bpf, arm64: Fix bpf trampoline instruction endianness

The sparse tool complains as follows:

arch/arm64/net/bpf_jit_comp.c:1684:16:
	warning: incorrect type in assignment (different base types)
arch/arm64/net/bpf_jit_comp.c:1684:16:
	expected unsigned int [usertype] *branch
arch/arm64/net/bpf_jit_comp.c:1684:16:
	got restricted __le32 [usertype] *
arch/arm64/net/bpf_jit_comp.c:1700:52:
	error: subtraction of different types can't work (different base
	types)
arch/arm64/net/bpf_jit_comp.c:1734:29:
	warning: incorrect type in assignment (different base types)
arch/arm64/net/bpf_jit_comp.c:1734:29:
	expected unsigned int [usertype] *
arch/arm64/net/bpf_jit_comp.c:1734:29:
	got restricted __le32 [usertype] *
arch/arm64/net/bpf_jit_comp.c:1918:52:
	error: subtraction of different types can't work (different base
	types)

This is because the variable branch in function invoke_bpf_prog and the
variable branches in function prepare_trampoline are defined as type
u32 *, which conflicts with ctx->image's type __le32 *, so sparse complains
when assignment or arithmetic operation are performed on these two
variables and ctx->image.

Since arm64 instructions are always little-endian, change the type of
these two variables to __le32 * and call cpu_to_le32() to convert
instruction to little-endian before writing it to memory. This is also
in line with emit() which internally does cpu_to_le32(), too.

Fixes: efc9909fdc ("bpf, arm64: Add bpf trampoline for arm64")
Reported-by: kernel test robot <lkp@intel.com>
Signed-off-by: Xu Kuohai <xukuohai@huawei.com>
Signed-off-by: Daniel Borkmann <daniel@iogearbox.net>
Reviewed-by: Jean-Philippe Brucker <jean-philippe@linaro.org>
Link: https://lore.kernel.org/bpf/20220808040735.1232002-1-xukuohai@huawei.com

arch/arm64/net/bpf_jit_comp.c

@@ -1643,7 +1643,7 @@ static void invoke_bpf_prog(struct jit_ctx *ctx, struct bpf_tramp_link *l,
 			    int args_off, int retval_off, int run_ctx_off,
 			    bool save_ret)
 {
-	u32 *branch;
+	__le32 *branch;
 	u64 enter_prog;
 	u64 exit_prog;
 	struct bpf_prog *p = l->link.prog;
@@ -1698,7 +1698,7 @@ static void invoke_bpf_prog(struct jit_ctx *ctx, struct bpf_tramp_link *l,
 
 	if (ctx->image) {
 		int offset = &ctx->image[ctx->idx] - branch;
-		*branch = A64_CBZ(1, A64_R(0), offset);
+		*branch = cpu_to_le32(A64_CBZ(1, A64_R(0), offset));
 	}
 
 	/* arg1: prog */
@@ -1713,7 +1713,7 @@ static void invoke_bpf_prog(struct jit_ctx *ctx, struct bpf_tramp_link *l,
 
 static void invoke_bpf_mod_ret(struct jit_ctx *ctx, struct bpf_tramp_links *tl,
 			       int args_off, int retval_off, int run_ctx_off,
-			       u32 **branches)
+			       __le32 **branches)
 {
 	int i;
 
@@ -1784,7 +1784,7 @@ static int prepare_trampoline(struct jit_ctx *ctx, struct bpf_tramp_image *im,
 	struct bpf_tramp_links *fexit = &tlinks[BPF_TRAMP_FEXIT];
 	struct bpf_tramp_links *fmod_ret = &tlinks[BPF_TRAMP_MODIFY_RETURN];
 	bool save_ret;
-	u32 **branches = NULL;
+	__le32 **branches = NULL;
 
 	/* trampoline stack layout:
 	 *                  [ parent ip         ]
@@ -1892,7 +1892,7 @@ static int prepare_trampoline(struct jit_ctx *ctx, struct bpf_tramp_image *im,
 				flags & BPF_TRAMP_F_RET_FENTRY_RET);
 
 	if (fmod_ret->nr_links) {
-		branches = kcalloc(fmod_ret->nr_links, sizeof(u32 *),
+		branches = kcalloc(fmod_ret->nr_links, sizeof(__le32 *),
 				   GFP_KERNEL);
 		if (!branches)
 			return -ENOMEM;
@@ -1916,7 +1916,7 @@ static int prepare_trampoline(struct jit_ctx *ctx, struct bpf_tramp_image *im,
 	/* update the branches saved in invoke_bpf_mod_ret with cbnz */
 	for (i = 0; i < fmod_ret->nr_links && ctx->image != NULL; i++) {
 		int offset = &ctx->image[ctx->idx] - branches[i];
-		*branches[i] = A64_CBNZ(1, A64_R(10), offset);
+		*branches[i] = cpu_to_le32(A64_CBNZ(1, A64_R(10), offset));
 	}
 
 	for (i = 0; i < fexit->nr_links; i++)