 with llvm-17
bpf/vmtest-bpf-VM_Test-38 success Logs for x86_64-llvm-18 / test (test_progs, false, 360) / test_progs on x86_64 with llvm-18
bpf/vmtest-bpf-VM_Test-39 success Logs for x86_64-llvm-18 / test (test_progs_cpuv4, false, 360) / test_progs_cpuv4 on x86_64 with llvm-18
bpf/vmtest-bpf-VM_Test-40 success Logs for x86_64-llvm-18 / test (test_progs_no_alu32, false, 360) / test_progs_no_alu32 on x86_64 with llvm-18
bpf/vmtest-bpf-VM_Test-15 success Logs for s390x-gcc / test (test_progs_no_alu32, false, 360) / test_progs_no_alu32 on s390x with gcc

Commit Message

Naveen N Rao July 14, 2024, 8:27 a.m. UTC 
Implement support for DYNAMIC_FTRACE_WITH_CALL_OPS similar to the
arm64 implementation.

This works by patching-in a pointer to an associated ftrace_ops
structure before each traceable function. If multiple ftrace_ops are
associated with a call site, then a special ftrace_list_ops is used to
enable iterating over all the registered ftrace_ops. If no ftrace_ops
are associated with a call site, then a special ftrace_nop_ops structure
is used to render the ftrace call as a no-op. ftrace trampoline can then
read the associated ftrace_ops for a call site by loading from an offset
from the LR, and branch directly to the associated function.

The primary advantage with this approach is that we don't have to
iterate over all the registered ftrace_ops for call sites that have a
single ftrace_ops registered. This is the equivalent of implementing
support for dynamic ftrace trampolines, which set up a special ftrace
trampoline for each registered ftrace_ops and have individual call sites
branch into those directly.

A secondary advantage is that this gives us a way to add support for
direct ftrace callers without having to resort to using stubs. The
address of the direct call trampoline can be loaded from the ftrace_ops
structure.

To support this, we reserve a nop before each function on 32-bit
powerpc. For 64-bit powerpc, two nops are reserved before each
out-of-line stub. During ftrace activation, we update this location with
the associated ftrace_ops pointer. Then, on ftrace entry, we load from
this location and call into ftrace_ops->func().

For 64-bit powerpc, we ensure that the out-of-line stub area is
doubleword aligned so that ftrace_ops address can be updated atomically.

Signed-off-by: Naveen N Rao <naveen@kernel.org>
---
 arch/powerpc/Kconfig                       |  1 +
 arch/powerpc/Makefile                      |  4 ++
 arch/powerpc/include/asm/ftrace.h          |  5 +-
 arch/powerpc/kernel/asm-offsets.c          |  4 ++
 arch/powerpc/kernel/trace/ftrace.c         | 59 +++++++++++++++++++++-
 arch/powerpc/kernel/trace/ftrace_entry.S   | 36 ++++++++++---
 arch/powerpc/tools/ftrace-gen-ool-stubs.sh |  5 +-
 7 files changed, 102 insertions(+), 12 deletions(-)
diff mbox series

Patch

diff --git a/arch/powerpc/Kconfig b/arch/powerpc/Kconfig
index a4dff8624510..cb6031d86dc9 100644
--- a/arch/powerpc/Kconfig
+++ b/arch/powerpc/Kconfig
@@ -235,6 +235,7 @@  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_REGS	if ARCH_USING_PATCHABLE_FUNCTION_ENTRY || MPROFILE_KERNEL || PPC32
 	select HAVE_EBPF_JIT
 	select HAVE_EFFICIENT_UNALIGNED_ACCESS
diff --git a/arch/powerpc/Makefile b/arch/powerpc/Makefile
index c973e6cd1ae8..7dede0ec0163 100644
--- a/arch/powerpc/Makefile
+++ b/arch/powerpc/Makefile
@@ -158,8 +158,12 @@  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
diff --git a/arch/powerpc/include/asm/ftrace.h b/arch/powerpc/include/asm/ftrace.h
index dc870824359c..267bd52fef21 100644
--- a/arch/powerpc/include/asm/ftrace.h
+++ b/arch/powerpc/include/asm/ftrace.h
@@ -138,8 +138,11 @@  static inline u8 this_cpu_get_ftrace_enabled(void) { return 1; }
 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,
diff --git a/arch/powerpc/kernel/asm-offsets.c b/arch/powerpc/kernel/asm-offsets.c
index 6854547d3164..60d1e388c2ba 100644
--- a/arch/powerpc/kernel/asm-offsets.c
+++ b/arch/powerpc/kernel/asm-offsets.c
@@ -678,5 +678,9 @@  int main(void)
 	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);
+#endif
+
 	return 0;
 }
diff --git a/arch/powerpc/kernel/trace/ftrace.c b/arch/powerpc/kernel/trace/ftrace.c
index b4de8b8cbe3a..291c6c3d3a78 100644
--- a/arch/powerpc/kernel/trace/ftrace.c
+++ b/arch/powerpc/kernel/trace/ftrace.c
@@ -38,8 +38,11 @@  unsigned long ftrace_call_adjust(unsigned long addr)
 		return 0;
 
 	if (IS_ENABLED(CONFIG_ARCH_USING_PATCHABLE_FUNCTION_ENTRY) &&
-	    !IS_ENABLED(CONFIG_PPC_FTRACE_OUT_OF_LINE))
+	    !IS_ENABLED(CONFIG_PPC_FTRACE_OUT_OF_LINE)) {
 		addr += MCOUNT_INSN_SIZE;
+		if (IS_ENABLED(CONFIG_DYNAMIC_FTRACE_WITH_CALL_OPS))
+			addr += MCOUNT_INSN_SIZE;
+	}
 
 	return addr;
 }
@@ -259,6 +262,46 @@  static int ftrace_init_ool_stub(struct module *mod, struct dyn_ftrace *rec)
 #endif
 }
 
+#ifdef CONFIG_DYNAMIC_FTRACE_WITH_CALL_OPS
+static const struct ftrace_ops *powerpc_rec_get_ops(struct dyn_ftrace *rec)
+{
+	const struct ftrace_ops *ops = NULL;
+
+	if (rec->flags & FTRACE_FL_CALL_OPS_EN) {
+		ops = ftrace_find_unique_ops(rec);
+		WARN_ON_ONCE(!ops);
+	}
+
+	if (!ops)
+		ops = &ftrace_list_ops;
+
+	return ops;
+}
+
+static int ftrace_rec_set_ops(struct dyn_ftrace *rec, const struct ftrace_ops *ops)
+{
+	if (IS_ENABLED(CONFIG_PPC_FTRACE_OUT_OF_LINE))
+		return patch_ulong((void *)(ftrace_get_ool_stub(rec) - sizeof(unsigned long)),
+				   (unsigned long)ops);
+	else
+		return patch_ulong((void *)(rec->ip - MCOUNT_INSN_SIZE - sizeof(unsigned long)),
+				   (unsigned long)ops);
+}
+
+static int ftrace_rec_set_nop_ops(struct dyn_ftrace *rec)
+{
+	return ftrace_rec_set_ops(rec, &ftrace_nop_ops);
+}
+
+static int ftrace_rec_update_ops(struct dyn_ftrace *rec)
+{
+	return ftrace_rec_set_ops(rec, powerpc_rec_get_ops(rec));
+}
+#else
+static int ftrace_rec_set_nop_ops(struct dyn_ftrace *rec) { return 0; }
+static int ftrace_rec_update_ops(struct dyn_ftrace *rec) { return 0; }
+#endif
+
 #ifdef CONFIG_DYNAMIC_FTRACE_WITH_REGS
 int ftrace_modify_call(struct dyn_ftrace *rec, unsigned long old_addr, unsigned long addr)
 {
@@ -289,6 +332,10 @@  int ftrace_make_call(struct dyn_ftrace *rec, unsigned long addr)
 	if (!ret)
 		ret = ftrace_modify_code(ip, old, new);
 
+	ret = ftrace_rec_update_ops(rec);
+	if (ret)
+		return ret;
+
 	if (!ret && IS_ENABLED(CONFIG_PPC_FTRACE_OUT_OF_LINE))
 		ret = ftrace_modify_code(rec->ip, ppc_inst(PPC_RAW_NOP()),
 			 ppc_inst(PPC_RAW_BRANCH((long)ftrace_get_ool_stub(rec) - (long)rec->ip)));
@@ -340,16 +387,19 @@  void ftrace_replace_code(int enable)
 		case FTRACE_UPDATE_MODIFY_CALL:
 			ret = ftrace_get_call_inst(rec, new_addr, &new_call_inst);
 			ret |= ftrace_get_call_inst(rec, addr, &call_inst);
+			ret |= ftrace_rec_update_ops(rec);
 			old = call_inst;
 			new = new_call_inst;
 			break;
 		case FTRACE_UPDATE_MAKE_NOP:
 			ret = ftrace_get_call_inst(rec, addr, &call_inst);
+			ret |= ftrace_rec_set_nop_ops(rec);
 			old = call_inst;
 			new = nop_inst;
 			break;
 		case FTRACE_UPDATE_MAKE_CALL:
 			ret = ftrace_get_call_inst(rec, new_addr, &call_inst);
+			ret |= ftrace_rec_update_ops(rec);
 			old = nop_inst;
 			new = call_inst;
 			break;
@@ -465,6 +515,13 @@  int ftrace_update_ftrace_func(ftrace_func_t func)
 	ppc_inst_t old, new;
 	int ret;
 
+	/*
+	 * When using CALL_OPS, the function to call is associated with the
+	 * call site, and we don't have a global function pointer to update.
+	 */
+	if (IS_ENABLED(CONFIG_DYNAMIC_FTRACE_WITH_CALL_OPS))
+		return 0;
+
 	old = ppc_inst_read((u32 *)&ftrace_call);
 	new = ftrace_create_branch_inst(ip, ppc_function_entry(func), 1);
 	ret = ftrace_modify_code(ip, old, new);
diff --git a/arch/powerpc/kernel/trace/ftrace_entry.S b/arch/powerpc/kernel/trace/ftrace_entry.S
index 86dbaa87532a..c019380bdd6a 100644
--- a/arch/powerpc/kernel/trace/ftrace_entry.S
+++ b/arch/powerpc/kernel/trace/ftrace_entry.S
@@ -85,11 +85,21 @@ 
 	/* Save callee's TOC in the ABI compliant location */
 	std	r2, STK_GOT(r1)
 	LOAD_PACA_TOC()		/* get kernel TOC in r2 */
+#endif
+
+#ifdef CONFIG_DYNAMIC_FTRACE_WITH_CALL_OPS
+	/* r7 points to the instruction following the call to ftrace */
+	PPC_LL	r5, -(MCOUNT_INSN_SIZE*2 + SZL)(r7)
+	PPC_LL	r12, FTRACE_OPS_FUNC(r5)
+	mtctr	r12
+#else /* !CONFIG_DYNAMIC_FTRACE_WITH_CALL_OPS */
+#ifdef CONFIG_PPC64
 	LOAD_REG_ADDR(r3, function_trace_op)
 	ld	r5,0(r3)
 #else
 	lis	r3,function_trace_op@ha
 	lwz	r5,function_trace_op@l(r3)
+#endif
 #endif
 
 	/* Save special regs */
@@ -205,20 +215,30 @@ 
 #endif
 .endm
 
-_GLOBAL(ftrace_regs_caller)
-	ftrace_regs_entry 1
-	/* ftrace_call(r3, r4, r5, r6) */
+.macro ftrace_regs_func allregs
+#ifdef CONFIG_DYNAMIC_FTRACE_WITH_CALL_OPS
+	bctrl
+#else
+	.if \allregs == 1
 .globl ftrace_regs_call
 ftrace_regs_call:
+	.else
+.globl ftrace_call
+ftrace_call:
+	.endif
+	/* ftrace_call(r3, r4, r5, r6) */
 	bl	ftrace_stub
+#endif
+.endm
+
+_GLOBAL(ftrace_regs_caller)
+	ftrace_regs_entry 1
+	ftrace_regs_func 1
 	ftrace_regs_exit 1
 
 _GLOBAL(ftrace_caller)
 	ftrace_regs_entry 0
-	/* ftrace_call(r3, r4, r5, r6) */
-.globl ftrace_call
-ftrace_call:
-	bl	ftrace_stub
+	ftrace_regs_func 0
 	ftrace_regs_exit 0
 
 _GLOBAL(ftrace_stub)
@@ -377,7 +397,7 @@  _GLOBAL(return_to_handler)
 #ifdef CONFIG_PPC_FTRACE_OUT_OF_LINE
 SYM_DATA(ftrace_ool_stub_text_count, .long CONFIG_PPC_FTRACE_OUT_OF_LINE_NUM_RESERVE)
 
-SYM_CODE_START(ftrace_ool_stub_text)
+SYM_START(ftrace_ool_stub_text, SYM_L_GLOBAL, .balign SZL)
 	.space CONFIG_PPC_FTRACE_OUT_OF_LINE_NUM_RESERVE * FTRACE_OOL_STUB_SIZE
 SYM_CODE_END(ftrace_ool_stub_text)
 #endif
diff --git a/arch/powerpc/tools/ftrace-gen-ool-stubs.sh b/arch/powerpc/tools/ftrace-gen-ool-stubs.sh
index 0d83adce4f23..a8dc26e10e66 100755
--- a/arch/powerpc/tools/ftrace-gen-ool-stubs.sh
+++ b/arch/powerpc/tools/ftrace-gen-ool-stubs.sh
@@ -27,12 +27,13 @@  num_ool_stubs_text_end=$(expr ${num_ool_stubs_text} - ${num_ool_stubs_text_built
 
 cat > ${arch_vmlinux_S} <<EOF
 #include <asm/asm-offsets.h>
+#include <asm/ppc_asm.h>
 #include <linux/linkage.h>
 
 .pushsection .tramp.ftrace.text,"aw"
 SYM_DATA(ftrace_ool_stub_text_end_count, .long ${num_ool_stubs_text_end})
 
-SYM_CODE_START(ftrace_ool_stub_text_end)
+SYM_START(ftrace_ool_stub_text_end, SYM_L_GLOBAL, .balign SZL)
 	.space ${num_ool_stubs_text_end} * FTRACE_OOL_STUB_SIZE
 SYM_CODE_END(ftrace_ool_stub_text_end)
 .popsection
@@ -40,7 +41,7 @@  SYM_CODE_END(ftrace_ool_stub_text_end)
 .pushsection .tramp.ftrace.init,"aw"
 SYM_DATA(ftrace_ool_stub_inittext_count, .long ${num_ool_stubs_inittext})
 
-SYM_CODE_START(ftrace_ool_stub_inittext)
+SYM_START(ftrace_ool_stub_inittext, SYM_L_GLOBAL, .balign SZL)
 	.space ${num_ool_stubs_inittext} * FTRACE_OOL_STUB_SIZE
 SYM_CODE_END(ftrace_ool_stub_inittext)
 .popsection