powerpc64/bpf: fix the address returned by bpf_get_func_ip

bpf_get_func_ip() helper function returns the address of the traced
function. It relies on the IP address stored at ctx - 16 by the bpf
trampoline. On 64-bit powerpc, this address is recovered from LR
accounting for OOL trampoline. But the address stored here was off
by 4-bytes. Ensure the address is the actual start of the traced
function.

Reported-by: Abhishek Dubey <adubey@linux.ibm.com>
Fixes: d243b62 ("powerpc64/bpf: Add support for bpf trampolines")
Cc: stable@vger.kernel.org
Tested-by: Venkat Rao Bagalkote <venkat88@linux.ibm.com>
Signed-off-by: Hari Bathini <hbathini@linux.ibm.com>
Signed-off-by: Madhavan Srinivasan <maddy@linux.ibm.com>
Link: https://patch.msgid.link/20260303181031.390073-3-hbathini@linux.ibm.com

Author: hbathini

arch/powerpc/net/bpf_jit_comp.c

@@ -785,9 +785,9 @@ static int __arch_prepare_bpf_trampoline(struct bpf_tramp_image *im, void *rw_im
 	 *       retval_off             [ return value      ]
 	 *                              [ reg argN          ]
 	 *                              [ ...               ]
-	 *       regs_off               [ reg_arg1          ] prog ctx context
-	 *       nregs_off              [ args count        ]
-	 *       ip_off                 [ traced function   ]
+	 *       regs_off               [ reg_arg1          ] prog_ctx
+	 *       nregs_off              [ args count        ] ((u64 *)prog_ctx)[-1]
+	 *       ip_off                 [ traced function   ] ((u64 *)prog_ctx)[-2]
 	 *                              [ ...               ]
 	 *       run_ctx_off            [ bpf_tramp_run_ctx ]
 	 *                              [ reg argN          ]
@@ -895,32 +895,42 @@ static int __arch_prepare_bpf_trampoline(struct bpf_tramp_image *im, void *rw_im
 
 	bpf_trampoline_save_args(image, ctx, func_frame_offset, nr_regs, regs_off);
 
-	/* Save our return address */
+	/* Save our LR/return address */
 	EMIT(PPC_RAW_MFLR(_R3));
 	if (IS_ENABLED(CONFIG_PPC_FTRACE_OUT_OF_LINE))
 		EMIT(PPC_RAW_STL(_R3, _R1, alt_lr_off));
 	else
 		EMIT(PPC_RAW_STL(_R3, _R1, bpf_frame_size + PPC_LR_STKOFF));
 
 	/*
-	 * Save ip address of the traced function.
-	 * We could recover this from LR, but we will need to address for OOL trampoline,
-	 * and optional GEP area.
+	 * Derive IP address of the traced function.
+	 * In case of CONFIG_PPC_FTRACE_OUT_OF_LINE or BPF program, LR points to the instruction
+	 * after the 'bl' instruction in the OOL stub. Refer to ftrace_init_ool_stub() and
+	 * bpf_arch_text_poke() for OOL stub of kernel functions and bpf programs respectively.
+	 * Relevant stub sequence:
+	 *
+	 *               bl <tramp>
+	 *   LR (R3) =>  mtlr r0
+	 *               b <func_addr+4>
+	 *
+	 * Recover kernel function/bpf program address from the unconditional
+	 * branch instruction at the end of OOL stub.
 	 */
 	if (IS_ENABLED(CONFIG_PPC_FTRACE_OUT_OF_LINE) || flags & BPF_TRAMP_F_IP_ARG) {
 		EMIT(PPC_RAW_LWZ(_R4, _R3, 4));
 		EMIT(PPC_RAW_SLWI(_R4, _R4, 6));
 		EMIT(PPC_RAW_SRAWI(_R4, _R4, 6));
 		EMIT(PPC_RAW_ADD(_R3, _R3, _R4));
-		EMIT(PPC_RAW_ADDI(_R3, _R3, 4));
 	}
 
 	if (flags & BPF_TRAMP_F_IP_ARG)
 		EMIT(PPC_RAW_STL(_R3, _R1, ip_off));
 
-	if (IS_ENABLED(CONFIG_PPC_FTRACE_OUT_OF_LINE))
+	if (IS_ENABLED(CONFIG_PPC_FTRACE_OUT_OF_LINE)) {
 		/* Fake our LR for unwind */
+		EMIT(PPC_RAW_ADDI(_R3, _R3, 4));
 		EMIT(PPC_RAW_STL(_R3, _R1, bpf_frame_size + PPC_LR_STKOFF));
+	}
 
 	/* Save function arg count -- see bpf_get_func_arg_cnt() */
 	EMIT(PPC_RAW_LI(_R3, nr_regs));