x86/ftrace: Make it call depth tracking aware

Since ftrace has trampolines, don't use thunks for the __fentry__ site
but instead require that every function called from there includes
accounting. This very much includes all the direct-call functions.

Additionally, ftrace uses ROP tricks in two places:

 - return_to_handler(), and
 - ftrace_regs_caller() when pt_regs->orig_ax is set by a direct-call.

return_to_handler() already uses a retpoline to replace an
indirect-jump to defeat IBT, since this is a jump-type retpoline, make
sure there is no accounting done and ALTERNATIVE the RET into a ret.

ftrace_regs_caller() does much the same and gets the same treatment.

Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org>
Signed-off-by: Thomas Gleixner <tglx@linutronix.de>
Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org>
Link: https://lore.kernel.org/r/20220915111148.927545073@infradead.org

5 files changed, 48 insertions, 7 deletions

diff --git a/arch/x86/include/asm/nospec-branch.h b/arch/x86/include/asm/nospec-branch.h
index 4771147c7c5a..82580adbca4b 100644
--- a/arch/x86/include/asm/nospec-branch.h
+++ b/arch/x86/include/asm/nospec-branch.h
@@ -343,6 +343,12 @@ static inline void x86_set_skl_return_thunk(void)
 {
 	x86_return_thunk = &__x86_return_skl;
 }
+
+#define CALL_DEPTH_ACCOUNT					\
+	ALTERNATIVE("",						\
+		    __stringify(INCREMENT_CALL_DEPTH),		\
+		    X86_FEATURE_CALL_DEPTH)
+
 #ifdef CONFIG_CALL_THUNKS_DEBUG
 DECLARE_PER_CPU(u64, __x86_call_count);
 DECLARE_PER_CPU(u64, __x86_ret_count);
@@ -351,6 +357,9 @@ DECLARE_PER_CPU(u64, __x86_ctxsw_count);
 #endif
 #else
 static inline void x86_set_skl_return_thunk(void) {}
+
+#define CALL_DEPTH_ACCOUNT ""
+
 #endif
 
 #ifdef CONFIG_RETPOLINE
diff --git a/arch/x86/kernel/callthunks.c b/arch/x86/kernel/callthunks.c
index a03d646b5e69..7d2c75ec9a8c 100644
--- a/arch/x86/kernel/callthunks.c
+++ b/arch/x86/kernel/callthunks.c
@@ -316,7 +316,7 @@ int x86_call_depth_emit_accounting(u8 **pprog, void *func)
 		return 0;
 
 	/* Is function call target a thunk? */
-	if (is_callthunk(func))
+	if (func && is_callthunk(func))
 		return 0;
 
 	memcpy(*pprog, tmpl, tmpl_size);
diff --git a/arch/x86/kernel/ftrace.c b/arch/x86/kernel/ftrace.c
index 4ac6692d5ef8..cf15ef5aecff 100644
--- a/arch/x86/kernel/ftrace.c
+++ b/arch/x86/kernel/ftrace.c
@@ -69,6 +69,10 @@ static const char *ftrace_nop_replace(void)
 
 static const char *ftrace_call_replace(unsigned long ip, unsigned long addr)
 {
+	/*
+	 * No need to translate into a callthunk. The trampoline does
+	 * the depth accounting itself.
+	 */
 	return text_gen_insn(CALL_INSN_OPCODE, (void *)ip, (void *)addr);
 }
 
@@ -317,7 +321,7 @@ create_trampoline(struct ftrace_ops *ops, unsigned int *tramp_size)
 	unsigned long size;
 	unsigned long *ptr;
 	void *trampoline;
-	void *ip;
+	void *ip, *dest;
 	/* 48 8b 15 <offset> is movq <offset>(%rip), %rdx */
 	unsigned const char op_ref[] = { 0x48, 0x8b, 0x15 };
 	unsigned const char retq[] = { RET_INSN_OPCODE, INT3_INSN_OPCODE };
@@ -404,10 +408,14 @@ create_trampoline(struct ftrace_ops *ops, unsigned int *tramp_size)
 	/* put in the call to the function */
 	mutex_lock(&text_mutex);
 	call_offset -= start_offset;
+	/*
+	 * No need to translate into a callthunk. The trampoline does
+	 * the depth accounting before the call already.
+	 */
+	dest = ftrace_ops_get_func(ops);
 	memcpy(trampoline + call_offset,
-	       text_gen_insn(CALL_INSN_OPCODE,
-			     trampoline + call_offset,
-			     ftrace_ops_get_func(ops)), CALL_INSN_SIZE);
+	       text_gen_insn(CALL_INSN_OPCODE, trampoline + call_offset, dest),
+	       CALL_INSN_SIZE);
 	mutex_unlock(&text_mutex);
 
 	/* ALLOC_TRAMP flags lets us know we created it */
diff --git a/arch/x86/kernel/ftrace_64.S b/arch/x86/kernel/ftrace_64.S
index b5b54f58957e..6a7e6d666a12 100644
--- a/arch/x86/kernel/ftrace_64.S
+++ b/arch/x86/kernel/ftrace_64.S
@@ -4,6 +4,7 @@
  */
 
 #include <linux/linkage.h>
+#include <asm/asm-offsets.h>
 #include <asm/ptrace.h>
 #include <asm/ftrace.h>
 #include <asm/export.h>
@@ -132,6 +133,7 @@
 #ifdef CONFIG_DYNAMIC_FTRACE
 
 SYM_FUNC_START(__fentry__)
+	CALL_DEPTH_ACCOUNT
 	RET
 SYM_FUNC_END(__fentry__)
 EXPORT_SYMBOL(__fentry__)
@@ -140,6 +142,8 @@ SYM_FUNC_START(ftrace_caller)
 	/* save_mcount_regs fills in first two parameters */
 	save_mcount_regs
 
+	CALL_DEPTH_ACCOUNT
+
 	/* Stack - skipping return address of ftrace_caller */
 	leaq MCOUNT_REG_SIZE+8(%rsp), %rcx
 	movq %rcx, RSP(%rsp)
@@ -155,6 +159,9 @@ SYM_INNER_LABEL(ftrace_caller_op_ptr, SYM_L_GLOBAL)
 	/* Only ops with REGS flag set should have CS register set */
 	movq $0, CS(%rsp)
 
+	/* Account for the function call below */
+	CALL_DEPTH_ACCOUNT
+
 SYM_INNER_LABEL(ftrace_call, SYM_L_GLOBAL)
 	ANNOTATE_NOENDBR
 	call ftrace_stub
@@ -189,6 +196,8 @@ SYM_FUNC_START(ftrace_regs_caller)
 	save_mcount_regs 8
 	/* save_mcount_regs fills in first two parameters */
 
+	CALL_DEPTH_ACCOUNT
+
 SYM_INNER_LABEL(ftrace_regs_caller_op_ptr, SYM_L_GLOBAL)
 	ANNOTATE_NOENDBR
 	/* Load the ftrace_ops into the 3rd parameter */
@@ -219,6 +228,9 @@ SYM_INNER_LABEL(ftrace_regs_caller_op_ptr, SYM_L_GLOBAL)
 	/* regs go into 4th parameter */
 	leaq (%rsp), %rcx
 
+	/* Account for the function call below */
+	CALL_DEPTH_ACCOUNT
+
 SYM_INNER_LABEL(ftrace_regs_call, SYM_L_GLOBAL)
 	ANNOTATE_NOENDBR
 	call ftrace_stub
@@ -282,7 +294,9 @@ SYM_INNER_LABEL(ftrace_regs_caller_end, SYM_L_GLOBAL)
 	int3
 .Ldo_rebalance:
 	add $8, %rsp
-	RET
+	ALTERNATIVE __stringify(RET), \
+		    __stringify(ANNOTATE_UNRET_SAFE; ret; int3), \
+		    X86_FEATURE_CALL_DEPTH
 
 SYM_FUNC_END(ftrace_regs_caller)
 STACK_FRAME_NON_STANDARD_FP(ftrace_regs_caller)
@@ -291,6 +305,8 @@ STACK_FRAME_NON_STANDARD_FP(ftrace_regs_caller)
 #else /* ! CONFIG_DYNAMIC_FTRACE */
 
 SYM_FUNC_START(__fentry__)
+	CALL_DEPTH_ACCOUNT
+
 	cmpq $ftrace_stub, ftrace_trace_function
 	jnz trace
 
@@ -347,6 +363,8 @@ SYM_CODE_START(return_to_handler)
 	int3
 .Ldo_rop:
 	mov %rdi, (%rsp)
-	RET
+	ALTERNATIVE __stringify(RET), \
+		    __stringify(ANNOTATE_UNRET_SAFE; ret; int3), \
+		    X86_FEATURE_CALL_DEPTH
 SYM_CODE_END(return_to_handler)
 #endif
diff --git a/arch/x86/net/bpf_jit_comp.c b/arch/x86/net/bpf_jit_comp.c
index a6b46740ea30..f46b62029d91 100644
--- a/arch/x86/net/bpf_jit_comp.c
+++ b/arch/x86/net/bpf_jit_comp.c
@@ -12,6 +12,7 @@
 #include <linux/memory.h>
 #include <linux/sort.h>
 #include <asm/extable.h>
+#include <asm/ftrace.h>
 #include <asm/set_memory.h>
 #include <asm/nospec-branch.h>
 #include <asm/text-patching.h>
@@ -2135,6 +2136,11 @@ int arch_prepare_bpf_trampoline(struct bpf_tramp_image *im, void *image, void *i
 	prog = image;
 
 	EMIT_ENDBR();
+	/*
+	 * This is the direct-call trampoline, as such it needs accounting
+	 * for the __fentry__ call.
+	 */
+	x86_call_depth_emit_accounting(&prog, NULL);
 	EMIT1(0x55);		 /* push rbp */
 	EMIT3(0x48, 0x89, 0xE5); /* mov rbp, rsp */
 	EMIT4(0x48, 0x83, 0xEC, stack_size); /* sub rsp, stack_size */