Merge tag 'bpf-fixes' of git://git.kernel.org/pub/scm/linux/kernel/git/bpf/bpf

Pull bpf fixes from Alexei Starovoitov:

 - Fix interaction between livepatch and BPF fexit programs (Song Liu)
   With Steven and Masami acks.

 - Fix stack ORC unwind from BPF kprobe_multi (Jiri Olsa)
   With Steven and Masami acks.

 - Fix out of bounds access in widen_imprecise_scalars() in the verifier
   (Eduard Zingerman)

 - Fix conflicts between MPTCP and BPF sockmap (Jiayuan Chen)

 - Fix net_sched storage collision with BPF data_meta/data_end (Eric
   Dumazet)

 - Add _impl suffix to BPF kfuncs with implicit args to avoid breaking
   them in bpf-next when KF_IMPLICIT_ARGS is added (Mykyta Yatsenko)

* tag 'bpf-fixes' of git://git.kernel.org/pub/scm/linux/kernel/git/bpf/bpf:
  selftests/bpf: Test widen_imprecise_scalars() with different stack depth
  bpf: account for current allocated stack depth in widen_imprecise_scalars()
  bpf: Add bpf_prog_run_data_pointers()
  selftests/bpf: Add mptcp test with sockmap
  mptcp: Fix proto fallback detection with BPF
  mptcp: Disallow MPTCP subflows from sockmap
  selftests/bpf: Add stacktrace ips test for raw_tp
  selftests/bpf: Add stacktrace ips test for kprobe_multi/kretprobe_multi
  x86/fgraph,bpf: Fix stack ORC unwind from kprobe_multi return probe
  Revert "perf/x86: Always store regs->ip in perf_callchain_kernel()"
  bpf: add _impl suffix for bpf_stream_vprintk() kfunc
  bpf:add _impl suffix for bpf_task_work_schedule* kfuncs
  selftests/bpf: Add tests for livepatch + bpf trampoline
  ftrace: bpf: Fix IPMODIFY + DIRECT in modify_ftrace_direct()
  ftrace: Fix BPF fexit with livepatch

3 files changed, 17 insertions, 6 deletions

diff --git a/arch/x86/events/core.c b/arch/x86/events/core.c
index 745caa6c15a3..fa6c47b50989 100644
--- a/arch/x86/events/core.c
+++ b/arch/x86/events/core.c
@@ -2789,13 +2789,13 @@ perf_callchain_kernel(struct perf_callchain_entry_ctx *entry, struct pt_regs *re
 		return;
 	}
 
-	if (perf_callchain_store(entry, regs->ip))
-		return;
-
-	if (perf_hw_regs(regs))
+	if (perf_hw_regs(regs)) {
+		if (perf_callchain_store(entry, regs->ip))
+			return;
 		unwind_start(&state, current, regs, NULL);
-	else
+	} else {
 		unwind_start(&state, current, NULL, (void *)regs->sp);
+	}
 
 	for (; !unwind_done(&state); unwind_next_frame(&state)) {
 		addr = unwind_get_return_address(&state);
diff --git a/arch/x86/include/asm/ftrace.h b/arch/x86/include/asm/ftrace.h
index 93156ac4ffe0..b08c95872eed 100644
--- a/arch/x86/include/asm/ftrace.h
+++ b/arch/x86/include/asm/ftrace.h
@@ -56,6 +56,11 @@ arch_ftrace_get_regs(struct ftrace_regs *fregs)
 	return &arch_ftrace_regs(fregs)->regs;
 }
 
+#define arch_ftrace_partial_regs(regs) do {	\
+	regs->flags &= ~X86_EFLAGS_FIXED;	\
+	regs->cs = __KERNEL_CS;			\
+} while (0)
+
 #define arch_ftrace_fill_perf_regs(fregs, _regs) do {	\
 		(_regs)->ip = arch_ftrace_regs(fregs)->regs.ip;		\
 		(_regs)->sp = arch_ftrace_regs(fregs)->regs.sp;		\
diff --git a/arch/x86/kernel/ftrace_64.S b/arch/x86/kernel/ftrace_64.S
index 367da3638167..823dbdd0eb41 100644
--- a/arch/x86/kernel/ftrace_64.S
+++ b/arch/x86/kernel/ftrace_64.S
@@ -354,12 +354,17 @@ SYM_CODE_START(return_to_handler)
 	UNWIND_HINT_UNDEFINED
 	ANNOTATE_NOENDBR
 
+	/* Restore return_to_handler value that got eaten by previous ret instruction. */
+	subq $8, %rsp
+	UNWIND_HINT_FUNC
+
 	/* Save ftrace_regs for function exit context  */
 	subq $(FRAME_SIZE), %rsp
 
 	movq %rax, RAX(%rsp)
 	movq %rdx, RDX(%rsp)
 	movq %rbp, RBP(%rsp)
+	movq %rsp, RSP(%rsp)
 	movq %rsp, %rdi
 
 	call ftrace_return_to_handler
@@ -368,7 +373,8 @@ SYM_CODE_START(return_to_handler)
 	movq RDX(%rsp), %rdx
 	movq RAX(%rsp), %rax
 
-	addq $(FRAME_SIZE), %rsp
+	addq $(FRAME_SIZE) + 8, %rsp
+
 	/*
 	 * Jump back to the old return address. This cannot be JMP_NOSPEC rdi
 	 * since IBT would demand that contain ENDBR, which simply isn't so for